@oh-my-pi/pi-coding-agent 15.6.0 → 15.7.1

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

@@ -1,6 +1,6 @@
 // Auto-generated by scripts/generate-docs-index.ts - DO NOT EDIT
 
-export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","ai-schema-normalize.md","approval-mode.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","compaction.md","config-usage.md","custom-tools.md","environment-variables.md","extension-loading.md","extensions.md","fs-scan-cache-architecture.md","gemini-manifest-extensions.md","handoff-generation-pipeline.md","hooks.md","install-id.md","keybindings.md","local-models.md","lsp-config.md","marketplace.md","mcp-config.md","mcp-protocol-transports.md","mcp-runtime-lifecycle.md","mcp-server-tool-authoring.md","memory.md","mnemosyne-memory-backend.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","plugin-manager-installer-plumbing.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","skills.md","skills/authoring-extensions.md","skills/authoring-hooks.md","skills/authoring-marketplaces.md","skills/examples/hello-extension/README.md","skills/examples/mini-marketplace/README.md","skills/examples/safety-hook/README.md","slash-command-internals.md","task-agent-discovery.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/recipe.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md","tui.md"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","ai-schema-normalize.md","approval-mode.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","compaction.md","config-usage.md","custom-tools.md","environment-variables.md","extension-loading.md","extensions.md","fs-scan-cache-architecture.md","gemini-manifest-extensions.md","handoff-generation-pipeline.md","hooks.md","install-id.md","keybindings.md","local-models.md","lsp-config.md","marketplace.md","mcp-config.md","mcp-protocol-transports.md","mcp-runtime-lifecycle.md","mcp-server-tool-authoring.md","memory.md","mnemosyne-memory-backend.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","plugin-manager-installer-plumbing.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","skills.md","skills/authoring-extensions.md","skills/authoring-hooks.md","skills/authoring-marketplaces.md","skills/examples/hello-extension/README.md","skills/examples/mini-marketplace/README.md","skills/examples/safety-hook/README.md","slash-command-internals.md","task-agent-discovery.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md","tui.md"];
 
 export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"ERRATA-GPT5-HARMONY.md": "# ERRATA — GPT-5 Harmony-Header Leakage\n\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 +\n   MLP)` 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.",
@@ -12,7 +12,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"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 four 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 threshold maintenance**: after a successful turn when context exceeds the resolved threshold.\n4. **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-retry 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.\n  - On success, agent auto-continues (`agent.continue()`) after compaction.\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 starts a new handoff session instead of writing a compaction entry; 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 hook context as `<additional-context>` list.\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. 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 both manual and auto-compaction 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  - threshold path emits `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` = `true`\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` 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.\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`\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.json` 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 (`queueMode`, `ask.timeout`, flat `theme`, `task.isolation.enabled`, `statusLine.plan_mode`).\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\tname: \"repo_stats\",\n\tlabel: \"Repo Stats\",\n\tdescription: \"Counts tracked TypeScript files\",\n\tparameters: pi.zod.object({\n\t\tglob: pi.zod.string().optional().default(\"**/*.ts\"),\n\t}),\n\n\tasync execute(toolCallId, params, onUpdate, ctx, signal) {\n\t\tonUpdate?.({\n\t\t\tcontent: [{ type: \"text\", text: \"Scanning files...\" }],\n\t\t\tdetails: { phase: \"scan\" },\n\t\t});\n\n\t\tconst result = await pi.exec(\"git\", [\"ls-files\", params.glob ?? \"**/*.ts\"], { signal, cwd: pi.cwd });\n\t\tif (result.killed) {\n\t\t\tthrow new Error(\"Scan was cancelled\");\n\t\t}\n\t\tif (result.code !== 0) {\n\t\t\tthrow new Error(result.stderr || \"git ls-files failed\");\n\t\t}\n\n\t\tconst files = result.stdout.split(\"\\n\").filter(Boolean);\n\t\treturn {\n\t\t\tcontent: [{ type: \"text\", text: `Found ${files.length} files` }],\n\t\t\tdetails: { count: files.length, sample: files.slice(0, 10) },\n\t\t};\n\t},\n\n\tonSession(event) {\n\t\tif (event.reason === \"shutdown\") {\n\t\t\t// cleanup resources if needed\n\t\t}\n\t},\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- `zod`: injected `zod` module (use `pi.zod.object`, `pi.zod.string`, …)\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\nLoader 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 schema via `z.infer<typeof schema>` (`Static<TParams>` in API types).\n- Runtime argument validation happens before execution in the agent loop.\n- `onUpdate` emits partial results for UI streaming.\n- `ctx` includes session/model state and an `abort()` helper.\n- `signal` carries cancellation.\n\n`CustomToolAdapter` bridges this to the agent tool interface and forwards calls in the correct argument order.\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| `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                                               |                                                                                                     |\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| `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` pairs and merged into request headers.\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 |\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) | Fallback: `GCLOUD_PROJECT`                                                                                                |\n| `GCLOUD_PROJECT`                 | Fallback                       | Used as alternate project ID source                                                                                       |\n| `GOOGLE_CLOUD_PROJECT_ID`        | OAuth login helper only        | Used by Gemini CLI OAuth project discovery                                                                                |\n| `GOOGLE_CLOUD_LOCATION`          | Yes (unless passed in options) | No default in provider                                                                                                    |\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_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\nAnthropic web search uses `findAnthropicAuth()` from `packages/ai/src/utils/anthropic-auth.ts` in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY` (+ optional `ANTHROPIC_SEARCH_BASE_URL`)\n2. `ANTHROPIC_FOUNDRY_API_KEY` when `CLAUDE_CODE_USE_FOUNDRY` is enabled\n3. Anthropic OAuth credentials from `agent.db` (must not expire within 5-minute buffer)\n4. Anthropic API-key credentials from `agent.db`\n5. Generic Anthropic env fallback: provider key (`ANTHROPIC_FOUNDRY_API_KEY` in Foundry mode, otherwise `ANTHROPIC_OAUTH_TOKEN`/`ANTHROPIC_API_KEY`) + optional `ANTHROPIC_BASE_URL` (`FOUNDRY_BASE_URL` when Foundry mode is enabled)\n\nRelated vars:\n\n| Variable                    | Default / behavior                                   |\n| --------------------------- | ---------------------------------------------------- |\n| `ANTHROPIC_SEARCH_API_KEY`  | Highest-priority explicit search key                 |\n| `ANTHROPIC_SEARCH_BASE_URL` | Defaults to `https://api.anthropic.com` when omitted |\n| `ANTHROPIC_SEARCH_MODEL`    | Defaults to `claude-haiku-4-5`                       |\n| `ANTHROPIC_BASE_URL`        | Generic fallback base URL for tier-4 auth path       |\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| `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 path lookup)                  |\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| `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| `KITTY_WINDOW_ID`, `TMUX_PANE`, `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_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| `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                                               |                                                                                                     |\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| `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` pairs and merged into request headers.\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 |\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) | Fallback: `GCLOUD_PROJECT`                                                                                                |\n| `GCLOUD_PROJECT`                 | Fallback                       | Used as alternate project ID source                                                                                       |\n| `GOOGLE_CLOUD_PROJECT_ID`        | OAuth login helper only        | Used by Gemini CLI OAuth project discovery                                                                                |\n| `GOOGLE_CLOUD_LOCATION`          | Yes (unless passed in options) | No default in provider                                                                                                    |\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_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\nAnthropic web search uses `findAnthropicAuth()` from `packages/ai/src/utils/anthropic-auth.ts` in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY` (+ optional `ANTHROPIC_SEARCH_BASE_URL`)\n2. `ANTHROPIC_FOUNDRY_API_KEY` when `CLAUDE_CODE_USE_FOUNDRY` is enabled\n3. Anthropic OAuth credentials from `agent.db` (must not expire within 5-minute buffer)\n4. Anthropic API-key credentials from `agent.db`\n5. Generic Anthropic env fallback: provider key (`ANTHROPIC_FOUNDRY_API_KEY` in Foundry mode, otherwise `ANTHROPIC_OAUTH_TOKEN`/`ANTHROPIC_API_KEY`) + optional `ANTHROPIC_BASE_URL` (`FOUNDRY_BASE_URL` when Foundry mode is enabled)\n\nRelated vars:\n\n| Variable                    | Default / behavior                                   |\n| --------------------------- | ---------------------------------------------------- |\n| `ANTHROPIC_SEARCH_API_KEY`  | Highest-priority explicit search key                 |\n| `ANTHROPIC_SEARCH_BASE_URL` | Defaults to `https://api.anthropic.com` when omitted |\n| `ANTHROPIC_SEARCH_MODEL`    | Defaults to `claude-haiku-4-5`                       |\n| `ANTHROPIC_BASE_URL`        | Generic fallback base URL for tier-4 auth path       |\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: DirectML on Windows, CUDA on Linux x64, CPU elsewhere; supports `cpu`, `cuda`, `dml`, `coreml`, `gpu`, `metal`/`webgpu`, `auto`) |\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| `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 path lookup)                  |\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| `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| `KITTY_WINDOW_ID`, `TMUX_PANE`, `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_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\nEffective native locations:\n\n- Project: `<cwd>/.omp/extensions`\n- User: `~/.omp/agent/extensions`\n\nPath roots come from the native provider (`SOURCE_PATHS.native`).\n\nNotes:\n\n- Native auto-discovery is currently `.omp` based.\n- Legacy `.pi` is still accepted in `package.json` manifest keys (`pi.extensions`), but not as 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. Settings `extensions` array (merged global + project settings)\n\nGlobal settings file:\n\n- `~/.omp/agent/config.yml` (or custom agent dir via `PI_CODING_AGENT_DIR`)\n\nProject settings file:\n\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 `docs/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`\n- `sendMessage`, `sendUserMessage`, `appendEntry`\n- `getActiveTools`, `getAllTools`, `setActiveTools`\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.zod` (injected `zod` module — use 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- `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\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  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.\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- 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## 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 and traversal policy, then lets higher-level operations (glob filtering, fuzzy scoring, grep file selection) run against those cached entries.\n\nPrimary goals:\n\n- avoid repeated filesystem walks for repeated discovery/search calls\n- keep consistency across `glob`, `fuzzyFind`, and `grep` 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`\n- JS binding/export:\n  - `packages/natives/src/glob/index.ts` (`invalidateFsScanCache`)\n  - `packages/natives/src/glob/types.ts`\n  - `packages/natives/src/grep/types.ts`\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\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- Consumers must pass stable semantics for hidden/gitignore/node_modules behavior; changing any flag creates a different cache partition.\n\n## Scan collection behavior\n\nCache population uses a deterministic walker (`ignore::WalkBuilder`) configured by `include_hidden`, `use_gitignore`, and `skip_node_modules`:\n\n- `follow_links(false)`\n- sorted by file path\n- `.git` is always skipped\n- `node_modules` is pruned at traversal time when `skip_node_modules=true`\n- entry file type + `mtime` are captured via `symlink_metadata`\n\nSearch roots are resolved by `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 cached entries + non-zero `cache_age_ms`\n  - on expired hit: evict key, rescan, store fresh entry\n- max entry enforcement is oldest-first eviction by `created_at`\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(...)` and retries\n- intended to reduce stale-negative results when files were recently added but cache is still within 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 selected candidate file list is empty\n\n## Consumer defaults and cache usage\n\nCache is opt-in on all exposed APIs (`cache?: boolean`, default `false`).\n\nCurrent defaults in native APIs:\n\n- `glob`: `hidden=false`, `gitignore=true`, `cache=false`, and `node_modules` included only when the pattern mentions `node_modules`\n- `fuzzyFind`: `hidden=false`, `gitignore=true`, `cache=false`, and `node_modules` is skipped\n- `grep`: `hidden=true`, `gitignore=true`, `cache=false`, and `node_modules` included only when the glob mentions `node_modules`\n\nCoding-agent callers today:\n\n- High-volume mention candidate discovery enables cache:\n  - `packages/coding-agent/src/utils/file-mentions.ts`\n  - profile: `hidden=true`, `gitignore=true`, `includeNodeModules=true`, `cache=true`\n- Tool-level `grep` integration currently disables scan cache (`cache: false`):\n  - `packages/coding-agent/src/tools/grep.ts`\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 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 (e.g., delete), fallback canonicalizes parent and reattaches 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 tool callsites:\n\n- `packages/coding-agent/src/tools/write.ts`\n- `packages/coding-agent/src/patch/index.ts` (hashline/patch/replace flows)\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 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, ...)`\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`/`grep` share scan entries only when key dimensions (`root`, `hidden`, `gitignore`, `skip_node_modules`) match.\n- `.git` is always excluded at scan collection time regardless of caller options.\n",
@@ -21,7 +21,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"hooks.md": "# Hooks\n\nThis document describes the **current hook subsystem code** in `src/extensibility/hooks/*`.\n\n## Current status in runtime\n\nThe hook package (`src/extensibility/hooks/`) is still exported and usable as an API surface, but the default CLI runtime now initializes the **extension runner** path. In current startup flow:\n\n- `--hook` is treated as an alias for `--extension` (CLI paths are merged into `additionalExtensionPaths`)\n- tools are wrapped by `ExtensionToolWrapper`, not `HookToolWrapper`\n- context transforms and lifecycle emissions go through `ExtensionRunner`\n\nSo this file documents the hook subsystem implementation itself (types/loader/runner/wrapper), including legacy behavior and constraints.\n\n## Key files\n\n- `src/extensibility/hooks/types.ts` — hook context, event types, and result contracts\n- `src/extensibility/hooks/loader.ts` — module loading and hook discovery bridge\n- `src/extensibility/hooks/runner.ts` — event dispatch, command lookup, error signaling\n- `src/extensibility/hooks/tool-wrapper.ts` — pre/post tool interception wrapper\n- `src/extensibility/hooks/index.ts` — exports/re-exports\n\n## What a hook module is\n\nA hook module must default-export a factory:\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function hook(pi: HookAPI): void {\n  pi.on(\"tool_call\", async (event, ctx) => {\n    if (\n      event.toolName === \"bash\" &&\n      String(event.input.command ?? \"\").includes(\"rm -rf\")\n    ) {\n      return { block: true, reason: \"blocked by policy\" };\n    }\n  });\n}\n```\n\nThe factory can:\n\n- register event handlers with `pi.on(...)`\n- send persistent custom messages with `pi.sendMessage(...)`\n- persist non-LLM state with `pi.appendEntry(...)`\n- register slash commands via `pi.registerCommand(...)`\n- register custom message renderers via `pi.registerMessageRenderer(...)`\n- run shell commands via `pi.exec(...)`\n\n## Discovery and loading\n\n`discoverAndLoadHooks(configuredPaths, cwd)` does:\n\n1. Load discovered hooks from capability registry (`loadCapability(\"hooks\")`)\n2. Append explicitly configured paths (deduped by absolute path)\n3. Call `loadHooks(allPaths, cwd)`\n\n`loadHooks` then imports each path and expects a `default` function.\n\n### Path resolution\n\n`loader.ts` resolves hook paths as:\n\n- absolute path: used as-is\n- `~` path: expanded\n- relative path: resolved against `cwd`\n\n### Important legacy mismatch\n\nDiscovery providers for `hookCapability` still model pre/post shell-style hook files (for example `.claude/hooks/pre/*`, `.omp/.../hooks/pre/*`).\n\nThe hook loader here uses dynamic module import and requires a default JS/TS hook factory. If a discovered hook path is not importable as a module, load fails and is reported in `LoadHooksResult.errors`.\n\n## Event surfaces\n\nHook events are strongly typed in `types.ts`.\n\n### Session events\n\n- `session_start`\n- `session_before_switch` → can return `{ cancel?: boolean }`\n- `session_switch`\n- `session_before_branch` → can return `{ cancel?: boolean; skipConversationRestore?: boolean }`\n- `session_branch`\n- `session_before_compact` → can return `{ cancel?: boolean; compaction?: CompactionResult }`\n- `session.compacting` → can return `{ context?: string[]; prompt?: string; preserveData?: Record<string, unknown> }`\n- `session_compact`\n- `session_before_tree` → can return `{ cancel?: boolean; summary?: { summary: string; details?: unknown } }`\n- `session_tree`\n- `session_shutdown`\n\n### Agent/context events\n\n- `context` → can return `{ messages?: Message[] }`\n- `before_agent_start` → can return `{ message?: { customType; content; display; details } }`\n- `agent_start`\n- `agent_end`\n- `turn_start`\n- `turn_end`\n- `auto_compaction_start`\n- `auto_compaction_end`\n- `auto_retry_start`\n- `auto_retry_end`\n- `ttsr_triggered`\n- `todo_reminder`\n\n### Tool events (pre/post model)\n\n- `tool_call` (pre-execution) → can return `{ block?: boolean; reason?: string }`\n- `tool_result` (post-execution) → can return `{ content?; details?; isError? }`\n\nThis is the hook subsystem’s core pre/post interception model.\n\n```text\nHook tool interception flow\n\ntool_call handlers\n   │\n   ├─ any { block: true }? ── yes ──> throw (tool blocked)\n   │\n   └─ no\n      │\n      ▼\n   execute underlying tool\n      │\n      ├─ success ──> tool_result handlers can override { content, details }\n      │\n      └─ error   ──> emit tool_result(isError=true) then rethrow original error\n```\n\n## Execution model and mutation semantics\n\n### 1) Pre-execution: `tool_call`\n\n`HookToolWrapper.execute()` emits `tool_call` before tool execution.\n\n- if any handler returns `{ block: true }`, execution stops\n- if handler throws, wrapper fails closed and blocks execution\n- returned `reason` becomes the thrown error text\n\n### 2) Tool execution\n\nUnderlying tool executes normally if not blocked.\n\n### 3) Post-execution: `tool_result`\n\nAfter success, wrapper emits `tool_result` with:\n\n- `toolName`, `toolCallId`, `input`\n- `content`\n- `details`\n- `isError: false`\n\nIf handler returns overrides:\n\n- `content` can replace result content\n- `details` can replace result details\n\nOn tool failure, wrapper emits `tool_result` with `isError: true` and error text content, then rethrows original error.\n\n### What hooks can mutate\n\n- LLM context for a single call via `context` (`messages` replacement chain)\n- tool output content/details on successful tool calls (`tool_result` path)\n- pre-agent injected message via `before_agent_start`\n- cancellation/custom compaction/tree behavior via `session_before_*` and `session.compacting`\n\n### What hooks cannot mutate in this implementation\n\n- raw tool input parameters in-place (only block/allow on `tool_call`)\n- execution continuation after thrown tool errors (error path rethrows)\n- final success/error status in wrapper behavior (returned `isError` is typed but not applied by `HookToolWrapper`)\n\n## Ordering and conflict behavior\n\n### Discovery-level ordering\n\nCapability providers are priority-sorted (higher first). Dedupe is by capability key, first wins.\n\nFor `hooks`, capability key is `${type}:${tool}:${name}`. Shadowed duplicates from lower-priority providers are marked and excluded from effective discovered list.\n\n### Load order\n\n`discoverAndLoadHooks` builds a flat `allPaths` list, deduped by resolved absolute path, then `loadHooks` iterates in that order.\nFile order within each discovered directory depends on `readdir` output; the hook loader does not perform an additional sort.\n\n### Runtime handler order\n\nInside `HookRunner`, order is deterministic by registration sequence:\n\n1. hooks array order\n2. handler registration order per hook/event\n\nConflict behavior by event type:\n\n- `tool_call`: last returned result wins unless a handler blocks; first block short-circuits\n- `tool_result`: last returned override wins (no short-circuit)\n- `context`: chained; each handler receives prior handler’s message output\n- `before_agent_start`: first returned message is kept; later messages ignored\n- `session_before_*`: latest returned result is tracked; `cancel: true` short-circuits immediately\n- `session.compacting`: latest returned result wins\n\nCommand/renderer conflicts:\n\n- `getCommand(name)` returns first match across hooks (first loaded wins)\n- `getMessageRenderer(customType)` returns first match\n- `getRegisteredCommands()` returns all commands (no dedupe)\n\n## UI interactions (`HookContext.ui`)\n\n`HookUIContext` includes:\n\n- `select`, `confirm`, `input`, `editor`\n- `notify`\n- `setStatus`\n- `custom`\n- `setEditorText`, `getEditorText`\n- `theme` getter\n\n`ctx.hasUI` indicates whether interactive UI is available.\n\nWhen running with no UI, the default no-op context behavior is:\n\n- `select/input/editor` return `undefined`\n- `confirm` returns `false`\n- `notify`, `setStatus`, `setEditorText` are no-ops\n- `getEditorText` returns `\"\"`\n\n### Status line behavior\n\nHook status text set via `ctx.ui.setStatus(key, text)` is:\n\n- stored per key\n- sorted by key name\n- sanitized (`\\r`, `\\n`, `\\t` → spaces; repeated spaces collapsed)\n- joined and width-truncated for display\n\n## Error propagation and fallback\n\n### Load-time\n\n- invalid module or missing default export → captured in `LoadHooksResult.errors`\n- loading continues for other hooks\n\n### Event-time\n\n`HookRunner.emit(...)` catches handler errors for most events and emits `HookError` to listeners (`hookPath`, `event`, `error`), then continues.\n\n`emitToolCall(...)` is stricter: handler errors are not swallowed there; they propagate to caller. In `HookToolWrapper`, this blocks the tool call (fail-safe).\n\n## Realistic API examples\n\n### Block unsafe bash commands\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function (pi: HookAPI): void {\n  pi.on(\"tool_call\", async (event, ctx) => {\n    if (event.toolName !== \"bash\") return;\n    const cmd = String(event.input.command ?? \"\");\n    if (!cmd.includes(\"rm -rf\")) return;\n\n    if (!ctx.hasUI) return { block: true, reason: \"rm -rf blocked (no UI)\" };\n    const ok = await ctx.ui.confirm(\"Dangerous command\", `Allow: ${cmd}`);\n    if (!ok) return { block: true, reason: \"user denied command\" };\n  });\n}\n```\n\n### Redact tool output on post-execution\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function (pi: HookAPI): void {\n  pi.on(\"tool_result\", async (event) => {\n    if (event.toolName !== \"read\" || event.isError) return;\n\n    const redacted = event.content.map((chunk) => {\n      if (chunk.type !== \"text\") return chunk;\n      return {\n        ...chunk,\n        text: chunk.text.replaceAll(/API_KEY=\\S+/g, \"API_KEY=[REDACTED]\"),\n      };\n    });\n\n    return { content: redacted };\n  });\n}\n```\n\n### Modify model context per LLM call\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function (pi: HookAPI): void {\n  pi.on(\"context\", async (event) => {\n    const filtered = event.messages.filter(\n      (msg) => !(msg.role === \"custom\" && msg.customType === \"debug-only\"),\n    );\n    return { messages: filtered };\n  });\n}\n```\n\n### Register slash command with command-safe context methods\n\n```ts\nimport type { HookAPI } from \"@oh-my-pi/pi-coding-agent/extensibility/hooks\";\n\nexport default function (pi: HookAPI): void {\n  pi.registerCommand(\"handoff\", {\n    description: \"Create a new session with setup message\",\n    handler: async (_args, ctx) => {\n      await ctx.waitForIdle();\n      await ctx.newSession({\n        parentSession: ctx.sessionManager.getSessionFile(),\n        setup: async (sm) => {\n          sm.appendMessage({\n            role: \"user\",\n            content: [\n              { type: \"text\", text: \"Continue from prior session summary.\" },\n            ],\n            timestamp: Date.now(),\n          });\n        },\n      });\n    },\n  });\n}\n```\n\n## Export surface\n\n`src/extensibility/hooks/index.ts` and the package subpath `@oh-my-pi/pi-coding-agent/extensibility/hooks` export:\n\n- loading APIs (`discoverAndLoadHooks`, `loadHooks`)\n- runner and wrapper (`HookRunner`, `HookToolWrapper`)\n- all hook types\n- `execCommand` re-export\n\nThe package root (`@oh-my-pi/pi-coding-agent`) does not re-export `HookAPI`; import legacy hook types from the hooks subpath.\n",
 	"install-id.md": "# Install ID\n\nA persistent per-install UUID that identifies a single oh-my-pi installation across sessions. Used as a stable correlation key for server-side dedup of telemetry-style pushes (currently the auto-QA grievance flush from `report_tool_issue`).\n\n## API\n\nExported from `@oh-my-pi/pi-utils` (`packages/utils/src/dirs.ts`):\n\n| Symbol | Purpose |\n| --- | --- |\n| `getInstallId(): string` | Returns the install ID, generating and persisting one on first call. Result is cached in-process for the lifetime of the runtime. |\n| `__resetInstallIdCacheForTests(): void` | Clears the in-process cache. Test-only — MUST NOT be called from production code. |\n\nThe returned value is a canonical lowercase RFC 4122 UUID matching `^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$`.\n\n## Storage\n\n- Path: `<config-root>/install-id` — i.e. `~/.omp/install-id` by default, respecting `PI_CONFIG_DIR` via `getConfigRootDir()`.\n- Format: a single UUID line (trailing `\\n`).\n- Permissions: file is created with mode `0o600`.\n- Lifecycle: independent of `~/.omp/agent/`. Wiping agent state (sessions, settings, DB) does NOT regenerate the install ID; only deleting the `install-id` file itself does.\n\n## Generation and lifecycle\n\n1. First call to `getInstallId()` reads the file. If contents parse as a valid UUID, that value is cached and returned.\n2. Otherwise the helper calls `crypto.randomUUID()` (Node's CSPRNG-backed UUID v4) to mint a new ID.\n3. The new value is written via `open(O_WRONLY | O_CREAT | O_EXCL, 0o600)`. The exclusive-create guard means two processes hitting first-call simultaneously cannot both succeed — the loser sees `EEXIST`, re-reads the winner's file, and adopts that ID.\n4. If the existing file contained non-empty garbage (failed UUID regex), it is `unlink`ed before the exclusive create so `O_EXCL` does not trip on stale data.\n5. Any other write failure (read-only FS, permission error) is swallowed: the freshly generated UUID is still cached in-memory so the rest of the process sees a stable value, and subsequent process launches will retry persistence.\n6. Subsequent in-process calls return the cached value without touching disk. Mutating the file on disk after the first call has no effect until the process restarts (or tests call `__resetInstallIdCacheForTests`).\n\n## Consumers\n\n- `packages/coding-agent/src/tools/report-tool-issue.ts` — included as `installId` in the auto-QA grievance push body so the backend can deduplicate repeated reports from the same install. See `dev.autoqaPush.*` settings and `PI_AUTO_QA_PUSH_*` env vars.\n\nNew consumers MUST treat the value as opaque and MUST NOT derive PII from it; the helper does not mix in hostname, username, or any other host-identifying entropy.\n\n## See also\n\n- [environment-variables.md](environment-variables.md) — `PI_CONFIG_DIR` controls where `install-id` lives.\n- [config-usage.md](config-usage.md) — broader config-root layout.\n",
 	"keybindings.md": "# Keybindings\n\nRun `/hotkeys` inside an `omp` session to see the active chords for your current build. The list reflects any remaps loaded from disk and any bindings added by extensions.\n\n## Customize keybindings\n\nUser remaps live in `~/.omp/agent/keybindings.json`. The file is a JSON object whose keys are keybinding action IDs and whose values are either one chord string or an array of chord strings. It is not read from `~/.omp/agent/config.yml`, and there is no nested `keybindings` object.\n\n```json\n{\n  \"app.model.cycleForward\": \"Ctrl+P\",\n  \"app.model.selectTemporary\": \"Alt+P\",\n  \"app.plan.toggle\": \"Alt+Shift+P\"\n}\n```\n\nChord names are case-insensitive and use the same notation shown in the UI, such as `Ctrl+P`, `Alt+Shift+P`, `Shift+Enter`, and `Ctrl+Backspace`.\n\nSet an action to an empty array to disable it:\n\n```json\n{\n  \"app.stt.toggle\": []\n}\n```\n\n## Common action IDs\n\n| Action ID | Default | Meaning |\n| --- | --- | --- |\n| `app.model.cycleForward` | `Ctrl+P` | Cycle role models forward |\n| `app.model.cycleBackward` | `Shift+Ctrl+P` | Cycle role models backward |\n| `app.model.selectTemporary` | `Alt+P` | Pick a model temporarily for this session |\n| `app.model.select` | `Ctrl+L` | Open the model selector and set roles |\n| `app.plan.toggle` | `Alt+Shift+P` | Toggle plan mode |\n| `app.history.search` | `Ctrl+R` | Search prompt history |\n| `app.tools.expand` | `Ctrl+O` | Toggle tool-output expansion |\n| `app.thinking.toggle` | `Ctrl+T` | Toggle thinking-block visibility |\n| `app.thinking.cycle` | `Shift+Tab` | Cycle thinking level |\n| `app.editor.external` | `Ctrl+G` | Edit the draft in `$VISUAL` / `$EDITOR` |\n| `app.message.followUp` | `Ctrl+Enter` | Queue a follow-up message |\n| `app.message.dequeue` | `Alt+Up` | Dequeue a queued message back into the editor |\n| `app.clipboard.copyLine` | `Alt+Shift+L` | Copy the current line |\n| `app.clipboard.copyPrompt` | `Alt+Shift+C` | Copy the whole prompt |\n| `app.stt.toggle` | `Alt+H` | Toggle speech-to-text recording |\n\nOlder unqualified action names are migrated when `keybindings.json` is loaded, but new docs and new configs should use the namespaced action IDs above.\n",
-	"local-models.md": "# Embedded Local Tiny-Model Experiments\n\nThis document summarizes the experiments behind the optional **local** tiny-model paths for two\ncoding-agent tasks: session-title generation (`providers.tinyModel`) and Mnemosyne memory\nextraction/consolidation (`providers.memoryModel`). It is a factual engineering record for\nmaintainers: what we measured, which recipes won, and which models we shipped. Both settings\ndefault to `online`, so existing users incur no downloads or CPU cost unless they opt in.\n\n## Runtime / environment findings\n\n- **Stack**: `@huggingface/transformers` (transformers.js) v4 running under Bun. In Bun the library\n  loads the **native `onnxruntime-node` backend** (not the WASM build). Available device options are\n  `cpu` / `coreml` / `webgpu` — there is **no `wasm` device** in the node build.\n- **Device verdict: use `device:\"cpu\"`.** CPU is the only reliable path.\n  - `coreml` EP is **broken for decoder LLMs**: it rejects the dynamic KV-cache `past_key_values`\n    zero-element first-token shape.\n  - `webgpu` runs but is **slower and numerically divergent** (worse output quality).\n- **Quantization: q4 is the sweet spot** — smaller on disk, faster to load, and fast at inference.\n  q8/int8 loads slower *and* infers slower on CPU.\n- **Load-time correction (important).** An earlier belief that \"q4 >=1B models take minutes to load\"\n  was a **measurement artifact** caused by running ~5 multi-GB HuggingFace downloads in parallel\n  (I/O saturation). Clean, isolated **warm** loads are all sub-3s:\n  - TinyLlama-1.1B q4: ~0.5s\n  - Llama-3.2-1B q4: ~2.8s (`graphOpt=all`) / ~0.5s (`disabled`)\n  - LFM2-1.2B q4: ~0.36s\n  - Qwen2.5-1.5B q4: ~1.5s\n  - Qwen3-1.7B q4: ~1.6s\n  - gemma-3-1b q4: ~1.1s\n  - Conclusion: **1B–1.7B models are viable on CPU.**\n- **`session_options.graphOptimizationLevel`** trades load vs inference speed: `disabled` = fastest\n  load, slightly slower inference; `all` = default.\n- **First run** downloads weights from the HF Hub to a cache dir (q4 weights ~200MB–1.1GB depending\n  on model); subsequent **warm** loads are sub-second to ~3s. Inference is async and\n  background-friendly for memory tasks; titles are semi-interactive.\n\n## Task 1: Session title generation (`providers.tinyModel`)\n\n**Task**: turn the first user message into a 3–6 word title. Tiny models (sub-1B) suffice.\n\n**Winning recipe**:\n\n- Plain system prompt (no few-shot).\n- **Prefill** the assistant turn with `<title>` and **stop at `</title>`**, then take the first line.\n- Greedy decoding (`do_sample:false`), `enable_thinking:false` in the chat template.\n\n**What we learned**:\n\n- **Few-shot examples HURT sub-0.6B models** for titles; the tag-prefill rescues even 270M models.\n- **Token biasing (`bad_words_ids`) is a confirmed no-op** here — the prefill already controls the\n  opener.\n\n**Leaderboard** (tag trick, CPU, warm):\n\n| Model | Verdict |\n| --- | --- |\n| LFM2-350M | Best speed/quality balance (~212MB) |\n| Qwen3-0.6B | Most robust |\n| gemma-3-270m | Smallest viable |\n| Qwen2.5-0.5B | Acceptable |\n| SmolLM2-135M | Too small |\n| flan-t5-small | Rejected — just echoes the input |\n\n**Shipped local options**: `lfm2-350m`, `qwen3-0.6b`, `gemma-270m`, `qwen2.5-0.5b`, `lfm2-700m`.\n**Default**: `online` (pi/smol).\n\n## Task 2: Mnemosyne memory (`providers.memoryModel`)\n\nMnemosyne runs two small-LLM tasks:\n\n1. **Extraction** — pull durable, structured items from a single message.\n2. **Consolidation** — summarize a list of memories into 1–3 faithful sentences.\n\nThese need **bigger models than titles: 1B–1.7B**. We tested LFM2-1.2B, Qwen2.5-1.5B, Qwen3-1.7B,\nand gemma-3-1b (q4, CPU) via four parallel agents each running 27–31 experiments.\n\n### Extraction findings\n\nThe stock 5-category JSON prompt fails on small models in two ways:\n\n1. The all-empty example `{\"facts\":[],...}` gets **copied verbatim** → 0 facts extracted.\n2. Capable models emit **JSON objects inside arrays**, which Mnemosyne's `String(item)` coerces into\n   the literal string `[object Object]`.\n\nThe robust fix is a **one-item-per-line output format** (consumed by Mnemosyne's parser line-fallback)\nor a **flat JSON array of strings**. Every model also over-extracts pure small talk; an explicit\nchit-chat → NONE example is the best mitigation.\n\n### Technique polarity flips vs titles\n\n- At 1B+, **few-shot is the dominant quality lever**: e.g. Qwen2.5-1.5B extraction F1 0.52 → 0.83\n  going 1 → 3 shots; gemma recall 0.65 → 0.92 with 2 shots.\n- **Prefill HURTS extraction** — it forces output on small talk, producing false positives.\n- **System-split** (instructions in the system role) helps models that have a system role.\n- **Greedy >= temperature** for both tasks.\n- **Token biasing** is again a no-op.\n\n### Per-model verdicts (head-to-head, 16-fixture set)\n\n- **Qwen3-1.7B** — most disciplined extraction: returns empty on small talk, no buried-fact leak,\n  preserves language, clean flat JSON. Weaknesses: coarse granularity, missed a multi-turn value\n  update.\n- **Qwen2.5-1.5B** — best extraction granularity (atomic facts), caught the value update, zero\n  small-talk leakage. Weaknesses: weakest consolidation (run-on, no dedup) and one degenerate\n  buried-fact output.\n- **gemma-3-1b** — best consolidation (dedup works, faithful, clean single-memory). Weaknesses: leaks\n  small talk and translated German.\n- **LFM2-1.2B** — solid and fastest to load. Weaknesses: `Label: value` noise, small-talk + buried\n  leaks, a fluffy single-memory summary.\n\n### Recommendation\n\nExtraction favors **precision** (do not pollute long-term memory) → **Qwen3-1.7B is the best single\npick** (its consolidation is good enough). If running a second model for consolidation, **gemma-3-1b**\nwins that task.\n\n**Shipped local options**: `qwen3-1.7b` (recommended), `gemma-3-1b`, `qwen2.5-1.5b`, `lfm2-1.2b`.\n**Default**: `online` (the configured smol model).\n\n### Known Mnemosyne parser bugs (surfaced by these experiments)\n\n- `String(item)` produces `[object Object]` on object array items.\n- The line-fallback drops items `<=10` chars, so a correct short fact like `Name: Can` is discarded.\n\n## Integration notes\n\n- Both settings default to `online`, so existing users get **no downloads or CPU cost** unless they\n  opt in.\n- Local inference runs **in a worker** (off the main thread); models are cached on disk and\n  downloaded on first use.\n- The memory local path applies the refined recipes (line-format + small-talk-guarded extraction\n  prompt, hardened consolidation prompt) via Mnemosyne prompt overrides; the **online path is\n  unchanged**.\n",
+	"local-models.md": "# Embedded Local Tiny-Model Experiments\n\nThis document summarizes the experiments behind the optional **local** tiny-model paths for two\ncoding-agent tasks: session-title generation (`providers.tinyModel`) and Mnemosyne memory\nextraction/consolidation (`providers.memoryModel`). It is a factual engineering record for\nmaintainers: what we measured, which recipes won, and which models we shipped. Both settings\ndefault to `online`, so existing users incur no downloads or on-device inference cost unless they opt in.\n\n## Runtime / environment findings\n\n- **Stack**: `@huggingface/transformers` (transformers.js) v4 running under Bun. In Bun the library\n  loads the **native `onnxruntime-node` backend** (not the WASM build).\n- **Device policy**: local tiny models request a worker-safe accelerated ONNX execution provider when\n  one is available, and retry once on `device:\"cpu\"` if acceleration cannot initialize.\n  - Defaults: DirectML on Windows, CUDA on Linux x64, and CPU elsewhere. Pick a provider persistently\n    with the `providers.tinyModelDevice` setting (`default` keeps the platform pick); the\n    `PI_TINY_DEVICE` env var overrides the setting.\n  - Direct `coreml` remains opt-in via `PI_TINY_DEVICE=coreml`; it is not part of the default because\n    cached decoder-LLM ONNX loads can fail during session initialization.\n  - WebGPU/Metal works for the single-process eval harness, but it is not enabled in the production\n    worker on macOS because ONNX Runtime/Bun currently hard-crashes on worker teardown after WebGPU\n    inference.\n  - Use `providers.tinyModelDevice: cpu` (or `PI_TINY_DEVICE=cpu`) for the old CPU-only path.\n- **Quantization: q4 is the sweet spot** — smaller on disk, faster to load, and fast at inference.\n  q8/int8 loads slower *and* infers slower on CPU. Every shipped model defaults to `q4`; override the\n  precision persistently with the `providers.tinyModelDtype` setting (`default` keeps `q4`, e.g. `fp16`\n  for higher fidelity), or per-run with `PI_TINY_DTYPE` (which overrides the setting). Accepts `auto`,\n  `fp32`, `fp16`, `q8`, `int8`, `uint8`, `q4`, `bnb4`, `q4f16`, `q2`, `q2f16`, `q1`, `q1f16`; an\n  unrecognized value fails loudly at worker startup.\n- **Load-time correction (important).** An earlier belief that \"q4 >=1B models take minutes to load\"\n  was a **measurement artifact** caused by running ~5 multi-GB HuggingFace downloads in parallel\n  (I/O saturation). Clean, isolated **warm** loads are all sub-3s:\n  - TinyLlama-1.1B q4: ~0.5s\n  - Llama-3.2-1B q4: ~2.8s (`graphOpt=all`) / ~0.5s (`disabled`)\n  - LFM2-1.2B q4: ~0.36s\n  - Qwen2.5-1.5B q4: ~1.5s\n  - Qwen3-1.7B q4: ~1.6s\n  - gemma-3-1b q4: ~1.1s\n  - Conclusion: **1B–1.7B models are viable on CPU.**\n- **`session_options.graphOptimizationLevel`** trades load vs inference speed: `disabled` = fastest\n  load, slightly slower inference; `all` = default.\n- **First run** downloads weights from the HF Hub to a cache dir (q4 weights ~200MB–1.1GB depending\n  on model); subsequent **warm** loads are sub-second to ~3s. Inference is async and\n  background-friendly for memory tasks; titles are semi-interactive.\n\n## Task 1: Session title generation (`providers.tinyModel`)\n\n**Task**: turn the first user message into a 3–6 word title. Tiny models (sub-1B) suffice.\n\n**Winning recipe**:\n\n- Plain system prompt (no few-shot).\n- **Prefill** the assistant turn with `<title>` and **stop at `</title>`**, then take the first line.\n- Greedy decoding (`do_sample:false`), `enable_thinking:false` in the chat template.\n\n**What we learned**:\n\n- **Few-shot examples HURT sub-0.6B models** for titles; the tag-prefill rescues even 270M models.\n- **Token biasing (`bad_words_ids`) is a confirmed no-op** here — the prefill already controls the\n  opener.\n\n**Leaderboard** (tag trick, CPU, warm):\n\n| Model | Verdict |\n| --- | --- |\n| LFM2-350M | Best speed/quality balance (~212MB) |\n| Qwen3-0.6B | Most robust |\n| gemma-3-270m | Smallest viable |\n| Qwen2.5-0.5B | Acceptable |\n| SmolLM2-135M | Too small |\n| flan-t5-small | Rejected — just echoes the input |\n\n**Shipped local options**: `lfm2-350m`, `qwen3-0.6b`, `gemma-270m`, `qwen2.5-0.5b`, `lfm2-700m`.\n**Default**: `online` (pi/smol).\n\n## Task 2: Mnemosyne memory (`providers.memoryModel`)\n\nMnemosyne runs two small-LLM tasks:\n\n1. **Extraction** — pull durable, structured items from a single message.\n2. **Consolidation** — summarize a list of memories into 1–3 faithful sentences.\n\nThese need **bigger models than titles: 1B–1.7B**. We tested LFM2-1.2B, Qwen2.5-1.5B, Qwen3-1.7B,\nand gemma-3-1b (q4, CPU) via four parallel agents each running 27–31 experiments.\n\n### Extraction findings\n\nThe stock 5-category JSON prompt fails on small models in two ways:\n\n1. The all-empty example `{\"facts\":[],...}` gets **copied verbatim** → 0 facts extracted.\n2. Capable models emit **JSON objects inside arrays**, which Mnemosyne's `String(item)` coerces into\n   the literal string `[object Object]`.\n\nThe robust fix is a **one-item-per-line output format** (consumed by Mnemosyne's parser line-fallback)\nor a **flat JSON array of strings**. Every model also over-extracts pure small talk; an explicit\nchit-chat → NONE example is the best mitigation.\n\n### Technique polarity flips vs titles\n\n- At 1B+, **few-shot is the dominant quality lever**: e.g. Qwen2.5-1.5B extraction F1 0.52 → 0.83\n  going 1 → 3 shots; gemma recall 0.65 → 0.92 with 2 shots.\n- **Prefill HURTS extraction** — it forces output on small talk, producing false positives.\n- **System-split** (instructions in the system role) helps models that have a system role.\n- **Greedy >= temperature** for both tasks.\n- **Token biasing** is again a no-op.\n\n### Per-model verdicts (head-to-head, 16-fixture set)\n\n- **Qwen3-1.7B** — most disciplined extraction: returns empty on small talk, no buried-fact leak,\n  preserves language, clean flat JSON. Weaknesses: coarse granularity, missed a multi-turn value\n  update.\n- **Qwen2.5-1.5B** — best extraction granularity (atomic facts), caught the value update, zero\n  small-talk leakage. Weaknesses: weakest consolidation (run-on, no dedup) and one degenerate\n  buried-fact output.\n- **gemma-3-1b** — best consolidation (dedup works, faithful, clean single-memory). Weaknesses: leaks\n  small talk and translated German.\n- **LFM2-1.2B** — solid and fastest to load. Weaknesses: `Label: value` noise, small-talk + buried\n  leaks, a fluffy single-memory summary.\n\n### Recommendation\n\nExtraction favors **precision** (do not pollute long-term memory) → **Qwen3-1.7B is the best single\npick** (its consolidation is good enough). If running a second model for consolidation, **gemma-3-1b**\nwins that task.\n\n**Shipped local options**: `qwen3-1.7b` (recommended), `gemma-3-1b`, `qwen2.5-1.5b`, `lfm2-1.2b`.\n**Default**: `online` (the configured smol model).\n\n### Known Mnemosyne parser bugs (surfaced by these experiments)\n\n- `String(item)` produces `[object Object]` on object array items.\n- The line-fallback drops items `<=10` chars, so a correct short fact like `Name: Can` is discarded.\n\n## Integration notes\n\n- Both settings default to `online`, so existing users get **no downloads or on-device inference cost**\n  unless they opt in.\n- Local inference runs **in a worker** (off the main thread); models are cached on disk and\n  downloaded on first use.\n- The memory local path applies the refined recipes (line-format + small-talk-guarded extraction\n  prompt, hardened consolidation prompt) via Mnemosyne prompt overrides; the **online path is\n  unchanged**.\n",
