@oh-my-pi/pi-coding-agent 14.9.5 → 14.9.7

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

@@ -9,7 +9,7 @@ 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- `src/session/compaction/compaction.ts`\n- `src/session/compaction/branch-summarization.ts`\n- `src/session/compaction/pruning.ts`\n- `src/session/compaction/utils.ts`\n- `src/session/session-manager.ts`\n- `src/session/agent-session.ts`\n- `src/session/messages.ts`\n- `src/extensibility/hooks/types.ts`\n- `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- `prompts/compaction/compaction-summary-context.md`\n- `prompts/compaction/branch-summary-context.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\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### 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 with AJV against a provided TypeBox 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` + TypeBox schema).\n- **Extension**: lifecycle/event framework that can register tools and intercept/modify events.\n- **Hook**: external pre/post command scripts.\n- **Skill**: static guidance/context package, not executable tool code.\n\nIf you need the model to call code directly, use a custom tool.\n\n## Integration paths in current code\n\nThere are two active integration styles:\n\n1. **SDK-provided custom tools** (`options.customTools`)\n   - Wrapped into agent tools via `CustomToolAdapter` or extension wrappers.\n   - Always included in the initial active tool set in SDK bootstrap.\n\n2. **Filesystem-discovered modules via loader API** (`discoverAndLoadCustomTools` / `loadCustomTools`)\n   - Exposed as library APIs in `src/extensibility/custom-tools/loader.ts`.\n   - Host code can call these to discover and load tool modules from config/provider/plugin paths.\n\n```text\nModel tool call flow\n\nLLM tool call\n   │\n   ▼\nTool registry (built-ins + custom tool adapters)\n   │\n   ▼\nCustomTool.execute(toolCallId, params, onUpdate, ctx, signal)\n   │\n   ├─ onUpdate(...)  -> streamed partial result\n   └─ return result  -> final tool content/details\n```\n\n## Discovery locations (loader API)\n\n`discoverAndLoadCustomTools(configuredPaths, cwd, builtInToolNames)` merges:\n\n1. Capability providers (`toolCapability`), including:\n   - Native OMP config (`~/.omp/agent/tools`, `.omp/tools`)\n   - Claude config (`~/.claude/tools`, `.claude/tools`)\n   - Codex config (`~/.codex/tools`, `.codex/tools`)\n   - Claude marketplace plugin cache provider\n2. Installed plugin manifests (`~/.omp/plugins/node_modules/*` via plugin loader)\n3. Explicit configured paths passed to the loader\n\n### Important behavior\n\n- Duplicate resolved paths are deduplicated.\n- Tool name conflicts are rejected against built-ins and already-loaded custom tools.\n- `.md` and `.json` files are discovered as tool metadata by some providers, but the executable module loader rejects them as runnable tools.\n- Relative configured paths are resolved from `cwd`; `~` is expanded.\n\n## Module contract\n\nA custom tool module must export a function (default export preferred):\n\n```ts\nimport type { CustomToolFactory } from \"@oh-my-pi/pi-coding-agent\";\n\nconst factory: CustomToolFactory = (pi) => ({\n  name: \"repo_stats\",\n  label: \"Repo Stats\",\n  description: \"Counts tracked TypeScript files\",\n  parameters: pi.typebox.Type.Object({\n    glob: pi.typebox.Type.Optional(\n      pi.typebox.Type.String({ default: \"**/*.ts\" }),\n    ),\n  }),\n\n  async execute(toolCallId, params, onUpdate, ctx, signal) {\n    onUpdate?.({\n      content: [{ type: \"text\", text: \"Scanning files...\" }],\n      details: { phase: \"scan\" },\n    });\n\n    const result = await pi.exec(\n      \"git\",\n      [\"ls-files\", params.glob ?? \"**/*.ts\"],\n      { signal, cwd: pi.cwd },\n    );\n    if (result.killed) {\n      throw new Error(\"Scan was cancelled\");\n    }\n    if (result.code !== 0) {\n      throw new Error(result.stderr || \"git ls-files failed\");\n    }\n\n    const files = result.stdout.split(\"\\n\").filter(Boolean);\n    return {\n      content: [{ type: \"text\", text: `Found ${files.length} files` }],\n      details: { count: files.length, sample: files.slice(0, 10) },\n    };\n  },\n\n  onSession(event) {\n    if (event.reason === \"shutdown\") {\n      // cleanup resources if needed\n    }\n  },\n});\n\nexport default factory;\n```\n\nFactory return type:\n\n- `CustomTool`\n- `CustomTool[]`\n- `Promise<CustomTool | CustomTool[]>`\n\n## API surface passed to factories (`CustomToolAPI`)\n\nFrom `types.ts` and `loader.ts`:\n\n- `cwd`: host working directory\n- `exec(command, args, options?)`: process execution helper\n- `ui`: UI context (can be no-op in headless modes)\n- `hasUI`: `false` in non-interactive flows\n- `logger`: shared file logger\n- `typebox`: injected `@sinclair/typebox`\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 TypeBox schema via `Static<TParams>`.\n- Runtime argument validation happens before execution in the agent loop.\n- `onUpdate` emits partial results for UI streaming.\n- `ctx` includes 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| `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---\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`                                                      | Enables bearer token auth path                                                                |\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 kernel availability checks/warm checks                                                         |\n| `PI_PYTHON_GATEWAY_URL`   | If set, uses external kernel gateway instead of local shared gateway                                                |\n| `PI_PYTHON_GATEWAY_TOKEN` | Optional auth token for external gateway (`Authorization: token <value>`)                                           |\n| `PI_PYTHON_IPC_TRACE`     | If `1`, enables low-level IPC trace path in kernel module                                                           |\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 `1`, enables startup/tool timing instrumentation logs                                           |\n| `PI_DEBUG_STARTUP`           | Enables startup stage debug prints to stderr in multiple startup paths                             |\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`, `atom`, `vim`, `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\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| `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---\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`                                                      | Enables bearer token auth path                                                                |\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 `1`, enables startup/tool timing instrumentation logs                                           |\n| `PI_DEBUG_STARTUP`           | Enables startup stage debug prints to stderr in multiple startup paths                             |\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`, `atom`, `vim`, `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\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\";\nimport { Type } from \"@sinclair/typebox\";\n\nexport default function (pi: ExtensionAPI) {\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: Type.Object({ name: Type.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.typebox`\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\npi.registerTool({\n  name: \"my_tool\",\n  label: \"My Tool\",\n  description: \"...\",\n  parameters: Type.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",
@@ -37,7 +37,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"porting-from-pi-mono.md": "# Porting From pi-mono: A Practical Merge Guide\n\nThis guide is a repeatable checklist for porting changes from pi-mono into this repo.\nUse it for any merge: single file, feature branch, or full release sync.\n\n## Last Sync Point (historical upstream marker)\n\n**Commit:** `b21b42d032919de2f2e6920a76fa9a37c3920c0a`\n**Date:** 2026-03-22\n\nUpdate this section after each sync; do not reuse the previous range. This commit is an upstream pi-mono marker and may not exist in this repo's local object database.\n\nWhen starting a new sync, generate patches from this commit forward in a pi-mono checkout or remote that contains the commit:\n\n```bash\ngit format-patch b21b42d032919de2f2e6920a76fa9a37c3920c0a..HEAD --stdout > changes.patch\n```\n\n## 0) Define the scope\n\n- Identify the upstream reference (commit, tag, or PR).\n- List the packages or folders you plan to touch.\n- Decide which features are in-scope and which are intentionally skipped.\n\n## 1) Bring code over safely\n\n- Prefer a clean, focused diff rather than a wholesale copy.\n- Avoid copying built artifacts or generated files.\n- If upstream added new files, add them explicitly and review contents.\n\n## 2) Match import extension conventions\n\nMost runtime TypeScript sources omit `.js` in internal imports, but several current entrypoints and tool modules keep `.js` for ESM/runtime compatibility. Follow the surrounding file and package export style; do not blanket-strip or blanket-add extensions.\n\n- In `packages/coding-agent` runtime sources, prefer extensionless internal imports when the surrounding module does, but preserve existing `.js` imports in files that already require them.\n- In `packages/tui/test` and `packages/natives/bench`, keep `.js` where surrounding files already use it.\n- Keep real file extensions when required by tooling or import assertions (e.g., `.json`, `.css`, `.md` text embeds).\n- Example: `import { x } from \"./foo.js\";` → `import { x } from \"./foo\";` only when that package/file convention is extensionless.\n\n## 3) Replace import scopes\n\nUpstream uses different package scopes. Replace them consistently.\n\n- Replace old scopes with the local scope used here.\n- Examples (adjust to match the actual packages you are porting):\n  - `@mariozechner/pi-coding-agent` → `@oh-my-pi/pi-coding-agent`\n  - `@mariozechner/pi-agent-core` → `@oh-my-pi/pi-agent-core`\n  - `@mariozechner/pi-tui` → `@oh-my-pi/pi-tui`\n  - `@mariozechner/pi-ai` → `@oh-my-pi/pi-ai`\n\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",
