@oh-my-pi/pi-coding-agent 14.9.2 → 14.9.5

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

@@ -1,8 +1,9 @@
 // Auto-generated by scripts/generate-docs-index.ts - DO NOT EDIT
 
-export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["bash-tool-runtime.md","blob-artifact-architecture.md","compaction.md","config-usage.md","custom-tools.md","environment-variables.md","extension-loading.md","extensions.md","fs-scan-cache-architecture.md","gemini-manifest-extensions.md","handoff-generation-pipeline.md","hooks.md","marketplace.md","mcp-config.md","mcp-protocol-transports.md","mcp-runtime-lifecycle.md","mcp-server-tool-authoring.md","memory.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","plugin-manager-installer-plumbing.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","skills.md","skills/authoring-extensions.md","skills/authoring-hooks.md","skills/authoring-marketplaces.md","skills/examples/hello-extension/README.md","skills/examples/mini-marketplace/README.md","skills/examples/safety-hook/README.md","slash-command-internals.md","task-agent-discovery.md","theme.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md","tui.md"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","bash-tool-runtime.md","blob-artifact-architecture.md","compaction.md","config-usage.md","custom-tools.md","environment-variables.md","extension-loading.md","extensions.md","fs-scan-cache-architecture.md","gemini-manifest-extensions.md","handoff-generation-pipeline.md","hooks.md","marketplace.md","mcp-config.md","mcp-protocol-transports.md","mcp-runtime-lifecycle.md","mcp-server-tool-authoring.md","memory.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","plugin-manager-installer-plumbing.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","skills.md","skills/authoring-extensions.md","skills/authoring-hooks.md","skills/authoring-marketplaces.md","skills/examples/hello-extension/README.md","skills/examples/mini-marketplace/README.md","skills/examples/safety-hook/README.md","slash-command-internals.md","task-agent-discovery.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/exit_plan_mode.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/recipe.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md","tui.md"];
 
 export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
+	"ERRATA-GPT5-HARMONY.md": "# ERRATA — GPT-5 Harmony-Header Leakage\n\n## 1. The problem\n\nOpenAI frames tool calls in the Harmony chat protocol:\n\n```\n<|start|>assistant<|channel|>commentary to=functions.<NAME><|message|>{ARGS}<|call|>\n```\n\n`<|channel|>commentary to=functions.NAME` is the **routing header** —\ncontrol tokens consumed by the runtime to dispatch the call. These\ntokens never appear as content under normal operation; the runtime\nstrips them.\n\nThe defect: gpt-5 models occasionally emit, **as ordinary content\ninside `{ARGS}`**, the **plain-text shadow** of these routing tokens —\nthe same characters without the `<|…|>` brackets — and continue\nproducing more pseudo-routing structure (channel name, body marker,\nmultilingual spam, fake tool-result framing). The contamination lives\ninside the visible tool argument and is dispatched to the tool as if it\nwere intended content.\n\n**Critical detail.** The actual `<|start|>` / `<|channel|>` /\n`<|message|>` / `<|call|>` special tokens almost never appear in tool\nargs. What leaks is the bracket-less spelling — `analysis to=functions.X\ncode …` — because OpenAI applies a logit mask suppressing the\ncontrol-token IDs inside the args region. The mass that would have gone\nto those special tokens redistributes onto the un-bracketed plain-text\nrepresentation the model also learned. This makes the leak structurally\ninvisible to the routing parser and lands it in the tool input verbatim.\n\nManifestation in tool args (real corpus example):\n\n```\n~      add_function(iso, ctx, ns, \"installSystemChangeObserver\",\n        os_install_system_change_observer);】【\"】【analysis to=functions.edit\n        code above เงินไทยฟรีuser to=functions.edit code …\n```\n\nThe leading code is real and intended. Everything after the first\nnon-Latin token through the next clean structural boundary is corruption.\n\n---\n\n## 2. Observed statistics & failure modes\n\nSource: `~/.omp/stats.db` (`ss_tool_calls`, `ss_assistant_msgs`), through\n2026-05-10. 1.05M tool calls scanned.\n\n### 2.1 Rate\n\n| Model            | Leaks in tool args | Calls   | per million |\n|------------------|-------------------:|--------:|------------:|\n| gpt-5.4          | 37                 | 226,957 | 163         |\n| gpt-5.3-codex    | 17                 | 112,243 | 151         |\n| gpt-5.5          | 2                  |  80,750 |  25         |\n| gpt-5.2-codex    | 0                  |    —    |   —         |\n\nPlus 15 hits in assistant visible text / thinking blobs.\n\n### 2.2 Tool distribution\n\n| Tool                | Hits |\n|---------------------|-----:|\n| `edit`              | 38   |\n| `eval`              | 11   |\n| `report_tool_issue` | 3    |\n| `grep`/`read`/`search`/`yield` | 1 each |\n\nConcentrated in tools with free-form (non-JSON-schema) argument formats.\n\n### 2.3 Leak shape (deterministic)\n\n```\nLEAK         ::= JUNK_PREFIX MARKER CHANNEL_BODY (LEAK)?\nMARKER       ::= \"to=functions.\" TOOL_NAME\nCHANNEL_BODY ::= \" code \" (SPAM | reasoning_prose | fake_tool_output)*\nJUNK_PREFIX  ::= (GLITCH_TOKEN | CHANNEL_WORD | NON_LATIN_RUN | \"}\" | \"】【\")+\n```\n\n**Cascading is common.** Of 96 marker occurrences across 71 contaminated\nrecords, 39 contain ≥2 markers and 7 contain ≥3 — the model emits\nmultiple fake `to=functions.X code …` blocks back-to-back, often with\nfake `code_output\\nCell N:\\n…` framing between them. Once the\nplain-text scaffolding is in the residual stream, the prefix now *looks\nlike* a fresh tool envelope start, so the macro prior over continuations\nkeeps voting for more scaffolding. Self-amplifying.