@oh-my-pi/pi-coding-agent 15.13.3 → 16.0.1

package/src/internal-urls/docs-index.generated.ts

@@ -1,10 +1,11 @@
 // Auto-generated by scripts/generate-docs-index.ts - DO NOT EDIT
 
-export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","adding-a-provider.md","ai-schema-normalize.md","approval-mode.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","collab.md","compaction.md","config-usage.md","context-files.md","custom-tools.md","environment-variables.md","extension-loading.md","extensions.md","fs-scan-cache-architecture.md","gemini-manifest-extensions.md","handoff-generation-pipeline.md","hooks.md","install-id.md","keybindings.md","local-models.md","lsp-config.md","macos-signing-notarization.md","marketplace.md","mcp-config.md","mcp-protocol-transports.md","mcp-runtime-lifecycle.md","mcp-server-tool-authoring.md","memory.md","mnemosyne-memory-backend.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","plugin-manager-installer-plumbing.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","providers.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","settings.md","skills.md","skills/authoring-extensions.md","skills/authoring-hooks.md","skills/authoring-marketplaces.md","skills/examples/hello-extension/README.md","skills/examples/mini-marketplace/README.md","skills/examples/safety-hook/README.md","slash-command-internals.md","system-prompt-customization.md","task-agent-discovery.md","theme.md","toolconv/anthropic.md","toolconv/deepseek.md","toolconv/gemini.md","toolconv/gemma.md","toolconv/glm-4.5.md","toolconv/harmony.md","toolconv/kimi-k2.md","toolconv/pi-native.md","toolconv/qwen3.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-core-renderer.md","tui-runtime-internals.md","tui.md"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","adding-a-provider.md","advisor-watchdog.md","ai-schema-normalize.md","approval-mode.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","collab.md","compaction.md","config-usage.md","context-files.md","custom-tools.md","environment-variables.md","extension-loading.md","extensions.md","fs-scan-cache-architecture.md","gemini-manifest-extensions.md","handoff-generation-pipeline.md","hooks.md","install-id.md","keybindings.md","local-models.md","lsp-config.md","macos-signing-notarization.md","marketplace.md","mcp-config.md","mcp-protocol-transports.md","mcp-runtime-lifecycle.md","mcp-server-tool-authoring.md","memory.md","mnemosyne-memory-backend.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","plugin-manager-installer-plumbing.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","providers.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","settings.md","skills.md","skills/authoring-extensions.md","skills/authoring-hooks.md","skills/authoring-marketplaces.md","skills/examples/hello-extension/README.md","skills/examples/mini-marketplace/README.md","skills/examples/safety-hook/README.md","slash-command-internals.md","system-prompt-customization.md","task-agent-discovery.md","theme.md","toolconv/anthropic.md","toolconv/deepseek.md","toolconv/gemini.md","toolconv/gemma.md","toolconv/glm-4.5.md","toolconv/harmony.md","toolconv/kimi-k2.md","toolconv/pi-native.md","toolconv/qwen3.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-core-renderer.md","tui-runtime-internals.md","tui.md"];
 
 export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"ERRATA-GPT5-HARMONY.md": "# ERRATA — GPT-5 Harmony-Header Leakage\n\nHistorical research note, not a current runtime contract. The statistics below\ncome from the named local stats database snapshot, not from checked-in tests or\nruntime code.\n\n## 1. The problem\n\nOpenAI frames tool calls in the Harmony chat protocol:\n\n```\n<|start|>assistant<|channel|>commentary to=functions.<NAME><|message|>{ARGS}<|call|>\n```\n\n`<|channel|>commentary to=functions.NAME` is the **routing header** —\ncontrol tokens consumed by the runtime to dispatch the call. These\ntokens never appear as content under normal operation; the runtime\nstrips them.\n\nThe defect: gpt-5 models occasionally emit, **as ordinary content\ninside `{ARGS}`**, the **plain-text shadow** of these routing tokens —\nthe same characters without the `<|…|>` brackets — and continue\nproducing more pseudo-routing structure (channel name, body marker,\nmultilingual spam, fake tool-result framing). The contamination lives\ninside the visible tool argument and is dispatched to the tool as if it\nwere intended content.\n\n**Critical detail.** The actual `<|start|>` / `<|channel|>` /\n`<|message|>` / `<|call|>` special tokens almost never appear in tool\nargs. What leaks is the bracket-less spelling — `analysis to=functions.X\ncode …` — because OpenAI applies a logit mask suppressing the\ncontrol-token IDs inside the args region. The mass that would have gone\nto those special tokens redistributes onto the un-bracketed plain-text\nrepresentation the model also learned. This makes the leak structurally\ninvisible to the routing parser and lands it in the tool input verbatim.\n\nManifestation in tool args (real corpus example):\n\n```\n~      add_function(iso, ctx, ns, \"installSystemChangeObserver\",\n        os_install_system_change_observer);】【\"】【analysis to=functions.edit\n        code above เงินไทยฟรีuser to=functions.edit code …\n```\n\nThe leading code is real and intended. Everything after the first\nnon-Latin token through the next clean structural boundary is corruption.\n\n---\n\n## 2. Observed statistics & failure modes\n\nSource: `~/.omp/stats.db` (`ss_tool_calls`, `ss_assistant_msgs`), through\n2026-05-10. 1.05M tool calls scanned.\n\n### 2.1 Rate\n\n| Model         | Leaks in tool args |   Calls | per million |\n| ------------- | -----------------: | ------: | ----------: |\n| gpt-5.4       |                 37 | 226,957 |         163 |\n| gpt-5.3-codex |                 17 | 112,243 |         151 |\n| gpt-5.5       |                  2 |  80,750 |          25 |\n| gpt-5.2-codex |                  0 |       — |           — |\n\nPlus 15 hits in assistant visible text / thinking blobs.\n\n### 2.2 Tool distribution\n\n| Tool                           |   Hits |\n| ------------------------------ | -----: |\n| `edit`                         |     38 |\n| `eval`                         |     11 |\n| `report_tool_issue`            |      3 |\n| `grep`/`read`/`search`/`yield` | 1 each |\n\nConcentrated in tools with free-form (non-JSON-schema) argument formats.\n\n### 2.3 Leak shape (deterministic)\n\n```\nLEAK         ::= JUNK_PREFIX MARKER CHANNEL_BODY (LEAK)?\nMARKER       ::= \"to=functions.\" TOOL_NAME\nCHANNEL_BODY ::= \" code \" (SPAM | reasoning_prose | fake_tool_output)*\nJUNK_PREFIX  ::= (GLITCH_TOKEN | CHANNEL_WORD | NON_LATIN_RUN | \"}\" | \"】【\")+\n```\n\n**Cascading is common.** Of 96 marker occurrences across 71 contaminated\nrecords, 39 contain ≥2 markers and 7 contain ≥3 — the model emits\nmultiple fake `to=functions.X code …` blocks back-to-back, often with\nfake `code_output\\nCell N:\\n…` framing between them. Once the\nplain-text scaffolding is in the residual stream, the prefix now _looks\nlike_ a fresh tool envelope start, so the macro prior over continuations\nkeeps voting for more scaffolding. Self-amplifying.\n\n### 2.4 Glitch tokens\n\nSingle-token identifiers in `o200k_base` whose embeddings appear to be\nnear-init from underrepresentation in post-training. ASCII residue\nimmediately before the marker in the natural corpus:\n\n| Surface string    | Single-token | Token ID |                  Hits in corpus |\n| ----------------- | :----------: | -------: | ------------------------------: |\n| `Japgolly`        |      ✅      |  199,745 |                               1 |\n| `Jsii`            |      ✅      |  114,318 | (subtoken of `Jsii_commentary`) |\n| `Jsii_commentary` |  — (3 toks)  |        — |                               2 |\n| `changedFiles`    |  — (2 toks)  |        — |                               8 |\n| `RTLU`            |  — (2 toks)  |        — |                               3 |\n\n`Japgolly` is in the last 0.13% of the vocabulary — the same family of\nGitHub-corpus residue that produced `SolidGoldMagikarp` in the 2023\nGPT-2 vocabulary (Rumbelow & Watkins). `SolidGoldMagikarp` itself\ntokenizes to 5 tokens in `o200k_base` — that specific token was retired,\nbut the class wasn't.\n\nFor the multi-token entries, the corpus-level signature is the surface\nstring; the underlying glitch trigger is a sub-token (e.g. `Jsii` inside\n`Jsii_commentary`). The detector list (`G` signal) keys on the surface\nstrings.\n\nStable across unrelated sessions. Treated as a high-precision detector\nsignal.\n\n### 2.5 Channel-word leakage\n\n`analysis` (5), `assistant` (5), `commentary` (3), `user` (1) appear\ndirectly preceding `to=`. Always bare words; never `<|channel|>analysis`\nor any other bracketed form. Consistent with §1 — the brackets are\nmasked, the words are not.\n\n### 2.6 Non-Latin spam residue\n\n96 marker hits, by script: CJK 40, Cyrillic 12, Telugu/Kannada/Malayalam\n18, Thai 8, Georgian 7, Armenian 7, Arabic 1. Recurring fragments are\nChinese gambling SEO (`大发时时彩`, `天天中彩票`), Georgian/Abkhaz junk,\nand Thai casino spam — well-known low-quality crawl residue.\n\nThis is the same script distribution observed in the controlled\nreproduction (§7.3), independent of the prompt's natural language.\n\n### 2.7 Failure-mode breakdown for the `edit` tool\n\nThe `edit` tool exists in two variants in the corpus:\n\n| Variant                              | Calls | Recovery                                                                                                                                             |\n| ------------------------------------ | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Patch-DSL (`§PATH`/anchor/`«»≔` ops) |    27 | **Recoverable** by op-truncation (§3.3)                                                                                                              |\n| JSON-schema (`{path,edits:[…]}`)     |    11 | **Not recoverable** — contamination is escaped _inside_ JSON strings, parser accepts it cleanly, content would be written verbatim into source files |\n\nFor Patch-DSL leaks specifically:\n\n- 20/27 cases: contamination on the last input line; nothing follows.\n- 7/27 cases: contamination mid-input; what follows is one of: a\n  duplicate replay of an earlier file/anchor, intended content for a\n  _different_ tool call (the model started its next call inline), or\n  pure hallucination. Post-contamination content is never trustworthy.\n\n### 2.8 Mechanism (confirmed)\n\n**Prior collapse from null-embedding glitch tokens, into a\ncontrol-token-masked basin whose mass redistributes onto the\nplain-text shadow of the Harmony protocol.**\n\nStep by step:\n\n1. The model is mid-`{ARGS}` of a Harmony tool call. The runtime applies\n   a logit mask suppressing structural control tokens (`<|channel|>`,\n   `<|message|>`, `<|call|>`, `<|start|>`, `<|end|>`) inside the args\n   region. Without this mask, normal generation would constantly\n   hallucinate envelope-closes; with it, those token IDs have logit\n   `-∞` in args.\n2. A glitch token `g` is sampled. By construction `g` was in the BPE\n   merge corpus but barely in LM/RL training, so its **input embedding\n   `e_g` ≈ near-init noise of small norm**.\n3. At position t+1, the residual update `h_{t+1} ≈ LN(h_t + e_g + Attn +\nMLP)` is dominated by the prefix-derived terms; the just-emitted-token\n   signal is effectively absent. Generation diversity normally comes\n   from `e_x` steering the residual into different sub-regions —\n   stripped here.\n4. The next-token distribution therefore collapses onto the **conditional\n   prior over continuations of the prefix, with local conditioning\n   removed**. In a tool-calling rollout context, that prior is sharply\n   peaked on Harmony scaffolding (control tokens + routing tokens) —\n   that's what RL trained.\n5. The mask zeros the control-token IDs. Mass redistributes onto the\n   **next-best continuation**: the un-bracketed surface-form spelling of\n   the same protocol (`analysis`, `commentary`, ` to=functions.X`,\n   `code`). This spelling is unmasked because those characters are\n   ordinary tokens.\n6. Once a few tokens of plain-text scaffolding land in the residual\n   stream, the prefix now resembles a fresh envelope start. The macro\n   prior keeps voting for more scaffolding. Cascading (§2.3) follows.\n7. Multilingual spam after the marker is the same prior-collapse\n   continuation, drawn from the training neighborhood of the glitch\n   token (often ESL/auto-generated multilingual web junk — exactly the\n   crawl residue in §2.6).\n\n**Two corollaries the corpus data demanded but only the experiment\nexplained:**\n\n- **The brackets never appear** (§1, §2.5). The mask is what makes the\n  leak land in plain text instead of as a real envelope-close.\n- **Counterintuitive grammar dependency** (§7.4). The leak is _worse_ in\n  formats closest to OpenAI's training distribution. Off-distribution\n  custom grammars dampen the macro-prior basin; the official\n  `*** Begin Patch` format is the strongest collapse target.\n\nThe 2023 SolidGoldMagikarp paper documented mechanism (1)+(2)+(4). The\nnew piece is (5): when constrained decoding masks the natural collapse\ntarget, the mass laundered through the un-masked plain-text shadow\nbecomes a structurally-invisible exfiltration channel.\n",
 	"adding-a-provider.md": "# Adding a provider\n\nA provider is described in two halves:\n\n- **Catalog half** (`packages/catalog`): one entry in the `CATALOG_PROVIDERS`\n  table (`packages/catalog/src/provider-models/descriptors.ts`) carrying the\n  `id`, `defaultModel`, runtime model-discovery factory, and catalog-generation\n  wiring. `KnownProvider`, `PROVIDER_DESCRIPTORS`, and\n  `DEFAULT_MODEL_PER_PROVIDER` are derived from this table.\n- **Auth half** (`packages/ai`): one declarative `ProviderDefinition` in the\n  registry carrying env-key fallbacks and login/refresh flows. The\n  `OAuthProvider` union, the env-key map, the `/login` provider list, the\n  `refreshOAuthToken` / `AuthStorage.login` dispatch, and the coding-agent\n  callback maps are derived from the registry.\n\n**Scope.** This is for a provider that reuses an existing wire API\n(`openai-completions`, `anthropic-messages`, `google-generative-ai`, …) — the\ncommon case for gateways and API-key providers, since stream dispatch keys on\n`model.api`, not `model.provider`. Adding a *new wire protocol* (a new\n`KnownApi`) is a separate task that also touches `stream.ts` dispatch,\n`api-registry.ts`, and the catalog `types.ts`.\n\n## Shape\n\nFor the common case, a provider is **one catalog entry + one def file + one registry line**:\n\n1. **Add an entry to `CATALOG_PROVIDERS`** in\n   `packages/catalog/src/provider-models/descriptors.ts` with the `id`,\n   `defaultModel`, the plain API-key env var(s) as `envVars`, and (usually) a\n   `createModelManagerOptions` factory. For a\n   simple OpenAI-compatible gateway, build the factory in\n   `packages/catalog/src/provider-models/openai-compat.ts` or inline with the\n   exported `createSimpleOpenAICompletionsOptions(providerId, baseUrl, config)`.\n2. **Create `packages/ai/src/registry/<id>.ts`** exporting one\n   `export const <camelId>Provider = { … } as const satisfies ProviderDefinition;`\n   with the auth fields (`login`, …). Plain env-var names live in the catalog\n   entry's `envVars`; set `envKeys` only for computed resolvers (Foundry/ADC/\n   Bedrock-style probes).\n3. **Add it to the `ALL` array** in `packages/ai/src/registry/registry.ts`\n   (one import + one array entry). `ALL` order is the `/login` list order for\n   loginable providers.\n\nThat is the full change for:\n- env-key-only providers,\n- providers with a simple inline API-key login flow,\n- most OpenAI-compatible gateways.\n\nFor a **non-trivial provider-local OAuth flow**, put the implementation in\n`packages/ai/src/registry/oauth/<vendor>.ts` and lazy-import it from the def\nfile. The shared OAuth flow infrastructure it builds on lives in the same\n`registry/oauth/` directory.\n\nDescriptors, the default-model map, env-key map, login list, and refresh\ndispatch all update automatically; the `KnownProvider` union gains the new id\nfrom the catalog table and `OAuthProvider` from the registry.\n\n## Field reference\n\n**Catalog table entry** (`ProviderCatalogEntry`, see\n`packages/catalog/src/provider-models/descriptor-types.ts` for JSDoc):\n\n| Field | Effect |\n|---|---|\n| `id` | Required. Member of `KnownProvider`. |\n| `defaultModel` | Required. Preferred model when no explicit selection is made. |\n| `envVars` | Env var name(s), in order, for the runtime API-key fallback (`getEnvApiKey`). |\n| `createModelManagerOptions` | Runtime model-discovery factory. Present (and not `specialModelManager`) ⇒ appears in `PROVIDER_DESCRIPTORS`. |\n| `allowUnauthenticated` | Runtime creates a model manager even without a key. |\n| `dynamicModelsAuthoritative` | Successful discovery replaces bundled models. |\n| `catalogDiscovery` | `{ label, envVars?, oauthProvider?, allowUnauthenticated? }` for offline catalog generation (`generate-models.ts`). `envVars` here overrides the entry-level list when generation uses different credentials (e.g. `cursor`). |\n| `specialModelManager` | Bespoke runtime factory (`google-antigravity` / `google-gemini-cli` / `openai-codex`); excluded from `PROVIDER_DESCRIPTORS`. |\n\n**Registry definition** (`ProviderDefinition`, see\n`packages/ai/src/registry/types.ts`):\n\n| Field | Effect |\n|---|---|\n| `id`, `name` | Required. `name` shows in the `/login` list. |\n| `envKeys` | Computed env fallback for `getEnvApiKey`, overriding the catalog entry's `envVars`: a var name string or a `() => string \\| undefined` resolver. Omit when `envVars` covers it. |\n| `login` | Interactive login. Present ⇒ member of `OAuthProvider`, shown in `/login`, dispatchable via `AuthStorage.login`. Returns an api-key `string` or `OAuthCredentials`. |\n| `refreshToken` | OAuth refresher; omit for static-token providers (the dispatch returns credentials unchanged). |\n| `storeCredentialsAs` | Store credentials under a different provider id (e.g. `openai-codex-device` ⇒ `openai-codex`). |\n| `callbackPort` | Present ⇒ entry in the auth-broker `CALLBACK_PORTS` map. |\n| `pasteCodeFlow` | OAuth flow needs a pasted code/redirect URL ⇒ member of `PASTE_CODE_LOGIN_PROVIDERS`. |\n\n## Conventions\n\n- Use `... as const satisfies ProviderDefinition` so the literal `id` is preserved\n  for the union derivation.\n- `login` / `refreshToken` for simple API-key or validation-based flows can live\n  directly in the provider def file (export the named login function there so\n  tests can import it directly).\n- `login` / `refreshToken` for heavy provider-local OAuth flows MUST reach the\n  adjacent `registry/oauth/*` module via a dynamic-import\n  thunk (`const { loginX } = await import(\"./oauth/x\"); return loginX(cb);`),\n  keeping those flows out of the eager startup graph.\n- All OAuth code lives under `registry/oauth/`: the shared flow infra\n  (`callback-server`, `pkce`, `google-oauth-shared`, `types`, the runtime API\n  `index`) plus every provider flow, including the `github-copilot` / `kimi` /\n  `openai-codex` helpers reused by the streaming and usage layers. The non-OAuth\n  API-key helpers (`api-key-login`, `api-key-validation`) sit beside the def\n  files in `registry/`, since they back simple paste-an-API-key logins.\n- For a simple OpenAI-compatible gateway, build the manager inline with the\n  exported `createSimpleOpenAICompletionsOptions(providerId, baseUrl, config)` —\n  no edits to `openai-compat.ts` required.\n- A `ProviderDefinition` may also be registered at runtime by an extension via\n  `registerOAuthProvider` (the `AuthStorage.login` dispatcher handles built-ins\n  and extensions through the same path).\n",
+	"advisor-watchdog.md": "# Advisor and WATCHDOG.md\n\nThe advisor is an optional second model attached to a session. It reviews the primary agent's transcript after each turn, can inspect the workspace with read-only tools, and injects concise advice back into the primary session.\n\nThe advisor is not a second executor. It cannot edit files, run commands, approve actions, or change session state directly.\n\n## Implementation files\n\n- [`src/advisor/runtime.ts`](../packages/coding-agent/src/advisor/runtime.ts)\n- [`src/advisor/advise-tool.ts`](../packages/coding-agent/src/advisor/advise-tool.ts)\n- [`src/advisor/watchdog.ts`](../packages/coding-agent/src/advisor/watchdog.ts)\n- [`src/prompts/advisor/system.md`](../packages/coding-agent/src/prompts/advisor/system.md)\n- [`src/prompts/advisor/advise-tool.md`](../packages/coding-agent/src/prompts/advisor/advise-tool.md)\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`src/slash-commands/builtin-registry.ts`](../packages/coding-agent/src/slash-commands/builtin-registry.ts)\n- [`src/config/settings-schema.ts`](../packages/coding-agent/src/config/settings-schema.ts)\n\n---\n\n## Enabling the advisor\n\nThe advisor requires both:\n\n1. `advisor.enabled: true`\n2. a model assigned to the `advisor` model role\n\nExample:\n\n```yaml\nmodelRoles:\n  advisor: anthropic/claude-sonnet-4-5:medium\n\nadvisor:\n  enabled: true\n```\n\nThe advisor role uses normal model-role resolution, including provider-prefixed ids, canonical ids, and optional thinking suffixes.\n\nSlash commands:\n\n| Command | Effect |\n|---|---|\n| `/advisor` | Toggle the persisted `advisor.enabled` setting. |\n| `/advisor on` | Enable the setting and start the runtime when an advisor model is assigned. |\n| `/advisor off` | Disable the setting and stop the runtime. |\n| `/advisor status` | Show active model, context usage, token usage, and cost. |\n| `/advisor dump` | Print the advisor's compact transcript. |\n| `/advisor dump raw` | Print the advisor's full dump with system prompt, tools, thinking, and calls. |\n\nIf `advisor.enabled` is true but no `modelRoles.advisor` value resolves to an available model, status reports that the setting is enabled but no advisor model is assigned.\n\n## What the advisor sees\n\nAt each primary turn end, `AdvisorRuntime` receives only the new transcript delta since the last advisor update. Deltas are rendered with `formatSessionHistoryMarkdown(..., { includeThinking: true })`, so the advisor can review assistant reasoning as well as user-visible text, tool calls, and tool results.\n\nAdvisor messages already injected into the primary transcript are filtered out before the next delta is rendered. This prevents the advisor from recursively reviewing its own advice.\n\nWhen the primary transcript is rewritten, the advisor runtime is reset:\n\n- compaction\n- session switch/resume\n- branch/fork style history replacement\n- context-maintenance re-prime when the advisor's own context cannot fit\n\nReset clears the advisor's private in-memory transcript and rewinds its cursor. The next advisor update replays the current bounded primary transcript instead of continuing from stale pre-rewrite context.\n\nWhen the advisor is enabled mid-session, the cursor seeds to the current primary transcript length. That avoids replaying the whole old conversation on the first enabled turn.\n\n## Tools and isolation\n\nThe advisor receives a hard-isolated read-only tool set:\n\n- `read`\n- `search`\n- `find`\n- `advise`\n\nThe read/search/find tools are built against a distinct `ToolSession` whose session id is suffixed with `-advisor`. The advisor therefore does not share the primary agent's file snapshots, seen-lines tracking, conflict state, summary cache, or edit/yield capabilities.\n\nThe `advise` tool accepts one note and an optional severity:\n\n| Severity | Delivery | Intended use |\n|---|---|---|\n| omitted / `nit` | Non-interrupting aside, batched into the primary transcript at the next step boundary. | Cleanup, simplification, low-risk edge cases. |\n| `concern` | Interrupting steering message. | Material risk, likely wrong direction, missing constraint, hallucinated API. |\n| `blocker` | Interrupting steering message. | Continuing would clearly waste work or produce broken output. |\n\nInterrupting advice is sent through the steering channel and can abort in-flight tools at the next steering boundary. Non-interrupting notes are batched into one custom `advisor` transcript card with this prefix:\n\n```text\nAdvisor (a senior reviewer watching your work — weigh it, don't blindly obey):\n```\n\nWhen you deliberately interrupt the agent (Esc, or a cancel from collab, ACP, RPC, the SDK, or an extension), the advisor stops auto-resuming it. An interrupting `concern`/`blocker` raised while the run is stopped is recorded as a visible advisor card instead of restarting the turn, and a concern already in flight when you interrupt is preserved the same way rather than driving a surprise resume. The advice re-enters context the next time you resume — a new message, the `.`/`c` continue shortcut, or a steer/follow-up. A normal yield is unaffected: the advisor can still steer and resume a run the agent ended on its own.\n\n## Bounded catch-up with `advisor.syncBacklog`\n\n`advisor.syncBacklog` is not lockstep turn execution. It is a bounded catch-up delay for the primary agent when the advisor falls behind.\n\nAllowed values:\n\n- `off` — never wait for advisor catch-up\n- `1`\n- `3`\n- `5`\n\nOn primary turn end:\n\n1. the primary turn delta is queued for the advisor\n2. the advisor drain loop starts or continues in the background\n3. if `advisor.syncBacklog` is not `off`, the primary agent waits only while advisor backlog is at or above the configured threshold\n4. the wait is capped at 30 seconds\n5. if the advisor catches up below the threshold, the primary continues immediately\n6. if the cap expires, the primary continues anyway\n\nPractical interpretation:\n\n- `off` favors maximum primary throughput.\n- `1` is the closest mode to synchronous review: after each queued advisor delta, the primary waits up to 30 seconds for backlog to return to zero.\n- `3` and `5` allow more advisor lag before the primary pauses.\n\nAdvisor failures do not permanently stall the primary. A failed advisor prompt is retried; after three consecutive advisor failures, the runtime logs a warning, drops the backlog, and lets the session continue.\n\n## WATCHDOG.md\n\n`WATCHDOG.md` is advisor-only guidance. It is appended to the advisor system prompt; it is not injected into the primary agent's normal context and does not behave like `AGENTS.md`, `RULES.md`, or other context files.\n\nUse it for review priorities: risks the advisor should watch for, project-specific traps, dangerous APIs, architectural boundaries, and quality bars that are useful to a reviewer but too noisy for the main executor.\n\nExample:\n\n```markdown\n# Watchdog notes\n\nEspecially watch for:\n\n- Changes that bypass the durable queue in `src/jobs/`.\n- UI renderer paths that display unsanitized tool output.\n- New worker spawns that do not re-enter the CLI host.\n```\n\n### Discovery locations\n\n`discoverWatchdogFiles(cwd, agentDir)` loads every readable candidate from these locations:\n\n1. user level: `<active agent dir>/WATCHDOG.md` (`~/.omp/agent/WATCHDOG.md` by default; relocated by `PI_CODING_AGENT_DIR`)\n2. project levels while walking from `cwd` upward to the git repository root, or to the home directory when no repo root is found:\n   - `<dir>/WATCHDOG.md`\n   - `<dir>/.omp/WATCHDOG.md`\n\nUnlike native context files, watchdog discovery does not stop at the nearest project file. Multiple project watchdog files can load together.\n\nCandidates in hidden owner directories are ignored unless the file is inside an `.omp` directory. This keeps unrelated dot-directory conventions from being picked up accidentally while still allowing `.omp/WATCHDOG.md`.\n\n### `@` imports\n\n`WATCHDOG.md` content is expanded with the same `@` import helper used by context files:\n\n- relative imports resolve from the importing file's directory\n- `~/` resolves from the user's home directory\n- imports inside fenced code blocks and inline code spans stay literal\n- cycles are skipped\n- missing or unreadable imports leave the original `@path` text in place\n\n### Prompt order\n\nLoaded watchdog blocks are sorted as:\n\n1. user-level `WATCHDOG.md`\n2. project-level files from farther ancestors down toward `cwd`\n\nEach file is appended to the advisor system prompt as:\n\n```xml\nEspecially pay attention to:\n<attention>\n...expanded watchdog content...\n</attention>\n```\n\nLater project files sit closer to the end of the advisor prompt, so narrower directory guidance is more prominent than broad ancestor guidance.\n\n## Subagents\n\n`advisor.subagents` controls whether spawned task/eval subagents also get an advisor runtime.\n\n- `false` (default): only the main session can run an advisor.\n- `true`: eligible subagent sessions build their own advisor with the same settings/model-role resolution, then rerun `WATCHDOG.md` discovery for that subagent session's `cwd` and agent directory.\n\nSubagent advisors remain isolated from the subagent's primary tool session in the same way the main advisor is isolated from the main agent.\n\n## Cost and context behavior\n\nAdvisor usage is separate model usage. `/advisor status` reports advisor token counts and cost from the advisor agent's own transcript.\n\nThe advisor has its own append-only context. Before each advisor prompt, `AgentSession` estimates incoming tokens and may maintain advisor context:\n\n1. try model-level context promotion when enabled and a larger compatible model is available\n2. if promotion cannot fit enough context, compact the advisor's own message history\n3. if compaction has no candidates or still cannot fit, re-prime from the current bounded primary transcript\n\nThe advisor transcript is in-memory for the session. It is retained while the session runs so `/advisor dump` can inspect it, but advisor state is not a replacement for the primary persisted transcript.\n",
 	"ai-schema-normalize.md": "# AI tool-schema normalization\n\n`@oh-my-pi/pi-ai` exposes one unified schema normalizer that providers consume\nbefore tools are sent on the wire. All walkers live in\n`packages/ai/src/utils/schema/normalize.ts`; the operational contract is\n`packages/ai/src/utils/schema/CONSTRAINTS.md`.\n\nThere is no separate `strict-mode.ts` module any more — OpenAI strict-mode\nsanitization, OpenAI Responses `oneOf` rewriting, Google/Vertex/Gemini-CLI\nsanitization, Cloud Code Assist Claude sanitization, and MCP sanitization all\nshare the same option-driven walk.\n\n## Entry points\n\nAll exports live under `@oh-my-pi/pi-ai/utils/schema`:\n\n- `normalizeSchema(value, options)` — generic option-driven walker.\n- `normalizeSchemaForGoogle(value)` — Gemini / Vertex / Gemini CLI.\n- `normalizeSchemaForCCA(value)` — Cloud Code Assist Claude (Antigravity + GCA).\n- `normalizeSchemaForMCP(value)` — MCP inputSchemas before they enter the\n  custom-tool registry. `tool-bridge.ts` runs every MCP `inputSchema` through\n  this dispatcher.\n- `normalizeSchemaForOpenAIResponses(schema)` (alias\n  `sanitizeSchemaForOpenAIResponses`) — rewrites `oneOf` → `anyOf` for the\n  Responses family.\n- `sanitizeSchemaForStrictMode(schema)` and\n  `enforceStrictSchema(schema)` / `tryEnforceStrictSchema(schema)` — the\n  OpenAI strict-mode pipeline (sanitize → enforce). All three are exported\n  from `normalize.ts`.\n- `adaptSchemaForStrict(schema, strict)` from `./adapt` — thin composer that\n  upgrades draft-07 inputs to 2020-12 and wraps `tryEnforceStrictSchema` for\n  provider call sites. `./adapt` also exports the `NO_STRICT` global-bypass\n  flag (env `PI_NO_STRICT`) honored by every provider that emits `strict: true`.\n\nRemoved in the unified-flow refactor:\n\n- `strict-mode.ts` (merged into `normalize.ts`).\n- `sanitize-google.ts` and `normalize-cca.ts` (replaced by\n  `normalizeSchemaFor*` dispatchers).\n- `StringEnum` helper — use `z.enum([...])` directly; Zod's emitted JSON\n  Schema is already wire-compatible with Google and other providers.\n- `sanitizeSchemaFor{Google,CCA,MCP}` / `prepareSchemaForCCA` — renamed to\n  `normalizeSchemaFor{Google,CCA,MCP}`.\n\n## Dispatcher mapping\n\n| Provider transport(s)                                              | Dispatcher                                  |\n| ------------------------------------------------------------------ | ------------------------------------------- |\n| `openai-completions`, `openai-responses`, `openai-codex-responses` | `adaptSchemaForStrict` (sanitize + enforce) |\n| `openai-responses` family (`oneOf` → `anyOf` only)                 | `normalizeSchemaForOpenAIResponses`         |\n| `google-generative-ai`, `google-vertex`, Gemini CLI                | `normalizeSchemaForGoogle`                  |\n| Cloud Code Assist Claude (Antigravity + GCA, `claude-*` model ids) | `normalizeSchemaForCCA`                     |\n| MCP `inputSchema` ingestion                                        | `normalizeSchemaForMCP`                     |\n| `anthropic-messages` (native, not CCA)                             | per-provider whitelist in `anthropic.ts`    |\n\nGemini CLI / Antigravity CCA MUST run the full `normalizeSchemaForCCA`\npipeline (not just the first keyword-stripping pass) to keep parity with the\nshared Google Claude path.\n\n## Walk semantics\n\n`normalizeSchema` first detoxifies serialized Zod-instance-shaped inputs, upgrades them to\nJSON Schema 2020-12, dereferences the tree, then walks it with the option set\npinned by the dispatcher. Each node:\n\n1. Renames `snake_case` combinator/property keys to camelCase\n   (`any_of` → `anyOf`, etc.; collisions follow python-genai\n   `pop(from)`/`set(to)` semantics — snake_case wins).\n2. Applies the `handle_null_fields` collapse for nullable unions before\n   recursing into children.\n3. Strips keys the target provider does not support, optionally lifting\n   human-meaningful keys (`pattern`, `format`, min/max, `default`,\n   `examples`, ...) into the sibling `description` via the spill formatter\n   (`spill.ts`). Structural/meta keys (`$ref`, `$defs`,\n   `additionalProperties`) are not spilled.\n4. Normalizes type unions (`type: [\"T\", \"null\"]` → `type: \"T\"` + nullable\n   marker on Google, plain `type: \"T\"` on CCA).\n5. Collapses object-only / same-type combiners, optionally lossy-collapses\n   mixed-type combiners (CCA only), and runs the residual-combiner fixpoint.\n6. Validates against AJV 2020 when `validateAndFallback` is set (CCA path)\n   and emits the per-tool fallback `{ \"type\": \"object\", \"properties\": {} }`\n   on residual incompatibility — `type` array, `type: \"null\"`, `nullable`\n   key, or any remaining `anyOf`/`oneOf`/`allOf`.\n\n## OpenAI strict-mode pipeline\n\n`adaptSchemaForStrict(schema, strict)` runs `tryEnforceStrictSchema`,\nwhich composes:\n\n1. **Sanitize** (`sanitizeSchemaForStrictMode`): strips non-structural\n   keywords (`format`, `pattern`, min/max, `examples`, `default`,\n   `if`/`then`/`else`, `not`, `unevaluated*`, `patternProperties`,\n   `dependent*`, `content*`, `min/maxProperties`, `$dynamicRef`, etc.). The\n   `default` value is inlined into the sibling `description` as\n   ` (default: X)` before being dropped, unless `description` already\n   contains `(default:` or no `description` exists.\n2. **Enforce** (`enforceStrictSchema`): every object node gets\n   `additionalProperties: false`, every property goes into `required`, and\n   optional properties become nullable unions\n   (`anyOf: [<original>, { \"type\": \"null\" }]`). Tuple `prefixItems` are\n   strictified recursively.\n\nThe two passes use cache/cycle guards, so refs, `allOf`, and nullable wrapping\nstay deterministic without recursing forever. `tryEnforceStrictSchema` is\nfail-open: if anything throws, it returns `{ strict: false, schema: upgraded }`\nso callers MUST emit `strict: true` only when enforcement actually succeeded.\n\n### Edge cases the strict-mode normalizer handles\n\n- **Local `$ref` inlining.** OpenAI strict mode rejects\n  `{ \"$ref\": \"...\", \"description\": \"...\" }` with sibling keys. The\n  sanitizer pre-resolves local `#/...` refs against the root and merges\n  with **sibling keys winning** over the resolved def — same precedence\n  as `openai-python`'s `_ensure_strict_json_schema`. Recursive refs are\n  guarded by the per-walk epoch.\n- **Single-item `allOf`.** A `{ \"allOf\": [X], ...siblings }` collapses to\n  `{ ...X, ...siblings }` with the inlined entry's keys winning over the\n  original siblings (matches `openai-python`'s `_pydantic.py:79-83`). Multi-\n  item `allOf` is left intact for the downstream validator to reject if\n  needed.\n- **Type-array branches and nullable unions.** When a node has\n  `type: [\"T\", \"U\"]`, the sanitizer emits one variant schema per type,\n  pruning type-specific keywords (e.g. `properties`/`required` only stay on\n  the `object` variant, `items` only on the `array` variant). The shared\n  `description` is **hoisted onto the `anyOf` wrapper** instead of being\n  duplicated on every branch — so a strict nullable union becomes\n  `{ anyOf: [T, { type: \"null\" }], description: \"...\" }`, not\n  `anyOf: [{ ..., description }, { ..., description }]`.\n- **Enum/const without a `type`.** Both sanitize and enforce paths call\n  `inferStrictPrimitiveTypeFromEnumOrConst` to infer the primitive `type`\n  from `enum` / `const` values. Mixed-primitive enums (`[1, \"two\", null]`),\n  enums containing objects/arrays, and non-primitive `const` values\n  (`{a:1}`, `[1,2,3]`) cannot be described by a single `type` keyword and\n  trigger the strict-mode fail-open path — emitting a typeless schema\n  would just be rejected on the wire by OpenAI.\n\n## Performance: static fingerprint cache\n\n`resolveProviderModels` in `packages/catalog/src/model-manager.ts` and\n`readModelCache`/`writeModelCache` in `packages/catalog/src/model-cache.ts`\ncooperate via a `static_fingerprint` column on the `model_cache` SQLite\ntable (current cache schema version 5).\n\n- `fingerprintStatic(staticModels)` hashes the static catalog slice\n  (`Bun.hash(JSON.stringify(models))` in base36) and memoizes the result\n  by tagging the array with a symbol property. Multiple cold-start arms\n  calling `resolveProviderModels` with the same `staticModels` array pay\n  the JSON+hash cost once.\n- On cache read, if the network fetch is being skipped, the cached row is\n  fresh + authoritative, and the cached `static_fingerprint` matches the\n  current one, `resolveProviderModels` returns the cached models verbatim\n  — the cache already incorporates the same static state, so re-running\n  `mergeDynamicModels(static, cache)` would just rebuild the same objects.\n- `mergeModelSources` and `mergeDynamicModels` short-circuit on\n  empty-source inputs (the common shape after `(static, [])` or for\n  providers without a static catalog), avoiding Map churn entirely.\n\nCache rows written before the current schema version are dropped by the\ncache-version check; the column defaults to `''` for any row that survives\na version upgrade so the fingerprint-equality check naturally fails closed\nand the full merge re-runs.\n\n## Related\n\n- `docs/models.md` — registry, equivalence, compat flags\n  (`supportsStrictMode`, `toolStrictMode`, `disableStrictTools`).\n- `docs/provider-streaming-internals.md` — how the normalized schemas are\n  used downstream during the provider stream loop.\n- `docs/mcp-server-tool-authoring.md` — MCP `inputSchema` ingestion via\n  `normalizeSchemaForMCP`.\n- `packages/ai/src/utils/schema/CONSTRAINTS.md` — operational contract for\n  every normalization rule.\n",
 	"approval-mode.md": "# Tool approval mode\n\nTool approval has two independent inputs:\n\n1. **Tool declaration** — every tool may declare an `approval` tier:\n   - `read`: reads data or updates UI-only session metadata.\n   - `write`: mutates workspace/session state but does not execute arbitrary code.\n   - `exec`: executes code, shells out, drives a browser, spawns agents, or performs similarly broad actions.\n2. **User policy** — `tools.approval.<toolName>: allow | deny | prompt` overrides the mode for that tool unless a non-yolo safety override forces a prompt.\n\nTools without an `approval` declaration are treated as `exec`. This is the safe default for MCP and unknown custom tools.\n\n## Modes\n\nConfigure with `tools.approvalMode`:\n\n| Mode             | Auto-approves           | Prompts for     |\n| ---------------- | ----------------------- | --------------- |\n| `always-ask`     | `read`                  | `write`, `exec` |\n| `write`          | `read`, `write`         | `exec`          |\n| `yolo` (default) | `read`, `write`, `exec` | none            |\n\n`--auto-approve` and `--yolo` force `tools.approvalMode: yolo` for the session.\n\n## User overrides\n\n`tools.approval` is honored in every mode:\n\n```yaml\ntools:\n  approvalMode: write\n  approval:\n    bash: prompt\n    read: allow\n    mcp__filesystem__delete: deny\n```\n\nResolution per tool call:\n\n1. Compute the tool's approval decision from `tool.approval(args)`; omitted means `exec`.\n2. Normalize `tools.approval.<tool>` if present; invalid values are ignored.\n3. In `yolo` mode, the user policy is used when present; otherwise the call is allowed. Safety `override` reasons do not force a prompt in `yolo`.\n4. In non-yolo modes, if the tool sets `override: true`, `deny` is blocked and all other cases prompt, even if user policy says `allow`.\n5. Otherwise, a valid user policy wins.\n6. Otherwise, the active mode auto-approves or prompts by tier.\n\n## Safety overrides\n\nA tool can force a prompt with object-form approval:\n\n```ts\napproval: { tier: \"exec\", override: true, reason: \"Critical pattern detected\" }\n```\n\n`bash` uses this for critical destructive patterns such as `rm -rf /`, fork bombs, remote-fetch-then-execute, writes to `/etc/passwd`, and host shutdown commands. These surface as `reason` in the approval prompt, but in `yolo` mode they are auto-approved unless a user policy for the tool is set to `prompt` or `deny`.\n\n## Per-tool prompt details\n\nTools can add approval-prompt body lines with `formatApprovalDetails(args)`. The standard prompt includes:\n\n- `Allow tool: <name>`\n- `Origin: MCP server tool` for unannotated `mcp__...` tools\n- `Reason: <reason>` when the tool decision supplies one\n- tool-specific details such as command, path, code, browser action, or subagent assignment\n\n## Defining approval on tools\n\nBuilt-in and custom tools share the same shape:\n\n```ts\nexport type ToolTier = \"read\" | \"write\" | \"exec\";\nexport type ToolApprovalDecision = ToolTier | { tier: ToolTier; reason?: string; override?: boolean };\nexport type ToolApproval = ToolApprovalDecision | ((args: unknown) => ToolApprovalDecision);\n\napproval?: ToolApproval;\nformatApprovalDetails?: (args: unknown) => string | string[] | undefined;\n```\n\nExamples:\n\n```ts\napproval: \"read\";\n\napproval: (args) => (LSP_READONLY_ACTIONS.has(args.action) ? \"read\" : \"write\");\n\napproval: (args) =>\n  isCritical(args.command)\n    ? { tier: \"exec\", override: true, reason: \"Critical pattern detected\" }\n    : \"exec\";\n```\n\n## Subagents\n\nSubagents run headless with `tools.approvalMode: yolo` so they do not stall waiting for UI. The parent `task` approval is the authorization boundary. User `tools.approval.<tool>` settings continue to control whether a tool is allowed, prompted, or blocked.\n",
 	"auth-broker-gateway.md": "# Auth Broker and Auth Gateway\n\nThe auth broker and auth gateway are two cooperating HTTP services that move OAuth refresh tokens and provider access tokens off developer laptops and into a single broker host.\n\n- **`omp auth-broker serve`** holds the canonical SQLite credential vault, performs OAuth refreshes, and exposes a small REST API (`/v1/snapshot`, `/v1/snapshot/stream`, `/v1/credential/:id/refresh`, `/v1/credential/:id/disable`, `/v1/credential`, `/v1/usage`, `/v1/healthz`).\n- **`omp auth-gateway serve`** is a forward-proxy. It accepts OpenAI Chat Completions, Anthropic Messages, OpenAI Responses, and pi-native stream requests, resolves the broker-backed credential, and dispatches through `pi-ai` provider logic. Clients (containerised omp, llm-git, the macOS usage widget, …) never see the access token.\n\nTransport security between operator, broker, and gateway is delegated to the operator (Tailscale / Wireguard / reverse proxy + TLS). Every endpoint except `/v1/healthz` (broker) and `/healthz` (gateway) requires a bearer token.\n\nSource: `packages/ai/src/auth-broker/`, `packages/ai/src/auth-gateway/`, `packages/coding-agent/src/cli/auth-broker-cli.ts`, `packages/coding-agent/src/cli/auth-gateway-cli.ts`, `packages/coding-agent/src/session/auth-broker-config.ts`.\n\n## Data flow\n\n```\n                ┌────────────────────────────────────────────────────────────┐\n                │ broker host                                                │\n                │                                                            │\n  developer ──▶ │  ┌──────────────────────────┐    ┌────────────────────┐    │\n  laptop /      │  │  omp auth-broker serve   │◀──▶│  SQLite agent.db    │    │\n  CI / robomp   │  │  - holds refresh tokens  │    │  (canonical writer)│    │\n                │  │  - background refresher  │    └────────────────────┘    │\n                │  │  /v1/{snapshot,refresh,…}│                              │\n                │  └─────────┬────────────────┘                              │\n                │            │  bearer ($CONFIG_DIR/auth-broker.token)       │\n                │            ▼                                               │\n                │  ┌──────────────────────────┐                              │\n                │  │  omp auth-gateway serve  │  RemoteAuthCredentialStore   │\n                │  │  /v1/{chat,messages,…}   │  receives snapshot stream,   │\n                │  │  /v1/usage,/v1/models    │  refreshes credentials by id │\n                │  │  /v1/credentials/check   │  via the broker on expiry    │\n                │  └─────────┬────────────────┘                              │\n                └────────────┼───────────────────────────────────────────────┘\n                             │  bearer ($CONFIG_DIR/auth-gateway.token)\n                             ▼\n                  gateway clients\n                  (llm-git, macOS widget, robomp containers, IDE plugins, …)\n                                │\n                                ▼ provider request with broker-resolved credential\n                  api.anthropic.com / api.openai.com / …\n```\n\nThe broker is the only writer of OAuth refresh tokens. Clients (including the gateway itself) load a redacted snapshot in which every `refresh` field has been replaced with `REMOTE_REFRESH_SENTINEL`; when an access token expires the client calls `POST /v1/credential/:id/refresh` and the broker performs the refresh server-side. `RemoteAuthCredentialStore` rejects local replace/upsert/delete-by-provider mutations, with errors pointing at `omp auth-broker login` / `omp auth-broker logout`.\n\n## auth-broker\n\n### CLI\n\n```\nomp auth-broker serve     [--bind=host:port]                    # boot the broker\nomp auth-broker token     [--regenerate] [--json]               # print or rotate the bearer token\nomp auth-broker login     [<provider>] [--via=user@host] [--dry-run]\nomp auth-broker logout    [<provider>]\nomp auth-broker list      [--json]\nomp auth-broker import    <file|dir> [--provider=<id>] [--include-disabled] [--dry-run] [--json]\nomp auth-broker migrate   --from-local [--include-oauth] [--include-env] [--dry-run] [--json]\nomp auth-broker status    [--json]\n```\n\n- `serve` opens the local SQLite store at `getAgentDbPath()` and binds an HTTP listener (default `127.0.0.1:8765`). On startup a token is ensured at `<config-dir>/auth-broker.token` (mode `0600`, `0700` parent dir). The background refresher refreshes any OAuth credential whose `expires - Date.now() < refreshSkewMs` (default 5 min) every `refreshIntervalMs` (default 60 s).\n- `token` prints the cached bearer or generates a new one. `--regenerate` rotates it.\n- `login [<provider>]` runs the per-provider OAuth flow locally — when no provider is supplied, it falls back to an interactive numbered picker. With `--via=user@host` it shells out `ssh -L <callback-port>:127.0.0.1:<callback-port> user@host omp auth-broker login <provider>` so the OAuth callback hits the local browser but the credential is written on the broker host (`--via` requires `<provider>`). Built-in callback ports: `anthropic:54545`, `openai-codex:1455`, `google-gemini-cli:8085`, `google-antigravity:51121`, `gitlab-duo:8080`. The OAuth dance is driven in-process via `AuthStorage.login()` — there is no longer a `pi-ai` bin to spawn.\n- `logout [<provider>]` deletes every credential row for `<provider>`. With no argument it shows an interactive numbered picker of currently-stored providers.\n- `list` enumerates every registered OAuth provider id/name (the union of built-ins + `registerOAuthProvider` custom providers). `--json` emits a machine-readable array.\n- `import <file|dir>` imports CLIProxyAPI-style JSON credentials into the local SQLite store. Maps `type` field → omp provider (`claude → anthropic`, `codex → openai-codex`, `gemini → google-gemini-cli`, `antigravity → google-antigravity`, `gemini-cli → google-gemini-cli`).\n- `migrate --from-local` uploads local SQLite credentials to the configured broker (`POST /v1/credential`). Local API keys are included by default; local OAuth rows are skipped unless `--include-oauth` is set; environment-derived API keys are skipped unless `--include-env` is set. Re-runs are idempotent against the broker snapshot.\n- `status` health-pings the configured remote broker.\n\n### Endpoints\n\n| Method | Path                         | Auth   | Purpose                                                 |\n| ------ | ---------------------------- | ------ | ------------------------------------------------------- |\n| `GET`  | `/v1/healthz`                | none   | Liveness + version                                      |\n| `GET`  | `/v1/snapshot`               | bearer | Redacted snapshot (refresh tokens replaced by sentinel) |\n| `GET`  | `/v1/snapshot/stream`        | bearer | SSE snapshot stream with delta events and keepalives    |\n| `POST` | `/v1/credential`             | bearer | Upsert one OAuth or API-key credential                  |\n| `POST` | `/v1/credential/:id/refresh` | bearer | Force-refresh one OAuth credential                      |\n| `POST` | `/v1/credential/:id/disable` | bearer | Disable one credential with a recorded cause            |\n| `GET`  | `/v1/usage`                  | bearer | Aggregate `UsageReport[]` across credentials            |\n\nRequests use `Authorization: Bearer <token>`. The server compares against an in-memory token allow-list; the gateway’s implementation uses a timing-safe comparison.\n\n### Background refresher\n\n`AuthBrokerRefresher` iterates active OAuth credentials at `refreshIntervalMs` cadence and refreshes any within `refreshSkewMs` of expiry. Refreshes are single-flighted per credential id so a slow refresh cannot be retriggered. The refresher distinguishes:\n\n- **definitive failures** (`invalid_grant`, `invalid_token`, `revoked`, unauthorized refresh-token, 401/403 not from a network blip) — credentials are passed to `AuthStorage.disableCredentialById(id, cause)` so the next snapshot pull surfaces a clean delete on the client;\n- **transient failures** (timeout / ECONNREFUSED / fetch failed) — left in place for the next sweep.\n\n## auth-gateway\n\n### CLI\n\n```\nomp auth-gateway serve   [--bind=host:port] [--no-auth]\nomp auth-gateway token   [--regenerate] [--json]\nomp auth-gateway status  [--json]\nomp auth-gateway check   [--strict] [--json]\n```\n\n- `serve` requires `OMP_AUTH_BROKER_URL` (or `auth.broker.url` in `config.yml`) — the gateway is itself a broker client. It calls `AuthBrokerClient.fetchSnapshot()`, wraps it in `RemoteAuthCredentialStore`, and constructs an `AuthStorage` that resolves access tokens through the broker. Default bind is `127.0.0.1:4000`. The gateway token is stored at `<config-dir>/auth-gateway.token` (`0600`); `--no-auth` disables the bearer check entirely (loopback-only use).\n- `token` / `status` manage and inspect the gateway bearer token and upstream broker readiness.\n- `check` probes broker-backed credentials through the gateway store. Without `--strict` it uses provider usage probes; `--strict` also exercises each credential against its chat-completion endpoint and can consume a small amount of quota.\n\n### Endpoints\n\n| Method | Path                    | Auth   | Purpose                                                      |\n| ------ | ----------------------- | ------ | ------------------------------------------------------------ |\n| `GET`  | `/healthz`              | none   | Liveness + version                                           |\n| `GET`  | `/v1/usage`             | bearer | Aggregate `UsageReport[]` (proxied through `AuthStorage`)    |\n| `GET`  | `/v1/models`            | bearer | Bundled-model catalog filtered to providers with credentials |\n| `GET`  | `/v1/credentials/check` | bearer | Per-credential auth health probe                             |\n| `POST` | `/v1/chat/completions`  | bearer | OpenAI Chat Completions wire format                          |\n| `POST` | `/v1/messages`          | bearer | Anthropic Messages wire format                               |\n| `POST` | `/v1/responses`         | bearer | OpenAI Responses wire format                                 |\n| `POST` | `/v1/pi/stream`         | bearer | Native `pi-ai` stream wire format                            |\n\nThe model id is read from the top-level `model` field for foreign wire formats and from the pi-native request body for `/v1/pi/stream`. The gateway picks the first bundled `Model<Api>` matching that id, parses the inbound wire format into an omp `Context`, resolves the provider credential from broker-backed `AuthStorage`, dispatches through `streamSimple()`, and re-encodes the result to the inbound format (SSE for streamed responses).\n\nThere is no raw provider passthrough path. All supported routes go through `pi-ai` provider logic so credential-specific request shaping, OAuth refresh-on-auth-error, and provider quirks stay centralized.\n\n`idleTimeout` on the underlying `Bun.serve` is set to `255 s` so long thinking-budget calls do not get killed by Bun’s default idle timeout.\n\n## Usage cache: server-side 5-min jitter + client-side 15 s single-flight\n\nTwo layers cache the aggregate provider-usage report. Both are intentional and stacked.\n\n### Server-side cache (broker `AuthStorage`)\n\n`AuthStorage` caches each credential’s `UsageReport` in the broker’s SQLite store at a **5-minute per-credential TTL with ±25 % jitter**. Anthropic and OpenAI rate-limit `/usage` aggressively per source IP, and a synchronized 5-credential fan-out trips 429s every cycle; the jitter decorrelates refresh times within a few cycles. On fetch failure the store keeps the **last-good** report for up to 24 h with a short jittered re-poll window — so a transient upstream blip never blanks out the widget.\n\nConstants: `USAGE_REPORT_TTL_MS = 5 * 60_000`, `USAGE_LAST_GOOD_RETENTION_MS = 24 * 60 * 60_000` (`packages/ai/src/auth-storage.ts`).\n\n### Client-side single-flight (`RemoteAuthCredentialStore`)\n\nWhen the gateway (or any other broker client) calls `fetchUsageReports()` / `getUsageReport(provider, credential)`, `RemoteAuthCredentialStore` coalesces concurrent calls into a single `GET /v1/usage` round-trip and caches the result for **15 s** in memory.\n\n- `USAGE_CACHE_TTL_MS = 15_000` (`packages/ai/src/auth-broker/remote-store.ts`).\n- A single `#usageInflight` promise is shared across all callers; a per-caller `AbortSignal` is **raced** against the shared promise, not threaded into it, so one caller’s abort never cascades into a peer’s in-flight request.\n- On fetch failure the rejected promise is logged and the awaited value is `null` — callers (`AuthStorage.fetchUsageReports`, `#getUsageReport`) treat a `null` report as \"no usage signal for this cycle\" and proceed without it. **This is the 15 s TTL fallback**: the client absorbs transient broker outages by suppressing the error, returning `null` to ranking, and re-attempting after the 15 s window.\n\nThe 15 s client window deliberately sits below the broker’s 5 min server cache, so almost every client poll is served from the broker’s already-cached value; the client cache exists to absorb the parallel fan-out generated by `AuthStorage.#rankOAuthSelections` into a single broker round-trip.\n\n## Client snapshot cache\n\n`discoverAuthStorage()` persists the broker snapshot to `~/.omp/cache/auth-broker-snapshot.enc` after the initial `/v1/snapshot` fetch and after later broker-sourced full snapshots. The file is AES-256-GCM encrypted with `SHA-256(OMP_AUTH_BROKER_TOKEN)` and authenticated with the broker URL as additional data, so changing either the token or URL makes the cache unreadable. The file is written atomically with mode `0600`.\n\nFreshness is anchored to the broker-stamped `snapshot.generatedAt`, not local write time. Default TTL is 1 h (`OMP_AUTH_BROKER_SNAPSHOT_TTL_MS`); `0` disables the cache and restores the old always-fetch boot path. When the cached snapshot is still fresh, `omp` boots from it and skips the blocking `/v1/snapshot` query. `RemoteAuthCredentialStore` still starts its normal SSE / long-poll background sync immediately, so deleted or rotated credentials reconcile after startup, and expired OAuth access tokens still refresh through `POST /v1/credential/:id/refresh`.\n\nIf the broker is down at boot and a fresh cache exists, startup now succeeds from the cached snapshot. If the cache is missing, expired, corrupt, written for a different URL, or encrypted with a different token, startup falls back to the live fetch and fails the same way it did before if the broker is unreachable.\n\n## Operator opt-in\n\nThe broker is **off** unless `OMP_AUTH_BROKER_URL` (or `auth.broker.url` in `config.yml`) is set. When set, `discoverAuthStorage` in `packages/coding-agent/src/sdk.ts` swaps the local SQLite credential store for `RemoteAuthCredentialStore` and every API call resolves credentials through the broker.\n\n### Environment variables\n\n| Variable                | Purpose                                                                                                                                            | Required when                                                                                                             |\n| ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- |\n| `OMP_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`). Selecting this puts the client in broker mode — local SQLite is bypassed. | Any time the omp client should resolve credentials through a broker (and required by `omp auth-gateway serve`).           |\n| `OMP_AUTH_BROKER_TOKEN` | Bearer token used for every broker endpoint except `/v1/healthz`.                                                                                  | When `OMP_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`. |\n| `OMP_AUTH_BROKER_SNAPSHOT_TTL_MS` | Freshness window for the encrypted local snapshot cache. Default `3600000` (1 h); `0` disables cache reads and writes. | Optional in broker mode. |\n| `OMP_AUTH_BROKER_SNAPSHOT_CACHE`  | Path override for the encrypted local snapshot cache. Default `~/.omp/cache/auth-broker-snapshot.enc` (or XDG cache equivalent). | Optional in broker mode. |\n\nResolution order in `resolveAuthBrokerConfig()`:\n\n1. `OMP_AUTH_BROKER_URL` env (else `auth.broker.url` from `config.yml`, resolved through `resolveConfigValue`);\n2. `OMP_AUTH_BROKER_TOKEN` env (else `auth.broker.token` from `config.yml`, else `<config-dir>/auth-broker.token`);\n3. URL set but no token resolvable → hard error pointing at the token file path.\n\nThe gateway has no dedicated env vars — it inherits `OMP_AUTH_BROKER_*` because it is itself a broker client.\n\n### `config.yml` keys\n\n| Key                 | Default | Purpose                                                                                                                                                                            |\n| ------------------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `auth.broker.url`   | unset   | Same as `OMP_AUTH_BROKER_URL`; env wins. Hidden from the settings UI. Values are resolved as a literal, an environment variable name, or `!<shell command>` to use trimmed stdout. |\n| `auth.broker.token` | unset   | Same as `OMP_AUTH_BROKER_TOKEN`; env wins. Values are resolved the same way.                                                                                                       |\n\n### Token files\n\n| Path                              | Owner                                                | Mode                          |\n| --------------------------------- | ---------------------------------------------------- | ----------------------------- |\n| `<config-dir>/auth-broker.token`  | `omp auth-broker serve` (created at first start)     | `0600` in a `0700` parent dir |\n| `<config-dir>/auth-gateway.token` | `omp auth-gateway serve` (skipped under `--no-auth`) | `0600` in a `0700` parent dir |\n\n`<config-dir>` resolves to `~/.omp/` (respecting `PI_CONFIG_DIR`).\n\n## Interaction with the local API-key resolution order\n\nThe broker only owns OAuth credentials and provider-API-key credentials that were uploaded to it. The standard credential ladder in `models.md` (`Auth and API key resolution order`) is preserved, with one addition committed alongside the gateway:\n\n- `AuthStorage.setConfigApiKey / removeConfigApiKey / clearConfigApiKeys` let a `models.yml` `apiKey` beat a stored OAuth token **without** overriding an explicit `--api-key`. This is what allows a broker-resolved OAuth credential to be reliably shadowed by a per-environment `models.yml` config key when both are present.\n\n## See also\n\n- [`secrets.md`](./secrets.md) — secret obfuscation around tokens that _do_ leak through (e.g. `OMP_AUTH_BROKER_TOKEN` in shell output).\n- [`models.md`](./models.md) — provider auth resolution order; the broker plugs in at layers 2–3 (stored credentials).\n- [`environment-variables.md`](./environment-variables.md) — full env reference including `OMP_AUTH_BROKER_URL` / `OMP_AUTH_BROKER_TOKEN`.\n",
@@ -15,7 +16,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"config-usage.md": "# Configuration Discovery and Resolution\n\nThis document describes how the coding-agent resolves configuration today: which roots are scanned, how precedence works, and how resolved config is consumed by settings, skills, hooks, tools, and extensions.\n\n## Scope\n\nPrimary implementation:\n\n- `packages/coding-agent/src/config.ts`\n- `packages/coding-agent/src/config/settings.ts`\n- `packages/coding-agent/src/config/settings-schema.ts`\n- `packages/coding-agent/src/discovery/builtin.ts`\n- `packages/coding-agent/src/discovery/helpers.ts`\n\nKey integration points:\n\n- `packages/coding-agent/src/capability/index.ts`\n- `packages/coding-agent/src/discovery/index.ts`\n- `packages/coding-agent/src/extensibility/skills.ts`\n- `packages/coding-agent/src/extensibility/hooks/loader.ts`\n- `packages/coding-agent/src/extensibility/custom-tools/loader.ts`\n- `packages/coding-agent/src/extensibility/extensions/loader.ts`\n\n---\n\n## Resolution flow (visual)\n\n```text\n         Generic helper order (`config.ts`)\n┌───────────────────────────────────────┐\n│ 1) ~/.omp/agent, ~/.claude, ...       │\n│ 2) <cwd>/.omp, <cwd>/.claude, ...     │\n└───────────────────────────────────────┘\n                    │\n                    ▼\n        capability providers enumerate items\n (native provider scans project .omp before user .omp;\n  other providers have their own loading rules)\n                    │\n                    ▼\n      provider priority sort + capability dedup\n                    │\n                    ▼\n          subsystem-specific consumption\n   (settings, skills, hooks, tools, extensions)\n```\n\n## 1) Config roots and source order\n\n## Canonical roots\n\n`src/config.ts` defines a fixed source priority list:\n\n1. `.omp` (native)\n2. `.claude`\n3. `.codex`\n4. `.gemini`\n\nUser-level bases:\n\n- `~/.omp/agent`\n- `~/.claude`\n- `~/.codex`\n- `~/.gemini`\n\nProject-level bases:\n\n- `<cwd>/.omp`\n- `<cwd>/.claude`\n- `<cwd>/.codex`\n- `<cwd>/.gemini`\n\n`CONFIG_DIR_NAME` is `.omp` (`packages/utils/src/dirs.ts`).\n\n## Profiles\n\nA named profile (`omp --profile <name>`, the `--alias` shortcut, or `OMP_PROFILE` / `PI_PROFILE`) relocates the OMP user base. When a profile is active, every OMP-native user-level path written here as `~/.omp/agent/...` resolves to `~/.omp/profiles/<name>/agent/...` instead.\n\nThe relocation is uniform across the native provider (`builtin.ts`) and the generic `config.ts` helpers, so it covers slash commands, rules, prompts, instructions, hooks, tools, extensions, settings, skills, and MCP, plus the top-level `SYSTEM.md` / `RULES.md` / `AGENTS.md` files and runtime state (sessions, blobs, `agent.db`). A profile sees only its own OMP config, never the default profile's `~/.omp/agent`.\n\nThe other source bases are not profile-scoped and load identically under every profile: the external-tool bases (`~/.claude`, `~/.codex`, `~/.gemini`) belong to those tools, and the project-level bases (`<cwd>/.omp`, `<cwd>/.claude`, ...) are keyed to the working directory. Throughout this document, read `~/.omp/agent` as shorthand for the active profile's agent directory.\n\n## Important constraint\n\nThe generic helpers in `src/config.ts` do **not** include `.pi` in source discovery order.\n\n---\n\n## 2) Core discovery helpers (`src/config.ts`)\n\n## `getConfigDirs(subpath, options)`\n\nReturns ordered entries:\n\n- User-level entries first (by source priority)\n- Then project-level entries (by same source priority)\n\nOptions:\n\n- `user` (default `true`)\n- `project` (default `true`)\n- `cwd` (default `getProjectDir()`)\n- `existingOnly` (default `false`)\n\nThis API is used for directory-based config lookups (commands, hooks, tools, agents, etc.).\n\n## `findConfigFile(subpath, options)` / `findConfigFileWithMeta(...)`\n\nSearches for the first existing file across ordered bases, returns first match (path-only or path+metadata).\n\n## `findAllNearestProjectConfigDirs(subpath, cwd)`\n\nWalks parent directories upward and returns the **nearest existing directory per source base** (`.omp`, `.claude`, `.codex`, `.gemini`), then sorts results by source priority.\n\nUse this when project config should be inherited from ancestor directories (monorepo/nested workspace behavior).\n\n---\n\n## 3) File config wrapper (`ConfigFile<T>` in `src/config.ts`)\n\n`ConfigFile<T>` is the schema-validated loader for single config files.\n\nSupported formats:\n\n- `.yml` / `.yaml`\n- `.json` / `.jsonc`\n\nBehavior:\n\n- Validates parsed data against a provided Zod schema.\n- Caches load result until `invalidate()`.\n- Returns tri-state result via `tryLoad()`:\n  - `ok`\n  - `not-found`\n  - `error` (`ConfigError` with schema/parse context)\n\nLegacy migration still supported:\n\n- If target path is `.yml`/`.yaml`, a sibling `.json` is auto-migrated once (`migrateJsonToYml`).\n\n---\n\n## 4) Settings resolution model (`src/config/settings.ts`)\n\nThe runtime settings model is layered:\n\n1. Global settings: `~/.omp/agent/config.yml`\n2. Project settings: discovered via settings capability (`settings.json` and `config.yml` from providers)\n3. CLI config overlays: `omp --config <path>` / repeated `--config` files, loaded as `config.yml`-style YAML for this process only\n4. Runtime overrides: in-memory, non-persistent\n5. Schema defaults: from `SETTINGS_SCHEMA`\n\nEffective precedence:\n\n`defaults <- global <- project <- CLI config overlays <- overrides`\n\nWrite behavior:\n\n- `settings.set(...)` writes to the **global** layer (`config.yml`) and queues background save.\n- Project settings are read-only from capability discovery.\n\n## Migration behavior still active\n\nOn startup, if `config.yml` is missing:\n\n1. Migrate from `~/.omp/agent/settings.json` (renamed to `.bak` on success)\n2. Merge with legacy DB settings from `agent.db`\n3. Write merged result to `config.yml`\n\nField-level migrations in `#migrateRawSettings`:\n\n- `queueMode` -> `steeringMode`\n- `ask.timeout` milliseconds -> seconds when old value looks like ms (`> 1000`)\n- Legacy flat `theme: \"...\"` -> `theme.dark/theme.light` structure\n\n---\n\n## 5) Capability/discovery integration\n\nMost non-core config loading flows through the capability registry (`src/capability/index.ts` + `src/discovery/index.ts`).\n\n## Provider ordering\n\nProviders are sorted by numeric priority (higher first). Example priorities:\n\n- Native OMP (`builtin.ts`): `100`\n- Claude: `80`\n- Codex / agents / Claude marketplace: `70`\n- Gemini: `60`\n\n```text\nProvider precedence (higher wins)\n\nnative (.omp)          priority 100\nclaude                 priority  80\ncodex / agents / ...   priority  70\ngemini                 priority  60\n```\n\n## Dedup semantics\n\nCapabilities define a `key(item)`:\n\n- same key => first item wins (higher-priority/earlier-loaded item)\n- no key (`undefined`) => no dedup, all items retained\n\nRelevant keys:\n\n- skills: `name`\n- tools: `name`\n- hooks: `${type}:${tool}:${name}`\n- extension modules: `name`\n- extensions: `name`\n- settings: no dedup (all items preserved)\n\n---\n\n## 6) Native `.omp` provider behavior (`packages/coding-agent/src/discovery/builtin.ts`)\n\nNative provider (`id: native`) reads native config from:\n\n- project: `<cwd>/.omp/...`\n- user: `~/.omp/agent/...`\n\n### Directory admission rules\n\n- Slash commands, rules, prompts, instructions, hooks, tools, extensions, extension modules, and settings use a project/user root only when the root directory exists and is non-empty.\n- Skills scan `<ancestor>/.omp/skills` for each ancestor from the current working directory up to the repo root/home boundary, plus `~/.omp/agent/skills`, without requiring the root `.omp` directory itself to be non-empty.\n- `SYSTEM.md` and `AGENTS.md` read user-level files directly and use nearest-ancestor project `.omp` lookup for project files, but the project `.omp` directory must be non-empty. See [`docs/system-prompt-customization.md`](./system-prompt-customization.md) for the full `SYSTEM.md` / `APPEND_SYSTEM.md` contract (replace vs. append, templating).\n\n### Scope-specific loading\n\n- Skills: `<ancestor>/.omp/skills/*/SKILL.md` and `~/.omp/agent/skills/*/SKILL.md`\n- Slash commands: `commands/*.md`\n- Rules: `rules/*.{md,mdc}`\n- Prompts: `prompts/*.md`\n- Instructions: `instructions/*.md`\n- Hooks: `hooks/pre/*`, `hooks/post/*`\n- Tools: `tools/*.{json,md,ts,js,sh,bash,py}` and `tools/<name>/index.ts`\n- Extension modules: discovered under `extensions/` (+ legacy `settings.json.extensions` string array)\n- Extensions: `extensions/<name>/gemini-extension.json`\n- Settings capability: `settings.json`, then `config.yml`\n\n### Nearest-project lookup nuance\n\n## For `SYSTEM.md` and `AGENTS.md`, native provider uses nearest-ancestor project `.omp` directory search (walk-up) and still requires the project `.omp` dir to be non-empty.\n\n## 7) How major subsystems consume config\n\n## Settings subsystem\n\n- `Settings.init()` loads global `config.yml` + discovered project settings capability items.\n- Only capability items with `level === \"project\"` are merged into project layer.\n\n### Session title prompt override\n\nCreate `TITLE_SYSTEM.md` in the same config locations as `SYSTEM.md` / `APPEND_SYSTEM.md`:\n\n```text\n# ~/.omp/agent/TITLE_SYSTEM.md\nGenerate a session name using lowercase `<type>:<primary-objective>`.\n```\n\n- Missing `TITLE_SYSTEM.md` keeps the bundled title prompts.\n- Discovery uses the same project-then-user config directory pattern as `SYSTEM.md`: project `.omp/TITLE_SYSTEM.md` first, then user `~/.omp/agent/TITLE_SYSTEM.md` and the other supported config bases.\n- The override replaces only the automatic session-title generation system prompt; normal `SYSTEM.md` / `APPEND_SYSTEM.md` prompt customization is unaffected.\n- The online path forces the `set_title` tool call when the title model honors a forced `tool_choice`. Tool-choice-less providers (chat-completions hosts without `tool_choice` support, Claude Fable/Mythos) instead receive a marker-based prompt and emit the title wrapped in `<title>...</title>`, which is parsed leniently (a plain sentence or a truncated/unclosed tag still works). A `TITLE_SYSTEM.md` override is reused in both modes; in marker mode the wrap-in-`<title>` instruction is appended after it. The local tiny-title path keeps the `<title>...</title>` prefill/stop wrapper and uses this file as its system turn.\n\n## Skills subsystem\n\n- `extensibility/skills.ts` loads via `loadCapability(skillCapability.id, { cwd })`.\n- Applies source toggles and filters (`ignoredSkills`, `includeSkills`, custom dirs).\n- Legacy-named toggles still exist (`skills.enablePiUser`, `skills.enablePiProject`) but they gate the native provider (`provider === \"native\"`).\n\n## Hooks subsystem\n\n- `discoverAndLoadHooks()` resolves hook paths from hook capability + explicit configured paths.\n- Then loads modules via Bun import.\n\n## Tools subsystem\n\n- `discoverAndLoadCustomTools()` resolves tool paths from tool capability + plugin tool paths + explicit configured paths.\n- Declarative `.md/.json` tool files are metadata only; executable loading expects code modules.\n\n## Extensions subsystem\n\n- `discoverAndLoadExtensions()` resolves extension modules from extension-module capability plus explicit paths.\n- Current implementation intentionally keeps only capability items with `_source.provider === \"native\"` before loading.\n\n---\n\n## 8) Precedence rules to rely on\n\nUse this mental model:\n\n1. Source directory ordering from `config.ts` determines candidate path order.\n2. Capability provider priority determines cross-provider precedence.\n3. Capability key dedup determines collision behavior (first wins for keyed capabilities).\n4. Subsystem-specific merge logic can further change effective precedence (especially settings).\n\n### Settings-specific caveat\n\nSettings capability items are not deduplicated; `Settings.#loadProjectSettings()` deep-merges project items in returned order. Because merge applies later item values over earlier values, effective override behavior depends on provider emission order, not just capability key semantics.\n\n---\n\n## 9) Legacy/compatibility behaviors still present\n\n- `ConfigFile` JSON -> YAML migration for YAML-targeted files.\n- Settings migration from `settings.json` and `agent.db` to `config.yml`.\n- Settings key migrations include `queueMode`, `ask.timeout`, flat `theme`, `task.isolation.enabled`, legacy `task.isolation.mode` values, removed edit modes, `statusLine.plan_mode`, `memories.enabled`, and hindsight scoping/name fields.\n- Legacy setting names `skills.enablePiUser` / `skills.enablePiProject` are still active gates for native skill source.\n\nIf these compatibility paths are removed in code, update this document immediately; several runtime behaviors still depend on them today.\n",
 	"context-files.md": "# Context files\n\nContext files are Markdown instruction files that `omp` discovers automatically before a session starts and injects into the agent's project context. Use them for repository conventions, architecture notes, test and review expectations, and instructions that should travel with a user account or a project.\n\nYou never have to ask the agent to go read `AGENTS.md`, `CLAUDE.md`, `GEMINI.md`, or similar files — the relevant ones are already discovered, loaded, and placed in context when the session begins.\n\n## How context files relate to other concepts\n\nFour similarly named things behave differently. Keep them straight:\n\n- **Context files** are read as plain Markdown and shown to the agent inside a `<context>` block. They are advisory background that stays in the session's opening context.\n- **Sticky rules** come from a top-level `RULES.md`. They are converted into an always-apply rule that is re-attached near the current turn, so they keep their hold even after the visible conversation grows. See \"Sticky rules vs normal context\" below.\n- **Discovery providers** are the config-source adapters (`native`, `claude`, `codex`, `gemini`, `opencode`, `github`, `agents`, `agents-md`) that know where each tool keeps its files. The same provider that contributes context files may also contribute MCP servers, slash commands, skills, hooks, tools, prompts, and settings.\n- **Model providers** are inference backends such as `anthropic`, `openai`, `google`, `groq`, `ollama`, and `openrouter`. They have nothing to do with context files except that both kinds of id share the one `disabledProviders` list — see \"Disabling discovery providers\" below and [Providers](./providers.md).\n\nAuthoring **skills** and **rule** files (as opposed to the sticky `RULES.md`) is covered in [Skills](./skills.md). Customizing the system prompt with `SYSTEM.md` is covered in [System prompt customization](./system-prompt-customization.md).\n\n## Native `.omp` files\n\nThe native provider is the recommended format for new projects. It reads from your user agent directory and from `.omp/` directories inside a project, and it has the highest discovery priority, so its files win over every other convention at the same scope.\n\n| File | Scope | Behavior |\n|---|---|---|\n| `~/.omp/agent/AGENTS.md` | User | User-level context for every session unless the `native` provider is disabled. |\n| `<ancestor>/.omp/AGENTS.md` | Project | Project context. `omp` walks upward from the current directory to the repository root and uses the **nearest** non-empty `.omp/AGENTS.md`. Farther native project files are not also included. |\n| `~/.omp/agent/RULES.md` | User | User-level sticky rule content. Loaded as an always-apply rule, not as a context file. |\n| `<ancestor>/.omp/RULES.md` | Project | Project sticky rule content. Same nearest-ancestor walk-up as above. Loaded as an always-apply rule. |\n\nTwo details matter:\n\n- **Walk-up to the repository root.** Discovery starts in the current working directory and climbs through each ancestor up to the repository root, stopping at the first ancestor that has a usable `.omp/` directory. The *nearest* match wins; ancestors above it are not loaded as native context.\n- **The `.omp/` directory must be non-empty.** An empty `.omp/` directory is skipped during the walk-up, so the search continues to the next ancestor. An empty `AGENTS.md` or `RULES.md` file contributes nothing.\n\n`~/.omp/agent` is the user base. If `PI_CODING_AGENT_DIR` is set, it relocates that base, so the user files become `$PI_CODING_AGENT_DIR/AGENTS.md` and `$PI_CODING_AGENT_DIR/RULES.md`.\n\n### Monorepo example\n\n```text\nrepo/\n  .omp/\n    AGENTS.md\n    RULES.md\n  packages/api/\n    .omp/\n      AGENTS.md\n```\n\nStarting a session in `repo/packages/api`:\n\n- The native context file is `repo/packages/api/.omp/AGENTS.md` (the nearest one). `repo/.omp/AGENTS.md` is **not** also included.\n- The project sticky rule is `repo/packages/api/.omp/RULES.md` if present; otherwise the walk-up continues and `repo/.omp/RULES.md` is used.\n\nPut broad, durable project background in `AGENTS.md`. Reserve `RULES.md` for short, hard requirements that must stay visible across long conversations.\n\n## Other supported context conventions\n\n`omp` also discovers the context files of other agent tools so existing projects keep working without migration. The table lists context-file behavior only; each provider may also contribute other capabilities.\n\n| Provider id | Convention path | Scope | Notes |\n|---|---|---|---|\n| `native` | `.omp/AGENTS.md` | User + project | Recommended `omp` format. User file at `~/.omp/agent/AGENTS.md`; project file is the nearest non-empty `.omp/AGENTS.md` walking up to the repo root. |\n| `claude` | `.claude/CLAUDE.md` | User + project | User file `~/.claude/CLAUDE.md`; project file `<cwd>/.claude/CLAUDE.md` only (no ancestor walk-up). |\n| `codex` | `.codex/AGENTS.md` | User | User file `~/.codex/AGENTS.md` only. Project-level Codex context comes from a standalone `AGENTS.md` via the `agents-md` provider, not from `<cwd>/.codex/AGENTS.md`. |\n| `gemini` | `.gemini/GEMINI.md` | User + project | User file `~/.gemini/GEMINI.md`; project file `<cwd>/.gemini/GEMINI.md` only (no ancestor walk-up). |\n| `opencode` | `.config/opencode/AGENTS.md` | User | User file `~/.config/opencode/AGENTS.md` only. |\n| `github` | `.github/copilot-instructions.md` | Project | Project-only GitHub Copilot instructions from `<cwd>/.github/copilot-instructions.md`. |\n| `agents` | `.agent/AGENTS.md`, `.agents/AGENTS.md` | User + project | User files from `~/.agent/` and `~/.agents/`; project files discovered while walking up from the current directory to the repository root. |\n| `agents-md` | `AGENTS.md` | Project | Standalone (non-config-directory) `AGENTS.md` files, discovered by walking up from the current directory to the repository root (or home when no repo root is known). Files whose parent directory name starts with `.` are ignored — those belong to a config-directory provider instead. |\n\nProviders marked \"(no ancestor walk-up)\" only look in the current working directory's config directory. If you need ancestor walk-up behavior, prefer the native `.omp/AGENTS.md` format or a standalone `AGENTS.md` (the `agents-md` provider), or launch `omp` from the directory that holds the config directory.\n\n## Load order and shadowing\n\nWhen two providers describe the *same* scope, the higher-priority provider wins. Provider priorities:\n\n| Priority | Provider id |\n|---:|---|\n| 100 | `native` |\n| 80 | `claude` |\n| 70 | `agents`, `codex` |\n| 60 | `gemini` |\n| 55 | `opencode` |\n| 30 | `github` |\n| 10 | `agents-md` |\n\nDiscovered files are then deduplicated by scope:\n\n- **One user context file** is kept across all providers. Because `native` has the highest priority, `~/.omp/agent/AGENTS.md` shadows every other user-level context file.\n- **One project context file per directory depth.** Depth is measured from the current directory: the cwd is depth 0, its parent depth 1, and so on. Config subdirectories of an ancestor (`.claude/`, `.github/`, `.gemini/`, …) count as the same depth as that ancestor.\n- **At the same depth, the higher-priority provider shadows the rest.**\n- **Across depths, multiple files survive.** In a monorepo, an ancestor `AGENTS.md` and a package-level one are different depths and both load.\n- **Byte-identical files are collapsed.** If two surviving files have exactly the same content, only the copy closest to the cwd is kept.\n\nAfter deduplication, project files are sorted so **farther ancestors appear first** and files **closer to the cwd appear last**. Later files sit nearer the end of the context block, where they are most prominent.\n\n### Worked shadowing example\n\n```text\nrepo/\n  AGENTS.md\n  packages/api/\n    AGENTS.md\n    .github/copilot-instructions.md\n```\n\nStarting in `repo/packages/api`:\n\n- `repo/AGENTS.md` is found by `agents-md` at depth 2 and kept.\n- `repo/packages/api/AGENTS.md` (`agents-md`, priority 10) and `repo/packages/api/.github/copilot-instructions.md` (`github`, priority 30) both resolve to depth 0. GitHub's higher priority shadows the package-level standalone `AGENTS.md`, so the Copilot file wins at that depth.\n- The two kept files are ordered root-first, package-last, so `packages/api`'s file is the more prominent one.\n- If you add `repo/packages/api/.omp/AGENTS.md`, `native` (priority 100) wins depth 0 outright, shadowing both lower-priority files.\n\n## Injection behavior\n\nDiscovered context files are injected into the opening project prompt as a single `<context>` block, one `<file>` element per surviving file, in the sort order above:\n\n```xml\n<context>\nYou MUST follow the context files below for all tasks:\n<file path=\"/abs/path/to/repo/AGENTS.md\">\n...root content...\n</file>\n<file path=\"/abs/path/to/repo/packages/api/.github/copilot-instructions.md\">\n...package content...\n</file>\n</context>\n```\n\nThe agent sees each file's absolute path and its fully expanded Markdown content (with `@` imports already resolved — see below). Loading is automatic — there is no need to instruct the agent to search for `AGENTS.md`, `CLAUDE.md`, `GEMINI.md`, `.cursorrules`, or similar files during a session.\n\nDeeper-directory `AGENTS.md` files that were *not* auto-loaded (for example, ones below the current directory) are surfaced separately in a `<dir-context>` block that lists their paths and tells the agent to read them before editing those directories. Those files are pointers, not full injected content.\n\n## `@` imports\n\nInside any context file, an `@path` token expands inline to the referenced file's content before injection:\n\n```markdown\n# Project notes\n\nRead @docs/architecture.md before changing storage code.\nShared release steps live in @../RELEASE.md and personal aliases in @~/.notes/aliases.md.\n```\n\nThe exact rules:\n\n- **Relative paths resolve from the importing file's own directory**, not the session's working directory.\n- **`~/` and `~`** resolve from the user's home directory; absolute paths are used as-is.\n- **Tokens inside fenced code blocks and inline code spans are left untouched** — useful when you want to *write about* an `@token` without expanding it.\n- **`git@github.com:org/repo.git` and `user@example.com`-style tokens are not treated as imports.** A token only counts when the `@` sits at the start of a line or after a space or tab.\n- **Trailing sentence punctuation is trimmed** off the path (`. , ; : ! ? ) ] } \" '`), so `@docs/setup.md.` imports `docs/setup.md`.\n- **Imports recurse up to five hops.** An imported file may itself contain `@` imports, up to a total depth of five.\n- **Cycles are skipped.** A file already pulled into the current expansion tree is not re-expanded, so mutual imports terminate cleanly.\n- **A missing or unreadable target leaves the original `@token` text in place** rather than erroring.\n\n## Sticky rules vs normal context\n\nUse a normal context file (`AGENTS.md`, `CLAUDE.md`, `GEMINI.md`, `.github/copilot-instructions.md`, …) for the bulk of your guidance: repository overview, code style, build and test commands, review expectations, and local conventions. These load into the opening `<context>` block.\n\nUse a top-level **`RULES.md`** for the handful of hard requirements that must stay active even after a long conversation has pushed the opening context far up the transcript:\n\n```markdown\n# ~/.omp/agent/RULES.md\n\nNever commit or push unless the user explicitly asks.\nDo not edit generated files.\n```\n\n`RULES.md` is special:\n\n- It is read **only** at the native locations — `~/.omp/agent/RULES.md` and the nearest `<ancestor>/.omp/RULES.md` from the cwd up to the repo root. A `RULES.md` anywhere else is not a context-file convention and is ignored.\n- It is loaded as an **always-apply rule**, not as a context file, so it is re-attached near the current turn and keeps its hold across long sessions.\n- It is **always sticky**: frontmatter cannot make it non-sticky. If you want conditional or opt-in behavior, write a normal rule file instead (see [Skills](./skills.md)).\n\nKeep `RULES.md` short. Long background belongs in `AGENTS.md`, where it costs context budget only once.\n\n## Disabling discovery providers\n\nTurn a provider off with the `disabledProviders` setting in `~/.omp/agent/config.yml`, a project's `.omp/config.yml`, or a `--config` overlay:\n\n```yaml\n# .omp/config.yml\ndisabledProviders:\n  - claude\n  - github\n```\n\n`disabledProviders` is a **whole-provider switch with one shared id namespace**, used by two unrelated subsystems:\n\n| Id kind | Examples | Effect when listed |\n|---|---|---|\n| Discovery provider ids | `native`, `claude`, `codex`, `gemini`, `opencode`, `github`, `agents`, `agents-md` | The entire config source is removed — not just its context files, but also any MCP servers, slash commands, skills, hooks, tools, prompts, and settings it would have contributed. |\n| Model provider ids | `anthropic`, `openai`, `google`, `groq`, `ollama`, `openrouter` | The model backend is removed from selection even when its credentials are present. See [Providers](./providers.md). |\n\nIds are exact and the two namespaces do not collide by accident: `google` disables the Google model backend, while `gemini` disables the Gemini CLI discovery files. Disabling a discovery provider is heavier than it looks — disabling `claude`, for instance, also drops Claude-discovered MCP servers, commands, skills, hooks, tools, and settings, not only `CLAUDE.md`.\n\nOnly `enabledModels` and `disabledProviders` support **path-scoped** entries, so you can vary provider availability per subtree:\n\n```yaml\ndisabledProviders:\n  - github            # disabled everywhere\n  - path: ~/work/legacy-claude\n    providers:\n      - claude         # disabled only under this directory\n```\n\nA scoped entry applies when the cwd equals the configured path or sits beneath it; `~` expands to home. Bare string entries apply everywhere.\n\nRemember that higher-precedence settings layers **replace** array settings rather than appending to them. If your global config disables `claude` but a project config sets `disabledProviders: [github]`, then inside that project Claude discovery is re-enabled and only GitHub is disabled. See [Settings](./settings.md) for the full layer precedence, merge rules, and path-scoped array details.\n\n## Troubleshooting\n\n### A file is not loaded\n\n- Native project context must live at `.omp/AGENTS.md`, and the `.omp/` directory must be non-empty; an empty `.omp/` is skipped and the walk-up continues to the next ancestor.\n- A standalone `AGENTS.md` is handled by `agents-md`, not `native`.\n- `.claude/CLAUDE.md`, `.gemini/GEMINI.md`, and `.github/copilot-instructions.md` are read only from the current working directory's config directory — not from every ancestor.\n- `~/.codex/AGENTS.md` and `~/.config/opencode/AGENTS.md` are user-level only and have no project equivalent.\n- Empty files contribute nothing for the native and standalone providers.\n- A disabled discovery provider contributes nothing — check `disabledProviders` across your global, project, and `--config` layers.\n\n### The wrong file wins\n\nAt one user scope or project depth, the higher-priority provider shadows the others (native > claude > agents/codex > gemini > opencode > github > agents-md). To force deterministic behavior, move your guidance into `.omp/AGENTS.md` (native always wins) or disable the competing discovery provider.\n\n### User context disappeared\n\nOnly one user-level context file survives, and `~/.omp/agent/AGENTS.md` has the highest priority. If it exists, it shadows user-level `~/.claude/CLAUDE.md`, `~/.codex/AGENTS.md`, `~/.gemini/GEMINI.md`, `~/.config/opencode/AGENTS.md`, and `~/.agent`/`~/.agents` files. Consolidate user guidance into the native file or remove the native one if you prefer another tool's file.\n\n### A `RULES.md` file is ignored\n\nOnly the native `RULES.md` locations are sticky: `~/.omp/agent/RULES.md` and the nearest `<ancestor>/.omp/RULES.md` from cwd to the repo root. A `RULES.md` in any other directory is not a recognized convention and will not be loaded.\n\n### An `@` import did not expand\n\nConfirm the target exists relative to the importing file (not the cwd). Imports inside fenced code blocks or inline code spans are intentionally left literal, `git@`/email-looking tokens are never imported, cycles are skipped, expansion stops after five hops, and a missing target leaves the original `@path` text unchanged.\n",
 	"custom-tools.md": "# Custom Tools\n\nCustom tools are model-callable functions that plug into the same tool execution pipeline as built-in tools.\n\nA custom tool is a TypeScript/JavaScript module that exports a factory. The factory receives a host API (`CustomToolAPI`) and returns one tool or an array of tools.\n\n## What this is (and is not)\n\n- **Custom tool**: callable by the model during a turn (`execute` + Zod parameter schema).\n- **Extension**: lifecycle/event framework that can register tools and intercept/modify events.\n- **Hook**: external pre/post command scripts.\n- **Skill**: static guidance/context package, not executable tool code.\n\nIf you need the model to call code directly, use a custom tool.\n\n## Integration paths in current code\n\nThere are two active integration styles:\n\n1. **SDK-provided custom tools** (`options.customTools`)\n   - Wrapped into agent tools via `CustomToolAdapter` or extension wrappers.\n   - Always included in the initial active tool set in SDK bootstrap.\n\n2. **Filesystem-discovered modules via loader API** (`discoverAndLoadCustomTools` / `loadCustomTools`)\n   - Exposed as library APIs in `src/extensibility/custom-tools/loader.ts`.\n   - Host code can call these to discover and load tool modules from config/provider/plugin paths.\n\n```text\nModel tool call flow\n\nLLM tool call\n   │\n   ▼\nTool registry (built-ins + custom tool adapters)\n   │\n   ▼\nCustomTool.execute(toolCallId, params, onUpdate, ctx, signal)\n   │\n   ├─ onUpdate(...)  -> streamed partial result\n   └─ return result  -> final tool content/details\n```\n\n## Discovery locations (loader API)\n\n`discoverAndLoadCustomTools(configuredPaths, cwd, builtInToolNames)` merges:\n\n1. Capability providers (`toolCapability`), including:\n   - Native OMP config (`~/.omp/agent/tools`, `.omp/tools`)\n   - Claude config (`~/.claude/tools`, `.claude/tools`)\n   - Codex config (`~/.codex/tools`, `.codex/tools`)\n   - Claude marketplace plugin cache provider\n2. Installed plugin manifests (`~/.omp/plugins/node_modules/*` via plugin loader)\n3. Explicit configured paths passed to the loader\n\n### Important behavior\n\n- Duplicate resolved paths are deduplicated.\n- Tool name conflicts are rejected against built-ins and already-loaded custom tools.\n- `.md` and `.json` files are discovered as tool metadata by some providers, but the executable module loader rejects them as runnable tools.\n- Relative configured paths are resolved from `cwd`; `~` is expanded.\n\n## Module contract\n\nA custom tool module must export a function (default export preferred):\n\n```ts\nimport type { CustomToolFactory } from \"@oh-my-pi/pi-coding-agent\";\n\nconst factory: CustomToolFactory = (pi) => ({\n  name: \"repo_stats\",\n  label: \"Repo Stats\",\n  description: \"Counts tracked TypeScript files\",\n  parameters: pi.zod.object({\n    glob: pi.zod.string().optional().default(\"**/*.ts\"),\n  }),\n\n  async execute(toolCallId, params, onUpdate, ctx, signal) {\n    onUpdate?.({\n      content: [{ type: \"text\", text: \"Scanning files...\" }],\n      details: { phase: \"scan\" },\n    });\n\n    const result = await pi.exec(\n      \"git\",\n      [\"ls-files\", params.glob ?? \"**/*.ts\"],\n      { signal, cwd: pi.cwd },\n    );\n    if (result.killed) {\n      throw new Error(\"Scan was cancelled\");\n    }\n    if (result.code !== 0) {\n      throw new Error(result.stderr || \"git ls-files failed\");\n    }\n\n    const files = result.stdout.split(\"\\n\").filter(Boolean);\n    return {\n      content: [{ type: \"text\", text: `Found ${files.length} files` }],\n      details: { count: files.length, sample: files.slice(0, 10) },\n    };\n  },\n\n  onSession(event) {\n    if (event.reason === \"shutdown\") {\n      // cleanup resources if needed\n    }\n  },\n});\n\nexport default factory;\n```\n\nSchemas are authored with Zod (`pi.zod`) and flow through the shared validation/wire pipeline.\n\nFactory return type:\n\n- `CustomTool`\n- `CustomTool[]`\n- `Promise<CustomTool | CustomTool[]>`\n\n## API surface passed to factories (`CustomToolAPI`)\n\nFrom `types.ts` and `loader.ts`:\n\n- `cwd`: host working directory\n- `exec(command, args, options?)`: process execution helper\n- `ui`: UI context (can be no-op in headless modes)\n- `hasUI`: `false` in non-interactive flows\n- `logger`: shared file logger\n- `typebox`: zod-backed compatibility shim for legacy TypeBox-style schemas\n- `zod`: injected `zod/v4` module (canonical for new schemas)\n- `pi`: injected `@oh-my-pi/pi-coding-agent` exports\n- `pushPendingAction(action)`: register a preview action for hidden `resolve` tool (`docs/resolve-tool-runtime.md`)\n  Loader starts with a no-op UI context and requires host code to call `setUIContext(...)` when real UI is ready.\n\n## Execution contract and typing\n\n`CustomTool.execute` signature:\n\n```ts\nexecute(toolCallId, params, onUpdate, ctx, signal);\n```\n\n- `params` is statically typed from your Zod/TypeBox schema via `Static<TParams>`.\n- Runtime argument validation happens before execution in the agent loop.\n- `onUpdate` emits partial results for UI streaming.\n- `ctx` includes `sessionManager`, `modelRegistry`, current `model`, `isIdle()`, `hasQueuedMessages()`, `abort()`, and optional `settings` / `autoApprove`.\n- `signal` carries cancellation.\n\n`CustomToolAdapter` bridges this to the agent tool interface and forwards calls in the correct argument order.\n\nTool definitions may also declare `strict`, `hidden`, `deferrable`, `mcpServerName`, `mcpToolName`, `approval`, and `formatApprovalDetails`.\n\n## How tools are exposed to the model\n\n- Tools are wrapped into `AgentTool` instances (`CustomToolAdapter` or extension wrappers).\n- They are inserted into the session tool registry by name.\n- In SDK bootstrap, custom and extension-registered tools are force-included in the initial active set.\n- CLI `--tools` currently validates only built-in tool names; custom tool inclusion is handled through discovery/registration paths and SDK options.\n\n## Rendering hooks\n\nOptional rendering hooks:\n\n- `renderCall(args, options, theme)`\n- `renderResult(result, options, theme, args?)`\n\nRuntime behavior in TUI:\n\n- If hooks exist, tool output is rendered inside a `Box` container.\n- `renderResult` receives `{ expanded, isPartial, spinnerFrame? }`.\n- Renderer errors are caught and logged; UI falls back to default text rendering.\n\n## Session/state handling\n\nOptional `onSession(event, ctx)` receives session lifecycle events, including:\n\n- `start`, `switch`, `branch`, `tree`, `shutdown`\n- `auto_compaction_start`, `auto_compaction_end`\n- `auto_retry_start`, `auto_retry_end`\n- `ttsr_triggered`, `todo_reminder`\n\nUse `ctx.sessionManager` to reconstruct state from history when branch/session context changes.\n\n## Failures and cancellation semantics\n\n### Synchronous/async failures\n\n- Throwing (or rejected promises) in `execute` is treated as tool failure.\n- Agent runtime converts failures into tool result messages with `isError: true` and error text content.\n- With extension wrappers, `tool_result` handlers can further rewrite content/details and even override error status.\n\n### Cancellation\n\n- Agent abort propagates through `AbortSignal` to `execute`.\n- Forward `signal` to subprocess work (`pi.exec(..., { signal })`) for cooperative cancellation.\n- `ctx.abort()` lets a tool request abort of the current agent operation.\n\n### onSession errors\n\n- `onSession` errors are caught and logged as warnings; they do not crash the session.\n\n## Real constraints to design for\n\n- Tool names must be globally unique in the active registry.\n- Prefer deterministic, schema-shaped outputs in `details` for renderer/state reconstruction.\n- Guard UI usage with `pi.hasUI`.\n- Treat `.md`/`.json` in tool directories as metadata, not executable modules.\n",