 	"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 and IPython Runtime\n\nThis document describes the current Python execution stack in `packages/coding-agent`.\nIt covers tool behavior, kernel/gateway lifecycle, environment handling, execution semantics, output rendering, 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- Kernel protocol + gateway integration: `src/eval/py/kernel.ts`\n- Shared local gateway coordinator: `src/eval/py/gateway-coordinator.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 through a Jupyter Kernel Gateway-backed kernel when `language: \"python\"` is selected or inferred (not by spawning `python -c` directly per cell).\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## Gateway lifecycle\n\n### Modes\n\nThere are two gateway paths:\n\n1. **External gateway** (`PI_PYTHON_GATEWAY_URL` set)\n   - Uses the configured URL directly.\n   - Optional auth with `PI_PYTHON_GATEWAY_TOKEN`.\n   - No local gateway process is spawned or managed.\n\n2. **Local shared gateway** (default path)\n   - Uses a single shared process coordinated under `~/.omp/agent/python-gateway`.\n   - Metadata file: `gateway.json`\n   - Lock file: `gateway.lock`\n   - Spawn command:\n     - `python -m kernel_gateway`\n     - bound to `127.0.0.1:<allocated-port>`\n     - startup health check: `GET /api/kernelspecs`\n\n### Local shared gateway coordination\n\n`acquireSharedGateway()`:\n\n- Takes a file lock (`gateway.lock`) with heartbeat.\n- Reuses `gateway.json` if PID is alive and health check passes.\n- Cleans stale info/PIDs when needed.\n- Starts a new gateway when no healthy one exists.\n\n`releaseSharedGateway()` is currently a no-op (kernel shutdown does not tear down shared gateway).\n\n`shutdownSharedGateway()` explicitly terminates the shared process and clears gateway metadata.\n\n### Important constraint\n\n`python.sharedGateway=false` is rejected at kernel start:\n\n- Error: `Shared Python gateway required; local gateways are disabled`\n- There is no per-process non-shared local gateway mode.\n\n## Kernel lifecycle\n\nKernels are created via `POST /api/kernels` on the selected gateway when a retained session needs a kernel or when `per-call` mode starts a request.\n\nKernel startup sequence:\n\n1. Availability check (`checkPythonKernelAvailability`)\n2. Create kernel (`/api/kernels`)\n3. Open websocket (`/api/kernels/:id/channels`)\n4. Initialize kernel env (`cwd`, env vars, `sys.path`)\n5. Execute `PYTHON_PRELUDE`\n6. Load extension modules from:\n   - user: `~/.omp/agent/modules/*.py`\n   - project: `<cwd>/.omp/modules/*.py` (overrides same-name user module)\n\nKernel shutdown:\n\n- Deletes remote kernel via `DELETE /api/kernels/:id`\n- Closes websocket\n- Calls shared gateway release hook (no-op today)\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\n- `per-call`\n  - Creates a fresh kernel for each execute request.\n  - Shuts kernel 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 gateway/kernel runtime:\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\nKernel startup receives the optional session file path from the 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- injects provided env entries into `os.environ`\n- ensures cwd is in `sys.path`\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`.\n\nThe tool combines:\n\n- caller abort signal\n- timeout abort signal\n\nwith `AbortSignal.any(...)`.\n\n### Kernel execution cancellation\n\nOn abort/timeout:\n\n- Execution is marked cancelled.\n- Kernel interrupt is attempted via REST (`POST /interrupt`) and control-channel `interrupt_request`.\n- Result includes `cancelled=true`.\n- Timeout path annotates output as `Command timed out after <n> seconds`.\n\n### stdin behavior\n\nInteractive stdin is not supported.\n\nIf kernel emits `input_request`:\n\n- Tool records `stdinRequested=true`\n- Emits explanatory text\n- Sends empty `input_reply`\n- Execution is treated as failure at executor layer\n\n## Output capture and rendering\n\n### Captured output classes\n\nFrom kernel messages:\n\n- `stream` -> plain text chunks\n- `display_data`/`execute_result` -> rich display handling\n- `error` -> traceback text\n- custom MIME `application/x-omp-status` -> 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 payloads\n- `application/x-omp-status` -> status events\n\n### Storage and truncation\n\nOutput is streamed through `OutputSink` and may be persisted to artifact storage.\n\nTool 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## External gateway support\n\nSet:\n\n```bash\nexport PI_PYTHON_GATEWAY_URL=\"http://127.0.0.1:8888\"\n# Optional:\nexport PI_PYTHON_GATEWAY_TOKEN=\"...\"\n```\n\nBehavior differences from local shared gateway:\n\n- No local gateway lock/info files\n- No local process spawn/termination\n- Health checks and kernel CRUD run against external endpoint\n- Auth failures are surfaced with explicit token guidance\n\n## Operational troubleshooting (current failure modes)\n\n- **Python backend not available**\n  - Check `eval.py`, Python kernel dependencies, and `PI_PY`.\n  - If preflight fails and `eval.js` is enabled, omit `language` or pass `language: \"js\"` to use JavaScript.\n\n- **Kernel availability errors**\n  - Local mode requires both `kernel_gateway` and `ipykernel` importable in resolved Python runtime.\n  - Install with:\n    ```bash\n    python -m pip install jupyter_kernel_gateway ipykernel\n    ```\n\n- **`python.sharedGateway=false` causes startup failure**\n  - This is expected with current implementation.\n\n- **External gateway auth/reachability failures**\n  - 401/403 -> set `PI_PYTHON_GATEWAY_TOKEN`.\n  - timeout/unreachable -> verify URL/network and gateway health.\n\n- **Execution hangs then times out**\n  - Increase tool `timeout` (max 600s) if workload is legitimate.\n  - For stuck code, cancellation triggers kernel interrupt but user code may still need refactor.\n\n- **stdin/input prompts in Python code**\n  - `input()` is not supported interactively in this runtime path; pass data programmatically.\n\n- **Resource exhaustion (`EMFILE` / too many open files)**\n  - Session manager triggers shared-gateway recovery (session teardown + shared gateway restart).\n\n- **Working directory errors**\n  - Tool validates `cwd` exists and is a directory before execution.\n\n## Relevant environment variables\n\n- `PI_PY` — tool exposure override (`bash-only`/`ipy-only`/`both` mapping above)\n- `PI_PYTHON_GATEWAY_URL` — use external gateway\n- `PI_PYTHON_GATEWAY_TOKEN` — optional external gateway auth token\n- `PI_PYTHON_SKIP_CHECK=1` — bypass Python preflight/warm checks\n- `PI_PYTHON_IPC_TRACE=1` — log kernel IPC send/receive traces\n- `PI_DEBUG_STARTUP=1` — emit startup-stage debug markers\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- `PI_DEBUG_STARTUP=1` — emit startup-stage debug markers\n",
 	"render-mermaid.md": "# RenderMermaid\n\n`RenderMermaid` is an optional built-in tool that renders Mermaid source to terminal-friendly text.\n\n## Enable it\n\nDisabled by default. Turn it on in `/settings` under **Tools → Render Mermaid**, or in `~/.omp/agent/config.yml`:\n\n```yaml\nrenderMermaid:\n  enabled: true\n```\n\n## What it does\n\n- Tool name: `render_mermaid`\n- Input: Mermaid source in the required `mermaid` field\n- Output: rendered ASCII/Unicode text, not SVG or PNG\n- Storage: when artifact storage is available, the full render is also saved as an `artifact://...`\n\nThere are no model-specific or environment-variable prerequisites. Once enabled, any model that can call built-in tools can use it.\n\n## Parameters\n\n```json\n{\n  \"mermaid\": \"graph TD\\n  A[Start] --> B[Stop]\",\n  \"config\": {\n    \"useAscii\": false,\n    \"paddingX\": 2,\n    \"paddingY\": 2,\n    \"boxBorderPadding\": 0\n  }\n}\n```\n\nAvailable `config` fields:\n\n- `useAscii` — `true` for plain ASCII, `false` for Unicode box-drawing characters (default and usually more readable)\n- `paddingX` — horizontal spacing between nodes\n- `paddingY` — vertical spacing between nodes\n- `boxBorderPadding` — inner padding inside node boxes\n\n## Current limitations\n\n`RenderMermaid` uses the `beautiful-mermaid` ASCII renderer. It works best for flowcharts and small diagrams.\n\nComplex sequence diagrams, especially with `alt` / `else` blocks, can become very wide in a terminal. That is current renderer behavior, not a provider or model configuration problem.\n\nIf a sequence diagram is hard to read:\n\n1. Keep Unicode output (`useAscii: false`)\n2. Reduce spacing with a tighter config such as `paddingX: 2`, `paddingY: 2`, `boxBorderPadding: 0`\n3. Prefer smaller sub-diagrams over one large sequence diagram\n4. Open the saved artifact if the inline preview is truncated in the TUI\n\n## Example\n\nInput:\n\n```mermaid\ngraph TD\n  A[Start] --> B{Decision}\n  B -->|Yes| C[Action]\n  B -->|No| D[End]\n```\n\nTypical result:\n\n```text\n┌─────┐\n│Start│\n└─────┘\n   │\n   ▼\n┌────────┐\n│Decision│\n└────────┘\n```\n",