\n\n### 2.4 Glitch tokens\n\nSingle-token identifiers in `o200k_base` whose embeddings appear to be\nnear-init from underrepresentation in post-training. ASCII residue\nimmediately before the marker in the natural corpus:\n\n| Surface string    | Single-token | Token ID | Hits in corpus |\n|-------------------|:-:|---------:|---:|\n| `Japgolly`        | ✅ | 199,745 | 1 |\n| `Jsii`            | ✅ | 114,318 | (subtoken of `Jsii_commentary`) |\n| `Jsii_commentary` | — (3 toks) | — | 2 |\n| `changedFiles`    | — (2 toks) | — | 8 |\n| `RTLU`            | — (2 toks) | — | 3 |\n\n`Japgolly` is in the last 0.13% of the vocabulary — the same family of\nGitHub-corpus residue that produced `SolidGoldMagikarp` in the 2023\nGPT-2 vocabulary (Rumbelow & Watkins). `SolidGoldMagikarp` itself\ntokenizes to 5 tokens in `o200k_base` — that specific token was retired,\nbut the class wasn't.\n\nFor the multi-token entries, the corpus-level signature is the surface\nstring; the underlying glitch trigger is a sub-token (e.g. `Jsii` inside\n`Jsii_commentary`). The detector list (`G` signal) keys on the surface\nstrings.\n\nStable across unrelated sessions. Treated as a high-precision detector\nsignal.\n\n### 2.5 Channel-word leakage\n\n`analysis` (5), `assistant` (5), `commentary` (3), `user` (1) appear\ndirectly preceding `to=`. Always bare words; never `<|channel|>analysis`\nor any other bracketed form. Consistent with §1 — the brackets are\nmasked, the words are not.\n\n### 2.6 Non-Latin spam residue\n\n96 marker hits, by script: CJK 40, Cyrillic 12, Telugu/Kannada/Malayalam\n18, Thai 8, Georgian 7, Armenian 7, Arabic 1. Recurring fragments are\nChinese gambling SEO (`大发时时彩`, `天天中彩票`), Georgian/Abkhaz junk,\nand Thai casino spam — well-known low-quality crawl residue.\n\nThis is the same script distribution observed in the controlled\nreproduction (§7.3), independent of the prompt's natural language.\n\n### 2.7 Failure-mode breakdown for the `edit` tool\n\nThe `edit` tool exists in two variants in the corpus:\n\n| Variant                  | Calls | Recovery |\n|--------------------------|------:|----------|\n| Patch-DSL (`@PATH`/anchor/`~payload`) | 27 | **Recoverable** by op-truncation (§3.3) |\n| JSON-schema (`{path,edits:[…]}`)      | 11 | **Not recoverable** — contamination is escaped *inside* JSON strings, parser accepts it cleanly, content would be written verbatim into source files |\n\nFor Patch-DSL leaks specifically:\n\n- 20/27 cases: contamination on the last input line; nothing follows.\n- 7/27 cases: contamination mid-input; what follows is one of: a\n  duplicate replay of an earlier file/anchor, intended content for a\n  *different* tool call (the model started its next call inline), or\n  pure hallucination. Post-contamination content is never trustworthy.\n\n### 2.8 Mechanism (confirmed)\n\n**Prior collapse from null-embedding glitch tokens, into a\ncontrol-token-masked basin whose mass redistributes onto the\nplain-text shadow of the Harmony protocol.**\n\nStep by step:\n\n1. The model is mid-`{ARGS}` of a Harmony tool call. The runtime applies\n   a logit mask suppressing structural control tokens (`<|channel|>`,\n   `<|message|>`, `<|call|>`, `<|start|>`, `<|end|>`) inside the args\n   region. Without this mask, normal generation would constantly\n   hallucinate envelope-closes; with it, those token IDs have logit\n   `-∞` in args.\n2. A glitch token `g` is sampled. By construction `g` was in the BPE\n   merge corpus but barely in LM/RL training, so its **input embedding\n   `e_g` ≈ near-init noise of small norm**.\n3. At position t+1, the residual update `h_{t+1} ≈ LN(h_t + e_g + Attn +\n   MLP)` is dominated by the prefix-derived terms; the just-emitted-token\n   signal is effectively absent. Generation diversity normally comes\n   from `e_x` steering the residual into different sub-regions —\n   stripped here.\n4. The next-token distribution therefore collapses onto the **conditional\n   prior over continuations of the prefix, with local conditioning\n   removed**. In a tool-calling rollout context, that prior is sharply\n   peaked on Harmony scaffolding (control tokens + routing tokens) —\n   that's what RL trained.\n5. The mask zeros the control-token IDs. Mass redistributes onto the\n   **next-best continuation**: the un-bracketed surface-form spelling of\n   the same protocol (`analysis`, `commentary`, ` to=functions.X`,\n   ` code `). This spelling is unmasked because those characters are\n   ordinary tokens.\n6. Once a few tokens of plain-text scaffolding land in the residual\n   stream, the prefix now resembles a fresh envelope start. The macro\n   prior keeps voting for more scaffolding. Cascading (§2.3) follows.\n7. Multilingual spam after the marker is the same prior-collapse\n   continuation, drawn from the training neighborhood of the glitch\n   token (often ESL/auto-generated multilingual web junk — exactly the\n   crawl residue in §2.6).\n\n**Two corollaries the corpus data demanded but only the experiment\nexplained:**\n\n- **The brackets never appear** (§1, §2.5). The mask is what makes the\n  leak land in plain text instead of as a real envelope-close.\n- **Counterintuitive grammar dependency** (§7.4). The leak is *worse* in\n  formats closest to OpenAI's training distribution. Off-distribution\n  custom grammars dampen the macro-prior basin; the official\n  `*** Begin Patch` format is the strongest collapse target.\n\nThe 2023 SolidGoldMagikarp paper documented mechanism (1)+(2)+(4). The\nnew piece is (5): when constrained decoding masks the natural collapse\ntarget, the mass laundered through the un-masked plain-text shadow\nbecomes a structurally-invisible exfiltration channel.",
