@oh-my-pi/pi-coding-agent 15.9.1 → 15.9.5

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

@@ -6,13 +6,13 @@ 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",
 	"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  wraps `tryEnforceStrictSchema` for provider call sites and consults\n  `PI_NO_STRICT` (env `PI_NO_STRICT`) for the global bypass.\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/ai/src/model-manager.ts` and\n`readModelCache`/`writeModelCache` in `model-cache.ts` cooperate via a\nschema-v3 `static_fingerprint` column on the `model_cache` SQLite table.\n\n- `fingerprintStatic(staticModels)` hashes the static catalog slice\n  (`Bun.hash(JSON.stringify(models))` in base36) and memoizes the result\n  in a per-process `WeakMap` keyed by the array reference. Multiple\n  cold-start arms calling `resolveProviderModels` with the same\n  `staticModels` array pay 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 schema v3 are dropped by the cache-version\ncheck; the column defaults to `''` for any row that survives a version\nupgrade so the fingerprint-equality check naturally fails closed and the\nfull 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## 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\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",
+	"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",
 	"bash-tool-runtime.md": "# Bash tool runtime\n\nThis document describes the **`bash` tool** runtime path used by agent tool calls, from command normalization to execution, truncation/artifacts, and rendering.\n\nIt also calls out where behavior diverges in interactive TUI, print mode, RPC mode, and user-initiated bang (`!`) shell execution.\n\n## Scope and runtime surfaces\n\nThere are two different bash execution surfaces in coding-agent:\n\n1. **Tool-call surface** (`toolName: \"bash\"`): used when the model calls the bash tool.\n   - Entry point: `BashTool.execute()`.\n   - Parameters include `command`, optional `env`, `timeout`, `cwd`, `pty`, and, when `async.enabled` is true, `async`.\n2. **User bang-command surface** (`!cmd` from interactive input or RPC `bash` command): session-level helper path.\n   - Entry point: `AgentSession.executeBash()`.\n\nBoth eventually use `executeBash()` in `src/exec/bash-executor.ts` for non-PTY execution, but only the tool-call path runs normalization/interception, optional managed background-job handling, and tool renderer logic.\n\n## End-to-end tool-call pipeline\n\n## 1) Input handling and parameter merge\n\n`BashTool.execute()` currently handles input before execution as follows:\n\n- validates optional `env` names against shell-variable syntax,\n- when `bash.stripTrailingHeadTail` is enabled (default), applies conservative native fixups that remove safe trailing `| head` / `| tail` pipes and redundant trailing `2>&1`,\n- extracts a leading single-line `cd <path> && ...` into `cwd` when `cwd` was not supplied,\n- rejects `async: true` when `async.enabled` is false.\n\nThere are no structured `head` or `tail` tool parameters in the current schema. Output limiting is handled by `OutputSink` truncation/artifacts, and the optional trailing-pipe fixup exists to avoid hiding output before the harness can capture it.\n\n## 2) Optional interception (blocked-command path)\n\nIf `bashInterceptor.enabled` is true, `BashTool` loads rules from settings and runs `checkBashInterception()` against the normalized command.\n\nInterception behavior:\n\n- command is blocked **only** when:\n  - regex rule matches, and\n  - the suggested tool is present in `ctx.toolNames`.\n- invalid regex rules are silently skipped.\n- on block, `BashTool` throws `ToolError` with message:\n  - `Blocked: ...`\n  - original command included.\n\nDefault rule patterns (defined in code) target common misuses:\n\n- file readers (`cat`, `head`, `tail`, ...)\n- search tools (`grep`, `rg`, ...)\n- file finders (`find`, `fd`, ...)\n- in-place editors (`sed -i`, `perl -i`, `awk -i inplace`)\n- shell redirection writes (`echo ... > file`, heredoc redirection)\n\n### Caveat\n\n`InterceptionResult` includes `suggestedTool`, but `BashTool` currently surfaces only the message text (no structured suggested-tool field in `details`).\n\n## 3) CWD validation and timeout clamping\n\n`cwd` is resolved relative to session cwd (`resolveToCwd`), then validated via `stat`:\n\n- missing path -> `ToolError(\"Working directory does not exist: ...\")`\n- non-directory -> `ToolError(\"Working directory is not a directory: ...\")`\n\nTimeout is clamped to `[1, 3600]` seconds and converted to milliseconds.\n\n## 4) Artifact allocation\n\nBefore execution, the tool allocates an artifact path/id (best-effort) for truncated output storage.\n\n- artifact allocation failure is non-fatal (execution continues without artifact spill file),\n- artifact id/path are passed into execution path for full-output persistence on truncation.\n\n## 5) PTY vs non-PTY execution selection\n\n`BashTool` chooses PTY execution only when all are true:\n\n- tool input `pty === true`\n- `PI_NO_PTY !== \"1\"`\n- tool context has UI (`ctx.hasUI === true` and `ctx.ui` set)\n\nOtherwise it uses non-interactive `executeBash()`.\n\nThat means print mode and non-UI RPC/tool contexts always use non-PTY.\n\n## Non-interactive execution engine (`executeBash`)\n\n## Shell session reuse model\n\n`executeBash()` caches native `Shell` instances in a process-global map keyed by:\n\n- shell path,\n- configured command prefix,\n- snapshot path,\n- serialized shell env,\n- optional agent session key.\n\nSession-level bang-command executions pass `sessionKey: this.sessionId`.\n\nTool-call executions pass `sessionKey: this.session.getSessionId?.()`, when available. In both surfaces, a session key isolates shell reuse per session; without one, reuse falls back to shell config/snapshot/env.\n\n## Shell config and snapshot behavior\n\nAt each call, executor loads settings shell config (`shell`, `env`, optional `prefix`).\n\nIf selected shell includes `bash`, it attempts `getOrCreateSnapshot()`:\n\n- snapshot captures aliases/functions/options from user rc,\n- snapshot creation is best-effort,\n- failure falls back to no snapshot.\n\nIf `prefix` is configured, command becomes:\n\n```text\n<prefix> <command>\n```\n\n## Streaming and cancellation\n\n`Shell.run()` streams chunks to `OutputSink` and optional `onChunk` callback.\n\nCancellation:\n\n- aborted signal triggers `shellSession.abort(...)`,\n- timeout from native result is mapped to `cancelled: true` + annotation text,\n- explicit cancellation similarly returns `cancelled: true` + annotation.\n\nNo exception is thrown inside executor for timeout/cancel; it returns structured `BashResult` and lets caller map error semantics.\n\n## Interactive PTY path (`runInteractiveBashPty`)\n\nWhen PTY is enabled, tool runs `runInteractiveBashPty()` which opens an overlay console component and drives a native `PtySession`.\n\nBehavior highlights:\n\n- xterm-headless virtual terminal renders viewport in overlay,\n- keyboard input is normalized (including Kitty sequences and application cursor mode handling),\n- `esc` while running kills the PTY session,\n- terminal resize propagates to PTY (`session.resize(cols, rows)`).\n\nEnvironment hardening defaults are injected for unattended runs:\n\n- pagers disabled (`PAGER=cat`, `GIT_PAGER=cat`, etc.),\n- editor prompts disabled (`GIT_EDITOR=true`, `EDITOR=true`, ...),\n- terminal/auth prompts reduced (`GIT_TERMINAL_PROMPT=0`, `SSH_ASKPASS=/usr/bin/false`, `CI=1`),\n- package-manager/tool automation flags for non-interactive behavior.\n\nPTY output is normalized (`CRLF`/`CR` to `LF`, `sanitizeText`) and written into `OutputSink`, including artifact spill support.\n\nOn PTY startup/runtime error, sink receives `PTY error: ...` line and command finalizes with undefined exit code.\n\n## Output handling: streaming, truncation, artifact spill\n\nBoth PTY and non-PTY paths use `OutputSink`.\n\n## OutputSink semantics\n\n- keeps an in-memory UTF-8-safe tail buffer (`DEFAULT_MAX_BYTES`, currently 50KB),\n- tracks total bytes/lines seen,\n- if artifact path exists and output overflows (or file already active), writes full stream to artifact file,\n- when memory threshold overflows, trims in-memory buffer to tail (UTF-8 boundary safe),\n- marks `truncated` when overflow/file spill occurs.\n\n`dump()` returns:\n\n- `output` (possibly annotated prefix),\n- `truncated`,\n- `totalLines/totalBytes`,\n- `outputLines/outputBytes`,\n- `artifactId` if artifact file was active.\n\n### Long-output caveat\n\nRuntime truncation is byte-threshold based in `OutputSink` (50KB default). It does not enforce a hard 2000-line cap in this code path.\n\n### Shell output minimizer\n\nNon-PTY execution also passes shell-minimizer settings into the native `Shell` session. When the minimizer rewrites verbose output, the executor replaces the sink's visible text with the minimized text and, when possible, saves the raw original capture as a separate `bash-original` artifact referenced by a `[raw output: artifact://<id>]` footer.\n\n## Live tool updates and async jobs\n\nFor non-PTY foreground execution, `BashTool` uses a separate `TailBuffer` for partial updates and emits `onUpdate` snapshots while command is running.\n\nFor PTY execution, live rendering is handled by custom UI overlay, not by `onUpdate` text chunks.\n\nWhen `async.enabled` is true and the call passes `async: true`, `BashTool` starts a managed bash job, returns a running job result with a job id, and stores completion through the session managed-job path. Auto-backgrounding can also start this path after `bash.autoBackground.thresholdMs`.\n\n## Result shaping, metadata, and error mapping\n\nAfter execution:\n\n1. `cancelled` handling:\n   - if abort signal is aborted -> throw `ToolAbortError` (abort semantics),\n   - else -> throw `ToolError` (treated as tool failure).\n2. PTY `timedOut` -> throw `ToolError`.\n3. empty output becomes `(no output)`.\n4. attach truncation metadata via `toolResult(...).truncationFromSummary(result, { direction: \"tail\" })`.\n5. exit-code mapping:\n   - missing exit code -> throw `ToolError(\"... missing exit status\")`\n   - non-zero exit -> error result with `\"Command exited with code N\"` and `details.exitCode`\n   - zero exit -> success result.\n\nSuccess payload structure:\n\n- `content`: text output,\n- `details.meta.truncation` when truncated, including:\n  - `direction`, `truncatedBy`, total/output line+byte counts,\n  - `shownRange`,\n  - `artifactId` when available.\n\nBecause built-in tools are wrapped with `wrapToolWithMetaNotice()`, truncation notice text is appended to final text content automatically (for example: `Full: artifact://<id>`).\n\n## Rendering paths\n\n## Tool-call renderer (`bashToolRenderer`)\n\n`bashToolRenderer` is used for tool-call messages (`toolCall` / `toolResult`):\n\n- collapsed mode shows visual-line-truncated preview,\n- expanded mode shows all currently available output text,\n- warning line includes truncation reason and `artifact://<id>` when truncated,\n- timeout value (from args) is shown in footer metadata line.\n\n### Caveat: full artifact expansion\n\n`BashRenderContext` has `isFullOutput`, but current renderer context builder does not set it for bash tool results. Expanded view still uses the text already in result content (tail/truncated output) unless another caller provides full artifact content.\n\n## User bang-command component (`BashExecutionComponent`)\n\n`BashExecutionComponent` is for user `!` commands in interactive mode (not model tool calls):\n\n- streams chunks live,\n- collapsed preview keeps last 20 logical lines,\n- line clamp at 4000 chars per line,\n- shows truncation + artifact warnings when metadata is present,\n- marks cancelled/error/exit state separately.\n\nThis component is wired by `CommandController.handleBashCommand()` and fed from `AgentSession.executeBash()`.\n\n## Mode-specific behavior differences\n\n| Surface                        | Entry path                                            | PTY eligible                                          | Live output UX                                                           | Error surfacing                                  |\n| ------------------------------ | ----------------------------------------------------- | ----------------------------------------------------- | ------------------------------------------------------------------------ | ------------------------------------------------ |\n| Interactive tool call          | `BashTool.execute`                                    | Yes, when `pty=true` and UI exists and `PI_NO_PTY!=1` | PTY overlay (interactive) or streamed tail updates                       | Tool errors become `toolResult.isError`          |\n| Print mode tool call           | `BashTool.execute`                                    | No (no UI context)                                    | No TUI overlay; output appears in event stream/final assistant text flow | Same tool error mapping                          |\n| RPC tool call (agent tooling)  | `BashTool.execute`                                    | Usually no UI -> non-PTY                              | Structured tool events/results                                           | Same tool error mapping                          |\n| Interactive bang command (`!`) | `AgentSession.executeBash` + `BashExecutionComponent` | No (uses executor directly)                           | Dedicated bash execution component                                       | Controller catches exceptions and shows UI error |\n| RPC `bash` command             | `rpc-mode` -> `session.executeBash`                   | No                                                    | Returns `BashResult` directly                                            | Consumer handles returned fields                 |\n\n## Operational caveats\n\n- Interceptor only blocks commands when suggested tool is currently available in context.\n- If artifact allocation fails, truncation still occurs but no `artifact://` back-reference is available.\n- Shell session cache has no explicit eviction in this module; lifetime is process-scoped.\n- PTY and non-PTY timeout surfaces differ:\n  - PTY exposes explicit `timedOut` result field,\n  - non-PTY maps timeout into `cancelled + annotation` summary.\n\n## Implementation files\n\n- [`src/tools/bash.ts`](../packages/coding-agent/src/tools/bash.ts) — tool entrypoint, input handling/interception, async and PTY/non-PTY selection, result/error mapping, bash tool renderer.\n- [`src/tools/bash-command-fixup.ts`](../packages/coding-agent/src/tools/bash-command-fixup.ts) — native-backed conservative cleanup for trailing `head`/`tail` pipes and redundant `2>&1`.\n- [`src/tools/bash-interceptor.ts`](../packages/coding-agent/src/tools/bash-interceptor.ts) — interceptor rule matching and blocked-command messages.\n- [`src/exec/bash-executor.ts`](../packages/coding-agent/src/exec/bash-executor.ts) — non-PTY executor, shell session reuse, cancellation wiring, output sink integration.\n- [`src/tools/bash-interactive.ts`](../packages/coding-agent/src/tools/bash-interactive.ts) — PTY runtime, overlay UI, input normalization, non-interactive env defaults.\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts) — `OutputSink`, `TailBuffer`, truncation/artifact spill, and summary metadata.\n- [`src/tools/output-meta.ts`](../packages/coding-agent/src/tools/output-meta.ts) — truncation metadata shape + notice injection wrapper.\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — session-level `executeBash`, message recording, abort lifecycle.\n- [`src/modes/components/bash-execution.ts`](../packages/coding-agent/src/modes/components/bash-execution.ts) — interactive `!` command execution component.\n- [`src/modes/controllers/command-controller.ts`](../packages/coding-agent/src/modes/controllers/command-controller.ts) — wiring for interactive `!` command UI stream/update completion.\n- [`src/modes/rpc/rpc-mode.ts`](../packages/coding-agent/src/modes/rpc/rpc-mode.ts) — RPC `bash` and `abort_bash` command surface.\n- [`src/internal-urls/artifact-protocol.ts`](../packages/coding-agent/src/internal-urls/artifact-protocol.ts) — `artifact://<id>` resolution.\n",
 	"blob-artifact-architecture.md": "# Blob and artifact storage architecture\n\nThis document describes how coding-agent stores large/binary payloads outside session JSONL, how truncated tool output is persisted, and how internal URLs (`artifact://`, `agent://`) resolve back to stored data.\n\n## Why two storage systems exist\n\nThe runtime uses two different persistence mechanisms for different data shapes:\n\n- **Content-addressed blobs** (`blob:sha256:<hash>`): global storage used to externalize large image base64 payloads and provider image data URLs from persisted session entries.\n- **Session-scoped artifacts** (files under `<sessionFile-without-.jsonl>/`): per-session text files used for full tool outputs and subagent outputs.\n\nThey are intentionally separate:\n\n- blob storage optimizes deduplication and stable references by content hash,\n- artifact storage optimizes append-only session tooling and human/tool retrieval by local IDs.\n\n## Storage boundaries and on-disk layout\n\n### Blob store boundary (global)\n\n`SessionManager` constructs `BlobStore(getBlobsDir())`, so blob files live in a shared global blob directory, not in a session folder.\n\nBlob file naming:\n\n- file path: `<blobsDir>/<sha256-hex>`\n- no extension\n- reference string stored in entries: `blob:sha256:<sha256-hex>`\n\nImplications:\n\n- same binary content across sessions resolves to the same hash/path,\n- writes are idempotent at the content level,\n- blobs can outlive any individual session file.\n\n## Artifact boundary (session-local)\n\n`ArtifactManager` derives artifact directory from session file path:\n\n- session file: `.../<timestamp>_<sessionId>.jsonl`\n- artifacts directory: `.../<timestamp>_<sessionId>/` (strip `.jsonl`)\n\nArtifact types share this directory:\n\n- truncated tool output files: `<numericId>.<toolType>.log` (for `artifact://`)\n- subagent output files: `<outputId>.md` (for `agent://`)\n- subagent session JSONL sidecars: `<outputId>.jsonl` when task execution receives an artifacts directory\n\nSubagents can adopt the parent `ArtifactManager`; in that case parent and subagent tree share one artifact directory and numeric artifact ID space.\n\n## ID and name allocation schemes\n\n### Blob IDs: content hash\n\n`BlobStore.put()` / `putSync()` computes SHA-256 over the bytes it is given and returns:\n\n- `hash`: hex digest,\n- `path`: `<blobsDir>/<hash>`,\n- `ref`: `blob:sha256:<hash>`.\n\nNo session-local counter is used.\n\n### Artifact IDs: session-local monotonic integer\n\n`ArtifactManager` scans existing `*.log` artifact files on first directory-backed allocation to find max existing numeric ID and sets `nextId = max + 1`.\n\nAllocation behavior:\n\n- file format: `{id}.{toolType}.log`\n- IDs are sequential strings (`\"0\"`, `\"1\"`, ...)\n- resume does not overwrite existing artifacts because scan happens before allocation\n- the directory is created lazily on first save/allocation\n\nIf the artifact directory is missing, scanning yields an empty list and allocation starts from `0`.\n\nNon-persistent sessions without an adopted manager can store `saveArtifact(...)` content in memory under numeric IDs, but `artifact://` resolution is file-backed through registered artifact directories.\n\n### Agent output IDs (`agent://`)\n\n`AgentOutputManager` allocates IDs for subagent outputs from the requested name, used verbatim the first time and suffixed (`-2`, `-3`, …) only when the same name repeats (e.g. `Anna`, `Anna-2`). Nested outputs are grouped under the parent prefix (e.g. `Parent.Child`). It scans existing `.md` files on initialization so a resumed session never reuses a name that would clobber a prior output.\n\n## Persistence dataflow\n\n### 1) Session entry persistence rewrite path\n\nBefore session entries are written (`#rewriteFile` / incremental persist), `SessionManager` calls `prepareEntryForPersistence()` / `prepareEntryForPersistenceSync()` through the truncation pipeline.\n\nKey behaviors:\n\n1. **Large string truncation**: oversized strings are cut and suffixed with `\"[Session persistence truncated large content]\"`; signature fields (`thinkingSignature`, `thoughtSignature`, `textSignature`) are cleared instead of truncated.\n2. **Transient field stripping**: `partialJson` and `jsonlEvents` are removed from persisted entries.\n3. **Image externalization to blobs**:\n   - image blocks in `content` arrays are externalized when `data` is not already a blob ref and base64 length is at least threshold (`BLOB_EXTERNALIZE_THRESHOLD = 1024`),\n   - provider-style `image_url` data URLs are externalized when they start with `data:image/` and contain `;base64,`,\n   - image block `data` is stored as decoded binary bytes,\n   - provider data URLs are stored as the original UTF-8 data URL string,\n   - persisted values are replaced with `blob:sha256:<hash>`.\n\nThis keeps session JSONL compact while preserving recoverability.\n\n### 2) Session load rehydration path\n\nWhen opening a session (`setSessionFile`), after migrations, `SessionManager` runs `resolveBlobRefsInEntries()`.\n\nFor message/custom-message image blocks with `blob:sha256:<hash>` and for persisted provider `image_url` fields with blob refs:\n\n- reads blob bytes from blob store,\n- converts image-block bytes back to base64,\n- converts provider `image_url` blobs back to the original string,\n- mutates in-memory entry fields for runtime consumers.\n\nIf a blob is missing:\n\n- image-block resolution logs a warning and keeps the original `blob:sha256:` ref string in memory,\n- provider `image_url` resolution logs a warning and keeps the original ref string,\n- load continues.\n\n### 3) Tool output spill/truncation path\n\n`OutputSink` powers streaming output in bash/python/ssh and related executors.\n\nBehavior:\n\n1. Every chunk is sanitized with `sanitizeWithOptionalSixelPassthrough(..., sanitizeText)` and appended to in-memory accounting.\n2. Optional live `onChunk` receives sanitized pre-column-cap chunks, throttled if configured.\n3. A per-line column cap can drop bytes from long lines in the LLM-facing buffer; when this happens, artifact mirroring starts so the on-disk file keeps the full sanitized stream.\n4. When the in-memory tail buffer would exceed spill threshold (`DEFAULT_MAX_BYTES`, 50KB), sink marks output truncated and starts artifact mirroring if an artifact path is available.\n5. If a file sink is opened, it first writes the current buffer, then all queued/subsequent sanitized chunks.\n6. In-memory buffer is trimmed to a tail window, or to head + elision marker + tail when head retention is configured.\n7. `dump()` returns summary including `artifactId` only when file sink creation succeeded.\n\nPractical effect:\n\n- UI/tool return shows bounded output,\n- full sanitized output is preserved in artifact file and referenced as `artifact://<id>` when file-backed artifact mirroring succeeded.\n\nIf file sink creation fails (I/O error, missing path, etc.), sink falls back to in-memory truncation only; full output is not persisted.\n\n## URL access model\n\n### `blob:` references\n\n`blob:sha256:<hash>` is a persistence reference inside session entry payloads, not an internal URL scheme handled by the router. Resolution is done by `SessionManager` during session load.\n\n### `artifact://<id>`\n\nHandled by `ArtifactProtocolHandler` over registered active session artifact directories:\n\n- requires a numeric ID,\n- searches each registered artifacts directory for filename prefix `<id>.`,\n- returns raw text (`text/plain`) from the matched `.log` file,\n- when missing, error includes available numeric artifact IDs from existing artifact files.\n\nFailure behavior:\n\n- if no artifact directories are registered: throws `No session - artifacts unavailable`,\n- if registered directories exist but none are present on disk: throws `No artifacts directory found`,\n- if ID is not numeric: throws `artifact:// ID must be numeric, got: <id>`.\n\n### `agent://<id>`\n\nHandled by `AgentProtocolHandler` over registered active session artifact directories and `<artifactsDir>/<id>.md`:\n\n- plain form returns markdown text,\n- `/path` or `?q=` forms perform JSON extraction,\n- path and query extraction cannot be combined,\n- if extraction requested, file content must parse as JSON.\n\nFailure behavior:\n\n- if no artifact directories are registered: throws `No session - agent outputs unavailable`,\n- if registered directories exist but none are present on disk: throws `No artifacts directory found`,\n- missing output throws `Not found: <id>` with available `.md` output IDs when directory listing succeeds.\n\nRead tool integration:\n\n- `read` supports offset/limit pagination for non-extraction internal URL reads,\n- rejects offset/limit when `agent://` extraction is used.\n\n## Resume, fork, and move semantics\n\n### Resume\n\n- `ArtifactManager` scans existing `{id}.*.log` files on first allocation and continues numbering.\n- `AgentOutputManager` scans existing `.md` output IDs and continues numbering.\n- `SessionManager` rehydrates blob refs to base64/data URLs on load.\n\n### Fork\n\n`SessionManager.fork()` creates a new session file with new session ID and `parentSession` link, then returns old/new file paths. Artifact copying is handled by `AgentSession.fork()`:\n\n- flushes current session first,\n- attempts recursive copy of old artifact directory to new artifact directory,\n- missing old directory is tolerated,\n- non-ENOENT copy errors are logged as warnings and fork still completes.\n\nID implications after fork:\n\n- if copy succeeded, artifact counters in the new session continue after max copied ID when the new `ArtifactManager` first scans,\n- if copy failed/skipped, new session artifact IDs start from `0`.\n\nBlob implications after fork:\n\n- blobs are global and content-addressed, so no blob directory copy is required.\n\n### Move to new cwd\n\n`SessionManager.moveTo()` renames both session file and artifact directory to the new default session directory, with rollback logic if a later step fails. This preserves artifact identity while relocating session scope.\n\n## Failure handling and fallback paths\n\n| Case                                                      | Behavior                                                             |\n| --------------------------------------------------------- | -------------------------------------------------------------------- |\n| Blob file missing during image-block rehydration          | Warn and keep `blob:sha256:` ref string in memory                    |\n| Blob file missing during provider `image_url` rehydration | Warn and keep `blob:sha256:` ref string in memory                    |\n| Blob read ENOENT via `BlobStore.get`                      | Returns `null`                                                       |\n| Artifact directory missing (`ArtifactManager.listFiles`)  | Returns empty list (allocation can start fresh)                      |\n| No registered artifact dirs (`artifact://`)               | Throws `No session - artifacts unavailable`                          |\n| No registered artifact dirs (`agent://`)                  | Throws `No session - agent outputs unavailable`                      |\n| Registered artifact dirs missing on disk                  | Throws explicit `No artifacts directory found`                       |\n| Artifact ID not found                                     | Throws with available IDs listing                                    |\n| OutputSink artifact writer init fails                     | Continues with bounded in-memory output only                         |\n| Non-persistent `saveArtifact`                             | Stores text in `SessionManager` memory map; not file-backed URL data |\n\n## Binary blob externalization vs text-output artifacts\n\n- **Blob externalization** is for image payloads inside persisted session entry content and provider image data URLs; it replaces inline payload strings in JSONL with stable content refs.\n- **Artifacts** are plain text files for execution output and subagent output; file-backed artifacts are addressable by session-local IDs through internal URLs.\n\nThe two systems intersect only indirectly: both reduce session JSONL bloat, but they have different identity, lifetime, and retrieval paths.\n\n## Implementation files\n\n- [`src/session/blob-store.ts`](../packages/coding-agent/src/session/blob-store.ts) — blob reference format, hashing, put/get, externalize/resolve helpers.\n- [`src/session/artifacts.ts`](../packages/coding-agent/src/session/artifacts.ts) — session artifact directory model and numeric artifact ID/path allocation.\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts) — `OutputSink` truncation/spill-to-file behavior and summary metadata.\n- [`src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts) — persistence transforms, blob rehydration on load, session fork/move interactions.\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — artifact directory copy during interactive fork.\n- [`src/internal-urls/artifact-protocol.ts`](../packages/coding-agent/src/internal-urls/artifact-protocol.ts) — `artifact://` resolver.\n- [`src/internal-urls/agent-protocol.ts`](../packages/coding-agent/src/internal-urls/agent-protocol.ts) — `agent://` resolver + JSON extraction.\n- [`src/internal-urls/router.ts`](../packages/coding-agent/src/internal-urls/router.ts) — internal URL router wiring.\n- [`src/task/output-manager.ts`](../packages/coding-agent/src/task/output-manager.ts) — session-scoped agent output ID allocation for `agent://`.\n- [`src/task/executor.ts`](../packages/coding-agent/src/task/executor.ts) — subagent output artifact writes (`<id>.md`) and session JSONL sidecars.\n",