 	"resolve-tool-runtime.md": "# Resolve tool runtime internals\n\nThis document explains how preview/apply workflows are modeled in coding-agent and how built-in or custom tools can participate via the tool-choice queue and `pushPendingAction`.\n\n## Scope and key files\n\n- [`src/tools/resolve.ts`](../packages/coding-agent/src/tools/resolve.ts)\n- [`src/tools/ast-edit.ts`](../packages/coding-agent/src/tools/ast-edit.ts)\n- [`src/extensibility/custom-tools/types.ts`](../packages/coding-agent/src/extensibility/custom-tools/types.ts)\n- [`src/extensibility/custom-tools/loader.ts`](../packages/coding-agent/src/extensibility/custom-tools/loader.ts)\n- [`src/sdk.ts`](../packages/coding-agent/src/sdk.ts)\n\n## What `resolve` does\n\n`resolve` is a hidden tool that finalizes a pending preview action.\n\n- `action: \"apply\"` executes the queued action's `apply(reason)` callback and returns that result with resolve metadata.\n- `action: \"discard\"` invokes `reject(reason)` if provided; otherwise returns `Discarded: <label>. Reason: <reason>`.\n\nIf no pending action exists, `resolve` fails with:\n\n- `No pending action to resolve. Nothing to apply or discard.`\n\n## Pending actions use the tool-choice queue\n\nPreview producers call `queueResolveHandler(...)`, which pushes a one-shot forced `resolve` directive onto the session tool-choice queue and adds a `resolve-reminder` steering message.\n\nRuntime behavior:\n\n- the queued handler owns the pending `apply`/`reject` callbacks,\n- `resolve` looks up the current queue invoker with `session.peekQueueInvoker()`,\n- if the model rejects the forced tool choice, the queue directive is requeued,\n- `resolve` does not maintain a separate pending-action stack.\n\nMultiple pending previews therefore follow the active tool-choice queue ordering, not an independent pending-action store.\n\n## Built-in producer example (`ast_edit`)\n\n`ast_edit` previews structural replacements first. When the preview has replacements and is not applied yet, it queues a resolve handler that contains:\n\n- label (human-readable summary)\n- `sourceToolName` (`ast_edit`)\n- `apply(reason: string)` callback that reruns AST edit with `dryRun: false`\n\n`resolve(action=\"apply\", reason=\"...\")` passes `reason` into this callback.\n\n## Custom tools: `pushPendingAction`\n\nCustom tools can register resolve-compatible pending actions through `CustomToolAPI.pushPendingAction(...)`. The custom tool loader forwards these actions to `queueResolveHandler(...)` when that hook is available.\n\n`CustomToolPendingAction`:\n\n- `label: string` (required)\n- `apply(reason: string): Promise<AgentToolResult<unknown>>` (required) — invoked on apply; `reason` is the string passed to `resolve`\n- `reject?(reason: string): Promise<AgentToolResult<unknown> | undefined>` (optional) — invoked on discard; return value replaces the default \"Discarded\" message if provided\n- `details?: unknown` exists on the public custom-tool type but is not currently forwarded by the loader into resolve metadata\n- `sourceToolName?: string` (optional, defaults to `\"custom_tool\"`)\n\n### Minimal usage example\n\n```ts\nimport type { CustomToolFactory } from \"@oh-my-pi/pi-coding-agent\";\n\nconst factory: CustomToolFactory = (pi) => ({\n  name: \"batch_rename_preview\",\n  label: \"Batch Rename Preview\",\n  description: \"Previews renames and defers commit to resolve\",\n  parameters: pi.typebox.Type.Object({\n    files: pi.typebox.Type.Array(pi.typebox.Type.String()),\n  }),\n\n  async execute(_toolCallId, params) {\n    const previewSummary = `Prepared rename plan for ${params.files.length} files`;\n\n    pi.pushPendingAction({\n      label: `Batch rename: ${params.files.length} files`,\n      sourceToolName: \"batch_rename_preview\",\n      apply: async (reason) => {\n        // apply writes here\n        return {\n          content: [\n            { type: \"text\", text: `Applied batch rename. Reason: ${reason}` },\n          ],\n        };\n      },\n      reject: async (reason) => {\n        // optional: cleanup or notify on discard\n        return {\n          content: [\n            { type: \"text\", text: `Discarded batch rename. Reason: ${reason}` },\n          ],\n        };\n      },\n    });\n\n    return {\n      content: [\n        {\n          type: \"text\",\n          text: `${previewSummary}. Call resolve to apply or discard.`,\n        },\n      ],\n    };\n  },\n});\n\nexport default factory;\n```\n\n## Runtime availability and failures\n\n`pushPendingAction` is wired by the custom tool loader through the active session's resolve queue hook.\n\nIf the runtime did not provide the resolve queue hook, `pushPendingAction` throws:\n\n- `Pending action store unavailable for custom tools in this runtime.`\n\n## Tool-choice behavior\n\nWhen `queueResolveHandler(...)` registers a preview, the agent runtime forces a one-shot `resolve` tool choice so pending previews are explicitly finalized before normal tool flow continues.\n\n## Developer guidance\n\n- Use pending actions only for destructive or high-impact operations that should support explicit apply/discard.\n- Keep `label` concise and specific; it is shown in resolve renderer output.\n- Ensure `apply(reason)` is deterministic and idempotent enough for one-shot execution; `reason` is informational and should not change behavior.\n- Implement `reject(reason)` when the discard needs cleanup (temp state, locks, notifications); omit it for stateless previews where the default message suffices.\n- If your tool can stage multiple previews, remember they are mediated by the tool-choice queue rather than a separate pending-action stack.\n",
 	"rpc.md": "# RPC Protocol Reference\n\nRPC mode runs the coding agent as a newline-delimited JSON protocol over stdio.\n\n- **stdin**: commands (`RpcCommand`), extension UI responses, and host-tool updates/results\n- **stdout**: a ready frame, command responses (`RpcResponse`), session/agent events, extension UI requests, host-tool requests/cancellations\n\nPrimary implementation:\n\n- `src/modes/rpc/rpc-mode.ts`\n- `src/modes/rpc/rpc-types.ts`\n- `src/session/agent-session.ts`\n- `packages/agent/src/agent.ts`\n- `packages/agent/src/agent-loop.ts`\n\n## Startup\n\n```bash\nomp --mode rpc [regular CLI options]\n```\n\nBehavior notes:\n\n- `@file` CLI arguments are rejected in RPC mode.\n- RPC mode disables automatic session title generation by default to avoid an extra model call.\n- RPC mode resets workflow-altering `todo.*`, `task.*`, `async.*`, and `bash.autoBackground.*` settings to their built-in defaults instead of inheriting user overrides.\n- The process reads stdin as JSONL (`readJsonl(Bun.stdin.stream())`).\n- At startup it writes `{ \"type\": \"ready\" }` before processing commands.\n- When stdin closes, pending host-tool calls are rejected and the process exits with code `0`.\n- Responses/events are written as one JSON object per line.\n\n## Transport and Framing\n\nEach frame is a single JSON object followed by `\\n`.\n\nThere is no envelope beyond the object shape itself.\n\n### Outbound frame categories (stdout)\n\n1. Ready frame (`{ type: \"ready\" }`)\n2. `RpcResponse` (`{ type: \"response\", ... }`)\n3. `AgentSessionEvent` objects (`agent_start`, `message_update`, etc.)\n4. `RpcExtensionUIRequest` (`{ type: \"extension_ui_request\", ... }`)\n5. Host tool requests/cancellations (`host_tool_call`, `host_tool_cancel`)\n6. Extension errors (`{ type: \"extension_error\", extensionPath, event, error }`)\n\n### Inbound frame categories (stdin)\n\n1. `RpcCommand`\n2. `RpcExtensionUIResponse` (`{ type: \"extension_ui_response\", ... }`)\n3. Host tool updates/results (`host_tool_update`, `host_tool_result`)\n\n## Request/Response Correlation\n\nAll commands accept optional `id?: string`.\n\n- If provided, normal command responses echo the same `id`.\n- `RpcClient` relies on this for pending-request resolution.\n\nImportant edge behavior from runtime:\n\n- Unknown command responses are emitted with `id: undefined` (even if the request had an `id`).\n- Parse/handler exceptions in the input loop emit `command: \"parse\"` with `id: undefined`.\n- `prompt` and `abort_and_prompt` return immediate success, then may emit a later error response with the **same** id if async prompt scheduling fails.\n\n## Command Schema (canonical)\n\n`RpcCommand` is defined in `src/modes/rpc/rpc-types.ts`:\n\n### Prompting\n\n- `{ id?, type: \"prompt\", message: string, images?: ImageContent[], streamingBehavior?: \"steer\" | \"followUp\" }`\n- `{ id?, type: \"steer\", message: string, images?: ImageContent[] }`\n- `{ id?, type: \"follow_up\", message: string, images?: ImageContent[] }`\n- `{ id?, type: \"abort\" }`\n- `{ id?, type: \"abort_and_prompt\", message: string, images?: ImageContent[] }`\n- `{ id?, type: \"new_session\", parentSession?: string }`\n\n### State\n\n- `{ id?, type: \"get_state\" }`\n- `{ id?, type: \"set_todos\", phases: TodoPhase[] }`\n- `{ id?, type: \"set_host_tools\", tools: RpcHostToolDefinition[] }`\n\n### Model\n\n- `{ id?, type: \"set_model\", provider: string, modelId: string }`\n- `{ id?, type: \"cycle_model\" }`\n- `{ id?, type: \"get_available_models\" }`\n\n### Thinking\n\n- `{ id?, type: \"set_thinking_level\", level: ThinkingLevel }`\n- `{ id?, type: \"cycle_thinking_level\" }`\n\n### Queue modes\n\n- `{ id?, type: \"set_steering_mode\", mode: \"all\" | \"one-at-a-time\" }`\n- `{ id?, type: \"set_follow_up_mode\", mode: \"all\" | \"one-at-a-time\" }`\n- `{ id?, type: \"set_interrupt_mode\", mode: \"immediate\" | \"wait\" }`\n\n### Compaction\n\n- `{ id?, type: \"compact\", customInstructions?: string }`\n- `{ id?, type: \"set_auto_compaction\", enabled: boolean }`\n\n### Retry\n\n- `{ id?, type: \"set_auto_retry\", enabled: boolean }`\n- `{ id?, type: \"abort_retry\" }`\n\n### Bash\n\n- `{ id?, type: \"bash\", command: string }`\n- `{ id?, type: \"abort_bash\" }`\n\n### Session\n\n- `{ id?, type: \"get_session_stats\" }`\n- `{ id?, type: \"export_html\", outputPath?: string }`\n- `{ id?, type: \"switch_session\", sessionPath: string }`\n- `{ id?, type: \"branch\", entryId: string }`\n- `{ id?, type: \"get_branch_messages\" }`\n- `{ id?, type: \"get_last_assistant_text\" }`\n- `{ id?, type: \"set_session_name\", name: string }`\n\n### Messages\n\n- `{ id?, type: \"get_messages\" }`\n\n## Response Schema\n\nAll command results use `RpcResponse`:\n\n- Success: `{ id?, type: \"response\", command: <command>, success: true, data?: ... }`\n- Failure: `{ id?, type: \"response\", command: string, success: false, error: string }`\n\nData payloads are command-specific and defined in `rpc-types.ts`.\n\n### `get_state` payload\n\n```json\n{\n  \"model\": { \"provider\": \"...\", \"id\": \"...