 	"bash-tool-runtime.md": "# Bash tool runtime\n\nThis document describes the **`bash` tool** runtime path used by agent tool calls, from command normalization to execution, truncation/artifacts, and rendering.\n\nIt also calls out where behavior diverges in interactive TUI, print mode, RPC mode, and user-initiated bang (`!`) shell execution.\n\n## Scope and runtime surfaces\n\nThere are two different bash execution surfaces in coding-agent:\n\n1. **Tool-call surface** (`toolName: \"bash\"`): used when the model calls the bash tool.\n   - Entry point: `BashTool.execute()`.\n   - Parameters include `command`, optional `env`, `timeout`, `cwd`, `head`, `tail`, `pty`, and, when `async.enabled` is true, `async`.\n2. **User bang-command surface** (`!cmd` from interactive input or RPC `bash` command): session-level helper path.\n   - Entry point: `AgentSession.executeBash()`.\n\nBoth eventually use `executeBash()` in `src/exec/bash-executor.ts` for non-PTY execution, but only the tool-call path runs normalization/interception, optional managed background-job handling, and tool renderer logic.\n\n## End-to-end tool-call pipeline\n\n## 1) Input handling and parameter merge\n\n`BashTool.execute()` currently handles input before execution as follows:\n\n- validates optional `env` names against shell-variable syntax,\n- extracts a leading `cd <path> && ...` into `cwd` when `cwd` was not supplied,\n- rejects `async: true` when `async.enabled` is false,\n- uses only explicit `head`/`tail` tool args for post-run filtering.\n\n`normalizeBashCommand()` still exists in `src/tools/bash-normalize.ts`, but `BashTool.execute()` does not call it in the current source. Trailing shell pipes such as `| head -n 50` remain part of the shell command unless the caller uses the structured `head`/`tail` args.\n\n## 2) Optional interception (blocked-command path)\n\nIf `bashInterceptor.enabled` is true, `BashTool` loads rules from settings and runs `checkBashInterception()` against the normalized command.\n\nInterception behavior:\n\n- command is blocked **only** when:\n  - regex rule matches, and\n  - the suggested tool is present in `ctx.toolNames`.\n- invalid regex rules are silently skipped.\n- on block, `BashTool` throws `ToolError` with message:\n  - `Blocked: ...`\n  - original command included.\n\nDefault rule patterns (defined in code) target common misuses:\n\n- file readers (`cat`, `head`, `tail`, ...)\n- search tools (`grep`, `rg`, ...)\n- file finders (`find`, `fd`, ...)\n- in-place editors (`sed -i`, `perl -i`, `awk -i inplace`)\n- shell redirection writes (`echo ... > file`, heredoc redirection)\n\n### Caveat\n\n`InterceptionResult` includes `suggestedTool`, but `BashTool` currently surfaces only the message text (no structured suggested-tool field in `details`).\n\n## 3) CWD validation and timeout clamping\n\n`cwd` is resolved relative to session cwd (`resolveToCwd`), then validated via `stat`:\n\n- missing path -> `ToolError(\"Working directory does not exist: ...\")`\n- non-directory -> `ToolError(\"Working directory is not a directory: ...\")`\n\nTimeout is clamped to `[1, 3600]` seconds and converted to milliseconds.\n\n## 4) Artifact allocation\n\nBefore execution, the tool allocates an artifact path/id (best-effort) for truncated output storage.\n\n- artifact allocation failure is non-fatal (execution continues without artifact spill file),\n- artifact id/path are passed into execution path for full-output persistence on truncation.\n\n## 5) PTY vs non-PTY execution selection\n\n`BashTool` chooses PTY execution only when all are true:\n\n- tool input `pty === true`\n- `PI_NO_PTY !== \"1\"`\n- tool context has UI (`ctx.hasUI === true` and `ctx.ui` set)\n\nOtherwise it uses non-interactive `executeBash()`.\n\nThat means print mode and non-UI RPC/tool contexts always use non-PTY.\n\n## Non-interactive execution engine (`executeBash`)\n\n## Shell session reuse model\n\n`executeBash()` caches native `Shell` instances in a process-global map keyed by:\n\n- shell path,\n- configured command prefix,\n- snapshot path,\n- serialized shell env,\n- optional agent session key.\n\nSession-level bang-command executions pass `sessionKey: this.sessionId`.\n\nTool-call executions pass `sessionKey: this.session.getSessionId?.()`, when available. In both surfaces, a session key isolates shell reuse per session; without one, reuse falls back to shell config/snapshot/env.\n\n## Shell config and snapshot behavior\n\nAt each call, executor loads settings shell config (`shell`, `env`, optional `prefix`).\n\nIf selected shell includes `bash`, it attempts `getOrCreateSnapshot()`:\n\n- snapshot captures aliases/functions/options from user rc,\n- snapshot creation is best-effort,\n- failure falls back to no snapshot.\n\nIf `prefix` is configured, command becomes:\n\n```text\n<prefix> <command>\n```\n\n## Streaming and cancellation\n\n`Shell.run()` streams chunks to `OutputSink` and optional `onChunk` callback.\n\nCancellation:\n\n- aborted signal triggers `shellSession.abort(...)`,\n- timeout from native result is mapped to `cancelled: true` + annotation text,\n- explicit cancellation similarly returns `cancelled: true` + annotation.\n\nNo exception is thrown inside executor for timeout/cancel; it returns structured `BashResult` and lets caller map error semantics.\n\n## Interactive PTY path (`runInteractiveBashPty`)\n\nWhen PTY is enabled, tool runs `runInteractiveBashPty()` which opens an overlay console component and drives a native `PtySession`.\n\nBehavior highlights:\n\n- xterm-headless virtual terminal renders viewport in overlay,\n- keyboard input is normalized (including Kitty sequences and application cursor mode handling),\n- `esc` while running kills the PTY session,\n- terminal resize propagates to PTY (`session.resize(cols, rows)`).\n\nEnvironment hardening defaults are injected for unattended runs:\n\n- pagers disabled (`PAGER=cat`, `GIT_PAGER=cat`, etc.),\n- editor prompts disabled (`GIT_EDITOR=true`, `EDITOR=true`, ...),\n- terminal/auth prompts reduced (`GIT_TERMINAL_PROMPT=0`, `SSH_ASKPASS=/usr/bin/false`, `CI=1`),\n- package-manager/tool automation flags for non-interactive behavior.\n\nPTY output is normalized (`CRLF`/`CR` to `LF`, `sanitizeText`) and written into `OutputSink`, including artifact spill support.\n\nOn PTY startup/runtime error, sink receives `PTY error: ...` line and command finalizes with undefined exit code.\n\n## Output handling: streaming, truncation, artifact spill\n\nBoth PTY and non-PTY paths use `OutputSink`.