-	"environment-variables.md": "# Environment Variables (Current Runtime Reference)\n\nThis reference is derived from current code paths in:\n\n- `packages/coding-agent/src/**`\n- `packages/ai/src/**` (provider/auth resolution used by coding-agent)\n- `packages/utils/src/**` and `packages/tui/src/**` where those vars directly affect coding-agent runtime\n\nIt documents only active behavior.\n\n## Resolution model and precedence\n\nMost runtime lookups use `$env` from `@oh-my-pi/pi-utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Agent `.env` (`~/.omp/agent/.env`, respecting `PI_CONFIG_DIR` / `PI_CODING_AGENT_DIR`) for keys not already set\n4. Config-root `.env` (`~/.omp/.env`, respecting `PI_CONFIG_DIR`) for keys not already set\n5. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule inside each `.env` file: `OMP_*` keys are mirrored to `PI_*` keys in that parsed file.\n\n---\n\n## 1) Model/provider authentication\n\nThese are consumed via `getEnvApiKey()` (`packages/ai/src/stream.ts`) unless noted otherwise.\n\n### Core provider credentials\n\n| Variable                        | Used for                                         | Required when                                                  | Notes / precedence                                                                                  |\n| ------------------------------- | ------------------------------------------------ | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- |\n| `ANTHROPIC_OAUTH_TOKEN`         | Anthropic API auth                               | Using Anthropic with OAuth token auth                          | Takes precedence over `ANTHROPIC_API_KEY` for provider auth resolution                              |\n| `ANTHROPIC_API_KEY`             | Anthropic API auth                               | Using Anthropic without OAuth token                            | Fallback after `ANTHROPIC_OAUTH_TOKEN`                                                              |\n| `ANTHROPIC_FOUNDRY_API_KEY`     | Anthropic via Azure Foundry / enterprise gateway | `CLAUDE_CODE_USE_FOUNDRY` enabled                              | Takes precedence over `ANTHROPIC_OAUTH_TOKEN` and `ANTHROPIC_API_KEY` when Foundry mode is enabled  |\n| `OPENAI_API_KEY`                | OpenAI auth                                      | Using OpenAI-family providers without explicit apiKey argument | Used by OpenAI Completions/Responses providers                                                      |\n| `GEMINI_API_KEY`                | Google Gemini auth                               | Using `google` provider models                                 | Primary key for Gemini provider mapping                                                             |\n| `GOOGLE_API_KEY`                | Gemini image tool auth fallback                  | Using `gemini_image` tool without `GEMINI_API_KEY`             | Used by coding-agent image tool fallback path                                                       |\n| `GROQ_API_KEY`                  | Groq auth                                        | Using Groq models                                              |                                                                                                     |\n| `CEREBRAS_API_KEY`              | Cerebras auth                                    | Using Cerebras models                                          |                                                                                                     |\n| `FIREWORKS_API_KEY`             | Fireworks auth                                   | Using Fireworks models                                         |                                                                                                     |\n| `FIREPASS_API_KEY`              | Fire Pass auth                                   | Using Fire Pass models                                         |                                                                                                     |\n| `TOGETHER_API_KEY`              | Together auth                                    | Using `together` provider                                      |                                                                                                     |\n| `AIMLAPI_API_KEY`               | AIML API auth                                   | Using `aimlapi` provider                                       | OpenAI-compatible AIML API endpoint at `https://api.aimlapi.com/v1`                                  |\n| `HUGGINGFACE_HUB_TOKEN`         | Hugging Face auth                                | Using `huggingface` provider                                   | Primary Hugging Face token env var                                                                  |\n| `HF_TOKEN`                      | Hugging Face auth                                | Using `huggingface` provider                                   | Fallback when `HUGGINGFACE_HUB_TOKEN` is unset                                                      |\n| `SYNTHETIC_API_KEY`             | Synthetic auth                                   | Using Synthetic models                                         |                                                                                                     |\n| `NVIDIA_API_KEY`                | NVIDIA auth                                      | Using `nvidia` provider                                        |                                                                                                     |\n| `NANO_GPT_API_KEY`              | NanoGPT auth                                     | Using `nanogpt` provider                                       |                                                                                                     |\n| `VENICE_API_KEY`                | Venice auth                                      | Using `venice` provider                                        |                                                                                                     |\n| `LITELLM_API_KEY`               | LiteLLM auth                                     | Using `litellm` provider                                       | OpenAI-compatible LiteLLM proxy key                                                                 |\n| `LM_STUDIO_API_KEY`             | LM Studio auth (optional)                        | Using `lm-studio` provider with authenticated hosts            | Local LM Studio usually runs without auth; any non-empty token works when a key is required         |\n| `OLLAMA_API_KEY`                | Ollama auth (optional)                           | Using `ollama` provider with authenticated hosts               | Local Ollama usually runs without auth; any non-empty token works when a key is required            |\n| `LLAMA_CPP_API_KEY`             | llama.cpp auth (optional)                        | Using `llama.cpp` provider with authenticated hosts            | Local llama.cpp usually runs without auth; any non-empty token works when a key is configured       |\n| `XIAOMI_API_KEY`                | Xiaomi MiMo auth                                 | Using `xiaomi` provider                                        |                                                                                                     |\n| `MOONSHOT_API_KEY`              | Moonshot auth                                    | Using `moonshot` provider                                      |                                                                                                     |\n| `XAI_API_KEY`                   | xAI auth                                         | Using xAI models or as fallback for `xai-oauth`                |                                                                                                     |\n| `XAI_OAUTH_TOKEN`               | xAI OAuth/SuperGrok auth                         | Using `xai-oauth` provider                                     | Takes precedence over `XAI_API_KEY` for `xai-oauth`                                                 |\n| `OPENROUTER_API_KEY`            | OpenRouter auth                                  | Using OpenRouter models                                        | Also used by image tool when preferred/auto provider is OpenRouter                                  |\n| `MISTRAL_API_KEY`               | Mistral auth                                     | Using Mistral models                                           |                                                                                                     |\n| `ZAI_API_KEY`                   | z.ai auth                                        | Using z.ai models                                              | Also used by z.ai web search provider                                                               |\n| `ZHIPU_API_KEY`                 | Zhipu Coding Plan auth                           | Using `zhipu-coding-plan` provider                             |                                                                                                     |\n| `MINIMAX_API_KEY`               | MiniMax auth                                     | Using `minimax` provider                                       |                                                                                                     |\n| `MINIMAX_CODE_API_KEY`          | MiniMax Code auth                                | Using `minimax-code` provider                                  |                                                                                                     |\n| `MINIMAX_CODE_CN_API_KEY`       | MiniMax Code CN auth                             | Using `minimax-code-cn` provider                               |                                                                                                     |\n| `OPENCODE_API_KEY`              | OpenCode auth                                    | Using `opencode-go` / `opencode-zen` models                    |                                                                                                     |\n| `QIANFAN_API_KEY`               | Qianfan auth                                     | Using `qianfan` provider                                       |                                                                                                     |\n| `QWEN_OAUTH_TOKEN`              | Qwen Portal auth                                 | Using `qwen-portal` with OAuth token                           | Takes precedence over `QWEN_PORTAL_API_KEY`                                                         |\n| `QWEN_PORTAL_API_KEY`           | Qwen Portal auth                                 | Using `qwen-portal` with API key                               | Fallback after `QWEN_OAUTH_TOKEN`                                                                   |\n| `ZENMUX_API_KEY`                | ZenMux auth                                      | Using `zenmux` provider                                        | Used for ZenMux OpenAI and Anthropic-compatible routes                                              |\n| `VLLM_API_KEY`                  | vLLM auth/discovery opt-in                       | Using `vllm` provider (local OpenAI-compatible servers)        | Any non-empty value works for no-auth local servers                                                 |\n| `CURSOR_ACCESS_TOKEN`           | Cursor provider auth                             | Using Cursor provider                                          |                                                                                                     |\n| `AI_GATEWAY_API_KEY`            | Vercel AI Gateway auth                           | Using `vercel-ai-gateway` provider                             |                                                                                                     |\n| `CLOUDFLARE_AI_GATEWAY_API_KEY` | Cloudflare AI Gateway auth                       | Using `cloudflare-ai-gateway` provider                         | Base URL must be configured as `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic` |\n| `ALIBABA_CODING_PLAN_API_KEY`   | Alibaba Coding Plan auth                         | Using `alibaba-coding-plan` provider                           |                                                                                                     |\n| `DEEPSEEK_API_KEY`              | DeepSeek auth                                    | Using DeepSeek models                                          |                                                                                                     |\n| `KILO_API_KEY`                  | Kilo auth                                        | Using Kilo models                                              |                                                                                                     |\n| `OLLAMA_CLOUD_API_KEY`          | Ollama Cloud auth                                | Using `ollama-cloud` provider                                  |                                                                                                     |\n| `WAFER_PASS_API_KEY`            | Wafer Pass auth                                  | Using `wafer-pass` provider                                    | Flat-rate Wafer subscription; validated against `https://pass.wafer.ai/v1/models`                   |\n| `WAFER_SERVERLESS_API_KEY`      | Wafer Serverless auth                            | Using `wafer-serverless` provider                              | Pay-as-you-go Wafer SKU; validated against `https://pass.wafer.ai/v1/models`                        |\n| `GITLAB_TOKEN`                  | GitLab Duo auth                                  | Using `gitlab-duo` provider                                    |                                                                                                     |\n\n### GitHub/Copilot tokens\n\n| Variable               | Used for                                         | Notes                                      |\n| ---------------------- | ------------------------------------------------ | ------------------------------------------ |\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth                     | Generic GitHub tokens are not used here    |\n| `GH_TOKEN`             | GitHub API auth in web scraper                   | Web scraper fallback after `GITHUB_TOKEN`  |\n| `GITHUB_TOKEN`         | GitHub API auth in web scraper                   | Web scraper checks this before `GH_TOKEN`  |\n\n### Auth broker / auth gateway (remote credential vault)\n\nWhen the broker is enabled, the local SQLite credential store is bypassed and all OAuth refresh / access tokens live on the broker host. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full protocol, CLI surface, and 5-min/15-s usage cache layering.\n\n| Variable                | Used for                                                                                     | Required when                                                                                                             | Notes / precedence                                                                                                                                                                         |\n| ----------------------- | -------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| `OMP_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`); selects broker mode | Resolving credentials through a broker; also required by `omp auth-gateway serve` (the gateway is itself a broker client) | Wins over `auth.broker.url` in `config.yml`. When set with no resolvable token, `resolveAuthBrokerConfig()` hard-errors instead of falling back to local SQLite.                           |\n| `OMP_AUTH_BROKER_TOKEN` | Bearer token sent on every broker endpoint except `/v1/healthz`                              | `OMP_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`       | Resolution: this env → `auth.broker.token` (`$ENV_NAME` indirection supported) → `<config-dir>/auth-broker.token` (mode `0600`). `<config-dir>` is `~/.omp/` (respecting `PI_CONFIG_DIR`). |\n| `OMP_AUTH_BROKER_SNAPSHOT_TTL_MS` | Freshness window for the encrypted local broker snapshot cache | Optional in broker mode | Default `3600000` (1 h). Freshness is based on broker `snapshot.generatedAt`; `0` disables cache reads/writes and forces the old blocking fetch every startup. |\n| `OMP_AUTH_BROKER_SNAPSHOT_CACHE` | Path to the encrypted local broker snapshot cache | Optional in broker mode | Defaults to `~/.omp/cache/auth-broker-snapshot.enc` (or XDG cache equivalent). Useful for tests, ephemeral hosts, or relocating the `0600` cache file. |\n\nThe gateway has no dedicated env vars — it inherits `OMP_AUTH_BROKER_*`. Its own inbound bearer token lives at `<config-dir>/auth-gateway.token` and is managed via `omp auth-gateway token`.\n\n---\n\n## 2) Provider-specific runtime configuration\n\n### Anthropic Foundry Gateway (Azure / enterprise proxy)\n\nWhen `CLAUDE_CODE_USE_FOUNDRY` is enabled, Anthropic requests switch to Foundry mode:\n\n- Base URL resolves from `FOUNDRY_BASE_URL` (fallback remains model/default base URL if unset).\n- API key resolution for provider `anthropic` becomes:\n  `ANTHROPIC_FOUNDRY_API_KEY` → `ANTHROPIC_OAUTH_TOKEN` → `ANTHROPIC_API_KEY`.\n- `ANTHROPIC_CUSTOM_HEADERS` is parsed as comma/newline-separated `key: value`\n  pairs and merged into request headers. They are also forwarded when\n  `ANTHROPIC_BASE_URL` points to a non-Anthropic host (e.g. a corporate API\n  gateway), so enterprise gateways requiring proprietary auth headers work\n  without enabling Foundry mode.\n- TLS client/server material can be injected from env values:\n  `NODE_EXTRA_CA_CERTS`, `CLAUDE_CODE_CLIENT_CERT`, `CLAUDE_CODE_CLIENT_KEY`.\n  Each accepts either:\n  - a filesystem path to PEM content, or\n  - inline PEM (including escaped `\\n` sequences).\n\n| Variable                    | Value type                                     | Behavior                                                                      |\n| --------------------------- | ---------------------------------------------- | ----------------------------------------------------------------------------- |\n| `CLAUDE_CODE_USE_FOUNDRY`   | Boolean-like string (`1`, `true`, `yes`, `on`) | Enables Foundry mode for Anthropic provider                                   |\n| `FOUNDRY_BASE_URL`          | URL string                                     | Anthropic endpoint base URL in Foundry mode                                   |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Token string                                   | Used for `Authorization: Bearer <token>`                                      |\n| `ANTHROPIC_CUSTOM_HEADERS`  | Header list string                             | Extra headers; format `header-a: value, header-b: value` or newline-separated. Also forwarded outside Foundry whenever `ANTHROPIC_BASE_URL` is non-Anthropic. |\n| `NODE_EXTRA_CA_CERTS`       | PEM path or inline PEM                         | Extra CA chain for server certificate validation                              |\n| `CLAUDE_CODE_CLIENT_CERT`   | PEM path or inline PEM                         | mTLS client certificate                                                       |\n| `CLAUDE_CODE_CLIENT_KEY`    | PEM path or inline PEM                         | mTLS client private key (must be paired with cert)                            |\n\n### Amazon Bedrock\n\n| Variable                                                                        | Default / behavior                                                                            |\n| ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `AWS_REGION`                                                                    | Primary region source                                                                         |\n| `AWS_DEFAULT_REGION`                                                            | Fallback if `AWS_REGION` unset                                                                |\n| `AWS_PROFILE`                                                                   | Enables named profile auth path                                                               |\n| `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`                                   | Enables IAM key auth path                                                                     |\n| `AWS_BEARER_TOKEN_BEDROCK`                                                      | Highest-precedence bearer token auth path; skips AWS profile/credential-chain lookup when set |\n| `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI` / `AWS_CONTAINER_CREDENTIALS_FULL_URI` | Marks Bedrock as available in provider detection (credential resolution itself covers env keys, profiles/SSO/`credential_process`, then IMDSv2) |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN`                                  | Marks Bedrock as available in provider detection (same caveat as the ECS variables above)     |\n| `AWS_BEDROCK_SKIP_AUTH`                                                         | If `1`, injects dummy credentials (proxy/non-auth scenarios)                                  |\n| `HTTPS_PROXY` / `HTTP_PROXY`                                                    | Honored via Bun's native fetch proxy support (the provider no longer ships an AWS SDK / proxy-agent transport) |\n| `NO_PROXY`                                                                      | Excludes matching hosts from Bun's native proxy routing                                       |\n\nRegion fallback in provider code: `options.region` → `AWS_REGION` → `AWS_DEFAULT_REGION` → `us-east-1`.\n\n### Azure OpenAI Responses\n\n| Variable                           | Default / behavior                                                          |\n| ---------------------------------- | --------------------------------------------------------------------------- |\n| `AZURE_OPENAI_API_KEY`             | Required unless API key passed as option                                    |\n| `AZURE_OPENAI_API_VERSION`         | Default `v1`                                                                |\n| `AZURE_OPENAI_BASE_URL`            | Direct base URL override                                                    |\n| `AZURE_OPENAI_RESOURCE_NAME`       | Used to construct base URL: `https://<resource>.openai.azure.com/openai/v1` |\n| `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` | Optional mapping string: `modelId=deploymentName,model2=deployment2`        |\n\nBase URL resolution: option `azureBaseUrl` → env `AZURE_OPENAI_BASE_URL` → option/env resource name → `model.baseUrl`.\n\n### Google Vertex AI\n\n| Variable                         | Required?                      | Notes                                                                                                                     |\n| -------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |\n| `GOOGLE_CLOUD_PROJECT`           | Yes (unless passed in options) | Primary project ID source                                                                                                 |\n| `GCP_PROJECT`                    | Fallback                       | Alternate project ID source                                                                                               |\n| `GCLOUD_PROJECT`                 | Fallback                       | Alternate project ID source                                                                                               |\n| `GOOGLE_CLOUD_PROJECT_ID`        | OAuth login helper only        | Used by Gemini CLI OAuth project discovery                                                                                |\n| `GOOGLE_VERTEX_LOCATION`         | Yes (unless passed in options) | Primary Vertex location source                                                                                            |\n| `GOOGLE_CLOUD_LOCATION`          | Fallback                       | Alternate Vertex location source                                                                                          |\n| `VERTEX_LOCATION`                | Fallback                       | Alternate Vertex location source                                                                                          |\n| `GOOGLE_CLOUD_API_KEY`           | Conditional                    | Direct Vertex API-key auth; otherwise ADC fallback can authenticate when project and location are set                     |\n| `GOOGLE_APPLICATION_CREDENTIALS` | Conditional                    | If set, file must exist; otherwise ADC fallback path is checked (`~/.config/gcloud/application_default_credentials.json`) |\n\n### Kimi\n\n| Variable               | Default / behavior                                       |\n| ---------------------- | -------------------------------------------------------- |\n| `KIMI_CODE_OAUTH_HOST` | Primary OAuth host override                              |\n| `KIMI_OAUTH_HOST`      | Fallback OAuth host override                             |\n| `KIMI_CODE_BASE_URL`   | Overrides Kimi usage endpoint base URL (`usage/kimi.ts`) |\n\nOAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth.kimi.com`.\n\n### Gemini CLI compatibility\n\n| Variable                   | Default / behavior                                              |\n| -------------------------- | --------------------------------------------------------------- |\n| `PI_AI_GEMINI_CLI_VERSION` | Overrides Gemini CLI user-agent version tag (`0.35.3` if unset) |\n\n### OpenAI Codex responses (feature/debug controls)\n\n| Variable                                   | Behavior                                             |\n| ------------------------------------------ | ---------------------------------------------------- |\n| `PI_CODEX_DEBUG`                           | `1`/`true` enables Codex provider debug logging      |\n| `PI_CODEX_WEBSOCKET`                       | `1`/`true` enables websocket transport preference    |\n| `PI_OPENAI_STATEFUL`                       | Overrides the stateful-chaining default for the platform OpenAI Responses API (`previous_response_id`, forces `store: true`): on by default against api.openai.com, off elsewhere |\n| `PI_CODEX_WEBSOCKET_IDLE_TIMEOUT_MS`       | Positive integer override (default 300000)           |\n| `PI_CODEX_WEBSOCKET_RETRY_BUDGET`          | Non-negative integer override (default 5)            |\n| `PI_CODEX_WEBSOCKET_RETRY_DELAY_MS`        | Positive integer base backoff override (default 500) |\n| `PI_OPENAI_STREAM_FIRST_EVENT_TIMEOUT_MS`  | Positive integer OpenAI first-event timeout override |\n| `PI_OPENAI_STREAM_IDLE_TIMEOUT_MS`         | Positive integer OpenAI stream idle timeout override |\n\n### Cursor provider debug\n\n| Variable           | Behavior                                                                 |\n| ------------------ | ------------------------------------------------------------------------ |\n| `DEBUG_CURSOR`     | Enables provider debug logs; `2`/`verbose` for detailed payload snippets |\n| `DEBUG_CURSOR_LOG` | Optional file path for JSONL debug log output                            |\n\n### Prompt cache compatibility switch\n\n| Variable             | Behavior                                                                                                          |\n| -------------------- | ----------------------------------------------------------------------------------------------------------------- |\n| `PI_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution) |\n\n---\n\n## 3) Web search subsystem\n\n### Search provider credentials\n\n| Variable                                            | Used by                                                       |\n| --------------------------------------------------- | ------------------------------------------------------------- |\n| `EXA_API_KEY`                                       | Exa search provider and Exa MCP tools                         |\n| `BRAVE_API_KEY`                                     | Brave search provider                                         |\n| `PERPLEXITY_API_KEY`                                | Perplexity search provider API-key mode                       |\n| `PERPLEXITY_COOKIES`                                | Perplexity cookie-auth search mode                            |\n| `TAVILY_API_KEY`                                    | Tavily search provider                                        |\n| `ZAI_API_KEY`                                       | z.ai search provider (also checks stored OAuth in `agent.db`) |\n| `OPENAI_API_KEY` / Codex OAuth in DB                | Codex search provider availability/auth                       |\n| `PI_CODEX_WEB_SEARCH_MODEL`                         | Codex search provider model override                          |\n| `MOONSHOT_SEARCH_API_KEY` / `KIMI_SEARCH_API_KEY`   | Kimi/Moonshot search provider env auth                        |\n| `MOONSHOT_SEARCH_BASE_URL` / `KIMI_SEARCH_BASE_URL` | Kimi/Moonshot search endpoint override                        |\n| `KAGI_API_KEY`                                      | Kagi search provider                                          |\n| `JINA_API_KEY`                                      | Jina search provider                                          |\n| `PARALLEL_API_KEY`                                  | Parallel search provider                                      |\n| `SEARXNG_ENDPOINT`, `SEARXNG_TOKEN`                 | SearXNG endpoint and optional bearer token                    |\n| `SEARXNG_BASIC_USERNAME`, `SEARXNG_BASIC_PASSWORD`  | SearXNG HTTP Basic Auth credentials                           |\n\nSearXNG also reads the equivalent `searxng.endpoint`, `searxng.token`, `searxng.basicUsername`, and `searxng.basicPassword` settings from `~/.omp/agent/config.yml`; environment variables are fallbacks.\n\n### Anthropic web search auth chain\n\n`searchAnthropic()` resolves credentials in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY`\n2. `authStorage.getApiKey(\"anthropic\")` fallback credentials (runtime/config overrides, stored API-key credentials, stored OAuth credentials, then generic Anthropic env fallback: `ANTHROPIC_FOUNDRY_API_KEY` in Foundry mode, otherwise `ANTHROPIC_OAUTH_TOKEN` / `ANTHROPIC_API_KEY`)\n\nFor either credential path, base URL resolution is:\n\n1. `ANTHROPIC_SEARCH_BASE_URL`\n2. `FOUNDRY_BASE_URL` when `CLAUDE_CODE_USE_FOUNDRY` is enabled\n3. `ANTHROPIC_BASE_URL`\n4. `https://api.anthropic.com`\n\nRelated vars:\n\n| Variable                    | Default / behavior                                                                                                                                                                                |\n| --------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `ANTHROPIC_SEARCH_API_KEY`  | API key used exclusively for the Anthropic web search provider. Highest-priority search auth; overrides `ANTHROPIC_API_KEY` / OAuth / Foundry for search calls without affecting chat completions. |\n| `ANTHROPIC_SEARCH_BASE_URL` | Base URL used exclusively for the Anthropic web search provider. Applied to either `ANTHROPIC_SEARCH_API_KEY` or fallback Anthropic credentials; overrides `ANTHROPIC_BASE_URL` (and `FOUNDRY_BASE_URL` in Foundry mode) for search calls. |\n| `ANTHROPIC_SEARCH_MODEL`    | Search model override. Defaults to `claude-haiku-4-5`.                                                                                                                                             |\n| `ANTHROPIC_BASE_URL`        | Generic fallback base URL for Anthropic requests when no search-specific base URL is set.                                                                                                          |\n\nUse `ANTHROPIC_SEARCH_BASE_URL` (optionally with `ANTHROPIC_SEARCH_API_KEY`) to keep chat routed through an enterprise gateway (`ANTHROPIC_BASE_URL` or `CLAUDE_CODE_USE_FOUNDRY=true`) while pointing web search at a direct Anthropic endpoint, or vice versa.\n\n### Perplexity OAuth flow behavior flag\n\n| Variable            | Behavior                                                                        |\n| ------------------- | ------------------------------------------------------------------------------- |\n| `PI_AUTH_NO_BORROW` | If set, disables macOS native-app token borrowing path in Perplexity login flow |\n\n---\n\n## 4) Python tooling and kernel runtime\n\n| Variable                | Default / behavior                                                                                                  |\n| ----------------------- | ------------------------------------------------------------------------------------------------------------------- |\n| `PI_PY`                 | Boolean-like override for the Python eval backend: truthy (`1`/`true`/`yes`/`on`) enables, any other value disables; unset defers to the `eval.py` setting (default enabled)        |\n| `PI_JS`                 | Same boolean-like override for the JavaScript eval backend; unset defers to the `eval.js` setting (default enabled)                                                                 |\n| `PI_PYTHON_SKIP_CHECK`  | If `1`, skips Python interpreter availability checks (subprocess runner still starts on demand)                     |\n| `PI_PYTHON_INTEGRATION` | If `1`, opts gated integration tests in (e.g. `python-runner.integration.test.ts`) into running against real Python |\n| `PI_PYTHON_IPC_TRACE`   | If `1`, logs NDJSON frames exchanged with the Python runner subprocess                                              |\n| `VIRTUAL_ENV`           | Highest-priority venv path for Python runtime resolution                                                            |\n\nExtra conditional behavior:\n\n- If `BUN_ENV=test` or `NODE_ENV=test`, Python availability checks are treated as OK and warming is skipped.\n- Python env filtering denies common API keys and allows safe base vars + `LC_`, `XDG_`, `PI_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable                     | Default / behavior                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |\n| ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `PI_SMOL_MODEL`              | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |\n| `PI_SLOW_MODEL`              | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |\n| `PI_PLAN_MODEL`              | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |\n| `PI_NO_TITLE`                | If set (any non-empty value), disables auto session title generation on first user message                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |\n| `PI_TINY_DEVICE`             | ONNX execution provider for local tiny models; overrides the `providers.tinyModelDevice` setting (default: CPU; supports `cpu`, `gpu`, `metal`/`webgpu`, `auto`, `cuda`, `dml`, `coreml`, `wasm`, `webnn`, `webnn-gpu`, `webnn-cpu`, `webnn-npu`)                                                                                                                                                                                                                                                                                                                                                          |\n| `PI_TINY_DTYPE`              | ONNX quantization/precision for local tiny models; overrides the `providers.tinyModelDtype` setting (default: each model's shipped dtype, currently `q4`; supports `auto`, `fp32`, `fp16`, `q8`, `int8`, `uint8`, `q4`, `bnb4`, `q4f16`, `q2`, `q2f16`, `q1`, `q1f16`)                                                                                                                                                                                                                                                                                                                                     |\n| `PI_NO_INTERLEAVED_THINKING` | If `1`, disables Anthropic interleaved thinking budget behavior and uses output-token inflation for older thinking mode                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |\n| `NULL_PROMPT`                | If `true`, system prompt builder returns empty string                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |\n| `PI_BLOCKED_AGENT`           | Blocks a specific subagent type in task tool                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |\n| `PI_SUBPROCESS_CMD`          | Overrides subagent spawn command (`omp` / `omp.cmd` resolution bypass)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |\n| `PI_TASK_MAX_OUTPUT_BYTES`   | Max captured output bytes per subagent (default `500000`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |\n| `PI_TASK_MAX_OUTPUT_LINES`   | Max captured output lines per subagent (default `5000`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |\n| `PI_TIMING`                  | If set (any non-empty value), prints a hierarchical timing-span tree to **stderr** via `logger.printTimings()`. In interactive mode the tree prints once the agent is ready (before the TUI starts); in print mode it prints after the whole prompt batch completes. Print-mode prompts are wrapped in `print:prompt:initial` / `print:prompt:next` spans so each user message shows up as its own row. `PI_TIMING=x` exits the process with code 0 right after printing in interactive mode (use to measure cold startup only). `PI_TIMING=full` lists every module-load entry instead of just the top N. |\n| `PI_DEBUG_STARTUP`           | If set (any non-empty value), streams one synchronous `[startup] <phase>:start` / `:done` marker line to **stderr** as each startup phase begins/ends — including command-module imports (`cli:load:<name>`) and the native addon extraction/`dlopen` (`native:*`). Unlike `PI_TIMING` (which prints only once startup completes), the markers survive a hard hang: the last line on stderr names the phase the process is stuck in. Combine with `PI_TIMING` freely; markers and the span tree share the same phase names.                                                                                |\n| `PI_PACKAGE_DIR`             | Overrides package asset base dir resolution (`docs/`, `examples/`, `CHANGELOG.md`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |\n| `PI_DISABLE_LSPMUX`          | If `1`, disables lspmux detection/integration and forces direct LSP server spawning                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |\n| `PI_RPC_EMIT_TITLE`          | Boolean-like flag enabling title events in RPC mode                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |\n| `SMITHERY_URL`               | Smithery web URL override (default `https://smithery.ai`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |\n| `SMITHERY_API_URL`           | Smithery API base URL override (default `https://api.smithery.ai`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |\n| `SMITHERY_API_KEY`           | Smithery API key for managed MCP auth lookup                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |\n| `PUPPETEER_EXECUTABLE_PATH`  | Browser tool Chromium executable override                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |\n| `LM_STUDIO_BASE_URL`         | Default implicit LM Studio discovery base URL override (`http://127.0.0.1:1234/v1` if unset)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |\n| `OLLAMA_BASE_URL`            | Default implicit Ollama discovery base URL override (`OLLAMA_HOST` if unset, then `http://127.0.0.1:11434`)                                                                                                                                                                                                                                                                                                                                                                                                                                     |\n| `OLLAMA_HOST`                | Ollama host used for implicit Ollama discovery when `OLLAMA_BASE_URL` is unset; accepts Ollama-style values such as `127.0.0.1:11434` or `http://host:11434`                                                                                                                                                                                                                                                                                                                                                                                     |\n| `OLLAMA_CONTEXT_LENGTH`      | Positive integer context-window override for implicit Ollama discovery; affects OMP context budgeting only and does not change Ollama's runtime `num_ctx`                                                                                                                                                                                                                                                                                                                                                                                           |\n| `LLAMA_CPP_BASE_URL`         | Default implicit Llama.cpp discovery base URL override (`http://127.0.0.1:8080` if unset)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |\n| `PI_EDIT_VARIANT`            | Forces edit tool variant when valid (`patch`, `replace`, `hashline`, `apply_patch`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |\n| `PI_FORCE_IMAGE_PROTOCOL`    | Forces supported image protocol (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) where used                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |\n| `PI_ALLOW_SIXEL_PASSTHROUGH` | Allows SIXEL passthrough when `PI_FORCE_IMAGE_PROTOCOL=sixel`                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |\n| `PI_NO_PTY`                  | If `1`, disables interactive PTY path for bash tool                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |\n| `OMP_MCP_TIMEOUT_MS`         | Overrides MCP client request timeout (ms) for every MCP server. `0` disables client-side timeouts (`AbortSignal` never fires). Invalid (negative or non-numeric) values are ignored with a warning and the per-server config or default (`30000`) is used.                                                                                                                                                                                                                                                                                                                                                 |\n\n`PI_NO_PTY` is also set internally when CLI `--no-pty` is used.\n\n---\n\n## 6) Storage and config root paths\n\nThese are consumed via `@oh-my-pi/pi-utils/dirs` and affect where coding-agent stores data.\n\n| Variable              | Default / behavior                                                            |\n| --------------------- | ----------------------------------------------------------------------------- |\n| `PI_CONFIG_DIR`       | Config root dirname under home (default `.omp`)                               |\n| `PI_CODING_AGENT_DIR` | Full override for agent directory (default `~/<PI_CONFIG_DIR or .omp>/agent`) |\n| `PWD`                 | Used when matching canonical current working directory in path helpers        |\n\n---\n\n## 7) Shell/tool execution environment\n\n(From `packages/utils/src/procmgr.ts` and coding-agent bash tool integration.)\n\n| Variable                   | Behavior                                                                       |\n| -------------------------- | ------------------------------------------------------------------------------ |\n| `PI_BASH_NO_CI`            | Suppresses automatic `CI=true` injection into spawned shell env                |\n| `CLAUDE_BASH_NO_CI`        | Legacy alias fallback for `PI_BASH_NO_CI`                                      |\n| `PI_BASH_NO_LOGIN`         | Disables login-shell mode; shell args become `['-c']` instead of `['-l','-c']` |\n| `CLAUDE_BASH_NO_LOGIN`     | Legacy alias fallback for `PI_BASH_NO_LOGIN`                                   |\n| `PI_SHELL_PREFIX`          | Optional command prefix wrapper                                                |\n| `CLAUDE_CODE_SHELL_PREFIX` | Legacy alias fallback for `PI_SHELL_PREFIX`                                    |\n| `VISUAL`                   | Preferred external editor command                                              |\n| `EDITOR`                   | Fallback external editor command                                               |\n\nCurrent implementation: `PI_BASH_NO_LOGIN`/`CLAUDE_BASH_NO_LOGIN` are active; when either is set, `getShellArgs()` returns `['-c']`.\n\n---\n\n## 8) UI/theme/session detection (auto-detected env)\n\nThese are read as runtime signals; they are usually set by the terminal/OS rather than manually configured.\n\n| Variable                                                                                                           | Used for                                                  |\n| ------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------- |\n| `COLORTERM`, `TERM`, `WT_SESSION`                                                                                  | Color capability detection (theme color mode)             |\n| `COLORFGBG`                                                                                                        | Terminal background light/dark auto-detection             |\n| `TERM_PROGRAM`, `TERM_PROGRAM_VERSION`, `TERMINAL_EMULATOR`                                                        | Terminal identity in system prompt/context                |\n| `TMUX_PANE`, `CMUX_SURFACE_ID`, `KITTY_WINDOW_ID`, `TERM_SESSION_ID`, `WT_SESSION`                                 | Stable per-terminal session breadcrumb IDs                |\n| `SHELL`, `ComSpec`, `TERM_PROGRAM`, `TERM`                                                                         | System info diagnostics                                   |\n| `APPDATA`, `XDG_CONFIG_HOME`                                                                                       | lspmux config path resolution                             |\n| `HOME`                                                                                                             | Path shortening in MCP command UI                         |\n\n---\n\n## 9) TUI runtime flags (shared package, affects coding-agent UX)\n\n| Variable                  | Behavior                                                                              |\n| ------------------------- | ------------------------------------------------------------------------------------- |\n| `PI_NOTIFICATIONS`        | `off` / `0` / `false` suppress desktop notifications                                  |\n| `PI_TUI_WRITE_LOG`        | If set, logs TUI writes to file                                                       |\n| `PI_HARDWARE_CURSOR`      | If `1`, enables hardware cursor mode                                                  |\n| `PI_NO_SYNC_OUTPUT`       | If set (any non-empty value), disables DEC 2026 synchronized-output wrappers while keeping TUI autowrap guards |\n| `PI_NO_DECCARA`           | If set (truthy), disables Kitty DECCARA rectangular-SGR background fills (forces padded-string rendering) |\n| `PI_DEBUG_REDRAW`         | If `1`, enables redraw debug logging                                                  |\n| `PI_FORCE_IMAGE_PROTOCOL` | Forces terminal image protocol detection (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) |\n\n---\n\n## 10) Commit generation controls\n\n| Variable                  | Behavior                                                            |\n| ------------------------- | ------------------------------------------------------------------- |\n| `PI_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `PI_COMMIT_NO_FALLBACK`   | If `true`, disables fallback when agent returns no proposal         |\n| `PI_COMMIT_MAP_REDUCE`    | If `false`, disables map-reduce commit analysis path                |\n| `DEBUG`                   | If set, commit agent error stack traces are printed                 |\n\n---\n\n## Security-sensitive variables\n\nTreat these as secrets; do not log or commit them:\n\n- Provider/API keys and OAuth/bearer credentials (all `*_API_KEY`, `*_TOKEN`, OAuth access/refresh tokens)\n- Cloud credentials (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS` path may expose service-account material)\n- Search/provider auth vars (`EXA_API_KEY`, `BRAVE_API_KEY`, `PERPLEXITY_API_KEY`, Anthropic search keys)\n- Foundry mTLS material (`CLAUDE_CODE_CLIENT_CERT`, `CLAUDE_CODE_CLIENT_KEY`, `NODE_EXTRA_CA_CERTS` when it points to private CA bundles)\n\nPython runtime also explicitly strips many common key vars before spawning kernel subprocesses (`packages/coding-agent/src/eval/py/runtime.ts`).\n",
+	"environment-variables.md": "# Environment Variables (Current Runtime Reference)\n\nThis reference is derived from current code paths in:\n\n- `packages/coding-agent/src/**`\n- `packages/ai/src/**` (provider/auth resolution used by coding-agent)\n- `packages/utils/src/**` and `packages/tui/src/**` where those vars directly affect coding-agent runtime\n\nIt documents only active behavior.\n\n## Resolution model and precedence\n\nMost runtime lookups use `$env` from `@oh-my-pi/pi-utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Agent `.env` (`~/.omp/agent/.env`, respecting `PI_CONFIG_DIR` / `PI_CODING_AGENT_DIR`) for keys not already set\n4. Config-root `.env` (`~/.omp/.env`, respecting `PI_CONFIG_DIR`) for keys not already set\n5. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule inside each `.env` file: `OMP_*` keys are mirrored to `PI_*` keys in that parsed file.\n\n---\n\n## 1) Model/provider authentication\n\nThese are consumed via `getEnvApiKey()` (`packages/ai/src/stream.ts`) unless noted otherwise.\n\n### Core provider credentials\n\n| Variable                        | Used for                                         | Required when                                                  | Notes / precedence                                                                                  |\n| ------------------------------- | ------------------------------------------------ | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- |\n| `ANTHROPIC_OAUTH_TOKEN`         | Anthropic API auth                               | Using Anthropic with OAuth token auth                          | Takes precedence over `ANTHROPIC_API_KEY` for provider auth resolution                              |\n| `ANTHROPIC_API_KEY`             | Anthropic API auth                               | Using Anthropic without OAuth token                            | Fallback after `ANTHROPIC_OAUTH_TOKEN`                                                              |\n| `ANTHROPIC_FOUNDRY_API_KEY`     | Anthropic via Azure Foundry / enterprise gateway | `CLAUDE_CODE_USE_FOUNDRY` enabled                              | Takes precedence over `ANTHROPIC_OAUTH_TOKEN` and `ANTHROPIC_API_KEY` when Foundry mode is enabled  |\n| `OPENAI_API_KEY`                | OpenAI auth                                      | Using OpenAI-family providers without explicit apiKey argument | Used by OpenAI Completions/Responses providers                                                      |\n| `GEMINI_API_KEY`                | Google Gemini auth                               | Using `google` provider models                                 | Primary key for Gemini provider mapping                                                             |\n| `GOOGLE_API_KEY`                | Gemini image tool auth fallback                  | Using `gemini_image` tool without `GEMINI_API_KEY`             | Used by coding-agent image tool fallback path                                                       |\n| `GROQ_API_KEY`                  | Groq auth                                        | Using Groq models                                              |                                                                                                     |\n| `CEREBRAS_API_KEY`              | Cerebras auth                                    | Using Cerebras models                                          |                                                                                                     |\n| `FIREWORKS_API_KEY`             | Fireworks auth                                   | Using Fireworks models                                         |                                                                                                     |\n| `FIREPASS_API_KEY`              | Fire Pass auth                                   | Using Fire Pass models                                         |                                                                                                     |\n| `TOGETHER_API_KEY`              | Together auth                                    | Using `together` provider                                      |                                                                                                     |\n| `AIMLAPI_API_KEY`               | AIML API auth                                   | Using `aimlapi` provider                                       | OpenAI-compatible AIML API endpoint at `https://api.aimlapi.com/v1`                                  |\n| `HUGGINGFACE_HUB_TOKEN`         | Hugging Face auth                                | Using `huggingface` provider                                   | Primary Hugging Face token env var                                                                  |\n| `HF_TOKEN`                      | Hugging Face auth                                | Using `huggingface` provider                                   | Fallback when `HUGGINGFACE_HUB_TOKEN` is unset                                                      |\n| `SYNTHETIC_API_KEY`             | Synthetic auth                                   | Using Synthetic models                                         |                                                                                                     |\n| `NVIDIA_API_KEY`                | NVIDIA auth                                      | Using `nvidia` provider                                        |                                                                                                     |\n| `NANO_GPT_API_KEY`              | NanoGPT auth                                     | Using `nanogpt` provider                                       |                                                                                                     |\n| `VENICE_API_KEY`                | Venice auth                                      | Using `venice` provider                                        |                                                                                                     |\n| `LITELLM_API_KEY`               | LiteLLM auth                                     | Using `litellm` provider                                       | OpenAI-compatible LiteLLM proxy key                                                                 |\n| `LM_STUDIO_API_KEY`             | LM Studio auth (optional)                        | Using `lm-studio` provider with authenticated hosts            | Local LM Studio usually runs without auth; any non-empty token works when a key is required         |\n| `OLLAMA_API_KEY`                | Ollama auth (optional)                           | Using `ollama` provider with authenticated hosts               | Local Ollama usually runs without auth; any non-empty token works when a key is required            |\n| `LLAMA_CPP_API_KEY`             | llama.cpp auth (optional)                        | Using `llama.cpp` provider with authenticated hosts            | Local llama.cpp usually runs without auth; any non-empty token works when a key is configured       |\n| `XIAOMI_API_KEY`                | Xiaomi MiMo auth                                 | Using `xiaomi` provider                                        |                                                                                                     |\n| `MOONSHOT_API_KEY`              | Moonshot auth                                    | Using `moonshot` provider                                      |                                                                                                     |\n| `XAI_API_KEY`                   | xAI auth                                         | Using xAI models or as fallback for `xai-oauth`                |                                                                                                     |\n| `XAI_OAUTH_TOKEN`               | xAI OAuth/SuperGrok auth                         | Using `xai-oauth` provider                                     | Takes precedence over `XAI_API_KEY` for `xai-oauth`                                                 |\n| `OPENROUTER_API_KEY`            | OpenRouter auth                                  | Using OpenRouter models                                        | Also used by image tool when preferred/auto provider is OpenRouter                                  |\n| `MISTRAL_API_KEY`               | Mistral auth                                     | Using Mistral models                                           |                                                                                                     |\n| `ZAI_API_KEY`                   | z.ai auth                                        | Using z.ai models                                              | Also used by z.ai web search provider                                                               |\n| `ZHIPU_API_KEY`                 | Zhipu Coding Plan auth                           | Using `zhipu-coding-plan` provider                             |                                                                                                     |\n| `UMANS_AI_CODING_PLAN_API_KEY` | Umans AI Coding Plan auth                        | Using `umans` provider                                         |                                                                                                     |\n| `MINIMAX_API_KEY`               | MiniMax auth                                     | Using `minimax` provider                                       |                                                                                                     |\n| `MINIMAX_CODE_API_KEY`          | MiniMax Code auth                                | Using `minimax-code` provider                                  |                                                                                                     |\n| `MINIMAX_CODE_CN_API_KEY`       | MiniMax Code CN auth                             | Using `minimax-code-cn` provider                               |                                                                                                     |\n| `OPENCODE_API_KEY`              | OpenCode auth                                    | Using `opencode-go` / `opencode-zen` models                    |                                                                                                     |\n| `QIANFAN_API_KEY`               | Qianfan auth                                     | Using `qianfan` provider                                       |                                                                                                     |\n| `QWEN_OAUTH_TOKEN`              | Qwen Portal auth                                 | Using `qwen-portal` with OAuth token                           | Takes precedence over `QWEN_PORTAL_API_KEY`                                                         |\n| `QWEN_PORTAL_API_KEY`           | Qwen Portal auth                                 | Using `qwen-portal` with API key                               | Fallback after `QWEN_OAUTH_TOKEN`                                                                   |\n| `ZENMUX_API_KEY`                | ZenMux auth                                      | Using `zenmux` provider                                        | Used for ZenMux OpenAI and Anthropic-compatible routes                                              |\n| `VLLM_API_KEY`                  | vLLM auth/discovery opt-in                       | Using `vllm` provider (local OpenAI-compatible servers)        | Any non-empty value works for no-auth local servers                                                 |\n| `CURSOR_ACCESS_TOKEN`           | Cursor provider auth                             | Using Cursor provider                                          |                                                                                                     |\n| `AI_GATEWAY_API_KEY`            | Vercel AI Gateway auth                           | Using `vercel-ai-gateway` provider                             |                                                                                                     |\n| `CLOUDFLARE_AI_GATEWAY_API_KEY` | Cloudflare AI Gateway auth                       | Using `cloudflare-ai-gateway` provider                         | Base URL must be configured as `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic` |\n| `ALIBABA_CODING_PLAN_API_KEY`   | Alibaba Coding Plan auth                         | Using `alibaba-coding-plan` provider                           |                                                                                                     |\n| `DEEPSEEK_API_KEY`              | DeepSeek auth                                    | Using DeepSeek models                                          |                                                                                                     |\n| `KILO_API_KEY`                  | Kilo auth                                        | Using Kilo models                                              |                                                                                                     |\n| `OLLAMA_CLOUD_API_KEY`          | Ollama Cloud auth                                | Using `ollama-cloud` provider                                  |                                                                                                     |\n| `WAFER_PASS_API_KEY`            | Wafer Pass auth                                  | Using `wafer-pass` provider                                    | Flat-rate Wafer subscription; validated against `https://pass.wafer.ai/v1/models`                   |\n| `WAFER_SERVERLESS_API_KEY`      | Wafer Serverless auth                            | Using `wafer-serverless` provider                              | Pay-as-you-go Wafer SKU; validated against `https://pass.wafer.ai/v1/models`                        |\n| `GITLAB_TOKEN`                  | GitLab Duo auth                                  | Using `gitlab-duo` provider                                    |                                                                                                     |\n\n### GitHub/Copilot tokens\n\n| Variable               | Used for                                         | Notes                                      |\n| ---------------------- | ------------------------------------------------ | ------------------------------------------ |\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth                     | Generic GitHub tokens are not used here    |\n| `GH_TOKEN`             | GitHub API auth in web scraper                   | Web scraper fallback after `GITHUB_TOKEN`  |\n| `GITHUB_TOKEN`         | GitHub API auth in web scraper                   | Web scraper checks this before `GH_TOKEN`  |\n\n### Auth broker / auth gateway (remote credential vault)\n\nWhen the broker is enabled, the local SQLite credential store is bypassed and all OAuth refresh / access tokens live on the broker host. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full protocol, CLI surface, and 5-min/15-s usage cache layering.\n\n| Variable                | Used for                                                                                     | Required when                                                                                                             | Notes / precedence                                                                                                                                                                         |\n| ----------------------- | -------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| `OMP_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`); selects broker mode | Resolving credentials through a broker; also required by `omp auth-gateway serve` (the gateway is itself a broker client) | Wins over `auth.broker.url` in `config.yml`. When set with no resolvable token, `resolveAuthBrokerConfig()` hard-errors instead of falling back to local SQLite.                           |\n| `OMP_AUTH_BROKER_TOKEN` | Bearer token sent on every broker endpoint except `/v1/healthz`                              | `OMP_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`       | Resolution: this env → `auth.broker.token` (`$ENV_NAME` indirection supported) → `<config-dir>/auth-broker.token` (mode `0600`). `<config-dir>` is `~/.omp/` (respecting `PI_CONFIG_DIR`). |\n| `OMP_AUTH_BROKER_SNAPSHOT_TTL_MS` | Freshness window for the encrypted local broker snapshot cache | Optional in broker mode | Default `3600000` (1 h). Freshness is based on broker `snapshot.generatedAt`; `0` disables cache reads/writes and forces the old blocking fetch every startup. |\n| `OMP_AUTH_BROKER_SNAPSHOT_CACHE` | Path to the encrypted local broker snapshot cache | Optional in broker mode | Defaults to `~/.omp/cache/auth-broker-snapshot.enc` (or XDG cache equivalent). Useful for tests, ephemeral hosts, or relocating the `0600` cache file. |\n\nThe gateway has no dedicated env vars — it inherits `OMP_AUTH_BROKER_*`. Its own inbound bearer token lives at `<config-dir>/auth-gateway.token` and is managed via `omp auth-gateway token`.\n\n---\n\n## 2) Provider-specific runtime configuration\n\n### Anthropic Foundry Gateway (Azure / enterprise proxy)\n\nWhen `CLAUDE_CODE_USE_FOUNDRY` is enabled, Anthropic requests switch to Foundry mode:\n\n- Base URL resolves from `FOUNDRY_BASE_URL` (fallback remains model/default base URL if unset).\n- API key resolution for provider `anthropic` becomes:\n  `ANTHROPIC_FOUNDRY_API_KEY` → `ANTHROPIC_OAUTH_TOKEN` → `ANTHROPIC_API_KEY`.\n- `ANTHROPIC_CUSTOM_HEADERS` is parsed as comma/newline-separated `key: value`\n  pairs and merged into request headers. They are also forwarded when\n  `ANTHROPIC_BASE_URL` points to a non-Anthropic host (e.g. a corporate API\n  gateway), so enterprise gateways requiring proprietary auth headers work\n  without enabling Foundry mode.\n- TLS client/server material can be injected from env values:\n  `NODE_EXTRA_CA_CERTS`, `CLAUDE_CODE_CLIENT_CERT`, `CLAUDE_CODE_CLIENT_KEY`.\n  Each accepts either:\n  - a filesystem path to PEM content, or\n  - inline PEM (including escaped `\\n` sequences).\n\n| Variable                    | Value type                                     | Behavior                                                                      |\n| --------------------------- | ---------------------------------------------- | ----------------------------------------------------------------------------- |\n| `CLAUDE_CODE_USE_FOUNDRY`   | Boolean-like string (`1`, `true`, `yes`, `on`) | Enables Foundry mode for Anthropic provider                                   |\n| `FOUNDRY_BASE_URL`          | URL string                                     | Anthropic endpoint base URL in Foundry mode                                   |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Token string                                   | Used for `Authorization: Bearer <token>`                                      |\n| `ANTHROPIC_CUSTOM_HEADERS`  | Header list string                             | Extra headers; format `header-a: value, header-b: value` or newline-separated. Also forwarded outside Foundry whenever `ANTHROPIC_BASE_URL` is non-Anthropic. |\n| `NODE_EXTRA_CA_CERTS`       | PEM path or inline PEM                         | Extra CA chain for server certificate validation                              |\n| `CLAUDE_CODE_CLIENT_CERT`   | PEM path or inline PEM                         | mTLS client certificate                                                       |\n| `CLAUDE_CODE_CLIENT_KEY`    | PEM path or inline PEM                         | mTLS client private key (must be paired with cert)                            |\n\n### Amazon Bedrock\n\n| Variable                                                                        | Default / behavior                                                                            |\n| ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `AWS_REGION`                                                                    | Primary region source                                                                         |\n| `AWS_DEFAULT_REGION`                                                            | Fallback if `AWS_REGION` unset                                                                |\n| `AWS_PROFILE`                                                                   | Enables named profile auth path                                                               |\n| `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`                                   | Enables IAM key auth path                                                                     |\n| `AWS_BEARER_TOKEN_BEDROCK`                                                      | Highest-precedence bearer token auth path; skips AWS profile/credential-chain lookup when set |\n| `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI` / `AWS_CONTAINER_CREDENTIALS_FULL_URI` | Marks Bedrock as available in provider detection (credential resolution itself covers env keys, profiles/SSO/`credential_process`, then IMDSv2) |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN`                                  | Marks Bedrock as available in provider detection (same caveat as the ECS variables above)     |\n| `AWS_BEDROCK_SKIP_AUTH`                                                         | If `1`, injects dummy credentials (proxy/non-auth scenarios)                                  |\n| `HTTPS_PROXY` / `HTTP_PROXY`                                                    | Honored via Bun's native fetch proxy support (the provider no longer ships an AWS SDK / proxy-agent transport) |\n| `NO_PROXY`                                                                      | Excludes matching hosts from Bun's native proxy routing                                       |\n\nRegion fallback in provider code: `options.region` → `AWS_REGION` → `AWS_DEFAULT_REGION` → `us-east-1`.\n\n### Azure OpenAI Responses\n\n| Variable                           | Default / behavior                                                          |\n| ---------------------------------- | --------------------------------------------------------------------------- |\n| `AZURE_OPENAI_API_KEY`             | Required unless API key passed as option                                    |\n| `AZURE_OPENAI_API_VERSION`         | Default `v1`                                                                |\n| `AZURE_OPENAI_BASE_URL`            | Direct base URL override                                                    |\n| `AZURE_OPENAI_RESOURCE_NAME`       | Used to construct base URL: `https://<resource>.openai.azure.com/openai/v1` |\n| `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` | Optional mapping string: `modelId=deploymentName,model2=deployment2`        |\n\nBase URL resolution: option `azureBaseUrl` → env `AZURE_OPENAI_BASE_URL` → option/env resource name → `model.baseUrl`.\n\n### Google Vertex AI\n\n| Variable                         | Required?                      | Notes                                                                                                                     |\n| -------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |\n| `GOOGLE_CLOUD_PROJECT`           | Yes (unless passed in options) | Primary project ID source                                                                                                 |\n| `GCP_PROJECT`                    | Fallback                       | Alternate project ID source                                                                                               |\n| `GCLOUD_PROJECT`                 | Fallback                       | Alternate project ID source                                                                                               |\n| `GOOGLE_CLOUD_PROJECT_ID`        | OAuth login helper only        | Used by Gemini CLI OAuth project discovery                                                                                |\n| `GOOGLE_VERTEX_LOCATION`         | Yes (unless passed in options) | Primary Vertex location source                                                                                            |\n| `GOOGLE_CLOUD_LOCATION`          | Fallback                       | Alternate Vertex location source                                                                                          |\n| `VERTEX_LOCATION`                | Fallback                       | Alternate Vertex location source                                                                                          |\n| `GOOGLE_CLOUD_API_KEY`           | Conditional                    | Direct Vertex API-key auth; otherwise ADC fallback can authenticate when project and location are set                     |\n| `GOOGLE_APPLICATION_CREDENTIALS` | Conditional                    | If set, file must exist; otherwise ADC fallback path is checked (`~/.config/gcloud/application_default_credentials.json`) |\n\n### Kimi\n\n| Variable               | Default / behavior                                       |\n| ---------------------- | -------------------------------------------------------- |\n| `KIMI_CODE_OAUTH_HOST` | Primary OAuth host override                              |\n| `KIMI_OAUTH_HOST`      | Fallback OAuth host override                             |\n| `KIMI_CODE_BASE_URL`   | Overrides Kimi usage endpoint base URL (`usage/kimi.ts`) |\n\nOAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth.kimi.com`.\n\n### Gemini CLI compatibility\n\n| Variable                   | Default / behavior                                              |\n| -------------------------- | --------------------------------------------------------------- |\n| `PI_AI_GEMINI_CLI_VERSION` | Overrides Gemini CLI user-agent version tag (`0.35.3` if unset) |\n\n### OpenAI Codex responses (feature/debug controls)\n\n| Variable                                   | Behavior                                             |\n| ------------------------------------------ | ---------------------------------------------------- |\n| `PI_CODEX_DEBUG`                           | `1`/`true` enables Codex provider debug logging      |\n| `PI_CODEX_WEBSOCKET`                       | `1`/`true` enables websocket transport preference    |\n| `PI_OPENAI_STATEFUL`                       | Overrides the stateful-chaining default for the platform OpenAI Responses API (`previous_response_id`, forces `store: true`): on by default against api.openai.com, off elsewhere |\n| `PI_CODEX_WEBSOCKET_IDLE_TIMEOUT_MS`       | Positive integer override (default 300000)           |\n| `PI_CODEX_WEBSOCKET_RETRY_BUDGET`          | Non-negative integer override (default 5)            |\n| `PI_CODEX_WEBSOCKET_RETRY_DELAY_MS`        | Positive integer base backoff override (default 500) |\n| `PI_OPENAI_STREAM_FIRST_EVENT_TIMEOUT_MS`  | Positive integer OpenAI first-event timeout override |\n| `PI_OPENAI_STREAM_IDLE_TIMEOUT_MS`         | Positive integer OpenAI stream idle timeout override |\n\n### Cursor provider debug\n\n| Variable           | Behavior                                                                 |\n| ------------------ | ------------------------------------------------------------------------ |\n| `DEBUG_CURSOR`     | Enables provider debug logs; `2`/`verbose` for detailed payload snippets |\n| `DEBUG_CURSOR_LOG` | Optional file path for JSONL debug log output                            |\n\n### Prompt cache compatibility switch\n\n| Variable             | Behavior                                                                                                          |\n| -------------------- | ----------------------------------------------------------------------------------------------------------------- |\n| `PI_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution) |\n\n---\n\n## 3) Web search subsystem\n\n### Search provider credentials\n\n| Variable                                            | Used by                                                       |\n| --------------------------------------------------- | ------------------------------------------------------------- |\n| `EXA_API_KEY`                                       | Exa search provider and Exa MCP tools                         |\n| `BRAVE_API_KEY`                                     | Brave search provider                                         |\n| `PERPLEXITY_API_KEY`                                | Perplexity search provider API-key mode                       |\n| `PERPLEXITY_COOKIES`                                | Perplexity cookie-auth search mode                            |\n| `TAVILY_API_KEY`                                    | Tavily search provider                                        |\n| `ZAI_API_KEY`                                       | z.ai search provider (also checks stored OAuth in `agent.db`) |\n| `OPENAI_API_KEY` / Codex OAuth in DB                | Codex search provider availability/auth                       |\n| `PI_CODEX_WEB_SEARCH_MODEL`                         | Codex search provider model override                          |\n| `MOONSHOT_SEARCH_API_KEY` / `KIMI_SEARCH_API_KEY`   | Kimi/Moonshot search provider env auth                        |\n| `MOONSHOT_SEARCH_BASE_URL` / `KIMI_SEARCH_BASE_URL` | Kimi/Moonshot search endpoint override                        |\n| `KAGI_API_KEY`                                      | Kagi search provider                                          |\n| `JINA_API_KEY`                                      | Jina search provider                                          |\n| `PARALLEL_API_KEY`                                  | Parallel search provider                                      |\n| `SEARXNG_ENDPOINT`, `SEARXNG_TOKEN`                 | SearXNG endpoint and optional bearer token                    |\n| `SEARXNG_BASIC_USERNAME`, `SEARXNG_BASIC_PASSWORD`  | SearXNG HTTP Basic Auth credentials                           |\n\nSearXNG also reads the equivalent `searxng.endpoint`, `searxng.token`, `searxng.basicUsername`, and `searxng.basicPassword` settings from `~/.omp/agent/config.yml`; environment variables are fallbacks.\n\n### Anthropic web search auth chain\n\n`searchAnthropic()` resolves credentials in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY`\n2. `authStorage.getApiKey(\"anthropic\")` fallback credentials (runtime/config overrides, stored API-key credentials, stored OAuth credentials, then generic Anthropic env fallback: `ANTHROPIC_FOUNDRY_API_KEY` in Foundry mode, otherwise `ANTHROPIC_OAUTH_TOKEN` / `ANTHROPIC_API_KEY`)\n\nFor either credential path, base URL resolution is:\n\n1. `ANTHROPIC_SEARCH_BASE_URL`\n2. `FOUNDRY_BASE_URL` when `CLAUDE_CODE_USE_FOUNDRY` is enabled\n3. `ANTHROPIC_BASE_URL`\n4. `https://api.anthropic.com`\n\nRelated vars:\n\n| Variable                    | Default / behavior                                                                                                                                                                                |\n| --------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `ANTHROPIC_SEARCH_API_KEY`  | API key used exclusively for the Anthropic web search provider. Highest-priority search auth; overrides `ANTHROPIC_API_KEY` / OAuth / Foundry for search calls without affecting chat completions. |\n| `ANTHROPIC_SEARCH_BASE_URL` | Base URL used exclusively for the Anthropic web search provider. Applied to either `ANTHROPIC_SEARCH_API_KEY` or fallback Anthropic credentials; overrides `ANTHROPIC_BASE_URL` (and `FOUNDRY_BASE_URL` in Foundry mode) for search calls. |\n| `ANTHROPIC_SEARCH_MODEL`    | Search model override. Defaults to `claude-haiku-4-5`.                                                                                                                                             |\n| `ANTHROPIC_BASE_URL`        | Generic fallback base URL for Anthropic requests when no search-specific base URL is set.                                                                                                          |\n\nUse `ANTHROPIC_SEARCH_BASE_URL` (optionally with `ANTHROPIC_SEARCH_API_KEY`) to keep chat routed through an enterprise gateway (`ANTHROPIC_BASE_URL` or `CLAUDE_CODE_USE_FOUNDRY=true`) while pointing web search at a direct Anthropic endpoint, or vice versa.\n\n### Perplexity OAuth flow behavior flag\n\n| Variable            | Behavior                                                                        |\n| ------------------- | ------------------------------------------------------------------------------- |\n| `PI_AUTH_NO_BORROW` | If set, disables macOS native-app token borrowing path in Perplexity login flow |\n\n---\n\n## 4) Python tooling and kernel runtime\n\n| Variable                | Default / behavior                                                                                                  |\n| ----------------------- | ------------------------------------------------------------------------------------------------------------------- |\n| `PI_PY`                 | Boolean-like override for the Python eval backend: truthy (`1`/`true`/`yes`/`on`) enables, any other value disables; unset defers to the `eval.py` setting (default enabled)        |\n| `PI_JS`                 | Same boolean-like override for the JavaScript eval backend; unset defers to the `eval.js` setting (default enabled)                                                                 |\n| `PI_PYTHON_SKIP_CHECK`  | If `1`, skips Python interpreter availability checks (subprocess runner still starts on demand)                     |\n| `PI_PYTHON_INTEGRATION` | If `1`, opts gated integration tests in (e.g. `python-runner.integration.test.ts`) into running against real Python |\n| `PI_PYTHON_IPC_TRACE`   | If `1`, logs NDJSON frames exchanged with the Python runner subprocess                                              |\n| `VIRTUAL_ENV`           | Highest-priority venv path for Python runtime resolution                                                            |\n\nExtra conditional behavior:\n\n- If `BUN_ENV=test` or `NODE_ENV=test`, Python availability checks are treated as OK and warming is skipped.\n- Python env filtering denies common API keys and allows safe base vars + `LC_`, `XDG_`, `PI_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable                     | Default / behavior                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |\n| ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `PI_SMOL_MODEL`              | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |\n| `PI_SLOW_MODEL`              | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |\n| `PI_PLAN_MODEL`              | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   |\n| `PI_NO_TITLE`                | If set (any non-empty value), disables auto session title generation on first user message                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |\n| `PI_TINY_DEVICE`             | ONNX execution provider for local tiny models; overrides the `providers.tinyModelDevice` setting (default: CPU; supports `cpu`, `gpu`, `metal`/`webgpu`, `auto`, `cuda`, `dml`, `coreml`, `wasm`, `webnn`, `webnn-gpu`, `webnn-cpu`, `webnn-npu`)                                                                                                                                                                                                                                                                                                                                                          |\n| `PI_TINY_DTYPE`              | ONNX quantization/precision for local tiny models; overrides the `providers.tinyModelDtype` setting (default: each model's shipped dtype, currently `q4`; supports `auto`, `fp32`, `fp16`, `q8`, `int8`, `uint8`, `q4`, `bnb4`, `q4f16`, `q2`, `q2f16`, `q1`, `q1f16`)                                                                                                                                                                                                                                                                                                                                     |\n| `PI_NO_INTERLEAVED_THINKING` | If `1`, disables Anthropic interleaved thinking budget behavior and uses output-token inflation for older thinking mode                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |\n| `NULL_PROMPT`                | If `true`, system prompt builder returns empty string                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      |\n| `PI_BLOCKED_AGENT`           | Blocks a specific subagent type in task tool                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |\n| `PI_SUBPROCESS_CMD`          | Overrides subagent spawn command (`omp` / `omp.cmd` resolution bypass)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     |\n| `PI_TASK_MAX_OUTPUT_BYTES`   | Max captured output bytes per subagent (default `500000`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |\n| `PI_TASK_MAX_OUTPUT_LINES`   | Max captured output lines per subagent (default `5000`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |\n| `PI_TIMING`                  | If set (any non-empty value), prints a hierarchical timing-span tree to **stderr** via `logger.printTimings()`. In interactive mode the tree prints once the agent is ready (before the TUI starts); in print mode it prints after the whole prompt batch completes. Print-mode prompts are wrapped in `print:prompt:initial` / `print:prompt:next` spans so each user message shows up as its own row. `PI_TIMING=x` exits the process with code 0 right after printing in interactive mode (use to measure cold startup only). `PI_TIMING=full` lists every module-load entry instead of just the top N. |\n| `PI_DEBUG_STARTUP`           | If set (any non-empty value), streams one synchronous `[startup] <phase>:start` / `:done` marker line to **stderr** as each startup phase begins/ends — including command-module imports (`cli:load:<name>`) and the native addon extraction/`dlopen` (`native:*`). Unlike `PI_TIMING` (which prints only once startup completes), the markers survive a hard hang: the last line on stderr names the phase the process is stuck in. Combine with `PI_TIMING` freely; markers and the span tree share the same phase names.                                                                                |\n| `PI_PACKAGE_DIR`             | Overrides package asset base dir resolution (`docs/`, `examples/`, `CHANGELOG.md`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |\n| `PI_DISABLE_LSPMUX`          | If `1`, disables lspmux detection/integration and forces direct LSP server spawning                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |\n| `PI_RPC_EMIT_TITLE`          | Boolean-like flag enabling title events in RPC mode                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |\n| `SMITHERY_URL`               | Smithery web URL override (default `https://smithery.ai`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |\n| `SMITHERY_API_URL`           | Smithery API base URL override (default `https://api.smithery.ai`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |\n| `SMITHERY_API_KEY`           | Smithery API key for managed MCP auth lookup                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |\n| `PUPPETEER_EXECUTABLE_PATH`  | Browser tool Chromium executable override                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |\n| `LM_STUDIO_BASE_URL`         | Default implicit LM Studio discovery base URL override (`http://127.0.0.1:1234/v1` if unset)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               |\n| `OLLAMA_BASE_URL`            | Default implicit Ollama discovery base URL override (`OLLAMA_HOST` if unset, then `http://127.0.0.1:11434`)                                                                                                                                                                                                                                                                                                                                                                                                                                     |\n| `OLLAMA_HOST`                | Ollama host used for implicit Ollama discovery when `OLLAMA_BASE_URL` is unset; accepts Ollama-style values such as `127.0.0.1:11434` or `http://host:11434`                                                                                                                                                                                                                                                                                                                                                                                     |\n| `OLLAMA_CONTEXT_LENGTH`      | Positive integer context-window override for implicit Ollama discovery; affects OMP context budgeting only and does not change Ollama's runtime `num_ctx`                                                                                                                                                                                                                                                                                                                                                                                           |\n| `LLAMA_CPP_BASE_URL`         | Default implicit Llama.cpp discovery base URL override (`http://127.0.0.1:8080` if unset)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |\n| `PI_EDIT_VARIANT`            | Forces edit tool variant when valid (`patch`, `replace`, `hashline`, `apply_patch`)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |\n| `PI_FORCE_IMAGE_PROTOCOL`    | Forces supported image protocol (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) where used                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |\n| `PI_ALLOW_SIXEL_PASSTHROUGH` | Allows SIXEL passthrough when `PI_FORCE_IMAGE_PROTOCOL=sixel`                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |\n| `PI_NO_PTY`                  | If `1`, disables interactive PTY path for bash tool                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |\n| `OMP_MCP_TIMEOUT_MS`         | Overrides MCP client request timeout (ms) for every MCP server. `0` disables client-side timeouts (`AbortSignal` never fires). Invalid (negative or non-numeric) values are ignored with a warning and the per-server config or default (`30000`) is used.                                                                                                                                                                                                                                                                                                                                                 |\n\n`PI_NO_PTY` is also set internally when CLI `--no-pty` is used.\n\n---\n\n## 6) Storage and config root paths\n\nThese are consumed via `@oh-my-pi/pi-utils/dirs` and affect where coding-agent stores data.\n\n| Variable              | Default / behavior                                                            |\n| --------------------- | ----------------------------------------------------------------------------- |\n| `PI_CONFIG_DIR`       | Config root dirname under home (default `.omp`)                               |\n| `PI_CODING_AGENT_DIR` | Full override for agent directory (default `~/<PI_CONFIG_DIR or .omp>/agent`) |\n| `PWD`                 | Used when matching canonical current working directory in path helpers        |\n\n---\n\n## 7) Shell/tool execution environment\n\n(From `packages/utils/src/procmgr.ts` and coding-agent bash tool integration.)\n\n| Variable                   | Behavior                                                                       |\n| -------------------------- | ------------------------------------------------------------------------------ |\n| `PI_BASH_NO_CI`            | Suppresses automatic `CI=true` injection into spawned shell env                |\n| `CLAUDE_BASH_NO_CI`        | Legacy alias fallback for `PI_BASH_NO_CI`                                      |\n| `PI_BASH_NO_LOGIN`         | Disables login-shell mode; shell args become `['-c']` instead of `['-l','-c']` |\n| `CLAUDE_BASH_NO_LOGIN`     | Legacy alias fallback for `PI_BASH_NO_LOGIN`                                   |\n| `PI_SHELL_PREFIX`          | Optional command prefix wrapper                                                |\n| `CLAUDE_CODE_SHELL_PREFIX` | Legacy alias fallback for `PI_SHELL_PREFIX`                                    |\n| `VISUAL`                   | Preferred external editor command                                              |\n| `EDITOR`                   | Fallback external editor command                                               |\n\nCurrent implementation: `PI_BASH_NO_LOGIN`/`CLAUDE_BASH_NO_LOGIN` are active; when either is set, `getShellArgs()` returns `['-c']`.\n\n---\n\n## 8) UI/theme/session detection (auto-detected env)\n\nThese are read as runtime signals; they are usually set by the terminal/OS rather than manually configured.\n\n| Variable                                                                                                           | Used for                                                  |\n| ------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------- |\n| `COLORTERM`, `TERM`, `WT_SESSION`                                                                                  | Color capability detection (theme color mode)             |\n| `COLORFGBG`                                                                                                        | Terminal background light/dark auto-detection             |\n| `TERM_PROGRAM`, `TERM_PROGRAM_VERSION`, `TERMINAL_EMULATOR`                                                        | Terminal identity in system prompt/context                |\n| `TMUX_PANE`, `CMUX_SURFACE_ID`, `KITTY_WINDOW_ID`, `TERM_SESSION_ID`, `WT_SESSION`                                 | Stable per-terminal session breadcrumb IDs                |\n| `SHELL`, `ComSpec`, `TERM_PROGRAM`, `TERM`                                                                         | System info diagnostics                                   |\n| `APPDATA`, `XDG_CONFIG_HOME`                                                                                       | lspmux config path resolution                             |\n| `HOME`                                                                                                             | Path shortening in MCP command UI                         |\n\n---\n\n## 9) TUI runtime flags (shared package, affects coding-agent UX)\n\n| Variable                  | Behavior                                                                              |\n| ------------------------- | ------------------------------------------------------------------------------------- |\n| `PI_NOTIFICATIONS`        | `off` / `0` / `false` suppress desktop notifications                                  |\n| `PI_TUI_WRITE_LOG`        | If set, logs TUI writes to file                                                       |\n| `PI_HARDWARE_CURSOR`      | If `1`, enables hardware cursor mode                                                  |\n| `PI_NO_SYNC_OUTPUT`       | If set (any non-empty value), disables DEC 2026 synchronized-output wrappers while keeping TUI autowrap guards |\n| `PI_NO_DECCARA`           | If set (truthy), disables Kitty DECCARA rectangular-SGR background fills (forces padded-string rendering) |\n| `PI_DEBUG_REDRAW`         | If `1`, enables redraw debug logging                                                  |\n| `PI_FORCE_IMAGE_PROTOCOL` | Forces terminal image protocol detection (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) |\n\n---\n\n## 10) Commit generation controls\n\n| Variable                  | Behavior                                                            |\n| ------------------------- | ------------------------------------------------------------------- |\n| `PI_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `PI_COMMIT_NO_FALLBACK`   | If `true`, disables fallback when agent returns no proposal         |\n| `PI_COMMIT_MAP_REDUCE`    | If `false`, disables map-reduce commit analysis path                |\n| `DEBUG`                   | If set, commit agent error stack traces are printed                 |\n\n---\n\n## Security-sensitive variables\n\nTreat these as secrets; do not log or commit them:\n\n- Provider/API keys and OAuth/bearer credentials (all `*_API_KEY`, `*_TOKEN`, OAuth access/refresh tokens)\n- Cloud credentials (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS` path may expose service-account material)\n- Search/provider auth vars (`EXA_API_KEY`, `BRAVE_API_KEY`, `PERPLEXITY_API_KEY`, Anthropic search keys)\n- Foundry mTLS material (`CLAUDE_CODE_CLIENT_CERT`, `CLAUDE_CODE_CLIENT_KEY`, `NODE_EXTRA_CA_CERTS` when it points to private CA bundles)\n\nPython runtime also explicitly strips many common key vars before spawning kernel subprocesses (`packages/coding-agent/src/eval/py/runtime.ts`).\n",
 	"extension-loading.md": "# Extension Loading (TypeScript/JavaScript Modules)\n\nThis document covers how the coding agent discovers and loads **extension modules** (`.ts`/`.js`) at startup.\n\nIt does **not** cover `gemini-extension.json` manifest extensions (documented separately).\n\n## What this subsystem does\n\nExtension loading builds a list of module entry files, imports each module with Bun, executes its factory, and returns:\n\n- loaded extension definitions\n- per-path load errors (without aborting the whole load)\n- a shared extension runtime object used later by `ExtensionRunner`\n\n## Primary implementation files\n\n- `src/extensibility/extensions/loader.ts` — path discovery + import/execution\n- `src/extensibility/extensions/index.ts` — public exports\n- `src/extensibility/extensions/runner.ts` — runtime/event execution after load\n- `src/discovery/builtin.ts` — native auto-discovery provider for extension modules\n- `src/config/settings.ts` — loads merged `extensions` / `disabledExtensions` settings\n\n---\n\n## Inputs to extension loading\n\n### 1) Auto-discovered native extension modules\n\n`discoverAndLoadExtensions()` first asks discovery providers for `extension-module` capability items, then keeps only provider `native` items.\n\nNative `extension-module` discovery comes from:\n\n- Project directory: `<cwd>/.omp/extensions`\n- User directory: `~/.omp/agent/extensions`\n- Native legacy/settings JSON entries: `<cwd>/.omp/settings.json#extensions` and `~/.omp/agent/settings.json#extensions`\n\nThe project root is the native provider's `.omp` directory (`SOURCE_PATHS.native.projectDir`), cwd-only; it does not walk ancestors. The user root is the active profile's agent directory via `getAgentDir()`, so under `omp --profile <name>` it becomes `~/.omp/profiles/<name>/agent/extensions` (and it honors `PI_CODING_AGENT_DIR`). See [Profiles](./config-usage.md#profiles).\n\nNotes:\n\n- Native auto-discovery is currently `.omp` based.\n- Legacy `.pi` is still accepted in package manifests (`pi.extensions`) and project override lookup, but `.pi/extensions` is not a native root here.\n\n### 2) Installed plugin extension entries\n\nAfter native auto-discovery, `discoverAndLoadExtensions()` appends extension entry points from enabled installed plugins via `getAllPluginExtensionPaths(cwd)`.\n\nPlugin extension entries come from package `omp.extensions` / `pi.extensions` manifests, including enabled feature entries.\n\n### 3) Explicitly configured paths\n\nAfter plugin extension entries, configured paths are appended and resolved.\n\nConfigured path sources in the main session startup path (`sdk.ts`):\n\n1. CLI-provided paths (`--extension/-e`, and `--hook` is also treated as an extension path)\n2. Merged settings `extensions` array\n\nSettings files:\n\n- User: `~/.omp/agent/config.yml` (or custom agent dir via `PI_CODING_AGENT_DIR`)\n- Project/native settings capability: `<cwd>/.omp/config.yml` and `<cwd>/.omp/settings.json`\n\nNative extension-module discovery also reads legacy JSON extension lists from:\n\n- `~/.omp/agent/settings.json`\n- `<cwd>/.omp/settings.json`\n\nExamples:\n\n```yaml\n# ~/.omp/agent/config.yml\nextensions:\n  - ~/my-exts/safety.ts\n  - ./local/ext-pack\n```\n\n```json\n{\n  \"extensions\": [\"./.omp/extensions/my-extra\"]\n}\n```\n\n---\n\n## Enable/disable controls\n\n### Disable discovery\n\n- CLI: `--no-extensions`\n- SDK option: `disableExtensionDiscovery`\n\nBehavior split:\n\n- SDK: when `disableExtensionDiscovery=true`, it still loads `additionalExtensionPaths` via `loadExtensions()`.\n- CLI path building (`main.ts`) currently clears CLI extension paths when `--no-extensions` is set, so explicit `-e/--hook` are not forwarded in that mode.\n\n### Disable specific extension modules\n\n`disabledExtensions` setting filters by extension id format:\n\n- `extension-module:<derivedName>`\n\n`derivedName` is based on entry path (`getExtensionNameFromPath`), for example:\n\n- `/x/foo.ts` -> `foo`\n- `/x/bar/index.ts` -> `bar`\n\nExample:\n\n```yaml\ndisabledExtensions:\n  - extension-module:foo\n```\n\n---\n\n## Path and entry resolution\n\n### Path normalization\n\nFor configured paths:\n\n1. Normalize unicode spaces\n2. Expand `~`\n3. If relative, resolve against current `cwd`\n\n### If configured path is a file\n\nIt is used directly as a module entry candidate.\n\n### If configured path is a directory\n\nResolution order:\n\n1. `package.json` in that directory with `omp.extensions` (or legacy `pi.extensions`) -> use declared entries\n2. `index.ts`\n3. `index.js`\n4. Otherwise scan one level for extension entries:\n   - direct `*.ts` / `*.js`\n   - subdir `index.ts` / `index.js`\n   - subdir `package.json` with `omp.extensions` / `pi.extensions`\n\nRules and constraints:\n\n- no recursive discovery beyond one subdirectory level\n- declared `extensions` manifest entries are resolved relative to that package directory\n- declared entries are included only if file exists/access is allowed\n- in `*/index.{ts,js}` pairs, TypeScript is preferred over JavaScript\n- symlinks are treated as eligible files/directories\n\n### Ignore behavior differs by source\n\n- Native auto-discovery (`discoverExtensionModulePaths` in discovery helpers) uses native glob with `gitignore: true` and `hidden: false`.\n- Explicit configured directory scanning in `loader.ts` uses `readdir` rules and does **not** apply gitignore filtering.\n\n---\n\n## Load order and precedence\n\n`discoverAndLoadExtensions()` builds one ordered list and then calls `loadExtensions()`.\n\nOrder:\n\n1. Native auto-discovered modules\n2. Installed plugin extension entries\n3. Explicit configured paths (in provided order)\n\nIn `sdk.ts`, configured order is:\n\n1. CLI additional paths\n2. Settings `extensions`\n\nDe-duplication:\n\n- absolute path based\n- first seen path wins\n- later duplicates are ignored\n\nImplication: if the same module path is both auto-discovered and explicitly configured, it is loaded once at the first position (auto-discovered stage).\n\n---\n\n## Module import and factory contract\n\nEach candidate path is loaded with dynamic import:\n\n- `await import(resolvedPath)`\n- factory is `module.default ?? module`\n- factory must be a function (`ExtensionFactory`)\n\nIf export is not a function, that path fails with a structured error and loading continues.\n\n---\n\n## Failure handling and isolation\n\n### During loading\n\nPer extension path, failures are captured as `{ path, error }` and do not stop other paths from loading.\n\nCommon cases:\n\n- import failure / missing file\n- invalid factory export (non-function)\n- exception thrown while executing factory\n\n### Runtime isolation model\n\n- Extensions are **not sandboxed** (same process/runtime).\n- They share one `EventBus` and one `ExtensionRuntime` instance.\n- During load, runtime action methods intentionally throw `ExtensionRuntimeNotInitializedError`; action wiring happens later in `ExtensionRunner.initialize()`.\n\n### After loading\n\nWhen events run through `ExtensionRunner`, handler exceptions are caught and emitted as extension errors instead of crashing the runner loop.\n\n---\n\n## Minimal user/project layout examples\n\n### User-level\n\n```text\n~/.omp/agent/\n  config.yml\n  extensions/\n    guardrails.ts\n    audit/\n      index.ts\n```\n\n### Project-level\n\n```text\n<repo>/\n  .omp/\n    settings.json\n    extensions/\n      checks/\n        package.json\n      lint-gates.ts\n```\n\n`checks/package.json`:\n\n```json\n{\n  \"omp\": {\n    \"extensions\": [\"./src/check-a.ts\", \"./src/check-b.js\"]\n  }\n}\n```\n\nLegacy manifest key still accepted:\n\n```json\n{\n  \"pi\": {\n    \"extensions\": [\"./index.ts\"]\n  }\n}\n```\n",