\" },\n  \"thinkingLevel\": \"off|minimal|low|medium|high|xhigh\",\n  \"isStreaming\": false,\n  \"isCompacting\": false,\n  \"steeringMode\": \"all|one-at-a-time\",\n  \"followUpMode\": \"all|one-at-a-time\",\n  \"interruptMode\": \"immediate|wait\",\n  \"sessionFile\": \"...\",\n  \"sessionId\": \"...\",\n  \"sessionName\": \"...\",\n  \"autoCompactionEnabled\": true,\n  \"messageCount\": 0,\n  \"queuedMessageCount\": 0,\n  \"todoPhases\": [\n    {\n      \"id\": \"phase-1\",\n      \"name\": \"Todos\",\n      \"tasks\": [\n        {\n          \"id\": \"task-1\",\n          \"content\": \"Map the tool surface\",\n          \"status\": \"in_progress\"\n        }\n      ]\n    }\n  ],\n  \"systemPrompt\": \"...\",\n  \"dumpTools\": [\n    {\n      \"name\": \"read\",\n      \"description\": \"Read files and URLs\",\n      \"parameters\": {}\n    }\n  ]\n}\n```\n\n### `set_todos` payload\n\nReplaces the in-memory todo state for the current session and returns the normalized phase list:\n\n```json\n{\n  \"id\": \"req_2\",\n  \"type\": \"set_todos\",\n  \"phases\": [\n    {\n      \"id\": \"phase-1\",\n      \"name\": \"Evaluation\",\n      \"tasks\": [\n        {\n          \"id\": \"task-1\",\n          \"content\": \"Map the read tool surface\",\n          \"status\": \"in_progress\"\n        },\n        {\n          \"id\": \"task-2\",\n          \"content\": \"Exercise edit operations\",\n          \"status\": \"pending\"\n        }\n      ]\n    }\n  ]\n}\n```\n\nThis is useful for hosts that want to pre-seed a plan before the first prompt.\n\n### `set_host_tools` payload\n\nReplaces the current set of host-owned tools that the RPC server may call back\ninto over stdio:\n\n```json\n{\n  \"id\": \"req_3\",\n  \"type\": \"set_host_tools\",\n  \"tools\": [\n    {\n      \"name\": \"echo_host\",\n      \"label\": \"Echo Host\",\n      \"description\": \"Echo a value from the embedding host\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"message\": { \"type\": \"string\" }\n        },\n        \"required\": [\"message\"],\n        \"additionalProperties\": false\n      }\n    }\n  ]\n}\n```\n\nThe response payload is:\n\n```json\n{\n  \"toolNames\": [\"echo_host\"]\n}\n```\n\nThese tools are added to the active session tool registry before the next model\ncall. Re-sending `set_host_tools` replaces the previous host-owned set.\n\n## Event Stream Schema\n\nRPC mode forwards `AgentSessionEvent` objects from `AgentSession.subscribe(...)`.\n\nCommon event types:\n\n- `agent_start`, `agent_end`\n- `turn_start`, `turn_end`\n- `message_start`, `message_update`, `message_end`\n- `tool_execution_start`, `tool_execution_update`, `tool_execution_end`\n- `auto_compaction_start`, `auto_compaction_end`\n- `auto_retry_start`, `auto_retry_end`\n- `ttsr_triggered`\n- `todo_reminder`\n- `todo_auto_clear`\n\nExtension runner errors are emitted separately as:\n\n```json\n{\n  \"type\": \"extension_error\",\n  \"extensionPath\": \"...\",\n  \"event\": \"...\",\n  \"error\": \"...\"\n}\n```\n\n`message_update` includes streaming deltas in `assistantMessageEvent` (text/thinking/toolcall deltas).\n\n## Prompt/Queue Concurrency and Ordering\n\nThis is the most important operational behavior.\n\n### Immediate ack vs completion\n\n`prompt` and `abort_and_prompt` are **acknowledged immediately**:\n\n```json\n{ \"id\": \"req_1\", \"type\": \"response\", \"command\": \"prompt\", \"success\": true }\n```\n\nThat means:\n\n- command acceptance != run completion\n- final completion is observed via `agent_end`\n\n### While streaming\n\n`AgentSession.prompt()` requires `streamingBehavior` during active streaming:\n\n- `\"steer\"` => queued steering message (interrupt path)\n- `\"followUp\"` => queued follow-up message (post-turn path)\n\nIf omitted during streaming, prompt fails.\n\n### Queue defaults\n\nFrom `packages/agent/src/agent.ts` defaults:\n\n- `steeringMode`: `\"one-at-a-time\"`\n- `followUpMode`: `\"one-at-a-time\"`\n- `interruptMode`: `\"immediate\"`\n\n### Mode semantics\n\n- `set_steering_mode` / `set_follow_up_mode`\n  - `\"one-at-a-time\"`: dequeue one queued message per turn\n  - `\"all\"`: dequeue entire queue at once\n- `set_interrupt_mode`\n  - `\"immediate\"`: tool execution checks steering between tool calls; pending steering can abort remaining tool calls in the turn\n  - `\"wait\"`: defer steering until turn completion\n\n## Extension UI Sub-Protocol\n\nExtensions in RPC mode use request/response UI frames.\n\n### Outbound request\n\n`RpcExtensionUIRequest` (`type: \"extension_ui_request\"`) methods:\n\n- `select`, `confirm`, `input`, `editor`, `cancel`\n- `notify`, `setStatus`, `setWidget`, `setTitle`, `set_editor_text`\n\nRuntime note:\n\n- Automatic session title generation is disabled in RPC mode, and `setTitle` UI\n  requests are also suppressed by default because most hosts do not have a\n  meaningful terminal-title surface. Set `PI_RPC_EMIT_TITLE=1` to opt back in to\n  the UI event only.\n\nExample:\n\n```json\n{\n  \"type\": \"extension_ui_request\",\n  \"id\": \"123\",\n  \"method\": \"confirm\",\n  \"title\": \"Confirm\",\n  \"message\": \"Continue?\",\n  \"timeout\": 30000\n}\n```\n\n### Inbound response\n\n`RpcExtensionUIResponse` (`type: \"extension_ui_response\"`):\n\n- `{ type: \"extension_ui_response\", id: string, value: string }`\n- `{ type: \"extension_ui_response\", id: string, confirmed: boolean }`\n- `{ type: \"extension_ui_response\", id: string, cancelled: true, timedOut?: boolean }`\n\nIf a dialog has a timeout, RPC mode resolves to a default value when timeout/abort fires.\n\n## Host Tool Sub-Protocol\n\nRPC hosts can expose custom tools to the agent by sending `set_host_tools`, then\nserving execution requests over the same transport.\n\n### Outbound request\n\nWhen the agent wants the host to execute one of those tools, RPC mode emits:\n\n```json\n{\n  \"type\": \"host_tool_call\",\n  \"id\": \"host_1\",\n  \"toolCallId\": \"toolu_123\",\n  \"toolName\": \"echo_host\",\n  \"arguments\": { \"message\": \"hello\" }\n}\n```\n\nIf the tool execution is later aborted, RPC mode emits:\n\n```json\n{\n  \"type\": \"host_tool_cancel\",\n  \"id\": \"host_cancel_1\",\n  \"targetId\": \"host_1\"\n}\n```\n\n### Inbound updates and completion\n\nHosts can optionally stream progress:\n\n```json\n{\n  \"type\": \"host_tool_update\",\n  \"id\": \"host_1\",\n  \"partialResult\": {\n    \"content\": [{ \"type\": \"text\", \"text\": \"working\" }]\n  }\n}\n```\n\nCompletion uses:\n\n```json\n{\n  \"type\": \"host_tool_result\",\n  \"id\": \"host_1\",\n  \"result\": {\n    \"content\": [{ \"type\": \"text\", \"text\": \"done\" }]\n  }\n}\n```\n\nSet top-level `isError: true` on `host_tool_result` to reject the pending host tool call and surface the returned text content as a tool error.\n\n## Error Model and Recoverability\n\n### Command-level failures\n\nFailures are `success: false` with string `error`.\n\n```json\n{\n  \"id\": \"req_2\",\n  \"type\": \"response\",\n  \"command\": \"set_model\",\n  \"success\": false,\n  \"error\": \"Model not found: provider/model\"\n}\n```\n\n### Recoverability expectations\n\n- Most command failures are recoverable; process remains alive.\n- Malformed JSONL / parse-loop exceptions emit a `parse` error response and continue reading subsequent lines.\n- Empty `set_session_name` is rejected (`Session name cannot be empty`).\n- Extension UI responses with unknown `id` are ignored.\n- Process termination conditions are stdin close or explicit extension-triggered shutdown after the current command.\n\n## Compact Command Flows\n\n### 1) Prompt and stream\n\nstdin:\n\n```json\n{ \"id\": \"req_1\", \"type\": \"prompt\", \"message\": \"Summarize this repo\" }\n```\n\nstdout sequence (typical):\n\n```json\n{ \"id\": \"req_1\", \"type\": \"response\", \"command\": \"prompt\", \"success\": true }\n{ \"type\": \"agent_start\" }\n{ \"type\": \"message_update\", \"assistantMessageEvent\": { \"type\": \"text_delta\", \"delta\": \"...\" }, \"message\": { \"role\": \"assistant\", \"content\": [] } }\n{ \"type\": \"agent_end\", \"messages\": [] }\n```\n\n### 2) Prompt during streaming with explicit queue policy\n\nstdin:\n\n```json\n{\n  \"id\": \"req_2\",\n  \"type\": \"prompt\",\n  \"message\": \"Also include risks\",\n  \"streamingBehavior\": \"followUp\"\n}\n```\n\n### 3) Inspect and tune queue behavior\n\nstdin:\n\n```json\n{ \"id\": \"q1\", \"type\": \"get_state\" }\n{ \"id\": \"q2\", \"type\": \"set_steering_mode\", \"mode\": \"all\" }\n{ \"id\": \"q3\", \"type\": \"set_interrupt_mode\", \"mode\": \"wait\" }\n```\n\n### 4) Extension UI round trip\n\nstdout:\n\n```json\n{\n  \"type\": \"extension_ui_request\",\n  \"id\": \"ui_7\",\n  \"method\": \"input\",\n  \"title\": \"Branch name\",\n  \"placeholder\": \"feature/...\"\n}\n```\n\nstdin:\n\n```json\n{ \"type\": \"extension_ui_response\", \"id\": \"ui_7\", \"value\": \"feature/rpc-host\" }\n```\n\n## Notes on `RpcClient` helper\n\n`src/modes/rpc/rpc-client.ts` is a convenience wrapper, not the protocol definition.\n\nCurrent helper characteristics:\n\n- Spawns `bun <cliPath> --mode rpc`\n- Correlates responses by generated `req_<n>` ids\n- Dispatches only recognized `AgentEvent` types to listeners\n- Supports host-owned custom tools via `setCustomTools()` and automatic handling of `host_tool_call` / `host_tool_cancel`\n- Does **not** expose helper methods for every protocol command (for example, `set_interrupt_mode` and `set_session_name` are in protocol types but not wrapped as dedicated methods)\n\nUse raw protocol frames if you need complete surface coverage.\n",