\n\n## OutputSink semantics\n\n- keeps an in-memory UTF-8-safe tail buffer (`DEFAULT_MAX_BYTES`, currently 50KB),\n- tracks total bytes/lines seen,\n- if artifact path exists and output overflows (or file already active), writes full stream to artifact file,\n- when memory threshold overflows, trims in-memory buffer to tail (UTF-8 boundary safe),\n- marks `truncated` when overflow/file spill occurs.\n\n`dump()` returns:\n\n- `output` (possibly annotated prefix),\n- `truncated`,\n- `totalLines/totalBytes`,\n- `outputLines/outputBytes`,\n- `artifactId` if artifact file was active.\n\n### Long-output caveat\n\nRuntime truncation is byte-threshold based in `OutputSink` (50KB default). It does not enforce a hard 2000-line cap in this code path.\n\n## Live tool updates and async jobs\n\nFor non-PTY foreground execution, `BashTool` uses a separate `TailBuffer` for partial updates and emits `onUpdate` snapshots while command is running.\n\nFor PTY execution, live rendering is handled by custom UI overlay, not by `onUpdate` text chunks.\n\nWhen `async.enabled` is true and the call passes `async: true`, `BashTool` starts a managed bash job, returns a running job result with a job id, and stores completion through the session managed-job path. Auto-backgrounding can also start this path after `bash.autoBackground.thresholdMs`.\n\n## Result shaping, metadata, and error mapping\n\nAfter execution:\n\n1. `cancelled` handling:\n   - if abort signal is aborted -> throw `ToolAbortError` (abort semantics),\n   - else -> throw `ToolError` (treated as tool failure).\n2. PTY `timedOut` -> throw `ToolError`.\n3. apply head/tail filters to final output text (`applyHeadTail`, head then tail).\n4. empty output becomes `(no output)`.\n5. attach truncation metadata via `toolResult(...).truncationFromSummary(result, { direction: \"tail\" })`.\n6. exit-code mapping:\n   - missing exit code -> `ToolError(\"... missing exit status\")`\n   - non-zero exit -> `ToolError(\"... Command exited with code N\")`\n   - zero exit -> success result.\n\nSuccess payload structure:\n\n- `content`: text output,\n- `details.meta.truncation` when truncated, including:\n  - `direction`, `truncatedBy`, total/output line+byte counts,\n  - `shownRange`,\n  - `artifactId` when available.\n\nBecause built-in tools are wrapped with `wrapToolWithMetaNotice()`, truncation notice text is appended to final text content automatically (for example: `Full: artifact://<id>`).\n\n## Rendering paths\n\n## Tool-call renderer (`bashToolRenderer`)\n\n`bashToolRenderer` is used for tool-call messages (`toolCall` / `toolResult`):\n\n- collapsed mode shows visual-line-truncated preview,\n- expanded mode shows all currently available output text,\n- warning line includes truncation reason and `artifact://<id>` when truncated,\n- timeout value (from args) is shown in footer metadata line.\n\n### Caveat: full artifact expansion\n\n`BashRenderContext` has `isFullOutput`, but current renderer context builder does not set it for bash tool results. Expanded view still uses the text already in result content (tail/truncated output) unless another caller provides full artifact content.\n\n## User bang-command component (`BashExecutionComponent`)\n\n`BashExecutionComponent` is for user `!` commands in interactive mode (not model tool calls):\n\n- streams chunks live,\n- collapsed preview keeps last 20 logical lines,\n- line clamp at 4000 chars per line,\n- shows truncation + artifact warnings when metadata is present,\n- marks cancelled/error/exit state separately.\n\nThis component is wired by `CommandController.handleBashCommand()` and fed from `AgentSession.executeBash()`.\n\n## Mode-specific behavior differences\n\n| Surface                        | Entry path                                            | PTY eligible                                                         | Live output UX                                                           | Error surfacing                                  |\n| ------------------------------ | ----------------------------------------------------- | -------------------------------------------------------------------- | ------------------------------------------------------------------------ | ------------------------------------------------ |\n| Interactive tool call          | `BashTool.execute`                                    | Yes, when `pty=true` and UI exists and `PI_NO_PTY!=1`                | PTY overlay (interactive) or streamed tail updates                       | Tool errors become `toolResult.isError`          |\n| Print mode tool call           | `BashTool.execute`                                    | No (no UI context)                                                   | No TUI overlay; output appears in event stream/final assistant text flow | Same tool error mapping                          |\n| RPC tool call (agent tooling)  | `BashTool.execute`                                    | Usually no UI -> non-PTY                                             | Structured tool events/results                                           | Same tool error mapping                          |\n| Interactive bang command (`!`) | `AgentSession.executeBash` + `BashExecutionComponent` | No (uses executor directly)                                          | Dedicated bash execution component                                       | Controller catches exceptions and shows UI error |\n| RPC `bash` command             | `rpc-mode` -> `session.executeBash`                   | No                                                                   | Returns `BashResult` directly                                            | Consumer handles returned fields                 |\n\n## Operational caveats\n\n- Interceptor only blocks commands when suggested tool is currently available in context.\n- If artifact allocation fails, truncation still occurs but no `artifact://` back-reference is available.\n- Shell session cache has no explicit eviction in this module; lifetime is process-scoped.