 	"compaction.md": "# Compaction and Branch Summaries\n\nCompaction and branch summaries are the two mechanisms that keep long sessions usable without losing prior work context.\n\n- **Compaction** rewrites old history into a summary on the current branch.\n- **Branch summary** captures abandoned branch context during `/tree` navigation.\n\nBoth are persisted as session entries and converted back into user-context messages when rebuilding LLM input.\n\n## Key implementation files\n\n- `packages/agent/src/compaction/compaction.ts` (context-full summarization and handoff generation)\n- `packages/agent/src/compaction/branch-summarization.ts`\n- `packages/agent/src/compaction/pruning.ts`\n- `packages/agent/src/compaction/utils.ts`\n- `packages/agent/src/compaction/openai.ts`\n- `packages/coding-agent/src/session/session-manager.ts`\n- `packages/coding-agent/src/session/agent-session.ts`\n- `packages/coding-agent/src/session/messages.ts`\n- `packages/coding-agent/src/extensibility/hooks/types.ts`\n- `packages/coding-agent/src/config/settings-schema.ts`\n\n## Session entry model\n\nCompaction and branch summaries are first-class session entries, not plain assistant/user messages.\n\n- `CompactionEntry`\n  - `type: \"compaction\"`\n  - `summary`, optional `shortSummary`\n  - `firstKeptEntryId` (compaction boundary)\n  - `tokensBefore`\n  - optional `details`, `preserveData`, `fromExtension`\n- `BranchSummaryEntry`\n  - `type: \"branch_summary\"`\n  - `fromId`, `summary`\n  - optional `details`, `fromExtension`\n\nWhen context is rebuilt (`buildSessionContext`):\n\n1. Latest compaction on the active path is converted to one `compactionSummary` message.\n2. Kept entries from `firstKeptEntryId` to the compaction point are re-included.\n3. Later entries on the path are appended.\n4. `branch_summary` entries are converted to `branchSummary` messages.\n5. `custom_message` entries are converted to `custom` messages.\n\nThose custom roles are then transformed into LLM-facing user messages in `convertToLlm()` using the static templates:\n\n- `packages/agent/src/compaction/prompts/compaction-summary-context.md`\n- `packages/agent/src/compaction/prompts/branch-summary-context.md`\n- `packages/agent/src/compaction/prompts/handoff-document.md`\n\n## Compaction pipeline\n\n### Triggers\n\nCompaction/context maintenance can run in five ways:\n\n1. **Manual context compaction**: `/compact [instructions]` calls `AgentSession.compact(...)`.\n2. **Automatic overflow recovery**: after a same-model assistant error that matches context overflow.\n3. **Automatic incomplete-output recovery**: after a same-model assistant message ends with `stopReason === \"length\"` (OpenAI/Codex `response.incomplete`).\n4. **Automatic threshold maintenance**: after a successful turn when context exceeds the resolved threshold.\n5. **Idle maintenance**: `runIdleCompaction()` can invoke the same auto-maintenance path with reason `\"idle\"`.\n\n### Compaction shape (visual)\n\n```text\nBefore compaction:\n\n  entry:  0     1     2     3      4     5     6      7      8     9\n        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┐\n        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │\n        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┘\n                └────────┬───────┘ └──────────────┬──────────────┘\n               messagesToSummarize            kept messages\n                                   ↑\n                          firstKeptEntryId (entry 4)\n\nAfter compaction (new entry appended):\n\n  entry:  0     1     2     3      4     5     6      7      8     9      10\n        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┬─────┐\n        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │ cmp │\n        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┴─────┘\n               └──────────┬──────┘ └──────────────────────┬───────────────────┘\n                 not sent to LLM                    sent to LLM\n                                                         ↑\n                                              starts from firstKeptEntryId\n\nWhat the LLM sees:\n\n  ┌────────┬─────────┬─────┬─────┬──────┬──────┬─────┬──────┐\n  │ system │ summary │ usr │ ass │ tool │ tool │ ass │ tool │\n  └────────┴─────────┴─────┴─────┴──────┴──────┴─────┴──────┘\n       ↑         ↑      └─────────────────┬────────────────┘\n    prompt   from cmp          messages from firstKeptEntryId\n```\n\n### Overflow/incomplete recovery vs threshold/idle maintenance\n\nThe automatic paths are intentionally different:\n\n- **Overflow recovery**\n  - Trigger: current-model assistant error is detected as context overflow and the error is not older than the latest compaction.\n  - The failing assistant error message is removed from active agent state before retry.\n  - Context promotion is tried first; if a configured larger model is available, the agent switches model and retries without compacting.\n  - If promotion is unavailable and compaction is enabled, context-full compaction runs with `reason: \"overflow\"` and `willRetry: true`; handoff strategy is not used for overflow because the handoff request would reuse the overflowing input.\n  - On success, `agent.continue()` is scheduled to retry the turn.\n\n- **Incomplete-output recovery**\n  - Trigger: same-model assistant message ends with `stopReason === \"length\"` and the message is not older than the latest compaction.\n  - The incomplete assistant message is removed from active agent state before recovery.\n  - Context promotion is tried first.\n  - If promotion is unavailable and compaction is enabled, auto maintenance runs with `reason: \"incomplete\"` and `willRetry: true`.\n  - Unlike overflow, `compaction.strategy: \"handoff\"` is allowed for incomplete-output recovery because the input context is still usable.\n  - On context-full success, `agent.continue()` is scheduled to retry the turn.\n\n- **Threshold maintenance**\n  - Trigger: successful, non-error assistant message whose adjusted context tokens exceed `resolveThresholdTokens(...)`.\n  - Tool-output pruning can reduce the measured token count before threshold comparison.\n  - Context promotion is tried before compaction.\n  - If promotion is unavailable, auto maintenance runs with `reason: \"threshold\"` and `willRetry: false`.\n  - With `compaction.strategy: \"handoff\"`, threshold maintenance normally schedules a post-prompt auto-handoff task instead of writing a compaction entry; pre-prompt checks run it inline to avoid racing the next turn. If handoff returns no document without aborting, it falls back to context-full compaction.\n  - On success, if `compaction.autoContinue !== false`, schedules an agent-authored developer auto-continue prompt from `prompts/system/auto-continue.md`.\n\n- **Idle maintenance**\n  - Trigger: `runIdleCompaction()` when not streaming or already compacting.\n  - Uses `reason: \"idle\"` and does not auto-continue afterward.\n\n### Pre-compaction pruning\n\nBefore compaction checks, tool-result pruning may run (`pruneToolOutputs`).\n\nDefault prune policy:\n\n- Protect newest `40_000` tool-output tokens.\n- Require at least `20_000` total estimated savings.\n- Never prune tool results from `skill` or `read`.\n\nPruned tool results are replaced with:\n\n- `[Output truncated - N tokens]`\n\nIf pruning changes entries, session storage is rewritten and agent message state is refreshed before compaction decisions.\n\n### Boundary and cut-point logic\n\n`prepareCompaction()` only considers entries since the last compaction entry (if any).\n\n1. Find previous compaction index.\n2. Compute `boundaryStart = prevCompactionIndex + 1`.\n3. Adapt `keepRecentTokens` using measured usage ratio when available.\n4. Run `findCutPoint()` over the boundary window.\n\nValid cut points include:\n\n- message entries with roles: `user`, `assistant`, `bashExecution`, `hookMessage`, `branchSummary`, `compactionSummary`\n- `custom_message` entries\n- `branch_summary` entries\n\nHard rule: never cut at `toolResult`.\n\nIf there are non-message metadata entries immediately before the cut point (`model_change`, `thinking_level_change`, labels, etc.), they are pulled into the kept region by moving cut index backward until a message or compaction boundary is hit.\n\n### Split-turn handling\n\nIf cut point is not at a user-turn start, compaction treats it as a split turn.\n\nTurn start detection treats these as user-turn boundaries:\n\n- `message.role === \"user\"`\n- `message.role === \"bashExecution\"`\n- `custom_message` entry\n- `branch_summary` entry\n\nSplit-turn compaction generates two summaries:\n\n1. History summary (`messagesToSummarize`)\n2. Turn-prefix summary (`turnPrefixMessages`)\n\nFinal stored summary is merged as:\n\n```markdown\n<history summary>\n\n---\n\n**Turn Context (split turn):**\n\n<turn prefix summary>\n```\n\n### Summary generation\n\n`compact(...)` builds summaries from serialized conversation text:\n\n1. Convert messages via `convertToLlm()`.\n2. Serialize with `serializeConversation()`.\n3. Wrap in `<conversation>...</conversation>`.\n4. Optionally include `<previous-summary>...</previous-summary>`.\n5. Optionally inject extension hook context and active memory-backend compaction context as `<additional-context>` entries.\n6. Execute summarization prompt with `SUMMARIZATION_SYSTEM_PROMPT`.\n\nPrompt selection:\n\n- first compaction: `compaction-summary.md`\n- iterative compaction with prior summary: `compaction-update-summary.md`\n- split-turn second pass: `compaction-turn-prefix.md`\n- short UI summary: `compaction-short-summary.md`\n- handoff document: `handoff-document.md` (used by `generateHandoff(...)`, not serialized compaction)\n\nRemote summarization modes:\n\n- If `compaction.remoteEndpoint` is set and remote compaction is enabled, local summary generation POSTs:\n  - `{ systemPrompt, prompt }`\n- Expects JSON containing at least `{ summary }`.\n- For OpenAI/OpenAI Codex models, compaction first tries the provider-native `/responses/compact` endpoint when remote compaction is enabled. It preserves provider replacement history in `preserveData.openaiRemoteCompaction` and falls back to local summarization if that native request fails.\n\n### Handoff generation\n\n`packages/agent/src/compaction/compaction.ts` also exports `generateHandoff(...)`. Handoff generation uses the same `completeSimple(...)` oneshot style as summarization, but it preserves the live agent cache prefix by sending the active system prompt, tool array, and real LLM message history, then appending one agent-attributed `user` message containing the handoff prompt. It forces `toolChoice: \"none\"` and returns joined text blocks directly.\n\nHandoff does not write a `CompactionEntry`. `AgentSession.handoff()` owns the session transition: it starts a new session, injects the generated document as a visible `custom_message` with `customType: \"handoff\"`, and rebuilds agent messages from that new session.\n\n### File-operation context in summaries\n\nCompaction tracks cumulative file activity using assistant tool calls:\n\n- `read(path)` → read set\n- `write(path)` → modified set\n- `edit(path)` → modified set\n\nCumulative behavior:\n\n- Includes prior compaction details only when prior entry is pi-generated (`fromExtension !== true`).\n- In split turns, includes turn-prefix file ops too.\n- `readFiles` excludes files also modified.\n\nSummary text gets file tags appended via prompt template:\n\n```xml\n<read-files>\n...\n</read-files>\n<modified-files>\n...\n</modified-files>\n```\n\n### Persist and reload\n\nAfter summary generation (or hook-provided summary), agent session:\n\n1. Appends `CompactionEntry` with `appendCompaction(...)` for context-full maintenance; handoff strategy creates a new session and injects a handoff `custom_message` instead.\n2. Rebuilds display context from the active leaf via `buildDisplaySessionContext()`.\n3. Replaces live agent messages with rebuilt context.\n4. Synchronizes active todo phases from the rebuilt branch and closes provider sessions whose history was rewritten.\n5. Emits `session_compact` hook event.\n\n## Branch summarization pipeline\n\nBranch summarization is tied to tree navigation, not token overflow.\n\n### Trigger\n\nDuring `navigateTree(...)`:\n\n1. Compute abandoned entries from old leaf to common ancestor using `collectEntriesForBranchSummary(...)`.\n2. If caller requested summary (`options.summarize`), generate summary before switching leaf.\n3. If summary exists, attach it at the navigation target using `branchWithSummary(...)`.\n\nOperationally this is commonly driven by `/tree` flow when `branchSummary.enabled` is enabled.\n\n### Branch switch shape (visual)\n\n```text\nTree before navigation:\n\n         ┌─ B ─ C ─ D (old leaf, being abandoned)\n    A ───┤\n         └─ E ─ F (target)\n\nCommon ancestor: A\nEntries to summarize: B, C, D\n\nAfter navigation with summary:\n\n         ┌─ B ─ C ─ D ─ [summary of B,C,D]\n    A ───┤\n         └─ E ─ F (new leaf)\n```\n\n### Preparation and token budget\n\n`generateBranchSummary(...)` computes budget as:\n\n- `tokenBudget = model.contextWindow - branchSummary.reserveTokens`\n\n`prepareBranchEntries(...)` then:\n\n1. First pass: collect cumulative file ops from all summarized entries, including prior pi-generated `branch_summary` details.\n2. Second pass: walk newest → oldest, adding messages until token budget is reached.\n3. Prefer preserving recent context.\n4. May still include large summary entries near budget edge for continuity.\n\nCompaction entries are included as messages (`compactionSummary`) during branch summarization input.\n\n### Summary generation and persistence\n\nBranch summarization:\n\n1. Converts and serializes selected messages.\n2. Wraps in `<conversation>`.\n3. Uses custom instructions if supplied, otherwise `branch-summary.md`.\n4. Calls summarization model with `SUMMARIZATION_SYSTEM_PROMPT`.\n5. Prepends `branch-summary-preamble.md`.\n6. Appends file-operation tags.\n\nResult is stored as `BranchSummaryEntry` with optional details (`readFiles`, `modifiedFiles`).\n\n## Extension and hook touchpoints\n\n### `session_before_compact`\n\nPre-compaction hook.\n\nCan:\n\n- cancel compaction (`{ cancel: true }`)\n- provide full custom compaction payload (`{ compaction: CompactionResult }`)\n\n### `session.compacting`\n\nPrompt/context customization hook for default compaction.\n\nCan return:\n\n- `prompt` (override base summary prompt)\n- `context` (extra context lines injected into `<additional-context>`)\n- `preserveData` (stored on compaction entry)\n\n### `session_compact`\n\nPost-compaction notification with saved `compactionEntry` and `fromExtension` flag.\n\n### `session_before_tree`\n\nRuns on tree navigation before default branch summary generation.\n\nCan:\n\n- cancel navigation\n- provide custom `{ summary: { summary, details } }` used when user requested summarization\n\n### `session_tree`\n\nPost-navigation event exposing new/old leaf and optional summary entry.\n\n## Runtime behavior and failure semantics\n\n- Manual compaction aborts current agent operation first.\n- `abortCompaction()` cancels manual compaction, auto-compaction, and handoff generation controllers.\n- Auto compaction emits start/end session events for UI/state updates.\n- Auto compaction can try multiple model candidates and retry transient failures; long retry delays prefer the next candidate when one is available.\n- Overflow errors are excluded from generic retry path because they are handled by context promotion/compaction.\n- If auto-compaction fails:\n  - overflow path emits `Context overflow recovery failed: ...`\n  - incomplete-output path emits `Incomplete response recovery failed: ...`\n  - threshold/idle paths emit `Auto-compaction failed: ...`\n- Branch summarization can be cancelled via abort signal (e.g., Escape), returning canceled/aborted navigation result.\n\n## Settings and defaults\n\nFrom `settings-schema.ts`:\n\n- `compaction.enabled` = `true`\n- `compaction.strategy` = `\"context-full\"` (`\"handoff\"` and `\"off\"` are also supported)\n- `compaction.reserveTokens` = `16384`\n- `compaction.keepRecentTokens` = `20000`\n- `compaction.autoContinue` = `true`\n- `compaction.remoteEnabled` = `true`\n- `compaction.remoteEndpoint` = `undefined`\n- `compaction.thresholdPercent` = `-1` and `compaction.thresholdTokens` = `-1`; when no positive override is set, the threshold is `contextWindow - max(15% of contextWindow, reserveTokens)`\n- `compaction.idleEnabled` = `false`\n- `compaction.idleThresholdTokens` = `200000`\n- `compaction.idleTimeoutSeconds` = `300`\n- `branchSummary.enabled` = `false`\n- `branchSummary.reserveTokens` = `16384`\n\nThese values are consumed at runtime by `AgentSession` and compaction/branch summarization modules.\n",
 	"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## 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. Runtime overrides: in-memory, non-persistent\n4. Schema defaults: from `SETTINGS_SCHEMA`\n\nEffective read path:\n\n`defaults <- global <- project <- 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## 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",
 	"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| `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 token chains\n\n| Variable               | Used for                                         | Chain                                                |\n| ---------------------- | ------------------------------------------------ | ---------------------------------------------------- |\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth                     | `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` |\n| `GH_TOKEN`             | Copilot fallback; GitHub API auth in web scraper | In web scraper: `GITHUB_TOKEN` → `GH_TOKEN`          |\n| `GITHUB_TOKEN`         | Copilot fallback; GitHub API auth in web scraper | In web scraper: checked 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\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` | Enables ECS task credential path                                                              |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN`                                  | Enables web identity auth path                                                                |\n| `AWS_BEDROCK_SKIP_AUTH`                                                         | If `1`, injects dummy credentials (proxy/non-auth scenarios)                                  |\n| `AWS_BEDROCK_FORCE_HTTP1`                                                       | If `1`, forces Node HTTP/1 request handler                                                    |\n| `HTTPS_PROXY` / `HTTP_PROXY` / `ALL_PROXY`                                      | Routes Bedrock runtime and AWS SSO credential calls through the configured proxy using HTTP/1 |\n| `NO_PROXY`                                                                      | Excludes matching hosts from proxy routing when a proxy variable is configured                |\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_CODEX_WEBSOCKET_V2`                    | `1`/`true` enables websocket v2 path                 |\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`                 | Eval backend override: `0`/`bash`=JavaScript only, `1`/`py`=Python only, `mix`/`both`=both; invalid values ignored  |\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_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 (`http://127.0.0.1:11434` if unset)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    |\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| `KDE_FULL_SESSION`, `XDG_CURRENT_DESKTOP`, `DESKTOP_SESSION`, `XDG_SESSION_DESKTOP`, `GDMSESSION`, `WINDOWMANAGER` | Desktop/window-manager detection 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_CLEAR_ON_SHRINK`      | If `1`, clears empty rows when content shrinks                                        |\n| `PI_NO_SYNC_OUTPUT`       | If `1`, 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_TUI_DEBUG`            | If `1`, enables deep TUI debug dump path                                              |\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| `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 token chains\n\n| Variable               | Used for                                         | Chain                                                |\n| ---------------------- | ------------------------------------------------ | ---------------------------------------------------- |\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth                     | `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` |\n| `GH_TOKEN`             | Copilot fallback; GitHub API auth in web scraper | In web scraper: `GITHUB_TOKEN` → `GH_TOKEN`          |\n| `GITHUB_TOKEN`         | Copilot fallback; GitHub API auth in web scraper | In web scraper: checked 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` | Enables ECS task credential path                                                              |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN`                                  | Enables web identity auth path                                                                |\n| `AWS_BEDROCK_SKIP_AUTH`                                                         | If `1`, injects dummy credentials (proxy/non-auth scenarios)                                  |\n| `AWS_BEDROCK_FORCE_HTTP1`                                                       | If `1`, forces Node HTTP/1 request handler                                                    |\n| `HTTPS_PROXY` / `HTTP_PROXY` / `ALL_PROXY`                                      | Routes Bedrock runtime and AWS SSO credential calls through the configured proxy using HTTP/1 |\n| `NO_PROXY`                                                                      | Excludes matching hosts from proxy routing when a proxy variable is configured                |\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_CODEX_WEBSOCKET_V2`                    | `1`/`true` enables websocket v2 path                 |\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`                 | Eval backend override: `0`/`bash`=JavaScript only, `1`/`py`=Python only, `mix`/`both`=both; invalid values ignored  |\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_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| `KDE_FULL_SESSION`, `XDG_CURRENT_DESKTOP`, `DESKTOP_SESSION`, `XDG_SESSION_DESKTOP`, `GDMSESSION`, `WINDOWMANAGER` | Desktop/window-manager detection 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_CLEAR_ON_SHRINK`      | If `1`, clears empty rows when content shrinks                                        |\n| `PI_NO_SYNC_OUTPUT`       | If `1`, 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_TUI_DEBUG`            | If `1`, enables deep TUI debug dump path                                              |\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\nPath roots come from the native provider (`SOURCE_PATHS.native`). Project lookup is cwd-only for these native roots; it does not walk ancestors.\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 (`nextTurn` ignores this)\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- `getContextUsage()`\n- `compact(...)`\n- `isIdle()`, `hasPendingMessages()`, `abort()`\n- `shutdown()`\n- `getSystemPrompt()`\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`, `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- `setEditorComponent`\n\nAlso note: `setWidget` currently routes to status-line text via `setHookWidget(...)`.\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, `setTitle`, `setEditorText`)\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### Background interactive mode\n\nBackground mode installs a non-interactive UI context object. In current implementation, `ctx.hasUI` may still be `true` while interactive dialogs return defaults/no-op behavior.\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`, `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\nCoding-agent callers today:\n\n- High-volume mention candidate discovery enables cache:\n  - `packages/coding-agent/src/utils/file-mentions.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",