 	"extensions.md": "# Extensions\n\nPrimary guide for authoring runtime extensions in `packages/coding-agent`.\n\nThis document covers the current extension runtime in:\n\n- `src/extensibility/extensions/types.ts`\n- `src/extensibility/extensions/runner.ts`\n- `src/extensibility/extensions/wrapper.ts`\n- `src/extensibility/extensions/index.ts`\n- `src/modes/controllers/extension-ui-controller.ts`\n\nFor discovery paths and filesystem loading rules, see [`extension-loading.md`](./extension-loading.md).\n\n## What an extension is\n\nAn extension is a TS/JS module exporting a default factory:\n\n```ts\nimport type { ExtensionAPI } from \"@oh-my-pi/pi-coding-agent\";\n\nexport default function myExtension(pi: ExtensionAPI) {\n  // register handlers/tools/commands/renderers\n}\n```\n\nExtensions can combine all of the following in one module:\n\n- event handlers (`pi.on(...)`)\n- LLM-callable tools (`pi.registerTool(...)`)\n- slash commands (`pi.registerCommand(...)`)\n- keyboard shortcuts and flags\n- custom message rendering\n- session/message injection APIs (`sendMessage`, `sendUserMessage`, `appendEntry`)\n\n## Runtime model\n\n1. Extensions are imported and their factory functions run.\n2. During that load phase, registration methods are valid; runtime action methods are not yet initialized.\n3. `ExtensionRunner.initialize(...)` wires live actions/contexts for the active mode.\n4. Session/agent/tool lifecycle events are emitted to handlers.\n5. Every tool execution is wrapped with extension interception (`tool_call` / `tool_result`).\n\n```text\nExtension lifecycle (simplified)\n\nload paths\n   │\n   ▼\nimport module + run factory (registration only)\n   │\n   ▼\nExtensionRunner.initialize(mode/session/tool registry)\n   │\n   ├─ emit session/agent events to handlers\n   ├─ wrap tool execution (tool_call/tool_result)\n   └─ expose runtime actions (sendMessage, setActiveTools, ...)\n```\n\nImportant constraint from `loader.ts`:\n\n- calling action methods like `pi.sendMessage()` during extension load throws `ExtensionRuntimeNotInitializedError`\n- register first; perform runtime behavior from events/commands/tools\n\n## Quick start\n\n```ts\nimport type { ExtensionAPI } from \"@oh-my-pi/pi-coding-agent\";\n\nexport default function (pi: ExtensionAPI) {\n  const { z } = pi.zod;\n\n  pi.setLabel(\"Safety + Utilities\");\n\n  pi.on(\"session_start\", async (_event, ctx) => {\n    ctx.ui.notify(`Extension loaded in ${ctx.cwd}`, \"info\");\n  });\n\n  pi.on(\"tool_call\", async (event) => {\n    if (event.toolName === \"bash\" && event.input.command?.includes(\"rm -rf\")) {\n      return { block: true, reason: \"Blocked by extension policy\" };\n    }\n  });\n\n  pi.registerTool({\n    name: \"hello_extension\",\n    label: \"Hello Extension\",\n    description: \"Return a greeting\",\n    parameters: z.object({ name: z.string() }),\n    async execute(_toolCallId, params, _signal, _onUpdate, _ctx) {\n      return {\n        content: [{ type: \"text\", text: `Hello, ${params.name}` }],\n        details: { greeted: params.name },\n      };\n    },\n  });\n\n  pi.registerCommand(\"hello-ext\", {\n    description: \"Show queue state\",\n    handler: async (_args, ctx) => {\n      ctx.ui.notify(`pending=${ctx.hasPendingMessages()}`, \"info\");\n    },\n  });\n}\n```\n\n## Extension API surfaces\n\n## 1) Registration and actions (`ExtensionAPI`)\n\nCore methods:\n\n- `on(event, handler)`\n- `registerTool`, `registerCommand`, `registerShortcut`, `registerFlag`\n- `registerMessageRenderer`, `registerAssistantThinkingRenderer`\n- `setLabel`, `getFlag`\n- `sendMessage`, `sendUserMessage`, `appendEntry`, `exec`\n- `getActiveTools`, `getAllTools`, `setActiveTools`\n- `getCommands`\n- `getSessionName`, `setSessionName`\n- `setModel`, `getThinkingLevel`, `setThinkingLevel`\n- `registerProvider`\n- `events` (shared event bus)\n\nIn interactive mode, `input` handlers run before the built-in first-message auto-title check. Extensions that call `await pi.setSessionName(...)` from `input` can set the persisted session name and prevent the default auto-generated title from running for that session.\n\nAlso exposed:\n\n- `pi.logger`\n- `pi.typebox` (zod-backed compatibility shim for legacy TypeBox-style schemas)\n- `pi.zod` (injected `zod/v4` module — canonical for tool parameter schemas)\n- `pi.pi` (package exports)\n\n### Message delivery semantics\n\n`pi.sendMessage(message, options)` supports:\n\n- `deliverAs: \"steer\"` (default) — interrupts current run\n- `deliverAs: \"followUp\"` — queued to run after current run\n- `deliverAs: \"nextTurn\"` — stored and injected on the next user prompt\n- `triggerTurn: true` — starts a turn when idle (also honored with `deliverAs: \"nextTurn\"`: idle prompts immediately; while streaming the queued message schedules an internal continuation)\n\n`pi.sendUserMessage(content, { deliverAs })` always goes through prompt flow; while streaming it queues as steer/follow-up.\n\n## 2) Handler context (`ExtensionContext`)\n\nHandlers and tool `execute` receive `ctx` with:\n\n- `ui`\n- `hasUI`\n- `cwd`\n- `sessionManager` (read-only)\n- `modelRegistry`, `model`\n- `models` (read-only model query — see below)\n- `getContextUsage()`\n- `compact(...)`\n- `isIdle()`, `hasPendingMessages()`, `abort()`\n- `shutdown()`\n- `getSystemPrompt()`\n\n### Model selection (`ctx.models`)\n\n`ctx.models` is a read-only facade for picking and comparing models the same way core does:\n\n- `list()` — authenticated models available this session.\n- `current()` — the live session model (read lazily, so it reflects `/model` switches).\n- `resolve(spec)` — a model string (`provider/id`, bare id) or role alias (`pi/slow`, a configured role) → `Model`, honoring the same settings-backed aliases and match preferences as `--model`. Returns `undefined` when nothing matches.\n- `family(model)` — an opaque lineage token for \"same family?\" checks (Claude point releases share a token; Claude and GPT differ). Compare it; don't persist it (the vocabulary tracks new releases).\n\n```ts\n// Pick a model from a different family than the current one (e.g. a cross-family reviewer).\nconst current = ctx.models.current();\nconst contrasting = ctx.models\n  .list()\n  .find(m => current && ctx.models.family(m) !== ctx.models.family(current));\n```\n\n## 3) Command context (`ExtensionCommandContext`)\n\nCommand handlers additionally get:\n\n- `waitForIdle()`\n- `newSession(...)`\n- `switchSession(...)`\n- `branch(entryId)`\n- `navigateTree(targetId, { summarize })`\n- `reload()`\n\nUse command context for session-control flows; these methods are intentionally separated from general event handlers.\n\n## Event surface (current names and behavior)\n\nCanonical event unions and payload types are in `types.ts`.\n\n### Session lifecycle\n\n- `session_start`\n- `session_before_switch` / `session_switch`\n- `session_before_branch` / `session_branch`\n- `session_before_compact` / `session.compacting` / `session_compact`\n- `session_before_tree` / `session_tree`\n- `session_shutdown`\n\nCancelable pre-events:\n\n- `session_before_switch` → `{ cancel?: boolean }`\n- `session_before_branch` → `{ cancel?: boolean; skipConversationRestore?: boolean }`\n- `session_before_compact` → `{ cancel?: boolean; compaction?: CompactionResult }`\n- `session_before_tree` → `{ cancel?: boolean; summary?: { summary: string; details?: unknown } }`\n\n### Prompt and turn lifecycle\n\n- `input`\n- `before_agent_start`\n- `before_provider_request` (may replace provider request payload)\n- `after_provider_response`\n- `context`\n- `agent_start` / `agent_end`\n- `turn_start` / `turn_end`\n- `message_start` / `message_update` / `message_end`\n\n### Tool lifecycle\n\n- `tool_call` (pre-exec, may block)\n- `tool_result` (post-exec, may patch content/details/isError)\n- `tool_execution_start` / `tool_execution_update` / `tool_execution_end` (observability)\n\n`tool_result` is middleware-style: handlers run in extension order and each sees prior modifications.\n\n### Reliability/runtime signals\n\n- `auto_compaction_start` / `auto_compaction_end`\n- `auto_retry_start` / `auto_retry_end`\n- `ttsr_triggered`\n- `todo_reminder`\n- `goal_updated`\n- `credential_disabled`\n\n### User command interception\n\n- `user_bash` (override with `{ result }`)\n- `user_python` (override with `{ result }`)\n\n### `resources_discover`\n\n`resources_discover` exists in extension types and `ExtensionRunner`.\nCurrent runtime note: `ExtensionRunner.emitResourcesDiscover(...)` is implemented, but there are no `AgentSession` callsites invoking it in the current codebase.\n\n## Tool authoring details\n\n`registerTool` uses `ToolDefinition` from `types.ts`.\n\nCurrent `execute` signature:\n\n```ts\nexecute(\n\ttoolCallId,\n\tparams,\n\tsignal,\n\tonUpdate,\n\tctx,\n): Promise<AgentToolResult>\n```\n\nTemplate:\n\n```ts\nconst { z } = pi.zod;\n\npi.registerTool({\n  name: \"my_tool\",\n  label: \"My Tool\",\n  description: \"...\",\n  parameters: z.object({}),\n  hidden: false,\n  defaultInactive: false,\n  deferrable: false,\n  async execute(_id, _params, signal, onUpdate, ctx) {\n    if (signal?.aborted) {\n      return { content: [{ type: \"text\", text: \"Cancelled\" }] };\n    }\n    onUpdate?.({ content: [{ type: \"text\", text: \"Working...\" }] });\n    return { content: [{ type: \"text\", text: \"Done\" }], details: {} };\n  },\n  onSession(event, ctx) {\n    // reason: start|switch|branch|tree|shutdown\n  },\n  renderCall(args, options, theme) {\n    // optional TUI render\n  },\n  renderResult(result, options, theme, args) {\n    // optional TUI render\n  },\n});\n```\n\n`tool_call`/`tool_result` intercept all tools once the registry is wrapped in `sdk.ts`, including built-ins and extension/custom tools. `ToolDefinition` also supports optional `hidden`, `defaultInactive`, `deferrable`, `approval`, `mcpServerName`, `mcpToolName`, `renderCall`, and `renderResult` fields.\n\n## UI integration points\n\n`ctx.ui` implements the `ExtensionUIContext` interface. Support differs by mode.\n\n### Interactive mode (`extension-ui-controller.ts`)\n\nSupported:\n\n- dialogs: `select`, `confirm`, `input`, `editor`\n- input editing: `setEditorText`, `getEditorText`, `pasteToEditor`, `editor`\n- terminal title and working message (`setTitle`, `setWorkingMessage`)\n- notifications/status/editor text/terminal input/custom overlays\n- theme listing/loading by name (`setTheme` supports string names)\n- tools expanded toggle\n\nCurrent no-op methods in this controller:\n\n- `setFooter`\n- `setHeader`\n\n`setEditorComponent` is wired to the live editor (`ctx.setEditorComponent(factory)`). `setWidget` renders real widget components above or below the editor via `setHookWidget(...)` (`placement: \"aboveEditor\" | \"belowEditor\"`; string-array content capped at 10 lines).\n\n### RPC mode (`rpc-mode.ts`)\n\n`ctx.ui` is backed by RPC `extension_ui_request` events:\n\n- dialog methods (`select`, `confirm`, `input`, `editor`) round-trip to client responses\n- fire-and-forget methods emit requests (`notify`, `setStatus`, `setWidget` for string arrays, `setEditorText`; `setTitle` emits only when `PI_RPC_EMIT_TITLE=1`)\n\nUnsupported/no-op in RPC implementation:\n\n- `onTerminalInput`\n- `custom`\n- `setFooter`, `setHeader`, `setEditorComponent`\n- `setWorkingMessage`\n- theme switching/loading (`setTheme` returns failure)\n- tool expansion controls are inert\n\n### Print/headless/subagent paths\n\nWhen no UI context is supplied to runner init, `ctx.hasUI` is `false` and methods are no-op/default-returning.\n\n### ACP mode\n\nACP installs an elicitation-bridged UI context (`createAcpExtensionUiContext` in `acp-agent.ts`). `ctx.hasUI` is `true` while only `select`/`confirm`/`input` round-trip (as ACP elicitations; defaults are returned when the client lacks the `elicitation.form` capability). The non-elicitation surface (widgets, editor, theming, terminal input) is stubbed no-op.\n\n## Session and state patterns\n\nFor durable extension state:\n\n1. Persist with `pi.appendEntry(customType, data)`.\n2. Rebuild state from `ctx.sessionManager.getBranch()` on `session_start`, `session_branch`, `session_tree`.\n3. Keep tool result `details` structured when state should be visible/reconstructible from tool result history.\n\nExample reconstruction pattern:\n\n```ts\npi.on(\"session_start\", async (_event, ctx) => {\n  let latest;\n  for (const entry of ctx.sessionManager.getBranch()) {\n    if (entry.type === \"custom\" && entry.customType === \"my-state\") {\n      latest = entry.data;\n    }\n  }\n  // restore from latest\n});\n```\n\n## Rendering extension points\n\n## Custom message renderer\n\n```ts\npi.registerMessageRenderer(\"my-type\", (message, { expanded }, theme) => {\n  // return pi-tui Component\n});\n```\n\nUsed by interactive rendering when custom messages are displayed.\n\n## Assistant thinking renderer\n\n```ts\nimport { Container, Text } from \"@oh-my-pi/pi-tui\";\n\npi.registerAssistantThinkingRenderer((context, theme) => {\n  const container = new Container();\n  container.addChild(new Text(theme.fg(\"dim\", `thinking chars: ${context.text.length}`), 1, 0));\n  return container;\n});\n```\n\nUsed by interactive rendering to add display-only supplemental UI below each visible assistant thinking block. The renderer receives the already-visible thinking text, content/thinking indexes, theme, and a `requestRender()` callback for async renderers. All registered renderers that return a component are appended in registration order. Renderers must not mutate messages; the original thinking block remains the provider/session source of truth.\n\n## Tool call/result renderer\n\nProvide `renderCall` / `renderResult` on `registerTool` definitions for custom tool visualization in TUI.\n\n## Constraints and pitfalls\n\n- Runtime actions are unavailable during extension load.\n- `tool_call` errors block execution (fail-closed).\n- Command name conflicts with built-ins are skipped with diagnostics.\n- Reserved shortcuts are ignored (`ctrl+c`, `ctrl+d`, `ctrl+z`, `ctrl+k`, `ctrl+p`, `ctrl+l`, `ctrl+o`, `ctrl+t`, `ctrl+g`, `ctrl+q`, `alt+m`, `shift+tab`, `shift+ctrl+p`, `alt+enter`, `escape`, `enter`).\n- Treat `ctx.reload()` as terminal for the current command handler frame.\n\n## Extensions vs hooks vs custom-tools\n\nUse the right surface:\n\n- **Extensions** (`src/extensibility/extensions/*`): unified system (events + tools + commands + renderers + provider registration).\n- **Hooks** (`src/extensibility/hooks/*`): separate legacy event API.\n- **Custom-tools** (`src/extensibility/custom-tools/*`): tool-focused modules; when loaded alongside extensions they are adapted and still pass through extension interception wrappers.\n\nIf you need one package that owns policy, tools, command UX, and rendering together, use extensions.\n",
 	"fs-scan-cache-architecture.md": "# Filesystem Scan Cache Architecture Contract\n\nThis document defines the current contract for the shared filesystem scan cache implemented in Rust (`crates/pi-natives/src/fs_cache.rs`) and consumed by native discovery/search APIs exposed to `packages/coding-agent`.\n\n## What this cache is\n\nThe cache stores full directory-scan entry lists (`GlobMatch[]`) keyed by scan scope, traversal policy, and requested metadata detail. Higher-level operations (`glob` filtering, `fuzzyFind` scoring, and cached `grep` candidate selection) run against those cached entries.\n\nPrimary goals:\n\n- avoid repeated filesystem walks for repeated discovery/search calls\n- keep consistency across native discovery/search flows when they share the same scan policy\n- allow explicit staleness recovery for empty results and explicit invalidation after file mutations\n\n## Ownership and public surface\n\n- Cache implementation and policy: `crates/pi-natives/src/fs_cache.rs`\n- Native consumers:\n  - `crates/pi-natives/src/glob.rs`\n  - `crates/pi-natives/src/fd.rs` (`fuzzyFind`)\n  - `crates/pi-natives/src/grep.rs` (cached directory mode only)\n- JS binding/export:\n  - `packages/natives/native/index.d.ts` (`invalidateFsScanCache`)\n  - `packages/natives/native/index.js`\n- Coding-agent mutation invalidation helpers:\n  - `packages/coding-agent/src/tools/fs-cache-invalidation.ts`\n\n## Cache key partitioning (hard contract)\n\nEach entry is keyed by:\n\n- canonicalized `root` directory path\n- `include_hidden` boolean\n- `use_gitignore` boolean\n- `skip_node_modules` boolean\n- `detail` (`ScanDetail::Minimal` or `ScanDetail::Full`)\n\nImplications:\n\n- Hidden and non-hidden scans do **not** share entries.\n- Gitignore-respecting and ignore-disabled scans do **not** share entries.\n- Scans that prune `node_modules` do **not** share entries with scans that include it.\n- Minimal scans (path + file type only) do **not** share entries with full scans (mtime + regular-file size metadata).\n- `follow_links` is part of `ScanOptions` used to build the walker, but is not currently part of `CacheKey`; calls that differ only by `follow_links` can share a cache entry.\n\nConsumers must pass stable semantics for hidden/gitignore/node_modules/detail behavior; changing any keyed flag creates a different cache partition.\n\n## Scan collection behavior\n\nCache population uses `ignore::WalkBuilder` configured by `include_hidden`, `use_gitignore`, `skip_node_modules`, and `follow_links`:\n\n- sorted by file path\n- `.git` is always pruned\n- `node_modules` is pruned at traversal time when `skip_node_modules=true`\n- cancellation is checked before the walk and every 128 visited entries per parallel visitor\n- `ScanDetail::Minimal` records normalized relative path and file type only\n- `ScanDetail::Full` also records mtime and regular-file size\n\nSearch roots for cache scans are resolved by `fs_cache::resolve_search_path`:\n\n- relative paths are resolved against current cwd\n- target must be an existing directory\n- root is canonicalized when possible\n\n## Freshness and eviction policy\n\nGlobal policy (environment-overridable):\n\n- `FS_SCAN_CACHE_TTL_MS` (default `1000`)\n- `FS_SCAN_EMPTY_RECHECK_MS` (default `200`)\n- `FS_SCAN_CACHE_MAX_ENTRIES` (default `16`)\n\nBehavior:\n\n- `get_or_scan(...)`\n  - if TTL is `0`: bypass cache entirely, always fresh scan (`cache_age_ms = 0`)\n  - on cache hit within TTL: return cloned cached entries + non-zero `cache_age_ms`\n  - on expired hit: evict key, rescan, store fresh entry\n- `force_rescan(..., store=false)`: remove any matching key, scan fresh, and do not repopulate cache\n- `force_rescan(..., store=true)`: remove any matching key, scan fresh, then store the new entry\n- max entry enforcement is oldest-first eviction by `created_at` after insert\n\n## Empty-result fast recheck (separate from normal hits)\n\nNormal cache hit:\n\n- a cache hit inside TTL returns cached entries and does nothing else.\n\nEmpty-result fast recheck:\n\n- this is a **caller-side** policy using `ScanResult.cache_age_ms`\n- if filtered/query result is empty and cached scan age is at least `empty_recheck_ms()`, caller performs one `force_rescan(..., store=true)` and retries\n- intended to reduce stale-negative results when files were added while the cache is still inside TTL\n\nCurrent consumers:\n\n- `glob`: rechecks when filtered matches are empty and scan age exceeds threshold\n- `fuzzyFind` (`fd.rs`): rechecks only when query is non-empty and scored matches are empty\n- `grep`: rechecks when cached directory candidate file list is empty\n\n## Consumer defaults and cache usage\n\nCache is opt-in on exposed scan/search APIs (`cache?: boolean`, default `false`).\n\nCurrent defaults in native APIs:\n\n- `glob`: `hidden=false`, `gitignore=true`, `cache=false`; `node_modules` is included only when `includeNodeModules=true` or the pattern mentions `node_modules`; full detail is used only when `sortByMtime=true`\n- `fuzzyFind`: `hidden=false`, `gitignore=true`, `cache=false`, `node_modules` is skipped, `follow_links=true`, minimal detail\n- `grep`: `hidden=true`, `gitignore=true`, `cache=false`; cached directory mode skips `node_modules` unless the glob mentions `node_modules`; minimal detail\n\nCurrent callers:\n\n- `@`-mention fuzzy file autocomplete enables cache (`fuzzyFind` with `cache: true`):\n  - `packages/tui/src/autocomplete.ts`\n- Mutation flows invalidate through `packages/coding-agent/src/tools/fs-cache-invalidation.ts`.\n- Tool-level search integration (`packages/coding-agent/src/tools/search.ts`) currently calls native `grep` with `cache: false`.\n\n## Invalidation contract\n\nNative invalidation entrypoint:\n\n- `invalidateFsScanCache(path?: string)`\n  - with `path`: remove cache entries whose root is a prefix of the target path\n  - without path: clear all scan cache entries\n\nPath handling details:\n\n- relative invalidation paths are resolved against cwd\n- invalidation attempts canonicalization\n- if target does not exist (for example after delete), fallback canonicalizes the parent and reattaches the filename when possible\n- this preserves invalidation behavior for create/delete/rename where one side may not exist\n\n## Coding-agent mutation flow responsibilities\n\nCoding-agent code must invalidate after successful filesystem mutations.\n\nCentral helpers:\n\n- `invalidateFsScanAfterWrite(path)`\n- `invalidateFsScanAfterDelete(path)`\n- `invalidateFsScanAfterRename(oldPath, newPath)` (invalidates both sides when paths differ)\n\nCurrent mutation callsites include:\n\n- `packages/coding-agent/src/tools/write.ts`\n- `packages/coding-agent/src/edit/hashline/filesystem.ts`\n- `packages/coding-agent/src/edit/modes/patch.ts`\n- `packages/coding-agent/src/edit/modes/replace.ts`\n\nRule: if a flow mutates filesystem content or location and bypasses these helpers, cache staleness bugs are expected.\n\n## Adding a new cache consumer safely\n\nWhen introducing cache use in a new scanner/search path:\n\n1. **Use stable scan policy inputs**\n   - decide hidden/gitignore/node_modules/detail semantics first\n   - pass them consistently to `get_or_scan`/`force_rescan` so cache partitions are intentional\n\n2. **Treat cache data as pre-filtered only by traversal policy**\n   - apply tool-specific filtering (glob patterns, type filters, scoring) after retrieval\n   - never assume cached entries already reflect your higher-level filters\n\n3. **Implement empty-result fast recheck only for stale-negative risk**\n   - use `scan.cache_age_ms >= empty_recheck_ms()`\n   - retry once with `force_rescan(..., store=true, ...)`\n   - keep this path separate from normal cache-hit logic\n\n4. **Respect no-cache mode explicitly**\n   - when caller disables cache, call `force_rescan(..., store=false, ...)` or use an uncached streaming walker\n   - do not populate shared cache in a no-cache request path\n\n5. **Wire mutation invalidation for any new write path**\n   - after successful write/edit/delete/rename, call the coding-agent invalidation helper\n   - for rename/move, invalidate both old and new paths\n\n6. **Do not add per-call TTL knobs**\n   - current contract is global policy only (env-configured), no per-request TTL override\n\n## Known boundaries\n\n- Cache scope is process-local in-memory (`DashMap`), not persisted across process restarts.\n- Cache stores scan entries, not final tool results.\n- `glob`/`fuzzyFind`/cached `grep` share scan entries only when key dimensions (`root`, `hidden`, `gitignore`, `skip_node_modules`, `detail`) match.\n- `.git` is always excluded at scan collection time regardless of caller options.\n",
@@ -27,14 +28,14 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"local-models.md": "# Embedded Local Tiny-Model Experiments\n\nThis document summarizes the experiments behind the optional **local** tiny-model paths for\nsession-title generation (`providers.tinyModel`), Mnemopi memory extraction/consolidation\n(`providers.memoryModel`), and the `auto` thinking-level difficulty classifier\n(`providers.autoThinkingModel`, which reuses the memory-model registry). It is a factual engineering\nrecord for maintainers: what we measured, which recipes won, and which models we shipped. All three\nsettings default to `online`, so existing users incur no downloads or on-device inference cost unless\nthey opt in.\n\n## Runtime / environment findings\n\n- **Stack**: `@huggingface/transformers` (transformers.js) v4 running under Bun. In Bun the library\n  loads the **native `onnxruntime-node` backend** (not the WASM build).\n- **Device policy**: local tiny models default to CPU-only inference and retry once on CPU if an\n  explicit accelerated provider cannot initialize.\n  - Pick a provider persistently with the `providers.tinyModelDevice` setting (`default` keeps CPU),\n    or per-run with the `PI_TINY_DEVICE` env var (which overrides the setting).\n  - Accepted values are `cpu`, `gpu`, `metal`/`webgpu`, `auto`, `cuda`, `dml`, `coreml`, `wasm`,\n    `webnn`, `webnn-gpu`, `webnn-cpu`, and `webnn-npu`.\n  - Direct `coreml` remains opt-in via `PI_TINY_DEVICE=coreml`; it is not part of the default because\n    cached decoder-LLM ONNX loads can fail during session initialization.\n  - WebGPU/Metal works for the single-process eval harness, but the production worker forces\n    Darwin `gpu`/`webgpu`/`auto` requests back to CPU because ONNX Runtime/Bun currently\n    hard-crashes on worker teardown after WebGPU inference.\n  - Use `providers.tinyModelDevice` or `PI_TINY_DEVICE` only when explicitly opting out of the CPU\n    default.\n- **Quantization: q4 is the sweet spot** — smaller on disk, faster to load, and fast at inference.\n  q8/int8 loads slower _and_ infers slower on CPU. Every shipped model defaults to `q4`; override the\n  precision persistently with the `providers.tinyModelDtype` setting (`default` keeps `q4`, e.g. `fp16`\n  for higher fidelity), or per-run with `PI_TINY_DTYPE` (which overrides the setting). Accepts `auto`,\n  `fp32`, `fp16`, `q8`, `int8`, `uint8`, `q4`, `bnb4`, `q4f16`, `q2`, `q2f16`, `q1`, `q1f16`; an\n  unrecognized value fails loudly at worker startup.\n- **Load-time correction (important).** An earlier belief that \"q4 >=1B models take minutes to load\"\n  was a **measurement artifact** caused by running ~5 multi-GB HuggingFace downloads in parallel\n  (I/O saturation). Clean, isolated **warm** loads are all sub-3s:\n  - TinyLlama-1.1B q4: ~0.5s\n  - Llama-3.2-1B q4: ~2.8s (`graphOpt=all`) / ~0.5s (`disabled`)\n  - LFM2-1.2B q4: ~0.36s\n  - Qwen2.5-1.5B q4: ~1.5s\n  - Qwen3-1.7B q4: ~1.6s\n  - gemma-3-1b q4: ~1.1s\n  - Conclusion: **1B–1.7B models are viable on CPU.**\n- **`session_options.graphOptimizationLevel`** trades load vs inference speed: `disabled` = fastest\n  load, slightly slower inference; `all` = default.\n- **First run** downloads weights from the HF Hub to a cache dir (q4 weights ~200MB–1.1GB depending\n  on model); subsequent **warm** loads are sub-second to ~3s. Inference is async and\n  background-friendly for memory tasks; titles are semi-interactive.\n\n## Task 1: Session title generation (`providers.tinyModel`)\n\n**Task**: turn the first user message into a 3–6 word title. Tiny models (sub-1B) suffice.\n\n**Winning recipe**:\n\n- Plain system prompt (no few-shot).\n- **Prefill** the assistant turn with `<title>` and **stop at `</title>`**, then take the first line.\n- Greedy decoding (`do_sample:false`), `enable_thinking:false` in the chat template.\n\n**What we learned**:\n\n- **Few-shot examples HURT sub-0.6B models** for titles; the tag-prefill rescues even 270M models.\n- **Token biasing (`bad_words_ids`) is a confirmed no-op** here — the prefill already controls the\n  opener.\n\n**Leaderboard** (tag trick, CPU, warm):\n\n| Model         | Verdict                             |\n| ------------- | ----------------------------------- |\n| LFM2-350M     | Best speed/quality balance (~212MB) |\n| Qwen3-0.6B    | Most robust                         |\n| gemma-3-270m  | Smallest viable                     |\n| Qwen2.5-0.5B  | Acceptable                          |\n| SmolLM2-135M  | Too small                           |\n| flan-t5-small | Rejected — just echoes the input    |\n\n**Shipped local options**: `lfm2-350m`, `qwen3-0.6b`, `gemma-270m`, `qwen2.5-0.5b`, `lfm2-700m`.\n**Default**: `online` (pi/smol).\n\n## Task 2: Mnemopi memory (`providers.memoryModel`)\n\nMnemopi runs two small-LLM tasks:\n\n1. **Extraction** — pull durable, structured items from a single message.\n2. **Consolidation** — summarize a list of memories into 1–3 faithful sentences.\n\nThese need **bigger models than titles: 1B–1.7B**. We tested LFM2-1.2B, Qwen2.5-1.5B, Qwen3-1.7B,\nand gemma-3-1b (q4, CPU) via four parallel agents each running 27–31 experiments.\n\n### Extraction findings\n\nThe stock 5-category JSON prompt fails on small models in two ways:\n\n1. The all-empty example `{\"facts\":[],...}` gets **copied verbatim** → 0 facts extracted.\n2. Capable models emit **JSON objects inside arrays**, which Mnemopi's `String(item)` coerces into\n   the literal string `[object Object]`.\n\nThe robust fix is a **one-item-per-line output format** (consumed by Mnemopi's parser line-fallback)\nor a **flat JSON array of strings**. Every model also over-extracts pure small talk; an explicit\nchit-chat → NONE example is the best mitigation.\n\n### Technique polarity flips vs titles\n\n- At 1B+, **few-shot is the dominant quality lever**: e.g. Qwen2.5-1.5B extraction F1 0.52 → 0.83\n  going 1 → 3 shots; gemma recall 0.65 → 0.92 with 2 shots.\n- **Prefill HURTS extraction** — it forces output on small talk, producing false positives.\n- **System-split** (instructions in the system role) helps models that have a system role.\n- **Greedy >= temperature** for both tasks.\n- **Token biasing** is again a no-op.\n\n### Per-model verdicts (head-to-head, 16-fixture set)\n\n- **Qwen3-1.7B** — most disciplined extraction: returns empty on small talk, no buried-fact leak,\n  preserves language, clean flat JSON. Weaknesses: coarse granularity, missed a multi-turn value\n  update.\n- **Qwen2.5-1.5B** — best extraction granularity (atomic facts), caught the value update, zero\n  small-talk leakage. Weaknesses: weakest consolidation (run-on, no dedup) and one degenerate\n  buried-fact output.\n- **gemma-3-1b** — best consolidation (dedup works, faithful, clean single-memory). Weaknesses: leaks\n  small talk and translated German.\n- **LFM2-1.2B** — solid and fastest to load. Weaknesses: `Label: value` noise, small-talk + buried\n  leaks, a fluffy single-memory summary.\n\n### Recommendation\n\nExtraction favors **precision** (do not pollute long-term memory) → **Qwen3-1.7B is the best single\npick** (its consolidation is good enough). If running a second model for consolidation, **gemma-3-1b**\nwins that task.\n\n**Shipped local options**: `qwen3-1.7b` (recommended), `gemma-3-1b`, `qwen2.5-1.5b`, `lfm2-1.2b`.\n**Default**: `online` (the configured smol model).\n\n### Known Mnemopi parser bugs (surfaced by these experiments)\n\n- `String(item)` produces `[object Object]` on object array items.\n- The line-fallback drops items `<=10` chars, so a correct short fact like `Name: Can` is discarded.\n\n\n## Integration notes\n\n- `providers.tinyModel`, `providers.memoryModel`, and `providers.autoThinkingModel` default to\n  `online`, so existing users get **no downloads or on-device inference cost** unless they opt in.\n- Local inference runs **in a worker** (off the main thread); models are cached on disk and\n  downloaded on first use.\n- The memory local path applies the refined recipes (line-format + small-talk-guarded extraction\n  prompt, hardened consolidation prompt) via Mnemopi prompt overrides; the **online path is\n  unchanged**.\n- `providers.autoThinkingModel` uses the same shipped local options as `providers.memoryModel`.\n",
 	"lsp-config.md": "# LSP configuration in OMP\n\nThis guide explains how to configure language servers for the OMP coding agent.\n\nSource of truth in code:\n\n- Server config type: `packages/coding-agent/src/lsp/types.ts` (`ServerConfig`)\n- Config loader: `packages/coding-agent/src/lsp/config.ts`\n- Built-in server definitions: `packages/coding-agent/src/lsp/defaults.json`\n\n## Auto-detection\n\nWhen no LSP config file is present, OMP auto-detects servers by intersecting two conditions:\n\n1. The project directory contains at least one of the server's `rootMarkers`.\n2. The server binary is available — checked in project-local bin directories first (e.g., `node_modules/.bin/`, `.venv/bin/`), then `$PATH`.\n\nNo configuration is required for common setups. The built-in server list covers most popular languages; see [`defaults.json`](../packages/coding-agent/src/lsp/defaults.json) for the full set.\n\n## Config file locations\n\nOMP merges LSP config from multiple files, lowest to highest priority:\n\n| Priority    | Location                                                                                                                    |\n| ----------- | --------------------------------------------------------------------------------------------------------------------------- |\n| 5 (lowest)  | `~/lsp.json`, `~/.lsp.json`, `~/lsp.yaml`, `~/.lsp.yaml`, `~/lsp.yml`, `~/.lsp.yml`                                         |\n| 4           | Plugin LSP configs (marketplace / `--plugin-dir` roots)                                                                     |\n| 3           | User config dirs: `~/.omp/agent/lsp.*`, `~/.claude/lsp.*`, `~/.codex/lsp.*`, `~/.gemini/lsp.*`                              |\n| 2           | Project config dirs: `<project>/.omp/lsp.*`, `<project>/.claude/lsp.*`, `<project>/.codex/lsp.*`, `<project>/.gemini/lsp.*` |\n| 1 (highest) | Project root: `<project>/lsp.*` and `<project>/.lsp.*`                                                                      |\n\nEach location accepts `.json`, `.yaml`, and `.yml` variants, including hidden-file versions (`.lsp.json`, `.lsp.yaml`, `.lsp.yml`). Files are merged in order: higher-priority files override lower-priority fields for the same server. Servers not mentioned in any override file remain at their built-in defaults.\n\n**Recommended locations:**\n\n- User-wide preferences → `~/.omp/agent/lsp.json`\n- Project-specific overrides → `<project>/.omp/lsp.json`\n\n> **Note:** Auto-detection is skipped only when at least one config file contributes server overrides. A config file that only sets `idleTimeoutMs` still lets OMP auto-detect built-in servers. When server overrides exist, OMP merges them with defaults and then loads servers that have matching `rootMarkers`, an available binary, and are not explicitly `disabled`.\n\n## File shape\n\nBoth JSON and YAML are accepted. The top-level object can use either a `servers` wrapper key or a flat map directly:\n\n```json\n{\n  \"servers\": {\n    \"server-name\": { ... }\n  },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nor (flat, without the `servers` wrapper):\n\n```json\n{\n  \"server-name\": { ... },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nTop-level keys:\n\n- `servers` — map of server name to `ServerConfig` (optional wrapper; flat form is equivalent)\n- `idleTimeoutMs` — shut down idle language servers after this many milliseconds; disabled by default\n\n## ServerConfig fields\n\n| Field             | Type       | Required | Description                                                                                                      |\n| ----------------- | ---------- | -------- | ---------------------------------------------------------------------------------------------------------------- |\n| `command`         | `string`   | yes      | Binary name (resolved via PATH/local bins) or absolute path                                                      |\n| `args`            | `string[]` | no       | Arguments passed to the binary                                                                                   |\n| `fileTypes`       | `string[]` | yes      | File extensions this server handles, e.g. `[\".ts\", \".tsx\"]`                                                      |\n| `rootMarkers`     | `string[]` | yes      | Files/dirs that indicate a project root; glob patterns (e.g. `*.cabal`) are supported                            |\n| `initOptions`     | `object`   | no       | Sent as `initializationOptions` during LSP handshake                                                             |\n| `settings`        | `object`   | no       | Workspace settings pushed via `workspace/didChangeConfiguration`                                                 |\n| `disabled`        | `boolean`  | no       | Set to `true` to disable this server entirely                                                                    |\n| `warmupTimeoutMs` | `number`   | no       | Startup timeout in ms for this server (overrides the global default)                                             |\n| `isLinter`        | `boolean`  | no       | Mark server as linter/formatter only; excluded from type-intelligence operations (hover, go-to-definition, etc.) |\n| `capabilities`    | `object`   | no       | Opt-in server-specific features; see [Capabilities](#capabilities)                                               |\n\n`resolvedCommand` is populated automatically at runtime — do not set it manually.\n\n### Capabilities\n\nThe `capabilities` object enables optional server-specific features that OMP supports on a per-server basis:\n\n```json\n{\n  \"capabilities\": {\n    \"flycheck\": true,\n    \"ssr\": true,\n    \"expandMacro\": true,\n    \"runnables\": true,\n    \"relatedTests\": true\n  }\n}\n```\n\nAll fields are boolean and optional. They are currently used by `rust-analyzer`.\n\n## Common recipes\n\n### Override a built-in server's settings\n\nPartial overrides are merged onto the built-in defaults. You only need to specify the fields you want to change.\n\n```json\n{\n  \"servers\": {\n    \"typescript-language-server\": {\n      \"args\": [\"--stdio\", \"--log-level\", \"4\"]\n    }\n  }\n}\n```\n\n```yaml\nservers:\n  gopls:\n    settings:\n      gopls:\n        gofumpt: false\n        staticcheck: false\n```\n\n### Disable a built-in server\n\n```json\n{\n  \"servers\": {\n    \"eslint\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\n### Register a custom server\n\nNew servers require `command`, `fileTypes`, and `rootMarkers`. All other fields are optional.\n\n```json\n{\n  \"servers\": {\n    \"my-lsp\": {\n      \"command\": \"my-lsp-server\",\n      \"args\": [\"--stdio\"],\n      \"fileTypes\": [\".xyz\"],\n      \"rootMarkers\": [\".xyz-project\", \".git\"]\n    }\n  }\n}\n```\n\n### Set a global idle timeout\n\nShut down language servers that have been inactive for more than five minutes:\n\n```json\n{\n  \"idleTimeoutMs\": 300000\n}\n```\n\n### Disable a server for one project, keep it globally\n\nPlace the override in `<project>/.omp/lsp.json`:\n\n```json\n{\n  \"servers\": {\n    \"pylsp\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\nThe user-level config in `~/.omp/agent/lsp.json` is unaffected; pylsp is only suppressed in this project.\n\n## Built-in server list\n\nThe following servers ship in `defaults.json` and are eligible for auto-detection:\n\n| Server key                    | Language(s)                   | Binary                            |\n| ----------------------------- | ----------------------------- | --------------------------------- |\n| `rust-analyzer`               | Rust                          | `rust-analyzer`                   |\n| `clangd`                      | C, C++, ObjC                  | `clangd`                          |\n| `zls`                         | Zig                           | `zls`                             |\n| `gopls`                       | Go                            | `gopls`                           |\n| `typescript-language-server`  | TypeScript, JavaScript        | `typescript-language-server`      |\n| `denols`                      | TypeScript, JavaScript (Deno) | `deno`                            |\n| `biome`                       | TS/JS/JSON (linter)           | `biome`                           |\n| `eslint`                      | TS/JS/Vue/Svelte (linter)     | `vscode-eslint-language-server`   |\n| `vscode-html-language-server` | HTML                          | `vscode-html-language-server`     |\n| `vscode-css-language-server`  | CSS, SCSS, Less               | `vscode-css-language-server`      |\n| `vscode-json-language-server` | JSON                          | `vscode-json-language-server`     |\n| `tailwindcss`                 | HTML, CSS, TS/JS              | `tailwindcss-language-server`     |\n| `svelte`                      | Svelte                        | `svelteserver`                    |\n| `vue-language-server`         | Vue                           | `vue-language-server`             |\n| `astro`                       | Astro                         | `astro-ls`                        |\n| `pyright`                     | Python                        | `pyright-langserver`              |\n| `basedpyright`                | Python                        | `basedpyright-langserver`         |\n| `pylsp`                       | Python                        | `pylsp`                           |\n| `ruff`                        | Python (linter)               | `ruff`                            |\n| `jdtls`                       | Java                          | `jdtls`                           |\n| `kotlin-lsp`                  | Kotlin                        | `kotlin-lsp`                      |\n| `metals`                      | Scala                         | `metals`                          |\n| `hls`                         | Haskell                       | `haskell-language-server-wrapper` |\n| `ocamllsp`                    | OCaml                         | `ocamllsp`                        |\n| `elixirls`                    | Elixir                        | `elixir-ls`                       |\n| `expert`                      | Elixir                        | `expert`                          |\n| `erlangls`                    | Erlang                        | `erlang_ls`                       |\n| `gleam`                       | Gleam                         | `gleam`                           |\n| `solargraph`                  | Ruby                          | `solargraph`                      |\n| `ruby-lsp`                    | Ruby                          | `ruby-lsp`                        |\n| `rubocop`                     | Ruby (linter)                 | `rubocop`                         |\n| `bashls`                      | Bash, Zsh                     | `bash-language-server`            |\n| `lua-language-server`         | Lua                           | `lua-language-server`             |\n| `intelephense`                | PHP                           | `intelephense`                    |\n| `phpactor`                    | PHP                           | `phpactor`                        |\n| `omnisharp`                   | C#                            | `omnisharp`                       |\n| `yamlls`                      | YAML                          | `yaml-language-server`            |\n| `terraformls`                 | Terraform                     | `terraform-ls`                    |\n| `dockerls`                    | Dockerfile                    | `docker-langserver`               |\n| `helm-ls`                     | Helm                          | `helm_ls`                         |\n| `nixd`                        | Nix                           | `nixd`                            |\n| `nil`                         | Nix                           | `nil`                             |\n| `ols`                         | Odin                          | `ols`                             |\n| `dartls`                      | Dart                          | `dart`                            |\n| `marksman`                    | Markdown                      | `marksman`                        |\n| `texlab`                      | LaTeX                         | `texlab`                          |\n| `graphql`                     | GraphQL                       | `graphql-lsp`                     |\n| `prismals`                    | Prisma                        | `prisma-language-server`          |\n| `vimls`                       | Vim script                    | `vim-language-server`             |\n| `emmet-language-server`       | HTML, CSS, JSX                | `emmet-language-server`           |\n| `sourcekit-lsp`               | Swift                         | `sourcekit-lsp`                   |\n| `swiftlint`                   | Swift (linter)                | `swiftlint`                       |\n| `tlaplus`                     | TLA+                          | `tlapm_lsp`                       |\n",
 	"macos-signing-notarization.md": "# macOS signing & notarization\n\nThe compiled macOS `omp` binaries shipped on GitHub Releases are signed with a\n**Developer ID Application** certificate and **notarized** by Apple. This makes\nthem Gatekeeper-acceptable and is the prerequisite for an official Homebrew\nsubmission (see [#776](https://github.com/can1357/oh-my-pi/issues/776)).\n\nSigning happens in CI, in the `release_binary` job's darwin matrix legs\n(`.github/workflows/ci.yml`), via `scripts/ci-macos-sign.sh`. It **auto-skips**\nuntil the `APPLE_*` repository secrets below are configured, so releases keep\nworking (ad-hoc signed, as before) in the meantime.\n\n## How it works\n\n1. `ci:release:build-binaries` builds and **ad-hoc** signs the binary (so it can\n   run on the build runner).\n2. `scripts/ci-macos-sign.sh` then:\n   - imports the Developer ID cert into a throwaway keychain;\n   - re-signs with `--options runtime --timestamp` (hardened runtime + secure\n     timestamp) and `--entitlements scripts/macos-entitlements.plist`;\n   - runs `--version` and `--smoke-test` under the new signature to fail fast;\n   - notarizes the binary via `notarytool submit --wait`.\n3. `release_github_verify` re-downloads the published arm64 asset and asserts it\n   is **not** ad-hoc, passes `codesign --verify --strict`, and boots cleanly.\n\n### Why the entitlements are mandatory\n\nThe binary is a Bun single-file executable, so the hardened runtime needs:\n\n| Entitlement | Reason |\n| --- | --- |\n| `com.apple.security.cs.allow-jit` | JavaScriptCore JITs at runtime. |\n| `com.apple.security.cs.allow-unsigned-executable-memory` | JSC executable memory pages. |\n| `com.apple.security.cs.disable-library-validation` | omp extracts its native addon (`pi_natives.<triple>.node`) and other optional dylibs to a runtime cache and `dlopen()`s them. They do not share the main binary's Team ID, so without this the hardened runtime aborts with *\"mapping process and mapped file have different Team IDs\"* — breaking effectively every command. |\n\nWithout `disable-library-validation`, a signed+notarized binary signs and\nnotarizes fine but **fails at first real use**. `scripts/ci-macos-sign.sh` runs\n`--smoke-test` after signing specifically to catch this before notarizing.\n\n### Stapling limitation (important)\n\nA bare Mach-O executable **cannot be stapled** (`stapler` only supports\n`.app`/`.pkg`/`.dmg`). The binary is genuinely notarized — `notarytool` returns\n`Accepted` and the ticket exists on Apple's servers keyed to its cdhash — but\nbecause there is no *stapled* ticket, a direct `spctl -a -t exec` assessment\nreports `rejected / source=Unnotarized Developer ID`. This is expected and is\n**not** a signing or credential failure.\n\nWhat this means in practice:\n\n- `curl https://omp.sh/install | sh` — `curl` sets no quarantine bit, so\n  Gatekeeper is never consulted; the binary just runs. ✅\n- Homebrew **formula** installs — Homebrew does not quarantine formula files, so\n  Gatekeeper is never consulted. ✅\n- Anything that **quarantines** the binary (a browser download, or a Homebrew\n  **cask**) and is assessed offline will be blocked, because there is no stapled\n  ticket. For that route, wrap the binary in a stapleable, notarized **`.pkg` or\n  `.dmg`** (`xcrun stapler staple` works on those). That is a follow-up and is\n  **not** required for the `curl`/formula paths.\n\n## Required GitHub secrets\n\nAdd these under **Settings → Secrets and variables → Actions** (repo secrets).\nAll five secrets (cert, password, and API key trio) must be present for\nsigning to engage.\n\n| Secret | What it is |\n| --- | --- |\n| `APPLE_CERTIFICATE_P12` | base64 of the exported Developer ID Application `.p12` (cert + private key). |\n| `APPLE_CERTIFICATE_PASSWORD` | password you set when exporting the `.p12`. |\n| `APPLE_API_KEY_ID` | App Store Connect API **Key ID**. |\n| `APPLE_API_ISSUER_ID` | App Store Connect API **Issuer ID** (UUID). |\n| `APPLE_API_KEY` | base64 of the App Store Connect `.p8` private key. |\n\n### Producing the credential files\n\nDrop these into a working directory (default `~/omp-signing`):\n\n| File | How |\n| --- | --- |\n| `*.p12` | **Keychain Access** → right-click your *Developer ID Application: …* identity (the entry that expands to a cert **with** a private key) → **Export…** → save as `.p12` and set a password. |\n| `p12-password.txt` | the password you just set on the `.p12`. |\n| `AuthKey_<KEYID>.p8` | App Store Connect → **Users and Access → Integrations → App Store Connect API** → create a key (**Account Holder** role also allows API cert creation; **Developer** is enough for notarization) → **download once** (non-recoverable). |\n| `issuer-id.txt` | the **Issuer ID** (UUID) shown above the keys table. |\n| `key-id.txt` | *optional* — the Key ID; otherwise read from the `.p8` filename. |\n\nThe App Store Connect API key is the one credential that **cannot** be minted\nfrom a CLI — it is the bootstrap credential for the API itself, and the `.p8`\ndownloads exactly once. Everything else is local.\n\n### Uploading (no value leaves disk)\n\n`scripts/ci-macos-upload-secrets.sh` validates the files (opens the `.p12` with\nyour password, sanity-checks the `.p8`) and pipes each value to `gh secret set`\nover stdin — no secret is ever printed to the terminal, argv, or shell history:\n\n```sh\nscripts/ci-macos-upload-secrets.sh ~/omp-signing --dry-run   # validate first\nscripts/ci-macos-upload-secrets.sh ~/omp-signing             # upload all five\ngh secret list --repo can1357/oh-my-pi                       # confirm\n```\n\nRe-run it whenever the certificate is renewed.\n\n### Finding your signing identity / Team ID (sanity check)\n\n```sh\nsecurity find-identity -v -p codesigning\n# e.g. \"Developer ID Application: Your Name (TEAMID1234)\"\n```\n\nThe script selects the first `Developer ID Application` identity automatically;\nyou do not need to store the identity string or Team ID as a secret.\n\n## Local dry run\n\nYou can exercise the full sign+notarize path locally (real cert + API key) by\nexporting the five env vars and running:\n\n```sh\nRELEASE_TARGETS=darwin-arm64 bun run ci:release:build-binaries\nAPPLE_CERTIFICATE_P12=… APPLE_CERTIFICATE_PASSWORD=… \\\nAPPLE_API_KEY_ID=… APPLE_API_ISSUER_ID=… APPLE_API_KEY=… \\\n  bash scripts/ci-macos-sign.sh packages/coding-agent/binaries/omp-darwin-arm64\n```\n",
-	"marketplace.md": "# Marketplace plugin system\n\nThe marketplace system lets you discover, install, and manage plugins from Git, local, or direct-catalog sources. It is compatible with the Claude Code plugin registry format.\n\n## Quick start\n\n```\n/marketplace add anthropics/claude-plugins-official\n/marketplace install wordpress.com@claude-plugins-official\n```\n\nIn the TUI, `/marketplace` with no arguments opens the interactive plugin browser. In non-TUI command handling, `/marketplace` lists configured marketplaces; use `/marketplace discover` to browse.\n\n## Concepts\n\nA **marketplace** is a Git repository (or local directory) containing a catalog file at `.claude-plugin/marketplace.json`. The catalog lists available plugins with their sources, descriptions, and metadata.\n\nA **plugin** is a directory containing Claude/OMP plugin content such as skills, commands, agents, hooks, tools, MCP servers, or LSP servers. Extension modules (`package.json` `omp.extensions` entry points) are not loaded from marketplace installs — they only load for npm-installed or `omp plugin link`ed plugins. Plugins are identified by `name@marketplace` (e.g. `code-review@claude-plugins-official`).\n\n**Scopes**: marketplace plugins can be installed at two scopes:\n\n- **user** (default) -- available in all projects, stored in `~/.omp/plugins/installed_plugins.json`\n- **project** -- available only in the active project, stored in the nearest project `.omp/plugins/installed_plugins.json`\n\nEnabled project-scoped installs shadow enabled user-scoped installs of the same plugin. A disabled project install does not shadow the user install.\n\n## Commands\n\n### Interactive mode\n\n| Command        | Effect                                    |\n| -------------- | ----------------------------------------- |\n| `/marketplace` | Open interactive plugin browser (install) |\n\n### Marketplace management\n\n| Command                      | Effect                                       |\n| ---------------------------- | -------------------------------------------- |\n| `/marketplace add <source>`  | Add a marketplace source                     |\n| `/marketplace remove <name>` | Remove a marketplace                         |\n| `/marketplace update [name]` | Re-fetch catalog(s); omit name to update all |\n| `/marketplace list`          | List configured marketplaces                 |\n\n### Plugin operations\n\n| Command                                                                   | Effect                                             |\n| ------------------------------------------------------------------------- | -------------------------------------------------- |\n| `/marketplace discover [marketplace]`                                     | Browse available plugins                           |\n| `/marketplace install [--force] [--scope user\\|project] name@marketplace` | Install a plugin                                   |\n| `/marketplace uninstall [--scope user\\|project] name@marketplace`         | Uninstall a plugin; no args opens the TUI selector |\n| `/marketplace installed`                                                  | List installed marketplace plugins                 |\n| `/marketplace upgrade [--scope user\\|project] [name@marketplace]`         | Upgrade one or all plugins                         |\n| `/plugins list`                                                           | List npm/link and marketplace plugins              |\n| `/plugins enable [--scope user\\|project] name@marketplace`                | Enable a marketplace plugin                        |\n| `/plugins disable [--scope user\\|project] name@marketplace`               | Disable a marketplace plugin                       |\n\n### CLI equivalents\n\nThe same operations are available from the command line:\n\n```\nomp plugin marketplace add <source>\nomp plugin marketplace remove <name>\nomp plugin marketplace update [name]\nomp plugin marketplace list\nomp plugin discover [marketplace]\nomp plugin install [--force] [--scope user|project] name@marketplace\nomp plugin uninstall [--scope user|project] name@marketplace\nomp plugin upgrade [--scope user|project] [name@marketplace]\nomp plugin enable [--scope user|project] name@marketplace\nomp plugin disable [--scope user|project] name@marketplace\n```\n\n## Marketplace sources\n\nWhen you run `/marketplace add <source>`, the system classifies the source:\n\n| Source format                   | Type                                               | Example                                |\n| ------------------------------- | -------------------------------------------------- | -------------------------------------- |\n| `owner/repo`                    | GitHub shorthand                                   | `anthropics/claude-plugins-official`   |\n| `https://...*.json`             | Direct catalog URL                                 | `https://example.com/marketplace.json` |\n| `https://...` / `http://...`    | Git repository unless the URL path ends in `.json` | `https://github.com/org/repo`          |\n| `git@...` / `ssh://...`         | Git repository                                     | `git@github.com:org/repo.git`          |\n| `./path` or `~/path` or `/path` | Local directory                                    | `./my-marketplace`                     |\n\nGit and local sources must contain `.claude-plugin/marketplace.json`. Direct catalog URLs cache only the JSON catalog; plugins in URL-sourced catalogs cannot use relative string sources like `\"./plugins/foo\"`.\n\n## Catalog format (marketplace.json)\n\nA marketplace catalog lives at `.claude-plugin/marketplace.json` in the repository root:\n\n```json\n{\n  \"$schema\": \"https://anthropic.com/claude-code/marketplace.schema.json\",\n  \"name\": \"my-marketplace\",\n  \"owner\": {\n    \"name\": \"Your Name\",\n    \"email\": \"you@example.com\"\n  },\n  \"metadata\": {\n    \"description\": \"A collection of plugins\",\n    \"version\": \"1.0.0\",\n    \"pluginRoot\": \"plugins\"\n  },\n  \"plugins\": [\n    {\n      \"name\": \"my-plugin\",\n      \"description\": \"What this plugin does\",\n      \"source\": \"./my-plugin\",\n      \"category\": \"development\",\n      \"homepage\": \"https://github.com/you/my-plugin\"\n    }\n  ]\n}\n```\n\n### Required fields\n\n| Field        | Description                                                                                                      |\n| ------------ | ---------------------------------------------------------------------------------------------------------------- |\n| `name`       | Marketplace name. Lowercase alphanumeric, hyphens, and dots. Must start and end with alphanumeric. Max 64 chars. |\n| `owner.name` | Marketplace owner name                                                                                           |\n| `plugins`    | Array of plugin entries                                                                                          |\n\nTop-level `metadata.description`, `metadata.version`, and `metadata.pluginRoot` are optional. When `metadata.pluginRoot` is set, it is prepended to relative plugin `source` paths.\n\n### Plugin entry fields\n\n| Field         | Required | Description                                                                             |\n| ------------- | -------- | --------------------------------------------------------------------------------------- |\n| `name`        | yes      | Plugin name (same rules as marketplace name)                                            |\n| `source`      | yes      | Where to find the plugin (see below)                                                    |\n| `description` | no       | Short description                                                                       |\n| `version`     | no       | Version string; install version falls back to plugin manifest, source SHA, then `0.0.0` |\n| `author`      | no       | `{ name, email? }`                                                                      |\n| `homepage`    | no       | URL                                                                                     |\n| `repository`  | no       | Repository URL/string                                                                   |\n| `license`     | no       | License string                                                                          |\n| `keywords`    | no       | Array of string keywords                                                                |\n| `category`    | no       | Category string (e.g. `development`, `productivity`, `security`)                        |\n| `tags`        | no       | Array of string tags                                                                    |\n| `strict`      | no       | Boolean                                                                                 |\n| `commands`    | no       | Slash commands provided                                                                 |\n| `agents`      | no       | Agents provided                                                                         |\n| `hooks`       | no       | Hook definitions                                                                        |\n| `mcpServers`  | no       | MCP server definitions                                                                  |\n| `lspServers`  | no       | LSP server definitions or path; copied to `.lsp.json` on install                        |\n\n### Plugin source formats\n\nThe `source` field supports these formats. String sources must start with `./` and are resolved inside the marketplace root, after optional `metadata.pluginRoot` is prepended:\n\n**Relative path** (within the marketplace repo):\n\n```json\n\"source\": \"./my-plugin\"\n```\n\n**Git repository URL**:\n\n```json\n\"source\": {\n  \"source\": \"url\",\n  \"url\": \"https://github.com/org/repo.git\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**GitHub shorthand**:\n\n```json\n\"source\": {\n  \"source\": \"github\",\n  \"repo\": \"org/repo\",\n  \"ref\": \"main\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**Git subdirectory** (monorepo):\n\n```json\n\"source\": {\n  \"source\": \"git-subdir\",\n  \"url\": \"https://github.com/org/monorepo.git\",\n  \"path\": \"plugins/my-plugin\",\n  \"ref\": \"main\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**npm package** (parsed but not installable yet):\n\n```json\n\"source\": {\n  \"source\": \"npm\",\n  \"package\": \"@scope/my-plugin\",\n  \"version\": \"1.0.0\"\n}\n```\n\nCurrent installer behavior rejects npm marketplace sources with `npm plugin sources are not yet supported`; use relative, GitHub, URL, or git-subdir sources.\n\n## On-disk layout\n\n```\n~/.omp/\n  marketplaces.json              # Registry of added marketplaces\n  plugins/\n    installed_plugins.json       # User-scoped marketplace plugins (version: 2)\n    cache/\n      marketplaces/<name>/       # Cached marketplace clone/catalog\n      plugins/<marketplace>___<plugin>___<version>/  # Cached plugin directories\n\n<project>/.omp/\n  plugins/\n    installed_plugins.json       # Project-scoped marketplace plugins (version: 2)\n```\n\n## Naming rules\n\nMarketplace and plugin names must:\n\n- Start and end with a lowercase letter or digit\n- Contain only lowercase letters, digits, hyphens, and dots\n- Be at most 64 characters\n\nPlugin IDs (`name@marketplace`) must be at most 128 characters total.\n\nValid examples: `my-plugin`, `code-review`, `wordpress.com`, `ai-firstify`\nInvalid examples: `-bad`, `bad-`, `.bad`, `Bad`, `under_score`\n",
+	"marketplace.md": "# Marketplace plugin system\n\nThe marketplace system lets you discover, install, and manage plugins from Git, local, or direct-catalog sources. It is compatible with the Claude Code plugin registry format.\n\n## Quick start\n\n```\n/marketplace add anthropics/claude-plugins-official\n/marketplace install wordpress.com@claude-plugins-official\n```\n\nIn the TUI, `/marketplace` with no arguments opens the interactive plugin browser. In non-TUI command handling, `/marketplace` lists configured marketplaces; use `/marketplace discover` to browse.\n\n## Concepts\n\nA **marketplace** is a Git repository (or local directory) containing a catalog file at `.omp-plugin/marketplace.json` (preferred) or `.claude-plugin/marketplace.json` (Claude Code-compatible fallback). The catalog lists available plugins with their sources, descriptions, and metadata.\n\nA **plugin** is a directory containing Claude/OMP plugin content such as skills, commands, agents, hooks, tools, MCP servers, or LSP servers. Extension modules (`package.json` `omp.extensions` entry points) are not loaded from marketplace installs — they only load for npm-installed or `omp plugin link`ed plugins. Plugins are identified by `name@marketplace` (e.g. `code-review@claude-plugins-official`).\n\n**Scopes**: marketplace plugins can be installed at two scopes:\n\n- **user** (default) -- available in all projects, stored in `~/.omp/plugins/installed_plugins.json`\n- **project** -- available only in the active project, stored in the nearest project `.omp/plugins/installed_plugins.json`\n\nEnabled project-scoped installs shadow enabled user-scoped installs of the same plugin. A disabled project install does not shadow the user install.\n\n## Commands\n\n### Interactive mode\n\n| Command        | Effect                                    |\n| -------------- | ----------------------------------------- |\n| `/marketplace` | Open interactive plugin browser (install) |\n\n### Marketplace management\n\n| Command                      | Effect                                       |\n| ---------------------------- | -------------------------------------------- |\n| `/marketplace add <source>`  | Add a marketplace source                     |\n| `/marketplace remove <name>` | Remove a marketplace                         |\n| `/marketplace update [name]` | Re-fetch catalog(s); omit name to update all |\n| `/marketplace list`          | List configured marketplaces                 |\n\n### Plugin operations\n\n| Command                                                                   | Effect                                             |\n| ------------------------------------------------------------------------- | -------------------------------------------------- |\n| `/marketplace discover [marketplace]`                                     | Browse available plugins                           |\n| `/marketplace install [--force] [--scope user\\|project] name@marketplace` | Install a plugin                                   |\n| `/marketplace uninstall [--scope user\\|project] name@marketplace`         | Uninstall a plugin; no args opens the TUI selector |\n| `/marketplace installed`                                                  | List installed marketplace plugins                 |\n| `/marketplace upgrade [--scope user\\|project] [name@marketplace]`         | Upgrade one or all plugins                         |\n| `/plugins list`                                                           | List npm/link and marketplace plugins              |\n| `/plugins enable [--scope user\\|project] name@marketplace`                | Enable a marketplace plugin                        |\n| `/plugins disable [--scope user\\|project] name@marketplace`               | Disable a marketplace plugin                       |\n\n### CLI equivalents\n\nThe same operations are available from the command line:\n\n```\nomp plugin marketplace add <source>\nomp plugin marketplace remove <name>\nomp plugin marketplace update [name]\nomp plugin marketplace list\nomp plugin discover [marketplace]\nomp plugin install [--force] [--scope user|project] name@marketplace\nomp plugin uninstall [--scope user|project] name@marketplace\nomp plugin upgrade [--scope user|project] [name@marketplace]\nomp plugin enable [--scope user|project] name@marketplace\nomp plugin disable [--scope user|project] name@marketplace\n```\n\n## Marketplace sources\n\nWhen you run `/marketplace add <source>`, the system classifies the source:\n\n| Source format                   | Type                                               | Example                                |\n| ------------------------------- | -------------------------------------------------- | -------------------------------------- |\n| `owner/repo`                    | GitHub shorthand                                   | `anthropics/claude-plugins-official`   |\n| `https://...*.json`             | Direct catalog URL                                 | `https://example.com/marketplace.json` |\n| `https://...` / `http://...`    | Git repository unless the URL path ends in `.json` | `https://github.com/org/repo`          |\n| `git@...` / `ssh://...`         | Git repository                                     | `git@github.com:org/repo.git`          |\n| `./path` or `~/path` or `/path` | Local directory                                    | `./my-marketplace`                     |\n\nGit and local sources must contain a catalog at `.omp-plugin/marketplace.json` (preferred) or `.claude-plugin/marketplace.json` (Claude Code-compatible fallback). Direct catalog URLs cache only the JSON catalog; plugins in URL-sourced catalogs cannot use relative string sources like `\"./plugins/foo\"`.\n\n## Catalog format (marketplace.json)\n\nA marketplace catalog lives at `.omp-plugin/marketplace.json` in the repository root. When omp is the only intended consumer, prefer this path. To remain Claude Code-compatible (omp loads the same shape from either path), publish at `.claude-plugin/marketplace.json` instead — omp uses it as a fallback when `.omp-plugin/marketplace.json` is absent. A repository may ship both: omp reads the `.omp-plugin/` copy, Claude Code reads the `.claude-plugin/` copy. Same catalog format either way:\n\n```json\n{\n  \"$schema\": \"https://anthropic.com/claude-code/marketplace.schema.json\",\n  \"name\": \"my-marketplace\",\n  \"owner\": {\n    \"name\": \"Your Name\",\n    \"email\": \"you@example.com\"\n  },\n  \"metadata\": {\n    \"description\": \"A collection of plugins\",\n    \"version\": \"1.0.0\",\n    \"pluginRoot\": \"plugins\"\n  },\n  \"plugins\": [\n    {\n      \"name\": \"my-plugin\",\n      \"description\": \"What this plugin does\",\n      \"source\": \"./my-plugin\",\n      \"category\": \"development\",\n      \"homepage\": \"https://github.com/you/my-plugin\"\n    }\n  ]\n}\n```\n\n### Required fields\n\n| Field        | Description                                                                                                      |\n| ------------ | ---------------------------------------------------------------------------------------------------------------- |\n| `name`       | Marketplace name. Lowercase alphanumeric, hyphens, and dots. Must start and end with alphanumeric. Max 64 chars. |\n| `owner.name` | Marketplace owner name                                                                                           |\n| `plugins`    | Array of plugin entries                                                                                          |\n\nTop-level `metadata.description`, `metadata.version`, and `metadata.pluginRoot` are optional. When `metadata.pluginRoot` is set, it is prepended to relative plugin `source` paths.\n\n### Plugin entry fields\n\n| Field         | Required | Description                                                                             |\n| ------------- | -------- | --------------------------------------------------------------------------------------- |\n| `name`        | yes      | Plugin name (same rules as marketplace name)                                            |\n| `source`      | yes      | Where to find the plugin (see below)                                                    |\n| `description` | no       | Short description                                                                       |\n| `version`     | no       | Version string; install version falls back to plugin manifest, source SHA, then `0.0.0` |\n| `author`      | no       | `{ name, email? }`                                                                      |\n| `homepage`    | no       | URL                                                                                     |\n| `repository`  | no       | Repository URL/string                                                                   |\n| `license`     | no       | License string                                                                          |\n| `keywords`    | no       | Array of string keywords                                                                |\n| `category`    | no       | Category string (e.g. `development`, `productivity`, `security`)                        |\n| `tags`        | no       | Array of string tags                                                                    |\n| `strict`      | no       | Boolean                                                                                 |\n| `commands`    | no       | Slash commands provided                                                                 |\n| `agents`      | no       | Agents provided                                                                         |\n| `hooks`       | no       | Hook definitions                                                                        |\n| `mcpServers`  | no       | MCP server definitions                                                                  |\n| `lspServers`  | no       | LSP server definitions or path; copied to `.lsp.json` on install                        |\n\n### Plugin source formats\n\nThe `source` field supports these formats. String sources must start with `./` and are resolved inside the marketplace root, after optional `metadata.pluginRoot` is prepended:\n\n**Relative path** (within the marketplace repo):\n\n```json\n\"source\": \"./my-plugin\"\n```\n\n**Git repository URL**:\n\n```json\n\"source\": {\n  \"source\": \"url\",\n  \"url\": \"https://github.com/org/repo.git\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**GitHub shorthand**:\n\n```json\n\"source\": {\n  \"source\": \"github\",\n  \"repo\": \"org/repo\",\n  \"ref\": \"main\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**Git subdirectory** (monorepo):\n\n```json\n\"source\": {\n  \"source\": \"git-subdir\",\n  \"url\": \"https://github.com/org/monorepo.git\",\n  \"path\": \"plugins/my-plugin\",\n  \"ref\": \"main\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**npm package** (parsed but not installable yet):\n\n```json\n\"source\": {\n  \"source\": \"npm\",\n  \"package\": \"@scope/my-plugin\",\n  \"version\": \"1.0.0\"\n}\n```\n\nCurrent installer behavior rejects npm marketplace sources with `npm plugin sources are not yet supported`; use relative, GitHub, URL, or git-subdir sources.\n\n## On-disk layout\n\n```\n~/.omp/\n  marketplaces.json              # Registry of added marketplaces\n  plugins/\n    installed_plugins.json       # User-scoped marketplace plugins (version: 2)\n    cache/\n      marketplaces/<name>/       # Cached marketplace clone/catalog\n      plugins/<marketplace>___<plugin>___<version>/  # Cached plugin directories\n\n<project>/.omp/\n  plugins/\n    installed_plugins.json       # Project-scoped marketplace plugins (version: 2)\n```\n\n## Naming rules\n\nMarketplace and plugin names must:\n\n- Start and end with a lowercase letter or digit\n- Contain only lowercase letters, digits, hyphens, and dots\n- Be at most 64 characters\n\nPlugin IDs (`name@marketplace`) must be at most 128 characters total.\n\nValid examples: `my-plugin`, `code-review`, `wordpress.com`, `ai-firstify`\nInvalid examples: `-bad`, `bad-`, `.bad`, `Bad`, `under_score`\n",
 	"mcp-config.md": "# MCP configuration in OMP\n\nThis guide explains how to add, edit, and validate MCP servers for the OMP coding agent.\n\nSource of truth in code:\n\n- Runtime config types: `packages/coding-agent/src/mcp/types.ts`\n- Config writer: `packages/coding-agent/src/mcp/config-writer.ts`\n- Loader + validation: `packages/coding-agent/src/mcp/config.ts`\n- Standalone `mcp.json` discovery: `packages/coding-agent/src/discovery/mcp-json.ts`\n- Schema: `packages/coding-agent/src/config/mcp-schema.json`\n\n## Preferred config locations\n\nOMP can discover MCP servers from multiple tools (`.claude/`, `.cursor/`, `.vscode/`, `opencode.json`, and more), but for OMP-native configuration you should usually use one of these primary files:\n\n- Project: `.omp/mcp.json`\n- User: `~/.omp/agent/mcp.json` (or `~/.omp/profiles/<name>/agent/mcp.json` when a named profile is active — see [Profiles](#profiles))\n\nThe native provider also reads `.omp/.mcp.json` and `~/.omp/agent/.mcp.json` for compatibility, but OMP writes to the primary `mcp.json` paths above.\n\nOMP also accepts fallback standalone files in the project root:\n\n- `mcp.json`\n- `.mcp.json`\n\nUse `.omp/mcp.json` or `~/.omp/agent/mcp.json` when you want OMP to own the configuration. Use root `mcp.json` / `.mcp.json` only when you want a portable fallback file that other MCP clients may also read.\n\n### Profiles\n\nNamed profiles (`omp --profile <name>`, the `--alias` shortcut, or `OMP_PROFILE`/`PI_PROFILE`) isolate user-level MCP config. When a profile is active, the **user** scope resolves to the profile's agent directory instead of the default one:\n\n- Default profile: `~/.omp/agent/mcp.json`\n- Profile `<name>`: `~/.omp/profiles/<name>/agent/mcp.json`\n\nDiscovery, the `/mcp` commands, and the config writer all follow the active profile, so a profile sees **only** its own user-level servers — never the default profile's `~/.omp/agent/mcp.json`. Add a server to a profile by launching under it (`omp --profile <name>`) and running `/mcp add` → User level, or by editing `~/.omp/profiles/<name>/agent/mcp.json` directly.\n\nProject-scoped MCP config (`.omp/mcp.json`) is keyed to the working directory, not the profile, so it applies under every profile. External-tool configs (`.claude/`, `.cursor/`, etc.) are also profile-independent because they belong to those tools rather than to an OMP profile.\n\nMCP follows the same profile rules as the rest of OMP-native config; see [Configuration Discovery → Profiles](./config-usage.md#profiles).\n\n## Add a schema reference\n\nAdd this line at the top of the file for editor autocomplete and validation:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {}\n}\n```\n\nOMP now writes this automatically when `/mcp add`, `/mcp enable`, `/mcp disable`, `/mcp reauth`, or other config-writing flows create or update an OMP-managed MCP file.\n\n## File shape\n\nOMP supports this top-level structure:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"server-name\": {\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"some-mcp-server\"]\n    }\n  },\n  \"disabledServers\": [\"server-name\"]\n}\n```\n\nTop-level keys:\n\n- `$schema` — optional JSON Schema URL for tooling\n- `mcpServers` — map of server name to server config\n- `disabledServers` — user-level denylist used to turn off discovered servers by name; runtime loading reads this list from the active profile's user MCP file (`~/.omp/agent/mcp.json`, or `~/.omp/profiles/<name>/agent/mcp.json` under a named profile)\n\nServer names must match `^[a-zA-Z0-9_.-]{1,100}$`.\n\n## Supported server fields\n\nShared fields for every transport:\n\n- `enabled?: boolean` — skip this server when `false`\n- `timeout?: number` — MCP request timeout in milliseconds; `0` disables client-side MCP timeouts\n- `auth?: { ... }` — auth metadata used by OMP for OAuth/API-key flows\n- `oauth?: { ... }` — explicit OAuth client settings used during auth/reauth\n\nSet `OMP_MCP_TIMEOUT_MS=0` to disable the client-side timeout for every MCP server in the current process. Set it to a positive millisecond value, such as `OMP_MCP_TIMEOUT_MS=120000`, to apply one global timeout without editing each server entry.\n\n### `stdio` transport\n\n`stdio` is the default when `type` is omitted.\n\nRequired:\n\n- `command: string`\n\nOptional:\n\n- `type?: \"stdio\"`\n- `args?: string[]`\n- `env?: Record<string, string>`\n- `cwd?: string`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol/server-filesystem\",\n        \"/Users/alice/projects\",\n        \"/Users/alice/Documents\"\n      ]\n    }\n  }\n}\n```\n\nThis follows the official Filesystem MCP server package (`@modelcontextprotocol/server-filesystem`).\n\n### `http` transport\n\nRequired:\n\n- `type: \"http\"`\n- `url: string`\n\nOptional:\n\n- `headers?: Record<string, string>`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\"\n    }\n  }\n}\n```\n\nThis matches GitHub's hosted GitHub MCP server endpoint.\n\n### `sse` transport\n\nRequired:\n\n- `type: \"sse\"`\n- `url: string`\n\nOptional:\n\n- `headers?: Record<string, string>`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"legacy-remote\": {\n      \"type\": \"sse\",\n      \"url\": \"https://example.com/mcp/sse\"\n    }\n  }\n}\n```\n\n`sse` is still supported for compatibility, but the MCP spec now prefers Streamable HTTP (`type: \"http\"`) for new servers.\n\n## Auth fields\n\nOMP understands two auth-related objects.\n\n### `auth`\n\n```json\n{\n  \"type\": \"oauth\" | \"apikey\",\n  \"credentialId\": \"optional-stored-credential-id\",\n  \"tokenUrl\": \"optional-token-endpoint\",\n  \"clientId\": \"optional-client-id\",\n  \"clientSecret\": \"optional-client-secret\",\n  \"resource\": \"optional-mcp-resource-uri\"\n}\n```\n\nUse this when OMP should remember how to rehydrate credentials for a server.\n\nYou normally do not need to write this block: when OMP completes an OAuth flow\nfor an `http`/`sse` server it stores the credential under a deterministic id\nderived from the active profile and server URL\n(`mcp_oauth:profile:<profile>:<url>`), with the refresh material embedded. Any\nconfig that points at the same URL — including a *definition-only* entry in a\nshared project `mcp.json` with no `auth` block at all — resolves the active\nprofile's own credential automatically, including when auth storage is backed by\na shared auth broker. This is what makes project-scoped servers safe across\nprofiles: commit the definition, and each profile authorizes (and stays signed\nin as) its own account via `/mcp reauth <name>`. An explicit `credentialId` is\nstill honored when it resolves; if it points at another profile's row, OMP falls\nback to the profile-scoped url-keyed binding.\n\n`/mcp reauth` on a definition-only entry leaves the file untouched — the\ncredential (refresh material included) lives entirely in the active profile's\nauth storage (local `agent.db` or broker), so a committed project config never\npicks up local auth state. An explicitly\nconfigured `Authorization` header always wins over the url-keyed binding.\n\nThe binding is per profile but not per project: once a profile has authorized\na URL, *any* checkout whose `mcp.json` defines a server at that URL connects\nwith that profile's credential automatically. Committed MCP definitions are\ntrusted input — the same already applies to `stdio` entries, which run\narbitrary commands — so review a repository's `mcp.json` before opening it\nwith a profile that holds credentials you care about, or use a dedicated\nprofile for untrusted checkouts.\n\n### `oauth`\n\n```json\n{\n  \"clientId\": \"...\",\n  \"clientSecret\": \"...\",\n  \"redirectUri\": \"...\",\n  \"callbackPort\": 3334,\n  \"callbackPath\": \"/oauth/callback\",\n  \"prompt\": \"consent\"\n}\n```\n\nUse this when the MCP server requires explicit OAuth client settings.\n\n`prompt` controls the OAuth `prompt` parameter sent with the authorization request. It defaults to `\"consent\"` so the provider always shows its consent/account screen — without it, a provider with an active browser session silently re-approves the same account, making it impossible to switch accounts or workspaces when reauthorizing (e.g. to use a different Linear workspace per OMP profile). Set it to `\"\"` to omit the parameter for providers that reject it, or to another value the provider understands (e.g. `\"select_account\"`).\n\nSlack is the clearest current example. Slack's MCP server is hosted at `https://mcp.slack.com/mcp`, uses Streamable HTTP, and requires confidential OAuth with your Slack app's client credentials.\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"slack\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.slack.com/mcp\",\n      \"oauth\": {\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      },\n      \"auth\": {\n        \"type\": \"oauth\",\n        \"tokenUrl\": \"https://slack.com/api/oauth.v2.user.access\",\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      }\n    }\n  }\n}\n```\n\nRelevant Slack endpoints from Slack's docs:\n\n- MCP endpoint: `https://mcp.slack.com/mcp`\n- Authorization endpoint: `https://slack.com/oauth/v2_user/authorize`\n- Token endpoint: `https://slack.com/api/oauth.v2.user.access`\n\n## Common copy-paste examples\n\n### Filesystem server via stdio\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol/server-filesystem\",\n        \"/absolute/path/one\",\n        \"/absolute/path/two\"\n      ]\n    }\n  }\n}\n```\n\n### GitHub hosted server via HTTP\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\"\n    }\n  }\n}\n```\n\n### GitHub local server via Docker\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"docker\",\n      \"args\": [\n        \"run\",\n        \"-i\",\n        \"--rm\",\n        \"-e\",\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\",\n        \"ghcr.io/github/github-mcp-server\"\n      ],\n      \"env\": {\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"\n      }\n    }\n  }\n}\n```\n\nThis matches GitHub's official local Docker image `ghcr.io/github/github-mcp-server`.\n\n### Slack hosted server via OAuth\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"slack\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.slack.com/mcp\",\n      \"oauth\": {\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      },\n      \"auth\": {\n        \"type\": \"oauth\",\n        \"tokenUrl\": \"https://slack.com/api/oauth.v2.user.access\",\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      }\n    }\n  }\n}\n```\n\n## Secrets and variable resolution\n\nThis is the part that usually trips people up.\n\n### Discovery-time `${...}` expansion\n\nOMP expands `${VAR}` and `${VAR:-default}` placeholders while discovering MCP configs from OMP-native files and standalone fallback files. Expansion applies recursively to string values in `command`, `args`, `env`, `cwd`, `url`, `headers`, `auth`, and `oauth`; unresolved placeholders remain literal strings.\n\nExample:\n\n```json\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\",\n      \"headers\": {\n        \"Authorization\": \"Bearer ${GITHUB_TOKEN}\"\n      }\n    }\n  }\n}\n```\n\n### Pre-connect env/header resolution\n\nBefore OMP launches a stdio server or makes an HTTP/SSE request, it resolves stdio `env` values and HTTP/SSE `headers` values like this:\n\n1. If a value starts with `!`, OMP runs the rest as a shell command with a 10s timeout and uses trimmed stdout.\n2. If the command fails, times out, or prints only whitespace, that `env`/`headers` entry is omitted.\n3. Otherwise OMP checks whether the value names an environment variable.\n4. If that environment variable is set to a non-empty value, OMP uses the environment value; otherwise it uses the string literally.\n\nExamples:\n\n```json\n{\n  \"env\": {\n    \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"\n  },\n  \"headers\": {\n    \"X-MCP-Insiders\": \"true\"\n  }\n}\n```\n\nThat means this is valid and convenient for local secrets:\n\n- `\"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"` → copy from the current shell environment\n- `\"Authorization\": \"Bearer hardcoded-token\"` → use the literal value\n- `\"Authorization\": \"!printf 'Bearer %s' \\\"$GITHUB_TOKEN\\\"\"` → build the header from a command\n\n## `disabledServers`\n\n`disabledServers` is read from the user config file (`~/.omp/agent/mcp.json`) when a server is discovered from any source and you want OMP to ignore it without editing that other tool's config.\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"disabledServers\": [\"github\", \"slack\"]\n}\n```\n\n## `/mcp add` vs editing JSON directly\n\nUse `/mcp add` when you want guided setup.\n\nUse direct JSON editing when:\n\n- you need a transport or auth option the wizard does not prompt for yet\n- you want to paste a server definition from another MCP client\n- you want schema-backed validation in your editor\n\nAfter editing, use:\n\n- `/mcp reload` to rediscover and reconnect servers in the current session\n- `/mcp list` to see which config file a server came from\n- `/mcp test <name>` to test a single server\n- `/mcp reconnect <name>` to reconnect one server without rediscovering all configs\n- `/mcp resources`, `/mcp prompts`, and `/mcp notifications` to inspect non-tool MCP capabilities\n\n## Validation rules OMP enforces\n\nFrom `validateServerConfig()` in `packages/coding-agent/src/mcp/config.ts`:\n\n- `stdio` requires `command`\n- `http` and `sse` require `url`\n- a server cannot set both `command` and `url`\n- unknown `type` values are rejected\n\nPractical implications:\n\n- Omitting `type` means `stdio`\n- If you paste a remote server config and forget `\"type\": \"http\"`, OMP will treat it as `stdio` and complain that `command` is missing\n- `sse` remains valid for compatibility, but new hosted servers should usually be configured as `http`\n\n## Discovery and precedence\n\nOMP does not merge duplicate server definitions across files. Discovery providers are prioritized, and the higher-priority definition wins. Separately, `disabledServers` from `~/.omp/agent/mcp.json` can suppress a discovered server by name.\n\nIn practice:\n\n- prefer `.omp/mcp.json` or `~/.omp/agent/mcp.json` when you want an OMP-specific override\n- keep server names unique across tools when possible\n- use `disabledServers` in the user config when a third-party config keeps reintroducing a server you do not want\n\n## Troubleshooting\n\n### `Server \"name\": stdio server requires \"command\" field`\n\nYou probably omitted `type: \"http\"` on a remote server.\n\n### `Server \"name\": both \"command\" and \"url\" are set`\n\nPick one transport. OMP treats `command` as stdio and `url` as http/sse.\n\n### `/mcp add` worked but the server still does not connect\n\nThe JSON is valid, but the server may still be unreachable. Use `/mcp test <name>` and check whether:\n\n- the binary or Docker image exists\n- required environment variables are set\n- the remote URL is reachable\n- the OAuth or API token is valid\n\n### The server exists in another tool's config but not in OMP\n\nRun `/mcp list`. OMP discovers many third-party MCP files, but project-level loading can also be disabled via the `mcp.enableProjectConfig` setting, and a user-level `disabledServers` entry can suppress a server by name.\n\n## References\n\n- MCP transport spec: https://modelcontextprotocol.io/specification/2025-03-26/basic/transports\n- Filesystem server package: https://www.npmjs.com/package/@modelcontextprotocol/server-filesystem\n- GitHub MCP server: https://github.com/github/github-mcp-server\n- Slack MCP server docs: https://docs.slack.dev/ai/slack-mcp-server/\n",
 	"mcp-protocol-transports.md": "# MCP Protocol and Transport Internals\n\nThis document describes how coding-agent implements MCP JSON-RPC messaging and how protocol concerns are split from transport concerns.\n\n## Scope\n\nCovers:\n\n- JSON-RPC request/response and notification flow\n- Server-to-client request handling (`ping`, `roots/list`)\n- Request correlation and lifecycle for stdio and HTTP/SSE transports\n- Timeout, cancellation, and auth-refresh behavior\n- Error propagation and malformed payload handling\n- Transport selection boundaries (`stdio` vs `http`/`sse`)\n- Which reconnect/retry responsibilities are transport-level vs manager/tool-bridge-level\n\nDoes not cover extension authoring UX or command UI.\n\n## Implementation files\n\n- [`src/mcp/types.ts`](../packages/coding-agent/src/mcp/types.ts)\n- [`src/mcp/transports/stdio.ts`](../packages/coding-agent/src/mcp/transports/stdio.ts)\n- [`src/mcp/transports/http.ts`](../packages/coding-agent/src/mcp/transports/http.ts)\n- [`src/mcp/transports/index.ts`](../packages/coding-agent/src/mcp/transports/index.ts)\n- [`src/mcp/json-rpc.ts`](../packages/coding-agent/src/mcp/json-rpc.ts)\n- [`src/mcp/client.ts`](../packages/coding-agent/src/mcp/client.ts)\n- [`src/mcp/manager.ts`](../packages/coding-agent/src/mcp/manager.ts)\n\n## Layer boundaries\n\n### Protocol layer (JSON-RPC + MCP methods)\n\n- Message shapes are defined in `types.ts` (`JsonRpcRequest`, `JsonRpcNotification`, `JsonRpcResponse`, `JsonRpcMessage`).\n- MCP client logic (`client.ts`) decides method order and session handshake:\n  1. `initialize` request\n  2. for HTTP/SSE transports, start the optional background SSE listener after the initialize response has established any session id\n  3. `notifications/initialized` notification\n  4. method calls like `tools/list`, `tools/call`\n\n### Transport layer (`MCPTransport`)\n\n`MCPTransport` abstracts delivery and lifecycle:\n\n- `request(method, params, options?) -> Promise<T>`\n- `notify(method, params?) -> Promise<void>`\n- `close()`\n- `connected`\n- optional callbacks: `onClose`, `onError`, `onNotification`, `onRequest`\n\nTransport implementations own framing and I/O details:\n\n- `StdioTransport`: newline-delimited JSON over subprocess stdio\n- `HttpTransport`: JSON-RPC over HTTP POST, with optional SSE responses/listening\n\n### Manager/client wiring\n\n`connectToServer()` always installs an `onRequest` handler for standard server-to-client requests. `MCPManager` installs notification handlers, OAuth refresh hooks for HTTP OAuth servers, and `onClose` reconnect handling for managed connections.\n\n## Transport selection\n\n`client.ts:createTransport()` chooses transport from config:\n\n- `type` omitted or `\"stdio\"` -> `createStdioTransport`\n- `\"http\"` or `\"sse\"` -> `createHttpTransport`\n\n`\"sse\"` is treated as an HTTP transport variant (same class), not a separate transport implementation.\n\n## JSON-RPC message flow and correlation\n\n## Request IDs\n\nEach transport generates per-request IDs with `Snowflake.next()`. IDs are transport-local correlation tokens.\n\n## Stdio correlation path\n\n- Outbound request is serialized as one JSON object + `\\n`.\n- `#pendingRequests: Map<id, {resolve,reject}>` stores in-flight requests.\n- Read loop parses JSONL from stdout and calls `#handleMessage`.\n- If inbound message has matching `id`, request resolves/rejects.\n- If inbound message has `method` and no `id`, treated as notification and sent to `onNotification`.\n- If inbound message has both `method` and `id`, treated as a server-to-client request and answered through `onRequest`; without a handler the transport replies with JSON-RPC `-32601 Method not found`.\n\nUnknown response IDs are ignored (no rejection, no error callback).\n\n## HTTP correlation path\n\n- Outbound request is HTTP `POST` with JSON body and generated `id`.\n- Non-SSE response path: parse one JSON-RPC response and return `result`/throw on `error`.\n- SSE response path (`Content-Type: text/event-stream`): stream events, return first message whose `id` matches expected request ID and has `result` or `error`.\n- SSE messages with `method` and no `id` are treated as notifications.\n- SSE messages with both `method` and `id` are treated as server-to-client requests and answered with a POSTed JSON-RPC response.\n\nIf SSE stream ends before matching response, request fails with `No response received for request ID ...`. After the matching response is captured, the transport drains remaining SSE messages in the background.\n\n## Notifications\n\nClient emits JSON-RPC notifications via `transport.notify(...)`.\n\n- Stdio: writes notification frame to stdin (`jsonrpc`, `method`, `params`) plus newline via `writeFrame()`; a failed write closes the transport and throws.\n- HTTP: sends POST body without `id`; success accepts `2xx` or `202 Accepted`.\n\nServer-initiated notifications are surfaced through transport `onNotification`; `MCPManager` consumes known MCP list/update notifications and can forward all notifications through its own callback.\n\n## Stdio transport internals\n\n## Lifecycle and state transitions\n\n- Initial: `connected=false`, `process=null`, pending map empty\n- `connect()`:\n  - spawn subprocess with configured command/args/env/cwd\n  - mark connected\n  - start stdout read loop (`readJsonl`)\n  - start stderr loop (read/discard; currently silent)\n- `close()`:\n  - `#handleClose()`: mark disconnected, reject all pending requests (`Transport closed`), emit `onClose`\n  - kill subprocess\n  - await read loop shutdown\n\nIf read loop exits unexpectedly, `finally` triggers `#handleClose()` which performs the same pending-request rejection and close callback.\n\n## Timeout and cancellation\n\nPer request:\n\n- timeout from `resolveMCPTimeoutMs`: `OMP_MCP_TIMEOUT_MS` env override, else `config.timeout ?? 30000`; `0` disables\n- optional `AbortSignal` from caller\n- abort and timeout both reject the pending promise and clean map entry\n\nCancellation is local only: transport does not send protocol-level cancellation notification to the server.\n\n## Malformed payload handling\n\nIn read loop:\n\n- each parsed JSONL line is passed to `#handleMessage` in `try/catch`\n- malformed/invalid message handling exceptions are dropped (`Skip malformed lines` comment)\n- loop continues, so one bad message does not kill the connection\n\nIf the underlying stream parser throws, `onError` is invoked (when still connected), then connection closes.\n\n## Disconnect/failure behavior\n\nWhen process exits or stream closes:\n\n- all in-flight requests are rejected with `Transport closed`\n- no automatic restart or reconnect\n- higher layers must reconnect by creating a new transport\n\n## Backpressure/streaming notes\n\n- `request()` awaits `stdin.write()` + `flush()` so broken-pipe failures reject the request; `notify()` writes through `writeFrame()`, which does not await and neutralizes async EPIPE rejections.\n- There is no explicit queue or high-watermark management in transport.\n- Inbound processing is stream-driven (`for await` over `readJsonl`), one parsed message at a time.\n\n## HTTP/SSE transport internals\n\n## Lifecycle and connection semantics\n\nHTTP transport has logical connection state, but request path is stateless per HTTP call:\n\n- `connect()` sets `connected=true` (no socket/session handshake)\n- optional server session tracking via `Mcp-Session-Id` header\n- `close()` optionally sends `DELETE` with `Mcp-Session-Id`, aborts SSE listener, emits `onClose`\n\nSo `connected` means \"transport usable\", not \"persistent stream established\".\n\n## Session header behavior\n\n- On POST response, if `Mcp-Session-Id` header is present, transport stores it.\n- Subsequent requests/notifications include `Mcp-Session-Id`.\n- `close()` tries to terminate server session with HTTP DELETE; termination failures are ignored.\n\n## Timeout, cancellation, and auth refresh\n\nFor `request()`:\n\n- timeout uses `AbortController` via `createMCPTimeout` (`OMP_MCP_TIMEOUT_MS` override, else `config.timeout ?? 30000`; `0` disables)\n- external signal, if provided, is merged via `AbortSignal.any([...])`\n- AbortError handling distinguishes caller abort vs timeout\n\nFor `notify()`:\n\n- timeout uses an internal `AbortController` with the same resolved timeout\n- there is no external abort option on the transport interface\n\nFor HTTP OAuth configs managed by `MCPManager`, outbound requests and best-effort server-request responses retry once on `HTTP 401`/`403` if token refresh returns replacement headers.\n\n## HTTP error propagation\n\nOn non-OK response:\n\n- response text is included in thrown error (`HTTP <status>: <text>`)\n- if present, auth hints from `WWW-Authenticate` and `Mcp-Auth-Server` are appended\n\nOn JSON-RPC error object:\n\n- throws `MCP error <code>: <message>`\n\nMalformed JSON body (`response.json()` failure) propagates as parse exception.\n\n## SSE behavior and modes\n\nTwo SSE paths exist:\n\n1. **Per-request SSE response** (`#parseSSEResponse`)\n   - used when POST response content type is `text/event-stream`\n   - consumes stream until matching response id found\n   - can process interleaved notifications during same stream\n\n2. **Background SSE listener** (`startSSEListener()`)\n   - optional GET listener for server-initiated notifications and server-to-client requests\n   - `connectToServer()` starts it for HTTP/SSE transports after `initialize` and before `notifications/initialized`\n   - listener startup waits up to one second, or less for very small request timeouts; `timeout: 0` / `OMP_MCP_TIMEOUT_MS=0` disables that startup deadline\n   - if GET returns `405`, another non-OK status, no body, or times out, listener silently disables itself\n\n## Malformed payload and disconnect handling\n\nSSE JSON parsing errors bubble out of `readSseJson` and reject request/listener.\n\n- Request SSE parse errors reject the active request.\n- Background listener errors trigger `onError` (except AbortError), and an established listener ending while still connected triggers `onClose` so the manager can reconnect.\n- Transport does not restart the listener itself; managed connections may reconnect through manager `onClose` handling.\n\n## `json-rpc.ts` utility vs transport abstraction\n\n`src/mcp/json-rpc.ts` provides `callMCP()` and `parseSSE()` helpers for direct HTTP MCP calls (used by Exa integration), not the `MCPTransport` abstraction used by `MCPClient`/`MCPManager`.\n\nNotable differences from `HttpTransport`:\n\n- parses entire response text first, then extracts first `data: ` line (`parseSSE`), with JSON fallback\n- optional caller `AbortSignal` (`CallMcpOptions`), with a hard 60s `AbortSignal.timeout` default when none is given; no session-id handling, no transport lifecycle\n- returns raw JSON-RPC envelope object\n\nThis path is lightweight but less robust than full transport implementation.\n\n## Retry/reconnect responsibilities\n\n## Transport-level\n\nCurrent transport implementations do **not**:\n\n- retry ordinary failed requests, except the HTTP transport's single OAuth-refresh retry when `onAuthError` is wired\n- reconnect after stdio process exit\n- reconnect SSE listeners by themselves\n- resend in-flight requests after disconnect\n\nThey fail fast and propagate errors.\n\n## Manager/tool-bridge level\n\n`MCPManager` wires `transport.onClose` for managed connections and runs `reconnectServer(name)` when a transport closes unexpectedly. Reconnect tears down the stale connection, re-resolves auth/config values, retries with backoff (`500`, `1000`, `2000`, `4000` ms), reloads tools, and preserves stale tools while reconnecting.\n\n`MCPTool` and `DeferredMCPTool` also attempt one reconnect + retry for retriable connection errors during a tool call. This is tool availability recovery, not transport-level retry.\n\n## Failure scenarios summary\n\n- **Malformed stdio message line**: dropped; stream continues.\n- **Stdio stream/process ends**: transport closes; pending requests rejected as `Transport closed`; manager-managed connections trigger reconnect.\n- **HTTP non-2xx**: request/notify throws HTTP error; managed OAuth requests can refresh auth and retry once on 401/403.\n- **Invalid JSON response**: parse exception propagated.\n- **SSE ends without matching id**: request fails with `No response received for request ID ...`.\n- **Timeout**: transport-specific timeout error.\n- **Caller abort**: AbortError/reason propagated from caller signal where the method accepts one.\n\n## Practical boundary rule\n\nIf the concern is message shape, id correlation, or MCP method ordering, it belongs to protocol/client logic.\n\nIf the concern is framing (JSONL vs HTTP/SSE), stream parsing, fetch/spawn lifecycle, timeout clocks, or connection teardown, it belongs to transport implementation.\n",