 	"lsp-config.md": "# LSP configuration in OMP\n\nThis guide explains how to configure language servers for the OMP coding agent.\n\nSource of truth in code:\n\n- Server config type: `packages/coding-agent/src/lsp/types.ts` (`ServerConfig`)\n- Config loader: `packages/coding-agent/src/lsp/config.ts`\n- Built-in server definitions: `packages/coding-agent/src/lsp/defaults.json`\n\n## Auto-detection\n\nWhen no LSP config file is present, OMP auto-detects servers by intersecting two conditions:\n\n1. The project directory contains at least one of the server's `rootMarkers`.\n2. The server binary is available — checked in project-local bin directories first (e.g., `node_modules/.bin/`, `.venv/bin/`), then `$PATH`.\n\nNo configuration is required for common setups. The built-in server list covers most popular languages; see [`defaults.json`](../packages/coding-agent/src/lsp/defaults.json) for the full set.\n\n## Config file locations\n\nOMP merges LSP config from multiple files, lowest to highest priority:\n\n| Priority | Location |\n|----------|----------|\n| 5 (lowest) | `~/lsp.json`, `~/.lsp.json`, `~/lsp.yaml`, `~/.lsp.yaml` |\n| 4 | Plugin LSP configs (marketplace / `--plugin-dir` roots) |\n| 3 | `~/.omp/agent/lsp.json`, `~/.omp/agent/lsp.yaml`, `~/.claude/lsp.*` |\n| 2 | `<project>/.omp/lsp.json`, `<project>/.omp/lsp.yaml`, `<project>/.claude/lsp.*` |\n| 1 (highest) | `<project>/lsp.json`, `<project>/.lsp.json`, `<project>/lsp.yaml` |\n\nEach location accepts both `.json` and `.yaml` / `.yml` variants, as well as hidden-file versions (`.lsp.json`, `.lsp.yaml`). Files are merged in order: higher-priority files override lower-priority fields for the same server. Servers not mentioned in any override file remain at their built-in defaults.\n\n**Recommended locations:**\n\n- User-wide preferences → `~/.omp/agent/lsp.json`\n- Project-specific overrides → `<project>/.omp/lsp.json`\n\n> **Note:** The presence of any LSP config file disables auto-detection. When at least one file is found, OMP skips the binary-scan phase and loads all servers that have matching `rootMarkers`, an available binary, and are not explicitly `disabled`.\n\n## File shape\n\nBoth JSON and YAML are accepted. The top-level object can use either a `servers` wrapper key or a flat map directly:\n\n```json\n{\n  \"servers\": {\n    \"server-name\": { ... }\n  },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nor (flat, without the `servers` wrapper):\n\n```json\n{\n  \"server-name\": { ... },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nTop-level keys:\n\n- `servers` — map of server name to `ServerConfig` (optional wrapper; flat form is equivalent)\n- `idleTimeoutMs` — shut down idle language servers after this many milliseconds; disabled by default\n\n## ServerConfig fields\n\n| Field | Type | Required | Description |\n|-------|------|----------|-------------|\n| `command` | `string` | yes | Binary name (resolved via PATH/local bins) or absolute path |\n| `args` | `string[]` | no | Arguments passed to the binary |\n| `fileTypes` | `string[]` | yes | File extensions this server handles, e.g. `[\".ts\", \".tsx\"]` |\n| `rootMarkers` | `string[]` | yes | Files/dirs that indicate a project root; glob patterns (e.g. `*.cabal`) are supported |\n| `initOptions` | `object` | no | Sent as `initializationOptions` during LSP handshake |\n| `settings` | `object` | no | Workspace settings pushed via `workspace/didChangeConfiguration` |\n| `disabled` | `boolean` | no | Set to `true` to disable this server entirely |\n| `warmupTimeoutMs` | `number` | no | Startup timeout in ms for this server (overrides the global default) |\n| `isLinter` | `boolean` | no | Mark server as linter/formatter only; excluded from type-intelligence operations (hover, go-to-definition, etc.) |\n| `capabilities` | `object` | no | Opt-in server-specific features; see [Capabilities](#capabilities) |\n\n`resolvedCommand` is populated automatically at runtime — do not set it manually.\n\n### Capabilities\n\nThe `capabilities` object enables optional server-specific features that OMP supports on a per-server basis:\n\n```json\n{\n  \"capabilities\": {\n    \"flycheck\": true,\n    \"ssr\": true,\n    \"expandMacro\": true,\n    \"runnables\": true,\n    \"relatedTests\": true\n  }\n}\n```\n\nAll fields are boolean and optional. They are currently used by `rust-analyzer`.\n\n## Common recipes\n\n### Override a built-in server's settings\n\nPartial overrides are merged onto the built-in defaults. You only need to specify the fields you want to change.\n\n```json\n{\n  \"servers\": {\n    \"typescript-language-server\": {\n      \"args\": [\"--stdio\", \"--log-level\", \"4\"]\n    }\n  }\n}\n```\n\n```yaml\nservers:\n  gopls:\n    settings:\n      gopls:\n        gofumpt: false\n        staticcheck: false\n```\n\n### Disable a built-in server\n\n```json\n{\n  \"servers\": {\n    \"eslint\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\n### Register a custom server\n\nNew servers require `command`, `fileTypes`, and `rootMarkers`. All other fields are optional.\n\n```json\n{\n  \"servers\": {\n    \"my-lsp\": {\n      \"command\": \"my-lsp-server\",\n      \"args\": [\"--stdio\"],\n      \"fileTypes\": [\".xyz\"],\n      \"rootMarkers\": [\".xyz-project\", \".git\"]\n    }\n  }\n}\n```\n\n### Set a global idle timeout\n\nShut down language servers that have been inactive for more than five minutes:\n\n```json\n{\n  \"idleTimeoutMs\": 300000\n}\n```\n\n### Disable a server for one project, keep it globally\n\nPlace the override in `<project>/.omp/lsp.json`:\n\n```json\n{\n  \"servers\": {\n    \"pylsp\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\nThe user-level config in `~/.omp/agent/lsp.json` is unaffected; pylsp is only suppressed in this project.\n\n## Built-in server list\n\nThe following servers ship in `defaults.json` and are eligible for auto-detection:\n\n| Server key | Language(s) | Binary |\n|---|---|---|\n| `rust-analyzer` | Rust | `rust-analyzer` |\n| `clangd` | C, C++, ObjC | `clangd` |\n| `zls` | Zig | `zls` |\n| `gopls` | Go | `gopls` |\n| `typescript-language-server` | TypeScript, JavaScript | `typescript-language-server` |\n| `denols` | TypeScript, JavaScript (Deno) | `deno` |\n| `biome` | TS/JS/JSON (linter) | `biome` |\n| `eslint` | TS/JS/Vue/Svelte (linter) | `vscode-eslint-language-server` |\n| `vscode-html-language-server` | HTML | `vscode-html-language-server` |\n| `vscode-css-language-server` | CSS, SCSS, Less | `vscode-css-language-server` |\n| `vscode-json-language-server` | JSON | `vscode-json-language-server` |\n| `tailwindcss` | HTML, CSS, TS/JS | `tailwindcss-language-server` |\n| `svelte` | Svelte | `svelteserver` |\n| `vue-language-server` | Vue | `vue-language-server` |\n| `astro` | Astro | `astro-ls` |\n| `pyright` | Python | `pyright-langserver` |\n| `basedpyright` | Python | `basedpyright-langserver` |\n| `pylsp` | Python | `pylsp` |\n| `ruff` | Python (linter) | `ruff` |\n| `jdtls` | Java | `jdtls` |\n| `kotlin-lsp` | Kotlin | `kotlin-lsp` |\n| `metals` | Scala | `metals` |\n| `hls` | Haskell | `haskell-language-server-wrapper` |\n| `ocamllsp` | OCaml | `ocamllsp` |\n| `elixirls` | Elixir | `elixir-ls` |\n| `erlangls` | Erlang | `erlang_ls` |\n| `gleam` | Gleam | `gleam` |\n| `solargraph` | Ruby | `solargraph` |\n| `ruby-lsp` | Ruby | `ruby-lsp` |\n| `rubocop` | Ruby (linter) | `rubocop` |\n| `bashls` | Bash, Zsh | `bash-language-server` |\n| `lua-language-server` | Lua | `lua-language-server` |\n| `intelephense` | PHP | `intelephense` |\n| `phpactor` | PHP | `phpactor` |\n| `omnisharp` | C# | `omnisharp` |\n| `yamlls` | YAML | `yaml-language-server` |\n| `terraformls` | Terraform | `terraform-ls` |\n| `dockerls` | Dockerfile | `docker-langserver` |\n| `helm-ls` | Helm | `helm_ls` |\n| `nixd` | Nix | `nixd` |\n| `nil` | Nix | `nil` |\n| `ols` | Odin | `ols` |\n| `dartls` | Dart | `dart` |\n| `marksman` | Markdown | `marksman` |\n| `texlab` | LaTeX | `texlab` |\n| `graphql` | GraphQL | `graphql-lsp` |\n| `prismals` | Prisma | `prisma-language-server` |\n| `vimls` | Vim script | `vim-language-server` |\n| `emmet-language-server` | HTML, CSS, JSX | `emmet-language-server` |\n| `sourcekit-lsp` | Swift | `sourcekit-lsp` |\n| `swiftlint` | Swift (linter) | `swiftlint` |\n| `tlaplus` | TLA+ | `tlapm_lsp` |\n",
 	"marketplace.md": "# Marketplace plugin system\n\nThe marketplace system lets you discover, install, and manage plugins from Git-hosted catalogs. It is compatible with the Claude Code plugin registry format.\n\n## Quick start\n\n```\n/marketplace add anthropics/claude-plugins-official\n/marketplace install wordpress.com@claude-plugins-official\n```\n\nOr just type `/marketplace` with no arguments to open the interactive plugin browser.\n\n## Concepts\n\nA **marketplace** is a Git repository (or local directory) containing a catalog file at `.claude-plugin/marketplace.json`. The catalog lists available plugins with their sources, descriptions, and metadata.\n\nA **plugin** is a directory containing skills, commands, hooks, MCP servers, or LSP servers. Plugins are identified by `name@marketplace` (e.g. `code-review@claude-plugins-official`).\n\n**Scopes**: plugins can be installed at two scopes:\n\n- **user** (default) -- available in all projects, stored in `~/.omp/plugins/installed_plugins.json`\n- **project** -- available only in the current project, stored in `.omp/plugins/installed_plugins.json`\n\nProject-scoped installs shadow user-scoped installs of the same plugin.\n\n## Commands\n\n### Interactive mode\n\n| Command        | Effect                                    |\n| -------------- | ----------------------------------------- |\n| `/marketplace` | Open interactive plugin browser (install) |\n\n### Marketplace management\n\n| Command                      | Effect                                       |\n| ---------------------------- | -------------------------------------------- |\n| `/marketplace add <source>`  | Add a marketplace source                     |\n| `/marketplace remove <name>` | Remove a marketplace                         |\n| `/marketplace update [name]` | Re-fetch catalog(s); omit name to update all |\n| `/marketplace list`          | List configured marketplaces                 |\n\n### Plugin operations\n\n| Command                                                                   | Effect                             |\n| ------------------------------------------------------------------------- | ---------------------------------- |\n| `/marketplace discover [marketplace]`                                     | Browse available plugins           |\n| `/marketplace install [--force] [--scope user\\|project] name@marketplace` | Install a plugin                   |\n| `/marketplace uninstall [--scope user\\|project] name@marketplace`         | Uninstall a plugin                 |\n| `/marketplace installed`                                                  | List installed marketplace plugins |\n| `/marketplace upgrade [--scope user\\|project] [name@marketplace]`         | Upgrade one or all plugins         |\n\n### CLI equivalents\n\nThe same operations are available from the command line:\n\n```\nomp plugin marketplace add <source>\nomp plugin marketplace remove <name>\nomp plugin marketplace update [name]\nomp plugin marketplace list\nomp plugin discover [marketplace]\nomp plugin install [--force] [--scope user|project] name@marketplace\nomp plugin uninstall [--scope user|project] name@marketplace\nomp plugin upgrade [--scope user|project] [name@marketplace]\n```\n\n## Marketplace sources\n\nWhen you run `/marketplace add <source>`, the system classifies the source:\n\n| Source format                   | Type               | Example                                |\n| ------------------------------- | ------------------ | -------------------------------------- |\n| `owner/repo`                    | GitHub shorthand   | `anthropics/claude-plugins-official`   |\n| `https://...*.json`             | Direct catalog URL | `https://example.com/marketplace.json` |\n| `https://...*.git` or `git@...` | Git repository     | `https://github.com/org/repo.git`      |\n| `./path` or `~/path` or `/path` | Local directory    | `./my-marketplace`                     |\n\nThe system clones the repository (or reads the local directory), locates `.claude-plugin/marketplace.json`, validates it, and caches the catalog locally.\n\n## Catalog format (marketplace.json)\n\nA marketplace catalog lives at `.claude-plugin/marketplace.json` in the repository root:\n\n```json\n{\n  \"$schema\": \"https://anthropic.com/claude-code/marketplace.schema.json\",\n  \"name\": \"my-marketplace\",\n  \"owner\": {\n    \"name\": \"Your Name\",\n    \"email\": \"you@example.com\"\n  },\n  \"description\": \"A collection of plugins\",\n  \"plugins\": [\n    {\n      \"name\": \"my-plugin\",\n      \"description\": \"What this plugin does\",\n      \"source\": \"./plugins/my-plugin\",\n      \"category\": \"development\",\n      \"homepage\": \"https://github.com/you/my-plugin\"\n    }\n  ]\n}\n```\n\n### Required fields\n\n| Field        | Description                                                                                                      |\n| ------------ | ---------------------------------------------------------------------------------------------------------------- |\n| `name`       | Marketplace name. Lowercase alphanumeric, hyphens, and dots. Must start and end with alphanumeric. Max 64 chars. |\n| `owner.name` | Marketplace owner name                                                                                           |\n| `plugins`    | Array of plugin entries                                                                                          |\n\n### Plugin entry fields\n\n| Field         | Required | Description                                                      |\n| ------------- | -------- | ---------------------------------------------------------------- |\n| `name`        | yes      | Plugin name (same rules as marketplace name)                     |\n| `source`      | yes      | Where to find the plugin (see below)                             |\n| `description` | no       | Short description                                                |\n| `version`     | no       | Version string                                                   |\n| `author`      | no       | `{ name, email? }`                                               |\n| `homepage`    | no       | URL                                                              |\n| `category`    | no       | Category string (e.g. `development`, `productivity`, `security`) |\n| `tags`        | no       | Array of string tags                                             |\n| `strict`      | no       | Boolean                                                          |\n| `commands`    | no       | Slash commands provided                                          |\n| `agents`      | no       | Agents provided                                                  |\n| `hooks`       | no       | Hook definitions                                                 |\n| `mcpServers`  | no       | MCP server definitions                                           |\n| `lspServers`  | no       | LSP server definitions                                           |\n\n### Plugin source formats\n\nThe `source` field supports several formats:\n\n**Relative path** (within the marketplace repo):\n\n```json\n\"source\": \"./plugins/my-plugin\"\n```\n\n**Git repository URL**:\n\n```json\n\"source\": {\n  \"source\": \"url\",\n  \"url\": \"https://github.com/org/repo.git\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**GitHub shorthand**:\n\n```json\n\"source\": {\n  \"source\": \"github\",\n  \"repo\": \"org/repo\",\n  \"ref\": \"main\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**Git subdirectory** (monorepo):\n\n```json\n\"source\": {\n  \"source\": \"git-subdir\",\n  \"url\": \"https://github.com/org/monorepo.git\",\n  \"path\": \"plugins/my-plugin\",\n  \"ref\": \"main\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**npm package**:\n\n```json\n\"source\": {\n  \"source\": \"npm\",\n  \"package\": \"@scope/my-plugin\",\n  \"version\": \"1.0.0\"\n}\n```\n\n## On-disk layout\n\n```\n~/.omp/\n  marketplaces.json              # Registry of added marketplaces\n  plugins/\n    installed_plugins.json       # User-scoped installed plugins\n    cache/\n      marketplaces/              # Cached marketplace catalogs\n      plugins/                   # Cached plugin directories\n\n<project>/.omp/\n  plugins/\n    installed_plugins.json       # Project-scoped installed plugins\n```\n\n## Naming rules\n\nMarketplace and plugin names must:\n\n- Start and end with a lowercase letter or digit\n- Contain only lowercase letters, digits, hyphens, and dots\n- Be at most 64 characters\n\nPlugin IDs (`name@marketplace`) must be at most 128 characters total.\n\nValid examples: `my-plugin`, `code-review`, `wordpress.com`, `ai-firstify`\nInvalid examples: `-bad`, `bad-`, `.bad`, `Bad`, `under_score`\n",
 	"mcp-config.md": "# MCP configuration in OMP\n\nThis guide explains how to add, edit, and validate MCP servers for the OMP coding agent.\n\nSource of truth in code:\n\n- Runtime config types: `packages/coding-agent/src/mcp/types.ts`\n- Config writer: `packages/coding-agent/src/mcp/config-writer.ts`\n- Loader + validation: `packages/coding-agent/src/mcp/config.ts`\n- Standalone `mcp.json` discovery: `packages/coding-agent/src/discovery/mcp-json.ts`\n- Schema: `packages/coding-agent/src/config/mcp-schema.json`\n\n## Preferred config locations\n\nOMP can discover MCP servers from multiple tools (`.claude/`, `.cursor/`, `.vscode/`, `opencode.json`, and more), but for OMP-native configuration you should usually use one of these files:\n\n- Project: `.omp/mcp.json`\n- User: `~/.omp/agent/mcp.json`\n\nOMP also accepts fallback standalone files in the project root:\n\n- `mcp.json`\n- `.mcp.json`\n\nUse `.omp/mcp.json` or `~/.omp/agent/mcp.json` when you want OMP to own the configuration. Use root `mcp.json` / `.mcp.json` only when you want a portable fallback file that other MCP clients may also read.\n\n## Add a schema reference\n\nAdd this line at the top of the file for editor autocomplete and validation:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {}\n}\n```\n\nOMP now writes this automatically when `/mcp add`, `/mcp enable`, `/mcp disable`, `/mcp reauth`, or other config-writing flows create or update an OMP-managed MCP file.\n\n## File shape\n\nOMP supports this top-level structure:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"server-name\": {\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"some-mcp-server\"]\n    }\n  },\n  \"disabledServers\": [\"server-name\"]\n}\n```\n\nTop-level keys:\n\n- `$schema` — optional JSON Schema URL for tooling\n- `mcpServers` — map of server name to server config\n- `disabledServers` — user-level denylist used to turn off discovered servers by name; runtime loading reads this list from `~/.omp/agent/mcp.json`\n\nServer names must match `^[a-zA-Z0-9_.-]{1,100}$`.\n\n## Supported server fields\n\nShared fields for every transport:\n\n- `enabled?: boolean` — skip this server when `false`\n- `timeout?: number` — MCP request timeout in milliseconds; `0` disables client-side MCP timeouts\n- `auth?: { ... }` — auth metadata used by OMP for OAuth/API-key flows\n- `oauth?: { ... }` — explicit OAuth client settings used during auth/reauth\n\nSet `OMP_MCP_TIMEOUT_MS=0` to disable the client-side timeout for every MCP server in the current process. Set it to a positive millisecond value, such as `OMP_MCP_TIMEOUT_MS=120000`, to apply one global timeout without editing each server entry.\n\n### `stdio` transport\n\n`stdio` is the default when `type` is omitted.\n\nRequired:\n\n- `command: string`\n\nOptional:\n\n- `type?: \"stdio\"`\n- `args?: string[]`\n- `env?: Record<string, string>`\n- `cwd?: string`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol/server-filesystem\",\n        \"/Users/alice/projects\",\n        \"/Users/alice/Documents\"\n      ]\n    }\n  }\n}\n```\n\nThis follows the official Filesystem MCP server package (`@modelcontextprotocol/server-filesystem`).\n\n### `http` transport\n\nRequired:\n\n- `type: \"http\"`\n- `url: string`\n\nOptional:\n\n- `headers?: Record<string, string>`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\"\n    }\n  }\n}\n```\n\nThis matches GitHub's hosted GitHub MCP server endpoint.\n\n### `sse` transport\n\nRequired:\n\n- `type: \"sse\"`\n- `url: string`\n\nOptional:\n\n- `headers?: Record<string, string>`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"legacy-remote\": {\n      \"type\": \"sse\",\n      \"url\": \"https://example.com/mcp/sse\"\n    }\n  }\n}\n```\n\n`sse` is still supported for compatibility, but the MCP spec now prefers Streamable HTTP (`type: \"http\"`) for new servers.\n\n## Auth fields\n\nOMP understands two auth-related objects.\n\n### `auth`\n\n```json\n{\n  \"type\": \"oauth\" | \"apikey\",\n  \"credentialId\": \"optional-stored-credential-id\",\n  \"tokenUrl\": \"optional-token-endpoint\",\n  \"clientId\": \"optional-client-id\",\n  \"clientSecret\": \"optional-client-secret\"\n}\n```\n\nUse this when OMP should remember how to rehydrate credentials for a server.\n\n### `oauth`\n\n```json\n{\n  \"clientId\": \"...\",\n  \"clientSecret\": \"...\",\n  \"redirectUri\": \"...\",\n  \"callbackPort\": 3334,\n  \"callbackPath\": \"/oauth/callback\"\n}\n```\n\nUse this when the MCP server requires explicit OAuth client settings.\n\nSlack is the clearest current example. Slack's MCP server is hosted at `https://mcp.slack.com/mcp`, uses Streamable HTTP, and requires confidential OAuth with your Slack app's client credentials.\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"slack\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.slack.com/mcp\",\n      \"oauth\": {\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      },\n      \"auth\": {\n        \"type\": \"oauth\",\n        \"tokenUrl\": \"https://slack.com/api/oauth.v2.user.access\",\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      }\n    }\n  }\n}\n```\n\nRelevant Slack endpoints from Slack's docs:\n\n- MCP endpoint: `https://mcp.slack.com/mcp`\n- Authorization endpoint: `https://slack.com/oauth/v2_user/authorize`\n- Token endpoint: `https://slack.com/api/oauth.v2.user.access`\n\n## Common copy-paste examples\n\n### Filesystem server via stdio\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol/server-filesystem\",\n        \"/absolute/path/one\",\n        \"/absolute/path/two\"\n      ]\n    }\n  }\n}\n```\n\n### GitHub hosted server via HTTP\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\"\n    }\n  }\n}\n```\n\n### GitHub local server via Docker\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"docker\",\n      \"args\": [\n        \"run\",\n        \"-i\",\n        \"--rm\",\n        \"-e\",\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\",\n        \"ghcr.io/github/github-mcp-server\"\n      ],\n      \"env\": {\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"\n      }\n    }\n  }\n}\n```\n\nThis matches GitHub's official local Docker image `ghcr.io/github/github-mcp-server`.\n\n### Slack hosted server via OAuth\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"slack\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.slack.com/mcp\",\n      \"oauth\": {\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      },\n      \"auth\": {\n        \"type\": \"oauth\",\n        \"tokenUrl\": \"https://slack.com/api/oauth.v2.user.access\",\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      }\n    }\n  }\n}\n```\n\n## Secrets and variable resolution\n\nThis is the part that usually trips people up.\n\n### In `.omp/mcp.json` and `~/.omp/agent/mcp.json`\n\nBefore OMP launches a stdio server or makes an HTTP/SSE request, it resolves stdio `env` values and HTTP/SSE `headers` values like this:\n\n1. If a value starts with `!`, OMP runs the rest as a shell command with a 10s timeout and uses trimmed stdout.\n2. If the command fails, times out, or prints only whitespace, that `env`/`headers` entry is omitted.\n3. Otherwise OMP checks whether the value names an environment variable.\n4. If that environment variable is set to a non-empty value, OMP uses the environment value; otherwise it uses the string literally.\n\nExamples:\n\n```json\n{\n  \"env\": {\n    \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"\n  },\n  \"headers\": {\n    \"X-MCP-Insiders\": \"true\"\n  }\n}\n```\n\nThat means this is valid and convenient for local secrets:\n\n- `\"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"` → copy from the current shell environment\n- `\"Authorization\": \"Bearer hardcoded-token\"` → use the literal value\n- `\"Authorization\": \"!printf 'Bearer %s' \\\"$GITHUB_TOKEN\\\"\"` → build the header from a command\n\n### In root `mcp.json` and `.mcp.json`\n\nThe standalone fallback loader also expands `${VAR}` and `${VAR:-default}` inside strings during discovery for `command`, `args`, `env`, `cwd`, `url`, `headers`, `auth`, and `oauth`.\n\nExample:\n\n```json\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\",\n      \"headers\": {\n        \"Authorization\": \"Bearer ${GITHUB_TOKEN}\"\n      }\n    }\n  }\n}\n```\n\nIf you want the least surprising OMP behavior, prefer `.omp/mcp.json` or `~/.omp/agent/mcp.json` and use explicit env/header values.\n\n## `disabledServers`\n\n`disabledServers` is read from the user config file (`~/.omp/agent/mcp.json`) when a server is discovered from any source and you want OMP to ignore it without editing that other tool's config.\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"disabledServers\": [\"github\", \"slack\"]\n}\n```\n\n## `/mcp add` vs editing JSON directly\n\nUse `/mcp add` when you want guided setup.\n\nUse direct JSON editing when:\n\n- you need a transport or auth option the wizard does not prompt for yet\n- you want to paste a server definition from another MCP client\n- you want schema-backed validation in your editor\n\nAfter editing, use:\n\n- `/mcp reload` to rediscover and reconnect servers in the current session\n- `/mcp list` to see which config file a server came from\n- `/mcp test <name>` to test a single server\n- `/mcp reconnect <name>` to reconnect one server without rediscovering all configs\n- `/mcp resources`, `/mcp prompts`, and `/mcp notifications` to inspect non-tool MCP capabilities\n\n## Validation rules OMP enforces\n\nFrom `validateServerConfig()` in `packages/coding-agent/src/mcp/config.ts`:\n\n- `stdio` requires `command`\n- `http` and `sse` require `url`\n- a server cannot set both `command` and `url`\n- unknown `type` values are rejected\n\nPractical implications:\n\n- Omitting `type` means `stdio`\n- If you paste a remote server config and forget `\"type\": \"http\"`, OMP will treat it as `stdio` and complain that `command` is missing\n- `sse` remains valid for compatibility, but new hosted servers should usually be configured as `http`\n\n## Discovery and precedence\n\nOMP does not merge duplicate server definitions across files. Discovery providers are prioritized, and the higher-priority definition wins. Separately, `disabledServers` from `~/.omp/agent/mcp.json` can suppress a discovered server by name.\n\nIn practice:\n\n- prefer `.omp/mcp.json` or `~/.omp/agent/mcp.json` when you want an OMP-specific override\n- keep server names unique across tools when possible\n- use `disabledServers` in the user config when a third-party config keeps reintroducing a server you do not want\n\n## Troubleshooting\n\n### `Server \"name\": stdio server requires \"command\" field`\n\nYou probably omitted `type: \"http\"` on a remote server.\n\n### `Server \"name\": both \"command\" and \"url\" are set`\n\nPick one transport. OMP treats `command` as stdio and `url` as http/sse.\n\n### `/mcp add` worked but the server still does not connect\n\nThe JSON is valid, but the server may still be unreachable. Use `/mcp test <name>` and check whether:\n\n- the binary or Docker image exists\n- required environment variables are set\n- the remote URL is reachable\n- the OAuth or API token is valid\n\n### The server exists in another tool's config but not in OMP\n\nRun `/mcp list`. OMP discovers many third-party MCP files, but project-level loading can also be disabled via the `mcp.enableProjectConfig` setting, and a user-level `disabledServers` entry can suppress a server by name.\n\n## References\n\n- MCP transport spec: https://modelcontextprotocol.io/specification/2025-03-26/basic/transports\n- Filesystem server package: https://www.npmjs.com/package/@modelcontextprotocol/server-filesystem\n- GitHub MCP server: https://github.com/github/github-mcp-server\n- Slack MCP server docs: https://docs.slack.dev/ai/slack-mcp-server/\n",
@@ -31,8 +31,8 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"memory.md": "# Autonomous Memory\n\nWhen enabled, the agent automatically extracts durable knowledge from past sessions and injects a compact summary into each new session. 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 via `/settings` or `config.yml`:\n\n```yaml\nmemories:\n  enabled: true\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 memory injection payload      |\n| `clear` / `reset`     | Delete all memory data and generated artifacts |\n| `enqueue` / `rebuild` | Force consolidation to run at next startup     |\n\n## How it works\n\nMemories are built by a background pipeline that runs at startup or when manually triggered via slash command.\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, or currently active 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 to prevent double-running when multiple processes start simultaneously. Stale skill directories from prior runs are pruned automatically.\n\nAll output is scanned for secrets before being 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| `memories.enabled`                    | `false` | Master switch                                             |\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": "# Mnemosyne memory backend\n\nOh My Pi can use `@oh-my-pi/pi-mnemosyne` as a local long-term memory backend.\n\nSet:\n\n```yaml\nmemory:\n  backend: mnemosyne\n```\n\nExample:\n\n```yaml\nmemory:\n  backend: mnemosyne\nmnemosyne:\n  scoping: per-project-tagged\n```\n\nWith this backend enabled, the coding agent:\n\n1. Opens a local Mnemosyne SQLite database.\n2. Recalls relevant memories into a `<memories>` block before the first model turn.\n3. Retains completed conversation turns into the same bank after agent turns.\n4. Uses the normal `/memory view`, `/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 `mnemosyne` to enable this backend. |\n| `mnemosyne.dbPath` | agent memories dir | Optional SQLite database path. |\n| `mnemosyne.bank` | project directory name | Base bank name passed to `Mnemosyne`; the coding-agent wrapper scopes from this base according to `mnemosyne.scoping`. |\n| `mnemosyne.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| `mnemosyne.autoRecall` | `true` | Recall memory on the first turn of a session. |\n| `mnemosyne.autoRetain` | `true` | Retain completed turns automatically. |\n| `mnemosyne.retainEveryNTurns` | `4` | Minimum user turns between automatic retain writes. |\n| `mnemosyne.recallLimit` | `8` | Maximum recalled memories in the prompt block. |\n| `mnemosyne.recallContextTurns` | `3` | Prior user-bounded turns included in recall queries. |\n| `mnemosyne.recallMaxQueryChars` | `4000` | Maximum composed recall query length. |\n| `mnemosyne.injectionTokenLimit` | `5000` | Approximate token budget for memory prompt injection. |\n| `mnemosyne.debug` | `false` | Enable debug logging for backend failures. |\n| `mnemosyne.noEmbeddings` | `false` | Pass `noEmbeddings` to `Mnemosyne` and force FTS-only recall. |\n| `mnemosyne.embeddingModel` | env/default | Embedding model passed to `Mnemosyne`. |\n| `mnemosyne.embeddingApiUrl` | env/default | OpenAI-compatible embedding endpoint passed to `Mnemosyne`. |\n| `mnemosyne.embeddingApiKey` | env/default | Embedding API key passed to `Mnemosyne`. |\n| `mnemosyne.llmMode` | `smol` | `smol` uses the configured pi-ai smol model, `remote` uses the settings below, and `none` disables LLM calls. |\n| `mnemosyne.llmBaseUrl` | env/default | OpenAI-compatible LLM endpoint for `llmMode: remote`. |\n| `mnemosyne.llmApiKey` | env/default | LLM API key for `llmMode: remote`. |\n| `mnemosyne.llmModel` | env/default | LLM model id for `llmMode: remote`. |\n\n## Scoping\n\nThe coding-agent wrapper applies scoping on top of the underlying `Mnemosyne` package:\n\n- `global` uses one shared bank for every project.\n- `per-project` uses a separate bank per project.\n- `per-project-tagged` keeps writes project-local while recall can also read from shared global memory.\n\nThe combined project-plus-global behavior lives in the wrapper. The `@oh-my-pi/pi-mnemosyne` package itself still exposes banks and constructor options directly, including `bank` for selecting a bank name.\n## LLM and embeddings\n\nThe backend passes these settings to the `Mnemosyne` constructor; if a setting is omitted, Mnemosyne falls back to its `MNEMOSYNE_*` 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: mnemosyne\nmnemosyne:\n  noEmbeddings: true\n```\n\nEquivalent constructor shape:\n\n```ts\nnew Mnemosyne({ noEmbeddings: true });\n```\n\nRemote embeddings:\n\n```yaml\nmnemosyne:\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 Mnemosyne({\n  embeddingModel: \"text-embedding-3-small\",\n  embeddingApiUrl: \"https://api.openai.com/v1\",\n  embeddingApiKey,\n});\n```\n\nRemote LLM:\n\n```yaml\nmnemosyne:\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 Mnemosyne({ llm: { baseUrl, apiKey, model } });\nnew Mnemosyne({ llmBaseUrl: baseUrl, llmApiKey: apiKey, llmModel: model });\n```\n\nDynamic function LLM for rotating OAuth tokens:\n\n```ts\nnew Mnemosyne({\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\nmnemosyne:\n  llmMode: smol\n```\n\nThe coding agent resolves its configured smol role and passes a dynamic completion function so every Mnemosyne LLM call can fetch the current provider credentials at call time:\n\n```ts\nnew Mnemosyne({\n  llm: async (prompt, opts) => completeSmolWithCurrentAuth(prompt, opts),\n});\n```\n\n## Operational notes\n\n- The default database lives under the agent memories directory in `mnemosyne/mnemosyne.db`.\n- `/memory clear` removes the active Mnemosyne SQLite database and sidecar WAL/SHM files.\n- `/memory enqueue` forces retention of the current session and runs Mnemosyne sleep/consolidation.\n- Subagents do not auto-retain separate transcript windows; parent sessions own durable retention.\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\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- `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`, `input`, `cost`, `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 Spark -> non-Spark on the same provider:\n\n```yaml\nproviders:\n  openai-codex:\n    modelOverrides:\n      gpt-5.3-codex-spark:\n        contextPromotionTarget: openai-codex/gpt-5.3-codex\n```\n\nThe built-in model generator also assigns this automatically for `*-spark` models when a same-provider base model exists.\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/model-registry.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- `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- `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- `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`) 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## 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 the authoritative compiled-binary signal when present.\n- Optionally materialize an embedded addon into a versioned per-user cache directory.\n- Attempt candidates in deterministic order and return the first addon that `require(...)` loads.\n\nThe current loader does **not** run a separate `validateNative(...)` export-presence gate. API shape is provided by the generated N-API binding file (`native/index.d.ts`) and the loaded addon itself. A stale binary therefore normally fails as a missing property or native load error rather than as a custom \"missing exports\" validation error.\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  - `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- **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:\n\n1. `<nativeDir>/<filename>`\n2. `<execDir>/<filename>`\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, when produced, 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- `files[]` entries with `variant`, `filename`, and `filePath`\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. Reuse `<versionedDir>/<selected filename>` if it already exists.\n3. Otherwise read `selectedEmbeddedFile.filePath` and write the target path.\n4. Return the target path as the first candidate.\n\nDirectory creation 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 -> try extract to versionedDir (record errors, continue)\n       no  -> skip extraction\n  -> For each runtime candidate in order:\n       require(candidate)\n       -> success: 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(...)` 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\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 now a two-layer package around a loader:\n\n1. **CommonJS loader/package entrypoint** resolves and loads the correct `.node` addon and patches generated enum objects onto the export object.\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 directly at generated native bindings:\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 enum exports appended 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`, text width/slicing/wrapping/sanitization, syntax highlighting, token counting.\n- **Execution/process/terminal primitives**: `executeShell`, `Shell`, `PtySession`, process-tree helpers, key parsing.\n- **System/media/conversion primitives**: clipboard, image resize/encode/SIXEL, HTML-to-Markdown, macOS appearance/power helpers, work profiling, Windows ProjFS overlay helpers.\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}-${process.arch}`.\n- Supported tags are currently:\n  - `linux-x64`\n  - `linux-arm64`\n  - `darwin-x64`\n  - `darwin-arm64`\n  - `win32-x64`\n- x64 can use CPU variants:\n  - `modern` (AVX2-capable)\n  - `baseline` (fallback)\n- Non-x64 uses the default filename without a variant suffix.\n\nFilename strategy:\n\n- Default: `pi_natives.<platform>-<arch>.node`\n- x64 variant: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- x64 runtime fallback includes the unsuffixed default filename after variant candidates.\n\n### Platform-specific variant detection\n\nFor x64, variant selection uses:\n\n- Linux: `/proc/cpuinfo`\n- macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`\n- Windows: PowerShell check for `System.Runtime.Intrinsics.X86.Avx2`\n\n`PI_NATIVE_VARIANT` can force `modern` or `baseline`; invalid values are ignored.\n\n### Binary distribution and extraction model\n\n`packages/natives/package.json` publishes `native/`, which contains the loader, generated declarations, generated enum patch, embedded-addon manifest stub, and prebuilt `.node` artifacts.\n\nFor compiled binaries, loader behavior is:\n\n1. Check versioned user cache path: `<getNativesDir()>/<packageVersion>/...`.\n2. Check legacy compiled-binary location:\n   - Windows: `%LOCALAPPDATA%/omp` (fallback `%USERPROFILE%/AppData/Local/omp`)\n   - non-Windows: `~/.local/bin`\n3. Fall back to packaged `native/` and executable directory candidates.\n\n`getNativesDir()` uses `$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. The loader can extract the matching embedded `.node` into the versioned cache directory before candidate probing.\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 extraction errors**: directory/write failures are recorded and included in final load diagnostics if no candidate loads.\n\nThe current loader does not perform a separate post-`require` export validation pass.\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- `clipboard`\n- `fd`\n- `fs_cache`\n- `glob`\n- `glob_util`\n- `grep`\n- `highlight`\n- `html`\n- `image`\n- `keys`\n- `language`\n- `power`\n- `prof`\n- `projfs_overlay`\n- `ps`\n- `pty`\n- `shell`\n- `task`\n- `text`\n- `tokens`\n- `utils` (crate-private helpers)\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 extraction\n  - generated TypeScript declarations and enum export 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 binary extraction occurs for compiled distributions.\n4. The first `require(candidate)` that succeeds becomes the exported addon object.\n5. Generated enum objects are appended to `module.exports`.\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- **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- **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 file references generated into `native/embedded-addon.js` so compiled binaries can extract matching `.node` payloads.\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 the authoritative compiled-binary signal when present.\n- Optionally materialize an embedded addon into a versioned per-user cache directory.\n- Attempt candidates in deterministic order and return the first addon that `require(...)` loads.\n\nThe current loader does **not** run a separate `validateNative(...)` export-presence gate. API shape is provided by the generated N-API binding file (`native/index.d.ts`) and the loaded addon itself. A stale binary therefore normally fails as a missing property or native load error rather than as a custom \"missing exports\" validation error.\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- **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.\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, when produced, 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- `files[]` entries with `variant`, `filename`, and `filePath`\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. Reuse `<versionedDir>/<selected filename>` if it already exists.\n3. Otherwise read `selectedEmbeddedFile.filePath` and write the target path.\n4. Return the target path as the first candidate.\n\nDirectory creation 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 -> try extract to versionedDir (record errors, continue)\n       no  -> skip extraction\n  -> For each runtime candidate in order:\n       require(candidate)\n       -> success: 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(...)` 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\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 now a two-layer package around a loader:\n\n1. **CommonJS loader/package entrypoint** resolves and loads the correct `.node` addon and patches generated enum objects onto the export object.\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 directly at generated native bindings:\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 enum exports appended 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`, text width/slicing/wrapping/sanitization, syntax highlighting, token counting.\n- **Execution/process/terminal primitives**: `executeShell`, `Shell`, `PtySession`, process-tree helpers, key parsing.\n- **System/media/conversion primitives**: clipboard, image resize/encode/SIXEL, HTML-to-Markdown, macOS appearance/power helpers, work profiling, Windows ProjFS overlay helpers.\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 CommonJS 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. 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. The loader can extract the matching embedded `.node` into the versioned cache directory before 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).\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 extraction errors**: directory/write failures are recorded and included in final load diagnostics if no candidate loads.\n\nThe current loader does not perform a separate post-`require` export validation pass.\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- `clipboard`\n- `fd`\n- `fs_cache`\n- `glob`\n- `glob_util`\n- `grep`\n- `highlight`\n- `html`\n- `image`\n- `keys`\n- `language`\n- `power`\n- `prof`\n- `projfs_overlay`\n- `ps`\n- `pty`\n- `shell`\n- `task`\n- `text`\n- `tokens`\n- `utils` (crate-private helpers)\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 extraction\n  - generated TypeScript declarations and enum export 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 binary extraction occurs for compiled distributions.\n4. The first `require(candidate)` that succeeds becomes the exported addon object.\n5. Generated enum objects are appended to `module.exports`.\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- **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 file references 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 CommonJS loader 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. **Generated runtime loader** (`native/index.js`)\n   - computes candidates and `require(...)`s the `.node` addon;\n   - exports the loaded addon object directly;\n   - appends enum 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 `validateNative(...)` required-export list in the loader.\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              | `glob(options, onMatch?)`                                                                                  | `glob.rs`                                                   | `Promise<GlobResult>`         |\n| Glob cache        | `invalidateFsScanCache(path?)`                                                                             | `fs_cache.rs`                                               | `void`                        |\n| AST search/edit   | `astGrep(options)`, `astEdit(options)`                                                                     | `ast.rs`                                                    | `Promise<...>`                |\n| Shell             | `executeShell(options, onChunk?)`                                                                          | `shell.rs`                                                  | `Promise<ShellExecuteResult>` |\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           | `killTree(pid, signal)`, `listDescendants(pid)`                                                            | `ps.rs`                                                     | sync                          |\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| Image             | `PhotonImage`, `encodeSixel`                                                                               | `image.rs`                                                  | class / sync / promises       |\n| Clipboard         | `copyToClipboard`, `readImageFromClipboard`                                                                | `clipboard.rs`                                              | sync / promise                |\n| Tokens            | `countTokens(input, encoding?)`                                                                            | `tokens.rs`                                                 | sync                          |\n| System            | `detectMacOSAppearance`, `MacAppearanceObserver`, `MacOSPowerAssertion`, `getWorkProfile`, ProjFS helpers  | `appearance.rs`, `power.rs`, `prof.rs`, `projfs_overlay.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, image parse/resize/encode, clipboard image read).\n- **Synchronous exports** for deterministic in-memory transforms/parsers or direct system calls (`search`, `hasMatch`, highlighting, text utilities, token counting, process queries, `copyToClipboard`, `encodeSixel`).\n- **Constructor exports** for stateful runtime objects (`Shell`, `PtySession`, `PhotonImage`, 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`\n- `System`/media payloads such as `ClipboardImage`, `WorkProfile`, `ParsedKittyResult`\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 appended to `module.exports` by `scripts/gen-enums.ts`, because the loader is hand-maintained CommonJS around the generated addon. Current enum objects include:\n\n- `AstMatchStrictness`\n- `Ellipsis`\n- `Encoding`\n- `FileType`\n- `GrepOutputMode`\n- `ImageFormat`\n- `KeyEventType`\n- `MacOSAppearance`\n- `SamplingFilter`\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 does not verify the full export set after `require(...)`; stale or mismatched 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",