@@ -67,7 +67,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"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 TypeBox 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/coding-agent/src/prompts/tools/hashline.md`\n- Key collaborators:\n  - `packages/coding-agent/src/utils/edit-mode.ts` — selects active edit mode\n  - `packages/coding-agent/src/hashline/grammar.lark` — custom-tool grammar for hashline mode\n  - `packages/coding-agent/src/hashline/input.ts` — splits `@PATH` sections\n  - `packages/coding-agent/src/hashline/parser.ts` — parses ops and payload lines\n  - `packages/coding-agent/src/hashline/apply.ts` — validates anchors and applies edits\n  - `packages/coding-agent/src/hashline/anchors.ts` — stale-anchor mismatch formatting\n  - `packages/coding-agent/src/hashline/recovery.ts` — cache-based stale-anchor recovery\n  - `packages/coding-agent/src/hashline/hash.ts` — computes `LINEhh|` anchors shared with `read`/`search`\n  - `packages/coding-agent/src/edit/file-read-cache.ts` — per-session read snapshot cache\n  - `packages/coding-agent/src/tools/read.ts` — emits anchored lines and records read snapshots\n  - `packages/coding-agent/src/tools/search.ts` — records sparse snapshots from matches/context\n  - `packages/coding-agent/src/tools/fs-cache-invalidation.ts` — invalidates FS scan caches after writes\n  - `packages/coding-agent/src/edit/streaming.ts` — computes in-flight diff previews for the TUI\n\n## Inputs\n\n### Hashline mode (default)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `input` | `string` | Yes | One or more edit sections. First non-blank line must be `@PATH` unless the caller supplies the legacy fallback `path` outside the model schema and the body already looks like hashline ops (`packages/coding-agent/src/hashline/input.ts`). Optional `*** Begin Patch` / `*** End Patch` envelope is ignored if present. |\n\nPatch language inside `input`:\n\n- Section header: `@PATH`\n- Insert after: `+ ANCHOR`\n- Insert before: `< ANCHOR`\n- Delete range: `- A..B`\n- Replace range: `= A..B`\n- Payload line: `~TEXT` by default; separator is `HL_EDIT_SEP` and can be overridden once at process start by `PI_HL_SEP` (`packages/coding-agent/src/hashline/hash.ts`)\n- Special anchors: `BOF`, `EOF`\n- Anchor token: `<line><2-char-hash>`, for example `41th`\n\nAnchors come from `read`/`search` output. `read` formats lines as `LINEhh|TEXT` via `formatHashLine` / `formatHashLines` in `packages/coding-agent/src/hashline/hash.ts`; copy only the token left of `|` into op lines.\n\nOther edit modes exist (`replace`, `patch`, `vim`, `apply_patch`) and are selected outside the tool payload by `resolveEditMode()` in `packages/coding-agent/src/utils/edit-mode.ts`. Their schemas are different; this document covers the default hashline mode.\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/coding-agent/src/hashline/diff-preview.ts`, or\n  - `Updated <path>` / `Created <path>` when no compact preview text is emitted.\n- Parse 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- While the model is still typing arguments, the TUI can compute a diff preview with `packages/coding-agent/src/edit/streaming.ts`; that preview is not a deferred action and does not block execution.\n\n## Flow\n1. `EditTool.execute()` in `packages/coding-agent/src/edit/index.ts` resolves the active mode. Default is `hashline`; `customFormat` exposes `packages/coding-agent/src/hashline/grammar.lark` with `$HFMT$` / `$HSEP$` placeholders filled from `packages/coding-agent/src/hashline/hash.ts`.\n2. `executeHashlineSingle()` in `packages/coding-agent/src/hashline/execute.ts` splits the raw `input` into `@PATH` sections with `splitHashlineInputs()`.\n3. If multiple sections target the same path, `mergeSamePathSections()` concatenates them before execution so every op still refers to the original file snapshot.\n4. Multi-section calls run a preflight pass (`preflightHashlineSection()`): parse ops, enforce plan-mode write rules, load the current file, reject anchor-scoped edits against missing files, reject auto-generated files, apply edits in memory, and fail if the result is a no-op. This prevents partial batches.\n5. `parseHashlineWithWarnings()` in `packages/coding-agent/src/hashline/parser.ts` tokenizes the diff body:\n   - ignores blank lines and optional `*** Begin Patch`\n   - stops at `*** End Patch`\n   - stops at `*** Abort` and emits `ABORT_WARNING`\n   - turns `+` / `<` payload runs into one `insert` edit per payload line\n   - turns `- A..B` into one `delete` edit per line in the range\n   - turns `= A..B` into inserts before `A`, then deletes for `A..B`; no payload means replace with a single empty line\n6. `applyHashlineEdits()` in `packages/coding-agent/src/hashline/apply.ts` validates every referenced anchor before mutating anything. Each anchor hash is recomputed from current file content with `computeLineHash()`.\n7. If any anchor hash differs, `applyHashlineEdits()` throws `HashlineMismatchError`. `execute.ts` catches only that class and calls `tryRecoverHashlineWithCache()`.\n8. Recovery replays the edits against the most recent cached read/search snapshot for that path (`packages/coding-agent/src/edit/file-read-cache.ts`), then 3-way merges the result onto current disk content using `Diff.applyPatch(..., { fuzzFactor: 3 })` in `packages/coding-agent/src/hashline/recovery.ts`. On success the edit proceeds with a warning; on failure the original mismatch error is re-thrown.\n9. Before splicing lines, `absorbReplacementBoundaryDuplicates()` normalizes some malformed-but-recoverable ranges:\n   - duplicate prefix/suffix lines adjacent to a replacement can be absorbed by widening the delete range\n   - pure inserts can auto-drop duplicated leading/trailing payload lines when `edit.hashlineAutoDropPureInsertDuplicates` is enabled\n   - all such fixes append warnings\n10. `after_anchor` inserts are normalized to `before_anchor` of the next line, or `EOF` if the anchor was the last line.\n11. Anchor-targeted edits are bucketed by target line and applied bottom-up so earlier splices do not invalidate later original line numbers. `BOF` and `EOF` inserts are applied after that.\n12. The edited text is restored to the original BOM and line ending style with helpers from `packages/coding-agent/src/edit/normalize.ts` and persisted via `serializeEditFileText()` in `packages/coding-agent/src/edit/read-file.ts`.\n13. The writethrough callback from `createLspWritethrough()` may format the file and fetch diagnostics. Late diagnostics are queued back into session state as a hidden deferred message by `EditTool.#injectLateDiagnostics()` in `packages/coding-agent/src/edit/index.ts`.\n14. `invalidateFsScanAfterWrite()` calls `invalidateFsScanCache(path)` so filesystem-backed tools do not serve stale scan results.\n15. The session file-read cache is refreshed with the post-edit file text via `recordContiguous()`, making the just-written content the new recovery base for subsequent stale-anchor merges.\n16. The final response is built from a unified diff (`generateDiffString()`), a compact preview, and any accumulated warnings.\n\n## Modes / Variants\n- `hashline` — default mode; line-anchored patch language described here (`packages/coding-agent/src/utils/edit-mode.ts`).\n- `replace` — exact/fuzzy old/new text replacement (`packages/coding-agent/src/edit/modes/replace.ts`).\n- `patch` — structured JSON diff-hunk mode (`packages/coding-agent/src/edit/modes/patch.ts`).\n- `apply_patch` — freeform Codex-style `*** Begin Patch` envelope, internally expanded into patch-mode entries (`packages/coding-agent/src/edit/modes/apply-patch.ts`).\n- `vim` — persistent modal editing buffer (`packages/coding-agent/src/tools/vim.ts`).\n\nHashline op examples:\n\n```text\n@src/a.ts\n+ 4fb\n~const added = true;\n```\n\n```text\n@src/a.ts\n< 4fb\n~const addedBefore = true;\n```\n\n```text\n@src/a.ts\n- 4fb..6qx\n```\n\n```text\n@src/a.ts\n= 4fb..5dm\n~const clean = (name || DEF).trim();\n~return clean.length === 0 ? DEF : clean.toUpperCase();\n```\n\nBOF/EOF examples:\n\n```text\n@src/a.ts\n+ BOF\n~const HEADER = true;\n```\n\n```text\n@src/a.ts\n+ EOF\n~export const done = true;\n```\n\n## Side Effects\n- Filesystem\n  - Reads target files with `readEditFileText()`.\n  - Writes full updated file contents with `serializeEditFileText()`.\n  - Preserves BOM and original line-ending style.\n- Subprocesses / native bindings\n  - `createLspWritethrough()` may trigger formatter / diagnostics work through the LSP subsystem.\n  - `invalidateFsScanAfterWrite()` calls native `invalidateFsScanCache()` from `@oh-my-pi/pi-natives`.\n- Session state\n  - Reads and updates the per-session `FileReadCache` used for stale-anchor recovery.\n  - Stores pending deferred-diagnostics abort controllers per path inside `EditTool`.\n  - Queues late diagnostics back into the session transcript as a hidden custom message.\n- Background work / cancellation\n  - A new edit to the same path aborts the prior deferred diagnostics fetch for that path (`packages/coding-agent/src/edit/index.ts`).\n  - The tool itself is marked `nonAbortable = true` and `concurrency = \"exclusive\"` in `packages/coding-agent/src/edit/index.ts`.\n\n## Limits & Caps\n- Default mode is `hashline` (`DEFAULT_EDIT_MODE`) in `packages/coding-agent/src/utils/edit-mode.ts`.\n- Anchor hashes are always 2 lowercase letters from a stable 647-entry bigram table (`HL_BIGRAMS_COUNT`) in `packages/coding-agent/src/hashline/hash.ts`.\n- The visible mismatch report shows 2 lines of context on each side (`MISMATCH_CONTEXT`) in `packages/coding-agent/src/hashline/constants.ts`.\n- Stale-anchor recovery uses `fuzzFactor: 3` (`HASHLINE_RECOVERY_FUZZ_FACTOR`) in `packages/coding-agent/src/hashline/recovery.ts`.\n- The per-session read cache keeps at most 30 paths (`MAX_PATHS_PER_SESSION`) in `packages/coding-agent/src/edit/file-read-cache.ts`.\n- Hashline streaming chunk defaults are 200 lines or 64 KiB per chunk (`packages/coding-agent/src/hashline/types.ts`, consumed by `packages/coding-agent/src/hashline/stream.ts`).\n- `HL_EDIT_SEP` defaults to `~`; `HL_BODY_SEP` is always `|` (`packages/coding-agent/src/hashline/hash.ts`).\n\n## Errors\n- Missing section header:\n  - `input must begin with \"@PATH\" on the first non-blank line; got: ... Example: \"@src/foo.ts\" then edit ops.`\n- Empty header:\n  - `Input header \"@\" is empty; provide a file path.`\n- Bad anchor token:\n  - `line N: expected a full anchor such as \"119sr\"; got \"...