 	"mcp-runtime-lifecycle.md": "# MCP runtime lifecycle\n\nThis document describes how MCP servers are discovered, connected, exposed as tools, refreshed, and torn down in the coding-agent runtime.\n\n## Lifecycle at a glance\n\n1. **SDK startup** kicks off MCP discovery (unless MCP is disabled): headless/SDK sessions await `discoverAndLoadMCPTools()`; interactive sessions (`hasUI: true`) create the manager up front and defer `discoverAndConnect()` until the session is live.\n2. **Discovery** (`loadAllMCPConfigs`) resolves MCP server configs from capability sources, filters disabled/project/Exa entries and browser MCP servers when the built-in browser tool is enabled, and preserves source metadata.\n3. **Manager connect phase** (`MCPManager.connectServers`) starts per-server connect + `tools/list` in parallel.\n4. **Fast startup gate** waits up to 250ms, then may return:\n   - fully loaded `MCPTool`s,\n   - failures per server,\n   - or cached `DeferredMCPTool`s for still-pending servers.\n5. **SDK wiring** merges MCP tools into runtime tool registry for the session.\n6. **Post-connect enrichment** best-effort loads resources, resource templates, prompts, and optional resource subscriptions.\n7. **Live session** can refresh MCP tools via `/mcp` flows (`disconnectAll` + rediscover + `session.refreshMCPTools`) and can reconnect individual servers on transport close or `/mcp reconnect`.\n8. **Teardown** happens when callers invoke `disconnectServer`/`disconnectAll`; manager also clears MCP tool/resource/prompt registrations for disconnected servers.\n\n## Discovery and load phase\n\n### Entry path from SDK\n\n`createAgentSession()` in `src/sdk.ts` performs MCP startup when `enableMCP` is true (default). There are two paths:\n\n- **Headless/SDK** (no UI, no provided manager): awaits `discoverAndLoadMCPTools(cwd, { ... })` and merges the returned tools into the startup `customTools` set.\n- **Interactive/TUI** (`hasUI: true`, no provided manager): constructs `MCPManager` immediately (with cache + auth storage), defers `discoverAndConnect()` to a background task started after the session exists, then binds tools via `session.refreshMCPTools(...)` (disposing the manager if the session was torn down mid-connect).\n\nBoth paths:\n\n- pass `authStorage`, cache storage, `mcp.enableProjectConfig`, and browser-MCP filtering based on the `browser.enabled` setting,\n- always set `filterExa: true`,\n- log per-server load/connect errors,\n- store the manager in `toolSession.mcpManager` and the session result.\n\nIf `enableMCP` is false, MCP discovery is skipped entirely.\n\n### Config discovery and filtering\n\n`loadAllMCPConfigs()` (`src/mcp/config.ts`) loads canonical MCP server items through capability discovery, then converts to legacy `MCPServerConfig`.\n\nFiltering behavior:\n\n- `enableProjectConfig: false` removes project-level entries (`_source.level === \"project\"`).\n- `enabled: false` servers are skipped before connect attempts.\n- Exa servers are filtered out by default and API keys are extracted for native Exa tool integration; browser automation MCP servers are filtered when `filterBrowser` is true.\n\nResult includes both `configs` and `sources` (metadata used later for provider labeling).\n\n### Discovery-level failure behavior\n\n`discoverAndLoadMCPTools()` distinguishes two failure classes:\n\n- **Discovery hard failure** (exception from `manager.discoverAndConnect`, typically from config discovery): returns an empty tool set and one synthetic error `{ path: \".mcp.json\", error }`.\n- **Per-server runtime/connect failure**: manager returns partial success with `errors` map; other servers continue.\n\nSo startup does not fail the whole agent session when individual MCP servers fail.\n\n## Manager state model\n\n`MCPManager` tracks runtime lifecycle with separate registries:\n\n- `#connections: Map<string, MCPServerConnection>` — fully connected servers.\n- `#pendingConnections: Map<string, Promise<MCPServerConnection>>` — handshake in progress.\n- `#pendingToolLoads: Map<string, Promise<{ connection, serverTools }>>` — connected but tools still loading.\n- `#tools: CustomTool[]` — current MCP tool view exposed to callers.\n- `#sources: Map<string, SourceMeta>` — provider/source metadata even before connect completes.\n- `#pendingReconnections: Map<string, Promise<MCPServerConnection | null>>` — reconnects in progress after a dropped transport or explicit reconnect.\n- `#serverConfigs: Map<string, MCPServerConfig>` — original unresolved configs preserved so reconnect can re-resolve credentials without leaking resolved tokens.\n\n`getConnectionStatus(name)` derives status from these maps:\n\n- `connected` if in `#connections`,\n- `connecting` if pending connect, pending tool load, or pending reconnect,\n- `disconnected` otherwise.\n\n## Connection establishment and startup timing\n\n## Per-server connect pipeline\n\nFor each discovered server in `connectServers()`:\n\n1. store/update source metadata,\n2. skip if already connected/pending/reconnecting,\n3. validate transport fields (`validateServerConfig`),\n4. resolve auth/shell substitutions (`#resolveAuthConfig`),\n5. call `connectToServer(name, resolvedConfig)` with manager notification/request handlers,\n6. wire HTTP OAuth refresh and transport `onClose` reconnect handling,\n7. call `listTools(connection)`,\n8. cache tool definitions (`MCPToolCache.set`) best-effort,\n9. best-effort load resources, resource templates, prompts, and subscriptions after tools load.\n\n`connectToServer()` behavior (`src/mcp/client.ts`):\n\n- creates stdio or HTTP/SSE transport,\n- performs MCP `initialize`,\n- for HTTP/SSE, starts the optional background SSE listener before `notifications/initialized`,\n- sends `notifications/initialized`,\n- uses timeout (`OMP_MCP_TIMEOUT_MS`, `config.timeout`, or 30s default; `0` disables the client-side timeout),\n- closes transport on init failure.\n\n### Fast startup gate + deferred fallback\n\n`connectServers()` waits on a race between:\n\n- all connect/tool-load tasks settled, and\n- `STARTUP_TIMEOUT_MS = 250`.\n\nAfter 250ms:\n\n- fulfilled tasks become live `MCPTool`s,\n- rejected tasks produce per-server errors,\n- still-pending tasks:\n  - use cached tool definitions if available (`MCPToolCache.get`) to create `DeferredMCPTool`s,\n  - otherwise contribute no tools at startup; they stay in flight, and the background continuation registers their tools via `#onToolsChanged` once connect/list finishes (a slow server no longer blocks startup — issue #2100).\n\nThis is a hybrid startup model: fast return with deferred handles when cache is available, late background registration when it is not.\n\n### Background completion behavior\n\nEach pending `toolsPromise` also has a background continuation that eventually:\n\n- replaces that server’s tool slice in manager state via `#replaceServerTools`,\n- writes cache,\n- logs late failures only after startup (`allowBackgroundLogging`).\n\n## Tool exposure and live-session availability\n\n### Startup registration\n\n`discoverAndLoadMCPTools()` converts manager tools into `LoadedCustomTool[]` and decorates paths (`mcp:<server> via <providerName>` when known).\n\n`createAgentSession()` then pushes these tools into `customTools`, which are wrapped and added to the runtime tool registry with names like `mcp__<server>_<tool>`.\n\n### Tool calls\n\n- `MCPTool` calls tools through an already connected `MCPServerConnection`.\n- `DeferredMCPTool` waits for `waitForConnection(server)` before calling; this allows cached tools to exist before connection is ready.\n- Both attempt a reconnect + single retry for retriable connection failures.\n\nBoth return structured tool output and convert remaining transport/tool errors into `MCP error: ...` tool content (abort remains abort).\n\n## Refresh/reload paths (startup vs live reload)\n\n### Initial startup path\n\n- one-time discovery/load in `sdk.ts`,\n- tools are registered in initial session tool registry.\n\n### Interactive reload path\n\n`/mcp reload` path (`src/modes/controllers/mcp-command-controller.ts`) does:\n\n1. `mcpManager.disconnectAll()`,\n2. `mcpManager.discoverAndConnect()`,\n3. `session.refreshMCPTools(mcpManager.getTools())`.\n\n`session.refreshMCPTools()` (`src/session/agent-session.ts`) removes all `mcp__` tools, re-wraps latest MCP tools, and re-activates tool set so MCP changes apply without restarting session.\n\nThere is also a follow-up path for late connections: after waiting for a specific server, if status becomes `connected`, it re-runs `session.refreshMCPTools(...)` so newly available tools are rebound in-session.\n\n## Health, reconnect, and partial failure behavior\n\nCurrent runtime behavior is connection-event driven:\n\n- **No autonomous polling health monitor** in manager/client.\n- **Automatic reconnect is wired to `transport.onClose`** for managed connections.\n- Reconnect retries with backoff (`500`, `1000`, `2000`, `4000` ms), reloads tools, and notifies consumers on success. A crash-storm circuit breaker suspends automatic reconnects for a server after more than 5 reconnect attempts within 30s; manual `/mcp reconnect` resets that history.\n- Tool calls that see retriable connection errors also attempt one reconnect + retry.\n- Reconnect is also explicit via `/mcp reconnect <name>` or broader `/mcp reload`.\n\nOperationally:\n\n- one server failing does not remove tools from healthy servers,\n- connect/list failures are isolated per server,\n- stale tools may remain visible while reconnect is attempted; calls report MCP errors if recovery fails,\n- tool cache, resource/prompt loading, subscriptions, and background updates are best-effort (warnings/errors logged, no hard stop).\n\n## Teardown semantics\n\n### Server-level teardown\n\n`disconnectServer(name)`:\n\n- removes pending entries, source metadata, saved config, resource refresh/subscription state,\n- detaches `onClose` so explicit close does not trigger reconnect,\n- closes transport if connected,\n- removes manager tool entries using the current raw-name prefix filter (`mcp__${name}_`); generated tool names are sanitized by `tool-bridge.ts`.\n\n### Global teardown\n\n`disconnectAll()`:\n\n- detaches `onClose` for all active transports, then closes them with `Promise.allSettled`,\n- clears pending maps, sources, saved configs, connections, subscriptions, resource refreshes, and manager tool list.\n\nIn current wiring, explicit teardown is used in MCP command flows (for reload/remove/disable). Startup stores the manager on the session; callers that need deterministic MCP shutdown should invoke manager disconnect methods.\n\n## Failure modes and guarantees\n\n| Scenario                                             | Behavior                                                                                                                  | Hard fail vs best-effort       |\n| ---------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------ |\n| Discovery throws (capability/config load path)       | Loader returns empty tools + synthetic `.mcp.json` error                                                                  | Best-effort session startup    |\n| Invalid server config                                | Server skipped with validation error entry                                                                                | Best-effort per server         |\n| Connect timeout/init failure                         | Server error recorded; others continue                                                                                    | Best-effort per server         |\n| `tools/list` still pending at startup with cache hit | Deferred tools returned immediately                                                                                       | Best-effort fast startup       |\n| `tools/list` still pending at startup without cache  | No tools at startup; background continuation registers them via `#onToolsChanged` when ready                              | Best-effort late registration  |\n| Late background tool-load failure                    | Logged after startup gate                                                                                                 | Best-effort logging            |\n| Runtime dropped transport                            | Manager attempts reconnect; stale tools remain while reconnecting and future calls may retry once or fail with MCP errors | Best-effort automatic recovery |\n\n## Public API surface\n\n`src/mcp/index.ts` re-exports loader/manager/client APIs for external callers. `src/sdk.ts` exposes `discoverMCPServers()` as a convenience wrapper returning the same loader result shape.\n\n## Implementation files\n\n- [`src/mcp/loader.ts`](../packages/coding-agent/src/mcp/loader.ts) — loader facade, discovery error normalization, `LoadedCustomTool` conversion.\n- [`src/mcp/manager.ts`](../packages/coding-agent/src/mcp/manager.ts) — lifecycle state registries, parallel connect/list flow, refresh/disconnect.\n- [`src/mcp/client.ts`](../packages/coding-agent/src/mcp/client.ts) — transport setup, initialize handshake, list/call/disconnect.\n- [`src/mcp/index.ts`](../packages/coding-agent/src/mcp/index.ts) — MCP module API exports.\n- [`src/sdk.ts`](../packages/coding-agent/src/sdk.ts) — startup wiring into session/tool registry.\n- [`src/mcp/config.ts`](../packages/coding-agent/src/mcp/config.ts) — config discovery/filtering/validation used by manager.\n- [`src/mcp/tool-bridge.ts`](../packages/coding-agent/src/mcp/tool-bridge.ts) — `MCPTool` and `DeferredMCPTool` runtime behavior.\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — `refreshMCPTools` live rebinding.\n- [`src/modes/controllers/mcp-command-controller.ts`](../packages/coding-agent/src/modes/controllers/mcp-command-controller.ts) — interactive reload/reconnect flows.\n- [`src/task/executor.ts`](../packages/coding-agent/src/task/executor.ts) — subagent MCP proxying via parent manager connections.\n",
 	"mcp-server-tool-authoring.md": "# MCP server and tool authoring\n\nThis document explains how MCP server definitions become callable `mcp__*` tools in coding-agent, and what operators should expect when configs are invalid, duplicated, disabled, or auth-gated.\n\n## Architecture at a glance\n\n```text\nConfig sources (.omp/.claude/.cursor/.vscode/mcp.json, mcp.json, etc.)\n  -> discovery providers normalize to canonical MCPServer\n  -> capability loader dedupes by server name (higher provider priority wins)\n  -> loadAllMCPConfigs converts to MCPServerConfig + skips enabled:false\n  -> MCPManager connects/listTools (with auth/header/env resolution)\n  -> manager best-effort loads resources/prompts and subscribes to resource updates when enabled\n  -> MCPTool/DeferredMCPTool bridge exposes tools as mcp__<server>_<tool>\n  -> AgentSession.refreshMCPTools replaces live MCP tools immediately\n```\n\n## 1) Server config model and validation\n\n`src/mcp/types.ts` defines the authoring shape used by MCP config writers and runtime:\n\n- `stdio` (default when `type` missing): requires `command`, optional `args`, `env`, `cwd`\n- `http`: requires `url`, optional `headers`\n- `sse`: requires `url`, optional `headers` (kept for compatibility)\n- shared fields: `enabled`, `timeout`, `auth`, `oauth`\n\n`validateServerConfig()` (`src/mcp/config.ts`) enforces transport basics:\n\n- rejects configs that set both `command` and `url`\n- requires `command` for stdio\n- requires `url` for http/sse\n- rejects unknown `type`\n\n`config-writer.ts` applies this validation for add/update operations and also validates server names:\n\n- non-empty\n- max 100 chars\n- only `[a-zA-Z0-9_.-]`\n\n### Transport pitfalls\n\n- `type` omitted means stdio. If you intended HTTP/SSE but omitted `type`, `command` becomes mandatory.\n- `sse` is still accepted but treated as HTTP transport internally (`createHttpTransport`).\n- Validation is structural, not reachability: a syntactically valid URL can still fail at connect time.\n\n## 2) Discovery, normalization, and precedence\n\n### Capability-based discovery\n\n`loadAllMCPConfigs()` (`src/mcp/config.ts`) loads canonical `MCPServer` items via `loadCapability(mcpCapability.id)`.\n\nThe capability layer (`src/capability/index.ts`) then:\n\n1. loads providers in priority order\n2. dedupes by `server.name` (first win = highest priority)\n3. validates deduped items\n\nResult: duplicate server names across sources are not merged. One definition wins; lower-priority duplicates are shadowed.\n\n### `.mcp.json` and related files\n\nThe dedicated fallback provider in `src/discovery/mcp-json.ts` reads project-root `mcp.json` and `.mcp.json` (low priority).\n\nIn practice MCP servers also come from higher-priority providers (for example native `.omp/...` and tool-specific config dirs). Authoring guidance:\n\n- Prefer `.omp/mcp.json` (project) or `~/.omp/agent/mcp.json` (user) for explicit control.\n- Use root `mcp.json` / `.mcp.json` when you need fallback compatibility.\n- Reusing the same server name in multiple sources causes precedence shadowing, not merge.\n\n### Normalization behavior\n\n`convertToLegacyConfig()` (`src/mcp/config.ts`) maps canonical `MCPServer` to runtime `MCPServerConfig`.\n\nKey behavior:\n\n- transport inferred as `server.transport ?? (command ? \"stdio\" : url ? \"http\" : \"stdio\")`\n- disabled servers (`enabled === false`) and names in the user `disabledServers` list are dropped before connection\n- optional fields are preserved when present\n\n### Environment expansion during discovery\n\nOMP-native MCP config (`.omp/mcp.json`, `~/.omp/agent/mcp.json`, plus their `.mcp.json` variants) expands `${VAR}` and `${VAR:-default}` placeholders recursively before converting to runtime config. It also accepts boolean/string forms for `enabled` (`true`, `false`, `1`, `0`) and numeric strings for `timeout`.\n\nThe standalone fallback provider in `src/discovery/mcp-json.ts` reads project-root `mcp.json` and `.mcp.json`, expands the same `${...}` placeholders, and type-checks `enabled`/`timeout` without coercing string values.\n\nInvalid `enabled`/`timeout` values are ignored with warnings rather than failing the whole file.\n\n## 3) Auth and runtime value resolution\n\n`MCPManager.prepareConfig()`/`#resolveAuthConfig()` (`src/mcp/manager.ts`) is the final pre-connect pass.\n\n### OAuth credential injection\n\nIf config has:\n\n```ts\nauth: { type: \"oauth\", credentialId: \"...\" }\n```\n\nand credential exists in auth storage:\n\n- `http`/`sse`: injects `Authorization: Bearer <access_token>` header\n- `stdio`: injects `OAUTH_ACCESS_TOKEN` env var\n\nIf credential lookup fails, manager logs a warning and continues with unresolved auth.\n\n### Header/env value resolution\n\nBefore connect, manager resolves stdio `env` values and HTTP/SSE `headers` values via `resolveConfigValue()` (`src/config/resolve-config-value.ts`):\n\n- value starting with `!` => execute shell command, use trimmed stdout (cached)\n- failed, timed-out, or whitespace-only commands produce `undefined`, so that entry is omitted\n- otherwise, treat value as environment variable name first (`process.env[name]`), fallback to literal value\n\nOperational caveat: a mistyped `!` secret command can silently remove that header/env entry, producing downstream 401/403 or server startup failures. A mistyped environment variable name is sent literally unless that literal happens to be meaningful to the server.\n\n## 4) Tool bridge: MCP -> agent-callable tools\n\n`src/mcp/tool-bridge.ts` converts MCP tool definitions into `CustomTool`s.\n\n### Naming and collision domain\n\nTool names are generated as:\n\n```text\nmcp__<sanitized_server_name>_<sanitized_tool_name>\n```\n\nRules:\n\n- lowercases\n- non-`[a-z_]` chars become `_`\n- repeated underscores collapse\n- redundant `<server>_` prefix in tool name is stripped once\n\nThis avoids many collisions, but not all. Different raw names can still sanitize to the same identifier (for example `my-server` and `my.server` both sanitize similarly), and registry insertion is last-write-wins.\n\n### Schema mapping\n\n`tool-bridge.ts` passes each MCP `inputSchema` through `normalizeSchemaForMCP()` before registering it as a `CustomTool` schema.\n\n### Execution mapping\n\n`MCPTool.execute()` / `DeferredMCPTool.execute()`:\n\n- calls MCP `tools/call`\n- flattens MCP content into displayable text\n- returns structured details (`serverName`, `mcpToolName`, provider metadata)\n- maps server-reported `isError` to `Error: ...` text result\n- attempts reconnect + one retry for retriable connection errors\n- maps remaining thrown transport/runtime failures to `MCP error: ...`\n- preserves abort semantics by translating AbortError into `ToolAbortError`\n\n## 5) Operator lifecycle: add/edit/remove and live updates\n\nInteractive mode exposes `/mcp` in `src/modes/controllers/mcp-command-controller.ts`.\n\nSupported operations:\n\n- `add` (wizard or quick-add)\n- `remove` / `rm`\n- `enable` / `disable`\n- `test`\n- `reauth` / `unauth`\n- `reconnect`\n- `reload`\n- `resources`, `prompts`, `notifications`\n- Smithery search/login/logout flows\n\nConfig writes are atomic (`writeMCPConfigFile`: temp file + rename).\n\nAfter changes, controller calls `#reloadMCP()`:\n\n1. `mcpManager.disconnectAll()`\n2. `mcpManager.discoverAndConnect()`\n3. `session.refreshMCPTools(mcpManager.getTools())`\n\n`refreshMCPTools()` replaces all `mcp__` registry entries and immediately re-activates the latest MCP tool set, so changes take effect without restarting the session.\n\n### Mode differences\n\n- **Interactive/TUI mode**: `/mcp` gives in-app UX (wizard, OAuth flow, connection status text, immediate runtime rebinding).\n- **SDK/headless integration**: `discoverAndLoadMCPTools()` (`src/mcp/loader.ts`) returns loaded tools + per-server errors; no `/mcp` command UX.\n\n## 6) User-visible error surfaces\n\nCommon error strings users/operators see:\n\n- add/update validation failures:\n  - `Invalid server config: ...`\n  - `Server \"<name>\" already exists in <path>`\n- quick-add argument issues:\n  - `Use either --url or -- <command...>, not both.`\n  - `--token requires --url (HTTP/SSE transport).`\n- connect/test failures:\n  - `Failed to connect to \"<name>\": <message>`\n  - timeout help text suggests increasing timeout\n  - auth help text for `401/403`\n- auth/OAuth flows:\n  - `Authentication required ... OAuth endpoints could not be discovered`\n  - `OAuth flow timed out. Please try again.`\n  - `OAuth authentication failed: ...`\n- disabled server usage:\n  - `Server \"<name>\" is disabled. Run /mcp enable <name> first.`\n\nBad source JSON in discovery is generally handled as warnings/logs; config-writer paths throw explicit errors.\n\n## 7) Practical authoring guidance\n\nFor robust MCP authoring in this codebase:\n\n1. Keep server names globally unique across all MCP-capable config sources.\n2. Prefer names that remain distinct after MCP tool-name sanitization to avoid generated `mcp__` collisions.\n3. Use explicit `type` to avoid accidental stdio defaults.\n4. Treat `enabled: false` as hard-off: server is omitted from runtime connect set.\n5. For OAuth configs, store a valid `credentialId`; otherwise auth injection is skipped.\n6. If using command-based secret resolution (`!cmd`), verify command output is stable and non-empty.\n\n## Implementation files\n\n- [`src/mcp/types.ts`](../packages/coding-agent/src/mcp/types.ts)\n- [`src/mcp/config.ts`](../packages/coding-agent/src/mcp/config.ts)\n- [`src/mcp/config-writer.ts`](../packages/coding-agent/src/mcp/config-writer.ts)\n- [`src/mcp/tool-bridge.ts`](../packages/coding-agent/src/mcp/tool-bridge.ts)\n- [`src/discovery/mcp-json.ts`](../packages/coding-agent/src/discovery/mcp-json.ts)\n- [`src/modes/controllers/mcp-command-controller.ts`](../packages/coding-agent/src/modes/controllers/mcp-command-controller.ts)\n- [`src/mcp/manager.ts`](../packages/coding-agent/src/mcp/manager.ts)\n- [`src/capability/index.ts`](../packages/coding-agent/src/capability/index.ts)\n- [`src/config/resolve-config-value.ts`](../packages/coding-agent/src/config/resolve-config-value.ts)\n- [`src/mcp/loader.ts`](../packages/coding-agent/src/mcp/loader.ts)\n",
 	"memory.md": "# Autonomous Memory\n\nWhen the local memory backend is enabled, the agent automatically extracts durable knowledge from past sessions and injects a compact summary into future sessions for the same project. Over time it builds a project-scoped memory store — technical decisions, recurring workflows, pitfalls — that carries forward without manual effort.\n\nDisabled by default. Enable the local summary pipeline via `/settings` or `config.yml`:\n\n```yaml\nmemory:\n  backend: local\n```\n\n## Usage\n\n### What gets injected\n\nAt session start, if a memory summary exists for the current project, it is injected into the system prompt as a **Memory Guidance** block. The agent is instructed to:\n\n- Treat memory as heuristic context — useful for process and prior decisions, not authoritative on current repo state.\n- Cite the memory artifact path when memory changes the plan, and pair it with current-repo evidence before acting.\n- Prefer repo state and user instruction when they conflict with memory; treat conflicting memory as stale.\n\n### Reading memory artifacts\n\nThe agent can read memory files directly using `memory://` URLs with the `read` tool:\n\n| URL                                    | Content                             |\n| -------------------------------------- | ----------------------------------- |\n| `memory://root`                        | Compact summary injected at startup |\n| `memory://root/MEMORY.md`              | Full long-term memory document      |\n| `memory://root/skills/<name>/SKILL.md` | A generated skill playbook          |\n\n### `/memory` slash command\n\n| Subcommand            | Effect                                                    |\n| --------------------- | --------------------------------------------------------- |\n| `view`                | Show the current backend injection payload                |\n| `stats`               | Show backend-specific memory statistics, when supported   |\n| `diagnose`            | Show backend-specific diagnostics, when supported         |\n| `clear` / `reset`     | Delete active backend memory data/artifacts               |\n| `enqueue` / `rebuild` | Force consolidation/retention work for the active backend |\n\n## How it works\n\nLocal summary memories are built by a background pipeline that runs at startup; `/memory enqueue` marks consolidation work that the next startup picks up. The pipeline is skipped for subagents and for sessions that are not persisted to a session file.\n\n**Phase 1 — per-session extraction:** For each past session that has changed since it was last processed, a model reads the session history and extracts durable signal: technical decisions, constraints, resolved failures, recurring workflows. Sessions that are too recent, too old, currently active, or beyond the configured scan/age limits are skipped. Each extraction produces a raw memory block and a short synopsis for that session.\n\n**Phase 2 — consolidation:** After extraction, a second model pass reads all per-session extractions and produces three outputs written to disk:\n\n- `MEMORY.md` — a curated long-term memory document\n- `memory_summary.md` — the compact text injected at session start\n- `skills/` — reusable procedural playbooks, each in its own subdirectory\n\nPhase 2 uses a lease and heartbeat to prevent double-running when multiple processes start simultaneously. Stale skill directories from prior runs are pruned automatically.\n\nConsolidated output is redacted for common secret/token patterns before `MEMORY.md`, `memory_summary.md`, or generated skills are written to disk.\n\n### Extraction behavior\n\nMemory extraction and consolidation behavior is driven by static prompt files in `packages/coding-agent/src/prompts/memories/`.\n\n| File                     | Purpose                                      | Variables                                   |\n| ------------------------ | -------------------------------------------- | ------------------------------------------- |\n| `stage_one_system.md`    | System prompt for per-session extraction     | —                                           |\n| `stage_one_input.md`     | User-turn template wrapping session content  | `{{thread_id}}`, `{{response_items_json}}`  |\n| `consolidation_system.md`| System prompt for cross-session consolidation | —                                          |\n| `consolidation.md`       | User-turn prompt for cross-session consolidation | `{{raw_memories}}`, `{{rollout_summaries}}` |\n| `read-path.md`           | Memory guidance injected into live sessions  | `{{memory_summary}}`                        |\n\n### Model selection\n\nMemory piggybacks on the model role system.\n\n| Phase                   | Role                                                                | Purpose                          |\n| ----------------------- | ------------------------------------------------------------------- | -------------------------------- |\n| Phase 1 (extraction)    | `default`                                                           | Per-session knowledge extraction |\n| Phase 2 (consolidation) | `smol` (falls back to `default`, then current/first registry model) | Cross-session synthesis          |\n\nIf the requested memory role is not configured, memory model resolution falls back to the `default` role, then the active session model, then the first model in the registry.\n\n## Configuration\n\n| Setting                               | Default | Description                                                                                                                              |\n| ------------------------------------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------- |\n| `memory.backend`                      | `off`   | Select `local` for this pipeline; legacy `memories.enabled: true` is migrated to `memory.backend: local` when no explicit backend is set |\n| `memories.maxRolloutAgeDays`          | `30`    | Sessions older than this are not processed                                                                                               |\n| `memories.minRolloutIdleHours`        | `12`    | Sessions active more recently than this are skipped                                                                                      |\n| `memories.maxRolloutsPerStartup`      | `64`    | Cap on sessions processed in a single startup                                                                                            |\n| `memories.summaryInjectionTokenLimit` | `5000`  | Max tokens of the summary injected into the system prompt                                                                                |\n\nAdditional tuning knobs (concurrency, lease durations, token budgets) are available in config for advanced use.\n\n## Key files\n\n- `packages/coding-agent/src/memories/index.ts` — pipeline orchestration, injection, clear/enqueue entry points (the `/memory` command routes here via `packages/coding-agent/src/memory-backend/local-backend.ts`)\n- `packages/coding-agent/src/memories/storage.ts` — SQLite-backed job queue and thread registry\n- `packages/coding-agent/src/prompts/memories/` — memory prompt templates\n- `packages/coding-agent/src/internal-urls/memory-protocol.ts` — `memory://` URL handler\n",
 	"mnemosyne-memory-backend.md": "# Mnemopi memory backend\n\nOh My Pi can use `@oh-my-pi/pi-mnemopi` as a local long-term memory backend.\n\nSet:\n\n```yaml\nmemory:\n  backend: mnemopi\n```\n\nExample:\n\n```yaml\nmemory:\n  backend: mnemopi\nmnemopi:\n  scoping: per-project-tagged\n```\n\nWith this backend enabled, the coding agent:\n\n1. Opens one or more local Mnemopi SQLite databases according to the configured bank scoping.\n2. Recalls relevant memories into a `<memories>` block for the first model turn of a session and refreshes the base prompt if recall happens from the `agent_start` listener.\n3. Retains completed conversation turns into the retain bank after agent turns, no more often than `mnemopi.retainEveryNTurns`.\n4. Adds recalled memory as extra compaction context when compaction asks the memory backend for `preCompactionContext`.\n5. Uses the normal `/memory view`, `/memory stats`, `/memory diagnose`, `/memory clear`, and `/memory enqueue` commands through the shared memory backend interface.\n\nRecalled memory is background context, not instructions. Current user messages and tool output take precedence when they conflict.\n\n## Settings\n\n| Setting                         | Default                | Description                                                                                                                                                             |\n| ------------------------------- | ---------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `memory.backend`                | `off`                  | Set to `mnemopi` to enable this backend.                                                                                                                              |\n| `mnemopi.dbPath`              | agent memories dir     | Optional SQLite database path.                                                                                                                                          |\n| `mnemopi.bank`                | unset                  | Optional shared bank base name passed to `Mnemopi`; the coding-agent wrapper scopes from this base according to `mnemopi.scoping`. Unset → shared bank `default`; per-project modes derive a project bank from the project root name plus a stable hash. |\n| `mnemopi.scoping`             | `per-project`          | Memory visibility mode: `global` = one shared bank, `per-project` = isolated project memory, `per-project-tagged` = project-local writes plus global recall visibility. |\n| `mnemopi.autoRecall`          | `true`                 | Recall memory on the first turn of a session.                                                                                                                           |\n| `mnemopi.autoRetain`          | `true`                 | Retain completed turns automatically.                                                                                                                                   |\n| `mnemopi.polyphonicRecall`    | `false`                | Enable 4-voice polyphonic recall (vector, graph, fact, temporal) with reciprocal rank fusion; `MNEMOPI_POLYPHONIC_RECALL` overrides when set.                            |\n| `mnemopi.enhancedRecall`      | `false`                | Enable the tiered query result cache for repeated/similar recall queries; `MNEMOPI_ENHANCED_RECALL` overrides when set.                                                  |\n| `mnemopi.retainEveryNTurns`   | `4`                    | Minimum user turns between automatic retain writes.                                                                                                                     |\n| `mnemopi.recallLimit`         | `8`                    | Maximum recalled memories in the prompt block.                                                                                                                          |\n| `mnemopi.recallContextTurns`  | `3`                    | Prior user-bounded turns included in recall queries.                                                                                                                    |\n| `mnemopi.recallMaxQueryChars` | `4000`                 | Maximum composed recall query length.                                                                                                                                   |\n| `mnemopi.injectionTokenLimit` | `5000`                 | Approximate token budget for memory prompt injection.                                                                                                                   |\n| `mnemopi.debug`               | `false`                | Enable debug logging for backend failures.                                                                                                                              |\n| `mnemopi.noEmbeddings`        | `false`                | Pass `noEmbeddings` to `Mnemopi` and force FTS-only recall.                                                                                                           |\n| `mnemopi.embeddingModel`      | env/default            | Embedding model passed to `Mnemopi`.                                                                                                                                  |\n| `mnemopi.embeddingApiUrl`     | env/default            | OpenAI-compatible embedding endpoint passed to `Mnemopi`.                                                                                                             |\n| `mnemopi.embeddingApiKey`     | env/default            | Embedding API key passed to `Mnemopi`.                                                                                                                                |\n| `mnemopi.llmMode`             | `smol`                 | `smol` uses the configured pi-ai smol model, `remote` uses the settings below, and `none` disables LLM calls.                                                           |\n| `mnemopi.llmBaseUrl`          | env/default            | OpenAI-compatible LLM endpoint for `llmMode: remote`.                                                                                                                   |\n| `mnemopi.llmApiKey`           | env/default            | LLM API key for `llmMode: remote`.                                                                                                                                      |\n| `mnemopi.llmModel`            | env/default            | LLM model id for `llmMode: remote`.                                                                                                                                     |\n\n## Scoping\n\nThe coding-agent wrapper applies scoping on top of the underlying `Mnemopi` package:\n\n- `global` uses one shared bank for recall and writes.\n- `per-project` writes to and recalls from a bank derived from the current git repository root (or cwd) plus a stable hash.\n- `per-project-tagged` writes to the project-local bank and recalls from both the project-local bank and the shared global bank, with duplicate recall results merged.\n\nThe combined project-plus-global behavior lives in the wrapper. The `@oh-my-pi/pi-mnemopi` package itself still exposes banks and constructor options directly, including `bank` for selecting a bank name. Project-local banks other than the shared bank are stored as sibling bank databases managed by Mnemopi's `BankManager`.\n\n## LLM and embeddings\n\nThe backend passes these settings to the `Mnemopi` constructor; if a setting is omitted, Mnemopi falls back to its `MNEMOPI_*` environment defaults. The backend does not download or run a local GGUF LLM. LLM-dependent paths use a configured pi-ai model, an opt-in local on-device memory model (`providers.memoryModel`, ONNX — overrides `smol`/`remote` when set to a local model), a dynamic completion function, a remote OpenAI-compatible endpoint, or deterministic no-LLM fallbacks.\n\nFTS-only:\n\n```yaml\nmemory:\n  backend: mnemopi\nmnemopi:\n  noEmbeddings: true\n```\n\nEquivalent constructor shape:\n\n```ts\nnew Mnemopi({ noEmbeddings: true });\n```\n\nRemote embeddings:\n\n```yaml\nmnemopi:\n  embeddingModel: text-embedding-3-small\n  embeddingApiUrl: https://api.openai.com/v1\n  embeddingApiKey: ${OPENAI_API_KEY}\n```\n\nEquivalent constructor shape:\n\n```ts\nnew Mnemopi({\n  embeddingModel: \"text-embedding-3-small\",\n  embeddingApiUrl: \"https://api.openai.com/v1\",\n  embeddingApiKey,\n});\n```\n\nRemote LLM:\n\n```yaml\nmnemopi:\n  llmMode: remote\n  llmBaseUrl: https://api.openai.com/v1\n  llmApiKey: ${OPENAI_API_KEY}\n  llmModel: gpt-4.1-mini\n```\n\nEquivalent constructor shapes:\n\n```ts\nnew Mnemopi({ llm: { baseUrl, apiKey, model } });\nnew Mnemopi({ llmBaseUrl: baseUrl, llmApiKey: apiKey, llmModel: model });\n```\n\nDynamic function LLM for rotating OAuth tokens:\n\n```ts\nnew Mnemopi({\n  llm: async (prompt, opts) => {\n    const token = await getFreshOauthToken();\n    return await completeWithPiAi(prompt, {\n      token,\n      maxTokens: opts?.maxTokens,\n      temperature: opts?.temperature,\n    });\n  },\n});\n```\n\npi-ai smol model LLM:\n\n```yaml\nmnemopi:\n  llmMode: smol\n```\n\nThe coding agent resolves its configured smol role and passes a dynamic completion function so every Mnemopi LLM call can fetch the current provider credentials at call time:\n\n```ts\nnew Mnemopi({\n  llm: async (prompt, opts) => completeSmolWithCurrentAuth(prompt, opts),\n});\n```\n\n## Operational notes\n\n- The default shared database lives under the agent memories directory in `mnemopi/mnemopi.db`; project-scoped banks use sibling database paths under that Mnemopi directory.\n- `/memory clear` removes every scoped Mnemopi SQLite database and sidecar WAL/SHM files for the active configuration.\n- `/memory enqueue` forces retention of the current session, flushes pending fact extractions, and runs Mnemopi sleep/consolidation.\n- `/memory stats` and `/memory diagnose` render backend-specific bank statistics/diagnostics when the Mnemopi backend is active.\n- Subagents do not own separate Mnemopi retain loops; they alias the parent state when a parent Mnemopi state exists, and otherwise remain inert.\n",
-	"models.md": "# Model and Provider Configuration (`models.yml`)\n\nThis document describes how the coding-agent currently loads models, applies overrides, resolves credentials, and chooses models at runtime.\n\n## What controls model behavior\n\nPrimary implementation files:\n\n- `src/config/model-registry.ts` — loads built-in + custom models, provider overrides, runtime discovery, auth integration\n- `src/config/model-resolver.ts` — parses model patterns and selects initial/smol/slow models\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/catalog/src/models.ts` and `packages/catalog/src/types.ts` — built-in providers/models (`getBundledModels` / `getBundledProviders`) and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.omp/agent/models.yml`\n\nLegacy behavior still present:\n\n- If `models.yml` is missing and `models.json` exists at the same location, it is migrated to `models.yml`.\n- Explicit `.json` / `.jsonc` config paths are still supported when passed programmatically to `ModelRegistry`.\n\n## `models.yml` shape\n\n```yaml\nproviders:\n  <provider-id>:\n    # provider-level config\nequivalence:\n  overrides:\n    <provider-id>/<model-id>: <canonical-model-id>\n  exclude:\n    - <provider-id>/<model-id>\n```\n\n`provider-id` is the canonical provider key used across selection and auth lookup.\n\n`equivalence` is optional and configures canonical model grouping on top of concrete provider models:\n\n- `overrides` maps an exact concrete selector (`provider/modelId`) to an official upstream canonical id\n- `exclude` opts a concrete selector out of canonical grouping\n\n## Provider-level fields\n\n```yaml\nproviders:\n  my-provider:\n    baseUrl: https://api.example.com/v1\n    apiKey: MY_PROVIDER_API_KEY\n    api: openai-completions\n    headers:\n      X-Team: platform\n    authHeader: true\n    auth: apiKey\n    disableStrictTools: false # set true for Anthropic-compatible endpoints that reject the strict field\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `anthropic-messages`\n- `google-generative-ai`\n- `google-vertex`\n\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `discovery.type`: `ollama`, `llama.cpp`, `lm-studio`, `openai-models-list`, or `proxy`\n- `transport`: `pi-native` only. When set, every model under that provider is sent to an `omp auth-gateway` compatible `baseUrl` via `POST /v1/pi/stream`; `apiKey` is the gateway bearer.\n\n## Validation rules (current)\n\n### Full custom provider (`models` is non-empty)\n\nRequired:\n\n- `baseUrl`\n- `apiKey` unless `auth: none`\n- `api` at provider level or each model\n\n### Override-only provider (`models` missing or empty)\n\nMust define at least one of:\n\n- `baseUrl`\n- `apiKey`\n- `headers`\n- `compat`\n- `disableStrictTools`\n- `modelOverrides`\n- `discovery`\n\n### Discovery\n\n- `discovery` requires provider-level `api`, except `discovery.type: proxy` (per-model wire auto-detected).\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\n\n### Command-resolved secrets\n\nProvider `apiKey` values and provider/model `headers` values may start with `!` to read a secret from command stdout. The command is run with a 10 s timeout, stdout is trimmed, and empty/failing commands are omitted:\n\n```yaml\nproviders:\n  openai:\n    apiKey: \"!op read op://dev/openai/api-key\"\n    headers:\n      X-Team-Key: \"!bw get password omp-team-key\"\n```\n\nSuccessful command outputs are cached for the process lifetime so the command is not re-run for every model.\n\n## Merge and override order\n\nModelRegistry pipeline (on refresh):\n\n1. Load built-in providers/models from `@oh-my-pi/pi-ai`.\n2. Load `models.yml` custom config.\n3. Apply provider overrides (`baseUrl`, `headers`, `disableStrictTools`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (current schema version 5) with a `static_fingerprint` column that\nhashes the static catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process by tagging the static-models array with a symbol\nproperty, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `claude-opus-4-6`\n- `claude-haiku-4-5`\n- `gpt-5.3-codex`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: codex\n        name: Zenmux Codex\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/codex: gpt-5.3-codex\n    p-codex/codex: gpt-5.3-codex\n  exclude:\n    - demo/codex-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `thinking`, `input`, `cost`, `premiumMultiplier`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL`, or `OLLAMA_HOST`, or `http://127.0.0.1:11434`\n- context window: `OLLAMA_CONTEXT_LENGTH` if set, otherwise Ollama `/api/show` metadata, otherwise `128000`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n`OLLAMA_CONTEXT_LENGTH` does not configure Ollama's runtime `num_ctx`; set that in Ollama/model configuration separately.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\nThis path also works for local OpenAI-compatible servers that are not LM Studio. For example, if oMLX is bound to Ollama's usual port, set `LM_STUDIO_BASE_URL=http://127.0.0.1:11434/v1` to discover it through the existing `/v1/models` flow. Running oMLX and Ollama side by side requires assigning a different port to one of them. Do not configure oMLX as `ollama`: Ollama discovery uses native `/api/tags` and `/api/show` endpoints, not OpenAI `/v1/models`.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Proxy discovery (`discovery.type: proxy`)\n\nFor Anthropic+OpenAI-compatible proxies (new-api / one-api / similar)\nthat expose both `/v1/messages` and `/v1/chat/completions` behind the same\nhost. Discovery hits `GET /v1/models` (10s timeout, OpenAI-style payload) and\nderives each model's `api` from the entry's `supported_endpoint_types`:\n\n- contains `\"anthropic\"` -> `api: anthropic-messages` (routes via `/v1/messages`)\n- contains `\"openai\"` -> `api: openai-completions` (routes via `/v1/chat/completions`)\n- otherwise -> falls back to provider-level `api` if set, else dropped\n\nProvider-level `api` is **optional** with `discovery.type: proxy` because the\nper-model wire is auto-detected. The Anthropic SDK strips a trailing `/v1`\nfrom `baseUrl` before appending `/v1/messages`, so a single discovery `baseUrl`\n(ending in `/v1`) round-trips correctly to both wires.\n\n```yaml\nproviders:\n  newapi-reseller:\n    baseUrl: https://api.example.com/v1\n    apiKey: xxxx\n    authHeader: true # injects Authorization: Bearer for openai models\n    disableStrictTools: true # most anthropic-fronted proxies reject `strict`\n    discovery:\n      type: proxy\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `OMP_AUTH_BROKER_URL` (or `auth.broker.url`) is set, the local SQLite credential store is replaced by `RemoteAuthCredentialStore`. Layers 2 and 3 above (stored API key / OAuth in `agent.db`) are served from a broker-supplied snapshot whose `refresh` tokens are redacted; expiry triggers `POST /v1/credential/:id/refresh` on the broker rather than a local refresh.\n\n`AuthStorage.setConfigApiKey` lets a `models.yml` `apiKey` win over a broker-resolved OAuth token without overriding a runtime `--api-key`. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full broker / gateway design and env surface (`OMP_AUTH_BROKER_URL`, `OMP_AUTH_BROKER_TOKEN`, `auth.broker.url`, `auth.broker.token`).\n\n## Model availability vs all models\n\n- `getAll()` returns the loaded model registry (built-in + merged custom + discovered).\n- `getAvailable()` filters to models that are keyless or have resolvable auth.\n\nSo a model can exist in registry but not be selectable until auth is available.\n\n## Runtime model resolution\n\n### CLI and pattern parsing\n\n`model-resolver.ts` supports:\n\n- exact `provider/modelId`\n- exact canonical model id\n- exact model id (provider inferred)\n- fuzzy/substring matching\n- glob scope patterns in `--models` (e.g. `openai/*`, `*sonnet*`)\n- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh`)\n\n`--provider` is legacy; `--model` is preferred.\n\nResolution precedence for exact selectors:\n\n1. exact `provider/modelId` bypasses coalescing\n2. exact canonical id resolves through the canonical index\n3. exact bare concrete id still works\n4. fuzzy and glob matching run after the exact paths\n\n### Initial model selection priority\n\n`findInitialModel(...)` uses this order:\n\n1. explicit CLI provider+model\n2. first scoped model (if not resuming)\n3. saved default provider/model\n4. known provider defaults (e.g. OpenAI/Anthropic/etc.) among available models\n5. first available model\n\n### Role aliases and settings\n\nSupported model roles:\n\n- `default`, `smol`, `slow`, `vision`, `plan`, `designer`, `commit`, `title`, `task`\n\nRole aliases like `pi/smol` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI Codex transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-codex` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - claude-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/claude-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `omp models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `omp models` prints provider-grouped tables of every concrete model, and `omp models canonical` prints the coalesced canonical view\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI Codex websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for an explicit OpenAI fallback:\n\n```yaml\nproviders:\n  openai-codex:\n    modelOverrides:\n      gpt-5.5:\n        contextPromotionTarget: openai-codex/gpt-5.4\n```\n\nThe built-in model policy currently links OpenAI `codex-spark` variants to `gpt-5.5`, and `gpt-5.5` to `gpt-5.4`, when that target exists on the same provider/API.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/catalog/src/compat/openai.ts` (`buildOpenAICompat`). It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/models-config-schema.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/catalog/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `supportsMultipleSystemMessages` — preserve separate leading system/developer messages instead of coalescing them. Default: auto (known OpenAI-compatible hosted APIs preserve; strict-template/local hosts coalesce).\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `disableReasoningOnToolChoice` — drop reasoning fields whenever any `tool_choice` is sent. Default: auto (DeepSeek reasoning models).\n- `alwaysSendMaxTokens` — always send a max-token field when the caller did not provide one. Default: auto (Kimi-family models derive TPM limits from `max_tokens`).\n- `strictResponsesPairing` — Responses-API tool-call/result history must be strictly paired. Default: auto (Azure OpenAI, GitHub Copilot).\n- `streamIdleTimeoutMs` — stream-watchdog idle-timeout floor in ms for slow reasoning hosts. Default: auto (GLM coding-plan hosts, direct DeepSeek reasoning).\n- `cacheControlFormat` — `\"anthropic\"` to include Anthropic-style prompt-cache markers in chat-completions payloads. Default: auto (OpenRouter `anthropic/*` models).\n- `supportsLongPromptCacheRetention` — host honors `prompt_cache_retention: \"24h\"` on the Responses API. Default: auto (api.openai.com).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok, Z.ai/Zhipu, and Xiaomi MiMo).\n- `supportsReasoningParams` — whether request shaping may send reasoning params at all. Default: auto (off for GitHub Copilot chat-completions).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `allowsSyntheticReasoningContentForToolCalls` — allow a placeholder reasoning field when a prior assistant tool-call turn lacks provider reasoning content. Default: `true`; set `false` for providers that validate the exact reasoning value.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n- `whenThinking` — partial compat overrides applied only when a request actually engages thinking mode (deep-merged over the baseline compat).\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/catalog/src/types.ts`). The `models.yml` schema exposes the strict-tools opt-out as a top-level provider field (see below) plus two Anthropic-side flags in the same `compat` slot — `requiresToolResultId` (non-standard `id` alias on `tool_result` blocks for Z.AI-style proxies) and `replayUnsignedThinking` (replay unsigned thinking blocks as native thinking instead of demoting them to text); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`, `supportsMidConversationSystem`, `supportsForcedToolChoice`, `supportsSamplingParams`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. OMP enables it by default for a small allowlist of high-frequency built-in `anthropic-messages` tools (`bash`, `python`, `edit`, and `find`) whose schemas fit Anthropic's strict grammar limits; other tools still send normalized schemas but omit `strict`.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out of strict mode for the allowlisted tools:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: claude-sonnet-4-20250514\n        name: Claude Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider. It disables the Anthropic `strict` marker only for tools that OMP would otherwise mark strict; it does not change runtime tool argument validation. OMP can automatically retry without strict tools after Anthropic reports a strict-grammar-too-large error before the first streamed token, but proxies that reject the `strict` field for other reasons should set this flag explicitly.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\nFor oMLX or another local OpenAI-compatible server with a discoverable `/v1/models` endpoint, prefer discovery instead of listing models by hand. Set `api` to the endpoint family your server actually exposes: `openai-completions` uses `/v1/chat/completions`; servers that expose `/v1/responses` need `openai-responses` instead.\n\n```yaml\nproviders:\n  omlx:\n    baseUrl: http://127.0.0.1:11434/v1\n    auth: none\n    api: openai-completions\n    discovery:\n      type: openai-models-list\n```\n\nThe built-in vLLM provider can be pointed at a non-default endpoint without declaring a custom discovery type. OMP uses vLLM's `/v1/models` metadata and preserves vLLM's `max_model_len` field as the discovered context window.\n\n```yaml\nproviders:\n  vllm:\n    baseUrl: http://192.168.5.3:8085/v1\n    auth: none\n```\n\nFor multiple vLLM endpoints, use arbitrary provider IDs with the generic OpenAI-compatible discovery path. Set `auth: none` for local no-auth servers or `apiKey` for authenticated ones. Generic discovery reads `max_model_len` first and then `context_length` as a generic OpenAI-compatible fallback.\n\n```yaml\nproviders:\n  vllm-fast:\n    baseUrl: http://host-a:8000/v1\n    auth: none\n    api: openai-completions\n    discovery:\n      type: openai-models-list\n  vllm-long:\n    baseUrl: http://host-b:8000/v1\n    auth: none\n    api: openai-completions\n    discovery:\n      type: openai-models-list\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true # if the proxy doesn't support strict tool schemas\n    models:\n      - id: claude-sonnet-4-20250514\n        name: Claude Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/claude-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.omp/agent/models.yml`.\n\n## Failure mode\n\nIf `models.yml` fails schema or validation checks:\n\n- registry keeps operating with built-in models\n- error is exposed via `ModelRegistry.getError()` and surfaced in UI/notifications\n",
+	"models.md": "# Model and Provider Configuration (`models.yml`)\n\nThis document describes how the coding-agent currently loads models, applies overrides, resolves credentials, and chooses models at runtime.\n\n## What controls model behavior\n\nPrimary implementation files:\n\n- `src/config/model-registry.ts` — loads built-in + custom models, provider overrides, runtime discovery, auth integration\n- `src/config/model-resolver.ts` — parses model patterns and selects initial/smol/slow models\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/catalog/src/models.ts` and `packages/catalog/src/types.ts` — built-in providers/models (`getBundledModels` / `getBundledProviders`) and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.omp/agent/models.yml`\n\nLegacy behavior still present:\n\n- If `models.yml` is missing and `models.json` exists at the same location, it is migrated to `models.yml`.\n- Explicit `.json` / `.jsonc` config paths are still supported when passed programmatically to `ModelRegistry`.\n\n## `models.yml` shape\n\n```yaml\nproviders:\n  <provider-id>:\n    # provider-level config\nequivalence:\n  overrides:\n    <provider-id>/<model-id>: <canonical-model-id>\n  exclude:\n    - <provider-id>/<model-id>\n```\n\n`provider-id` is the canonical provider key used across selection and auth lookup.\n\n`equivalence` is optional and configures canonical model grouping on top of concrete provider models:\n\n- `overrides` maps an exact concrete selector (`provider/modelId`) to an official upstream canonical id\n- `exclude` opts a concrete selector out of canonical grouping\n\n## Provider-level fields\n\n```yaml\nproviders:\n  my-provider:\n    baseUrl: https://api.example.com/v1\n    apiKey: MY_PROVIDER_API_KEY\n    api: openai-completions\n    headers:\n      X-Team: platform\n    authHeader: true\n    auth: apiKey\n    disableStrictTools: false # set true for Anthropic-compatible endpoints that reject the strict field\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `anthropic-messages`\n- `google-generative-ai`\n- `google-vertex`\n\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `discovery.type`: `ollama`, `llama.cpp`, `lm-studio`, `openai-models-list`, or `proxy`\n- `transport`: `pi-native` only. When set, every model under that provider is sent to an `omp auth-gateway` compatible `baseUrl` via `POST /v1/pi/stream`; `apiKey` is the gateway bearer.\n\n## Validation rules (current)\n\n### Full custom provider (`models` is non-empty)\n\nRequired:\n\n- `baseUrl`\n- `apiKey` unless `auth: none`\n- `api` at provider level or each model\n\n### Override-only provider (`models` missing or empty)\n\nMust define at least one of:\n\n- `baseUrl`\n- `apiKey`\n- `headers`\n- `compat`\n- `disableStrictTools`\n- `modelOverrides`\n- `discovery`\n\n### Discovery\n\n- `discovery` requires provider-level `api`, except `discovery.type: proxy` (per-model wire auto-detected).\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\n\n### Command-resolved secrets\n\nProvider `apiKey` values and provider/model `headers` values may start with `!` to read a secret from command stdout. The command is run with a 10 s timeout, stdout is trimmed, and empty/failing commands are omitted:\n\n```yaml\nproviders:\n  openai:\n    apiKey: \"!op read op://dev/openai/api-key\"\n    headers:\n      X-Team-Key: \"!bw get password omp-team-key\"\n```\n\nSuccessful command outputs are cached for the process lifetime so the command is not re-run for every model.\n\n## Merge and override order\n\nModelRegistry pipeline (on refresh):\n\n1. Load built-in providers/models from `@oh-my-pi/pi-ai`.\n2. Load `models.yml` custom config.\n3. Apply provider overrides (`baseUrl`, `headers`, `disableStrictTools`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (current schema version 5) with a `static_fingerprint` column that\nhashes the static catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process by tagging the static-models array with a symbol\nproperty, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `claude-opus-4-6`\n- `claude-haiku-4-5`\n- `gpt-5.3-codex`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: codex\n        name: Zenmux Codex\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/codex: gpt-5.3-codex\n    p-codex/codex: gpt-5.3-codex\n  exclude:\n    - demo/codex-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `thinking`, `input`, `cost`, `premiumMultiplier`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL`, or `OLLAMA_HOST`, or `http://127.0.0.1:11434`\n- context window: `OLLAMA_CONTEXT_LENGTH` if set, otherwise Ollama `/api/show` metadata, otherwise `128000`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n`OLLAMA_CONTEXT_LENGTH` does not configure Ollama's runtime `num_ctx`; set that in Ollama/model configuration separately.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\nThis path also works for local OpenAI-compatible servers that are not LM Studio. For example, if oMLX is bound to Ollama's usual port, set `LM_STUDIO_BASE_URL=http://127.0.0.1:11434/v1` to discover it through the existing `/v1/models` flow. Running oMLX and Ollama side by side requires assigning a different port to one of them. Do not configure oMLX as `ollama`: Ollama discovery uses native `/api/tags` and `/api/show` endpoints, not OpenAI `/v1/models`.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Proxy discovery (`discovery.type: proxy`)\n\nFor Anthropic+OpenAI-compatible proxies (new-api / one-api / similar)\nthat expose both `/v1/messages` and `/v1/chat/completions` behind the same\nhost. Discovery hits `GET /v1/models` (10s timeout, OpenAI-style payload) and\nderives each model's `api` from the entry's `supported_endpoint_types`:\n\n- contains `\"anthropic\"` -> `api: anthropic-messages` (routes via `/v1/messages`)\n- contains `\"openai\"` -> `api: openai-completions` (routes via `/v1/chat/completions`)\n- otherwise -> falls back to provider-level `api` if set, else dropped\n\nProvider-level `api` is **optional** with `discovery.type: proxy` because the\nper-model wire is auto-detected. The Anthropic SDK strips a trailing `/v1`\nfrom `baseUrl` before appending `/v1/messages`, so a single discovery `baseUrl`\n(ending in `/v1`) round-trips correctly to both wires.\n\n```yaml\nproviders:\n  newapi-reseller:\n    baseUrl: https://api.example.com/v1\n    apiKey: xxxx\n    authHeader: true # injects Authorization: Bearer for openai models\n    disableStrictTools: true # most anthropic-fronted proxies reject `strict`\n    discovery:\n      type: proxy\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `OMP_AUTH_BROKER_URL` (or `auth.broker.url`) is set, the local SQLite credential store is replaced by `RemoteAuthCredentialStore`. Layers 2 and 3 above (stored API key / OAuth in `agent.db`) are served from a broker-supplied snapshot whose `refresh` tokens are redacted; expiry triggers `POST /v1/credential/:id/refresh` on the broker rather than a local refresh.\n\n`AuthStorage.setConfigApiKey` lets a `models.yml` `apiKey` win over a broker-resolved OAuth token without overriding a runtime `--api-key`. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full broker / gateway design and env surface (`OMP_AUTH_BROKER_URL`, `OMP_AUTH_BROKER_TOKEN`, `auth.broker.url`, `auth.broker.token`).\n\n## Model availability vs all models\n\n- `getAll()` returns the loaded model registry (built-in + merged custom + discovered).\n- `getAvailable()` filters to models that are keyless or have resolvable auth.\n\nSo a model can exist in registry but not be selectable until auth is available.\n\n## Runtime model resolution\n\n### CLI and pattern parsing\n\n`model-resolver.ts` supports:\n\n- exact `provider/modelId`\n- exact canonical model id\n- exact model id (provider inferred)\n- fuzzy/substring matching\n- glob scope patterns in `--models` (e.g. `openai/*`, `*sonnet*`)\n- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh`)\n\n`--provider` is legacy; `--model` is preferred.\n\nResolution precedence for exact selectors:\n\n1. exact `provider/modelId` bypasses coalescing\n2. exact canonical id resolves through the canonical index\n3. exact bare concrete id still works\n4. fuzzy and glob matching run after the exact paths\n\n### Initial model selection priority\n\n`findInitialModel(...)` uses this order:\n\n1. explicit CLI provider+model\n2. first scoped model (if not resuming)\n3. saved default provider/model\n4. known provider defaults (e.g. OpenAI/Anthropic/etc.) among available models\n5. first available model\n\n### Role aliases and settings\n\nSupported model roles:\n\n- `default`, `smol`, `slow`, `vision`, `plan`, `designer`, `commit`, `title`, `task`, `advisor`\n\nRole aliases like `pi/smol` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI Codex transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-codex` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - claude-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/claude-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `omp models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `omp models` prints provider-grouped tables of every concrete model, and `omp models canonical` prints the coalesced canonical view\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI Codex websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for an explicit OpenAI fallback:\n\n```yaml\nproviders:\n  openai-codex:\n    modelOverrides:\n      gpt-5.5:\n        contextPromotionTarget: openai-codex/gpt-5.4\n```\n\nThe built-in model policy currently links OpenAI `codex-spark` variants to `gpt-5.5`, and `gpt-5.5` to `gpt-5.4`, when that target exists on the same provider/API.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/catalog/src/compat/openai.ts` (`buildOpenAICompat`). It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/models-config-schema.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/catalog/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `supportsMultipleSystemMessages` — preserve separate leading system/developer messages instead of coalescing them. Default: auto (known OpenAI-compatible hosted APIs preserve; strict-template/local hosts coalesce).\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `disableReasoningOnToolChoice` — drop reasoning fields whenever any `tool_choice` is sent. Default: auto (DeepSeek reasoning models).\n- `alwaysSendMaxTokens` — always send a max-token field when the caller did not provide one. Default: auto (Kimi-family models derive TPM limits from `max_tokens`).\n- `strictResponsesPairing` — Responses-API tool-call/result history must be strictly paired. Default: auto (Azure OpenAI, GitHub Copilot).\n- `streamIdleTimeoutMs` — stream-watchdog idle-timeout floor in ms for slow reasoning hosts. Default: auto (GLM coding-plan hosts, direct DeepSeek reasoning).\n- `cacheControlFormat` — `\"anthropic\"` to include Anthropic-style prompt-cache markers in chat-completions payloads. Default: auto (OpenRouter `anthropic/*` models).\n- `supportsLongPromptCacheRetention` — host honors `prompt_cache_retention: \"24h\"` on the Responses API. Default: auto (api.openai.com).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok, Z.ai/Zhipu, and Xiaomi MiMo).\n- `supportsReasoningParams` — whether request shaping may send reasoning params at all. Default: auto (off for GitHub Copilot chat-completions).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `allowsSyntheticReasoningContentForToolCalls` — allow a placeholder reasoning field when a prior assistant tool-call turn lacks provider reasoning content. Default: `true`; set `false` for providers that validate the exact reasoning value.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n- `whenThinking` — partial compat overrides applied only when a request actually engages thinking mode (deep-merged over the baseline compat).\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/catalog/src/types.ts`). The `models.yml` schema exposes the strict-tools opt-out as a top-level provider field (see below) plus two Anthropic-side flags in the same `compat` slot — `requiresToolResultId` (non-standard `id` alias on `tool_result` blocks for Z.AI-style proxies) and `replayUnsignedThinking` (replay unsigned thinking blocks as native thinking instead of demoting them to text); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`, `supportsMidConversationSystem`, `supportsForcedToolChoice`, `supportsSamplingParams`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. OMP enables it by default for a small allowlist of high-frequency built-in `anthropic-messages` tools (`bash`, `python`, `edit`, and `find`) whose schemas fit Anthropic's strict grammar limits; other tools still send normalized schemas but omit `strict`.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out of strict mode for the allowlisted tools:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: claude-sonnet-4-20250514\n        name: Claude Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider. It disables the Anthropic `strict` marker only for tools that OMP would otherwise mark strict; it does not change runtime tool argument validation. OMP can automatically retry without strict tools after Anthropic reports a strict-grammar-too-large error before the first streamed token, but proxies that reject the `strict` field for other reasons should set this flag explicitly.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\nFor oMLX or another local OpenAI-compatible server with a discoverable `/v1/models` endpoint, prefer discovery instead of listing models by hand. Set `api` to the endpoint family your server actually exposes: `openai-completions` uses `/v1/chat/completions`; servers that expose `/v1/responses` need `openai-responses` instead.\n\n```yaml\nproviders:\n  omlx:\n    baseUrl: http://127.0.0.1:11434/v1\n    auth: none\n    api: openai-completions\n    discovery:\n      type: openai-models-list\n```\n\nThe built-in vLLM provider can be pointed at a non-default endpoint without declaring a custom discovery type. OMP uses vLLM's `/v1/models` metadata and preserves vLLM's `max_model_len` field as the discovered context window.\n\n```yaml\nproviders:\n  vllm:\n    baseUrl: http://192.168.5.3:8085/v1\n    auth: none\n```\n\nFor multiple vLLM endpoints, use arbitrary provider IDs with the generic OpenAI-compatible discovery path. Set `auth: none` for local no-auth servers or `apiKey` for authenticated ones. Generic discovery reads `max_model_len` first and then `context_length` as a generic OpenAI-compatible fallback.\n\n```yaml\nproviders:\n  vllm-fast:\n    baseUrl: http://host-a:8000/v1\n    auth: none\n    api: openai-completions\n    discovery:\n      type: openai-models-list\n  vllm-long:\n    baseUrl: http://host-b:8000/v1\n    auth: none\n    api: openai-completions\n    discovery:\n      type: openai-models-list\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true # if the proxy doesn't support strict tool schemas\n    models:\n      - id: claude-sonnet-4-20250514\n        name: Claude Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/claude-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.omp/agent/models.yml`.\n\n## Failure mode\n\nIf `models.yml` fails schema or validation checks:\n\n- registry keeps operating with built-in models\n- error is exposed via `ModelRegistry.getError()` and surfaced in UI/notifications\n",
 	"natives-addon-loader-runtime.md": "# Natives Addon Loader Runtime\n\nThis document covers the runtime loader shipped by `@oh-my-pi/pi-natives`: how `native/index.js` decides which `.node` file to require, how compiled-binary embedded payloads are extracted, and what startup failures report.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/package.json`\n\n## Scope and responsibility\n\nThe loader is intentionally narrow:\n\n- Build a platform/CPU-aware candidate list for addon filenames and directories.\n- Treat an embedded-addon manifest as a compiled-binary signal when present.\n- Optionally materialize embedded addon archive contents into a versioned per-user cache directory.\n- On Windows `node_modules` installs, stage addon files into the versioned cache to avoid locked-DLL update failures.\n- Attempt candidates in deterministic order and return the first addon that `require(...)` loads and validates.\n\nFor install and compiled-binary paths, the loader verifies a release sentinel export named from `package.json#version` (for example `__piNativesV15_7_2`). Workspace-dev loads skip this validation so a local checkout can rebuild after a pull. The loader does not validate the full export surface; stale same-version or incomplete binaries still surface as missing members or native errors at use sites.\n\n## Runtime inputs and derived state\n\nAt module initialization, `native/index.js` computes:\n\n- **Platform tag**: `${process.platform}-${process.arch}` (for example `darwin-arm64`).\n- **Package version**: from `packages/natives/package.json`.\n- **Core directories**:\n  - `leafPackageDir`: directory of the platform leaf package, resolved via `require.resolve(\"@oh-my-pi/pi-natives-<tag>/package.json\")`; `null` when no leaf is installed (e.g. local dev) and forced to `null` in compiled-binary mode.\n  - `nativeDir`: package-local `packages/natives/native`.\n  - `execDir`: directory containing `process.execPath`.\n  - `versionedDir`: `<getNativesDir()>/<packageVersion>`.\n  - `userDataDir` fallback:\n    - Windows: `%LOCALAPPDATA%/omp` or `%USERPROFILE%/AppData/Local/omp`.\n    - Non-Windows: `~/.local/bin`.\n- **Natives cache root** (`getNativesDir()`):\n  - if `$XDG_DATA_HOME/omp` exists, `$XDG_DATA_HOME/omp/natives`;\n  - otherwise `~/.omp/natives`.\n- **Compiled-binary mode** (`detectCompiledBinary`): true if any of:\n  - embedded-addon manifest is non-null,\n  - `PI_COMPILED` env var is set,\n  - `import.meta.url` contains Bun embedded markers (`$bunfs`, `~BUN`, `%7EBUN`).\n- **Windows staging mode** (`shouldStageNodeModulesAddon`): true only on Windows, in non-compiled mode, when `nativeDir` is inside `node_modules`.\n- **Variant override**: `PI_NATIVE_VARIANT` (`modern`/`baseline` only; invalid values ignored).\n- **Selected variant**: explicit override, otherwise runtime AVX2 detection on x64 (`modern` if AVX2, else `baseline`).\n\n## Platform support and tag resolution\n\n`SUPPORTED_PLATFORMS` is fixed to:\n\n- `linux-x64`\n- `linux-arm64`\n- `darwin-x64`\n- `darwin-arm64`\n- `win32-x64`\n\nUnsupported platforms are not rejected before probing. The loader first tries the computed candidate paths. If all fail and `platformTag` is unsupported, it throws an unsupported-platform error listing supported tags.\n\n## Variant selection (`modern` / `baseline` / default)\n\n### x64 behavior\n\n1. `PI_NATIVE_VARIANT=modern|baseline` wins when valid.\n2. Otherwise AVX2 support is detected:\n   - Linux: scan `/proc/cpuinfo` for `avx2`.\n   - macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`.\n   - Windows: PowerShell `[System.Runtime.Intrinsics.X86.Avx2]::IsSupported`.\n3. AVX2 selects `modern`; unavailable or undetectable AVX2 selects `baseline`.\n\n### Non-x64 behavior\n\nNo variant suffix is used; the filename is `pi_natives.<platform>-<arch>.node`.\n\n### Filename construction\n\n`loader-state.js#getAddonFilenames` returns:\n\n- Non-x64 or no variant: `pi_natives.<tag>.node`\n- x64 + `modern`:\n  1. `pi_natives.<tag>-modern.node`\n  2. `pi_natives.<tag>-baseline.node`\n  3. `pi_natives.<tag>.node`\n- x64 + `baseline`:\n  1. `pi_natives.<tag>-baseline.node`\n  2. `pi_natives.<tag>.node`\n\nThe default unsuffixed fallback remains part of the x64 candidate list.\n\n## Candidate path construction and fallback ordering\n\n`resolveLoaderCandidates(...)` expands every filename across directories, then de-duplicates while preserving first occurrence order.\n\n### Non-compiled runtime\n\nCandidates are grouped by directory class, in order:\n\n1. `<leafPackageDir>/<filename>` for every filename (omitted when `leafPackageDir` is `null`)\n2. `<nativeDir>/<filename>` then `<execDir>/<filename>`, per filename\n\nThe leaf package dir comes first so the optional-dependency binary published with the release is preferred over any `.node` left in the core package's `native/` (e.g. a stale local-dev build).\n\nOn Windows installs where `nativeDir` is inside a `node_modules` segment (`shouldStageNodeModulesAddon`), `<versionedDir>/<filename>` staging candidates are prepended ahead of the leaf candidates so a locked `node_modules` binary can be sidestepped during `bun install -g` updates. The staged file is copied from `leafPackageDir ?? nativeDir` before probing.\n\n### Compiled runtime\n\nCandidates are grouped, in order:\n\n1. `<versionedDir>/<filename>` then `<userDataDir>/<filename>`, per filename\n2. `<nativeDir>/<filename>` then `<execDir>/<filename>`, per filename\n\nAt load time, an extracted embedded candidate, or a staged Windows candidate when no embedded candidate exists, is prepended ahead of these de-duplicated candidates.\n\n## Embedded addon extraction lifecycle\n\n`embedded-addon.js` is generated by `scripts/embed-native.ts`. The reset stub exports `embeddedAddon = null`. A populated manifest has:\n\n- `platformTag`\n- `version`\n- `archive`: `{ format: \"tar.gz\", filename, filePath }`\n- `files[]` entries with `variant`, `filename`, and `size`\n\nExtraction (`maybeExtractEmbeddedAddon`) runs only when:\n\n1. compiled-binary mode is true,\n2. `embeddedAddon` is non-null,\n3. manifest `platformTag` equals the runtime platform tag,\n4. manifest `version` equals the package version,\n5. a variant-appropriate embedded file exists.\n\nVariant file selection:\n\n- Non-x64: prefer `default`, then first available file.\n- x64 + `modern`: prefer `modern`, fallback to `baseline`.\n- x64 + `baseline`: require `baseline`.\n\nMaterialization:\n\n1. Ensure `<versionedDir>` exists.\n2. Select `<versionedDir>/<selected filename>`.\n3. If the current cached file exists and its size matches manifest metadata, reuse it.\n4. Otherwise extract `embeddedAddon.archive.filePath` into `<versionedDir>` using the manifest `files[]` allowlist.\n5. Verify the selected target by size and return it as the first candidate.\n\nArchive, directory, or write failures are appended to the loader error list; probing continues through normal candidates.\n\n## Lifecycle and state transitions\n\n```text\nInit\n  -> Load package metadata and embedded-addon manifest\n  -> Compute platform/version/variant/filenames/candidate paths\n  -> (compiled + embedded manifest matches?)\n       yes -> extract archive to versionedDir when needed (record errors, continue)\n       no  -> skip extraction\n  -> (Windows non-compiled node_modules install and no embedded candidate?)\n       yes -> stage leaf/core addon to versionedDir (record errors, continue)\n       no  -> skip staging\n  -> For each runtime candidate in order:\n       require(candidate)\n       -> sentinel validation passes or is workspace-dev: return addon exports (READY)\n       -> failure: record error, continue\n  -> none loaded:\n       if unsupported platform tag -> throw Unsupported platform\n       else -> throw Failed to load (tried-path diagnostics + hints)\n```\n\n## Failure behavior and diagnostics\n\n### Unsupported platform\n\nIf all candidates fail and `platformTag` is not supported, the loader throws:\n\n- `Unsupported platform: <tag>`\n- supported platform list\n- issue-reporting guidance\n\n### No loadable candidate\n\nIf the platform is supported but no candidate can be loaded, the final error includes:\n\n- `Failed to load pi_natives native addon for <platformTag>` or `<platformTag> (<variant>)`\n- every attempted path with the corresponding `require(...)` or sentinel-validation error\n- mode-specific remediation hints\n\n### Compiled-binary startup failures\n\nCompiled mode diagnostics include:\n\n- expected versioned cache target paths (`<versionedDir>/<filename>`),\n- remediation to delete the versioned cache and rerun,\n- direct release download `curl` commands for each expected filename.\n- release sentinel mismatch details when a loadable `.node` belongs to another `@oh-my-pi/pi-natives` version.\n\n### Non-compiled startup failures\n\nNormal package/runtime diagnostics include:\n\n- reinstall hint (`bun install @oh-my-pi/pi-natives`),\n- local rebuild command (`bun --cwd=packages/natives run build`),\n- optional x64 variant build hint (`TARGET_VARIANT=baseline|modern bun --cwd=packages/natives run build`).\n",
 	"natives-architecture.md": "# Natives Architecture\n\n`@oh-my-pi/pi-natives` is a two-layer package around an ESM loader:\n\n1. **ESM loader/package entrypoint** resolves and loads the correct `.node` addon with `createRequire`, validates the release sentinel outside workspace-dev loads, and re-exports generated classes/functions plus enum runtime objects as explicit named ESM exports.\n2. **Rust N-API module layer** implements the exported functions/classes and emits the generated TypeScript declarations.\n\nThis document is the foundation for deeper module-level docs.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n\n## Package entrypoint and public surface\n\n`packages/natives/package.json` points at generated native artifacts:\n\n- `main`: `./native/index.js`\n- `types`: `./native/index.d.ts`\n- `exports[\".\"].types`: `./native/index.d.ts`\n- `exports[\".\"].import`: `./native/index.js`\n\nThere is no current `packages/natives/src` TypeScript wrapper layer. Consumers import functions/classes/enums directly from `@oh-my-pi/pi-natives`; the type contract is the generated `native/index.d.ts` plus the explicit named exports generated into `native/index.js` by `scripts/gen-enums.ts`.\n\nCurrent capability groups in the generated API include:\n\n- **Search/text/code primitives**: `grep`, `search`, `hasMatch`, `fuzzyFind`, `glob`, `astGrep`, `astEdit`, `blockRangeAt`, `summarizeCode`, text width/slicing/wrapping/sanitization, syntax highlighting, token counting.\n- **Execution/process/terminal primitives**: `executeShell`, `Shell`, `PtySession`, `Process`, key parsing, bash fixups.\n- **System/media/isolation/conversion primitives**: clipboard, SIXEL encoding, HTML-to-Markdown, macOS appearance/power helpers, work profiling, workspace scanning, isolation backend helpers (`iso*`).\n\n## Loader layer\n\n`packages/natives/native/index.js` owns runtime addon selection and optional embedded extraction.\n\n### Candidate resolution model\n\n- Platform tag is `${process.platform}-${process.arch}`.\n- Supported tags are currently:\n  - `linux-x64`\n  - `linux-arm64`\n  - `darwin-x64`\n  - `darwin-arm64`\n  - `win32-x64`\n- x64 can use CPU variants:\n  - `modern` (AVX2-capable)\n  - `baseline` (fallback)\n- Non-x64 uses the default filename without a variant suffix.\n\nFilename strategy:\n\n- Default: `pi_natives.<platform>-<arch>.node`\n- x64 variant: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- x64 runtime fallback includes the unsuffixed default filename after variant candidates.\n\n### Platform-specific variant detection\n\nFor x64, variant selection uses:\n\n- Linux: `/proc/cpuinfo`\n- macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`\n- Windows: PowerShell check for `System.Runtime.Intrinsics.X86.Avx2`\n\n`PI_NATIVE_VARIANT` can force `modern` or `baseline`; invalid values are ignored.\n\n### Binary distribution and extraction model\n\nThe published `@oh-my-pi/pi-natives` package ships **only** the loader layer in `native/`: the ESM loader (`index.js`), generated declarations (`index.d.ts`), the `loader-state.js`/`.d.ts` helpers, and the embedded-addon manifest stub (`embedded-addon.js`). It carries no `.node` binaries.\n\nEach platform's prebuilt `.node` is published as a separate optional-dependency leaf package — `@oh-my-pi/pi-natives-<platform>-<arch>`, one per supported tag — which the core lists in `optionalDependencies` at the lockstep version during publish. npm/bun install only the leaf whose `os`/`cpu` match the host. The working-tree package keeps built `.node` files under `native/` for local dev; the release-publish rewrite (`prepareNativeCorePackage` in `scripts/ci-release-publish.ts`) strips them from the core tarball, and the leaves are generated by `packages/natives/scripts/gen-npm-packages.ts` (`LEAF_TARGETS`). Adding a build target therefore requires a matching `LEAF_TARGETS` entry, or the binary never reaches npm users.\n\nFor compiled binaries, loader behavior is:\n\n1. Check versioned user cache path: `<getNativesDir()>/<packageVersion>/...`.\n2. Check legacy compiled-binary location:\n   - Windows: `%LOCALAPPDATA%/omp` (fallback `%USERPROFILE%/AppData/Local/omp`)\n   - non-Windows: `~/.local/bin`\n3. Fall back to packaged `native/` and executable directory candidates.\n\n`getNativesDir()` uses `$XDG_DATA_HOME/omp/natives` when `$XDG_DATA_HOME/omp` exists; otherwise it uses `~/.omp/natives`.\n\nIf a populated embedded addon manifest is present, it is also treated as a compiled-binary signal. Current embedded manifests point at a gzip-compressed tar archive (`embedded-addons.<tag>.tar.gz`) that contains one or more matching `.node` files. The loader extracts the archive into the versioned cache directory, validates the selected file by size, and prepends that cache path before normal candidate probing.\n\nFor npm/bun installs (non-compiled), `loader-state.js` resolves the platform leaf directory via `require.resolve(\"@oh-my-pi/pi-natives-<tag>/package.json\")` and probes its `.node` **before** the core package's `native/` directory and the executable directory. The optional-dependency binary is therefore preferred over any `.node` left in the core (e.g. a stale local-dev build). On Windows `node_modules` installs, the loader first stages the selected leaf/core addon into `<getNativesDir()>/<packageVersion>/...` and prepends that staged path so running processes do not lock the `node_modules` copy during global updates.\n\n### Failure modes\n\nLoader failures are explicit:\n\n- **Unsupported platform tag**: after failed probing, throws with supported platform list.\n- **No loadable candidate**: throws with all attempted paths and remediation hints.\n- **Embedded/staging errors**: directory/write/archive/staging failures are recorded and included in final load diagnostics if no candidate loads.\n- **Release mismatch**: outside workspace-dev loads, a candidate that loads but lacks the version sentinel export for `package.json#version` is rejected with a reinstall hint.\n\n## Rust N-API module layer\n\n`crates/pi-natives/src/lib.rs` declares exported module ownership:\n\n- `appearance`\n- `ast`\n- `block`\n- `clipboard`\n- `crash_handler`\n- `fd`\n- `fs_cache`\n- `glob`\n- `glob_util`\n- `grep`\n- `highlight`\n- `html`\n- `iso`\n- `keys`\n- `language` (re-exported from `pi_ast`)\n- `power`\n- `prof`\n- `ps`\n- `pty`\n- `shell`\n- `sixel`\n- `snapcompact`\n- `summary`\n- `task`\n- `text`\n- `tokens`\n- `utils` (crate-private helpers)\n- `workspace`\n\nN-API exports are generated from Rust `#[napi]` functions/classes/objects/enums. Snake_case Rust names are exposed as camelCase JavaScript names unless explicitly configured by napi-rs.\n\n## Ownership boundaries\n\n- **Loader/package ownership (`packages/natives/native`, `packages/natives/scripts`)**\n  - runtime binary selection\n  - CPU variant selection and override handling\n  - compiled-binary embedded archive extraction\n  - Windows `node_modules` addon staging\n  - generated TypeScript declarations and explicit ESM export/enum patching\n- **Rust ownership (`crates/pi-natives/src`)**\n  - algorithmic and system-level implementation\n  - platform-native behavior and performance-sensitive logic\n  - N-API symbol implementation consumed directly by package callers\n- **Consumer ownership (`packages/coding-agent`, `packages/tui`)**\n  - user-facing policy and fallbacks that are not built into the native API\n  - higher-level rendering, artifact, shell-session, and command behavior\n\n## Runtime flow (high level)\n\n1. Consumer imports from `@oh-my-pi/pi-natives`.\n2. `native/index.js` computes platform/arch/variant and candidate paths.\n3. Optional embedded archive extraction or Windows `node_modules` staging can prepend a versioned-cache candidate.\n4. Each candidate is `require(...)`d; install/compiled loads must expose the package-version sentinel.\n5. The loaded addon object is bound to explicit named ESM exports, including generated enum objects.\n6. Caller invokes generated N-API functions/classes directly.\n\n## Glossary\n\n- **Native addon**: A `.node` binary loaded via Node-API (N-API).\n- **Platform tag**: Runtime tuple `platform-arch` (for example `darwin-arm64`).\n- **Platform leaf package**: Per-platform npm package `@oh-my-pi/pi-natives-<tag>` that carries one platform's prebuilt `.node`. The core depends on every leaf via `optionalDependencies`; the package manager installs only the host-matching one (`os`/`cpu`).\n- **Variant**: x64 CPU-specific build flavor (`modern` AVX2, `baseline` fallback).\n- **Generated binding declaration**: `native/index.d.ts` emitted by napi-rs during `build-native.ts`.\n- **Version sentinel**: Rust export named from the package version (for example `__piNativesV15_7_2`) that lets the loader reject a `.node` from a different release.\n- **Compiled binary mode**: Runtime mode where the CLI is bundled and native addons are resolved from embedded/cache paths before package-local paths.\n- **Embedded addon**: Build artifact metadata and archive reference generated into `native/embedded-addon.js` so compiled binaries can extract matching `.node` payloads.\n",
 	"natives-binding-contract.md": "# Natives Binding Contract (JavaScript/TypeScript Side)\n\nThis document defines the JS/TS contract between `@oh-my-pi/pi-natives` callers and the loaded N-API addon.\n\nCurrent package shape is direct-to-native: there is no `packages/natives/src/<module>` TypeScript wrapper layer. The public API is the generated `packages/natives/native/index.d.ts` declaration file, the ESM loader/export wrapper in `packages/natives/native/index.js`, and the Rust `#[napi]` exports in `crates/pi-natives/src`.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n- Rust modules under `crates/pi-natives/src/*.rs`\n\n## Contract model\n\nThe contract has three parts:\n\n1. **ESM runtime loader/export wrapper** (`native/index.js`)\n   - calls `loadNative()` from `loader-state.js`, which `require(...)`s the `.node` addon;\n   - binds generated classes/functions as explicit named ESM exports;\n   - emits enum runtime objects generated by `scripts/gen-enums.ts`.\n2. **Generated TypeScript declarations** (`native/index.d.ts`)\n   - generated by napi-rs during `scripts/build-native.ts`;\n   - declares exported functions, classes, object interfaces, and native enums;\n   - is the package `types` entry.\n3. **Rust N-API exports** (`crates/pi-natives/src`)\n   - `#[napi]` functions/classes/objects/enums are the source of generated declarations and runtime symbols;\n   - snake_case Rust names become camelCase JavaScript names by napi-rs convention.\n\nThere is no current `NativeBindings` declaration-merging lifecycle and no full required-export list in the loader. Install/compiled loads do validate the package-version sentinel export; workspace-dev loads skip that check.\n\n## Public export surface organization\n\n`packages/natives/package.json` exposes the package root only:\n\n```json\n{\n  \"main\": \"./native/index.js\",\n  \"types\": \"./native/index.d.ts\",\n  \"exports\": {\n    \".\": {\n      \"types\": \"./native/index.d.ts\",\n      \"import\": \"./native/index.js\"\n    }\n  }\n}\n```\n\nConsumers in `packages/coding-agent` and `packages/tui` import directly from `@oh-my-pi/pi-natives`.\n\n## JS API ↔ native export mapping (representative)\n\n| Category          | Public JS API                                                                                             | Rust source                                      | Return style               |\n| ----------------- | --------------------------------------------------------------------------------------------------------- | ------------------------------------------------ | -------------------------- |\n| Grep              | `grep(options, onMatch?)`                                                                                 | `grep.rs`                                        | `Promise<GrepResult>`      |\n| Grep              | `search(content, options)`                                                                                | `grep.rs`                                        | `SearchResult`             |\n| Grep              | `hasMatch(content, pattern, ignoreCase?, multiline?)`                                                     | `grep.rs`                                        | `boolean`                  |\n| Fuzzy path search | `fuzzyFind(options)`                                                                                      | `fd.rs`                                          | `Promise<FuzzyFindResult>` |\n| Glob/workspace    | `glob(options, onMatch?)`, `listWorkspace(options)`                                                       | `glob.rs`, `workspace.rs`                        | `Promise<...>`             |\n| Glob cache        | `invalidateFsScanCache(path?)`                                                                            | `fs_cache.rs`                                    | `void`                     |\n| AST/block/summary | `astGrep(options)`, `astEdit(options)`, `blockRangeAt(options)`, `summarizeCode(options)`                 | `ast.rs`, `block.rs`, `summary.rs`               | mixed                      |\n| Shell             | `executeShell(options, onChunk?)`                                                                         | `shell.rs`                                       | `Promise<ShellRunResult>`  |\n| Shell             | `new Shell(options?)`, `shell.run(...)`, `shell.abort()`                                                  | `shell.rs`                                       | class / promises           |\n| PTY               | `new PtySession()`, `start/write/resize/kill`                                                             | `pty.rs`                                         | class / promises           |\n| Process           | `Process.fromPid/fromPath`, `status/children/killTree/terminate/waitForExit`                              | `ps.rs`                                          | class / mixed              |\n| Keys              | `parseKey`, `matchesKey`, Kitty/legacy helpers                                                            | `keys.rs`                                        | sync                       |\n| Text              | `wrapTextWithAnsi`, `truncateToWidth`, `sliceWithWidth`, `extractSegments`, `visibleWidth`                | `text.rs`                                        | sync                       |\n| Highlight         | `highlightCode`, `supportsLanguage`, `getSupportedLanguages`                                              | `highlight.rs`                                   | sync                       |\n| HTML              | `htmlToMarkdown(html, options?)`                                                                          | `html.rs`                                        | `Promise<string>`          |\n| SIXEL             | `encodeSixel`                                                                                             | `sixel.rs`                                       | sync                       |\n| Clipboard         | `copyToClipboard`, `readImageFromClipboard`                                                               | `clipboard.rs`                                   | sync / promise             |\n| Tokens            | `countTokens(input, encoding?)`                                                                           | `tokens.rs`                                      | sync                       |\n| System/isolation  | `detectMacOSAppearance`, `MacAppearanceObserver`, `MacOSPowerAssertion`, `getWorkProfile`, `iso*` helpers | `appearance.rs`, `power.rs`, `prof.rs`, `iso.rs` | mixed                      |\n\n## Sync vs async contract differences\n\nThe contract preserves Rust/N-API call style:\n\n- **Promise-returning exports** for worker-thread or async runtime work (`grep`, `glob`, `fuzzyFind`, `astGrep`, `astEdit`, `htmlToMarkdown`, shell/PTY runs, `isoStart`/`isoStop`/`isoDiff`, clipboard image read, workspace scan).\n- **Synchronous exports** for deterministic in-memory transforms/parsers or direct system calls (`search`, `hasMatch`, highlighting, text utilities, token counting, process construction/status, `copyToClipboard`, `encodeSixel`, isolation probe/resolve helpers).\n- **Constructor exports** for stateful runtime objects (`Shell`, `PtySession`, `Process`, macOS observer/power handles).\n\nChanging sync ↔ async for an existing export is a breaking public API change because consumers call these exports directly.\n\n## Object and enum typing patterns\n\n### Object patterns\n\n`#[napi(object)]` Rust structs become TS interfaces, for example:\n\n- `GrepResult`, `SearchResult`, `GlobResult`, `FuzzyFindResult`\n- `ShellRunResult`, `PtyRunResult`, `MinimizerResult`\n- `AstFindResult`, `AstReplaceResult`, `BlockRange`, `SummaryResult`\n- `System`/media/isolation payloads such as `ClipboardImage`, `WorkProfile`, `ParsedKittyResult`, `IsoResolveResult`\n\nRuntime shape correctness is owned by napi-rs and the Rust implementation.\n\n### Enum patterns\n\nNative enums are represented in generated declarations and also emitted as runtime objects by `scripts/gen-enums.ts`, because napi-rs string enums are TS-only without explicit JS exports. Current enum objects include:\n\n- `AstMatchStrictness`\n- `Ellipsis`\n- `Encoding`\n- `FileType`\n- `GrepOutputMode`\n- `IsoBackendKind`\n- `IsoChangeKind`\n- `KeyEventType`\n- `MacOSAppearance`\n- `ProcessStatus`\n\n## Error behavior and caveats\n\n- Addon load failure or unsupported platform throws during package import from `native/index.js`.\n- The loader rejects install/compiled candidates that lack the package-version sentinel export. It does not verify the full export set after `require(...)`; stale same-version or incomplete binaries surface as native load errors or missing members at use sites.\n- N-API conversion validates basic argument conversion, but TS optional fields do not guarantee semantic validity for untyped callers.\n- Numeric enum declarations do not prevent out-of-range numeric values from untyped callers unless the Rust function rejects them during conversion.\n- Callback exports use napi-rs `ThreadsafeFunction` shape: `(error: Error | null, value) => void`. Native code generally emits successful values; hard failures reject/throw through the owning call.\n\n## Maintainer checklist for binding changes\n\nWhen adding/changing an export, update all of:\n\n1. Rust `#[napi]` implementation in the owning `crates/pi-natives/src/<module>.rs`.\n2. `crates/pi-natives/src/lib.rs` if a new module is added.\n3. Any consumer imports/callsites in `packages/coding-agent` or `packages/tui`.\n4. Build output by running the natives build so `native/index.d.ts` and `native/index.js` stay in sync.\n5. `scripts/gen-enums.ts` if enum runtime export patching needs to change.\n\nDo not add a parallel TS wrapper convention unless the package design intentionally moves back to wrappers; current consumers depend on the direct generated API.\n",