 	"natives-build-release-debugging.md": "# Natives Build, Release, and Debugging Runbook\n\nThis runbook describes how `@oh-my-pi/pi-natives` produces `.node` addons, generated declarations, and compiled-binary embedded payloads, and how to debug loader/build failures.\n\nIt follows the architecture terms from `docs/natives-architecture.md`:\n\n- **build-time artifact production** (`scripts/build-native.ts`)\n- **embedded addon manifest generation** (`scripts/embed-native.ts`)\n- **runtime addon loading** (`native/index.js`, `native/loader-state.js`)\n\n## Implementation files\n\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- `packages/natives/native/index.js`\n- `packages/natives/native/loader-state.js`\n- `crates/pi-natives/Cargo.toml`\n\n## Build pipeline overview\n\n### 1) Build entrypoints\n\n`packages/natives/package.json` scripts:\n\n- `bun scripts/build-native.ts` (`build`) → N-API build, addon install, generated declarations install, enum export patch.\n- `bun scripts/embed-native.ts` (`embed:native`) → generate `native/embedded-addon.js` from built files.\n\nRoot scripts include `build:native` as `bun --cwd=packages/natives run build`.\n\n### 2) N-API/Rust artifact build\n\n`build-native.ts` invokes the `@napi-rs/cli` binary directly from `node_modules/.bin` with:\n\n- `napi build`\n- `--manifest-path crates/pi-natives/Cargo.toml`\n- `--package-json-path packages/natives/package.json`\n- `--platform`\n- `--no-js`\n- `--dts index.d.ts`\n- `--profile local` for non-CI local native builds, otherwise `--profile ci`\n- optional `--target <CROSS_TARGET>`\n\n`crates/pi-natives/Cargo.toml` declares `crate-type = [\"cdylib\"]`; napi-rs emits `.node` artifacts plus generated `index.d.ts` in an isolated temporary output directory under `packages/natives/native/.build/`.\n\n### 3) Artifact install\n\nAfter napi-rs succeeds, `build-native.ts`:\n\n1. resolves the built addon in the isolated output directory;\n2. normalizes its name to `pi_natives.<platform>-<arch>(-variant).node` when needed;\n3. installs the addon into `packages/natives/native/` with temp-file + rename semantics;\n4. copies generated `index.js` and `index.d.ts` into `packages/natives/native/` when present;\n5. runs `generateEnumExports()` to append enum runtime objects to `native/index.js`.\n\nWindows locked-DLL replacement failures are reported with an explicit close-running-processes hint.\n\n## Target/variant model and naming conventions\n\n## Platform tag\n\nBoth build and runtime use platform tag:\n\n`<platform>-<arch>` (example: `darwin-arm64`, `linux-x64`).\n\n## Variant model (x64 only)\n\nx64 supports CPU variants:\n\n- `modern` (AVX2-capable path)\n- `baseline` (fallback)\n\nNon-x64 uses a single default artifact with no variant suffix.\n\n### Output filenames\n\n- x64: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- non-x64: `pi_natives.<platform>-<arch>.node`\n\nRuntime x64 candidate order also includes the unsuffixed default filename after the selected variant candidates.\n\n## Environment flags and build options\n\n## Runtime flags\n\n- `PI_NATIVE_VARIANT`: x64 runtime override; valid values are `modern` and `baseline`.\n- `PI_COMPILED`: legacy compiled-mode signal. A populated embedded-addon manifest is also a compiled-mode signal and is the authoritative signal for Bun standalone builds that do not preserve `process.env.PI_COMPILED`.\n\n## Build-time flags/options\n\n- `CROSS_TARGET`: passed to napi-rs as `--target <CROSS_TARGET>`.\n- `TARGET_PLATFORM`: override output platform tag naming.\n- `TARGET_ARCH`: override output arch naming.\n- `TARGET_VARIANT` (x64 only): force `modern` or `baseline` for output filename and RUSTFLAGS policy.\n- `CARGO_TARGET_DIR`: respected if set; otherwise the default `target/` dir is used so `Swatinem/rust-cache` can cache cleanly.\n- `RUSTFLAGS`:\n  - if unset and not cross-compiling, script sets:\n    - modern: `-C target-cpu=x86-64-v3`\n    - baseline: `-C target-cpu=x86-64-v2`\n    - non-x64 / no variant: `-C target-cpu=native`\n  - if already set, script does not override.\n\n## Build state/lifecycle transitions\n\n### Build lifecycle (`build-native.ts`)\n\n1. **Init**: parse env, resolve target tuple, cross/local mode, profile label.\n2. **Variant resolve**:\n   - non-x64 → no variant;\n   - x64 + `TARGET_VARIANT` → explicit variant;\n   - x64 cross-build without `TARGET_VARIANT` → hard error;\n   - x64 local build without override → detect host AVX2.\n3. **CPU policy**: set `RUSTFLAGS` for the resolved variant unless the caller already provided one.\n4. **Compile**: run napi-rs against `crates/pi-natives` into an isolated output directory.\n5. **Locate artifact**: accept the canonical filename or a single napi-rs-generated `pi_natives.<platform>-<arch>*.node` candidate.\n6. **Install**: copy/rename addon into `packages/natives/native`.\n7. **Install generated bindings**: copy `index.js`/`index.d.ts` if needed.\n8. **Patch enums**: append generated enum runtime exports.\n9. **Cleanup**: remove the temporary build output directory.\n\nFailure exits have explicit error text for invalid variants, failed napi build, missing/multiple output artifacts, generated binding install failure, and install/rename failure.\n\n### Embed lifecycle (`embed-native.ts`)\n\n1. **Init**: compute platform tag from `TARGET_PLATFORM`/`TARGET_ARCH` or host values.\n2. **Candidate set**:\n   - x64 looks for `modern` and `baseline` files;\n   - non-x64 looks for one default file.\n3. **Validate availability**: at least one expected file must exist in `packages/natives/native`.\n4. **Generate manifest** (`native/embedded-addon.js`) with Bun `file` imports and package version.\n5. **Runtime extraction ready** for compiled mode.\n\n`--reset` writes the null manifest stub (`embeddedAddon = null`) without validating addon availability.\n\n## Dev workflow vs shipped/compiled behavior\n\n## Local development workflow\n\nTypical local loop:\n\n1. Build addon: `bun --cwd=packages/natives run build`.\n2. Loader resolves package-local `native/` candidates, then executable-dir fallback candidates.\n3. Generated declarations in `native/index.d.ts` describe the public TS API.\n\n## Shipped/compiled binary workflow\n\nIn compiled mode (`PI_COMPILED`, Bun embedded URL markers, or populated embedded manifest):\n\n1. Loader computes versioned cache dir: `<getNativesDir()>/<packageVersion>`.\n2. If embedded manifest matches current platform+version, loader may extract the selected embedded file into that versioned dir.\n3. Runtime candidate order includes:\n   - versioned cache dir,\n   - legacy compiled-binary dir (`%LOCALAPPDATA%/omp` on Windows, `~/.local/bin` elsewhere),\n   - package/executable directories.\n4. First successfully loaded addon is returned.\n\nThis is why packaging + runtime loader expectations must align: filenames, platform tags, CPU variants, and embedded manifest version must match what `native/index.js` probes.\n\n## JS API ↔ Rust export mapping (build sanity subset)\n\nGenerated declarations currently include exports from these Rust modules:\n\n| Area                   | Representative JS exports                                                                         | Rust source                                                                             |\n| ---------------------- | ------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |\n| Search                 | `grep`, `search`, `hasMatch`, `fuzzyFind`, `glob`, `invalidateFsScanCache`                        | `grep.rs`, `fd.rs`, `glob.rs`, `fs_cache.rs`                                            |\n| AST                    | `astGrep`, `astEdit`                                                                              | `ast.rs`                                                                                |\n| Text/highlight/tokens  | `visibleWidth`, `truncateToWidth`, `highlightCode`, `countTokens`                                 | `text.rs`, `highlight.rs`, `tokens.rs`                                                  |\n| Shell/PTY/process/keys | `executeShell`, `Shell`, `PtySession`, `killTree`, `parseKey`                                     | `shell.rs`, `pty.rs`, `ps.rs`, `keys.rs`                                                |\n| Media/system           | `PhotonImage`, `encodeSixel`, clipboard, macOS appearance/power, `getWorkProfile`, ProjFS helpers | `image.rs`, `clipboard.rs`, `appearance.rs`, `power.rs`, `prof.rs`, `projfs_overlay.rs` |\n\n## Failure behavior and diagnostics\n\n## Build-time failures\n\n- Invalid variant configuration:\n  - `TARGET_VARIANT` set on non-x64 → immediate error.\n  - unsupported `TARGET_VARIANT` value → immediate error.\n  - x64 cross-build without explicit `TARGET_VARIANT` → immediate error.\n- napi-rs build failure: script surfaces non-zero exit and stderr.\n- Artifact not found or ambiguous: script prints expected/candidate filenames and output directory contents.\n- Install failure: explicit message; Windows includes locked-file hint.\n- Generated binding install failure: explicit source/destination message.\n\n## Runtime loader failures (`native/index.js`)\n\n- Unsupported platform tag: throws with supported platform list after probing fails.\n- No candidate could load: throws with full candidate error list and mode-specific remediation hints.\n- Embedded extraction problems: extraction mkdir/write errors are recorded and included in final diagnostics if load fails.\n\n## Troubleshooting matrix\n\n| Symptom                                                                | Likely cause                                                                                | Verify                                                            | Fix                                                                                           |\n| ---------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `Cannot find module` or dynamic library load error for every candidate | Missing release artifact, wrong platform tag, or stale compiled cache                       | Inspect loader error list and `packages/natives/native` filenames | Build correct target/variant; delete stale cache for the package version                      |\n| Export is missing at runtime but present in TypeScript                 | Stale `.node` loaded, generated declarations newer than binary, or Rust export not compiled | Require the actual candidate and inspect `Object.keys(mod)`       | Rebuild native package and remove stale candidate/cache paths                                 |\n| x64 machine loads baseline when modern expected                        | `PI_NATIVE_VARIANT=baseline`, no AVX2 detected, or modern file unavailable                  | Check env and filenames in `native/`                              | Build modern variant (`TARGET_VARIANT=modern ... build`) and ship it                          |\n| Cross-build produces wrong-labeled binary                              | Mismatch between `CROSS_TARGET` and `TARGET_PLATFORM`/`TARGET_ARCH`, or missing x64 variant | Confirm env tuple and output filename                             | Re-run with consistent env values and explicit x64 `TARGET_VARIANT`                           |\n| Compiled binary fails after upgrade                                    | Stale extracted cache or embedded manifest version mismatch                                 | Inspect `<getNativesDir()>/<version>` and loader error list       | Delete versioned cache for the package version; regenerate embedded manifest during packaging |\n| `embed:native` fails with `No native addons found`                     | Required platform artifact was not built before embedding                                   | Check expected list in error text                                 | Build at least one expected artifact for the target, then rerun `embed:native`                |\n\n## Operational commands\n\n```bash\n# Release artifact for current host\nbun --cwd=packages/natives run build\n\n# Build explicit x64 variants\nTARGET_VARIANT=modern bun --cwd=packages/natives run build\nTARGET_VARIANT=baseline bun --cwd=packages/natives run build\n\n# Generate embedded addon manifest from built native files\nbun --cwd=packages/natives run embed:native\n\n# Reset embedded manifest to null stub\nbun --cwd=packages/natives run embed:native -- --reset\n```\n\n## Orchestrator-side content-addressed build cache (robomp)\n\nWhen `pi-natives` is built inside the robomp orchestrator (`python/robomp/`), workspaces share built artifacts through a content-addressed cache instead of rebuilding from scratch in every per-issue worktree. The cache is **orchestrator-side only** — `bun --cwd=packages/natives run build` itself is unchanged; the cache lives outside the build pipeline and is populated/captured around `ensure_workspace` and post-task success in `python/robomp/src/natives_cache.py`.\n\n### What is cached\n\nThe complete set of files in `packages/natives/native/` that are pure functions of the cache-key inputs:\n\n- `pi_natives.<platform>-<arch>[-variant].node` (glob `pi_natives.*.node`)\n- `index.d.ts`\n- `index.js`\n- `embedded-addon.js`\n- `manifest.json` (cache metadata: key, target triple, capture timestamp, source workspace, commit)\n\nAn entry is only considered a hit when the `.node` glob matches AND every companion plus the manifest is present. Partial entries are evicted on GC.\n\n### Cache key\n\nThe key is `sha256` over `(path \\t git-tree-hash \\n)` pairs for the following inputs, in this order (order is significant), followed by the target triple:\n\n1. `crates` (whole subtree — pi-natives transitively depends on other workspace crates)\n2. `Cargo.lock`\n3. `Cargo.toml`\n4. `rust-toolchain.toml`\n5. `packages/natives` (whole subtree — build script, `scripts/*`, package.json with napi config)\n\nTree hashes come from one `git cat-file --batch-check` invocation against `HEAD`; paths missing from `HEAD` fold in as a fixed null hash so the key stays deterministic across repos that don't ship every input. The target-triple suffix matches the napi addon basename convention (`<platform>-<arch>` for non-x64, `<platform>-<arch>-<variant>` for x64). When `TARGET_VARIANT` is unset on an x64 host the variant component is `host` rather than autodetected — the key is stable on a given machine but a `modern`/`baseline` build with an explicit `TARGET_VARIANT` gets a different key.\n\nAnything outside this input set (Rust toolchain auto-installed delta, host glibc, env vars other than `TARGET_VARIANT`) is **not** in the key. If you need to invalidate after such a change, delete the cache directory by hand or bump one of the input files.\n\n### Layout and ownership\n\n- Root: `/data/cache/pi-natives` (provisioned by `entrypoint.sh` alongside the cargo caches, owned `root:omp`, mode `02770` setgid so cached files inherit `gid=omp` and stay readable by every slot user).\n- Per-repo subdirectory: `<root>/<repo-slug>/` where the slug is `owner__repo` (mirrors `SandboxManager.pool_path`).\n- Per-entry directory: `<root>/<repo-slug>/<sha256-key>/` containing the cached files plus `manifest.json`.\n- Per-repo lockfile: `<root>/<repo-slug>/.lock` (advisory `fcntl.flock`, exclusive on capture and GC).\n- Staging dirs (`.<key>.tmp.<pid>`) during capture; renamed atomically into the final entry path. Stale staging dirs from crashed captures are swept on GC.\n\n### Populate and capture semantics\n\n- **Populate** (workspace ← cache) runs inside `ensure_workspace`. On a key hit the `.node` is **hardlinked** into the workspace (zero-copy, shared inode); the companion `index.d.ts` / `index.js` / `embedded-addon.js` are **copied** (independent inodes) because the napi build's `installGeneratedBindings` and `gen-enums.ts` rewrite those files via `open(..., 'w')` — an in-place truncate that would otherwise propagate through a hardlink and corrupt the cache. Cross-device hardlink failures (`EXDEV`) fall back to copy.\n- **Capture** (cache ← workspace) runs from the post-task success path when the build produced a complete artifact set. Capture uses **copy**, not hardlink: hardlinking a slot-owned workspace file would preserve slot UID ownership on the cached inode and defeat the shared-group model. Copying creates a fresh root-owned, `gid=omp` inode via the setgid cache root. Capture is idempotent under the per-repo flock: a concurrent capture for the same key returns the existing entry.\n\n### Garbage collection\n\nA periodic GC loop runs in `WorkerPool` with two caps per repo. When either cap is exceeded, oldest entries (by `manifest.json.captured_at`) are dropped first:\n\n- entry count cap (`max_entries_per_repo`, default 8)\n- byte cap (`max_bytes`, default 4 GiB)\n\nWorkspaces that hardlinked a `.node` before GC retain access via the kernel inode refcount — `rmtree` of the cache entry does not delete the file from the workspace.\n\n### Configuration (settings on `robomp.config.Settings`)\n\n| Env var                                      | Default                  | Effect                                                        |\n| -------------------------------------------- | ------------------------ | ------------------------------------------------------------- |\n| `ROBOMP_NATIVES_CACHE_ENABLED`               | `true`                   | Master switch. When false the populate/capture hooks no-op and every workspace builds from scratch. |\n| `ROBOMP_NATIVES_CACHE_ROOT`                  | `/data/cache/pi-natives` | Cache root directory. Must be `root:omp 02770` for cross-slot reads.                                  |\n| `ROBOMP_NATIVES_CACHE_MAX_ENTRIES_PER_REPO`  | `8`                      | LRU entry-count cap, per repo slug.                                                                  |\n| `ROBOMP_NATIVES_CACHE_MAX_BYTES`             | `4294967296` (4 GiB)     | LRU byte cap, per repo slug.                                                                          |\n| `ROBOMP_NATIVES_CACHE_GC_INTERVAL_SECONDS`   | `3600`                   | Period of the background GC loop in `WorkerPool`.                                                    |\n\n### Manual invalidation\n\n- One key: `rm -rf /data/cache/pi-natives/<repo-slug>/<sha256>`.\n- One repo: `rm -rf /data/cache/pi-natives/<repo-slug>`.\n- Everything: `rm -rf /data/cache/pi-natives/*` (preserve the root so its setgid mode survives).\n- Stuck lock: `rm /data/cache/pi-natives/<repo-slug>/.lock` (only when no orchestrator process is touching the repo).\n\nTrigger an automatic miss by editing any path in the key set: a single touched byte under `crates/`, `Cargo.lock`, `Cargo.toml`, `rust-toolchain.toml`, or `packages/natives/` shifts the tree hash and forces a fresh build at the next populate.\n",
 	"natives-media-system-utils.md": "# Natives media + system utilities\n\nThis document covers the media/system/conversion exports in `@oh-my-pi/pi-natives`: image processing, HTML conversion, clipboard access, token counting, macOS appearance/power helpers, ProjFS helpers, and work profiling.\n\n## Implementation files\n\n- `crates/pi-natives/src/image.rs`\n- `crates/pi-natives/src/html.rs`\n- `crates/pi-natives/src/clipboard.rs`\n- `crates/pi-natives/src/tokens.rs`\n- `crates/pi-natives/src/appearance.rs`\n- `crates/pi-natives/src/power.rs`\n- `crates/pi-natives/src/projfs_overlay.rs`\n- `crates/pi-natives/src/prof.rs`\n- `crates/pi-natives/src/task.rs`\n- `packages/natives/native/index.d.ts`\n\n> Note: there is no `crates/pi-natives/src/work.rs`; work profiling is implemented in `prof.rs` and fed by instrumentation in `task.rs`.\n\n## JS API ↔ Rust export/module mapping\n\n| JS export                                           | Rust N-API export              | Rust module         |\n| --------------------------------------------------- | ------------------------------ | ------------------- |\n| `PhotonImage.parse(bytes)`                          | `PhotonImage::parse`           | `image.rs`          |\n| `PhotonImage#resize(width, height, filter)`         | `PhotonImage::resize`          | `image.rs`          |\n| `PhotonImage#encode(format, quality)`               | `PhotonImage::encode`          | `image.rs`          |\n| `encodeSixel(bytes, targetWidthPx, targetHeightPx)` | `encode_sixel`                 | `image.rs`          |\n| `htmlToMarkdown(html, options?)`                    | `html_to_markdown`             | `html.rs`           |\n| `copyToClipboard(text)`                             | `copy_to_clipboard`            | `clipboard.rs`      |\n| `readImageFromClipboard()`                          | `read_image_from_clipboard`    | `clipboard.rs`      |\n| `countTokens(input, encoding?)`                     | `count_tokens`                 | `tokens.rs`         |\n| `detectMacOSAppearance()`                           | `detect_mac_os_appearance`     | `appearance.rs`     |\n| `MacAppearanceObserver.start(callback)`             | `MacAppearanceObserver::start` | `appearance.rs`     |\n| `MacOSPowerAssertion.start(options?)`               | `MacOSPowerAssertion::start`   | `power.rs`          |\n| `projfsOverlayProbe/start/stop`                     | ProjFS exports                 | `projfs_overlay.rs` |\n| `getWorkProfile(lastSeconds)`                       | `get_work_profile`             | `prof.rs`           |\n\n## Data format boundaries and conversions\n\n### Image (`image`)\n\n- **JS input boundary**: `Uint8Array` encoded image bytes for `PhotonImage.parse` and `encodeSixel`.\n- **Rust decode boundary**: bytes are copied/read, format is guessed with `ImageReader::with_guessed_format()`, then decoded to `DynamicImage`.\n- **In-memory state**: `PhotonImage` stores `Arc<DynamicImage>`.\n- **Output boundary**:\n  - `PhotonImage#encode(format, quality)` returns a promise for encoded bytes (`Vec<u8>` in Rust; generated TS currently declares `Promise<Array<number>>`).\n  - `encodeSixel(...)` returns a SIXEL escape string synchronously.\n\nFormat IDs:\n\n- `0`: PNG\n- `1`: JPEG\n- `2`: WebP\n- `3`: GIF\n\nEncoding behavior:\n\n- JPEG uses the provided `quality` with `JpegEncoder::new_with_quality`.\n- WebP uses the `webp` crate encoder with `quality` as `f32` in the same 0..=100 range.\n- PNG/GIF ignore `quality`.\n- Invalid dimensions for SIXEL (`0` width or height) fail with `Target SIXEL dimensions must be greater than zero`.\n\n### HTML conversion (`html`)\n\n- **JS input boundary**: HTML `string` + optional `{ cleanContent?: boolean; skipImages?: boolean }`.\n- **Rust conversion boundary**: conversion is scheduled through `task::blocking(\"html_to_markdown\", (), ...)`.\n- **Output boundary**: Markdown `string` promise.\n\nConversion behavior:\n\n- `cleanContent` defaults to `false`.\n- When `cleanContent=true`, preprocessing uses `PreprocessingPreset::Aggressive` and hard-removal flags for navigation/forms.\n- `skipImages` defaults to `false`.\n\n### Clipboard (`clipboard`)\n\n- `copyToClipboard(text)` is a synchronous native call using `arboard::Clipboard::set_text`.\n- `readImageFromClipboard()` runs in `task::blocking(\"clipboard.read_image\", (), ...)`.\n- Image read returns `null`/`undefined` when `arboard` reports `ContentNotAvailable`.\n- Successful image read re-encodes clipboard RGBA data as PNG and returns `{ data: Uint8Array, mimeType: \"image/png\" }`.\n- Clipboard access or image encoding failures reject/throw as native errors.\n\nThere is no current `packages/natives` TS wrapper that emits OSC52, handles Termux, or suppresses native clipboard failures. Any best-effort clipboard policy must live in consumers.\n\n### Tokens (`tokens`)\n\n- `countTokens(input, encoding?)` accepts a single string or an array of strings.\n- Arrays return one aggregate token count; encoding work is parallelized in Rust.\n- Default encoding is `O200kBase`; `Cl100kBase` is also exported.\n- The implementation uses ordinary encoding, not special-token handling.\n\n### macOS appearance and power helpers\n\n- `detectMacOSAppearance()` returns `\"dark\"`, `\"light\"`, or `null` on non-macOS.\n- `MacAppearanceObserver.start(callback)` returns a handle with `stop()`; on macOS it uses distributed notifications plus a 2-second polling fallback, and on non-macOS it is a no-op observer.\n- `MacOSPowerAssertion.start(options?)` returns a handle with `stop()`; on macOS it acquires an IOKit assertion, and on other platforms it is a no-op handle.\n\n### Windows ProjFS helpers\n\n- `projfsOverlayProbe()` reports whether ProjFS APIs are available.\n- `projfsOverlayStart(lowerRoot, projectionRoot)` starts an overlay.\n- `projfsOverlayStop(projectionRoot)` stops an overlay session.\n\nThese helpers are platform-specific; availability must be checked before relying on overlay behavior.\n\n### Work profiling (`work`)\n\n- **Collection boundary**: profiling samples are produced by `profile_region(tag)` guards in `task::blocking` and `task::future`.\n- **Storage format**: fixed-size circular buffer (`MAX_SAMPLES = 10_000`) storing stack path, duration, and timestamp.\n- **Output boundary**: `getWorkProfile(lastSeconds)` returns:\n  - `folded`: folded-stack text (flamegraph input)\n  - `summary`: markdown table summary\n  - `svg`: optional flamegraph SVG\n  - `totalMs`, `sampleCount`\n\n## Lifecycle and state transitions\n\n### Image lifecycle\n\n1. `PhotonImage.parse(bytes)` schedules a blocking decode task (`image.decode`).\n2. On success, a native `PhotonImage` handle exists in JS.\n3. `resize(...)` creates a new native handle (`image.resize`); old and new handles can coexist.\n4. `encode(...)` schedules `image.encode` and materializes bytes without mutating image dimensions.\n5. `encodeSixel(...)` decodes, optionally resizes to exact target dimensions with Lanczos3, and returns SIXEL text synchronously.\n\nFailure transitions:\n\n- Format detection/decode failure rejects parse promise or throws from SIXEL encoding.\n- Encode failure rejects encode promise.\n- Invalid SIXEL dimensions throw.\n\n### HTML lifecycle\n\n1. `htmlToMarkdown(html, options)` schedules a blocking conversion task.\n2. Conversion runs with defaulted options (`cleanContent=false`, `skipImages=false`) unless specified.\n3. Returns markdown string or rejects.\n\n### Clipboard lifecycle\n\n- Text copy constructs an `arboard::Clipboard` and calls `set_text` synchronously.\n- Image read constructs an `arboard::Clipboard`, calls `get_image`, encodes PNG on success, maps `ContentNotAvailable` to `None`, and rejects other errors.\n\n### Work profiling lifecycle\n\n1. No explicit start: profiling is active when task helpers execute.\n2. Every instrumented task scope records one sample on guard drop.\n3. Samples overwrite oldest entries after buffer capacity is reached.\n4. `getWorkProfile(lastSeconds)` reads a time window and derives folded/summary/svg artifacts.\n\nFailure transitions:\n\n- SVG generation failure is soft (`svg` omitted/undefined), while folded and summary still return.\n- Empty sample windows return empty folded data and no SVG, not an error.\n\n## Unsupported operations and error propagation\n\n### Image\n\n- Unsupported decode input or corrupted bytes: strict failure.\n- Invalid SIXEL target dimensions: strict failure.\n- No JS fallback path in the natives package.\n\n### HTML\n\n- Conversion errors are strict failures.\n- Option omission is defaulting, not failure.\n\n### Clipboard\n\n- Text copy is strict at the native API surface.\n- Image read distinguishes \"no image\" (`null`/`undefined`) from operational failure (rejection).\n\n### Work profiling\n\n- Retrieval is strict for the function call itself.\n- Flamegraph SVG generation is nullable/optional.\n- Buffer truncation is expected ring-buffer behavior.\n\n## Platform caveats\n\n- Clipboard access depends on OS/session support exposed through `arboard`.\n- macOS appearance and power helpers intentionally return no-op/null behavior on unsupported platforms.\n- ProjFS helpers are Windows-specific and should be gated by `projfsOverlayProbe()`.\n",
@@ -43,7 +43,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"notebook-tool-runtime.md": "# Notebook tool runtime internals\n\nThis document describes the current `notebook` tool implementation and its relationship to the kernel-backed Python runtime.\n\nThe critical distinction: **`notebook` is a JSON notebook editor, not a notebook executor**. It edits `.ipynb` cell sources directly; it does not start or talk to a Python kernel.\n\n## Implementation files\n\n- [`src/edit/notebook.ts`](../packages/coding-agent/src/edit/notebook.ts)\n- [`src/eval/py/executor.ts`](../packages/coding-agent/src/eval/py/executor.ts)\n- [`src/eval/py/kernel.ts`](../packages/coding-agent/src/eval/py/kernel.ts)\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts)\n- [`src/tools/eval.ts`](../packages/coding-agent/src/tools/eval.ts)\n\n## 1) Runtime boundary: editing vs executing\n\n## `notebook` tool (`src/edit/notebook.ts`)\n\n- Supports `action: edit | insert | delete` on a `.ipynb` file.\n- Resolves path relative to session CWD (`resolveToCwd`).\n- Loads notebook JSON, validates `cells` array, validates `cell_index` bounds.\n- Applies source edits in-memory and writes full notebook JSON back with `JSON.stringify(notebook, null, 1)`.\n- Returns textual summary + structured `details` (`action`, `cellIndex`, `cellType`, `totalCells`, `cellSource`).\n\nNo kernel lifecycle exists in this tool:\n\n- no gateway acquisition\n- no kernel session ID\n- no `execute_request`\n- no stream chunks from kernel channels\n- no rich display capture (`image/png`, JSON display, status MIME)\n\n## Notebook-like execution path (`src/tools/eval.ts` + `src/eval/py/*`)\n\nWhen the agent needs to run cell-style Python code (sequential cells, persistent state, rich displays), that goes through the **`eval` tool** with `language: \"python\"`, not `notebook`.\n\nThat path is where kernel modes, restart/cancel behavior, chunk streaming, and output artifact truncation live.\n\n## 2) Notebook cell handling semantics (`notebook` tool)\n\n## Source normalization\n\n`content` is split into `source: string[]` with newline preservation:\n\n- each non-final line keeps trailing `\\n`\n- final line has no forced trailing newline\n\nThis mirrors notebook JSON conventions and avoids accidental line concatenation on later edits.\n\n## Action behavior\n\n- `edit`\n  - replaces `cells[cell_index].source`\n  - preserves existing `cell_type`\n- `insert`\n  - inserts at `[0..cellCount]`\n  - `cell_type` defaults to `code`\n  - code cells initialize `execution_count: null` and `outputs: []`\n  - markdown cells initialize only `metadata` + `source`\n- `delete`\n  - removes `cells[cell_index]`\n  - returns removed `source` in details for renderer preview\n\n## Error surfaces\n\nHard failures are thrown for:\n\n- missing notebook file\n- invalid JSON\n- missing/non-array `cells`\n- out-of-range index (insert and non-insert have different valid ranges)\n- missing `content` for `edit`/`insert`\n\nThese become `Error:` tool responses upstream; renderer uses notebook path + formatted error text.\n\n## 3) Kernel session semantics (where they actually exist)\n\nKernel semantics are implemented in `executePython` / `PythonKernel` and apply to the Python backend of the `eval` tool.\n\n## Modes\n\n`PythonKernelMode`:\n\n- `session` (default)\n  - kernels cached in `kernelSessions` map\n  - max 4 sessions; oldest evicted on overflow\n  - idle/dead cleanup every 30s, timeout after 5 minutes\n  - per-session queue serializes execution (`session.queue`)\n- `per-call`\n  - creates kernel for request\n  - executes\n  - always shuts down kernel in `finally`\n\n## Reset behavior\n\n`eval` passes `reset` only for the first cell in a multi-cell Python call; later cells always run with `reset: false`.\n\n## Kernel death / restart / retry\n\nIn session mode (`withKernelSession`):\n\n- dead kernel detected by heartbeat (`kernel.isAlive()` check every 5s) or execute failure.\n- pre-run dead state triggers `restartKernelSession`.\n- execute-time crash path retries once: restart kernel, rerun handler.\n- `restartCount > 1` in same session throws `Python kernel restarted too many times in this session`.\n\nStartup retry behavior:\n\n- shared gateway kernel creation retries once on `SharedGatewayCreateError` with HTTP 5xx.\n\nResource exhaustion recovery:\n\n- detects `EMFILE`/`ENFILE`/\"Too many open files\" style failures\n- clears tracked sessions\n- calls `shutdownSharedGateway()`\n- retries kernel session creation once\n\n## 4) Environment/session variable injection\n\nKernel startup receives the optional session file path from executor:\n\n- `PI_SESSION_FILE` (session state file path)\n\n`PythonKernel.#initializeKernelEnvironment(...)` then runs init script inside kernel to:\n\n- `os.chdir(cwd)`\n- inject env entries into `os.environ`\n- prepend cwd to `sys.path` if missing\n\nImplication:\n\n- prelude helpers that read session context rely on this env var in Python process state.\n\n## 5) Streaming/chunk and display handling (kernel-backed path)\n\nThe kernel client processes Jupyter protocol messages per execution:\n\n- `stream` -> text chunk to `onChunk`\n- `execute_result` / `display_data` ->\n  - display text chosen by MIME precedence: `text/markdown` > `text/plain` > converted `text/html`\n  - structured outputs captured separately:\n    - `application/json` -> `{ type: \"json\" }`\n    - `image/png` -> `{ type: \"image\" }`\n    - `application/x-omp-status` -> `{ type: \"status\" }` (no text emission)\n- `error` -> traceback text pushed to chunk stream + structured error metadata\n- `input_request` -> emits stdin warning text, sends empty `input_reply`, marks stdin requested\n- completion waits for both `execute_reply` and kernel `status=idle`\n\nCancellation/timeout:\n\n- abort signal triggers `interrupt()` (REST `/interrupt` + control-channel `interrupt_request`)\n- result marks `cancelled=true`\n- timeout path annotates output with `Command timed out after <n> seconds`\n\n## 6) Truncation and artifact behavior\n\n`OutputSink` in `src/session/streaming-output.ts` is used by kernel execution paths (`executeWithKernel`):\n\n- sanitizes every chunk (`sanitizeText`)\n- tracks total/output lines and bytes\n- optional artifact spill file (`artifactPath`, `artifactId`)\n- when in-memory buffer exceeds threshold (`DEFAULT_MAX_BYTES` unless overridden):\n  - marks truncated\n  - keeps tail bytes in memory (UTF-8 safe boundary)\n  - can spill full stream to artifact sink\n\n`dump()` returns:\n\n- visible output text (possibly tail-truncated)\n- truncation flag + counts\n- artifact ID (for `artifact://<id>` references)\n\n`eval` converts this metadata into result truncation notices and TUI warnings.\n\n`notebook` tool does **not** use `OutputSink`; it has no stream/artifact truncation pipeline because it does not execute code.\n\n## 7) Renderer assumptions and formatting\n\n## Notebook renderer (`notebookToolRenderer`)\n\n- call view: status line with action + notebook path + cell/type metadata\n- result view:\n  - success summary derived from `details`\n  - `cellSource` rendered via `renderCodeCell`\n  - markdown cells set language hint `markdown`; other cells have no explicit language override\n  - collapsed code preview limit is `PREVIEW_LIMITS.COLLAPSED_LINES * 2`\n  - supports expanded mode via shared render options\n  - uses render cache keyed by width + expanded state\n\nError rendering assumption:\n\n- if first text content starts with `Error:`, renderer formats as notebook error block.\n\n## Python renderer (for actual execution output)\n\nKernel-backed execution rendering expects:\n\n- per-cell status transitions (`pending/running/complete/error`)\n- optional structured status event section\n- optional JSON output trees\n- truncation warnings + optional `artifact://<id>` pointer\n\nThis renderer behavior is unrelated to `notebook` JSON editing results except that both reuse shared TUI primitives.\n\n## 8) Divergence from eval Python backend behavior\n\nIf \"plain Python execution\" means the `eval` tool with `language: \"python\"`:\n\n- `eval` executes code in a kernel, persists state by mode, streams chunks, captures rich displays, handles interrupts/timeouts, and supports output truncation/artifacts.\n- `notebook` performs deterministic notebook JSON mutations only; no execution, no kernel state, no chunk stream, no display outputs, no artifact pipeline.\n\nIf a workflow needs both:\n\n1. edit notebook source with `notebook`\n2. execute code cells via `eval` with `language: \"python\"` (manually passing code), not through `notebook`\n\nCurrent implementation does not provide a single tool that both mutates `.ipynb` and executes notebook cells through kernel context.\n",
 	"plugin-manager-installer-plumbing.md": "# Plugin manager and installer plumbing\n\nThis document describes how `omp plugin` operations mutate plugin state on disk and how installed plugins become runtime capabilities (tools and extensions today, hooks/commands path resolution available).\n\n## Scope and architecture\n\nThere are two plugin-management implementations in the codebase:\n\n1. **Active path used by CLI commands**: `PluginManager` (`src/extensibility/plugins/manager.ts`)\n2. **Legacy helper module**: installer functions (`src/extensibility/plugins/installer.ts`)\n\n`omp plugin ...` command execution goes through `PluginManager`.\n\n`installer.ts` still documents important safety checks and filesystem behavior, but it is not the path used by `src/commands/plugin.ts` + `src/cli/plugin-cli.ts`.\n\n## Lifecycle: from CLI invocation to runtime availability\n\n```text\nomp plugin <action> ...\n  -> src/commands/plugin.ts\n  -> runPluginCommand(...) in src/cli/plugin-cli.ts\n  -> PluginManager method (install/list/uninstall/link/...)\n  -> mutate ~/.omp/plugins/{package.json,node_modules,omp-plugins.lock.json}\n  -> runtime discovery: discoverAndLoadCustomTools(...) and discoverAndLoadExtensions(...)\n  -> getAllPluginToolPaths(cwd) / getAllPluginExtensionPaths(cwd)\n  -> custom tool loader imports tool modules; extension loader imports extension modules\n```\n\n### Command entrypoints\n\n- `src/commands/plugin.ts` defines command/flags and forwards to `runPluginCommand`.\n- `src/cli/plugin-cli.ts` maps subcommands to `PluginManager` methods:\n  - `install`, `uninstall`, `list`, `link`, `doctor`, `features`, `config`, `enable`, `disable`\n- No explicit `update` action exists; update is done by re-running `install` with a new package/version spec.\n\n## On-disk model\n\nGlobal plugin state lives under `~/.omp/plugins`:\n\n- `package.json` — dependency manifest used by `bun install`/`bun uninstall`\n- `node_modules/` — installed plugin packages or symlinks\n- `omp-plugins.lock.json` — runtime state:\n  - enabled/disabled per plugin\n  - selected feature set per plugin\n  - persisted plugin settings\n\nProject-local overrides live at:\n\n- `<cwd>/.omp/plugin-overrides.json`\n\nOverrides are read-only from manager/loader perspective (no write path here) and can disable plugins or override features/settings for this project.\n\n## Plugin spec parsing and metadata interpretation\n\n## Install spec grammar\n\n`parsePluginSpec` (`parser.ts`) supports:\n\n- `pkg` -> `features: null` (defaults behavior)\n- `pkg[*]` -> enable all manifest features\n- `pkg[]` -> enable no optional features\n- `pkg[a,b]` -> enable named features\n- `@scope/pkg@1.2.3[feat]` -> scoped + versioned package with explicit feature selection\n\n`extractPackageName` strips version suffix for on-disk path lookup after install.\n\n## Manifest source and required fields\n\nManifest is resolved as:\n\n1. `package.json.omp`\n2. fallback `package.json.pi`\n3. fallback `{ version: package.version }`\n\nImplications:\n\n- There is no strict schema validation in manager/loader.\n- A package missing `omp`/`pi` is still installable and listable.\n- Runtime plugin loading (`getEnabledPlugins`) skips packages without `omp`/`pi` manifest.\n- `manifest.version` is always overwritten from package `version`.\n\nMalformed `package.json` JSON is a hard failure at read time; malformed manifest shape may fail later only when specific fields are consumed.\n\n## Install/update flow (`PluginManager.install`)\n\n1. Parse feature bracket syntax from install spec.\n2. Validate package name against regex + shell-metacharacter denylist.\n3. Ensure plugin `package.json` exists (`omp-plugins`, private dependencies map).\n4. Run `bun install <packageSpec>` in `~/.omp/plugins`.\n5. Read installed package `node_modules/<name>/package.json`.\n6. Resolve manifest and compute `enabledFeatures`:\n   - `[*]`: all declared features (or `null` if no feature map)\n   - `[a,b]`: validates each feature exists in manifest features map\n   - `[]`: empty feature list\n   - bare spec: `null` (use defaults policy later in loader)\n7. Upsert lockfile runtime state: `{ version, enabledFeatures, enabled: true }`.\n\n### Update semantics\n\nBecause update is install-driven:\n\n- `omp plugin install pkg@newVersion` updates dependency and lockfile version.\n- Existing settings are preserved; state entry is overwritten for version/features/enabled.\n- No separate “check updates” or transactional migration logic exists.\n\n## Remove flow (`PluginManager.uninstall`)\n\n1. Validate package name.\n2. Run `bun uninstall <name>` in plugin dir.\n3. Remove plugin runtime state from lockfile:\n   - `config.plugins[name]`\n   - `config.settings[name]`\n\nIf uninstall command fails, runtime state is not changed.\n\n## List flow (`PluginManager.list`)\n\n1. Read plugin dependency map from `~/.omp/plugins/package.json`.\n2. Load lockfile runtime config (missing file -> empty defaults).\n3. Load project overrides (`<cwd>/.omp/plugin-overrides.json`, parse/read errors -> empty object with warning).\n4. For each dependency with a resolvable package.json:\n   - build `InstalledPlugin` record\n   - merge feature/enable state:\n     - base from lockfile (or defaults)\n     - project overrides can replace feature selection\n     - project `disabled` list masks plugin as disabled\n\nThis is the effective state used by CLI status output and settings/features operations.\n\n## Link flow (`PluginManager.link`)\n\n`link` supports local plugin development by symlinking a local package into `~/.omp/plugins/node_modules/<pkg.name>`.\n\nBehavior:\n\n1. Resolve `localPath` against manager cwd.\n2. Require local `package.json` and `name` field.\n3. Ensure plugin dirs exist.\n4. For scoped names, create scope directory.\n5. Remove existing path at target link location.\n6. Create symlink.\n7. Add runtime lockfile entry enabled with default features (`null`).\n\nCaveat: current `PluginManager.link` does not enforce the `cwd` path-boundary check present in legacy `installer.ts` (`normalizedPath.startsWith(normalizedCwd)`), so trust is the caller’s responsibility.\n\n## Runtime loading: from installed plugin to callable capabilities\n\n## Discovery gate\n\n`getEnabledPlugins(cwd)` (`plugins/loader.ts`) reads:\n\n- plugin dependency manifest (`package.json`)\n- lockfile runtime state\n- project overrides via `getConfigDirPaths(\"plugin-overrides.json\", { user: false, cwd })`\n\nFiltering:\n\n- skip if no plugin package.json\n- skip if manifest (`omp`/`pi`) absent\n- skip if globally disabled in lockfile\n- skip if project-disabled\n\n## Capability path resolution\n\nFor each enabled plugin:\n\n- `resolvePluginExtensionPaths(plugin)`\n- `resolvePluginToolPaths(plugin)`\n- `resolvePluginHookPaths(plugin)`\n- `resolvePluginCommandPaths(plugin)`\n\nEach resolver includes base entries plus feature entries:\n\n- explicit feature list -> only selected features\n- `enabledFeatures === null` -> enable features marked `default: true`\n\nMissing files are silently skipped (`existsSync` guard).\n\n## Current runtime wiring differences\n\n- **Tools are wired into runtime today** via `discoverAndLoadCustomTools` (`custom-tools/loader.ts`), which calls `getAllPluginToolPaths(cwd)`.\n- **Extensions are wired into runtime today** via `discoverAndLoadExtensions` (`extensions/loader.ts`), which calls `getAllPluginExtensionPaths(cwd)`.\n- Paths are de-duplicated by resolved absolute path in custom tool and extension discovery (`seen` set, first path wins).\n- **Hooks/commands resolvers exist** and are exported, but this code path does not currently wire them into a runtime registry in the same way tools and extensions are wired.\n\n## Lock/state management details\n\n`PluginManager` caches runtime config in memory per instance (`#runtimeConfig`) and lazily loads once.\n\nLoad behavior:\n\n- lockfile missing -> `{ plugins: {}, settings: {} }`\n- lockfile read/parse failure -> warning + same empty defaults\n\nSave behavior:\n\n- writes full lockfile JSON pretty-printed each mutation\n\nNo cross-process locking or merge strategy exists; concurrent writers can overwrite each other.\n\n## Safety checks and trust boundaries\n\n## Input/package validation\n\nActive manager path enforces package-name validation:\n\n- regex for scoped/unscoped package specs (optionally with version)\n- explicit shell metacharacter denylist (`[;&|`$(){}[]<>\\\\]`)\n\nThis limits command-injection risk when invoking `bun install/uninstall`.\n\n## Filesystem trust boundary\n\n- Plugin code executes in-process when custom tool modules are imported; no sandboxing.\n- Manifest relative paths are joined against plugin package directory and only existence-checked.\n- The plugin package itself is trusted code once installed.\n\n## Legacy installer-only checks\n\n`installer.ts` includes additional link-time checks not mirrored in `PluginManager.link`:\n\n- local path must resolve inside project cwd\n- extra package name/path traversal guards for symlink target naming\n\nBecause CLI uses `PluginManager`, these stricter link guards are not currently on the main path.\n\n## Failure, partial success, and rollback behavior\n\nThe plugin manager is not transactional.\n\n| Operation stage                                          | Failure behavior           | Rollback                                                                      |\n| -------------------------------------------------------- | -------------------------- | ----------------------------------------------------------------------------- |\n| `bun install` fails                                      | install aborts with stderr | N/A (no state writes yet)                                                     |\n| Install succeeds, then manifest/feature validation fails | command fails              | No uninstall rollback; dependency may remain in `node_modules`/`package.json` |\n| Install succeeds, then lockfile write fails              | command fails              | No rollback of installed package                                              |\n| `bun uninstall` succeeds, lockfile write fails           | command fails              | Package removed, stale runtime state may remain                               |\n| `link` removes old target then symlink creation fails    | command fails              | No restoration of previous link/dir                                           |\n\nOperationally, `doctor --fix` can repair some drift (`bun install`, orphaned config cleanup, invalid-feature cleanup), but it is best-effort.\n\n## Malformed/missing manifest behavior summary\n\n- Missing `omp`/`pi` field:\n  - install/list: tolerated (minimal manifest)\n  - runtime enabled-plugin discovery: skipped as non-plugin\n- Missing feature referenced by install spec or `features --set/--enable`: hard error with available feature list\n- Invalid `plugin-overrides.json`: ignored with fallback to `{}` in both manager and loader paths\n- Missing tool/hook/command file paths referenced by manifest: silently ignored during resolver expansion; flagged as errors only by `doctor`\n\n## Mode differences and precedence\n\n- `--dry-run` (install): returns synthetic install result, no filesystem/network/state writes.\n- `--json`: output formatting only, no behavior change.\n- Project overrides always take precedence over global lockfile for feature/settings view.\n- Effective enablement is `runtimeEnabled && !projectDisabled`.\n\n## Implementation files\n\n- [`src/commands/plugin.ts`](../packages/coding-agent/src/commands/plugin.ts) — CLI command declaration and flag mapping\n- [`src/cli/plugin-cli.ts`](../packages/coding-agent/src/cli/plugin-cli.ts) — action dispatch, user-facing command handlers\n- [`src/extensibility/plugins/manager.ts`](../packages/coding-agent/src/extensibility/plugins/manager.ts) — active install/remove/list/link/state/doctor implementation\n- [`src/extensibility/plugins/installer.ts`](../packages/coding-agent/src/extensibility/plugins/installer.ts) — legacy installer helpers and additional link safety checks\n- [`src/extensibility/plugins/loader.ts`](../packages/coding-agent/src/extensibility/plugins/loader.ts) — enabled-plugin discovery and tool/hook/command path resolution\n- [`src/extensibility/plugins/parser.ts`](../packages/coding-agent/src/extensibility/plugins/parser.ts) — install spec and package-name parsing helpers\n- [`src/extensibility/plugins/types.ts`](../packages/coding-agent/src/extensibility/plugins/types.ts) — manifest/runtime/override type contracts\n- [`src/extensibility/custom-tools/loader.ts`](../packages/coding-agent/src/extensibility/custom-tools/loader.ts) — runtime wiring for plugin-provided tool modules\n- [`src/extensibility/extensions/loader.ts`](../packages/coding-agent/src/extensibility/extensions/loader.ts) — runtime wiring for plugin-provided extension modules\n",