\n- PTY and non-PTY timeout surfaces differ:\n  - PTY exposes explicit `timedOut` result field,\n  - non-PTY maps timeout into `cancelled + annotation` summary.\n\n## Implementation files\n\n- [`src/tools/bash.ts`](../packages/coding-agent/src/tools/bash.ts) — tool entrypoint, input handling/interception, async and PTY/non-PTY selection, result/error mapping, bash tool renderer.\n- [`src/tools/bash-normalize.ts`](../packages/coding-agent/src/tools/bash-normalize.ts) — post-run head/tail filtering; also contains an unused command-normalization helper.\n- [`src/tools/bash-interceptor.ts`](../packages/coding-agent/src/tools/bash-interceptor.ts) — interceptor rule matching and blocked-command messages.\n- [`src/exec/bash-executor.ts`](../packages/coding-agent/src/exec/bash-executor.ts) — non-PTY executor, shell session reuse, cancellation wiring, output sink integration.\n- [`src/tools/bash-interactive.ts`](../packages/coding-agent/src/tools/bash-interactive.ts) — PTY runtime, overlay UI, input normalization, non-interactive env defaults.\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts) — `OutputSink`, `TailBuffer`, truncation/artifact spill, and summary metadata.\n- [`src/tools/output-meta.ts`](../packages/coding-agent/src/tools/output-meta.ts) — truncation metadata shape + notice injection wrapper.\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — session-level `executeBash`, message recording, abort lifecycle.\n- [`src/modes/components/bash-execution.ts`](../packages/coding-agent/src/modes/components/bash-execution.ts) — interactive `!` command execution component.\n- [`src/modes/controllers/command-controller.ts`](../packages/coding-agent/src/modes/controllers/command-controller.ts) — wiring for interactive `!` command UI stream/update completion.\n- [`src/modes/rpc/rpc-mode.ts`](../packages/coding-agent/src/modes/rpc/rpc-mode.ts) — RPC `bash` and `abort_bash` command surface.\n- [`src/internal-urls/artifact-protocol.ts`](../packages/coding-agent/src/internal-urls/artifact-protocol.ts) — `artifact://<id>` resolution.\n",
 	"blob-artifact-architecture.md": "# Blob and artifact storage architecture\n\nThis document describes how coding-agent stores large/binary payloads outside session JSONL, how truncated tool output is persisted, and how internal URLs (`artifact://`, `agent://`) resolve back to stored data.\n\n## Why two storage systems exist\n\nThe runtime uses two different persistence mechanisms for different data shapes:\n\n- **Content-addressed blobs** (`blob:sha256:<hash>`): global storage used to externalize large image base64 payloads and provider image data URLs from persisted session entries.\n- **Session-scoped artifacts** (files under `<sessionFile-without-.jsonl>/`): per-session text files used for full tool outputs and subagent outputs.\n\nThey are intentionally separate:\n\n- blob storage optimizes deduplication and stable references by content hash,\n- artifact storage optimizes append-only session tooling and human/tool retrieval by local IDs.\n\n## Storage boundaries and on-disk layout\n\n## Blob store boundary (global)\n\n`SessionManager` constructs `BlobStore(getBlobsDir())`, so blob files live in a shared global blob directory (not in a session folder).\n\nBlob file naming:\n\n- file path: `<blobsDir>/<sha256-hex>`\n- no extension\n- reference string stored in entries: `blob:sha256:<sha256-hex>`\n\nImplications:\n\n- same binary content across sessions resolves to the same hash/path,\n- writes are idempotent at the content level,\n- blobs can outlive any individual session file.\n\n## Artifact boundary (session-local)\n\n`ArtifactManager` derives artifact directory from session file path:\n\n- session file: `.../<timestamp>_<sessionId>.jsonl`\n- artifacts directory: `.../<timestamp>_<sessionId>/` (strip `.jsonl`)\n\nArtifact types share this directory:\n\n- truncated tool output files: `<numericId>.<toolType>.log` (for `artifact://`)\n- subagent output files: `<outputId>.md` (for `agent://`)\n\n## ID and name allocation schemes\n\n## Blob IDs: content hash\n\n`BlobStore.put()` computes SHA-256 over the bytes it is given and returns:\n\n- `hash`: hex digest,\n- `path`: `<blobsDir>/<hash>`,\n- `ref`: `blob:sha256:<hash>`.\n\nNo session-local counter is used.\n\n## Artifact IDs: session-local monotonic integer\n\n`ArtifactManager` scans existing `*.log` artifact files on first use to find max existing numeric ID and sets `nextId = max + 1`.\n\nAllocation behavior:\n\n- file format: `{id}.{toolType}.log`\n- IDs are sequential strings (`\"0\"`, `\"1\"`, ...)\n- resume does not overwrite existing artifacts because scan happens before allocation.\n\nIf artifact directory is missing, scanning yields empty list and allocation starts from `0`.\n\n## Agent output IDs (`agent://`)\n\n`AgentOutputManager` allocates IDs for subagent outputs as `<index>-<requestedId>` (optionally nested under parent prefix, e.g. `0-Parent.1-Child`). It scans existing `.md` files on initialization to continue from the next index on resume.\n\n## Persistence dataflow\n\n## 1) Session entry persistence rewrite path\n\nBefore session entries are written (`#rewriteFile` / incremental persist), `SessionManager` calls `prepareEntryForPersistence()` (via `truncateForPersistence`).\n\nKey behaviors:\n\n1. **Large string truncation**: oversized strings are cut and suffixed with `\"[Session persistence truncated large content]\"`; signature fields (`thinkingSignature`, `thoughtSignature`, `textSignature`) are cleared instead of truncated.\n2. **Transient field stripping**: `partialJson` and `jsonlEvents` are removed from persisted entries.\n3. **Image externalization to blobs**:\n   - image blocks in `content` arrays are externalized when `data` is not already a blob ref and base64 length is at least threshold (`BLOB_EXTERNALIZE_THRESHOLD = 1024`),\n   - provider-style `image_url` data URLs are externalized when they start with `data:image/` and contain `;base64,`,\n   - image block `data` is stored as decoded binary bytes,\n   - provider data URLs are stored as the original UTF-8 data URL string,\n   - persisted values are replaced with `blob:sha256:<hash>`.