@@ -30,7 +30,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"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 or when manually triggered via slash command. 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.md`    | 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, slash command handling\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`                | project directory name | Base bank name passed to `Mnemopi`; the coding-agent wrapper scopes from this base according to `mnemopi.scoping`.                                                  |\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.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, 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/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models 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`.\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\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 (schema v3) with a `static_fingerprint` column that hashes the\nstatic 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 via a WeakMap keyed by the static-models array\nreference, 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 `http://127.0.0.1:11434`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\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\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`, `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 `--list-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- `--list-models` prints a canonical section plus the concrete provider rows\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/ai/src/providers/openai-completions-compat.ts`. 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/ai/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- `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 and zAI).\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\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/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`, `supportsMidConversationSystem`) 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. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\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:\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.\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\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/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models 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`.\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\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 (schema v3) with a `static_fingerprint` column that hashes the\nstatic 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 via a WeakMap keyed by the static-models array\nreference, 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\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`, `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 `--list-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- `--list-models` prints a canonical section plus the concrete provider rows\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/ai/src/providers/openai-completions-compat.ts`. 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/ai/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- `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 and zAI).\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\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/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`, `supportsMidConversationSystem`) 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. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\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:\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.\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\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}-${process.arch}` (for example `darwin-arm64`).\n- **Package version**: from `packages/natives/package.json`.\n- **Core directories**:\n  - `leafPackageDir`: directory of the platform leaf package, resolved via `require.resolve(\"@oh-my-pi/pi-natives-<tag>/package.json\")`; `null` when no leaf is installed (e.g. local dev).\n  - `nativeDir`: package-local `packages/natives/native`.\n  - `execDir`: directory containing `process.execPath`.\n  - `versionedDir`: `<getNativesDir()>/<packageVersion>`.\n  - `userDataDir` fallback:\n    - Windows: `%LOCALAPPDATA%/omp` or `%USERPROFILE%/AppData/Local/omp`.\n    - Non-Windows: `~/.local/bin`.\n- **Natives cache root** (`getNativesDir()`):\n  - if `$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\nFor each filename, candidates are, in order:\n\n1. `<leafPackageDir>/<filename>` (omitted when `leafPackageDir` is `null`)\n2. `<nativeDir>/<filename>`\n3. `<execDir>/<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\nFor each filename, candidates are:\n\n1. `<versionedDir>/<filename>`\n2. `<userDataDir>/<filename>`\n3. `<nativeDir>/<filename>`\n4. `<execDir>/<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- `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- `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`, `ShellExecuteResult`, `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",
@@ -56,7 +56,7 @@ 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/--<cwd-encoded>--/*.jsonl`\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   - breadcrumb cwd matches current cwd (resolved path compare)\n   - referenced file still exists\n3. If breadcrumb is invalid/missing, fall back to newest file by mtime in the session dir (`findMostRecentSession`)\n4. 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 matched session cwd differs from current cwd, CLI prompts whether to fork into current project\n- yes -> `SessionManager.forkFrom(...)`\n- no -> throws error (`Session \"...\" is in another project (...)`)\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: print `No sessions found` and exit early\n3. open TUI picker (`selectSession`)\n4. if canceled: print `No session selected` and exit early\n5. if selected: `SessionManager.open(selectedPath)`\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)` creates a standalone TUI with `SessionSelectorComponent` and resolves exactly once:\n\n- selection -> resolves selected path\n- cancel (Esc) -> resolves `null`\n- hard exit (Ctrl+C path) -> stops TUI and `process.exit(0)`\n\n## Interactive in-session picker (`SelectorController.showSessionSelector`)\n\nFlow:\n\n1. fetch sessions from current session dir via `SessionManager.list(currentCwd, currentSessionDir)`\n2. mount `SessionSelectorComponent` in editor area using `showSelector(...)`\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- fuzzy search across session id/title/cwd/first message/all messages/path\n\nEmpty-list render behavior:\n\n- renders `No sessions in current folder. Press Tab to view all.`\n- Enter/Delete on empty do nothing (no callback)\n- Esc/Ctrl+C still work\n\nCaveat: the empty-state UI mentions Tab, but this component currently has no Tab handler and current wiring only lists current-scope sessions.\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. clear queued steering/follow-up/next-turn message buffers\n7. flush session writer (`sessionManager.flush()`) to persist pending writes\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 default model from `sessionContext.models.default` if available and present in 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 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- clear chat container and rerender from session context (`renderInitialMessages`)\n- reload todos from new session artifacts\n- show `Resumed session`\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 `#restoreModeFromSession()` to re-enter persisted mode state (currently plan/plan_paused).\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- No dedicated post-switch mode restore call is made in selector flow; mode re-entry behavior is not symmetric with startup `#restoreModeFromSession()`.\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/modes/controllers/input-controller.ts` — command routing (`/tree`, `/branch`, double-escape behavior)\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 user-role content messages\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/--<cwd-encoded>--/<timestamp>_<sessionId>.jsonl\n```\n\n`<cwd-encoded>` is derived from the working directory by stripping leading slash and replacing `/`, `\\\\`, and `:` with `-`.\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?)` resolves what is sent to the model.\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`, move operations, and tool-call arg rewrites.\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`, `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`, `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)`\n- FTS5 index: `history_fts` with trigger-maintained sync\n- Deduplicates consecutive identical prompts using in-memory last-prompt cache\n- Async insertion (`setImmediate`) so prompt capture does not block turn execution\n\nUse session files for conversation graph/state replay; use `HistoryStorage` for prompt history UX.\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- 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  - `skills.customDirectories` scans via `scanSkillsFromDir` in `src/discovery/helpers.ts` (non-recursive)\n- non-native providers can load skills without description\n\n## Discovery pipeline\n\n`discoverSkills()` 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:` or `--extension`/`-e`\n3. `claude` (priority 80)\n4. priority 70 group (in registration order):\n   - `claude-plugins`\n   - `agents`\n   - `codex`\n5. `opencode` (priority 55)\n\nDedup key is skill name. First item with a given name wins.\n\n### Source toggles and filtering\n\n`discoverSkills()` applies these controls:\n\n- source toggles: `enableCodexUser`, `enableClaudeUser`, `enableClaudeProject`, `enablePiUser`, `enablePiProject`\n- `disabledExtensions` entries with `skill:<name>`\n- `ignoredSkills` (exclude)\n- `includeSkills` (include allowlist; 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   For providers other than codex/claude/native (for example `agents`, `claude-plugins`, `opencode`), enablement currently falls back to: enabled if **any** built-in 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 `discoverSkillsFromDir({ 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:243-249` for Enter, `input-controller.ts:462-500` 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 (up to depth 20), excluding hidden-directory segments.\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.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- 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  - `skills.customDirectories` scans via `scanSkillsFromDir` in `src/discovery/helpers.ts` (non-recursive)\n- non-native providers can load skills without description\n\n## Discovery pipeline\n\n`discoverSkills()` 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:` or `--extension`/`-e`\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`discoverSkills()` applies these controls:\n\n- source toggles: `enableCodexUser`, `enableClaudeUser`, `enableClaudeProject`, `enablePiUser`, `enablePiProject`\n- `disabledExtensions` entries with `skill:<name>`\n- `ignoredSkills` (exclude)\n- `includeSkills` (include allowlist; 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   For providers other than codex/claude/native (for example `agents`, `claude-plugins`, `opencode`), enablement currently falls back to: enabled if **any** built-in 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 `discoverSkillsFromDir({ 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:243-249` for Enter, `input-controller.ts:462-500` 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 (up to depth 20), excluding hidden-directory segments.\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. Marketplace-installed plugins from the OMP and Claude plugin registries.\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`, `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// Matches common API key patterns: sk-..., pk-..., AKIA..., ghp_..., etc.\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  /\\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      package.json\n      index.ts\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\nEach plugin directory (regardless of source type) should contain:\n\n```\nmy-plugin/\n  package.json          ← required: declares omp.extensions entry points\n  src/\n    main.ts             ← extension factory\n  README.md             ← recommended: description + usage\n```\n\nMinimum `package.json`:\n\n```json\n{\n  \"name\": \"my-plugin\",\n  \"omp\": {\n    \"extensions\": [\"./src/main.ts\"]\n  }\n}\n```\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",
@@ -65,7 +65,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"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",
 	"slash-command-internals.md": "# Slash command internals\n\nThis document describes how slash commands are discovered, deduplicated, surfaced in interactive mode, and expanded at prompt time in `coding-agent`.\n\n## Implementation files\n\n- [`src/extensibility/slash-commands.ts`](../packages/coding-agent/src/extensibility/slash-commands.ts)\n- [`src/capability/slash-command.ts`](../packages/coding-agent/src/capability/slash-command.ts)\n- [`src/discovery/builtin.ts`](../packages/coding-agent/src/discovery/builtin.ts)\n- [`src/discovery/claude.ts`](../packages/coding-agent/src/discovery/claude.ts)\n- [`src/discovery/codex.ts`](../packages/coding-agent/src/discovery/codex.ts)\n- [`src/discovery/claude-plugins.ts`](../packages/coding-agent/src/discovery/claude-plugins.ts)\n- [`src/capability/index.ts`](../packages/coding-agent/src/capability/index.ts)\n- [`src/discovery/helpers.ts`](../packages/coding-agent/src/discovery/helpers.ts)\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`src/modes/interactive-mode.ts`](../packages/coding-agent/src/modes/interactive-mode.ts)\n- [`src/modes/controllers/input-controller.ts`](../packages/coding-agent/src/modes/controllers/input-controller.ts)\n- [`src/modes/utils/ui-helpers.ts`](../packages/coding-agent/src/modes/utils/ui-helpers.ts)\n- [`src/modes/controllers/command-controller.ts`](../packages/coding-agent/src/modes/controllers/command-controller.ts)\n\n## 1) Discovery model\n\nSlash commands are a capability (`id: \"slash-commands\"`) keyed by command name (`key: cmd => cmd.name`).\n\nThe capability registry loads all registered providers, sorted by provider priority descending, and deduplicates by key with **first wins** semantics.\n\n### Provider precedence\n\nCurrent slash-command providers and priorities:\n\n1. `native` (OMP) — priority `100`\n2. `claude` — priority `80`\n3. `claude-plugins` — priority `70`\n4. `codex` — priority `70`\n5. `opencode` — priority `55`\n\nTie behavior: equal-priority providers keep registration order. Current import order registers `claude-plugins` before `codex`, so plugin commands win over codex commands on name collisions.\n\n### Name-collision behavior\n\nFor `slash-commands`, collisions are resolved strictly by capability dedup:\n\n- highest-precedence item is kept in `result.items`\n- lower-precedence duplicates remain only in `result.all` and are marked `_shadowed = true`\n\nThis applies across providers and also within a provider if it returns duplicate names.\n\n### File scanning behavior\n\nProviders mostly use `loadFilesFromDir(...)`, which currently:\n\n- defaults to non-recursive matching (`*.md`)\n- uses native glob with `gitignore: true`, `hidden: false`, `fileType: File`\n- reads matching files in parallel and transforms them into `SlashCommand` items\n\nSo hidden files/directories are not loaded, ignored paths are skipped, and file order follows native glob result order unless a provider adds its own ordering.\n\n## 2) Provider-specific source paths and local precedence\n\n## `native` provider (`builtin.ts`)\n\nSearch roots come from `.omp` directories:\n\n- project: `<cwd>/.omp/commands/*.md`\n- user: `~/.omp/agent/commands/*.md`\n\n`getConfigDirs()` returns project first, then user, so **project native commands beat user native commands** when names collide.\n\n## `claude` provider (`claude.ts`)\n\nLoads, subject to `commands.enableClaudeUser` and `commands.enableClaudeProject` settings:\n\n- user: `~/.claude/commands/*.md`\n- project: `<cwd>/.claude/commands/*.md`\n\nThe provider pushes user items before project items, so **user Claude commands beat project Claude commands** on same-name collisions inside this provider.\n\n## `codex` provider (`codex.ts`)\n\nLoads:\n\n- user: `~/.codex/commands/*.md`\n- project: `<cwd>/.codex/commands/*.md`\n\nBoth sides are loaded then flattened in user-first order, so **user Codex commands beat project Codex commands** on collisions.\n\nCodex command content is parsed with frontmatter stripping (`parseFrontmatter`), and command name can be overridden by frontmatter `name`; otherwise filename is used.\n\n## `opencode` provider (`opencode.ts`)\n\nLoads, subject to `commands.enableOpencodeUser` and `commands.enableOpencodeProject` settings:\n\n- user: `~/.config/opencode/commands/*.md`\n- project: `<cwd>/.opencode/commands/*.md`\n\nBoth sides are loaded then flattened in user-first order, so **user OpenCode commands beat project OpenCode commands** on collisions. OpenCode command content is parsed with frontmatter stripping, and command name can be overridden by frontmatter `name`; otherwise filename is used.\n\n## `claude-plugins` provider (`claude-plugins.ts`)\n\nLoads plugin command roots from `~/.claude/plugins/installed_plugins.json`, then scans `<pluginRoot>/commands/*.md`.\n\nOrdering follows registry iteration order and per-plugin entry order from that JSON data. There is no additional sort step.\n\n## 3) Materialization to runtime `FileSlashCommand`\n\n`loadSlashCommands()` in `src/extensibility/slash-commands.ts` converts capability items into `FileSlashCommand` objects used at prompt time.\n\nFor each command:\n\n1. parse frontmatter/body (`parseFrontmatter`)\n2. description source:\n   - `frontmatter.description` if present\n   - else first non-empty body line (trimmed, max 60 chars with `...`)\n3. keep parsed body as executable template content\n4. compute a display source string like `via Claude Code Project`\n\nFrontmatter parse severity is source-dependent:\n\n- `native` level -> parse errors are `fatal`\n- `user`/`project` levels -> parse errors are `warn` with fallback parsing\n\n### Bundled fallback commands\n\nAfter filesystem/provider commands, embedded command templates are appended (`EMBEDDED_COMMAND_TEMPLATES`) if their names are not already present.\n\nCurrent embedded set comes from `src/task/commands.ts` and is used as a fallback (`source: \"bundled\"`).\n\n## 4) Interactive mode: where command lists come from\n\nInteractive mode combines multiple command sources for autocomplete and command routing.\n\nAt construction time it builds a pending command list from:\n\n- built-ins (`BUILTIN_SLASH_COMMANDS`, includes argument completion and inline hints for selected commands)\n- extension-registered slash commands (`extensionRunner.getRegisteredCommands(...)`)\n- TypeScript custom commands (`session.customCommands`), mapped to slash command labels\n- optional skill commands (`/skill:<name>`) when `skills.enableSkillCommands` is enabled\n\nThen `init()` calls `refreshSlashCommandState(...)` to load file-based commands and install one `CombinedAutocompleteProvider` containing:\n\n- pending commands above\n- discovered file-based commands\n\n`refreshSlashCommandState(...)` also updates `session.setSlashCommands(...)` so prompt expansion uses the same discovered file command set.\n\n### Refresh lifecycle\n\nSlash command state is refreshed:\n\n- during interactive init\n- after `/move` changes working directory (`handleMoveCommand` calls `resetCapabilities()` then `refreshSlashCommandState(newCwd)`)\n\nThere is no continuous file watcher for command directories.\n\n### Other surfacing\n\nThe Extensions dashboard also loads `slash-commands` capability and displays active/shadowed command entries, including `_shadowed` duplicates.\n\n## 5) Prompt pipeline placement\n\n`AgentSession.prompt(...)` slash handling order (when `expandPromptTemplates !== false`):\n\n1. **Extension commands** (`#tryExecuteExtensionCommand`)  \n   If `/name` matches extension-registered command, handler executes immediately and prompt returns.\n2. **TypeScript custom commands** (`#tryExecuteCustomCommand`)  \n   Boundary only: if matched, it executes and may return:\n   - `string` -> replace prompt text with that string\n   - `void/undefined` -> treated as handled; no LLM prompt\n3. **File-based slash commands** (`expandSlashCommand`)  \n   If text still starts with `/`, attempt markdown command expansion.\n4. **Prompt templates** (`expandPromptTemplate`)  \n   Applied after slash/custom processing.\n5. **Delivery**\n   - idle: prompt is sent immediately to agent\n   - streaming: prompt is queued as steer/follow-up depending on `streamingBehavior`\n\nThis is why slash command expansion sits before prompt-template expansion, and why custom commands can transform away the leading slash before file-command matching.\n\n## 6) Expansion semantics for file-based slash commands\n\n`expandSlashCommand(text, fileCommands)` behavior:\n\n- only runs when text begins with `/`\n- parses command name from first token after `/`\n- parses args from remaining text via `parseCommandArgs`\n- finds exact name match in loaded `fileCommands`\n- if matched, applies:\n  - positional replacement: `$1`, `$2`, ...\n  - slice replacement: `$@[start]` / `$@[start:length]` using 1-based positions\n  - aggregate replacement: `$ARGUMENTS` and `$@`\n  - template rendering via `prompt.render` with `{ args, ARGUMENTS, arguments }`\n  - inline-argument fallback append when the template did not use an inline argument placeholder\n\n### `parseCommandArgs` caveats\n\nThe parser is simple quote-aware splitting:\n\n- supports `'single'` and `\"double\"` quoting to keep spaces\n- strips quote delimiters\n- does not implement backslash escaping rules\n- unmatched quote is not an error; parser consumes until end\n\n## 7) Unknown `/...` behavior\n\nUnknown slash input is **not rejected** by core slash logic.\n\nIf command is not handled by extension/custom/file layers, `expandSlashCommand` returns original text, and the literal `/...` prompt proceeds through normal prompt-template expansion and LLM delivery.\n\nInteractive mode separately hard-handles many built-ins in `InputController` (for example `/settings`, `/model`, `/mcp`, `/move`, `/exit`). Those are consumed before `session.prompt(...)` and therefore never reach file-command expansion in that path.\n\n## 8) Streaming-time differences vs idle\n\n## Idle path\n\n- `session.prompt(\"/x ...\")` runs command pipeline and either executes command immediately or sends expanded text directly.\n\n## Streaming path (`session.isStreaming === true`)\n\n- `prompt(...)` still runs extension/custom/file/template transforms first\n- then requires `streamingBehavior`:\n  - `\"steer\"` -> queue interrupt message (`agent.steer`)\n  - `\"followUp\"` -> queue post-turn message (`agent.followUp`)\n- if `streamingBehavior` is omitted, prompt throws an error\n\n### Important command-specific streaming behavior\n\n- Extension commands are executed immediately even during streaming (not queued as text).\n- `steer(...)`/`followUp(...)` helper methods reject extension commands (`#throwIfExtensionCommand`) to avoid queuing command text for handlers that must run synchronously.\n- Compaction queue replay uses `isKnownSlashCommand(...)` to decide whether queued entries should be replayed via `session.prompt(...)` (for known slash commands) vs raw steer/follow-up methods.\n\n## 9) Error handling and failure surfaces\n\n- Provider load failures are isolated; registry collects warnings and continues with other providers.\n- Invalid slash command items (missing name/path/content or invalid level) are dropped by capability validation.\n- Frontmatter parse failures:\n  - native commands: fatal parse error bubbles\n  - non-native commands: warning + fallback key/value parse\n- Extension/custom command handler exceptions are caught and reported via extension error channel (or logger fallback for custom commands without extension runner), and treated as handled (no unintended fallback execution).\n",