 	"porting-from-pi-mono.md": "# Porting From pi-mono: A Practical Merge Guide\n\nThis guide is a repeatable checklist for porting changes from pi-mono into this repo.\nUse it for any merge: single file, feature branch, or full release sync.\n\n## Last Sync Point (historical upstream marker)\n\n**Commit:** `b21b42d032919de2f2e6920a76fa9a37c3920c0a`\n**Date:** 2026-03-22\n\nUpdate this section after each sync; do not reuse the previous range. This commit is an upstream pi-mono marker and may not exist in this repo's local object database.\n\nWhen starting a new sync, generate patches from this commit forward in a pi-mono checkout or remote that contains the commit:\n\n```bash\ngit format-patch b21b42d032919de2f2e6920a76fa9a37c3920c0a..HEAD --stdout > changes.patch\n```\n\n## 0) Define the scope\n\n- Identify the upstream reference (commit, tag, or PR).\n- List the packages or folders you plan to touch.\n- Decide which features are in-scope and which are intentionally skipped.\n\n## 1) Bring code over safely\n\n- Prefer a clean, focused diff rather than a wholesale copy.\n- Avoid copying built artifacts or generated files.\n- If upstream added new files, add them explicitly and review contents.\n\n## 2) Match import extension conventions\n\nMost runtime TypeScript sources omit `.js` in internal imports, but several current entrypoints and tool modules keep `.js` for ESM/runtime compatibility. Follow the surrounding file and package export style; do not blanket-strip or blanket-add extensions.\n\n- In `packages/coding-agent` runtime sources, prefer extensionless internal imports when the surrounding module does, but preserve existing `.js` imports in files that already require them.\n- In `packages/tui/test` and `packages/natives/bench`, keep `.js` where surrounding files already use it.\n- Keep real file extensions when required by tooling or import assertions (e.g., `.json`, `.css`, `.md` text embeds).\n- Example: `import { x } from \"./foo.js\";` → `import { x } from \"./foo\";` only when that package/file convention is extensionless.\n\n## 3) Replace import scopes\n\nUpstream uses different package scopes. Replace them consistently.\n\n- Replace old scopes with the local scope used here.\n- Examples (adjust to match the actual packages you are porting):\n  - `@mariozechner/pi-coding-agent` → `@oh-my-pi/pi-coding-agent`\n  - `@mariozechner/pi-agent-core` → `@oh-my-pi/pi-agent-core`\n  - `@mariozechner/pi-tui` → `@oh-my-pi/pi-tui`\n  - `@mariozechner/pi-ai` → `@oh-my-pi/pi-ai`\n\n## 4) Use Bun APIs where they improve on Node\n\nWe run on Bun, but the current source intentionally mixes Bun APIs with small Node standard-library APIs. Replace Node APIs only when Bun provides a clearer, safer, or simpler implementation; do not mechanically rewrite every Node import.\n\n**Prefer replacing when porting new code:**\n\n- Process spawning: prefer Bun Shell `$` for simple commands; use `Bun.spawn`/`Bun.spawnSync` for streaming or process control. Keep existing `child_process` only where its exact semantics are needed.\n- HTTP clients: `node-fetch`, `axios` → native `fetch`\n- SQLite: `better-sqlite3` → `bun:sqlite`\n- Env loading: `dotenv` → Bun loads `.env` automatically\n- Runtime text/assets: prefer Bun imports such as `with { type: \"text\" }` or `Bun.file()` over copy steps or bundled fallback file reads.\n\n**DO NOT replace (these work fine in Bun):**\n\n- `os.homedir()` — do NOT replace with `Bun.env.HOME` or literal `\"~\"`\n- `os.tmpdir()` — do NOT replace with `Bun.env.TMPDIR || \"/tmp\"` or hardcoded paths\n- `fs.mkdtempSync()` — do NOT replace with manual path construction\n- `path.join()`, `path.resolve()`, etc. — these are fine\n\n**Import style:** Use the `node:` prefix for Node standard-library imports. Namespace imports are common, but named imports are acceptable where the surrounding code already uses them.\n\n**Additional Bun conventions:**\n\n- Prefer Bun Shell `$` for short, non-streaming commands; use `Bun.spawn` only when you need streaming I/O or process control.\n- Use `Bun.file()`/`Bun.write()` for simple files and `node:fs/promises` for directory-oriented operations. Existing synchronous `node:fs` calls are acceptable when the calling flow is intentionally synchronous.\n- Avoid `Bun.file().exists()` checks; use `isEnoent` handling in try/catch.\n- Prefer `Bun.sleep(ms)` over `setTimeout` wrappers.\n\n**Wrong:**\n\n```typescript\n// BROKEN: env vars may be undefined, \"~\" is not expanded\nconst home = Bun.env.HOME || \"~\";\nconst tmp = Bun.env.TMPDIR || \"/tmp\";\n```\n\n**Correct:**\n\n```typescript\nimport * as os from \"node:os\";\nimport * as fs from \"node:fs\";\nimport * as path from \"node:path\";\n\nconst configDir = path.join(os.homedir(), \".config\", \"myapp\");\nconst tempDir = fs.mkdtempSync(path.join(os.tmpdir(), \"myapp-\"));\n```\n\n## 5) Prefer Bun embeds (no copying)\n\nDo not add new runtime asset copy steps. Keep assets in repo and prefer Bun embeds/imports; preserve existing explicit generation workflows such as `packages/coding-agent/src/export/html/template.generated.ts`.\n\n- If upstream copies assets into a dist folder, replace with Bun-friendly embeds.\n- Prompts are static `.md` files; use Bun text imports (`with { type: \"text\" }`) and Handlebars instead of inline prompt strings.\n- Use `import.meta.dir` + `Bun.file` to load adjacent non-text resources.\n- Keep assets in-repo and let the bundler include them.\n- Eliminate copy scripts unless the user explicitly requests them or the package already has an intentional generation step.\n- If upstream reads a bundled fallback file at runtime, replace filesystem reads with a Bun text embed import unless the current package already uses a generated asset pipeline.\n  - Example (Codex instructions fallback):\n    - `const FALLBACK_PROMPT_PATH = join(import.meta.dir, \"codex-instructions.md\");` -> removed\n    - `import FALLBACK_INSTRUCTIONS from \"./codex-instructions.md\" with { type: \"text\" };`\n    - Use `return FALLBACK_INSTRUCTIONS;` instead of `readFileSync(FALLBACK_PROMPT_PATH, \"utf8\")`\n\n## 6) Port `package.json` carefully\n\nTreat `package.json` as a contract. Merge intentionally.\n\n- Keep existing `name`, `version`, `type`, `exports`, and `bin` unless the port requires changes.\n- Replace npm/node scripts with Bun equivalents (e.g., `bun check`, `bun test`).\n- Ensure dependencies use the correct scope.\n- Do not downgrade dependencies to fix type errors; upgrade instead.\n- Validate workspace package links and `peerDependencies`.\n\n## 7) Align code style and tooling\n\n- Keep existing formatting conventions.\n- Do not introduce `any` unless required.\n- Avoid dynamic imports unless they are required for optional dependencies, startup cost, or runtime-only modules; prefer top-level imports otherwise.\n- Never build prompts in code; prompts are static `.md` files rendered with Handlebars.\n- In `packages/coding-agent`, use `logger` from `@oh-my-pi/pi-utils` for internal/runtime logging; CLI command files may use `console.*` for intentional user-facing output.\n- Use `Promise.withResolvers()` instead of `new Promise((resolve, reject) => ...)`.\n- Prefer ES `#` private fields for new encapsulated state. Constructor parameter properties already exist in current code and are acceptable; do not churn unrelated access modifiers while porting.\n- Prefer existing helpers and utilities over new ad-hoc code.\n  Preserve Bun-first infrastructure changes already made in this repo:\n  - Runtime is Bun (no Node entry points for the main CLI).\n  - Package manager is Bun (no npm lockfiles).\n  - Heavy Node APIs should not be introduced casually; current source still uses selected Node APIs (`node:crypto`, `node:readline`, synchronous `node:fs`, and `child_process`) where they fit provider, CLI, or process-control semantics.\n  - Lightweight Node APIs (`os.homedir`, `os.tmpdir`, `fs.mkdtempSync`, `path.*`) are kept.\n  - CLI shebangs use `bun` (not `node`, not `tsx`).\n  - TypeScript packages generally use source files directly; `@oh-my-pi/pi-natives` exports generated native bindings from `packages/natives/native`.\n  - CI workflows run Bun for install/check/test.\n\n## 8) Remove old compatibility layers\n\nUnless requested, remove upstream compatibility shims.\n\n- Delete old APIs that were replaced.\n- Update all call sites to the new API directly.\n- Do not keep `*_v2` or parallel versions.\n\n## 9) Update docs and references\n\n- Replace pi-mono repo links where appropriate.\n- Update examples to use Bun and correct package scopes.\n- Ensure README instructions still match the current repo behavior.\n\n## 10) Validate the port\n\nRun the standard checks after changes:\n\n- `bun check`\n\nIf the repo already has failing checks unrelated to your changes, call that out.\nTests use Bun's runner (not Vitest), but only run `bun test` when explicitly requested.\n\n## 11) Protect improved features (regression trap list)\n\nIf you already improved behavior locally, treat those as **non‑negotiable**. Before porting, write down\nthe improvements and add explicit checks so they don’t get lost in the merge.\n\n- **Freeze the expected behavior**: add a short “before/after” note for each improvement (inputs, outputs,\n  defaults, edge cases). This prevents silent rollback.\n- **Map old → new APIs**: if upstream renamed concepts (hooks → extensions, custom tools → tools, etc.),\n  ensure every old entry point still wires through. One missed flag or export equals lost functionality.\n- **Verify exports**: check `package.json` `exports`, public types, and barrel files. Upstream ports often\n  forget to re-export local additions.\n- **Cover non‑happy paths**: if you fixed error handling, timeouts, or fallback logic, add a test or at\n  least a manual checklist that exercises those paths.\n- **Check defaults and config merge order**: improvements often live in defaults. Confirm new defaults\n  didn’t revert (e.g., new config precedence, disabled features, tool lists).\n- **Audit env/shell behavior**: if you fixed execution or sandboxing, verify the new path still uses your\n  sanitized env and does not reintroduce alias/function overrides.\n- **Re-run targeted samples**: keep a minimal set of \"known good\" examples and run them after the port\n  (CLI flags, extension registration, tool execution).\n\n## 12) Detect and handle reworked code\n\nBefore porting a file, check if upstream significantly refactored it:\n\n```bash\n# Compare the file you're about to port against what you have locally\ngit diff HEAD upstream/main -- path/to/file.ts\n```\n\nIf the diff shows the file was **reworked** (not just patched):\n\n- New abstractions, renamed concepts, merged modules, changed data flow\n\nThen you must **read the new implementation thoroughly** before porting. Blind merging of reworked code loses functionality because:\n\nNote: interactive mode was recently split into controllers/utils/types. When backporting related changes, port updates into the individual files we created and ensure `interactive-mode.ts` wiring stays in sync.\n\n1. **Defaults change silently** - A new variable `defaultFoo = [a, b]` may replace an old `getAllFoo()` that returned `[a, b, c, d, e]`.\n\n2. **API options get dropped** - When systems merge (e.g., `hooks` + `customTools` → `extensions`), old options may not wire through to the new implementation.\n\n3. **Code paths go stale** - A renamed concept (e.g., `hookMessage` → `custom`) needs updates in every switch statement, type guard, and handler—not just the definition.\n\n4. **Context/capabilities shrink** - Old APIs may have exposed `{ logger, typebox, pi }` that new APIs forgot to include.\n\n### Semantic porting process\n\nWhen upstream reworked a module:\n\n1. **Read the old implementation** - Understand what it did, what options it accepted, what it exposed.\n\n2. **Read the new implementation** - Understand the new abstractions and how they map to old behavior.\n\n3. **Verify feature parity** - For each capability in the old code, confirm the new code preserves it or explicitly removes it.\n\n4. **Grep for stragglers** - Search for old names/concepts that may have been missed in switch statements, handlers, UI components.\n\n5. **Test the boundaries** - CLI flags, SDK options, event handlers, default values—these are where regressions hide.\n\n### Quick checks\n\n```bash\n# Find all uses of an old concept that may need updating\nrg \"oldConceptName\" --type ts\n\n# Compare default values between versions\ngit show upstream/main:path/to/file.ts | rg \"default|DEFAULT\"\n\n# Check if all enum/union values have handlers\nrg \"case \\\"\" path/to/file.ts\n```\n\n## 13) Quick audit checklist\n\nUse this as a final pass before you finish:\n\n- [ ] Import extensions follow the local package convention (no blanket `.js` stripping)\n- [ ] No newly introduced Node-only APIs unless they match an existing justified pattern\n- [ ] All package scopes updated\n- [ ] `package.json` scripts use Bun\n- [ ] Prompts are `.md` text imports (no inline prompt strings)\n- [ ] No internal/runtime `console.*` in coding-agent; CLI user-facing output is intentional\n- [ ] Assets load via Bun embed/import patterns, or through an existing intentional generation pipeline\n- [ ] Tests or checks run (or explicitly noted as blocked)\n- [ ] No functionality regressions (see sections 11-12)\n\n## 14) Commit message format\n\nWhen committing a backport, follow the repo format `<type>(scope): <past-tense description>` and keep the commit\nrange in the title.\n\n```\nfix(coding-agent): backported pi-mono changes (<from>..<to>)\n\npackages/<package>:\n- <type>: <description>\n- <type>: <description> (#<issue> by @<contributor>)\n\npackages/<other-package>:\n- <type>: <description>\n```\n\n**Example:**\n\n```\nfix(coding-agent): backported pi-mono changes (9f3eef65f..52532c7c0)\n\npackages/ai:\n- fix: handle \"sensitive\" stop reason from Anthropic API\n- fix: normalize tool call IDs with special characters for Responses API\n- fix: add overflow detection for Bedrock, MiniMax, Kimi providers\n- fix: 429 status is rate limiting, not context overflow\n\npackages/tui:\n- fix: refactored autocomplete state tracking\n- fix: file autocomplete should not trigger on empty text\n- fix: configurable autocomplete max visible items\n- fix: improved table column width calculation with word-aware wrapping\n\npackages/coding-agent:\n- fix: preserve external config.yml edits on save (#1046 by @nicobailonMD)\n- fix: resolve macOS NFD and curly quote variants in file paths\n```\n\n**Rules:**\n\n- Group changes by package\n- Use conventional commit types (`fix`, `feat`, `refactor`, `perf`, `docs`)\n- Include upstream issue/PR numbers and contributor attribution for external contributions\n- The commit range in the title helps track sync points\n\n## 15) Intentional Divergences\n\nOur fork has architectural decisions that differ from upstream. **Do not port these upstream patterns:**\n\n### UI Architecture\n\n| Upstream                                    | Our Fork                                                  | Reason                                                                |\n| ------------------------------------------- | --------------------------------------------------------- | --------------------------------------------------------------------- |\n| `FooterDataProvider` class                  | `StatusLineComponent`                                     | Simpler, integrated status line                                       |\n| `ctx.ui.setHeader()` / `ctx.ui.setFooter()` | No-op stubs in current extension contexts                 | Not currently wired to replace the TUI status/header UI               |\n| `ctx.ui.setEditorComponent()`               | No-op stubs in current extension contexts                 | Custom editor replacement is not currently wired                      |\n| `InteractiveModeOptions` options object     | Positional constructor args (options type still exported) | Keep constructor signature; update the type when upstream adds fields |\n\n### Component Naming\n\n| Upstream                     | Our Fork                |\n| ---------------------------- | ----------------------- |\n| `extension-input.ts`         | `hook-input.ts`         |\n| `extension-selector.ts`      | `hook-selector.ts`      |\n| `ExtensionInputComponent`    | `HookInputComponent`    |\n| `ExtensionSelectorComponent` | `HookSelectorComponent` |\n\n### API Naming\n\n| Upstream                                 | Our Fork                                 | Notes                                     |\n| ---------------------------------------- | ---------------------------------------- | ----------------------------------------- |\n| `sessionManager.appendSessionInfo(name)` | `sessionManager.setSessionName(name)`    | We use `sessionName` throughout           |\n| `sessionManager.getSessionName()`        | `sessionManager.getSessionName()`        | Same (we unified to match upstream's RPC) |\n| `agent.sessionName` / `setSessionName()` | `agent.sessionName` / `setSessionName()` | Same                                      |\n\n### File Consolidation\n\n| Upstream                                           | Our Fork                                                  | Reason                                        |\n| -------------------------------------------------- | --------------------------------------------------------- | --------------------------------------------- |\n| `clipboard.ts` + `clipboard-image.ts` (tool files) | `src/utils/clipboard.ts` backed by `@oh-my-pi/pi-natives` | Native implementation with a small TS wrapper |\n\n### Test Framework\n\n| Upstream                  | Our Fork                      |\n| ------------------------- | ----------------------------- |\n| `vitest` with `vi.mock()` | `bun:test` with `vi` from bun |\n| `node:test` assertions    | `expect()` matchers           |\n\n### Tool Architecture\n\n| Upstream                            | Our Fork                                                                                                      | Notes                                                     |\n| ----------------------------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- |\n| `createTool(cwd: string, options?)` | `createTools(session: ToolSession)` via `BUILTIN_TOOLS` registry                                              | Tool factories accept `ToolSession` and can return `null` |\n| Per-tool `*Operations` interfaces   | Only current per-tool override interfaces remain (for example `FindOperations`)                               | Used for SSH/remote overrides where present               |\n| Node.js `fs/promises` everywhere    | Bun file APIs for simple file writes/reads, `node:fs/promises` for dirs, selected sync `node:fs` where needed | Prefer Bun APIs when they simplify                        |\n\n### Auth Storage\n\n| Upstream                        | Our Fork                                    | Notes                                        |\n| ------------------------------- | ------------------------------------------- | -------------------------------------------- |\n| `proper-lockfile` + `auth.json` | `agent.db` (bun:sqlite)                     | Credentials stored exclusively in `agent.db` |\n| Single credential per provider  | Multi-credential with round-robin selection | Session affinity and backoff logic preserved |\n\n### Extensions\n\n| Upstream                      | Our Fork                                          |\n| ----------------------------- | ------------------------------------------------- |\n| `jiti` for TypeScript loading | Native Bun `import()`                             |\n| `pkg.pi` manifest field       | `pkg.omp` preferred; fallback to `pkg.pi` remains |\n\n### Skip These Upstream Features\n\nWhen porting, **skip** these files/features entirely:\n\n- `footer-data-provider.ts` — we use StatusLineComponent\n- `clipboard-image.ts` — image clipboard support is exposed through `src/utils/clipboard.ts` backed by `@oh-my-pi/pi-natives`\n- GitHub workflow files — we have our own CI\n- `models.generated.ts` — auto-generated, regenerate locally (as models.json instead)\n\n### Features We Added (Preserve These)\n\nThese exist in our fork but not upstream. **Never overwrite:**\n\n- `StatusLineComponent` in interactive mode\n- Multi-credential auth with session affinity\n- Capability-based discovery system (`defineCapability`, `registerProvider`, `loadCapability`, `skillCapability`, etc.)\n- MCP/Exa/SSH integrations\n- LSP writethrough for format-on-save\n- Bash interception (`checkBashInterception`)\n- Fuzzy path suggestions in read tool\n",
-	"porting-to-natives.md": "# Porting to pi-natives (N-API) — Field Notes\n\nThis is a practical guide for moving hot paths into `crates/pi-natives` and wiring them through the generated native package entrypoint. It exists to avoid the same failures happening twice.\n\n## When to port\n\nPort when any of these are true:\n\n- The hot path runs in render loops, tight UI updates, or large batches.\n- JS allocations dominate (string churn, regex backtracking, large arrays).\n- You already have a JS baseline and can benchmark both versions side by side.\n- The work is CPU-bound or blocking I/O that can run on the libuv thread pool.\n- The work is async I/O that can run on Tokio's runtime (for example shell execution).\n\nAvoid ports that depend on JS-only state or dynamic imports. N-API exports should be data-in/data-out. Long-running work should go through `task::blocking` (CPU-bound/blocking I/O) or `task::future` (async I/O) with cancellation where the caller needs `timeoutMs` or `AbortSignal`.\n\n## Current package shape\n\n`@oh-my-pi/pi-natives` no longer has a `packages/natives/src/<module>` TypeScript wrapper layer. The package root points at generated native artifacts:\n\n- runtime entry: `packages/natives/native/index.js`\n- types entry: `packages/natives/native/index.d.ts`\n- loader helpers: `packages/natives/native/loader-state.js`\n- embedded manifest: `packages/natives/native/embedded-addon.js`\n\nConsumers import directly from `@oh-my-pi/pi-natives`. The generated declarations are produced during `bun --cwd=packages/natives run build`.\n\n## Anatomy of a native export\n\n**Rust side:**\n\n- Implementation lives in `crates/pi-natives/src/<module>.rs`.\n- If you add a new module, register it in `crates/pi-natives/src/lib.rs`.\n- Export with `#[napi]`; snake_case exports are converted to camelCase automatically. Use explicit JS names only for true aliases/non-default names. Use `#[napi(object)]` for object-shaped structs.\n- For CPU-bound or blocking work, use `task::blocking(tag, cancel_token, work)`.\n- For async work that needs Tokio, use `task::future(env, tag, work)`.\n- Pass a `CancelToken` when the API exposes `timeoutMs` or `AbortSignal`, and call `heartbeat()` inside long loops.\n\n**Package/build side:**\n\n- `packages/natives/scripts/build-native.ts` runs napi-rs, installs the `.node` artifact, copies generated `index.js`/`index.d.ts`, and appends enum runtime exports.\n- `packages/natives/native/index.js` is the loader that chooses a candidate `.node` file and returns the loaded addon.\n- `packages/natives/package.json` exposes only the package root (`@oh-my-pi/pi-natives`).\n\n**Consumer side:**\n\n- Update direct imports/callsites in `packages/coding-agent` or `packages/tui` when the new export replaces a JS implementation.\n- Keep higher-level policy in consumers unless it belongs in the native primitive itself.\n\n## Porting checklist\n\n1. **Add the Rust implementation**\n\n- Put the core logic in a plain Rust function.\n- If it is a new module, add it to `crates/pi-natives/src/lib.rs`.\n- Expose it with `#[napi]` so the default snake_case -> camelCase mapping stays consistent.\n- Keep signatures owned and simple: `String`, `Vec<String>`, `Uint8Array`, `Either<JsString, Uint8Array>`, or `#[napi(object)]` structs.\n- For CPU-bound or blocking work, use `task::blocking`; for async work, use `task::future`.\n- If exposing cancellation, include `timeout_ms: Option<u32>` and `signal: Option<Unknown<'env>>` in options, create `CancelToken::new(...)`, and heartbeat in long loops.\n\n2. **Build generated bindings**\n\n- Run `bun --cwd=packages/natives run build`.\n- Confirm the generated `packages/natives/native/index.d.ts` includes the new export with the intended JS name/signature.\n- Confirm `packages/natives/native/index.js` still has generated enum exports appended when enum changes are involved.\n\n3. **Update consumers**\n\n- Import the new export directly from `@oh-my-pi/pi-natives`.\n- Replace only callsites where the native implementation is faster/equivalent and preserves behavior.\n- Remove obsolete JS implementation code in the same change when the native path becomes canonical.\n\n4. **Add benchmarks**\n\n- Put benchmarks next to the owning package (`packages/tui/bench`, `packages/natives/bench`, or `packages/coding-agent/bench`).\n- Include a JS baseline and native version in the same run.\n- Use `Bun.nanoseconds()` and a fixed iteration count.\n- Keep benchmark inputs realistic for the hot path.\n\n5. **Run focused verification**\n\n- Build the native package.\n- Run the benchmark.\n- Run the narrow tests or scenario covering the changed export/callsites.\n\n## Pain points and how to avoid them\n\n### 1) Stale platform/variant artifacts\n\nThe loader probes platform-tagged artifacts in deterministic order. For x64, selected variant candidates are tried before the unsuffixed default fallback:\n\n- `modern`: `pi_natives.<tag>-modern.node`, then `...-baseline.node`, then `pi_natives.<tag>.node`.\n- `baseline`: `pi_natives.<tag>-baseline.node`, then `pi_natives.<tag>.node`.\n\nNon-x64 uses `pi_natives.<tag>.node`.\n\nCompiled binaries also probe `<getNativesDir()>/<version>/...` and a legacy user-data directory before package/executable locations. If any earlier candidate is stale, a new export may appear missing.\n\n**Fix:** remove stale candidate/cache files and rebuild.\n\n```bash\nrm packages/natives/native/pi_natives.<platform>-<arch>.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-modern.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-baseline.node\nbun --cwd=packages/natives run build\n```\n\nFor compiled binaries, delete the versioned addon cache shown in the loader error (normally under `~/.omp/natives/<version>` unless `$XDG_DATA_HOME/omp` is used).\n\n### 2) Generated types do not match loaded binary\n\nThis can happen when `native/index.d.ts` was regenerated but the `.node` file being loaded is stale or from a different platform/variant.\n\nVerify the loaded export set from the actual candidate path:\n\n```bash\nbun -e 'const tag = `${process.platform}-${process.arch}`; const mod = require(`./packages/natives/native/pi_natives.${tag}.node`); console.log(Object.keys(mod).sort())'\n```\n\nFix the build/candidate mismatch. Do not paper over it with optional consumer checks if the export is required.\n\n### 3) Rust signature mismatch\n\nKeep N-API signatures simple and owned. Avoid borrowed references like `&str` in public exports. If you need structured data, use `#[napi(object)]` structs. If you need callbacks, use napi-rs `ThreadsafeFunction` and keep callback error/value behavior explicit.\n\n### 4) Enum runtime exports\n\nnapi-rs declarations alone are not enough for JS callers that use enum objects at runtime. `scripts/gen-enums.ts` appends enum objects to `native/index.js`. If you add or change a native enum, verify both `native/index.d.ts` and the generated enum export block in `native/index.js`.\n\n### 5) Benchmarking mistakes\n\n- Do not compare different inputs or allocations.\n- Keep JS and native using identical input arrays.\n- Run both in the same benchmark file to avoid skew.\n- Include enough iterations to smooth startup noise, but keep inputs realistic.\n\n## Benchmark template\n\n```ts\nconst ITERATIONS = 2000;\n\nfunction bench(name: string, fn: () => void): number {\n  const start = Bun.nanoseconds();\n  for (let i = 0; i < ITERATIONS; i++) fn();\n  const elapsed = (Bun.nanoseconds() - start) / 1e6;\n  console.log(\n    `${name}: ${elapsed.toFixed(2)}ms total (${(elapsed / ITERATIONS).toFixed(6)}ms/op)`,\n  );\n  return elapsed;\n}\n\nbench(\"feature/js\", () => {\n  jsImpl(sample);\n});\n\nbench(\"feature/native\", () => {\n  nativeImpl(sample);\n});\n```\n\n## Verification checklist\n\n- Generated `native/index.d.ts` includes the new export and intended TS signature.\n- The loaded `.node` file's `Object.keys(require(candidate))` includes the new export.\n- Runtime enum objects are present when the change adds/changes enums.\n- Bench numbers are recorded in the PR/notes.\n- Call sites are updated only if native is faster/equal and behavior-compatible.\n- Obsolete JS code is removed when the native implementation becomes canonical.\n\n## Rule of thumb\n\n- If native is slower, do not switch callsites. Keep or remove the export based on whether it has a near-term owner.\n- If native is faster and behavior-compatible, switch callsites and keep a benchmark to catch regressions.\n",
+	"porting-to-natives.md": "# Porting to pi-natives (N-API) — Field Notes\n\nThis is a practical guide for moving hot paths into `crates/pi-natives` and wiring them through the generated native package entrypoint. It exists to avoid the same failures happening twice.\n\n## When to port\n\nPort when any of these are true:\n\n- The hot path runs in render loops, tight UI updates, or large batches.\n- JS allocations dominate (string churn, regex backtracking, large arrays).\n- You already have a JS baseline and can benchmark both versions side by side.\n- The work is CPU-bound or blocking I/O that can run on the libuv thread pool.\n- The work is async I/O that can run on Tokio's runtime (for example shell execution).\n\nAvoid ports that depend on JS-only state or dynamic imports. N-API exports should be data-in/data-out. Long-running work should go through `task::blocking` (CPU-bound/blocking I/O) or `task::future` (async I/O) with cancellation where the caller needs `timeoutMs` or `AbortSignal`.\n\n## Current package shape\n\n`@oh-my-pi/pi-natives` no longer has a `packages/natives/src/<module>` TypeScript wrapper layer. The package root points at generated native artifacts:\n\n- runtime entry: `packages/natives/native/index.js`\n- types entry: `packages/natives/native/index.d.ts`\n- loader helpers: `packages/natives/native/loader-state.js`\n- embedded manifest: `packages/natives/native/embedded-addon.js`\n\nConsumers import directly from `@oh-my-pi/pi-natives`. The generated declarations are produced during `bun --cwd=packages/natives run build`.\n\n## Anatomy of a native export\n\n**Rust side:**\n\n- Implementation lives in `crates/pi-natives/src/<module>.rs`.\n- If you add a new module, register it in `crates/pi-natives/src/lib.rs`.\n- Export with `#[napi]`; snake_case exports are converted to camelCase automatically. Use explicit JS names only for true aliases/non-default names. Use `#[napi(object)]` for object-shaped structs.\n- For CPU-bound or blocking work, use `task::blocking(tag, cancel_token, work)`.\n- For async work that needs Tokio, use `task::future(env, tag, work)`.\n- Pass a `CancelToken` when the API exposes `timeoutMs` or `AbortSignal`, and call `heartbeat()` inside long loops.\n\n**Package/build side:**\n\n- `packages/natives/scripts/build-native.ts` runs napi-rs, installs the `.node` artifact, copies generated `index.js`/`index.d.ts`, and appends enum runtime exports.\n- `packages/natives/native/index.js` is the loader that chooses a candidate `.node` file and returns the loaded addon.\n- `packages/natives/package.json` exposes only the package root (`@oh-my-pi/pi-natives`) as the import surface. At publish time the binaries are split out: the core ships the loader only (no `.node`), and each platform's `.node` is published as an optional-dependency leaf package `@oh-my-pi/pi-natives-<tag>` (`scripts/ci-release-publish.ts` + `packages/natives/scripts/gen-npm-packages.ts`). This is transparent to importers — you still `import` from `@oh-my-pi/pi-natives`.\n\n**Consumer side:**\n\n- Update direct imports/callsites in `packages/coding-agent` or `packages/tui` when the new export replaces a JS implementation.\n- Keep higher-level policy in consumers unless it belongs in the native primitive itself.\n\n## Porting checklist\n\n1. **Add the Rust implementation**\n\n- Put the core logic in a plain Rust function.\n- If it is a new module, add it to `crates/pi-natives/src/lib.rs`.\n- Expose it with `#[napi]` so the default snake_case -> camelCase mapping stays consistent.\n- Keep signatures owned and simple: `String`, `Vec<String>`, `Uint8Array`, `Either<JsString, Uint8Array>`, or `#[napi(object)]` structs.\n- For CPU-bound or blocking work, use `task::blocking`; for async work, use `task::future`.\n- If exposing cancellation, include `timeout_ms: Option<u32>` and `signal: Option<Unknown<'env>>` in options, create `CancelToken::new(...)`, and heartbeat in long loops.\n\n2. **Build generated bindings**\n\n- Run `bun --cwd=packages/natives run build`.\n- Confirm the generated `packages/natives/native/index.d.ts` includes the new export with the intended JS name/signature.\n- Confirm `packages/natives/native/index.js` still has generated enum exports appended when enum changes are involved.\n\n3. **Update consumers**\n\n- Import the new export directly from `@oh-my-pi/pi-natives`.\n- Replace only callsites where the native implementation is faster/equivalent and preserves behavior.\n- Remove obsolete JS implementation code in the same change when the native path becomes canonical.\n\n4. **Add benchmarks**\n\n- Put benchmarks next to the owning package (`packages/tui/bench`, `packages/natives/bench`, or `packages/coding-agent/bench`).\n- Include a JS baseline and native version in the same run.\n- Use `Bun.nanoseconds()` and a fixed iteration count.\n- Keep benchmark inputs realistic for the hot path.\n\n5. **Run focused verification**\n\n- Build the native package.\n- Run the benchmark.\n- Run the narrow tests or scenario covering the changed export/callsites.\n\n## Pain points and how to avoid them\n\n### 1) Stale platform/variant artifacts\n\nThe loader probes platform-tagged artifacts in deterministic order. For x64, selected variant candidates are tried before the unsuffixed default fallback:\n\n- `modern`: `pi_natives.<tag>-modern.node`, then `...-baseline.node`, then `pi_natives.<tag>.node`.\n- `baseline`: `pi_natives.<tag>-baseline.node`, then `pi_natives.<tag>.node`.\n\nNon-x64 uses `pi_natives.<tag>.node`.\n\nCompiled binaries also probe `<getNativesDir()>/<version>/...` and a legacy user-data directory before package/executable locations. If any earlier candidate is stale, a new export may appear missing.\n\n**Fix:** remove stale candidate/cache files and rebuild.\n\n```bash\nrm packages/natives/native/pi_natives.<platform>-<arch>.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-modern.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-baseline.node\nbun --cwd=packages/natives run build\n```\n\nFor compiled binaries, delete the versioned addon cache shown in the loader error (normally under `~/.omp/natives/<version>` unless `$XDG_DATA_HOME/omp` is used).\n\n### 2) Generated types do not match loaded binary\n\nThis can happen when `native/index.d.ts` was regenerated but the `.node` file being loaded is stale or from a different platform/variant.\n\nVerify the loaded export set from the actual candidate path:\n\n```bash\nbun -e 'const tag = `${process.platform}-${process.arch}`; const mod = require(`./packages/natives/native/pi_natives.${tag}.node`); console.log(Object.keys(mod).sort())'\n```\n\nFix the build/candidate mismatch. Do not paper over it with optional consumer checks if the export is required.\n\n### 3) Rust signature mismatch\n\nKeep N-API signatures simple and owned. Avoid borrowed references like `&str` in public exports. If you need structured data, use `#[napi(object)]` structs. If you need callbacks, use napi-rs `ThreadsafeFunction` and keep callback error/value behavior explicit.\n\n### 4) Enum runtime exports\n\nnapi-rs declarations alone are not enough for JS callers that use enum objects at runtime. `scripts/gen-enums.ts` appends enum objects to `native/index.js`. If you add or change a native enum, verify both `native/index.d.ts` and the generated enum export block in `native/index.js`.\n\n### 5) Benchmarking mistakes\n\n- Do not compare different inputs or allocations.\n- Keep JS and native using identical input arrays.\n- Run both in the same benchmark file to avoid skew.\n- Include enough iterations to smooth startup noise, but keep inputs realistic.\n\n## Benchmark template\n\n```ts\nconst ITERATIONS = 2000;\n\nfunction bench(name: string, fn: () => void): number {\n  const start = Bun.nanoseconds();\n  for (let i = 0; i < ITERATIONS; i++) fn();\n  const elapsed = (Bun.nanoseconds() - start) / 1e6;\n  console.log(\n    `${name}: ${elapsed.toFixed(2)}ms total (${(elapsed / ITERATIONS).toFixed(6)}ms/op)`,\n  );\n  return elapsed;\n}\n\nbench(\"feature/js\", () => {\n  jsImpl(sample);\n});\n\nbench(\"feature/native\", () => {\n  nativeImpl(sample);\n});\n```\n\n## Verification checklist\n\n- Generated `native/index.d.ts` includes the new export and intended TS signature.\n- The loaded `.node` file's `Object.keys(require(candidate))` includes the new export.\n- Runtime enum objects are present when the change adds/changes enums.\n- Bench numbers are recorded in the PR/notes.\n- Call sites are updated only if native is faster/equal and behavior-compatible.\n- Obsolete JS code is removed when the native implementation becomes canonical.\n\n## Rule of thumb\n\n- If native is slower, do not switch callsites. Keep or remove the export based on whether it has a near-term owner.\n- If native is faster and behavior-compatible, switch callsites and keep a benchmark to catch regressions.\n",
 	"provider-streaming-internals.md": "# Provider streaming internals\n\nThis document explains how token/tool streaming is normalized in `@oh-my-pi/pi-ai`, then propagated through `@oh-my-pi/pi-agent-core` and `coding-agent` session events.\n\n## End-to-end flow\n\n1. `streamSimple()` (`packages/ai/src/stream.ts`) maps generic options and dispatches to a provider stream function.\n2. Provider stream functions translate provider-native stream events into the unified `AssistantMessageEvent` sequence. Current built-ins include Anthropic, OpenAI Responses/Completions/Codex/Azure Responses, Google Gemini/Gemini CLI/Vertex, Bedrock Converse, Ollama, Cursor, plus GitLab Duo/Kimi wrappers and extension-registered custom APIs.\n3. Each provider pushes events into `AssistantMessageEventStream` (`packages/ai/src/utils/event-stream.ts`), which throttles delta events and exposes:\n   - async iteration for incremental updates\n   - `result()` for final `AssistantMessage`\n4. `agentLoop` (`packages/agent/src/agent-loop.ts`) consumes those events, mutates in-flight assistant state, and emits `message_update` events carrying the raw `assistantMessageEvent`.\n5. `AgentSession` (`packages/coding-agent/src/session/agent-session.ts`) subscribes to agent events, persists messages, drives extension hooks, and applies session behaviors (retry, compaction, TTSR, streaming-edit abort checks).\n\n## Unified stream contract in `@oh-my-pi/pi-ai`\n\nAll providers emit the same shape (`AssistantMessageEvent` in `packages/ai/src/types.ts`):\n\n- `start`\n- content block lifecycle triplets:\n  - text: `text_start` → `text_delta`\\* → `text_end`\n  - thinking: `thinking_start` → `thinking_delta`\\* → `thinking_end`\n  - tool call: `toolcall_start` → `toolcall_delta`\\* → `toolcall_end`\n- terminal event:\n  - `done` with `reason: \"stop\" | \"length\" | \"toolUse\"`\n  - or `error` with `reason: \"aborted\" | \"error\"`\n\n`AssistantMessageEventStream` guarantees:\n\n- final result is resolved by terminal event (`done` or `error`)\n- deltas are batched/throttled (~50ms)\n- buffered deltas are flushed before non-delta events and before completion\n\n## Delta throttling and harmonization behavior\n\n`AssistantMessageEventStream` treats `text_delta`, `thinking_delta`, and `toolcall_delta` as mergeable events:\n\n- buffered deltas are merged only when **type + contentIndex** match\n- merge keeps the latest `partial` snapshot\n- non-delta events force immediate flush\n\nThis smooths high-frequency provider streams for TUI/event consumers, but is not provider backpressure: providers still produce at full speed, while the local stream buffers.\n\n## Provider normalization details\n\n## Anthropic (`anthropic-messages`)\n\nSource: `packages/ai/src/providers/anthropic.ts`\n\nNormalization points:\n\n- `message_start` initializes usage (input/output/cache tokens)\n- `content_block_start` maps to text/thinking/toolcall starts\n- `content_block_delta` maps:\n  - `text_delta` → `text_delta`\n  - `thinking_delta` → `thinking_delta`\n  - `input_json_delta` → `toolcall_delta`\n  - `signature_delta` updates `thinkingSignature` only (no event)\n- `content_block_stop` emits corresponding `*_end`\n- `message_delta.stop_reason` maps via `mapStopReason()`\n\nTool-call argument streaming:\n\n- each tool block carries internal `partialJson`\n- every JSON delta appends to `partialJson`\n- `arguments` are reparsed on each delta via `parseStreamingJson()`\n- `toolcall_end` reparses once more, then strips `partialJson`\n\n## OpenAI Responses family (`openai-responses`, `openai-codex-responses`, `azure-openai-responses`)\n\nSources: `packages/ai/src/providers/openai-responses.ts`, `openai-codex-responses.ts`, and `azure-openai-responses.ts`\n\nNormalization points:\n\n- `response.output_item.added` starts reasoning/text/function-call blocks\n- reasoning summary events (`response.reasoning_summary_text.delta`) become `thinking_delta`\n- output/refusal deltas become `text_delta`\n- `response.function_call_arguments.delta` becomes `toolcall_delta`\n- `response.output_item.done` emits `thinking_end` / `text_end` / `toolcall_end`\n- `response.completed` maps status to stop reason and usage\n\nTool-call argument streaming:\n\n- same `partialJson` accumulation pattern as Anthropic\n- providers that send only `response.function_call_arguments.done` still populate final args\n- tool call IDs are normalized as `\"<call_id>|<item_id>\"`\n\n## Google Generative AI (`google-generative-ai`)\n\nSource: `packages/ai/src/providers/google.ts`\n\nNormalization points:\n\n- iterates `candidate.content.parts`\n- text parts are split into thinking vs text by `isThinkingPart(part)`\n- block transitions close previous block before starting a new one\n- `part.functionCall` is treated as a complete tool call (start/delta/end emitted immediately)\n- finish reason mapped by `mapStopReason()` from `google-shared.ts`\n\nTool-call argument streaming:\n\n- function call args arrive as structured object, not incremental JSON text\n- implementation emits one synthetic `toolcall_delta` containing `JSON.stringify(arguments)`\n- no partial JSON parser needed for Google in this path\n\n## Partial tool-call JSON accumulation and recovery\n\nShared behavior for Anthropic/OpenAI Responses uses `parseStreamingJson()` (`packages/ai/src/utils/json-parse.ts`):\n\n1. try `JSON.parse`\n2. fallback to `partial-json` parser for incomplete fragments\n3. if both fail, return `{}`\n\nImplications:\n\n- malformed or truncated argument deltas do not crash stream processing immediately\n- in-progress `arguments` may temporarily be `{}`\n- later valid deltas can recover structured arguments because parsing is retried on every append\n- final `toolcall_end` performs one more parse attempt before emission\n\n## Stop reasons vs transport/runtime errors\n\nProvider stop reasons are mapped to normalized `stopReason`:\n\n- Anthropic: `end_turn`→`stop`, `max_tokens`→`length`, `tool_use`→`toolUse`, safety/refusal cases→`error`\n- OpenAI Responses: `completed`→`stop`, `incomplete`→`length`, `failed/cancelled`→`error`\n- Google: `STOP`→`stop`, `MAX_TOKENS`→`length`, safety/prohibited/malformed-function-call classes→`error`\n\nError semantics are split in two stages:\n\n1. **Model completion semantics** (provider reported finish reason/status)\n2. **Transport/runtime failure** (network/client/parser/abort exceptions)\n\nIf provider stream throws or signals failure, each provider wrapper catches and emits terminal `error` event with:\n\n- `stopReason = \"aborted\"` when abort signal is set\n- otherwise `stopReason = \"error\"`\n- `errorMessage = formatErrorMessageWithRetryAfter(error)`\n\n## Malformed chunk / SSE parse failure behavior\n\nFor these provider paths, chunk/SSE framing is handled by vendor SDK streams (Anthropic SDK, OpenAI SDK, Google SDK). This code does not implement a custom SSE decoder here.\n\nObserved behavior in current implementation:\n\n- malformed chunk/SSE parsing at SDK level surfaces as an exception or stream `error` event\n- provider wrapper converts that into unified terminal `error` event\n- no provider-specific resume/retry inside the stream function itself\n- higher-level retries are handled in `AgentSession` auto-retry logic (message-level retry, not stream-chunk replay)\n\n## Cancellation boundaries\n\nCancellation is layered:\n\n- AI provider request: `options.signal` is passed into provider client stream call.\n- Provider wrapper: after stream loop, aborted signal forces error path (`\"Request was aborted\"`).\n- Agent loop: checks `signal.aborted` before handling each provider event and can synthesize an aborted assistant message from the latest partial.\n- Session/agent controls: `AgentSession.abort()` -> `agent.abort()` -> shared abort controller cancellation.\n\nTool execution cancellation is separate from model stream cancellation:\n\n- tool runners use `AbortSignal.any([agentSignal, steeringAbortSignal])`\n- steering interrupts can abort remaining tool execution while preserving already-produced tool results\n\n## Backpressure boundaries\n\nThere is no hard backpressure mechanism between provider SDK stream and downstream consumers:\n\n- `EventStream` uses in-memory queues with no max size\n- throttling reduces UI update rate but does not slow provider intake\n- if consumers lag significantly, queued events can grow until completion\n\nCurrent design favors responsiveness and simple ordering over bounded-buffer flow control.\n\n## How stream events surface as agent/session events\n\n`agentLoop.streamAssistantResponse()` bridges `AssistantMessageEvent` to `AgentEvent`:\n\n- on `start`: pushes placeholder assistant message and emits `message_start`\n- on block events (`text_*`, `thinking_*`, `toolcall_*`): updates last assistant message, emits `message_update` with raw `assistantMessageEvent`\n- on terminal (`done`/`error`): resolves final message from `response.result()`, emits `message_end`\n\n`AgentSession` then consumes those events for session-level behaviors:\n\n- TTSR watches `message_update.assistantMessageEvent` for `text_delta`, `thinking_delta`, and `toolcall_delta`\n- streaming edit guard inspects `toolcall_delta`/`toolcall_end` on `edit` calls and can abort early\n- persistence writes finalized messages at `message_end`\n- auto-retry examines assistant `stopReason === \"error\"` plus `errorMessage` heuristics\n\n## Unified vs provider-specific responsibilities\n\nUnified (common contract):\n\n- event shape (`AssistantMessageEvent`)\n- final result extraction (`done`/`error`)\n- delta throttling + merge rules\n- agent/session event propagation model\n\nProvider-specific (not fully abstracted):\n\n- upstream event taxonomies and mapping logic\n- stop-reason translation tables\n- tool-call ID conventions\n- reasoning/thinking block semantics and signatures\n- usage token semantics and availability timing\n- message conversion constraints per API\n\n## Implementation files\n\n- [`../../ai/src/stream.ts`](../packages/ai/src/stream.ts) — provider dispatch, option mapping, API key/session plumbing, custom API dispatch, and provider-specific credential handling.\n- [`../../ai/src/utils/event-stream.ts`](../packages/ai/src/utils/event-stream.ts) — generic stream queue + assistant delta throttling.\n- [`../../ai/src/utils/json-parse.ts`](../packages/ai/src/utils/json-parse.ts) — partial JSON parsing for streamed tool arguments.\n- [`../../ai/src/providers/anthropic.ts`](../packages/ai/src/providers/anthropic.ts) — Anthropic event translation and tool JSON delta accumulation.\n- [`../../ai/src/providers/openai-responses.ts`](../packages/ai/src/providers/openai-responses.ts), [`openai-codex-responses.ts`](../packages/ai/src/providers/openai-codex-responses.ts), [`azure-openai-responses.ts`](../packages/ai/src/providers/azure-openai-responses.ts) — Responses-family event translation and status mapping.\n- [`../../ai/src/providers/google.ts`](../packages/ai/src/providers/google.ts), [`google-gemini-cli.ts`](../packages/ai/src/providers/google-gemini-cli.ts), [`google-vertex.ts`](../packages/ai/src/providers/google-vertex.ts) — Gemini stream chunk-to-block translation variants.\n- [`../../ai/src/providers/google-shared.ts`](../packages/ai/src/providers/google-shared.ts) — Gemini finish-reason mapping and shared conversion rules.\n- [`../../ai/src/providers/amazon-bedrock.ts`](../packages/ai/src/providers/amazon-bedrock.ts), [`openai-completions.ts`](../packages/ai/src/providers/openai-completions.ts), [`ollama.ts`](../packages/ai/src/providers/ollama.ts), [`cursor.ts`](../packages/ai/src/providers/cursor.ts) — additional built-in stream adapters using the same event contract.\n- [`../../agent/src/agent-loop.ts`](../packages/agent/src/agent-loop.ts) — provider stream consumption and `message_update` bridging.\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — session-level handling of streaming updates, abort, retry, and persistence.\n",
 	"python-repl.md": "# Eval Tool Python Backend\n\nThis document describes the Python execution stack in `packages/coding-agent`.\nIt covers tool behavior, runner lifecycle, environment handling, execution semantics, output rendering, supported magics, and operational failure modes.\n\n## Scope and Key Files\n\n- Tool surface: `src/tools/eval.ts`\n- Session/per-call kernel orchestration: `src/eval/py/executor.ts`\n- Subprocess kernel client: `src/eval/py/kernel.ts`\n- Python wrapper / NDJSON server: `src/eval/py/runner.py`\n- Prelude helpers loaded into every kernel: `src/eval/py/prelude.py`\n- MIME bundle renderer (text + structured outputs): `src/eval/py/display.ts`\n- Interactive-mode renderer for user-triggered Python runs: `src/modes/components/eval-execution.ts`\n- Runtime/env filtering and Python resolution: `src/eval/py/runtime.ts`\n\n## What eval's Python backend is\n\nThe `eval` tool executes one or more Python cells inside a long-lived `python3` subprocess that speaks NDJSON over stdin/stdout. No Jupyter, no kernel gateway, no extra pip dependencies — a vanilla Python 3.8+ interpreter is enough. Rich `display()` output (PIL, pandas, plotly, matplotlib figures) keeps working because the wrapper reimplements the MIME-bundle dispatch that IPython previously provided.\n\nTool params:\n\n```ts\n{\n  cells: Array<{ code: string; title?: string }>;\n  timeout?: number; // seconds, clamped to 1..600, default 30\n  reset?: boolean; // reset selected runtime before the first cell only\n}\n```\n\nThe tool is `concurrency = \"exclusive\"` for a session, so calls do not overlap.\n\n## Kernel lifecycle\n\nEach kernel is a single Python subprocess: `python -u <runner.py>`. The runner is bundled with the host binary (Bun text import), written to `~/.omp/python-env`-adjacent tmp cache once per script-hash, and reused by every subsequent spawn.\n\nKernel startup sequence:\n\n1. Availability check (`checkPythonKernelAvailability`) — verifies that a Python interpreter resolves and runs.\n2. Spawn `python -u runner.py` with filtered env and `cwd`.\n3. Send an init request that runs `os.chdir(cwd)`, injects env entries, and adds `cwd` to `sys.path`.\n4. Execute `PYTHON_PRELUDE` (idempotent — only initializes once per process).\n\nKernel shutdown:\n\n- Send `{\"type\": \"exit\"}` over stdin.\n- Wait for process exit with `SHUTDOWN_GRACE_MS` budget.\n- Escalate to `SIGTERM` and finally `SIGKILL` if the process does not exit in time.\n\n## Wire protocol (NDJSON, host ↔ runner)\n\nOne JSON object per line, UTF-8, `\\n` terminated.\n\nHost → runner:\n\n```jsonc\n{\"id\": \"<reqId>\", \"code\": \"<source>\", \"silent\": false, \"storeHistory\": true}\n{\"type\": \"exit\"}\n```\n\nRunner → host:\n\n```jsonc\n{\"type\": \"started\",  \"id\": \"<reqId>\"}\n{\"type\": \"stdout\",   \"id\": \"<reqId>\", \"data\": \"...\"}\n{\"type\": \"stderr\",   \"id\": \"<reqId>\", \"data\": \"...\"}\n{\"type\": \"display\",  \"id\": \"<reqId>\", \"bundle\": {<mime>: <value>}}\n{\"type\": \"result\",   \"id\": \"<reqId>\", \"bundle\": {<mime>: <value>}}\n{\"type\": \"error\",    \"id\": \"<reqId>\", \"ename\": \"...\", \"evalue\": \"...\", \"traceback\": [\"...\"]}\n{\"type\": \"done\",     \"id\": \"<reqId>\", \"status\": \"ok\"|\"error\", \"executionCount\": N, \"cancelled\": false}\n```\n\nStatus events the prelude emits (e.g. `_emit_status(\"find\", count=…)`) ship inside display bundles under `application/x-omp-status` so the existing TUI status renderer keeps working.\n\n## Magics\n\nThe runner's source transformer rewrites IPython-style magics to plain Python calls before parsing. Supported set:\n\n| Magic | Effect |\n| --- | --- |\n| `%pip <args>` | `python -m pip <args>` with live streaming output. Newly installed packages are evicted from `sys.modules` so the next `import` picks up the fresh install. |\n| `%cd <path>` | `os.chdir(path)` (with `~` expansion); emits status event. |\n| `%pwd` | Returns `os.getcwd()`. |\n| `%ls [path]` | Returns `sorted(os.listdir(path))`. |\n| `%env [KEY[=VAL]]` | List, read, or set env vars (matches prelude `env()` semantics). |\n| `%set_env KEY VALUE` | Set `os.environ[KEY]`. |\n| `%time <expr>` / `%timeit <expr>` | Time the expression; emits status event with elapsed ms. |\n| `%who` / `%whos` | List user-namespace names. |\n| `%reset` | Clear user globals and re-inject prelude. |\n| `%load <path>` | Read a file into a fresh cell and execute. |\n| `%run <path>` | `runpy.run_path` and merge globals back. |\n| `%%bash` / `%%sh` | Run the cell body via `bash`/`sh`. |\n| `%%capture [name]` | Run body with stdout/stderr captured into `name`. |\n| `%%timeit` | Time the cell body. |\n| `%%writefile <path>` | Write body to file. |\n| `!cmd` / `var = !cmd` | Run command via subprocess shell; returns an SList-style result with `.n` / `.s` helpers. |\n| `var = %name args` | Assignment forms work for line magics and `!cmd`. |\n\nUnknown magic names raise `NameError: UsageError: ...` inside the cell.\n\n## Session persistence semantics\n\n`python.kernelMode` controls retained kernel reuse:\n\n- `session` (default)\n  - Reuses kernel sessions keyed by session file plus cwd when a session file exists; otherwise by cwd.\n  - Execution is serialized per session via a queue.\n  - Idle sessions are evicted after 5 minutes.\n  - At most 4 sessions; oldest is evicted on overflow.\n  - Heartbeat checks detect dead kernels.\n  - Auto-restart allowed once; repeated crash ⇒ hard failure.\n- `per-call`\n  - Spawns a fresh subprocess for each request.\n  - Shuts the subprocess down after the request.\n  - No cross-call state persistence.\n\n### Multi-cell behavior in a single tool call\n\nCells run sequentially in the same kernel instance for that tool call.\n\nIf an intermediate cell fails:\n\n- Earlier cell state remains in memory.\n- Tool returns a targeted error indicating which cell failed.\n- Later cells are not executed.\n\n`reset=true` only applies to the first cell execution in that call.\n\n## Environment filtering and runtime resolution\n\nEnvironment is filtered before launching the runner:\n\n- Allowlist includes core vars like `PATH`, `HOME`, locale vars, `VIRTUAL_ENV`, `PYTHONPATH`, etc.\n- Allow-prefixes: `LC_`, `XDG_`, `PI_`\n- Denylist strips common API keys (OpenAI/Anthropic/Gemini/etc.)\n\nRuntime selection order:\n\n1. Active/located venv (`VIRTUAL_ENV`, then `<cwd>/.venv`, `<cwd>/venv`)\n2. Managed venv at `~/.omp/python-env`\n3. `python` or `python3` on PATH\n\nWhen a venv is selected, its bin/Scripts path is prepended to `PATH`.\n\nThe runner additionally receives `PYTHONUNBUFFERED=1` and `PYTHONIOENCODING=utf-8` so streamed output reaches the host promptly.\n\n## Tool availability and mode selection\n\n`eval.py` / `eval.js` (both default `true`) plus optional `PI_PY` override controls eval backend exposure:\n\n- Python backend only (`eval.py=true`, `eval.js=false`)\n- JavaScript backend only (`eval.py=false`, `eval.js=true`)\n- both backends\n\n`PI_PY` accepted values:\n\n- `0` / `bash` → JavaScript backend only\n- `1` / `py` → Python backend only\n- `mix` / `both` → both backends\n\nIf Python preflight fails and `eval.js` is enabled, `eval` remains available and dispatches to JavaScript unless `language: \"python\"` is explicitly requested.\n\n## Execution flow and cancellation/timeout\n\n### Tool-level timeout\n\n`eval` timeout is in seconds, default 30, clamped to `1..600`. The tool combines caller abort signal and timeout signal with `AbortSignal.any(...)`.\n\n### Kernel execution cancellation\n\nOn abort/timeout:\n\n- The host sends `kill(\"SIGINT\")` to the runner subprocess.\n- The runner's exec-time signal handler raises `KeyboardInterrupt` inside the user code.\n- Result includes `cancelled=true`; timeout path annotates output as `Command timed out after <n> seconds`.\n- Between requests the runner installs `SIG_IGN` for SIGINT so a stray cancel does not tear down the kernel.\n\nIf a second cancel is required (runner stuck in C code), the host escalates to `SIGTERM` and the session restarts on the next call.\n\n### stdin behavior\n\nInteractive stdin is not supported. The runner does not forward `input()` prompts; user code that calls `input()` blocks until cancellation.\n\n## Output capture and rendering\n\n### Captured output classes\n\nFrom runner frames:\n\n- `stdout` / `stderr` → plain text chunks\n- `display` / `result` → rich display handling (MIME bundle)\n- `error` → traceback text\n- `application/x-omp-status` MIME inside `display` → structured status events\n\nDisplay MIME precedence:\n\n1. `text/markdown`\n2. `text/plain`\n3. `text/html` (converted to basic markdown)\n\nAdditionally captured as structured outputs:\n\n- `application/json` → JSON tree data\n- `image/png` / `image/jpeg` → image payloads\n- `application/x-omp-status` → status events\n\n### Matplotlib\n\nThe runner sets `MPLBACKEND=Agg` as an environ default so figures render off-screen. After every cell, `pyplot.get_fignums()` is iterated; each figure is saved to PNG, emitted as an `image/png` display, and closed.\n\n### Storage and truncation\n\nOutput is streamed through `OutputSink` and may be persisted to artifact storage. Tool results can include truncation metadata and `artifact://<id>` for full output recovery.\n\n### Renderer behavior\n\n- Tool renderer (`eval.ts`):\n  - shows code-cell blocks with per-cell status\n  - collapsed preview defaults to 10 lines\n  - supports expanded mode for full output and richer status detail\n- Interactive renderer (`eval-execution.ts`):\n  - used for user-triggered Python execution in TUI\n  - collapsed preview defaults to 20 lines\n  - clamps very long individual lines to 4000 chars for display safety\n  - shows cancellation/error/truncation notices\n\n## Operational troubleshooting\n\n- **Python backend not available** — Check `eval.py`, `PI_PY`, and that `python`/`python3` is on PATH. If preflight fails and `eval.js` is enabled, omit `language` or pass `language: \"js\"` to use JavaScript.\n- **No Python on PATH** — Install a system Python 3.8+ or place a venv at `~/.omp/python-env`. `omp setup python --check` reports the resolved interpreter.\n- **Execution hangs then times out** — Increase tool `timeout` (max 600s) if workload is legitimate. For stuck native code, cancellation triggers `SIGINT` first then escalates; the session restarts on the next request.\n- **stdin/input prompts in Python code** — `input()` is not supported; pass data programmatically.\n- **Working directory errors** — Tool validates `cwd` exists and is a directory before execution.\n\n## Relevant environment variables\n\n- `PI_PY` — tool exposure override\n- `PI_PYTHON_SKIP_CHECK=1` — bypass Python preflight/warm checks\n- `PI_PYTHON_INTEGRATION=1` — enable gated integration tests that spawn a real Python\n- `PI_PYTHON_IPC_TRACE=1` — log NDJSON frames exchanged with the runner subprocess\n",