@@ -49,7 +50,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"porting-from-pi-mono.md": "# Porting From pi-mono: A Practical Merge Guide\n\nThis guide is a repeatable checklist for porting changes from pi-mono into this repo.\nUse it for any merge: single file, feature branch, or full release sync.\n\n## Last Sync Point (historical upstream marker)\n\n**Commit:** `b21b42d032919de2f2e6920a76fa9a37c3920c0a`\n**Date:** 2026-03-22\n\nUpdate this section after each sync; do not reuse the previous range. This commit is an upstream pi-mono marker and may not exist in this repo's local object database.\n\nWhen starting a new sync, generate patches from this commit forward in a pi-mono checkout or remote that contains the commit:\n\n```bash\ngit format-patch b21b42d032919de2f2e6920a76fa9a37c3920c0a..HEAD --stdout > changes.patch\n```\n\n## 0) Define the scope\n\n- Identify the upstream reference (commit, tag, or PR).\n- List the packages or folders you plan to touch.\n- Decide which features are in-scope and which are intentionally skipped.\n\n## 1) Bring code over safely\n\n- Prefer a clean, focused diff rather than a wholesale copy.\n- Avoid copying built artifacts or generated files.\n- If upstream added new files, add them explicitly and review contents.\n\n## 2) Match import extension conventions\n\nMost runtime TypeScript sources omit `.js` in internal imports, but several current entrypoints and tool modules keep `.js` for ESM/runtime compatibility. Follow the surrounding file and package export style; do not blanket-strip or blanket-add extensions.\n\n- In `packages/coding-agent` runtime sources, prefer extensionless internal imports when the surrounding module does, but preserve existing `.js` imports in files that already require them.\n- In `packages/tui/test` and `packages/natives/bench`, keep `.js` where surrounding files already use it.\n- Keep real file extensions when required by tooling or import assertions (e.g., `.json`, `.css`, `.md` text embeds).\n- Example: `import { x } from \"./foo.js\";` → `import { x } from \"./foo\";` only when that package/file convention is extensionless.\n\n## 3) Replace import scopes\n\nUpstream uses different package scopes. Replace them consistently.\n\n- Replace old scopes with the local scope used here.\n- Examples (adjust to match the actual packages you are porting):\n  - `@mariozechner/pi-coding-agent` → `@oh-my-pi/pi-coding-agent`\n  - `@mariozechner/pi-agent-core` → `@oh-my-pi/pi-agent-core`\n  - `@mariozechner/pi-tui` → `@oh-my-pi/pi-tui`\n  - `@mariozechner/pi-ai` → `@oh-my-pi/pi-ai`\n  - `@mariozechner/pi-utils` → `@oh-my-pi/pi-utils`\n- Some upstream packages publish under the `@earendil-works/*` scope instead of `@mariozechner/*`. Map it the same way (`@earendil-works/pi-coding-agent` → `@oh-my-pi/pi-coding-agent`, and so on).\n- The bare `typebox` package is not an `@oh-my-pi/*` scope; do not rewrite it as one. See the Extensions divergence in section 15 for how tool-parameter schemas map.\n\n## 4) Use Bun APIs where they improve on Node\n\nWe run on Bun, but the current source intentionally mixes Bun APIs with small Node standard-library APIs. Replace Node APIs only when Bun provides a clearer, safer, or simpler implementation; do not mechanically rewrite every Node import.\n\n**Prefer replacing when porting new code:**\n\n- Process spawning: prefer Bun Shell `$` for simple commands; use `Bun.spawn`/`Bun.spawnSync` for streaming or process control. Keep existing `child_process` only where its exact semantics are needed.\n- HTTP clients: `node-fetch`, `axios` → native `fetch`\n- SQLite: `better-sqlite3` → `bun:sqlite`\n- Env loading: `dotenv` → Bun loads `.env` automatically\n- Runtime text/assets: prefer Bun imports such as `with { type: \"text\" }` or `Bun.file()` over copy steps or bundled fallback file reads.\n\n**DO NOT replace (these work fine in Bun):**\n\n- `os.homedir()` — do NOT replace with `Bun.env.HOME` or literal `\"~\"`\n- `os.tmpdir()` — do NOT replace with `Bun.env.TMPDIR || \"/tmp\"` or hardcoded paths\n- `fs.mkdtempSync()` — do NOT replace with manual path construction\n- `path.join()`, `path.resolve()`, etc. — these are fine\n\n**Import style:** Use the `node:` prefix for Node standard-library imports. Namespace imports are common, but named imports are acceptable where the surrounding code already uses them.\n\n**Additional Bun conventions:**\n\n- Prefer Bun Shell `$` for short, non-streaming commands; use `Bun.spawn` only when you need streaming I/O or process control.\n- Use `Bun.file()`/`Bun.write()` for simple files and `node:fs/promises` for directory-oriented operations. Existing synchronous `node:fs` calls are acceptable when the calling flow is intentionally synchronous.\n- Avoid `Bun.file().exists()` checks; use `isEnoent` handling in try/catch.\n- Prefer `Bun.sleep(ms)` over `setTimeout` wrappers.\n\n**Wrong:**\n\n```typescript\n// BROKEN: env vars may be undefined, \"~\" is not expanded\nconst home = Bun.env.HOME || \"~\";\nconst tmp = Bun.env.TMPDIR || \"/tmp\";\n```\n\n**Correct:**\n\n```typescript\nimport * as os from \"node:os\";\nimport * as fs from \"node:fs\";\nimport * as path from \"node:path\";\n\nconst configDir = path.join(os.homedir(), \".config\", \"myapp\");\nconst tempDir = fs.mkdtempSync(path.join(os.tmpdir(), \"myapp-\"));\n```\n\n## 5) Prefer Bun embeds (no copying)\n\nDo not add new runtime asset copy steps. Keep assets in repo and prefer Bun embeds/imports; preserve existing explicit generation workflows such as `packages/coding-agent/src/export/html/tool-views.generated.js` (built from collab-web sources via `bun run build-tool-views`).\n\n- If upstream copies assets into a dist folder, replace with Bun-friendly embeds.\n- Prompts are static `.md` files; use Bun text imports (`with { type: \"text\" }`) and Handlebars instead of inline prompt strings.\n- Use `import.meta.dir` + `Bun.file` to load adjacent non-text resources.\n- Keep assets in-repo and let the bundler include them.\n- Eliminate copy scripts unless the user explicitly requests them or the package already has an intentional generation step.\n- If upstream reads a bundled fallback file at runtime, replace filesystem reads with a Bun text embed import unless the current package already uses a generated asset pipeline.\n  - Example (Codex instructions fallback):\n    - `const FALLBACK_PROMPT_PATH = join(import.meta.dir, \"codex-instructions.md\");` -> removed\n    - `import FALLBACK_INSTRUCTIONS from \"./codex-instructions.md\" with { type: \"text\" };`\n    - Use `return FALLBACK_INSTRUCTIONS;` instead of `readFileSync(FALLBACK_PROMPT_PATH, \"utf8\")`\n\n## 6) Port `package.json` carefully\n\nTreat `package.json` as a contract. Merge intentionally.\n\n- Keep existing `name`, `version`, `type`, `exports`, and `bin` unless the port requires changes.\n- Replace npm/node scripts with Bun equivalents (e.g., `bun check`, `bun test`).\n- Ensure dependencies use the correct scope.\n- Do not downgrade dependencies to fix type errors; upgrade instead.\n- Validate workspace package links and `peerDependencies`.\n\n## 7) Align code style and tooling\n\n- Keep existing formatting conventions.\n- Do not introduce `any` unless required.\n- Avoid dynamic imports unless they are required for optional dependencies, startup cost, or runtime-only modules; prefer top-level imports otherwise.\n- Never build prompts in code; prompts are static `.md` files rendered with Handlebars.\n- In `packages/coding-agent`, use `logger` from `@oh-my-pi/pi-utils` for internal/runtime logging; CLI command files may use `console.*` for intentional user-facing output.\n- Use `Promise.withResolvers()` instead of `new Promise((resolve, reject) => ...)`.\n- Prefer ES `#` private fields for new encapsulated state. Constructor parameter properties already exist in current code and are acceptable; do not churn unrelated access modifiers while porting.\n- Prefer existing helpers and utilities over new ad-hoc code.\n  Preserve Bun-first infrastructure changes already made in this repo:\n  - Runtime is Bun (no Node entry points for the main CLI).\n  - Package manager is Bun (no npm lockfiles).\n  - Heavy Node APIs should not be introduced casually; current source still uses selected Node APIs (`node:crypto`, `node:readline`, synchronous `node:fs`, and `child_process`) where they fit provider, CLI, or process-control semantics.\n  - Lightweight Node APIs (`os.homedir`, `os.tmpdir`, `fs.mkdtempSync`, `path.*`) are kept.\n  - CLI shebangs use `bun` (not `node`, not `tsx`).\n  - TypeScript packages generally use source files directly; `@oh-my-pi/pi-natives` exports generated native bindings from `packages/natives/native`.\n  - CI workflows run Bun for install/check/test.\n\n## 8) Remove old compatibility layers\n\nUnless requested, remove upstream compatibility shims.\n\n- Delete old APIs that were replaced.\n- Update all call sites to the new API directly.\n- Do not keep `*_v2` or parallel versions.\n\n## 9) Update docs and references\n\n- Replace pi-mono repo links where appropriate.\n- Update examples to use Bun and correct package scopes.\n- Ensure README instructions still match the current repo behavior.\n\n## 10) Validate the port\n\nRun the standard checks after changes:\n\n- `bun check`\n\nIf the repo already has failing checks unrelated to your changes, call that out.\nTests use Bun's runner (not Vitest), but only run `bun test` when explicitly requested.\n\n## 11) Protect improved features (regression trap list)\n\nIf you already improved behavior locally, treat those as **non‑negotiable**. Before porting, write down\nthe improvements and add explicit checks so they don’t get lost in the merge.\n\n- **Freeze the expected behavior**: add a short “before/after” note for each improvement (inputs, outputs,\n  defaults, edge cases). This prevents silent rollback.\n- **Map old → new APIs**: if upstream renamed concepts (hooks → extensions, custom tools → tools, etc.),\n  ensure every old entry point still wires through. One missed flag or export equals lost functionality.\n- **Verify exports**: check `package.json` `exports`, public types, and barrel files. Upstream ports often\n  forget to re-export local additions.\n- **Cover non‑happy paths**: if you fixed error handling, timeouts, or fallback logic, add a test or at\n  least a manual checklist that exercises those paths.\n- **Check defaults and config merge order**: improvements often live in defaults. Confirm new defaults\n  didn’t revert (e.g., new config precedence, disabled features, tool lists).\n- **Audit env/shell behavior**: if you fixed execution or sandboxing, verify the new path still uses your\n  sanitized env and does not reintroduce alias/function overrides.\n- **Re-run targeted samples**: keep a minimal set of \"known good\" examples and run them after the port\n  (CLI flags, extension registration, tool execution).\n\n## 12) Detect and handle reworked code\n\nBefore porting a file, check if upstream significantly refactored it:\n\n```bash\n# Compare the file you're about to port against what you have locally\ngit diff HEAD upstream/main -- path/to/file.ts\n```\n\nIf the diff shows the file was **reworked** (not just patched):\n\n- New abstractions, renamed concepts, merged modules, changed data flow\n\nThen you must **read the new implementation thoroughly** before porting. Blind merging of reworked code loses functionality because:\n\nNote: interactive mode was recently split into controllers/utils/types. When backporting related changes, port updates into the individual files we created and ensure `interactive-mode.ts` wiring stays in sync.\n\n1. **Defaults change silently** - A new variable `defaultFoo = [a, b]` may replace an old `getAllFoo()` that returned `[a, b, c, d, e]`.\n\n2. **API options get dropped** - When systems merge (e.g., `hooks` + `customTools` → `extensions`), old options may not wire through to the new implementation.\n\n3. **Code paths go stale** - A renamed concept (e.g., `hookMessage` → `custom`) needs updates in every switch statement, type guard, and handler—not just the definition.\n\n4. **Context/capabilities shrink** - Old APIs may have exposed `{ logger, typebox, pi }` that new APIs forgot to include.\n\n### Semantic porting process\n\nWhen upstream reworked a module:\n\n1. **Read the old implementation** - Understand what it did, what options it accepted, what it exposed.\n\n2. **Read the new implementation** - Understand the new abstractions and how they map to old behavior.\n\n3. **Verify feature parity** - For each capability in the old code, confirm the new code preserves it or explicitly removes it.\n\n4. **Grep for stragglers** - Search for old names/concepts that may have been missed in switch statements, handlers, UI components.\n\n5. **Test the boundaries** - CLI flags, SDK options, event handlers, default values—these are where regressions hide.\n\n### Quick checks\n\n```bash\n# Find all uses of an old concept that may need updating\nrg \"oldConceptName\" --type ts\n\n# Compare default values between versions\ngit show upstream/main:path/to/file.ts | rg \"default|DEFAULT\"\n\n# Check if all enum/union values have handlers\nrg \"case \\\"\" path/to/file.ts\n```\n\n## 13) Quick audit checklist\n\nUse this as a final pass before you finish:\n\n- [ ] Import extensions follow the local package convention (no blanket `.js` stripping)\n- [ ] No newly introduced Node-only APIs unless they match an existing justified pattern\n- [ ] All package scopes updated\n- [ ] `package.json` scripts use Bun\n- [ ] Prompts are `.md` text imports (no inline prompt strings)\n- [ ] No internal/runtime `console.*` in coding-agent; CLI user-facing output is intentional\n- [ ] Assets load via Bun embed/import patterns, or through an existing intentional generation pipeline\n- [ ] Tests or checks run (or explicitly noted as blocked)\n- [ ] No functionality regressions (see sections 11-12)\n\n## 14) Commit message format\n\nWhen committing a backport, follow the repo format `<type>(scope): <past-tense description>` and keep the commit\nrange in the title.\n\n```\nfix(coding-agent): backported pi-mono changes (<from>..<to>)\n\npackages/<package>:\n- <type>: <description>\n- <type>: <description> (#<issue> by @<contributor>)\n\npackages/<other-package>:\n- <type>: <description>\n```\n\n**Example:**\n\n```\nfix(coding-agent): backported pi-mono changes (9f3eef65f..52532c7c0)\n\npackages/ai:\n- fix: handle \"sensitive\" stop reason from Anthropic API\n- fix: normalize tool call IDs with special characters for Responses API\n- fix: add overflow detection for Bedrock, MiniMax, Kimi providers\n- fix: 429 status is rate limiting, not context overflow\n\npackages/tui:\n- fix: refactored autocomplete state tracking\n- fix: file autocomplete should not trigger on empty text\n- fix: configurable autocomplete max visible items\n- fix: improved table column width calculation with word-aware wrapping\n\npackages/coding-agent:\n- fix: preserve external config.yml edits on save (#1046 by @nicobailonMD)\n- fix: resolve macOS NFD and curly quote variants in file paths\n```\n\n**Rules:**\n\n- Group changes by package\n- Use conventional commit types (`fix`, `feat`, `refactor`, `perf`, `docs`)\n- Include upstream issue/PR numbers and contributor attribution for external contributions\n- The commit range in the title helps track sync points\n\n## 15) Intentional Divergences\n\nOur fork has architectural decisions that differ from upstream. **Do not port these upstream patterns:**\n\n### UI Architecture\n\n| Upstream                                    | Our Fork                                                  | Reason                                                                |\n| ------------------------------------------- | --------------------------------------------------------- | --------------------------------------------------------------------- |\n| `FooterDataProvider` class                  | `StatusLineComponent`                                     | Simpler, integrated status line                                       |\n| `ctx.ui.setHeader()` / `ctx.ui.setFooter()` | No-op stubs in current extension contexts                 | Not currently wired to replace the TUI status/header UI               |\n| `ctx.ui.setEditorComponent()`               | No-op stubs in current extension contexts                 | Custom editor replacement is not currently wired                      |\n| `InteractiveModeOptions` options object     | Positional constructor args (options type still exported) | Keep constructor signature; update the type when upstream adds fields |\n\n### Component Naming\n\n| Upstream                     | Our Fork                |\n| ---------------------------- | ----------------------- |\n| `extension-input.ts`         | `hook-input.ts`         |\n| `extension-selector.ts`      | `hook-selector.ts`      |\n| `ExtensionInputComponent`    | `HookInputComponent`    |\n| `ExtensionSelectorComponent` | `HookSelectorComponent` |\n\n### API Naming\n\n| Upstream                                 | Our Fork                                 | Notes                                     |\n| ---------------------------------------- | ---------------------------------------- | ----------------------------------------- |\n| `sessionManager.appendSessionInfo(name)` | `sessionManager.setSessionName(name)`    | We use `sessionName` throughout           |\n| `sessionManager.getSessionName()`        | `sessionManager.getSessionName()`        | Same (we unified to match upstream's RPC) |\n| `agent.sessionName` / `setSessionName()` | `agent.sessionName` / `setSessionName()` | Same                                      |\n\n### File Consolidation\n\n| Upstream                                           | Our Fork                                                  | Reason                                        |\n| -------------------------------------------------- | --------------------------------------------------------- | --------------------------------------------- |\n| `clipboard.ts` + `clipboard-image.ts` (tool files) | `src/utils/clipboard.ts` backed by `@oh-my-pi/pi-natives` | Native implementation with a small TS wrapper |\n\n### Test Framework\n\n| Upstream                  | Our Fork                      |\n| ------------------------- | ----------------------------- |\n| `vitest` with `vi.mock()` | `bun:test` with `vi` from bun |\n| `node:test` assertions    | `expect()` matchers           |\n\n### Tool Architecture\n\n| Upstream                            | Our Fork                                                                                                      | Notes                                                     |\n| ----------------------------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- |\n| `createTool(cwd: string, options?)` | `createTools(session: ToolSession)` via `BUILTIN_TOOLS` registry                                              | Tool factories accept `ToolSession` and can return `null` |\n| Per-tool `*Operations` interfaces   | Only current per-tool override interfaces remain (for example `FindOperations`)                               | Used for SSH/remote overrides where present               |\n| Node.js `fs/promises` everywhere    | Bun file APIs for simple file writes/reads, `node:fs/promises` for dirs, selected sync `node:fs` where needed | Prefer Bun APIs when they simplify                        |\n\n### Auth Storage\n\n| Upstream                        | Our Fork                                    | Notes                                        |\n| ------------------------------- | ------------------------------------------- | -------------------------------------------- |\n| `proper-lockfile` + `auth.json` | `agent.db` (bun:sqlite)                     | Credentials stored exclusively in `agent.db` |\n| Single credential per provider  | Multi-credential with round-robin selection | Session affinity and backoff logic preserved |\n\n### Extensions\n\n| Upstream                                                         | Our Fork                                                                                          |\n| ---------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- |\n| `jiti` for TypeScript loading                                    | Native Bun `import()`                                                                              |\n| `pkg.pi` manifest field                                          | `pkg.omp` preferred; fallback to `pkg.pi` remains                                                  |\n| `StringEnum` from `pi-ai`                                        | `Type.Enum` from the `pi.typebox` shim (or author the schema with `pi.zod`); `pi-ai` no longer exports `StringEnum` |\n| `formatSize` from `pi-coding-agent`                              | `formatBytes` from `@oh-my-pi/pi-utils`                                                            |\n| `DefaultResourceLoader` / `DefaultPackageManager` / `SettingsManager` / `createEventBus` | Capability-based discovery (`loadCapability(...)`) plus the `Settings` singleton and `EventBus` |\n\n### Skip These Upstream Features\n\nWhen porting, **skip** these files/features entirely:\n\n- `footer-data-provider.ts` — we use StatusLineComponent\n- `clipboard-image.ts` — image clipboard support is exposed through `src/utils/clipboard.ts` backed by `@oh-my-pi/pi-natives`\n- GitHub workflow files — we have our own CI\n- `models.generated.ts` — auto-generated, regenerate locally (as models.json instead)\n\n### Features We Added (Preserve These)\n\nThese exist in our fork but not upstream. **Never overwrite:**\n\n- `StatusLineComponent` in interactive mode\n- Multi-credential auth with session affinity\n- Capability-based discovery system (`defineCapability`, `registerProvider`, `loadCapability`, `skillCapability`, etc.)\n- MCP/Exa/SSH integrations\n- LSP writethrough for format-on-save\n- Bash interception (`checkBashInterception`)\n- Fuzzy path suggestions in read tool\n",
 	"porting-to-natives.md": "# Porting to pi-natives (N-API) — Field Notes\n\nThis is a practical guide for moving hot paths into `crates/pi-natives` and wiring them through the generated native package entrypoint. It exists to avoid the same failures happening twice.\n\n## When to port\n\nPort when any of these are true:\n\n- The hot path runs in render loops, tight UI updates, or large batches.\n- JS allocations dominate (string churn, regex backtracking, large arrays).\n- You already have a JS baseline and can benchmark both versions side by side.\n- The work is CPU-bound or blocking I/O that can run on the libuv thread pool.\n- The work is async I/O that can run on Tokio's runtime (for example shell execution).\n\nAvoid ports that depend on JS-only state or dynamic imports. N-API exports should be data-in/data-out. Long-running work should go through `task::blocking` (CPU-bound/blocking I/O) or `task::future` (async I/O) with cancellation where the caller needs `timeoutMs` or `AbortSignal`.\n\n## Current package shape\n\n`@oh-my-pi/pi-natives` no longer has a `packages/natives/src/<module>` TypeScript wrapper layer. The package root points at generated native artifacts:\n\n- runtime entry/export wrapper: `packages/natives/native/index.js`\n- types entry: `packages/natives/native/index.d.ts`\n- loader helpers: `packages/natives/native/loader-state.js`\n- embedded manifest: `packages/natives/native/embedded-addon.js`\n\nConsumers import directly from `@oh-my-pi/pi-natives`. The generated declarations and explicit ESM exports are produced during `bun --cwd=packages/natives run build`.\n\n## Anatomy of a native export\n\n**Rust side:**\n\n- Implementation lives in `crates/pi-natives/src/<module>.rs`.\n- If you add a new module, register it in `crates/pi-natives/src/lib.rs`.\n- Export with `#[napi]`; snake_case exports are converted to camelCase automatically. Use explicit JS names only for true aliases/non-default names. Use `#[napi(object)]` for object-shaped structs.\n- For CPU-bound or blocking work, use `task::blocking(tag, cancel_token, work)`.\n- For async work that needs Tokio, use `task::future(env, tag, work)`.\n- Pass a `CancelToken` when the API exposes `timeoutMs` or `AbortSignal`, and call `heartbeat()` inside long loops.\n\n**Package/build side:**\n\n- `packages/natives/scripts/build-native.ts` runs napi-rs, installs the `.node` artifact, copies generated `index.d.ts`, and regenerates explicit ESM class/function exports plus enum runtime exports in the checked-in `native/index.js`.\n- `packages/natives/native/index.js` is the ESM entrypoint that calls the loader, exposes named exports, and rejects install/compiled `.node` files that do not expose the package-version sentinel.\n- `packages/natives/package.json` exposes only the package root (`@oh-my-pi/pi-natives`) as the import surface. At publish time the binaries are split out: the core ships the loader only (no `.node`), and each platform's `.node` is published as an optional-dependency leaf package `@oh-my-pi/pi-natives-<tag>` (`scripts/ci-release-publish.ts` + `packages/natives/scripts/gen-npm-packages.ts`). This is transparent to importers — you still `import` from `@oh-my-pi/pi-natives`.\n\n**Consumer side:**\n\n- Update direct imports/callsites in `packages/coding-agent` or `packages/tui` when the new export replaces a JS implementation.\n- Keep higher-level policy in consumers unless it belongs in the native primitive itself.\n\n## Porting checklist\n\n1. **Add the Rust implementation**\n\n- Put the core logic in a plain Rust function.\n- If it is a new module, add it to `crates/pi-natives/src/lib.rs`.\n- Expose it with `#[napi]` so the default snake_case -> camelCase mapping stays consistent.\n- Keep signatures owned and simple: `String`, `Vec<String>`, `Uint8Array`, `Either<JsString, Uint8Array>`, or `#[napi(object)]` structs.\n- For CPU-bound or blocking work, use `task::blocking`; for async work, use `task::future`.\n- If exposing cancellation, include `timeout_ms: Option<u32>` and `signal: Option<Unknown<'env>>` in options, create `CancelToken::new(...)`, and heartbeat in long loops.\n\n2. **Build generated bindings**\n\n- Run `bun --cwd=packages/natives run build`.\n- Confirm the generated `packages/natives/native/index.d.ts` includes the new export with the intended JS name/signature.\n- Confirm `packages/natives/native/index.js` has generated explicit ESM exports for the new class/function and enum objects when enum changes are involved.\n\n3. **Update consumers**\n\n- Import the new export directly from `@oh-my-pi/pi-natives`.\n- Replace only callsites where the native implementation is faster/equivalent and preserves behavior.\n- Remove obsolete JS implementation code in the same change when the native path becomes canonical.\n\n4. **Add benchmarks**\n\n- Put benchmarks next to the owning package (`packages/tui/bench`, `packages/natives/bench`, or `packages/coding-agent/bench`).\n- Include a JS baseline and native version in the same run.\n- Use `Bun.nanoseconds()` and a fixed iteration count.\n- Keep benchmark inputs realistic for the hot path.\n\n5. **Run focused verification**\n\n- Build the native package.\n- Run the benchmark.\n- Run the narrow tests or scenario covering the changed export/callsites.\n\n## Pain points and how to avoid them\n\n### 1) Stale platform/variant artifacts\n\nThe loader probes platform-tagged artifacts in deterministic order. For x64, selected variant candidates are tried before the unsuffixed default fallback:\n\n- `modern`: `pi_natives.<tag>-modern.node`, then `...-baseline.node`, then `pi_natives.<tag>.node`.\n- `baseline`: `pi_natives.<tag>-baseline.node`, then `pi_natives.<tag>.node`.\n\nNon-x64 uses `pi_natives.<tag>.node`.\n\nCompiled binaries also probe `<getNativesDir()>/<version>/...` and a legacy user-data directory before package/executable locations. Windows `node_modules` installs stage leaf/core addons into the same versioned directory before probing. If any earlier candidate is stale, a new export may appear missing unless the version sentinel rejects it first.\n\n**Fix:** remove stale candidate/cache files and rebuild.\n\n```bash\nrm packages/natives/native/pi_natives.<platform>-<arch>.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-modern.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-baseline.node\nbun --cwd=packages/natives run build\n```\n\nFor compiled binaries or Windows staging, delete the versioned addon cache shown in the loader error (normally under `~/.omp/natives/<version>` unless `$XDG_DATA_HOME/omp` is used).\n\n### 2) Generated types do not match loaded binary\n\nThis can happen when `native/index.d.ts` was regenerated but the `.node` file being loaded is stale, same-version incomplete, or from a different platform/variant. Different-version install/compiled binaries should be rejected by the version sentinel during loading.\n\nVerify the loaded export set from the actual candidate path reported by the loader:\n\n```bash\nbun -e 'import { createRequire } from \"node:module\"; const require = createRequire(import.meta.url); const mod = require(process.argv[2]); console.log(Object.keys(mod).sort())' -- /path/from/loader/error/pi_natives.<tag>[-variant].node\n```\n\nFix the build/candidate mismatch. Do not paper over it with optional consumer checks if the export is required.\n\n### 3) Rust signature mismatch\n\nKeep N-API signatures simple and owned. Avoid borrowed references like `&str` in public exports. If you need structured data, use `#[napi(object)]` structs. If you need callbacks, use napi-rs `ThreadsafeFunction` and keep callback error/value behavior explicit.\n\n### 4) Enum runtime exports and ESM named exports\n\nnapi-rs declarations alone are not enough for JS callers that import named symbols or use enum objects at runtime. `scripts/gen-enums.ts` reads `native/index.d.ts`, writes explicit `export const ... = nativeBindings...` entries for public classes/functions, and emits enum objects in `native/index.js`. If you add or change a native export, verify both `native/index.d.ts` and the generated export block in `native/index.js`.\n\n### 5) Benchmarking mistakes\n\n- Do not compare different inputs or allocations.\n- Keep JS and native using identical input arrays.\n- Run both in the same benchmark file to avoid skew.\n- Include enough iterations to smooth startup noise, but keep inputs realistic.\n\n## Benchmark template\n\n```ts\nconst ITERATIONS = 2000;\n\nfunction bench(name: string, fn: () => void): number {\n  const start = Bun.nanoseconds();\n  for (let i = 0; i < ITERATIONS; i++) fn();\n  const elapsed = (Bun.nanoseconds() - start) / 1e6;\n  console.log(\n    `${name}: ${elapsed.toFixed(2)}ms total (${(elapsed / ITERATIONS).toFixed(6)}ms/op)`,\n  );\n  return elapsed;\n}\n\nbench(\"feature/js\", () => {\n  jsImpl(sample);\n});\n\nbench(\"feature/native\", () => {\n  nativeImpl(sample);\n});\n```\n\n## Verification checklist\n\n- Generated `native/index.d.ts` includes the new export and intended TS signature.\n- `native/index.js` includes the generated named export; enum objects are present when the change adds/changes enums.\n- The loaded `.node` file's `Object.keys(require(candidate))` includes the new export and the package-version sentinel.\n- Bench numbers are recorded in the PR/notes.\n- Call sites are updated only if native is faster/equal and behavior-compatible.\n- Obsolete JS code is removed when the native implementation becomes canonical.\n\n## Rule of thumb\n\n- If native is slower, do not switch callsites. Keep or remove the export based on whether it has a near-term owner.\n- If native is faster and behavior-compatible, switch callsites and keep a benchmark to catch regressions.\n",
 	"provider-streaming-internals.md": "# Provider streaming internals\n\nThis document explains how token/tool streaming is normalized in `@oh-my-pi/pi-ai`, then propagated through `@oh-my-pi/pi-agent-core` and `coding-agent` session events.\n\n## End-to-end flow\n\n1. `streamSimple()` (`packages/ai/src/stream.ts`) maps generic options and dispatches to a provider stream function.\n2. Provider stream functions translate provider-native stream events into the unified `AssistantMessageEvent` sequence. Current built-ins include Anthropic, OpenAI Responses/Completions/Codex/Azure Responses, Google Gemini/Gemini CLI/Vertex, Bedrock Converse, Ollama, Cursor, pi-native gateway transport, plus GitLab Duo/Kimi/Synthetic/xAI-Grok-Responses wrappers and extension-registered custom APIs.\n3. Each provider pushes events into `AssistantMessageEventStream` (`packages/ai/src/utils/event-stream.ts`), which exposes:\n   - async iteration for incremental updates\n   - `result()` for final `AssistantMessage`\n4. `agentLoop` (`packages/agent/src/agent-loop.ts`) consumes those events, mutates in-flight assistant state, and emits `message_update` events carrying the raw `assistantMessageEvent`.\n5. `AgentSession` (`packages/coding-agent/src/session/agent-session.ts`) subscribes to agent events, persists messages, drives extension hooks, and applies session behaviors (retry, compaction, TTSR, streaming-edit abort checks).\n\n## Unified stream contract in `@oh-my-pi/pi-ai`\n\nAll providers emit the same shape (`AssistantMessageEvent` in `packages/ai/src/types.ts`):\n\n- `start`\n- content block lifecycle triplets:\n  - text: `text_start` → `text_delta`\\* → `text_end`\n  - thinking: `thinking_start` → `thinking_delta`\\* → `thinking_end`\n  - tool call: `toolcall_start` → `toolcall_delta`\\* → `toolcall_end`\n- terminal event:\n  - `done` with `reason: \"stop\" | \"length\" | \"toolUse\"`\n  - or `error` with `reason: \"aborted\" | \"error\"`\n\n`AssistantMessageEventStream` guarantees:\n\n- final result is resolved by terminal event (`done` or `error`)\n- events are delivered to consumers immediately, in push order (no batching or merging)\n\n## Delta throttling behavior\n\n`AssistantMessageEventStream` itself no longer throttles or merges delta events — every provider event is delivered as pushed. The per-delta cost control moved into tool-call argument parsing: providers accumulate partial JSON and re-parse it via `parseStreamingJsonThrottled()` (`packages/ai/src/utils/json-parse.ts`), which skips the re-parse until at least `STREAMING_JSON_PARSE_MIN_GROWTH` (256) new bytes have arrived, bounding mid-stream parse cost from quadratic to linear. The final `toolcall_end` parse is always unconditional and authoritative.\n\nThere is no provider backpressure: providers still produce at full speed, while the local stream queues.\n\n## Provider normalization details\n\n## Anthropic (`anthropic-messages`)\n\nSource: `packages/ai/src/providers/anthropic.ts`\n\nNormalization points:\n\n- `message_start` initializes usage (input/output/cache tokens)\n- `content_block_start` maps to text/thinking/toolcall starts\n- `content_block_delta` maps:\n  - `text_delta` → `text_delta`\n  - `thinking_delta` → `thinking_delta`\n  - `input_json_delta` → `toolcall_delta`\n  - `signature_delta` updates `thinkingSignature` only (no event)\n- `content_block_stop` emits corresponding `*_end`\n- `message_delta.stop_reason` maps via `mapStopReason()`\n\nTool-call argument streaming:\n\n- each tool block carries internal `partialJson`\n- every JSON delta appends to `partialJson`\n- `arguments` are reparsed on appended deltas via `parseStreamingJsonThrottled()` (re-parse only after ≥256 new bytes)\n- `toolcall_end` reparses once more, then strips `partialJson`\n\n## OpenAI Responses family (`openai-responses`, `openai-codex-responses`, `azure-openai-responses`)\n\nSources: `packages/ai/src/providers/openai-responses.ts`, `openai-codex-responses.ts`, and `azure-openai-responses.ts`\n\nNormalization points:\n\n- `response.output_item.added` starts reasoning/text/function-call/custom-tool blocks\n- reasoning summary events (`response.reasoning_summary_text.delta`) and raw reasoning events (`response.reasoning_text.delta`) become `thinking_delta`\n- output/refusal deltas become `text_delta`\n- `response.function_call_arguments.delta` and `response.custom_tool_call_input.delta` become `toolcall_delta`\n- `response.output_item.done` emits `thinking_end` / `text_end` / `toolcall_end`\n- `response.completed` maps status to stop reason and usage; `response.failed` / SDK `error` events throw into the wrapper's terminal `error` path\n\nTool-call argument streaming:\n\n- same `partialJson` accumulation pattern as Anthropic for function-call JSON arguments\n- custom tools stream raw string input and expose final arguments as `{ input: <raw> }`\n- providers that send only `response.function_call_arguments.done` still populate final args\n- tool call IDs are normalized as `\"<call_id>|<item_id>\"`\n\n## Google Generative AI (`google-generative-ai`)\n\nSource: `packages/ai/src/providers/google.ts` (thin request wrapper) and `google-shared.ts` (`streamGoogleGenAI`, shared chunk-to-block translation)\n\nNormalization points:\n\n- iterates `candidate.content.parts`\n- text parts are split into thinking vs text by `isThinkingPart(part)`\n- block transitions close previous block before starting a new one\n- `part.functionCall` is treated as a complete tool call (start/delta/end emitted immediately)\n- finish reason mapped by `mapStopReason()` from `google-shared.ts`\n\nTool-call argument streaming:\n\n- function call args arrive as structured object, not incremental JSON text\n- implementation emits one synthetic `toolcall_delta` containing `JSON.stringify(arguments)`\n- no partial JSON parser needed for Google in this path\n\n## Partial tool-call JSON accumulation and recovery\n\nShared behavior for Anthropic/OpenAI Responses uses `parseStreamingJson()` / `parseStreamingJsonThrottled()` (`packages/ai/src/utils/json-parse.ts`):\n\n1. try `JSON.parse`\n2. fallback to `repairJson()` + the `partial-json` parser for incomplete fragments\n3. if both fail, return `{}`\n\nImplications:\n\n- malformed or truncated argument deltas do not crash stream processing immediately\n- in-progress `arguments` may temporarily be `{}`\n- later valid deltas can recover structured arguments because parsing is retried as the buffer grows (throttled to ≥256-byte growth steps mid-stream)\n- final `toolcall_end` performs one more parse attempt before emission\n\n## Stop reasons vs transport/runtime errors\n\nProvider stop reasons are mapped to normalized `stopReason`:\n\n- Anthropic: `end_turn`→`stop`, `max_tokens`→`length`, `tool_use`→`toolUse`, safety/refusal cases→`error`\n- OpenAI Responses: `completed`→`stop`, `incomplete`→`length`, `failed/cancelled`→`error`\n- Google: `STOP`→`stop`, `MAX_TOKENS`→`length`, safety/prohibited/malformed-function-call classes→`error`\n\nError semantics are split in two stages:\n\n1. **Model completion semantics** (provider reported finish reason/status)\n2. **Transport/runtime failure** (network/client/parser/abort exceptions)\n\nIf provider stream throws or signals failure, each provider wrapper catches and emits terminal `error` event with:\n\n- `stopReason = \"aborted\"` when abort signal is set\n- otherwise `stopReason = \"error\"`\n- `errorMessage = formatErrorMessageWithRetryAfter(error)`\n\n## Malformed chunk / SSE parse failure behavior\n\nThe OpenAI Completions/Responses paths delegate chunk/SSE framing to the `openai` SDK stream. Anthropic uses the in-repo `AnthropicMessagesClient` (`packages/ai/src/providers/anthropic-client.ts`); the Google paths and the Codex SSE fallback read SSE via `readSseJson()` directly, and websocket Codex frames are normalized through the same event handler.\n\nObserved behavior in current implementation:\n\n- malformed SDK stream parsing surfaces as an exception or stream `error` event\n- malformed Codex SSE JSON/framing throws from the local SSE reader\n- provider wrapper converts failures into unified terminal `error` events\n- no provider-specific resume/retry inside the stream function itself, except Codex websocket-to-SSE transport fallback before replay-unsafe output is emitted\n- higher-level retries are handled in `AgentSession` auto-retry logic (message-level retry, not stream-chunk replay)\n\n## Cancellation boundaries\n\nCancellation is layered:\n\n- AI provider request: `options.signal` is passed into provider client stream call.\n- Provider wrapper: after stream loop, aborted signal forces error path (`\"Request was aborted\"`).\n- Agent loop: checks `signal.aborted` before handling each provider event and can synthesize an aborted assistant message from the latest partial.\n- Session/agent controls: `AgentSession.abort()` -> `agent.abort()` -> shared abort controller cancellation.\n\nTool execution cancellation is separate from model stream cancellation:\n\n- tool runners use `AbortSignal.any([agentSignal, steeringAbortSignal])`\n- steering interrupts can abort remaining tool execution while preserving already-produced tool results\n\n## Backpressure boundaries\n\nThere is no hard backpressure mechanism between provider SDK stream and downstream consumers:\n\n- `EventStream` uses in-memory queues with no max size\n- the throttled partial-JSON re-parse reduces per-delta CPU cost but does not slow provider intake\n- if consumers lag significantly, queued events can grow until completion\n\nCurrent design favors responsiveness and simple ordering over bounded-buffer flow control.\n\n## How stream events surface as agent/session events\n\n`agentLoop.streamAssistantResponse()` bridges `AssistantMessageEvent` to `AgentEvent`:\n\n- on `start`: pushes placeholder assistant message and emits `message_start`\n- on block events (`text_*`, `thinking_*`, `toolcall_*`): updates last assistant message, emits `message_update` with raw `assistantMessageEvent`\n- on terminal (`done`/`error`): resolves final message from `response.result()`, emits `message_end`\n\n`AgentSession` then consumes those events for session-level behaviors:\n\n- TTSR watches `message_update.assistantMessageEvent` for `text_delta`, `thinking_delta`, and `toolcall_delta`\n- streaming edit guard inspects `toolcall_delta`/`toolcall_end` on `edit` calls and can abort early\n- persistence writes finalized messages at `message_end`\n- auto-retry examines assistant `stopReason === \"error\"` plus `errorMessage` heuristics\n\n## Unified vs provider-specific responsibilities\n\nUnified (common contract):\n\n- event shape (`AssistantMessageEvent`)\n- final result extraction (`done`/`error`)\n- immediate in-order event delivery\n- agent/session event propagation model\n\nProvider-specific (not fully abstracted):\n\n- upstream event taxonomies and mapping logic\n- stop-reason translation tables\n- tool-call ID conventions\n- reasoning/thinking block semantics and signatures\n- usage token semantics and availability timing\n- message conversion constraints per API\n\n## Implementation files\n\n- [`../../ai/src/stream.ts`](../packages/ai/src/stream.ts) — provider dispatch, option mapping, API key/session plumbing, custom API dispatch, and provider-specific credential handling.\n- [`../../ai/src/utils/event-stream.ts`](../packages/ai/src/utils/event-stream.ts) — generic stream queue + final-result resolution.\n- [`../../ai/src/utils/json-parse.ts`](../packages/ai/src/utils/json-parse.ts) — partial JSON parsing for streamed tool arguments.\n- [`../../ai/src/providers/anthropic.ts`](../packages/ai/src/providers/anthropic.ts) — Anthropic event translation and tool JSON delta accumulation.\n- [`../../ai/src/providers/openai-responses.ts`](../packages/ai/src/providers/openai-responses.ts), [`openai-responses-shared.ts`](../packages/ai/src/providers/openai-responses-shared.ts), [`openai-codex-responses.ts`](../packages/ai/src/providers/openai-codex-responses.ts), [`azure-openai-responses.ts`](../packages/ai/src/providers/azure-openai-responses.ts) — Responses-family event translation and status mapping.\n- [`../../ai/src/providers/google.ts`](../packages/ai/src/providers/google.ts), [`google-gemini-cli.ts`](../packages/ai/src/providers/google-gemini-cli.ts), [`google-vertex.ts`](../packages/ai/src/providers/google-vertex.ts) — Gemini stream chunk-to-block translation variants.\n- [`../../ai/src/providers/google-shared.ts`](../packages/ai/src/providers/google-shared.ts) — Gemini finish-reason mapping and shared conversion rules.\n- [`../../ai/src/providers/amazon-bedrock.ts`](../packages/ai/src/providers/amazon-bedrock.ts), [`openai-completions.ts`](../packages/ai/src/providers/openai-completions.ts), [`ollama.ts`](../packages/ai/src/providers/ollama.ts), [`cursor.ts`](../packages/ai/src/providers/cursor.ts), [`pi-native-client.ts`](../packages/ai/src/providers/pi-native-client.ts) — additional built-in stream adapters using the same event contract.\n- [`../../agent/src/agent-loop.ts`](../packages/agent/src/agent-loop.ts) — provider stream consumption and `message_update` bridging.\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — session-level handling of streaming updates, abort, retry, and persistence.\n",
-	"providers.md": "# Providers\n\nProviders are the model backends `omp` can route requests to: Anthropic, OpenAI, Google Gemini, Groq, OpenRouter, Mistral, xAI, local engines like Ollama, hosted gateways, custom `models.yml` providers, and providers registered by extensions.\n\nA **provider** is the account or backend namespace, such as `anthropic`, `openai`, `google`, or `ollama`. A **model** is a concrete model under that provider, selected as `provider/model-id`, such as `anthropic/claude-opus-4-6`. Disabling a provider removes every model under it from selection; if you only want to narrow individual models, use model settings instead.\n\nThis page covers how providers become available, how credentials are resolved, the provider/environment-variable map, local engines, disabling providers, and custom providers. For model selection and the full `models.yml` schema, see [Model and Provider Configuration](./models.md). For config-file locations and merge precedence, see [Settings](./settings.md). For credential storage and login flows in depth, see [Secrets and credentials](./secrets.md). For the complete environment-variable reference, see [Environment variables](./environment-variables.md). For local engine setup, see [Local models](./local-models.md). For context-file discovery providers, see [Context files](./context-files.md).\n\n## How `omp` decides a provider is available\n\nAt startup the model registry assembles its catalog from four sources, in order:\n\n1. The bundled model catalog (every built-in provider and its known models).\n2. Custom provider and model entries from `~/.omp/agent/models.yml`.\n3. Runtime-discovered models for providers that support discovery (local engines and discovery-enabled gateways).\n4. Providers and models registered by extensions.\n\nThe registry can hold a model even when it is not currently selectable. A model becomes **available** only when both conditions hold:\n\n1. its provider ID is **not** in the effective `disabledProviders` list; **and**\n2. the provider is either **keyless** (an implicit local provider, or a custom provider with `auth: none`) **or** has resolvable credentials.\n\n`disabledProviders` is checked *before* credentials. If a provider ID is disabled, no stored key, OAuth session, environment variable, `.env` entry, or `models.yml` `apiKey` will make it selectable — the provider's models are dropped from availability regardless of credentials. Removing the ID from the effective list restores them.\n\nKeyless local engines are a special case: `ollama`, `llama.cpp`, and `lm-studio` are treated as keyless when no key is configured, so their discovered models are selectable as soon as the engine answers — no login required. See [Built-in local engines](#built-in-local-engines).\n\n## Credentials and precedence\n\nWhen a provider needs an API key, `omp` resolves it in this order (first match wins):\n\n1. **Runtime override** — a key supplied for the current process, e.g. CLI `--api-key`. Never persisted.\n2. **`models.yml` config key** — an `apiKey` pinned on a custom provider, registered as a config-sourced bearer. This deliberately beats stored OAuth, so a key supplied for a custom `baseUrl`/gateway is honored instead of forwarding an upstream OAuth token the proxy would reject.\n3. **Stored API key** — an API-key credential saved in the auth store.\n4. **Stored OAuth credential** — refreshed when needed; multiple accounts are ranked/rotated automatically.\n5. **Provider environment variable** — including values loaded from `.env` files (see [the env-var table](#environment-variables-and-env-files)).\n6. **`models.yml` fallback resolver** — keys for custom providers not otherwise registered.\n\nStored credentials live in the auth store at `~/.omp/agent/agent.db` for local auth, or in the configured auth-broker snapshot when running in broker mode. (`PI_CODING_AGENT_DIR` relocates the `~/.omp/agent` base, and the auth store moves with it.)\n\n### OAuth vs API key, and provider-scoped logins\n\nLogins are **provider-scoped**: authenticating `anthropic` does not authenticate `openai`, and each provider tracks its own credentials. A disabled provider stays disabled even with valid stored auth.\n\nUse the interactive slash commands inside a session:\n\n- `/login` — opens the OAuth/key selector. `/login <provider>` jumps straight to one provider (e.g. `/login anthropic`); for an OAuth flow that needs a pasted callback, run `/login <redirect-url>` to complete it.\n- `/logout` — opens the provider selector to remove stored credentials.\n\nFor headless or remote setups backed by a shared auth broker, the CLI exposes `omp auth-broker login <provider>` / `omp auth-broker logout` (and `status`, `list`, `import`, `migrate`). See [Secrets and credentials](./secrets.md) for the broker model.\n\nWhen a model has no credentials, `omp` tells you to run `/login` or set the provider's environment variable.\n\n### Pinning a key in `models.yml`\n\nA custom provider's `apiKey` is resolved as **environment-variable-name-or-literal**: if the value names an existing environment variable, that variable's value is used; otherwise the string itself is the key. Prefixing the value with `!` runs it as a shell command and uses the trimmed stdout (see [Model and Provider Configuration](./models.md) for the full value syntax).\n\n```yaml\n# ~/.omp/agent/models.yml\nproviders:\n  my-gateway:\n    baseUrl: https://gateway.example.com/v1\n    api: openai-completions\n    apiKey: MY_GATEWAY_API_KEY # reads this env var if set, else literal text\n    models:\n      - id: claude-sonnet\n        name: Claude Sonnet via Gateway\n        contextWindow: 200000\n        maxTokens: 8192\n```\n\nIf `authHeader: true` is set on a custom provider, the resolved key is injected as an `Authorization: Bearer <key>` header on every request to that provider.\n\n## Environment variables and `.env` files\n\nEach provider has one or more environment variables that supply a key when no stored credential exists. The table below is the verified provider → variable map; the full catalog is large, so it is split into core and additional providers. OAuth-backed providers can also accept a token variable in addition to (or instead of) an API key.\n\n### Core providers\n\n| Provider ID | Environment variable(s) |\n|---|---|\n| `anthropic` | `ANTHROPIC_OAUTH_TOKEN`, then `ANTHROPIC_API_KEY` (Foundry mode prefers `ANTHROPIC_FOUNDRY_API_KEY` when `CLAUDE_CODE_USE_FOUNDRY=true`) |\n| `openai` | `OPENAI_API_KEY` |\n| `openai-codex` | `OPENAI_CODEX_OAUTH_TOKEN` |\n| `google` | `GEMINI_API_KEY` |\n| `google-vertex` | `GOOGLE_CLOUD_API_KEY`, or Application Default Credentials (`GOOGLE_APPLICATION_CREDENTIALS` + `GOOGLE_CLOUD_PROJECT` + `GOOGLE_CLOUD_LOCATION`) |\n| `groq` | `GROQ_API_KEY` |\n| `openrouter` | `OPENROUTER_API_KEY` |\n| `mistral` | `MISTRAL_API_KEY` |\n| `xai` | `XAI_API_KEY` |\n| `xai-oauth` | `XAI_OAUTH_TOKEN`, then `XAI_API_KEY` |\n| `github-copilot` | `COPILOT_GITHUB_TOKEN` |\n| `cursor` | `CURSOR_ACCESS_TOKEN` |\n| `azure-openai-responses` | `AZURE_OPENAI_API_KEY` |\n| `amazon-bedrock` | `AWS_PROFILE`, or `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`, or an ECS/IRSA credential chain |\n\n### Additional hosted providers\n\n| Provider ID | Environment variable(s) |\n|---|---|\n| `cerebras` | `CEREBRAS_API_KEY` |\n| `deepseek` | `DEEPSEEK_API_KEY` |\n| `fireworks` | `FIREWORKS_API_KEY` |\n| `together` | `TOGETHER_API_KEY` |\n| `nvidia` | `NVIDIA_API_KEY` |\n| `huggingface` | `HUGGINGFACE_HUB_TOKEN`, then `HF_TOKEN` |\n| `moonshot` | `MOONSHOT_API_KEY` |\n| `kimi-code` | `KIMI_API_KEY` |\n| `nanogpt` | `NANO_GPT_API_KEY` |\n| `venice` | `VENICE_API_KEY` |\n| `vercel-ai-gateway` | `AI_GATEWAY_API_KEY` (also `VERCEL_AI_GATEWAY_API_KEY` for catalog discovery) |\n| `cloudflare-ai-gateway` | `CLOUDFLARE_AI_GATEWAY_API_KEY` |\n| `litellm` | `LITELLM_API_KEY` |\n| `kilo` | `KILO_API_KEY` |\n| `zai` | `ZAI_API_KEY` |\n| `zenmux` | `ZENMUX_API_KEY` |\n| `zhipu-coding-plan` | `ZHIPU_API_KEY` |\n| `qianfan` | `QIANFAN_API_KEY` |\n| `qwen-portal` | `QWEN_OAUTH_TOKEN`, then `QWEN_PORTAL_API_KEY` |\n| `synthetic` | `SYNTHETIC_API_KEY` |\n| `minimax` | `MINIMAX_API_KEY` |\n| `alibaba-coding-plan` | `ALIBABA_CODING_PLAN_API_KEY` |\n| `aimlapi` | `AIMLAPI_API_KEY` |\n| `gitlab-duo` | `GITLAB_TOKEN` |\n| `opencode-zen`, `opencode-go` | `OPENCODE_API_KEY` |\n| `firepass` | `FIREPASS_API_KEY` |\n| `wafer-pass` | `WAFER_PASS_API_KEY` |\n| `wafer-serverless` | `WAFER_SERVERLESS_API_KEY` |\n| `xiaomi` | `XIAOMI_API_KEY` |\n| `ollama-cloud` | `OLLAMA_CLOUD_API_KEY` |\n| `ollama` | `OLLAMA_API_KEY` (optional; local discovery is keyless by default) |\n| `lm-studio` | `LM_STUDIO_API_KEY` (optional; keyless by default) |\n| `llama.cpp` | `LLAMA_CPP_API_KEY` (only when the server requires auth) |\n\nOAuth-backed providers such as `anthropic`, `github-copilot`, `cursor`, `ollama-cloud`, `qwen-portal`, `xai-oauth`, `wafer-pass`, `wafer-serverless`, `google-gemini-cli`, and `google-antigravity` are normally reached through `/login` rather than an environment variable. See [Environment variables](./environment-variables.md) for search-tool and configuration variables not listed here.\n\n### `.env` discovery and precedence\n\n`omp` eagerly loads `.env` files into the process environment before any provider lookup. It reads four files and, for each variable, the **first** source that defines it wins. Effective precedence, high to low:\n\n1. The process environment inherited by `omp` (already-set variables always win).\n2. `<cwd>/.env`\n3. `~/.omp/agent/.env`\n4. `~/.omp/.env`\n5. `~/.env`\n\nA variable already present in the process environment is never overwritten by a `.env` file. Among the files, a value set in `<cwd>/.env` wins over `~/.omp/agent/.env`, which wins over `~/.omp/.env`, which wins over `~/.env`. So a shell-exported `OPENAI_API_KEY` beats every `.env` file, and a project's `<cwd>/.env` beats your home `~/.env`.\n\nProject-local `.env` is the simplest way to make one repository use a project-specific gateway, key, or local endpoint:\n\n```dotenv\n# <project>/.env\nOPENROUTER_API_KEY=sk-or-...\nOLLAMA_BASE_URL=http://127.0.0.1:11434\n```\n\n`.env` parsing is intentionally minimal:\n\n- blank lines and lines starting with `#` are ignored;\n- keys must match `[A-Za-z_][A-Za-z0-9_]*` (shell-identifier shape) — other names are dropped;\n- values may be wrapped in single or double quotes, which are stripped;\n- values containing a NUL byte are dropped;\n- an `OMP_`-prefixed key is also mirrored to the matching `PI_`-prefixed name.\n\n## Built-in local engines\n\nThree local engines are discovered automatically without needing a `models.yml` entry. Each uses a base URL that can be overridden by an environment variable:\n\n| Provider ID | Base URL (env override → default) | Notes |\n|---|---|---|\n| `ollama` | `OLLAMA_BASE_URL`, then `OLLAMA_HOST` (normalized), else `http://127.0.0.1:11434` | Keyless by default. |\n| `llama.cpp` | `LLAMA_CPP_BASE_URL`, else `http://127.0.0.1:8080` | Keyless unless a key is stored for `llama.cpp`. |\n| `lm-studio` | `LM_STUDIO_BASE_URL`, else `http://127.0.0.1:1234/v1` | Keyless by default. |\n\nThese implicit engines are **skipped** when:\n\n- a provider with the same ID is already configured in `models.yml` (your explicit config wins); or\n- the provider ID appears in the effective `disabledProviders` list.\n\nFor installing and running these engines, see [Local models](./local-models.md).\n\n## Disabling model providers\n\nUse the `disabledProviders` setting to remove a provider's models from selection:\n\n```yaml\n# ~/.omp/agent/config.yml or <project>/.omp/config.yml\ndisabledProviders:\n  - anthropic\n  - openai\n  - google\n  - groq\n```\n\nProvider IDs are matched exactly. Disable `google` to hide the Google Gemini API provider; the OAuth-backed Google providers `google-gemini-cli` and `google-antigravity` are separate IDs and must be disabled individually. Disable `ollama`, `llama.cpp`, or `lm-studio` to stop local discovery for that engine.\n\n`disabledProviders` applies uniformly to:\n\n- bundled catalog providers;\n- custom `models.yml` providers;\n- runtime-discovered provider models;\n- extension-registered providers;\n- implicit local engines.\n\nDisabling a provider does not delete its stored credentials — re-enable it by removing its ID from the effective list.\n\n## Project-specific provider control\n\nProject settings live in `<project>/.omp/config.yml`. Use them when one repository must allow or hide a different provider set than your global default:\n\n```yaml\n# <project>/.omp/config.yml\ndisabledProviders:\n  - openai\n  - openrouter\n```\n\nSettings arrays are **replaced** wholesale by the higher-precedence layer, not merged or appended. If the global file disables three providers and the project file disables one, the project sees only the project list:\n\n```yaml\n# ~/.omp/agent/config.yml\ndisabledProviders:\n  - anthropic\n  - openai\n  - google\n\n# <project>/.omp/config.yml\ndisabledProviders:\n  - groq\n```\n\nEffective result inside the project:\n\n```json\n[\"groq\"]\n```\n\nThe project array re-enables `anthropic`, `openai`, and `google` for sessions launched from that project. If you want a project to *add* to the global set, repeat the global IDs in the project file. See [Settings](./settings.md) for the full precedence chain, including `--config` overlays and runtime overrides.\n\n## Path-scoped `disabledProviders`\n\n`disabledProviders` can mix plain string entries (apply everywhere) with path-scoped entries (apply only when the current working directory matches a configured path):\n\n```yaml\ndisabledProviders:\n  - ollama\n  - path: ~/projects/sensitive\n    providers:\n      - anthropic\n      - openai\n  - paths:\n      - ~/work/client-a\n      - ~/work/client-b\n    values:\n      - openrouter\n```\n\n- Bare string entries always apply.\n- A scoped entry applies when the current working directory **is** the configured path or sits **under** it. `~` expands to the home directory.\n- Accepted path keys: `path`, `paths`, `pathPrefix`, `pathPrefixes`.\n- Accepted value keys: `providers`, `values`, `items`.\n\nFor the example above:\n\n- `ollama` is disabled everywhere.\n- `anthropic` and `openai` are additionally disabled under `~/projects/sensitive`.\n- `openrouter` is additionally disabled under `~/work/client-a` and `~/work/client-b`.\n\nPath scopes are resolved **after** the settings merge. Because a higher-precedence layer replaces the whole array, a project-level `disabledProviders` array drops any scoped entries that only existed in the global array. `enabledModels` is the only other setting that supports the same path-scoped form. See [Settings](./settings.md) for details.\n\n## Provider IDs vs discovery provider IDs\n\n`disabledProviders` uses a **single shared ID namespace** that gates two different subsystems:\n\n- **Model providers** — the backends on this page (`anthropic`, `openai`, `ollama`, a custom `models.yml` ID, …). Disabling one removes its models from selection.\n- **Discovery providers** — sources of context files, MCP servers, commands, skills, hooks, tools, prompts, and settings. Disabling one stops that source from contributing capability items.\n\n| Entry type | Examples | Effect |\n|---|---|---|\n| Model provider ID | `anthropic`, `openai`, `google`, `groq`, `openrouter`, `ollama`, `my-gateway` | Removes that provider's models from availability. |\n| Discovery provider ID | `native`, `claude`, `codex`, `gemini`, `agents`, `github` | Stops that discovery source from contributing capability items. |\n\nWatch the related names. The Google Gemini **API** models use the model provider ID `google`; `gemini` is a **discovery** provider ID (the source that reads `GEMINI.md`), not the Google model provider. Use discovery IDs only when you intend to disable an entire config source. See [Context files](./context-files.md) for the discovery-provider side.\n\n## Custom providers in `models.yml`\n\nCustom providers live in `~/.omp/agent/models.yml` under `providers:`. A provider ID defined there participates in the same selection, credential resolution, and `disabledProviders` rules as built-in providers.\n\nMinimal OpenAI-compatible provider:\n\n```yaml\nproviders:\n  my-openai-compatible:\n    baseUrl: https://api.example.com/v1\n    api: openai-completions\n    apiKey: MY_OPENAI_COMPATIBLE_KEY # env-var-name or literal\n    models:\n      - id: fast-chat\n        name: Fast Chat\n        contextWindow: 128000\n        maxTokens: 8192\n```\n\nKeyless local provider (no credentials required):\n\n```yaml\nproviders:\n  local-proxy:\n    baseUrl: http://127.0.0.1:4000/v1\n    api: openai-completions\n    auth: none\n    models:\n      - id: local-model\n        name: Local Model\n        contextWindow: 32768\n        maxTokens: 4096\n```\n\nDiscovery-enabled provider (models fetched from the endpoint at runtime):\n\n```yaml\nproviders:\n  team-proxy:\n    baseUrl: https://models.example.com/v1\n    apiKey: TEAM_PROXY_API_KEY\n    authHeader: true # send Authorization: Bearer <resolved key>\n    disableStrictTools: true\n    discovery:\n      type: proxy\n```\n\nFor the full schema, all allowed `api` values, discovery `type`s, model overrides, and equivalence settings, see [Model and Provider Configuration](./models.md).\n\nTo disable a custom provider, list its ID exactly:\n\n```yaml\ndisabledProviders:\n  - my-openai-compatible\n  - team-proxy\n```\n\n## Troubleshooting\n\n**A provider's models are not selectable.** Confirm the provider has credentials (`/login <provider>`, an exported environment variable, or a `models.yml` `apiKey`) and that its ID is not in the effective `disabledProviders` list. Remember the rule: not disabled **and** (keyless **or** has credentials). Keyless local engines only appear once the engine is actually running and responding.\n\n**The wrong key is being used (a stale key from `.env`).** Resolution favors runtime `--api-key`, then a `models.yml` config key, then stored credentials, then environment/`.env`. An already-set process environment variable also beats every `.env` file, and `<cwd>/.env` beats `~/.env`. If an unexpected key wins, check for an exported shell variable and the four `.env` files in precedence order, and clear the one that should not apply.\n\n**A provider still appears even though I disabled it.** `disabledProviders` arrays are replaced, not merged: a project `<project>/.omp/config.yml` array fully overrides the global one. Verify the *effective* list for the directory you are in (path-scoped entries only apply at or under their configured path), and confirm the ID is spelled exactly. Use `omp config get disabledProviders` to inspect the merged value (see [Settings](./settings.md)).\n\n**A discovery provider name had no effect on models (or vice-versa).** The ID namespace is shared. `gemini`, `codex`, `claude`, `native`, and `agents` are discovery-source IDs; the Google model backend is `google`. Make sure you are disabling the right kind of provider.\n\n**A custom `models.yml` provider does not load.** A YAML or schema error makes the registry skip the custom file. Validate the file with `omp models` (use `omp models find <substr>` to scope it to one provider), confirm each provider has a `baseUrl`, a valid `api`, and at least one model entry, and that an implicit local engine is not silently shadowing it (an explicit `ollama`/`lm-studio`/`llama.cpp` entry replaces the built-in discovery for that ID). See [Model and Provider Configuration](./models.md).\n",
+	"providers.md": "# Providers\n\nProviders are the model backends `omp` can route requests to: Anthropic, OpenAI, Google Gemini, Groq, OpenRouter, Mistral, xAI, local engines like Ollama, hosted gateways, custom `models.yml` providers, and providers registered by extensions.\n\nA **provider** is the account or backend namespace, such as `anthropic`, `openai`, `google`, or `ollama`. A **model** is a concrete model under that provider, selected as `provider/model-id`, such as `anthropic/claude-opus-4-6`. Disabling a provider removes every model under it from selection; if you only want to narrow individual models, use model settings instead.\n\nThis page covers how providers become available, how credentials are resolved, the provider/environment-variable map, local engines, disabling providers, and custom providers. For model selection and the full `models.yml` schema, see [Model and Provider Configuration](./models.md). For config-file locations and merge precedence, see [Settings](./settings.md). For credential storage and login flows in depth, see [Secrets and credentials](./secrets.md). For the complete environment-variable reference, see [Environment variables](./environment-variables.md). For local engine setup, see [Local models](./local-models.md). For context-file discovery providers, see [Context files](./context-files.md).\n\n## How `omp` decides a provider is available\n\nAt startup the model registry assembles its catalog from four sources, in order:\n\n1. The bundled model catalog (every built-in provider and its known models).\n2. Custom provider and model entries from `~/.omp/agent/models.yml`.\n3. Runtime-discovered models for providers that support discovery (local engines and discovery-enabled gateways).\n4. Providers and models registered by extensions.\n\nThe registry can hold a model even when it is not currently selectable. A model becomes **available** only when both conditions hold:\n\n1. its provider ID is **not** in the effective `disabledProviders` list; **and**\n2. the provider is either **keyless** (an implicit local provider, or a custom provider with `auth: none`) **or** has resolvable credentials.\n\n`disabledProviders` is checked *before* credentials. If a provider ID is disabled, no stored key, OAuth session, environment variable, `.env` entry, or `models.yml` `apiKey` will make it selectable — the provider's models are dropped from availability regardless of credentials. Removing the ID from the effective list restores them.\n\nKeyless local engines are a special case: `ollama`, `llama.cpp`, and `lm-studio` are treated as keyless when no key is configured, so their discovered models are selectable as soon as the engine answers — no login required. See [Built-in local engines](#built-in-local-engines).\n\n## Credentials and precedence\n\nWhen a provider needs an API key, `omp` resolves it in this order (first match wins):\n\n1. **Runtime override** — a key supplied for the current process, e.g. CLI `--api-key`. Never persisted.\n2. **`models.yml` config key** — an `apiKey` pinned on a custom provider, registered as a config-sourced bearer. This deliberately beats stored OAuth, so a key supplied for a custom `baseUrl`/gateway is honored instead of forwarding an upstream OAuth token the proxy would reject.\n3. **Stored API key** — an API-key credential saved in the auth store.\n4. **Stored OAuth credential** — refreshed when needed; multiple accounts are ranked/rotated automatically.\n5. **Provider environment variable** — including values loaded from `.env` files (see [the env-var table](#environment-variables-and-env-files)).\n6. **`models.yml` fallback resolver** — keys for custom providers not otherwise registered.\n\nStored credentials live in the auth store at `~/.omp/agent/agent.db` for local auth, or in the configured auth-broker snapshot when running in broker mode. (`PI_CODING_AGENT_DIR` relocates the `~/.omp/agent` base, and the auth store moves with it.)\n\n### OAuth vs API key, and provider-scoped logins\n\nLogins are **provider-scoped**: authenticating `anthropic` does not authenticate `openai`, and each provider tracks its own credentials. A disabled provider stays disabled even with valid stored auth.\n\nUse the interactive slash commands inside a session:\n\n- `/login` — opens the OAuth/key selector. `/login <provider>` jumps straight to one provider (e.g. `/login anthropic`); for an OAuth flow that needs a pasted callback, run `/login <redirect-url>` to complete it.\n- `/logout` — opens the provider selector to remove stored credentials.\n\nFor headless or remote setups backed by a shared auth broker, the CLI exposes `omp auth-broker login <provider>` / `omp auth-broker logout` (and `status`, `list`, `import`, `migrate`). See [Secrets and credentials](./secrets.md) for the broker model.\n\nWhen a model has no credentials, `omp` tells you to run `/login` or set the provider's environment variable.\n\n### Pinning a key in `models.yml`\n\nA custom provider's `apiKey` is resolved as **environment-variable-name-or-literal**: if the value names an existing environment variable, that variable's value is used; otherwise the string itself is the key. Prefixing the value with `!` runs it as a shell command and uses the trimmed stdout (see [Model and Provider Configuration](./models.md) for the full value syntax).\n\n```yaml\n# ~/.omp/agent/models.yml\nproviders:\n  my-gateway:\n    baseUrl: https://gateway.example.com/v1\n    api: openai-completions\n    apiKey: MY_GATEWAY_API_KEY # reads this env var if set, else literal text\n    models:\n      - id: claude-sonnet\n        name: Claude Sonnet via Gateway\n        contextWindow: 200000\n        maxTokens: 8192\n```\n\nIf `authHeader: true` is set on a custom provider, the resolved key is injected as an `Authorization: Bearer <key>` header on every request to that provider.\n\n## Environment variables and `.env` files\n\nEach provider has one or more environment variables that supply a key when no stored credential exists. The table below is the verified provider → variable map; the full catalog is large, so it is split into core and additional providers. OAuth-backed providers can also accept a token variable in addition to (or instead of) an API key.\n\n### Core providers\n\n| Provider ID | Environment variable(s) |\n|---|---|\n| `anthropic` | `ANTHROPIC_OAUTH_TOKEN`, then `ANTHROPIC_API_KEY` (Foundry mode prefers `ANTHROPIC_FOUNDRY_API_KEY` when `CLAUDE_CODE_USE_FOUNDRY=true`) |\n| `openai` | `OPENAI_API_KEY` |\n| `openai-codex` | `OPENAI_CODEX_OAUTH_TOKEN` |\n| `google` | `GEMINI_API_KEY` |\n| `google-vertex` | `GOOGLE_CLOUD_API_KEY`, or Application Default Credentials (`GOOGLE_APPLICATION_CREDENTIALS` + `GOOGLE_CLOUD_PROJECT` + `GOOGLE_CLOUD_LOCATION`) |\n| `groq` | `GROQ_API_KEY` |\n| `openrouter` | `OPENROUTER_API_KEY` |\n| `mistral` | `MISTRAL_API_KEY` |\n| `xai` | `XAI_API_KEY` |\n| `xai-oauth` | `XAI_OAUTH_TOKEN`, then `XAI_API_KEY` |\n| `github-copilot` | `COPILOT_GITHUB_TOKEN` |\n| `cursor` | `CURSOR_ACCESS_TOKEN` |\n| `azure-openai-responses` | `AZURE_OPENAI_API_KEY` |\n| `amazon-bedrock` | `AWS_PROFILE`, or `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`, or an ECS/IRSA credential chain |\n\n### Additional hosted providers\n\n| Provider ID | Environment variable(s) |\n|---|---|\n| `cerebras` | `CEREBRAS_API_KEY` |\n| `deepseek` | `DEEPSEEK_API_KEY` |\n| `fireworks` | `FIREWORKS_API_KEY` |\n| `together` | `TOGETHER_API_KEY` |\n| `nvidia` | `NVIDIA_API_KEY` |\n| `huggingface` | `HUGGINGFACE_HUB_TOKEN`, then `HF_TOKEN` |\n| `moonshot` | `MOONSHOT_API_KEY` |\n| `kimi-code` | `KIMI_API_KEY` |\n| `nanogpt` | `NANO_GPT_API_KEY` |\n| `venice` | `VENICE_API_KEY` |\n| `vercel-ai-gateway` | `AI_GATEWAY_API_KEY` (also `VERCEL_AI_GATEWAY_API_KEY` for catalog discovery) |\n| `cloudflare-ai-gateway` | `CLOUDFLARE_AI_GATEWAY_API_KEY` |\n| `litellm` | `LITELLM_API_KEY` |\n| `kilo` | `KILO_API_KEY` |\n| `zai` | `ZAI_API_KEY` |\n| `zenmux` | `ZENMUX_API_KEY` |\n| `zhipu-coding-plan` | `ZHIPU_API_KEY` |\n| `umans` | `UMANS_AI_CODING_PLAN_API_KEY` |\n| `qianfan` | `QIANFAN_API_KEY` |\n| `qwen-portal` | `QWEN_OAUTH_TOKEN`, then `QWEN_PORTAL_API_KEY` |\n| `synthetic` | `SYNTHETIC_API_KEY` |\n| `minimax` | `MINIMAX_API_KEY` |\n| `alibaba-coding-plan` | `ALIBABA_CODING_PLAN_API_KEY` |\n| `aimlapi` | `AIMLAPI_API_KEY` |\n| `gitlab-duo` | `GITLAB_TOKEN` |\n| `opencode-zen`, `opencode-go` | `OPENCODE_API_KEY` |\n| `firepass` | `FIREPASS_API_KEY` |\n| `wafer-pass` | `WAFER_PASS_API_KEY` |\n| `wafer-serverless` | `WAFER_SERVERLESS_API_KEY` |\n| `xiaomi` | `XIAOMI_API_KEY` |\n| `ollama-cloud` | `OLLAMA_CLOUD_API_KEY` |\n| `ollama` | `OLLAMA_API_KEY` (optional; local discovery is keyless by default) |\n| `lm-studio` | `LM_STUDIO_API_KEY` (optional; keyless by default) |\n| `llama.cpp` | `LLAMA_CPP_API_KEY` (only when the server requires auth) |\n\nOAuth-backed providers such as `anthropic`, `github-copilot`, `cursor`, `ollama-cloud`, `qwen-portal`, `xai-oauth`, `wafer-pass`, `wafer-serverless`, `google-gemini-cli`, and `google-antigravity` are normally reached through `/login` rather than an environment variable. See [Environment variables](./environment-variables.md) for search-tool and configuration variables not listed here.\n\n### `.env` discovery and precedence\n\n`omp` eagerly loads `.env` files into the process environment before any provider lookup. It reads four files and, for each variable, the **first** source that defines it wins. Effective precedence, high to low:\n\n1. The process environment inherited by `omp` (already-set variables always win).\n2. `<cwd>/.env`\n3. `~/.omp/agent/.env`\n4. `~/.omp/.env`\n5. `~/.env`\n\nA variable already present in the process environment is never overwritten by a `.env` file. Among the files, a value set in `<cwd>/.env` wins over `~/.omp/agent/.env`, which wins over `~/.omp/.env`, which wins over `~/.env`. So a shell-exported `OPENAI_API_KEY` beats every `.env` file, and a project's `<cwd>/.env` beats your home `~/.env`.\n\nProject-local `.env` is the simplest way to make one repository use a project-specific gateway, key, or local endpoint:\n\n```dotenv\n# <project>/.env\nOPENROUTER_API_KEY=sk-or-...\nOLLAMA_BASE_URL=http://127.0.0.1:11434\n```\n\n`.env` parsing is intentionally minimal:\n\n- blank lines and lines starting with `#` are ignored;\n- keys must match `[A-Za-z_][A-Za-z0-9_]*` (shell-identifier shape) — other names are dropped;\n- values may be wrapped in single or double quotes, which are stripped;\n- values containing a NUL byte are dropped;\n- an `OMP_`-prefixed key is also mirrored to the matching `PI_`-prefixed name.\n\n## Built-in local engines\n\nThree local engines are discovered automatically without needing a `models.yml` entry. Each uses a base URL that can be overridden by an environment variable:\n\n| Provider ID | Base URL (env override → default) | Notes |\n|---|---|---|\n| `ollama` | `OLLAMA_BASE_URL`, then `OLLAMA_HOST` (normalized), else `http://127.0.0.1:11434` | Keyless by default. |\n| `llama.cpp` | `LLAMA_CPP_BASE_URL`, else `http://127.0.0.1:8080` | Keyless unless a key is stored for `llama.cpp`. |\n| `lm-studio` | `LM_STUDIO_BASE_URL`, else `http://127.0.0.1:1234/v1` | Keyless by default. |\n\nThese implicit engines are **skipped** when:\n\n- a provider with the same ID is already configured in `models.yml` (your explicit config wins); or\n- the provider ID appears in the effective `disabledProviders` list.\n\nFor installing and running these engines, see [Local models](./local-models.md).\n\n## Disabling model providers\n\nUse the `disabledProviders` setting to remove a provider's models from selection:\n\n```yaml\n# ~/.omp/agent/config.yml or <project>/.omp/config.yml\ndisabledProviders:\n  - anthropic\n  - openai\n  - google\n  - groq\n```\n\nProvider IDs are matched exactly. Disable `google` to hide the Google Gemini API provider; the OAuth-backed Google providers `google-gemini-cli` and `google-antigravity` are separate IDs and must be disabled individually. Disable `ollama`, `llama.cpp`, or `lm-studio` to stop local discovery for that engine.\n\n`disabledProviders` applies uniformly to:\n\n- bundled catalog providers;\n- custom `models.yml` providers;\n- runtime-discovered provider models;\n- extension-registered providers;\n- implicit local engines.\n\nDisabling a provider does not delete its stored credentials — re-enable it by removing its ID from the effective list.\n\n## Project-specific provider control\n\nProject settings live in `<project>/.omp/config.yml`. Use them when one repository must allow or hide a different provider set than your global default:\n\n```yaml\n# <project>/.omp/config.yml\ndisabledProviders:\n  - openai\n  - openrouter\n```\n\nSettings arrays are **replaced** wholesale by the higher-precedence layer, not merged or appended. If the global file disables three providers and the project file disables one, the project sees only the project list:\n\n```yaml\n# ~/.omp/agent/config.yml\ndisabledProviders:\n  - anthropic\n  - openai\n  - google\n\n# <project>/.omp/config.yml\ndisabledProviders:\n  - groq\n```\n\nEffective result inside the project:\n\n```json\n[\"groq\"]\n```\n\nThe project array re-enables `anthropic`, `openai`, and `google` for sessions launched from that project. If you want a project to *add* to the global set, repeat the global IDs in the project file. See [Settings](./settings.md) for the full precedence chain, including `--config` overlays and runtime overrides.\n\n## Path-scoped `disabledProviders`\n\n`disabledProviders` can mix plain string entries (apply everywhere) with path-scoped entries (apply only when the current working directory matches a configured path):\n\n```yaml\ndisabledProviders:\n  - ollama\n  - path: ~/projects/sensitive\n    providers:\n      - anthropic\n      - openai\n  - paths:\n      - ~/work/client-a\n      - ~/work/client-b\n    values:\n      - openrouter\n```\n\n- Bare string entries always apply.\n- A scoped entry applies when the current working directory **is** the configured path or sits **under** it. `~` expands to the home directory.\n- Accepted path keys: `path`, `paths`, `pathPrefix`, `pathPrefixes`.\n- Accepted value keys: `providers`, `values`, `items`.\n\nFor the example above:\n\n- `ollama` is disabled everywhere.\n- `anthropic` and `openai` are additionally disabled under `~/projects/sensitive`.\n- `openrouter` is additionally disabled under `~/work/client-a` and `~/work/client-b`.\n\nPath scopes are resolved **after** the settings merge. Because a higher-precedence layer replaces the whole array, a project-level `disabledProviders` array drops any scoped entries that only existed in the global array. `enabledModels` is the only other setting that supports the same path-scoped form. See [Settings](./settings.md) for details.\n\n## Provider IDs vs discovery provider IDs\n\n`disabledProviders` uses a **single shared ID namespace** that gates two different subsystems:\n\n- **Model providers** — the backends on this page (`anthropic`, `openai`, `ollama`, a custom `models.yml` ID, …). Disabling one removes its models from selection.\n- **Discovery providers** — sources of context files, MCP servers, commands, skills, hooks, tools, prompts, and settings. Disabling one stops that source from contributing capability items.\n\n| Entry type | Examples | Effect |\n|---|---|---|\n| Model provider ID | `anthropic`, `openai`, `google`, `groq`, `openrouter`, `ollama`, `my-gateway` | Removes that provider's models from availability. |\n| Discovery provider ID | `native`, `claude`, `codex`, `gemini`, `agents`, `github` | Stops that discovery source from contributing capability items. |\n\nWatch the related names. The Google Gemini **API** models use the model provider ID `google`; `gemini` is a **discovery** provider ID (the source that reads `GEMINI.md`), not the Google model provider. Use discovery IDs only when you intend to disable an entire config source. See [Context files](./context-files.md) for the discovery-provider side.\n\n## Custom providers in `models.yml`\n\nCustom providers live in `~/.omp/agent/models.yml` under `providers:`. A provider ID defined there participates in the same selection, credential resolution, and `disabledProviders` rules as built-in providers.\n\nMinimal OpenAI-compatible provider:\n\n```yaml\nproviders:\n  my-openai-compatible:\n    baseUrl: https://api.example.com/v1\n    api: openai-completions\n    apiKey: MY_OPENAI_COMPATIBLE_KEY # env-var-name or literal\n    models:\n      - id: fast-chat\n        name: Fast Chat\n        contextWindow: 128000\n        maxTokens: 8192\n```\n\nKeyless local provider (no credentials required):\n\n```yaml\nproviders:\n  local-proxy:\n    baseUrl: http://127.0.0.1:4000/v1\n    api: openai-completions\n    auth: none\n    models:\n      - id: local-model\n        name: Local Model\n        contextWindow: 32768\n        maxTokens: 4096\n```\n\nDiscovery-enabled provider (models fetched from the endpoint at runtime):\n\n```yaml\nproviders:\n  team-proxy:\n    baseUrl: https://models.example.com/v1\n    apiKey: TEAM_PROXY_API_KEY\n    authHeader: true # send Authorization: Bearer <resolved key>\n    disableStrictTools: true\n    discovery:\n      type: proxy\n```\n\nFor the full schema, all allowed `api` values, discovery `type`s, model overrides, and equivalence settings, see [Model and Provider Configuration](./models.md).\n\nTo disable a custom provider, list its ID exactly:\n\n```yaml\ndisabledProviders:\n  - my-openai-compatible\n  - team-proxy\n```\n\n## Troubleshooting\n\n**A provider's models are not selectable.** Confirm the provider has credentials (`/login <provider>`, an exported environment variable, or a `models.yml` `apiKey`) and that its ID is not in the effective `disabledProviders` list. Remember the rule: not disabled **and** (keyless **or** has credentials). Keyless local engines only appear once the engine is actually running and responding.\n\n**The wrong key is being used (a stale key from `.env`).** Resolution favors runtime `--api-key`, then a `models.yml` config key, then stored credentials, then environment/`.env`. An already-set process environment variable also beats every `.env` file, and `<cwd>/.env` beats `~/.env`. If an unexpected key wins, check for an exported shell variable and the four `.env` files in precedence order, and clear the one that should not apply.\n\n**A provider still appears even though I disabled it.** `disabledProviders` arrays are replaced, not merged: a project `<project>/.omp/config.yml` array fully overrides the global one. Verify the *effective* list for the directory you are in (path-scoped entries only apply at or under their configured path), and confirm the ID is spelled exactly. Use `omp config get disabledProviders` to inspect the merged value (see [Settings](./settings.md)).\n\n**A discovery provider name had no effect on models (or vice-versa).** The ID namespace is shared. `gemini`, `codex`, `claude`, `native`, and `agents` are discovery-source IDs; the Google model backend is `google`. Make sure you are disabling the right kind of provider.\n\n**A custom `models.yml` provider does not load.** A YAML or schema error makes the registry skip the custom file. Validate the file with `omp models` (use `omp models find <substr>` to scope it to one provider), confirm each provider has a `baseUrl`, a valid `api`, and at least one model entry, and that an implicit local engine is not silently shadowing it (an explicit `ollama`/`lm-studio`/`llama.cpp` entry replaces the built-in discovery for that ID). See [Model and Provider Configuration](./models.md).\n",
 	"python-repl.md": "# Eval Tool Python Backend\n\nThis document describes the Python execution stack in `packages/coding-agent`.\nIt covers tool behavior, runner lifecycle, environment handling, execution semantics, output rendering, supported magics, and operational failure modes.\n\n## Scope and Key Files\n\n- Tool surface: `src/tools/eval.ts`\n- Session/per-call kernel orchestration: `src/eval/py/executor.ts`\n- Subprocess kernel client: `src/eval/py/kernel.ts`\n- Python wrapper / NDJSON server: `src/eval/py/runner.py`\n- Prelude helpers loaded into every kernel: `src/eval/py/prelude.py`\n- Host-side subagent helper bridge: `src/eval/agent-bridge.ts`\n- MIME bundle renderer (text + structured outputs): `src/eval/py/display.ts`\n- Interactive-mode renderer for user-triggered Python runs: `src/modes/components/eval-execution.ts`\n- Runtime/env filtering and Python resolution: `src/eval/py/runtime.ts`\n\n## What eval's Python backend is\n\nThe `eval` tool executes one or more Python cells inside a retained `python` subprocess that speaks NDJSON over stdin/stdout. No Jupyter gateway and no extra pip dependencies are required — a vanilla Python 3.8+ interpreter is enough. Rich `display()` output (PIL, pandas, plotly, matplotlib figures) keeps working because the wrapper implements MIME-bundle dispatch.\n\nTool params:\n\n```ts\n{\n  cells: Array<{\n    language: \"py\" | \"js\";\n    code: string;\n    title?: string;\n    timeout?: number; // seconds, clamped to 1..3600, default 30. Inactivity budget — see \"Cell timeout\".\n    reset?: boolean; // reset this cell's selected runtime before execution\n  }>;\n}\n```\n\nThe tool is `concurrency = \"exclusive\"` for a session, so calls do not overlap.\n\n## Kernel lifecycle\n\nEach Python kernel is a single subprocess: `<resolved-python> -u <runner.py>`. The runner is bundled with the host binary (Bun text import), written to an `omp-python-runner` cache under the OS temp directory once per script hash, and reused by subsequent spawns.\n\nKernel startup sequence:\n\n1. Availability check (`checkPythonKernelAvailability`) — verifies that a Python interpreter resolves and runs.\n2. Spawn `python -u runner.py` with filtered env and `cwd`.\n3. Send an init request that runs `os.chdir(cwd)`, injects env entries, and adds `cwd` to `sys.path`.\n4. Execute `PYTHON_PRELUDE` (idempotent — only initializes once per process).\n\nKernel shutdown:\n\n- Send `{\"type\": \"exit\"}` over stdin.\n- Wait for process exit with `SHUTDOWN_GRACE_MS` budget.\n- Escalate to `SIGTERM` and finally `SIGKILL` if the process does not exit in time.\n\n## Wire protocol (NDJSON, host ↔ runner)\n\nOne JSON object per line, UTF-8, `\\n` terminated.\n\nHost → runner:\n\n```jsonc\n{\"id\": \"<reqId>\", \"code\": \"<source>\", \"silent\": false, \"storeHistory\": true, \"cwd\": \"<optional>\", \"env\": {\"KEY\": \"VAL\"}}\n{\"type\": \"exit\"}\n```\n\nRunner → host:\n\n```jsonc\n{\"type\": \"started\",  \"id\": \"<reqId>\"}\n{\"type\": \"stdout\",   \"id\": \"<reqId>\", \"data\": \"...\"}\n{\"type\": \"stderr\",   \"id\": \"<reqId>\", \"data\": \"...\"}\n{\"type\": \"display\",  \"id\": \"<reqId>\", \"bundle\": {<mime>: <value>}}\n{\"type\": \"result\",   \"id\": \"<reqId>\", \"bundle\": {<mime>: <value>}}\n{\"type\": \"error\",    \"id\": \"<reqId>\", \"ename\": \"...\", \"evalue\": \"...\", \"traceback\": [\"...\"]}\n{\"type\": \"done\",     \"id\": \"<reqId>\", \"status\": \"ok\"|\"error\", \"executionCount\": N, \"cancelled\": false}\n```\n\nStatus events the prelude emits (e.g. `_emit_status(\"find\", count=…)`) ship inside display bundles under `application/x-omp-status` so the existing TUI status renderer keeps working.\n\n## Magics\n\nThe runner's source transformer rewrites IPython-style magics to plain Python calls before parsing. Supported set:\n\n| Magic                             | Effect                                                                                                                                                      |\n| --------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `%pip <args>`                     | `python -m pip <args>` with live streaming output. Newly installed packages are evicted from `sys.modules` so the next `import` picks up the fresh install. |\n| `%cd <path>`                      | `os.chdir(path)` (with `~` expansion); emits status event.                                                                                                  |\n| `%pwd`                            | Returns `os.getcwd()`.                                                                                                                                      |\n| `%ls [path]`                      | Returns `sorted(os.listdir(path))`.                                                                                                                         |\n| `%env [KEY[=VAL]]`                | List, read, or set env vars (matches prelude `env()` semantics).                                                                                            |\n| `%set_env KEY VALUE`              | Set `os.environ[KEY]`.                                                                                                                                      |\n| `%time <expr>` / `%timeit <expr>` | Time the expression; emits status event with elapsed ms.                                                                                                    |\n| `%who` / `%whos`                  | List user-namespace names.                                                                                                                                  |\n| `%reset`                          | Clear user globals and re-inject prelude.                                                                                                                   |\n| `%load <path>`                    | Read a file into a fresh cell and execute.                                                                                                                  |\n| `%run <path>`                     | `runpy.run_path` and merge globals back.                                                                                                                    |\n| `%%bash` / `%%sh`                 | Run the cell body via `bash`/`sh`.                                                                                                                          |\n| `%%capture [name]`                | Run body with stdout/stderr captured into `name`.                                                                                                           |\n| `%%timeit`                        | Time the cell body.                                                                                                                                         |\n| `%%writefile <path>`              | Write body to file.                                                                                                                                         |\n| `!cmd` / `var = !cmd`             | Run command via subprocess shell; returns an SList-style result with `.n` / `.s` helpers.                                                                   |\n| `var = %name args`                | Assignment forms work for line magics and `!cmd`.                                                                                                           |\n\nUnknown magic names raise `NameError: UsageError: ...` inside the cell.\n\n## Session persistence semantics\n\n`python.kernelMode` controls retained kernel reuse:\n\n- `session` (default)\n  - Reuses kernel sessions keyed by namespaced eval session id plus normalized cwd and interpreter.\n  - Multiple owners can share the same retained kernel for that key.\n  - Calls through the tool are exclusive, so tool invocations do not overlap.\n  - A dead retained subprocess is replaced before execution.\n  - If the subprocess dies during execution, it is replaced and the cell is retried once.\n- `per-call`\n  - Spawns a fresh subprocess for each request.\n  - Shuts the subprocess down after the request.\n  - No cross-call state persistence.\n\n### Multi-cell behavior in a single tool call\n\nPython cells run sequentially in the same selected Python kernel instance for that tool call.\n\nIf an intermediate cell fails:\n\n- Earlier cell state remains in memory.\n- Tool returns a targeted error indicating which cell failed.\n- Later cells are not executed.\n\n`reset=true` is per cell and resets that language runtime before the cell executes.\n\n## Environment filtering and runtime resolution\n\nEnvironment is filtered before launching the runner:\n\n- Allowlist includes core vars like `PATH`, `HOME`, locale vars, `VIRTUAL_ENV`, `PYTHONPATH`, etc.\n- Allow-prefixes: `LC_`, `XDG_`, `PI_`\n- Denylist strips common API keys (OpenAI/Anthropic/Gemini/etc.)\n\nRuntime selection order (skipped entirely when the `python.interpreter` setting names an explicit executable):\n\n1. Active/located venv (`VIRTUAL_ENV`, then `CONDA_PREFIX`, then `<cwd>/.venv`, `<cwd>/venv`)\n2. Managed venv at `~/.omp/python-env`\n3. `python` or `python3` on PATH\n\nWhen a venv is selected, its bin/Scripts path is prepended to `PATH`.\n\nThe runner additionally receives `PYTHONUNBUFFERED=1` and `PYTHONIOENCODING=utf-8` so streamed output reaches the host promptly.\n\n## Tool availability and mode selection\n\n`eval.py` / `eval.js` (both default `true`) plus optional boolean env flags `PI_PY` / `PI_JS` control eval backend exposure:\n\n- Python backend only (`eval.py=true`, `eval.js=false`, or `PI_PY=1 PI_JS=0`)\n- JavaScript backend only (`eval.py=false`, `eval.js=true`, or `PI_PY=0 PI_JS=1`)\n- both backends (`eval.py=true`, `eval.js=true`, or `PI_PY=1 PI_JS=1`)\n\n`PI_PY` and `PI_JS` use normal boolean flag parsing. Each flag, when set, overrides only its own setting; an unset flag falls back to its setting (`eval.py` / `eval.js`, both default `true`).\n\nIf Python preflight fails and `eval.js` is enabled, `eval` remains available for `js` cells; `py` cells fail with a Python-backend availability error.\n\nPython prelude helpers include `agent(prompt, *, agent_type=\"task\", model=None, label=None, schema=None)`. It synchronously calls the host bridge, runs one subagent through the task executor, and returns the final text. When `schema` is supplied, the helper parses the subagent's JSON output and returns the object.\n\n## Execution flow and cancellation/timeout\n\n### Cell timeout\n\nEach eval cell `timeout` is in seconds, defaults to 30, and is clamped to `1..3600`. It is a **wall-clock budget on the cell's own work** that the watchdog (`IdleTimeout`, `src/eval/idle-timeout.ts`) enforces, **but it is suspended while a host-side `agent()`/`parallel()`/`completion()` bridge call is in flight**: those calls emit synthetic pause/resume timeout-control status events (`withBridgeTimeoutPause`, `src/eval/bridge-timeout.ts`) that pause the watchdog entirely and start a fresh timeout window when control returns to the runtime, so a long fanout or a slow completion runs to completion instead of being killed mid-stream. Pause is reference-counted because `parallel()` can have multiple bridge calls in flight at once.\n\nThe pause/resume events are the **sole** mechanism that suspends the budget. Everything else the cell does — compute, `stdout`/`stderr`, `log()`/`phase()`, and ordinary (non-agent) tool calls — counts against `timeout`, so a cell that is not delegating to an agent/completion is bounded by a plain wall-clock timeout. The tool combines the caller abort signal, the session abort signal, and the watchdog's signal with `AbortSignal.any(...)`; no wall-clock deadline is passed to the backend, so neither runtime arms a competing fixed timer.\n\n### Kernel execution cancellation\n\nOn abort/timeout:\n\n- The host sends `kill(\"SIGINT\")` to the runner subprocess.\n- The runner's exec-time signal handler raises `KeyboardInterrupt` inside the user code.\n- Result includes `cancelled=true`; a kernel timeout is annotated as `eval cell timed out after <n>s; kernel interrupted but remains running. Reset the kernel via { reset: true } if state appears corrupted.`\n- Between requests the runner installs `SIG_IGN` for SIGINT so a stray cancel does not tear down the kernel.\n\nIf the runner does not emit `done` within 5s of the interrupt (`INTERRUPT_ESCALATION_MS` — e.g. stuck in C code holding the GIL), the host shuts the subprocess down (escalating `exit` → `SIGTERM` → `SIGKILL`), the cell is annotated as kernel-killed, and the kernel is recreated on the next call.\n\n### stdin behavior\n\nInteractive stdin is not supported. The runner does not forward `input()` prompts; user code that calls `input()` blocks until cancellation.\n\n## Output capture and rendering\n\n### Captured output classes\n\nFrom runner frames:\n\n- `stdout` / `stderr` → plain text chunks\n- `display` / `result` → rich display handling (MIME bundle)\n- `error` → traceback text\n- `application/x-omp-status` MIME inside `display` → structured status events\n\nDisplay MIME precedence:\n\n1. `text/markdown`\n2. `text/plain`\n3. `text/html` (converted to basic markdown)\n\nAdditionally captured as structured outputs:\n\n- `application/json` → JSON tree data\n- `image/png` / `image/jpeg` → image payloads\n- `application/x-omp-status` → status events\n\n### Matplotlib\n\nThe runner sets `MPLBACKEND=Agg` as an environ default so figures render off-screen. After every cell, `pyplot.get_fignums()` is iterated; each figure is saved to PNG, emitted as an `image/png` display, and closed.\n\n### Storage and truncation\n\nOutput is streamed through `OutputSink` and may be persisted to artifact storage. Tool results can include truncation metadata and `artifact://<id>` for full output recovery.\n\n### Renderer behavior\n\n- Tool renderer (`eval.ts`):\n  - shows code-cell blocks with per-cell status\n  - collapsed preview defaults to 10 lines\n  - supports expanded mode for all output retained in the tool result\n- Interactive renderer (`eval-execution.ts`):\n  - used for user-triggered Python execution in TUI\n  - collapsed preview defaults to 20 lines\n  - clamps very long individual lines to 4000 chars for display safety\n  - shows cancellation/error/truncation notices\n\n## Operational troubleshooting\n\n- **Python backend not available** — Check `eval.py`, `PI_PY`, and that `python`/`python3` is on PATH. If preflight fails and `eval.js` is enabled, use a `js` cell.\n- **No Python on PATH** — Install a system Python 3.8+ or place a venv at `~/.omp/python-env`. `omp setup python --check` reports the resolved interpreter.\n- **Execution hangs then times out** — Increase tool `timeout` (max 3600s) if workload is legitimate. For stuck native code, cancellation triggers `SIGINT` first then escalates; the session restarts on the next request.\n- **stdin/input prompts in Python code** — `input()` is not supported; pass data programmatically.\n- **Working directory errors** — Tool validates `cwd` exists and is a directory before execution.\n\n## Relevant environment variables\n\n- `PI_PY` / `PI_JS` — eval backend exposure overrides\n- `PI_PYTHON_SKIP_CHECK=1` — bypass Python preflight/warm checks\n- `PI_PYTHON_INTEGRATION=1` — enable gated integration tests that spawn a real Python\n- `PI_PYTHON_IPC_TRACE=1` — log NDJSON frames exchanged with the runner subprocess\n",
 	"render-mermaid.md": "# RenderMermaid\n\n`RenderMermaid` is an optional built-in tool that renders Mermaid source to terminal-friendly text.\n\n## Enable it\n\nDisabled by default. Turn it on in `/settings` under **Tools → Render Mermaid**, or in `~/.omp/agent/config.yml`:\n\n```yaml\nrenderMermaid:\n  enabled: true\n```\n\n## What it does\n\n- Tool name: `render_mermaid`\n- Input: Mermaid source in the required `mermaid` field\n- Output: rendered ASCII/Unicode text, not SVG or PNG\n- Storage: when artifact storage is available, the full render is also saved as an `artifact://...`\n\nThere are no model-specific or environment-variable prerequisites. Once enabled, any model that can call built-in tools can use it.\n\n## Parameters\n\n```json\n{\n  \"mermaid\": \"graph TD\\n  A[Start] --> B[Stop]\",\n  \"config\": {\n    \"useAscii\": false,\n    \"paddingX\": 2,\n    \"paddingY\": 2,\n    \"boxBorderPadding\": 0\n  }\n}\n```\n\nAvailable `config` fields:\n\n- `useAscii` — `true` for plain ASCII, `false` for Unicode box-drawing characters (default and usually more readable)\n- `paddingX` — horizontal spacing between nodes\n- `paddingY` — vertical spacing between nodes\n- `boxBorderPadding` — inner padding inside node boxes\n\n## Current limitations\n\n`RenderMermaid` uses the `beautiful-mermaid` ASCII renderer. It works best for flowcharts and small diagrams.\n\nComplex sequence diagrams, especially with `alt` / `else` blocks, can become very wide in a terminal. That is current renderer behavior, not a provider or model configuration problem.\n\nIf a sequence diagram is hard to read:\n\n1. Keep Unicode output (`useAscii: false`)\n2. Reduce spacing with a tighter config such as `paddingX: 2`, `paddingY: 2`, `boxBorderPadding: 0`\n3. Prefer smaller sub-diagrams over one large sequence diagram\n4. Open the saved artifact if the inline preview is truncated in the TUI\n\n## Example\n\nInput:\n\n```mermaid\ngraph TD\n  A[Start] --> B{Decision}\n  B -->|Yes| C[Action]\n  B -->|No| D[End]\n```\n\nTypical result:\n\n```text\n┌─────┐\n│Start│\n└─────┘\n   │\n   ▼\n┌────────┐\n│Decision│\n└────────┘\n```\n",
 	"resolve-tool-runtime.md": "# Resolve tool runtime internals\n\nThis document explains how preview/apply workflows are modeled in coding-agent and how built-in or custom tools can participate via the tool-choice queue and `pushPendingAction`.\n\n## Scope and key files\n\n- [`src/tools/resolve.ts`](../packages/coding-agent/src/tools/resolve.ts)\n- [`src/tools/ast-edit.ts`](../packages/coding-agent/src/tools/ast-edit.ts)\n- [`src/extensibility/custom-tools/types.ts`](../packages/coding-agent/src/extensibility/custom-tools/types.ts)\n- [`src/extensibility/custom-tools/loader.ts`](../packages/coding-agent/src/extensibility/custom-tools/loader.ts)\n- [`src/sdk.ts`](../packages/coding-agent/src/sdk.ts)\n\n## What `resolve` does\n\n`resolve` is a hidden tool that finalizes a pending preview action.\n\n- `action: \"apply\"` executes the queued action's `apply(reason, extra)` callback and returns that result with resolve metadata.\n- `action: \"discard\"` invokes `reject(reason, extra)` if provided; otherwise returns `Discarded: <label>. Reason: <reason>`.\n- `extra` is optional free-form metadata. Queue handlers receive it; producers decide whether it has meaning.\n\nIf no pending action exists, `resolve(action=\"apply\")` fails with:\n\n- `No pending action to resolve. Nothing to apply or discard.`\n\n`resolve(action=\"discard\")` with no pending action succeeds instead, returning `Nothing to discard; no pending action remains.` — the desired end-state (no staged change) already holds.\n\n## Pending actions use the tool-choice queue\n\nPreview producers call `queueResolveHandler(...)`, which pushes a one-shot forced `resolve` directive onto the session tool-choice queue and adds a `resolve-reminder` steering message.\n\nRuntime behavior:\n\n- the queued handler owns the pending `apply`/`reject` callbacks,\n- `resolve` looks up the current queue invoker with `session.peekQueueInvoker()`,\n- if the model rejects the forced tool choice, the queue directive is requeued,\n- `resolve` does not maintain a separate pending-action stack.\n\n`resolve` also checks a standing resolve handler after the queue invoker; this is used by long-lived approval flows that are not ordinary preview tool calls.\n\nMultiple pending previews therefore follow the active tool-choice queue ordering, not an independent pending-action store. If an apply callback throws, the queued helper re-pushes the same resolve directive and reminder so the preview can still be discarded or retried.\n\n## Built-in producer example (`ast_edit`)\n\n`ast_edit` previews structural replacements first. When the preview has replacements and is not applied yet, it queues a resolve handler that contains:\n\n- label (human-readable summary)\n- `sourceToolName` (`ast_edit`)\n- `apply(reason: string, extra?: Record<string, unknown>)` callback that reruns AST edit with `dryRun: false`\n\n`resolve(action=\"apply\", reason=\"...\")` passes `reason` into this callback. `ast_edit` currently ignores `extra`.\n\n## Custom tools: `pushPendingAction`\n\nCustom tools can register resolve-compatible pending actions through `CustomToolAPI.pushPendingAction(...)`. The custom tool loader forwards these actions to `queueResolveHandler(...)` when that hook is available.\n\n`CustomToolPendingAction`:\n\n- `label: string` (required)\n- `apply(reason: string): Promise<AgentToolResult<unknown>>` (required) — invoked on apply; `reason` is the string passed to `resolve`\n- `reject?(reason: string): Promise<AgentToolResult<unknown> | undefined>` (optional) — invoked on discard; return value replaces the default \"Discarded\" message if provided\n- `details?: unknown` exists on the public custom-tool type but is not currently forwarded by the loader into resolve metadata\n- `sourceToolName?: string` (optional, defaults to `\"custom_tool\"`)\n\n### Minimal usage example\n\n```ts\nimport type { CustomToolFactory } from \"@oh-my-pi/pi-coding-agent\";\n\nconst factory: CustomToolFactory = (pi) => ({\n  name: \"batch_rename_preview\",\n  label: \"Batch Rename Preview\",\n  description: \"Previews renames and defers commit to resolve\",\n  parameters: pi.zod.object({\n    files: pi.zod.array(pi.zod.string()),\n  }),\n\n  async execute(_toolCallId, params) {\n    const previewSummary = `Prepared rename plan for ${params.files.length} files`;\n\n    pi.pushPendingAction({\n      label: `Batch rename: ${params.files.length} files`,\n      sourceToolName: \"batch_rename_preview\",\n      apply: async (reason) => {\n        // apply writes here\n        return {\n          content: [\n            { type: \"text\", text: `Applied batch rename. Reason: ${reason}` },\n          ],\n        };\n      },\n      reject: async (reason) => {\n        // optional: cleanup or notify on discard\n        return {\n          content: [\n            { type: \"text\", text: `Discarded batch rename. Reason: ${reason}` },\n          ],\n        };\n      },\n    });\n\n    return {\n      content: [\n        {\n          type: \"text\",\n          text: `${previewSummary}. Call resolve to apply or discard.`,\n        },\n      ],\n    };\n  },\n});\n\nexport default factory;\n```\n\n## Runtime availability and failures\n\n`pushPendingAction` is wired by the custom tool loader through the active session's resolve queue hook.\n\nIf the runtime did not provide the resolve queue hook, `pushPendingAction` throws:\n\n- `Pending action store unavailable for custom tools in this runtime.`\n\n## Tool-choice behavior\n\nWhen `queueResolveHandler(...)` registers a preview, the agent runtime forces a one-shot `resolve` tool choice so pending previews are explicitly finalized before normal tool flow continues.\n\n## Developer guidance\n\n- Use pending actions only for destructive or high-impact operations that should support explicit apply/discard.\n- Keep `label` concise and specific; it is shown in resolve renderer output.\n- Ensure `apply(reason)` is deterministic and idempotent enough for one-shot execution; `reason` is informational and should not change behavior.\n- Implement `reject(reason)` when the discard needs cleanup (temp state, locks, notifications); omit it for stateless previews where the default message suffices.\n- If your tool can stage multiple previews, remember they are mediated by the tool-choice queue rather than a separate pending-action stack.\n",
@@ -61,11 +62,11 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"session-switching-and-recent-listing.md": "# Session switching and recent session listing\n\nThis document describes how coding-agent discovers recent sessions, resolves `--resume` targets, presents session pickers, and switches the active runtime session.\n\nIt focuses on current implementation behavior, including fallback paths and caveats.\n\n## Implementation files\n\n- [`../src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts)\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`../src/cli/session-picker.ts`](../packages/coding-agent/src/cli/session-picker.ts)\n- [`../src/modes/components/session-selector.ts`](../packages/coding-agent/src/modes/components/session-selector.ts)\n- [`../src/modes/controllers/selector-controller.ts`](../packages/coding-agent/src/modes/controllers/selector-controller.ts)\n- [`../src/main.ts`](../packages/coding-agent/src/main.ts)\n- [`../src/sdk.ts`](../packages/coding-agent/src/sdk.ts)\n- [`../src/modes/interactive-mode.ts`](../packages/coding-agent/src/modes/interactive-mode.ts)\n- [`../src/modes/utils/ui-helpers.ts`](../packages/coding-agent/src/modes/utils/ui-helpers.ts)\n\n## Recent-session discovery\n\n### Directory scope\n\n`SessionManager` stores sessions under a cwd-scoped directory by default:\n\n- `~/.omp/agent/sessions/<dir-encoded>/*.jsonl` (home-relative `-<rel>` names, `-tmp-<rel>` for temp paths, legacy `--<abs>--` otherwise)\n\n`SessionManager.list(cwd, sessionDir?)` reads only that directory unless an explicit `sessionDir` is provided.\n\n### Two listing paths with different payloads\n\nThere are two different listing pipelines:\n\n1. `getRecentSessions(sessionDir, limit)` (welcome/summary view)\n   - Reads only a 4KB prefix (`readTextSlices(..., 4096, 0)[0]`) from each file.\n   - Parses header + earliest user text preview.\n   - Returns lightweight `RecentSessionInfo` with lazy `name` and `timeAgo` getters.\n   - Sorts by file `mtime` descending.\n\n2. `SessionManager.list(...)` / `SessionManager.listAll()` (resume pickers and ID matching)\n   - Reads a 4KB prefix plus a bounded 32 KiB tail in one `readTextSlices(...)` call per file, not the full JSONL file.\n   - Builds `SessionInfo` objects (`id`, `cwd`, `title`, `messageCount`, `firstMessage`, `allMessagesText`, timestamps, lifecycle status).\n   - Uses prefix parsing plus marker counting for list text, and tail parsing for the final-message lifecycle status; later messages beyond the prefix may not be present in `allMessagesText`.\n   - Sorts by `modified` descending.\n\n### Metadata fallback behavior\n\nFor recent summaries (`RecentSessionInfo`):\n\n- display name preference: `header.title` -> first user prompt -> `header.id` -> filename\n- name is truncated to 40 chars for compact displays\n- control characters/newlines are stripped/sanitized from title-derived names\n\nFor `SessionInfo` list entries:\n\n- `title` is `header.title` or the last compaction `shortSummary` seen in the 4KB prefix\n- `firstMessage` is first user message text discoverable from the prefix or `\"(no messages)\"`\n\n## `--continue` resolution and terminal breadcrumb preference\n\n`SessionManager.continueRecent(cwd, sessionDir?)` resolves the target in this order:\n\n1. Read terminal-scoped breadcrumb (`~/.omp/agent/terminal-sessions/<terminal-id>`)\n2. Validate breadcrumb:\n   - current terminal can be identified\n   - referenced file still exists\n3. If the breadcrumb's cwd differs from the current cwd, that cwd no longer exists (moved/renamed dir), and the current directory has no sessions of its own, the breadcrumb session is re-rooted into the current directory (`SessionManager.open` + `moveTo`) instead of starting fresh\n4. Otherwise, if the breadcrumb cwd matches the current cwd (resolved path compare), use the breadcrumb session; else fall back to newest file by mtime in the session dir (`findMostRecentSession`)\n5. If none found, create a new session\n\nTerminal ID derivation prefers TTY path and falls back to env-based identifiers (`TMUX_PANE`, `CMUX_SURFACE_ID`, `KITTY_WINDOW_ID`, `TERM_SESSION_ID`, `WT_SESSION`).\n\nBreadcrumb writes are best-effort and non-fatal.\n\n## Startup-time resume target resolution (`main.ts`)\n\n### `--resume <value>`\n\n`createSessionManager(...)` handles string-valued `--resume` in two modes:\n\n1. Path-like value (contains `/`, `\\\\`, or ends with `.jsonl`)\n   - direct `SessionManager.open(sessionArg, parsed.sessionDir)`\n\n2. Resume key value\n   - `resolveResumableSession(...)` searches local sessions first, then all sessions when `sessionDir` is not forced\n   - matching is case-insensitive and accepts `id` prefix, full JSONL filename prefix, or the session-id suffix after the timestamp\n   - first match in modified-descending order is used (no ambiguity prompt)\n\nCross-project match behavior:\n\n- if the matched session's recorded cwd no longer exists (moved/renamed dir), CLI prompts `Move (re-root) it into the current directory? [Y/n]`; yes opens the session and `moveTo(cwd)` re-roots it (this also applies to local-scope matches whose recorded cwd is gone)\n- otherwise, if a global match's cwd differs from the current cwd, CLI prompts `Fork into current directory? [y/N]`\n- fork accepted -> `SessionManager.forkFrom(...)`\n- either prompt declined -> command cancels (`Resume cancelled: session is in another project.`)\n- non-TTY -> throws `SessionResolutionError` instead of prompting\n\nNo match -> throws error (`Session \"...\" not found.`).\n\n### `--resume` (no value)\n\nHandled after initial session-manager construction:\n\n1. list local sessions with `SessionManager.list(cwd, parsed.sessionDir)`\n2. if empty: preload `SessionManager.listAll()` and open the picker in all-projects scope; print `No sessions found` and exit early only when the global list is also empty\n3. open TUI picker (`selectSession`, with optional preloaded `allSessions`/`startInAllScope`)\n4. if canceled: print `No session selected` and exit early\n5. if selected: when the session belongs to another project, switch the process into that project's directory (`setProjectDir`, cache resets, settings reload) first; then `SessionManager.open(selected.path)`\n\n### `--continue`\n\nUses `SessionManager.continueRecent(...)` directly (breadcrumb-first behavior above).\n\n## Picker-based selection internals\n\n## CLI picker (`src/cli/session-picker.ts`)\n\n`selectSession(sessions, { allSessions?, startInAllScope? })` creates a standalone TUI with `SessionSelectorComponent` and resolves exactly once:\n\n- selection -> resolves selected `SessionInfo` (caller uses `.path` / `.cwd`)\n- cancel (Esc) -> resolves `null`\n- hard exit (Ctrl+C path) -> stops TUI and `process.exit(0)`\n- Tab toggles current-folder / all-projects scope; the all-projects list is loaded lazily via `SessionManager.listAll` (or preloaded via `allSessions`)\n- search ranking is augmented with prompt-history matches from `history.db` (`HistoryStorage.matchingSessionIds`) when available\n\n## Interactive in-session picker (`SelectorController.showSessionSelector`)\n\nFlow:\n\n1. fetch sessions from current session dir via `SessionManager.list(currentCwd, currentSessionDir)`; if empty, preload `SessionManager.listAll()` and open in all-projects scope\n2. mount `SessionSelectorComponent` in editor area using `showSelector(...)`, wired with `loadAllSessions: () => SessionManager.listAll()` and a `history.db` prompt matcher\n3. callbacks:\n   - select -> close selector and call `handleResumeSession(sessionPath)`\n   - cancel -> restore editor and rerender\n   - exit -> `ctx.shutdown()`\n\n## Session selector component behavior\n\n`SessionList` supports:\n\n- arrow/page navigation\n- Enter to select\n- Delete to delete after confirmation\n- Esc to cancel\n- Ctrl+C to exit\n- Tab to toggle current-folder / all-projects scope\n- ranked fuzzy search across session id/title/cwd/first message/all messages/path, merged with prompt-history matches from `history.db`\n\nEmpty-list render behavior:\n\n- current-folder scope renders `No sessions in current folder. Press Tab to view all.`; all-projects scope renders `No sessions found`\n- Enter/Delete on empty do nothing (no callback)\n- Esc/Ctrl+C still work\n\n## Runtime switch execution (`AgentSession.switchSession`)\n\n`switchSession(sessionPath)` is the core in-process switch path.\n\nLifecycle/state transition:\n\n1. capture `previousSessionFile`\n2. emit `session_before_switch` hook event (`reason: \"resume\"`, cancellable)\n3. if canceled -> return `false` with no switch\n4. disconnect from current agent event stream\n5. abort active generation/tool flow\n6. flush session writer (`sessionManager.flush()`) to persist pending writes, then capture rollback state\n7. clear queued steering/follow-up/next-turn message buffers\n8. `sessionManager.setSessionFile(sessionPath)`\n   - updates session file pointer\n   - writes terminal breadcrumb\n   - loads entries / migrates / blob-resolves / reindexes\n   - if missing/invalid file data: initializes a new session at that path and rewrites header\n9. update `agent.sessionId`\n10. rebuild display context via `buildDisplaySessionContext()`\n11. restore persisted/discovered MCP tool selections and rebuild active tools/system prompt when discovery is enabled\n12. emit `session_switch` hook event (`reason: \"resume\"`, `previousSessionFile`)\n13. replace agent messages with rebuilt context and sync todos\n14. close provider sessions when switching to a different session or when same-session reload changed replay messages\n15. restore model via `getRestorableSessionModels(sessionContext.models, lastModelChangeRole)` — tries the recorded models in fallback order and uses the first one present in the model registry\n16. restore thinking level and service tier:\n    - thinking uses persisted `thinking_level_change`, otherwise the configured default clamped to model capability\n    - service tier uses persisted `service_tier_change`, otherwise the configured `serviceTier` setting (`\"none\"` becomes unset)\n17. reconnect agent listeners, run the registered session-switch reconciler if any (interactive mode re-enters persisted modes; errors logged, not fatal), and return `true`\n\n## UI state rebuild after interactive switch\n\n`SelectorController.handleResumeSession` performs UI reset around `switchSession`:\n\n- stop loading animation\n- clear status container\n- clear pending-message UI and pending tool map\n- reset streaming component/message references\n- call `session.switchSession(...)`\n- if the resumed session's cwd differs from the previous one, re-point the process and cwd-derived caches at it (`applyCwdChange`)\n- clear chat container and rerender from session context (`renderInitialMessages`)\n- reload todos from new session artifacts\n- show `Resumed session` (or `Resumed session in <dir>` for a cross-project resume)\n\nSo visible conversation/todo state is rebuilt from the new session file.\n\n## Startup resume vs in-session switch\n\n### Startup resume (`--continue`, `--resume`, direct open)\n\n- Session file is chosen before `createAgentSession(...)`.\n- `sdk.ts` builds `existingSession = sessionManager.buildSessionContext()`.\n- Agent messages are restored once during session creation.\n- Model/thinking are selected during creation (including restore/fallback logic).\n- Interactive mode then runs `#reconcileModeFromSession()` to re-enter persisted mode state (e.g. plan mode).\n\n### In-session switch (`/resume`-style selector path)\n\n- Uses `AgentSession.switchSession(...)` on an already-running `AgentSession`.\n- Messages/model/thinking are rebuilt immediately in place.\n- Hook `session_before_switch`/`session_switch` events are emitted.\n- UI chat/todos are refreshed.\n- Mode re-entry is symmetric with startup: interactive mode registers `#reconcileModeFromSession()` as the session-switch reconciler (`setSessionSwitchReconciler`), and `switchSession()` invokes it after reconnecting.\n\n## Failure and edge-case behavior\n\n### Cancellation paths\n\n- CLI picker cancel -> returns `null`, caller prints `No session selected`, process exits early.\n- Interactive picker cancel -> editor restored, no session change.\n- Hook cancellation (`session_before_switch`) -> `switchSession()` returns `false`.\n\n### Empty list paths\n\n- CLI `--resume` (no value): empty list prints `No sessions found` and exits.\n- Interactive selector: empty list renders message and remains cancellable.\n\n### Missing/invalid target session file\n\nWhen opening/switching to a specific path (`setSessionFile`):\n\n- ENOENT -> treated as empty -> new session initialized at that exact path and persisted.\n- malformed/invalid header (or effectively unreadable parsed entries) -> treated as empty -> new session initialized and persisted.\n\nThis is recovery behavior, not hard failure.\n\n### Hard failures\n\nSwitch/open can still throw on true I/O failures (permission errors, rewrite failures, etc.), which propagate to callers.\n\n### ID prefix matching caveats\n\n- Matching uses `startsWith` on the lowercased session id, lowercased JSONL filename, and lowercased id suffix after the filename timestamp.\n- First match in modified-descending order wins; there is no ambiguity UI if multiple sessions share a prefix.\n- Prefix-listing metadata is intentionally lightweight, so search text may not include messages outside the first 4KB of the session file.\n",