\".`\n- Bad range syntax:\n  - `line N: explicit ranges are required for delete/replace...`\n  - `line N: range must include exactly two full anchors separated by \"..\".`\n  - `line N: range A..B ends before it starts.`\n  - `line N: range A..B uses two different hashes for the same line.`\n- Missing payload for `+` / `<`:\n  - `line N: + and < operations require at least one ~TEXT payload line.`\n- Stray payload line:\n  - `line N: payload line has no preceding +, <, or = operation.`\n- Unknown op:\n  - `line N: unrecognized op. Use < ANCHOR..., + ANCHOR..., - A..B..., = A..B...`\n- Missing file for anchor-scoped edits:\n  - `File not found: <path>`\n- Out-of-range anchor:\n  - `Line N does not exist (file has M lines)`\n- Stale anchors throw `HashlineMismatchError`. The error message contains re-read guidance and reprints nearby current file lines as `LINEhh|TEXT`; mismatched lines are marked `*`. `displayMessage` renders the same information in a code-frame style.\n- No-op edit:\n  - `Edits to <path> resulted in no changes being made.`\n- Recovery failure is silent internally: if cache-based merge cannot prove a valid result, the original mismatch error is surfaced unchanged.\n\n## Notes\n- `read` and `search` are the authoritative source of anchors. The edit parser does not want the trailing `|TEXT`; copy only the `LINEhh` token.\n- Multi-op patches are parsed against the original file snapshot. Do not renumber later anchors after earlier ops; `applyHashlineEdits()` buckets and applies them bottom-up.\n- `= A..B` is not a primitive replace in the parser. It expands to inserts before `A` plus deletes for `A..B`, which is why stale-anchor checking still happens on the original range lines.\n- Interior lines of a multi-line range use hash `**` (`RANGE_INTERIOR_HASH`) and are not individually verified; only the first and last anchor hashes are checked.\n- `computeLineHash()` trims trailing whitespace before hashing. Anchors survive line-ending changes and trailing-space-only changes, but not substantive line edits.\n- For punctuation-only lines, the hash mixes in the line number; identical `}` lines on different lines intentionally get different anchors.\n- `splitHashlineInputs()` normalizes absolute `@PATH` headers back to a cwd-relative path when the file is inside the current working tree.\n- Optional `*** Begin Patch` / `*** End Patch` markers are accepted in hashline mode, but the file sections are still `@PATH`-based, not Codex `*** Update File:` hunks.\n- `*** Abort` terminates parsing early and returns `ABORT_WARNING`; ops parsed before the marker still apply.\n- File-read cache invalidation is conflict-based, not write-through invalidation. If `read` later records content for a line that disagrees with the cached snapshot, the entire snapshot for that path is replaced with the newly observed lines (`packages/coding-agent/src/edit/file-read-cache.ts`).\n- There is no resolve-style apply/discard phase for hashline edits. The only preview path is the transient TUI diff preview in `packages/coding-agent/src/edit/streaming.ts`.\n",
-	"tools/eval.md": "# eval\n\n> Execute Python or JavaScript code in persistent cell-based runtimes.\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/parse.ts` — lenient cell parser\n  - `packages/coding-agent/src/eval/sniff.ts` — language sniffing heuristics\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\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `input` | `string` | Yes | Cell program text. Parsed by `parseEvalInput()` in `packages/coding-agent/src/eval/parse.ts`, not by JSON subfields. |\n\n`input` syntax accepted at runtime:\n\n- Cell header: `*** Begin <LANG>`; parser accepts `PY`, `PYTHON`, `IPY`, `IPYTHON`, `JS`, `JAVASCRIPT`, `TS`, `TYPESCRIPT` case-insensitively.\n- Optional attributes immediately after the header, first occurrence wins:\n  - `*** Title: ...`\n  - `*** Timeout: <n>[ms|s|m]` (default 30s)\n  - `*** Reset`\n- Cell body: every following line until `*** End ...`, the next `*** Begin ...`, or `*** Abort`.\n\nLeniencies in `packages/coding-agent/src/eval/parse.ts`:\n\n- Markers accept two or more leading `*` and flexible whitespace.\n- `*** End` does not need to repeat the language token.\n- Missing end markers between adjacent cells are tolerated; the next `*** Begin` closes the prior cell.\n- Bare code or a single markdown fence such as ```` ```py ```` is treated as one implicit cell.\n- If `*** Abort` appears, the in-progress cell is dropped and the result carries an abort warning.\n\nThe tool also exposes a custom Lark grammar from `packages/coding-agent/src/eval/eval.lark` for constrained sampling. That grammar is stricter than the runtime parser: it only advertises `PY` / `JS` / `TS` headers and an `*** End Cell` closer.\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\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 parsed code cells with syntax highlighting\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 / fallback / 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` parses `params.input` with `parseEvalInput()`.\n2. `parseEvalInput()` normalizes newlines, collects cells, parses attributes, and assigns each cell a language from the header, language sniffing, or the default `python`.\n3. Back in `execute()`, each parsed cell is resolved to a backend with `resolveBackend()`:\n   - explicit `python`/`js` requests are validated against session settings and backend availability\n   - otherwise `sniffEvalLanguage()` in `packages/coding-agent/src/eval/sniff.ts` tries shebangs and language markers\n   - if no explicit language was present, later cells prefer the previous runtime language before re-sniffing\n   - Python is preferred when available; JS is the fallback when Python is unavailable or disabled\n4. 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.\n5. Cells execute sequentially. For each cell, `execute()`:\n   - clamps the cell timeout 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`, 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### Parsing modes\n\n- Explicit multi-cell format with `*** Begin ...` / `*** End ...`\n- Implicit single-cell fallback for bare code or a single fenced block\n- Abort-recovery parse path when `*** Abort` is present\n\n### Backend selection\n\n- Explicit Python backend\n- Explicit JavaScript backend\n- Auto-detected backend via `sniffEvalLanguage()`\n- Fallback from requested/inferred Python to JS when Python is unavailable\n- Fallback notice when JS markers are seen but `eval.js` is disabled and Python is used instead\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 `vm.Context` instances keyed by `js:${sessionId}` in `vmContexts`\n- `*** Reset` calls `resetVmContext(sessionKey)` before the cell executes\n- Top-level `await` and bare `return` are supported by wrapping code in an async IIFE when `wrapCode()` sees `await` or `return`\n- Top-level static `import ... from ...` is rewritten to `await import(...)` by `rewriteStaticImports()`\n- The prelude installs globals:\n  - `display`, `print`\n  - `read`, `write`, `append`, `sort`, `uniq`, `counter`, `diff`, `tree`, `env`, `output`\n  - `tool.<name>(args)` proxy for arbitrary session tool calls\n- JS helpers are async because they cross the VM/tool boundary\n- `display(value)` behavior:\n  - plain objects/arrays become JSON outputs\n  - `{ type: \"image\", data, mimeType }` becomes an image output\n  - scalars become text\n- The VM exposes a restricted `process` subset plus `Buffer`, `fetch`, `Blob`, `File`, `Headers`, `Request`, `Response`, `fs`, `require`, and browser-style globals\n- Per-session VM runs are serialized with `runQueued()`\n\n### Python runtime\n\nImplemented in `packages/coding-agent/src/eval/py/executor.ts`, `packages/coding-agent/src/eval/py/kernel.ts`, and `packages/coding-agent/src/eval/py/prelude.py`. See `docs/python-repl.md` for gateway and kernel details.\n\n- Default mode is retained `session` kernels keyed by `python:${sessionId}`\n- Optional `python.kernelMode = \"per-call\"` creates a fresh kernel for each cell and shuts it down afterward\n- `*** Reset` 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 inside IPython/Jupyter, so top-level `await` works; the prompt warns not to use `asyncio.run(...)`\n- The Python prelude defines synchronous helpers with the same surface as JS (except `tool.<name>` exists only in JS)\n- `display(value)` wraps dict/list/tuple values in `IPython.display.JSON`; rich display MIME bundles are preserved\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### Multi-language call behavior\n\nA single tool call can mix Python and JS cells. Persistence is per language runtime:\n\n- resetting Python does not touch JS state\n- resetting JS 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 talks to a Jupyter kernel gateway over HTTP and WebSocket.\n  - External gateway mode uses `PI_PYTHON_GATEWAY_URL` and optional `PI_PYTHON_GATEWAY_TOKEN`.\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 may start or connect to a kernel gateway; details are 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?.()` and `session.getEvalKernelOwnerId?.()` influence kernel reuse and artifact lookup.\n  - JS VM contexts persist in `vmContexts` across eval calls until reset/disposal.\n  - Python retained kernels persist in `kernelSessions` until reset, eviction, idle cleanup, or owner cleanup.\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 interrupts a running Python kernel and aborts JS promise waits.\n\n## Limits & Caps\n\n- Per-cell timeout default: 30s (`DEFAULT_TIMEOUT_MS` in `packages/coding-agent/src/eval/parse.ts`; `TOOL_TIMEOUTS.eval.default` in `packages/coding-agent/src/tools/tool-timeouts.ts`)\n- Timeout clamp: 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- Parse errors from `parseEvalInput()` throw immediately, for example invalid timeout strings.