 	"render-mermaid.md": "# RenderMermaid\n\n`RenderMermaid` is an optional built-in tool that renders Mermaid source to terminal-friendly text.\n\n## Enable it\n\nDisabled by default. Turn it on in `/settings` under **Tools → Render Mermaid**, or in `~/.omp/agent/config.yml`:\n\n```yaml\nrenderMermaid:\n  enabled: true\n```\n\n## What it does\n\n- Tool name: `render_mermaid`\n- Input: Mermaid source in the required `mermaid` field\n- Output: rendered ASCII/Unicode text, not SVG or PNG\n- Storage: when artifact storage is available, the full render is also saved as an `artifact://...`\n\nThere are no model-specific or environment-variable prerequisites. Once enabled, any model that can call built-in tools can use it.\n\n## Parameters\n\n```json\n{\n  \"mermaid\": \"graph TD\\n  A[Start] --> B[Stop]\",\n  \"config\": {\n    \"useAscii\": false,\n    \"paddingX\": 2,\n    \"paddingY\": 2,\n    \"boxBorderPadding\": 0\n  }\n}\n```\n\nAvailable `config` fields:\n\n- `useAscii` — `true` for plain ASCII, `false` for Unicode box-drawing characters (default and usually more readable)\n- `paddingX` — horizontal spacing between nodes\n- `paddingY` — vertical spacing between nodes\n- `boxBorderPadding` — inner padding inside node boxes\n\n## Current limitations\n\n`RenderMermaid` uses the `beautiful-mermaid` ASCII renderer. It works best for flowcharts and small diagrams.\n\nComplex sequence diagrams, especially with `alt` / `else` blocks, can become very wide in a terminal. That is current renderer behavior, not a provider or model configuration problem.\n\nIf a sequence diagram is hard to read:\n\n1. Keep Unicode output (`useAscii: false`)\n2. Reduce spacing with a tighter config such as `paddingX: 2`, `paddingY: 2`, `boxBorderPadding: 0`\n3. Prefer smaller sub-diagrams over one large sequence diagram\n4. Open the saved artifact if the inline preview is truncated in the TUI\n\n## Example\n\nInput:\n\n```mermaid\ngraph TD\n  A[Start] --> B{Decision}\n  B -->|Yes| C[Action]\n  B -->|No| D[End]\n```\n\nTypical result:\n\n```text\n┌─────┐\n│Start│\n└─────┘\n   │\n   ▼\n┌────────┐\n│Decision│\n└────────┘\n```\n",
@@ -73,7 +73,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"tools/browser.md": "# browser\n\n> Open, reuse, close, and script Puppeteer tabs against headless Chromium or CDP-attached apps.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/browser.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/browser.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/browser/tab-supervisor.ts` — global tab registry; worker lifecycle; run/close coordination.\n  - `packages/coding-agent/src/tools/browser/tab-worker.ts` — executes `run` code; implements the `tab` helper API.\n  - `packages/coding-agent/src/tools/browser/tab-worker-entry.ts` — worker-thread transport bootstrap.\n  - `packages/coding-agent/src/tools/browser/registry.ts` — browser-handle registry keyed by browser kind.\n  - `packages/coding-agent/src/tools/browser/launch.ts` — Puppeteer loading, Chromium resolution/download, headless launch, stealth injection.\n  - `packages/coding-agent/src/tools/browser/attach.ts` — CDP attach/reuse, target picking, spawned-app process handling.\n  - `packages/coding-agent/src/tools/browser/tab-protocol.ts` — worker init/run/result message schema.\n  - `packages/coding-agent/src/tools/browser/readable.ts` — `tab.extract()` readability extraction.\n  - `packages/coding-agent/src/tools/browser/render.ts` — TUI rendering for `open`/`close` status lines and `run` JS cells.\n  - `packages/coding-agent/src/tools/puppeteer/00_stealth_tampering.txt` — mask patched functions/descriptors as native.\n  - `packages/coding-agent/src/tools/puppeteer/01_stealth_activity.txt` — synthesize visibility/focus/scroll activity.\n  - `packages/coding-agent/src/tools/puppeteer/02_stealth_hairline.txt` — fix Modernizr hairline detection.\n  - `packages/coding-agent/src/tools/puppeteer/03_stealth_botd.txt` — spoof `navigator.webdriver`, `window.chrome`, and Chrome fingerprint surfaces.\n  - `packages/coding-agent/src/tools/puppeteer/04_stealth_iframe.txt` — patch iframe `contentWindow`/`srcdoc` behavior.\n  - `packages/coding-agent/src/tools/puppeteer/05_stealth_webgl.txt` — spoof WebGL vendor/renderer/precision.\n  - `packages/coding-agent/src/tools/puppeteer/06_stealth_screen.txt` — normalize screen/viewport/device-pixel-ratio values.\n  - `packages/coding-agent/src/tools/puppeteer/07_stealth_fonts.txt` — spoof local fonts and perturb canvas text rendering.\n  - `packages/coding-agent/src/tools/puppeteer/08_stealth_audio.txt` — spoof audio latency/sample-rate and perturb offline rendering.\n  - `packages/coding-agent/src/tools/puppeteer/09_stealth_locale.txt` — force locale/languages/timezone/date strings.\n  - `packages/coding-agent/src/tools/puppeteer/10_stealth_plugins.txt` — synthesize `navigator.plugins`/`navigator.mimeTypes`.\n  - `packages/coding-agent/src/tools/puppeteer/11_stealth_hardware.txt` — spoof `navigator.hardwareConcurrency`.\n  - `packages/coding-agent/src/tools/puppeteer/12_stealth_codecs.txt` — spoof media codec support.\n  - `packages/coding-agent/src/tools/puppeteer/13_stealth_worker.txt` — carry UA/platform spoofing into `Worker`/`SharedWorker`.\n\n## Inputs\n\n### Shared fields\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | `\"open\" \\| \"close\" \\| \"run\"` | Yes | Dispatches to the open/close/run path. |\n| `name` | `string` | No | Tab id. Defaults to `\"main\"`. Tabs live in a process-global map, so the same name is reused across later calls and in-process subagents until closed. |\n| `timeout` | `number` | No | Tool wall-clock timeout in seconds. Defaults to `30`; clamped to the browser tool range before execution. |\n\n### `action: \"open\"`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `url` | `string` | No | Navigate after the tab is ready. Existing reusable tabs also navigate when `url` is supplied. |\n| `viewport` | `{ width: number; height: number; scale?: number }` | No | Requested viewport. For headless launch this becomes the initial viewport; for a page it is applied with `page.setViewport()`. `scale` maps to Puppeteer `deviceScaleFactor`. |\n| `wait_until` | `\"load\" \\| \"domcontentloaded\" \\| \"networkidle0\" \\| \"networkidle2\"` | No | Navigation wait condition. Defaults to `\"networkidle2\"` where omitted. |\n| `dialogs` | `\"accept\" \\| \"dismiss\"` | No | Installs a page `dialog` handler that auto-accepts or auto-dismisses dialogs. Omitted means no handler. |\n| `app` | `{ path?: string; cdp_url?: string; args?: string[]; target?: string }` | No | Selects browser kind. No `app` uses the session `browser.headless` setting. `app.path` is resolved against the session cwd and used as the executable path for spawn/attach reuse. `app.cdp_url` connects to an existing CDP endpoint. `args` are appended only when spawning `app.path`. `target` is only used for attached/spawned-app page selection. |\n\n### `action: \"close\"`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `all` | `boolean` | No | Close every known tab. Omitted closes only `name`. |\n| `kill` | `boolean` | No | When a tab release drops a spawned-app browser handle to refcount 0, also terminate its process tree. Has no effect on headless shutdown and only disconnects connected CDP browsers. |\n\n### `action: \"run\"`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `code` | `string` | Yes | Async-function body executed in a VM context with `page`, `browser`, `tab`, `display`, `assert`, `wait`, `console`, timers, `URL`, `TextEncoder`, `TextDecoder`, and `Buffer` in scope. |\n\n## Outputs\nThe tool returns one result per call; no streaming partial output is emitted from the browser implementation itself.\n\n- `open`: text content with `Opened` or `Reused`, browser description, URL, and optional title. `details` includes `action`, `name`, `browser`, `url`, `viewport`, and the same text in `details.result`.\n- `close`: text content with either `Closed ...` or `No tab named ...`. `details` includes `action`, `name`, and `details.result`.\n- `run`: ordered `content` array built as:\n  1. every `display(value)` call in execution order,\n  2. final return value, JSON-stringified unless already a string,\n  3. or `Ran code on tab \"...\"` if nothing else was produced.\n- `display(value)` coercion in `packages/coding-agent/src/tools/browser/tab-worker.ts`:\n  - `{ type: \"image\", data: string, mimeType: string }` becomes image content,\n  - `string` becomes text content,\n  - other values become pretty JSON text when serializable, else `String(value)`.\n- `tab.screenshot()` also appends text plus an image content item unless `silent: true`; `details.screenshots` records persisted screenshot metadata `{ dest, mimeType, bytes, width, height }`.\n- `run` `details` includes `action`, `name`, current `browser`/`url` when the tab exists, optional `screenshots`, and `details.result` containing only the concatenated text outputs.\n\n## Flow\n1. `BrowserTool.execute()` (`packages/coding-agent/src/tools/browser.ts`) abort-checks, clamps `timeout` via `clampTimeout(\"browser\", ...)`, defaults `name` to `\"main\"`, and dispatches on `action`.\n2. `open` resolves browser kind with `resolveBrowserKind()`:\n   - `app.cdp_url` → `{ kind: \"connected\" }` after trimming trailing slashes.\n   - `app.path` → `{ kind: \"spawned\" }` after resolving against session cwd.\n   - otherwise → `{ kind: \"headless\", headless: session.settings.get(\"browser.headless\") }`.\n3. `open` rejects reusing the same tab name across different browser kinds (`sameBrowserKind()`); callers must close first.\n4. `open` acquires a browser handle through `acquireBrowser()` (`packages/coding-agent/src/tools/browser/registry.ts`):\n   - existing connected handle is reused by browser-kind key;\n   - stale disconnected handles are disposed and recreated;\n   - headless launches via `launchHeadlessBrowser()`;\n   - `connected` waits for `${cdpUrl}/json/version`, then `puppeteer.connect()`;\n   - `spawned` first tries `findReusableCdp()`, else kills same-path processes, allocates a free loopback port, spawns the executable with `--remote-debugging-port=<port>`, waits for CDP, then connects.\n5. `open` acquires a tab through `acquireTab()` (`packages/coding-agent/src/tools/browser/tab-supervisor.ts`):\n   - same-name + same-browser + alive tab is reused unless `dialogs` changed;\n   - same-name but different browser handle, dead state, or changed dialog policy forces release and recreation;\n   - reusing with a new `url` navigates by issuing `await tab.goto(...)` through the worker.\n6. New tabs build a `WorkerInitPayload` in `buildInitPayload()`:\n   - headless mode sends `url`, `waitUntil`, `viewport`, `dialogs`, and timeout;\n   - attach mode resolves a page with `pickElectronTarget()`, gets its target id, and sends `targetId` plus `dialogs`.\n7. `acquireTab()` spawns a dedicated Bun `Worker` from `tab-worker-entry.ts`; if that fails it falls back to inline execution in the main thread (`spawnInlineWorker()`), preserving behavior but losing protection against synchronous infinite loops.\n8. `WorkerCore.#init()` (`packages/coding-agent/src/tools/browser/tab-worker.ts`) connects back to the browser websocket endpoint. Headless mode opens a new page, applies stealth patches, applies viewport, installs dialog handling if requested, and optionally navigates. Attach mode resolves the requested target page and optionally installs dialog handling.\n9. On success the worker sends `ready` with `{ url, title, viewport, targetId }`; the supervisor stores a `TabSession`, increments browser-handle refcount with `holdBrowser()`, and keeps the tab in a process-global `Map<string, TabSession>`.\n10. `run` requires non-empty `code`, looks up the tab with `getTab()`, then delegates to `runInTab()`.\n11. `runInTabWithSnapshot()` rejects dead tabs and concurrent runs (`Tab ... is busy`), captures session cwd plus optional `browser.screenshotDir`, registers an abort hook, sends a `run` message to the worker, and races the result against `timeoutMs + 750` ms. Timeouts force-kill the tab worker and, for headless tabs, close the orphaned page target.\n12. `WorkerCore.#run()` creates a VM context, exposes the raw Puppeteer `page`/`browser` plus a synthetic `tab` API, and executes `(async () => { ...code... })()` via `vm.runInContext()`.\n13. The `tab` helper API implemented in `#createTabApi()` is:\n   - `tab.name: string`\n   - `tab.page: Page`\n   - `tab.signal?: AbortSignal`\n   - `tab.url(): string`\n   - `tab.title(): Promise<string>`\n   - `tab.goto(url, { waitUntil? })`\n   - `tab.observe({ includeAll?, viewportOnly? })`\n   - `tab.screenshot({ selector?, fullPage?, save?, silent? })`\n   - `tab.extract(format = \"markdown\")`\n   - `tab.click(selector)`\n   - `tab.type(selector, text)`\n   - `tab.fill(selector, value)`\n   - `tab.press(key, { selector? })`\n   - `tab.scroll(deltaX, deltaY)`\n   - `tab.drag(from, to)`\n   - `tab.waitFor(selector)`\n   - `tab.evaluate(fn, ...args)`\n   - `tab.scrollIntoView(selector)`\n   - `tab.select(selector, ...values)`\n   - `tab.uploadFile(selector, ...filePaths)`\n   - `tab.waitForUrl(pattern, { timeout? })`\n   - `tab.waitForResponse(pattern, { timeout? })`\n   - `tab.id(n)`\n14. Selector handling in `normalizeSelector()` accepts plain CSS and Puppeteer query handlers, and rewrites legacy Playwright-style prefixes `p-text/`, `p-xpath/`, `p-pierce/`, `p-aria/`; other `p-*` prefixes throw a `ToolError`.\n15. `tab.observe()` clears the element cache, takes a Puppeteer accessibility snapshot, filters to interactive nodes unless `includeAll`, optionally filters to viewport-visible nodes, assigns numeric ids, caches `ElementHandle`s, and returns URL/title/viewport/scroll metadata plus `elements`.\n16. `tab.id(n)` resolves the cached `ElementHandle`, verifies `el.isConnected`, and throws a stale-id error after cache invalidation if the DOM changed or the cache was cleared.\n17. `tab.goto()` clears the cached element ids before navigating. Any new `tab.observe()` also clears and rebuilds the cache.\n18. `tab.click()` uses a custom retry loop for `text/...` selectors to find an actionable visible match; other selectors use `page.locator(...).click()` with the run timeout.\n19. `tab.screenshot()` captures either the whole page or a selector PNG, downsizes a copy for model output, chooses a persistence path, writes the image to disk, records metadata, and optionally emits text + image display entries.\n20. `display()` calls accumulate in an array. After code finishes, the worker posts `{ displays, returnValue, screenshots }`; `BrowserTool.#run()` appends the return value as trailing text content when not `undefined`.\n21. `close` releases one tab or all tabs via `releaseTab()` / `releaseAllTabs()`. Each tab aborts pending runs, asks the worker to close, waits up to `750` ms for a `closed` ack, terminates the worker, decrements browser refcount, and disposes the browser handle when refcount reaches zero.\n\n## Modes / Variants\n- **Action dispatch**\n  - `open` — acquire/reuse browser + tab.\n  - `close` — release one tab or all tabs.\n  - `run` — execute JS inside the tab worker.\n- **Browser kind**\n  - **Headless**: launches local Chromium with Puppeteer, applies stealth patches, and creates a fresh page per tab.\n  - **Spawned app (`app.path`)**: reuses an existing CDP-enabled process for that executable when possible; otherwise kills same-path processes, spawns the executable with remote debugging enabled, then attaches. No stealth patches are injected.\n  - **Connected browser (`app.cdp_url`)**: attaches to an already-running CDP endpoint. No process ownership; close only disconnects.\n- **Target selection for attached/spawned browsers**\n  - With `app.target`, `pickElectronTarget()` returns the first page whose URL or title contains the case-insensitive substring.\n  - Without `app.target`, it skips titles/URLs matching `request handler|devtools|background page|background host|service worker` and otherwise falls back to the first page.\n- **Worker mode**\n  - **Dedicated worker**: normal path; user code runs off the main thread and can be aborted even when it blocks synchronously.\n  - **Inline fallback**: activated when Bun worker spawn fails; behavior matches, but synchronous infinite loops on user code cannot be interrupted.\n- **Dialog policy**\n  - No `dialogs` field: no auto-handler.\n  - `accept`/`dismiss`: page `dialog` events are handled automatically.\n  - Changing dialog policy on an existing live tab forces tab recreation instead of mutating the worker in place.\n- **Screenshot persistence**\n  - `save` provided: persist full-resolution PNG at the resolved cwd-relative or absolute path.\n  - `browser.screenshotDir` session setting set: persist full-resolution PNG under that directory with a timestamped filename.\n  - Neither set: persist the resized image to a temp-file path under the OS temp dir.\n\n## Side Effects\n- Filesystem\n  - `loadPuppeteer()` writes `{}` to `<puppeteer-safe-dir>/package.json` before importing `puppeteer-core`.\n  - First headless launch may download Chromium into the Puppeteer cache directory returned by `getPuppeteerDir()`.\n  - `tab.screenshot()` creates parent directories and writes image files.\n  - `tab.uploadFile()` resolves supplied paths against the session cwd.\n- Network\n  - CDP attach paths poll `http://127.0.0.1:<port>/json/version` or the supplied `cdp_url` `/json/version`.\n  - Headless/browser-attach sessions create CDP websocket connections.\n  - Headless first-use Chromium download uses `@puppeteer/browsers`.\n  - User `page` / `tab` operations perform normal browser network traffic.\n- Subprocesses / native bindings\n  - Headless mode launches Chromium through Puppeteer.\n  - `app.path` mode may spawn the target executable via `Bun.spawn()`.\n  - `killExistingByPath()` / `gracefulKillTreeOnce()` use `@oh-my-pi/pi-natives` process inspection/termination.\n  - Worker mode uses Bun `Worker`; fallback mode does not.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Browser handles are cached in a process-global `Map` keyed by browser kind in `packages/coding-agent/src/tools/browser/registry.ts`.\n  - Tabs are cached in a process-global `Map` keyed by `name` in `packages/coding-agent/src/tools/browser/tab-supervisor.ts`.\n  - `run` captures session cwd and optional `browser.screenshotDir` for screenshot/save path resolution.\n  - `restartForModeChange()` drops only headless tabs.\n- User-visible prompts / interactive UI\n  - None beyond normal tool output. Dialog auto-handling is invisible unless it fails and emits debug logs.\n- Background work / cancellation\n  - `open`, `run`, CDP waits, and browser actions thread through abort signals.\n  - A timed-out `run` aborts the worker execution path and can tear down the tab.\n\n## Limits & Caps\n- Tool timeout clamp: default `30` s, min `1` s, max `30` s (`TOOL_TIMEOUTS.browser` in `packages/coding-agent/src/tools/tool-timeouts.ts`).\n- Supervisor grace period around init/run/close: `750` ms (`GRACE_MS` in `packages/coding-agent/src/tools/browser/tab-supervisor.ts`).\n- Puppeteer protocol timeout for launch/connect operations: `60_000` ms (`BROWSER_PROTOCOL_TIMEOUT_MS` in `packages/coding-agent/src/tools/browser/launch.ts`).\n- Connected-browser CDP readiness wait: `5_000` ms before `puppeteer.connect()` (`packages/coding-agent/src/tools/browser/registry.ts`).\n- Spawned-app CDP readiness wait after spawn: `30_000` ms (`packages/coding-agent/src/tools/browser/registry.ts`).\n- CDP polling cadence: 150 ms in `waitForCdp()` (`packages/coding-agent/src/tools/browser/attach.ts`).\n- Headless default viewport: `1365x768` at `deviceScaleFactor: 1.25` (`DEFAULT_VIEWPORT` in `packages/coding-agent/src/tools/browser/launch.ts`).\n- Screenshot model-attachment resize cap: `maxWidth 1024`, `maxHeight 1024`, `maxBytes 150 * 1024`, `jpegQuality 70` (`packages/coding-agent/src/tools/browser/tab-worker.ts`).\n- `tab.waitForUrl()` polling interval: `200` ms (`packages/coding-agent/src/tools/browser/tab-worker.ts`).\n- Drag simulation uses `12` mouse-move steps (`packages/coding-agent/src/tools/browser/tab-worker.ts`).\n\n## Errors\n- `BrowserTool.execute()` converts DOM-style `AbortError` into `ToolAbortError`; other errors propagate.\n- `run` hard-fails on missing code: `Missing required parameter 'code' for action 'run'.`\n- `open` fails when reusing a name across browser kinds: `Tab \"...\" is bound to a different browser (...). Close it first.`\n- `runInTabWithSnapshot()` fails when the tab is absent/dead (`Tab \"...\" is not alive. Reopen it.`) or already running (`Tab \"...\" is busy`).\n- Worker init failures and run failures are serialized through `RunErrorPayload`; `ToolError` and abort state are reconstructed on the host side by `errorFromPayload()`.\n- Attached-target mismatches surface as:\n  - `No page targets available on the attached browser`\n  - `No page target matched \"...\". Available pages:\\n...`\n  - `Target ... is no longer available on the attached browser`\n- Spawned-app path validation requires an absolute executable path, not an app bundle path.\n- Spawn/attach failures are wrapped into `ToolError`s such as `Timed out waiting for CDP endpoint ...`, `Failed to attach to ...`, or `Connected to ... but puppeteer.connect failed: ...`.\n- `tab` helper errors are user-visible `ToolError`s, including unsupported selector prefix, stale/unknown element id, invalid drag target, missing upload files, non-`<select>` for `tab.select()`, non-file-input for `tab.uploadFile()`, and screenshot selector misses.\n- On run timeout, the worker reports `Browser code execution timed out after <ms>ms`; the supervisor may escalate to `Browser code execution hung past grace; tab killed` if the worker does not respond after the grace window.\n\n## Notes\n- `loadPuppeteer()` and `loadPuppeteerInWorker()` temporarily redirect `cwd` to a safe Puppeteer directory before importing `puppeteer-core`, because Puppeteer probes the current working directory during module load.\n- Headless launch prefers a detected system Chrome/Chromium, then `PUPPETEER_EXECUTABLE_PATH`, and only then downloads Chromium.\n- Headless launch always passes `--no-sandbox`, `--disable-setuid-sandbox`, `--disable-blink-features=AutomationControlled`, and a `--window-size=...` matching the initial viewport. It also ignores Puppeteer default args `--disable-extensions`, `--disable-default-apps`, and `--disable-component-extensions-with-background-pages`.\n- Proxy-related env vars only affect headless launch: `PUPPETEER_PROXY`, `PUPPETEER_PROXY_BYPASS_LOOPBACK`, and `PUPPETEER_PROXY_IGNORE_CERT_ERRORS`.\n- Stealth patches are applied only in headless mode. Spawned or externally connected browsers are intentionally left untouched.\n- `applyStealthPatches()` also strips Puppeteer's `//# sourceURL=__puppeteer_evaluation_script__` suffix from CDP `Runtime.evaluate` / `Runtime.callFunctionOn` payloads.\n- `tab.extract()` reads `page.content()`, runs Readability first, then falls back to `main article`/`article`/`main`/`[role='main']`/`body`, and returns `null` if neither extraction path yields content.\n- `close(all: true, kill: false)` disconnects from spawned/connected browsers when the last tab closes but leaves spawned app processes running.\n- Headless orphan cleanup is best-effort: if a worker dies before closing its page, the supervisor searches browser targets by `targetId` and closes that page.\n- Console methods inside `run` do not appear in tool output; they are forwarded as debug/warn/error logs through the worker transport.",
 	"tools/checkpoint.md": "# checkpoint\n\n> Mark the current top-level conversation state so later `rewind` can collapse exploratory context into a report.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/checkpoint.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/checkpoint.md`\n- Key collaborators:\n  - `packages/coding-agent/src/session/agent-session.ts` — captures the active checkpoint after tool success.\n  - `packages/coding-agent/src/session/session-manager.ts` — persists the normal session entry stream; not the active checkpoint marker.\n  - `packages/coding-agent/src/tools/index.ts` — registers the tool and gates it behind `checkpoint.enabled`.\n  - `packages/coding-agent/src/config/settings-schema.ts` — defines the disabled-by-default feature flag.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `goal` | `string` | Yes | Investigation goal. Required by the schema and echoed in the tool result. |\n\n## Outputs\nThe tool returns a single text result plus structured details:\n\n- text body:\n  - `Checkpoint created.`\n  - `Goal: <goal>`\n  - `Run your investigation, then call rewind with a concise report.`\n- `details`:\n  - `goal: string`\n  - `startedAt: string` — ISO timestamp created inside `CheckpointTool.execute()`\n\nNo checkpoint ID, artifact URI, job handle, file path, or restore token is returned.\n\n## Flow\n1. `CheckpointTool.createIf()` in `packages/coding-agent/src/tools/checkpoint.ts` returns `null` for subagents by checking `session.taskDepth`; only top-level sessions can see the tool.\n2. `CheckpointTool.execute()` rejects subagent calls again with `ToolError(\"Checkpoint not available in subagents.\")`.\n3. It rejects nested checkpoints with `ToolError(\"Checkpoint already active.\")` when `session.getCheckpointState?.()` is already set.\n4. It creates `startedAt = new Date().toISOString()` and returns a normal `toolResult()` payload. The tool itself does not persist anything.\n5. On the later `tool_execution_end` event, `AgentSession` in `packages/coding-agent/src/session/agent-session.ts` detects successful `checkpoint` execution and captures three in-memory fields:\n   - `checkpointMessageCount` — current `agent.state.messages.length`, after the checkpoint tool result has already been appended\n   - `checkpointEntryId` — `sessionManager.getEntries().at(-1)?.id ?? null`, i.e. the last persisted session entry ID at checkpoint time\n   - `startedAt` — copied from tool details or regenerated\n6. `AgentSession` stores that object in its private `#checkpointState` field and clears `#pendingRewindReport`.\n\n## Side Effects\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Sets `AgentSession.#checkpointState` in memory.\n  - Records the checkpoint boundary as a message count plus a session entry ID.\n  - Enables the later yield guard: if a checkpoint is active and no rewind report is pending, `#enforceRewindBeforeYield()` injects a developer-role warning and schedules another turn.\n- User-visible prompts / interactive UI\n  - The tool result tells the model to call `rewind` after the investigation.\n  - If the agent tries to `yield` first, `AgentSession` injects:\n\n```text\n<system-warning>\nYou are in an active checkpoint. You MUST call rewind with your investigation findings before yielding. Do NOT yield without completing the checkpoint.\n</system-warning>\n```\n\n## Limits & Caps\n- Availability is gated by `checkpoint.enabled`, default `false`, in `packages/coding-agent/src/config/settings-schema.ts`.\n- The tool is registered as discoverable in `packages/coding-agent/src/tools/index.ts`.\n- Only one active checkpoint is allowed per top-level session.\n- Checkpoint state is not persisted as a dedicated session entry. If the process exits, a resumed session can reload the conversation history, but not the live `#checkpointState` guard.\n- Session persistence still applies to the ordinary checkpoint tool call message. Global session persistence truncation is `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(\"Checkpoint already active.\")` — thrown when a prior checkpoint has not been rewound or cleared.\n- The tool body has no local `try/catch`; unexpected exceptions propagate.\n\n## Notes\n- Despite the summary string `Create a git-based checkpoint to save and restore session state`, the implementation does not call git and does not snapshot filesystem state.\n- Captured state is conversation/session metadata only:\n  - in-memory message count\n  - session entry ID in the session tree\n  - timestamp\n- Not captured:\n  - working tree contents\n  - staged changes\n  - artifacts\n  - blob-store contents\n  - SQLite history rows from `packages/coding-agent/src/session/history-storage.ts`\n  - auth or agent records from `packages/coding-agent/src/session/agent-storage.ts`\n- If the turn ends with `stopReason === \"aborted\"` while a checkpoint is active, `AgentSession` clears `#checkpointState` and `#pendingRewindReport` instead of preserving a half-finished checkpoint.\n",
 	"tools/debug.md": "# debug\n\n> Drive one DAP debug session; adjacent debug UI code reuses the same subsystem for logs, raw SSE capture, reports, profiling, and system diagnostics.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/debug.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/debug.md`\n- Key collaborators:\n  - `packages/coding-agent/src/dap/session.ts` — session lifecycle, breakpoint/state cache\n  - `packages/coding-agent/src/dap/client.ts` — adapter process/socket transport, DAP message loop\n  - `packages/coding-agent/src/dap/config.ts` — adapter resolution and auto-selection\n  - `packages/coding-agent/src/dap/defaults.json` — built-in adapter definitions\n  - `packages/coding-agent/src/dap/types.ts` — request/response/capability shapes\n  - `packages/coding-agent/src/tools/tool-timeouts.ts` — per-tool timeout clamp\n  - `packages/coding-agent/src/debug/index.ts` — interactive debug selector menu\n  - `packages/coding-agent/src/debug/log-viewer.ts` — recent-log TUI viewer\n  - `packages/coding-agent/src/debug/raw-sse.ts` — raw SSE TUI viewer\n  - `packages/coding-agent/src/debug/raw-sse-buffer.ts` — bounded SSE capture buffer\n  - `packages/coding-agent/src/debug/profiler.ts` — CPU/heap profiling helpers\n  - `packages/coding-agent/src/debug/report-bundle.ts` — `.tar.gz` report bundling, log source, cache cleanup\n  - `packages/coding-agent/src/debug/system-info.ts` — system snapshot collection and env redaction\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | `\"launch\" \\| \"attach\" \\| \"set_breakpoint\" \\| \"remove_breakpoint\" \\| \"set_instruction_breakpoint\" \\| \"remove_instruction_breakpoint\" \\| \"data_breakpoint_info\" \\| \"set_data_breakpoint\" \\| \"remove_data_breakpoint\" \\| \"continue\" \\| \"step_over\" \\| \"step_in\" \\| \"step_out\" \\| \"pause\" \\| \"evaluate\" \\| \"stack_trace\" \\| \"threads\" \\| \"scopes\" \\| \"variables\" \\| \"disassemble\" \\| \"read_memory\" \\| \"write_memory\" \\| \"modules\" \\| \"loaded_sources\" \\| \"custom_request\" \\| \"output\" \\| \"terminate\" \\| \"sessions\"` | Yes | Dispatch key for the tool switch in `packages/coding-agent/src/tools/debug.ts`. |\n| `program` | `string` | No | Launch target path. Required for `launch`. Resolved relative to `cwd` if provided, otherwise session cwd. |\n| `args` | `string[]` | No | Program argv for `launch`. |\n| `adapter` | `string` | No | Explicit adapter name. Otherwise `selectLaunchAdapter()` / `selectAttachAdapter()` auto-pick from `packages/coding-agent/src/dap/config.ts`. |\n| `cwd` | `string` | No | Launch/attach working directory. Defaults to session cwd. |\n| `file` | `string` | No | Source file path for source breakpoints. |\n| `line` | `number` | No | Source line for source breakpoints. |\n| `function` | `string` | No | Function breakpoint name. Mutually exclusive with `file`+`line` in breakpoint actions. |\n| `name` | `string` | No | Data breakpoint info target name. Required for `data_breakpoint_info`. |\n| `condition` | `string` | No | Conditional expression for source/function/instruction/data breakpoints. |\n| `hit_condition` | `string` | No | Hit-count condition for instruction/data breakpoints. |\n| `expression` | `string` | No | Expression or raw debugger command. Required for `evaluate`. |\n| `context` | `string` | No | Evaluate context. Defaults to `\"repl\"`. Passed through as DAP evaluate context. |\n| `frame_id` | `number` | No | Frame selector for `evaluate`, `scopes`, `data_breakpoint_info`. `scopes` and `evaluate` default to the current stopped frame when omitted. |\n| `scope_id` | `number` | No | Variables reference from a scope. Accepted by `variables`; also used as a fallback variables reference for `data_breakpoint_info`. |\n| `variable_ref` | `number` | No | Variables reference for `variables`; preferred over `scope_id` when both are present. |\n| `pid` | `number` | No | Local process id for `attach`. `attach` requires `pid` or `port`. |\n| `port` | `number` | No | Remote attach port. If no adapter is forced, attach prefers `debugpy` when `port` is present. |\n| `host` | `string` | No | Remote attach host for `attach`. |\n| `levels` | `number` | No | Max stack frames for `stack_trace`. |\n| `memory_reference` | `string` | No | Memory reference/address for `disassemble`, `read_memory`, `write_memory`. `disassemble` also accepts it via `instruction_reference` fallback logic in `resolveDisassemblyReference()`. |\n| `instruction_reference` | `string` | No | Instruction breakpoint reference; required for instruction breakpoint actions. |\n| `instruction_count` | `number` | No | Required for `disassemble`. |\n| `instruction_offset` | `number` | No | Instruction offset for `disassemble`. |\n| `count` | `number` | No | Byte count for `read_memory`. Required there. |\n| `data` | `string` | No | Base64 payload for `write_memory`. Required there. |\n| `data_id` | `string` | No | Data breakpoint id. Required for `set_data_breakpoint` / `remove_data_breakpoint`. |\n| `access_type` | `\"read\" \\| \"write\" \\| \"readWrite\"` | No | Access filter for `set_data_breakpoint`. |\n| `command` | `string` | No | Custom DAP request command. Required for `custom_request`. |\n| `arguments` | `Record<string, unknown>` | No | Custom DAP request body for `custom_request`. |\n| `offset` | `number` | No | Offset for instruction breakpoints, disassembly, memory read, memory write. |\n| `resolve_symbols` | `boolean` | No | `disassemble` symbol-resolution flag. |\n| `allow_partial` | `boolean` | No | `write_memory` partial-write allowance. |\n| `start_module` | `number` | No | Modules pagination start index for `modules`. |\n| `module_count` | `number` | No | Modules pagination count for `modules`. |\n| `timeout` | `number` | No | Per-request timeout in seconds. Default `30`, clamped to `5..300`. |\n\n### Action-specific requirements\n- `launch`: `program`\n- `attach`: `pid` or `port`\n- `set_breakpoint` / `remove_breakpoint`: `function`, or `file` + `line`\n- `set_instruction_breakpoint` / `remove_instruction_breakpoint`: `instruction_reference`\n- `data_breakpoint_info`: `name`\n- `set_data_breakpoint` / `remove_data_breakpoint`: `data_id`\n- `evaluate`: `expression`\n- `variables`: `variable_ref` or `scope_id`\n- `disassemble`: capability `supportsDisassembleRequest`, plus `instruction_count`\n- `read_memory`: capability `supportsReadMemoryRequest`, plus `memory_reference` and `count`\n- `write_memory`: capability `supportsWriteMemoryRequest`, plus `memory_reference` and `data`\n- `modules`: capability `supportsModulesRequest`\n- `loaded_sources`: capability `supportsLoadedSourcesRequest`\n- `custom_request`: `command`\n\n### Interactive selector values\n`packages/coding-agent/src/debug/index.ts` also exposes a fixed UI-only selector with values `open-artifacts`, `performance`, `work`, `dump`, `memory`, `logs`, `system`, `raw-sse`, `transcript`, `clear-cache`. These are not model-callable through `debugSchema`; they are local TUI menu routes.\n\n## Outputs\nThe agent tool returns a standard `toolResult()` payload from `packages/coding-agent/src/tools/debug.ts`:\n- `content`: one text block. Every action renders human-readable text; there is no structured JSON block in `content`.\n- `details.action`: echoed action.\n- `details.success`: always initialized `true`; failures surface by throwing before a result is returned.\n- `details.snapshot`: present for actions that operate on or create a session, using `DapSessionSummary` from `packages/coding-agent/src/dap/types.ts`.\n- Action-specific `details` fields:\n  - `launch` / `attach`: `adapter`\n  - breakpoint actions: `breakpoints`, `functionBreakpoints`, `instructionBreakpoints`, `dataBreakpoints`\n  - `data_breakpoint_info`: `dataBreakpointInfo`\n  - `continue` / `step_*`: `state`, `timedOut`\n  - `threads`: `threads`\n  - `stack_trace`: `stackFrames`\n  - `scopes`: `scopes`\n  - `variables`: `variables`\n  - `evaluate`: `evaluation`\n  - `disassemble`: `disassembly`\n  - `read_memory`: `memoryAddress`, `memoryData`, `unreadableBytes`\n  - `write_memory`: `bytesWritten`\n  - `modules`: `modules`\n  - `loaded_sources`: `sources`\n  - `custom_request`: `customBody`\n  - `output`: `output`\n  - `sessions`: `sessions`\n\nStreaming/UI behavior:\n- The tool renderer merges call and result (`mergeCallAndResult: true`) and renders inline.\n- `debug.ts` itself does not emit progress updates through `_onUpdate`; result delivery is single-shot.\n- The interactive selector is UI-driven instead of model-driven. It swaps TUI components, appends status lines to the chat pane, opens files in external viewers, or writes archives/temp files.\n\nSide-channel artifacts outside the model tool result:\n- `createReportBundle()` writes `omp-report-<timestamp>.tar.gz` under the reports dir and returns the filesystem path to the UI handler.\n- `#handleWorkReport()` writes `/tmp/work-profile-<Date.now()>.svg` before opening it.\n- `RawSseViewerComponent` and `DebugLogViewerComponent` can copy captured text to the clipboard.\n\n## Flow\n1. Tool registration is conditional: `DebugTool.createIf()` in `packages/coding-agent/src/tools/debug.ts` returns `null` unless `session.settings.get(\"debug.enabled\")` is true. `packages/coding-agent/src/tools/index.ts` wires the factory and rechecks the same setting in tool filtering.\n2. `DebugTool.execute()` clamps `params.timeout` through `clampTimeout(\"debug\", params.timeout)` and composes the caller `AbortSignal` with `AbortSignal.timeout(...)`.\n3. `launch` and `attach` resolve cwd/program paths, select an adapter in `packages/coding-agent/src/dap/config.ts`, then delegate to `dapSessionManager.launch()` / `.attach()`.\n4. `DapSessionManager.launch()` / `.attach()` enforce the single-session rule with `#ensureLaunchSlot()`, spawn the adapter through `DapClient.spawn()`, register listeners, send `initialize`, cache capabilities, start listening for an initial stop event before sending `launch`/`attach`, then complete the `initialized` → `configurationDone` handshake in `#completeConfigurationHandshake()`.\n5. `DapClient.spawn()` starts the adapter detached with `NON_INTERACTIVE_ENV`. Most adapters use stdio; socket-mode adapters (`dlv`) use `#spawnSocketUnix()` on Linux or `#spawnSocketClientAddr()` on macOS/other.\n6. `#registerSession()` in `packages/coding-agent/src/dap/session.ts` installs reverse-request handlers:\n   - `runInTerminal`: spawns the requested debuggee command detached via `ptree.spawn()` and returns `{ processId }`\n   - `startDebugging`: logs the child-session request and returns `{}`; it does not create nested sessions\n   - events: `output`, `initialized`, `stopped`, `continued`, `exited`, `terminated` update cached session state\n7. Operational actions (`set_breakpoint`, `evaluate`, `threads`, `read_memory`, `custom_request`, and similar) call `dapSessionManager` methods. Most flow through `#sendRequestWithConfig()`, which first sends `configurationDone` when required, then sends the DAP request, then updates `lastUsedAt`.\n8. Breakpoint actions maintain local cached breakpoint sets in `DapSessionManager` and remap adapter responses back onto those cached records.\n9. `continue` and the three step actions clear cached stop state, subscribe for `stopped`/`terminated`/`exited` before sending the DAP request, then `#awaitStopOutcome()` either returns the new stopped location or reports that the program is still running after timeout.\n10. `pause` sends DAP `pause`, waits for a stopped event if needed, and reuses cached stop state if the program was already stopped.\n11. `stack_trace`, `scopes`, `variables`, and `evaluate` default to the current stopped thread/frame when the caller omits ids and cached state is available.\n12. `output` reads the in-memory output ring from `DapSessionManager.getOutput()`. `terminate` sends `terminate` when supported, always attempts `disconnect`, marks the session terminated, and disposes the client.\n13. `sessions` reads the manager’s current map and formats all summaries. Although the manager stores a map, only one active session can exist because new launch/attach calls are blocked until the active one is terminated or cleaned up.\n14. The interactive selector in `packages/coding-agent/src/debug/index.ts` builds a `SelectList` of fixed values and dispatches each to a handler:\n   - `performance`: `startCpuProfile()`, wait for Enter/Escape, stop profiling, read a 30-second work profile with `getWorkProfile(30)`, then bundle via `createReportBundle()`\n   - `work`: read `getWorkProfile(30)`, write a temp SVG, open it externally\n   - `dump`: create a report bundle immediately\n   - `memory`: force GC, call `Bun.generateHeapSnapshot(\"v8\")`, then bundle\n   - `logs`: build a `DebugLogSource` and mount `DebugLogViewerComponent`\n   - `raw-sse`: resolve a `RawSseDebugBuffer` from the session and mount `RawSseViewerComponent`\n   - `system`: call `collectSystemInfo()` and render `formatSystemInfo()` into the chat pane\n   - `open-artifacts`: open the current session artifact directory if it exists\n   - `transcript`: delegates to `ctx.handleDebugTranscriptCommand()`\n   - `clear-cache`: show confirmation, then remove artifact directories older than 30 days with `clearArtifactCache()`\n\n## Modes / Variants\n- **Availability gate**\n  - Tool hidden when `debug.enabled` is false.\n- **Adapter selection**\n  - `launch`: explicit `adapter` wins; otherwise `selectLaunchAdapter()` ranks available adapters by extension match, root-marker match, then native-debugger preference (`gdb`, `lldb-dap`) for extensionless binaries.\n  - `attach`: explicit `adapter` wins; otherwise remote `port` prefers `debugpy`, then native debuggers, then first available adapter.\n- **Transport**\n  - stdio adapters: direct `stdin`/`stdout` framing.\n  - socket adapters: Unix domain socket on Linux; TCP callback on macOS/other.\n- **DAP agent-tool actions**\n  - `launch` — spawn adapter, initialize session, maybe stop on entry; returns formatted session snapshot and `details.adapter`.\n  - `attach` — connect to a live process or remote port; same output shape as `launch`.\n  - `set_breakpoint` — source or function breakpoint add/update; returns the current breakpoint list for that target.\n  - `remove_breakpoint` — source or function breakpoint removal; returns the remaining breakpoint list.\n  - `set_instruction_breakpoint` / `remove_instruction_breakpoint` — require `supportsInstructionBreakpoints`; return current instruction breakpoint list.\n  - `data_breakpoint_info` — require `supportsDataBreakpoints`; asks the adapter for a `dataId`, access types, and description for `name`.\n  - `set_data_breakpoint` / `remove_data_breakpoint` — require `supportsDataBreakpoints`; return the cached data-breakpoint list.\n  - `continue` / `step_over` / `step_in` / `step_out` — return text describing whether execution stopped, terminated, or kept running, plus `details.state` and `details.timedOut`.\n  - `pause` — interrupts a running target and returns a stopped snapshot.\n  - `evaluate` — adapter expression evaluation; defaults context to `repl`.\n  - `stack_trace` — fetches frames for the resolved thread.\n  - `threads` — fetches current threads.\n  - `scopes` — frame scopes for an explicit `frame_id` or the current stopped frame.\n  - `variables` — variables for `variable_ref` or `scope_id`.\n  - `disassemble` — require `supportsDisassembleRequest`; disassembles around a memory reference.\n  - `read_memory` — require `supportsReadMemoryRequest`; returns address, base64 data, unreadable-byte count.\n  - `write_memory` — require `supportsWriteMemoryRequest`; writes base64 data and reports bytes written.\n  - `modules` — require `supportsModulesRequest`; optional pagination via `start_module` / `module_count`.\n  - `loaded_sources` — require `supportsLoadedSourcesRequest`; returns loaded source descriptors.\n  - `custom_request` — sends any DAP request name with arbitrary arguments.\n  - `output` — dumps captured stdout/stderr/console text from the session cache.\n  - `terminate` — disconnects and disposes the active session; returns `No debug session to terminate.` when none exists.\n  - `sessions` — lists all cached session summaries.\n- **Interactive selector routes (UI-only)**\n  - `logs` — loads today’s log tail and optional older daily log files into `DebugLogViewerComponent`; supports copy, range selection, pid filtering, load-older.\n  - `raw-sse` — live view over the session’s `RawSseDebugBuffer`; supports tail-follow, scrolling, copy-all.\n  - `performance` — CPU profile + 30-second work profile + report bundle.\n  - `memory` — heap snapshot + report bundle.\n  - `dump` — report bundle without profiler artifacts.\n  - `work` — standalone work-profile flamegraph export/open.\n  - `system` — formatted OS/arch/CPU/memory/version/cwd/shell/terminal dump.\n  - `open-artifacts` / `transcript` / `clear-cache` — artifact directory open, transcript export, artifact-cache pruning.\n\n## Side Effects\n- Filesystem\n  - Resolves program/file/cwd paths against the session cwd.\n  - Report creation writes `.tar.gz` bundles and may read the session JSONL, artifact files, subagent session JSONLs, and log files.\n  - Work-profile export writes `/tmp/work-profile-<timestamp>.svg`.\n  - Log source reads daily log files from the logs dir.\n  - Artifact-cache cleanup removes session artifact directories older than the cutoff.\n  - `resolveRawSseDebugBuffer()` may attach a non-enumerable `rawSseDebugBuffer` property to the owner object.\n- Network\n  - Socket-mode adapters bind/connect local sockets.\n  - Remote attach may connect through the adapter to a remote debug port.\n- Subprocesses / native bindings\n  - Spawns debugger adapters (`gdb`, `lldb-dap`, `python -m debugpy.adapter`, `dlv`, and others from `defaults.json`) detached.\n  - Reverse DAP `runInTerminal` requests spawn the debuggee detached via `ptree.spawn()`.\n  - `getWorkProfile(30)` comes from `@oh-my-pi/pi-natives`.\n  - CPU profiling uses `node:inspector/promises`; heap snapshots use `Bun.generateHeapSnapshot(\"v8\")`; raw/log viewers sanitize text via `@oh-my-pi/pi-natives`.\n  - `openPath()` launches the OS default file/browser handler for artifact dirs and SVGs.\n  - Log/raw-SSE viewers can call `copyToClipboard()`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - `DapSessionManager` keeps session summaries, breakpoints, threads, stack frames, stop location, output capture, capabilities, and last-used timestamps in memory.\n  - Active-session id is global to the singleton `dapSessionManager`.\n  - `RawSseDebugBuffer` stores recent SSE events per owner/session.\n  - The tool is `exclusive`; concurrent debug tool calls are blocked by the scheduler.\n- User-visible prompts / interactive UI\n  - Debug selector shows confirmation before cache deletion.\n  - Performance profiling temporarily hijacks editor Enter/Escape handlers until profiling stops.\n  - Log/raw-SSE viewers replace the editor pane with custom components.\n- Background work / cancellation\n  - Every DAP request accepts an `AbortSignal`; timeouts and caller cancellation abort the active request, not the whole session lifetime.\n  - `DapSessionManager` runs a background cleanup loop every 30 seconds.\n  - Raw SSE viewers subscribe to buffer updates until closed.\n\n## Limits & Caps\n- Tool timeout clamp: `default=30`, `min=5`, `max=300` in `packages/coding-agent/src/tools/tool-timeouts.ts`.\n- Per-request DAP default timeout: `DEFAULT_REQUEST_TIMEOUT_MS = 30_000` in `packages/coding-agent/src/dap/client.ts`.\n- Single active session: enforced by `#ensureLaunchSlot()` in `packages/coding-agent/src/dap/session.ts`.\n- Idle session cleanup: `IDLE_TIMEOUT_MS = 10 * 60 * 1000`, checked every `CLEANUP_INTERVAL_MS = 30 * 1000`.\n- Adapter liveness heartbeat: `HEARTBEAT_INTERVAL_MS = 5 * 1000`.\n- Output capture cap: `MAX_OUTPUT_BYTES = 128 * 1024`; older text is trimmed in ~1 KiB slices and `outputTruncated` is recorded.\n- Initial stop capture timeout after launch/attach: `STOP_CAPTURE_TIMEOUT_MS = 5_000`.\n- Socket-mode adapter readiness timeout: `10_000` ms in `waitForCondition()` and TCP connect timeout logic in `packages/coding-agent/src/dap/client.ts`.\n- Raw SSE buffer caps in `packages/coding-agent/src/debug/raw-sse-buffer.ts`:\n  - `MAX_RAW_SSE_EVENTS = 1_000`\n  - `MAX_RAW_SSE_CHARS = 512_000`\n  - `MAX_RAW_SSE_EVENT_CHARS = 64_000` per event, with `: omp-debug-truncated ...` marker appended on trim\n- Log viewer window in `packages/coding-agent/src/debug/log-viewer.ts`:\n  - `INITIAL_LOG_CHUNK = 50`\n  - `LOAD_OLDER_CHUNK = 50`\n- Report/log ingestion caps in `packages/coding-agent/src/debug/report-bundle.ts`:\n  - `MAX_LOG_LINES = 5000` for interactive log reading\n  - `MAX_LOG_BYTES = 2 * 1024 * 1024` tail-read ceiling\n  - report bundles include only the last `1000` log lines\n  - subagent session inclusion is capped at the most recent `10` JSONL files\n- Interactive profiling windows in `packages/coding-agent/src/debug/index.ts`: both performance and work reports request `getWorkProfile(30)`.\n- Artifact cache pruning default: `30` days in `clearArtifactCache()` and the selector confirmation text.\n\n## Errors\n- Parameter validation in `packages/coding-agent/src/tools/debug.ts` throws `ToolError` with explicit messages such as:\n  - `program is required for launch`\n  - `attach requires pid or port`\n  - `set_breakpoint requires file+line or function`\n  - `variables requires variable_ref or scope_id`\n  - `memory_reference is required for read_memory`\n  - `count is required for read_memory`\n  - `data is required for write_memory`\n  - `command is required for custom_request`\n- Adapter selection failure throws `No debugger adapter available. Installed adapters: ...`.\n- Capability-gated actions throw from `requireCapability(...)`, e.g. `Active adapter does not support memory reads.`\n- No-session and state errors come from `DapSessionManager`, e.g. `No active debug session. Launch or attach first.`, `No active stack frame. Run stack_trace first or supply frame_id.`, `Debugger reported no threads.`\n- Launching a second live session throws `Debug session <id> is still active. Terminate it before launching another.`\n- DAP transport/request failures surface as thrown errors from `DapClient`:\n  - `DAP request <command> timed out after <ms>ms`\n  - `DAP event <event> timed out after <ms>ms`\n  - `DAP adapter <name> is not running`\n  - `DAP adapter exited (code N): <stderr>` or `DAP adapter exited unexpectedly (code N)`\n  - adapter response `message` when a DAP request fails\n- `continue` / `step_*` are intentionally non-fatal when the target stays running past the timeout: they return `details.timedOut = true` and `state: \"running\"` instead of throwing.\n- `terminate` suppresses adapter errors while sending `terminate`/`disconnect`; it still disposes the client and returns the last summary when possible.\n- Interactive selector handlers report UI errors instead of throwing:\n  - profiler start/stop, report bundling, log reading, system-info collection, cache clearing, and artifact opening use `ctx.showError(...)` / `ctx.showWarning(...)`\n  - empty logs and empty artifact caches are warnings/status messages, not failures\n  - copy failures in log/raw-SSE viewers become status/error text in the UI\n- Report-bundle helpers are intentionally best-effort for many file reads: missing session files, missing artifact dirs, unreadable artifact files, missing log dirs, inaccessible cache dirs, and missing subagent files are skipped silently.\n- `collectSystemInfo()` is best-effort for CPU probing; failure there falls back to `Unknown CPU`.\n\n## Notes\n- `packages/coding-agent/src/prompts/tools/debug.md` tells the model only one active session is supported; that is not advisory, it is enforced in code.\n- `configurationDone` is sent automatically both during launch/attach handshake and lazily before later requests if the adapter required it and the initial handshake did not complete.\n- `startDebugging` reverse requests are acknowledged but not implemented; child debug sessions are not spawned.\n- `output` exposes the merged `output` event stream only; the tool does not distinguish stdout, stderr, and console categories.\n- Session summaries expose `needsConfigurationDone`; this is derived from adapter capabilities and whether `configurationDone` has been sent.\n- Source breakpoint file paths are normalized with `path.resolve()` before caching and sending to the adapter.\n- `evaluate` defaults to `repl`, so the tool can forward raw debugger commands when the adapter supports them.\n- `disassemble` resolves its target from `memory_reference` first, then `instruction_reference`; it throws if neither is present.\n- `RawSseDebugBuffer.recordEvent()` increments `totalEvents` before bounded retention. A snapshot can therefore show fewer retained records than total observed events.\n- Raw SSE buffer listener failures are swallowed so viewer bugs do not break capture.\n- `createDebugLogSource()` walks daily log files newest-first, but `loadOlderLogs()` reverses each requested slice before concatenation so older chunks prepend in chronological order.\n- `clearArtifactCache()` deletes directories by directory mtime, not per-file age.\n- `addDirectoryToArchive()` reads artifact files as text with `Bun.file(...).text()`. Binary artifact contents are not preserved byte-for-byte in the report bundle.\n- The tool renderer truncates displayed output for the TUI preview, but the underlying text result still contains the full returned string.\n",