 	"session-tree-plan.md": "# Session tree architecture (current)\n\nReference: [session.md](../docs/session.md)\n\nThis document describes how session tree navigation works today: in-memory tree model, leaf movement rules, branching behavior, and extension/event integration.\n\n## What this subsystem is\n\nThe session is stored as an append-only entry log, but runtime behavior is tree-based:\n\n- Every non-header entry has `id` and `parentId`.\n- The active position is `leafId` in `SessionManager`.\n- Appending an entry always creates a child of the current leaf.\n- Branching does **not** rewrite history; it only changes where the leaf points before the next append.\n\nKey files:\n\n- `src/session/session-manager.ts` — tree data model, traversal, leaf movement, branch/session extraction\n- `src/session/agent-session.ts` — `/tree` navigation flow, summarization, hook/event emission\n- `src/modes/components/tree-selector.ts` — interactive tree UI behavior and filtering\n- `src/modes/controllers/selector-controller.ts` — selector orchestration for `/tree` and `/branch`\n- `src/slash-commands/builtin-registry.ts` — command routing (`/tree`, `/branch`)\n- `src/modes/controllers/input-controller.ts` — double-escape behavior and `app.session.tree`/`app.session.fork` keybinding wiring\n- `src/session/messages.ts` — conversion of `branch_summary`, `compaction`, and `custom_message` entries into LLM context messages\n\n## Tree data model in `SessionManager`\n\nRuntime indices:\n\n- `#byId: Map<string, SessionEntry>` — fast lookup for any entry\n- `#leafId: string | null` — current position in the tree\n- `#labelsById: Map<string, string>` — resolved labels by target entry id\n\nTree APIs:\n\n- `getBranch(fromId?)` walks parent links to root and returns root→node path\n- `getTree()` returns `SessionTreeNode[]` (`entry`, `children`, `label`)\n  - parent links become children arrays\n  - entries with missing parents are treated as roots\n  - children are sorted oldest→newest by timestamp\n- `getChildren(parentId)` returns direct children\n- `getLabel(id)` resolves current label from `labelsById`\n\n`getTree()` is a runtime projection; persistence remains append-only JSONL entries.\n\n## Leaf movement semantics\n\nThere are three leaf movement primitives:\n\n1. `branch(entryId)`\n   - Validates entry exists\n   - Sets `leafId = entryId`\n   - No new entry is written\n\n2. `resetLeaf()`\n   - Sets `leafId = null`\n   - Next append creates a new root entry (`parentId = null`)\n\n3. `branchWithSummary(branchFromId, summary, details?, fromExtension?)`\n   - Accepts `branchFromId: string | null`\n   - Sets `leafId = branchFromId`\n   - Appends a `branch_summary` entry as child of that leaf\n   - When `branchFromId` is `null`, `fromId` is persisted as `\"root\"`\n\n## `/tree` navigation behavior (same session file)\n\n`AgentSession.navigateTree()` is navigation, not file forking.\n\nFlow:\n\n1. Validate target and compute abandoned path (`collectEntriesForBranchSummary`)\n2. Emit `session_before_tree` with `TreePreparation`\n3. Optionally summarize abandoned entries (hook-provided summary or built-in summarizer)\n4. Compute new leaf target:\n   - selecting a **user** message: leaf moves to its parent, and message text is returned for editor prefill\n   - selecting a **custom_message**: same rule as user message (leaf = parent, text prefills editor)\n   - selecting any other entry: leaf = selected entry id\n5. Apply leaf move:\n   - with summary: `branchWithSummary(newLeafId, ...)`\n   - without summary and `newLeafId === null`: `resetLeaf()`\n   - otherwise: `branch(newLeafId)`\n6. Rebuild agent context from new leaf and emit `session_tree`\n\nImportant: summary entries are attached at the **new navigation position**, not on the abandoned branch tail.\n\n## `/branch` behavior (new session file)\n\n`/branch` and `/tree` are intentionally different:\n\n- `/tree` navigates within the current session file.\n- `/branch` creates a new session branch file (or in-memory replacement for non-persistent mode).\n\nUser-facing `/branch` flow (`SelectorController.showUserMessageSelector` → `AgentSession.branch`):\n\n- Branch source must be a **user message**.\n- Selected user text is extracted for editor prefill.\n- If selected user message is root (`parentId === null`): start a new session via `newSession({ parentSession: previousSessionFile })`.\n- Otherwise: `createBranchedSession(selectedEntry.parentId)` to fork history up to the selected prompt boundary.\n\n`SessionManager.createBranchedSession(leafId)` specifics:\n\n- Builds root→leaf path via `getBranch(leafId)`; throws if missing.\n- Excludes existing `label` entries from copied path.\n- Rebuilds fresh label entries from resolved `labelsById` for entries that remain in path.\n- Persistent mode: writes new JSONL file and switches manager to it; returns new file path.\n- In-memory mode: replaces in-memory entries; returns `undefined`.\n\n## Context reconstruction and summary/custom integration\n\n`buildSessionContext()` (in `session-manager.ts`) resolves the active root→leaf path and builds effective LLM context state:\n\n- Tracks latest thinking/model/service-tier/mode/TTSR/MCP-selection state on path.\n- Handles latest compaction on path:\n  - emits compaction summary first\n  - replays kept messages from `firstKeptEntryId` to compaction point\n  - then replays post-compaction messages\n- Includes `branch_summary` and `custom_message` entries as `AgentMessage` objects.\n\n`session/messages.ts` then maps these message types for model input:\n\n- `branchSummary` and `compactionSummary` become user-role templated context messages\n- `custom`/`hookMessage` become developer-role content messages (via agent-core's `convertMessageToLlm`)\n\nSo tree movement changes context by changing the active leaf path, not by mutating old entries.\n\n## Labels and tree UI behavior\n\nLabel persistence:\n\n- `appendLabelChange(targetId, label?)` writes `label` entries on the current leaf chain.\n- `labelsById` is updated immediately (set or delete).\n- `getTree()` resolves current label onto each returned node.\n\nTree selector behavior (`tree-selector.ts`):\n\n- Flattens tree for navigation, keeps active-path highlighting, and prioritizes displaying the active branch first.\n- Supports filter modes: `default`, `no-tools`, `user-only`, `labeled-only`, `all`.\n  - `default` suppresses `label`, `custom`, `model_change`, and `thinking_level_change`; it is not a complete \"hide all internal entries\" filter.\n- Supports free-text search over rendered semantic content.\n- `Shift+L` opens inline label editing and writes via `appendLabelChange`.\n\nCommand routing:\n\n- `/tree` always opens tree selector.\n- `/branch` opens user-message selector unless `doubleEscapeAction=tree`, in which case it also uses tree selector UX.\n\n## Extension and hook touchpoints for tree operations\n\nCommand-time extension API (`ExtensionCommandContext`):\n\n- `branch(entryId)` — create branched session file\n- `navigateTree(targetId, { summarize? })` — move within current tree/file\n\nEvents around tree navigation:\n\n- `session_before_tree`\n  - receives `TreePreparation`:\n    - `targetId`\n    - `oldLeafId`\n    - `commonAncestorId`\n    - `entriesToSummarize`\n    - `userWantsSummary`\n  - may cancel navigation\n  - may provide summary payload used instead of built-in summarizer\n  - receives abort `signal` (Escape cancellation path)\n- `session_tree`\n  - emits `newLeafId`, `oldLeafId`\n  - includes `summaryEntry` when a summary was created\n  - `fromExtension` indicates summary origin\n\nAdjacent but related lifecycle hooks:\n\n- `session_before_branch` / `session_branch` for `/branch` flow\n- `session_before_compact`, `session.compacting`, `session_compact` for compaction entries that later affect tree-context reconstruction\n\n## Real constraints and edge conditions\n\n- `branch()` cannot target `null`; use `resetLeaf()` for root-before-first-entry state.\n- `branchWithSummary()` supports `null` target and records `fromId: \"root\"`.\n- Selecting current leaf in tree selector is a no-op.\n- Summarization requires an active model; if absent, summarize navigation fails fast.\n- If summarization is aborted, navigation is cancelled and leaf is unchanged.\n- In-memory sessions never return a branch file path from `createBranchedSession`.\n- Tree context reconstruction includes service-tier and MCP tool-selection state, but those entries do not become LLM messages.\n\n## Plan approval session naming\n\nWhen a user approves a plan from plan mode (`InteractiveMode.#approvePlan`), the approval handler seeds the session name from the plan's title so the resulting (fresh or compacted) session does not stay unnamed.\n\nTrigger:\n\n- Plan approval reaches `#approvePlan(...)` with `options.title` populated from the plan-approval details.\n- This runs for every approval choice (`Approve and execute`, `Approve and compact context`, plain `Approve`); the synthetic `plan-approved` prompt is what otherwise bypasses the input-controller's title-generation path.\n\nNaming source:\n\n- The normalized plan title is humanized via `humanizePlanTitle(title)` (`packages/coding-agent/src/plan-mode/approved-plan.ts`):\n  - replaces runs of `-`/`_` with a single space\n  - trims whitespace\n  - capitalizes the first character\n  - returns `\"\"` for whitespace-only / separator-only input\n- The humanized name is applied only when the current session has no name (`!sessionManager.getSessionName()`). It then calls `sessionManager.setSessionName(name, \"auto\")`, which also refuses to overwrite user-named sessions.\n- On successful apply, the terminal title (`setSessionTerminalTitle`) and the editor border color are refreshed to reflect the new name.\n\nExamples (from `humanizePlanTitle`):\n\n- `migrate-mcp-loader` → `Migrate mcp loader`\n- `fix_session_naming` → `Fix session naming`\n- `foo--bar__baz` → `Foo bar baz`\n- `RefactorRouter` → `RefactorRouter` (no separators to expand)\n- `\"\"` / `\"---\"` → `\"\"` (no name applied)\n\n## Legacy compatibility still present\n\nSession migrations still run on load:\n\n- v1→v2 adds `id`/`parentId` and converts compaction index anchor to id anchor\n- v2→v3 migrates legacy `hookMessage` role to `custom`\n\nCurrent runtime behavior is version-3 tree semantics after migration.\n",
 	"session.md": "# Session Storage and Entry Model\n\nThis document is the source of truth for how coding-agent sessions are represented, persisted, migrated, and reconstructed at runtime.\n\n## Scope\n\nCovers:\n\n- Session JSONL format and versioning\n- Entry taxonomy and tree semantics (`id`/`parentId` + leaf pointer)\n- Migration/compatibility behavior when loading old or malformed files\n- Context reconstruction (`buildSessionContext`)\n- Persistence guarantees, failure behavior, truncation/blob externalization\n- Storage abstractions (`FileSessionStorage`, `MemorySessionStorage`) and related utilities\n\nDoes not cover `/tree` UI rendering behavior beyond semantics that affect session data.\n\n## Implementation Files\n\n- [`src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts)\n- [`src/session/messages.ts`](../packages/coding-agent/src/session/messages.ts)\n- [`src/session/session-storage.ts`](../packages/coding-agent/src/session/session-storage.ts)\n- [`src/session/history-storage.ts`](../packages/coding-agent/src/session/history-storage.ts)\n- [`src/session/blob-store.ts`](../packages/coding-agent/src/session/blob-store.ts)\n\n## On-Disk Layout\n\nDefault session file location:\n\n```text\n~/.omp/agent/sessions/<dir-encoded>/<timestamp>_<sessionId>.jsonl\n```\n\n`<dir-encoded>` depends on where the canonicalized cwd lives:\n\n- inside the home directory: `-<relative-path>` with `/`, `\\\\`, and `:` replaced by `-` (bare `-` for home itself)\n- inside the OS temp root: `-tmp-<relative-path>` with the same replacement\n- anywhere else: legacy absolute form `--<cwd-without-leading-slash-with-same-replacement>--`\n\nOld `--<home-encoded>-*--` directories are migrated to the new home-relative names once per sessions root on first access (best-effort).\n\nBlob store location:\n\n```text\n~/.omp/agent/blobs/<sha256>\n```\n\nTerminal breadcrumb files are written under:\n\n```text\n~/.omp/agent/terminal-sessions/<terminal-id>\n```\n\nBreadcrumb content is two lines: original cwd, then session file path. `continueRecent()` prefers this terminal-scoped pointer before scanning most-recent mtime.\n\n## File Format\n\nSession files are JSONL: one JSON object per line.\n\n- Line 1 is always the session header (`type: \"session\"`).\n- Remaining lines are `SessionEntry` values.\n- Entries are append-only at runtime; branch navigation moves a pointer (`leafId`) rather than mutating existing entries.\n\n### Header (`SessionHeader`)\n\n```json\n{\n  \"type\": \"session\",\n  \"version\": 3,\n  \"id\": \"1f9d2a6b9c0d1234\",\n  \"timestamp\": \"2026-02-16T10:20:30.000Z\",\n  \"cwd\": \"/work/pi\",\n  \"title\": \"optional session title\",\n  \"titleSource\": \"auto\",\n  \"parentSession\": \"optional lineage marker\"\n}\n```\n\nNotes:\n\n- `version` is optional in v1 files; absence means v1.\n- `parentSession` is an opaque lineage string. Current code writes either a session id or a session path depending on flow (`fork`, `forkFrom`, `createBranchedSession`, or explicit `newSession({ parentSession })`). Treat as metadata, not a typed foreign key.\n\n### Entry Base (`SessionEntryBase`)\n\nAll non-header entries include:\n\n```json\n{\n  \"type\": \"...\",\n  \"id\": \"8-char-id\",\n  \"parentId\": \"previous-or-branch-parent\",\n  \"timestamp\": \"2026-02-16T10:20:30.000Z\"\n}\n```\n\n`parentId` can be `null` for a root entry (first append, or after `resetLeaf()`).\n\n## Entry Taxonomy\n\n`SessionEntry` is the union of:\n\n- `message`\n- `thinking_level_change`\n- `model_change`\n- `service_tier_change`\n- `compaction`\n- `branch_summary`\n- `custom`\n- `custom_message`\n- `label`\n- `ttsr_injection`\n- `session_init`\n- `mode_change`\n- `mcp_tool_selection`\n\n### `message`\n\nStores an `AgentMessage` directly.\n\n```json\n{\n  \"type\": \"message\",\n  \"id\": \"a1b2c3d4\",\n  \"parentId\": null,\n  \"timestamp\": \"2026-02-16T10:21:00.000Z\",\n  \"message\": {\n    \"role\": \"assistant\",\n    \"provider\": \"anthropic\",\n    \"model\": \"claude-sonnet-4-5\",\n    \"content\": [{ \"type\": \"text\", \"text\": \"Done.\" }],\n    \"usage\": {\n      \"input\": 100,\n      \"output\": 20,\n      \"cacheRead\": 0,\n      \"cacheWrite\": 0,\n      \"cost\": {\n        \"input\": 0,\n        \"output\": 0,\n        \"cacheRead\": 0,\n        \"cacheWrite\": 0,\n        \"total\": 0\n      }\n    },\n    \"timestamp\": 1760000000000\n  }\n}\n```\n\n### `model_change`\n\n```json\n{\n  \"type\": \"model_change\",\n  \"id\": \"b1c2d3e4\",\n  \"parentId\": \"a1b2c3d4\",\n  \"timestamp\": \"2026-02-16T10:21:30.000Z\",\n  \"model\": \"openai/gpt-4o\",\n  \"role\": \"default\"\n}\n```\n\n`role` is optional; missing is treated as `default` in context reconstruction.\n\n### `service_tier_change`\n\n```json\n{\n  \"type\": \"service_tier_change\",\n  \"id\": \"c1d2e3f4\",\n  \"parentId\": \"b1c2d3e4\",\n  \"timestamp\": \"2026-02-16T10:21:45.000Z\",\n  \"serviceTier\": \"flex\"\n}\n```\n\n`serviceTier` can also be `null`.\n\n### `thinking_level_change`\n\n```json\n{\n  \"type\": \"thinking_level_change\",\n  \"id\": \"c1d2e3f4\",\n  \"parentId\": \"b1c2d3e4\",\n  \"timestamp\": \"2026-02-16T10:22:00.000Z\",\n  \"thinkingLevel\": \"high\"\n}\n```\n\n### `compaction`\n\n```json\n{\n  \"type\": \"compaction\",\n  \"id\": \"d1e2f3a4\",\n  \"parentId\": \"c1d2e3f4\",\n  \"timestamp\": \"2026-02-16T10:23:00.000Z\",\n  \"summary\": \"Conversation summary\",\n  \"shortSummary\": \"Short recap\",\n  \"firstKeptEntryId\": \"a1b2c3d4\",\n  \"tokensBefore\": 42000,\n  \"details\": { \"readFiles\": [\"src/a.ts\"] },\n  \"preserveData\": { \"hookState\": true },\n  \"fromExtension\": false\n}\n```\n\n### `branch_summary`\n\n```json\n{\n  \"type\": \"branch_summary\",\n  \"id\": \"e1f2a3b4\",\n  \"parentId\": \"a1b2c3d4\",\n  \"timestamp\": \"2026-02-16T10:24:00.000Z\",\n  \"fromId\": \"a1b2c3d4\",\n  \"summary\": \"Summary of abandoned path\",\n  \"details\": { \"note\": \"optional\" },\n  \"fromExtension\": true\n}\n```\n\nIf branching from root (`branchFromId === null`), `fromId` is the literal string `\"root\"`.\n\n### `custom`\n\nExtension state persistence; ignored by `buildSessionContext`.\n\n```json\n{\n  \"type\": \"custom\",\n  \"id\": \"f1a2b3c4\",\n  \"parentId\": \"e1f2a3b4\",\n  \"timestamp\": \"2026-02-16T10:25:00.000Z\",\n  \"customType\": \"my-extension\",\n  \"data\": { \"state\": 1 }\n}\n```\n\n### `custom_message`\n\nExtension-provided message that does participate in LLM context. `content` can be a string or text/image content blocks, and `attribution` records whether the user or agent initiated it.\n\n```json\n{\n  \"type\": \"custom_message\",\n  \"id\": \"a2b3c4d5\",\n  \"parentId\": \"f1a2b3c4\",\n  \"timestamp\": \"2026-02-16T10:26:00.000Z\",\n  \"customType\": \"my-extension\",\n  \"content\": \"Injected context\",\n  \"display\": true,\n  \"details\": { \"debug\": false },\n  \"attribution\": \"agent\"\n}\n```\n\n### `label`\n\n```json\n{\n  \"type\": \"label\",\n  \"id\": \"b2c3d4e5\",\n  \"parentId\": \"a2b3c4d5\",\n  \"timestamp\": \"2026-02-16T10:27:00.000Z\",\n  \"targetId\": \"a1b2c3d4\",\n  \"label\": \"checkpoint\"\n}\n```\n\n`label: undefined` clears a label for `targetId`.\n\n### `ttsr_injection`\n\n```json\n{\n  \"type\": \"ttsr_injection\",\n  \"id\": \"c2d3e4f5\",\n  \"parentId\": \"b2c3d4e5\",\n  \"timestamp\": \"2026-02-16T10:28:00.000Z\",\n  \"injectedRules\": [\"ruleA\", \"ruleB\"]\n}\n```\n\n### `mcp_tool_selection`\n\n```json\n{\n  \"type\": \"mcp_tool_selection\",\n  \"id\": \"d2e3f4a5\",\n  \"parentId\": \"c2d3e4f5\",\n  \"timestamp\": \"2026-02-16T10:28:30.000Z\",\n  \"selectedToolNames\": [\"server.tool\"]\n}\n```\n\n### `session_init`\n\n```json\n{\n  \"type\": \"session_init\",\n  \"id\": \"d2e3f4a5\",\n  \"parentId\": \"c2d3e4f5\",\n  \"timestamp\": \"2026-02-16T10:29:00.000Z\",\n  \"systemPrompt\": \"...\",\n  \"task\": \"...\",\n  \"tools\": [\"read\", \"edit\"],\n  \"outputSchema\": { \"type\": \"object\" }\n}\n```\n\n### `mode_change`\n\n```json\n{\n  \"type\": \"mode_change\",\n  \"id\": \"e2f3a4b5\",\n  \"parentId\": \"d2e3f4a5\",\n  \"timestamp\": \"2026-02-16T10:30:00.000Z\",\n  \"mode\": \"plan\",\n  \"data\": { \"planFile\": \"/tmp/plan.md\" }\n}\n```\n\n## Versioning and Migration\n\nCurrent session version: `3`.\n\n### v1 -> v2\n\nApplied when header `version` is missing or `< 2`:\n\n- Adds `id` and `parentId` to each non-header entry.\n- Reconstructs a linear parent chain using file order.\n- Migrates compaction field `firstKeptEntryIndex` -> `firstKeptEntryId` when present.\n- Sets header `version = 2`.\n\n### v2 -> v3\n\nApplied when header `version < 3`:\n\n- For `message` entries: rewrites legacy `message.role === \"hookMessage\"` to `\"custom\"`.\n- Sets header `version = 3`.\n\n### Migration Trigger and Persistence\n\n- Migrations run during session load (`setSessionFile`).\n- If any migration ran, the entire file is rewritten to disk immediately.\n- Migration mutates in-memory entries first, then persists rewritten JSONL.\n\n## Load and Compatibility Behavior\n\n`loadEntriesFromFile(path)` behavior:\n\n- Missing file (`ENOENT`) -> returns `[]`.\n- Non-parseable lines are handled by lenient JSONL parser (`parseJsonlLenient`).\n- If first parsed entry is not a valid session header (`type !== \"session\"` or missing string `id`) -> returns `[]`.\n\n`SessionManager.setSessionFile()` behavior:\n\n- `[]` from loader is treated as empty/nonexistent session and replaced with a new initialized session file at that path.\n- Valid files are loaded, migrated if needed, blob refs resolved, then indexed.\n\n## Tree and Leaf Semantics\n\nThe underlying model is append-only tree + mutable leaf pointer:\n\n- Every append method creates exactly one new entry whose `parentId` is current `leafId`.\n- The new entry becomes the new `leafId`.\n- `branch(entryId)` moves only `leafId`; existing entries remain unchanged.\n- `resetLeaf()` sets `leafId = null`; next append creates a new root entry (`parentId: null`).\n- `branchWithSummary()` sets leaf to branch target and appends a `branch_summary` entry.\n\n`getEntries()` returns all non-header entries in insertion order. Existing entries are not deleted in normal operation; rewrites preserve logical history while updating representation (migrations, move, targeted rewrite helpers).\n\n## Context Reconstruction (`buildSessionContext`)\n\n`buildSessionContext(entries, leafId?, byId?, options?)` resolves what is sent to the model. Passing `options.transcript: true` instead builds the full-history display transcript (compactions emitted inline at the position they fired) — display-only, never sent to a provider.\n\nAlgorithm:\n\n1. Determine leaf:\n   - `leafId === null` -> return empty context.\n   - explicit `leafId` -> use that entry if found.\n   - otherwise fallback to last entry.\n2. Walk `parentId` chain from leaf to root and reverse to root->leaf path.\n3. Derive runtime state across path:\n   - `thinkingLevel` from latest `thinking_level_change` (default `\"off\"`)\n   - `serviceTier` from latest `service_tier_change`\n   - model map from `model_change` entries (`role ?? \"default\"`)\n   - fallback `models.default` from assistant message provider/model if no explicit model change\n   - deduplicated `injectedTtsrRules` from all `ttsr_injection` entries\n   - selected MCP discovery tools from latest `mcp_tool_selection`\n   - mode/modeData from latest `mode_change` (default mode `\"none\"`)\n4. Build message list:\n   - `message` entries pass through\n   - `custom_message` entries become `custom` AgentMessages via `createCustomMessage`\n   - `branch_summary` entries become `branchSummary` AgentMessages via `createBranchSummaryMessage`\n   - if a `compaction` exists on path:\n     - emit compaction summary first (`createCompactionSummaryMessage`)\n     - emit path entries starting at `firstKeptEntryId` up to the compaction boundary\n     - emit entries after the compaction boundary\n\n`custom`, `session_init`, `service_tier_change`, `mcp_tool_selection`, and `ttsr_injection` entries do not inject model context directly.\n\n## Persistence Guarantees and Failure Model\n\n### Persist vs in-memory\n\n- `SessionManager.create/open/continueRecent/forkFrom` -> persistent mode (`persist = true`).\n- `SessionManager.inMemory` -> non-persistent mode (`persist = false`) with `MemorySessionStorage`.\n\n### Write pipeline\n\nWrites are serialized through an internal promise chain (`#persistChain`) and `NdjsonFileWriter`.\n\n- `append*` updates in-memory state immediately.\n- Persistence is deferred until at least one assistant message exists.\n  - Before first assistant: entries are retained in memory; no file append occurs.\n  - When first assistant exists: full in-memory session is flushed to file.\n  - Afterwards: new entries append incrementally.\n\nRationale in code: avoid persisting sessions that never produced an assistant response.\n\n### Durability operations\n\n- `flush()` flushes writer and calls `fsync()`.\n- Atomic full rewrites (`#rewriteFile`) write to temp file, flush+fsync, close, then rename over target.\n- Used for migrations, `setSessionName`, `rewriteEntries` (tool-output pruning/supersede passes), and move/fork operations.\n\n### Error behavior\n\n- Persistence errors are latched (`#persistError`) and rethrown on subsequent operations.\n- First error is logged once with session file context.\n- Writer close is best-effort but propagates the first meaningful error.\n\n## Data Size Controls and Blob Externalization\n\nBefore persisting entries:\n\n- Large strings are truncated to `MAX_PERSIST_CHARS` (500,000 chars) with notice:\n  - `\"[Session persistence truncated large content]\"`\n- Transient fields `partialJson` and `jsonlEvents` are removed.\n- If object has both `content` and `lineCount`, line count is recomputed after truncation.\n- Image blocks in `content` arrays with base64 length >= 1024 are externalized to blob refs:\n  - stored as `blob:sha256:<hash>`\n  - raw bytes written to blob store (`BlobStore.put`)\n\nOn load, blob refs are resolved back to base64 for message/custom_message image blocks.\n\n## Storage Abstractions\n\n`SessionStorage` interface provides all filesystem operations used by `SessionManager`:\n\n- sync: `ensureDirSync`, `existsSync`, `writeTextSync`, `statSync`, `listFilesSync`\n- async: `exists`, `readText`, `readTextSlices`, `writeText`, `rename`, `unlink`, `deleteSessionWithArtifacts`, `openWriter`\n\nImplementations:\n\n- `FileSessionStorage`: real filesystem (Bun + node fs)\n- `MemorySessionStorage`: map-backed in-memory implementation for tests/non-persistent sessions\n\n`SessionStorageWriter` exposes `writeLine`, `writeLineSync`, `flush`, `fsync`, `close`, `getError`.\n\n## Session Discovery Utilities\n\nDefined in `session-manager.ts`:\n\n- `getRecentSessions(sessionDir, limit)` -> lightweight metadata for UI/session picker, capped by `limit`\n- `findMostRecentSession(sessionDir)` -> newest by mtime\n- `list(cwd, sessionDir?)` -> sessions in one project scope\n- `listAll()` -> sessions across all project scopes under `~/.omp/agent/sessions`\n- `resolveResumableSession(sessionArg, cwd, sessionDir?)` -> local then global resume/fork target lookup\n\nMetadata extraction for `getRecentSessions` reads a prefix via `readTextSlices(..., 4096, 0)`. `list`/`listAll` read a 4KB prefix plus a bounded 32 KiB tail through one `readTextSlices(...)` call per file, using the prefix for metadata and the tail for lifecycle status. Resume matching is case-insensitive and accepts session id prefixes, full filename prefixes, or the id suffix after the timestamp in `<timestamp>_<sessionId>.jsonl`.\n\n## Related but Distinct: Prompt History Storage\n\n`HistoryStorage` (`history-storage.ts`) is a separate SQLite subsystem for prompt recall/search, not session replay.\n\n- DB: `~/.omp/agent/history.db`\n- Table: `history(id, prompt, created_at, cwd, session_id)`\n- FTS5 index: `history_fts` with trigger-maintained sync\n- Deduplicates consecutive identical prompts using in-memory last-prompt cache\n- Inserts are batched through an async drain queue (~100 ms delay) so prompt capture does not block turn execution\n\nUse session files for conversation graph/state replay; use `HistoryStorage` for prompt history UX.\n",
-	"settings.md": "# Settings\n\n`omp` resolves settings from built-in defaults, a persistent global config file, optional project-local config, one-shot CLI overlays, and in-memory runtime overrides. Reach for project settings when one repository needs a different provider set, model role, tool policy, memory backend, or UI behavior than your global defaults — without touching your machine-wide configuration.\n\nSettings are stored as plain YAML mappings. Every key, its type, default, and enum values come from the settings schema, and you can inspect or change any of them with `omp config` or the interactive `/settings` panel.\n\n- For model/provider credentials, `.env` files, and the env-var table that resolves API keys, see [Providers](./providers.md).\n- For custom model definitions in `models.yml`, see [Models](./models.md).\n- For instruction files discovered into the agent context (`AGENTS.md`, `.omp/`, etc.), see [Context files](./context-files.md).\n- For the full catalog of environment variables, see [Environment variables](./environment-variables.md).\n\n## Where settings live\n\n| Scope | Path | Read behavior | Write behavior |\n|---|---|---|---|\n| Global | `~/.omp/agent/config.yml` | The main persistent settings file. Always loaded. | `/settings`, `omp config set`, and `omp config reset` write here. |\n| Global legacy | `~/.omp/agent/settings.json` | Migrated into `config.yml` once, only when `config.yml` does not yet exist. | Not written after migration; the original is renamed to `settings.json.bak`. |\n| Project | `<cwd>/.omp/config.yml` (plus `.omp/settings.json`) | Loaded when the process working directory has a non-empty `.omp/`. | Read-only from settings commands; edit the file by hand. |\n| Project legacy | `<cwd>/.omp/settings.json` | Still read; project `config.yml` is merged on top of it. | Not written by settings commands. |\n| CLI overlay | Any file passed with `--config <file>` | Loaded after global and project settings, for that one process. Repeatable. | Never persisted. |\n| Runtime overrides | In-memory only | Set by dedicated CLI flags (`--model`, `--approval-mode`, …) and feature env vars. | Never persisted. |\n\n`PI_CODING_AGENT_DIR` relocates the `~/.omp/agent` base directory. When it is set, the global `config.yml`, the auth store (`agent.db`), and everything else under the agent directory move with it. Use `omp config path` to print the active agent directory.\n\nNative project settings are intentionally scoped to the process working directory's `.omp/` folder — settings discovery does **not** walk ancestor directories looking for the nearest `.omp/`. Other discovery providers (Claude, Codex, Gemini, Cursor, OpenCode) can also contribute project-level settings from their own files; those are read-only from `omp` settings commands and can be turned off by provider id (see [Provider and source disabling](#provider-and-source-disabling)).\n\n## Config file formats\n\nThe global `config.yml` is always YAML. The generic config loader used for other files (for example `models.yml`) accepts `.yml`, `.yaml`, `.json`, and `.jsonc`:\n\n- When a `.yml`/`.yaml` path is requested and only a sibling `.json` exists, it is migrated to YAML automatically (idempotent, once per process).\n- `.json` and `.jsonc` configs are read as-is, with no migration.\n- A file whose top level is not a mapping (a bare array or scalar) is treated as empty for persistent settings, and is a hard error for `--config` overlays.\n\n## Reading and writing settings\n\nUse the interactive `/settings` panel inside a session, or the `omp config` command from a shell. Both operate on the merged effective settings, but every persistent write lands in the **global** file only.\n\n```bash\nomp config list                 # all settings with current effective values\nomp config list --json          # same, machine-readable\nomp config get theme.dark       # one value\nomp config get theme.dark --json\nomp config set compaction.enabled false\nomp config set defaultThinkingLevel medium\nomp config reset steeringMode   # restore a key to its schema default\nomp config path                 # print the active agent directory\n```\n\n### Subcommands\n\n| Command | Effect |\n|---|---|\n| `omp config list` | Print every setting grouped by tab, with its current value and type. `--json` emits an object keyed by setting path with `{ value, type, description }`. |\n| `omp config get <key>` | Print the effective value of one key. Unknown keys exit non-zero. `--json` emits `{ key, value, type, description }`. |\n| `omp config set <key> <value>` | Parse `<value>` against the key's schema type and write it to the global `config.yml`. |\n| `omp config reset <key>` | Write the key's schema **default** back to the global config (this persists the default, it does not delete the key). |\n| `omp config path` | Print the active agent directory (honors `PI_CODING_AGENT_DIR`). |\n\n`omp config` with no subcommand, or `--help`, prints the help and lists settings. The `--json` flag is accepted by `list`, `get`, `set`, and `reset`.\n\n### Value parsing\n\n`omp config set` parses the value string according to the target key's schema type. The string is trimmed first.\n\n| Type | Accepted input | Notes |\n|---|---|---|\n| boolean | `true`, `false`, `yes`, `no`, `on`, `off`, `1`, `0` | Case-insensitive. Anything else is rejected. |\n| number | Any finite JavaScript number | `Infinity`/`NaN` are rejected. |\n| enum | One of the key's allowed values | Must match exactly; the error lists the valid values. |\n| array | A JSON array | e.g. `'[\"anthropic\",\"openai\"]'`. Must parse and be an array. |\n| record | A JSON object | e.g. `'{\"bash\":\"prompt\"}'`. Must parse and be a non-array object. |\n| string | Stored as given (trimmed) | Multi-word values are joined with spaces. |\n\nKeys must match a real schema path exactly. There is no shorthand — set `theme.dark`, not `theme`.\n\n### Where writes go\n\n`omp config set`, `omp config reset`, `/settings`, and any runtime settings change all write to the global `config.yml` under the active agent directory. They never write to `<cwd>/.omp/config.yml`. To create a project-local override, edit that file directly (see [Project-local config](#project-local-config)). Saves are debounced and re-read the file under a lock, so external edits made while a session is open are preserved.\n\n## Precedence\n\nFrom lowest to highest priority, the effective value of a setting is built as:\n\n```text\nbuilt-in defaults  <-  global config  <-  project config  <-  CLI overlays  <-  runtime overrides\n```\n\nFrom highest to lowest:\n\n1. **Runtime overrides** — dedicated CLI flags and feature env vars applied in memory for the current process: `--model`, `--smol`, `--slow`, `--plan`, `--approval-mode`, `--auto-approve`/`--yolo`, `--hide-thinking`, `--no-pty`, `--api-key`, and protocol-mode defaults. Never persisted.\n2. **CLI config overlays** — each `--config <file>`; later overlay files override earlier ones.\n3. **Project settings** — `<cwd>/.omp/settings.json` then `<cwd>/.omp/config.yml` (and contributions from other discovery providers at project level).\n4. **Global settings** — `~/.omp/agent/config.yml`.\n5. **Built-in defaults** — from the settings schema.\n\nA key that is unset at every layer resolves to its schema default at read time.\n\n### Environment overrides\n\nEnvironment variables are **not** a single settings layer. Each is read by the feature that owns the value, usually as a per-machine override or fallback, and is never written back to `config.yml`. The ones that map directly onto a setting:\n\n| Env var | Overrides setting | Notes |\n|---|---|---|\n| `PI_SMOL_MODEL` | `modelRoles.smol` | Also exposed as `--smol`. |\n| `PI_SLOW_MODEL` | `modelRoles.slow` | Also exposed as `--slow`. |\n| `PI_PLAN_MODEL` | `modelRoles.plan` | Also exposed as `--plan`. |\n| `PI_NO_PTY=1` | (disables PTY bash) | Equivalent to `--no-pty` for the process. |\n| `PI_PY` | `eval.py` | `PI_PY=0` disables the Python eval backend. |\n| `PI_JS` | `eval.js` | `PI_JS=0` disables the JavaScript eval backend. |\n| `PI_TINY_DEVICE` | `providers.tinyModelDevice` | ONNX execution provider for local tiny models. |\n| `PI_TINY_DTYPE` | `providers.tinyModelDtype` | ONNX precision for local tiny models. |\n| `OMP_AUTH_BROKER_URL` | `auth.broker.url` | Env value takes precedence over config. |\n| `OMP_AUTH_BROKER_TOKEN` | `auth.broker.token` | Env value takes precedence over config. |\n| `PI_CODING_AGENT_DIR` | (relocates agent dir) | Moves `config.yml`, `agent.db`, and the whole agent base. |\n\nProvider API keys are resolved separately (stored auth, OAuth, `models.yml`, environment, and `.env` files); see [Providers](./providers.md) and the full [Environment variables](./environment-variables.md) reference.\n\n## Merge rules\n\nLayers are combined with a deep merge:\n\n- **Objects are deep-merged** — keys present only in a lower layer are kept; keys present in a higher layer override.\n- **Scalars and arrays are replaced wholesale** by the higher-precedence layer. A higher layer's array does not append to a lower layer's array.\n\nUse nested YAML mappings for dotted setting paths:\n\n```yaml\ntheme:\n  dark: titanium\n  light: light\n\ntools:\n  approvalMode: write\n  approval:\n    bash: prompt\n    read: allow\n```\n\n### Worked example: global vs. project\n\n```yaml\n# ~/.omp/agent/config.yml\ntools:\n  approvalMode: write\n  approval:\n    bash: prompt\n    read: allow\ndisabledProviders:\n  - anthropic\n  - openai\n  - gemini\n\n# <repo>/.omp/config.yml\ntools:\n  approval:\n    bash: allow\ndisabledProviders:\n  - groq\n```\n\nEffective settings inside `<repo>`:\n\n```yaml\ntools:\n  approvalMode: write   # kept from global (object deep-merge)\n  approval:\n    bash: allow         # overridden by project\n    read: allow         # kept from global\ndisabledProviders:\n  - groq                # project array REPLACES the global array\n```\n\nArray replacement is the most common surprise: the project's `disabledProviders` does not extend the global list — it becomes the entire list for that project. The same applies to `enabledModels`, `cycleOrder`, `extensions`, and every other array-typed setting.\n\n## Project-local config\n\nCreate `<repo>/.omp/config.yml` when a repository needs its own settings:\n\n```yaml\n# <repo>/.omp/config.yml\nmodelRoles:\n  default: anthropic/claude-sonnet-4-5\n  smol: openai/gpt-4.1-mini\n  slow: anthropic/claude-opus-4-5:high\n\ntools:\n  approvalMode: write\n  approval:\n    bash: prompt\n\ncompaction:\n  strategy: context-full\n  thresholdPercent: 80\n\ntheme:\n  dark: titanium\n```\n\nKeep secrets out of committed project config unless your repository policy allows it. Prefer environment variables, stored auth, an auth broker, or an untracked `--config` overlay for credentials.\n\n### One-shot overlays\n\nUse `--config` for a temporary layer that should not persist:\n\n```bash\nomp --config ./local/ci-settings.yml \"check this failure\"\nomp --config ./base.yml --config ./experiment.yml \"try this model\"\n```\n\nOverlay paths are resolved relative to the process working directory (and `~` is expanded). Each overlay must parse as a YAML mapping; a missing file, invalid YAML, or a top-level array/scalar is a hard error — it does **not** silently fall back to lower-precedence settings.\n\n## Path-scoped arrays\n\nTwo array settings — `enabledModels` and `disabledProviders` — accept path-scoped entries in addition to bare strings, so a single global config can behave differently per directory:\n\n```yaml\nenabledModels:\n  - claude-sonnet-4-5            # applies everywhere\n  - path: ~/work/high-context\n    models:\n      - anthropic/claude-opus-4-5\n\ndisabledProviders:\n  - ollama                       # applies everywhere\n  - paths:\n      - ~/projects/sensitive\n      - ~/clients/acme\n    providers:\n      - anthropic\n      - openai\n```\n\nBare string entries apply everywhere. A scoped entry applies when the current working directory **is** the configured path or is **under** it. `~` expands to your home directory and relative paths are resolved before matching.\n\nAccepted **path** keys (any of them, combined): `path`, `paths`, `pathPrefix`, `pathPrefixes`.\n\nAccepted **value** keys:\n\n- `models` (for `enabledModels`) or `providers` (for `disabledProviders`)\n- `values` or `items` (for either setting)\n\nOnly string values are kept; malformed scoped entries are ignored. Path scoping is resolved **after** the layer merge, so it reads the final effective array.\n\n## Provider and source disabling\n\n`disabledProviders` is a single shared id namespace that gates two different subsystems, before any credential check:\n\n| Entry kind | Example ids | Effect |\n|---|---|---|\n| Model providers | `anthropic`, `openai`, `gemini`, `groq`, `ollama`, `openrouter` | Removes those backends from model selection, even when credentials are available. See [Providers](./providers.md). |\n| Discovery sources | `native`, `claude`, `codex`, `gemini`, `github`, `opencode`, `cursor`, `agents-md` | Stops that source from contributing context files, MCP servers, commands, skills, hooks, tools, prompts, or settings. See [Context files](./context-files.md). |\n\nMost provider-control use cases list model provider ids. Disabling the `claude` discovery source is different from disabling the `anthropic` model provider — one stops Claude-format config discovery, the other stops the Anthropic model backend.\n\nBecause arrays replace rather than append, a project that sets `disabledProviders` must list the complete desired set:\n\n```yaml\n# ~/.omp/agent/config.yml\ndisabledProviders:\n  - anthropic\n  - openai\n\n# <repo>/.omp/config.yml — inside this repo ONLY groq is disabled\ndisabledProviders:\n  - groq\n```\n\nThe default is an empty array (nothing disabled). For the two subsystems' provider ids and ordering, see [Providers](./providers.md) and [Context files](./context-files.md).\n\n## Settings catalog\n\nEvery key below is defined in the settings schema; `omp config list` shows the full set with current values. Defaults and enum values are taken from the schema. Settings that accept an env or flag override are noted; those overrides are process-local and not persisted.\n\n### Models\n\n`modelRoles`, `modelTags`, and `cycleOrder` work together to define the models you can switch between. Role values may carry a thinking suffix (`:minimal`, `:low`, `:medium`, `:high`, `:xhigh`).\n\n```yaml\nmodelRoles:\n  default: anthropic/claude-sonnet-4-5\n  smol: openai/gpt-4.1-mini\n  slow: anthropic/claude-opus-4-5:high\n  vision: gemini/gemini-3-pro-preview\n  plan: anthropic/claude-opus-4-5\n\ncycleOrder:\n  - smol\n  - default\n  - slow\n\nmodelProviderOrder:\n  - anthropic\n  - openai\n\nenabledModels:\n  - claude-sonnet-4-5\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `modelRoles` | record | `{}` | Map of role name -> model id. Built-in roles: `default`, `smol`, `slow`, `vision`, `plan`, `designer`, `commit`, `title`, `task`. Per-role env/flags: `--model`/`--smol`/`--slow`/`--plan`. |\n| `modelTags` | record | `{}` | Custom role/tag metadata; can introduce additional roles. |\n| `modelProviderOrder` | array | `[]` | Preferred provider order when a model id is ambiguous. |\n| `cycleOrder` | array | `[\"smol\",\"default\",\"slow\"]` | Roles cycled by the model switcher. |\n| `enabledModels` | array | `[]` | Allow-list of models; supports [path-scoped entries](#path-scoped-arrays). Empty means all available models. |\n| `disabledProviders` | array | `[]` | Disabled model/discovery providers; supports path-scoped entries. See [above](#provider-and-source-disabling). |\n| `includeModelInPrompt` | boolean | `true` | Include the active model name in the system prompt. |\n\nSee [Models](./models.md) for the `models.yml` schema and custom-provider definitions.\n\n### Thinking\n\n```yaml\ndefaultThinkingLevel: high\nhideThinkingBlock: false\nthinkingBudgets:\n  minimal: 1024\n  low: 2048\n  medium: 8192\n  high: 16384\n  xhigh: 32768\n```\n\n| Key | Type | Default | Values |\n|---|---|---|---|\n| `defaultThinkingLevel` | enum | `high` | `minimal`, `low`, `medium`, `high`, `xhigh`, `auto`. Override per run with `--thinking`. |\n| `hideThinkingBlock` | boolean | `false` | Hide thinking blocks in output. `--hide-thinking` sets it for the run (display only). |\n| `thinkingBudgets.minimal` | number | `1024` | Token budget for the `minimal` level. |\n| `thinkingBudgets.low` | number | `2048` | Token budget for `low`. |\n| `thinkingBudgets.medium` | number | `8192` | Token budget for `medium`. |\n| `thinkingBudgets.high` | number | `16384` | Token budget for `high`. |\n| `thinkingBudgets.xhigh` | number | `32768` | Token budget for `xhigh`. |\n\n### Sampling\n\nA value of `-1` means \"use the provider/model default\" — `omp` does not send that parameter.\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `temperature` | number | `-1` | Sampling temperature. |\n| `topP` | number | `-1` | Nucleus sampling. |\n| `topK` | number | `-1` | Top-K sampling. |\n| `minP` | number | `-1` | Minimum-probability cutoff. |\n| `presencePenalty` | number | `-1` | Presence penalty. |\n| `repetitionPenalty` | number | `-1` | Repetition penalty. |\n| `serviceTier` | enum | `none` | `none`, `auto`, `default`, `flex`, `scale`, `priority`, `openai-only`, `claude-only`. |\n| `personality` | enum | `default` | `default`, `friendly`, `pragmatic`, `none`. |\n\n### Retry and fallback\n\n```yaml\nretry:\n  enabled: true\n  maxRetries: 10\n  baseDelayMs: 500\n  maxDelayMs: 300000\n  modelFallback: true\n  fallbackRevertPolicy: cooldown-expiry\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `retry.enabled` | boolean | `true` | Retry transient provider errors. |\n| `retry.maxRetries` | number | `10` | Max retries per request. |\n| `retry.baseDelayMs` | number | `500` | Initial backoff. |\n| `retry.maxDelayMs` | number | `300000` | Backoff ceiling (5 min). |\n| `retry.modelFallback` | boolean | `true` | Fall back to another model when one is unavailable. |\n| `retry.fallbackChains` | record | `{}` | Per-model fallback chains. |\n| `retry.fallbackRevertPolicy` | enum | `cooldown-expiry` | `cooldown-expiry`, `never`. |\n\n### Tools and approvals\n\n```yaml\ntools:\n  approvalMode: yolo          # default\n  approval:\n    bash: prompt\n    edit: allow\n  discoveryMode: auto\n  maxTimeout: 0\n  intentTracing: true\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `tools.approvalMode` | enum | `yolo` | `always-ask` (auto-approve read-only), `write` (auto-approve read + workspace-write), `yolo` (auto-approve all tiers). `--approval-mode` and `--auto-approve`/`--yolo` override per run. |\n| `tools.approval` | record | `{}` | Per-tool policy keyed by tool name; each value is `allow`, `deny`, or `prompt`. e.g. `omp config set tools.approval '{\"bash\":\"prompt\"}'`. |\n| `tools.discoveryMode` | enum | `auto` | `auto`, `off`, `mcp-only`, `all`. Controls dynamic tool discovery. |\n| `tools.essentialOverride` | array | `[]` | Tool names kept available even when tools are narrowed. |\n| `tools.maxTimeout` | number | `0` | Max tool runtime in seconds; `0` = no cap. |\n| `tools.intentTracing` | boolean | `true` | Record per-call intent strings. |\n| `tools.outputMaxColumns` | number | `768` | Per-line byte cap for streaming output; `0` disables. |\n| `tools.artifactSpillThreshold` | number | `50` | KB of tool output above which output spills to an artifact. |\n| `tools.artifactHeadBytes` | number | `20` | KB of head kept inline on spill; `0` = tail-only. |\n| `tools.artifactTailBytes` | number | `20` | KB of tail kept inline on spill. |\n| `tools.artifactTailLines` | number | `500` | Max tail lines kept inline on spill. |\n\nIndividual built-in tools are toggled by their own keys, e.g. `bash.enabled`, `eval.py`, `eval.js`, `find.enabled`, `search.enabled`, `fetch.enabled`, `browser.enabled`, `astEdit.enabled`, `astGrep.enabled`, `web_search.enabled`, `inspect_image.enabled`, `renderMermaid.enabled`.\n\n### Shell, eval, and LSP\n\n```yaml\nbash:\n  enabled: true\n  stripTrailingHeadTail: true\n  autoBackground:\n    enabled: false\n    thresholdMs: 60000\n\neval:\n  py: true\n  js: true\n\npython:\n  kernelMode: session       # session, per-call\n  interpreter: \"\"\n\nlsp:\n  enabled: true\n  lazy: true\n  diagnosticsOnWrite: true\n  diagnosticsOnEdit: false\n  formatOnWrite: false\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `bash.enabled` | boolean | `true` | Enable the bash tool. |\n| `bash.stripTrailingHeadTail` | boolean | `true` | Strip trailing head/tail noise from output. |\n| `bash.autoBackground.enabled` | boolean | `false` | Auto-background long-running commands. |\n| `bash.autoBackground.thresholdMs` | number | `60000` | Threshold before auto-backgrounding. |\n| `eval.py` | boolean | `true` | Python eval backend. `PI_PY=0` disables for the process. |\n| `eval.js` | boolean | `true` | JavaScript eval backend. `PI_JS=0` disables for the process. |\n| `python.kernelMode` | enum | `session` | `session` (persistent kernel) or `per-call`. |\n| `python.interpreter` | string | `\"\"` | Path to a Python interpreter; empty = auto-detect. |\n| `lsp.enabled` | boolean | `true` | Language-server integration. `--no-lsp` disables for the run. |\n| `lsp.lazy` | boolean | `true` | Start servers on demand. |\n| `lsp.diagnosticsOnWrite` | boolean | `true` | Run diagnostics after a write. |\n| `lsp.diagnosticsOnEdit` | boolean | `false` | Run diagnostics after an edit. |\n| `lsp.formatOnWrite` | boolean | `false` | Format files on write. |\n| `lsp.diagnosticsDeduplicate` | boolean | `true` | Collapse duplicate diagnostics. |\n| `shellPath` | string | _(unset)_ | Override the shell binary used by bash. |\n\n### Files: editing and reading\n\n```yaml\nedit:\n  mode: hashline            # apply_patch, hashline, patch, replace\n  fuzzyMatch: true\n  fuzzyThreshold: 0.95\n  blockAutoGenerated: true\n\nread:\n  defaultLimit: 300\n  toolResultPreview: false\n  summarize:\n    enabled: true\n    prose: false\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `edit.mode` | enum | `hashline` | `apply_patch`, `hashline`, `patch`, `replace`. |\n| `edit.fuzzyMatch` | boolean | `true` | Allow fuzzy anchor matching. |\n| `edit.fuzzyThreshold` | number | `0.95` | Similarity threshold for fuzzy matching. |\n| `edit.blockAutoGenerated` | boolean | `true` | Refuse to edit generated/lockfile-like files. |\n| `edit.streamingAbort` | boolean | `false` | Abort on streaming edit mismatch. |\n| `read.defaultLimit` | number | `300` | Default line count for `read` without a selector. |\n| `read.summarize.enabled` | boolean | `true` | Structural summaries for code reads. |\n| `read.summarize.prose` | boolean | `false` | Summarize prose files too. |\n| `read.toolResultPreview` | boolean | `false` | Inline preview of tool results. |\n| `readHashLines` | boolean | `true` | Show hashline tags in read output. |\n| `readLineNumbers` | boolean | `false` | Show plain line numbers. |\n\n### Context, compaction, and memory\n\n```yaml\ncontextPromotion:\n  enabled: true\n\ncompaction:\n  enabled: true\n  strategy: context-full     # context-full, handoff, shake, snapcompact, off\n  thresholdPercent: -1       # -1 = default reserve-based behavior\n  thresholdTokens: -1        # fixed token limit when > 0\n  remoteEnabled: true\n\nmemory:\n  backend: off               # off, local, hindsight, mnemopi\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `contextPromotion.enabled` | boolean | `true` | Promote relevant earlier context. |\n| `compaction.enabled` | boolean | `true` | Automatic conversation compaction. |\n| `compaction.strategy` | enum | `context-full` | `context-full`, `handoff`, `shake`, `snapcompact`, `off`. |\n| `compaction.thresholdPercent` | number | `-1` | Percent-of-context trigger; `-1` = reserve-based default. |\n| `compaction.thresholdTokens` | number | `-1` | Fixed token trigger when `> 0`. |\n| `compaction.reserveTokens` | number | `16384` | Tokens reserved for the next turn. |\n| `compaction.keepRecentTokens` | number | `20000` | Recent tokens always preserved. |\n| `compaction.remoteEnabled` | boolean | `true` | Allow remote compaction service. |\n| `compaction.autoContinue` | boolean | `true` | Continue automatically after compaction. |\n| `memory.backend` | enum | `off` | `off`, `local`, `hindsight`, `mnemopi`. Each backend has its own `hindsight.*` / `mnemopi.*` / `memories.*` tuning keys. |\n| `autolearn.enabled` | boolean | `false` | Experimental: after the agent stops, nudge it to capture lessons to memory and create/enhance isolated managed skills under `~/.omp/agent/managed-skills`. Enables the `manage_skill` tool (and `learn` when a memory backend is active). |\n| `autolearn.autoContinue` | boolean | `false` | When `autolearn.enabled`, auto-run one capture turn at stop (uses extra tokens). Off = a passive reminder rides your next turn. |\n| `autolearn.minToolCalls` | number | `5` | Only nudge after a turn that used at least this many tools. |\n\n`compaction` has additional tuning keys (idle compaction, supersede/drop heuristics) visible in `omp config list`. See [Compaction](./compaction.md) for the full strategy reference.\n\n### Appearance and terminal\n\n```yaml\ntheme:\n  dark: titanium\n  light: light\nsymbolPreset: unicode        # unicode, nerd, ascii\ncolorBlindMode: false\n\nstatusLine:\n  preset: default            # default, minimal, compact, full, nerd, ascii, custom\n  separator: powerline-thin\n  transparent: false\n  showHookStatus: true\n\nterminal:\n  showImages: true\nimages:\n  autoResize: true\n  blockImages: false\ntui:\n  hyperlinks: auto           # off, auto, always\n```\n\n| Key | Type | Default | Values |\n|---|---|---|---|\n| `theme.dark` | string | `titanium` | Theme used on a dark terminal background. |\n| `theme.light` | string | `light` | Theme used on a light terminal background. |\n| `symbolPreset` | enum | `unicode` | `unicode`, `nerd`, `ascii`. |\n| `colorBlindMode` | boolean | `false` | Use blue instead of green for diff additions. |\n| `showHardwareCursor` | boolean | `true` | Show the terminal hardware cursor. |\n| `statusLine.preset` | enum | `default` | `default`, `minimal`, `compact`, `full`, `nerd`, `ascii`, `custom`. |\n| `statusLine.separator` | enum | `powerline-thin` | `powerline`, `powerline-thin`, `slash`, `pipe`, `block`, `none`, `ascii`. |\n| `statusLine.sessionAccent` | boolean | `true` | Tint the editor border with the session color. |\n| `statusLine.transparent` | boolean | `false` | Use the terminal background for the status line. |\n| `statusLine.showHookStatus` | boolean | `true` | Show hook status messages. |\n| `terminal.showImages` | boolean | `true` | Render images inline (when the terminal supports it). |\n| `images.autoResize` | boolean | `true` | Resize large images for model compatibility. |\n| `images.blockImages` | boolean | `false` | Never send images to providers. |\n| `tui.hyperlinks` | enum | `auto` | `off`, `auto`, `always`. |\n\nFor a custom status line, set `statusLine.preset: custom` and configure `statusLine.leftSegments`, `statusLine.rightSegments`, and `statusLine.segmentOptions`.\n\n### Interaction\n\n| Key | Type | Default | Values |\n|---|---|---|---|\n| `steeringMode` | enum | `one-at-a-time` | `all`, `one-at-a-time`. How queued steering messages are delivered. |\n| `followUpMode` | enum | `one-at-a-time` | `all`, `one-at-a-time`. |\n| `interruptMode` | enum | `immediate` | `immediate`, `wait`. |\n| `doubleEscapeAction` | enum | `tree` | `branch`, `tree`, `none`. |\n| `autoResume` | boolean | `false` | Auto-resume the most recent session in the cwd. |\n| `ask.timeout` | number | `0` | Seconds before an `ask` prompt times out; `0` = no timeout. (Legacy ms values are migrated to seconds.) |\n| `ask.notify` | enum | `on` | `on`, `off`. |\n\n### Providers and services\n\n```yaml\nproviders:\n  webSearch: auto\n  image: auto\n  fetch: auto\n  tinyModel: online\n  tinyModelDevice: default\n  tinyModelDtype: default\n  openaiWebsockets: auto\n  openrouterVariant: default\n  kimiApiFormat: anthropic\n\nprovider:\n  appendOnlyContext: auto    # auto, on, off\n\nexa:\n  enabled: true\n  enableSearch: true\n  enableResearcher: false\n  enableWebsets: false\n\nsearxng:\n  endpoint: https://search.example.com\n  token: SEARXNG_TOKEN\n```\n\n| Key | Type | Default | Values / notes |\n|---|---|---|---|\n| `providers.webSearch` | enum | `auto` | `auto` plus the configured search providers (`tavily`, `perplexity`, `brave`, `jina`, `kimi`, `anthropic`, `gemini`, `codex`, `zai`, `exa`, `parallel`, `kagi`, `synthetic`, `searxng`). |\n| `providers.image` | enum | `auto` | `auto`, `openai`, `antigravity`, `xai`, `gemini`, `openrouter`. |\n| `providers.fetch` | enum | `auto` | `auto`, `native`, `trafilatura`, `lynx`, `parallel`, `jina`. |\n| `providers.tinyModel` | enum | `online` | `online` or a local model (`lfm2-350m`, `qwen3-0.6b`, `gemma-270m`, `qwen2.5-0.5b`, `lfm2-700m`). |\n| `providers.tinyModelDevice` | enum | `default` | ONNX execution provider for local tiny models. Overridden by `PI_TINY_DEVICE`. |\n| `providers.tinyModelDtype` | enum | `default` | ONNX precision for local tiny models. Overridden by `PI_TINY_DTYPE`. |\n| `providers.openaiWebsockets` | enum | `auto` | `auto`, `off`, `on`. |\n| `providers.openrouterVariant` | enum | `default` | `default`, `nitro`, `floor`, `online`, `exacto`. |\n| `providers.kimiApiFormat` | enum | `anthropic` | `openai`, `anthropic`. |\n| `provider.appendOnlyContext` | enum | `auto` | `auto`, `on`, `off`. |\n| `exa.enabled` | boolean | `true` | Enable Exa integration. |\n| `exa.enableSearch` | boolean | `true` | Exa search. |\n| `exa.enableResearcher` | boolean | `false` | Exa researcher. |\n| `exa.enableWebsets` | boolean | `false` | Exa websets. |\n| `searxng.endpoint` | string | _(unset)_ | SearXNG instance URL. |\n| `searxng.token` | string | _(unset)_ | SearXNG token; also `searxng.basicUsername`/`searxng.basicPassword`/`searxng.categories`/`searxng.language`. |\n| `auth.broker.url` | string | _(unset)_ | Auth-broker URL. Overridden by `OMP_AUTH_BROKER_URL`. |\n| `auth.broker.token` | string | _(unset)_ | Auth-broker token. Overridden by `OMP_AUTH_BROKER_TOKEN`. |\n\nProvider credentials and custom model definitions are configured separately — see [Providers](./providers.md) and [Models](./models.md).\n\n### Other groups\n\n`omp config list` exposes many more grouped settings, including: `task.*` (subagent concurrency, isolation, model overrides), `skills.*` and `commands.*` (discovery toggles), `mcp.*`, `github.*`, `async.*`, `goal.*`, `loop.*`, `todo.*`, `magicKeywords.*`, `ttsr.*` (sticky rules), `display.*`, `startup.*`, `share.*`, `collab.*`, `stt.*`/`tts.*`, `memories.*`/`hindsight.*`/`mnemopi.*` (memory backends), and `bashInterceptor.*`. Each follows the same type/default rules shown above.\n\n## Legacy migration\n\n`omp` migrates older config shapes automatically. None of these require action; they are listed so you know what changes you may see in `config.yml`.\n\n### Startup migration to `config.yml`\n\nWhen `~/.omp/agent/config.yml` does not exist, startup builds it once from legacy sources, then writes the result:\n\n1. `~/.omp/agent/settings.json` (renamed to `settings.json.bak` after a successful migration).\n2. Settings persisted in `agent.db`.\n\nAfter `config.yml` exists, these legacy sources are no longer consulted. The generic config loader also performs `.json` -> `.yml` migration for other config files when only the `.json` form is present.\n\n### Field-level migrations\n\nApplied whenever raw settings are loaded (global, project, overlays, and runtime overrides):\n\n| Old | New |\n|---|---|\n| `queueMode` | `steeringMode` |\n| `ask.timeout` in milliseconds (value `> 1000`) | seconds (divided by 1000) |\n| flat `theme: \"<name>\"` string | `theme.dark` / `theme.light` (slot chosen by luminance; built-in `light`/`dark` are dropped to use defaults) |\n| `task.isolation.enabled: true/false` | `task.isolation.mode: auto/none` |\n| `task.simple` | removed |\n| legacy `task.isolation.mode` (`worktree`, `fuse-overlay`, `fuse-projfs`) | `rcopy`, `overlayfs`, `projfs` |\n| `lastChangelogVersion` | moved to a marker file and stripped from `config.yml` |\n\n## Troubleshooting\n\n### A project setting is not taking effect\n\n- Start `omp` from the directory that contains `.omp/config.yml`. Settings discovery only checks the current working directory's `.omp/`, not ancestor directories.\n- Ensure `.omp/` is non-empty; empty config directories are ignored.\n- Confirm the file is valid YAML and its top level is a mapping.\n- Run `omp config get <key>` from that directory to see the effective value.\n- Remember that `--config` overlays and runtime flags override project config.\n\n### A global array disappeared in a project\n\nArrays replace; they do not append. If a project sets `disabledProviders`, `enabledModels`, `cycleOrder`, `extensions`, or any other array, include the **complete** desired value in the project layer — the global array is fully replaced.\n\n### A provider is still available after editing config\n\n- Check whether you disabled the model provider id (e.g. `anthropic`) or a discovery source id (e.g. `claude`) — they are different namespaces with different effects.\n- Check for a project (or overlay) `disabledProviders` array replacing your global one.\n- Credentials can still come from environment variables, `.env`, OAuth, stored auth, or `models.yml`; disabling a provider blocks selection regardless, but verify you edited the right layer. See [Providers](./providers.md).\n- Restart the session if the model list was already initialized.\n\n### `omp config set` changed the wrong file\n\n`omp config set` and `omp config reset` always write the global `config.yml` under the active agent directory. Run `omp config path` to print it. For project-local settings, edit `<repo>/.omp/config.yml` directly.\n\n### `omp config reset` did not remove my key\n\n`reset` writes the schema **default** value into the global config — it persists the default rather than deleting the key. To stop overriding a project value from global config, delete the key from `~/.omp/agent/config.yml` by hand.\n\n### A `--config` overlay fails at startup\n\n`--config` files are process-local YAML mappings. A missing file, invalid YAML, or a top-level array/scalar is a hard error — it does not silently fall back to lower-precedence settings. Fix the path or contents.\n\n### An environment variable beats my config\n\nSome settings (model roles, eval backends, tiny-model device/precision, auth broker, PTY) are overridable by env vars or CLI flags for per-machine convenience, and those take precedence over `config.yml`. Unset the variable or drop the flag to let the persisted value win. See [Environment overrides](#environment-overrides) and [Environment variables](./environment-variables.md).\n\n### `omp config set <key>` says \"Unknown setting\"\n\nKeys must match a schema path exactly, with no shorthand. Use `theme.dark`, not `theme`. Run `omp config list` to see every valid key.\n",
+	"settings.md": "# Settings\n\n`omp` resolves settings from built-in defaults, a persistent global config file, optional project-local config, one-shot CLI overlays, and in-memory runtime overrides. Reach for project settings when one repository needs a different provider set, model role, tool policy, memory backend, or UI behavior than your global defaults — without touching your machine-wide configuration.\n\nSettings are stored as plain YAML mappings. Every key, its type, default, and enum values come from the settings schema, and you can inspect or change any of them with `omp config` or the interactive `/settings` panel.\n\n- For model/provider credentials, `.env` files, and the env-var table that resolves API keys, see [Providers](./providers.md).\n- For custom model definitions in `models.yml`, see [Models](./models.md).\n- For instruction files discovered into the agent context (`AGENTS.md`, `.omp/`, etc.), see [Context files](./context-files.md).\n- For the full catalog of environment variables, see [Environment variables](./environment-variables.md).\n\n## Where settings live\n\n| Scope | Path | Read behavior | Write behavior |\n|---|---|---|---|\n| Global | `~/.omp/agent/config.yml` | The main persistent settings file. Always loaded. | `/settings`, `omp config set`, and `omp config reset` write here. |\n| Global legacy | `~/.omp/agent/settings.json` | Migrated into `config.yml` once, only when `config.yml` does not yet exist. | Not written after migration; the original is renamed to `settings.json.bak`. |\n| Project | `<cwd>/.omp/config.yml` (plus `.omp/settings.json`) | Loaded when the process working directory has a non-empty `.omp/`. | Read-only from settings commands; edit the file by hand. |\n| Project legacy | `<cwd>/.omp/settings.json` | Still read; project `config.yml` is merged on top of it. | Not written by settings commands. |\n| CLI overlay | Any file passed with `--config <file>` | Loaded after global and project settings, for that one process. Repeatable. | Never persisted. |\n| Runtime overrides | In-memory only | Set by dedicated CLI flags (`--model`, `--approval-mode`, …) and feature env vars. | Never persisted. |\n\n`PI_CODING_AGENT_DIR` relocates the `~/.omp/agent` base directory. When it is set, the global `config.yml`, the auth store (`agent.db`), and everything else under the agent directory move with it. Use `omp config path` to print the active agent directory.\n\nNative project settings are intentionally scoped to the process working directory's `.omp/` folder — settings discovery does **not** walk ancestor directories looking for the nearest `.omp/`. Other discovery providers (Claude, Codex, Gemini, Cursor, OpenCode) can also contribute project-level settings from their own files; those are read-only from `omp` settings commands and can be turned off by provider id (see [Provider and source disabling](#provider-and-source-disabling)).\n\n## Config file formats\n\nThe global `config.yml` is always YAML. The generic config loader used for other files (for example `models.yml`) accepts `.yml`, `.yaml`, `.json`, and `.jsonc`:\n\n- When a `.yml`/`.yaml` path is requested and only a sibling `.json` exists, it is migrated to YAML automatically (idempotent, once per process).\n- `.json` and `.jsonc` configs are read as-is, with no migration.\n- A file whose top level is not a mapping (a bare array or scalar) is treated as empty for persistent settings, and is a hard error for `--config` overlays.\n\n## Reading and writing settings\n\nUse the interactive `/settings` panel inside a session, or the `omp config` command from a shell. Both operate on the merged effective settings, but every persistent write lands in the **global** file only.\n\n```bash\nomp config list                 # all settings with current effective values\nomp config list --json          # same, machine-readable\nomp config get theme.dark       # one value\nomp config get theme.dark --json\nomp config set compaction.enabled false\nomp config set defaultThinkingLevel medium\nomp config reset steeringMode   # restore a key to its schema default\nomp config path                 # print the active agent directory\n```\n\n### Subcommands\n\n| Command | Effect |\n|---|---|\n| `omp config list` | Print every setting grouped by tab, with its current value and type. `--json` emits an object keyed by setting path with `{ value, type, description }`. |\n| `omp config get <key>` | Print the effective value of one key. Unknown keys exit non-zero. `--json` emits `{ key, value, type, description }`. |\n| `omp config set <key> <value>` | Parse `<value>` against the key's schema type and write it to the global `config.yml`. |\n| `omp config reset <key>` | Write the key's schema **default** back to the global config (this persists the default, it does not delete the key). |\n| `omp config path` | Print the active agent directory (honors `PI_CODING_AGENT_DIR`). |\n\n`omp config` with no subcommand, or `--help`, prints the help and lists settings. The `--json` flag is accepted by `list`, `get`, `set`, and `reset`.\n\n### Value parsing\n\n`omp config set` parses the value string according to the target key's schema type. The string is trimmed first.\n\n| Type | Accepted input | Notes |\n|---|---|---|\n| boolean | `true`, `false`, `yes`, `no`, `on`, `off`, `1`, `0` | Case-insensitive. Anything else is rejected. |\n| number | Any finite JavaScript number | `Infinity`/`NaN` are rejected. |\n| enum | One of the key's allowed values | Must match exactly; the error lists the valid values. |\n| array | A JSON array | e.g. `'[\"anthropic\",\"openai\"]'`. Must parse and be an array. |\n| record | A JSON object | e.g. `'{\"bash\":\"prompt\"}'`. Must parse and be a non-array object. |\n| string | Stored as given (trimmed) | Multi-word values are joined with spaces. |\n\nKeys must match a real schema path exactly. There is no shorthand — set `theme.dark`, not `theme`.\n\n### Where writes go\n\n`omp config set`, `omp config reset`, `/settings`, and any runtime settings change all write to the global `config.yml` under the active agent directory. They never write to `<cwd>/.omp/config.yml`. To create a project-local override, edit that file directly (see [Project-local config](#project-local-config)). Saves are debounced and re-read the file under a lock, so external edits made while a session is open are preserved.\n\n## Precedence\n\nFrom lowest to highest priority, the effective value of a setting is built as:\n\n```text\nbuilt-in defaults  <-  global config  <-  project config  <-  CLI overlays  <-  runtime overrides\n```\n\nFrom highest to lowest:\n\n1. **Runtime overrides** — dedicated CLI flags and feature env vars applied in memory for the current process: `--model`, `--smol`, `--slow`, `--plan`, `--approval-mode`, `--auto-approve`/`--yolo`, `--hide-thinking`, `--no-pty`, `--api-key`, and protocol-mode defaults. Never persisted.\n2. **CLI config overlays** — each `--config <file>`; later overlay files override earlier ones.\n3. **Project settings** — `<cwd>/.omp/settings.json` then `<cwd>/.omp/config.yml` (and contributions from other discovery providers at project level).\n4. **Global settings** — `~/.omp/agent/config.yml`.\n5. **Built-in defaults** — from the settings schema.\n\nA key that is unset at every layer resolves to its schema default at read time.\n\n### Environment overrides\n\nEnvironment variables are **not** a single settings layer. Each is read by the feature that owns the value, usually as a per-machine override or fallback, and is never written back to `config.yml`. The ones that map directly onto a setting:\n\n| Env var | Overrides setting | Notes |\n|---|---|---|\n| `PI_SMOL_MODEL` | `modelRoles.smol` | Also exposed as `--smol`. |\n| `PI_SLOW_MODEL` | `modelRoles.slow` | Also exposed as `--slow`. |\n| `PI_PLAN_MODEL` | `modelRoles.plan` | Also exposed as `--plan`. |\n| `PI_NO_PTY=1` | (disables PTY bash) | Equivalent to `--no-pty` for the process. |\n| `PI_PY` | `eval.py` | `PI_PY=0` disables the Python eval backend. |\n| `PI_JS` | `eval.js` | `PI_JS=0` disables the JavaScript eval backend. |\n| `PI_TINY_DEVICE` | `providers.tinyModelDevice` | ONNX execution provider for local tiny models. |\n| `PI_TINY_DTYPE` | `providers.tinyModelDtype` | ONNX precision for local tiny models. |\n| `OMP_AUTH_BROKER_URL` | `auth.broker.url` | Env value takes precedence over config. |\n| `OMP_AUTH_BROKER_TOKEN` | `auth.broker.token` | Env value takes precedence over config. |\n| `PI_CODING_AGENT_DIR` | (relocates agent dir) | Moves `config.yml`, `agent.db`, and the whole agent base. |\n\nProvider API keys are resolved separately (stored auth, OAuth, `models.yml`, environment, and `.env` files); see [Providers](./providers.md) and the full [Environment variables](./environment-variables.md) reference.\n\n## Merge rules\n\nLayers are combined with a deep merge:\n\n- **Objects are deep-merged** — keys present only in a lower layer are kept; keys present in a higher layer override.\n- **Scalars and arrays are replaced wholesale** by the higher-precedence layer. A higher layer's array does not append to a lower layer's array.\n\nUse nested YAML mappings for dotted setting paths:\n\n```yaml\ntheme:\n  dark: titanium\n  light: light\n\ntools:\n  approvalMode: write\n  approval:\n    bash: prompt\n    read: allow\n```\n\n### Worked example: global vs. project\n\n```yaml\n# ~/.omp/agent/config.yml\ntools:\n  approvalMode: write\n  approval:\n    bash: prompt\n    read: allow\ndisabledProviders:\n  - anthropic\n  - openai\n  - gemini\n\n# <repo>/.omp/config.yml\ntools:\n  approval:\n    bash: allow\ndisabledProviders:\n  - groq\n```\n\nEffective settings inside `<repo>`:\n\n```yaml\ntools:\n  approvalMode: write   # kept from global (object deep-merge)\n  approval:\n    bash: allow         # overridden by project\n    read: allow         # kept from global\ndisabledProviders:\n  - groq                # project array REPLACES the global array\n```\n\nArray replacement is the most common surprise: the project's `disabledProviders` does not extend the global list — it becomes the entire list for that project. The same applies to `enabledModels`, `cycleOrder`, `extensions`, and every other array-typed setting.\n\n## Project-local config\n\nCreate `<repo>/.omp/config.yml` when a repository needs its own settings:\n\n```yaml\n# <repo>/.omp/config.yml\nmodelRoles:\n  default: anthropic/claude-sonnet-4-5\n  smol: openai/gpt-4.1-mini\n  slow: anthropic/claude-opus-4-5:high\n\ntools:\n  approvalMode: write\n  approval:\n    bash: prompt\n\ncompaction:\n  strategy: context-full\n  thresholdPercent: 80\n\ntheme:\n  dark: titanium\n```\n\nKeep secrets out of committed project config unless your repository policy allows it. Prefer environment variables, stored auth, an auth broker, or an untracked `--config` overlay for credentials.\n\n### One-shot overlays\n\nUse `--config` for a temporary layer that should not persist:\n\n```bash\nomp --config ./local/ci-settings.yml \"check this failure\"\nomp --config ./base.yml --config ./experiment.yml \"try this model\"\n```\n\nOverlay paths are resolved relative to the process working directory (and `~` is expanded). Each overlay must parse as a YAML mapping; a missing file, invalid YAML, or a top-level array/scalar is a hard error — it does **not** silently fall back to lower-precedence settings.\n\n## Path-scoped arrays\n\nTwo array settings — `enabledModels` and `disabledProviders` — accept path-scoped entries in addition to bare strings, so a single global config can behave differently per directory:\n\n```yaml\nenabledModels:\n  - claude-sonnet-4-5            # applies everywhere\n  - path: ~/work/high-context\n    models:\n      - anthropic/claude-opus-4-5\n\ndisabledProviders:\n  - ollama                       # applies everywhere\n  - paths:\n      - ~/projects/sensitive\n      - ~/clients/acme\n    providers:\n      - anthropic\n      - openai\n```\n\nBare string entries apply everywhere. A scoped entry applies when the current working directory **is** the configured path or is **under** it. `~` expands to your home directory and relative paths are resolved before matching.\n\nAccepted **path** keys (any of them, combined): `path`, `paths`, `pathPrefix`, `pathPrefixes`.\n\nAccepted **value** keys:\n\n- `models` (for `enabledModels`) or `providers` (for `disabledProviders`)\n- `values` or `items` (for either setting)\n\nOnly string values are kept; malformed scoped entries are ignored. Path scoping is resolved **after** the layer merge, so it reads the final effective array.\n\n## Provider and source disabling\n\n`disabledProviders` is a single shared id namespace that gates two different subsystems, before any credential check:\n\n| Entry kind | Example ids | Effect |\n|---|---|---|\n| Model providers | `anthropic`, `openai`, `gemini`, `groq`, `ollama`, `openrouter` | Removes those backends from model selection, even when credentials are available. See [Providers](./providers.md). |\n| Discovery sources | `native`, `claude`, `codex`, `gemini`, `github`, `opencode`, `cursor`, `agents-md` | Stops that source from contributing context files, MCP servers, commands, skills, hooks, tools, prompts, or settings. See [Context files](./context-files.md). |\n\nMost provider-control use cases list model provider ids. Disabling the `claude` discovery source is different from disabling the `anthropic` model provider — one stops Claude-format config discovery, the other stops the Anthropic model backend.\n\nBecause arrays replace rather than append, a project that sets `disabledProviders` must list the complete desired set:\n\n```yaml\n# ~/.omp/agent/config.yml\ndisabledProviders:\n  - anthropic\n  - openai\n\n# <repo>/.omp/config.yml — inside this repo ONLY groq is disabled\ndisabledProviders:\n  - groq\n```\n\nThe default is an empty array (nothing disabled). For the two subsystems' provider ids and ordering, see [Providers](./providers.md) and [Context files](./context-files.md).\n\n## Settings catalog\n\nEvery key below is defined in the settings schema; `omp config list` shows the full set with current values. Defaults and enum values are taken from the schema. Settings that accept an env or flag override are noted; those overrides are process-local and not persisted.\n\n### Models\n\n`modelRoles`, `modelTags`, and `cycleOrder` work together to define the models you can switch between. Role values may carry a thinking suffix (`:minimal`, `:low`, `:medium`, `:high`, `:xhigh`).\n\n```yaml\nmodelRoles:\n  default: anthropic/claude-sonnet-4-5\n  smol: openai/gpt-4.1-mini\n  slow: anthropic/claude-opus-4-5:high\n  vision: gemini/gemini-3-pro-preview\n  plan: anthropic/claude-opus-4-5\n  advisor: anthropic/claude-sonnet-4-5:medium\n\ncycleOrder:\n  - smol\n  - default\n  - slow\n\nmodelProviderOrder:\n  - anthropic\n  - openai\n\nenabledModels:\n  - claude-sonnet-4-5\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `modelRoles` | record | `{}` | Map of role name -> model id. Built-in roles: `default`, `smol`, `slow`, `vision`, `plan`, `designer`, `commit`, `title`, `task`, `advisor`. Per-role env/flags exist only for `--model`/`--smol`/`--slow`/`--plan`; configure the advisor with `modelRoles.advisor`. |\n| `modelTags` | record | `{}` | Custom role/tag metadata; can introduce additional roles. |\n| `modelProviderOrder` | array | `[]` | Preferred provider order when a model id is ambiguous. |\n| `cycleOrder` | array | `[\"smol\",\"default\",\"slow\"]` | Roles cycled by the model switcher. |\n| `enabledModels` | array | `[]` | Allow-list of models; supports [path-scoped entries](#path-scoped-arrays). Empty means all available models. |\n| `disabledProviders` | array | `[]` | Disabled model/discovery providers; supports path-scoped entries. See [above](#provider-and-source-disabling). |\n| `includeModelInPrompt` | boolean | `true` | Include the active model name in the system prompt. |\n\nSee [Models](./models.md) for the `models.yml` schema and custom-provider definitions.\n\n### Advisor\n\nThe advisor is a second model that reviews each completed turn and can inject advice into the primary session. Assign a model with `modelRoles.advisor`, then enable it with `advisor.enabled` or `/advisor on`. There is no `--advisor` flag.\n\nSee [Advisor and WATCHDOG.md](./advisor-watchdog.md) for runtime behavior, `WATCHDOG.md` discovery, and bounded catch-up semantics.\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `advisor.enabled` | boolean | `false` | Enable the advisor runtime when `modelRoles.advisor` resolves to an available model. |\n| `advisor.subagents` | boolean | `false` | Also enable advisor runtimes for spawned task/eval subagents. |\n| `advisor.syncBacklog` | enum | `off` | Bounded advisor catch-up delay: `off`, `1`, `3`, or `5`. The primary waits up to 30 seconds only while advisor backlog is at or above the threshold. |\n\n### Thinking\n\n```yaml\ndefaultThinkingLevel: high\nhideThinkingBlock: false\nthinkingBudgets:\n  minimal: 1024\n  low: 2048\n  medium: 8192\n  high: 16384\n  xhigh: 32768\n```\n\n| Key | Type | Default | Values |\n|---|---|---|---|\n| `defaultThinkingLevel` | enum | `high` | `minimal`, `low`, `medium`, `high`, `xhigh`, `auto`. Override per run with `--thinking`. |\n| `hideThinkingBlock` | boolean | `false` | Hide thinking blocks in output. `--hide-thinking` sets it for the run (display only). |\n| `thinkingBudgets.minimal` | number | `1024` | Token budget for the `minimal` level. |\n| `thinkingBudgets.low` | number | `2048` | Token budget for `low`. |\n| `thinkingBudgets.medium` | number | `8192` | Token budget for `medium`. |\n| `thinkingBudgets.high` | number | `16384` | Token budget for `high`. |\n| `thinkingBudgets.xhigh` | number | `32768` | Token budget for `xhigh`. |\n\n### Sampling\n\nA value of `-1` means \"use the provider/model default\" — `omp` does not send that parameter.\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `temperature` | number | `-1` | Sampling temperature. |\n| `topP` | number | `-1` | Nucleus sampling. |\n| `topK` | number | `-1` | Top-K sampling. |\n| `minP` | number | `-1` | Minimum-probability cutoff. |\n| `presencePenalty` | number | `-1` | Presence penalty. |\n| `repetitionPenalty` | number | `-1` | Repetition penalty. |\n| `serviceTier` | enum | `none` | `none`, `auto`, `default`, `flex`, `scale`, `priority`, `openai-only`, `claude-only`. |\n| `personality` | enum | `default` | `default`, `friendly`, `pragmatic`, `none`. |\n\n### Retry and fallback\n\n```yaml\nretry:\n  enabled: true\n  maxRetries: 10\n  baseDelayMs: 500\n  maxDelayMs: 300000\n  modelFallback: true\n  fallbackRevertPolicy: cooldown-expiry\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `retry.enabled` | boolean | `true` | Retry transient provider errors. |\n| `retry.maxRetries` | number | `10` | Max retries per request. |\n| `retry.baseDelayMs` | number | `500` | Initial backoff. |\n| `retry.maxDelayMs` | number | `300000` | Backoff ceiling (5 min). |\n| `retry.modelFallback` | boolean | `true` | Fall back to another model when one is unavailable. |\n| `retry.fallbackChains` | record | `{}` | Per-model fallback chains. |\n| `retry.fallbackRevertPolicy` | enum | `cooldown-expiry` | `cooldown-expiry`, `never`. |\n\n### Tools and approvals\n\n```yaml\ntools:\n  approvalMode: yolo          # default\n  approval:\n    bash: prompt\n    edit: allow\n  discoveryMode: auto\n  maxTimeout: 0\n  intentTracing: true\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `tools.approvalMode` | enum | `yolo` | `always-ask` (auto-approve read-only), `write` (auto-approve read + workspace-write), `yolo` (auto-approve all tiers). `--approval-mode` and `--auto-approve`/`--yolo` override per run. |\n| `tools.approval` | record | `{}` | Per-tool policy keyed by tool name; each value is `allow`, `deny`, or `prompt`. e.g. `omp config set tools.approval '{\"bash\":\"prompt\"}'`. |\n| `tools.discoveryMode` | enum | `auto` | `auto`, `off`, `mcp-only`, `all`. Controls dynamic tool discovery. |\n| `tools.essentialOverride` | array | `[]` | Tool names kept available even when tools are narrowed. |\n| `tools.maxTimeout` | number | `0` | Max tool runtime in seconds; `0` = no cap. |\n| `tools.intentTracing` | boolean | `true` | Record per-call intent strings. |\n| `tools.outputMaxColumns` | number | `768` | Per-line byte cap for streaming output; `0` disables. |\n| `tools.artifactSpillThreshold` | number | `50` | KB of tool output above which output spills to an artifact. |\n| `tools.artifactHeadBytes` | number | `20` | KB of head kept inline on spill; `0` = tail-only. |\n| `tools.artifactTailBytes` | number | `20` | KB of tail kept inline on spill. |\n| `tools.artifactTailLines` | number | `500` | Max tail lines kept inline on spill. |\n\nIndividual built-in tools are toggled by their own keys, e.g. `bash.enabled`, `eval.py`, `eval.js`, `find.enabled`, `search.enabled`, `fetch.enabled`, `browser.enabled`, `astEdit.enabled`, `astGrep.enabled`, `web_search.enabled`, `inspect_image.enabled`, `renderMermaid.enabled`.\n\n### Shell, eval, and LSP\n\n```yaml\nbash:\n  enabled: true\n  stripTrailingHeadTail: true\n  autoBackground:\n    enabled: false\n    thresholdMs: 60000\n\neval:\n  py: true\n  js: true\n\npython:\n  kernelMode: session       # session, per-call\n  interpreter: \"\"\n\nlsp:\n  enabled: true\n  lazy: true\n  diagnosticsOnWrite: true\n  diagnosticsOnEdit: false\n  formatOnWrite: false\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `bash.enabled` | boolean | `true` | Enable the bash tool. |\n| `bash.stripTrailingHeadTail` | boolean | `true` | Strip trailing head/tail noise from output. |\n| `bash.autoBackground.enabled` | boolean | `false` | Auto-background long-running commands. |\n| `bash.autoBackground.thresholdMs` | number | `60000` | Threshold before auto-backgrounding. |\n| `eval.py` | boolean | `true` | Python eval backend. `PI_PY=0` disables for the process. |\n| `eval.js` | boolean | `true` | JavaScript eval backend. `PI_JS=0` disables for the process. |\n| `python.kernelMode` | enum | `session` | `session` (persistent kernel) or `per-call`. |\n| `python.interpreter` | string | `\"\"` | Path to a Python interpreter; empty = auto-detect. |\n| `lsp.enabled` | boolean | `true` | Language-server integration. `--no-lsp` disables for the run. |\n| `lsp.lazy` | boolean | `true` | Start servers on demand. |\n| `lsp.diagnosticsOnWrite` | boolean | `true` | Run diagnostics after a write. |\n| `lsp.diagnosticsOnEdit` | boolean | `false` | Run diagnostics after an edit. |\n| `lsp.formatOnWrite` | boolean | `false` | Format files on write. |\n| `lsp.diagnosticsDeduplicate` | boolean | `true` | Collapse duplicate diagnostics. |\n| `shellPath` | string | _(unset)_ | Override the shell binary used by bash. |\n\n### Files: editing and reading\n\n```yaml\nedit:\n  mode: hashline            # apply_patch, hashline, patch, replace\n  fuzzyMatch: true\n  fuzzyThreshold: 0.95\n  blockAutoGenerated: true\n\nread:\n  defaultLimit: 300\n  toolResultPreview: false\n  summarize:\n    enabled: true\n    prose: false\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `edit.mode` | enum | `hashline` | `apply_patch`, `hashline`, `patch`, `replace`. |\n| `edit.fuzzyMatch` | boolean | `true` | Allow fuzzy anchor matching. |\n| `edit.fuzzyThreshold` | number | `0.95` | Similarity threshold for fuzzy matching. |\n| `edit.blockAutoGenerated` | boolean | `true` | Refuse to edit generated/lockfile-like files. |\n| `edit.streamingAbort` | boolean | `false` | Abort on streaming edit mismatch. |\n| `read.defaultLimit` | number | `300` | Default line count for `read` without a selector. |\n| `read.summarize.enabled` | boolean | `true` | Structural summaries for code reads. |\n| `read.summarize.prose` | boolean | `false` | Summarize prose files too. |\n| `read.toolResultPreview` | boolean | `false` | Inline preview of tool results. |\n| `readHashLines` | boolean | `true` | Show hashline tags in read output. |\n| `readLineNumbers` | boolean | `false` | Show plain line numbers. |\n\n### Context, compaction, and memory\n\n```yaml\ncontextPromotion:\n  enabled: true\n\ncompaction:\n  enabled: true\n  strategy: context-full     # context-full, handoff, shake, snapcompact, off\n  thresholdPercent: -1       # -1 = default reserve-based behavior\n  thresholdTokens: -1        # fixed token limit when > 0\n  remoteEnabled: true\n\nmemory:\n  backend: off               # off, local, hindsight, mnemopi\n```\n\n| Key | Type | Default | Notes |\n|---|---|---|---|\n| `contextPromotion.enabled` | boolean | `true` | Promote relevant earlier context. |\n| `compaction.enabled` | boolean | `true` | Automatic conversation compaction. |\n| `compaction.strategy` | enum | `context-full` | `context-full`, `handoff`, `shake`, `snapcompact`, `off`. |\n| `compaction.thresholdPercent` | number | `-1` | Percent-of-context trigger; `-1` = reserve-based default. |\n| `compaction.thresholdTokens` | number | `-1` | Fixed token trigger when `> 0`. |\n| `compaction.reserveTokens` | number | `16384` | Tokens reserved for the next turn. |\n| `compaction.keepRecentTokens` | number | `20000` | Recent tokens always preserved. |\n| `compaction.remoteEnabled` | boolean | `true` | Allow remote compaction service. |\n| `compaction.autoContinue` | boolean | `true` | Continue automatically after compaction. |\n| `memory.backend` | enum | `off` | `off`, `local`, `hindsight`, `mnemopi`. Each backend has its own `hindsight.*` / `mnemopi.*` / `memories.*` tuning keys. |\n| `autolearn.enabled` | boolean | `false` | Experimental: after the agent stops, nudge it to capture lessons to memory and create/enhance isolated managed skills under `~/.omp/agent/managed-skills`. Enables the `manage_skill` tool (and `learn` when a memory backend is active). |\n| `autolearn.autoContinue` | boolean | `false` | When `autolearn.enabled`, auto-run one capture turn at stop (uses extra tokens). Off = a passive reminder rides your next turn. |\n| `autolearn.minToolCalls` | number | `5` | Only nudge after a turn that used at least this many tools. |\n\n`compaction` has additional tuning keys (idle compaction, supersede/drop heuristics) visible in `omp config list`. See [Compaction](./compaction.md) for the full strategy reference.\n\n### Appearance and terminal\n\n```yaml\ntheme:\n  dark: titanium\n  light: light\nsymbolPreset: unicode        # unicode, nerd, ascii\ncolorBlindMode: false\n\nstatusLine:\n  preset: default            # default, minimal, compact, full, nerd, ascii, custom\n  separator: powerline-thin\n  transparent: false\n  showHookStatus: true\n\nterminal:\n  showImages: true\nimages:\n  autoResize: true\n  blockImages: false\ntui:\n  hyperlinks: auto           # off, auto, always\n```\n\n| Key | Type | Default | Values |\n|---|---|---|---|\n| `theme.dark` | string | `titanium` | Theme used on a dark terminal background. |\n| `theme.light` | string | `light` | Theme used on a light terminal background. |\n| `symbolPreset` | enum | `unicode` | `unicode`, `nerd`, `ascii`. |\n| `colorBlindMode` | boolean | `false` | Use blue instead of green for diff additions. |\n| `showHardwareCursor` | boolean | `true` | Show the terminal hardware cursor. |\n| `statusLine.preset` | enum | `default` | `default`, `minimal`, `compact`, `full`, `nerd`, `ascii`, `custom`. |\n| `statusLine.separator` | enum | `powerline-thin` | `powerline`, `powerline-thin`, `slash`, `pipe`, `block`, `none`, `ascii`. |\n| `statusLine.sessionAccent` | boolean | `true` | Tint the editor border with the session color. |\n| `statusLine.transparent` | boolean | `false` | Use the terminal background for the status line. |\n| `statusLine.showHookStatus` | boolean | `true` | Show hook status messages. |\n| `terminal.showImages` | boolean | `true` | Render images inline (when the terminal supports it). |\n| `images.autoResize` | boolean | `true` | Resize large images for model compatibility. |\n| `images.blockImages` | boolean | `false` | Never send images to providers. |\n| `tui.hyperlinks` | enum | `auto` | `off`, `auto`, `always`. |\n\nFor a custom status line, set `statusLine.preset: custom` and configure `statusLine.leftSegments`, `statusLine.rightSegments`, and `statusLine.segmentOptions`.\n\n### Interaction\n\n| Key | Type | Default | Values |\n|---|---|---|---|\n| `steeringMode` | enum | `one-at-a-time` | `all`, `one-at-a-time`. How queued steering messages are delivered. |\n| `followUpMode` | enum | `one-at-a-time` | `all`, `one-at-a-time`. |\n| `interruptMode` | enum | `immediate` | `immediate`, `wait`. |\n| `doubleEscapeAction` | enum | `tree` | `branch`, `tree`, `none`. |\n| `autoResume` | boolean | `false` | Auto-resume the most recent session in the cwd. |\n| `ask.timeout` | number | `0` | Seconds before an `ask` prompt times out; `0` = no timeout. (Legacy ms values are migrated to seconds.) |\n| `ask.notify` | enum | `on` | `on`, `off`. |\n\n### Providers and services\n\n```yaml\nproviders:\n  webSearch: auto\n  image: auto\n  fetch: auto\n  tinyModel: online\n  tinyModelDevice: default\n  tinyModelDtype: default\n  openaiWebsockets: auto\n  openrouterVariant: default\n  kimiApiFormat: anthropic\n\nprovider:\n  appendOnlyContext: auto    # auto, on, off\n\nexa:\n  enabled: true\n  enableSearch: true\n  enableResearcher: false\n  enableWebsets: false\n\nsearxng:\n  endpoint: https://search.example.com\n  token: SEARXNG_TOKEN\n```\n\n| Key | Type | Default | Values / notes |\n|---|---|---|---|\n| `providers.webSearch` | enum | `auto` | `auto` plus the configured search providers (`tavily`, `perplexity`, `brave`, `jina`, `kimi`, `anthropic`, `gemini`, `codex`, `zai`, `exa`, `parallel`, `kagi`, `synthetic`, `searxng`). |\n| `providers.image` | enum | `auto` | `auto`, `openai`, `antigravity`, `xai`, `gemini`, `openrouter`. |\n| `providers.fetch` | enum | `auto` | `auto`, `native`, `trafilatura`, `lynx`, `parallel`, `jina`. |\n| `providers.tinyModel` | enum | `online` | `online` or a local model (`lfm2-350m`, `qwen3-0.6b`, `gemma-270m`, `qwen2.5-0.5b`, `lfm2-700m`). |\n| `providers.tinyModelDevice` | enum | `default` | ONNX execution provider for local tiny models. Overridden by `PI_TINY_DEVICE`. |\n| `providers.tinyModelDtype` | enum | `default` | ONNX precision for local tiny models. Overridden by `PI_TINY_DTYPE`. |\n| `providers.openaiWebsockets` | enum | `auto` | `auto`, `off`, `on`. |\n| `providers.openrouterVariant` | enum | `default` | `default`, `nitro`, `floor`, `online`, `exacto`. |\n| `providers.kimiApiFormat` | enum | `anthropic` | `openai`, `anthropic`. |\n| `provider.appendOnlyContext` | enum | `auto` | `auto`, `on`, `off`. |\n| `exa.enabled` | boolean | `true` | Enable Exa integration. |\n| `exa.enableSearch` | boolean | `true` | Exa search. |\n| `exa.enableResearcher` | boolean | `false` | Exa researcher. |\n| `exa.enableWebsets` | boolean | `false` | Exa websets. |\n| `searxng.endpoint` | string | _(unset)_ | SearXNG instance URL. |\n| `searxng.token` | string | _(unset)_ | SearXNG token; also `searxng.basicUsername`/`searxng.basicPassword`/`searxng.categories`/`searxng.language`. |\n| `auth.broker.url` | string | _(unset)_ | Auth-broker URL. Overridden by `OMP_AUTH_BROKER_URL`. |\n| `auth.broker.token` | string | _(unset)_ | Auth-broker token. Overridden by `OMP_AUTH_BROKER_TOKEN`. |\n\nProvider credentials and custom model definitions are configured separately — see [Providers](./providers.md) and [Models](./models.md).\n\n### Other groups\n\n`omp config list` exposes many more grouped settings, including: `task.*` (subagent concurrency, isolation, model overrides), `skills.*` and `commands.*` (discovery toggles), `mcp.*`, `github.*`, `async.*`, `goal.*`, `loop.*`, `todo.*`, `magicKeywords.*`, `ttsr.*` (sticky rules), `display.*`, `startup.*`, `share.*`, `collab.*`, `stt.*`/`tts.*`, `memories.*`/`hindsight.*`/`mnemopi.*` (memory backends), and `bashInterceptor.*`. Each follows the same type/default rules shown above.\n\n## Legacy migration\n\n`omp` migrates older config shapes automatically. None of these require action; they are listed so you know what changes you may see in `config.yml`.\n\n### Startup migration to `config.yml`\n\nWhen `~/.omp/agent/config.yml` does not exist, startup builds it once from legacy sources, then writes the result:\n\n1. `~/.omp/agent/settings.json` (renamed to `settings.json.bak` after a successful migration).\n2. Settings persisted in `agent.db`.\n\nAfter `config.yml` exists, these legacy sources are no longer consulted. The generic config loader also performs `.json` -> `.yml` migration for other config files when only the `.json` form is present.\n\n### Field-level migrations\n\nApplied whenever raw settings are loaded (global, project, overlays, and runtime overrides):\n\n| Old | New |\n|---|---|\n| `queueMode` | `steeringMode` |\n| `ask.timeout` in milliseconds (value `> 1000`) | seconds (divided by 1000) |\n| flat `theme: \"<name>\"` string | `theme.dark` / `theme.light` (slot chosen by luminance; built-in `light`/`dark` are dropped to use defaults) |\n| `task.isolation.enabled: true/false` | `task.isolation.mode: auto/none` |\n| `task.simple` | removed |\n| legacy `task.isolation.mode` (`worktree`, `fuse-overlay`, `fuse-projfs`) | `rcopy`, `overlayfs`, `projfs` |\n| `lastChangelogVersion` | moved to a marker file and stripped from `config.yml` |\n\n## Troubleshooting\n\n### A project setting is not taking effect\n\n- Start `omp` from the directory that contains `.omp/config.yml`. Settings discovery only checks the current working directory's `.omp/`, not ancestor directories.\n- Ensure `.omp/` is non-empty; empty config directories are ignored.\n- Confirm the file is valid YAML and its top level is a mapping.\n- Run `omp config get <key>` from that directory to see the effective value.\n- Remember that `--config` overlays and runtime flags override project config.\n\n### A global array disappeared in a project\n\nArrays replace; they do not append. If a project sets `disabledProviders`, `enabledModels`, `cycleOrder`, `extensions`, or any other array, include the **complete** desired value in the project layer — the global array is fully replaced.\n\n### A provider is still available after editing config\n\n- Check whether you disabled the model provider id (e.g. `anthropic`) or a discovery source id (e.g. `claude`) — they are different namespaces with different effects.\n- Check for a project (or overlay) `disabledProviders` array replacing your global one.\n- Credentials can still come from environment variables, `.env`, OAuth, stored auth, or `models.yml`; disabling a provider blocks selection regardless, but verify you edited the right layer. See [Providers](./providers.md).\n- Restart the session if the model list was already initialized.\n\n### `omp config set` changed the wrong file\n\n`omp config set` and `omp config reset` always write the global `config.yml` under the active agent directory. Run `omp config path` to print it. For project-local settings, edit `<repo>/.omp/config.yml` directly.\n\n### `omp config reset` did not remove my key\n\n`reset` writes the schema **default** value into the global config — it persists the default rather than deleting the key. To stop overriding a project value from global config, delete the key from `~/.omp/agent/config.yml` by hand.\n\n### A `--config` overlay fails at startup\n\n`--config` files are process-local YAML mappings. A missing file, invalid YAML, or a top-level array/scalar is a hard error — it does not silently fall back to lower-precedence settings. Fix the path or contents.\n\n### An environment variable beats my config\n\nSome settings (model roles, eval backends, tiny-model device/precision, auth broker, PTY) are overridable by env vars or CLI flags for per-machine convenience, and those take precedence over `config.yml`. Unset the variable or drop the flag to let the persisted value win. See [Environment overrides](#environment-overrides) and [Environment variables](./environment-variables.md).\n\n### `omp config set <key>` says \"Unknown setting\"\n\nKeys must match a schema path exactly, with no shorthand. Use `theme.dark`, not `theme`. Run `omp config list` to see every valid key.\n",