 	"system-prompt-customization.md": "# System Prompt Customization\n\nHow the coding-agent assembles the system prompt sent to the model, and what users can control via `SYSTEM.md`, `APPEND_SYSTEM.md`, and the matching CLI flags.\n\nPrimary implementation:\n\n- `packages/coding-agent/src/system-prompt.ts` (`buildSystemPrompt`, `loadSystemPromptFiles`)\n- `packages/coding-agent/src/main.ts` (`discoverSystemPromptFile`, `discoverAppendSystemPromptFile`)\n- `packages/coding-agent/src/prompts/system/system-prompt.md` (default stable instruction template)\n- `packages/coding-agent/src/prompts/system/custom-system-prompt.md` (internal custom-prompt template; not the normal CLI `SYSTEM.md` path)\n- `packages/coding-agent/src/prompts/system/project-prompt.md` (project/environment footer)\n\n---\n\n## 1) Inputs\n\nFour user-controllable inputs feed prompt assembly. All four resolve a value as either a literal string or, if the argument looks like a file path, the contents of that file (`resolvePromptInput`).\n\n| Input | Source | Effect |\n|---|---|---|\n| `--system-prompt <text-or-file>` | CLI flag | Replaces block 0: the default stable instructions. Highest precedence. |\n| `SYSTEM.md` | `<cwd>/.omp/SYSTEM.md`, then `~/.omp/agent/SYSTEM.md` (and equivalent paths under `.claude`, `.codex`, `.gemini`) | Same effect as `--system-prompt`; used when the flag is absent. |\n| `--append-system-prompt <text-or-file>` | CLI flag | Adds a prompt block. Without a custom system prompt it goes after all default blocks; with one it goes after the custom block and before the preserved project/environment footer. |\n| `APPEND_SYSTEM.md` | Same discovery as `SYSTEM.md` | Same effect as `--append-system-prompt`; used when the flag is absent. |\n\nDiscovery for `SYSTEM.md` / `APPEND_SYSTEM.md` uses `findConfigFile` (`packages/coding-agent/src/config.ts`): the first existing file across the ordered bases (`.omp`, `.claude`, `.codex`, `.gemini` — project-level at `<cwd>` first, then user-level at `~`) wins. **No ancestor walk-up.** Running `omp` from `<repo>/subdir` does not pick up `<repo>/.omp/SYSTEM.md`; the file must live directly under the cwd's config base or in the user-level location. See [`docs/config-usage.md`](./config-usage.md) for the full discovery contract.\n\nPrecedence (highest first):\n\n1. `--system-prompt`\n2. project `SYSTEM.md`\n3. user `SYSTEM.md`\n\nFor append, the same precedence applies between `--append-system-prompt`, project `APPEND_SYSTEM.md`, and user `APPEND_SYSTEM.md`.\n\n---\n\n## 2) Replace vs. append\n\nNormal CLI startup builds the default provider-facing prompt blocks first, then applies CLI / discovered file overrides in `packages/coding-agent/src/main.ts`:\n\n```ts\nif (resolvedSystemPrompt && resolvedAppendPrompt) {\n  options.systemPrompt = defaultPrompt => [resolvedSystemPrompt, resolvedAppendPrompt, ...defaultPrompt.slice(1)];\n} else if (resolvedSystemPrompt) {\n  options.systemPrompt = defaultPrompt => [resolvedSystemPrompt, ...defaultPrompt.slice(1)];\n} else if (resolvedAppendPrompt) {\n  options.systemPrompt = defaultPrompt => [...defaultPrompt, resolvedAppendPrompt];\n}\n```\n\nThe default blocks come from `buildSystemPrompt`:\n\n- block 0: `system-prompt.md` — the stable default instructions (staff-engineer preamble, tool inventory, exploration rules, workflow rules, etc.);\n- block 1, when non-empty: `project-prompt.md` — dynamic project/environment context (workstation info, context files, dir-context list, workspace tree, current date/cwd, and other project footer content).\n\nConsequences for normal CLI use:\n\n- Providing `--system-prompt` or `SYSTEM.md` replaces only block 0. The stable default instructions are removed, but the dynamic project/environment footer from `project-prompt.md` remains as `defaultPrompt.slice(1)`.\n- Providing `--append-system-prompt` or `APPEND_SYSTEM.md` without a custom system prompt appends a new block after all default blocks.\n- Providing both a custom system prompt and an append prompt produces: custom system prompt block, append prompt block, then the preserved dynamic project/environment footer.\n\nIf you want to keep both default blocks and add to them, use `--append-system-prompt` / `APPEND_SYSTEM.md` without `--system-prompt` / `SYSTEM.md`. If you want to replace the stable default instructions while keeping the dynamic footer, use `--system-prompt` / `SYSTEM.md`.\n\n---\n\n## 3) Templating contract\n\n**Contents of `SYSTEM.md`, `APPEND_SYSTEM.md`, `--system-prompt`, and `--append-system-prompt` are treated as plain text.** They are resolved before prompt-block replacement and are not rendered as Handlebars templates.\n\nThe built-in prompt templates are Handlebars (`packages/utils/src/prompt.ts`), but user-provided strings are not compiled with that renderer. The secondary capability path can insert `systemPromptCustomization` into a Handlebars parent template, but a `{{value}}` reference in Handlebars still does not recursively render its substituted contents — the value is emitted as a string. Concretely:\n```handlebars\n{{! parent template — handled by Handlebars }}\n{{#if systemPromptCustomization}}\n{{systemPromptCustomization}}\n{{/if}}\n```\n\nIf `SYSTEM.md` contains:\n\n```handlebars\nWorking in {{cwd}} on {{date}}.\n{{#if hasMemoryRoot}}Memory enabled.{{/if}}\n```\n\nthe rendered output contains those characters verbatim — `{{cwd}}`, `{{#if hasMemoryRoot}}`, etc. are NOT substituted. They will be shown to the model as literal Handlebars syntax.\n\nThis is by design. The internal template variables (`cwd`, `date`, `environment`, `workspaceTree`, `skills`, `rules`, `toolRefs`, `hasMemoryRoot`, `hasObsidian`, `mcpDiscoveryServerSummaries`, ...) are not a supported public surface — they change between releases as the prompt is rewritten, and they would couple user configs to internals. Treat them as private.\n\nIf a future release exposes a templating surface for `SYSTEM.md`, it will be opt-in (e.g. via a settings flag or a different filename) and documented here.\n\n---\n\n## 4) Recommended patterns\n\n### \"Tweak the default\" — keep default, add a few rules\n\nUse `APPEND_SYSTEM.md` (or `--append-system-prompt`) without `SYSTEM.md`. The default stable instructions and the dynamic project/environment footer stay intact; your text is appended as an additional block.\n\n```text\n# ~/.omp/agent/APPEND_SYSTEM.md\nPrefer Bun APIs over Node APIs in this project.\nWhen you change a public function, run `bun check` before yielding.\n```\n\n### \"Replace the stable default instructions\" — bring your own base prompt\n\nUse `SYSTEM.md` (or `--system-prompt`). You replace the stable default instructions in block 0, but normal CLI startup still preserves the dynamic project/environment footer block (`project-prompt.md`): workstation info, context files, dir-context list, workspace tree, current date, cwd, and related project context.\n\n```text\n# ~/.omp/agent/SYSTEM.md\nYou are a code reviewer. Read diffs, surface issues, never edit files.\n- Cite paths with backticks.\n- Prefer concrete fixes over abstract advice.\n```\n\nIf you do this and want default tool guidance, exploration rules, or workflow rules, copy what you need from `packages/coding-agent/src/prompts/system/system-prompt.md` and maintain it yourself — there is currently no way to inherit selected sections from that stable default instruction block.\n\n### \"Customize while keeping generated skills/rules/tool guidance\"\n\nUse `APPEND_SYSTEM.md`, not `SYSTEM.md`. Skills, rulebook summaries, always-apply rules, the tool inventory, and the built-in guidance that tells the model when to read `skill://<name>` are part of block 0 (`system-prompt.md`). Because `SYSTEM.md` replaces block 0, those generated lists are not available to the model in a custom system prompt.\n\nThe dynamic project/environment footer that remains after `SYSTEM.md` is only block 1 (`project-prompt.md`): workstation info, AGENTS.md context files, dir-context list, workspace tree, current date, cwd, and related project context. It does not include discovered skills.\n\nThere is currently no supported CLI mode for \"replace the stable default instructions but keep the generated skills/rules/tool guidance.\" If you need automatic skills loading, keep the default block and add your customization via `APPEND_SYSTEM.md`. If you fully replace with `SYSTEM.md`, you must hard-code any skill names/instructions you want the model to know about, and those will not track discovery automatically.\n\n### \"Replace everything, including project context\" — SDK-only\n\nThe normal CLI file/flag path intentionally preserves `defaultPrompt.slice(1)`. Code using `CreateAgentSessionOptions.systemPrompt` directly can return a full replacement array and omit the project footer, but that is not what `.omp/SYSTEM.md`, `~/.omp/agent/SYSTEM.md`, or `--system-prompt` do.\n\n### \"Replace, but keep one section of the default instructions\" — not directly supported\n\nThere is no built-in way to inherit specific sections from `system-prompt.md` while replacing the rest. The supported CLI modes are: append to the default prompt, or replace block 0 and keep the dynamic footer.\n\n---\n\n## 5) Deduplication\n\nThe CLI path avoids double-injecting discovered `SYSTEM.md` by replacing block 0 after the default prompt blocks are rendered. Any `systemPromptCustomization` from the secondary capability path would have been rendered into block 0, and that block is discarded when `main.ts` applies `[resolvedSystemPrompt, ...defaultPrompt.slice(1)]`.\n\nInside `buildSystemPrompt` itself, secondary customization and always-apply rules are still deduplicated:\n\n- `dedupePromptSource` drops a `systemPromptCustomization` block when it already appears in an internally supplied `customPrompt` or append prompt.\n- `dedupeAlwaysApplyRules` omits always-apply rules whose body appears verbatim in any of `{customPrompt, appendPrompt, systemPromptCustomization}`.\n\n---\n\n## 6) Discovery paths\n\nOnly one path actually drives the customization a CLI user sees: the primary CLI path. The capability layer exists but its `SYSTEM.md` output never reaches the rendered prompt under normal CLI startup.\n\n- The primary CLI path (`discoverSystemPromptFile` / `discoverAppendSystemPromptFile` in `main.ts`, which feeds `resolvedSystemPrompt` / `resolvedAppendPrompt`) calls `findConfigFile`. `findConfigFile` checks only `<cwd>/.omp`, `<cwd>/.claude`, `<cwd>/.codex`, `<cwd>/.gemini`, and the user-level equivalents — it does **not** walk up ancestors. Files in `<ancestor>/.omp/SYSTEM.md` are ignored when `omp` is started from a subdirectory.\n- The secondary capability path (`loadSystemPromptFiles` → builtin discovery) does walk up via `findNearestProjectConfigDir` and requires the project `.omp/` directory to be non-empty. Its result is rendered into the template variable `systemPromptCustomization`. Under normal CLI startup the default template (`system-prompt.md`) never references that variable, so ancestor-walk capability content has no user-visible effect.\n\nNet effect for CLI users: put `SYSTEM.md` / `APPEND_SYSTEM.md` directly under `<cwd>/.omp` (or another supported config base under cwd) or in the user-level location (`~/.omp/agent/SYSTEM.md` etc.). Ancestor paths are not searched.\n\n---\n\n## 7) Quick reference\n\n| Goal | Use |\n|---|---|\n| Add an instruction on top of the full default prompt | `APPEND_SYSTEM.md` or `--append-system-prompt` |\n| Replace the stable default instructions but keep project/environment context | `SYSTEM.md` or `--system-prompt` |\n| Preserve generated skills/rules/tool guidance while customizing | `APPEND_SYSTEM.md`; `SYSTEM.md` replaces that generated block |\n| Use `{{cwd}}` / `{{date}}` / other internals in my file | Not supported. Files are inserted verbatim. |\n| Inherit specific sections from `system-prompt.md` | Not supported; use append, or copy what you need into `SYSTEM.md`. |\n| Override at a per-repo level | Project `.omp/SYSTEM.md` under the cwd you launch `omp` from |\n| Override globally | `~/.omp/agent/SYSTEM.md` or `~/.omp/agent/APPEND_SYSTEM.md` |\n",
-	"task-agent-discovery.md": "# Task Agent Discovery and Selection\n\nThis document describes how the task subsystem discovers agent definitions, merges multiple sources, and resolves a requested agent at execution time.\n\nIt covers runtime behavior as implemented today, including precedence, invalid-definition handling, and spawn/depth constraints that can make an agent effectively unavailable.\n\n## Implementation files\n\n- [`src/task/discovery.ts`](../packages/coding-agent/src/task/discovery.ts)\n- [`src/task/agents.ts`](../packages/coding-agent/src/task/agents.ts)\n- [`src/task/types.ts`](../packages/coding-agent/src/task/types.ts)\n- [`src/task/index.ts`](../packages/coding-agent/src/task/index.ts)\n- [`src/task/commands.ts`](../packages/coding-agent/src/task/commands.ts)\n- [`src/prompts/agents/task.md`](../packages/coding-agent/src/prompts/agents/task.md)\n- [`src/prompts/tools/task.md`](../packages/coding-agent/src/prompts/tools/task.md)\n- [`src/discovery/helpers.ts`](../packages/coding-agent/src/discovery/helpers.ts)\n- [`src/config.ts`](../packages/coding-agent/src/config.ts)\n- [`src/task/executor.ts`](../packages/coding-agent/src/task/executor.ts)\n\n---\n\n## Agent definition shape\n\nTask agents normalize into `AgentDefinition` (`src/task/types.ts`):\n\n- `name`, `description`, `systemPrompt` (required for a valid loaded agent)\n- optional `tools`, `spawns`, `model`, `thinkingLevel`, `output`, `blocking`\n- `source`: `\"bundled\" | \"user\" | \"project\"`\n- optional `filePath`\n\nParsing comes from frontmatter via `parseAgentFields()` (`src/discovery/helpers.ts`):\n\n- missing `name` or `description` => invalid (`null`), caller treats as parse failure\n- `tools` accepts CSV or array; if provided, `yield` is auto-added\n- `spawns` accepts `*`, CSV, or array\n- backward-compat behavior: if `spawns` missing but `tools` includes `task`, `spawns` becomes `*`\n- `output` is passed through as opaque schema data\n\n## Bundled agents\n\nBundled agents are embedded at build time (`src/task/agents.ts`) using text imports.\n\n`EMBEDDED_AGENT_DEFS` defines:\n\n- `explore`, `plan`, `designer`, `reviewer` from prompt files\n- `task` and `quick_task` from shared `task.md` body plus injected frontmatter\n\nLoading path:\n\n1. `loadBundledAgents()` parses embedded markdown with `parseAgent(..., \"bundled\", \"fatal\")`\n2. results are cached in-memory (`bundledAgentsCache`)\n3. `clearBundledAgentsCache()` is test-only cache reset\n\nBecause bundled parsing uses `level: \"fatal\"`, malformed bundled frontmatter throws and can fail discovery entirely.\n\n## Filesystem and plugin discovery\n\n`discoverAgents(cwd, home)` (`src/task/discovery.ts`) merges agents from multiple places before appending bundled definitions.\n\n### Discovery inputs\n\n1. User config agent dirs from `getConfigDirs(\"agents\", { project: false })`\n2. Nearest project agent dirs from `findAllNearestProjectConfigDirs(\"agents\", cwd)`\n3. Claude plugin roots (`listClaudePluginRoots(home)`) with `agents/` subdirs\n4. Bundled agents (`loadBundledAgents()`)\n\n### Actual source order\n\nSource-family order comes from `getConfigDirs(\"\", { project: false })`, which is derived from `priorityList` in `src/config.ts`:\n\n1. `.omp`\n2. `.claude`\n3. `.codex`\n4. `.gemini`\n\nFor each source family, discovery order is:\n\n1. nearest project dir for that source (if found)\n2. user dir for that source\n\nAfter all source-family dirs, plugin `agents/` dirs are appended (project-scope plugins first, then user-scope).\n\nBundled agents are appended last.\n\n### Important caveat: stale comments vs current code\n\n`discovery.ts` header comments still mention `.pi` and do not mention `.codex`/`.gemini`. Actual runtime order is driven by `src/config.ts` and currently uses `.omp`, `.claude`, `.codex`, `.gemini`.\n\n## Merge and collision rules\n\nDiscovery uses first-wins dedup by exact `agent.name`:\n\n- A `Set<string>` tracks seen names.\n- Loaded agents are flattened in directory order and kept only if name unseen.\n- Bundled agents are filtered against the same set and only added if still unseen.\n\nImplications:\n\n- Project overrides user for same source family.\n- Higher-priority source family overrides lower (`.omp` before `.claude`, etc.).\n- Non-bundled agents override bundled agents with the same name.\n- Name matching is case-sensitive (`Task` and `task` are distinct).\n- Within one directory, markdown files are read in lexicographic filename order before dedup.\n\n## Invalid/missing agent file behavior\n\nPer directory (`loadAgentsFromDir`):\n\n- unreadable/missing directory: treated as empty (`readdir(...).catch(() => [])`)\n- file read or parse failure: warning logged, file skipped\n- parse path uses `parseAgent(..., level: \"warn\")`\n\nFrontmatter failure behavior comes from `parseFrontmatter`:\n\n- parse error at `warn` level logs warning\n- parser falls back to a simple `key: value` line parser\n- if required fields are still missing, `parseAgentFields` fails, then `AgentParsingError` is thrown and caught by caller (file skipped)\n\nNet effect: one bad custom agent file does not abort discovery of other files.\n\n## Agent lookup and selection\n\nLookup is exact-name linear search:\n\n- `getAgent(agents, name)` => `agents.find(a => a.name === name)`\n\nIn synchronous task execution (`TaskTool.#executeSync`):\n\n1. agents are rediscovered at execution time (`discoverAgents(this.session.cwd)`)\n2. requested `params.agent` is resolved through `getAgent`\n3. missing agent returns immediate tool response:\n   - `Unknown agent \"...\". Available: ...`\n   - no subprocess runs\n\n### Description vs execution-time discovery\n\n`TaskTool.create()` builds the tool description from discovery results at initialization time. `#executeSync` rediscovers agents, so the runtime set can differ from what was listed in the earlier tool description if agent files changed mid-session. The async entry path still uses the initialization-time list to decide whether an agent is marked `blocking` before scheduling.\n\n## Structured-output guardrails and schema precedence\n\nRuntime output schema precedence in `TaskTool.execute`:\n\n1. task call `params.schema` when `task.simple` allows custom schemas\n2. agent frontmatter `output`\n3. parent session `outputSchema`\n\n(`effectiveOutputSchema = outputSchema ?? effectiveAgent.output ?? this.session.outputSchema` when custom task schemas are enabled; otherwise task-call schema is skipped.)\n\nPrompt-time guardrail text in `src/prompts/tools/task.md` warns about mismatch behavior for structured-output agents (`explore`, `reviewer`): output-format instructions in prose can conflict with built-in schema and produce `null` outputs.\n\nThis is guidance, not hard runtime validation logic in `discoverAgents`.\n\n## Command discovery interaction\n\n`src/task/commands.ts` is parallel infrastructure for workflow commands (not agent definitions), but it follows the same overall pattern:\n\n- discover from capability providers first\n- deduplicate by name with first-wins\n- append bundled commands if still unseen\n- exact-name lookup via `getCommand`\n\nIn `src/task/index.ts`, command helpers are re-exported with agent discovery helpers. Agent discovery itself does not depend on command discovery at runtime.\n\n## Availability constraints beyond discovery\n\nAn agent can be discoverable but still unavailable to run because of execution guardrails.\n\n### Disabled-agent settings\n\n`TaskTool.#executeSync` checks `task.disabledAgents` after resolving the agent. If the requested name is disabled, execution returns an immediate error listing enabled alternatives when available.\n\n### Parent spawn policy\n\n`TaskTool.#executeSync` checks `session.getSessionSpawns()`:\n\n- `\"*\"` => allow any\n- `\"\"` => deny all\n- CSV list => allow only listed names\n\nIf denied: immediate `Cannot spawn '...'. Allowed: ...` response.\n\n### Blocked self-recursion env guard\n\n`PI_BLOCKED_AGENT` is read at tool construction. If request matches, execution is rejected with recursion-prevention message.\n\n### Recursion-depth gating (task tool availability inside child sessions)\n\nIn `runSubprocess` (`src/task/executor.ts`):\n\n- depth computed from `taskDepth`\n- `task.maxRecursionDepth` controls cutoff\n- when at max depth:\n  - `task` tool is removed from child tool list\n  - child `spawns` env is set to empty\n\nSo deeper levels cannot spawn further tasks even if the agent definition includes `spawns`.\n\n## Plan mode behavior\n\nWhen parent plan mode is enabled, `TaskTool.execute` builds an `effectiveAgent` before launching subprocesses:\n\n- prepends the plan-mode subagent system prompt\n- restricts tools to `read`, `search`, `find`, `lsp`, and `web_search`\n- clears child spawns\n\nThe same `effectiveAgent` is used for subprocess launch, model/thinking overrides, and output-schema selection.\n",
+	"task-agent-discovery.md": "# Task Agent Discovery and Selection\n\nThis document describes how the task subsystem discovers agent definitions, merges multiple sources, and resolves a requested agent at execution time.\n\nIt covers runtime behavior as implemented today, including precedence, invalid-definition handling, and spawn/depth constraints that can make an agent effectively unavailable.\n\n## Implementation files\n\n- [`src/task/discovery.ts`](../packages/coding-agent/src/task/discovery.ts)\n- [`src/task/agents.ts`](../packages/coding-agent/src/task/agents.ts)\n- [`src/task/types.ts`](../packages/coding-agent/src/task/types.ts)\n- [`src/task/index.ts`](../packages/coding-agent/src/task/index.ts)\n- [`src/task/commands.ts`](../packages/coding-agent/src/task/commands.ts)\n- [`src/prompts/agents/task.md`](../packages/coding-agent/src/prompts/agents/task.md)\n- [`src/prompts/tools/task.md`](../packages/coding-agent/src/prompts/tools/task.md)\n- [`src/discovery/helpers.ts`](../packages/coding-agent/src/discovery/helpers.ts)\n- [`src/config.ts`](../packages/coding-agent/src/config.ts)\n- [`src/task/executor.ts`](../packages/coding-agent/src/task/executor.ts)\n\n---\n\n## Agent definition shape\n\nTask agents normalize into `AgentDefinition` (`src/task/types.ts`):\n\n- `name`, `description`, `systemPrompt` (required for a valid loaded agent)\n- optional `tools`, `spawns`, `model`, `thinkingLevel`, `output`, `blocking`, `autoloadSkills`, `readSummarize`\n- `source`: `\"bundled\" | \"user\" | \"project\"`\n- optional `filePath`\n\nParsing comes from frontmatter via `parseAgentFields()` (`src/discovery/helpers.ts`):\n\n- missing `name` or `description` => invalid (`null`), caller treats as parse failure\n- `tools` accepts CSV or array; if provided, `yield` is auto-added\n- `spawns` accepts `*`, CSV, or array\n- backward-compat behavior: if `spawns` missing but `tools` includes `task`, `spawns` becomes `*`\n- `output` is passed through as opaque schema data\n- `read-summarize: false` (parsed as `readSummarize`) forces the subagent's `read` tool to return verbatim file content instead of structural summaries — `runSubprocess` applies it as a `read.summarize.enabled: false` override on the subagent's isolated settings (`src/task/executor.ts`). `explore` and `librarian` ship with it disabled. Defaults to enabled when the field is absent.\n\n## Bundled agents\n\nBundled agents are embedded at build time (`src/task/agents.ts`) using text imports.\n\n`EMBEDDED_AGENT_DEFS` defines:\n\n- `explore`, `plan`, `designer`, `reviewer` from prompt files\n- `task` and `quick_task` from shared `task.md` body plus injected frontmatter\n\nLoading path:\n\n1. `loadBundledAgents()` parses embedded markdown with `parseAgent(..., \"bundled\", \"fatal\")`\n2. results are cached in-memory (`bundledAgentsCache`)\n3. `clearBundledAgentsCache()` is test-only cache reset\n\nBecause bundled parsing uses `level: \"fatal\"`, malformed bundled frontmatter throws and can fail discovery entirely.\n\n## Filesystem and plugin discovery\n\n`discoverAgents(cwd, home)` (`src/task/discovery.ts`) merges agents from multiple places before appending bundled definitions.\n\n### Discovery inputs\n\n1. User config agent dirs from `getConfigDirs(\"agents\", { project: false })`\n2. Nearest project agent dirs from `findAllNearestProjectConfigDirs(\"agents\", cwd)`\n3. Claude plugin roots (`listClaudePluginRoots(home)`) with `agents/` subdirs\n4. Bundled agents (`loadBundledAgents()`)\n\n### Actual source order\n\nSource-family order comes from `getConfigDirs(\"\", { project: false })`, which is derived from `priorityList` in `src/config.ts`:\n\n1. `.omp`\n2. `.claude`\n3. `.codex`\n4. `.gemini`\n\nFor each source family, discovery order is:\n\n1. nearest project dir for that source (if found)\n2. user dir for that source\n\nAfter all source-family dirs, plugin `agents/` dirs are appended (project-scope plugins first, then user-scope).\n\nBundled agents are appended last.\n\n### Important caveat: stale comments vs current code\n\n`discovery.ts` header comments still mention `.pi` and do not mention `.codex`/`.gemini`. Actual runtime order is driven by `src/config.ts` and currently uses `.omp`, `.claude`, `.codex`, `.gemini`.\n\n## Merge and collision rules\n\nDiscovery uses first-wins dedup by exact `agent.name`:\n\n- A `Set<string>` tracks seen names.\n- Loaded agents are flattened in directory order and kept only if name unseen.\n- Bundled agents are filtered against the same set and only added if still unseen.\n\nImplications:\n\n- Project overrides user for same source family.\n- Higher-priority source family overrides lower (`.omp` before `.claude`, etc.).\n- Non-bundled agents override bundled agents with the same name.\n- Name matching is case-sensitive (`Task` and `task` are distinct).\n- Within one directory, markdown files are read in lexicographic filename order before dedup.\n\n## Invalid/missing agent file behavior\n\nPer directory (`loadAgentsFromDir`):\n\n- unreadable/missing directory: treated as empty (`readdir(...).catch(() => [])`)\n- file read or parse failure: warning logged, file skipped\n- parse path uses `parseAgent(..., level: \"warn\")`\n\nFrontmatter failure behavior comes from `parseFrontmatter`:\n\n- parse error at `warn` level logs warning\n- parser falls back to a simple `key: value` line parser\n- if required fields are still missing, `parseAgentFields` fails, then `AgentParsingError` is thrown and caught by caller (file skipped)\n\nNet effect: one bad custom agent file does not abort discovery of other files.\n\n## Agent lookup and selection\n\nLookup is exact-name linear search:\n\n- `getAgent(agents, name)` => `agents.find(a => a.name === name)`\n\nIn synchronous task execution (`TaskTool.#executeSync`):\n\n1. agents are rediscovered at execution time (`discoverAgents(this.session.cwd)`)\n2. requested `params.agent` is resolved through `getAgent`\n3. missing agent returns immediate tool response:\n   - `Unknown agent \"...\". Available: ...`\n   - no subprocess runs\n\n### Description vs execution-time discovery\n\n`TaskTool.create()` builds the tool description from discovery results at initialization time. `#executeSync` rediscovers agents, so the runtime set can differ from what was listed in the earlier tool description if agent files changed mid-session. The async entry path still uses the initialization-time list to decide whether an agent is marked `blocking` before scheduling.\n\n## Structured-output guardrails and schema precedence\n\nRuntime output schema precedence in `TaskTool.execute`:\n\n1. task call `params.schema` when `task.simple` allows custom schemas\n2. agent frontmatter `output`\n3. parent session `outputSchema`\n\n(`effectiveOutputSchema = outputSchema ?? effectiveAgent.output ?? this.session.outputSchema` when custom task schemas are enabled; otherwise task-call schema is skipped.)\n\nPrompt-time guardrail text in `src/prompts/tools/task.md` warns about mismatch behavior for structured-output agents (`explore`, `reviewer`): output-format instructions in prose can conflict with built-in schema and produce `null` outputs.\n\nThis is guidance, not hard runtime validation logic in `discoverAgents`.\n\n## Command discovery interaction\n\n`src/task/commands.ts` is parallel infrastructure for workflow commands (not agent definitions), but it follows the same overall pattern:\n\n- discover from capability providers first\n- deduplicate by name with first-wins\n- append bundled commands if still unseen\n- exact-name lookup via `getCommand`\n\nIn `src/task/index.ts`, command helpers are re-exported with agent discovery helpers. Agent discovery itself does not depend on command discovery at runtime.\n\n## Availability constraints beyond discovery\n\nAn agent can be discoverable but still unavailable to run because of execution guardrails.\n\n### Disabled-agent settings\n\n`TaskTool.#executeSync` checks `task.disabledAgents` after resolving the agent. If the requested name is disabled, execution returns an immediate error listing enabled alternatives when available.\n\n### Parent spawn policy\n\n`TaskTool.#executeSync` checks `session.getSessionSpawns()`:\n\n- `\"*\"` => allow any\n- `\"\"` => deny all\n- CSV list => allow only listed names\n\nIf denied: immediate `Cannot spawn '...'. Allowed: ...` response.\n\n### Blocked self-recursion env guard\n\n`PI_BLOCKED_AGENT` is read at tool construction. If request matches, execution is rejected with recursion-prevention message.\n\n### Recursion-depth gating (task tool availability inside child sessions)\n\nIn `runSubprocess` (`src/task/executor.ts`):\n\n- depth computed from `taskDepth`\n- `task.maxRecursionDepth` controls cutoff\n- when at max depth:\n  - `task` tool is removed from child tool list\n  - child `spawns` env is set to empty\n\nSo deeper levels cannot spawn further tasks even if the agent definition includes `spawns`.\n\n## Plan mode behavior\n\nWhen parent plan mode is enabled, `TaskTool.execute` builds an `effectiveAgent` before launching subprocesses:\n\n- prepends the plan-mode subagent system prompt\n- restricts tools to `read`, `search`, `find`, `lsp`, and `web_search`\n- clears child spawns\n\nThe same `effectiveAgent` is used for subprocess launch, model/thinking overrides, and output-schema selection.\n",