-	"tools/edit.md": "# edit\n\n> Applies source edits; default mode is the hashline patch language consumed from a single `input` string.\n\n## Source\n- Entry: `packages/coding-agent/src/edit/index.ts`\n- Model-facing prompt: `packages/hashline/src/prompt.md`\n- Key collaborators:\n  - `packages/coding-agent/src/utils/edit-mode.ts` — selects active edit mode\n  - `packages/hashline/src/grammar.lark` — canonical constrained-decoding grammar\n  - `packages/hashline/src/format.ts` — sigils and header constants (`¶`, `#`, `+`, `replace`, `delete`, `insert`)\n  - `packages/hashline/src/input.ts` — parses `¶PATH#TAG` sections\n  - `packages/hashline/src/tokenizer.ts` / `packages/hashline/src/parser.ts` — tokenizes and parses ops\n  - `packages/hashline/src/apply.ts` — applies parsed edits to file text\n  - `packages/hashline/src/mismatch.ts` — stale-anchor mismatch formatting\n  - `packages/hashline/src/recovery.ts` — snapshot-based stale-anchor recovery\n  - `packages/hashline/src/snapshots.ts` — mints and resolves per-path opaque snapshot tags\n\n## Inputs\n\n### Hashline mode (default)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `input` | `string` | Yes | One or more file sections. Anchored sections start with `¶PATH#TAG`; hashless `¶PATH` is allowed only for new-file creation or purely `insert head:` / `insert tail:` inserts. Optional `*** Begin Patch` / `*** End Patch` envelope is ignored if present. |\n\nPatch language inside `input`:\n\n- **File header**: `¶PATH#TAG` (or `¶PATH` for new-file / head/tail-only inserts). `TAG` is three uppercase-hex chars minted by the session snapshot store.\n- **Operations**:\n  - `replace N..M:` — replace original lines N..M with the body rows below.\n  - `delete N..M` — delete original lines N..M. No body.\n  - `insert before N:` — insert body rows immediately before line N.\n  - `insert after N:` — insert body rows immediately after line N.\n  - `insert head:` — insert body rows at the start of the file.\n  - `insert tail:` — insert body rows at the end of the file.\n- **Body rows**:\n  - Only body-bearing headers end in `:`.\n  - Every body row is `+TEXT`; `+` alone adds a blank line.\n  - `delete` never has body rows.\n  - There is no repeat row kind. To keep a line, leave it out of every range; split edits into multiple hunks when needed.\n  - `-` rows are invalid. Literal text beginning with `-` or `+` must be written as `+-text` / `++text`.\n\nAnchors come from `read`/`search` output. `read` emits a `¶PATH#TAG` header from the session snapshot store and lines as `LINE:TEXT`; copy the header into the edit section and copy only the line number into hunk headers.\n\n### Tolerated input shapes (lenient parsing)\n\nThe canonical grammar is strict, but the hand parser accepts a few non-dangerous variants:\n\n- `replace N:` — accepted as `replace N..N:`.\n- `delete N` — accepted as single-line delete.\n- Missing trailing colon on `replace` or `insert` — accepted.\n- `replace N-M:`, `replace N…M:`, and `replace N M:` — accepted as `replace N..M:`.\n- Bare body rows with no `+` prefix are auto-prepended with `+` and a `BARE_BODY_AUTO_PIPED_WARNING` is appended.\n- `*** Begin Patch` / `*** End Patch` envelopes are silently consumed. `*** Abort` terminates parsing silently — ops parsed before the marker still apply, no warning surfaced.\n- `*** Update File:` / `*** Add File:` / `*** Delete File:` / `*** Move to:` apply_patch sentinels throw an `apply_patch sentinel … is not valid in hashline` error.\n- `@@`-bracketed hunk headers are rejected with guidance to write a verb header.\n- Bare `N` and bare `N M` / `N..M` headers are rejected with guidance to write `replace` or `delete`.\n- `delete N..M:` and any body rows under `delete` are rejected.\n- Empty `replace` / `insert` hunks are rejected.\n- `-` body rows are rejected with `MINUS_ROW_REJECTED`.\n\n## Outputs\n- Single-shot tool result; hashline mode does not use a `resolve` preview/apply handshake.\n- `content` contains one text block per call. For a successful single-file edit it is either:\n  - `<path>:` plus a compact diff preview from `packages/hashline/src/diff-preview.ts`, or\n  - `Updated <path>` / `Created <path>` when no compact preview text is emitted.\n- Parse, apply, or recovery warnings are appended as:\n\n```text\nWarnings:\n...\n```\n\n- `details` is `EditToolDetails` from `packages/coding-agent/src/edit/renderer.ts`:\n  - `diff`: unified diff string\n  - `firstChangedLine`: first changed post-edit line\n  - `diagnostics`: LSP/format result if available\n  - `op`: `\"create\"` or `\"update\"` for hashline mode\n  - `meta`: output metadata\n  - `perFileResults`: present for multi-section input\n- Multi-section input returns one aggregated result with combined text and per-file details.\n\n## Worked examples\n\nReference file (the exact shape `read` returns):\n\n```text\n¶a.ts#0A3\n1:const X = \"a\";\n2:const Y = X;\n3:\n4:console.log(X);\n5:console.log(Y);\n6:export { X, Y };\n```\n\nReplace line 1 with two lines:\n\n```text\n¶a.ts#0A3\nreplace 1..1:\n+const X = \"b\";\n+export const Y = X;\n```\n\nInsert below line 5:\n\n```text\n¶a.ts#0A3\ninsert after 5:\n+console.log(X + Y);\n```\n\nInsert above line 5:\n\n```text\n¶a.ts#0A3\ninsert before 5:\n+console.log(X + Y);\n```\n\nDelete lines 4..5 entirely:\n\n```text\n¶a.ts#0A3\ndelete 4..5\n```\n\nInsert at start and end of file:\n\n```text\n¶a.ts#0A3\ninsert head:\n+// header\ninsert tail:\n+// trailer\n```\n\nMulti-file:\n\n```text\n¶src/a.ts#0A3\nreplace 4..4:\n+const enabled = true;\n¶src/b.ts#1F7\ndelete 20\n```\n\n## Limits & Caps\n- File snapshot tags are exactly three uppercase-hex chars minted by the per-session snapshot store.\n- The visible mismatch report shows 2 lines of context on each side (`MISMATCH_CONTEXT`) in `packages/hashline/src/messages.ts`.\n- Stale-anchor recovery uses `fuzzFactor: 0` in `packages/hashline/src/recovery.ts`.\n- `HL_FILE_PREFIX` is `¶`, `HL_PAYLOAD_REPLACE` is `+`, `HL_RANGE_SEP` is `..`, `HL_FILE_HASH_SEP` is `#`, and hunk keyword constants are `replace` / `delete` / `insert` (`packages/hashline/src/format.ts`).\n\n## Errors\n- Missing section header:\n  - `input must begin with \"¶PATH#HASH\" on the first non-blank line for anchored edits; got: ...`\n- Missing tag for anchored edit:\n  - `Missing hashline snapshot tag for anchored edit to <path>; use ¶<path>#tag from your latest read/search output.`\n- Stray payload line:\n  - `line N: payload line has no preceding hunk header. Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` above the body. Got \"...\".`\n- Minus row:\n  - ``line N: `-` rows are not valid; hashline ranges already name the lines being changed. To insert a literal line starting with `-`, write `+-…`.``\n- Empty body-bearing hunk:\n  - `line N: \\`replace N..M:\\` needs at least one \\`+TEXT\\` body row. To delete lines, use \\`delete N..M\\`.`\n  - `line N: \\`insert\\` needs at least one \\`+TEXT\\` body row.`\n- Delete with body:\n  - `line N: \\`delete N..M\\` does not take body rows. Remove the body, or use \\`replace N..M:\\`.`\n- Range out of order:\n  - `line N: range A..B ends before it starts.`\n- Overlapping hunks on the same anchor:\n  - `line N: anchor line X is already targeted by another hunk on line Y. Issue ONE hunk per range; payload is only the final desired content, never a before/after pair.`\n- apply_patch / unified-diff contamination:\n  - `line N: apply_patch sentinel \"*** …\" is not valid in hashline. File sections start with \\`¶path#HASH\\` (no \\`Update File:\\` / \\`Add File:\\` keyword). Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` ops.`\n  - `line N: unified-diff hunk header (\\`@@ -N,M +N,M @@\\`) is not valid in hashline. Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` ops.`\n  - `line N: \\`@@\\`-bracketed hunk header \"@@ …\" is not valid in hashline. Drop the \\`@@ ... @@\\` brackets and write a verb header such as \\`replace N..M:\\`.`\n  - `line N: hunk headers need a verb. Use \\`replace N..N:\\` to replace, or \\`delete N\\` to delete.`\n  - `line N: bare range hunk header \"N M\" is not valid. Hunk headers need a verb: write \\`replace N..M:\\` or \\`delete N..M\\`.`\n- Out-of-range anchor:\n  - `Line N does not exist (file has M lines)`\n- Stale snapshot tag: the `Patcher` first attempts snapshot-based recovery. When recovery cannot prove a valid result it throws `MismatchError`, which distinguishes recognized-but-drifted hashes from never-recorded hashes. The error includes the current file hash plus context around each anchor.\n- No-op edit:\n  - `Edits to <path> parsed and applied cleanly, but produced no change: your body row(s) are byte-identical to the file at the targeted lines. The bug is somewhere else — re-read the file before issuing another edit. Do NOT widen the payload or add lines; verify the anchor first.`\n- Recovery failure is silent internally: if cache-based merge cannot prove a valid result, the mismatch error is surfaced unchanged.\n\n## Warnings\n- `Auto-prefixed bare body row(s) with +. Body rows must be +TEXT literal lines …` (`BARE_BODY_AUTO_PIPED_WARNING`)\n- Recovery banners: `RECOVERY_EXTERNAL_WARNING`, `RECOVERY_SESSION_CHAIN_WARNING`, `RECOVERY_SESSION_REPLAY_WARNING` (`packages/hashline/src/messages.ts`).\n",
+	"tools/edit.md": "# edit\n\n> Applies source edits; default mode is the hashline patch language consumed from a single `input` string.\n\n## Source\n- Entry: `packages/coding-agent/src/edit/index.ts`\n- Model-facing prompt: `packages/hashline/src/prompt.md`\n- Key collaborators:\n  - `packages/coding-agent/src/utils/edit-mode.ts` — selects active edit mode\n  - `packages/hashline/src/grammar.lark` — canonical constrained-decoding grammar\n  - `packages/hashline/src/format.ts` — sigils and header constants (`¶`, `#`, `+`, `replace`, `delete`, `insert`)\n  - `packages/hashline/src/input.ts` — parses `¶PATH#TAG` sections\n  - `packages/hashline/src/tokenizer.ts` / `packages/hashline/src/parser.ts` — tokenizes and parses ops\n  - `packages/hashline/src/apply.ts` — applies parsed edits to file text\n  - `packages/hashline/src/mismatch.ts` — stale-anchor mismatch formatting\n  - `packages/hashline/src/recovery.ts` — snapshot-based stale-anchor recovery\n  - `packages/hashline/src/snapshots.ts` — mints and resolves per-path opaque snapshot tags\n\n## Inputs\n\n### Hashline mode (default)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `input` | `string` | Yes | One or more file sections. Anchored sections start with `¶PATH#TAG`; hashless `¶PATH` is allowed only for new-file creation or purely `insert head:` / `insert tail:` inserts. Optional `*** Begin Patch` / `*** End Patch` envelope is ignored if present. |\n\nPatch language inside `input`:\n\n- **File header**: `¶PATH#TAG` (or `¶PATH` for new-file / head/tail-only inserts). `TAG` is three uppercase-hex chars minted by the session snapshot store.\n- **Operations**:\n  - `replace N..M:` — replace original lines N..M with the body rows below.\n  - `replace block N:` — replace the whole tree-sitter block beginning on line N (its header line through its closing line) with the body rows. The line span is resolved at apply time from the file's parse tree; point N at the line that opens the construct. Errors (and steers to `replace N..M:`) when the language is unsupported, line N is blank or a closing delimiter, no node begins there, or the resolved block has a syntax error.\n  - `delete N..M` — delete original lines N..M. No body.\n  - `delete block N` — delete the whole tree-sitter block beginning on line N (resolved like `replace block N`). No body. Same resolution failure modes and `delete N..M` fallback.\n  - `insert before N:` — insert body rows immediately before line N.\n  - `insert after N:` — insert body rows immediately after line N.\n  - `insert head:` — insert body rows at the start of the file.\n  - `insert tail:` — insert body rows at the end of the file.\n- **Body rows**:\n  - Only body-bearing headers end in `:`.\n  - Every body row is `+TEXT`; `+` alone adds a blank line.\n  - `delete` never has body rows.\n  - There is no repeat row kind. To keep a line, leave it out of every range; split edits into multiple hunks when needed.\n  - `-` rows are invalid. Literal text beginning with `-` or `+` must be written as `+-text` / `++text`.\n\nAnchors come from `read`/`search` output. `read` emits a `¶PATH#TAG` header from the session snapshot store and lines as `LINE:TEXT`; copy the header into the edit section and copy only the line number into hunk headers.\n\n### Tolerated input shapes (lenient parsing)\n\nThe canonical grammar is strict, but the hand parser accepts a few non-dangerous variants:\n\n- `replace N:` — accepted as `replace N..N:`.\n- `delete N` — accepted as single-line delete.\n- Missing trailing colon on `replace` or `insert` — accepted.\n- `replace N-M:`, `replace N…M:`, and `replace N M:` — accepted as `replace N..M:`.\n- Bare body rows with no `+` prefix are auto-prepended with `+` and a `BARE_BODY_AUTO_PIPED_WARNING` is appended.\n- `*** Begin Patch` / `*** End Patch` envelopes are silently consumed. `*** Abort` terminates parsing silently — ops parsed before the marker still apply, no warning surfaced.\n- `*** Update File:` / `*** Add File:` / `*** Delete File:` / `*** Move to:` apply_patch sentinels throw an `apply_patch sentinel … is not valid in hashline` error.\n- `@@`-bracketed hunk headers are rejected with guidance to write a verb header.\n- Bare `N` and bare `N M` / `N..M` headers are rejected with guidance to write `replace` or `delete`.\n- `delete N..M:` and any body rows under `delete` / `delete block` are rejected.\n- Empty `replace` / `insert` / `replace block` hunks are rejected.\n- `-` body rows are rejected with `MINUS_ROW_REJECTED`.\n- `replace block N:` / `delete block N` require a wired tree-sitter resolver; `replace block` additionally needs at least one `+TEXT` body row, while `delete block` takes none. An unresolvable block (unsupported language, blank/closing-delimiter line, no node beginning on N, or a syntax error in the resolved block) is rejected on the apply/final-preview path; the streaming preview silently drops it instead.\n\n## Outputs\n- Single-shot tool result; hashline mode does not use a `resolve` preview/apply handshake.\n- `content` contains one text block per call. For a successful single-file edit it is either:\n  - `<path>:` plus a compact diff preview from `packages/hashline/src/diff-preview.ts`, or\n  - `Updated <path>` / `Created <path>` when no compact preview text is emitted.\n- Parse, apply, or recovery warnings are appended as:\n\n```text\nWarnings:\n...\n```\n\n- `details` is `EditToolDetails` from `packages/coding-agent/src/edit/renderer.ts`:\n  - `diff`: unified diff string\n  - `firstChangedLine`: first changed post-edit line\n  - `diagnostics`: LSP/format result if available\n  - `op`: `\"create\"` or `\"update\"` for hashline mode\n  - `meta`: output metadata\n  - `perFileResults`: present for multi-section input\n- Multi-section input returns one aggregated result with combined text and per-file details.\n\n## Worked examples\n\nReference file (the exact shape `read` returns):\n\n```text\n¶a.ts#0A3\n1:const X = \"a\";\n2:const Y = X;\n3:\n4:console.log(X);\n5:console.log(Y);\n6:export { X, Y };\n```\n\nReplace line 1 with two lines:\n\n```text\n¶a.ts#0A3\nreplace 1..1:\n+const X = \"b\";\n+export const Y = X;\n```\n\nInsert below line 5:\n\n```text\n¶a.ts#0A3\ninsert after 5:\n+console.log(X + Y);\n```\n\nInsert above line 5:\n\n```text\n¶a.ts#0A3\ninsert before 5:\n+console.log(X + Y);\n```\n\nDelete lines 4..5 entirely:\n\n```text\n¶a.ts#0A3\ndelete 4..5\n```\n\nInsert at start and end of file:\n\n```text\n¶a.ts#0A3\ninsert head:\n+// header\ninsert tail:\n+// trailer\n```\n\nMulti-file:\n\n```text\n¶src/a.ts#0A3\nreplace 4..4:\n+const enabled = true;\n¶src/b.ts#1F7\ndelete 20\n```\n\n## Limits & Caps\n- File snapshot tags are exactly three uppercase-hex chars minted by the per-session snapshot store.\n- The visible mismatch report shows 2 lines of context on each side (`MISMATCH_CONTEXT`) in `packages/hashline/src/messages.ts`.\n- Stale-anchor recovery uses `fuzzFactor: 0` in `packages/hashline/src/recovery.ts`.\n- `HL_FILE_PREFIX` is `¶`, `HL_PAYLOAD_REPLACE` is `+`, `HL_RANGE_SEP` is `..`, `HL_FILE_HASH_SEP` is `#`, and hunk keyword constants are `replace` / `delete` / `insert` (`packages/hashline/src/format.ts`).\n\n## Errors\n- Missing section header:\n  - `input must begin with \"¶PATH#HASH\" on the first non-blank line for anchored edits; got: ...`\n- Missing tag for anchored edit:\n  - `Missing hashline snapshot tag for anchored edit to <path>; use ¶<path>#tag from your latest read/search output.`\n- Stray payload line:\n  - `line N: payload line has no preceding hunk header. Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` above the body. Got \"...\".`\n- Minus row:\n  - ``line N: `-` rows are not valid; hashline ranges already name the lines being changed. To insert a literal line starting with `-`, write `+-…`.``\n- Empty body-bearing hunk:\n  - `line N: \\`replace N..M:\\` needs at least one \\`+TEXT\\` body row. To delete lines, use \\`delete N..M\\`.`\n  - `line N: \\`insert\\` needs at least one \\`+TEXT\\` body row.`\n  - `line N: \\`replace block N:\\` needs at least one \\`+TEXT\\` body row. To delete a block, use \\`delete N..M\\` with the block's line range.`\n- Unresolvable `replace block N:` (apply / final-preview path only):\n  - `line N: \\`replace block X:\\` could not resolve a syntactic block beginning on line X. The language may be unsupported, the line may be blank or a closing delimiter, or the block may not parse. Use \\`replace X..M:\\` with the block's explicit end line instead.`\n- Delete with body:\n  - `line N: \\`delete N..M\\` does not take body rows. Remove the body, or use \\`replace N..M:\\`.`\n  - `line N: \\`delete block N\\` does not take body rows. Remove the body, or use \\`replace block N:\\` to replace the block.`\n- Range out of order:\n  - `line N: range A..B ends before it starts.`\n- Overlapping hunks on the same anchor:\n  - `line N: anchor line X is already targeted by another hunk on line Y. Issue ONE hunk per range; payload is only the final desired content, never a before/after pair.`\n- apply_patch / unified-diff contamination:\n  - `line N: apply_patch sentinel \"*** …\" is not valid in hashline. File sections start with \\`¶path#HASH\\` (no \\`Update File:\\` / \\`Add File:\\` keyword). Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` ops.`\n  - `line N: unified-diff hunk header (\\`@@ -N,M +N,M @@\\`) is not valid in hashline. Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` ops.`\n  - `line N: \\`@@\\`-bracketed hunk header \"@@ …\" is not valid in hashline. Drop the \\`@@ ... @@\\` brackets and write a verb header such as \\`replace N..M:\\`.`\n  - `line N: hunk headers need a verb. Use \\`replace N..N:\\` to replace, or \\`delete N\\` to delete.`\n  - `line N: bare range hunk header \"N M\" is not valid. Hunk headers need a verb: write \\`replace N..M:\\` or \\`delete N..M\\`.`\n- Out-of-range anchor:\n  - `Line N does not exist (file has M lines)`\n- Stale snapshot tag: the `Patcher` first attempts snapshot-based recovery. When recovery cannot prove a valid result it throws `MismatchError`, which distinguishes recognized-but-drifted hashes from never-recorded hashes. The error includes the current file hash plus context around each anchor.\n- No-op edit:\n  - `Edits to <path> parsed and applied cleanly, but produced no change: your body row(s) are byte-identical to the file at the targeted lines. The bug is somewhere else — re-read the file before issuing another edit. Do NOT widen the payload or add lines; verify the anchor first.`\n- Recovery failure is silent internally: if cache-based merge cannot prove a valid result, the mismatch error is surfaced unchanged.\n\n## Warnings\n- `Auto-prefixed bare body row(s) with +. Body rows must be +TEXT literal lines …` (`BARE_BODY_AUTO_PIPED_WARNING`)\n- Recovery banners: `RECOVERY_EXTERNAL_WARNING`, `RECOVERY_SESSION_CHAIN_WARNING`, `RECOVERY_SESSION_REPLAY_WARNING` (`packages/hashline/src/messages.ts`).\n",
 	"tools/eval.md": "# eval\n\n> Execute Python or JavaScript code in persistent cell-based runtimes.\n\n> **Notice:** Do not shell out to `python -c`/`python -e`, `bun -e`, or `node -e` via the `bash` tool for ad-hoc code execution. Use this tool instead — it gives you persistent state across cells, structured `display()` output, image/JSON capture, and proper cancellation/timeout handling that one-shot `-e`/`-c` invocations cannot provide.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/eval.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/eval.md`\n- Key collaborators:\n  - `packages/coding-agent/src/eval/backend.ts` — backend execution contract\n  - `packages/coding-agent/src/eval/js/index.ts` — JS backend adapter\n  - `packages/coding-agent/src/eval/js/executor.ts` — JS execution + output sink\n  - `packages/coding-agent/src/eval/js/context-manager.ts` — persistent VM contexts, prelude, tool bridge\n  - `packages/coding-agent/src/eval/js/prelude.txt` — JS global helpers\n  - `packages/coding-agent/src/eval/py/index.ts` — Python backend adapter\n  - `packages/coding-agent/src/eval/py/executor.ts` — kernel session retention, reset, cleanup\n  - `packages/coding-agent/src/eval/py/kernel.ts` — Jupyter gateway/kernel protocol, display capture\n  - `packages/coding-agent/src/eval/py/prelude.py` — Python helper functions and status events\n  - `packages/coding-agent/src/session/streaming-output.ts` — truncation, artifacts, streamed chunks\n  - `docs/python-repl.md` — Python kernel/gateway internals\n\n## Inputs\n\nTool parameters are a JSON object with a single `cells` field — an ordered array of cell objects. Each cell is a structured record; there is no `*** Cell` header parsing, no language sniffing, and no implicit single-cell fallback. Cells run in array order; state persists within each language across cells and across tool calls.\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `cells` | `EvalCellInput[]` | Yes | Cells executed in order. At least one cell is required (`.min(1)`). |\n\nEach `EvalCellInput` (from `evalCellSchema` in `packages/coding-agent/src/tools/eval.ts`):\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `language` | `\"py\" \\| \"js\"` | Yes | Backend selector. `\"py\"` maps to the IPython/Jupyter kernel (`python` backend); `\"js\"` maps to the persistent JavaScript VM. |\n| `code` | `string` | Yes | Cell body, verbatim. JSON-encoded — embed newlines, quotes, and indentation directly; no fences, no headers. |\n| `title` | `string` | No | Short label rendered in the transcript (e.g. `\"imports\"`, `\"load config\"`). |\n| `timeout` | `integer` | No | Per-cell timeout in seconds, clamped to `1..600`. Defaults to 30 when omitted. |\n| `reset` | `boolean` | No | Wipe this cell's language kernel before running. Reset is per-language: a `py` cell's reset does not touch the JS VM and vice versa. Defaults to `false`. |\n\nMinimal example matching the live schema:\n\n```json\n{\n  \"cells\": [\n    { \"language\": \"py\", \"title\": \"imports\", \"timeout\": 10, \"code\": \"import json\\nfrom pathlib import Path\" },\n    { \"language\": \"py\", \"title\": \"load config\", \"code\": \"data = json.loads(read('package.json'))\\ndisplay(data)\" },\n    { \"language\": \"js\", \"title\": \"summary\", \"reset\": true, \"code\": \"const data = JSON.parse(await read('package.json'));\\ndisplay(data);\\nreturn data.name;\" }\n  ]\n}\n```\n\n## Outputs\n\nFinal result from `EvalTool.execute()` is single-shot, but `onUpdate` streams partial text and `details` while cells run.\n\nReturned shape:\n\n- `content`: one text block containing combined cell output, or `(no text output)` / `(no output)` when only rich outputs exist.\n- `details` (`EvalToolDetails` from `packages/coding-agent/src/eval/types.ts`):\n  - `cells`: per-cell code, status (`pending`/`running`/`complete`/`error`), output, duration, exit code, status events, markdown flag\n  - `language`: first backend used\n  - `languages`: distinct backends used, in first-use order\n  - `jsonOutputs`: structured values emitted via `display(...)`\n  - `images`: image payloads emitted by Python rich display or JS `display({ type: \"image\", ... })`\n  - `statusEvents`: aggregated helper/tool status events\n  - `notice`: backend fallback notice (currently unused; reserved for future per-cell notices)\n  - `meta`: truncation metadata\n  - `isError`: set on cell failure or cancellation\n\nRenderer behavior in `packages/coding-agent/src/tools/eval.ts`:\n\n- call preview renders each cell's `code` with syntax highlighting based on its declared `language`\n- result view renders each cell separately, including status, duration, and output\n- markdown outputs are rendered with the Markdown component instead of plain text\n- `jsonOutputs` render as a tree, collapsed or expanded depending on UI state\n- timeout / truncation notices render as dim metadata lines\n- images are carried in `details.images`; generic tool UI image handling renders them outside the text block\n\nSide-channel artifacts:\n\n- `session.allocateOutputArtifact?.(\"eval\")` may allocate an `artifact://...` backing store for spilled output.\n- Truncated output metadata points at that artifact when available.\n\n## Flow\n\n1. `EvalTool.execute()` in `packages/coding-agent/src/tools/eval.ts` receives `params.cells` already validated by the Zod schema — no string parsing step.\n2. For each cell, `execute()` maps `cell.language` to an `EvalLanguage` (`\"py\"` → `\"python\"`, `\"js\"` → `\"js\"`) and calls `resolveBackend(session, language)`:\n   - `python` is gated on `eval.py !== false` and `pythonBackend.isAvailable(session)`.\n   - `js` is gated on `eval.js !== false`.\n   - A disabled or unavailable requested backend throws `ToolError`; there is no auto-fallback or sniffing.\n3. The tool allocates an `OutputSink`, a `TailBuffer`, per-cell result objects, and a `sessionAbortController`. `session.trackEvalExecution?.(...)` can wrap the whole run for external cancellation tracking.\n4. It resolves the executor session id from `session.getEvalSessionId?.()`, falling back to `defaultEvalSessionId(session)`. Subagents inherit the parent's id so both sides share the same JS VM and Python kernel for each backend.\n5. Cells execute sequentially within one eval tool call. For each cell, `execute()`:\n   - clamps `(cell.timeout ?? 30) * 1000` ms through `clampTimeout(\"eval\", ...)`\n   - builds a combined abort signal from the tool signal, the timeout, and the session abort controller\n   - marks the cell `running` and emits an update\n   - calls the backend’s `execute()` with `cwd`, `sessionId`, `sessionFile`, `kernelOwnerId`, `deadlineMs`, `reset` (defaults to `false`), artifact info, and chunk callback\n6. JS cells dispatch through `packages/coding-agent/src/eval/js/index.ts` into `executeJs()`; Python cells dispatch through `packages/coding-agent/src/eval/py/index.ts` into `executePython()`.\n7. Backend text chunks stream into the shared `OutputSink`; rich outputs are accumulated separately as JSON, images, markdown markers, and status events.\n8. After each cell:\n   - text output is trimmed and stored on that cell result\n   - multi-cell runs prefix text with `[i/n]` and the optional title\n   - cancellations return early with `isError: true` and a cell-specific abort message\n   - non-zero exit codes return early with `isError: true` and a message naming the failed cell\n   - later cells are skipped after the first error, but earlier cell state persists in the underlying runtime\n9. On success, the tool joins all cell outputs, synthesizes `(no text output)` or `(no output)` when needed, and attaches truncation metadata from `summarizeFinal()`.\n10. The renderer uses `details.cells`, `details.jsonOutputs`, and `details.statusEvents` to build notebook-style output. `mergeCallAndResult = true` and `inline = true`, so call and result render together in the transcript.\n\n## Modes / Variants\n\n### Backend selection\n\nBackend choice is **explicit per cell** — there is no auto-detection.\n\n- `language: \"py\"` → Python (IPython/Jupyter) backend\n- `language: \"js\"` → JavaScript VM backend\n\nIf the requested backend is disabled or unavailable, the tool throws `ToolError` for that cell. The caller chooses; the tool does not silently substitute.\n\n### JavaScript runtime\n\nImplemented in `packages/coding-agent/src/eval/js/context-manager.ts` and `packages/coding-agent/src/eval/js/prelude.txt`.\n\n- Persistent worker-backed VM sessions keyed by `js:${sessionId}`\n- `reset: true` calls `resetVmContext(sessionKey)` before the cell executes; reset is destructive for all live runs on that JS session\n- Top-level `await` and bare `return` are supported by wrapping code in an async IIFE when `wrapCode()` sees `await` or `return`\n- Top-level static `import ... from ...` and dynamic `import(...)` calls are routed through `rewriteImports()`, which sends them via `__omp_import__` so the specifier resolves against the session cwd\n- Module cache is busted for **local** imports between cells so edits to source files are picked up without restarting the runtime. `__omp_import__` deletes `require.cache[absPath]` before re-importing whenever the original specifier is a filesystem path: relative (`./x`, `../x`, `.`, `..`), POSIX-absolute (`/...`), home-prefixed (`~/...`), or Windows drive-letter (`C:\\...` / `C:/...`). Bare specifiers (`react`, `lodash/x`) and URL/scheme specifiers (`node:fs`, `file://...`, `https://...`) are left in cache so package identity stays stable across cells. The cache-bust only fires when the resolved target is an absolute path — unresolved bare-package fallbacks (`resolveImportSpecifier()` returning the original specifier) skip it.\n- The prelude installs globals:\n  - `display`, `print`\n  - `read`, `write`, `append`, `sort`, `uniq`, `counter`, `diff`, `tree`, `env`, `output`\n  - `tool.<name>(args)` proxy for arbitrary session tool calls\n  - `llm(prompt, opts)` for oneshot, stateless LLM calls (see _Oneshot LLM helper_ below)\n- JS helpers are async because they cross the VM/tool boundary\n- `display(value)` behavior:\n  - plain objects/arrays become JSON outputs\n  - `{ type: \"image\", data, mimeType }` becomes an image output\n  - scalars become text\n- The VM exposes a restricted `process` subset plus `Buffer`, `fetch`, `Blob`, `File`, `Headers`, `Request`, `Response`, `fs`, `require`, and browser-style globals\n- Concurrent runs on the same VM are not queued end-to-end. Synchronous JS still runs on the single event loop; awaited regions can interleave with sibling runs.\n\n### Python runtime\n\nImplemented in `packages/coding-agent/src/eval/py/executor.ts`, `packages/coding-agent/src/eval/py/kernel.ts`, and `packages/coding-agent/src/eval/py/prelude.py`. See `docs/python-repl.md` for gateway and kernel details.\n\n- Default mode is retained `session` kernels keyed by `python:${sessionId}`\n- Optional `python.kernelMode = \"per-call\"` creates a fresh kernel for each cell and shuts it down afterward\n- `reset: true` disposes the retained kernel for that session before the cell runs; later Python cells in the same tool call reuse the fresh kernel\n- Startup path:\n  - availability check\n  - create/connect kernel\n  - initialize cwd / env / `sys.path`\n  - execute `PYTHON_PRELUDE`\n- Python cells run in the runner's persistent asyncio event loop, so top-level `await` works; the prompt warns not to use `asyncio.run(...)`\n- The Python prelude defines helpers with the same surface as JS where practical, including `tool.<name>(args)` through a per-run loopback bridge\n- Synchronous statement blocks run in the default executor with ContextVar state copied in; the GIL still serializes bytecode execution, but awaited regions can interleave with sibling cells\n- Kernel `display_data` / `execute_result` messages map to:\n  - `application/x-omp-status` → status event\n  - `image/png` → image output\n  - `application/json` → JSON output\n  - `text/markdown` → markdown output\n  - `text/plain` → text output\n  - `text/html` → HTML converted to markdown with `htmlToBasicMarkdown()`\n- Interactive stdin is rejected: `input_request` sends an empty reply, marks `stdinRequested`, and the executor returns exit code `1`\n\n### Oneshot LLM helper (`llm`)\n\nBoth runtimes expose `llm()` — a single stateless completion against a model tier. It is intentionally minimal: no conversation history, no agent-visible tools, pure text in / text (or object) out. Implemented host-side in `packages/coding-agent/src/eval/llm-bridge.ts` and routed through the existing tool bridge under the reserved name `__llm__`.\n\n- Signatures:\n  - JS: `await llm(prompt, { model?, system?, schema? })`\n  - Python: `llm(prompt, *, model=\"default\", system=None, schema=None)`\n- `model` selects a tier (default `\"default\"`):\n  - `\"smol\"` → `pi/smol` role (fast / cheap)\n  - `\"default\"` → the session's active model, falling back to the `pi/default` role\n  - `\"slow\"` → `pi/slow` role; requests high reasoning effort only on reasoning-capable models\n- `system` (optional) supplies a system prompt.\n- `schema` (optional) is a plain JSON-Schema object. When present, the model is forced to call a single synthetic `respond` tool with that schema (loose, non-strict), and the helper returns the parsed object. When absent, the helper returns the completion string.\n- Errors surface as exceptions: unresolved tier, missing API key, an `error`/`aborted` stop reason, or empty output each raise.\n\n### Multi-language call behavior\n\nA single tool call can mix Python and JS cells. Persistence is per language runtime:\n\n- `reset: true` on a Python cell does not touch JS state\n- `reset: true` on a JS cell does not touch Python state\n- each backend keeps its own retained session keyed from the same session-derived ID\n\n## Side Effects\n\n- Filesystem\n  - JS/Python prelude helpers can read, write, append, diff, and traverse files under the session cwd or absolute paths.\n  - Output may spill to an artifact file via `OutputSink`.\n- Network\n  - Python backend speaks NDJSON to a local `python3` subprocess over stdin/stdout (no network).\n  - JS runtime exposes `fetch` and `tool.<name>()`; those tools may perform additional network I/O.\n- Subprocesses / native bindings\n  - Python availability check runs `<python> -c ...`.\n  - Python backend spawns one `python -u runner.py` subprocess per kernel; cancellation sends `SIGINT`. Details in `docs/python-repl.md`.\n- Session state\n  - `session.assertEvalExecutionAllowed?.()` can block execution.\n  - `session.trackEvalExecution?.(...)` can register cancellable eval work.\n  - `session.getSessionFile?.()`, `session.getEvalSessionId?.()`, and `session.getEvalKernelOwnerId?.()` influence VM/kernel reuse and artifact lookup.\n  - JS VM contexts persist across eval calls until reset/disposal.\n  - Python retained kernels persist until reset, owner cleanup, or process exit.\n- User-visible prompts / interactive UI\n  - none; stdin requests are rejected programmatically\n- Background work / cancellation\n  - Python retained kernels have heartbeat and idle cleanup timers.\n  - Cancellation hard-kills/resets the shared executor for that backend: JS terminates the worker, Python sends SIGINT and may escalate to subprocess shutdown.\n\n## Limits & Caps\n\n- Per-cell timeout default: 30s (applied when `timeout` is omitted in `EvalTool.execute()`; clamped through `TOOL_TIMEOUTS.eval.default` in `packages/coding-agent/src/tools/tool-timeouts.ts`)\n- Schema-level `timeout` range: integer `1..600` seconds (enforced by Zod on the cell schema)\n- Timeout clamp at runtime: 1s minimum, 600s maximum (`TOOL_TIMEOUTS.eval` in `packages/coding-agent/src/tools/tool-timeouts.ts`)\n- Transcript code/output preview: 10 lines by default (`EVAL_DEFAULT_PREVIEW_LINES` in `packages/coding-agent/src/tools/eval.ts`)\n- Output truncation window: 50KB default (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`)\n- Output line cap inside truncation helpers: 3000 lines (`DEFAULT_MAX_LINES` in `packages/coding-agent/src/session/streaming-output.ts`)\n- Streaming tail buffer for live updates: `DEFAULT_MAX_BYTES * 2` = 100KB (`packages/coding-agent/src/tools/eval.ts`)\n- Python retained kernel idle timeout: 5 minutes (`IDLE_TIMEOUT_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python retained kernel cap: 4 sessions (`MAX_KERNEL_SESSIONS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python retained kernel cleanup sweep: every 30s (`CLEANUP_INTERVAL_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python owner-cleanup shutdown wait: 2000ms (`OWNER_CLEANUP_KERNEL_SHUTDOWN_TIMEOUT_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python heartbeat interval: 5s (`ensureKernelHeartbeat()` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python external gateway availability check timeout: 5s (`AbortSignal.timeout(5000)` in `packages/coding-agent/src/eval/py/kernel.ts`)\n- Python auto-restart budget: one restart per retained session before hard failure (`restartCount > 1` in `packages/coding-agent/src/eval/py/executor.ts`)\n\n## Errors\n\n- Zod validation rejects malformed `cells` arrays before `execute()` runs (missing `language`/`code`, out-of-range `timeout`, empty `cells`).\n- Missing session without proxy executor throws `ToolError(\"Eval tool requires a session when not using proxy executor\")`.\n- Disabled/unavailable backends throw `ToolError` from `resolveBackend()`:\n  - `eval.py = false` and a `py` cell is requested\n  - `eval.js = false` and a `js` cell is requested\n  - Python kernel unavailable and a `py` cell is requested\n- JS runtime exceptions are converted into text output plus `exitCode: 1`; cancellations return `cancelled: true` and may append `Command timed out`.\n- Python execution errors from the kernel become text output and `exitCode: 1`; later cells are skipped.\n- Python stdin requests are treated as errors with the message `Kernel requested stdin; interactive input is not supported.`\n- Cancellation is returned, not thrown, once backend execution has started. The tool formats it as a cell failure and sets `details.isError = true`.\n- If output truncates, the tool still succeeds; truncation is surfaced through `details.meta` and artifact-backed full output when available.\n\n## Shared executor trade-offs\n\n- Parent agents and subagents share eval state bidirectionally when a subagent inherits the parent's executor id. Mutations in either direction are visible to the other participant.\n- Async regions of concurrent runs can interleave. Synchronous JS still blocks the VM event loop; synchronous Python still contends on the GIL.\n- Cancelling one run is destructive to the shared backend executor. This is intentional: JS worker termination and Python SIGINT/subprocess shutdown are the only reliable way to interrupt arbitrary user code.\n- `reset: true` is destructive for every live run on that backend session id. New starts on that backend are rejected while reset is in flight.\n\n## Notes\n\n- Backend selection is now strictly explicit per cell: `language` must be `\"py\"` or `\"js\"`. The previous `*** Cell` header parser, the `eval.lark` constrained grammar, and the sniffer-based fallback have all been removed.\n- `EvalTool.customFormat` no longer exists. Tool calls flow through the standard JSON schema; there is no Lark-constrained sampling path.\n- `tool.<name>()` exists in both JS and Python. Python calls route through a per-run loopback bridge keyed by the current cell id.\n- JS helper paths reject protocol URIs (`://`) in `resolvePath()`; the JS prelude is filesystem-only unless the code calls `tool.read(...)` or another tool explicitly.\n- Python helper `output(...)` depends on `PI_SESSION_FILE`; it fails outside a session-backed run.\n- `display()` can produce text and structured outputs from the same value; the renderer prefers markdown over `text/plain` when both exist.\n- JS static imports are rewritten only at top level. Nested imports stay invalid and surface normal JS syntax/runtime errors.\n- `EvalTool` is `concurrency = \"exclusive\"` within one agent session, but parent and subagent sessions can run eval concurrently when they share an inherited executor id.\n- The tool description shown to the model is templated by backend availability (`getEvalToolDescription()`); if Python is unavailable, the prompt omits Python-specific instructions.\n",