\n\nThis keeps session JSONL compact while preserving recoverability.\n\n## 2) Session load rehydration path\n\nWhen opening a session (`setSessionFile`), after migrations, `SessionManager` runs `resolveBlobRefsInEntries()`.\n\nFor message/custom-message image blocks with `blob:sha256:<hash>` and for persisted provider `image_url` fields with blob refs:\n\n- reads blob bytes from blob store,\n- converts image-block bytes back to base64,\n- converts provider `image_url` blobs back to the original string,\n- mutates in-memory entry fields for runtime consumers.\n\nIf blob is missing:\n\n- `resolveImageData()` logs warning,\n- returns original ref string unchanged,\n- load continues (no hard crash).\n\n## 3) Tool output spill/truncation path\n\n`OutputSink` powers streaming output in bash/python/ssh and related executors.\n\nBehavior:\n\n1. Every chunk is sanitized and appended to in-memory tail buffer.\n2. When in-memory bytes exceed spill threshold (`DEFAULT_MAX_BYTES`, 50KB), sink marks output truncated.\n3. If an artifact path is available, sink opens a file writer and writes:\n   - existing buffered content once,\n   - all subsequent chunks.\n4. In-memory buffer is always trimmed to tail window for display.\n5. `dump()` returns summary including `artifactId` only when file sink was successfully created.\n\nPractical effect:\n\n- UI/tool return shows truncated tail,\n- full output is preserved in artifact file and referenced as `artifact://<id>`.\n\nIf file sink creation fails (I/O error, missing path, etc.), sink silently falls back to in-memory truncation only; full output is not persisted.\n\n## URL access model\n\n## `blob:` references\n\n`blob:sha256:<hash>` is a persistence reference inside session entry payloads, not an internal URL scheme handled by the router. Resolution is done by `SessionManager` during session load.\n\n## `artifact://<id>`\n\nHandled by `ArtifactProtocolHandler`:\n\n- requires active session artifact directory,\n- ID must be numeric,\n- resolves by matching filename prefix `<id>.`,\n- returns raw text (`text/plain`) from the matched `.log` file,\n- when missing, error includes list of available artifact IDs.\n\nMissing directory behavior:\n\n- if artifacts directory does not exist, throws `No artifacts directory found`.\n\n## `agent://<id>`\n\nHandled by `AgentProtocolHandler` over `<artifactsDir>/<id>.md`:\n\n- plain form returns markdown text,\n- `/path` or `?q=` forms perform JSON extraction,\n- path and query extraction cannot be combined,\n- if extraction requested, file content must parse as JSON.\n\nMissing directory behavior:\n\n- throws `No artifacts directory found`.\n\nMissing output behavior:\n\n- throws `Not found: <id>` with available IDs from existing `.md` files.\n\nRead tool integration:\n\n- `read` supports offset/limit pagination for non-extraction internal URL reads,\n- rejects `offset/limit` when `agent://` extraction is used.\n\n## Resume, fork, and move semantics\n\n## Resume\n\n- `ArtifactManager` scans existing `{id}.*.log` files on first allocation and continues numbering.\n- `AgentOutputManager` scans existing `.md` output IDs and continues numbering.\n- `SessionManager` rehydrates blob refs to base64 on load.\n\n## Fork\n\n`SessionManager.fork()` creates a new session file with new session ID and `parentSession` link, then returns old/new file paths. Artifact copying is handled by `AgentSession.fork()`:\n\n- attempts recursive copy of old artifact directory to new artifact directory,\n- missing old directory is tolerated,\n- non-ENOENT copy errors are logged as warnings and fork still completes.\n\nID implications after fork:\n\n- if copy succeeded, artifact counters in new session continue after max copied ID,\n- if copy failed/skipped, new session artifact IDs start from `0`.\n\nBlob implications after fork:\n\n- blobs are global and content-addressed, so no blob directory copy is required.\n\n## Move to new cwd\n\n`SessionManager.moveTo()` renames both session file and artifact directory to the new default session directory, with rollback logic if a later step fails. This preserves artifact identity while relocating session scope.\n\n## Failure handling and fallback paths\n\n| Case                                                     | Behavior                                                              |\n| -------------------------------------------------------- | --------------------------------------------------------------------- |\n| Blob file missing during rehydration                     | Warn and keep `blob:sha256:` ref string in-memory                     |\n| Blob read ENOENT via `BlobStore.get`                     | Returns `null`                                                        |\n| Artifact directory missing (`ArtifactManager.listFiles`) | Returns empty list (allocation can start fresh)                       |\n| Artifact directory missing (`artifact://` / `agent://`)  | Throws explicit `No artifacts directory found`                        |\n| Artifact ID not found                                    | Throws with available IDs listing                                     |\n| OutputSink artifact writer init fails                    | Continues with tail-only truncation (no full-output artifact)         |\n| No session file (some task paths)                        | Task tool falls back to temp artifacts directory for subagent outputs |\n\n## Binary blob externalization vs text-output artifacts\n\n- **Blob externalization** is for image payloads inside persisted session entry content and provider image data URLs; it replaces inline payload strings in JSONL with stable content refs.\n- **Artifacts** are plain text files for execution output and subagent output; they are addressable by session-local IDs through internal URLs.\n\nThe two systems intersect only indirectly (both reduce session JSONL bloat) but have different identity, lifetime, and retrieval paths.