 	"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 (14)\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 ~60fps 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 (`Display -> Dark theme` or `Display -> 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",
 	"tools/ask.md": "# ask\n\n> Prompts the interactive user for one or more option-picker or free-form answers.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ask.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ask.md`\n- Key collaborators:\n  - `packages/coding-agent/src/config/settings-schema.ts` — `ask.timeout` / `ask.notify` defaults\n  - `packages/coding-agent/src/modes/theme/theme.ts` — checkbox and tree glyphs for TUI rendering\n  - `packages/coding-agent/src/tui.ts` — status-line rendering\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `questions` | `Question[]` | Yes | One or more questions. Empty arrays are rejected by schema and also guarded at runtime. |\n\n### `Question`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `id` | `string` | Yes | Stable identifier used in multi-question results. |\n| `question` | `string` | Yes | Prompt text shown to the user. |\n| `options` | `{ label: string }[]` | Yes | Option labels for the picker. The schema does not require a minimum length; the UI always appends `Other (type your own)`, and callers must not include it. |\n| `multi` | `boolean` | No | Enables multi-select mode. Default: `false`. |\n| `recommended` | `number` | No | Zero-based recommended option index. In single-select mode the label gets ` (Recommended)` appended in the UI. |\n\n## Outputs\n- Single-shot result.\n- `content[0].text` is plain text:\n  - single question: `User selected: ...` and/or `User provided custom input: ...`\n  - multiple questions: `User answers:` followed by one line per `id`\n- `details`:\n  - single question: `{ question, options, multi, selectedOptions, customInput? }`\n  - multiple questions: `{ results: QuestionResult[] }`, where each item includes `id`, `question`, `options`, `multi`, `selectedOptions`, and optional `customInput`\n- Cancellation and headless cases throw instead of returning a structured success result.\n\n## Flow\n1. `AskTool.createIf()` only registers the tool when `session.hasUI` is true; headless sessions never get it.\n2. `execute()` requires `context.ui`; if missing it aborts the context and throws `ToolAbortError(\"Ask tool requires interactive mode\")`.\n3. It reads `ask.timeout` from settings, converts seconds to milliseconds (`0` disables timeout), and disables timeout entirely while plan mode is enabled (`packages/coding-agent/src/tools/ask.ts`).\n4. If `ask.notify` is not `off`, it sends a terminal notification: `Waiting for input`.\n5. For each question, `askSingleQuestion()` drives either:\n   - single-select list + optional editor for `Other`\n   - multi-select checkbox loop + `Done selecting` sentinel + optional editor for `Other`\n6. In multi-question mode, left/right arrow handlers enable back/forward navigation between questions and preserve prior selections.\n7. If a timeout fires before any selection/custom input, the tool auto-selects the recommended option, or the first option when no valid `recommended` index exists.\n8. If the user cancels without timeout, `execute()` aborts the tool context and throws `ToolAbortError(\"Ask tool was cancelled by the user\")`.\n9. On success it formats human-readable text plus structured `details`; the TUI renderer uses `details` for rich display.\n\n## Modes / Variants\n- Single question: returns flattened `details` fields for one question.\n- Multiple questions: returns `details.results[]` and allows back/forward navigation across questions.\n- Single-select: one option or custom input.\n- Multi-select: toggled checkbox list, `Done selecting` sentinel only when forward navigation is not active.\n\n## Side Effects\n- User-visible prompts / interactive UI\n  - Opens a selection dialog via `context.ui.select(...)`.\n  - Opens a text editor dialog via `context.ui.editor(...)` for `Other`.\n  - Sends a terminal notification unless `ask.notify=off`.\n- Session state\n  - Reads plan-mode state to disable timeouts.\n  - Calls `context.abort()` on headless use or user cancellation.\n- Background work / cancellation\n  - Wraps UI waits in `untilAborted(...)` so abort signals interrupt pending dialogs.\n\n## Limits & Caps\n- `questions` must contain at least 1 item (`askSchema` in `packages/coding-agent/src/tools/ask.ts`).\n- `ask.timeout` default is `0` seconds, which disables timeout (`packages/coding-agent/src/config/settings-schema.ts`). Configured non-zero values are seconds.\n- Prompt guidance says provide 2-5 options, but code only requires the `options` array field and does not enforce a minimum or maximum length (`packages/coding-agent/src/prompts/tools/ask.md`).\n- Timeout only applies to the option picker; once the user chooses `Other`, the editor has no timeout (`packages/coding-agent/src/prompts/tools/ask.md`).\n\n## Errors\n- Missing interactive UI: throws `ToolAbortError(\"Ask tool requires interactive mode\")`.\n- User cancels picker/editor without timeout: throws `ToolAbortError(\"Ask tool was cancelled by the user\")`.\n- Abort signal during input: converted to `ToolAbortError(\"Ask input was cancelled\")`.\n- Empty `questions` at runtime returns a text error payload instead of throwing: `Error: questions must not be empty`.\n\n## Notes\n- `recommended` is only a UI hint; invalid indexes are ignored.\n- In single-select mode the returned `selectedOptions` value strips the appended ` (Recommended)` suffix.\n- Multi-select results preserve selection order by `Set` insertion order, not original option order after arbitrary toggles.\n- Option labels and prompt text are returned verbatim in `details`; the tool does not interpret them beyond UI affordances like `Other` and ` (Recommended)`.\n",
 	"tools/ast-edit.md": "# ast_edit\n\n> Preview and apply structural rewrites over source files via native ast-grep.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ast-edit.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ast-edit.md`\n- Key collaborators:\n  - `crates/pi-natives/src/ast.rs` — native rewrite planning and file mutation\n  - `crates/pi-ast/src/language/mod.rs` — language aliases and extension inference used by the native wrapper.\n  - `packages/coding-agent/src/tools/path-utils.ts` — path/glob parsing and multi-path resolution\n  - `packages/coding-agent/src/tools/resolve.ts` — preview/apply queueing\n  - `packages/coding-agent/src/tools/render-utils.ts` — parse-error dedupe and display caps\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — hashline vs line-number diff references\n  - `packages/hashline/src/format.ts` — stable hashline header formatting for preview anchors\n  - `packages/natives/native/index.d.ts` — JS-visible native binding contract\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `ops` | `{ pat: string; out: string }[]` | Yes | One or more rewrite rules. `pat` must be non-empty. Duplicate `pat` values fail before native execution. Empty `out` deletes the matched node. |\n| `paths` | `string[]` | Yes | One or more files, directories, globs, or internal URLs with backing files. Empty entries are rejected. Globs are forbidden for internal URLs. |\n\nShared AST pattern grammar and language catalog: see [`ast_grep`](./ast-grep.md#inputs).\n\n- `ast_edit` uses the same `$NAME`, `$_`, `$$$NAME`, and `$$$` metavariable semantics.\n- The tool prompt adds rewrite-specific constraints:\n  - metavariable names must be uppercase and must stand for whole AST nodes,\n  - captures from `pat` are substituted into `out`,\n  - each rewrite is a 1:1 structural substitution; one capture cannot expand into multiple sibling nodes unless the grammar itself permits that expansion at that position.\n\n## Outputs\n- Single-shot preview result from `ast_edit` itself.\n- Model-facing `content` is one text block showing proposed edits, grouped by file for directory/multi-file runs.\n  - Each change renders as two lines. Hashline mode uses `-LINE:before` / `+LINE:after` under a `¶PATH#TAG` header; plain mode uses `-LINE:COLUMN before` / `+LINE:COLUMN after`.\n  - Only the first line of each `before`/`after` snippet is shown, truncated to 120 characters in the wrapper.\n  - `Limit reached; narrow paths.` and formatted parse issues are appended when applicable.\n- If no rewrites match, text is `No replacements made` plus formatted parse issues when present.\n- `details` includes aggregate preview metadata:\n  - `totalReplacements`, `filesTouched`, `filesSearched`, `applied`, `limitReached`\n  - optional `parseErrors`, `scopePath`, `files`, `fileReplacements`, `displayContent`, `meta`\n- The tool always previews first (`applied: false` in the direct result). Actual file writes happen only later through `resolve(action: \"apply\", ...)`.\n- When preview produced replacements, `ast_edit` also queues a pending `resolve` action. Successful apply returns a separate `resolve` result, not another `ast_edit` result.\n\n## Flow\n1. `AstEditTool.execute()` validates each op in `packages/coding-agent/src/tools/ast-edit.ts`:\n   - empty `pat` fails,\n   - at least one op is required,\n   - duplicate `pat` values fail,\n   - ops are converted to a `Record<pattern, replacement>`.\n2. The wrapper reads `PI_MAX_AST_FILES` via `$envpos(..., 1000)` and uses that as the native `maxFiles` cap for both preview and apply.\n3. Path normalization, internal URL handling, missing-path partitioning, and multi-path resolution follow the same `path-utils.ts` flow as `ast_grep`.\n4. The wrapper stats the resolved base path to decide whether to render grouped directory output.\n5. `runAstEditOnce(...)` always runs native `astEdit(...)` with `dryRun: true` and `failOnParseError: false` on the first pass.\n6. Native `ast_edit` in `crates/pi-natives/src/ast.rs`:\n   - normalizes the rewrite map and sorts rules by pattern string,\n   - resolves strictness (`smart` by default),\n   - collects candidate files from a file or gitignore-aware directory scan,\n   - infers a single language for the whole call unless `lang` was supplied,\n   - compiles every rewrite pattern for that language,\n   - parses each file, skips files with syntax-error trees, collects `replace_by(...)` edits for every match, enforces replacement and file caps, and returns textual before/after slices plus source ranges.\n7. The TS wrapper deduplicates parse errors, groups changes by file, and renders preview diff lines.\n8. If preview found replacements and `applied` is false, `queueResolveHandler(...)` registers a forced `resolve` action and injects a `resolve-reminder` steering message.\n9. On `resolve(action: \"apply\")`, the queued callback reruns the same rewrite set with `dryRun: false`, recomputes counts, and returns an error result if the live result no longer matches the preview (`stalePreview`). The current implementation compares replacement totals and per-file counts after the rerun; if the new run has already written different counts, the result is marked error.\n10. On a non-stale apply, the callback returns `Applied N replacements in M files.`; on discard, `resolve` returns a discard message without mutating files.\n\n## Modes / Variants\n- Single file: preview or apply against one file.\n- Directory + optional glob: native scan walks the directory, then filters by compiled glob.\n- Multiple explicit paths/globs: wrapper unions them into one synthetic scope or runs per-target native calls when paths only meet at root.\n- Internal URL inputs: only supported when the router resolves them to a backing file path.\n- Preview mode: always the direct `ast_edit` tool result.\n- Apply mode: only reachable through the queued `resolve` callback after a preview.\n- Hashline output mode vs plain line/column mode: controlled by `resolveFileDisplayMode()`.\n\n## Side Effects\n- Filesystem\n  - Preview reads files and scans directories.\n  - Apply rewrites files in place with `std::fs::write(...)`, but only when the computed output differs from the original source.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Queues a one-shot forced `resolve` tool choice through `queueResolveHandler(...)`.\n  - Adds a `resolve-reminder` steering message.\n- User-visible prompts / interactive UI\n  - Direct `ast_edit` results are previews.\n  - Follow-up apply/discard is exposed through the hidden `resolve` tool.\n- Background work / cancellation\n  - Native preview/apply work runs on a blocking worker via `task::blocking(...)`.\n  - Cancellation and optional native timeout are cooperative through `CancelToken::heartbeat()`.\n\n## Limits & Caps\n- File cap exposed by the wrapper: `PI_MAX_AST_FILES`, default `1000`, in `packages/coding-agent/src/tools/ast-edit.ts`.\n- Native `maxFiles` and `maxReplacements` are both clamped to at least `1` when provided in `crates/pi-natives/src/ast.rs`.\n- The wrapper never sets `maxReplacements`; native behavior therefore defaults to effectively unbounded replacements for a run.\n- Parse issues are rendered with at most `PARSE_ERRORS_LIMIT = 20` lines in `packages/coding-agent/src/tools/render-utils.ts`; `details.parseErrors` is deduplicated but not capped.\n- Directory scans use `include_hidden: true`, `use_gitignore: true`, and skip `node_modules` unless the glob text explicitly mentions `node_modules` in `crates/pi-natives/src/ast.rs`.\n- No separate glob-expansion count cap exists. Candidate count is whatever the resolved path/glob expands to after gitignore filtering, then native `maxFiles` stops mutations after the configured number of touched files.\n- Preview text truncates each rendered `before` and `after` first line to 120 characters in `packages/coding-agent/src/tools/ast-edit.ts`.\n\n## Errors\n- TS wrapper throws `ToolError` for empty patterns, duplicate rewrite patterns, empty path entries, unsupported internal-URL globs, internal URLs without `sourcePath`, and missing paths.\n- Native code returns hard errors for:\n  - inability to infer one language across all candidates when `lang` is absent,\n  - unsupported explicit `lang`,\n  - bad glob compilation or unreadable search roots,\n  - overlapping computed edits (`Overlapping replacements detected; refine pattern to avoid ambiguous edits`),\n  - out-of-bounds edit ranges or non-UTF-8 replacement text,\n  - write failures during apply,\n  - cancellation or timeout.\n- With `failOnParseError: false` (the wrapper always uses this), pattern compile failures and file parse failures become `parseErrors` instead of aborting the whole run.\n- If every rewrite pattern fails to compile, native `ast_edit` returns a successful zero-replacement result with `parseErrors` populated.\n- Files containing tree-sitter error nodes are skipped for rewriting; they do not get partial edits.\n- Apply can fail after a successful preview if the preview becomes stale. The resolve callback compares replacement totals and per-file counts and returns an error result rather than silently reporting success for a mismatched preview.\n\n## Notes\n- `ast_edit` does not expose the native `lang`, `strictness`, `selector`, `maxReplacements`, `failOnParseError`, or `timeoutMs` fields to the model. The runtime fixes the call shape to a preview-first, smart-strictness, best-effort parse mode.\n- Because the wrapper does not expose `lang`, mixed-language rewrites only succeed when every candidate infers to the same canonical language. This is stricter than `ast_grep`.\n- Idempotency is not enforced syntactically. A rewrite like `foo($A) -> foo($A)` previews zero changes because output equals input; a rewrite that keeps matching its own output may still produce replacements on repeated calls.\n- Rewrites are accumulated per file, then applied from the end of the file backward after an overlap check. Independent matches can coexist; overlapping matches abort the run.\n- Native rewrite rule order is by pattern-string sort, not by the original `ops` array order, because `normalize_rewrite_map(...)` sorts the `(pattern, rewrite)` pairs.\n- Preview/apply parity is validated by totals and per-file counts after the apply rerun, not by a byte-for-byte diff of every replacement payload.",
@@ -90,7 +90,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"tools/retain.md": "# retain\n\n> Store durable facts through the active long-term memory backend.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/memory-retain.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/retain.md`\n- Hindsight collaborators:\n  - `packages/coding-agent/src/hindsight/state.ts` — per-session queue, flush, auto-retain.\n  - `packages/coding-agent/src/hindsight/backend.ts` — session bootstrap, prompt injection, subagent aliasing.\n  - `packages/coding-agent/src/hindsight/bank.ts` — bank id derivation, tag scoping, mission setup.\n  - `packages/coding-agent/src/hindsight/client.ts` — HTTP `retain` / `retainBatch` calls.\n  - `packages/coding-agent/src/hindsight/content.ts` — retention transcript shaping, memory-tag stripping.\n  - `packages/coding-agent/src/hindsight/mental-models.ts` — bank-scoped mental-model seeding and cache rendering.\n  - `packages/coding-agent/src/hindsight/seeds.json` — built-in mental-model seed definitions.\n  - `packages/coding-agent/src/hindsight/transcript.ts` — extracts user/assistant turns for auto-retain.\n- Mnemopi collaborators:\n  - `packages/coding-agent/src/mnemopi/backend.ts` — local backend bootstrap, prompt injection, subagent aliasing, enqueue/clear.\n  - `packages/coding-agent/src/mnemopi/state.ts` — scoped recall/retain state and local writes.\n  - `packages/coding-agent/src/mnemopi/config.ts` — local SQLite path, bank, scoping, provider settings.\n  - `packages/mnemopi/src/core/memory.ts` — local memory runtime used by `remember(...)`.\n\n## Inputs\n\n| Field | Type | Required | Description |\n|---|---|---:|---|\n| `items` | `Array<{ content: string; context?: string }>` | Yes | One or more memories to store. `minItems: 1`. Each item must be self-contained; `context` is optional per-item provenance. |\n\n## Outputs\nThe output depends on the active `memory.backend`.\n\nHindsight:\n- `content[0].type = \"text\"`\n- `content[0].text = \"<count> memory queued.\"` or `\"<count> memories queued.\"`\n- `details = { count: number }`\n- The write is not confirmed before the tool returns. The queue flushes later; flush failures emit a session warning notice and are not returned to the model.\n\nMnemopi:\n- `content[0].type = \"text\"`\n- `content[0].text = \"<count> memory stored.\"` or `\"<count> memories stored.\"`\n- `details = { count: number }`\n- The tool calls the local backend synchronously, but `rememberScoped(...)` catches per-item write failures and returns `undefined`; the tool still reports the requested count.\n\n## Flow\n1. `MemoryRetainTool.createIf(...)` exposes the tool when `memory.backend` is either `\"hindsight\"` or `\"mnemopi\"`.\n2. `execute(...)` re-reads `memory.backend` and dispatches to the matching session state.\n3. If the backend is `mnemopi`:\n   - it fetches `session.getMnemopiSessionState()` and throws if the backend was not started;\n   - for each item, it calls `state.rememberScoped(item.content, ...)` with `source: \"coding-agent-retain\"`, `importance: 0.75`, `scope: \"bank\"`, `extract: true`, `extractEntities: true`, `veracity: \"tool\"`, `memoryType: \"fact\"`, and metadata `{ session_id, cwd, context, tool: \"retain\" }`;\n   - writes go to the scoped retain bank selected by `packages/coding-agent/src/mnemopi/config.ts`.\n4. If the backend is `hindsight`:\n   - it fetches `session.getHindsightSessionState()` and throws if the backend was not started;\n   - each input item is handed to `HindsightSessionState.enqueueRetain(...)`;\n   - `HindsightRetainQueue.enqueue(...)` appends the item and either flushes immediately when the queue reaches `RETAIN_FLUSH_BATCH_SIZE`, or starts a debounce timer for `RETAIN_FLUSH_INTERVAL_MS`;\n   - on flush, `HindsightRetainQueue.#doFlush(...)` verifies ownership, best-effort initializes the bank mission, maps items to `MemoryItemInput` with `context ?? config.retainContext`, `metadata.session_id`, and bank-scope tags, then sends one async `retainBatch(...)` request.\n\n## Modes / Variants\n- Hindsight tool path: queued batch write only.\n- Mnemopi tool path: direct local `remember(...)` into the scoped retain bank.\n- Hindsight bank scoping from `computeBankScope(...)`:\n  - `global` — one shared bank, no project tags.\n  - `per-project` — bank id gets `-<cwd basename>` appended.\n  - `per-project-tagged` — shared bank plus `project:<cwd basename>` tags on retained memories.\n- Mnemopi bank scoping from `resolveBankScope(...)`:\n  - `global` — retain and recall use the shared bank.\n  - `per-project` — retain and recall use the project bank.\n  - `per-project-tagged` — retain writes project-local memories; recall also reads the shared bank.\n- Session scope:\n  - tool-called retains are per-session work for the active backend;\n  - persisted Hindsight memories are cross-session server-side bank data;\n  - persisted Mnemopi memories are local SQLite data;\n  - subagents alias parent memory state for both supported backends.\n\n## Side Effects\n- Filesystem\n  - Hindsight: none for retained memories. No local memory file is written.\n  - Mnemopi: writes to local SQLite under `mnemopi.dbPath`, defaulting beneath the agent memories directory (`mnemopi/mnemopi.db`) with one database file per scoped bank when needed.\n- Network\n  - Hindsight: `POST /v1/default/banks/{bank_id}/memories` via `retainBatch(...)`, plus optional `PUT /v1/default/banks/{bank_id}` via `ensureBankMission(...)` before first write per bank/process.\n  - Mnemopi: none unless configured embedding or LLM providers make calls during extraction.\n- Session state\n  - Hindsight: appends to the in-memory `HindsightRetainQueue`, includes `metadata.session_id`, and shares parent state for subagents.\n  - Mnemopi: writes through the session's scoped `Mnemopi` instance, includes `session_id`, `cwd`, and optional `context`, and shares scoped resources with subagents.\n- User-visible prompts / interactive UI\n  - Hindsight async flush failures emit `session.emitNotice(\"warning\", ...)`; the model is not told.\n  - Mnemopi write failures are logged by `rememberInScope(...)`; the tool response does not expose per-item failures.\n- Background work / cancellation\n  - Hindsight flush runs later on timer, queue-size threshold, `agent_end`, backend `enqueue(...)`, or backend `clear(...)`.\n  - Mnemopi fact/entity extraction may continue in the Mnemopi runtime; backend `enqueue(...)` calls `flushExtractions()` before sleeping sessions.\n\n## Limits & Caps\n- Input schema requires `items.length >= 1`.\n- Tool availability requires `memory.backend` to be `\"hindsight\"` or `\"mnemopi\"`; default `memory.backend` is `\"off\"`.\n- Hindsight queue flush threshold: `RETAIN_FLUSH_BATCH_SIZE = 16`.\n- Hindsight queue debounce: `RETAIN_FLUSH_INTERVAL_MS = 5_000`.\n- Hindsight queue writes use `retainBatch(..., { async: true })`; the client does not wait for server-side consolidation.\n- Hindsight auto-retain settings:\n  - `hindsight.retainEveryNTurns` default `3`\n  - `hindsight.retainOverlapTurns` default `2`\n  - `hindsight.retainContext` default `\"omp\"`\n  - `hindsight.retainMode` default `\"full-session\"`\n- Mnemopi retain settings:\n  - `mnemopi.retainEveryNTurns` default `4`\n  - `mnemopi.autoRetain` controls automatic retention of completed conversation turns\n  - `mnemopi.scoping` selects `global`, `per-project`, or `per-project-tagged`\n\n## Errors\n- Throws `Mnemopi backend is not initialised for this session.` when `memory.backend == \"mnemopi\"` but no state exists.\n- Throws `Hindsight backend is not initialised for this session.` when `memory.backend == \"hindsight\"` but no state exists.\n- Hindsight queue enqueue on disposed state throws `Hindsight retain queue is closed.`\n- Hindsight flush-time API failures are caught in `HindsightRetainQueue.#doFlush(...)`, logged, and converted into a warning notice instead of a tool error.\n- Hindsight mission creation failures are swallowed in `ensureBankMission(...)`; writes continue.\n- Mnemopi `remember(...)` failures are caught in `MnemopiSessionState.rememberInScope(...)`, logged, and not rethrown to the tool caller.\n\n## Notes\n- Hindsight storage is server-side. `hindsightBackend.clear(...)` only clears local cache/state and warns that upstream deletion must happen in Hindsight UI or `deleteBank`.\n- Mnemopi storage is local SQLite. `mnemopiBackend.clear(...)` removes the scoped database files for the active configuration.\n- Hindsight auto-retain uses the same bank but a different path than this tool: `retainSession(...)` extracts plain user/assistant transcript, strips `<memories>` / `<mental_models>` blocks, and calls single-item `retain(...)`.\n- Mnemopi auto-retain stores prepared transcripts with `source: \"coding-agent-transcript\"`, `importance: 0.65`, `veracity: \"unknown\"`, and `memoryType: \"episode\"`.\n- Hindsight mental-model bootstrap lives in the shared backend: `HindsightSessionState.runMentalModelLoad(...)` optionally resolves seeds, creates missing models, then caches a rendered `<mental_models>` block for prompt injection.\n- Built-in Hindsight seeds are `user-preferences`, `project-conventions`, and `project-decisions`. `projectTagged: true` seeds inherit the active scope's retain tags; untagged seeds read the whole bank.\n- Hindsight mental-model defaults: `hindsight.mentalModelsEnabled = true`, `hindsight.mentalModelAutoSeed = true`, `hindsight.mentalModelRefreshIntervalMs = 5 * 60 * 1000`, `hindsight.mentalModelMaxRenderChars = 16_000`. First-turn loading waits up to `MENTAL_MODEL_FIRST_TURN_DEADLINE_MS = 1500`.\n- Hindsight seed lifecycle is create-only. Changing `packages/coding-agent/src/hindsight/seeds.json` does not mutate existing server-side models.\n- `recall.md` and `reflect.md` rely on the same backend selection and scoping behavior.\n",