 	"skills.md": "# Skills\n\nSkills are file-backed capability packs discovered at startup and exposed to the model as:\n\n- lightweight metadata in the system prompt (name + description)\n- on-demand content via the `read` tool against `skill://...`\n- optional interactive `/skill:<name>` commands\n\nThis document covers current runtime behavior in `src/extensibility/skills.ts`, `src/discovery/builtin.ts`, `src/internal-urls/skill-protocol.ts`, and `src/discovery/agents-md.ts`.\n\n## What a skill is in this codebase\n\nA discovered skill is represented as:\n\n- `name`\n- `description`\n- `filePath` (the `SKILL.md` path)\n- `baseDir` (skill directory)\n- source metadata (`provider`, `level`, path)\n\nThe runtime only requires `name` and `path` for validity. In practice, matching quality depends on `description` being meaningful.\n\n## Required layout and SKILL.md expectations\n\n### Directory layout\n\nFor provider-based discovery (native/Claude/Codex/Agents/plugin providers), skills are discovered as **one level under `skills/`**:\n\n- `<skills-root>/<skill-name>/SKILL.md`\n\nNested patterns like `<skills-root>/group/<skill>/SKILL.md` are not discovered by provider loaders.\n\nFor `skills.customDirectories`, scanning uses the same non-recursive layout (`*/SKILL.md`).\n\n```text\nProvider-discovered layout (non-recursive under skills/):\n\n<root>/skills/\n  ├─ postgres/\n  │   └─ SKILL.md      ✅ discovered\n  ├─ pdf/\n  │   └─ SKILL.md      ✅ discovered\n  └─ team/\n      └─ internal/\n          └─ SKILL.md  ❌ not discovered by provider loaders\n\nCustom-directory scanning is also non-recursive, so nested paths are ignored unless you point `customDirectories` at that nested parent.\n```\n\n### `SKILL.md` frontmatter\n\nSupported frontmatter fields on the skill type:\n\n- `name?: string`\n- `description?: string`\n- `globs?: string[]`\n- `alwaysApply?: boolean`\n- `hide?: boolean`\n- `disableModelInvocation?: boolean` (Agent Skills equivalent of `hide`; normalized from kebab-case `disable-model-invocation`)\n- additional keys are preserved as unknown metadata\n\nCurrent runtime behavior:\n\n- `name` defaults to the skill directory name\n- `description` is required for:\n  - native `.omp` provider skill discovery (`requireDescription: true`)\n  - `omp-plugins` extension-package skills and the `github` provider (`.github/skills/`), which also pass `requireDescription: true`\n  - `skills.customDirectories` scans via `scanSkillsFromDir` in `src/discovery/helpers.ts` (non-recursive)\n- the claude/codex/agents/opencode/claude-plugins providers can load skills without description\n\n## Discovery pipeline\n\n`loadSkills()` in `src/extensibility/skills.ts` does two passes:\n\n1. **Capability providers** via `loadCapability(\"skills\")`\n2. **Custom directories** via `scanSkillsFromDir(..., { requireDescription: true })` (one-level directory enumeration)\n\nIf `skills.enabled` is `false`, discovery returns no skills.\n\n### Built-in skill providers and precedence\n\nProvider ordering is priority-first (higher wins), then registration order for ties.\n\nCurrent registered skill providers:\n\n1. `native` (priority 100) — `.omp` user/project skills via `src/discovery/builtin.ts`\n2. `omp-plugins` (priority 90) — `skills/` bundled next to extension packages loaded through `extensions:`, `--extension`/`-e`, or installed plugins under `~/.omp/plugins/node_modules`\n3. `claude` (priority 80)\n4. priority 70 group (in registration order):\n   - `claude-plugins`\n   - `agents`\n   - `codex`\n5. `opencode` (priority 55)\n6. `github` (priority 30) — `.github/skills/<name>/SKILL.md` (GitHub Agent Skills layout, project-only)\n\nDedup key is skill name. First item with a given name wins.\n\n### Source toggles and filtering\n\n`loadSkills()` applies these controls:\n\n- source toggles: `enableCodexUser`, `enableClaudeUser`, `enableClaudeProject`, `enablePiUser`, `enablePiProject`, `enableAgentsUser`, `enableAgentsProject`\n- `disabledExtensions` entries with `skill:<name>`\n- `ignoredSkills` (exclude; glob patterns)\n- `includeSkills` (include allowlist; glob patterns; empty means include all)\n\nFilter order is:\n\n1. not disabled by `disabledExtensions`\n2. source enabled\n3. not ignored\n4. included (if include list present)\n\nThe `agents` provider (`.agent[s]/skills`) is the canonical OMP-native location and has its own `enableAgentsUser`/`enableAgentsProject` toggles — disabling Claude/Codex/Pi does **not** turn it off. For providers without a dedicated toggle (`claude-plugins`, `opencode`, `gemini`, `github`, …), enablement falls back to: enabled if **any** named source toggle is enabled.\n\n### Collision and duplicate handling\n\n- Capability dedup already keeps first skill per name (highest-precedence provider)\n- `extensibility/skills.ts` additionally:\n  - de-duplicates identical files by `realpath` (symlink-safe)\n  - emits collision warnings when a later skill name conflicts\n  - keeps the convenience `loadSkillsFromDir({ dir, source })` API as a thin adapter over `scanSkillsFromDir`\n- Custom-directory skills are merged after provider skills and follow the same collision behavior\n\n## Runtime usage behavior\n\n### System prompt exposure\n\nSystem prompt construction (`src/system-prompt.ts`) uses discovered skills as follows:\n\n- if `read` tool is available:\n  - include discovered skills list in prompt, excluding skills with `hide: true`\n- otherwise:\n  - omit discovered list\n\n`hide: true` does not disable the skill. Hidden skills are still loaded and remain reachable through `skill://<name>` and `/skill:<name>` when skill commands are enabled.\n\nTask tool subagents receive the session's discovered/provided skills list via normal session creation; there is no per-task skill pinning override.\n\n### Interactive `/skill:<name>` commands\n\nIf `skills.enableSkillCommands` is true, interactive mode registers one slash command per discovered skill.\n\n`/skill:<name> [args]` behavior:\n\n- reads the skill file directly from `filePath`\n- strips frontmatter\n- injects skill body as a custom message\n- delivery mode follows the **submission keybinding**:\n  - **Enter** → invokes the skill on the `steer` queue while streaming (matches free-text Enter, which also steers), or as a normal idle prompt when the agent is not streaming\n  - **Ctrl+Enter** (`app.message.followUp`) → invokes the skill on the `followUp` queue while streaming, or as a normal idle prompt when the agent is not streaming\n- appends metadata (`Skill: <path>`, optional `User: <args>`)\n\nThere is no flag, mode-selector, or frontmatter knob to override this — the keybinding _is_ the choice, identical to how free text is routed during streaming (`input-controller.ts:436-442` for Enter, `input-controller.ts:770-775` for Ctrl+Enter; both dispatch through `#invokeSkillCommand`).\n\n## `skill://` URL behavior\n\n`src/internal-urls/skill-protocol.ts` supports:\n\n- `skill://<name>` → resolves to that skill's `SKILL.md`\n- `skill://<name>/<relative-path>` → resolves inside that skill directory\n\n```text\nskill:// URL resolution\n\nskill://pdf\n  -> <pdf-base>/SKILL.md\n\nskill://pdf/references/tables.md\n  -> <pdf-base>/references/tables.md\n\nGuards:\n- reject absolute paths\n- reject `..` traversal\n- reject any resolved path escaping <pdf-base>\n```\n\nResolution details:\n\n- skill name must match exactly\n- relative paths are URL-decoded\n- absolute paths are rejected\n- path traversal (`..`) is rejected\n- resolved path must remain within `baseDir`\n- missing files return an explicit `File not found` error\n\nContent type:\n\n- `.md` => `text/markdown`\n- everything else => `text/plain`\n\nNo fallback search is performed for missing assets.\n\n## Skills vs AGENTS.md, commands, tools, hooks\n\n### Skills vs AGENTS.md\n\n- **Skills**: named, optional capability packs selected by task context or explicitly requested\n- **AGENTS.md/context files**: persistent instruction files loaded as context-file capability and merged by level/depth rules\n\n`src/discovery/agents-md.ts` specifically walks ancestor directories from `cwd` to discover standalone `AGENTS.md` files (stopping at the repo root, or home when no repo root is known), skipping files whose containing directory name starts with a dot.\n\n### Skills vs slash commands\n\n- **Skills**: model-readable knowledge/workflow content\n- **Slash commands**: user-invoked command entry points\n- `/skill:<name>` is a convenience wrapper that injects skill text; it does not change skill discovery semantics\n\n### Skills vs custom tools\n\n- **Skills**: documentation/workflow content loaded through prompt context and `read`\n- **Custom tools**: executable tool APIs callable by the model with schemas and runtime side effects\n\n### Skills vs hooks\n\n- **Skills**: passive content\n- **Hooks**: event-driven runtime interceptors that can block/modify behavior during execution\n\n## Practical authoring guidance tied to discovery logic\n\n- Put each skill in its own directory: `<skills-root>/<skill-name>/SKILL.md`\n- Always include explicit `name` and `description` frontmatter\n- Keep referenced assets under the same skill directory and access with `skill://<name>/...`\n- For nested taxonomy (`team/domain/skill`), point `skills.customDirectories` to the nested parent directory; scanning itself remains non-recursive\n- Avoid duplicate skill names across sources; first match wins by provider precedence\n",
 	"skills/authoring-extensions.md": "---\nname: authoring-extensions\ndescription: Use when creating a new omp extension. Covers ExtensionAPI, factory signature, tool/command/event registration, and local-dev testing.\n---\n\n# Authoring Extensions\n\nExtensions are the primary way to add capabilities to `oh-my-pi`. A single extension module can register tools the LLM can call, slash commands users can invoke, and event handlers that run throughout the session lifecycle — all from one TypeScript file.\n\n## Minimum viable extension\n\n```ts\nimport type { ExtensionAPI } from \"@oh-my-pi/pi-coding-agent\";\n\nexport default function (pi: ExtensionAPI) {\n  pi.on(\"session_start\", async (_event, ctx) => {\n    ctx.ui.notify(\"My extension loaded!\", \"info\");\n  });\n}\n```\n\nThat is a working extension. Drop it into `~/.omp/agent/extensions/hello.ts` and restart omp to see the notification.\n\n## Full example\n\nThe following extension registers a slash command, a tool, and a session-start hook:\n\n```ts\nimport type { ExtensionAPI } from \"@oh-my-pi/pi-coding-agent\";\n\nexport default function myExtension(pi: ExtensionAPI) {\n  const z = pi.zod;\n\n  // Runs once when the session loads\n  pi.on(\"session_start\", async (_event, ctx) => {\n    ctx.ui.notify(`Session ready in ${ctx.cwd}`, \"info\");\n  });\n\n  // Slash command: /greet\n  pi.registerCommand(\"greet\", {\n    description: \"Send a greeting into the conversation\",\n    handler: async (args, ctx) => {\n      const name = args.trim() || \"world\";\n      pi.sendMessage(\n        {\n          customType: \"greeting\",\n          content: `Hello, ${name}!`,\n          display: true,\n          attribution: \"user\",\n        },\n        { triggerTurn: false }\n      );\n      ctx.ui.notify(`Greeted ${name}`, \"info\");\n    },\n  });\n\n  // LLM-callable tool\n  pi.registerTool({\n    name: \"word_count\",\n    label: \"Word Count\",\n    description: \"Count the words in a string\",\n    parameters: z.object({\n      text: z.string().describe(\"Text to count\"),\n    }),\n    async execute(_id, params, _signal, _onUpdate, _ctx) {\n      const count = params.text.split(/\\s+/).filter(Boolean).length;\n      return {\n        content: [{ type: \"text\", text: String(count) }],\n        details: { count },\n      };\n    },\n  });\n}\n```\n\n## Discovery paths\n\nomp loads extension modules from these sources:\n\n1. Native `.omp` locations discovered through the capability system:\n   - `<cwd>/.omp/extensions/`\n   - `~/.omp/agent/extensions/`\n   - legacy extension paths listed in `.omp/settings.json#extensions` or `~/.omp/agent/settings.json#extensions`\n2. Installed plugins under `~/.omp/plugins/node_modules` (`omp plugin install` npm/git specs, or `omp plugin link`) via their `omp.extensions`/`pi.extensions` manifests. Marketplace cache installs do not feed extension modules — they surface skills/commands/hooks/tools/MCP only.\n3. Explicit configured paths passed by the CLI (`omp --extension ./my-ext.ts`, also `-e`; `--hook` is treated as an alias) and by the `extensions:` setting in config.\n\nThe runtime de-duplicates by resolved absolute path — first seen wins.\n\nWhen a path points to a directory, omp resolves the entry point in this order:\n\n1. `package.json` with `omp.extensions` (or legacy `pi.extensions`) field\n2. `index.ts`\n3. `index.js`\n\nWhen scanning an `extensions/` directory, omp also loads direct `*.ts`/`*.js` files and one-level subdirectories that have `index.ts`, `index.js`, or a manifest.\n\nExtension packages can also bundle sibling capability directories. When a package is loaded through `extensions:` or `--extension`/`-e`, the `omp-plugins` provider discovers its `skills/`, `hooks/pre|post/`, `tools/`, `commands/`, `rules/`, `prompts/`, and `.mcp.json`.\n\n## package.json manifest\n\nTo package an extension as an installable plugin, add an `omp` field to `package.json`:\n\n```json\n{\n  \"name\": \"my-omp-extension\",\n  \"omp\": {\n    \"extensions\": [\"./src/main.ts\"]\n  }\n}\n```\n\nThe legacy `pi` key is also accepted for backwards compatibility:\n\n```json\n{\n  \"pi\": {\n    \"extensions\": [\"./index.ts\"]\n  }\n}\n```\n\nMultiple entry points are supported:\n\n```json\n{\n  \"omp\": {\n    \"extensions\": [\"./src/safety.ts\", \"./src/tools.ts\"]\n  }\n}\n```\n\n## Registering commands\n\n```ts\npi.registerCommand(\"my-cmd\", {\n  description: \"What the command does\",\n  handler: async (args, ctx) => {\n    // args: everything the user typed after /my-cmd\n    // ctx: ExtensionCommandContext — includes ctx.ui, ctx.cwd, session controls\n    ctx.ui.notify(\"Running!\", \"info\");\n    await ctx.waitForIdle();\n    await ctx.newSession();\n  },\n});\n```\n\n`ExtensionCommandContext` session-control methods (safe to call from commands only):\n\n| Method | Effect |\n|---|---|\n| `waitForIdle()` | Wait for the agent to finish streaming |\n| `newSession(opts?)` | Open a fresh session |\n| `switchSession(path)` | Switch to an existing session file |\n| `branch(entryId)` | Fork from a specific history entry |\n| `navigateTree(id, opts?)` | Jump to a different point in the session tree |\n| `reload()` | Reload the session runtime |\n| `compact(opts?)` | Compact the current context |\n\n## Registering tools\n\nTools are called by the LLM. Parameters use [Zod](https://zod.dev) schemas, available at `pi.zod`:\n\n```ts\nconst z = pi.zod;\n\npi.registerTool({\n  name: \"search_notes\",           // snake_case, unique\n  label: \"Search Notes\",          // human-readable label for TUI\n  description: \"Full-text search through project notes\",\n  parameters: z.object({\n    query: z.string().describe(\"Search query\"),\n    limit: z.number().default(10).describe(\"Max results\").optional(),\n  }),\n  async execute(toolCallId, params, signal, onUpdate, ctx) {\n    if (signal?.aborted) {\n      return { content: [{ type: \"text\", text: \"Cancelled\" }] };\n    }\n    onUpdate?.({ content: [{ type: \"text\", text: \"Searching...\" }] });\n    // ... do work ...\n    return {\n      content: [{ type: \"text\", text: `Found N results for \"${params.query}\"` }],\n      details: { query: params.query, count: 0 },\n    };\n  },\n});\n```\n\n## Subscribing to events\n\n```ts\npi.on(\"tool_call\", async (event, ctx) => {\n  // event.toolName, event.input, event.toolCallId\n  if (event.toolName !== \"bash\") return;\n\n  const command = String((event.input as { command?: unknown }).command ?? \"\");\n  if (command.includes(\"rm -rf /\")) {\n    return { block: true, reason: \"Blocked by safety policy\" };\n  }\n});\n\npi.on(\"turn_end\", async (_event, ctx) => {\n  ctx.ui.setStatus(\"tokens\", `~${ctx.getContextUsage()?.tokens ?? \"?\"} tokens`);\n});\n```\n\nFull event catalog: see [hooks authoring guide](./authoring-hooks.md).\n\n## Extension vs hook — when to use which\n\n| Need | Use |\n|---|---|\n| Tools + commands + events in one module | **Extension** (`ExtensionAPI`) |\n| Pure event interception (policy, redaction) | **Extension** or **Hook** (both work; extension is preferred) |\n| Legacy hook module already exists | **Hook** (`HookAPI` from `@oh-my-pi/pi-coding-agent/extensibility/hooks`) |\n| Registering provider / custom message renderer | **Extension only** |\n| Shipping as a marketplace plugin | **Extension** (use `package.json` manifest) |\n\nExtensions are a strict superset of hooks. New authoring should use `ExtensionAPI`.\n\n## Debugging\n\nStart omp with `--log-level debug` to see extension load diagnostics:\n\n```\nomp --log-level debug\n```\n\nFailed extension loads are logged with their path and error. Loaded extensions may also emit their own debug logs via `pi.logger`.\n\nTo temporarily disable a specific extension module by name without removing the file:\n\n```yaml\n# ~/.omp/agent/config.yml\ndisabledExtensions:\n  - extension-module:my-ext\n```\n\nThe derived name is the filename stem (or directory name for `index.ts`-style entries): `/path/to/my-ext.ts` → `my-ext`.\n\n## Important constraints\n\n- **Do not call runtime actions during load.** Methods like `pi.sendMessage()` throw `ExtensionRuntimeNotInitializedError` if called synchronously during module evaluation (before a session is active). Register handlers/tools/commands during load; perform runtime actions only from event handlers, tools, or commands.\n- **`tool_call` errors are fail-closed.** If a `tool_call` handler throws, the tool is blocked.\n- **Command names must not clash with built-ins.** Conflicts are skipped with a diagnostic log.\n- **Reserved shortcuts are ignored** (`ctrl+c`, `ctrl+d`, `ctrl+z`, `ctrl+k`, `ctrl+p`, `ctrl+l`, `ctrl+o`, `ctrl+t`, `ctrl+g`, `ctrl+q`, `alt+m`, `shift+tab`, `shift+ctrl+p`, `alt+enter`, `escape`, `enter`).\n\n## Further reading\n\n- `docs/extensions.md` — runtime internals and full API surface reference\n- `docs/extension-loading.md` — detailed path resolution rules\n- `docs/hooks.md` — hook subsystem internals\n- `docs/skills/examples/hello-extension/` — complete working example\n",
 	"skills/authoring-hooks.md": "---\nname: authoring-hooks\ndescription: Use when creating a new omp hook. Covers HookAPI, event catalog, blocking/overriding tool calls, and context modification.\n---\n\n# Authoring Hooks\n\nHooks are event-driven interceptors that run alongside the agent loop. They are best used for cross-cutting concerns: safety policy, secret redaction, context pruning, audit logging. A hook module registers handlers via `pi.on(event, handler)` and can block tool execution, override tool output, or rewrite the message context before each LLM call.\n\n> **Relationship to extensions:** The hook subsystem (`HookAPI`) is the legacy API. The extension runner now handles everything hooks can do plus more. `ExtensionAPI` supports the hook event model plus extension-only events. Use `ExtensionAPI` for new work; use `HookAPI` only if you are maintaining an existing hook module.\n\n## Factory signature\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function myHook(omp: HookAPI): void {\n  omp.on(\"tool_call\", async (event, ctx) => {\n    // intercept every tool call\n  });\n}\n```\n\nThe default export must be a plain function (not async, not a class). It receives a `HookAPI` instance and must register all handlers synchronously during execution.\n\nAlternatively, using `ExtensionAPI` (preferred):\n\n```ts\nimport type { ExtensionAPI } from \"@oh-my-pi/pi-coding-agent\";\n\nexport default function myExtension(pi: ExtensionAPI): void {\n  pi.on(\"tool_call\", async (event, ctx) => { /* ... */ });\n}\n```\n\n## Event catalog\n\n### Tool lifecycle\n\n| Event | Fires | Can return |\n|---|---|---|\n| `tool_call` | Before every tool execution | `{ block?: boolean; reason?: string }` |\n| `tool_result` | After every tool execution | `{ content?; details?; isError?: boolean }` |\n\n### Session lifecycle\n\n| Event | Fires | Can return |\n|---|---|---|\n| `session_start` | On initial session load | — |\n| `session_before_switch` | Before session switch | `{ cancel?: boolean }` |\n| `session_switch` | After session switch | — |\n| `session_before_branch` | Before session branch | `{ cancel?: boolean; skipConversationRestore?: boolean }` |\n| `session_branch` | After session branch | — |\n| `session_before_compact` | Before compaction | `{ cancel?: boolean; compaction?: CompactionResult }` |\n| `session.compacting` | During compaction (inject context) | `{ context?: string[]; prompt?: string; preserveData?: Record<string, unknown> }` |\n| `session_compact` | After compaction | — |\n| `session_before_tree` | Before tree navigation | `{ cancel?: boolean; summary?: { summary: string; details?: unknown } }` |\n| `session_tree` | After tree navigation | — |\n| `session_shutdown` | On session shutdown | — |\n\n### Agent/turn lifecycle\n\n| Event | Fires | Can return |\n|---|---|---|\n| `before_agent_start` | Before agent starts a turn | `{ message?: { customType; content; display; details; attribution? } }` |\n| `agent_start` | Agent streaming starts | — |\n| `agent_end` | Agent streaming ends | — |\n| `turn_start` | Start of a user→agent turn | — |\n| `turn_end` | End of a user→agent turn | — |\n| `context` | Before each LLM API call | `{ messages?: Message[] }` |\n| `auto_compaction_start` | Auto-compaction begins | — |\n| `auto_compaction_end` | Auto-compaction ends | — |\n| `auto_retry_start` | Auto-retry begins | — |\n| `auto_retry_end` | Auto-retry ends | — |\n| `ttsr_triggered` | TTSR (too-short response) triggered | — |\n| `todo_reminder` | Todo reminder fires | — |\n\nExtension-only events such as `tool_execution_start`, `tool_execution_update`, `tool_execution_end`, `input`, `user_bash`, and `user_python` require `ExtensionAPI`.\n\n## Pre-tool blocking contract\n\nReturn `{ block: true, reason: \"...\" }` from a `tool_call` handler to prevent execution:\n\n```ts\nomp.on(\"tool_call\", async (event, ctx) => {\n  if (event.toolName === \"bash\") {\n    const cmd = String(event.input.command ?? \"\");\n    if (/\\brm\\s+-rf\\s+\\//.test(cmd)) {\n      return { block: true, reason: \"Refusing to delete root filesystem\" };\n    }\n  }\n});\n```\n\nContract:\n\n- If **any** handler returns `{ block: true }`, execution stops immediately.\n- `reason` is returned to the LLM as the tool error text.\n- If a handler **throws**, the tool is also blocked (fail-closed).\n- Last non-blocking return wins for non-blocking results; first `block: true` short-circuits.\n\n## Post-tool override contract\n\nReturn `{ content, details, isError }` from a `tool_result` handler to patch what the LLM sees:\n\n```ts\nomp.on(\"tool_result\", async (event, ctx) => {\n  if (event.toolName === \"read\" && !event.isError) {\n    const redacted = event.content.map(chunk => {\n      if (chunk.type !== \"text\") return chunk;\n      return {\n        ...chunk,\n        text: chunk.text.replace(/(?:sk|pk)-[a-zA-Z0-9]{20,}/g, \"[REDACTED_API_KEY]\"),\n      };\n    });\n    return { content: redacted };\n  }\n});\n```\n\nContract:\n\n- Handlers run in registration order. For `HookAPI`, each handler receives the original tool result event, and the last returned override wins.\n- `content` replaces the full content array for the LLM.\n- `details` replaces the structured details object.\n- `isError` exists on the shared result type, but `HookToolWrapper` does not propagate it into a successful tool result; on a tool failure, the original error is rethrown after handlers complete.\n- On a tool failure, `tool_result` is still emitted with `isError: true`.\n\n## Context modification contract\n\nReturn `{ messages: [...] }` from a `context` handler to rewrite the message list before each LLM API call:\n\n```ts\nomp.on(\"context\", async (event, ctx) => {\n  // Remove debug-only custom messages from LLM context\n  const filtered = event.messages.filter(\n    msg => !(msg.role === \"custom\" && msg.customType === \"debug-only\")\n  );\n  return { messages: filtered };\n});\n```\n\nContract:\n\n- `event.messages` is the current accumulated list.\n- Handlers run in order; each receives the output of the previous handler.\n- Return `undefined` (or nothing) to pass messages through unmodified.\n\n## Three complete examples\n\n### 1. rm-rf blocker\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function rmRfBlocker(omp: HookAPI): void {\n  omp.on(\"tool_call\", async (event, ctx) => {\n    if (event.toolName !== \"bash\") return;\n\n    const cmd = String(event.input.command ?? \"\");\n    if (!/\\brm\\s+-rf\\s+\\//.test(cmd)) return;\n\n    // Allow if user explicitly confirms (interactive mode only)\n    if (ctx.hasUI) {\n      const allow = await ctx.ui.confirm(\n        \"Dangerous command\",\n        `This command deletes from root:\\n${cmd}\\n\\nProceed?`\n      );\n      if (allow) return;\n    }\n\n    return { block: true, reason: \"rm -rf / blocked by safety policy\" };\n  });\n}\n```\n\n### 2. API-key redactor\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\n// Common API-key shapes. Not exhaustive — providers using bespoke formats\n// (Anthropic `sk-ant-…`, JWT-style bearers, gateway-specific prefixes, etc.)\n// need their own entries.\nconst SECRET_PATTERNS = [\n  /\\b(sk|pk)-[a-zA-Z0-9]{20,}\\b/g,\n  /\\bAKIA[A-Z0-9]{16}\\b/g,\n  /\\bghp_[a-zA-Z0-9]{36}\\b/g,\n  // Zhipu / GLM Coding Plan: `<id>.<secret>` (no `sk-` prefix).\n  /\\b[a-zA-Z0-9]{16,}\\.[a-zA-Z0-9]{16,}\\b/g,\n  /\\b[a-zA-Z0-9_-]{20,}\\s*=\\s*[\"']?[a-zA-Z0-9._/+=-]{20,}[\"']?/g,\n];\n\nexport default function apiKeyRedactor(omp: HookAPI): void {\n  omp.on(\"tool_result\", async (event) => {\n    if (event.isError) return;\n\n    let changed = false;\n    const redacted = event.content.map(chunk => {\n      if (chunk.type !== \"text\") return chunk;\n      let text = chunk.text;\n      for (const pattern of SECRET_PATTERNS) {\n        const next = text.replace(pattern, \"[REDACTED]\");\n        if (next !== text) { changed = true; text = next; }\n      }\n      return { ...chunk, text };\n    });\n\n    if (changed) return { content: redacted };\n  });\n}\n```\n\n### 3. Context filter\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function contextFilter(omp: HookAPI): void {\n  omp.on(\"context\", async (event) => {\n    const MAX_TOOL_OUTPUT_CHARS = 8_000;\n\n    const trimmed = event.messages.map(msg => {\n      // Truncate very large tool results to keep context manageable\n      if (msg.role !== \"tool\") return msg;\n      const content = msg.content.map(chunk => {\n        if (chunk.type !== \"text\" || chunk.text.length <= MAX_TOOL_OUTPUT_CHARS) return chunk;\n        return {\n          ...chunk,\n          text: chunk.text.slice(0, MAX_TOOL_OUTPUT_CHARS) + \"\\n[... truncated by context-filter hook]\",\n        };\n      });\n      return { ...msg, content };\n    });\n\n    return { messages: trimmed };\n  });\n}\n```\n\n## UI methods in hook context\n\n`ctx.ui` is a `HookUIContext`. Available methods:\n\n| Method | Description |\n|---|---|\n| `notify(message, type?)` | Show an in-app notification |\n| `setStatus(key, text)` | Set footer status text (keyed, sorted by key) |\n| `select(title, options)` | Show a selection dialog |\n| `confirm(title, message)` | Show a yes/no dialog |\n| `input(title, placeholder?)` | Show a text input dialog |\n| `editor(title, prefill?, { signal }?, { promptStyle }?)` | Show a multi-line editor |\n| `setEditorText(text)` | Set the input editor content |\n| `getEditorText()` | Get current input editor content |\n| `custom(factory)` | Render a custom TUI component |\n| `theme` | Current theme object |\n\nPass `{ promptStyle: true }` as the fourth argument when Enter should submit and Shift+Enter should insert a newline. The default hook editor behavior keeps Enter as newline and Ctrl+Enter as submit.\n\n`ctx.hasUI` is `false` in headless/print/subagent mode — always guard interactive calls.\n\n## Further reading\n\n- `docs/hooks.md` — hook subsystem internals, ordering rules, error propagation\n- `docs/extensions.md` — `ExtensionAPI` (superset of `HookAPI`)\n- `docs/skills/examples/safety-hook/` — complete working example\n",
-	"skills/authoring-marketplaces.md": "---\nname: authoring-marketplaces\ndescription: Use when creating a new omp marketplace. Covers marketplace.json schema, source types, install commands, and publishing.\n---\n\n# Authoring Marketplaces\n\nA marketplace is a Git repository (or local directory) that contains a catalog file at `.claude-plugin/marketplace.json`. Anyone can author one. Users add it with `/marketplace add owner/repo` and then install individual plugins from it.\n\n## Minimum viable marketplace\n\n```\nmy-marketplace/\n  .claude-plugin/\n    marketplace.json\n  plugins/\n    my-plugin/\n      skills/\n        my-skill/\n          SKILL.md\n```\n\n```json\n{\n  \"name\": \"my-marketplace\",\n  \"owner\": { \"name\": \"Your Name\" },\n  \"plugins\": [\n    {\n      \"name\": \"my-plugin\",\n      \"description\": \"What it does\",\n      \"source\": \"./plugins/my-plugin\"\n    }\n  ]\n}\n```\n\nPush to GitHub. Users install with:\n\n```\n/marketplace add your-github-username/my-marketplace\n/marketplace install my-plugin@my-marketplace\n```\n\n## marketplace.json schema\n\nThe catalog file must live at `.claude-plugin/marketplace.json` in the repository root.\n\n### Top-level fields\n\n| Field | Required | Description |\n|---|---|---|\n| `name` | yes | Marketplace name. Lowercase alphanumeric, hyphens, dots. Must start and end with alphanumeric. Max 64 chars. |\n| `owner` | yes | Object with at minimum `owner.name` (string) |\n| `owner.name` | yes | Marketplace owner name |\n| `owner.email` | no | Owner contact email |\n| `plugins` | yes | Array of plugin entries (see below) |\n| `metadata.description` | no | Short description of the marketplace |\n| `metadata.version` | no | Catalog metadata version string |\n| `metadata.pluginRoot` | no | String prepended to all relative plugin source paths |\n| extra top-level fields | no | Preserved by the parser but not used by marketplace install/runtime logic |\n\n### Plugin entry fields\n\n| Field | Required | Description |\n|---|---|---|\n| `name` | yes | Plugin name (same naming rules as marketplace name) |\n| `source` | yes | Where to find the plugin — string or object (see source types below) |\n| `description` | no | Short plugin description |\n| `version` | no | Version string |\n| `author` | no | `{ name, email? }` |\n| `homepage` | no | URL |\n| `category` | no | e.g. `development`, `productivity`, `security` |\n| `tags` / `keywords` | no | Arrays of string tags/keywords |\n| `repository` | no | Repository URL |\n| `license` | no | License string |\n| `strict` | no | Boolean plugin metadata flag |\n| `commands`, `agents`, `hooks`, `mcpServers`, `lspServers` | no | Capability metadata used by plugin tooling and selectors |\n\n### Full catalog example\n\n```json\n{\n  \"$schema\": \"https://anthropic.com/claude-code/marketplace.schema.json\",\n  \"name\": \"acme-plugins\",\n  \"owner\": {\n    \"name\": \"Acme Corp\",\n    \"email\": \"plugins@acme.example\"\n  },\n  \"metadata\": {\n    \"description\": \"Official Acme plugins for oh-my-pi\"\n  },\n  \"plugins\": [\n    {\n      \"name\": \"acme-linter\",\n      \"description\": \"Enforce Acme coding standards\",\n      \"category\": \"development\",\n      \"source\": \"./plugins/linter\"\n    },\n    {\n      \"name\": \"acme-deploy\",\n      \"description\": \"One-command deploy to Acme cloud\",\n      \"category\": \"devops\",\n      \"source\": {\n        \"source\": \"github\",\n        \"repo\": \"acme-corp/omp-deploy-plugin\",\n        \"ref\": \"main\"\n      }\n    }\n  ]\n}\n```\n\n## Plugin source types\n\n### 1. Relative path string\n\nPoints to a subdirectory inside the marketplace repository itself. Must start with `./`.\n\n```json\n\"source\": \"./plugins/my-plugin\"\n```\n\nThe path is resolved relative to the marketplace repository root. Path traversal outside the repo root is rejected.\n\nUse `metadata.pluginRoot` to avoid repeating a common prefix:\n\n```json\n{\n  \"metadata\": { \"pluginRoot\": \"./plugins\" },\n  \"plugins\": [\n    { \"name\": \"plugin-a\", \"source\": \"./plugin-a\" },\n    { \"name\": \"plugin-b\", \"source\": \"./plugin-b\" }\n  ]\n}\n```\n\n### 2. Git URL\n\nA full Git repository URL. Optionally pin to a branch/tag (`ref`) or exact commit (`sha`):\n\n```json\n\"source\": {\n  \"source\": \"url\",\n  \"url\": \"https://github.com/org/my-plugin.git\",\n  \"ref\": \"main\",\n  \"sha\": \"a1b2c3d4...\"\n}\n```\n\n### 3. GitHub shorthand\n\nShorthand for GitHub repositories. Functionally equivalent to a Git URL but more concise:\n\n```json\n\"source\": {\n  \"source\": \"github\",\n  \"repo\": \"org/my-plugin\",\n  \"ref\": \"v2.1.0\",\n  \"sha\": \"a1b2c3d4...\"\n}\n```\n\n### 4. Git subdirectory (monorepo)\n\nFor plugins living inside a subdirectory of a larger repository. `url` accepts a full HTTPS URL or a GitHub `owner/repo` shorthand:\n\n```json\n\"source\": {\n  \"source\": \"git-subdir\",\n  \"url\": \"https://github.com/org/monorepo.git\",\n  \"path\": \"packages/my-plugin\",\n  \"ref\": \"main\",\n  \"sha\": \"a1b2c3d4...\"\n}\n```\n\nThe `path` must resolve inside the cloned repository — directory escape is rejected.\n\n### 5. NPM package\n\nDeclares the plugin as an npm package. `version` is optional:\n\n```json\n\"source\": {\n  \"source\": \"npm\",\n  \"package\": \"@acme/omp-plugin\",\n  \"version\": \"1.2.0\"\n}\n```\n\n> Note: npm plugin sources are declared in the schema but installation support is not yet fully implemented. Use Git-based sources for plugins that need to work today.\n\n## Plugin structure\n\nA plugin directory (regardless of source type) ships its content in conventional locations, all optional:\n\n```\nmy-plugin/\n  skills/<name>/SKILL.md   ← skills\n  commands/*.md            ← slash commands\n  agents/*.md              ← subagent definitions\n  hooks/pre/, hooks/post/  ← hooks\n  tools/                   ← custom tools\n  .mcp.json                ← MCP server definitions\n  package.json             ← optional; its version is a fallback when the catalog entry has no version\n  README.md                ← recommended: description + usage\n```\n\n> Note: extension modules declared via `package.json` `omp.extensions` are **not** loaded from marketplace installs — that mechanism only applies to npm-installed or `omp plugin link`ed plugins. Ship marketplace plugin behavior through the conventional directories above.\n\n## Install command\n\n```\n/marketplace install name@marketplace-name\n/marketplace install --force name@marketplace-name     # reinstall\n/marketplace install --scope project name@marketplace  # project-scoped\n```\n\nCLI equivalent:\n\n```\nomp plugin marketplace add owner/repo\nomp plugin install name@marketplace-name\n```\n\nScope behavior:\n\n- **user** (default) — installed in `~/.omp/plugins/installed_plugins.json`, available in all projects\n- **project** — installed in `<project>/.omp/plugins/installed_plugins.json`, available only in that project\n\nProject-scoped installs shadow user-scoped installs of the same plugin name.\n\n## Naming rules\n\nMarketplace names and plugin names must:\n\n- Contain only lowercase letters, digits, hyphens (`-`), and dots (`.`)\n- Start and end with a lowercase letter or digit\n- Be at most 64 characters\n\nPlugin IDs (`name@marketplace`) must be at most 128 characters total.\n\nValid: `my-plugin`, `code-review`, `acme.tools`, `ai-v2`\nInvalid: `-bad-start`, `bad-end-`, `.dot-start`, `Under_score`, `HAS_CAPS`\n\n## Publishing workflow\n\n1. Create `marketplace.json` at `.claude-plugin/marketplace.json` in a new Git repo.\n2. Add plugin entries pointing to subdirectories (or external sources).\n3. Push to GitHub.\n4. Share the `owner/repo` string. Users add it with `/marketplace add owner/repo`.\n5. When you update the catalog, users run `/marketplace update your-marketplace-name` to pull the latest.\n\nTo test locally before publishing:\n\n```\n/marketplace add ./path/to/my-marketplace\n```\n\nLocal path sources also accept `~/` and absolute paths.\n\n## Further reading\n\n- `docs/marketplace.md` — marketplace system internals, on-disk layout, command reference\n- `docs/skills/authoring-extensions.md` — how to author the extension modules inside plugins\n- `docs/skills/examples/mini-marketplace/` — minimal working marketplace example\n",
+	"skills/authoring-marketplaces.md": "---\nname: authoring-marketplaces\ndescription: Use when creating a new omp marketplace. Covers marketplace.json schema, source types, install commands, and publishing.\n---\n\n# Authoring Marketplaces\n\nA marketplace is a Git repository (or local directory) that contains a catalog file at either `.omp-plugin/marketplace.json` (preferred for omp-specific catalogs) or `.claude-plugin/marketplace.json` (Claude Code-compatible; used as the fallback). Anyone can author one. Users add it with `/marketplace add owner/repo` and then install individual plugins from it.\n\n## Minimum viable marketplace\n\n```\nmy-marketplace/\n  .claude-plugin/\n    marketplace.json\n  plugins/\n    my-plugin/\n      skills/\n        my-skill/\n          SKILL.md\n```\n\n```json\n{\n  \"name\": \"my-marketplace\",\n  \"owner\": { \"name\": \"Your Name\" },\n  \"plugins\": [\n    {\n      \"name\": \"my-plugin\",\n      \"description\": \"What it does\",\n      \"source\": \"./plugins/my-plugin\"\n    }\n  ]\n}\n```\n\nPush to GitHub. Users install with:\n\n```\n/marketplace add your-github-username/my-marketplace\n/marketplace install my-plugin@my-marketplace\n```\n\n## marketplace.json schema\n\nThe catalog file lives at either `.omp-plugin/marketplace.json` or `.claude-plugin/marketplace.json` in the repository root. omp prefers the `.omp-plugin/` path and falls back to the Claude path; a repository may publish both to expose tool-specific catalogs from a single source tree.\n\n### Top-level fields\n\n| Field | Required | Description |\n|---|---|---|\n| `name` | yes | Marketplace name. Lowercase alphanumeric, hyphens, dots. Must start and end with alphanumeric. Max 64 chars. |\n| `owner` | yes | Object with at minimum `owner.name` (string) |\n| `owner.name` | yes | Marketplace owner name |\n| `owner.email` | no | Owner contact email |\n| `plugins` | yes | Array of plugin entries (see below) |\n| `metadata.description` | no | Short description of the marketplace |\n| `metadata.version` | no | Catalog metadata version string |\n| `metadata.pluginRoot` | no | String prepended to all relative plugin source paths |\n| extra top-level fields | no | Preserved by the parser but not used by marketplace install/runtime logic |\n\n### Plugin entry fields\n\n| Field | Required | Description |\n|---|---|---|\n| `name` | yes | Plugin name (same naming rules as marketplace name) |\n| `source` | yes | Where to find the plugin — string or object (see source types below) |\n| `description` | no | Short plugin description |\n| `version` | no | Version string |\n| `author` | no | `{ name, email? }` |\n| `homepage` | no | URL |\n| `category` | no | e.g. `development`, `productivity`, `security` |\n| `tags` / `keywords` | no | Arrays of string tags/keywords |\n| `repository` | no | Repository URL |\n| `license` | no | License string |\n| `strict` | no | Boolean plugin metadata flag |\n| `commands`, `agents`, `hooks`, `mcpServers`, `lspServers` | no | Capability metadata used by plugin tooling and selectors |\n\n### Full catalog example\n\n```json\n{\n  \"$schema\": \"https://anthropic.com/claude-code/marketplace.schema.json\",\n  \"name\": \"acme-plugins\",\n  \"owner\": {\n    \"name\": \"Acme Corp\",\n    \"email\": \"plugins@acme.example\"\n  },\n  \"metadata\": {\n    \"description\": \"Official Acme plugins for oh-my-pi\"\n  },\n  \"plugins\": [\n    {\n      \"name\": \"acme-linter\",\n      \"description\": \"Enforce Acme coding standards\",\n      \"category\": \"development\",\n      \"source\": \"./plugins/linter\"\n    },\n    {\n      \"name\": \"acme-deploy\",\n      \"description\": \"One-command deploy to Acme cloud\",\n      \"category\": \"devops\",\n      \"source\": {\n        \"source\": \"github\",\n        \"repo\": \"acme-corp/omp-deploy-plugin\",\n        \"ref\": \"main\"\n      }\n    }\n  ]\n}\n```\n\n## Plugin source types\n\n### 1. Relative path string\n\nPoints to a subdirectory inside the marketplace repository itself. Must start with `./`.\n\n```json\n\"source\": \"./plugins/my-plugin\"\n```\n\nThe path is resolved relative to the marketplace repository root. Path traversal outside the repo root is rejected.\n\nUse `metadata.pluginRoot` to avoid repeating a common prefix:\n\n```json\n{\n  \"metadata\": { \"pluginRoot\": \"./plugins\" },\n  \"plugins\": [\n    { \"name\": \"plugin-a\", \"source\": \"./plugin-a\" },\n    { \"name\": \"plugin-b\", \"source\": \"./plugin-b\" }\n  ]\n}\n```\n\n### 2. Git URL\n\nA full Git repository URL. Optionally pin to a branch/tag (`ref`) or exact commit (`sha`):\n\n```json\n\"source\": {\n  \"source\": \"url\",\n  \"url\": \"https://github.com/org/my-plugin.git\",\n  \"ref\": \"main\",\n  \"sha\": \"a1b2c3d4...\"\n}\n```\n\n### 3. GitHub shorthand\n\nShorthand for GitHub repositories. Functionally equivalent to a Git URL but more concise:\n\n```json\n\"source\": {\n  \"source\": \"github\",\n  \"repo\": \"org/my-plugin\",\n  \"ref\": \"v2.1.0\",\n  \"sha\": \"a1b2c3d4...\"\n}\n```\n\n### 4. Git subdirectory (monorepo)\n\nFor plugins living inside a subdirectory of a larger repository. `url` accepts a full HTTPS URL or a GitHub `owner/repo` shorthand:\n\n```json\n\"source\": {\n  \"source\": \"git-subdir\",\n  \"url\": \"https://github.com/org/monorepo.git\",\n  \"path\": \"packages/my-plugin\",\n  \"ref\": \"main\",\n  \"sha\": \"a1b2c3d4...\"\n}\n```\n\nThe `path` must resolve inside the cloned repository — directory escape is rejected.\n\n### 5. NPM package\n\nDeclares the plugin as an npm package. `version` is optional:\n\n```json\n\"source\": {\n  \"source\": \"npm\",\n  \"package\": \"@acme/omp-plugin\",\n  \"version\": \"1.2.0\"\n}\n```\n\n> Note: npm plugin sources are declared in the schema but installation support is not yet fully implemented. Use Git-based sources for plugins that need to work today.\n\n## Plugin structure\n\nA plugin directory (regardless of source type) ships its content in conventional locations, all optional:\n\n```\nmy-plugin/\n  skills/<name>/SKILL.md   ← skills\n  commands/*.md            ← slash commands\n  agents/*.md              ← subagent definitions\n  hooks/pre/, hooks/post/  ← hooks\n  tools/                   ← custom tools\n  .mcp.json                ← MCP server definitions\n  package.json             ← optional; its version is a fallback when the catalog entry has no version\n  README.md                ← recommended: description + usage\n```\n\n> Note: extension modules declared via `package.json` `omp.extensions` are **not** loaded from marketplace installs — that mechanism only applies to npm-installed or `omp plugin link`ed plugins. Ship marketplace plugin behavior through the conventional directories above.\n\n## Install command\n\n```\n/marketplace install name@marketplace-name\n/marketplace install --force name@marketplace-name     # reinstall\n/marketplace install --scope project name@marketplace  # project-scoped\n```\n\nCLI equivalent:\n\n```\nomp plugin marketplace add owner/repo\nomp plugin install name@marketplace-name\n```\n\nScope behavior:\n\n- **user** (default) — installed in `~/.omp/plugins/installed_plugins.json`, available in all projects\n- **project** — installed in `<project>/.omp/plugins/installed_plugins.json`, available only in that project\n\nProject-scoped installs shadow user-scoped installs of the same plugin name.\n\n## Naming rules\n\nMarketplace names and plugin names must:\n\n- Contain only lowercase letters, digits, hyphens (`-`), and dots (`.`)\n- Start and end with a lowercase letter or digit\n- Be at most 64 characters\n\nPlugin IDs (`name@marketplace`) must be at most 128 characters total.\n\nValid: `my-plugin`, `code-review`, `acme.tools`, `ai-v2`\nInvalid: `-bad-start`, `bad-end-`, `.dot-start`, `Under_score`, `HAS_CAPS`\n\n## Publishing workflow\n\n1. Create `marketplace.json` at `.omp-plugin/marketplace.json` (omp-only) or `.claude-plugin/marketplace.json` (shared with Claude Code) in a new Git repo.\n2. Add plugin entries pointing to subdirectories (or external sources).\n3. Push to GitHub.\n4. Share the `owner/repo` string. Users add it with `/marketplace add owner/repo`.\n5. When you update the catalog, users run `/marketplace update your-marketplace-name` to pull the latest.\n\nTo test locally before publishing:\n\n```\n/marketplace add ./path/to/my-marketplace\n```\n\nLocal path sources also accept `~/` and absolute paths.\n\n## Further reading\n\n- `docs/marketplace.md` — marketplace system internals, on-disk layout, command reference\n- `docs/skills/authoring-extensions.md` — how to author the extension modules inside plugins\n- `docs/skills/examples/mini-marketplace/` — minimal working marketplace example\n",
 	"skills/examples/hello-extension/README.md": "# hello-extension\n\nA minimal `oh-my-pi` extension that demonstrates the two most common authoring patterns: subscribing to `session_start` to notify on load, and registering a `/hello` slash command that sends a greeting into the conversation. It is intentionally small — use it as a copy-paste starting point for your own extension.\n\n## Install\n\n**Option A — drop into user extensions directory:**\n\n```\ncp -r . ~/.omp/agent/extensions/hello-extension\n```\n\nRestart `omp`. You will see the startup notification immediately.\n\n**Option B — point the settings `extensions` array at it:**\n\n```yaml\n# ~/.omp/agent/config.yml\nextensions:\n  - /path/to/hello-extension\n```\n\n**Option C — load once via CLI flag:**\n\n```\nomp --extension ./hello-extension\n```\n\n## Usage\n\nAfter loading, type `/hello` or `/hello Ada` in the omp prompt. The command sends a visible greeting custom message into the conversation and shows a \"Message sent!\" notification.\n\n## What it demonstrates\n\n- Default export factory receiving `ExtensionAPI`\n- `pi.on(\"session_start\", ...)` — session lifecycle hook\n- `pi.registerCommand(...)` — slash command registration\n- `ctx.ui.notify(...)` — user-facing notification\n- `package.json` with `omp.extensions` manifest field\n",
 	"skills/examples/mini-marketplace/README.md": "# mini-marketplace\n\nA minimal `oh-my-pi` marketplace catalog that demonstrates the `marketplace.json` format. It lists one plugin (`my-plugin`) using a relative path source.\n\n## Install command\n\n```\n/marketplace add ./docs/skills/examples/mini-marketplace\n/marketplace install my-plugin@example-marketplace\n```\n\nOr from the CLI:\n\n```\nomp plugin marketplace add ./docs/skills/examples/mini-marketplace\nomp plugin install my-plugin@example-marketplace\n```\n\n## What it demonstrates\n\n- Minimum required `marketplace.json` fields: `name`, `owner.name`, `plugins`\n- Relative path plugin source using `./` prefix (`\"source\": \"./my-plugin\"`)\n- Plugin bundled inside the same directory tree as the marketplace catalog\n- Extra catalog metadata: the example includes a top-level `description`; current marketplace parsing preserves extra top-level fields, while runtime behavior uses required fields and plugin entries.\n\n## Structure\n\n```\nmini-marketplace/\n  .claude-plugin/\n    marketplace.json      ← catalog\n  README.md\n  my-plugin/\n    package.json          ← omp.extensions manifest\n    index.ts              ← extension entry point\n```\n\nPublished and local marketplaces use the same catalog location: `.claude-plugin/marketplace.json` inside the marketplace root. Point `/marketplace add` at this folder to load the example.\n",
 	"skills/examples/safety-hook/README.md": "# safety-hook\n\nAn `oh-my-pi` extension that demonstrates `tool_call` blocking. It intercepts `bash` tool calls and returns `{ block: true, reason: \"...\" }` when the command contains `rm -rf /` with normal whitespace, preventing the tool from executing.\n\n## What it demonstrates\n\n- `pi.on(\"tool_call\", ...)` — pre-execution interception\n- `return { block: true, reason: \"...\" }` — blocking contract\n- Regex guard on bash input (`/\\brm\\s+-rf\\s+\\//`)\n\n## Install\n\n```\ncp -r . ~/.omp/agent/extensions/safety-hook\n```\n\nRestart `omp`. The hook is active for all sessions.\n\nOr load once:\n\n```\nomp --extension ./safety-hook\n```\n\n## How it works\n\n```\nLLM calls bash tool\n       │\n       ▼\ntool_call handlers run\n       │\n       ├─ command matches /\\brm\\s+-rf\\s+\\// ?\n       │       yes → { block: true, reason: \"...\" }  ←  execution stops, reason sent to LLM\n       │       no  → undefined                        ←  execution continues normally\n       ▼\ntool executes (if not blocked)\n```\n\nThe `reason` text is what the LLM receives as the tool error, so it can understand why the call was rejected and try a different approach.\n",
@@ -75,8 +76,8 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"theme.md": "# Theming Reference\n\nThis document describes how theming works in the coding-agent today: schema, loading, runtime behavior, and failure modes.\n\n## What the theme system controls\n\nThe theme system drives:\n\n- foreground/background color tokens used across the TUI\n- markdown styling adapters (`getMarkdownTheme()`)\n- selector/editor/settings list adapters (`getSelectListTheme()`, `getEditorTheme()`, `getSettingsListTheme()`)\n- symbol preset + symbol overrides (`unicode`, `nerd`, `ascii`)\n- syntax highlighting colors used by native highlighter (`@oh-my-pi/pi-natives`)\n- status line segment colors\n\nPrimary implementation: `src/modes/theme/theme.ts`.\n\n## Theme JSON shape\n\nTheme files are JSON objects validated against the runtime schema in `theme.ts` (`themeJsonSchema`) and mirrored by `src/modes/theme/theme-schema.json`.\n\nTop-level fields:\n\n- `name` (required)\n- `colors` (required; all color tokens required)\n- `vars` (optional; reusable color variables)\n- `export` (optional; HTML export colors)\n- `symbols` (optional)\n  - `preset` (optional: `unicode | nerd | ascii`)\n  - `overrides` (optional: key/value overrides for `SymbolKey`)\n\nColor values accept:\n\n- hex string (`\"#RRGGBB\"`)\n- 256-color index (`0..255`)\n- variable reference string (resolved through `vars`)\n- empty string (`\"\"`) meaning terminal default (`\\x1b[39m` fg, `\\x1b[49m` bg)\n\n## Required color tokens (current)\n\nAll tokens below are required in `colors`.\n\n### Core text and borders (11)\n\n`accent`, `border`, `borderAccent`, `borderMuted`, `success`, `error`, `warning`, `muted`, `dim`, `text`, `thinkingText`\n\n### Background blocks (7)\n\n`selectedBg`, `userMessageBg`, `customMessageBg`, `toolPendingBg`, `toolSuccessBg`, `toolErrorBg`, `statusLineBg`\n\n### Message/tool text (5)\n\n`userMessageText`, `customMessageText`, `customMessageLabel`, `toolTitle`, `toolOutput`\n\n### Markdown (10)\n\n`mdHeading`, `mdLink`, `mdLinkUrl`, `mdCode`, `mdCodeBlock`, `mdCodeBlockBorder`, `mdQuote`, `mdQuoteBorder`, `mdHr`, `mdListBullet`\n\n### Tool diff + syntax highlighting (12)\n\n`toolDiffAdded`, `toolDiffRemoved`, `toolDiffContext`,\n`syntaxComment`, `syntaxKeyword`, `syntaxFunction`, `syntaxVariable`, `syntaxString`, `syntaxNumber`, `syntaxType`, `syntaxOperator`, `syntaxPunctuation`\n\n### Mode/thinking borders (8)\n\n`thinkingOff`, `thinkingMinimal`, `thinkingLow`, `thinkingMedium`, `thinkingHigh`, `thinkingXhigh`, `bashMode`, `pythonMode`\n\n### Status line segment colors (13)\n\n`statusLineSep`, `statusLineModel`, `statusLinePath`, `statusLineGitClean`, `statusLineGitDirty`, `statusLineContext`, `statusLineSpend`, `statusLineStaged`, `statusLineDirty`, `statusLineUntracked`, `statusLineOutput`, `statusLineCost`, `statusLineSubagents`\n\n## Optional tokens\n\n### `export` section (optional)\n\nUsed for HTML export theming helpers:\n\n- `export.pageBg`\n- `export.cardBg`\n- `export.infoBg`\n\nIf omitted, export code derives defaults from resolved theme colors.\n\n### `symbols` section (optional)\n\n- `symbols.preset` sets a theme-level default symbol set.\n- `symbols.overrides` can override individual `SymbolKey` values.\n- `symbols.spinnerFrames` overrides the loading spinner frames. Accepts either a flat `string[]` (applied to both spinner types) or an object `{ \"status\"?: string[], \"activity\"?: string[] }` to override each type independently. Any type not specified falls back to the symbol preset's default frames. `status` drives the ~12.5fps spinner used by loaders and tool-execution indicators; `activity` drives the ~30fps spinner used by markdown progress bars and similar high-frequency UI.\n\nRuntime precedence:\n\n1. settings `symbolPreset` override (if set)\n2. theme JSON `symbols.preset`\n3. fallback `\"unicode\"`\n\nInvalid override keys are ignored and logged (`logger.debug`).\n\n## Built-in vs custom theme sources\n\nTheme lookup order (`loadThemeJson`):\n\n1. built-in embedded themes (`dark.json`, `light.json`, and all `defaults/*.json` compiled into `defaultThemes`)\n2. custom theme file: `<customThemesDir>/<name>.json`\n\nCustom themes directory comes from `getCustomThemesDir()`:\n\n- default: `~/.omp/agent/themes`\n- overridden by `PI_CODING_AGENT_DIR` (`$PI_CODING_AGENT_DIR/themes`)\n\n`getAvailableThemes()` returns merged built-in + custom names, sorted, with built-ins taking precedence on name collision.\n\n## Loading, validation, and resolution\n\nFor custom theme files:\n\n1. read JSON\n2. parse JSON\n3. validate against `ThemeJsonSchema`\n4. resolve `vars` references recursively\n5. convert resolved values to ANSI by terminal capability mode\n\nValidation behavior:\n\n- missing required color tokens: explicit grouped error message\n- bad token types/values: validation errors with JSON path\n- unknown theme file: `Theme not found: <name>`\n\nVar reference behavior:\n\n- supports nested references\n- throws on missing variable reference\n- throws on circular references\n\n## Terminal color mode behavior\n\nColor mode detection (`detectColorMode`):\n\n- `COLORTERM=truecolor|24bit` => truecolor\n- `WT_SESSION` => truecolor\n- `TERM` in `dumb`, `linux`, or empty => 256color\n- otherwise => truecolor\n\nConversion behavior:\n\n- hex -> `Bun.color(..., \"ansi-16m\" | \"ansi-256\")`\n- numeric -> `38;5` / `48;5` ANSI\n- `\"\"` -> default fg/bg reset\n\n## Runtime switching behavior\n\n### Initial theme (`initTheme`)\n\n`main.ts` initializes theme with settings:\n\n- `symbolPreset`\n- `colorBlindMode`\n- `theme.dark`\n- `theme.light`\n\nAuto theme slot selection uses terminal appearance in this order:\n\n1. terminal-reported OSC 11 background luminance, unless the macOS/Zellij fallback path is active\n2. `COLORFGBG` background index (`< 8` => dark, `>= 8` => light)\n3. macOS appearance fallback only for the known-broken macOS/Zellij OSC 11 path\n4. dark slot fallback\n\nCurrent defaults from settings schema:\n\n- `theme.dark = \"titanium\"`\n- `theme.light = \"light\"`\n- `symbolPreset = \"unicode\"`\n- `colorBlindMode = false`\n\n### Explicit switching (`setTheme`)\n\n- loads selected theme\n- updates global `theme` singleton\n- optionally starts watcher\n- triggers `onThemeChange` callback\n\nOn failure:\n\n- falls back to built-in `dark`\n- returns `{ success: false, error }`\n\n### Preview switching (`previewTheme`)\n\n- applies temporary preview theme to global `theme`\n- does **not** change persisted settings by itself\n- returns success/error without fallback replacement\n\nSettings UI uses this for live preview and restores prior theme on cancel.\n\n## Watchers and live reload\n\nWhen watcher is enabled (`setTheme(..., true)` / interactive init):\n\n- watches `<customThemesDir>/<currentTheme>.json` only when that file exists\n- built-ins are effectively not watched; built-in theme lookup also takes precedence over same-name custom files\n- matching file changes schedule a debounced reload; reload errors or temporary file absence keep the last successfully loaded theme\n- the watcher does not perform a delete/rename fallback; it waits for a future successful reload or explicit theme switch\n\nAuto mode also reevaluates dark/light slot mapping from terminal appearance changes, `SIGWINCH`, and the macOS fallback observer when active.\n\n## Color-blind mode behavior\n\n`colorBlindMode` changes only one token at runtime:\n\n- `toolDiffAdded` is HSV-adjusted (green shifted toward blue)\n- adjustment is applied only when resolved value is a hex string\n\nOther tokens are unchanged.\n\n## Where theme settings are persisted\n\nTheme-related settings are persisted by `Settings` to global config YAML:\n\n- path: `<agentDir>/config.yml`\n- default agent dir: `~/.omp/agent`\n- effective default file: `~/.omp/agent/config.yml`\n\nPersisted keys:\n\n- `theme.dark`\n- `theme.light`\n- `symbolPreset`\n- `colorBlindMode`\n\nLegacy migration exists: old flat `theme: \"name\"` is migrated to nested `theme.dark` or `theme.light` based on luminance detection.\n\n## Creating a custom theme (practical)\n\n1. Create file in custom themes dir, e.g. `~/.omp/agent/themes/my-theme.json`.\n2. Include `name`, optional `vars`, and **all required** `colors` tokens.\n3. Optionally include `symbols` and `export`.\n4. Select the theme in Settings (`Appearance -> Dark Theme` or `Appearance -> Light Theme`) depending on which auto slot you want.\n\nMinimal skeleton:\n\n```json\n{\n  \"name\": \"my-theme\",\n  \"vars\": {\n    \"accent\": \"#7aa2f7\",\n    \"muted\": 244\n  },\n  \"colors\": {\n    \"accent\": \"accent\",\n    \"border\": \"#4c566a\",\n    \"borderAccent\": \"accent\",\n    \"borderMuted\": \"muted\",\n    \"success\": \"#9ece6a\",\n    \"error\": \"#f7768e\",\n    \"warning\": \"#e0af68\",\n    \"muted\": \"muted\",\n    \"dim\": 240,\n    \"text\": \"\",\n    \"thinkingText\": \"muted\",\n\n    \"selectedBg\": \"#2a2f45\",\n    \"userMessageBg\": \"#1f2335\",\n    \"userMessageText\": \"\",\n    \"customMessageBg\": \"#24283b\",\n    \"customMessageText\": \"\",\n    \"customMessageLabel\": \"accent\",\n    \"toolPendingBg\": \"#1f2335\",\n    \"toolSuccessBg\": \"#1f2d2a\",\n    \"toolErrorBg\": \"#2d1f2a\",\n    \"toolTitle\": \"\",\n    \"toolOutput\": \"muted\",\n\n    \"mdHeading\": \"accent\",\n    \"mdLink\": \"accent\",\n    \"mdLinkUrl\": \"muted\",\n    \"mdCode\": \"#c0caf5\",\n    \"mdCodeBlock\": \"#c0caf5\",\n    \"mdCodeBlockBorder\": \"muted\",\n    \"mdQuote\": \"muted\",\n    \"mdQuoteBorder\": \"muted\",\n    \"mdHr\": \"muted\",\n    \"mdListBullet\": \"accent\",\n\n    \"toolDiffAdded\": \"#9ece6a\",\n    \"toolDiffRemoved\": \"#f7768e\",\n    \"toolDiffContext\": \"muted\",\n\n    \"syntaxComment\": \"#565f89\",\n    \"syntaxKeyword\": \"#bb9af7\",\n    \"syntaxFunction\": \"#7aa2f7\",\n    \"syntaxVariable\": \"#c0caf5\",\n    \"syntaxString\": \"#9ece6a\",\n    \"syntaxNumber\": \"#ff9e64\",\n    \"syntaxType\": \"#2ac3de\",\n    \"syntaxOperator\": \"#89ddff\",\n    \"syntaxPunctuation\": \"#9aa5ce\",\n\n    \"thinkingOff\": 240,\n    \"thinkingMinimal\": 244,\n    \"thinkingLow\": \"#7aa2f7\",\n    \"thinkingMedium\": \"#2ac3de\",\n    \"thinkingHigh\": \"#bb9af7\",\n    \"thinkingXhigh\": \"#f7768e\",\n\n    \"bashMode\": \"#2ac3de\",\n    \"pythonMode\": \"#bb9af7\",\n\n    \"statusLineBg\": \"#16161e\",\n    \"statusLineSep\": 240,\n    \"statusLineModel\": \"#bb9af7\",\n    \"statusLinePath\": \"#7aa2f7\",\n    \"statusLineGitClean\": \"#9ece6a\",\n    \"statusLineGitDirty\": \"#e0af68\",\n    \"statusLineContext\": \"#2ac3de\",\n    \"statusLineSpend\": \"#7dcfff\",\n    \"statusLineStaged\": \"#9ece6a\",\n    \"statusLineDirty\": \"#e0af68\",\n    \"statusLineUntracked\": \"#f7768e\",\n    \"statusLineOutput\": \"#c0caf5\",\n    \"statusLineCost\": \"#ff9e64\",\n    \"statusLineSubagents\": \"#bb9af7\"\n  }\n}\n```\n\n## Testing custom themes\n\nUse this workflow:\n\n1. Start interactive mode (watcher enabled from startup).\n2. Open settings and preview theme values (live `previewTheme`).\n3. For custom theme files, edit the JSON while running and confirm auto-reload on save.\n4. Exercise critical surfaces:\n   - markdown rendering\n   - tool blocks (pending/success/error)\n   - diff rendering (added/removed/context)\n   - status line readability\n   - thinking level border changes\n   - bash/python mode border colors\n5. Validate both symbol presets if your theme depends on glyph width/appearance.\n\n## Real constraints and caveats\n\n- All `colors` tokens are required for custom themes.\n- `export` and `symbols` are optional.\n- `$schema` in theme JSON is informational; runtime validation is enforced by a Zod schema in code.\n- `setTheme` failure falls back to `dark`; `previewTheme` failure does not replace current theme.\n- File watcher reload errors or temporary missing files keep the current loaded theme until a successful reload or explicit theme switch.\n",
 	"toolconv/anthropic.md": "# Anthropic Claude tool use (Messages API content blocks)\n\nAnthropic's Claude is a closed, hosted model family; there are no released weights and therefore no `--tool-call-parser` flag to set. The canonical tool-calling convention is the **Messages API** (`POST /v1/messages`, header `anthropic-version: 2023-06-01`): tools are advertised in a top-level `tools` array, the model returns structured `tool_use` **content blocks** with `stop_reason: \"tool_use\"`, and you feed results back as `tool_result` content blocks inside a `user` message. Tool use is \"enabled\" simply by including the `tools` parameter (optionally with `tool_choice`); the API then injects a tool-use system prompt and parses the model's output back into JSON blocks for you. This applies to all current models (Claude Opus / Sonnet / Haiku 3.x, 4, 4.x) and is mirrored by gateways such as LiteLLM and by third-party Claude-compatible servers.\n\nUnder the hood the model is trained to emit an **XML** function-call syntax (`<function_calls>` / `<invoke>` / `<parameter>`); the API serializes your JSON-Schema tools into a system prompt and converts the model's XML output into JSON `tool_use` blocks. That underlying format is documented as the *secondary* convention below, together with the older, now-retired prompt-based **legacy XML** format (`<tool_name>` / `<parameters>` / `<function_results>`) that pre-dates the Messages API and still surfaces when you do tool use purely through prompting.\n\nThe primary, authoritative shape for any parser/renderer is the JSON content-block format. The XML is informational (and the only thing visible if you reconstruct prompts at the token level).\n\n---\n\n## Content-block types & stop reasons\n\nAnthropic has no token-level tool delimiters in the public API. The unit is the **content block**: every `message.content` is an array of typed blocks. Tool calling adds two block types and one stop reason; streaming adds a delta type.\n\n| Item | Where | Shape / meaning |\n| --- | --- | --- |\n| `text` block | assistant & user | `{\"type\":\"text\",\"text\":\"...\"}`. Plain prose. Assistant may emit text *before* its tool calls. |\n| `tool_use` block | assistant | `{\"type\":\"tool_use\",\"id\":\"toolu_...\",\"name\":\"<tool>\",\"input\":{...}}`. The function call. `input` is a **nested JSON object** (already parsed), conforming to the tool's `input_schema`. |\n| `tool_result` block | user | `{\"type\":\"tool_result\",\"tool_use_id\":\"toolu_...\",\"content\":<string \\| block[]>,\"is_error\":<bool?>}`. The executed result, sent back in a `user` message. |\n| `server_tool_use` block | assistant | `{\"type\":\"server_tool_use\",\"id\":\"srvtoolu_...\",\"name\":\"web_search\",\"input\":{...}}`. Emitted for Anthropic-executed server tools; you do **not** return a `tool_result` for these. |\n| `web_search_tool_result` (and similar) | assistant | Server-tool output, injected by Anthropic inline in the assistant turn. |\n| `thinking` / `redacted_thinking` block | assistant | Extended-thinking reasoning blocks; carry a `signature`. Must be preserved verbatim across turns when thinking + tools are combined. |\n| `stop_reason: \"tool_use\"` | response top level | The model invoked one or more tools and is waiting for results. Drives the agentic loop. |\n| `stop_reason: \"end_turn\"` | response top level | Natural completion (no tool call); the loop exits. |\n| Other `stop_reason` | response top level | `\"max_tokens\"`, `\"stop_sequence\"`, `\"pause_turn\"` (long server-tool turn, resend as-is to continue), `\"refusal\"`. |\n| `id` prefixes | — | Messages `msg_…`; client tool calls `toolu_…`; server tool calls `srvtoolu_…`. |\n\nStreaming adds these SSE events / delta types (full list under [Roles / channels](#roles--channels--turn-structure) and [Tool-call format](#tool-call-format)):\n\n| Streaming item | Shape / meaning |\n| --- | --- |\n| `message_start` | Carries a `Message` skeleton with empty `content`, `stop_reason: null`. |\n| `content_block_start` | Opens a block at `index`. For a tool call: `content_block.{type:\"tool_use\",id,name,input:{}}` — `input` starts as an **empty object**. |\n| `content_block_delta` / `input_json_delta` | `{\"type\":\"input_json_delta\",\"partial_json\":\"<chunk>\"}` — a **partial JSON string** fragment of `tool_use.input`. |\n| `content_block_delta` / `text_delta` | `{\"type\":\"text_delta\",\"text\":\"...\"}`. |\n| `content_block_delta` / `thinking_delta`, `signature_delta` | Extended-thinking content / signature. |\n| `content_block_stop` | Closes the block at `index`; this is when accumulated `partial_json` is complete and safe to `JSON.parse`. |\n| `message_delta` | Top-level updates; carries the final `delta.stop_reason` (e.g. `\"tool_use\"`) and **cumulative** `usage`. |\n| `message_stop` | End of stream. |\n| `ping` / `error` | Keep-alive; `error` (e.g. `overloaded_error`) may appear mid-stream. |\n\n### Legacy XML tags (prompt-based, pre-Messages-API)\n\nThe retired prompt-based format used these tags. They are nested-element tags (no attributes), distinct from the modern attribute form (`<invoke name=\"…\">`). Verified against Anthropic's archived \"Legacy tool use\" doc (see [Sources](#sources)).\n\n| Tag | Role | Notes |\n| --- | --- | --- |\n| `<tools>` … `</tools>` | tool advertising | Container in the system prompt wrapping all `<tool_description>` entries. |\n| `<tool_description>` | tool advertising | One per tool: holds `<tool_name>`, `<description>`, `<parameters>`. |\n| `<tool_name>` | both | Function name (used in definitions, calls, and results). |\n| `<parameters>` / `<parameter>` | definition | `<parameters>` wraps `<parameter>` entries, each with `<name>`, `<type>`, `<description>`. |\n| `<function_calls>` | model output | Wraps one or more `<invoke>` blocks. |\n| `<invoke>` | model output | One function call; contains `<tool_name>` + a `<parameters>` block of `<paramName>value</paramName>` child tags. |\n| `<function_results>` | tool result (fed back) | Wraps `<result>` (success) or `<error>` (failure). |\n| `<result>` / `<stdout>` | tool result | `<result>` holds `<tool_name>` + `<stdout>`; the output text goes in `<stdout>`. |\n| `<error>` | tool result | Replaces `<result>` when the function raised. |\n| `</function_calls>` | stop sequence | Passed as `stop_sequence` so generation halts after a call. |\n| `<scratchpad>` / `<answer>` | model output | Conventionally used for chain-of-thought and final answer in legacy prompts. |\n\n---\n\n## Roles / channels / turn structure\n\nThe Messages API uses only two conversational roles, `user` and `assistant`, alternating. There is **no** dedicated `tool`/`function` role and **no** top-level `system` role — the system prompt is a separate top-level `system` parameter (string or text-block array). Tool data rides inside the normal roles:\n\n- `assistant` messages contain AI-generated `text`, `thinking`, and `tool_use` (and `server_tool_use`) blocks.\n- `user` messages contain your `text`/`image`/`document` content and `tool_result` blocks.\n\nThere are no named \"channels\". The closest analogue to a reasoning channel is the extended-thinking `thinking` content block (a first-class block with a cryptographic `signature`), kept separate from the user-visible `text` block. When thinking is enabled alongside tools, the `thinking` block(s) from a tool-calling turn must be passed back unmodified in the follow-up request.\n\nThe agentic loop is keyed on `stop_reason`:\n\n1. Send `tools` + the user message.\n2. Claude responds with `stop_reason: \"tool_use\"` and one or more `tool_use` blocks (optionally preceded by a `text` block).\n3. Execute each tool; build a `tool_result` block per call.\n4. Append the assistant message **and** a `user` message carrying all `tool_result` blocks; resend.\n5. Repeat while `stop_reason == \"tool_use\"`; exit on `end_turn` (or another terminal reason).\n\nStrict ordering rules (a 400 otherwise):\n- `tool_result` blocks must come **first** in the `user` message's `content` array (any text after them).\n- The `tool_result` `user` message must **immediately follow** the assistant `tool_use` message — nothing in between.\n- Every `tool_use.id` must be answered by a `tool_result.tool_use_id` in that next message.\n\n---\n\n## Tool definitions\n\nTools are passed in the top-level `tools` array. Each user-defined (client) tool is a **flat** object — no `{\"type\":\"function\", \"function\":{…}}` wrapper (that wrapper is OpenAI's). Fields:\n\n- `name` — matches `^[a-zA-Z0-9_-]{1,64}$`.\n- `description` — detailed plaintext (the single biggest driver of tool-call quality).\n- `input_schema` — a JSON Schema object (**not** `parameters`) describing the input the model must produce.\n- Optional: `input_examples`, `cache_control`, `strict`, `defer_loading`, `allowed_callers`.\n\n```json\n{\n  \"name\": \"get_weather\",\n  \"description\": \"Get the current weather in a given location\",\n  \"input_schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"location\": {\n        \"type\": \"string\",\n        \"description\": \"The city and state, e.g. San Francisco, CA\"\n      },\n      \"unit\": {\n        \"type\": \"string\",\n        \"enum\": [\"celsius\", \"fahrenheit\"],\n        \"description\": \"The unit of temperature, either 'celsius' or 'fahrenheit'\"\n      }\n    },\n    \"required\": [\"location\"]\n  }\n}\n```\n\nAnthropic-schema client tools (`bash`, `text_editor`, `computer`, `memory`) and server tools (`web_search`, `web_fetch`, `code_execution`, `tool_search`) instead carry a versioned `type`, e.g. `{\"type\": \"web_search_20250305\", \"name\": \"web_search\"}`.\n\n`tool_choice` controls invocation (four options):\n- `{\"type\":\"auto\"}` — model decides (default when `tools` present).\n- `{\"type\":\"any\"}` — must call some tool.\n- `{\"type\":\"tool\",\"name\":\"get_weather\"}` — must call that specific tool.\n- `{\"type\":\"none\"}` — no tools (default when no `tools`).\n\nWith `any` or `tool` the API prefills the assistant turn, so no leading natural-language text precedes the `tool_use` block. Add `\"disable_parallel_tool_use\": true` inside `tool_choice` to cap at one tool per turn. (Extended thinking only supports `auto`/`none`.)\n\n### How the API turns this into a prompt (the bridge to XML)\n\nWhen `tools` is present, the API constructs a tool-use system prompt with this skeleton (verified from \"Define tools\"):\n\n```text\nIn this environment you have access to a set of tools you can use to answer the user's question.\n{{ FORMATTING INSTRUCTIONS }}\nString and scalar parameters should be specified as is, while lists and objects should use JSON format. Note that spaces for string values are not stripped. The output is not expected to be valid XML and is parsed with regular expressions.\nHere are the functions available in JSONSchema format:\n{{ TOOL DEFINITIONS IN JSON SCHEMA }}\n{{ USER SYSTEM PROMPT }}\n{{ TOOL CONFIGURATION }}\n```\n\n`{{ TOOL DEFINITIONS IN JSON SCHEMA }}` is your `tools` array serialized to JSON Schema. `{{ FORMATTING INSTRUCTIONS }}` is the (unpublished) block teaching the model the XML syntax with `antml:` namespace prefixes (shown under [Tool-call format → underlying XML](#underlying-xml-modern-attribute-form-with-antml-namespace)). The note \"parsed with regular expressions\" is why output need not be well-formed XML.\n\n---\n\n## Tool-call format\n\nThe wire format your application consumes is JSON. A single call is one `tool_use` content block in the assistant message, with `stop_reason: \"tool_use\"` at the top level:\n\n```json\n{\n  \"id\": \"msg_01Aq9w938a90dw8q\",\n  \"type\": \"message\",\n  \"role\": \"assistant\",\n  \"model\": \"claude-opus-4-8\",\n  \"content\": [\n    {\n      \"type\": \"text\",\n      \"text\": \"I'll check the current weather in San Francisco for you.\"\n    },\n    {\n      \"type\": \"tool_use\",\n      \"id\": \"toolu_01A09q90qw90lq917835lq9\",\n      \"name\": \"get_weather\",\n      \"input\": { \"location\": \"San Francisco, CA\", \"unit\": \"celsius\" }\n    }\n  ],\n  \"stop_reason\": \"tool_use\",\n  \"stop_sequence\": null,\n  \"usage\": { \"input_tokens\": 472, \"output_tokens\": 65 }\n}\n```\n\nKey facts for a parser:\n- `tool_use.input` is an already-parsed **object**, never a JSON string.\n- A leading `text` block is optional and informational; do not rely on its wording.\n- Match calls to results by `id` → `tool_use_id`.\n\n### Underlying XML (modern attribute form with antml: namespace)\n\nBefore the API converts it, the model literally emits an XML block. The current (Claude 3+) form is attribute-based:\n\n```text\n<function_calls>\n<invoke name=\"get_weather\">\n<parameter name=\"location\">San Francisco, CA</parameter>\n<parameter name=\"unit\">celsius</parameter>\n</invoke>\n</function_calls>\n```\n\nCurrent Claude models prefix these tags with an `antml:` XML namespace prefix (e.g. `antml:function_calls`, `antml:invoke name=\"…\"`, `antml:parameter name=\"…\"`). The API strips all of this and exposes only the JSON `tool_use` block; integrators should target the JSON, not the XML.\n\n---\n\n## Multiple / parallel tool calls\n\nParallel calls are the default. Claude emits **multiple `tool_use` blocks in a single assistant message**:\n\n```json\n{\n  \"role\": \"assistant\",\n  \"content\": [\n    { \"type\": \"text\", \"text\": \"Let me check both cities.\" },\n    {\n      \"type\": \"tool_use\",\n      \"id\": \"toolu_01weather_sf\",\n      \"name\": \"get_weather\",\n      \"input\": { \"location\": \"San Francisco, CA\" }\n    },\n    {\n      \"type\": \"tool_use\",\n      \"id\": \"toolu_02weather_nyc\",\n      \"name\": \"get_weather\",\n      \"input\": { \"location\": \"New York, NY\" }\n    }\n  ]\n}\n```\n\nYou return **all** results in **one** `user` message, one `tool_result` per call, results first:\n\n```json\n{\n  \"role\": \"user\",\n  \"content\": [\n    {\n      \"type\": \"tool_result\",\n      \"tool_use_id\": \"toolu_01weather_sf\",\n      \"content\": \"San Francisco: 68F, partly cloudy\"\n    },\n    {\n      \"type\": \"tool_result\",\n      \"tool_use_id\": \"toolu_02weather_nyc\",\n      \"content\": \"New York: 45F, clear skies\"\n    }\n  ]\n}\n```\n\nCalls in one turn are **unordered** and may be run concurrently. If two batched calls turn out to depend on each other, return the natural error in a `tool_result` with `\"is_error\": true`; Claude reissues the dependent call on a later turn. (In the legacy XML format, parallelism is multiple `<invoke>` blocks inside one `<function_calls>`.)\n\n---\n\n## Tool-result format\n\nA result is a `tool_result` block inside a `user` message:\n\n- `tool_use_id` (required) — the `id` of the `tool_use` it answers.\n- `content` (optional) — a string, **or** an array of `text`/`image`/`document` blocks. Omit for an empty result.\n- `is_error` (optional) — `true` for execution failures; put a useful message in `content`.\n\n```json\n{\n  \"role\": \"user\",\n  \"content\": [\n    {\n      \"type\": \"tool_result\",\n      \"tool_use_id\": \"toolu_01A09q90qw90lq917835lq9\",\n      \"content\": \"15 degrees\"\n    }\n  ]\n}\n```\n\nError result:\n\n```json\n{\n  \"role\": \"user\",\n  \"content\": [\n    {\n      \"type\": \"tool_result\",\n      \"tool_use_id\": \"toolu_01A09q90qw90lq917835lq9\",\n      \"content\": \"ConnectionError: the weather service API is not available (HTTP 500)\",\n      \"is_error\": true\n    }\n  ]\n}\n```\n\nRich result (text + image blocks):\n\n```json\n{\n  \"role\": \"user\",\n  \"content\": [\n    {\n      \"type\": \"tool_result\",\n      \"tool_use_id\": \"toolu_01A09q90qw90lq917835lq9\",\n      \"content\": [\n        { \"type\": \"text\", \"text\": \"15 degrees\" },\n        {\n          \"type\": \"image\",\n          \"source\": { \"type\": \"base64\", \"media_type\": \"image/jpeg\", \"data\": \"/9j/4AAQSkZJRg...\" }\n        }\n      ]\n    }\n  ]\n}\n```\n\nServer tools require **no** `tool_result` from you — Anthropic executes them and injects the result inline in the assistant turn. (Legacy XML feeds results back as `<function_results><result><tool_name>…</tool_name><stdout>…</stdout></result></function_results>`, or `<error>…</error>` on failure.)\n\n---\n\n## End-to-end example\n\nA complete multi-turn weather exchange. All JSON is valid.\n\n**Request 1 — system + tools + user question:**\n\n```json\n{\n  \"model\": \"claude-opus-4-8\",\n  \"max_tokens\": 1024,\n  \"system\": \"You are a helpful weather assistant. Use the provided tools to answer.\",\n  \"tools\": [\n    {\n      \"name\": \"get_weather\",\n      \"description\": \"Get the current weather in a given location\",\n      \"input_schema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"location\": { \"type\": \"string\", \"description\": \"The city and state, e.g. San Francisco, CA\" },\n          \"unit\": { \"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"], \"description\": \"Unit for the temperature\" }\n        },\n        \"required\": [\"location\"]\n      }\n    }\n  ],\n  \"messages\": [\n    { \"role\": \"user\", \"content\": \"What's the weather in San Francisco?\" }\n  ]\n}\n```\n\n**Response 1 — assistant requests the tool (`stop_reason: \"tool_use\"`):**\n\n```json\n{\n  \"id\": \"msg_01Aq9w938a90dw8q\",\n  \"type\": \"message\",\n  \"role\": \"assistant\",\n  \"model\": \"claude-opus-4-8\",\n  \"content\": [\n    { \"type\": \"text\", \"text\": \"I'll check the current weather in San Francisco for you.\" },\n    {\n      \"type\": \"tool_use\",\n      \"id\": \"toolu_01A09q90qw90lq917835lq9\",\n      \"name\": \"get_weather\",\n      \"input\": { \"location\": \"San Francisco, CA\", \"unit\": \"celsius\" }\n    }\n  ],\n  \"stop_reason\": \"tool_use\",\n  \"stop_sequence\": null,\n  \"usage\": { \"input_tokens\": 472, \"output_tokens\": 65 }\n}\n```\n\n**Request 2 — replay history, append the assistant turn and the `tool_result`:**\n\n```json\n{\n  \"model\": \"claude-opus-4-8\",\n  \"max_tokens\": 1024,\n  \"system\": \"You are a helpful weather assistant. Use the provided tools to answer.\",\n  \"tools\": [\n    {\n      \"name\": \"get_weather\",\n      \"description\": \"Get the current weather in a given location\",\n      \"input_schema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"location\": { \"type\": \"string\", \"description\": \"The city and state, e.g. San Francisco, CA\" },\n          \"unit\": { \"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"], \"description\": \"Unit for the temperature\" }\n        },\n        \"required\": [\"location\"]\n      }\n    }\n  ],\n  \"messages\": [\n    { \"role\": \"user\", \"content\": \"What's the weather in San Francisco?\" },\n    {\n      \"role\": \"assistant\",\n      \"content\": [\n        { \"type\": \"text\", \"text\": \"I'll check the current weather in San Francisco for you.\" },\n        {\n          \"type\": \"tool_use\",\n          \"id\": \"toolu_01A09q90qw90lq917835lq9\",\n          \"name\": \"get_weather\",\n          \"input\": { \"location\": \"San Francisco, CA\", \"unit\": \"celsius\" }\n        }\n      ]\n    },\n    {\n      \"role\": \"user\",\n      \"content\": [\n        {\n          \"type\": \"tool_result\",\n          \"tool_use_id\": \"toolu_01A09q90qw90lq917835lq9\",\n          \"content\": \"15 degrees Celsius, partly cloudy\"\n        }\n      ]\n    }\n  ]\n}\n```\n\n**Response 2 — assistant's final answer (`stop_reason: \"end_turn\"`):**\n\n```json\n{\n  \"id\": \"msg_01EeFG3hijk2lmno4PqrSt\",\n  \"type\": \"message\",\n  \"role\": \"assistant\",\n  \"model\": \"claude-opus-4-8\",\n  \"content\": [\n    { \"type\": \"text\", \"text\": \"It's currently 15 degrees Celsius and partly cloudy in San Francisco.\" }\n  ],\n  \"stop_reason\": \"end_turn\",\n  \"stop_sequence\": null,\n  \"usage\": { \"input_tokens\": 530, \"output_tokens\": 18 }\n}\n```\n\n### Streaming (SSE) shape of the tool call\n\nThe same tool call, streamed. Note `tool_use` opens with an empty `input`, the arguments arrive as `input_json_delta.partial_json` fragments, and the final `stop_reason` lands in `message_delta`. This block is reproduced verbatim from Anthropic's streaming docs:\n\n```text\nevent: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"msg_014p7gG3wDgGV9EUtLvnow3U\",\"type\":\"message\",\"role\":\"assistant\",\"model\":\"claude-opus-4-8\",\"stop_sequence\":null,\"usage\":{\"input_tokens\":472,\"output_tokens\":2},\"content\":[],\"stop_reason\":null}}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":0,\"content_block\":{\"type\":\"text\",\"text\":\"\"}}\n\nevent: ping\ndata: {\"type\": \"ping\"}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"Okay\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" let\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"'s\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\" check\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":0}\n\nevent: content_block_start\ndata: {\"type\":\"content_block_start\",\"index\":1,\"content_block\":{\"type\":\"tool_use\",\"id\":\"toolu_01T1x1fJ34qAmk2tNTrN7Up6\",\"name\":\"get_weather\",\"input\":{}}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"{\\\"location\\\":\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\" \\\"San\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\" Francisc\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\"o,\"}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":1,\"delta\":{\"type\":\"input_json_delta\",\"partial_json\":\" CA\\\"}\"}}\n\nevent: content_block_stop\ndata: {\"type\":\"content_block_stop\",\"index\":1}\n\nevent: message_delta\ndata: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"tool_use\",\"stop_sequence\":null},\"usage\":{\"output_tokens\":89}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n```\n\nReassembly: concatenate every `partial_json` for a given `index` (`\"\" + \"{\\\"location\\\":\" + \" \\\"San\" + \" Francisc\" + \"o,\" + \" CA\\\"}\"` → `{\"location\": \"San Francisco, CA\"}`), then `JSON.parse` at that block's `content_block_stop`. Tool use also supports fine-grained streaming (`eager_input_streaming` per tool) for finer `partial_json` chunking.\n\n---\n\n## OpenAI-compatible API mapping\n\nAnthropic integrates tools into the `user`/`assistant` message structure rather than using OpenAI's separate `tool` role and `function` wrapper. Field-by-field:\n\n| Concept | Anthropic Messages API | OpenAI Chat Completions |\n| --- | --- | --- |\n| Tool definition wrapper | flat `{\"name\",\"description\",\"input_schema\"}` in `tools[]` | `{\"type\":\"function\",\"function\":{\"name\",\"description\",\"parameters\"}}` in `tools[]` |\n| Tool schema key | `input_schema` (JSON Schema) | `parameters` (JSON Schema) |\n| \"Must call a tool\" | `tool_choice:{\"type\":\"any\"}` / `{\"type\":\"tool\",\"name\":…}` | `tool_choice:\"required\"` / `{\"type\":\"function\",\"function\":{\"name\":…}}` |\n| Disable parallel calls | `tool_choice:{…,\"disable_parallel_tool_use\":true}` | `parallel_tool_calls:false` (top level) |\n| Assistant call container | `tool_use` **content block** in `content[]` | `tool_calls[]` on the assistant `message` |\n| Call id | `tool_use.id` = `toolu_…` | `tool_calls[].id` = `call_…` |\n| Function name | `tool_use.name` | `tool_calls[].function.name` |\n| Function arguments | `tool_use.input` = **nested JSON object** (parsed) | `tool_calls[].function.arguments` = **JSON string** (must `JSON.parse`) |\n| \"Tools were called\" signal | `stop_reason:\"tool_use\"` | `finish_reason:\"tool_calls\"` |\n| Result message role | `user` message containing `tool_result` block(s) | dedicated `{\"role\":\"tool\",…}` message(s) |\n| Result ↔ call linkage | `tool_result.tool_use_id` | `tool` message `tool_call_id` |\n| Result payload | `tool_result.content` = string **or** block array (text/image/document) | `tool` message `content` = string |\n| Error result | `tool_result` with `is_error:true` | no dedicated flag; encode in `content` |\n| System prompt | top-level `system` param (no `system` role) | `{\"role\":\"system\",…}` message |\n| Streamed args | `input_json_delta.partial_json` fragments | `tool_calls[].function.arguments` string deltas |\n\nConversion gotchas:\n- **Object vs string:** to emit OpenAI shape, `JSON.stringify(tool_use.input)`; to consume OpenAI shape into Anthropic, `JSON.parse(arguments)`.\n- **Role reshaping:** collapse N OpenAI `tool` messages into one Anthropic `user` message of N `tool_result` blocks (order them before any text), and vice-versa.\n- **No `type:\"function\"`** wrapper on Anthropic custom tools; add/remove it when translating.\n- Id prefixes differ (`toolu_` vs `call_`); never assume one format's id is valid in the other.\n\n---\n\n## Parsing notes & gotchas\n\n- **`input` is an object, not a string.** Unlike OpenAI's `arguments`, do not `JSON.parse` `tool_use.input` from a non-streamed response — it is already an object. Only the *streaming* `partial_json` fragments are strings.\n- **Streaming tool args need reassembly.** `content_block_start` for a `tool_use` always has `input: {}`. Buffer `partial_json` per `index` and parse only at `content_block_stop`; mid-stream fragments are not valid JSON on their own (e.g. `{\"location\":`). Current models emit one complete key/value at a time, so expect bursts and gaps.\n- **`stop_reason` placement.** In streaming, `stop_reason` is `null` in `message_start` and final value (`\"tool_use\"`/`\"end_turn\"`) arrives in `message_delta`, not `message_stop`. `usage` in `message_delta` is **cumulative**.\n- **Ordering is enforced.** `tool_result` blocks must be first in their `user` message and must immediately follow the assistant `tool_use` message; every `tool_use.id` needs a matching `tool_result.tool_use_id`, or you get HTTP 400 (\"tool_use ids were found without tool_result blocks immediately after\").\n- **`tool_choice:any`/`tool` suppress preamble.** The API prefills the assistant turn, so no leading `text` block appears before `tool_use` — don't write a parser that expects explanatory text.\n- **Parallel results in one message.** Splitting parallel `tool_result`s across multiple `user` messages breaks the contract; send them together.\n- **Treat result content as untrusted.** Tool results can carry indirect prompt injection; keep them inside `tool_result` blocks, never promote to `system`/`user` text.\n- **Server tools differ.** `server_tool_use` / `web_search_tool_result` blocks are produced and consumed by Anthropic; never synthesize `tool_result` for them. `stop_reason:\"pause_turn\"` means resend the response as-is to let a long server-tool turn continue.\n- **Extended thinking + tools.** Preserve `thinking`/`redacted_thinking` blocks (with their `signature`) verbatim across turns; forced `tool_choice` (`any`/`tool`) is rejected when thinking is on.\n- **Output is not valid XML.** The underlying model output is parsed by Anthropic with regular expressions, not an XML parser (\"The output is not expected to be valid XML\"). If you reconstruct prompts at token level, do not assume well-formedness; rely on the JSON the API returns.\n- **Legacy vs modern XML are different tag sets.** Legacy: `<invoke>` + child `<tool_name>` + `<parameters>` with per-name child tags; results in `<function_results>/<result>/<stdout>`. Modern: `<invoke name=\"…\">` + `<parameter name=\"…\">`. Mixing them up will misparse. The legacy format also required passing `</function_calls>` as a `stop_sequence` and is not optimized for Claude 3+.\n\n### Legacy XML format (secondary, prompt-based — fully verified, now retired)\n\nBefore the Messages API, tools were defined and called entirely in the prompt. Anthropic's archived \"Legacy tool use\" doc specifies it verbatim.\n\nTool definition (inside a `<tools>` block in the system prompt):\n\n```text\n<tool_description>\n<tool_name>get_weather</tool_name>\n<description>\nRetrieves the current weather for a specified location.\nReturns a dictionary with two fields:\n- temperature: float, the current temperature in Fahrenheit\n- conditions: string, a brief description of the current weather conditions\nRaises ValueError if the provided location cannot be found.\n</description>\n<parameters>\n<parameter>\n<name>location</name>\n<type>string</type>\n<description>The city and state, e.g. San Francisco, CA</description>\n</parameter>\n</parameters>\n</tool_description>\n```\n\nModel-emitted call (multiple `<invoke>` for parallel calls; pass `</function_calls>` as a `stop_sequence`):\n\n```text\n<function_calls>\n<invoke>\n<tool_name>get_weather</tool_name>\n<parameters>\n<location>San Francisco, CA</location>\n</parameters>\n</invoke>\n</function_calls>\n```\n\nResult fed back into the next user turn:\n\n```text\n<function_results>\n<result>\n<tool_name>get_weather</tool_name>\n<stdout>\n59 degrees Fahrenheit, partly cloudy\n</stdout>\n</result>\n</function_results>\n```\n\nError result:\n\n```text\n<function_results>\n<error>\nerror message goes here\n</error>\n</function_results>\n```\n\nThe legacy system-prompt preamble (verbatim from the archived doc) was:\n\n```text\nIn this environment you have access to a set of tools you can use to answer the user's question.\nYou may call them like this:\n<function_calls>\n<invoke>\n<tool_name>$TOOL_NAME</tool_name>\n<parameters>\n<$PARAMETER_NAME>$PARAMETER_VALUE</$PARAMETER_NAME>\n...\n</parameters>\n</invoke>\n</function_calls>\n\nHere are the tools available:\n<tools>\n...one <tool_description> per tool...\n</tools>\n```\n\nLegacy notes: no built-in tools (everything is prompt-defined); Anthropic recommended ≤3–5 tools; the model conventionally wrapped reasoning in `<scratchpad>` and final output in `<answer>`. This format is \"out of date\" and \"not optimized for Claude 3\" — use the JSON Messages API for anything current.\n\n---\n\n## Sources\n\n- Tool use overview — https://docs.claude.com/en/docs/agents-and-tools/tool-use/overview\n- How tool use works — https://docs.claude.com/en/docs/agents-and-tools/tool-use/how-tool-use-works\n- Define tools (tool schema, `input_schema`, `tool_choice`, constructed system prompt) — https://docs.claude.com/en/docs/agents-and-tools/tool-use/define-tools\n- Handle tool calls (`tool_use`/`tool_result`, `is_error`, ordering rules) — https://docs.claude.com/en/docs/agents-and-tools/tool-use/handle-tool-calls\n- Parallel tool use — https://docs.claude.com/en/docs/agents-and-tools/tool-use/parallel-tool-use\n- Streaming messages (SSE events, `input_json_delta`, verbatim tool-use stream) — https://docs.claude.com/en/docs/build-with-claude/streaming\n- Messages API reference (`stop_reason` enum, response shape, `tools`) — https://docs.claude.com/en/api/messages\n- Legacy tool use (archived; verbatim XML tags and prompt) — https://web.archive.org/web/20240528231249/https://docs.anthropic.com/en/docs/legacy-tool-use ; also live localized copies, e.g. https://docs.anthropic.com/de/docs/legacy-tool-use (English path now redirects to the tool-use overview)\n",
 	"toolconv/deepseek.md": "# DeepSeek tool-calling wire format\n\nDeepSeek's chat models (DeepSeek-V3, V3-0324, R1, R1-0528, and DeepSeek-V3.1) share a\nsingle tokenizer family and a distinctive envelope built from **fullwidth-pipe** special\ntokens such as `<｜begin▁of▁sentence｜>` and `<｜User｜>`. Tool calling is emitted as a run\nof dedicated special tokens (`<｜tool▁calls▁begin｜>` … `<｜tool▁calls▁end｜>`) rather than\nJSON-in-text or XML. This document centers on **DeepSeek-V3.1** (the current hybrid\nthinking/non-thinking model) and documents the older **DeepSeek-V3-0324** and\n**DeepSeek-R1-0528** format as an explicit version difference, because their on-the-wire\ntool syntax is *not* the same as V3.1's.\n\nAn inference server enables it with a chat template plus a tool-call parser:\n\n- vLLM V3.1: `--enable-auto-tool-choice --tool-call-parser deepseek_v31 --chat-template examples/tool_chat_template_deepseekv31.jinja` (optionally `--reasoning-parser deepseek_r1`).\n- vLLM V3-0324 / R1-0528: `--enable-auto-tool-choice --tool-call-parser deepseek_v3 --chat-template examples/tool_chat_template_deepseekv3.jinja` (V3-0324) or `tool_chat_template_deepseekr1.jinja` (R1-0528).\n- The model's own `tokenizer_config.json` `chat_template` (and the identical `assets/chat_template.jinja`) renders the V3.1 envelope, tool calls, and tool outputs; it does **not** synthesize the `## Tools` advertisement block, so vLLM ships a template that does (see below).\n\n> Verified against: the DeepSeek-V3.1 model card \"Chat Template\" / \"ToolCall\" sections, the\n> byte-identical `chat_template` in `tokenizer_config.json` and `assets/chat_template.jinja`,\n> the `added_tokens` in `tokenizer.json` (token IDs), `config.json` (bos/eos IDs), the\n> DeepSeek-V3-0324 and DeepSeek-R1-0528 `tokenizer_config.json` chat templates, the vLLM\n> `tool_chat_template_deepseekv31.jinja`, and the vLLM tool-calling / reasoning-outputs docs.\n\n## A note on the unusual Unicode (do not substitute ASCII)\n\nDeepSeek's markers do **not** use the ASCII vertical bar `|` (U+007C) or ASCII underscore\n`_`. They use:\n\n- `｜` — **U+FF5C FULLWIDTH VERTICAL LINE**, as the delimiter just inside the angle brackets.\n- `▁` — **U+2581 LOWER ONE EIGHTH BLOCK** (the SentencePiece word-boundary glyph), as the\n  separator *between words* inside a token, e.g. `begin▁of▁sentence`, `tool▁calls▁begin`.\n\nSo `<｜tool▁calls▁begin｜>` is `<` + `｜`(FF5C) + `tool` + `▁`(2581) + `calls` + `▁`(2581) +\n`begin` + `｜`(FF5C) + `>`. Copying these tokens as `<|tool_calls_begin|>` (ASCII pipe +\nunderscore) produces tokens the model never trained on and will silently break parsing and\ngeneration. The only DeepSeek markers that use ASCII brackets are the thinking tags\n`<think>` / `</think>` (plain `<`, `/`, `>`) and the rarely used `<|EOT|>` (ASCII pipes).\n\n## Special tokens\n\nToken IDs are from DeepSeek-V3.1 `tokenizer.json` (`added_tokens`); `vocab_size` is 129280.\nThe `special` column reflects the tokenizer's `\"special\"` flag (it governs\n`skip_special_tokens`); note that the role/think/tool markers are `special: false`.\n\n| Token (verbatim) | ID | `special` | Purpose |\n| --- | --- | --- | --- |\n| `<｜begin▁of▁sentence｜>` | 0 | true | BOS; prepended once at the very start of the prompt. |\n| `<｜end▁of▁sentence｜>` | 1 | true | EOS; ends every assistant/tool turn and is the stop token. |\n| `<｜▁pad▁｜>` | 2 | true | Padding (`pad_token`; the model card/config also reuse EOS as pad). |\n| `<｜search▁begin｜>` | 128796 | false | Search-agent query open (thinking-mode search tool). |\n| `<｜search▁end｜>` | 128797 | false | Search-agent query close. |\n| `<think>` | 128798 | false | Opens the reasoning/thinking span. ASCII brackets. |\n| `</think>` | 128799 | false | Closes the reasoning span; **also emitted in non-thinking mode** (see below). |\n| `<｜fim▁hole｜>` / `<｜fim▁begin｜>` / `<｜fim▁end｜>` | 128800–128802 | false | Fill-in-the-middle (not chat). |\n| `<｜User｜>` | 128803 | false | User role marker. |\n| `<｜Assistant｜>` | 128804 | false | Assistant role marker. |\n| `<\\|EOT\\|>` | 128805 | true | End-of-turn (legacy; ASCII pipes, rarely used in chat). |\n| `<｜tool▁calls▁begin｜>` | 128806 | false | Opens the assistant's batch of tool calls. |\n| `<｜tool▁calls▁end｜>` | 128807 | false | Closes the batch of tool calls. |\n| `<｜tool▁call▁begin｜>` | 128808 | false | Opens a single tool call inside the batch. |\n| `<｜tool▁call▁end｜>` | 128809 | false | Closes a single tool call. |\n| `<｜tool▁outputs▁begin｜>` | 128810 | false | Opens a batch of tool results (**R1-0528 / V3-0324 only**). |\n| `<｜tool▁outputs▁end｜>` | 128811 | false | Closes a batch of tool results (**R1-0528 / V3-0324 only**). |\n| `<｜tool▁output▁begin｜>` | 128812 | false | Opens a single tool result. |\n| `<｜tool▁output▁end｜>` | 128813 | false | Closes a single tool result. |\n| `<｜tool▁sep｜>` | 128814 | false | Separator inside a tool call (between name and arguments). |\n\n`config.json` confirms `bos_token_id: 0`, `eos_token_id: 1`.\n\n## Roles / channels / turn structure\n\nThere is no OpenAI-style `system`/`developer` channel token. Roles are inline markers and\nthe prompt is one flat string:\n\n```text\n<｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{query}<｜Assistant｜>{response}<｜end▁of▁sentence｜>\n```\n\n- **System prompt** has no marker. All `system` messages are concatenated (joined with\n  `\\n\\n` when there are several) and emitted immediately after `<｜begin▁of▁sentence｜>`,\n  before the first `<｜User｜>`. When tools are present the `## Tools` block is appended to\n  this system text (separated by `\\n\\n`).\n- **User turn**: `<｜User｜>` + content. (No EOS after the user text in V3.1; the assistant\n  marker follows directly.)\n- **Assistant turn**: opens with `<｜Assistant｜>`, then a thinking tag, then content, then\n  `<｜end▁of▁sentence｜>`.\n- **Thinking vs non-thinking (V3.1 hybrid)** — selected by the template, not by the model:\n  - Non-thinking generation prefix: `…<｜Assistant｜></think>` — the model starts *after* a\n    `</think>` it never had to open. Unlike DeepSeek-V3, V3.1 always injects this `</think>`.\n  - Thinking generation prefix: `…<｜Assistant｜><think>` — the model emits its chain of\n    thought, closes with `</think>`, then the answer.\n  - In multi-turn context, **every** stored assistant turn keeps a `</think>`; only the last\n    turn's leading thinking tag reflects the requested mode. When rendering a stored\n    assistant message, any text up to and including `</think>` is stripped from `content`\n    before re-emitting (the template does `content.split('</think>', 1)[1]`).\n- **Tool calling runs in non-thinking mode.** The model card states \"Toolcall is supported\n  in non-thinking mode,\" and the V3.1 tool template opens the tool-call turn with\n  `<｜Assistant｜></think>`. With vLLM, V3.1 reasoning is disabled by default; enable it via\n  `chat_template_kwargs={\"thinking\": true}`.\n- **Search-agent channel**: a separate thinking-mode protocol using `<｜search▁begin｜>` /\n  `<｜search▁end｜>` (see the model card's `assets/search_tool_trajectory.html`); out of\n  scope for ordinary function calling.\n\n## Tool definitions\n\nTools are advertised as a **Markdown block injected into the system area** (after the system\nprompt, before the first `<｜User｜>`). The chat template in `tokenizer_config.json` does not\nbuild this block from a `tools=[…]` argument; the caller (or vLLM's\n`tool_chat_template_deepseekv31.jinja`) constructs it. Reproduced verbatim from the\nDeepSeek-V3.1 model card, the full layout is\n`<｜begin▁of▁sentence｜>{system prompt}\\n\\n{tool_description}<｜User｜>{query}<｜Assistant｜></think>`\nwhere `{tool_description}` is:\n\n```text\n## Tools\nYou have access to the following tools:\n\n### {tool_name1}\nDescription: {description}\n\nParameters: {json.dumps(parameters)}\n\nIMPORTANT: ALWAYS adhere to this exact format for tool use:\n<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>tool_call_name<｜tool▁sep｜>tool_call_arguments<｜tool▁call▁end｜>{additional_tool_calls}<｜tool▁calls▁end｜>\n\nWhere:\n- `tool_call_name` must be an exact match to one of the available tools\n- `tool_call_arguments` must be valid JSON that strictly follows the tool's Parameters Schema\n- For multiple tool calls, chain them directly without separators or spaces\n```\n\nEach tool contributes one `### {name}` section with a `Description:` line and a\n`Parameters: {…}` line whose value is the compact JSON of the JSON-Schema parameters object\n(`json.dumps(parameters)` in the card, `parameters | tojson` in vLLM's template). The\n`IMPORTANT:` instruction block is appended once, after the last tool.\n\n## Tool-call format\n\nThe model emits one batch wrapper containing one or more calls. Each call is\n`name <｜tool▁sep｜> arguments`, where **arguments is a raw JSON object string** (no code\nfence). Minimal single call (what the model generates after the `<｜Assistant｜></think>`\nprefix):\n\n```text\n<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>get_weather<｜tool▁sep｜>{\"location\": \"San Francisco, CA\"}<｜tool▁call▁end｜><｜tool▁calls▁end｜>\n```\n\nGrammar (V3.1):\n\n```text\n<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>{name}<｜tool▁sep｜>{json_args}<｜tool▁call▁end｜>{…more calls…}<｜tool▁calls▁end｜>\n```\n\n- `{name}` must exactly match an advertised tool name. It comes **first**, immediately after\n  `<｜tool▁call▁begin｜>`.\n- `{json_args}` is valid JSON conforming to the tool's parameter schema, inlined directly.\n- The whole assistant turn is then closed by the template/server with\n  `<｜end▁of▁sentence｜>`.\n\n(V3.1 has **no** `type` field and **no** ` ```json ` fence around arguments — that is the\nolder R1/V3-0324 convention; see Version differences.)\n\n## Multiple / parallel tool calls\n\nAll calls live inside one `<｜tool▁calls▁begin｜>…<｜tool▁calls▁end｜>` wrapper. After the\nfirst `<｜tool▁call▁begin｜>…<｜tool▁call▁end｜>`, each additional call is **another\n`<｜tool▁call▁begin｜>…<｜tool▁call▁end｜>` chained directly, with no separator, newline, or\nspace between calls** (the card: \"chain them directly without separators or spaces\"):\n\n```text\n<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>get_weather<｜tool▁sep｜>{\"location\": \"San Francisco, CA\"}<｜tool▁call▁end｜><｜tool▁call▁begin｜>get_weather<｜tool▁sep｜>{\"location\": \"Seattle, WA\"}<｜tool▁call▁end｜><｜tool▁calls▁end｜>\n```\n\nNote that `<｜tool▁calls▁begin｜>` (plural, id 128806) appears exactly once; each call uses\nthe singular `<｜tool▁call▁begin｜>` (id 128808) / `<｜tool▁call▁end｜>` (id 128809).\n\n## Tool-result format\n\nExecuted results are fed back as `tool`-role messages. In **V3.1** each result is wrapped in\nthe singular output tokens, with **no** plural `<｜tool▁outputs▁…｜>` wrapper, emitted right\nafter the assistant tool-call turn's `<｜end▁of▁sentence｜>`:\n\n```text\n<｜tool▁output▁begin｜>{result_text}<｜tool▁output▁end｜>\n```\n\n`{result_text}` is the raw tool output (typically a JSON string, but any text). For multiple\nresults, the V3.1 template emits one `<｜tool▁output▁begin｜>…<｜tool▁output▁end｜>` per `tool`\nmessage, concatenated directly. There is **no tool-call ID in the wire format** — results are\nmatched to calls **positionally** (order of outputs ↔ order of calls).\n\nThe model then produces its final answer **directly after `<｜tool▁output▁end｜>`** with no\n`<｜Assistant｜>` marker and no `</think>` (see Parsing notes — the V3.1 reference template\ndeliberately renders post-tool assistant content as just `content<｜end▁of▁sentence｜>`).\n\n> R1-0528 / V3-0324 differ: results are enclosed in a `<｜tool▁outputs▁begin｜>` …\n> `<｜tool▁outputs▁end｜>` batch wrapper, with each result as\n> `<｜tool▁output▁begin｜>…<｜tool▁output▁end｜>` and multiple results newline-separated.\n\n## End-to-end example\n\nA complete DeepSeek-V3.1 **non-thinking** multi-turn exchange. Everything is one flat string;\ninline `←` comments mark where the model's generation begins (they are not part of the\nstream). Whitespace inside the `## Tools` block is literal newlines.\n\n```text\n<｜begin▁of▁sentence｜>You are a helpful assistant.\n\n## Tools\nYou have access to the following tools:\n\n### get_weather\nDescription: Get the current weather for a location\n\nParameters: {\"type\": \"object\", \"properties\": {\"location\": {\"type\": \"string\", \"description\": \"City and state, e.g. San Francisco, CA\"}, \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]}}, \"required\": [\"location\"]}\n\nIMPORTANT: ALWAYS adhere to this exact format for tool use:\n<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>tool_call_name<｜tool▁sep｜>tool_call_arguments<｜tool▁call▁end｜>{additional_tool_calls}<｜tool▁calls▁end｜>\n\nWhere:\n- `tool_call_name` must be an exact match to one of the available tools\n- `tool_call_arguments` must be valid JSON that strictly follows the tool's Parameters Schema\n- For multiple tool calls, chain them directly without separators or spaces\n<｜User｜>What's the weather in San Francisco?<｜Assistant｜></think><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>get_weather<｜tool▁sep｜>{\"location\": \"San Francisco, CA\", \"unit\": \"celsius\"}<｜tool▁call▁end｜><｜tool▁calls▁end｜><｜end▁of▁sentence｜><｜tool▁output▁begin｜>{\"temperature\": 18, \"unit\": \"celsius\", \"condition\": \"Foggy\"}<｜tool▁output▁end｜>It's currently 18°C and foggy in San Francisco.<｜end▁of▁sentence｜>\n```\n\nReading the spans:\n\n1. `<｜begin▁of▁sentence｜>` + system text + `\\n\\n` + `## Tools…` block — prompt prefix.\n2. `<｜User｜>What's the weather in San Francisco?` — user turn.\n3. `<｜Assistant｜></think>` — non-thinking generation prefix (prompt). **Model generates from here.**\n4. `<｜tool▁calls▁begin｜>…<｜tool▁calls▁end｜>` — the model's tool call; server appends `<｜end▁of▁sentence｜>` and stops with `finish_reason: \"tool_calls\"`.\n5. `<｜tool▁output▁begin｜>…<｜tool▁output▁end｜>` — your executed result, appended to the prompt.\n6. `It's currently 18°C and foggy in San Francisco.<｜end▁of▁sentence｜>` — **the model generates the final answer directly after the tool output** (no new `<｜Assistant｜>` marker), ending with EOS.\n\n## OpenAI-compatible API mapping\n\nWhen fronted by an OpenAI-compatible server (e.g. vLLM with `--tool-call-parser\ndeepseek_v31`):\n\n- **`finish_reason`**: `\"tool_calls\"` when the model emitted a `<｜tool▁calls▁begin｜>…`\n  batch; otherwise `\"stop\"`.\n- **`message.tool_calls[]`**: one element per `<｜tool▁call▁begin｜>…<｜tool▁call▁end｜>`.\n  - `.type` = `\"function\"`.\n  - `.function.name` = the text between `<｜tool▁call▁begin｜>` and `<｜tool▁sep｜>`.\n  - `.function.arguments` = the text between `<｜tool▁sep｜>` and `<｜tool▁call▁end｜>`, returned\n    as a **JSON string** (per the OpenAI spec), not a nested object. The model already emits\n    raw JSON there, so it is passed through.\n  - `.id` = **synthesized by the server** (e.g. `chatcmpl-tool-…`). DeepSeek's wire format\n    carries no call ID.\n- **Tool result messages**: `{\"role\": \"tool\", \"tool_call_id\": \"<id>\", \"content\": \"<result>\"}`.\n  The server renders `content` into `<｜tool▁output▁begin｜>…<｜tool▁output▁end｜>`. Because the\n  prompt has no IDs, `tool_call_id` is used only for client-side bookkeeping; **the model\n  relies on ordering**, so preserve the order of results relative to the calls.\n- **Assistant replay**: when you send a prior assistant turn back with `tool_calls`, the\n  template inlines `function.arguments`. The HF reference template inlines it **verbatim**\n  (assumes it is already a JSON string); vLLM's `tool_chat_template_deepseekv31.jinja` pipes\n  it through `| tojson`. Send `arguments` as a JSON **string** per the OpenAI spec (see the\n  gotcha below about double-encoding).\n\n## Parsing notes & gotchas\n\n- **Unicode is load-bearing.** Match `｜` = U+FF5C and `▁` = U+2581 exactly. ASCII\n  `<|tool_calls_begin|>` will not tokenize to the special tokens. `<think>`/`</think>` use\n  ASCII brackets; the rare `<|EOT|>` uses ASCII pipes.\n- **Tool/role markers are `special: false`.** Only `<｜begin▁of▁sentence｜>`,\n  `<｜end▁of▁sentence｜>`, `<｜▁pad▁｜>`, and `<|EOT|>` are flagged `special: true`. So\n  decoding with `skip_special_tokens=True` will **not** strip `<｜tool▁calls▁begin｜>`,\n  `<｜tool▁sep｜>`, `<｜Assistant｜>`, `</think>`, etc. — they remain in the decoded string for\n  the parser to find. (Conversely, do not assume special-token filtering removes them.)\n- **No code fence / no `type` field in V3.1.** A parser written for R1/V3-0324\n  (`function<｜tool▁sep｜>name` + ` ```json ` block) will not parse V3.1, and vice-versa.\n  V3.1 is `name<｜tool▁sep｜>raw_json`.\n- **Chaining has no delimiter in V3.1.** Calls abut directly:\n  `…<｜tool▁call▁end｜><｜tool▁call▁begin｜>…`. Do not split on newlines/whitespace; split on\n  the `<｜tool▁call▁begin｜>` / `<｜tool▁call▁end｜>` boundaries. (R1/V3-0324 put a `\\n` before\n  each subsequent call.)\n- **No tool-call IDs on the wire.** Match results to calls by position. A server must\n  generate synthetic `tool_call_id`s for the OpenAI shape.\n- **`</think>` appears even in non-thinking mode.** Strip the leading `</think>` (and any\n  preceding reasoning) before treating the remainder as the visible answer; the template does\n  `content.split('</think>', 1)[1]` when replaying stored turns.\n- **Post-tool generation prompt quirk.** The reference V3.1 chat template only appends the\n  `<｜Assistant｜></think>` generation prefix when the **last message is `user`**. After a\n  `tool` message it appends nothing and the model continues straight after\n  `<｜tool▁output▁end｜>`. Agent loops that re-template a conversation ending in a tool result\n  must not expect (or double-insert) an assistant marker there.\n- **`arguments` double-encoding risk.** On replay, vLLM's example template applies\n  `arguments | tojson`. If `arguments` is already a JSON string (the OpenAI convention), that\n  pipe will JSON-encode the string again (wrapping it in quotes and escaping it). Pass an\n  object where the template expects `| tojson`, or a string where the template inlines\n  verbatim — match the template you actually run.\n- **Streaming.** Tool calls arrive token-by-token; the name is complete only at\n  `<｜tool▁sep｜>`, and arguments are partial JSON until `<｜tool▁call▁end｜>`. Buffer per call\n  boundary; do not attempt to `json.loads` arguments before the closing tool-call token.\n- **Malformed output.** With `tool_choice=\"auto\"` and no structural-tag constraint\n  (`VLLM_ENFORCE_STRICT_TOOL_CALLING=false`), the model can emit invalid JSON in\n  `tool_call_arguments` or a `tool_call_name` that does not match any tool; the parser\n  extracts best-effort. Named/`required` tool choice uses the structured-outputs backend and\n  guarantees schema-valid arguments.\n\n## Version differences: V3.1 vs V3-0324 / R1-0528\n\nThe pre-V3.1 models (DeepSeek-V3-0324 and DeepSeek-R1-0528) share an older tool-call\nencoding, served in vLLM with `--tool-call-parser deepseek_v3`. The per-call body is:\n\n````text\n<｜tool▁call▁begin｜>function<｜tool▁sep｜>{name}\n```json\n{json_args}\n```<｜tool▁call▁end｜>\n````\n\nDifferences from V3.1:\n\n| Aspect | V3.1 (`deepseek_v31`) | V3-0324 / R1-0528 (`deepseek_v3`) |\n| --- | --- | --- |\n| Field order in a call | `{name}<｜tool▁sep｜>{args}` | `function<｜tool▁sep｜>{name}` (the literal `type`, then name) |\n| Arguments wrapping | raw JSON, inline | fenced ` ```json … ``` ` block (name and args separated by `\\n`) |\n| Chaining of calls | abut directly, **no separator** | each subsequent call prefixed with `\\n` |\n| Tool results | `<｜tool▁output▁begin｜>…<｜tool▁output▁end｜>` per message, no batch wrapper | wrapped in `<｜tool▁outputs▁begin｜>…<｜tool▁outputs▁end｜>`, results newline-separated |\n| User→assistant boundary | user turn = `<｜User｜>{q}`; `<｜Assistant｜></think>` added at generation | user turn = `<｜User｜>{q}<｜Assistant｜>` (assistant marker appended in the user branch) |\n| Thinking | hybrid; `thinking` kwarg toggles `<think>` vs `</think>` prefix | R1-0528 always reasoning (bare `<｜Assistant｜>` generation prefix, model opens `<think>` itself); V3-0324 non-reasoning |\n| vLLM parser | `--tool-call-parser deepseek_v31` | `--tool-call-parser deepseek_v3` |\n\nExample R1-0528 / V3-0324 parallel call with its result batch:\n\n````text\n<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>function<｜tool▁sep｜>get_weather\n```json\n{\"location\": \"San Francisco, CA\"}\n```<｜tool▁call▁end｜>\n<｜tool▁call▁begin｜>function<｜tool▁sep｜>get_weather\n```json\n{\"location\": \"Seattle, WA\"}\n```<｜tool▁call▁end｜><｜tool▁calls▁end｜><｜end▁of▁sentence｜><｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>{\"temperature\": 18}<｜tool▁output▁end｜>\n<｜tool▁output▁begin｜>{\"temperature\": 14}<｜tool▁output▁end｜><｜tool▁outputs▁end｜>\n````\n\nThe `deepseek_r1` **reasoning** parser (`--reasoning-parser deepseek_r1`) applies to the R1\nseries **and** to DeepSeek-V3.1; it extracts the `<think>…</think>` span into the response's\n`reasoning` field. It is independent of the tool-call parser.\n\n## Sources\n\n- DeepSeek-V3.1 model card (Chat Template / ToolCall sections): <https://huggingface.co/deepseek-ai/DeepSeek-V3.1>\n- DeepSeek-V3.1 `assets/chat_template.jinja`: <https://huggingface.co/deepseek-ai/DeepSeek-V3.1/resolve/main/assets/chat_template.jinja>\n- DeepSeek-V3.1 `tokenizer_config.json` (`chat_template`, byte-identical to the jinja): <https://huggingface.co/deepseek-ai/DeepSeek-V3.1/resolve/main/tokenizer_config.json>\n- DeepSeek-V3.1 `tokenizer.json` (`added_tokens` → token IDs and `special` flags): <https://huggingface.co/deepseek-ai/DeepSeek-V3.1/resolve/main/tokenizer.json>\n- DeepSeek-V3.1 `config.json` (`bos_token_id`, `eos_token_id`, `vocab_size`): <https://huggingface.co/deepseek-ai/DeepSeek-V3.1/resolve/main/config.json>\n- DeepSeek-R1-0528 model card and `tokenizer_config.json` (older tool format): <https://huggingface.co/deepseek-ai/DeepSeek-R1-0528> · <https://huggingface.co/deepseek-ai/DeepSeek-R1-0528/resolve/main/tokenizer_config.json>\n- DeepSeek-R1 model card: <https://huggingface.co/deepseek-ai/DeepSeek-R1>\n- DeepSeek-V3-0324 `tokenizer_config.json` (older tool format): <https://huggingface.co/deepseek-ai/DeepSeek-V3-0324/resolve/main/tokenizer_config.json>\n- vLLM tool-call template for V3.1 (`## Tools` injection + `| tojson`): <https://github.com/vllm-project/vllm/blob/main/examples/tool_chat_template_deepseekv31.jinja>\n- vLLM Tool Calling docs (`deepseek_v3`, `deepseek_v31` parser flags): <https://docs.vllm.ai/en/latest/features/tool_calling/>\n- vLLM Reasoning Outputs docs (`deepseek_r1` reasoning parser; V3.1 thinking default): <https://docs.vllm.ai/en/latest/features/reasoning_outputs/>\n",