 	"tools/find.md": "# find\n\n> Find filesystem paths by glob; use `search` when you need content matches instead of path matches.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/find.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/find.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/path-utils.ts` — normalize inputs; split base path vs glob.\n  - `packages/coding-agent/src/tools/list-limit.ts` — apply result-count caps.\n  - `packages/coding-agent/src/session/streaming-output.ts` — truncate text output at byte cap.\n  - `packages/coding-agent/src/tools/tool-result.ts` — build `content` and `details.meta`.\n  - `packages/coding-agent/src/tools/output-meta.ts` — encode limit / truncation metadata.\n  - `packages/coding-agent/src/tools/tool-errors.ts` — map user-facing tool errors.\n  - `packages/coding-agent/src/tools/index.ts` — register the built-in local implementation.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `paths` | `string[]` | Yes | One or more globs, files, or directories. Empty strings are rejected. Multiple entries may be merged into one brace-union search when their base paths can be resolved together. |\n| `hidden` | `boolean` | No | Whether hidden files are included. Defaults to `true` (`hidden ?? true`). |\n| `limit` | `number` | No | Max returned paths. Defaults to `1000`. Must be a finite positive number; non-integers are floored. |\n\n## Outputs\nThe tool returns a single text block plus structured `details`.\n\n- Success text: newline-delimited paths, one per line, relative to the session cwd when possible; absolute when outside cwd. Exact file inputs return that file path as one line.\n- Empty result text: `No files found matching pattern`.\n- Multi-path partial miss: appends `Skipped missing paths: ...` after the result block, or after the empty-result line.\n- `details` may include:\n  - `scopePath`: display form of the searched root or merged roots.\n  - `fileCount`: number of paths returned after result limiting.\n  - `files`: returned paths as an array.\n  - `truncated`: whether result count or byte truncation occurred.\n  - `resultLimitReached`: reached result limit.\n  - `missingPaths`: skipped missing inputs in multi-path calls.\n  - `truncation` / `meta.limits`: structured truncation and limit metadata for renderers.\n- Streaming: when the runtime supplies `onUpdate`, the local implementation emits incremental newline-delimited text snapshots during globbing, throttled to 200 ms.\n\n## Flow\n1. `FindTool.execute()` normalizes each `paths` entry with `normalizePathLikeInput()` and `/\\\\/g -> \"/\"` (`packages/coding-agent/src/tools/find.ts`). Empty normalized entries fail with `` `paths` must contain non-empty globs or paths ``.\n2. For multi-path local calls, `partitionExistingPaths(..., parseFindPattern)` (`packages/coding-agent/src/tools/path-utils.ts`) stats each base path. Missing entries are skipped; if all are missing, the tool throws `Path not found: ...`. Single missing paths still hard-fail.\n3. The tool tries `resolveExplicitFindPatterns()` to merge multiple inputs into one search rooted at a common base path. If that does not apply, it parses one input with `parseFindPattern()`.\n4. `parseFindPattern()` determines `(basePath, globPattern, hasGlob)`:\n   - no glob chars (`*`, `?`, `[`, `{`) => search that path with implicit `**/*`.\n   - glob in the first segment => search from `.` and, unless the pattern already starts with `**/`, prefix it with `**/`.\n   - glob later in the path => split at the first glob-bearing segment.\n5. `resolveToCwd()` converts the base path to an absolute path under the session cwd. A resolved `/` is rejected with `Searching from root directory '/' is not allowed`.\n6. `limit` is defaulted to `DEFAULT_LIMIT` (`1000`) and validated as a positive finite integer. `hidden` defaults to `true`. The tool also creates a 5 s timeout via `AbortSignal.timeout(GLOB_TIMEOUT_MS)`.\n7. Execution then branches:\n   - **Custom operations branch**: if `FindToolOptions.operations.glob` exists, the tool checks existence with `operations.exists()`, short-circuits exact-file inputs via `operations.stat()` when available, then calls `operations.glob(globPattern, searchPath, { ignore: [\"**/node_modules/**\", \"**/.git/**\"], limit })`.\n   - **Built-in local branch**: the tool stats `searchPath`. Exact-file inputs return immediately. Directory inputs call `natives.glob()` with `fileType: File`, `hidden`, `maxResults: limit`, `sortByMtime: true`, `gitignore: true`, and the combined abort signal.\n8. In the local branch, optional `onMatch` callbacks convert each match to a cwd-relative display path and emit throttled progress updates.\n9. After native glob returns, JS sorts `result.matches` by `mtime` descending (`(b.mtime ?? 0) - (a.mtime ?? 0)`) before formatting paths.\n10. `buildResult()` applies `applyListLimit()` to cap the array again at `limit`, joins paths with `\\n`, then runs `truncateHead()` with `maxLines: Number.MAX_SAFE_INTEGER`. In practice this leaves the 50 KB byte cap in place while disabling the default 3000-line cap.\n11. `toolResult()` packages text plus `details`, and records result-limit / truncation metadata for renderers.\n\n## Modes / Variants\n- **Exact file path**: if the parsed input has no glob and the resolved path stats as a file, output is that one path.\n- **Directory path**: if the parsed input has no glob and stats as a directory, the tool searches it with implicit `**/*`.\n- **Single glob path**: one input parsed by `parseFindPattern()`.\n- **Merged multi-path search**: multiple inputs resolved by `resolveExplicitFindPatterns()` into one brace-union glob rooted at a common base path.\n- **Partial multi-path search with missing inputs**: local multi-path calls skip missing base paths and surface them as `missingPaths` / `Skipped missing paths: ...`.\n- **Custom delegated search**: uses injected `FindOperations` instead of local fs + native glob.\n\n## Side Effects\n- Filesystem\n  - Stats the resolved base path, and in local multi-path mode stats every candidate base path up front.\n  - Does not write files.\n- Subprocesses / native bindings\n  - Built-in local mode calls the native `@oh-my-pi/pi-natives` glob implementation.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Emits structured progress updates when `onUpdate` is provided.\n  - Adds truncation / limit metadata to the tool result.\n- Background work / cancellation\n  - Local globbing is cancellable through the caller abort signal plus an internal 5 s timeout.\n\n## Limits & Caps\n- Default result limit: `1000` (`DEFAULT_LIMIT` in `packages/coding-agent/src/tools/find.ts`).\n- Local glob timeout: `5000` ms (`GLOB_TIMEOUT_MS` in `packages/coding-agent/src/tools/find.ts`).\n- Output byte cap: `50 * 1024` bytes (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`).\n- Default generic line cap in `truncateHead()` is `3000`, but `find` overrides `maxLines` to `Number.MAX_SAFE_INTEGER`, so byte size — not line count — is the practical output truncation cap.\n- Streaming update throttle: `200` ms between `onUpdate` emissions.\n- Sort order: most recent `mtime` first in the built-in local branch and promised in the prompt. The tool re-sorts in JS even though native glob receives `sortByMtime: true` so native code can still stop early at `maxResults`.\n\n## Errors\n- User-facing `ToolError`s from `FindTool.execute()` include:\n  - `` `paths` must contain non-empty globs or paths ``\n  - `Path not found: ...`\n  - `Searching from root directory '/' is not allowed`\n  - `Limit must be a positive number`\n  - `Path is not a directory: ...`\n  - `find timed out after 5s`\n- If the caller aborts, the local branch converts `AbortError` into `ToolAbortError`.\n- Non-`ENOENT` stat failures and other unexpected errors are rethrown.\n- Empty matches are not errors; they return the no-files text result.\n\n## Notes\n- Reach for `find` for filename / path discovery. Reach for `search` when the selection criterion is file contents or regex matches; `search` takes a `pattern` and returns anchored content matches, while `find` only returns matching paths (`packages/coding-agent/src/prompts/tools/find.md`, `packages/coding-agent/src/prompts/tools/search.md`).\n- Bare top-level globs are made recursive. `*.ts` is parsed as base `.` plus glob `**/*.ts`; `src/*.ts` stays rooted at `src` with a non-recursive `*.ts` segment; `src/**/*.ts` preserves explicit recursion.\n- `.gitignore` is always enabled in the built-in local branch (`gitignore: true`). There is no model-facing flag to disable it.\n- `hidden` defaults to `true`; hidden-file exclusion is opt-out, not opt-in.\n- Multi-path missing-input tolerance only applies in the built-in local branch. The custom-operations branch hard-fails the first missing `searchPath` it checks.\n- The custom `FindOperations.glob()` hook receives `ignore` and `limit`, but not the `hidden` flag or an explicit `.gitignore` toggle. A remote delegate must account for that itself if it wants parity with the local branch.\n- Built-in local globbing asks the native layer for `fileType: File`, so recursive directory searches yield files, not directories. Directory outputs are only possible through exact-path passthrough or custom delegates that return them.\n",
 	"tools/github.md": "# github\n\n> Dispatch GitHub CLI operations for repositories, issues, pull requests, search, and Actions run watching.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/gh.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/github.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/gh-format.ts` — shorten commit SHAs for summaries.\n  - `packages/coding-agent/src/tools/gh-renderer.ts` — TUI rendering, especially `run_watch` live/result views.\n  - `packages/coding-agent/src/utils/git.ts` — `gh`/`git` process wrappers, repo locking, branch config writes.\n  - `packages/utils/src/dirs.ts` — base directory for dedicated PR worktrees.\n  - `packages/coding-agent/src/sdk.ts` — session artifact allocation hook.\n  - `packages/coding-agent/src/session/artifacts.ts` — artifact filename format `<id>.<toolType>.log`.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `\"repo_view\" \\| \"pr_create\" \\| \"pr_checkout\" \\| \"pr_push\" \\| \"search_issues\" \\| \"search_prs\" \\| \"search_code\" \\| \"search_commits\" \\| \"search_repos\" \\| \"run_watch\"` | Yes | Dispatch selector. `GithubTool.execute()` switches only on this field. |\n| `repo` | `string` | No | `owner/repo` override. Ignored when the identifier argument is already a full GitHub URL. For `search_issues`/`search_prs`/`search_code`/`search_commits`, defaults to the current checkout's `owner/repo` when omitted (skipped when the query already contains a `repo:`/`org:`/`user:`/`owner:` qualifier or when current-repo resolution fails). Required in practice when `gh` cannot infer repo context from the current checkout. |\n| `branch` | `string` | No | Used by `repo_view`, `pr_push`, and `run_watch`. `run_watch` falls back to current git branch when `run` is omitted; `pr_push` falls back to current branch. |\n| `pr` | `string \\| string[]` | No | Used by `pr_checkout`. Each item may be a PR number, branch name, or GitHub PR URL. Array form enables batching. Omitted means current branch PR. |\n| `force` | `boolean` | No | Used only by `pr_checkout`. Defaults to `false`; allows resetting an existing `pr-<number>` local branch to the PR head commit. |\n| `forceWithLease` | `boolean` | No | Used only by `pr_push`; passed through to git push. |\n| `title` | `string` | No | Used only by `pr_create`. Required unless `fill` is `true`. |\n| `body` | `string` | No | Used only by `pr_create`. Mutually exclusive with `fill`. Empty/omitted body becomes `--body \"\"` to suppress the interactive editor. Non-empty body is written to a temp file and passed as `--body-file`. |\n| `base` | `string` | No | Used only by `pr_create`; passed as `--base`. |\n| `head` | `string` | No | Used only by `pr_create`; passed as `--head`. |\n| `draft` | `boolean` | No | Used only by `pr_create`. Defaults to `false`. |\n| `fill` | `boolean` | No | Used only by `pr_create`. Defaults to `false`. Mutually exclusive with `title` and `body`. |\n| `reviewer` | `string[]` | No | Used only by `pr_create`; each entry becomes `--reviewer`. |\n| `assignee` | `string[]` | No | Used only by `pr_create`; each entry becomes `--assignee`. |\n| `label` | `string[]` | No | Used only by `pr_create`; each entry becomes `--label`. |\n| `query` | `string` | No | Used by all `search_*` ops. Required there. |\n| `limit` | `number` | No | Used by all `search_*` ops. Defaults to `10`, floored, clamped to `50`, and must be `> 0`. |\n| `run` | `string` | No | Used only by `run_watch`. Must be a numeric run ID or full GitHub Actions run URL. |\n| `tail` | `number` | No | Used only by `run_watch`. Defaults to `15`, floored, clamped to `200`, and must be `> 0`. |\n\n## Outputs\nThe tool returns a single text result built by `buildTextResult()` in `packages/coding-agent/src/tools/gh.ts`.\n\n- `content`: one text block. Multi-item ops join sections with blank lines and `---` separators.\n- `sourceUrl`: set for single repo/PR/run results when a canonical URL is known.\n- `details`: optional structured metadata used by the TUI renderer.\n  - Common fields: `artifactId`, `repo`, `branch`, `worktreePath`, `remote`, `remoteBranch`, `headSha`, `runId`, `runIds`, `status`, `conclusion`, `failedJobs`.\n  - `pr_checkout` adds `checkouts: GhPrCheckoutSummary[]`.\n  - `run_watch` adds `watch: GhRunWatchViewDetails`, which drives the custom live/result renderer in `packages/coding-agent/src/tools/gh-renderer.ts`.\n- Artifact trailer: when `artifactId` is present, the text body gets an appended line like `Full failed-job logs: artifact://<id>`.\n  - `run_watch` allocates artifacts with `session.allocateOutputArtifact(\"github\")`; persistent sessions therefore save failed-log bodies as `<artifact-dir>/<id>.github.log`.\n\n`run_watch` is the only streaming op. It emits `onUpdate` snapshots while polling, then returns one final text result.\n\n## Flow\n1. `GithubTool.createIf()` exposes the tool only when `git.github.available()` finds `gh` on `PATH`.\n2. `GithubTool.execute()` wraps dispatch in `untilAborted()` and switches on `params.op`.\n3. Each op normalizes optional strings, arrays, booleans, and numeric caps locally in `packages/coding-agent/src/tools/gh.ts`.\n4. CLI execution goes through `git.github.run/json/text()` in `packages/coding-agent/src/utils/git.ts`:\n   - spawns `gh ...` with `Bun.spawn()`;\n   - trims stdout/stderr unless `trimOutput: false`;\n   - maps common auth/repo-context failures into tool-facing `ToolError` messages;\n   - `json()` rejects empty or invalid JSON.\n5. Read-style ops (`repo_view`, `search_*`) fetch JSON and format Markdown-like text summaries. Single-issue and single-PR views were moved out of the tool and now resolve through the `issue://` / `pr://` internal URL schemes, which share the same SQLite cache.\n7. PR diffs moved out of the tool. `pr://<N>/diff` lists changed files, `pr://<N>/diff/<i>` slices a single file, and `pr://<N>/diff/all` returns the full unified diff — see `docs/tools/read.md`. All three variants share one `gh pr diff` invocation through the `pr-diff` cache row.\n8. `pr_checkout` resolves PR metadata first, then enters `git.withRepoLock()` before any git mutation so parallel checkout calls for the same primary repo do not race on shared `.git` state.\n9. `pr_push` reads PR head metadata back from git branch config, derives a refspec, then pushes with `git.push()`.\n10. `pr_create` shells out once, then best-effort re-reads the created PR for a richer summary.\n11. `run_watch` chooses either run mode (`run` supplied) or commit mode (`run` omitted), polls GitHub Actions APIs every 3 seconds, emits streaming updates, and may save a full failed-log artifact before returning.\n12. Final text goes through `toolResult().text(...)`; if `session.allocateOutputArtifact()` returns a slot, failed-log text is persisted with `Bun.write()`.\n\n## Modes / Variants\n\n### `repo_view`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `branch` |\n| `gh` command | `gh repo view [<repo>] [--branch <branch>] --json <GH_REPO_FIELDS>` |\n| Batching | None |\n| Output | `# <owner/repo>` header, description, URL, default branch, requested branch, visibility, permission, primary language, stars, forks, archive/fork flags, updated timestamp, homepage, topics. `sourceUrl = data.url`. |\n\nIf `repo` is omitted, `gh` repository resolution is used.\n\nSingle-issue and single-PR reads live in the `issue://<N>` / `pr://<N>` URL schemes (see `docs/tools/read.md`). They share `~/.omp/cache/github-cache.db` (override via `OMP_GITHUB_CACHE_DB`) and the `github.cache.softTtlSec` / `github.cache.hardTtlSec` / `github.cache.enabled` settings. The cache retains rendered Markdown plus the raw JSON payload returned by `gh`, including private bodies, comments, reviews, and review comments when comments are enabled; rows are scoped by the local GitHub credential fingerprint. Root and repo-scoped reads (`issue://`, `pr://owner/repo`) issue a live `gh issue list` / `gh pr list` for browsing; query params `state`, `limit`, `author`, `label` pass through to `gh` (`issue://` accepts `state=open|closed|all`; `pr://` also accepts `merged`). PR diffs ride the same cache under `pr://<N>/diff[/…]`: the listing, full diff, and per-file slices all share one `pr-diff` row keyed by repo and PR number.\n\n### `pr_create`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` plus either `fill=true` or `title` |\n| Optional fields | `repo`, `title`, `body`, `base`, `head`, `draft`, `fill`, `reviewer[]`, `assignee[]`, `label[]` |\n| `gh` command | `gh pr create ...` with flags assembled from provided fields |\n| Batching | None |\n| Output | `# Created Pull Request ...` summary with URL, state, draft flag, base/head, author, created time, labels, optional body. `sourceUrl` is the created PR URL. |\n\nBranches:\n- `fill && (title || body !== undefined)` throws.\n- Non-empty `body` is written under a temp dir `gh-pr-body-*` in `os.tmpdir()`, passed as `--body-file`, then removed in `finally`.\n- After creation, the tool parses the returned URL and best-effort runs `gh pr view <number> --repo <repo> --json <GH_PR_FIELDS_NO_COMMENTS>`; failures there are swallowed.\n\n### `pr_checkout`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `pr`, `force` |\n| `gh` command | For each requested PR: `gh pr view [<pr>] [--repo <repo>] --json <GH_PR_CHECKOUT_FIELDS>`; cross-repo PRs may also call `gh repo view <headRepository> --json <GH_REPO_CLONE_FIELDS>`. |\n| Batching | Yes. `pr` may be `string[]`; each PR is resolved in parallel, but git mutations are serialized per primary repo by `git.withRepoLock()`. |\n| Output | Single PR: checkout/worktree summary plus `details.repo`, `details.branch`, `details.worktreePath`, `details.remote`, `details.remoteBranch`, `details.checkouts`. Batched: `# <n> Pull Request Worktrees (...)` plus one section per PR and aggregated `details.checkouts`. |\n\nWorktree and metadata behavior:\n- Local branch name is always `pr-<number>`.\n- Worktree path is `path.join(getWorktreesDir(), encodeRepoPathForFilesystem(primaryRepoRoot), localBranch)`, where `getWorktreesDir()` is `~/.omp/wt`; effective path is `~/.omp/wt/<encoded-primary-repo-root>/pr-<number>`.\n- Existing worktree detection is by branch ref `refs/heads/pr-<number>` from `git.worktree.list()`.\n- New worktree creation calls `git.worktree.add(repoRoot, finalWorktreePath, localBranch, { signal })` after verifying the path is neither already registered nor already present on disk.\n- For same-repo PRs, remote is `origin`. For cross-repo PRs, the tool resolves a clone URL for the head repo, reuses an existing remote with the same URL when possible, or creates `fork-<owner>` / `fork-<owner>-<n>`.\n- The branch push metadata is persisted with `git config` under the repository's shared `.git/config` as:\n  - `branch.pr-<number>.remote`\n  - `branch.pr-<number>.merge`\n  - `branch.pr-<number>.pushRemote`\n  - `branch.pr-<number>.ompPrHeadRef`\n  - `branch.pr-<number>.ompPrUrl`\n  - `branch.pr-<number>.ompPrIsCrossRepository`\n  - `branch.pr-<number>.ompPrMaintainerCanModify`\n- If `refs/heads/pr-<number>` already exists at a different commit, checkout fails unless `force=true`, in which case `git branch --force` resets it to the fetched PR head.\n- If a matching worktree already exists, the tool reuses it and reports `reused: true`.\n\n### `pr_push`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `branch`, `forceWithLease` |\n| `gh` command | None. This path uses git, not `gh`. |\n| Batching | None |\n| Output | `# Pushed Pull Request Branch` summary with local branch, remote, remote branch, remote URL, PR URL, and force-with-lease flag. `sourceUrl = prUrl` when known. |\n\nPush target resolution reads the `branch.<name>.ompPrHeadRef`, `pushRemote`/`remote`, `ompPrUrl`, `ompPrMaintainerCanModify`, and `ompPrIsCrossRepository` git-config keys written by `pr_checkout`. If the current checked-out branch matches the target branch, the source ref is `HEAD`; otherwise it pushes `refs/heads/<branch>`. The refspec is `HEAD:refs/heads/<headRef>` or `refs/heads/<branch>:refs/heads/<headRef>`.\n\n### `search_issues`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh api -X GET /search/issues -f q=\"<query> [repo:<repo>] is:issue\" -F per_page=<limit>` |\n| Batching | None |\n| Output | `# GitHub issues search`, echoed query, optional repo, result count, then one bullet per issue with repo/state/author/labels/timestamps/URL. |\n\n`repo` defaults to the current checkout's `owner/repo` via `resolveSearchRepoScope()` when omitted. The default is suppressed when the query already contains a leading `repo:`/`org:`/`user:`/`owner:` qualifier or when `gh repo view` fails to resolve the current checkout (e.g. outside a github remote).\n\n### `search_prs`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh api -X GET /search/issues -f q=\"<query> [repo:<repo>] is:pr\" -F per_page=<limit>` |\n| Batching | None |\n| Output | Same shape as `search_issues`, labeled as pull requests. |\n\n`repo` defaults to the current checkout's `owner/repo` as in `search_issues`.\n\n### `search_code`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh api -X GET /search/code -f q=\"<query> [repo:<repo>]\" -F per_page=<limit> -H \"Accept: application/vnd.github.text-match+json\"` |\n| Batching | None |\n| Output | `# GitHub code search`, result count, then one bullet per match with path, repo, short commit SHA, URL, and first normalized text-match fragment line when present. |\n\n`repo` defaults to the current checkout's `owner/repo` as in `search_issues`.\n\n### `search_commits`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh api -X GET /search/commits -f q=\"<query> [repo:<repo>]\" -F per_page=<limit>` |\n| Batching | None |\n| Output | `# GitHub commits search`, result count, then one bullet per commit: short SHA + first commit-message line, repo, author, date, URL. |\n\n`repo` defaults to the current checkout's `owner/repo` as in `search_issues`.\n\n### `search_repos`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `limit` |\n| `gh` command | `gh api -X GET /search/repositories -f q=\"<query>\" -F per_page=<limit>` |\n| Batching | None |\n| Output | `# GitHub repositories search`, result count, then one bullet per repo with first description line, language, stars, forks, open issues, visibility, archive/fork flags, updated time, URL. |\n\n`repo` is intentionally not used for this op.\n\n### `run_watch`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `branch`, `run`, `tail` |\n| `gh` command | Repo resolution: `gh repo view --json nameWithOwner -q .nameWithOwner` when `repo` and run URL repo are both absent. Single-run mode uses `gh api --method GET /repos/<repo>/actions/runs/<runId>` and `gh api --method GET /repos/<repo>/actions/runs/<runId>/jobs`. Commit mode uses `gh api --method GET /repos/<repo>/branches/<branch>`, `gh api --method GET /repos/<repo>/actions/runs`, `gh api --method GET /repos/<repo>/actions/runs/<runId>/jobs`, and `gh api /repos/<repo>/actions/jobs/<jobId>/logs` for failed jobs. |\n| Batching | Implicit batching only in commit mode: all workflow runs for one commit are tracked together. |\n| Output | Streaming watch snapshots via `onUpdate`, then a final text report. On failure, appends `Full failed-job logs: artifact://<id>` and sets `details.artifactId`. |\n\nWatch flow:\n- `run` parsing accepts either a decimal run ID or a full run URL. URL repo must match explicit `repo` when both are given.\n- Poll interval is fixed at 3 seconds (`RUN_WATCH_INTERVAL_DEFAULT`).\n- Failure grace period is fixed at 5 seconds (`RUN_WATCH_GRACE_DEFAULT`). When any failed job appears before completion, the tool emits a note, waits once, re-fetches state, then collects logs so concurrent failures are included.\n- Failed-job logs are fetched with `gh api /repos/<repo>/actions/jobs/<jobId>/logs` via `git.github.run()`, not `json()`. Non-zero exit leaves `available: false` instead of failing the whole watch.\n- Inline result includes only the last `tail` lines per failed job. The saved artifact contains full logs (`mode: \"full\"`).\n- In commit mode, success is intentionally double-checked: once all known runs are successful, the tool waits one more poll interval and succeeds only if the set of run IDs is unchanged. This avoids returning before late workflow runs appear for the same commit.\n- `details.watch` drives a specialized renderer in `packages/coding-agent/src/tools/gh-renderer.ts`; non-watch results fall back to generic text rendering.\n\n## Side Effects\n- Filesystem\n  - `pr_create` may create a temp dir under `os.tmpdir()` named `gh-pr-body-*`, write `body.md`, then remove the dir in `finally`.\n  - `pr_checkout` may create directories under `~/.omp/wt/<encoded-primary-repo-root>/` and add git worktrees there.\n  - `run_watch` may write a session artifact with full failed-job logs.\n- Network\n  - Every op shells out to `gh`, which then talks to GitHub APIs except `pr_push`.\n  - `pr_push` uses git network transport to the configured remote.\n- Subprocesses / native bindings\n  - All `gh` calls use `Bun.spawn([\"gh\", ...args])`.\n  - `pr_checkout` and `pr_push` also invoke git helpers from `packages/coding-agent/src/utils/git.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - `run_watch` consumes `session.allocateOutputArtifact()` when failed-job logs are persisted.\n  - Returned `details` objects carry run/checkouts metadata for the renderer/UI.\n- User-visible prompts / interactive UI\n  - `gh` interactive editor fallback is suppressed for `pr_create` by forcing either `--body-file` or `--body \"\"`.\n  - `gh-renderer` provides compact headers for all ops and a custom live watch view for `run_watch`.\n- Background work / cancellation\n  - `run_watch` loops until success/failure and uses `scheduler.wait()` between polls.\n  - `GithubTool.execute()` is wrapped in `untilAborted()`; `git.github.run()` forwards the abort signal into `Bun.spawn()`.\n\n## Limits & Caps\n- Search result default: `10` (`SEARCH_LIMIT_DEFAULT` in `packages/coding-agent/src/tools/gh.ts`).\n- Search result max: `50` (`SEARCH_LIMIT_MAX`).\n- PR file preview inside the `pr://` view: first `50` files only (`FILE_PREVIEW_LIMIT` in `gh.ts`).\n- Run-watch poll interval: `3s` (`RUN_WATCH_INTERVAL_DEFAULT`).\n- Run-watch failure grace period: `5s` (`RUN_WATCH_GRACE_DEFAULT`).\n- Run-watch failed-log tail default: `15` lines (`RUN_WATCH_TAIL_DEFAULT`).\n- Run-watch failed-log tail max: `200` lines (`RUN_WATCH_TAIL_MAX`).\n- PR review comments page size: `100` (`REVIEW_COMMENTS_PAGE_SIZE`).\n- Actions jobs page size: `100` (`RUN_JOBS_PAGE_SIZE`).\n- Search and tail numeric inputs are floored with `Math.floor()`, clamped to the max, and rejected when non-finite or `<= 0`.\n- `pr_checkout` batch fan-out is unbounded in tool code; all requested PRs are launched with `Promise.all()`.\n\n## Errors\n- Tool creation is skipped entirely when `gh` is not installed.\n- `git.github.run()` throws `ToolError(\"GitHub CLI (gh) is not installed...\")` if `gh` is missing at execution time.\n- `git.github.text/json()` map common failures to model-facing messages:\n  - not authenticated → `GitHub CLI is not authenticated. Run \\`gh auth login\\`.`\n  - missing repo context without explicit `repo` → `GitHub repository context is unavailable. Pass \\`repo\\` explicitly or run the tool inside a GitHub checkout.`\n  - otherwise stderr/stdout text, or fallback `GitHub CLI command failed: gh ...`\n- `json()` also throws on empty stdout or invalid JSON.\n- Local validation errors throw `ToolError`, including:\n  - missing required per-op fields (`query`, `title unless fill=true`)\n  - invalid numeric `limit` / `tail`\n  - invalid `run` format\n  - `fill` combined with `title` or `body`\n  - missing git repo / branch / HEAD context for checkout, push, or watch\n  - `pr_push` on a branch without `ompPrHeadRef` metadata\n  - conflicting existing worktree path or branch without `force`\n- `run_watch` treats failed-job log fetches specially: missing log content does not fail the watch; it marks that log `available: false` and prints `Log tail unavailable.` / `Full log unavailable.`.\n- `pr_create` swallows only the post-create best-effort `gh pr view` refresh; the create step itself still fails normally.\n\n## Notes\n- `appendRepoFlag()` intentionally skips `--repo` when the identifier argument is already a full GitHub URL; that lets `gh` derive repo/number from the URL.\n- `normalizePrIdentifierList()` accepts `reviewer`, `assignee`, and `label` arrays too; the helper name is broader than its callers.\n- `pr_push` depends on `pr_checkout` having run first for that local branch; there is no alternate metadata source.\n- `pr_checkout` stores push metadata in branch config, not in the worktree directory. Reusing the same `pr-<number>` branch reuses those config keys.\n- Worktree write serialization is keyed by the primary repo root, not the current worktree path, because git worktrees share `.git/config`, `packed-refs`, commit-graph, and worktree metadata files.\n- `search_repos` is the only search op that never forwards `repo`; repository scoping must be expressed in the query itself.\n- `run_watch` success on commit mode means “all observed runs succeeded and no additional runs appeared one poll later”, not merely “latest poll looked green”.\n- The TUI renderer collapses failed log previews unless the result view is expanded; the underlying text result still contains the same tailed lines plus any artifact reference.\n",
@@ -83,7 +83,6 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"tools/lsp.md": "# lsp\n\n> Query language servers for diagnostics, navigation, symbols, renames, code actions, capabilities, and raw requests.\n\n## Source\n- Entry: `packages/coding-agent/src/lsp/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/lsp.md`\n- Key collaborators:\n  - `packages/coding-agent/src/lsp/client.ts` — client process lifecycle and JSON-RPC\n  - `packages/coding-agent/src/lsp/config.ts` — config loading, auto-detect, server selection\n  - `packages/coding-agent/src/lsp/lspmux.ts` — optional `lspmux` command wrapping\n  - `packages/coding-agent/src/lsp/edits.ts` — apply `WorkspaceEdit` and text edits\n  - `packages/coding-agent/src/lsp/utils.ts` — URI conversion, symbol resolution, formatting, glob expansion\n  - `packages/coding-agent/src/lsp/types.ts` — tool schema and protocol types\n  - `packages/coding-agent/src/lsp/clients/index.ts` — custom linter client cache/factory\n  - `packages/coding-agent/src/lsp/clients/lsp-linter-client.ts` — LSP-backed linter adapter\n  - `packages/coding-agent/src/lsp/clients/biome-client.ts` — Biome CLI diagnostics/formatting adapter\n  - `packages/coding-agent/src/lsp/clients/swiftlint-client.ts` — SwiftLint CLI diagnostics adapter\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and `lsp.enabled` gating\n  - `packages/coding-agent/src/tools/tool-timeouts.ts` — timeout defaults and clamping\n  - `packages/coding-agent/src/lsp/defaults.json` — built-in server definitions for auto-detect\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | string enum | Yes | One of `diagnostics`, `definition`, `references`, `hover`, `symbols`, `rename`, `rename_file`, `code_actions`, `type_definition`, `implementation`, `status`, `reload`, `capabilities`, `request`. |\n| `file` | string | No | File path; for `diagnostics` also a glob; for workspace forms use `\"*\"`; for `rename_file` this is the source path. |\n| `line` | number | No | 1-indexed line number for position-based actions. Defaults to `1` on the single-file action path. |\n| `symbol` | string | No | Substring used to resolve the column on `line`. Supports `name#N` occurrence selectors; `N` is 1-indexed and defaults to `1`. |\n| `query` | string | No | Workspace symbol query, code-action selector/filter, or LSP method name for `action=request`. |\n| `new_name` | string | No | Required for `rename` and `rename_file`. |\n| `apply` | boolean | No | For `rename`/`rename_file`, apply unless explicitly `false`. For `code_actions`, list unless explicitly `true`. |\n| `timeout` | number | No | Seconds, clamped by `clampTimeout(\"lsp\", ...)` to `5..60`, default `20`. |\n| `payload` | string | No | JSON string for `action=request`; overrides auto-built params. |\n\n## Outputs\n- Single-shot `AgentToolResult`.\n- `content` is always one text block: `[{ type: \"text\", text: string }]`.\n- `details` is `LspToolDetails`: `action`, `success`, optional `serverName`, optional original `request`.\n- No streaming updates.\n- No artifact URIs or background jobs.\n- Many validation failures are returned as ordinary text results with `details.success: false`; aborts throw `ToolAbortError` instead.\n\n## Flow\n1. `packages/coding-agent/src/tools/index.ts` registers `lsp: LspTool.createIf`; session creation also gates it behind `session.enableLsp !== false` and `settings.get(\"lsp.enabled\")`.\n2. `LspTool.execute()` in `packages/coding-agent/src/lsp/index.ts` clamps `timeout` with `clampTimeout(\"lsp\", ...)`, builds an `AbortSignal.timeout(...)`, and combines it with the caller signal.\n3. `getConfig()` loads and caches `LspConfig` per cwd, applies idle-timeout config via `setIdleTimeout()`, and reuses the cached config on later calls.\n4. Config loading in `packages/coding-agent/src/lsp/config.ts` merges `defaults.json` with JSON/YAML overrides from project, project config dirs, user config dirs, plugin roots, and home; if there are no overrides it auto-detects servers from root markers plus executable discovery.\n5. Server routing uses `getServersForFile()` / `getServerForFile()` from `config.ts`: extension or basename match, then sort primary servers before linters. `index.ts` further filters custom linter clients out of navigation/refactor paths with `getLspServersForFile()` / `getLspServerForFile()`.\n6. `getOrCreateClient()` in `client.ts` creates one process per `command:cwd`, optionally wraps supported commands with `lspmux`, spawns the server, starts the background message reader, sends `initialize`, stores server capabilities, then sends `initialized`.\n7. The message reader in `client.ts` parses LSP frames, resolves pending requests, caches `publishDiagnostics`, tracks `$/progress` tokens for project-load completion, answers `workspace/configuration`, and applies `workspace/applyEdit` requests through `applyWorkspaceEdit()`.\n8. File-scoped actions call `ensureFileOpen()` before requests. Column resolution uses `resolveSymbolColumn()` from `utils.ts`: read the target file, pick first non-whitespace when `symbol` is omitted, otherwise find the exact or case-insensitive match on the target line and honor `#N` occurrence selectors.\n9. Actions dispatch in `LspTool.execute()` through dedicated branches: workspace-only branches (`status`, some `diagnostics`, workspace `symbols`, workspace `reload`, `capabilities`, `request`) run before the single-file switch; all other single-file actions share one client lookup and `switch(action)`.\n10. Requests go through `sendRequest()` in `client.ts`, which allocates an incrementing JSON-RPC id, installs abort and timeout handling, sends `$/cancelRequest` on abort, and rejects on timeout or process exit.\n11. Actions that return edits either preview with `formatWorkspaceEdit()` or apply with `applyWorkspaceEdit()` from `edits.ts`; `rename_file` also performs the filesystem rename and then sends `workspace/didRenameFiles`.\n12. Non-abort failures inside the single-file action block are converted to `LSP error: ...`; many precondition failures return explicit text without throwing.\n\n## Modes / Variants\n### Routing and workspace scope\n- `file: \"*\"` is only special for `diagnostics`, `symbols`, and `reload`.\n- `status` ignores `file`.\n- `capabilities` with omitted `file` or `\"*\"` inspects all non-custom LSP servers; with a concrete file it scopes to matching non-custom servers.\n- `request` with omitted `file` or `\"*\"` chooses the first available non-custom LSP server; with a concrete file it chooses that file's primary non-linter server.\n- `rename_file` sends `workspace/willRenameFiles` and `workspace/didRenameFiles` to every non-custom LSP server from `getLspServers(config)`, not just one file-scoped server.\n- Diagnostics are the only tool action that queries both normal LSP servers and custom linter clients (`BiomeClient`, `SwiftLintClient`, or `LspLinterClient`).\n\n### `diagnostics`\n**Inputs**\n- Required: `file`, unless using workspace mode with `file: \"*\"`.\n- Optional: `timeout`.\n\n**Execution**\n- `file: \"*\"`: `runWorkspaceDiagnostics()` detects project type from root markers and runs one subprocess command: Rust `cargo check --message-format=short`, TypeScript `npx tsc --noEmit`, Go `go build ./...`, Python `pyright`.\n- Concrete file or glob: `resolveDiagnosticTargets()` treats non-globs as one target, otherwise expands a `Bun.Glob` up to `MAX_GLOB_DIAGNOSTIC_TARGETS`.\n- Per file, every matching server runs: custom clients call `lint(file)`; real LSP servers optionally wait for project load, capture `diagnosticsVersion`, `refreshFile()`, then `waitForDiagnostics()` for fresh `publishDiagnostics`.\n- Results are deduplicated by range+message and severity-sorted.\n\n**Output text**\n- Single target with no issues: `OK`.\n- Single target with issues: `<summary>:\\n<grouped diagnostics>`.\n- Batch/glob target: one section per file, plus an initial truncation warning when the glob exceeds the file cap.\n- Workspace mode: `Workspace diagnostics (<detected description>):\\n<command output>`.\n\n### `definition`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/definition` with `{ textDocument, position }`.\n- Accepts `Location`, `Location[]`, `LocationLink`, or `LocationLink[]`; `normalizeLocationResult()` converts `LocationLink` to `targetSelectionRange ?? targetRange`.\n- Waits for project load before the request.\n\n**Output text**\n- `No definition found` or `Found N definition(s):` followed by `file:line:col` and one context line above/below each location.\n\n### `type_definition`\nSame as `definition`, but sends `textDocument/typeDefinition` and reports `type definition(s)`.\n\n### `implementation`\nSame as `definition`, but sends `textDocument/implementation` and reports `implementation(s)`.\n\n### `references`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/references` with `includeDeclaration: true`.\n- For project-aware servers, retries up to `REFERENCES_RETRY_COUNT` times when the only hit is the queried declaration; between retries it waits for project load and sleeps `REFERENCES_RETRY_DELAY_MS`.\n- First `REFERENCE_CONTEXT_LIMIT` references include surrounding context; the rest are location-only.\n\n**Output text**\n- `No references found` or `Found N reference(s):` with contextual entries first, then `... M additional reference(s) shown without context` when truncated.\n\n### `hover`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/hover`.\n- `extractHoverText()` flattens strings, markup content, marked-string objects, or arrays into plain text.\n\n**Output text**\n- `No hover information` or the extracted hover text.\n\n### `symbols`\n**Inputs**\n- Workspace mode: `file: \"*\"` or omitted file on the early workspace branch, plus required `query`.\n- Document mode: required `file`.\n- Optional: `timeout`.\n\n**Execution**\n- Workspace mode sends `workspace/symbol` to every non-custom LSP server, post-filters matches with `filterWorkspaceSymbols()`, deduplicates with `dedupeWorkspaceSymbols()`, then truncates to `WORKSPACE_SYMBOL_LIMIT`.\n- Document mode sends `textDocument/documentSymbol` to the primary server. If the first item has `selectionRange`, it formats hierarchical `DocumentSymbol`s; otherwise it formats flat `SymbolInformation`s.\n\n**Output text**\n- Workspace mode: `Found N symbol(s) matching \"query\":` plus formatted `name @ file:line:col`, with an omission line when over the limit.\n- Document mode: `Symbols in <file>:` plus hierarchical or flat symbol lines.\n\n### `rename`\n**Inputs**\n- Required: `file`, `new_name`.\n- Optional: `line`, `symbol`, `apply`, `timeout`.\n\n**Execution**\n- Waits for project load, sends `textDocument/rename`, receives a `WorkspaceEdit`.\n- `apply !== false` applies edits immediately with `applyWorkspaceEdit()`.\n- `apply === false` renders a preview with `formatWorkspaceEdit()`.\n\n**Output text**\n- `Rename returned no edits`, `Applied rename:` plus applied change lines, or `Rename preview:` plus summarized edits.\n\n### `rename_file`\n**Inputs**\n- Required: `file` source path, `new_name` destination path.\n- Optional: `apply`, `timeout`.\n\n**Execution**\n- Resolves absolute source and destination, rejects identical paths, missing source, existing destination, empty rename set, or directories with more than `MAX_RENAME_PAIRS` files.\n- `enumerateRenamePairs()` returns one `{oldUri,newUri}` pair for a file or walks every regular file in a directory tree.\n- Sends `workspace/willRenameFiles` with `{ files: pairs }` to every non-custom LSP server; collects returned `WorkspaceEdit`s and server notes.\n- Preview mode (`apply === false`) only formats those edits.\n- Apply mode runs each returned `WorkspaceEdit`, renames the source path on disk, sends `textDocument/didClose` for every renamed open file, deletes those `openFiles` entries, then sends `workspace/didRenameFiles`.\n\n**Output text**\n- Preview: `Rename preview: <file-count label> → <dest>` plus per-server edit summaries and optional server notes.\n- Apply: `Renamed <file-count label> → <dest>` plus applied edit summaries, filesystem rename line, and optional server notes.\n\n### `code_actions`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `query`, `apply`, `timeout`.\n\n**Execution**\n- Reads cached diagnostics for the open URI from `client.diagnostics` and sends `textDocument/codeAction` for a zero-width range at the resolved position.\n- When `apply !== true`, `query` is passed as `context.only: [query]`; this is a server-side kind filter.\n- When `apply === true`, `query` becomes a required client-side selector: either a zero-based numeric index or a case-insensitive substring of the action title.\n- Applying a `CodeAction` uses `applyCodeAction()`: optionally `codeAction/resolve`, then `applyWorkspaceEdit(edit)`, then optional `workspace/executeCommand`.\n- Applying a bare `Command` only runs `workspace/executeCommand`.\n\n**Output text**\n- List mode: `N code action(s):` plus `index: [kind] title` lines.\n- Apply mode success: `Applied \"title\":` plus `Workspace edit:` and/or `Executed command(s):` sections.\n- Apply mode miss: `No code action matches \"query\". Available actions:`.\n- Apply mode with no edit/command: `Action \"title\" has no workspace edit or command to apply`.\n\n### `status`\n**Inputs**\n- None.\n\n**Execution**\n- Reads configured servers from cached `LspConfig`, not `getActiveClients()`.\n- Calls `detectLspmux()` and appends status text when `lspmux` is installed.\n\n**Output text**\n- `Active language servers: ...` or `No language servers configured for this project`, optionally followed by `lspmux: active (multiplexing enabled)` or `lspmux: installed but server not running`.\n\n### `reload`\n**Inputs**\n- Workspace mode: `file: \"*\"` or omitted `file`.\n- Single-file mode: required `file`.\n- Optional: `timeout`.\n\n**Execution**\n- Workspace mode reloads every non-custom LSP server.\n- Single-file mode reloads the primary server for that file.\n- `reloadServer()` tries `rust-analyzer/reloadWorkspace`, then `workspace/didChangeConfiguration` with `{ settings: {} }`; if neither works it kills the process so the next request cold-starts a new client.\n\n**Output text**\n- One line per server: `Reloaded <server>`, `Restarted <server>`, or `Failed to reload <server>: ...`.\n\n### `capabilities`\n**Inputs**\n- Optional: `file`, `timeout`.\n\n**Execution**\n- With a concrete `file`, inspects matching non-custom servers for that file.\n- With omitted `file` or `\"*\"`, inspects every non-custom configured server.\n- Starts servers as needed and dumps `client.serverCapabilities ?? {}` as pretty JSON.\n\n**Output text**\n- Per server: `<server>:` followed by indented `capabilities: { ... }`, or `<server>: failed to start (...)`.\n\n### `request`\n**Inputs**\n- Required: `query` method name.\n- Optional: `file`, `line`, `symbol`, `payload`, `timeout`.\n\n**Execution**\n- Chooses one non-custom server: file-scoped primary server, otherwise the first configured non-custom server.\n- Param building precedence:\n  1. If `payload` is present, parse JSON and use it verbatim.\n  2. Else if `file` is concrete and `line` is present, build `{ textDocument: { uri }, position: { line: line - 1, character } }` using `resolveSymbolColumn()`.\n  3. Else if `file` is concrete, build `{ textDocument: { uri } }`.\n  4. Else use `{}`.\n- Opens the file first when `file` is concrete.\n\n**Output text**\n- Success: `<server> ← <method>:\\n<formatted result>`, where non-string results are `JSON.stringify(..., null, 2)` and nullish values become `null`.\n- Failure: `LSP error from <server> on <method>: ...`.\n\n## Side Effects\n- Filesystem\n  - Reads config files, target files, and root markers.\n  - `rename` and `code_actions` may edit/create/delete/rename files via `applyWorkspaceEdit()`.\n  - `rename_file` always renames the source path on disk in apply mode.\n  - Server-initiated `workspace/applyEdit` requests also mutate files through `applyWorkspaceEdit()`.\n- Network\n  - None directly; communication is local stdio JSON-RPC to subprocesses.\n- Subprocesses / native bindings\n  - Spawns language servers with `ptree.spawn()`.\n  - Workspace diagnostics spawns `cargo`, `npx`, `go`, or `pyright`.\n  - `BiomeClient` and `SwiftLintClient` spawn CLI tools.\n  - Optional `lspmux` detection spawns `lspmux status`; supported servers may be wrapped through `lspmux client`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Caches config per cwd in `configCache`.\n  - Caches LSP clients per `command:cwd`, with `pendingRequests`, `diagnostics`, `openFiles`, `serverCapabilities`, and project-load state.\n  - Caches custom linter clients by `serverName:cwd`.\n  - Updates client `lastActivity`; optional idle-timeout cleanup is driven by `setIdleTimeout()`.\n- Background work / cancellation\n  - Every request has an abortable timeout signal.\n  - Aborting an in-flight LSP request sends `$/cancelRequest`.\n  - Background message readers persist for each live client until process exit/shutdown.\n\n## Limits & Caps\n- Tool timeout clamp: default `20`, min `5`, max `60` seconds — `TOOL_TIMEOUTS.lsp` in `packages/coding-agent/src/tools/tool-timeouts.ts`.\n- LSP request default timeout inside `sendRequest()`: `30_000ms` — `DEFAULT_REQUEST_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Warmup initialize timeout default: `5_000ms` — `WARMUP_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Project-load wait fallback: `15_000ms` — `PROJECT_LOAD_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Idle-client sweep interval when enabled: `60_000ms` — `IDLE_CHECK_INTERVAL_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Diagnostic message output cap: first `50` messages — `DIAGNOSTIC_MESSAGE_LIMIT` in `packages/coding-agent/src/lsp/index.ts`.\n- Single-file diagnostics wait: `3_000ms` — `SINGLE_DIAGNOSTICS_WAIT_TIMEOUT_MS`.\n- Batch/glob diagnostics wait per file: `400ms` — `BATCH_DIAGNOSTICS_WAIT_TIMEOUT_MS`.\n- Glob diagnostic target cap: first `20` matches — `MAX_GLOB_DIAGNOSTIC_TARGETS`.\n- Workspace symbol cap: first `200` entries — `WORKSPACE_SYMBOL_LIMIT`.\n- Reference context cap: first `50` references include source context — `REFERENCE_CONTEXT_LIMIT`.\n- References retry count: `2` retries, `250ms` backoff — `REFERENCES_RETRY_COUNT`, `REFERENCES_RETRY_DELAY_MS`.\n- Directory rename cap: `1_000` file pairs — `MAX_RENAME_PAIRS`.\n- `detectLspmux()` state cache TTL: `5 * 60 * 1000ms`; liveness check timeout: `1_000ms` — `STATE_CACHE_TTL_MS`, `LIVENESS_TIMEOUT_MS` in `packages/coding-agent/src/lsp/lspmux.ts`.\n- Workspace diagnostics output cap: first `50` lines from the subprocess.\n\n## Errors\n- Missing or invalid inputs are usually returned as text with `details.success: false`, not thrown:\n  - missing `file`/`query`/`new_name`\n  - invalid JSON in `payload`\n  - no matching server\n  - invalid `rename_file` source/destination conditions\n- `resolveSymbolColumn()` throws explicit errors for missing files, missing symbols, and out-of-bounds `#N` selectors; these surface as `LSP error: ...` or request-specific error text.\n- `sendRequest()` rejects on timeout with `LSP request <method> timed out after <ms>ms`.\n- Client process exit rejects all pending requests with an exit-code/stderr error assembled in `getOrCreateClient()`.\n- Single-file action failures inside the main `try` become `LSP error: <message>`.\n- `request` has its own error envelope: `LSP error from <server> on <method>: <message>`.\n- Some server failures are intentionally softened:\n  - diagnostics continue when one server fails\n  - `rename_file` suppresses `workspace/willRenameFiles` “method not found” errors and records other server errors as notes\n  - `code_actions` ignores `codeAction/resolve` failures and applies unresolved actions when possible\n- Aborts are not converted to text: `ToolAbortError` is rethrown.\n\n## Notes\n- `status` reports configured/available servers from `LspConfig`, not currently active client processes from `getActiveClients()`.\n- `getLspServerForFile()` excludes `createClient` adapters and linter-only servers; navigation/refactor actions never target Biome/SwiftLint custom clients.\n- `getServersForFile()` matches both file extensions and exact basenames from `fileTypes`; config can target names like `Dockerfile` if present.\n- `symbol` matching is exact first, then case-insensitive, and falls back to the Nth occurrence on the specified line only; it never scans other lines.\n- `code_actions` uses `query` in two different ways: server-side `context.only` filter in list mode, client-side title/index selector in apply mode.\n- `rename` and `rename_file` default to apply. Preview requires `apply: false`.\n- `request` with `file: \"*\"` is treated the same as omitted `file`: it does not build workspace-specific params.\n- `reload` does not recreate a client immediately after killing it; the next request triggers reinitialization.\n- `workspace/applyEdit` can apply edits initiated by the server outside the direct tool action result path.\n- `detectLspmux()` can be disabled with `PI_DISABLE_LSPMUX=1`; only `rust-analyzer` is in `DEFAULT_SUPPORTED_SERVERS`.\n- Startup LSP warmup (`discoverStartupLspServers(cwd)` in `sdk.ts`) is gated on `enableLsp && options.hasUI && settings.get(\"lsp.diagnosticsOnWrite\")` — print/RPC/ACP/script sessions skip it and let `getOrCreateClient()` cold-start servers on demand. See `docs/sdk.md` § Startup performance.\n- `configCache` is per-process and never auto-invalidated; config changes require a fresh process to be observed by `getConfig()` callers.",