 	"tools/rewind.md": "# rewind\n\n> End an active checkpoint by pruning exploratory context and retaining a concise report.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/checkpoint.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/rewind.md`\n- Key collaborators:\n  - `packages/coding-agent/src/session/agent-session.ts` — validates pending rewind state, applies the actual rewind, and injects the retained report.\n  - `packages/coding-agent/src/session/session-manager.ts` — branches the persisted session tree and appends persisted summary/report entries.\n  - `packages/coding-agent/src/session/messages.ts` — converts persisted `branch_summary` entries into LLM-visible branch-summary messages on rebuilt context.\n  - `packages/coding-agent/src/tools/index.ts` — registers the tool and shares the `checkpoint.enabled` gate.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `report` | `string` | Yes | Investigation findings. `execute()` trims it and rejects the empty result. |\n\n## Outputs\nThe tool returns a single text result plus structured details:\n\n- text body:\n  - `Rewind requested.`\n  - `Report captured for context replacement.`\n- `details`:\n  - `report: string` — trimmed report text\n  - `rewound: true`\n\nThe returned tool result is not the final rewind. `AgentSession` waits until `turn_end`, then applies the rewind side effects asynchronously.\n\n## Flow\n1. `RewindTool.createIf()` in `packages/coding-agent/src/tools/checkpoint.ts` hides the tool from subagents.\n2. `RewindTool.execute()` rejects subagent calls with `ToolError(\"Checkpoint not available in subagents.\")`.\n3. It rejects calls with no active checkpoint using `ToolError(\"No active checkpoint.\")`.\n4. It trims `params.report`; if empty, it throws `ToolError(\"Report cannot be empty.\")`.\n5. It returns a `toolResult()` with `details.report` and `details.rewound = true`.\n6. On `tool_execution_end`, `AgentSession` extracts the report from `details.report` or the first text content block and stores it in `#pendingRewindReport`.\n7. On `turn_end`, if `#pendingRewindReport` is set, `AgentSession.#applyRewind()` runs.\n8. `#applyRewind()` computes `safeCount = clamp(checkpointMessageCount, 0, agent.state.messages.length)` and calls `agent.replaceMessages(agent.state.messages.slice(0, safeCount))`.\n9. It then calls `sessionManager.branchWithSummary(checkpointEntryId, report, { startedAt })`. That moves the persisted session leaf back to the checkpoint entry and appends a new `branch_summary` entry whose `summary` is the rewind report.\n10. If `checkpointEntryId` no longer resolves, it logs a warning and falls back to `branchWithSummary(null, report, { startedAt })`, branching from root instead.\n11. `#applyRewind()` appends a hidden in-memory custom message `{ customType: \"rewind-report\", content: report, display: false }` and persists the same payload through `sessionManager.appendCustomMessageEntry(\"rewind-report\", ...)` with `details = { startedAt, rewoundAt }`.\n12. Finally it clears `#checkpointState` and `#pendingRewindReport`.\n\n## Modes / Variants\n- Normal rewind: checkpoint entry exists; session history branches from that exact entry.\n- Fallback rewind: checkpoint entry ID is missing from the current session tree; rewind branches from root and logs a warning.\n- Immediate turn-end apply: rewind side effects happen only after the surrounding assistant turn finishes, not inside `RewindTool.execute()`.\n\n## Side Effects\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Replaces in-memory conversation history with the prefix ending at the checkpoint tool result.\n  - Adds a hidden custom message `rewind-report` carrying the retained report.\n  - Clears the active checkpoint state and pending rewind report.\n  - Repositions the persisted session leaf to the checkpoint branch point and appends new session entries.\n- Filesystem\n  - Persists the new `branch_summary` and `custom_message` entries into the session `.jsonl` file through normal `SessionManager` append persistence.\n  - Session files are named `<ISO-timestamp-with-:-and-.-replaced>_<uuidv7>.jsonl` in the session directory; default directory selection is documented in `SessionManager.create()` as `~/.omp/agent/sessions/<encoded-cwd>/` when no override is passed.\n- User-visible prompts / interactive UI\n  - The tool result itself is visible.\n  - The persisted `branch_summary` becomes an LLM-visible `branchSummary` message when context is rebuilt from `SessionManager.buildSessionContext()`; `messages.ts` renders it as a user-role text message using `packages/agent/src/compaction/prompts/branch-summary-context.md`.\n  - The persisted `rewind-report` custom message also participates in rebuilt LLM context because `custom_message` entries are converted through `createCustomMessage()`.\n- Background work / cancellation\n  - Rewind application is deferred to `turn_end`. There is no separate job object or cancel handle.\n\n## Limits & Caps\n- Availability is gated by `checkpoint.enabled`, default `false`, in `packages/coding-agent/src/config/settings-schema.ts`.\n- Top-level sessions only.\n- Requires exactly one active checkpoint; there is no path to name or choose among multiple checkpoints.\n- Report text must be non-empty after `trim()`.\n- Rewind restores only the message prefix recorded by `checkpointMessageCount`; there is no file restore, artifact restore, blob restore, or process restore path.\n- Persisted report/summary content is still subject to the global session persistence cap `MAX_PERSIST_CHARS = 500_000` in `packages/coding-agent/src/session/session-manager.ts`.\n\n## Errors\n- `ToolError(\"Checkpoint not available in subagents.\")` — thrown for subagent sessions.\n- `ToolError(\"No active checkpoint.\")` — thrown when no checkpoint state is present.\n- `ToolError(\"Report cannot be empty.\")` — thrown when the trimmed report is empty.\n- Missing checkpoint entry IDs during apply do not fail the tool call; `#applyRewind()` catches the error, logs `Rewind branch checkpoint missing, falling back to root`, and branches from root.\n\n## Notes\n- Checkpoint selection is implicit. `rewind` always targets the single `#checkpointState` captured by the last successful `checkpoint`; there is no checkpoint list, label, or ID parameter.\n- Restored state is transcript/session-tree state only:\n  - in-memory `agent.state.messages` prefix up to `checkpointMessageCount`\n  - persisted session leaf reset to `checkpointEntryId` or root fallback\n  - retained rewind report as `branch_summary` and hidden `rewind-report` custom message\n- Not restored:\n  - filesystem contents\n  - git state\n  - artifacts under `packages/coding-agent/src/session/artifacts.ts`\n  - blob-store payloads under `packages/coding-agent/src/session/blob-store.ts`\n  - prompt history rows in `packages/coding-agent/src/session/history-storage.ts`\n  - auth or other agent storage in `packages/coding-agent/src/session/agent-storage.ts`\n- There is no concurrent-edit reconciliation. If code or session-adjacent state changes during the checkpoint window, rewind does not merge or revert them; it only drops conversation context and rewires the session branch.\n- Rewind is not destructive to persisted session history. `branchWithSummary()` appends a new `branch_summary` entry and moves the leaf; it does not delete the abandoned path from the `.jsonl` session log. The active context is cut over to the new branch, but the old entries remain in session storage.\n",
 	"tools/search.md": "# search\n\n> Search file contents with a regex across files, directories, globs, and internal URLs.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/search.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/search.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/match-line-format.ts` — model-facing anchor formatting.\n  - `packages/coding-agent/src/tools/path-utils.ts` — path normalization, glob splitting, internal URL resolution.\n  - `packages/coding-agent/src/tools/file-recorder.ts` — file ordering for grouped output.\n  - `packages/coding-agent/src/tools/grouped-file-output.ts` — grouped per-file text layout.\n  - `packages/coding-agent/src/session/streaming-output.ts` — line truncation and final byte truncation.\n  - `packages/coding-agent/src/config/settings-schema.ts` — default context lines.\n  - `packages/natives/native/index.d.ts` — native `grep()` types exposed to TS.\n  - `crates/pi-natives/src/grep.rs` — native regex/file search implementation.\n  - `docs/natives-text-search-pipeline.md` — native search pipeline overview.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `pattern` | `string` | Yes | Regex pattern. `search.ts` trims it and rejects empty input. The native matcher enables multiline only when the pattern text contains a literal newline or the two-character sequence `\\\\n`. The model prompt explicitly documents literal-brace escaping such as ``interface\\\\{\\\\}``, although the native layer also auto-escapes braces that cannot be valid repetition quantifiers. |\n| `paths` | `string \\| string[]` | Yes | One file path, directory path, glob-like path, archive member, internal URL, or an array of those. Append a line-range selector such as `:50-100` or `:5-16,960-973` to a single file/archive/internal-resource input to constrain matches. Empty strings are rejected after trimming/quote stripping. Single entries accidentally joined with comma, semicolon, or whitespace are expanded only after existence validation; existing paths containing delimiters stay intact. Filesystem-backed internal URLs search their backing file; virtual internal resources search resolved text in memory. Internal URLs cannot contain glob characters. |\n| `i` | `boolean` | No | Case-insensitive search. Defaults to `false`. Passed to native `ignoreCase` or JS `RegExp` flags for virtual resources. |\n| `gitignore` | `boolean` | No | Respect `.gitignore` during directory scans. Defaults to `true`. Passed to native `gitignore`. |\n| `skip` | `number` | No | File-page offset for multi-file results. Defaults to `0`; `search.ts` floors finite numbers and rejects negative or non-finite values. Single-file searches ignore it because they do not paginate by file. |\n\n## Outputs\nThe tool returns a single text block in `content[0].text` plus structured `details`.\n\n- Match lines are formatted by `formatMatchLine()` as `*LINE:content` for matches and ` LINE:content` for context under a `¶PATH#TAG` header in hashline mode.\n  - Hashline mode: `¶src/login.ts#1F2A`, `*5:content`, ` 9:content`.\n  - Plain mode: `*5|content`, ` 9|content`.\n- Directory and multi-file results are grouped by file, with `# <path>#TAG` headings when editable hashline anchors are available and `# <path>` headings otherwise.\n- `details` may include:\n  - `scopePath` — formatted search scope.\n  - `matchCount`, `fileCount`, `files`, `fileMatches` — counts for the returned page.\n  - `fileLimitReached` — more matching files remain beyond the current 20-file page.\n  - `perFileLimitReached` — a hot file was trimmed to the per-file match cap.\n  - `linesTruncated` — one or more matched lines were shortened to `512` chars plus `…`.\n  - `truncated` and `meta.truncation` — final text output was head-truncated by `truncateHead()`.\n  - `displayContent` — TUI-only rendering text with `│` gutters instead of model anchors.\n  - `missingPaths` — multi-path entries skipped because their base path did not exist.\n- No-match result text is `No matches found`, optionally followed by skipped missing-path or unreadable-archive notes.\n\n## Flow\n1. `SearchTool.execute()` validates and normalizes input in `packages/coding-agent/src/tools/search.ts`:\n   - trims `pattern`, rejects empty patterns;\n   - normalizes `skip` to a non-negative integer;\n   - expands delimiter-flattened `paths` entries with `expandDelimitedPathEntries()`, keeping existing delimiter-containing paths intact, accepting comma/semicolon splits when at least one part resolves, and accepting whitespace splits only when every part resolves;\n   - peels any line-range selector from each resulting entry;\n   - reads `search.contextBefore` and `search.contextAfter` from session settings (`1` and `3` by default);\n   - enables multiline only when `pattern` contains `\\n` or an actual newline.\n2. Each `paths` entry is normalized with `normalizePathLikeInput()` again during shared scope resolution; this is a no-op for entries already normalized by delimiter expansion.\n3. Archive member paths such as `bundle.zip:src/foo.ts` are materialized to temporary UTF-8 scratch files before native grep. Binary or non-UTF-8 archive members are reported as skipped/unreadable.\n4. Internal URLs are resolved before filesystem scope resolution:\n   - glob metacharacters (`*`, `?`, `[`, `{`) are rejected for internal URLs;\n   - resources with `sourcePath` are searched through their backing file;\n   - resources without `sourcePath` are searched in memory with JavaScript `RegExp`;\n   - `omp://` expands to every embedded documentation file via URL completion;\n   - immutable sources are tracked so output can suppress editable hashline numbered output per file.\n5. For multi-path calls, `partitionExistingPaths()` skips only ENOENT entries. If every filesystem entry is missing and no virtual internal resources remain, the tool errors.\n6. Path resolution branches:\n   - one entry: `parseSearchPath()` splits `basePath` and optional glob;\n   - multiple entries: `resolveExplicitSearchPaths()` computes a common base directory, brace-union glob, exact-file list, or degenerate-root target list.\n7. Line-range selectors are validated after path/archive/internal resolution. They are allowed only for single files, archive members, or virtual resources; glob/directory line-range selectors error.\n8. `search.ts` stats the resolved base path to decide file vs directory behavior.\n9. It calls native `grep()` from `@oh-my-pi/pi-natives` with:\n   - `pattern`, `ignoreCase`, `multiline`, `gitignore`;\n   - `hidden: true`;\n   - `cache: false`;\n   - `contextBefore` / `contextAfter` from settings;\n   - `maxColumns: DEFAULT_MAX_COLUMN` (`512`);\n   - `maxCount: INTERNAL_TOTAL_CAP` (`2000`);\n   - `mode: content`.\n10. Native execution happens in `crates/pi-natives/src/grep.rs`:\n   - `build_matcher()` sanitizes non-quantifier braces before regex compile;\n   - if compile fails with unopened/unclosed-group errors, it retries after escaping previously unescaped parentheses;\n   - directory scans use the grep pipeline described in `docs/natives-text-search-pipeline.md`.\n11. Search dispatch differs by resolved path set:\n   - exact explicit files or degenerate-root multi-targets: JS loops over targets and merges `grep()` results itself;\n   - single file/directory base: one `grep()` call handles native scanning.\n12. Virtual internal resources are searched in JS with `RegExp`; archive scratch paths and virtual paths are remapped back to user-facing selectors before rendering.\n13. JS output shaping then:\n   - caps multi-file output to 20 files per page (`DEFAULT_FILE_LIMIT`), using `skip` as the next file offset;\n   - caps matches per file to 20 for multi-file scopes and 200 for single-file scopes;\n   - round-robins selected per-file matches so one file does not monopolize the page;\n   - formats lines through `formatMatchLine()` for the model and `formatCodeFrameLine()` for TUI;\n   - records non-truncated matched/context lines into the session file-read cache with `recordSparse()`.\n14. Final text is passed through `truncateHead(rawOutput, { maxLines: Number.MAX_SAFE_INTEGER })`, so the effective cap is the default byte cap from `streaming-output.ts`, not the default line cap.\n15. `toolResult()` attaches text plus limit/truncation metadata.\n\n## Modes / Variants\n1. **Single file path**\n   - `grep()` searches one file.\n   - Output is a flat list of match/context lines.\n   - Visible limit is the first `200` matches after native matching and JS per-file capping.\n2. **Single directory path or single glob-like path**\n   - `parseSearchPath()` may split the input into `path` + `glob`.\n   - One native `grep()` scans the directory tree with `gitignore` and `hidden:true`.\n   - Results are grouped into a 20-file page; use `skip` with the next file offset shown in the limit message.\n   - JS round-robins the selected files' matches.\n3. **Multiple explicit paths/globs**\n   - `resolveExplicitSearchPaths()` collapses them into a common base and either a brace-union glob, an explicit file list, or per-target searches when the only common base is the filesystem root.\n   - Missing entries are skipped non-fatally unless all are missing.\n4. **Archive member paths**\n   - Supported for UTF-8 text entries only. The member is extracted to a temporary scratch file for native grep, then displayed as `archive.ext:member`.\n5. **Internal URL paths**\n   - Filesystem-backed resources search their resolved `sourcePath`.\n   - Virtual resources without `sourcePath` search their resolved content in memory.\n   - `omp://` expands to all embedded documentation files so it can be used as a docs search root.\n   - No internal-URL globbing.\n   - Immutable and virtual sources suppress editable hashline anchors.\n\n## Side Effects\n- Filesystem\n  - Stats resolved search roots and input paths.\n  - Reads matched files through native `grep()`.\n  - Records sparse matched/context lines into the session file-read cache via `getFileReadCache(...).recordSparse(...)`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Reads session settings for context defaults.\n  - Uses `session.internalRouter` to resolve internal URLs.\n  - Populates tool `details.meta` with truncation/limit metadata.\n- Background work / cancellation\n  - Wrapped in `untilAborted(signal, ...)` at the JS level.\n  - `search.ts` does not pass `signal` or `timeoutMs` into native `grep()`, so native grep cancellation/timeouts are not used by this tool.\n\n## Limits & Caps\n- File page limit: `20` files (`DEFAULT_FILE_LIMIT` in `packages/coding-agent/src/tools/search.ts`).\n- Per-file match caps: `20` for multi-file scopes (`MULTI_FILE_PER_FILE_MATCHES`), `200` for single-file scopes (`SINGLE_FILE_MATCHES`).\n- Native/JS preselection cap: `2000` matches (`INTERNAL_TOTAL_CAP`).\n- Line truncation: `512` characters per emitted line (`DEFAULT_MAX_COLUMN` in `packages/coding-agent/src/session/streaming-output.ts`). Native grep marks truncated lines; JS reports `linesTruncated`.\n- Final text truncation: `truncateHead()` default byte cap `50 * 1024` bytes (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`). `search.ts` overrides `maxLines` to `Number.MAX_SAFE_INTEGER`, so normal search output is byte-capped, not line-capped.\n- Context defaults: `search.contextBefore = 1`, `search.contextAfter = 3` in `packages/coding-agent/src/config/settings-schema.ts`.\n- Pagination: `skip` is a file-page offset for multi-file scopes. The result text says `Use skip=<N> for the next page` when more files remain.\n- Native directory-scan cache: available in `grep.rs`, but this tool always sets `cache: false`.\n\n## Errors\n- `Pattern must not be empty` when trimmed `pattern` is empty.\n- `Skip must be a non-negative number` for negative or non-finite `skip`.\n- `` `paths` must contain non-empty paths or globs `` when any normalized path is empty.\n- `Glob patterns are not supported for internal URLs: ...` for internal URL + glob metacharacters.\n- Line-range selector errors include `Line-range selector requires a single file, not a glob: ...`, `Line-range selector requires a single file: ... is a directory`, and `Path not found for line-range selector: ...`.\n- `Cannot search archive member(s): ...` when all archive selectors are unreadable, binary, or non-UTF-8.\n- `Path not found: ...` when a filesystem-backed resolved base path is missing, or when every multi-path filesystem entry is missing.\n- Virtual internal URL regex compile failures are reported as `Invalid regex: ...` from JavaScript `RegExp`; filesystem-backed regex failures beginning with `regex` or `regex parse error` are normalized to `Invalid regex: ...`.\n- Multi-file native scans skip per-file open/search failures inside `grep.rs`; the scan continues with surviving files.\n\n## Notes\n- The model-facing prompt documents Rust regex syntax for filesystem-backed searches and JavaScript `RegExp` for virtual internal URL content.\n- Native `build_matcher()` already auto-escapes braces that cannot be valid quantifiers, so patterns like `${platform}` become searchable instead of failing. Valid quantifiers like `a{2,4}` remain unchanged.\n- Native compile retry also escapes unescaped literal parentheses only after an unopened/unclosed-group parse error. It is a fallback, not a general parser mode.\n- Internal URLs are resolved before path existence checks. Backed resources become ordinary filesystem paths; virtual resources stay in memory and do not mint editable hashline anchors.\n- `hidden:true` is hard-coded in `search.ts`; there is no model-facing flag to exclude dotfiles.\n- `gitignore:false` only affects native directory traversal. It does not disable the tool's own path normalization or explicit-file handling.\n- When `paths` resolves to multiple exact files, each target uses the `2000` internal cap before JS grouping.\n- The section tag in hashline mode is a four-hex opaque snapshot tag from the session snapshot store; `search` records whole-file snapshots when possible and prints bare line numbers beneath the header.\n",
-	"tools/search_tool_bm25.md": "# search_tool_bm25\n\n> Search the hidden tool-discovery index and activate the top matches for the current session.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/search-tool-bm25.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/search-tool-bm25.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tool-discovery/tool-index.ts` — discoverable-tool metadata and BM25 index/search.\n  - `packages/coding-agent/src/session/agent-session.ts` — session discovery mode, corpus assembly, activation, cache invalidation.\n  - `packages/coding-agent/src/sdk.ts` — initial hiding of discoverable built-ins and prompt-time discoverable summary.\n  - `packages/coding-agent/src/tools/index.ts` — tool-session discovery hooks, essential/discoverable load modes, registry wiring.\n  - `packages/coding-agent/src/config/settings-schema.ts` — `tools.discoveryMode` and legacy `mcp.discoveryMode` settings.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `query` | `string` | Yes | Natural-language or keyword query. Trimmed before search; empty-after-trim is rejected. |\n| `limit` | `integer` | No | Max matches to return and activate. Minimum `1`. Defaults to `8` (`DEFAULT_LIMIT`). |\n\n## Outputs\n- Single-shot `AgentToolResult`.\n- Model-visible `content` is one text part containing JSON with:\n\n```json\n{\"query\":\"...\",\"activated_tools\":[\"...\"],\"match_count\":2,\"total_tools\":17}\n```\n\n- Runtime-only `details` carries the ranked matches used by the TUI renderer:\n  - `query`, `limit`, `total_tools`\n  - `activated_tools`: tool names activated by this call\n  - `active_selected_tools`: cumulative discovered-tool selections still active\n  - `tools`: array of match objects with\n    - `name`\n    - `label`\n    - `description` (`tool.summary`; this is the only snippet-like field)\n    - optional `server_name`\n    - optional `mcp_tool_name`\n    - `schema_keys`\n    - `score` rounded to 6 decimals\n- The renderer shows a status line plus up to 5 collapsed tree items by default (`COLLAPSED_MATCH_LIMIT`), each with label, optional server name, score to 3 decimals, and truncated description. The ranked match list is not serialized into `content`.\n\n## Flow\n1. `SearchToolBm25Tool.createIf()` in `packages/coding-agent/src/tools/search-tool-bm25.ts` exposes the tool only when `tools.discoveryMode` is set to a non-`\"off\"` value or legacy `mcp.discoveryMode === true`, and only if the session implements the discovery hooks.\n2. `description` is rendered from `packages/coding-agent/src/prompts/tools/search-tool-bm25.md` via `renderSearchToolBm25Description()`, using the current discoverable-tool list plus per-server summary/count.\n3. `execute()` re-checks capability and settings:\n   - missing discovery hooks -> `ToolError(\"Tool discovery is unavailable in this session.\")`\n   - discovery disabled -> `ToolError(\"Tool discovery is disabled. Enable tools.discoveryMode or mcp.discoveryMode to use search_tool_bm25.\")`\n4. `query` is trimmed and validated; `limit` is defaulted/validated.\n5. `getDiscoverableToolSearchIndexForExecution()` fetches the cached generic search index from the session when available, otherwise falls back to the legacy MCP cache, otherwise rebuilds an index from the current discoverable-tool list.\n6. `getSelectedToolNames()` reads the current discovered selections so already-selected tools can be excluded from fresh results.\n7. `searchDiscoverableTools()` in `packages/coding-agent/src/tool-discovery/tool-index.ts` tokenizes the query, scores every document with BM25, sorts by descending score then `tool.name`, and returns up to `searchIndex.documents.length` results; `execute()` then filters already-selected names and slices to `limit`.\n8. If any matches remain, `activateTools()` activates all matched tool names through `session.activateDiscoveredTools()` or legacy `activateDiscoveredMCPTools()`.\n9. `details` is assembled from the activated names, current selected names, corpus size, and formatted matches; `content` is reduced to the compact JSON summary from `buildSearchToolBm25Content()`.\n10. `searchToolBm25Renderer` renders either:\n   - the structured `details` view, or\n   - a fallback text-only warning block if `details` is absent.\n\n## Modes / Variants\n- Discovery-mode gating:\n  - `tools.discoveryMode = \"all\"`: searches hidden discoverable built-ins plus hidden MCP tools.\n  - `tools.discoveryMode = \"mcp-only\"`: searches hidden MCP tools only.\n  - legacy `mcp.discoveryMode = true` with `tools.discoveryMode = \"off\"`: same as MCP-only.\n- Search-index source:\n  - generic cached discoverable index from the session\n  - legacy cached MCP index, cast to the generic shape\n  - rebuilt ad hoc from the current discoverable-tool list if neither cache path works\n- Activation backend:\n  - generic `activateDiscoveredTools()`\n  - legacy `activateDiscoveredMCPTools()` fallback\n\n## Side Effects\n- Session state\n  - Adds matched tools to the active session tool set through `activateDiscoveredTools()` / `activateDiscoveredMCPTools()`.\n  - Updates discovered-tool selection state so repeated searches accumulate selections instead of replacing them.\n  - Invalidates the cached discoverable search index when newly activated built-ins change the hidden corpus (`packages/coding-agent/src/session/agent-session.ts`).\n  - Tool availability changes before the next model call in the same turn; the prompt text says this explicitly.\n- User-visible prompts / interactive UI\n  - The tool description includes discoverable server summaries and total discoverable-tool count.\n  - The TUI renderer shows ranked matches, but the model-visible text summary does not.\n\n## Limits & Caps\n- Default result cap: `8` (`DEFAULT_LIMIT` in `packages/coding-agent/src/tools/search-tool-bm25.ts`).\n- `limit` must be a positive integer; no tool-level upper bound beyond corpus size.\n- Renderer collapsed list cap: `5` (`COLLAPSED_MATCH_LIMIT`).\n- Renderer truncation widths:\n  - label: `72` chars (`MATCH_LABEL_LEN`)\n  - description: `96` chars (`MATCH_DESCRIPTION_LEN`)\n- BM25+ parameters in `packages/coding-agent/src/tool-discovery/tool-index.ts`:\n  - `BM25_K1 = 1.2`\n  - `BM25_B = 0.75`\n  - `BM25_DELTA = 1.0`\n- Weighted corpus fields (`FIELD_WEIGHTS`):\n  - `name`: `6`\n  - `label`: `4`\n  - `mcpToolName`: `4`\n  - `serverName`: `2`\n  - `summary`: `2`\n  - each `schemaKey`: `1`\n- Summary fallback length for discoverable metadata: first `200` chars of `description` when no explicit summary exists (`getDiscoverableTool()` in `packages/coding-agent/src/tool-discovery/tool-index.ts`).\n\n## Errors\n- `execute()` throws `ToolError` for unavailable discovery hooks, disabled discovery mode, empty trimmed query, and non-positive/non-integer `limit`.\n- `searchDiscoverableTools()` throws `Error(\"Query must contain at least one letter or number.\")` if tokenization produces no letter/number tokens; `execute()` catches `Error` and rethrows `ToolError(error.message)`.\n- Empty corpus is not an error; search returns `[]`, activation is skipped, and the renderer message becomes either `No discoverable tools are currently loaded.` or `No matching tools found.`\n- `getDiscoverableToolsForDescription()` and `getDiscoverableToolSearchIndexForExecution()` swallow discovery-hook/cache errors and fall back to an empty corpus or rebuilt index.\n\n## Notes\n- The tool wire name stays `search_tool_bm25` for persisted-session back-compat, even though the source file is `search-tool-bm25.ts`.\n- Corpus composition is session-dependent and excludes already-active tools:\n  - MCP entries come from `#discoverableMCPTools`, filtered to names not currently active, mapped with `summary = description`.\n  - Built-in entries appear only in `\"all\"` mode and only for registry tools whose `loadMode === \"discoverable\"` and are not currently active.\n  - Hidden/internal built-ins are intentionally excluded from the built-in corpus: `resolve`, `yield`, `report_finding`, `report_tool_issue` are called out in the `#collectDiscoverableBuiltinTools()` comment.\n- `DiscoverableToolSource` includes `\"extension\"` and `\"custom\"`, but `AgentSession.getDiscoverableTools()` currently assembles only built-in and MCP sources.\n- On startup, `packages/coding-agent/src/sdk.ts` hides non-essential discoverable built-ins in `tools.discoveryMode = \"all\"`; defaults are `read`, `bash`, and `edit` unless `tools.essentialOverride` changes them.\n- Query tokenization is simple and deterministic: Unicode is NFKD-normalized, combining marks are dropped, acronym/camelCase and digit-to-capital boundaries are split, non-letter/non-number characters become spaces, tokens are lowercased, and only non-empty tokens survive.\n- Scores are rounded differently by surface: `details.tools[].score` keeps 6 decimals; the TUI line renders 3.\n",