-	"toolconv/gemini.md": "# Gemini Pythonic tool-calling format (`tool_code` / `default_api`)\n\nTool-calling convention of Google's hosted **Gemini** models (current generation, incl. `gemini-3.5-flash` / `*-pro` / `*-preview`) and the **Gemma 3** open-weights family. Both drive tool use **entirely through prompt engineering** — there are **no dedicated special tokens**. The model emits each invocation as **Python source**: a call `default_api.<function_name>(<kwargs>)`, conventionally wrapped in `print(...)` and placed inside a fenced ```` ```tool_code ```` block; it reads results back from a ```` ```tool_outputs ```` block. Because the mechanism is plain text the model was post-trained to produce, the exact same syntax periodically leaks into ordinary output (surfaced by Vertex/AI-Studio as `finish_reason = MALFORMED_FUNCTION_CALL`) — that leak is the clearest public evidence of the format.\n\nVerified against: the official Gemma 3 function-calling guide (`ai.google.dev/gemma/docs/capabilities/function-calling` — the two recommended prompts, one Pythonic and one JSON), Simon Willison's transcription of those two prompts, Philipp Schmid's Gemma 3 walkthrough (`philschmid.de/gemma-function-calling`), and the reverse-engineered hosted-Gemini form recovered from `MALFORMED_FUNCTION_CALL` reports: `google/adk-go#492` (`Malformed function call: print(default_api.`), `google-gemini/cookbook#929` (`executableCode` part = `print(default_api.get_complaint_number_tool(consumer_number_or_mobile_number='2001234567'))`), `firebase/genkit#2628` (the ```` ```tool_code ```` markdown wrapper), and the Google AI dev-forum thread \"Gemini 2 flash returns raw markdown instead of function call\" (71964).\n\n## \"Special\" tokens\n\n**None.** Nothing here is a control token in the tokenizer's special-token table — every marker below BPE-splits into ordinary text and survives a `skip_special_tokens=True` decode. This is the defining property of the convention and the reason it both (a) works across hosted Gemini and open Gemma without tokenizer support and (b) leaks. The functional markers are:\n\n| Marker (verbatim) | Role |\n|---|---|\n| ` ```tool_code ` | Opens a fenced block whose body is Python the app must execute. Closed by a bare ` ``` `. |\n| ` ```tool_outputs ` | Opens a fenced block carrying the executed results back to the model. Closed by a bare ` ``` `. |\n| `default_api` | Synthetic module namespace the hosted stack bundles un-namespaced tools into. Calls read `default_api.<name>(...)`. |\n| `print(...)` | Conventional wrapper around the call in the hosted-Gemini form (the model is trained to \"print\" the call). Semantically irrelevant — the runtime parses the call, it does not execute Python. |\n\nThere is **no** per-call id on the wire and **no** in-band reasoning marker — Gemini reasoning travels out of band as API \"thought signatures\", never as `<think>`-style text.\n\n## Roles / turn structure\n\nThe Pythonic payload is independent of the envelope, and the envelope differs by deployment:\n\n- **Hosted Gemini** uses the normal `contents[]` turn structure (`role: \"user\" | \"model\"`); the `tool_code` block appears inside a `model` turn's text, and `tool_outputs` is supplied as the next turn.\n- **Gemma 3** (open weights) uses the Gemma chat template (`<start_of_turn>user … <end_of_turn>` / `<start_of_turn>model`); the tool prompt is prepended to the first user turn and the blocks live inside model/user turns.\n\nThis document specifies the **payload** (the two fenced blocks + the Python call form); the surrounding turn tokens belong to whichever template hosts it.\n\n## Tool definitions\n\nTools are advertised in the prompt as a JSON-Schema catalog. Gemma 3's official guide ships **two** interchangeable system-prompt templates that differ only in how the model is told to answer:\n\n1. **Pythonic** (the one this spec targets):\n   > You have access to functions. If you decide to invoke any of the function(s), you MUST put it in the format of `[func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)]`\n   > You SHOULD NOT include any other text in the response if you call a function\n\n2. **JSON** (the sibling convention — see `qwen3.md` for the closely related Hermes shape):\n   > … you MUST put it in the format of `{\"name\": function name, \"parameters\": dictionary of argument name and its value}`\n\nHosted Gemini wraps the same idea in markdown fences and the `default_api` namespace. The function signatures themselves are passed as OpenAI-style tool JSON (`{\"type\":\"function\",\"function\":{name,description,parameters}}`).\n\n## Tool-call format\n\nOne call is a Python call expression. The hosted-Gemini canonical form is a `print()` of a `default_api` method, fenced:\n\n````text\n```tool_code\nprint(default_api.get_current_temperature(location=\"London\", unit=\"celsius\"))\n```\n````\n\nAll of the following are accepted equivalents seen in the wild and across Gemma/Gemini variants; a robust parser normalizes them to `{name, arguments}`:\n\n- `print(default_api.NAME(KWARGS))` — hosted Gemini canonical.\n- `default_api.NAME(KWARGS)` — `print`/namespace are optional sugar.\n- `NAME(KWARGS)` — bare call (Gemma 3 Pythonic prompt).\n- `result = NAME(KWARGS)` — assignment form (Gemma 3 docs use `result = convert(...)`).\n\nArgument values are **Python literals**, not JSON:\n\n| Python literal | Example | Decoded |\n|---|---|---|\n| string | `'London'` or `\"London\"` | `\"London\"` |\n| int / float | `42`, `3.14` | `42`, `3.14` |\n| bool | `True` / `False` | `true` / `false` |\n| null | `None` | `null` |\n| list | `[\"a\", \"b\"]` | `[\"a\",\"b\"]` |\n| dict | `{\"k\": 1}` | `{\"k\":1}` |\n\nStrings use Python escaping (`\\n`, `\\t`, `\\\\`, `\\'`, `\\\"`); hosted Gemini emits single quotes (`location='London'`), Gemma examples use double quotes — both are valid. Arguments are keyword form (`name=value`); positional arguments are not used because the runtime maps to a named schema.\n\n## Multiple / parallel tool calls\n\nTwo encodings exist, both inside a single `tool_code` block:\n\n- **Gemma 3 Pythonic prompt** — a Python **list** of call expressions:\n  ````text\n  ```tool_code\n  [get_current_temperature(location=\"London\"), get_temperature_date(location=\"London\", date=\"2024-10-01\")]\n  ```\n  ````\n- **Hosted Gemini** — one `print(default_api...)` **statement per line**:\n  ````text\n  ```tool_code\n  print(default_api.get_current_temperature(location=\"London\"))\n  print(default_api.get_temperature_date(location=\"London\", date=\"2024-10-01\"))\n  ```\n  ````\n\nEither way the calls are returned in source order; the application executes them and returns one result per call in the same order.\n\n## Tool-result format\n\nExecuted results are returned to the model in a ```` ```tool_outputs ```` block. Gemma 3 docs use assignment-style values (`result = 92.3`); for opaque tool output the block simply carries the returned text/JSON:\n\n````text\n```tool_outputs\n{\"temperature\": 26.1, \"location\": \"London\", \"unit\": \"celsius\"}\n```\n````\n\nThe model then continues with either a natural-language answer or another `tool_code` block.\n\n## End-to-end example\n\n````text\n<user>\nWhat's the temperature in London?\n\n<model>\n```tool_code\nprint(default_api.get_current_temperature(location=\"London\", unit=\"celsius\"))\n```\n\n<user>\n```tool_outputs\n{\"temperature\": 11.4, \"location\": \"London\", \"unit\": \"celsius\"}\n```\n\n<model>\nIt's currently 11.4°C in London.\n````\n\n## OpenAI-compatible / native API mapping\n\n- Hosted Gemini's native API normally returns a structured `functionCall` part (`{name, args}`); for Gemini 3 each carries an `id` that must be echoed in the matching `functionResponse`, plus a `thoughtSignature` that must be preserved. The Pythonic text form is what you get when the structured path *fails* (`finish_reason = MALFORMED_FUNCTION_CALL`) or when tool use is driven purely by prompt (Gemma, or Gemini via the code-execution `executableCode` part).\n- When parsed out of an OpenAI-compatible shim, each recovered call becomes `tool_calls[i] = {id (server-minted), type:\"function\", function:{name, arguments:<JSON string>}}` — the Python kwargs are re-serialized to a JSON string at that boundary.\n- Feed results back as the deployment's tool/`functionResponse` turn (hosted) or a `tool_outputs` block in the next user turn (prompt-driven).\n\n## Parsing notes & gotchas\n\n- **Python, not JSON.** `True`/`False`/`None` (not `true`/`false`/`null`), single-quoted strings, and trailing commas are all legal. A JSON parser will reject valid calls; decode Python literals.\n- **Strip the wrapper.** Normalize away `print(...)`, a `default_api.` (or any `module.`) prefix, and an `LHS =` assignment before reading the call name. `print` is never a tool name.\n- **Skip string contents when scanning.** A call like `search(pattern=\"foo(\")` contains a `(` inside a string; a naive `\\w+\\(` scan mis-detects `foo` as a callee. Track string state and only treat top-level `(` as a call opener.\n- **Fence ambiguity.** The body terminates at the first bare ` ``` `; a string argument literally containing ` ``` ` will truncate the block early (rare, accepted limitation).\n- **It leaks.** Because nothing is a special token, the format appears verbatim in normal responses when the model \"decides\" to call a tool but the structured decoder misfires. Production code reading raw text should detect ` ```tool_code ` and parse it; production code on the structured API should retry on `MALFORMED_FUNCTION_CALL`.\n- **Variant divergence.** Gemma **4** abandoned this Pythonic form for a token-delimited brace syntax (`<|tool_call>call:NAME{…}<tool_call|>`) — a different convention documented in `gemma.md`. This spec covers hosted Gemini and Gemma 3.\n\n## Sources\n\n- Gemma 3 function calling (two recommended prompts): https://ai.google.dev/gemma/docs/capabilities/function-calling\n- Simon Willison, \"Function calling with Gemma\": https://simonwillison.net/2025/Mar/26/function-calling-with-gemma/\n- Philipp Schmid, \"Google Gemma 3 Function Calling Example\": https://www.philschmid.de/gemma-function-calling\n- Gemini 3 thought signatures + functionCall ids: https://ai.google.dev/gemini-api/docs/gemini-3\n- `default_api` / `tool_code` leak evidence: https://github.com/google/adk-go/issues/492 · https://github.com/google-gemini/cookbook/issues/929 · https://github.com/firebase/genkit/issues/2628 · https://discuss.ai.google.dev/t/gemini-2-flash-api-returns-raw-markdown-instead-of-function-call/71964\n",
-	"toolconv/gemma.md": "# Gemma 4 tool-calling format (token-delimited `call:NAME{…}`)\n\nTool-calling convention of Google's **Gemma 4** open-weights family (`google/gemma-4-*-it`). It is a clean break from the prompt-engineered Pythonic `tool_code` form used by Gemma 3 and hosted Gemini (see `gemini.md`): Gemma 4 introduces **dedicated special tokens** and a compact **token-delimited brace syntax**. Tool declarations, calls, and responses each get their own paired markers, and every string value is wrapped in a `<|\"|>` token rather than ASCII quotes. The model emits one call as `<|tool_call>call:NAME{key:value,…}<tool_call|>`; the developer parses it, runs the tool, and appends `<|tool_response>response:NAME{…}<tool_response|>`.\n\nVerified against: the official \"Function calling with Gemma 4\" guide (`ai.google.dev/gemma/docs/capabilities/text/function-calling-gemma4`), including the byte-exact `processor.apply_chat_template(...)` renderings and the reference `extract_tool_calls` regex it ships. All example streams below are copied from that page (model `google/gemma-4-E2B-it`).\n\n## Special tokens\n\nGemma 4 wraps each structural element in a paired token. Note the **asymmetric pipe placement** — an opener carries the pipe on the left (`<|x>`) and its closer carries it on the right (`<x|>`):\n\n| Open | Close | Purpose |\n|---|---|---|\n| `<bos>` | — | Beginning of sequence |\n| `<|turn>` | `<turn|>` | One conversation turn; the role name is the first line of the body |\n| `<|tool>` | `<tool|>` | A tool **declaration** block (in the system turn) |\n| `<|tool_call>` | `<tool_call|>` | One tool **call** emitted by the model |\n| `<|tool_response>` | `<tool_response|>` | One tool **result** fed back to the model |\n| `<|\"|>` | `<|\"|>` | String-literal delimiter (same token on both ends) |\n| `<eos>` | — | End of sequence |\n\nBecause the string delimiter is a token (`<|\"|>`), values may contain raw ASCII quotes and commas without escaping — only a literal `<|\"|>` token sequence cannot appear inside a string.\n\n## Roles / turn structure\n\nEach turn is `<|turn>{role}\\n{body}<turn|>`. Roles are `system`, `user`, `model`. With a generation prompt the stream ends at `<|turn>model\\n` and the model continues. Tool declarations are merged into the `system` turn; tool calls and the following tool responses are emitted inside the `model` turn (the response block immediately follows the call block in the re-rendered history).\n\n## Tool definitions\n\nEach tool is declared in the system turn as `<|tool>declaration:NAME{…}<tool|>`, where the body is the schema serialized in the same brace syntax used by calls. Types are upper-cased strings (`STRING`, `OBJECT`, …). Byte-exact, from the guide:\n\n```text\n<|tool>declaration:get_current_temperature{description:<|\"|>Gets the current temperature for a given location.<|\"|>,parameters:{properties:{location:{description:<|\"|>The city name, e.g. San Francisco<|\"|>,type:<|\"|>STRING<|\"|>} },required:[<|\"|>location<|\"|>],type:<|\"|>OBJECT<|\"|>} }<tool|>\n```\n\n## Tool-call format\n\nThe model emits one call per `<|tool_call>…<tool_call|>` block. The body is `call:NAME{ARGS}`, where `ARGS` is a comma-separated list of `key:value` pairs:\n\n```text\n<|tool_call>call:get_current_temperature{location:<|\"|>London<|\"|>}<tool_call|>\n```\n\nValue grammar inside `{…}`:\n\n| Value kind | Encoding | Example |\n|---|---|---|\n| string | `<|\"|>text<|\"|>` | `location:<|\"|>London<|\"|>` |\n| int / float | bare | `count:42` |\n| bool | bare | `flag:true` |\n| null | bare | `unit:null` |\n| list | `[v,v,…]` | `tags:[<|\"|>a<|\"|>,<|\"|>b<|\"|>]` |\n| nested object | `{k:v,…}` | `config:{theme:<|\"|>dark<|\"|>}` |\n\nThe reference parser shipped in the guide:\n\n```python\n[{\n    \"name\": name,\n    \"arguments\": {\n        k: cast((v1 or v2).strip())\n        for k, v1, v2 in re.findall(r'(\\w+):(?:<\\|\"\\|>(.*?)<\\|\"\\|>|([^,}]*))', args)\n    }\n} for name, args in re.findall(r\"<\\|tool_call>call:(\\w+)\\{(.*?)\\}<tool_call\\|>\", text, re.DOTALL)]\n```\n\ni.e. each argument value is either a `<|\"|>…<|\"|>` string or a bare run of non-`,}` characters (cast to int/float/bool, else kept as a string).\n\n## Multiple / parallel tool calls\n\nParallel calls are consecutive `<|tool_call>…<tool_call|>` blocks (one call each), returned in order. The application returns one `<|tool_response>` per call in the same order.\n\n## Tool-result format\n\nEach result is `<|tool_response>response:NAME{…}<tool_response|>`, the response object serialized in the same brace syntax. Byte-exact, from the guide's re-rendered history:\n\n```text\n<|tool_response>response:get_current_weather{temperature:15,weather:<|\"|>sunny<|\"|>}<tool_response|>\n```\n\n## End-to-end example\n\nByte-exact `apply_chat_template` output from the guide (system + tool, user, model call, tool response, final answer — note the response block sits in the same model turn, right after the call):\n\n```text\n<bos><|turn>system\nYou are a helpful assistant.<|tool>declaration:get_current_weather{description:<|\"|>Gets the current weather in a given location.<|\"|>,parameters:{properties:{location:{description:<|\"|>The city and state, e.g. \"San Francisco, CA\" or \"Tokyo, JP\"<|\"|>,type:<|\"|>STRING<|\"|>},unit:{description:<|\"|>The unit to return the temperature in.<|\"|>,enum:[<|\"|>celsius<|\"|>,<|\"|>fahrenheit<|\"|>],type:<|\"|>STRING<|\"|>} },required:[<|\"|>location<|\"|>],type:<|\"|>OBJECT<|\"|>} }<tool|><turn|>\n<|turn>user\nHey, what's the weather in Tokyo right now?<turn|>\n<|turn>model\n<|tool_call>call:get_current_weather{location:<|\"|>Tokyo, JP<|\"|>}<tool_call|><|tool_response>response:get_current_weather{temperature:15,weather:<|\"|>sunny<|\"|>}<tool_response|>The current weather in Tokyo is 15 degrees Celsius and sunny.<turn|>\n```\n\n## Parsing notes & gotchas\n\n- **String delimiter is a token, not a quote.** Inside `<|\"|>…<|\"|>` the bytes `\"` and `,` are literal data — the example `<|\"|>The city and state, e.g. \"San Francisco, CA\"…<|\"|>` contains both. Split arguments on `,`/`}` only **outside** a `<|\"|>…<|\"|>` span.\n- **Asymmetric pipes.** The closer is `<tool_call|>`, not `</tool_call>` or `<|tool_call>`. Matching the wrong pipe side will never close the block.\n- **One call per block.** Unlike a JSON `tool_calls[]` array, parallelism is \"more blocks\", not \"more entries in one block\".\n- **Bare scalars.** A value not wrapped in `<|\"|>` is `true`/`false` → bool, `null`/`none` → null, numeric → number, otherwise a bare string (e.g. an unquoted enum or type name like `STRING`).\n- **Not Gemma 3 / hosted Gemini.** Those use the Pythonic `tool_code` / `default_api` form in `gemini.md`. Gemma 4 replaced it with this token syntax; the two are not interchangeable.\n\n## Sources\n\n- Function calling with Gemma 4 (byte-exact chat-template renderings + reference parser): https://ai.google.dev/gemma/docs/capabilities/text/function-calling-gemma4\n- Gemma 4 prompt formatting: https://ai.google.dev/gemma/docs/core/prompt-formatting-gemma4\n",
+	"toolconv/gemini.md": "# Gemini Pythonic tool-calling format (`tool_code` / `default_api`)\n\nTool-calling convention of Google's hosted **Gemini** models (current generation, incl. `gemini-3.5-flash` / `*-pro` / `*-preview`) and the **Gemma 3** open-weights family. Both drive tool use **entirely through prompt engineering** — there are **no dedicated special tokens**. The model emits each invocation as **Python source**: a call `default_api.<function_name>(<kwargs>)`, conventionally wrapped in `print(...)` and placed inside a fenced ```` ```tool_code ```` block; it reads results back from a ```` ```tool_outputs ```` block. Because the mechanism is plain text the model was post-trained to produce, the exact same syntax periodically leaks into ordinary output (surfaced by Vertex/AI-Studio as `finish_reason = MALFORMED_FUNCTION_CALL`) — that leak is the clearest public evidence of the format.\n\nVerified against: the official Gemma 3 function-calling guide (`ai.google.dev/gemma/docs/capabilities/function-calling` — the two recommended prompts, one Pythonic and one JSON), Simon Willison's transcription of those two prompts, Philipp Schmid's Gemma 3 walkthrough (`philschmid.de/gemma-function-calling`), and the reverse-engineered hosted-Gemini form recovered from `MALFORMED_FUNCTION_CALL` reports: `google/adk-go#492` (`Malformed function call: print(default_api.`), `google-gemini/cookbook#929` (`executableCode` part = `print(default_api.get_complaint_number_tool(consumer_number_or_mobile_number='2001234567'))`), `firebase/genkit#2628` (the ```` ```tool_code ```` markdown wrapper), and the Google AI dev-forum thread \"Gemini 2 flash returns raw markdown instead of function call\" (71964).\n\n## \"Special\" tokens\n\n**None.** Nothing here is a control token in the tokenizer's special-token table — every marker below BPE-splits into ordinary text and survives a `skip_special_tokens=True` decode. This is the defining property of the convention and the reason it both (a) works across hosted Gemini and open Gemma without tokenizer support and (b) leaks. The functional markers are:\n\n| Marker (verbatim) | Role |\n|---|---|\n| ` ```tool_code ` | Opens a fenced block whose body is Python the app must execute. Closed by a bare ` ``` `. |\n| ` ```tool_outputs ` | Opens a fenced block carrying the executed results back to the model. Closed by a bare ` ``` `. |\n| `default_api` | Synthetic module namespace the hosted stack bundles un-namespaced tools into. Calls read `default_api.<name>(...)`. |\n| `print(...)` | Conventional wrapper around the call in the hosted-Gemini form (the model is trained to \"print\" the call). Semantically irrelevant — the runtime parses the call, it does not execute Python. |\n\nThere is **no** per-call id on the wire and **no** in-band reasoning marker — Gemini reasoning travels out of band as API \"thought signatures\", never as `<think>`-style text.\n\n> **OMP dialect note:** because this convention carries no native in-band reasoning marker, the OMP `gemini` dialect layers a sibling fenced ` ```thinking ` block (closed by a bare ` ``` `, exactly like ` ```tool_code `) so prompt-driven Gemini / Gemma-3 deployments can express reasoning in-band. This is an OMP convention, not part of Google's format.\n\n## Roles / turn structure\n\nThe Pythonic payload is independent of the envelope, and the envelope differs by deployment:\n\n- **Hosted Gemini** uses the normal `contents[]` turn structure (`role: \"user\" | \"model\"`); the `tool_code` block appears inside a `model` turn's text, and `tool_outputs` is supplied as the next turn.\n- **Gemma 3** (open weights) uses the Gemma chat template (`<start_of_turn>user … <end_of_turn>` / `<start_of_turn>model`); the tool prompt is prepended to the first user turn and the blocks live inside model/user turns.\n\nThis document specifies the **payload** (the two fenced blocks + the Python call form); the surrounding turn tokens belong to whichever template hosts it.\n\n## Tool definitions\n\nTools are advertised in the prompt as a JSON-Schema catalog. Gemma 3's official guide ships **two** interchangeable system-prompt templates that differ only in how the model is told to answer:\n\n1. **Pythonic** (the one this spec targets):\n   > You have access to functions. If you decide to invoke any of the function(s), you MUST put it in the format of `[func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)]`\n   > You SHOULD NOT include any other text in the response if you call a function\n\n2. **JSON** (the sibling convention — see `qwen3.md` for the closely related Hermes shape):\n   > … you MUST put it in the format of `{\"name\": function name, \"parameters\": dictionary of argument name and its value}`\n\nHosted Gemini wraps the same idea in markdown fences and the `default_api` namespace. The function signatures themselves are passed as OpenAI-style tool JSON (`{\"type\":\"function\",\"function\":{name,description,parameters}}`).\n\n## Tool-call format\n\nOne call is a Python call expression. The hosted-Gemini canonical form is a `print()` of a `default_api` method, fenced:\n\n````text\n```tool_code\nprint(default_api.get_current_temperature(location=\"London\", unit=\"celsius\"))\n```\n````\n\nAll of the following are accepted equivalents seen in the wild and across Gemma/Gemini variants; a robust parser normalizes them to `{name, arguments}`:\n\n- `print(default_api.NAME(KWARGS))` — hosted Gemini canonical.\n- `default_api.NAME(KWARGS)` — `print`/namespace are optional sugar.\n- `NAME(KWARGS)` — bare call (Gemma 3 Pythonic prompt).\n- `result = NAME(KWARGS)` — assignment form (Gemma 3 docs use `result = convert(...)`).\n\nArgument values are **Python literals**, not JSON:\n\n| Python literal | Example | Decoded |\n|---|---|---|\n| string | `'London'` or `\"London\"` | `\"London\"` |\n| int / float | `42`, `3.14` | `42`, `3.14` |\n| bool | `True` / `False` | `true` / `false` |\n| null | `None` | `null` |\n| list | `[\"a\", \"b\"]` | `[\"a\",\"b\"]` |\n| dict | `{\"k\": 1}` | `{\"k\":1}` |\n\nStrings use Python escaping (`\\n`, `\\t`, `\\\\`, `\\'`, `\\\"`); hosted Gemini emits single quotes (`location='London'`), Gemma examples use double quotes — both are valid. Arguments are keyword form (`name=value`); positional arguments are not used because the runtime maps to a named schema.\n\n## Multiple / parallel tool calls\n\nTwo encodings exist, both inside a single `tool_code` block:\n\n- **Gemma 3 Pythonic prompt** — a Python **list** of call expressions:\n  ````text\n  ```tool_code\n  [get_current_temperature(location=\"London\"), get_temperature_date(location=\"London\", date=\"2024-10-01\")]\n  ```\n  ````\n- **Hosted Gemini** — one `print(default_api...)` **statement per line**:\n  ````text\n  ```tool_code\n  print(default_api.get_current_temperature(location=\"London\"))\n  print(default_api.get_temperature_date(location=\"London\", date=\"2024-10-01\"))\n  ```\n  ````\n\nEither way the calls are returned in source order; the application executes them and returns one result per call in the same order.\n\n## Tool-result format\n\nExecuted results are returned to the model in a ```` ```tool_outputs ```` block. Gemma 3 docs use assignment-style values (`result = 92.3`); for opaque tool output the block simply carries the returned text/JSON:\n\n````text\n```tool_outputs\n{\"temperature\": 26.1, \"location\": \"London\", \"unit\": \"celsius\"}\n```\n````\n\nThe model then continues with either a natural-language answer or another `tool_code` block.\n\n## End-to-end example\n\n````text\n<user>\nWhat's the temperature in London?\n\n<model>\n```tool_code\nprint(default_api.get_current_temperature(location=\"London\", unit=\"celsius\"))\n```\n\n<user>\n```tool_outputs\n{\"temperature\": 11.4, \"location\": \"London\", \"unit\": \"celsius\"}\n```\n\n<model>\nIt's currently 11.4°C in London.\n````\n\n## OpenAI-compatible / native API mapping\n\n- Hosted Gemini's native API normally returns a structured `functionCall` part (`{name, args}`); for Gemini 3 each carries an `id` that must be echoed in the matching `functionResponse`, plus a `thoughtSignature` that must be preserved. The Pythonic text form is what you get when the structured path *fails* (`finish_reason = MALFORMED_FUNCTION_CALL`) or when tool use is driven purely by prompt (Gemma, or Gemini via the code-execution `executableCode` part).\n- When parsed out of an OpenAI-compatible shim, each recovered call becomes `tool_calls[i] = {id (server-minted), type:\"function\", function:{name, arguments:<JSON string>}}` — the Python kwargs are re-serialized to a JSON string at that boundary.\n- Feed results back as the deployment's tool/`functionResponse` turn (hosted) or a `tool_outputs` block in the next user turn (prompt-driven).\n\n## Parsing notes & gotchas\n\n- **Python, not JSON.** `True`/`False`/`None` (not `true`/`false`/`null`), single-quoted strings, and trailing commas are all legal. A JSON parser will reject valid calls; decode Python literals.\n- **Strip the wrapper.** Normalize away `print(...)`, a `default_api.` (or any `module.`) prefix, and an `LHS =` assignment before reading the call name. `print` is never a tool name.\n- **Skip string contents when scanning.** A call like `search(pattern=\"foo(\")` contains a `(` inside a string; a naive `\\w+\\(` scan mis-detects `foo` as a callee. Track string state and only treat top-level `(` as a call opener.\n- **Fence ambiguity.** The body terminates at the first bare ` ``` `; a string argument literally containing ` ``` ` will truncate the block early (rare, accepted limitation).\n- **It leaks.** Because nothing is a special token, the format appears verbatim in normal responses when the model \"decides\" to call a tool but the structured decoder misfires. Production code reading raw text should detect ` ```tool_code ` and parse it; production code on the structured API should retry on `MALFORMED_FUNCTION_CALL`.\n- **Variant divergence.** Gemma **4** abandoned this Pythonic form for a token-delimited brace syntax (`<|tool_call>call:NAME{…}<tool_call|>`) — a different convention documented in `gemma.md`. This spec covers hosted Gemini and Gemma 3.\n\n## Sources\n\n- Gemma 3 function calling (two recommended prompts): https://ai.google.dev/gemma/docs/capabilities/function-calling\n- Simon Willison, \"Function calling with Gemma\": https://simonwillison.net/2025/Mar/26/function-calling-with-gemma/\n- Philipp Schmid, \"Google Gemma 3 Function Calling Example\": https://www.philschmid.de/gemma-function-calling\n- Gemini 3 thought signatures + functionCall ids: https://ai.google.dev/gemini-api/docs/gemini-3\n- `default_api` / `tool_code` leak evidence: https://github.com/google/adk-go/issues/492 · https://github.com/google-gemini/cookbook/issues/929 · https://github.com/firebase/genkit/issues/2628 · https://discuss.ai.google.dev/t/gemini-2-flash-api-returns-raw-markdown-instead-of-function-call/71964\n",
+	"toolconv/gemma.md": "# Gemma 4 tool-calling format (token-delimited `call:NAME{…}`)\n\nTool-calling convention of Google's **Gemma 4** open-weights family (`google/gemma-4-*-it`). It is a clean break from the prompt-engineered Pythonic `tool_code` form used by Gemma 3 and hosted Gemini (see `gemini.md`): Gemma 4 introduces **dedicated special tokens** and a compact **token-delimited brace syntax**. Tool declarations, calls, and responses each get their own paired markers, and every string value is wrapped in a `<|\"|>` token rather than ASCII quotes. The model emits one call as `<|tool_call>call:NAME{key:value,…}<tool_call|>`; the developer parses it, runs the tool, and appends `<|tool_response>response:NAME{…}<tool_response|>`.\n\nVerified against: the official \"Function calling with Gemma 4\" guide (`ai.google.dev/gemma/docs/capabilities/text/function-calling-gemma4`), including the byte-exact `processor.apply_chat_template(...)` renderings and the reference `extract_tool_calls` regex it ships. All example streams below are copied from that page (model `google/gemma-4-E2B-it`).\n\n## Special tokens\n\nGemma 4 wraps each structural element in a paired token. Note the **asymmetric pipe placement** — an opener carries the pipe on the left (`<|x>`) and its closer carries it on the right (`<x|>`):\n\n| Open | Close | Purpose |\n|---|---|---|\n| `<bos>` | — | Beginning of sequence |\n| `<|turn>` | `<turn|>` | One conversation turn; the role name is the first line of the body |\n| `<|tool>` | `<tool|>` | A tool **declaration** block (in the system turn) |\n| `<|tool_call>` | `<tool_call|>` | One tool **call** emitted by the model |\n| `<|tool_response>` | `<tool_response|>` | One tool **result** fed back to the model |\n| `<|think|>` | — | Thinking-mode enable flag, injected in the system turn |\n| `<|channel>` | `<channel|>` | Reasoning channel; `<|channel>thought` opens the model's chain-of-thought (closed by `<channel|>`) before the visible reply |\n| `<|\"|>` | `<|\"|>` | String-literal delimiter (same token on both ends) |\n| `<eos>` | — | End of sequence |\n\nBecause the string delimiter is a token (`<|\"|>`), values may contain raw ASCII quotes and commas without escaping — only a literal `<|\"|>` token sequence cannot appear inside a string.\n\nThinking variants emit reasoning in a dedicated channel — `<|channel>thought\\n…\\n<channel|>` at the start of the model turn, before the reply (`enable_thinking` injects a `<|think|>` flag into the system turn). Prior-turn thoughts are stripped from history except on a tool-calling turn, where they are preserved between the call and its response.\n\n## Roles / turn structure\n\nEach turn is `<|turn>{role}\\n{body}<turn|>`. Roles are `system`, `user`, `model`. With a generation prompt the stream ends at `<|turn>model\\n` and the model continues. Tool declarations are merged into the `system` turn; tool calls and the following tool responses are emitted inside the `model` turn (the response block immediately follows the call block in the re-rendered history).\n\n## Tool definitions\n\nEach tool is declared in the system turn as `<|tool>declaration:NAME{…}<tool|>`, where the body is the schema serialized in the same brace syntax used by calls. Types are upper-cased strings (`STRING`, `OBJECT`, …). Byte-exact, from the guide:\n\n```text\n<|tool>declaration:get_current_temperature{description:<|\"|>Gets the current temperature for a given location.<|\"|>,parameters:{properties:{location:{description:<|\"|>The city name, e.g. San Francisco<|\"|>,type:<|\"|>STRING<|\"|>} },required:[<|\"|>location<|\"|>],type:<|\"|>OBJECT<|\"|>} }<tool|>\n```\n\n## Tool-call format\n\nThe model emits one call per `<|tool_call>…<tool_call|>` block. The body is `call:NAME{ARGS}`, where `ARGS` is a comma-separated list of `key:value` pairs:\n\n```text\n<|tool_call>call:get_current_temperature{location:<|\"|>London<|\"|>}<tool_call|>\n```\n\nValue grammar inside `{…}`:\n\n| Value kind | Encoding | Example |\n|---|---|---|\n| string | `<|\"|>text<|\"|>` | `location:<|\"|>London<|\"|>` |\n| int / float | bare | `count:42` |\n| bool | bare | `flag:true` |\n| null | bare | `unit:null` |\n| list | `[v,v,…]` | `tags:[<|\"|>a<|\"|>,<|\"|>b<|\"|>]` |\n| nested object | `{k:v,…}` | `config:{theme:<|\"|>dark<|\"|>}` |\n\nThe reference parser shipped in the guide:\n\n```python\n[{\n    \"name\": name,\n    \"arguments\": {\n        k: cast((v1 or v2).strip())\n        for k, v1, v2 in re.findall(r'(\\w+):(?:<\\|\"\\|>(.*?)<\\|\"\\|>|([^,}]*))', args)\n    }\n} for name, args in re.findall(r\"<\\|tool_call>call:(\\w+)\\{(.*?)\\}<tool_call\\|>\", text, re.DOTALL)]\n```\n\ni.e. each argument value is either a `<|\"|>…<|\"|>` string or a bare run of non-`,}` characters (cast to int/float/bool, else kept as a string).\n\n## Multiple / parallel tool calls\n\nParallel calls are consecutive `<|tool_call>…<tool_call|>` blocks (one call each), returned in order. The application returns one `<|tool_response>` per call in the same order.\n\n## Tool-result format\n\nEach result is `<|tool_response>response:NAME{…}<tool_response|>`, the response object serialized in the same brace syntax. Byte-exact, from the guide's re-rendered history:\n\n```text\n<|tool_response>response:get_current_weather{temperature:15,weather:<|\"|>sunny<|\"|>}<tool_response|>\n```\n\n## End-to-end example\n\nByte-exact `apply_chat_template` output from the guide (system + tool, user, model call, tool response, final answer — note the response block sits in the same model turn, right after the call):\n\n```text\n<bos><|turn>system\nYou are a helpful assistant.<|tool>declaration:get_current_weather{description:<|\"|>Gets the current weather in a given location.<|\"|>,parameters:{properties:{location:{description:<|\"|>The city and state, e.g. \"San Francisco, CA\" or \"Tokyo, JP\"<|\"|>,type:<|\"|>STRING<|\"|>},unit:{description:<|\"|>The unit to return the temperature in.<|\"|>,enum:[<|\"|>celsius<|\"|>,<|\"|>fahrenheit<|\"|>],type:<|\"|>STRING<|\"|>} },required:[<|\"|>location<|\"|>],type:<|\"|>OBJECT<|\"|>} }<tool|><turn|>\n<|turn>user\nHey, what's the weather in Tokyo right now?<turn|>\n<|turn>model\n<|tool_call>call:get_current_weather{location:<|\"|>Tokyo, JP<|\"|>}<tool_call|><|tool_response>response:get_current_weather{temperature:15,weather:<|\"|>sunny<|\"|>}<tool_response|>The current weather in Tokyo is 15 degrees Celsius and sunny.<turn|>\n```\n\n## Parsing notes & gotchas\n\n- **String delimiter is a token, not a quote.** Inside `<|\"|>…<|\"|>` the bytes `\"` and `,` are literal data — the example `<|\"|>The city and state, e.g. \"San Francisco, CA\"…<|\"|>` contains both. Split arguments on `,`/`}` only **outside** a `<|\"|>…<|\"|>` span.\n- **Asymmetric pipes.** The closer is `<tool_call|>`, not `</tool_call>` or `<|tool_call>`. Matching the wrong pipe side will never close the block.\n- **One call per block.** Unlike a JSON `tool_calls[]` array, parallelism is \"more blocks\", not \"more entries in one block\".\n- **Bare scalars.** A value not wrapped in `<|\"|>` is `true`/`false` → bool, `null`/`none` → null, numeric → number, otherwise a bare string (e.g. an unquoted enum or type name like `STRING`).\n- **Not Gemma 3 / hosted Gemini.** Those use the Pythonic `tool_code` / `default_api` form in `gemini.md`. Gemma 4 replaced it with this token syntax; the two are not interchangeable.\n\n## Sources\n\n- Function calling with Gemma 4 (byte-exact chat-template renderings + reference parser): https://ai.google.dev/gemma/docs/capabilities/text/function-calling-gemma4\n- Gemma 4 prompt formatting: https://ai.google.dev/gemma/docs/core/prompt-formatting-gemma4\n",
 	"toolconv/glm-4.5.md": "# GLM-4.5 / GLM-4.6 tool-calling format\n\nNative tool-calling convention of Zhipu AI / Z.ai's **GLM-4.5** family (`zai-org/GLM-4.5` 355B-A32B and `zai-org/GLM-4.5-Air` 106B-A12B, `model_type: \"glm4_moe\"`), shared byte-for-byte by **GLM-4.6**. Unlike the JSON-in-a-tag conventions used by most families, GLM emits each tool call as an **XML-like** block: `<tool_call>{name}` followed by alternating `<arg_key>`/`<arg_value>` element pairs, closed by `</tool_call>`. The prompt is a GLM-style sequence opened by `[gMASK]<sop>` with turn markers `<|system|>`, `<|user|>`, `<|assistant|>`, `<|observation|>`. An inference server turns the raw stream into OpenAI-style `tool_calls` with a parser plus a reasoning parser: both vLLM and SGLang expose `--tool-call-parser glm45 --reasoning-parser glm45` (vLLM additionally needs `--enable-auto-tool-choice`). Tool calling and reasoning are driven entirely by the bundled `chat_template.jinja`; thinking mode is on by default and is disabled per-request with `chat_template_kwargs={\"enable_thinking\": false}`.\n\nThis document was verified against the authoritative `chat_template.jinja` from the HF repo (fetched raw and **rendered locally with Jinja2** — `trim_blocks=True, lstrip_blocks=True`, transformers' `tojson` filter — to produce the byte-exact streams below), `tokenizer_config.json` and `generation_config.json` for the exact token IDs and stop tokens, the model card, and the vLLM (`Glm4MoeModelToolParser`) and SGLang (`Glm4MoeDetector`) parser sources. The HF `resolve`/`blob` web paths redirect to the model-card API; the byte-exact source was obtained via the `resolve/main/...:raw` cache (template commit `cbb2c7cfb52fa128a9660cb1a7a78e017899e115`). The GLM-4.5 and GLM-4.6 `chat_template.jinja` files are identical (same content hash `41478957…`).\n\n## Special tokens\n\nToken IDs are from `tokenizer_config.json` (`added_tokens_decoder`). Note the split: the turn/role markers are registered as **special** tokens, whereas the structural tool-call and thinking tags are each a single dedicated vocabulary token but flagged **`special: false`** (they are emitted/printed as ordinary text, not stripped as control tokens).\n\n| Token (verbatim) | ID | `special` | Purpose |\n|---|---|---|---|\n| `[gMASK]` | 151331 | true | GLM prefix / blank-infilling sentinel; first token of every prompt |\n| `<sop>` | 151333 | true | \"Start of piece\" — immediately follows `[gMASK]` to open the sequence |\n| `<eop>` | 151334 | true | \"End of piece\" (not emitted by the chat template) |\n| `<\\|system\\|>` | 151335 | true | Opens a system turn (and the injected tools turn) |\n| `<\\|user\\|>` | 151336 | true | Opens a user turn (also an EOS id — see below) |\n| `<\\|assistant\\|>` | 151337 | true | Opens an assistant turn / generation prompt |\n| `<\\|observation\\|>` | 151338 | true | Opens a tool-result (observation) turn (also an EOS id) |\n| `<\\|endoftext\\|>` | 151329 | true | End-of-text; `eos_token` and `pad_token` |\n| `<think>` | 151350 | false | Opens the reasoning span inside an assistant turn |\n| `</think>` | 151351 | false | Closes the reasoning span |\n| `<tool_call>` | 151352 | false | Opens one tool call; function name follows on the same line |\n| `</tool_call>` | 151353 | false | Closes one tool call |\n| `<arg_key>` | 151356 | false | Opens an argument-name element |\n| `</arg_key>` | 151357 | false | Closes an argument-name element |\n| `<arg_value>` | 151358 | false | Opens an argument-value element |\n| `</arg_value>` | 151359 | false | Closes an argument-value element |\n| `<tool_response>` | 151354 | false | Wraps one tool result inside an observation turn |\n| `</tool_response>` | 151355 | false | Closes a tool result |\n| `/nothink` | 151360 | true | Soft switch appended to user text to suppress thinking |\n\nNotes on exactness:\n- All pipes are ASCII `|` (U+007C); GLM uses no fullwidth `｜` (U+FF5C) or `▁` (U+2581) variants (unlike DeepSeek). Reproduce `<|system|>`, `<|user|>`, `<|assistant|>`, `<|observation|>` exactly, and `[gMASK]` with literal square brackets.\n- Because `<tool_call>`, `<arg_key>`, `<arg_value>`, `<tool_response>`, `<think>` (and their closers) each map to exactly **one** token ID, they cost one token apiece in the stream — but being `special: false` they round-trip through detokenization as plain text. Parsers therefore match them as literal substrings in the decoded text, not as control-token ids.\n- `eos_token_id` is a **list**: `[151329, 151336, 151338]` = `<|endoftext|>`, `<|user|>`, `<|observation|>` (from `generation_config.json`). This is how a tool-call turn ends: after `</tool_call>` the model emits `<|observation|>`, which is an EOS id, so generation halts and the server reports a tool call (see Turn structure).\n\n## Roles / channels / turn structure\n\nEvery prompt begins with the literal two-token prefix `[gMASK]<sop>` (no following newline). Turns are then concatenated, each introduced by its role marker; there is no per-turn terminator token in rendered history (the next marker, or an EOS id during generation, ends a turn).\n\n- **System** (`<|system|>`): role marker, newline, then the message text. When `tools` are supplied, a synthetic tools system turn is rendered **first**, before any user-supplied system turn (the two are separate `<|system|>` blocks — see Tool definitions).\n- **User** (`<|user|>`): role marker, newline, then text. If `enable_thinking` is false, the literal `/nothink` is appended to the user text (unless it already ends with `/nothink`).\n- **Assistant** (`<|assistant|>`): role marker, then a reasoning span and/or visible content and/or tool calls. The reasoning span is `\\n<think>{reasoning}</think>`; visible content follows on its own line; tool calls follow as `<tool_call>…</tool_call>` blocks.\n- **Tool result** (`<|observation|>`): role marker introducing one or more `<tool_response>…</tool_response>` blocks (see Tool-result format).\n\nThinking / reasoning channel:\n- Reasoning lives in `<think>…</think>` inside the assistant turn. The `--reasoning-parser glm45` extracts it into a separate `reasoning_content` field; the visible answer is whatever follows `</think>`.\n- **Only the reasoning of assistant turns after the last user message is kept.** The template renders every earlier assistant turn with an empty `<think></think>` and drops its `reasoning_content` (or any inline `<think>…</think>` embedded in `content`). This keeps stale chains of thought out of the context on later turns.\n- An assistant turn with neither preserved reasoning nor an explicit chain renders `\\n<think></think>` (empty), then content/tool calls.\n\nGeneration prompt (`add_generation_prompt=True`):\n- **Thinking mode (default):** the prompt ends with a bare `<|assistant|>`; the model continues with `\\n<think>…</think>` then its answer or tool calls.\n- **Non-thinking mode** (`enable_thinking=false`): the prompt ends with `<|assistant|>\\n<think></think>`, pre-filling an empty reasoning span so the model goes straight to the answer.\n\nHow a tool-call turn terminates: there is no dedicated \"stop after tool call\" token. The model emits `</tool_call>` and then `<|observation|>` (token 151338), which is one of the three EOS ids, so decoding stops. The server inspects the text, finds `<tool_call>`, and returns `finish_reason: \"tool_calls\"`.\n\n## Tool definitions\n\nWhen the request carries `tools`, the template prepends one `<|system|>` turn containing a fixed preamble, the tool list wrapped in `<tools>…</tools>`, and a literal description of the output format. Each tool is serialized with `tool | tojson(ensure_ascii=False)` — i.e. the **entire OpenAI tool object verbatim**, including the `{\"type\": \"function\", \"function\": {…}}` wrapper, with default JSON spacing (`\", \"` / `\": \"`). One tool per line.\n\n```text\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_weather\", \"description\": \"Get current weather for a city\", \"parameters\": {\"type\": \"object\", \"properties\": {\"location\": {\"type\": \"string\", \"description\": \"City name\"}, \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]}}, \"required\": [\"location\"]}}}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}\n<arg_key>{arg-key-1}</arg_key>\n<arg_value>{arg-value-1}</arg_value>\n<arg_key>{arg-key-2}</arg_key>\n<arg_value>{arg-value-2}</arg_value>\n...\n</tool_call>\n```\n\nThe `<tool_call>{function-name}` / `<arg_key>` / `<arg_value>` lines above are part of the **prompt text** (the format spec the model is told to follow), not an example call. This tools turn is emitted only when `tools` is non-empty, and it is closed implicitly by the next role marker (e.g. a user-supplied `<|system|>` or the first `<|user|>`), with no blank line between them.\n\n## Tool-call format\n\nThe model emits a call as an `<tool_call>` block: the function **name on the same line** as the opening tag, a newline, then one `<arg_key>…</arg_key>` + `<arg_value>…</arg_value>` pair per argument, closed by `</tool_call>`. Minimal single call (assistant generation in thinking mode; reasoning shown for realism):\n\n```text\n<think>The user wants the weather in Beijing. I'll call get_weather.</think>\n<tool_call>get_weather\n<arg_key>location</arg_key>\n<arg_value>Beijing</arg_value>\n<arg_key>unit</arg_key>\n<arg_value>celsius</arg_value>\n</tool_call>\n```\n\nAnatomy and value encoding (this is the single most error-prone part):\n\n- The function name is the text between `<tool_call>` and the first newline — there is **no** wrapping tag around it and **no** space after `<tool_call>`.\n- Each argument is two adjacent elements: `<arg_key>name</arg_key>` then `<arg_value>value</arg_value>`, conventionally one pair per line.\n- **Argument values are NOT uniformly JSON.** The template renders each value as `value | tojson(ensure_ascii=False) if value is not string else value`:\n  - **string** values are emitted **raw, without surrounding quotes** → `<arg_value>Beijing</arg_value>` (not `\"Beijing\"`).\n  - **non-string** values (number, boolean, null, object, array) are JSON-encoded → `<arg_value>3</arg_value>`, `<arg_value>true</arg_value>`, `<arg_value>{\"k\": 1}</arg_value>`.\n- A **zero-argument** call has no pairs: the name is followed by a newline and the closer — `<tool_call>get_time\\n</tool_call>`.\n\nBecause string values lose their quotes, a parser must decide per argument whether to JSON-decode or treat the value as a literal string. Both reference parsers do this by consulting the tool's JSON Schema: if the parameter's type is `string`, the raw text is taken as-is; otherwise the value is JSON-decoded (with `ast.literal_eval` and raw-string fallbacks). The model is trained to follow the schema, so it emits a bare string exactly when the parameter is string-typed.\n\n## Multiple / parallel tool calls\n\nTwo or more calls in one turn are emitted as consecutive `<tool_call>…</tool_call>` blocks separated by a single newline (no wrapper element around the set). Raw assistant emission for two parallel calls with mixed argument types:\n\n```text\n<think>Two cities. Call get_weather twice in parallel.</think>\n<tool_call>get_weather\n<arg_key>location</arg_key>\n<arg_value>Beijing</arg_value>\n<arg_key>unit</arg_key>\n<arg_value>celsius</arg_value>\n</tool_call>\n<tool_call>get_weather\n<arg_key>location</arg_key>\n<arg_value>Shanghai</arg_value>\n<arg_key>days</arg_key>\n<arg_value>3</arg_value>\n<arg_key>verbose</arg_key>\n<arg_value>true</arg_value>\n</tool_call>\n```\n\nNote `Beijing`/`Shanghai`/`celsius` (string) are bare, while `3` (number) and `true` (boolean) are JSON literals. Parsers split on the non-greedy `<tool_call>.*?</tool_call>` regex, so any number of calls is supported; each becomes a separate entry in `tool_calls[]`.\n\n## Tool-result format\n\nResults are returned in an **observation** turn. For a single result: the `<|observation|>` marker, a newline, then the result wrapped in `<tool_response>` / `</tool_response>`:\n\n```text\n<|observation|>\n<tool_response>\n{\"temperature\": 26, \"unit\": \"celsius\", \"condition\": \"Sunny\"}\n</tool_response>\n```\n\nThe content between the tags is inserted **verbatim** (callers typically pass a JSON string, but any text is allowed). For **multiple** results from a set of parallel calls, the `<|observation|>` marker appears **once** and each result gets its own `<tool_response>` block (consecutive `tool`-role messages are merged under a single observation turn):\n\n```text\n<|observation|>\n<tool_response>\n{\"temperature\": 26, \"condition\": \"Sunny\"}\n</tool_response>\n<tool_response>\n{\"temperature\": 30, \"condition\": \"Cloudy\"}\n</tool_response>\n```\n\nThe chat template reads **only** the tool message's `content` — it does not consult any `tool_call_id`. Results are therefore correlated to calls **positionally / by order**, not by an embedded id (GLM's wire format carries no per-call id; see API mapping).\n\n## End-to-end example\n\nA complete multi-turn weather exchange. These are the exact locally rendered streams; newlines inside a turn are literal and turns are otherwise contiguous (no separators between markers).\n\n**Stage 1 — prompt fed to the model** (`tools` set, one prior system message, `add_generation_prompt=True`, thinking mode):\n\n```text\n[gMASK]<sop><|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_weather\", \"description\": \"Get current weather for a city\", \"parameters\": {\"type\": \"object\", \"properties\": {\"location\": {\"type\": \"string\", \"description\": \"City name\"}, \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]}}, \"required\": [\"location\"]}}}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}\n<arg_key>{arg-key-1}</arg_key>\n<arg_value>{arg-value-1}</arg_value>\n<arg_key>{arg-key-2}</arg_key>\n<arg_value>{arg-value-2}</arg_value>\n...\n</tool_call><|system|>\nYou are a helpful assistant.<|user|>\nWhat's the weather in Beijing?<|assistant|>\n```\n\n**Assistant generation** (model output; it ends by emitting `<|observation|>`, an EOS id, so decoding stops there; server returns `finish_reason: \"tool_calls\"`):\n\n```text\n<think>The user wants the weather in Beijing. I'll call get_weather.</think>\n<tool_call>get_weather\n<arg_key>location</arg_key>\n<arg_value>Beijing</arg_value>\n<arg_key>unit</arg_key>\n<arg_value>celsius</arg_value>\n</tool_call>\n```\n\n**Stage 2 — prompt for the next turn**, after appending the assistant tool-call turn and the tool result, then `add_generation_prompt=True`:\n\n```text\n[gMASK]<sop><|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_weather\", \"description\": \"Get current weather for a city\", \"parameters\": {\"type\": \"object\", \"properties\": {\"location\": {\"type\": \"string\", \"description\": \"City name\"}, \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]}}, \"required\": [\"location\"]}}}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}\n<arg_key>{arg-key-1}</arg_key>\n<arg_value>{arg-value-1}</arg_value>\n<arg_key>{arg-key-2}</arg_key>\n<arg_value>{arg-value-2}</arg_value>\n...\n</tool_call><|system|>\nYou are a helpful assistant.<|user|>\nWhat's the weather in Beijing?<|assistant|>\n<think>The user wants the weather in Beijing. I'll call get_weather.</think>\n<tool_call>get_weather\n<arg_key>location</arg_key>\n<arg_value>Beijing</arg_value>\n<arg_key>unit</arg_key>\n<arg_value>celsius</arg_value>\n</tool_call><|observation|>\n<tool_response>\n{\"temperature\": 26, \"unit\": \"celsius\", \"condition\": \"Sunny\"}\n</tool_response><|assistant|>\n```\n\n**Final assistant generation** (natural-language answer, terminated by `<|endoftext|>`; `finish_reason: \"stop\"`):\n\n```text\n<think>Got it, 26C and sunny.</think>\nIt's 26°C and sunny in Beijing right now.\n```\n\nTwo subtleties visible above: (1) the reasoning of the assistant tool-call turn is **preserved** in Stage 2 only because it is the segment after the last user message; with another user turn after it, that `<think>…</think>` would be re-rendered empty. (2) The tool-call turn and the observation turn abut directly (`</tool_call><|observation|>`), and the observation abuts the next assistant marker (`</tool_response><|assistant|>`).\n\nFor **non-thinking** mode the user text carries the soft switch and the generation prompt pre-fills an empty think span:\n\n```text\n<|user|>\nHi there/nothink<|assistant|>\n<think></think>\n```\n\n## OpenAI-compatible API mapping\n\nWith a server parser active (`--tool-call-parser glm45 --reasoning-parser glm45`), the raw stream maps onto Chat Completions as follows:\n\n- `choices[].finish_reason` = `\"tool_calls\"` when the output contained at least one `<tool_call>` (otherwise `\"stop\"`).\n- `choices[].message.content` = the text **before** the first `<tool_call>` (normalized to `null` if empty/whitespace). The `<think>…</think>` reasoning is removed by the reasoning parser and surfaced separately as `message.reasoning_content`.\n- `choices[].message.tool_calls[]` — one entry per `<tool_call>…</tool_call>` block:\n  - `.id` = a **server-generated** id (e.g. vLLM's `make_tool_call_id()`), **not** present in the model output. GLM emits no per-call id in the stream.\n  - `.type` = `\"function\"`.\n  - `.function.name` = the text after `<tool_call>` up to the first newline.\n  - `.function.arguments` = a **JSON string** (an object), reconstructed from the `<arg_key>`/`<arg_value>` pairs with per-argument typing from the tool schema. vLLM returns `json.dumps(arg_dct, ensure_ascii=False)`, e.g. `\"{\\\"location\\\": \\\"Beijing\\\", \\\"unit\\\": \\\"celsius\\\"}\"`. Clients `json.loads()` it before use.\n- **Request side — tool results** are sent back as `role: \"tool\"` messages, e.g.:\n\n  ```json\n  {\"role\": \"tool\", \"tool_call_id\": \"call_abc123\", \"content\": \"{\\\"temperature\\\": 26, \\\"unit\\\": \\\"celsius\\\", \\\"condition\\\": \\\"Sunny\\\"}\"}\n  ```\n\n  The chat template renders only `content` (inside `<tool_response>`); `tool_call_id` is **ignored by the template** and matters only for the client's own bookkeeping. Order results to match the calls.\n- **Request side — assistant tool-call history**: the OpenAI shape carries `function.arguments` as a JSON **string**, but the chat template iterates `arguments.items()` and therefore needs an **object**. vLLM/SGLang parse the string back into a dict before rendering; if you call `tokenizer.apply_chat_template` directly, pass `arguments` as a dict (and optionally `reasoning_content` as a string) or the template will raise.\n- Disable thinking via `extra_body={\"chat_template_kwargs\": {\"enable_thinking\": false}}` (OpenAI Python client) — this flips the template to the `/nothink` + pre-filled `<think></think>` path.\n\n## Parsing notes & gotchas\n\n- **String values are unquoted; typing needs the schema.** The decisive rule: a `<arg_value>` is a literal string iff the parameter is string-typed in the tool's JSON Schema; otherwise it is JSON. vLLM's `_is_string_type` and SGLang's `get_argument_type` both walk `properties[arg].type` (handling `anyOf`/`oneOf`/`enum`/`allOf`/type-arrays). If the schema is missing/loose, they fall back to \"try `json.loads`, then `ast.literal_eval`, then treat as string\" — so a bare word like `celsius` survives as a string, while `26` becomes a number. A string value that *looks* like JSON (e.g. a parameter typed `string` whose value is `{\"a\":1}`) is correctly kept as the literal string only because the schema says `string`.\n- **Extraction regexes (GLM-4.5/4.6).** vLLM: calls via `<tool_call>.*?</tool_call>` (DOTALL); name/body via `<tool_call>([^\\n]*)\\n(.*)</tool_call>`; pairs via `<arg_key>(.*?)</arg_key>\\s*<arg_value>(.*?)</arg_value>`. The name regex **requires a newline** after the name — matching the 4.5/4.6 template. SGLang uses an equivalent `(?:\\\\n|\\n)` form so it also tolerates literal escaped `\\n`.\n- **`</arg_value>` in a value breaks parsing.** Values are captured non-greedily up to the next `</arg_value>`; a value whose text contains `</arg_value>` (or `</tool_call>`) truncates early. There is no escaping mechanism in the wire format.\n- **Tool calls are parsed from `content` only, not from reasoning.** A `<tool_call>` emitted inside `<think>…</think>` is ignored by the tool parser (vLLM's reasoning/tool parsers cooperate so only post-`</think>` content is scanned). Don't expect calls made \"while thinking\" to fire.\n- **Guided decoding is suppressed for GLM.** For `tool_choice: \"required\"` or a named tool, vLLM deliberately does **not** apply JSON structured-outputs/guided decoding, because that would force JSON output and conflict with GLM's XML syntax; the parser extracts from free-form XML instead.\n- **`skip_special_tokens` must be off.** Although the tool/think tags are `special: false`, vLLM forces `skip_special_tokens = False` when tools are enabled (defensive against transformers 5.x detokenization changes) so the literal `<tool_call>`/`</tool_call>` text survives for the regex.\n- **Streaming.** Long string arguments used to be buffered until the closing tag (vLLM issue #32829); the current parser re-parses the accumulated text each delta and emits only the diff, streaming incremental string content with an open-quote-then-fill strategy and holding back any partial trailing tag (`partial_tag_overlap`). The streamed tool name is the text before the first `\\n` or `<arg_key>`. SGLang implements the same as an explicit XML→JSON state machine (`INIT → IN_KEY → WAITING_VALUE → IN_VALUE`). Malformed tails (a missing `</arg_value>` before `</tool_call>`) are closed off heuristically.\n- **Lineage — GLM-4.5 vs GLM-4.6:** identical wire format and identical `chat_template.jinja` (same content hash); the same `glm45` parser serves both.\n- **Lineage — GLM-4.7 / GLM-5 changed the format.** Newer models drop the structural newlines: the function name may sit **directly** before the first `<arg_key>` (no newline), zero-argument calls may be `<tool_call>func</tool_call>`, and parallel calls may be emitted **back-to-back with no separator** (`…</tool_call><tool_call>…`). These require the distinct `Glm47MoeModelToolParser` (vLLM, `structural_tag_model=\"glm_4_7\"`) / `Glm47MoeDetector` (SGLang), whose `func_detail_regex` makes the newline and the argument section optional (`<tool_call>\\s*(\\S+?)\\s*(<arg_key>.*)?</tool_call>`). Do **not** use a GLM-4.7 stream to validate a GLM-4.5 parser or vice versa.\n\n## Sources\n\n- Chat template (authoritative; rendered locally for the byte-exact streams), GLM-4.5 commit `cbb2c7c…`: https://huggingface.co/zai-org/GLM-4.5/resolve/main/chat_template.jinja — the `blob`/web path redirects to the model-card API; verified via the raw `resolve/main` cache.\n- Identical GLM-4.6 template (same content hash, confirming shared format): https://huggingface.co/zai-org/GLM-4.6/resolve/main/chat_template.jinja\n- Special-token IDs and `special` flags (`added_tokens_decoder`, `additional_special_tokens`): https://huggingface.co/zai-org/GLM-4.5/resolve/main/tokenizer_config.json\n- Stop tokens (`eos_token_id = [151329, 151336, 151338]`): https://huggingface.co/zai-org/GLM-4.5/resolve/main/generation_config.json\n- Model card (server flags `--tool-call-parser glm45 --reasoning-parser glm45`, `enable_thinking` switch, parser links): https://huggingface.co/zai-org/GLM-4.5\n- vLLM GLM-4.5/4.6 tool parser (`Glm4MoeModelToolParser`: regexes, schema-driven string typing, JSON-string `arguments`, streaming, `skip_special_tokens`): https://github.com/vllm-project/vllm/blob/main/vllm/tool_parsers/glm4_moe_tool_parser.py\n- vLLM GLM-4.7 tool parser (`Glm47MoeModelToolParser`: same-line name, optional/zero args): https://github.com/vllm-project/vllm/blob/main/vllm/tool_parsers/glm47_moe_tool_parser.py\n- SGLang GLM-4.5/4.6 detector (`Glm4MoeDetector`: format docstring, XML→JSON state machine, argument typing): https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/function_call/glm4_moe_detector.py\n- SGLang GLM-4.7 detector (`Glm47MoeDetector`: newline-less / back-to-back calls): https://github.com/sgl-project/sglang/blob/main/python/sglang/srt/function_call/glm47_moe_detector.py\n- vLLM tool-calling docs: https://docs.vllm.ai/en/latest/features/tool_calling/\n",
 	"toolconv/harmony.md": "# OpenAI Harmony response format\n\nHarmony is the response format OpenAI trained its open-weight `gpt-oss` models on (`gpt-oss-20b`, `gpt-oss-120b`, released August 2025). It defines the conversation envelope, the multi-channel reasoning/answer separation, and the function-calling wire syntax. The models will not work correctly if prompted without it. The format deliberately mirrors the OpenAI *Responses* API (roles, channels, recipients) rather than the older Chat Completions shape.\n\nTokens are produced with the `o200k_harmony` encoding (the `o200k_base` BPE vocab plus a block of Harmony special tokens; see the table below). The reference renderer/parser is the Rust crate `openai-harmony` (Python bindings: `pip install openai-harmony`; encoding name `HarmonyEncodingName.HARMONY_GPT_OSS`).\n\nYou only deal with raw Harmony if you build your own inference loop. Served through an OpenAI-compatible endpoint the server handles it for you:\n\n- **Ollama / LM Studio / HuggingFace**: Harmony is applied internally; you send normal OpenAI-style JSON.\n- **vLLM**: `vllm serve openai/gpt-oss-120b --enable-auto-tool-choice --tool-call-parser openai --reasoning-parser openai_gptoss`. Note the tool-call parser flag is `openai` (not `harmony`). vLLM also exposes a Harmony-native path through the `/v1/responses` endpoint.\n- **SGLang**: `python3 -m sglang.launch_server --model-path openai/gpt-oss-20b --reasoning-parser gpt-oss --tool-call-parser gpt-oss` (in NVIDIA Dynamo disaggregated mode: `--dyn-tool-call-parser harmony --dyn-reasoning-parser gpt_oss`).\n\nThe chat template shipped with the gpt-oss weights renders these same token sequences from the standard `messages`/`tools` arrays.\n\n## Special tokens\n\nAll Harmony control tokens have the literal form `<|type|>` (ASCII pipes `|`, U+007C — no unicode variants). They are real single tokens in `o200k_harmony`, not text that is BPE-split. The structurally meaningful ones:\n\n| Token (verbatim) | Token ID | Purpose |\n| :--------------- | :------- | :------ |\n| `<\\|start\\|>`     | `200006` | Begins a message; immediately followed by the header (role, optional recipient/channel/content-type). |\n| `<\\|end\\|>`       | `200007` | Ends a fully-formed message. |\n| `<\\|message\\|>`   | `200008` | Header → content transition. Everything after it (until a stop/end token) is the message body. |\n| `<\\|channel\\|>`   | `200005` | Introduces the channel field of the header (`analysis` / `commentary` / `final`). |\n| `<\\|constrain\\|>` | `200003` | Marks the content-type / constrained-decoding format in a tool-call header (e.g. `<\\|constrain\\|>json`). |\n| `<\\|return\\|>`    | `200002` | Stop token: the model finished its final answer. Decode-time only (see normalization note). |\n| `<\\|call\\|>`      | `200012` | Stop token: the model is emitting a tool call and wants it executed. |\n\n`<|return|>` and `<|call|>` are the two valid generation stop tokens — halt inference on either.\n\nThe encoding also defines (same `o200k_harmony` block, IDs `199998`–`200013`) `<|startoftext|>` (199998), `<|endoftext|>` (199999), and reserved slots `<|reserved_200000|>`, `<|reserved_200001|>`, `<|reserved_200004|>`, `<|reserved_200009|>`–`<|reserved_200011|>`, `<|reserved_200013|>`, plus a bulk reserved range `<|reserved_200014|>`…`<|reserved_201088|>`. The renderer additionally knows the names `<|refusal|>`, `<|untrusted|>`, `<|end_untrusted|>`, `<|meta_end|>` but they are not part of the committed gpt-oss vocabulary and do not appear in normal traffic.\n\n## Roles / channels / turn structure\n\n**Message envelope.** Every message is:\n\n```text\n<|start|>{header}<|message|>{content}<|end|>\n```\n\n`{header}` always begins with the role and may carry an optional recipient (`to=...`), channel, and content-type. A completed message ends with `<|end|>`; an assistant message being generated ends instead with a stop token (`<|return|>` or `<|call|>`).\n\n**Roles** (five). The instruction hierarchy used to resolve conflicts is `system` > `developer` > `user` > `assistant` > `tool`.\n\n| Role | Purpose |\n| :--- | :------ |\n| `system` | Identity, knowledge cutoff / current date, reasoning effort, valid-channels declaration, built-in tools. NOT the user-facing \"system prompt\". |\n| `developer` | The conventional \"system prompt\": instructions + the `# Tools` function declarations + (optional) structured-output schema. |\n| `user` | End-user input. |\n| `assistant` | Model output. Carries a channel and, for tool calls, a recipient. |\n| `tool` | Output of an executed tool. The message's *author/role is the tool's own name* (e.g. `functions.get_current_weather`), not the literal word `tool`. |\n\n**Channels** (assistant output only; the channel is mandatory on every assistant message):\n\n| Channel | Purpose |\n| :------ | :------ |\n| `analysis` | Raw chain-of-thought (reasoning). Not held to the same safety bar as `final`; do not show to end users. Built-in `python`/`browser` calls usually go here. |\n| `commentary` | Function tool calls, and user-visible \"preambles\" (action plans) before calling multiple tools. |\n| `final` | The user-facing answer. |\n\n**Reasoning effort** is set in the system message as `Reasoning: high` (or `medium` / `low`; default is medium). The model emits CoT into `analysis` and the answer into `final`.\n\n**CoT carry-over rule.** On the next turn, drop prior `analysis` messages *if* the last assistant turn ended in a `final` message. The exception is an in-progress tool-calling turn: the `analysis` that preceded a tool call MUST be fed back in alongside the tool result so the model can continue its reasoning (the `openai-harmony` renderer does this via `RenderConversationConfig { auto_drop_analysis: true }`).\n\n## Tool definitions\n\nFunction tools are advertised in the **developer** message under a `# Tools` section, inside a TypeScript-style `namespace functions { ... }`. (Built-in `browser`/`python` tools are instead declared in the **system** message under their own `# Tools` / `## browser` / `## python` headings.) The renderer converts each JSON Schema into a TS type with these rules:\n\n- No-arg function → `type name = () => any;`\n- With args → the single parameter is named `_` and its object type is inlined: `type name = (_: { ... }) => any;`\n- Return type is always `any`.\n- A property `description` becomes a `//` comment on the line *above* the field; a JSON Schema `title` renders as `// TITLE` followed by a `//` blank-comment line; `examples` render as `// Examples:` then `// - \"value\"` lines.\n- Optional (non-`required`) fields get a trailing `?`. A `default` renders as a trailing `// default: <value>` comment; an `enum` becomes a `\"a\" | \"b\"` union; `oneOf` becomes a multi-line `|` union; JSON `integer` maps to TS `number`.\n- One blank line separates function definitions; the block closes with `} // namespace functions`.\n\nIf the developer message has no instruction text, the `# Instructions` heading is omitted and the message is just the `# Tools` block. When any function is defined, the system message gains the routing line `Calls to these tools must go to the commentary channel: 'functions'.`\n\nVerbatim developer-message example (instructions + two functions), exactly as the renderer emits it:\n\n```text\n<|start|>developer<|message|># Instructions\n\nUse a friendly tone.\n\n# Tools\n\n## functions\n\nnamespace functions {\n\n// Gets the location of the user.\ntype get_location = () => any;\n\n// Gets the current weather in the provided location.\ntype get_current_weather = (_: {\n// The city and state, e.g. San Francisco, CA\nlocation: string,\nformat?: \"celsius\" | \"fahrenheit\", // default: celsius\n}) => any;\n\n// Gets the current weather in the provided list of locations.\ntype get_multiple_weathers = (_: {\n// List of city and state, e.g. [\"San Francisco, CA\", \"New York, NY\"]\nlocations: string[],\nformat?: \"celsius\" | \"fahrenheit\", // default: celsius\n}) => any;\n\n} // namespace functions<|end|>\n```\n\n## Tool-call format\n\nA function call is an **assistant** message on the **commentary** channel, addressed to the tool via recipient `to=functions.<name>`, with the JSON arguments as the body, terminated by the `<|call|>` stop token.\n\nThe recipient may appear in the *role section* or the *channel section* of the header — both are valid Harmony and the parser accepts either. The model commonly emits it in the channel section. The pi renderer omits the optional content-type marker:\n\n```text\n<|start|>assistant<|channel|>commentary to=functions.get_current_weather<|message|>{\"location\":\"San Francisco, CA\"}<|call|>\n```\n\nSome Harmony serializers include an explicit JSON content type and place the recipient in the role section instead:\n\n```text\n<|start|>assistant to=functions.get_current_weather<|channel|>commentary <|constrain|>json<|message|>{\"location\":\"San Francisco, CA\"}<|call|>\n```\n\nThe arguments body is a raw JSON object. The optional `<|constrain|>json` content-type signals JSON (and is the hook for constrained/grammar-based decoding); the content-type may also be a bare word such as `code` (seen with built-in tools). Built-in tools differ only in channel and recipient: they typically render on `analysis`, with recipient `browser.search` / `browser.open` / `browser.find` or always `python`.\n\n## Multiple / parallel tool calls\n\nHarmony has no special \"parallel\" wrapper. Multiple calls are just multiple consecutive messages. The model may first emit an optional **preamble** — a *user-visible* assistant message on the `commentary` channel (unlike `analysis`, this is meant to be shown) — then one tool-call message per function. Each individual call still ends with its own `<|call|>` stop token, so a host that stops on `<|call|>` collects calls one at a time, executes, feeds the result back, and resumes:\n\n```text\n<|channel|>analysis<|message|>{reasoning}<|end|><|start|>assistant<|channel|>commentary<|message|>**Action plan**:\n1. Generate an HTML file\n2. Generate a JavaScript for the Node.js server\n3. Start the server\n---\nWill start executing the plan step by step<|end|><|start|>assistant<|channel|>commentary to=functions.generate_file<|message|>{\"template\": \"basic_html\", \"path\": \"index.html\"}<|call|>\n```\n\n## Tool-result format\n\nThe executed tool's output is fed back as a message whose **author/role is the tool's name**, addressed back to the assistant (`to=assistant`), on the **commentary** channel, ending with `<|end|>`. This is the canonical (recommended) form:\n\n```text\n<|start|>functions.get_current_weather to=assistant<|channel|>commentary<|message|>{\"sunny\": true, \"temperature\": 20}<|end|>\n```\n\nThe header ordering is `{toolname} to=assistant<|channel|>commentary`. Built-in tool results follow the same shape (e.g. `<|start|>browser.search to=assistant<|channel|>commentary<|message|>{\"result\": \"https://openai.com/\"}<|end|>`). The minimal form the renderer accepts when channel/recipient are not set on the message is just `<|start|>{toolname}<|message|>{output}<|end|>`, but emitting the full `to=assistant<|channel|>commentary` header is what the reference parser round-trips and is recommended. After appending the result, restart generation by emitting the next `<|start|>assistant`.\n\n## End-to-end example\n\nComplete multi-turn weather exchange: system + developer prompt → user question → assistant analysis CoT → assistant commentary tool call → tool result → assistant final answer. This is a single contiguous token stream (newlines inside headers are only between top-level messages for readability; in practice messages are concatenated with no separator).\n\n```text\n<|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.\nKnowledge cutoff: 2024-06\nCurrent date: 2025-06-28\n\nReasoning: high\n\n# Valid channels: analysis, commentary, final. Channel must be included for every message.\nCalls to these tools must go to the commentary channel: 'functions'.<|end|><|start|>developer<|message|># Instructions\n\nUse a friendly tone.\n\n# Tools\n\n## functions\n\nnamespace functions {\n\n// Gets the current weather in the provided location.\ntype get_current_weather = (_: {\n// The city and state, e.g. San Francisco, CA\nlocation: string,\nformat?: \"celsius\" | \"fahrenheit\", // default: celsius\n}) => any;\n\n} // namespace functions<|end|><|start|>user<|message|>What is the weather like in SF?<|end|><|start|>assistant<|channel|>analysis<|message|>User wants the weather in San Francisco. Use get_current_weather.<|end|><|start|>assistant<|channel|>commentary to=functions.get_current_weather<|message|>{\"location\":\"San Francisco, CA\"}<|call|><|start|>functions.get_current_weather to=assistant<|channel|>commentary<|message|>{\"sunny\": true, \"temperature\": 20}<|end|><|start|>assistant<|channel|>final<|message|>It's sunny and about 20°C in San Francisco right now.<|return|>\n```\n\nTurn boundaries:\n\n- The host stops generation at `<|call|>`, parses the `commentary` call, runs `get_current_weather`, and appends the `functions.get_current_weather to=assistant` result message.\n- It then appends `<|start|>assistant` and resumes. The preceding `analysis` message is kept (the turn ended in a tool call, not a `final`), so the model can continue its reasoning.\n- Generation stops at `<|return|>`. When this turn is persisted into history for a *later* turn, normalize the trailing `<|return|>` to `<|end|>` (see next note).\n\n**`<|return|>` normalization.** `<|return|>` is a decode-time stop token only. When you store the assistant's reply into history for the next turn, replace the trailing `<|return|>` with `<|end|>` so every stored message is a well-formed `<|start|>{header}<|message|>{content}<|end|>`. (For supervised training targets, ending the example with `<|return|>` is correct.)\n\n## OpenAI-compatible API mapping\n\nWhen a server (vLLM/SGLang/Ollama) bridges Harmony to Chat Completions JSON:\n\n- **`finish_reason`**: `tool_calls` when generation stopped on `<|call|>`; `stop` when it stopped on `<|return|>`.\n- **`message.tool_calls[]`**: one entry per `commentary` `to=functions.*` call. `function.name` is the recipient with the `functions.` namespace stripped (`get_current_weather`). `function.arguments` is a **JSON string** (the verbatim `<|message|>` body), matching OpenAI semantics — not a parsed object.\n- **`tool_call_id`**: Harmony has no native call ID. The server synthesizes one (e.g. `call_abc123`) and is responsible for correlating the follow-up `role:\"tool\"` message back to the Harmony tool-result envelope (recipient `to=functions.<name>` / call order).\n- **Tool result messages** (`{\"role\":\"tool\",\"tool_call_id\":...,\"content\":...}`) are rendered into `<|start|>{toolname} to=assistant<|channel|>commentary<|message|>{content}<|end|>`. The server maps `tool_call_id` → the original function name to build the `{toolname}` author.\n- **Reasoning**: `analysis`-channel text is surfaced as `reasoning_content` (vLLM/SGLang) or as a `reasoning`/`thinking` field, and is generally not echoed back on subsequent requests. `final`-channel text is the normal `message.content`. `commentary` preambles, if surfaced, also map to assistant content.\n- **`tools` / `tool_choice`** request fields are compiled by the chat template into the developer-message `namespace functions { ... }` block; the system message gains the commentary-routing line.\n\n## Parsing notes & gotchas\n\n- **Two stop tokens.** Always stop on both `<|return|>` and `<|call|>`. Stopping only on `<|return|>` will run past tool calls; stopping only on `<|end|>` is wrong for assistant generation.\n- **Recipient position varies.** `to=functions.<name>` may be in the role section (`<|start|>assistant to=...<|channel|>commentary`) or the channel section (`<|channel|>commentary to=...`). A parser must accept both.\n- **Channel is mandatory** on assistant messages; the system message even reminds the model (\"Channel must be included for every message.\"). Missing-channel output is malformed.\n- **Tool author, not `tool`.** The tool-result message's role is the tool's *name* (`functions.get_current_weather`), not the literal string `tool`. Splitting `functions.x` into namespace + function is the parser's job.\n- **CoT dropping is conditional.** Drop `analysis` only when the previous assistant turn ended on `final`. Dropping the `analysis` that immediately precedes a `<|call|>` breaks multi-step tool reasoning.\n- **`arguments` is a string.** Do not double-encode. The body after `<|message|>` is already serialized JSON; pass it through as the `arguments` string.\n- **Content-type variants.** `<|constrain|>json` is optional. If present, it is metadata, not a guarantee of valid JSON. Enforce JSON validity with constrained decoding / your own grammar — the prompt format alone does not guarantee schema adherence (same caveat applies to structured-output `# Response Formats`).\n- **Streaming.** Use a stateful parser (the library ships `StreamableParser`) so partial UTF-8 and the header/channel/recipient/content-type fields are reconstructed incrementally; a naive substring scan mishandles multi-byte splits and the optional header fields. `parse_messages_from_completion_tokens` takes `strict=True|False` — `strict=False` tolerates some malformed headers. Do not pass the trailing stop token into the parser.\n- **Encoding.** Use `o200k_harmony` (the `o200k_base` ranks plus the Harmony specials above). Treat the `<|...|>` tokens as atomic special tokens during both encode and decode; encoding them as ordinary text yields different ranks and corrupts the stream.\n\n## Sources\n\n- OpenAI Cookbook — OpenAI harmony response format: https://cookbook.openai.com/articles/openai-harmony\n- openai/harmony renderer (README): https://github.com/openai/harmony\n- openai/harmony canonical format guide: https://raw.githubusercontent.com/openai/harmony/main/docs/format.md\n- openai/harmony special-token registry (`o200k_harmony` IDs): https://raw.githubusercontent.com/openai/harmony/main/src/tiktoken_ext/public_encodings.rs\n- openai/harmony renderer/parser tests and schema→TS logic: https://raw.githubusercontent.com/openai/harmony/main/src/tests.rs , https://raw.githubusercontent.com/openai/harmony/main/src/encoding.rs\n- openai/harmony test fixtures (verbatim rendered streams): `test-data/test_render_functions_with_parameters.txt`, `test-data/test_does_not_drop_if_ongoing_analysis.txt`, `test-data/test_tool_response_parsing.txt`, `test-data/test_streamable_parser.txt`, `test-data/test_browser_and_function_tool.txt` (https://github.com/openai/harmony/tree/main/test-data)\n- vLLM tool calling / gpt-oss parser flags: https://docs.vllm.ai/en/latest/features/tool_calling/\n- SGLang gpt-oss usage (`--tool-call-parser gpt-oss`): https://docs.sglang.io/basic_usage/gpt_oss.html\n",
 	"toolconv/kimi-k2.md": "# Kimi K2 tool-calling format\n\nNative tool-calling convention of Moonshot AI's **Kimi K2** family (`moonshotai/Kimi-K2-Instruct` and `-Base`, `model_type: \"kimi_k2\"`, 1T-param MoE). It is a ChatML-like envelope built on a TikToken tokenizer (160K vocab): every turn is `<|im_{class}|>{name}<|im_middle|>{body}<|im_end|>`, and tool calls are emitted inside the assistant turn wrapped by a dedicated `<|tool_calls_section_begin|>…<|tool_calls_section_end|>` block. All control tokens are plain ASCII `<|…|>` forms (no fullwidth/unicode variants, unlike DeepSeek). An inference server turns the raw stream into OpenAI-style `tool_calls` with a parser: vLLM and SGLang both expose `--tool-call-parser kimi_k2` (vLLM additionally requires `--enable-auto-tool-choice`). The chat template (a standalone `chat_template.jinja` since the 2025.8.11 update) injects the tool schemas and renders the per-turn markers.\n\nThis document was verified against the model card, the official `docs/tool_call_guidance.md` and `docs/deploy_guidance.md` (GitHub `MoonshotAI/Kimi-K2`), the raw `chat_template.jinja` and `tokenizer_config.json` from the HF repo (rendered locally for the byte-exact streams below), and the vLLM `kimi_k2` tool parser source.\n\n## Special tokens\n\nThe five tool-call markers required for manual parsing, plus the ChatML envelope markers. Token IDs are from `tokenizer_config.json` (`added_tokens_decoder`).\n\n| Token (verbatim) | ID | Purpose |\n|---|---|---|\n| `<\\|tool_calls_section_begin\\|>` | 163595 | Opens the tool-call section inside an assistant turn |\n| `<\\|tool_call_begin\\|>` | 163597 | Opens one individual tool call |\n| `<\\|tool_call_argument_begin\\|>` | 163598 | Separates the tool-call ID from its JSON arguments |\n| `<\\|tool_call_end\\|>` | 163599 | Closes one individual tool call |\n| `<\\|tool_calls_section_end\\|>` | 163596 | Closes the tool-call section |\n| `<\\|im_system\\|>` | 163594 | Start marker for system-class turns (`system`, `tool`, `tool_declare`) |\n| `<\\|im_user\\|>` | 163587 | Start marker for a user turn |\n| `<\\|im_assistant\\|>` | 163588 | Start marker for an assistant turn |\n| `<\\|im_middle\\|>` | 163601 | Separates the role/name header from the message body |\n| `<\\|im_end\\|>` | 163586 | Ends any turn |\n| `[BOS]` | 163584 | Sequence-begin token (see notes; not emitted by the chat template) |\n| `[EOS]` | 163585 | Sequence-end token |\n\nNotes on exactness:\n- The five tool tokens use ASCII pipe `|` (U+007C) and underscores; reproduce them exactly. There are no fullwidth pipe (`｜`) or `▁` variants in Kimi K2.\n- `<|im_middle|>` is the only envelope token whose ID (163601) is out of sequence with the others (163586–163599); a `163600` slot is unused.\n- Image inputs render via a content macro as the literal sequence `<|media_start|>image<|media_content|><|media_pad|><|media_end|>`. These media markers appear in the template but are **not** registered in `added_tokens_decoder`, so they tokenize as ordinary text rather than single special tokens. They are irrelevant to text tool calling and are listed here only for completeness.\n\n## Roles / channels / turn structure\n\nKimi K2 uses a ChatML-style envelope. Every message is rendered as:\n\n```text\n<|im_{class}|>{name}<|im_middle|>{body}<|im_end|>\n```\n\n- There are exactly **three** start-marker tokens, chosen by `role`:\n  - `user` → `<|im_user|>`\n  - `assistant` → `<|im_assistant|>`\n  - everything else (`system`, `tool`, and the synthetic `tool_declare`) → `<|im_system|>`\n- The `{name}` segment between the marker and `<|im_middle|>` is `message.name or message.role`. This is the only \"channel\"/sub-role label Kimi K2 has. For ordinary turns it is literally `system`, `user`, or `assistant`; for a tool-result turn it is the tool's `name` (the function name) when supplied, otherwise `tool`; for the tool-schema turn it is the literal `tool_declare`.\n- `<|im_end|>` terminates every turn. The chat template does **not** emit `[BOS]`/`[EOS]`; turn boundaries are purely `<|im_*|>` markers (the tokenizer is TikToken-based with `add_bos_token`/`add_eos_token` unset, and the manual-parse flow feeds the rendered template straight to `/completions`).\n- **Default system prompt:** if the first message is not a `system` message, the template injects `<|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|>` before the first turn.\n- **Generation prompt:** with `add_generation_prompt=True` the template ends with `<|im_assistant|>assistant<|im_middle|>`, and the model generates from there.\n- **Thinking/reasoning:** `Kimi-K2-Instruct` is a \"reflex-grade\" model with no long thinking, so there is no reasoning channel in this format. (Thinking variants are handled separately — vLLM ships a distinct `kimi_k2` reasoning parser keyed on a `</think>` token — but that is out of scope for the Instruct tool-call format documented here.)\n\n## Tool definitions\n\nAvailable tools are advertised in a single dedicated turn placed at the very top of the prompt (before any system/user turn), using the synthetic `tool_declare` sub-role under the `<|im_system|>` marker:\n\n```text\n<|im_system|>tool_declare<|im_middle|>{TOOLS_JSON}<|im_end|>\n```\n\n`{TOOLS_JSON}` is the standard OpenAI-style `tools` array serialized to JSON with **compact separators** `(',', ':')` (no spaces). The array elements are passed through verbatim, i.e. each is `{\"type\":\"function\",\"function\":{\"name\":…,\"description\":…,\"parameters\":{…}}}` with a JSON-Schema `parameters` object. Example (single tool, exactly as emitted):\n\n```text\n<|im_system|>tool_declare<|im_middle|>[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get weather information. Call this tool when the user needs to get weather information\",\"parameters\":{\"type\":\"object\",\"required\":[\"city\"],\"properties\":{\"city\":{\"type\":\"string\",\"description\":\"City name\"}}}}}]<|im_end|>\n```\n\nThe `tool_declare` turn is rendered only when `tools` is non-empty.\n\n## Tool-call format\n\nWhen the model decides to call a function, it emits — inside the assistant turn, after any natural-language content — a tool-calls section. Minimal single call (this is the assistant generation that follows `<|im_assistant|>assistant<|im_middle|>`):\n\n```text\n<|tool_calls_section_begin|><|tool_call_begin|>functions.get_weather:0<|tool_call_argument_begin|>{\"city\": \"Beijing\"}<|tool_call_end|><|tool_calls_section_end|>\n```\n\nAnatomy of one call:\n\n```text\n<|tool_call_begin|>  functions.{func_name}:{idx}  <|tool_call_argument_begin|>  {JSON arguments}  <|tool_call_end|>\n```\n\n- The token between `<|tool_call_begin|>` and `<|tool_call_argument_begin|>` is the **tool-call ID**, with the fixed form `functions.{func_name}:{idx}`.\n  - `functions.` is a literal prefix (it is not derived from the tool schema).\n  - `{func_name}` is the called function's name; the function name is recovered by parsing it back out of this ID, not from a separate field.\n  - `{idx}` is the **0-based call index** within the current assistant turn (`0` for the first call, `1` for the second, …).\n- After `<|tool_call_argument_begin|>` comes the raw JSON arguments object (e.g. `{\"city\": \"Beijing\"}`), terminated by `<|tool_call_end|>`.\n- All calls of the turn live between one `<|tool_calls_section_begin|>` / `<|tool_calls_section_end|>` pair. Any assistant text content precedes `<|tool_calls_section_begin|>`.\n- The whole assistant turn is still closed by `<|im_end|>` and the completion's `finish_reason` becomes `tool_calls`.\n\n## Multiple / parallel tool calls\n\nTwo or more calls in one turn are emitted as consecutive `<|tool_call_begin|>…<|tool_call_end|>` blocks inside a single section, with the index incrementing per call. Raw assistant emission for two parallel calls:\n\n```text\n<|tool_calls_section_begin|><|tool_call_begin|>functions.get_weather:0<|tool_call_argument_begin|>{\"city\": \"Beijing\"}<|tool_call_end|><|tool_call_begin|>functions.get_weather:1<|tool_call_argument_begin|>{\"city\": \"Shanghai\"}<|tool_call_end|><|tool_calls_section_end|>\n```\n\nNote the IDs `functions.get_weather:0` and `functions.get_weather:1` — same function, distinct trailing index. The index is per-turn (it resets to `0` in the next assistant turn).\n\n## Tool-result format\n\nTool execution results are fed back as a turn with `role: \"tool\"`. Because `tool` is not `user`/`assistant`, it renders under the `<|im_system|>` marker; the sub-role label is the message's `name` (the function name) when present, else `tool`. The body is a literal `## Return of {tool_call_id}` header line followed by the result content:\n\n```text\n<|im_system|>get_weather<|im_middle|>## Return of functions.get_weather:0\n{\"weather\": \"Sunny\"}<|im_end|>\n```\n\n- `{tool_call_id}` echoes the exact ID from the originating call (`functions.get_weather:0`), which is how the model correlates a result with the call that produced it.\n- The result `content` is inserted verbatim on the line after the header; callers typically pass a JSON string (e.g. `json.dumps(tool_result)`).\n- If the `tool` message omits `name`, the envelope becomes `<|im_system|>tool<|im_middle|>## Return of …`.\n\n## End-to-end example\n\nA complete multi-turn weather exchange. These are the exact rendered streams (system + user supplied explicitly; line breaks inside a turn are literal, turns are otherwise contiguous).\n\n**Stage 1 — prompt fed to the model** (`tools` set, `add_generation_prompt=True`):\n\n```text\n<|im_system|>tool_declare<|im_middle|>[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get weather information. Call this tool when the user needs to get weather information\",\"parameters\":{\"type\":\"object\",\"required\":[\"city\"],\"properties\":{\"city\":{\"type\":\"string\",\"description\":\"City name\"}}}}}]<|im_end|><|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|><|im_user|>user<|im_middle|>What's the weather like in Beijing today? Use the tool to check.<|im_end|><|im_assistant|>assistant<|im_middle|>\n```\n\n**Assistant generation** (model output; server reports `finish_reason: \"tool_calls\"`):\n\n```text\n<|tool_calls_section_begin|><|tool_call_begin|>functions.get_weather:0<|tool_call_argument_begin|>{\"city\": \"Beijing\"}<|tool_call_end|><|tool_calls_section_end|><|im_end|>\n```\n\n**Stage 2 — prompt for the next turn**, after appending the assistant tool-call turn and the tool result turn (`add_generation_prompt=True`):\n\n```text\n<|im_system|>tool_declare<|im_middle|>[{\"type\":\"function\",\"function\":{\"name\":\"get_weather\",\"description\":\"Get weather information. Call this tool when the user needs to get weather information\",\"parameters\":{\"type\":\"object\",\"required\":[\"city\"],\"properties\":{\"city\":{\"type\":\"string\",\"description\":\"City name\"}}}}}]<|im_end|><|im_system|>system<|im_middle|>You are Kimi, an AI assistant created by Moonshot AI.<|im_end|><|im_user|>user<|im_middle|>What's the weather like in Beijing today? Use the tool to check.<|im_end|><|im_assistant|>assistant<|im_middle|><|tool_calls_section_begin|><|tool_call_begin|>functions.get_weather:0<|tool_call_argument_begin|>{\"city\": \"Beijing\"}<|tool_call_end|><|tool_calls_section_end|><|im_end|><|im_system|>get_weather<|im_middle|>## Return of functions.get_weather:0\n{\"weather\": \"Sunny\"}<|im_end|><|im_assistant|>assistant<|im_middle|>\n```\n\n**Final assistant generation** (model produces natural-language answer terminated by `<|im_end|>`; `finish_reason: \"stop\"`):\n\n```text\nIt's sunny in Beijing today.<|im_end|>\n```\n\n## OpenAI-compatible API mapping\n\nWith a server parser active (`--tool-call-parser kimi_k2`), the raw stream maps onto the Chat Completions shape as follows:\n\n- `choices[].finish_reason` = `\"tool_calls\"` when the turn contained a tool-calls section (otherwise `\"stop\"`).\n- `choices[].message.tool_calls[]` — one entry per `<|tool_call_begin|>…<|tool_call_end|>` block:\n  - `.id` = the raw call ID verbatim, e.g. `\"functions.get_weather:0\"`.\n  - `.type` = `\"function\"`.\n  - `.function.name` = the function name parsed out of the ID. vLLM computes `id.split(\":\")[0].split(\".\")[-1]` → `\"get_weather\"`.\n  - `.function.arguments` = a **JSON string** (the raw text captured between `<|tool_call_argument_begin|>` and `<|tool_call_end|>`), e.g. `\"{\\\"city\\\": \\\"Beijing\\\"}\"`. Clients `json.loads()` it before use.\n- Tool results are sent back as messages of the form:\n\n  ```json\n  {\"role\": \"tool\", \"tool_call_id\": \"functions.get_weather:0\", \"name\": \"get_weather\", \"content\": \"{\\\"weather\\\": \\\"Sunny\\\"}\"}\n  ```\n\n  `tool_call_id` must equal the `id` returned for the call; `name` becomes the `<|im_system|>{name}<|im_middle|>` sub-role; `content` becomes the body after `## Return of …`.\n- Streaming: deltas arrive as `choices[].delta.tool_calls[]` with an `index`; the function `name`/`id` stream once the call header is complete, then `function.arguments` streams as incremental string fragments to be concatenated (standard OpenAI tool-call streaming assembly).\n\nMoonshot's hosted API (`platform.moonshot.ai`) exposes both OpenAI- and Anthropic-compatible endpoints; the Anthropic-compatible one scales temperature as `real_temperature = request_temperature * 0.6`. Recommended sampling temperature for `Kimi-K2-Instruct` is `0.6`.\n\n## Parsing notes & gotchas\n\n- **ID → name parsing differs between references.** The official `tool_call_guidance.md` extracts the name with `function_id.split('.')[1].split(':')[0]`, which assumes the ID is exactly `functions.{name}` with no extra dots. vLLM uses the more robust `function_id.split(\":\")[0].split(\".\")[-1]` (takes the last dot-segment before `:{idx}`). Prefer the vLLM form so function names containing `.` are handled.\n- **Extraction regexes differ too.** Guidance: `<\\|tool_call_begin\\|>\\s*(?P<tool_call_id>[\\w\\.]+:\\d+)\\s*<\\|tool_call_argument_begin\\|>\\s*(?P<function_arguments>.*?)\\s*<\\|tool_call_end\\|>`. vLLM: ID class is `[^<]+:\\d+` and the argument body uses a negative lookahead `(?:(?!<\\|tool_call_begin\\|>).)*?` so adjacent calls aren't merged. Both run with `DOTALL`.\n- **`skip_special_tokens` must be False.** The parser depends on the literal marker text surviving detokenization; vLLM forces `skip_special_tokens = False` when tools are enabled and `tool_choice != \"none\"`. If markers are stripped, no tool call is detected.\n- **Arguments are unvalidated raw text.** Whatever the model emits between the argument marker and `<|tool_call_end|>` is passed straight through as the `arguments` string; it must be valid JSON for downstream `json.loads`, and the model can emit malformed/truncated JSON. Validate before executing.\n- **Index semantics.** `{idx}` is the per-turn call counter starting at `0`; it is not a global counter and resets each assistant turn. Do not assume IDs are unique across turns — disambiguate by turn when persisting history.\n- **Streaming marker splits.** Section and call markers can be split across token boundaries. vLLM holds back any trailing suffix that partially matches a marker (`partial_tag_overlap`) to avoid leaking marker bytes into streamed content, and only streams a call's name once its header is fully received.\n- **`finish_reason` varies by engine.** The official guide explicitly warns the terminal `finish_reason` for tool calls \"may vary across different engines\"; loop on `finish_reason == \"tool_calls\"` but be defensive.\n- **Engine fallback.** Kimi K2 reuses the DeepSeek-V3 architecture; `config.json` sets `model_type: \"kimi_k2\"` so engines apply the right parser. If you force `model_type: \"deepseek_v3\"` as a compatibility workaround, no native Kimi tool parser is available and you must parse the `<|tool_calls_section_*|>` markers manually.\n- **Parser availability.** vLLM ships both a Python (`KimiK2ToolParser`) and a newer Rust tool parser; SGLang implements its own `kimi_k2` parser. All key off the same five markers and the `functions.{name}:{idx}` ID convention documented here.\n- **Whitespace artifact.** When no `system` message is supplied, the template injects the default system prompt and a small `\\n  ` (newline + two spaces) can appear before the first `<|im_user|>` marker. It is harmless (tokenizes around the markers), but supplying an explicit system message yields the clean streams shown above.\n\n## Sources\n\n- Model card (Tool Calling section, OpenAI-style example, deployment/API notes): https://huggingface.co/moonshotai/Kimi-K2-Instruct\n- Official tool-call guidance (markers, ID convention, manual parser, `extract_tool_call_info`): https://raw.githubusercontent.com/MoonshotAI/Kimi-K2/main/docs/tool_call_guidance.md (the HF `resolve`/`blob` paths redirected to the model card; verified against this GitHub raw file)\n- Deployment guide (`--tool-call-parser kimi_k2`, `--enable-auto-tool-choice`, SGLang flag, `model_type` fallback): https://raw.githubusercontent.com/MoonshotAI/Kimi-K2/main/docs/deploy_guidance.md\n- Chat template (`chat_template.jinja`, rendered locally for byte-exact streams): https://huggingface.co/moonshotai/Kimi-K2-Instruct/resolve/main/chat_template.jinja\n- Tokenizer config (special-token IDs in `added_tokens_decoder`): https://huggingface.co/moonshotai/Kimi-K2-Instruct/resolve/main/tokenizer_config.json\n- vLLM `kimi_k2` tool parser (markers, regex, name-parsing, `skip_special_tokens`, streaming): https://github.com/vllm-project/vllm/blob/main/vllm/tool_parsers/kimi_k2_tool_parser.py\n- vLLM PR adding the parser: https://github.com/vllm-project/vllm/pull/20789\n- vLLM tool-calling docs: https://docs.vllm.ai/en/latest/features/tool_calling/\n",