\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`\n  - `eval.js = false`\n  - Python kernel unavailable\n  - no backend available\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 parsing encountered `*** Abort`, the final text appends `ABORT_WARNING`, explicitly telling the model that earlier cells ran and state persists.\n- If output truncates, the tool still succeeds; truncation is surfaced through `details.meta` and artifact-backed full output when available.\n\n## Notes\n\n- The runtime parser is intentionally more permissive than `packages/coding-agent/src/eval/eval.lark`; maintain both when changing syntax.\n- Cell language in `ParsedEvalCell` is not the last word: `EvalTool.execute()` may override backend selection for cells without an explicit header by inheriting the previous runtime language.\n- `tool.<name>()` exists only in JS. Python prelude helpers do not call back into the full tool registry.\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\"`, so eval calls do not overlap within a session.\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/eval.md": "# eval\n\n> Execute Python or JavaScript code in persistent cell-based runtimes.\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/parse.ts` — lenient cell parser\n  - `packages/coding-agent/src/eval/sniff.ts` — language sniffing heuristics\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\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `input` | `string` | Yes | Cell program text. Parsed by `parseEvalInput()` in `packages/coding-agent/src/eval/parse.ts`, not by JSON subfields. |\n\n`input` syntax accepted at runtime:\n\n- Cell header: `*** Cell <attrs...>`. Attributes are space-separated tokens with quoted titles (`\"...\"` or `'...'`).\n- Canonical tokens (advertised in the prompt):\n  - `<lang>:\"<title>\"` — language + title shorthand. `lang` is `py` or `js` (lenient: also `ts`, plus the long-form aliases `python`, `javascript`, `typescript`, `ipy`, `ipython`).\n  - `t:<n>[ms|s|m]` — per-cell timeout (default 30s).\n  - `rst` — wipe this cell's language kernel before running.\n- Lenient additional tokens (accepted by the parser, not advertised):\n  - bare language token (`py`, `js`)\n  - `id:\"...\"` / `title:\"...\"` / `name:\"...\"` / `cell:\"...\"` / `file:\"...\"` / `label:\"...\"` — title aliases\n  - `timeout:` / `duration:` / `time:` — `t:` aliases\n  - `reset` — `rst` alias\n  - `rst:true|false|1|0|yes|no|on|off` — explicit boolean form\n  - a bare positional duration token (`30s`, `2m`, `500ms`)\n  - any unclassified bare token folds into a positional title fragment\n- Cell body: every following line until the next `*** Cell ...`, the optional `*** End`, or `*** Abort`. `*** End` is a quirk fix for GPT-trained models that emit terminators and is not documented in the prompt.\n\nLeniencies in `packages/coding-agent/src/eval/parse.ts`:\n\n- Markers accept two or more leading `*` and flexible whitespace.\n- `*** End` is optional everywhere; the parser silently consumes trailing tokens (e.g. `*** End py`).\n- Missing terminators between adjacent cells are tolerated; the next `*** Cell` closes the prior cell, and stray non-marker lines between cells fold into the prior cell's body without crashing.\n- Bare code or a single markdown fence such as ```` ```py ```` is treated as one implicit cell.\n- If `*** Abort` appears, the in-progress cell is dropped and the result carries an abort warning. To preserve a completed cell before `*** Abort`, emit `*** End` first.\n\nThe tool also exposes a custom Lark grammar from `packages/coding-agent/src/eval/eval.lark` for constrained sampling. That grammar is stricter than the runtime parser: it requires the canonical `*** Cell <lang>:\"title\"` header form with a fixed attribute order, advertises only `py` / `js`, and pins the trailing `*** End` so GPT-trained models' natural terminator habit aligns with the constrained output.\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\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 parsed code cells with syntax highlighting\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 / fallback / 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` parses `params.input` with `parseEvalInput()`.\n2. `parseEvalInput()` normalizes newlines, collects cells, parses attributes, and assigns each cell a language from the header, language sniffing, or the default `python`.\n3. Back in `execute()`, each parsed cell is resolved to a backend with `resolveBackend()`:\n   - explicit `python`/`js` requests are validated against session settings and backend availability\n   - otherwise `sniffEvalLanguage()` in `packages/coding-agent/src/eval/sniff.ts` tries shebangs and language markers\n   - if no explicit language was present, later cells prefer the previous runtime language before re-sniffing\n   - Python is preferred when available; JS is the fallback when Python is unavailable or disabled\n4. 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.\n5. Cells execute sequentially. For each cell, `execute()`:\n   - clamps the cell timeout 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`, 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### Parsing modes\n\n- Explicit multi-cell format with `*** Cell ...` headers\n- Implicit single-cell fallback for bare code or a single fenced block\n- Abort-recovery parse path when `*** Abort` is present\n\n### Backend selection\n\n- Explicit Python backend\n- Explicit JavaScript backend\n- Auto-detected backend via `sniffEvalLanguage()`\n- Fallback from requested/inferred Python to JS when Python is unavailable\n- Fallback notice when JS markers are seen but `eval.js` is disabled and Python is used instead\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 `vm.Context` instances keyed by `js:${sessionId}` in `vmContexts`\n- `rst` calls `resetVmContext(sessionKey)` before the cell executes\n- Top-level `await` and bare `return` are supported by wrapping code in an async IIFE when `wrapCode()` sees `await` or `return`\n- Top-level static `import ... from ...` is rewritten to `await import(...)` by `rewriteStaticImports()`\n- The prelude installs globals:\n  - `display`, `print`\n  - `read`, `write`, `append`, `sort`, `uniq`, `counter`, `diff`, `tree`, `env`, `output`\n  - `tool.<name>(args)` proxy for arbitrary session tool calls\n- JS helpers are async because they cross the VM/tool boundary\n- `display(value)` behavior:\n  - plain objects/arrays become JSON outputs\n  - `{ type: \"image\", data, mimeType }` becomes an image output\n  - scalars become text\n- The VM exposes a restricted `process` subset plus `Buffer`, `fetch`, `Blob`, `File`, `Headers`, `Request`, `Response`, `fs`, `require`, and browser-style globals\n- Per-session VM runs are serialized with `runQueued()`\n\n### Python runtime\n\nImplemented in `packages/coding-agent/src/eval/py/executor.ts`, `packages/coding-agent/src/eval/py/kernel.ts`, and `packages/coding-agent/src/eval/py/prelude.py`. See `docs/python-repl.md` for gateway and kernel details.\n\n- Default mode is retained `session` kernels keyed by `python:${sessionId}`\n- Optional `python.kernelMode = \"per-call\"` creates a fresh kernel for each cell and shuts it down afterward\n- `rst` 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 inside IPython/Jupyter, so top-level `await` works; the prompt warns not to use `asyncio.run(...)`\n- The Python prelude defines synchronous helpers with the same surface as JS (except `tool.<name>` exists only in JS)\n- `display(value)` wraps dict/list/tuple values in `IPython.display.JSON`; rich display MIME bundles are preserved\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### Multi-language call behavior\n\nA single tool call can mix Python and JS cells. Persistence is per language runtime:\n\n- resetting Python does not touch JS state\n- resetting JS 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?.()` and `session.getEvalKernelOwnerId?.()` influence kernel reuse and artifact lookup.\n  - JS VM contexts persist in `vmContexts` across eval calls until reset/disposal.\n  - Python retained kernels persist in `kernelSessions` until reset, eviction, idle cleanup, or owner cleanup.\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 interrupts a running Python kernel and aborts JS promise waits.\n\n## Limits & Caps\n\n- Per-cell timeout default: 30s (`DEFAULT_TIMEOUT_MS` in `packages/coding-agent/src/eval/parse.ts`; `TOOL_TIMEOUTS.eval.default` in `packages/coding-agent/src/tools/tool-timeouts.ts`)\n- Timeout clamp: 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- Parse errors from `parseEvalInput()` throw immediately, for example invalid timeout strings.\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`\n  - `eval.js = false`\n  - Python kernel unavailable\n  - no backend available\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 parsing encountered `*** Abort`, the final text appends `ABORT_WARNING`, explicitly telling the model that earlier cells ran and state persists.\n- If output truncates, the tool still succeeds; truncation is surfaced through `details.meta` and artifact-backed full output when available.\n\n## Notes\n\n- The runtime parser is intentionally more permissive than `packages/coding-agent/src/eval/eval.lark`; maintain both when changing syntax.\n- Cell language in `ParsedEvalCell` is not the last word: `EvalTool.execute()` may override backend selection for cells without an explicit header by inheriting the previous runtime language.\n- `tool.<name>()` exists only in JS. Python prelude helpers do not call back into the full tool registry.\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\"`, so eval calls do not overlap within a session.\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/exit_plan_mode.md": "# exit_plan_mode\n\n> Submits the current plan-mode plan for user approval.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/exit-plan-mode.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/exit-plan-mode.