 	"tools/read.md": "# read\n\n> Read files, directories, archives, SQLite databases, internal resources, images, documents, and URLs through one `path` string.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/read.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/read.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/path-utils.ts` — split `path` from trailing selectors; normalize local paths.\n  - `packages/coding-agent/src/tools/archive-reader.ts` — detect `archive.ext:inner/path`, index archives, list/read entries.\n  - `packages/coding-agent/src/tools/sqlite-reader.ts` — detect SQLite targets, parse selectors, render tables.\n  - `packages/coding-agent/src/tools/fetch.ts` — URL parsing, fetch/render pipeline, URL cache/artifacts.\n  - `packages/coding-agent/src/internal-urls/router.ts` — resolve `agent://`, `artifact://`, `local://`, `mcp://`, `memory://`, `omp://`, `rule://`, `skill://`.\n  - `packages/coding-agent/src/edit/notebook.ts` — convert `.ipynb` to editable `# %% [...] cell:N` text.\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — decide hashline vs line-number vs raw display.\n  - `packages/coding-agent/src/workspace-tree.ts` — render directory trees.\n  - `packages/coding-agent/src/edit/file-snapshot-store.ts` — stores read lines for later hashline edit verification/recovery.\n  - `packages/coding-agent/src/tools/index.ts` — registers `read: s => new ReadTool(s)`.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `path` | `string` | Yes | Filesystem path, internal URL, or web URL. May end with a trailing selector such as `:50-100` or `:raw`. |\n\n### Selector grammar\n\nFor normal file-like reads, `splitPathAndSel()` in `packages/coding-agent/src/tools/path-utils.ts` recognizes the final suffix only when it matches one of these forms:\n\n| Suffix | Meaning |\n| --- | --- |\n| `:raw` | Raw/verbatim mode. Disables structural summaries and line prefixes. |\n| `:N` / `:LN` | Start at 1-indexed line `N`, open-ended. |\n| `:A-B` / `:LA-LB` | Inclusive 1-indexed line range. |\n| `:A+C` / `:LA+LC` | `C` lines starting at `A`; tool converts this to end line `A + C - 1`. |\n| `:range:raw` or `:raw:range` | Same line selection, but raw output. |\n\nValidation in `parseLineRangeChunk()`:\n- line numbers are 1-indexed; `:0` throws.\n- `+` counts must be `>= 1`.\n- `-` end must be `>= start`.\n\nSelector parsing intentionally falls through for unrecognized trailing `:...`; archive and SQLite paths consume their own colon syntax.\n\nURL selectors are parsed separately in `packages/coding-agent/src/tools/fetch.ts` and support only `:raw`, `:N`, `:A-B`, and `:A+C` — no optional `L` prefix there.\n\n## Outputs\n- Single-shot `AgentToolResult` built through `toolResult()` in `packages/coding-agent/src/tools/tool-result.ts`.\n- `content` is usually one text block. Image reads may return `[text, image]`.\n- `details` is path-dependent. `ReadToolDetails` may include:\n  - `kind: \"file\" | \"url\"` (URL path uses `kind: \"url\"`; file reads usually omit `kind`)\n  - `isDirectory`\n  - `resolvedPath`\n  - `suffixResolution`\n  - URL fields: `url`, `finalUrl`, `contentType`, `method`, `notes`\n  - `truncation`\n  - `displayContent` (unprefixed text + starting line for TUI rendering)\n  - `summary` (`lines`, `elidedSpans`, `elidedLines`) for structural summaries\n  - `meta` from `packages/coding-agent/src/tools/output-meta.ts`\n- `details.meta.source` is set to the backing path, URL, or internal URL.\n- `details.meta.truncation` carries shown range, total lines/bytes, next offset, and optional `artifactId` for cached URL output.\n- Directory/archive listings and SQLite table lists also set `details.meta.limits` when list limits trigger.\n\n## Flow\n1. `ReadTool.execute()` accepts `{ path }`. `file://...` inputs are expanded first with `expandPath()`.\n2. It tries URL handling first via `parseReadUrlTarget()` from `packages/coding-agent/src/tools/fetch.ts`.\n   - Plain URL reads call `executeReadUrl()`.\n   - URL reads with line selectors load or refresh the URL cache with `loadReadUrlCacheEntry()` and paginate the cached text locally with `#buildInMemoryTextResult()`.\n3. If not a web URL, it checks `session.internalRouter.canHandle(...)`.\n   - Internal URLs are resolved with `internalRouter.resolve()`.\n   - `agent://` query extraction (`/path` or `?q=`) bypasses pagination and returns the extracted content directly.\n   - Other internal resources are paginated in-memory by `#buildInMemoryTextResult()`.\n4. It tries archive resolution next with `#resolveArchiveReadPath()`.\n   - `parseArchivePathCandidates()` scans for `.tar`, `.tar.gz`, `.tgz`, or `.zip` anywhere before `:sub/path`.\n   - On success, `#readArchive()` either lists a directory or decodes an entry as UTF-8 text.\n5. It tries SQLite resolution with `#resolveSqliteReadPath()`.\n   - `parseSqlitePathCandidates()` scans for `.sqlite`, `.sqlite3`, `.db`, `.db3` before any `:table`, `:key`, or `?query` suffix.\n   - `#readSqlite()` dispatches on `parseSqliteSelector()`.\n6. Otherwise it treats the input as a local filesystem path.\n   - `resolveReadPath()` expands `~`, resolves relative to session cwd, treats bare `/` as session cwd, and retries macOS screenshot/NFD/curly-quote variants.\n   - If the path does not exist, `findUniqueSuffixMatch()` does a workspace glob-based unique suffix lookup (skipped for remote mounts).\n7. Directories go through `#readDirectory()`.\n8. Non-directories branch by content type:\n   - image metadata / inline image\n   - editable notebook text\n   - markit-converted document\n   - structural summary for parseable code/prose\n   - streamed text/line-range read\n9. Local text reads are streamed by `streamLinesFromFile()` rather than loading the whole file. The tool adds up to 3 lines of context before/after explicit bounded ranges.\n10. Non-empty contiguous local reads are recorded into `getFileReadCache(session)` for later hashline edit recovery.\n11. If suffix resolution happened, the first text block is prefixed with `[Path '...' not found; resolved to '...' via suffix match]`.\n\n## Modes / Variants\n\n### Local text files\n- No selector: if summarization is enabled and the file is small enough, `#trySummarize()` calls `summarizeCode()`.\n  - Guards: file size `<= 2 MiB` (`MAX_SUMMARY_BYTES`), line count `<= 20_000` (`MAX_SUMMARY_LINES`).\n  - Summary output keeps selected declarations and replaces elided spans with `...`. When at least one span is elided, the text content ends with a footer like `[NN lines across MM elided regions; read <path>:raw or a line range like <path>:1-9999 for verbatim content]` so the agent has a concrete recovery selector instead of a bare marker.\n  - When an elided block sits between matching brace lines, `#renderSummary()` may merge them into one anchored line rather than emitting separate opener/closer lines.\n- Explicit selector or summarization miss: streamed text read.\n  - Default open-ended limit is `min(session setting read.defaultLimit, DEFAULT_MAX_LINES)`.\n  - Explicit ranges expand by `RANGE_LEADING_CONTEXT_LINES = 1` / `RANGE_TRAILING_CONTEXT_LINES = 3` on the constrained sides only.\n  - Non-raw output uses `resolveFileDisplayMode()`:\n    - hashline numbered output when edit mode is hashline, read is not raw, source is mutable, edit tool exists, and `readHashLines !== false`\n    - otherwise optional line numbers when `readLineNumbers === true`\n    - raw mode suppresses both\n- Prefix format in hashline mode is a `¶PATH#TAG` header followed by `LINE:TEXT`, e.g. `¶src/foo.ts#0a` and `41:def alpha():`, from the session snapshot store plus `formatNumberedLine()` / `formatHashlineHeader()`.\n- The `edit`/hashline path consumes that header plus bare line numbers later; the two-hex tag is opaque and only meaningful in the session snapshot store that minted it. Immutable sources and `:raw` intentionally suppress hashline headers.\n\n### Directory listings\n- `#readDirectory()` calls `buildDirectoryTree()` with:\n  - `maxDepth = 2`\n  - `perDirLimit = 12`\n  - `rootLimit = null`\n  - `lineCap = limit` when a line selector was present, else unlimited at this layer\n- `buildDirectoryTree()` sorts siblings by recency, shows file sizes and relative ages, and may mark `limits.resultLimit` when the tree truncates.\n- Empty directories render as `(empty directory)`.\n\n### Archives\n- Supported archive containers: `.tar`, `.tar.gz`, `.tgz`, `.zip`.\n- Syntax: `archive.ext`, `archive.ext:path/inside`, `archive.ext:path/inside:50-60`.\n- `openArchive()` reads the whole archive into memory, then:\n  - tar/tgz uses `new Bun.Archive(bytes)`\n  - zip uses `fflate.unzipSync()`\n- Archive paths normalize `/`, drop `.` segments, and reject `..`.\n- Directory reads list immediate children; files show `name` plus ` (size)` when size > 0.\n- Directory listing default limit is `500` entries in `#readArchiveDirectory()`.\n- File entries are UTF-8 decoded. Non-UTF-8 entries return `[Cannot read binary archive entry '...' (...)]` instead of bytes.\n- Text archive entries reuse the normal in-memory pagination/anchoring path.\n\n### SQLite databases\n- Database detection requires both a matching extension and a valid SQLite file header (`isSqliteFile()`).\n- Selector forms from `parseSqliteSelector()`:\n\n#### `db.sqlite`\n- `kind: \"list\"`\n- Lists non-`sqlite_%` tables with row counts.\n- `#readSqlite()` caps the rendered list to `500` tables via `applyListLimit()`.\n\n#### `db.sqlite:table`\n- `kind: \"schema\"`\n- Returns `sqlite_master.sql` plus sample rows.\n- Sample size is `DEFAULT_SCHEMA_SAMPLE_LIMIT = 5`.\n\n#### `db.sqlite:table:key`\n- `kind: \"row\"`\n- Resolves by primary key when the table has exactly one PK column; otherwise falls back to `rowid` lookup.\n- No query parameters allowed on row lookups.\n\n#### `db.sqlite:table?limit=...&offset=...&order=...&where=...`\n- `kind: \"query\"`\n- Defaults: `limit = 20`, `offset = 0`.\n- `limit` is capped at `500`.\n- `order` accepts `column` or `column:asc|desc` and must name an existing column.\n- `where` is accepted only after `validateWhereClause()` rejects comments, semicolons, and control keywords like `LIMIT`, `OFFSET`, `UNION`, `ATTACH`, `PRAGMA`.\n- Unknown query parameters throw.\n\n#### `db.sqlite?q=SELECT ...`\n- `kind: \"raw\"`\n- Cannot be combined with table selectors or any other query param.\n- Empty `q` throws.\n- `executeReadQuery()` runs `db.prepare(sql).all()` and rejects bound parameters; it does not verify that the SQL starts with `SELECT`.\n\n- Rendering caps in `packages/coding-agent/src/tools/sqlite-reader.ts`:\n  - ASCII table width `120` (`MAX_RENDER_WIDTH`)\n  - per-column width `40` (`MAX_COLUMN_WIDTH`)\n- `#readSqlite()` opens Bun SQLite in `{ readonly: true, strict: true }` and sets `PRAGMA busy_timeout = 3000`.\n\n### Documents\n- `CONVERTIBLE_EXTENSIONS` in `packages/coding-agent/src/tools/read.ts` covers `.pdf`, `.doc`, `.docx`, `.ppt`, `.pptx`, `.xls`, `.xlsx`, `.rtf`, `.epub`.\n- `convertFileWithMarkit()` converts the file to text/markdown.\n- Converted output is then head-truncated with normal shared limits; there is no line selector support inside the source document before conversion.\n- Conversion failures return a text block like `[Cannot read .pdf file: ...]`.\n\n### Jupyter notebooks\n- `.ipynb` goes through `readEditableNotebookText()` unless `:raw` was requested.\n- Output is editable plain text with markers like:\n\n```text\n# %% [code] cell:0\n...\n```\n\n- Raw mode bypasses that conversion and falls back to file-text reading.\n\n### Images\n- Image detection is metadata-based (`readImageMetadata()`).\n- Max accepted image size is `20 MiB` (`MAX_IMAGE_INPUT_BYTES`, re-exported as `MAX_IMAGE_SIZE`). Larger files throw.\n- If `inspect_image.enabled` is true, `read` returns metadata only (MIME, bytes, dimensions, channels, alpha) plus a suggestion to call `inspect_image`.\n- Otherwise it calls `loadImageInput()` and returns:\n  - a text note from the image loader\n  - an inline image block\n- Unsupported/undecodable image formats throw a `ToolError`.\n\n### Internal URLs\n- `read` does not resolve these itself; it delegates to `session.internalRouter.resolve()`.\n- Registered protocols are outside this file, but the router in `packages/coding-agent/src/internal-urls/router.ts` is built for `agent://`, `artifact://`, `issue://`, `local://`, `mcp://`, `memory://`, `omp://`, `pr://`, `rule://`, and `skill://`.\n- `#handleInternalUrl()` behavior:\n  - parses the URL with `parseInternalUrl()` so colons inside the host segment are legal\n  - for `agent://`, treats non-root path extraction or `?q=` extraction as a special no-pagination mode\n  - otherwise paginates the resolved text in memory\n  - passes `immutable` through to `resolveFileDisplayMode()` so anchors are suppressed for immutable resources such as artifacts, skills, memory, and agent outputs\n  - sets `ignoreResultLimits: true` for `skill://` so the full skill text is paginated only by explicit selectors, not by the normal default line limit\n- `issue://<N>` / `pr://<N>` (and the long form `issue://<owner>/<repo>/<N>` / `pr://<owner>/<repo>/<N>`) route through the same SQLite cache the `github` tool writes to; `?comments=0` selects the no-comments rendering. Bare `issue://` / `pr://` (and `issue://<owner>/<repo>` / `pr://<owner>/<repo>`) issue a live `gh issue list` / `gh pr list` for browsing, accepting `?state=`, `?limit=`, `?author=`, `?label=`. PR diffs share the same cache through `pr://<N>/diff` (numbered file listing with per-file hints), `pr://<N>/diff/<i>` (single file slice; 1-indexed), and `pr://<N>/diff/all` (verbatim unified diff); the listing and per-file slices are reconstructed from the cached unified-diff payload, so all three variants share one `gh pr diff` invocation per PR. Diff content is served as `text/plain`. Soft TTL `github.cache.softTtlSec` (default 5 minutes), hard TTL `github.cache.hardTtlSec` (default 7 days). Stale-hit returns the cached row and schedules a background refresh.\n\n### Web URLs\n- `parseReadUrlTarget()` accepts `http://`, `https://`, or `www.` targets.\n- Plain URL reads call `executeReadUrl()` in `packages/coding-agent/src/tools/fetch.ts`.\n- `:raw` means raw HTML/body fallback path; plain URL reads prefer rendered/reader-friendly output.\n- `:N`, `:A-B`, `:A+C` do not refetch. They page over cached output from the prior or current URL render.\n- URL render pipeline in `renderUrl()`:\n  1. normalize scheme (`https://` added for bare `www.`)\n  2. try special handlers for known sites unless raw\n  3. fetch with `loadPage()`\n  4. if content is image/PDF/DOCX/etc., try binary fetch + markit/image handling\n  5. handle JSON directly, feeds via feed parser, plain text directly\n  6. for HTML and non-raw mode, try markdown alternates, `URL.md`, content negotiation, feed alternates, HTML-to-text renderers, extracted linked documents, then `llms.txt`\n  7. fall back to raw body text/html\n- URL output is wrapped with a small header:\n\n```text\nURL: ...\nContent-Type: ...\nMethod: ...\nNotes: ...\n\n---\n```\n\n- `method` records the winning path (`json`, `feed`, `text`, `alternate-markdown`, `md-suffix`, `content-negotiation`, `image`, `markit`, `llms.txt`, `raw`, `raw-html`, etc.).\n- URL reads may return an inline image block when the fetched resource is a supported image and survives resizing.\n\n## Side Effects\n- Filesystem\n  - Opens and streams local files.\n  - Reads entire archives into memory before indexing.\n  - May read URL-cache artifact files from the session artifacts directory.\n  - Writes URL output artifacts when URL output is truncated or when line-range pagination needs a persisted cache body.\n- Network\n  - URL mode performs HTTP fetches, binary refetches, and alternate-endpoint probes.\n- Subprocesses / native bindings\n  - Uses Bun SQLite for `.db`/`.sqlite*`.\n  - Uses `Bun.Archive` for tar/tgz and `fflate` for zip.\n  - URL HTML rendering can delegate into site handlers and HTML-to-text backends from `packages/coding-agent/src/tools/fetch.ts`.\n- Session state\n  - Records local text lines into `session.fileReadCache` for later stale-anchor recovery.\n  - Uses `session.internalRouter` for internal URLs.\n  - Uses `session.allocateOutputArtifact()` for cached/truncated URL output.\n- Background work / cancellation\n  - Most branches honor `AbortSignal`; the tool itself is marked `nonAbortable = true`, but helper paths still call `throwIfAborted(signal)`.\n\n## Limits & Caps\n- Shared text truncation defaults from `packages/coding-agent/src/session/streaming-output.ts`:\n  - `DEFAULT_MAX_LINES = 3000`\n  - `DEFAULT_MAX_BYTES = 50 * 1024`\n- Local text open-ended default line limit: `read.defaultLimit`, clamped to `[1, DEFAULT_MAX_LINES]`.\n- Explicit line ranges add `1` leading and `3` trailing context lines on the constrained sides (`RANGE_LEADING_CONTEXT_LINES` / `RANGE_TRAILING_CONTEXT_LINES`).\n- File streaming chunk size: `8 * 1024` bytes (`READ_CHUNK_SIZE`).\n- Local streamed byte budget for line reads: `max(DEFAULT_MAX_BYTES, maxLinesToCollect * 512)`.\n- Structural summaries only run when file size `<= 2 MiB` and line count `<= 20_000`.\n- Image input max: `20 MiB`.\n- Directory tree caps for local directories: depth `2`, per-directory children `12`.\n- Archive directory default list cap: `500` entries.\n- SQLite:\n  - default row query limit `20`\n  - schema sample limit `5`\n  - max query limit `500`\n  - table list cap `500`\n  - render width `120`, column width `40`\n  - busy timeout `3000` ms\n- URL read result shown to the model is truncated to `300` lines and `50 KiB` in `executeReadUrl()`; full cached output can be attached as an artifact.\n- Inline fetched URL images:\n  - source bytes cap `20 MiB`\n  - post-resize inline output cap `300 KiB`\n- Unique suffix auto-resolution glob timeout: `5000` ms.\n- File-read cache holds `30` paths per session.\n\n## Errors\n- Validation and operational failures surface as `ToolError`.\n- Selector errors include:\n  - `Line selector 0 is invalid; lines are 1-indexed. Use :1.`\n  - invalid `A+B` / `A-B` shapes\n  - `Cannot combine query extraction with offset/limit` for `agent://.../path:50`\n- Missing local/archive/sqlite paths first attempt unique suffix resolution; if no unique match exists they error.\n- Out-of-bounds line reads do not throw. They return explanatory text with a suggestion such as `Use :1 ...` or `Use :<last line> ...`.\n- Binary archive entries do not throw; they return a text notice.\n- Document conversion failure returns a text notice.\n- Image oversize/unsupported/invalid cases throw.\n- SQLite parser rejects unsupported parameter combinations early; DB/runtime errors are caught and rethrown as `ToolError(message)`.\n- URL fetch failure does not throw when HTTP fetch succeeds but `response.ok === false`; it returns a failed URL read with `method: \"failed\"` and explanatory notes.\n\n## Notes\n- `readSchema` examples include `https://example.com:L1-L40`, but URL selector parsing in `packages/coding-agent/src/tools/fetch.ts` does not accept `L` prefixes.\n- Hashline anchors are suppressed for raw reads and immutable internal resources because there is no editable backing target for later `edit` consumption.\n- `splitPathAndSel()` intentionally treats unknown trailing `:...` as part of the path so `archive.zip:inner/file` and `db.sqlite:table:key` still work.\n- `resolveReadPath()` contains macOS-specific filename fallbacks for screenshot timestamps, NFD Unicode normalization, and curly apostrophes.\n- A bare `/` resolves to the session cwd, not the filesystem root.\n- URL cache keys are session-scoped and normalized by requested URL + raw/rendered mode; both requested URL and final redirected URL are cached.\n- URL line-range reads request `ensureArtifact: true, preferCached: true` so a later paginated read can reopen the same rendered body from artifact storage.\n- Raw SQLite `q=` execution is not keyword-restricted beyond “no bound parameters”; the read tool relies on the surrounding contract to keep it read-only.\n- The file-read cache is not a read acceleration cache. It exists to recover hashline edits when the file changed after the read.",
 	"tools/recall.md": "# recall\n\n> Search the active Hindsight bank and return raw matching memories.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/hindsight-recall.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/recall.md`\n- Key collaborators:\n  - `packages/coding-agent/src/hindsight/state.ts` — session state, recall query defaults, prompt-side auto-recall.\n  - `packages/coding-agent/src/hindsight/content.ts` — result formatting and UTC timestamp formatting.\n  - `packages/coding-agent/src/hindsight/client.ts` — HTTP `recall` call and error mapping.\n  - `packages/coding-agent/src/hindsight/bank.ts` — bank id and tag-filter scoping.\n  - `docs/tools/retain.md` — shared backend, storage, seeding, and mental-model bootstrap.\n\n## Inputs\n\n| Field | Type | Required | Description |\n|---|---|---:|---|\n| `query` | `string` | Yes | Natural-language search query. The tool passes it through unchanged. |\n\n## Outputs\nReturns a single-shot tool result.\n\nWhen matches exist:\n- `content[0].type = \"text\"`\n- `content[0].text = \"Found <n> relevant memories (as of YYYY-MM-DD HH:MM UTC):\\n\\n<bullet list>\"`\n- each bullet is `- <text> [<type>] (<mentioned_at>)`; the type and timestamp suffixes appear only when those fields are present\n- `details = {}`\n\nWhen no matches exist:\n- `content[0].text = \"No relevant memories found.\"`\n- `details = {}`\n\n## Flow\n1. `HindsightRecallTool.createIf(...)` only exposes the tool when `memory.backend == \"hindsight\"`.\n2. `execute(...)` wraps the whole operation in `untilAborted(...)` from `@oh-my-pi/pi-utils`.\n3. It reads the active `HindsightSessionState`; missing state throws `Hindsight backend is not initialised for this session.`\n4. It calls `state.client.recall(...)` with:\n   - `bankId` from session bootstrap,\n   - the model-supplied `query`,\n   - `budget`, `maxTokens`, and `types` from `HindsightConfig`,\n   - tag filters from the bank scope (`recallTags`, `recallTagsMatch`).\n5. `HindsightApi.recall(...)` POSTs `/v1/default/banks/{bank_id}/memories/recall`.\n6. Results are formatted into a plain-text list with `formatMemories(...)`; empty results map to the fixed no-match string.\n7. Failures are logged with `logger.warn(\"recall failed\", ...)` and rethrown.\n\n## Modes / Variants\n- Tool path: explicit query-only recall. The tool does not compose context from recent turns; that richer path is reserved for backend auto-recall in `HindsightSessionState.beforeAgentStartPrompt(...)` / `maybeRecallOnAgentStart(...)`.\n- Bank scoping is inherited from the active `HindsightSessionState`:\n  - `global` — no tag filter.\n  - `per-project` — separate bank id per cwd basename.\n  - `per-project-tagged` — shared bank id plus `project:<cwd basename>` filter with `tagsMatch = \"any\"`, so project-tagged and untagged global memories can both surface.\n- Session scope: reads cross-session server-side memories, but uses per-session cached config and scope.\n\n## Side Effects\n- Network\n  - `POST /v1/default/banks/{bank_id}/memories/recall` via `packages/coding-agent/src/hindsight/client.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - None on success. Unlike backend auto-recall, this tool does not update `lastRecallSnippet` or refresh the system prompt.\n- Background work / cancellation\n  - Aborts through `untilAborted(...)` if the tool call signal is cancelled.\n\n## Limits & Caps\n- Client default budget for raw `HindsightApi.recall(...)` is `\"mid\"`; this tool overrides from config in `packages/coding-agent/src/hindsight/state.ts`.\n- Default recall settings from `packages/coding-agent/src/config/settings-schema.ts`:\n  - `hindsight.recallBudget = \"mid\"`\n  - `hindsight.recallMaxTokens = 1024`\n  - `hindsight.recallTypes = [\"world\", \"experience\"]`\n- The explicit tool path does not apply `hindsight.recallContextTurns` or `hindsight.recallMaxQueryChars`; those caps only affect backend auto-recall query composition.\n\n## Errors\n- Throws `Hindsight backend is not initialised for this session.` when no state exists.\n- HTTP and fetch failures become `HindsightError` from `packages/coding-agent/src/hindsight/client.ts` with `statusCode` and parsed `details` when available.\n- Non-`Error` failures are normalized to `new Error(String(err))` before rethrow.\n\n## Notes\n- Shared backend details are in `docs/tools/retain.md`: server-side storage, subagent aliasing, bank scoping, mission setup, and mental-model bootstrap.\n- Mental models are not fetched by this tool. They may still already be present in the agent's developer instructions because the backend caches a `<mental_models>` block separately from recall results.\n- The tool returns raw memory hits; it does not synthesize across them. Use `reflect` for that path.\n",
-	"tools/recipe.md": "# recipe\n\n> Run a task exposed by a detected project task runner.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/recipe/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/recipe.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/recipe/runner.ts` — op parsing, task resolution, prompt model.\n  - `packages/coding-agent/src/tools/recipe/render.ts` — shell-style call/result rendering.\n  - `packages/coding-agent/src/tools/recipe/runners/index.ts` — runner registration order.\n  - `packages/coding-agent/src/tools/recipe/runners/just.ts` — detect `just` recipes from justfiles.\n  - `packages/coding-agent/src/tools/recipe/runners/pkg.ts` — detect `package.json` scripts and workspaces.\n  - `packages/coding-agent/src/tools/recipe/runners/cargo.ts` — detect Cargo run/test targets.\n  - `packages/coding-agent/src/tools/recipe/runners/make.ts` — parse make targets from makefiles.\n  - `packages/coding-agent/src/tools/recipe/runners/task.ts` — detect Taskfile tasks via `task --list-all`.\n  - `packages/coding-agent/src/tools/bash.ts` — actual command execution, truncation, cwd/env handling.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `string` | Yes | Single string containing the task selector plus trailing arguments. The first whitespace-delimited token selects the task; the remainder is appended verbatim to the resolved runner command. Examples from schema/prompt: `test`, `build --release`, `pkg-a/test`, `crate/bin/server`, `pkg:test --watch`. |\n\n### `op` grammar\n\n```text\nop          := S* head (S+ tail)?\nhead        := explicit-runner / implicit-task\nexplicit-runner := runner-id \":\" task-token\nimplicit-task   := task-token\nrunner-id   := detected runner id (`just` | `pkg` | `cargo` | `make` | `task`)\ntask-token  := first non-whitespace token; may contain `/`\ntail        := remaining characters after the first whitespace run\n```\n\nResolution rules from `resolveRunnerAndTask()`:\n- Leading whitespace is ignored; an empty `op` throws `ToolError` with the available task list.\n- Only the first token is parsed structurally. Everything after the first whitespace run becomes `tail` and is appended to the command unchanged.\n- If `head` contains `:` and the prefix matches a detected runner id, the suffix must exactly match a task in that runner.\n- Otherwise `head` is treated as a task name and matched across all detected runners.\n- If exactly one runner has that task, it is used.\n- If multiple runners have that task, the call is rejected and the error tells the model to use `<runner-id>:<task>`.\n- Namespaced task names generated by runners use `/`, not `:`. `/` is part of the task name, not a parser separator.\n\n## Outputs\n- Delegates directly to `BashTool.execute()` and returns the same `AgentToolResult<BashToolDetails>` shape.\n- Success path: one text content block containing merged command output (`result.output` from bash execution, or `(no output)`), plus any timeout clamp notice appended after a blank line.\n- Recipe does not return separate `stdout`, `stderr`, or `exitCode` fields. `stdout`/`stderr` are already merged into the text block by bash execution; `exitCode` is only observed indirectly (success requires `0`, non-zero becomes an error).\n- Error path: throws `ToolError`; for non-zero exits the message is the merged output followed by `Command exited with code <n>`.\n- `details` may include:\n  - `timeoutSeconds`: effective timeout used by bash.\n  - `requestedTimeoutSeconds`: only when bash clamped a requested timeout; recipe never sets one itself.\n  - `meta`: output truncation metadata from bash execution.\n  - `async`: defined by bash background execution paths, but recipe does not expose an `async` input.\n- When bash output is truncated, the full text is stored in an artifact and referenced via bash truncation metadata.\n- Call/result rendering in the TUI uses bash shell rendering with a resolved title, command preview, and optional task cwd.\n\n## Flow\n1. `RecipeTool.createIf()` in `packages/coding-agent/src/tools/recipe/index.ts` checks `session.settings.get(\"recipe.enabled\")`; disabled returns `null`.\n2. It probes every runner in `RUNNERS` from `packages/coding-agent/src/tools/recipe/runners/index.ts` with `Promise.all(...)` in this order: `just`, `pkg`, `cargo`, `make`, `task`.\n3. Each runner returns either `null` or a `DetectedRunner { id, label, commandPrefix, tasks }`; runners with zero tasks are discarded.\n4. If no runners remain, the tool is not registered.\n5. Constructor stores detected runners, instantiates `BashTool`, renders the model-facing description by passing `buildPromptModel(runners)` into `packages/coding-agent/src/prompts/tools/recipe.md`, and builds shell renderers from `createRecipeToolRenderer()`.\n6. On execution, `RecipeTool.execute()` calls `resolveCommand(op, this.#runners)`.\n7. `resolveCommand()` in `packages/coding-agent/src/tools/recipe/runner.ts`:\n   1. `parseOp()` trims only leading whitespace, extracts the first non-whitespace token as `head`, and keeps the remainder as `tail`.\n   2. `resolveRunnerAndTask()` resolves `head` either as `runnerId:taskName` or as an unqualified task name.\n   3. It throws `ToolError` for empty ops, missing explicit tasks, ambiguous task names, or unknown tasks; all error variants include the available task list.\n   4. It builds the final shell command with `buildCommand(commandPrefix, commandName, tail)`, joining non-empty parts with spaces.\n   5. If the task defines `cwd`, that relative path is returned alongside the command.\n8. `RecipeTool.execute()` forwards `{ command, cwd }` into `BashTool.execute()`; recipe does not pass timeout, env, async, or pty options.\n9. `BashTool.execute()` resolves internal URLs, validates/normalizes cwd against `session.cwd`, clamps timeout, applies bash interception rules, runs the command, and formats the final result.\n\n## Modes / Variants\n- Tool enablement:\n  - Disabled by `recipe.enabled` setting: tool is absent.\n  - Enabled but no detected tasks: tool is absent.\n- Task selection:\n  - Unqualified task name: succeeds only when exactly one detected runner owns that task.\n  - Explicit runner-qualified task: `<runner-id>:<task>`.\n- Runner detection paths:\n  - `just`: requires `just` on `PATH`, a justfile, and successful `just --dump --dump-format=json`.\n  - `pkg`: requires a readable root `package.json`; picks a package manager command from lockfiles or `bun` availability; discovers root scripts and workspace package scripts.\n  - `cargo`: requires `cargo` on `PATH`, `Cargo.toml`, and successful `cargo metadata --no-deps --format-version=1`.\n  - `make`: requires `make` on `PATH` and a makefile; parses targets statically.\n  - `task`: requires `task` on `PATH`, a Taskfile, and successful `task --list-all --json`.\n- Execution path:\n  - Always the synchronous `bash` call surface from recipe inputs.\n  - Bash may still auto-background long-running work if `bash.autoBackground.enabled` and session async job support are enabled.\n\n## Side Effects\n- Filesystem\n  - Reads manifests from the session cwd during detection: justfiles, `package.json`, workspace `package.json` files, `Cargo.toml`, makefiles, `Taskfile.yml` / `Taskfile.yaml`.\n  - Command execution runs in `session.cwd` or a task-specific relative cwd resolved under it.\n  - Bash may allocate output artifacts for truncated command output.\n- Subprocesses / native bindings\n  - Detection may spawn `just --dump --dump-format=json`, `cargo metadata --no-deps --format-version=1`, and `task --list-all --json`.\n  - Execution spawns the resolved shell command through `BashTool` / `executeBash()`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Tool availability depends on session settings.\n  - Constructor prompt text is specialized to detected runners/tasks.\n  - Bash execution may create async job records and output artifacts if bash auto-background triggers.\n- User-visible prompts / interactive UI\n  - The model-facing tool description lists detected runners and up to 20 tasks per runner.\n  - TUI rendering shows a shell-style preview using the resolved title/command/cwd.\n- Background work / cancellation\n  - Detection is parallelized across runners.\n  - Runtime command execution honors the passed abort signal through `BashTool`.\n\n## Limits & Caps\n- Prompt task listing is capped at `PROMPT_TASK_LIMIT = 20` per runner in `packages/coding-agent/src/tools/recipe/runner.ts`; this affects the rendered tool description, not execution.\n- Recipe itself defines no timeout input; delegated bash execution therefore uses bash's default `timeout = 300` seconds from `packages/coding-agent/src/tools/bash.ts`.\n- Bash clamps timeouts to the configured bash range (`clampTimeout(\"bash\", ...)` in `packages/coding-agent/src/tools/bash.ts`), but recipe cannot request a custom value.\n- `pkg` workspace discovery normalizes workspace globs to `.../package.json` and sorts matched package files lexicographically before task generation.\n- `cargo` deduplicates generated task names with a `Set`, so duplicate targets collapse to one recipe task.\n\n## Errors\n- Detection failures in runner modules are mostly soft-failed:\n  - Missing binaries, missing manifests, parse failures, or non-zero probe exits usually return `null` and log with `logger.debug(...)`.\n  - Result: the affected runner disappears instead of surfacing an error to the model.\n- Invocation failures are hard errors from `resolveRunnerAndTask()`:\n  - Empty `op`.\n  - Explicit runner prefix with missing/empty task.\n  - Ambiguous unqualified task name across runners.\n  - Unknown task name.\n- Execution failures come from `BashTool.execute()`:\n  - Invalid cwd.\n  - Bash interceptor blocks.\n  - Aborts/timeouts.\n  - Non-zero exit codes.\n  - Missing exit status.\n- All `resolveRunnerAndTask()` errors include the current available task list to help the model retry.\n\n## Notes\n- `RecipeTool` sets `concurrency = \"exclusive\"`; calls do not run concurrently with other exclusive tools.\n- Tool registration is all-or-nothing per runner: a detected runner with zero tasks is dropped.\n- Runner ids are fixed string literals from the runner modules: `just`, `pkg`, `cargo`, `make`, `task`.\n- `buildPromptModel()` includes each task's rendered command (`commandPrefix` + `commandName`) and relative cwd when present; the prompt therefore exposes the exact shell form recipe will run.\n- `pkg` task names:\n  - Root `package.json` scripts keep bare names like `test`.\n  - Workspace scripts are always namespaced as `<package-name-or-dir>/<script>` and set `cwd` to that package directory.\n  - Script names are shell-quoted into `commandName`, so a task like `build` becomes `bun run 'build'` / `npm run 'build'` / similar.\n- `pkg` command prefix selection prefers lockfiles in this order: `bun.lock`/`bun.lockb`, `pnpm-lock.yaml`, `yarn.lock`, `package-lock.json`/`npm-shrinkwrap.json`; otherwise it falls back to `bun run` if `bun` exists, else `npm run`.\n- `cargo` task names are generated from metadata targets:\n  - Single-package manifests: `bin/<name>`, `example/<name>`, `test/<name>`.\n  - Multi-package workspaces: `<package>/bin/<name>`, `<package>/example/<name>`, `<package>/test/<name>`.\n  - Each task overrides `commandPrefix` to the full `cargo run ... --bin|--example` or `cargo test ... --test` prefix, and `commandName` to the quoted target name.\n- `make` target parsing is static text parsing, not `make -qp` output:\n  - Recognizes makefiles named `Makefile`, `makefile`, `GNUmakefile`.\n  - Uses `.PHONY` lines to decide whether to include undocumented file targets; without any `.PHONY`, all parsed targets are exposed.\n  - If `.PHONY` exists, documented non-phony targets are kept with ` (file target)` appended to `doc`.\n- `just` detection ignores private recipes and preserves declared parameter names only for prompt display; execution still accepts arbitrary `tail` text.\n- `task` detection uses `desc` first, then `summary`, for task documentation.\n- Recipe has no env input of its own. Commands inherit whatever environment `BashTool` supplies for normal bash execution in the session.",
 	"tools/reflect.md": "# reflect\n\n> Ask the Hindsight server to synthesize an answer over the active memory bank.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/hindsight-reflect.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/reflect.md`\n- Key collaborators:\n  - `packages/coding-agent/src/hindsight/bank.ts` — best-effort bank mission initialization.\n  - `packages/coding-agent/src/hindsight/state.ts` — session state, shared bank scope, recall/reflect config.\n  - `packages/coding-agent/src/hindsight/client.ts` — HTTP `reflect` call and error mapping.\n  - `docs/tools/retain.md` — shared backend, storage, seeding, and mental-model bootstrap.\n\n## Inputs\n\n| Field | Type | Required | Description |\n|---|---|---:|---|\n| `query` | `string` | Yes | Question to answer from long-term memory. |\n| `context` | `string` | No | Extra guidance sent to the Hindsight reflect endpoint. |\n\n## Outputs\nReturns a single-shot tool result:\n\n- `content[0].type = \"text\"`\n- `content[0].text = response.text?.trim() || \"No relevant information found to reflect on.\"`\n- `details = {}`\n\nThe tool returns the Hindsight server's synthesized text directly; it does not expose raw recall hits.\n\n## Flow\n1. `HindsightReflectTool.createIf(...)` only exposes the tool when `memory.backend == \"hindsight\"`.\n2. `execute(...)` runs under `untilAborted(...)`.\n3. It reads the active `HindsightSessionState`; missing state throws `Hindsight backend is not initialised for this session.`\n4. Before reflecting, it calls `ensureBankMission(...)` with the current `bankId`, config, and process-local `missionsSet`.\n5. `ensureBankMission(...)` best-effort `PUT`s `/v1/default/banks/{bank_id}` with `reflect_mission` and optional `retain_mission` exactly once per bank/process; failures are swallowed.\n6. It calls `state.client.reflect(...)` with the model `query`, optional `context`, configured recall budget, and bank-scope tag filters.\n7. `HindsightApi.reflect(...)` POSTs `/v1/default/banks/{bank_id}/reflect` and defaults its own budget to `\"low\"` when callers omit one; this tool always passes the configured budget.\n8. Blank or whitespace-only responses are replaced with `No relevant information found to reflect on.`\n9. Failures are logged with `logger.warn(\"reflect failed\", ...)` and rethrown.\n\n## Modes / Variants\n- Tool path: one reflect request, optionally focused by `context`.\n- Bank scoping is inherited from the active `HindsightSessionState`:\n  - `global` — no tag filter.\n  - `per-project` — separate bank id per cwd basename.\n  - `per-project-tagged` — shared bank id plus `project:<cwd basename>` filter with `tagsMatch = \"any\"`.\n- Session scope: reads cross-session server-side memories, but does not persist local output.\n\n## Side Effects\n- Network\n  - Optional `PUT /v1/default/banks/{bank_id}` from `ensureBankMission(...)`.\n  - `POST /v1/default/banks/{bank_id}/reflect` via `packages/coding-agent/src/hindsight/client.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Reads session-held bank scope and config only. Does not update `lastRecallSnippet`, the mental-model cache, or the retain queue.\n- Background work / cancellation\n  - Aborts through `untilAborted(...)` if the tool call signal is cancelled.\n\n## Limits & Caps\n- Tool-level params: only `query` is required; `context` is optional.\n- Default budget setting comes from `hindsight.recallBudget` in `packages/coding-agent/src/config/settings-schema.ts`; default `\"mid\"`.\n- `reflect` itself has no client-side token cap parameter here; unlike `recall`, the tool does not pass `maxTokens`.\n- Mission initialization tracks up to `MISSION_SET_CAP = 10_000` bank ids in `packages/coding-agent/src/hindsight/bank.ts`, then drops the oldest half of the sorted set.\n\n## Errors\n- Throws `Hindsight backend is not initialised for this session.` when no state exists.\n- HTTP and fetch failures become `HindsightError` from `packages/coding-agent/src/hindsight/client.ts` with `statusCode` and parsed `details` when available.\n- `ensureBankMission(...)` failures are silent to the tool caller; only the later reflect request can fail visibly.\n- Non-`Error` failures are normalized to `new Error(String(err))` before rethrow.\n\n## Notes\n- Shared backend details are in `docs/tools/retain.md`: server-side storage, subagent aliasing, bank scoping, seed mental models from `packages/coding-agent/src/hindsight/seeds.json`, and mental-model prompt injection.\n- `reflect` does not read the cached `<mental_models>` block directly. It queries the Hindsight server over the bank contents. The same session may also have separate mental-model context injected into its developer instructions.\n- Reflect mission and retain mission are bank-level server settings, not per-request payload. The tool just ensures they are present best-effort before reflecting.\n",
 	"tools/render_mermaid.md": "# render_mermaid\n\n> Convert Mermaid source into terminal-friendly ASCII/Unicode text.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/render-mermaid.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/render-mermaid.md`\n- Key collaborators:\n  - `packages/utils/src/mermaid-ascii.ts` — thin wrapper over renderer package.\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and enablement gate.\n  - `packages/coding-agent/src/sdk.ts` — session-facing artifact allocation hook.\n  - `packages/coding-agent/src/session/session-manager.ts` — persistent-session artifact path allocation.\n  - `packages/coding-agent/src/session/artifacts.ts` — artifact filename generation and writes.\n- Related user/runtime doc: `docs/render-mermaid.md`\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `mermaid` | `string` | Yes | Mermaid source text. Schema example: `graph TD; A-->B`. |\n| `config` | `object` | No | Optional renderer options. Sanitized before rendering; numeric fields are floored and clamped to `>= 0`. |\n\n`config` fields:\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `useAscii` | `boolean` | No | `true` for plain ASCII, `false`/omitted for Unicode box-drawing output. Passed through unchanged. |\n| `paddingX` | `number` | No | Horizontal spacing. `Math.floor`, then `Math.max(0, value)`. |\n| `paddingY` | `number` | No | Vertical spacing. `Math.floor`, then `Math.max(0, value)`. |\n| `boxBorderPadding` | `number` | No | Inner box padding. `Math.floor`, then `Math.max(0, value)`. |\n\n## Outputs\nThe tool returns a single text content block:\n\n- inline body: rendered diagram text\n- optional trailer: `Saved artifact: artifact://<id>` when artifact storage is available\n\n`details` may include:\n\n- `artifactId?: string`\n\nNo image path, SVG, PNG, or binary payload is returned. Stored artifacts are plain text `.log` files; artifact filenames are allocated as `<id>.render_mermaid.log` by `packages/coding-agent/src/session/artifacts.ts`.\n\n## Flow\n1. `RenderMermaidTool.execute()` in `packages/coding-agent/src/tools/render-mermaid.ts` receives `mermaid` and optional `config`.\n2. `sanitizeRenderConfig()` normalizes `paddingX`, `paddingY`, and `boxBorderPadding` to non-negative integers; `useAscii` is passed through.\n3. The tool calls `renderMermaidAscii()` from `@oh-my-pi/pi-utils`.\n4. `packages/utils/src/mermaid-ascii.ts` forwards directly to `renderMermaidASCII()` from the `beautiful-mermaid` package.\n5. The tool optionally asks the session for an artifact slot with `allocateOutputArtifact(\"render_mermaid\")`.\n6. If a path is returned, `Bun.write()` persists the full rendered text to that file.\n7. The tool returns the rendered text, plus an `artifact://` line and `details.artifactId` when persistence succeeded.\n\n## Modes / Variants\n- Default render: Unicode box-drawing output when `config.useAscii` is omitted or false.\n- ASCII render: plain ASCII output when `config.useAscii` is true.\n- Persistent-session path: artifact text is written when `allocateOutputArtifact()` returns a path.\n- Ephemeral-session path: no artifact is written; the inline text result is still returned.\n\n## Side Effects\n- Filesystem\n  - May write one session artifact via `Bun.write()`.\n  - Artifact filename format is `<id>.render_mermaid.log`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Consumes the session artifact allocator hook.\n  - Returns `details.artifactId` for the tool result.\n\n## Limits & Caps\n- No tool-local timeout, retry, truncation, or streaming path.\n- Numeric config fields are quantized to integers with `Math.floor()` and clamped to `0` minimum in `sanitizeRenderConfig()`.\n- Renderer engine is `beautiful-mermaid@1.1.3` per root `package.json` / `bun.lock`.\n- The tool is registered as discoverable and gated by `renderMermaid.enabled` in `packages/coding-agent/src/tools/index.ts`.\n\n## Errors\n- `renderMermaidAscii()` is not wrapped in a local `try/catch`; renderer exceptions propagate out of `execute()`.\n- Invalid Mermaid syntax therefore fails the tool call rather than returning partial output.\n- Artifact allocation failures inside the SDK hook are swallowed there and converted to `{}` in `packages/coding-agent/src/sdk.ts`; rendering still succeeds, just without a saved artifact.\n- Artifact write failures from `Bun.write()` are not caught in the tool and will fail the call.\n\n## Notes\n- The tool summary string says `Render a Mermaid diagram to an image`, but the implementation and prompt both produce text, not images.\n- Despite the name, this tool does not use Puppeteer, browser rendering, Mermaid CLI, or native bindings; rendering stays in-process through the JS package wrapper.\n- `docs/render-mermaid.md` covers operator-facing behavior and enablement; keep this file focused on the tool contract and runtime path.\n",
 	"tools/resolve.md": "# resolve\n\n> Finalizes a queued preview action by applying or discarding it.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/resolve.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/resolve.md`\n- Key collaborators:\n  - `docs/resolve-tool-runtime.md` — preview/apply runtime reference\n  - `packages/coding-agent/src/extensibility/custom-tools/loader.ts` — forwards custom pending actions into the queue\n  - `packages/coding-agent/src/tools/ast-edit.ts` — built-in preview producer example\n  - `packages/coding-agent/src/session/agent-session.ts` — tool-choice queue and invoker access\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | `\"apply\" | \"discard\"` | Yes | Whether to commit or reject the queued preview. |\n| `reason` | `string` | Yes | Required explanation passed through to the queued callback. |\n\n## Outputs\n- Single-shot result.\n- `execute()` returns whatever the queued invoker returns, with `details` wrapped/augmented to include:\n  - `action`\n  - `reason`\n  - `sourceToolName?`\n  - `label?`\n  - `sourceResultDetails?` — original `result.details` from the apply/reject callback when present\n- If `discard` has no custom reject callback, the default success payload is `Discarded: <label>. Reason: <reason>`.\n- The TUI renderer is inline and merges call+result into one block.\n\n## Flow\n1. Preview-producing code calls `queueResolveHandler(...)` with a label, source tool name, and `apply(reason)` callback, plus optional `reject(reason)`.\n2. `queueResolveHandler(...)` asks the session for a forced `resolve` tool choice and pushes it into the tool-choice queue with `pushOnce(...)`.\n3. The queued entry is marked `now: true`; if the model rejects that forced tool choice, `onRejected` returns `requeue`, so the reminder comes back.\n4. `queueResolveHandler(...)` also injects a `resolve-reminder` steering message: `This is a preview. Call the resolve tool to apply or discard these changes.`\n5. When `resolve.execute()` runs, it wraps the call in `untilAborted(...)` and fetches the current queue invoker with `session.peekQueueInvoker()`.\n6. If no invoker exists, it throws `ToolError(\"No pending action to resolve. Nothing to apply or discard.\")`.\n7. Otherwise it invokes the queued callback with `{ action, reason }`.\n8. For `apply`, it always executes the producer's `apply(reason)` callback.\n9. For `discard`, it executes `reject(reason)` when provided; if that callback is absent or returns `undefined`, `resolve` fabricates the default discard message.\n10. Before returning, it merges resolve metadata into `result.details` so renderer/UI code can show the action, label, and originating tool.\n\n## Modes / Variants\n- `apply`: runs the queued `apply(reason)` callback and returns its content.\n- `discard` with reject callback: runs `reject(reason)` and returns that callback's content.\n- `discard` without reject callback: returns the built-in `Discarded: ...` text payload.\n\n## Side Effects\n- Session state\n  - Consumes the current pending preview through the session tool-choice queue; there is no separate pending-action stack.\n  - Adds a `resolve-reminder` steering message when a preview is queued.\n- User-visible prompts / interactive UI\n  - No direct prompt. The visible effect depends on the preview-producing tool and the resolve renderer.\n- Background work / cancellation\n  - `untilAborted(...)` lets abort signals interrupt resolution before invoking the callback completes.\n\n## Limits & Caps\n- Hidden tool: not discoverable in the normal tool index (`packages/coding-agent/src/tools/resolve.ts`, `packages/coding-agent/src/session/agent-session.ts`).\n- Exactly one active queue invoker is consulted per call via `session.peekQueueInvoker()`.\n- There is no independent queue depth cap in this tool; ordering follows the shared tool-choice queue (`docs/resolve-tool-runtime.md`).\n\n## Errors\n- No pending preview: throws `ToolError(\"No pending action to resolve. Nothing to apply or discard.\")`.\n- Any exception from the queued `apply` / `reject` callback propagates through `resolve`.\n- Aborts during `untilAborted(...)` surface as the underlying abort error from the utility.\n\n## Notes\n- `reason` is informational; `resolve` passes it through but does not interpret it.\n- `queueResolveHandler(...)` is the canonical built-in integration point; custom tools use `pushPendingAction(...)`, which the loader forwards into the same mechanism.\n- The tool only works because another tool already staged a preview and forced a one-shot `resolve` choice.\n- `sourceResultDetails` is added only when the apply/reject callback returned a non-null `details` field; custom pending-action `details` are not forwarded automatically by the loader.\n",