+	"tools/search_tool_bm25.md": "# search_tool_bm25\n\n> Search the hidden tool-discovery index and activate the top matches for the current session.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/search-tool-bm25.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/search-tool-bm25.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tool-discovery/tool-index.ts` — discoverable-tool metadata and BM25 index/search.\n  - `packages/coding-agent/src/session/agent-session.ts` — session discovery mode, corpus assembly, activation, cache invalidation.\n  - `packages/coding-agent/src/sdk.ts` — initial hiding of discoverable built-ins and prompt-time discoverable summary.\n  - `packages/coding-agent/src/tools/index.ts` — tool-session discovery hooks, essential/discoverable load modes, registry wiring.\n  - `packages/coding-agent/src/config/settings-schema.ts` — `tools.discoveryMode` and legacy `mcp.discoveryMode` settings.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `query` | `string` | Yes | Natural-language or keyword query. Trimmed before search; empty-after-trim is rejected. |\n| `limit` | `integer` | No | Max matches to return and activate. Minimum `1`. Defaults to `8` (`DEFAULT_LIMIT`). |\n\n## Outputs\n- Single-shot `AgentToolResult`.\n- Model-visible `content` is one text part containing JSON with:\n\n```json\n{\"query\":\"...\",\"activated_tools\":[\"...\"],\"match_count\":2,\"total_tools\":17}\n```\n\n- Runtime-only `details` carries the ranked matches used by the TUI renderer:\n  - `query`, `limit`, `total_tools`\n  - `activated_tools`: tool names activated by this call\n  - `active_selected_tools`: cumulative discovered-tool selections still active\n  - `tools`: array of match objects with\n    - `name`\n    - `label`\n    - `description` (`tool.summary`; this is the only snippet-like field)\n    - optional `server_name`\n    - optional `mcp_tool_name`\n    - `schema_keys`\n    - `score` rounded to 6 decimals\n- The renderer shows a status line plus up to 5 collapsed tree items by default (`COLLAPSED_MATCH_LIMIT`), each with label, optional server name, score to 3 decimals, and truncated description. The ranked match list is not serialized into `content`.\n\n## Flow\n1. `SearchToolBm25Tool.createIf()` in `packages/coding-agent/src/tools/search-tool-bm25.ts` exposes the tool for explicit discovery modes (`\"mcp-only\"` / `\"all\"`) or legacy `mcp.discoveryMode === true`. The default `\"auto\"` mode is resolved later by `createAgentSession()` after MCP/extension tools are registered.\n2. `description` is rendered from `packages/coding-agent/src/prompts/tools/search-tool-bm25.md` via `renderSearchToolBm25Description()`, using the current discoverable-tool list plus per-server summary/count.\n3. `execute()` re-checks capability and settings:\n   - missing discovery hooks -> `ToolError(\"Tool discovery is unavailable in this session.\")`\n   - discovery disabled -> `ToolError(\"Tool discovery is disabled. Enable tools.discoveryMode or mcp.discoveryMode to use search_tool_bm25.\")`\n4. `query` is trimmed and validated; `limit` is defaulted/validated.\n5. `getDiscoverableToolSearchIndexForExecution()` fetches the cached generic search index from the session when available, otherwise falls back to the legacy MCP cache, otherwise rebuilds an index from the current discoverable-tool list.\n6. `getSelectedToolNames()` reads the current discovered selections so already-selected tools can be excluded from fresh results.\n7. `searchDiscoverableTools()` in `packages/coding-agent/src/tool-discovery/tool-index.ts` tokenizes the query, scores every document with BM25, sorts by descending score then `tool.name`, and returns up to `searchIndex.documents.length` results; `execute()` then filters already-selected names and slices to `limit`.\n8. If any matches remain, `activateTools()` activates all matched tool names through `session.activateDiscoveredTools()` or legacy `activateDiscoveredMCPTools()`.\n9. `details` is assembled from the activated names, current selected names, corpus size, and formatted matches; `content` is reduced to the compact JSON summary from `buildSearchToolBm25Content()`.\n10. `searchToolBm25Renderer` renders either:\n   - the structured `details` view, or\n   - a fallback text-only warning block if `details` is absent.\n\n## Modes / Variants\n- Discovery-mode gating:\n  - `tools.discoveryMode = \"auto\"` (default): when the registered tool set has more than 40 tools, searches hidden MCP tools only; otherwise discovery stays off.\n  - `tools.discoveryMode = \"all\"`: searches hidden discoverable built-ins plus hidden MCP tools.\n  - `tools.discoveryMode = \"mcp-only\"`: searches hidden MCP tools only.\n  - legacy `mcp.discoveryMode = true`: same as MCP-only.\n- Search-index source:\n  - generic cached discoverable index from the session\n  - legacy cached MCP index, cast to the generic shape\n  - rebuilt ad hoc from the current discoverable-tool list if neither cache path works\n- Activation backend:\n  - generic `activateDiscoveredTools()`\n  - legacy `activateDiscoveredMCPTools()` fallback\n\n## Side Effects\n- Session state\n  - Adds matched tools to the active session tool set through `activateDiscoveredTools()` / `activateDiscoveredMCPTools()`.\n  - Updates discovered-tool selection state so repeated searches accumulate selections instead of replacing them.\n  - Invalidates the cached discoverable search index when newly activated built-ins change the hidden corpus (`packages/coding-agent/src/session/agent-session.ts`).\n  - Tool availability changes before the next model call in the same turn; the prompt text says this explicitly.\n- User-visible prompts / interactive UI\n  - The tool description includes discoverable server summaries and total discoverable-tool count.\n  - The TUI renderer shows ranked matches, but the model-visible text summary does not.\n\n## Limits & Caps\n- Default result cap: `8` (`DEFAULT_LIMIT` in `packages/coding-agent/src/tools/search-tool-bm25.ts`).\n- `limit` must be a positive integer; no tool-level upper bound beyond corpus size.\n- Renderer collapsed list cap: `5` (`COLLAPSED_MATCH_LIMIT`).\n- Renderer truncation widths:\n  - label: `72` chars (`MATCH_LABEL_LEN`)\n  - description: `96` chars (`MATCH_DESCRIPTION_LEN`)\n- BM25+ parameters in `packages/coding-agent/src/tool-discovery/tool-index.ts`:\n  - `BM25_K1 = 1.2`\n  - `BM25_B = 0.75`\n  - `BM25_DELTA = 1.0`\n- Weighted corpus fields (`FIELD_WEIGHTS`):\n  - `name`: `6`\n  - `label`: `4`\n  - `mcpToolName`: `4`\n  - `serverName`: `2`\n  - `summary`: `2`\n  - each `schemaKey`: `1`\n- Summary fallback length for discoverable metadata: first `200` chars of `description` when no explicit summary exists (`getDiscoverableTool()` in `packages/coding-agent/src/tool-discovery/tool-index.ts`).\n\n## Errors\n- `execute()` throws `ToolError` for unavailable discovery hooks, disabled discovery mode, empty trimmed query, and non-positive/non-integer `limit`.\n- `searchDiscoverableTools()` throws `Error(\"Query must contain at least one letter or number.\")` if tokenization produces no letter/number tokens; `execute()` catches `Error` and rethrows `ToolError(error.message)`.\n- Empty corpus is not an error; search returns `[]`, activation is skipped, and the renderer message becomes either `No discoverable tools are currently loaded.` or `No matching tools found.`\n- `getDiscoverableToolsForDescription()` and `getDiscoverableToolSearchIndexForExecution()` swallow discovery-hook/cache errors and fall back to an empty corpus or rebuilt index.\n\n## Notes\n- The tool wire name stays `search_tool_bm25` for persisted-session back-compat, even though the source file is `search-tool-bm25.ts`.\n- Corpus composition is session-dependent and excludes already-active tools:\n  - MCP entries come from `#discoverableMCPTools`, filtered to names not currently active, mapped with `summary = description`.\n  - Built-in entries appear only in `\"all\"` mode and only for registry tools whose `loadMode === \"discoverable\"` and are not currently active.\n  - Hidden/internal built-ins are intentionally excluded from the built-in corpus: `resolve`, `yield`, `report_finding`, `report_tool_issue` are called out in the `#collectDiscoverableBuiltinTools()` comment.\n- `DiscoverableToolSource` includes `\"extension\"` and `\"custom\"`, but `AgentSession.getDiscoverableTools()` currently assembles only built-in and MCP sources.\n- On startup, `packages/coding-agent/src/sdk.ts` resolves `\"auto\"` after the full registry exists and injects `search_tool_bm25` when the count exceeds 40. It hides non-essential discoverable built-ins only in `tools.discoveryMode = \"all\"`; defaults are `read`, `bash`, and `edit` unless `tools.essentialOverride` changes them.\n- Query tokenization is simple and deterministic: Unicode is NFKD-normalized, combining marks are dropped, acronym/camelCase and digit-to-capital boundaries are split, non-letter/non-number characters become spaces, tokens are lowercased, and only non-empty tokens survive.\n- Scores are rounded differently by surface: `details.tools[].score` keeps 6 decimals; the TUI line renders 3.\n",
 	"tools/ssh.md": "# ssh\n\n> Execute one remote command on a discovered SSH host.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ssh.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ssh.md`\n- Key collaborators:\n  - `packages/coding-agent/src/ssh/ssh-executor.ts` — runs `ssh`, captures output\n  - `packages/coding-agent/src/ssh/connection-manager.ts` — master-connection reuse, host probing\n  - `packages/coding-agent/src/ssh/sshfs-mount.ts` — optional `sshfs` mount side effect\n  - `packages/coding-agent/src/discovery/ssh.ts` — discovers host configs\n  - `packages/coding-agent/src/capability/ssh.ts` — canonical host shape\n  - `packages/coding-agent/src/session/streaming-output.ts` — tail streaming, truncation, artifacts\n  - `packages/coding-agent/src/tools/tool-timeouts.ts` — timeout clamp rules\n  - `packages/utils/src/dirs.ts` — user/project ssh config paths\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `host` | `string` | Yes | Host name key from discovered SSH config entries, not an arbitrary hostname/IP. |\n| `command` | `string` | Yes | Remote command string passed to `ssh` as the remote command. |\n| `cwd` | `string` | No | Remote working directory. The tool prepends a shell-specific `cd`/`Set-Location` wrapper. |\n| `timeout` | `number` | No | Timeout in seconds. Default `60`; clamped to `1..3600`. |\n\n## Outputs\nThe tool returns a standard text tool result built in `packages/coding-agent/src/tools/ssh.ts`:\n\n- `content`: one text block containing combined remote stdout+stderr, or `\"(no output)\"` when empty.\n- `details.meta.truncation`: present when output exceeded the in-memory tail window; derived from the executor summary.\n\nStreaming behavior:\n\n- While the command runs, `onUpdate` receives tail-only text snapshots built from `TailBuffer` in `packages/coding-agent/src/session/streaming-output.ts`.\n- Final output is single-shot after process exit.\n\nSide-channel artifacts:\n\n- When session artifact allocation is available and output exceeds the spill threshold, full output is written to a session artifact file and the returned summary carries its `artifactId` internally.\n- The ssh tool itself does not print the `artifact://...` URI into the result text.\n\nFailure behavior:\n\n- Unknown host, missing host config, timeout, cancellation, SSH startup failure, key validation failure, or non-zero remote exit all surface as thrown `ToolError`s.\n- Non-zero remote exit includes captured output plus `Command exited with code N`.\n\n## Flow\n1. `loadSshTool()` in `packages/coding-agent/src/tools/ssh.ts` calls `loadCapability(sshCapability.id, { cwd: session.cwd })` to discover hosts.\n2. `packages/coding-agent/src/discovery/ssh.ts` loads host entries from, in this order: project managed ssh config, user managed ssh config, `ssh.json` in the repo root, `.ssh.json` in the repo root.\n3. `getSSHConfigPath(\"project\")` and `getSSHConfigPath(\"user\")` in `packages/utils/src/dirs.ts` resolve those managed files to `.omp/ssh.json` in the project and `~/.omp/agent/ssh.json` in the user config dir. This tool does not read `~/.ssh/config`.\n4. Capability loading deduplicates by host name with first item winning; provider order is priority-sorted and the SSH JSON provider registers at priority `5`.\n5. `loadHosts()` in `packages/coding-agent/src/tools/ssh.ts` builds `hostsByName` and drops later duplicates again with `if (!hostsByName.has(host.name))`.\n6. Tool description text is built from `packages/coding-agent/src/prompts/tools/ssh.md` plus an `Available hosts:` list. Each host entry calls `getHostInfoForHost()` to show detected shell/OS when cached; otherwise it renders `detecting...`.\n7. On execute, `SshTool.execute()` rejects any `host` not in the discovered host-name set.\n8. `ensureHostInfo()` in `packages/coding-agent/src/ssh/connection-manager.ts` ensures an SSH master connection exists, loads cached host info from disk if present, and probes remote OS/shell when cache is missing or stale.\n9. `buildRemoteCommand()` in `packages/coding-agent/src/tools/ssh.ts` prepends a cwd change when `cwd` is provided:\n   - Unix-like or Windows compat shells: `cd -- '<cwd>' && <command>`\n   - Windows PowerShell: `Set-Location -Path '<cwd>'; <command>`\n   - Windows cmd: `cd /d \"<cwd>\" && <command>`\n10. `clampTimeout(\"ssh\", rawTimeout)` applies the `1..3600` second clamp from `packages/coding-agent/src/tools/tool-timeouts.ts`.\n11. `executeSSH()` in `packages/coding-agent/src/ssh/ssh-executor.ts` calls `ensureConnection(host)` again, opportunistically mounts the remote host root with `sshfs` if available, optionally wraps the command in `bash -c` or `sh -c` for Windows compat mode, then spawns `ssh` with `ptree.spawn`.\n12. Output from both stdout and stderr is piped into one `OutputSink`; chunks are sanitized and forwarded to streaming updates through `streamTailUpdates()`.\n13. On normal exit, the sink returns combined output plus truncation counters. On timeout or abort, `executeSSH()` returns `cancelled: true` and prefixes the output with a notice line such as `[SSH: ...]` or `[Command aborted: ...]`.\n14. `SshTool.execute()` converts `cancelled: true` into `ToolError`, converts non-zero exit codes into `ToolError`, otherwise returns the text result with truncation metadata.\n\n## Modes / Variants\n- **Tool unavailable**: `loadSshTool()` returns `null` when discovery finds no hosts, so the tool is not registered for that session.\n- **Unix-like target**: remote command is passed through directly, with optional `cd -- ... &&` prefix.\n- **Windows native shell**: cwd wrapper uses PowerShell `Set-Location` or cmd `cd /d`; command otherwise runs in the remote default Windows shell.\n- **Windows compat shell**: if host probing finds `bash` or `sh` on Windows, `executeSSH()` wraps the remote command as `bash -c '...'` or `sh -c '...'`. Host config can force compat on/off with `compat`.\n- **Cached vs probed host info**: shell/OS detection comes from in-memory cache, persisted JSON under the remote-host dir, or a fresh probe over SSH.\n- **Truncated vs untruncated output**: small output stays in memory; large output keeps only the last 50 KiB in memory and may spill full output to an artifact file.\n\n## Side Effects\n- Filesystem\n  - Reads managed SSH config JSON plus legacy `ssh.json` / `.ssh.json`.\n  - Validates private-key path existence and permissions before connecting.\n  - Persists probed host info as JSON under the remote-host cache dir via `persistHostInfo()`.\n  - May create the SSH control socket dir and, when `sshfs` exists, remote mount dirs.\n  - May write full command output to a session artifact file.\n- Network\n  - Opens SSH connections to the selected host.\n  - May issue extra probe commands to detect OS/shell and compat shells.\n- Subprocesses / native bindings\n  - Requires `ssh` on `PATH`; spawns it for connection checks, master startup, probing, and command execution.\n  - May call `sshfs`, `mountpoint`, `fusermount`/`fusermount3`, or `umount`.\n  - Sanitizes streamed text with `@oh-my-pi/pi-natives` text sanitization.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Uses session artifact allocation when available.\n  - Registers postmortem cleanup hooks for SSH master connections and sshfs mounts.\n  - Tool concurrency is `exclusive`, so the agent scheduler should not run multiple ssh tool calls concurrently.\n- Background work / cancellation\n  - Process spawn receives the tool `AbortSignal`.\n  - Cancellation/timeout ends the running ssh process and returns a cancelled result that the tool turns into an error.\n\n## Limits & Caps\n- Timeout defaults/clamps: `default=60`, `min=1`, `max=3600` in `packages/coding-agent/src/tools/tool-timeouts.ts`.\n- Output tail window: `DEFAULT_MAX_BYTES = 50 * 1024` in `packages/coding-agent/src/session/streaming-output.ts`.\n- Output sink spill threshold defaults to the same `50 KiB`; once exceeded, only the tail remains in memory.\n- SSH master reuse persistence: `ControlPersist=3600` in `packages/coding-agent/src/ssh/connection-manager.ts` and `packages/coding-agent/src/ssh/sshfs-mount.ts`.\n- SSH host info schema version: `HOST_INFO_VERSION = 2` in `packages/coding-agent/src/ssh/connection-manager.ts`; stale cache entries are reprobed.\n- Streaming tail buffer compacts after more than `10` pending chunks (`MAX_PENDING`) before trimming.\n\n## Errors\n- `Unknown SSH host: ... Available hosts: ...` when the model passes a host name not present in discovery.\n- `SSH host not loaded: ...` if the discovered-name set and `hostsByName` map diverge.\n- `ssh binary not found on PATH` when `ssh` is unavailable.\n- `SSH key not found: ...`, `SSH key is not a file: ...`, or `SSH key permissions must be 600 or stricter: ...` from key validation.\n- `Failed to start SSH master for <target>: <stderr>` when control-master startup fails.\n- Non-zero remote command exit becomes `ToolError` with captured output and `Command exited with code N`.\n- Timeout becomes a cancelled result with output notice `[SSH: <timeout message>]`, then `ToolError`.\n- Abort becomes a cancelled result with output notice `[Command aborted: <message>]`, then `ToolError`.\n- `sshfs` mount failures are logged and ignored in `executeSSH()`; they do not fail the tool call.\n- Discovery parse problems do not fail tool loading; they become capability warnings. If all sources are empty/invalid, the tool simply does not load.\n\n## Notes\n- Host discovery is JSON-based only. The tool does not parse OpenSSH config files.\n- Discovery expands environment variables recursively in the parsed JSON and expands `~` in `key`/`keyPath`.\n- Host names are capability keys; the model must pass the config key, not the raw hostname.\n- Commands run without a PTY. `executeSSH()` uses `ptree.spawn(..., { stdin: \"pipe\", stderr: \"full\" })` and does not request an interactive terminal.\n- The tool exposes `cwd` but no `env`, `pty`, upload, download, or explicit file-transfer fields.\n- Lower layers support an `artifactId` for full output and a `remotePath` mount target, but `SshTool.execute()` does not expose those knobs.\n- Both stdout and stderr are merged into one output stream; ordering is whatever arrives through the two streams.\n- `StrictHostKeyChecking=accept-new` and `BatchMode=yes` are always set for connection checks, master startup, and command runs.\n- Connection reuse is keyed by discovered host name, not by raw target tuple alone.\n- `closeAllConnections()` and sshfs unmount cleanup run through postmortem hooks, not per-call teardown.\n",
 	"tools/task.md": "# task\n\n> Launch subagents for parallel, optionally isolated work.\n\n## Source\n- Entry: `packages/coding-agent/src/task/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/task.md`\n- Key collaborators:\n  - `packages/coding-agent/src/task/types.ts` — dynamic schema, progress/result types, output caps.\n  - `packages/coding-agent/src/task/discovery.ts` — discover project/user/plugin/bundled agents.\n  - `packages/coding-agent/src/task/agents.ts` — bundled agent definitions and frontmatter parsing.\n  - `packages/coding-agent/src/task/executor.ts` — create child sessions, run subagents, collect output.\n  - `packages/coding-agent/src/task/parallel.ts` — concurrency-limited scheduling and async semaphore.\n  - `packages/coding-agent/src/task/isolation-backend.ts` — isolation backend resolution and platform fallback.\n  - `packages/coding-agent/src/task/worktree.ts` — worktree / FUSE / ProjFS setup, patch capture, branch merge.\n  - `packages/coding-agent/src/task/output-manager.ts` — session-scoped `agent://` id allocation.\n  - `packages/coding-agent/src/task/simple-mode.ts` — `default` / `schema-free` / `independent` field gating.\n  - `packages/coding-agent/src/internal-urls/agent-protocol.ts` — resolve `agent://<id>` to saved subagent output.\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and recursion-depth gating.\n  - `packages/coding-agent/src/sdk.ts` — child-session router/tool wiring and per-subagent `AgentOutputManager`.\n  - `docs/task-agent-discovery.md` — deeper discovery and precedence notes.\n  - `docs/handoff-generation-pipeline.md` — session artifact/handoff persistence patterns used by the wider session layer.\n\n## Inputs\n\n### Default mode (`task.simple = \"default\"`)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `agent` | `string` | Yes | Exact agent name for every task item. Resolved at execution time through `discoverAgents(...)`. |\n| `tasks` | `Array<{ id: string; description: string; assignment: string }>` | Yes | Batch of small, self-contained task items. `id` max length 48 in schema; duplicate ids are rejected case-insensitively at runtime. |\n| `context` | `string` | No | Shared background prepended to every subagent system prompt. Trimmed before use. |\n| `schema` | `string` | No | JSON-encoded JTD schema. Overrides agent/session output schema when this mode allows task-level schemas. |\n| `isolated` | `boolean` | No | Only present when the tool is created with isolation enabled. Requests isolated execution for the whole batch. |\n\n`tasks[].description` is UI-only. `tasks[].assignment` is the actual per-task instruction.\n\n### Schema-free mode (`task.simple = \"schema-free\"`)\n\nSame as default, except `schema` is rejected by `validateTaskModeParams(...)` in `packages/coding-agent/src/task/index.ts`.\n\n### Independent mode (`task.simple = \"independent\"`)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `agent` | `string` | Yes | Exact agent name. |\n| `tasks` | `Array<{ id: string; description: string; assignment: string }>` | Yes | Same item shape, but each `assignment` must carry all required background because shared `context` is disabled. |\n| `isolated` | `boolean` | No | Same conditional field as above. |\n\nIn this mode both `context` and `schema` are rejected.\n\n## Outputs\nThe tool returns one text block plus `details: TaskToolDetails`.\n\n`details` fields:\n- `projectAgentsDir: string | null` — nearest discovered project `agents/` dir.\n- `results: SingleResult[]` — one entry per task in input order for synchronous execution; empty for async-launch responses.\n- `totalDurationMs: number`\n- `usage?: Usage` — sum of per-subagent assistant-message usage.\n- `outputPaths?: string[]` — written `.md` artifact paths for completed subagent outputs.\n- `progress?: AgentProgress[]` — live or final per-task progress snapshots.\n- `async?: { state: \"running\" | \"completed\" | \"failed\"; jobId: string; type: \"task\" }` — present for background execution updates/results.\n\n`SingleResult` includes:\n- identity: `index`, `id`, `agent`, `agentSource`, `description`, optional `assignment`\n- status: `exitCode`, optional `error`, optional `aborted`, optional `abortReason`\n- output: `output`, `stderr`, `truncated`, `durationMs`, `tokens`\n- artifact metadata: `outputPath?`, `patchPath?`, `branchName?`, `nestedPatches?`, `outputMeta?