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/plan-mode-guard.ts` — resolves canonical plan paths during plan mode\n  - `packages/coding-agent/src/plan-mode/approved-plan.ts` — renames approved plan artifact after user approval\n  - `packages/coding-agent/src/modes/interactive-mode.ts` — approval popup, plan preview, mode exit, tool restoration\n  - `packages/coding-agent/src/plan-mode/state.ts` — plan-mode state shape\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `title` | `string` | Yes | Final plan title. `.md` is optional; the runtime normalizes to `local://<title>.md`. Allowed characters: letters, numbers, `_`, `-`. |\n\n## Outputs\n- Single-shot success result with `content[0].text = \"Plan ready for approval.\"`.\n- `details` contains:\n  - `planFilePath` — current plan artifact path from plan-mode state, typically `local://PLAN.md`\n  - `planExists` — whether that file existed at call time\n  - `title` — normalized title without `.md`\n  - `finalPlanFilePath` — normalized destination, always `local://<title>.md`\n- The actual rename and mode transition happen later in the interactive controller after the user chooses an approval action.\n\n## Flow\n1. `execute()` reads `session.getPlanModeState()` and rejects the call unless `state.enabled` is true.\n2. `normalizePlanTitle()` trims whitespace, rejects empty values, rejects `/`, `\\\\`, and `..`, appends `.md` if missing, and enforces `^[A-Za-z0-9_-]+\\.md$`.\n3. The tool computes `finalPlanFilePath = local://<normalized>.md` and resolves both source and destination through `resolvePlanPath(...)` to validate them against plan-mode path rules.\n4. It `stat`s the current plan file path; if the plan artifact does not exist it throws a `ToolError` telling the caller to write the finalized plan first.\n5. On success it returns the approval-ready payload; it does not mutate files itself.\n6. `packages/coding-agent/src/modes/controllers/event-controller.ts` watches successful `exit_plan_mode` results and forwards `details` to `InteractiveMode.handleExitPlanModeTool(...)`.\n7. The interactive controller aborts the agent, renders the current plan, and shows four choices: `Approve and execute`, `Approve and keep context`, `Refine plan`, `Stay in plan mode`.\n8. If the user approves, `#approvePlan(...)` renames `local://PLAN.md` to `local://<title>.md`, exits plan mode, restores the previous tool set, optionally clears session context, writes the approved plan into the new local root when context is reset, and injects a synthetic system prompt instructing execution from the finalized artifact.\n\n## Side Effects\n- Filesystem\n  - Tool itself only `stat`s the current plan file.\n  - Approval path later renames the plan artifact via `fs.rename(...)` and may rewrite the approved plan into a fresh local root with `Bun.write(...)`.\n- Session state\n  - Requires active plan-mode state.\n  - Approval flow aborts the current agent loop, exits plan mode, restores previous active tools, clears or preserves context depending on the user choice, and records the approved plan reference path.\n- User-visible prompts / interactive UI\n  - Successful calls trigger a plan preview and an approval/refinement selector in interactive mode.\n- Background work / cancellation\n  - The controller aborts the running agent before showing the popup to prevent repeated `exit_plan_mode` calls.\n\n## Limits & Caps\n- `title` accepts only `[A-Za-z0-9_-]` plus optional `.md` (`packages/coding-agent/src/tools/exit-plan-mode.ts`).\n- Destination must be under the `local:` scheme; approval rename rejects non-`local:` source or destination paths (`packages/coding-agent/src/plan-mode/approved-plan.ts`).\n- In plan mode, only the plan file may be edited; other writes are blocked by `enforcePlanModeWrite(...)` in `packages/coding-agent/src/tools/plan-mode-guard.ts`.\n\n## Errors\n- Plan mode inactive: throws `ToolError(\"Plan mode is not active.\")`.\n- Empty title: throws `ToolError(\"Title is required and must not be empty.\")`.\n- Path traversal / separators: throws `ToolError(\"Title must not contain path separators or '..'.\")`.\n- Invalid characters: throws `ToolError(\"Title may only contain letters, numbers, underscores, or hyphens.\")`.\n- Missing plan artifact: throws `ToolError(\"Plan file not found at ... Write the finalized plan ... before calling exit_plan_mode.\")`.\n- Approval-time failures surface in the UI from `InteractiveMode.handleExitPlanModeTool(...)`, including destination already exists and rename failures from `renameApprovedPlanFile(...)`.\n\n## Notes\n- This tool is hidden/internal: it is injected when `plan.enabled` is on and is not part of normal discoverable built-ins (`packages/coding-agent/src/tools/index.ts`, `packages/coding-agent/src/session/agent-session.ts`).\n- The tool returning success does not mean plan mode has ended; it only means the request was handed off to the approval UI.\n- `resolvePlanPath(...)` special-cases bare filenames matching the plan basename so `PLAN.md` maps back to the canonical session-scoped `local://PLAN.md` artifact.\n- `Approve and keep context` skips the full conversation reset; `Approve and execute` clears context, then copies the approved plan into the new session-local artifact root before execution resumes.\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\" \\| \"issue_view\" \\| \"pr_create\" \\| \"pr_view\" \\| \"pr_diff\" \\| \"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. 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| `issue` | `string` | No | Used only by `issue_view`. Required there; accepts an issue number or GitHub issue URL. |\n| `pr` | `string \\| string[]` | No | Used by `pr_view`, `pr_diff`, `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| `comments` | `boolean` | No | Used by `issue_view` and `pr_view`. Defaults to `true`. |\n| `nameOnly` | `boolean` | No | Used only by `pr_diff`; adds `--name-only`. |\n| `exclude` | `string[]` | No | Used only by `pr_diff`; each entry becomes `--exclude <pattern>`. Empty strings are rejected. |\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/issue/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`, `issue_view`, `pr_view`, `search_*`) fetch JSON and format Markdown-like text summaries.\n6. `pr_view` optionally makes an extra REST call to `/repos/<repo>/pulls/<n>/comments` so inline review comments are included; this is separate from `gh pr view --json`.\n7. `pr_diff` fetches raw text from `gh pr diff`; multi-PR batches are handled with `Promise.all()`.\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 with `gh pr view` 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\n### `issue_view`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `issue` |\n| Optional fields | `repo`, `comments` |\n| `gh` command | `gh issue view <issue> [--repo <repo>] --json <GH_ISSUE_FIELDS or GH_ISSUE_FIELDS_NO_COMMENTS>` |\n| Batching | None |\n| Output | Single issue summary with metadata, `## Body`, and optional `## Comments`. `sourceUrl = data.url`. |\n\n`comments: false` switches the requested JSON field set and suppresses comment rendering.\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_view`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `pr`, `comments` |\n| `gh` command | For each requested PR: `gh pr view [<pr>] [--repo <repo>] --json <GH_PR_FIELDS or GH_PR_FIELDS_NO_COMMENTS>` |\n| Batching | Yes. `pr` may be `string[]`; each entry is fetched independently with `Promise.all()`. Omitted `pr` means one fetch for current branch PR. |\n| Output | Single PR: one PR summary with body, up to 50 files, optional reviews, inline review comments, and issue comments. Batched: `# <n> Pull Requests` plus per-PR sections. |\n\nWhen comments are enabled and both repo + PR number are known, the tool paginates `/repos/<repo>/pulls/<n>/comments` with `per_page=100` to supplement `gh pr view` output.\n\n### `pr_diff`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `pr`, `nameOnly`, `exclude[]` |\n| `gh` command | For each requested PR: `gh pr diff [<pr>] [--repo <repo>] --color never [--name-only] [--exclude <glob> ...]` |\n| Batching | Yes. Same `pr` normalization as `pr_view`; fetched with `Promise.all()`. |\n| Output | Single PR: `# Pull Request Diff` or `# Pull Request Files` followed by raw CLI output. Batched: `# <n> Pull Request Diffs` / `File Lists` plus labeled sections. |\n\nDiff stdout is preserved without trimming. Empty output becomes `No diff output.` or `No changed files.`.\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 search issues --limit <limit> --json <GH_SEARCH_FIELDS> [--repo <repo>] -- <query>` |\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### `search_prs`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh search prs --limit <limit> --json <GH_SEARCH_FIELDS> [--repo <repo>] -- <query>` |\n| Batching | None |\n| Output | Same shape as `search_issues`, labeled as pull requests. |\n\n### `search_code`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh search code --limit <limit> --json <GH_SEARCH_CODE_FIELDS> [--repo <repo>] -- <query>` |\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### `search_commits`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh search commits --limit <limit> --json <GH_SEARCH_COMMITS_FIELDS> [--repo <repo>] -- <query>` |\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### `search_repos`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `limit` |\n| `gh` command | `gh search repos --limit <limit> --json <GH_SEARCH_REPOS_FIELDS> -- <query>` |\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 `abortableSleep()` 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 `pr_view`: first `50` files only (`FILE_PREVIEW_LIMIT`).\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_view`/`pr_diff`/`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 (`issue`, `query`, `title unless fill=true`)\n  - invalid numeric `limit` / `tail`\n  - invalid `run` format\n  - `fill` combined with `title` or `body`\n  - empty exclude patterns\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",