\n\n## Implementation files\n\n- [`src/session/blob-store.ts`](../packages/coding-agent/src/session/blob-store.ts) — blob reference format, hashing, put/get, externalize/resolve helpers.\n- [`src/session/artifacts.ts`](../packages/coding-agent/src/session/artifacts.ts) — session artifact directory model and numeric artifact ID/path allocation.\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts) — `OutputSink` truncation/spill-to-file behavior and summary metadata.\n- [`src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts) — persistence transforms, blob rehydration on load, session fork/move interactions.\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — artifact directory copy during interactive fork.\n- [`src/internal-urls/artifact-protocol.ts`](../packages/coding-agent/src/internal-urls/artifact-protocol.ts) — `artifact://` resolver.\n- [`src/internal-urls/agent-protocol.ts`](../packages/coding-agent/src/internal-urls/agent-protocol.ts) — `agent://` resolver + JSON extraction.\n- [`src/sdk.ts`](../packages/coding-agent/src/sdk.ts) — internal URL router wiring and artifacts-dir resolver.\n- [`src/task/output-manager.ts`](../packages/coding-agent/src/task/output-manager.ts) — session-scoped agent output ID allocation for `agent://`.\n- [`src/task/executor.ts`](../packages/coding-agent/src/task/executor.ts) — subagent output artifact writes (`<id>.md`) and temp artifact directory fallback.\n",
 	"compaction.md": "# Compaction and Branch Summaries\n\nCompaction and branch summaries are the two mechanisms that keep long sessions usable without losing prior work context.\n\n- **Compaction** rewrites old history into a summary on the current branch.\n- **Branch summary** captures abandoned branch context during `/tree` navigation.\n\nBoth are persisted as session entries and converted back into user-context messages when rebuilding LLM input.\n\n## Key implementation files\n\n- `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",
@@ -57,6 +58,38 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"slash-command-internals.md": "# Slash command internals\n\nThis document describes how slash commands are discovered, deduplicated, surfaced in interactive mode, and expanded at prompt time in `coding-agent`.\n\n## Implementation files\n\n- [`src/extensibility/slash-commands.ts`](../packages/coding-agent/src/extensibility/slash-commands.ts)\n- [`src/capability/slash-command.ts`](../packages/coding-agent/src/capability/slash-command.ts)\n- [`src/discovery/builtin.ts`](../packages/coding-agent/src/discovery/builtin.ts)\n- [`src/discovery/claude.ts`](../packages/coding-agent/src/discovery/claude.ts)\n- [`src/discovery/codex.ts`](../packages/coding-agent/src/discovery/codex.ts)\n- [`src/discovery/claude-plugins.ts`](../packages/coding-agent/src/discovery/claude-plugins.ts)\n- [`src/capability/index.ts`](../packages/coding-agent/src/capability/index.ts)\n- [`src/discovery/helpers.ts`](../packages/coding-agent/src/discovery/helpers.ts)\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`src/modes/interactive-mode.ts`](../packages/coding-agent/src/modes/interactive-mode.ts)\n- [`src/modes/controllers/input-controller.ts`](../packages/coding-agent/src/modes/controllers/input-controller.ts)\n- [`src/modes/utils/ui-helpers.ts`](../packages/coding-agent/src/modes/utils/ui-helpers.ts)\n- [`src/modes/controllers/command-controller.ts`](../packages/coding-agent/src/modes/controllers/command-controller.ts)\n\n## 1) Discovery model\n\nSlash commands are a capability (`id: \"slash-commands\"`) keyed by command name (`key: cmd => cmd.name`).\n\nThe capability registry loads all registered providers, sorted by provider priority descending, and deduplicates by key with **first wins** semantics.\n\n### Provider precedence\n\nCurrent slash-command providers and priorities:\n\n1. `native` (OMP) — priority `100`\n2. `claude` — priority `80`\n3. `claude-plugins` — priority `70`\n4. `codex` — priority `70`\n5. `opencode` — priority `55`\n\nTie behavior: equal-priority providers keep registration order. Current import order registers `claude-plugins` before `codex`, so plugin commands win over codex commands on name collisions.\n\n### Name-collision behavior\n\nFor `slash-commands`, collisions are resolved strictly by capability dedup:\n\n- highest-precedence item is kept in `result.items`\n- lower-precedence duplicates remain only in `result.all` and are marked `_shadowed = true`\n\nThis applies across providers and also within a provider if it returns duplicate names.\n\n### File scanning behavior\n\nProviders mostly use `loadFilesFromDir(...)`, which currently:\n\n- defaults to non-recursive matching (`*.md`)\n- uses native glob with `gitignore: true`, `hidden: false`, `fileType: File`\n- reads matching files in parallel and transforms them into `SlashCommand` items\n\nSo hidden files/directories are not loaded, ignored paths are skipped, and file order follows native glob result order unless a provider adds its own ordering.\n\n## 2) Provider-specific source paths and local precedence\n\n## `native` provider (`builtin.ts`)\n\nSearch roots come from `.omp` directories:\n\n- project: `<cwd>/.omp/commands/*.md`\n- user: `~/.omp/agent/commands/*.md`\n\n`getConfigDirs()` returns project first, then user, so **project native commands beat user native commands** when names collide.\n\n## `claude` provider (`claude.ts`)\n\nLoads, subject to `commands.enableClaudeUser` and `commands.enableClaudeProject` settings:\n\n- user: `~/.claude/commands/*.md`\n- project: `<cwd>/.claude/commands/*.md`\n\nThe provider pushes user items before project items, so **user Claude commands beat project Claude commands** on same-name collisions inside this provider.\n\n## `codex` provider (`codex.ts`)\n\nLoads:\n\n- user: `~/.codex/commands/*.md`\n- project: `<cwd>/.codex/commands/*.md`\n\nBoth sides are loaded then flattened in user-first order, so **user Codex commands beat project Codex commands** on collisions.\n\nCodex command content is parsed with frontmatter stripping (`parseFrontmatter`), and command name can be overridden by frontmatter `name`; otherwise filename is used.