`\n- extracted tool data: `extractedToolData?` from registered subprocess tool handlers such as `yield` and `report_finding`\n\nArtifacts and side channels:\n- Every subagent with an artifacts dir writes `<id>.md`; `agent://<id>` resolves to that file.\n- If the output file is JSON, `agent://<id>/<path>` and `agent://<id>?q=<query>` perform JSON extraction in `packages/coding-agent/src/internal-urls/agent-protocol.ts`.\n- When the parent session persists artifacts, each subagent also gets `<id>.jsonl` session history.\n- Isolated patch mode writes `<id>.patch` per successful task before merge.\n- Async mode returns immediately after job registration, then emits `onUpdate(...)` progress snapshots and later hands completion to the session async-job pipeline.\n\n## Flow\n1. `TaskTool.create(...)` in `packages/coding-agent/src/task/index.ts` calls `discoverAgents(session.cwd)` once to build the dynamic prompt description from current agents and `task.simple` capabilities.\n2. `execute(...)` validates mode-gated fields with `validateTaskModeParams(...)`.\n3. It decides async vs sync:\n   - sync when `async.enabled` is false\n   - sync when the selected cached agent has `blocking === true`\n   - sync when `tasks.length === 0`\n   - otherwise async job scheduling\n4. Async path:\n   - allocate unique output ids with `AgentOutputManager.allocateBatch(...)`\n   - create one async job per task through `session.asyncJobManager.register(...)`\n   - limit concurrent job bodies with `Semaphore(task.maxConcurrency)` from `packages/coding-agent/src/task/parallel.ts`\n   - each job body calls `#executeSync(...)` with a one-task batch and the preallocated id\n   - `onUpdate(...)` emits aggregate `progress` snapshots and `details.async`\n5. Sync path (`#executeSync(...)`) rediscovers agents from disk via `discoverAgents(...)`, so runtime resolution can differ from the earlier prompt description.\n6. It resolves the requested agent with `getAgent(...)`, rejects unknown or disabled agents, and enforces parent spawn policy plus `PI_BLOCKED_AGENT` self-recursion prevention.\n7. It derives the effective output schema in priority order: task call `schema` (if allowed) → agent frontmatter `output` → inherited parent session schema.\n8. It validates task ids: missing ids and case-insensitive duplicates are immediate errors.\n9. If `isolated` was requested, it requires a git repo (`getRepoRoot(...)` / `captureBaseline(...)`) and resolves the actual backend through `resolveIsolationBackendForTaskExecution(...)`.\n10. It chooses an artifacts dir from the parent session when available, otherwise a temp dir, and writes `context.md` there when `session.getCompactContext?.()` returns content.\n11. It allocates unique ids again if the caller did not preallocate them, then builds `tasksWithUniqueIds`.\n12. For each task, it seeds an `AgentProgress` entry and runs `runTask(...)` through `mapWithConcurrencyLimit(...)` using `task.maxConcurrency`.\n13. Non-isolated `runTask(...)` calls `runSubprocess(...)` directly with parent cwd.\n14. Isolated `runTask(...)`:\n   - creates an isolation workspace (`ensureWorktree(...)`, `ensureFuseOverlay(...)`, or `ensureProjfsOverlay(...)`)\n   - applies the captured baseline for worktrees\n   - runs `runSubprocess(...)` inside that workspace\n   - on success, either commits to a per-task branch (`mergeMode === \"branch\"`) or captures a patch with `captureDeltaPatch(...)`\n   - always cleans up the isolation workspace/backend\n15. `runSubprocess(...)` in `packages/coding-agent/src/task/executor.ts` creates a child agent session with:\n   - isolated settings snapshot via `Settings.isolated(...)`, forcing `async.enabled = false` and `bash.autoBackground.enabled = false`\n   - child `agentId` / `parentTaskPrefix` equal to the allocated task id\n   - child internal URL router and `AgentOutputManager` from `packages/coding-agent/src/sdk.ts`\n   - the shared `context`, optional `context.md` reference, optional isolation worktree path, output schema, and IRC peer roster in the system prompt template\n16. Child tool availability is derived from the agent definition plus runtime guards:\n   - explicit `agent.tools` if provided\n   - auto-add `task` when the agent has `spawns` and recursion depth allows it\n   - remove `task` at or past `task.maxRecursionDepth`\n   - expand `exec` to `eval` and `bash`\n   - strip parent-owned `todo` after session creation\n17. `runSubprocess(...)` subscribes to child agent events, coalesces progress updates every 150 ms, forwards lifecycle/progress events on the parent event bus, and extracts tool data through `subprocessToolRegistry`.\n18. The child must finish through the hidden `yield` tool. If it does not, `runSubprocess(...)` sends up to 3 reminder prompts; the last reminder forces `toolChoice = yield` when supported.\n19. Finalization uses `finalizeSubprocessOutput(...)` to reconcile raw assistant text, `yield` payloads, structured schemas, `report_finding` data, and abort states. Output is truncated with `MAX_OUTPUT_BYTES` / `MAX_OUTPUT_LINES` before returning to the parent, but the full raw output is still written to `<id>.md`.\n20. After all sync tasks finish, `#executeSync(...)` aggregates usage, collects artifact paths, and if isolation was used merges results back:\n   - branch mode: cherry-pick per-task branches with `mergeTaskBranches(...)`, then delete merged branches with `cleanupTaskBranches(...)`\n   - patch mode: combine non-empty patch artifacts, dry-check with `git.patch.canApplyText(...)`, then apply or leave manual artifacts\n   - nested repo patches are applied separately with `applyNestedPatches(...)`\n21. The final text summary is rendered from `packages/coding-agent/src/prompts/tools/task-summary.md` and includes `agent://<id>` handles for outputs that exist.\n\n## Modes / Variants\n- Execution mode\n  - Sync inline execution — default path.\n  - Async background execution — one async job per task item when `async.enabled` is on and the chosen agent is not marked `blocking`.\n- Simple mode\n  - `default` — accepts shared `context` and per-call `schema`.\n  - `schema-free` — accepts `context`, rejects `schema`.\n  - `independent` — rejects `context` and `schema`; each assignment stands alone.\n- Isolation backend\n  - `none` — no isolation.\n  - `worktree` — detached git worktree plus baseline replay.\n  - `fuse-overlay` — Unix FUSE overlay mount.\n  - `fuse-projfs` — Windows ProjFS overlay.\n- Isolation merge strategy\n  - Patch mode — capture/apply root patches, keep patch artifacts when application fails.\n  - Branch mode — commit each task onto `omp/task/<id>` branch, cherry-pick into parent, preserve failed branches for manual resolution.\n- Agent source\n  - Project custom agents — nearest project config/plugin agent directories, first by source-family precedence.\n  - User custom agents — user config/plugin agent directories after project dirs of the same source family.\n  - Bundled agents — appended last from `packages/coding-agent/src/task/agents.ts`.\n- Bundled agent types\n  - `explore` — read-only scout with structured handoff output.\n  - `plan` — architecture/planning agent; may spawn `explore`.\n  - `designer` — UI/UX specialist.\n  - `reviewer` — review agent with `report_finding` extraction.\n  - `task` — general-purpose worker with full capabilities.\n  - `quick_task` — low-reasoning mechanical worker using the same task prompt body.\n  - `librarian` — source-grounded external API/library researcher.\n  - `oracle` — senior-engineer implementation/debugging/general consultation agent.\n\n## Side Effects\n- Filesystem\n  - Writes `context.md`, `<id>.jsonl`, and `<id>.md` under the session artifacts dir or a temp task dir.\n  - In isolated patch mode writes `<id>.patch` artifacts.\n  - Creates/removes worktrees or overlay mount directories.\n  - In branch mode creates temporary worktrees and task branches.\n- Network\n  - Child sessions may use whichever networked tools/models their active tool set permits.\n  - MCP proxy tools can call existing parent MCP connections with a 60_000 ms timeout.\n- Subprocesses / native bindings\n  - `fuse-overlayfs` and `fusermount`/`fusermount3` for FUSE isolation.\n  - ProjFS native bindings via `@oh-my-pi/pi-natives` on Windows.\n  - Git operations for baseline capture, patch apply, worktrees, branches, stash, cherry-pick, commits.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Creates child `AgentSession` instances with isolated settings snapshots.\n  - Registers async jobs in `session.asyncJobManager` for background task mode.\n  - Emits `task:subagent:event`, `task:subagent:progress`, and `task:subagent:lifecycle` on the parent event bus.\n  - Allocates session-scoped output ids through `AgentOutputManager` so `agent://` remains unique across invocations and resumes.\n  - Shares the parent `local://` root with subagents by passing `localProtocolOptions` through `createAgentSession(...)`.\n- User-visible prompts / interactive UI\n  - Async mode streams aggregate progress updates.\n  - Missing-`yield` recovery sends up to three internal reminder prompts to the child session.\n  - Final summaries include `<system-notification>` blocks for isolation fallbacks or merge failures.\n- Background work / cancellation\n  - Parent abort stops scheduling new work, aborts active child sessions, and marks unscheduled tasks as skipped.\n  - Async jobs keep their own cancellation via `AsyncJobManager`.\n\n## Limits & Caps\n- Per-subagent output truncation: `MAX_OUTPUT_BYTES = 500_000` and `MAX_OUTPUT_LINES = 5000` in `packages/coding-agent/src/task/types.ts`. Full raw output is still written to `<id>.md` before truncation is returned to the caller.\n- Progress coalescing in child execution: `PROGRESS_COALESCE_MS = 150` in `packages/coding-agent/src/task/executor.ts`.\n- Recent output tail for progress: `RECENT_OUTPUT_TAIL_BYTES = 8 * 1024` and `recentOutput` keeps the last 8 non-empty lines in `packages/coding-agent/src/task/executor.ts`.\n- Missing-`yield` reminder retries: `MAX_YIELD_RETRIES = 3` in `packages/coding-agent/src/task/executor.ts`.\n- MCP proxy timeout: `MCP_CALL_TIMEOUT_MS = 60_000` in `packages/coding-agent/src/task/executor.ts`.\n- Task id schema cap: `tasks[].id` `maxLength: 48` in `packages/coding-agent/src/task/types.ts`.\n- Prompt text says ids should be `≤32` chars, but the runtime schema allows 48; this mismatch is real.\n- Async/full sync parallelism both use `task.maxConcurrency` from settings:\n  - sync path: `mapWithConcurrencyLimit(...)`\n  - async path: `Semaphore(...)` around job bodies\n- Recursion depth gate: `task.maxRecursionDepth` from settings; `packages/coding-agent/src/tools/index.ts` hides the `task` tool at or beyond the limit, and `runSubprocess(...)` also strips child `task` access at max depth.\n- Final inline summary preview per task uses `fullOutputThreshold = 5000` chars in `packages/coding-agent/src/task/index.ts`; longer outputs are summarized while `agent://<id>` points to the full artifact.\n\n## Errors\n- Most validation failures are returned as normal tool text with empty `results`, not thrown:\n  - invalid simple-mode fields\n  - unknown/disabled agent\n  - missing tasks\n  - missing/duplicate task ids\n  - spawn-policy denial\n  - requesting `isolated` while isolation mode is `none`\n- Isolated execution without a git repo returns `Isolated task execution requires a git repository. ...`.\n- Backend resolution can return a hard error (`ProjFS isolation initialization failed...`) or a non-fatal warning with fallback to `worktree`.\n- `mapWithConcurrencyLimit(...)` fails fast on non-abort worker exceptions; already completed results are preserved only in the thrown path’s local state, not surfaced unless the caller catches and converts them.\n- Child-session failures surface as `SingleResult.exitCode = 1` with `stderr`/`error` populated.\n- If the child omits `yield`, `finalizeSubprocessOutput(...)` injects warnings such as `SYSTEM WARNING: Subagent exited without calling yield tool after 3 reminders.`\n- Async scheduling failures are accumulated per task; if no jobs start, the tool returns `Failed to start background task jobs: ...`.\n- `agent://<id>` resolution errors are model-visible when another tool reads them: no session, no artifacts dir, missing id, conflicting extraction syntax, or invalid JSON for extraction.\n\n## Notes\n- Agent discovery precedence is first-wins by exact name: project dirs before user dirs within a source family, plugin agent dirs after config dirs, bundled agents last. See `packages/coding-agent/src/task/discovery.ts` and `docs/task-agent-discovery.md`.\n- `TaskTool.create(...)` caches discovered agents only for description rendering and the async blocking-agent decision. `#executeSync(...)` rediscovers agents each call.\n- Custom agent frontmatter can override bundled agents by name. Bundled definitions are embedded at build time in `packages/coding-agent/src/task/agents.ts`.\n- Child sessions do not inherit conversation history automatically. The only built-in carry-over is shared `context`, optional `context.md`, workspace tree/skills/context files, and shared `local://` root.\n- `Settings.isolated(...)` gives each child a session-isolated settings snapshot; tool enablement is recomputed inside the child session rather than sharing mutable parent tool state.\n- When the parent passes `mcpManager`, child sessions disable standalone MCP discovery and instead get proxy tools that reuse the parent connections.\n- Plan mode mutates an `effectiveAgent` with a read-only tool subset and plan-mode prompt text, but `runSubprocess(...)` is still invoked with `agent` rather than `effectiveAgent`. Model/thinking/schema overrides use the effective agent; prompt/tool/spawn restrictions do not fully flow through this call path.\n- Branch-mode merge temporarily stashes the parent repo before cherry-picking task branches. A stash-pop conflict is treated as merge failure and leaves recovery state behind.\n- Patch-mode only applies combined root patches if every successful task produced a patch and `git.patch.canApplyText(...)` succeeds.\n- Nested git repos are handled separately from the root repo. They are copied into isolated worktrees, diffed independently, and merged later with `applyNestedPatches(...)` because parent git cannot track their file-level changes.\n- `agent://` ids are name-based (`Task` first, `Task-2`/`Task-3` only when the name repeats, nested like `Parent.Child`) by `AgentOutputManager`; this is what prevents artifact collisions across repeated or nested task invocations.\n",
 	"tools/todo.md": "# todo\n\n> Applies ordered mutations to the session todo list and returns a text summary plus the full phase/task state.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/todo.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/todo.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/index.ts` — registers tool, exposes session hooks, gates availability.\n  - `packages/coding-agent/src/modes/controllers/event-controller.ts` — updates the visible todo UI on tool completion.\n  - `packages/coding-agent/src/session/agent-session.ts` — stores cached phases, auto-clears done/dropped tasks, emits failure reminders.\n  - `packages/coding-agent/src/modes/controllers/todo-command-controller.ts` — `/todo` command path, custom-entry persistence, transcript reminder injection.\n  - `packages/coding-agent/src/tools/render-utils.ts` — collapsed-preview cap for renderer trees.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `ops` | `TodoOpEntry[]` | Yes | Ordered operations to apply. `minItems: 1`.\n\n### `TodoOpEntry`\n\n| Op | Required fields | Optional fields | Effect |\n| --- | --- | --- | --- |\n| `init` | `list` | None of the other fields are used | Replaces the entire list with `list`; every new task starts `pending` before normalization. |\n| `start` | `task` | None | Marks one task `in_progress`; any other `in_progress` task is demoted to `pending`. |\n| `done` | `task` or `phase` or neither | None | Marks the target task, phase, or all tasks `completed`. |\n| `drop` | `task` or `phase` or neither | None | Marks the target task, phase, or all tasks `abandoned`. |\n| `rm` | `task` or `phase` or neither | None | Removes the target task, clears the phase's task list, or clears all task lists. |\n| `append` | `phase`, `items` | None | Appends new `pending` tasks to a phase; creates the phase if missing. |\n| `note` | `task`, `text` | None | Appends one trimmed note string to the task's `notes` array. |\n\n### Fields used inside ops\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `\"init\" | \"start\" | \"done\" | \"rm\" | \"drop\" | \"append\" | \"note\"` | Yes | Operation discriminator. |\n| `list` | `{ phase: string; items: string[] }[]` | For `init` | Full replacement payload. Each `items` array has `minItems: 1`. |\n| `task` | `string` | For `start`; for task-targeted `done`/`drop`/`rm`/`note` | Exact task content match. |\n| `phase` | `string` | For `append`; for phase-targeted `done`/`drop`/`rm` | Exact phase name match, except `append` lazily creates a missing phase. |\n| `items` | `string[]` | For `append` | Tasks to append. `minItems: 1`. |\n| `text` | `string` | For `note` | Note text; trailing whitespace is stripped before storing. Empty-after-trim is rejected. |\n\n## Outputs\nThe tool returns a single-shot `AgentToolResult`:\n\n- `content`: one text part containing the summary from `formatSummary(...)`.\n  - Empty final state with no errors: `Todo list cleared.`\n  - Non-empty final state: remaining-item list, current phase progress, then a per-phase tree.\n  - If the active `in_progress` task has notes, the summary includes the note bodies inline.\n  - If any op produced validation/runtime errors, the summary starts with `Errors: ...`; the returned tool result is marked `isError: true` and still includes the mutated state.\n- `details`:\n  - `phases: TodoPhase[]`\n  - `storage: \"session\" | \"memory\"`\n  - `completedTasks?: TodoCompletionTransition[]` when a task changed from non-completed to `completed` during the batch\n\n`TodoPhase` / `TodoItem` state model:\n\n- `TodoPhase`: `{ name: string, tasks: TodoItem[] }`\n- `TodoItem`: `{ content: string, status: \"pending\" | \"in_progress\" | \"completed\" | \"abandoned\", notes?: string[] }`\n\nThe TUI renderer (`todoToolRenderer`) merges call and result into one transcript block, renders phases as a tree, shows note counts as superscripts, and renders the note bodies only for the current `in_progress` task. Collapsed transcript previews cap tree items at `PREVIEW_LIMITS.COLLAPSED_ITEMS` (`8`).\n\n## Flow\n1. `TodoTool.execute(...)` clones the current cached phases from `session.getTodoPhases?.() ?? []` (`packages/coding-agent/src/tools/todo.ts`).\n2. `applyParams(...)` walks `params.ops` in order and applies each entry with `applyEntry(...)`.\n3. Each op mutates the working phase array:\n   - `initPhases(...)` rebuilds the list from scratch.\n   - `start` resolves a task by exact `content`, demotes every other `in_progress` task to `pending`, then marks the target `in_progress`.\n   - `done` / `drop` use `getTaskTargets(...)` to target one task, one phase, or every task.\n   - `rm` removes one task, clears one phase's `tasks`, or clears all phases' task arrays.\n   - `appendItems(...)` resolves or creates the target phase and pushes new `pending` tasks unless the same task content already exists anywhere.\n   - `note` trims trailing whitespace, rejects empty text, and appends the note to `task.notes`.\n4. Missing task/phase references are recorded in an `errors` array by `resolveTaskOrError(...)` / `resolvePhaseOrError(...)`; execution continues through the rest of the batch.\n5. After the full batch, `normalizeInProgressTask(...)` enforces the single-active-task invariant:\n   - if multiple tasks are `in_progress`, only the first stays active and the rest become `pending`;\n   - if none are `in_progress`, the first `pending` task in phase/task order is auto-promoted to `in_progress`.\n6. `execute(...)` stores the normalized phases with `session.setTodoPhases?.(...)` and reports `storage` as `\"session\"` when `session.getSessionFile()` exists, else `\"memory\"`.\n7. `getCompletionTransitions(...)` compares the previous and updated phases; newly completed tasks are returned in `details.completedTasks`.\n8. The agent runtime also watches `todo` tool results in `packages/coding-agent/src/session/agent-session.ts`; successful results refresh cached todos, failed results inject a hidden next-turn reminder telling the model that todo progress is not visible until it retries.\n9. The event controller updates the visible todo UI from `result.details.phases` on success, or shows a warning on error (`packages/coding-agent/src/modes/controllers/event-controller.ts`).\n\n## Modes / Variants\n### State transitions\n\n| Current status | `start` | `done` | `drop` | `rm` | `append` | `note` |\n| --- | --- | --- | --- | --- | --- | --- |\n| `pending` | `in_progress` on target | `completed` | `abandoned` | Removed | New tasks enter as `pending` | No status change |\n| `in_progress` | Target stays `in_progress`; non-target active tasks become `pending` | `completed` | `abandoned` | Removed | No status change | No status change |\n| `completed` | Can be set back to `in_progress` if targeted | Stays `completed` | Becomes `abandoned` if targeted | Removed | No status change | No status change |\n| `abandoned` | Can be set back to `in_progress` if targeted | Becomes `completed` if targeted | Stays `abandoned` | Removed | No status change | No status change |\n\nNormalization then re-applies the single-active-task rule after the full op batch.\n\n### Op targeting rules\n- `done`, `drop`, `rm`:\n  - `task` set: affect one exact-content task.\n  - else `phase` set: affect every task in that exact-name phase.\n  - else: affect every task in every phase.\n- `append` is the only op that creates a missing phase.\n- `note` only targets a single task.\n- `init` discards previous phases entirely.\n\n### Markdown round-trip helpers\nThe same file also exposes non-tool helpers used by `/todo`:\n- `phasesToMarkdown(...)` serializes phases as headings plus checklist items (`[ ]`, `[/]`, `[x]`, `[-]`) with blockquote note bodies.\n- `markdownToPhases(...)` parses that format, defaults orphan tasks into a `Todos` phase, accepts `>` as an `in_progress` marker and `~` as `abandoned`, and runs the same normalization step.\n\n## Side Effects\n- Filesystem\n  - None in the tool itself.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Mutates the session todo cache through `setTodoPhases`.\n  - `storage` reports whether the session has a backing session file, but the tool does not append a custom session entry itself.\n  - Successful tool-result messages carry `details.phases`; `getLatestTodoPhasesFromEntries(...)` can reconstruct state later from those transcript entries.\n  - Failed `todo` results cause `agent-session` to enqueue a hidden next-turn reminder (`customType: \"todo-error-reminder\"`).\n- User-visible prompts / interactive UI\n  - Transcript block is rendered by `todoToolRenderer` and merged with the call line.\n  - `event-controller` updates the visible todo panel from successful results.\n  - On error, `event-controller` shows `Todo update failed...`; the visible panel may stay stale until a later successful call.\n- Background work / cancellation\n  - `AgentSession.setTodoPhases(...)` schedules auto-clear timers for `completed` / `abandoned` tasks via `tasks.todoClearDelay`.\n\n## Limits & Caps\n- `ops` array: `minItems: 1` (`todoSchema`).\n- `init.list[*].items`: `minItems: 1`.\n- `append.items`: `minItems: 1`.\n- Renderer collapsed preview: `PREVIEW_LIMITS.COLLAPSED_ITEMS = 8` (`packages/coding-agent/src/tools/render-utils.ts`).\n- Auto-clear delay: `tasks.todoClearDelay` default `60` seconds; `< 0` disables auto-clear, `0` clears on the next microtask (`packages/coding-agent/src/session/agent-session.ts`).\n- Tool execution mode: `concurrency = \"exclusive\"`, `strict = true`, `loadMode = \"discoverable\"`.\n\n## Errors\n- Ordinary bad op payloads are accumulated as human-readable strings in `errors`; the tool still returns the mutated state, but marks the result `isError: true`.\n- Error strings come from the helpers in `packages/coding-agent/src/tools/todo.ts`, including:\n  - `Missing list for init operation`\n  - `Missing task content`\n  - `Task \"...\" not found` with an extra empty-list hint when applicable\n  - `Missing phase name`\n  - `Phase \"...\" not found`\n  - `Missing phase name for append operation`\n  - `Missing items for append operation`\n  - `Task \"...\" already exists`\n  - `Missing text for note operation`\n- Because ops are processed in order, earlier errors do not roll back later ops.\n- Runtime-level tool failure is handled outside the tool body: `agent-session` injects a hidden reminder and the event controller warns the user that visible progress may be stale.\n- Idempotency is op-specific:\n  - `init` is a full replacement; replaying the same payload yields the same state.\n  - `start`, `done`, and `drop` are effectively idempotent on an existing target state, but `start` also demotes any other active task.\n  - `rm` is not idempotent for targeted removals: the second call errors because the task or phase is gone.\n  - `append` is not idempotent: duplicate task content is rejected with `Task \"...\" already exists`.\n  - `note` is append-only and never idempotent; replaying it adds another note entry.\n\n## Notes\n- Task lookup is exact string equality inside the tool. The model-facing prompt says task content and phase names are identifiers and should stay unique; `append` enforces task uniqueness globally, but `init` does not validate duplicate task or phase names.\n- `findTaskByContent(...)` returns the first matching task across phases. Duplicate task contents make later targeted ops ambiguous.\n- `normalizeInProgressTask(...)` runs after the whole batch, not after each op. A single call can intentionally build an intermediate invalid state and rely on final normalization.\n- `storage: \"session\"` means the session has a session-file backing; it does not mean this tool wrote a durable custom entry.\n- Reload persistence differs by path:\n  - plain `todo` calls survive in transcript tool-result details;\n  - `/todo` command edits additionally append `customType: \"user_todo_edit\"` entries and inject a visible-to-model `<system-reminder>` developer message describing the manual edit.\n- On session resume, `AgentSession.#syncTodoPhasesFromBranch()` strips `completed` and `abandoned` tasks before restoring the cached list. The `/todo` command works around that by reading the latest transcript/custom-entry state so historical done/dropped tasks still appear to the user.\n- Tool availability is gated by `todo.enabled`, and the registry excludes it when `includeYield` is enabled (`packages/coding-agent/src/tools/index.ts`).\n- Subagents do not inherit `todo`; `packages/coding-agent/src/task/executor.ts` filters it out as a parent-owned tool.\n",