\n\n## `opencode` provider (`opencode.ts`)\n\nLoads, subject to `commands.enableOpencodeUser` and `commands.enableOpencodeProject` settings:\n\n- user: `~/.config/opencode/commands/*.md`\n- project: `<cwd>/.opencode/commands/*.md`\n\nBoth sides are loaded then flattened in user-first order, so **user OpenCode commands beat project OpenCode commands** on collisions. OpenCode command content is parsed with frontmatter stripping, and command name can be overridden by frontmatter `name`; otherwise filename is used.\n\n## `claude-plugins` provider (`claude-plugins.ts`)\n\nLoads plugin command roots from `~/.claude/plugins/installed_plugins.json`, then scans `<pluginRoot>/commands/*.md`.\n\nOrdering follows registry iteration order and per-plugin entry order from that JSON data. There is no additional sort step.\n\n## 3) Materialization to runtime `FileSlashCommand`\n\n`loadSlashCommands()` in `src/extensibility/slash-commands.ts` converts capability items into `FileSlashCommand` objects used at prompt time.\n\nFor each command:\n\n1. parse frontmatter/body (`parseFrontmatter`)\n2. description source:\n   - `frontmatter.description` if present\n   - else first non-empty body line (trimmed, max 60 chars with `...`)\n3. keep parsed body as executable template content\n4. compute a display source string like `via Claude Code Project`\n\nFrontmatter parse severity is source-dependent:\n\n- `native` level -> parse errors are `fatal`\n- `user`/`project` levels -> parse errors are `warn` with fallback parsing\n\n### Bundled fallback commands\n\nAfter filesystem/provider commands, embedded command templates are appended (`EMBEDDED_COMMAND_TEMPLATES`) if their names are not already present.\n\nCurrent embedded set comes from `src/task/commands.ts` and is used as a fallback (`source: \"bundled\"`).\n\n## 4) Interactive mode: where command lists come from\n\nInteractive mode combines multiple command sources for autocomplete and command routing.\n\nAt construction time it builds a pending command list from:\n\n- built-ins (`BUILTIN_SLASH_COMMANDS`, includes argument completion and inline hints for selected commands)\n- extension-registered slash commands (`extensionRunner.getRegisteredCommands(...)`)\n- TypeScript custom commands (`session.customCommands`), mapped to slash command labels\n- optional skill commands (`/skill:<name>`) when `skills.enableSkillCommands` is enabled\n\nThen `init()` calls `refreshSlashCommandState(...)` to load file-based commands and install one `CombinedAutocompleteProvider` containing:\n\n- pending commands above\n- discovered file-based commands\n\n`refreshSlashCommandState(...)` also updates `session.setSlashCommands(...)` so prompt expansion uses the same discovered file command set.\n\n### Refresh lifecycle\n\nSlash command state is refreshed:\n\n- during interactive init\n- after `/move` changes working directory (`handleMoveCommand` calls `resetCapabilities()` then `refreshSlashCommandState(newCwd)`)\n\nThere is no continuous file watcher for command directories.\n\n### Other surfacing\n\nThe Extensions dashboard also loads `slash-commands` capability and displays active/shadowed command entries, including `_shadowed` duplicates.\n\n## 5) Prompt pipeline placement\n\n`AgentSession.prompt(...)` slash handling order (when `expandPromptTemplates !== false`):\n\n1. **Extension commands** (`#tryExecuteExtensionCommand`)  \n   If `/name` matches extension-registered command, handler executes immediately and prompt returns.\n2. **TypeScript custom commands** (`#tryExecuteCustomCommand`)  \n   Boundary only: if matched, it executes and may return:\n   - `string` -> replace prompt text with that string\n   - `void/undefined` -> treated as handled; no LLM prompt\n3. **File-based slash commands** (`expandSlashCommand`)  \n   If text still starts with `/`, attempt markdown command expansion.\n4. **Prompt templates** (`expandPromptTemplate`)  \n   Applied after slash/custom processing.\n5. **Delivery**\n   - idle: prompt is sent immediately to agent\n   - streaming: prompt is queued as steer/follow-up depending on `streamingBehavior`\n\nThis is why slash command expansion sits before prompt-template expansion, and why custom commands can transform away the leading slash before file-command matching.\n\n## 6) Expansion semantics for file-based slash commands\n\n`expandSlashCommand(text, fileCommands)` behavior:\n\n- only runs when text begins with `/`\n- parses command name from first token after `/`\n- parses args from remaining text via `parseCommandArgs`\n- finds exact name match in loaded `fileCommands`\n- if matched, applies:\n  - positional replacement: `$1`, `$2`, ...\n  - slice replacement: `$@[start]` / `$@[start:length]` using 1-based positions\n  - aggregate replacement: `$ARGUMENTS` and `$@`\n  - template rendering via `prompt.render` with `{ args, ARGUMENTS, arguments }`\n  - inline-argument fallback append when the template did not use an inline argument placeholder\n\n### `parseCommandArgs` caveats\n\nThe parser is simple quote-aware splitting:\n\n- supports `'single'` and `\"double\"` quoting to keep spaces\n- strips quote delimiters\n- does not implement backslash escaping rules\n- unmatched quote is not an error; parser consumes until end\n\n## 7) Unknown `/...` behavior\n\nUnknown slash input is **not rejected** by core slash logic.\n\nIf command is not handled by extension/custom/file layers, `expandSlashCommand` returns original text, and the literal `/...` prompt proceeds through normal prompt-template expansion and LLM delivery.\n\nInteractive mode separately hard-handles many built-ins in `InputController` (for example `/settings`, `/model`, `/mcp`, `/move`, `/exit`). Those are consumed before `session.prompt(...)` and therefore never reach file-command expansion in that path.\n\n## 8) Streaming-time differences vs idle\n\n## Idle path\n\n- `session.prompt(\"/x ...\")` runs command pipeline and either executes command immediately or sends expanded text directly.\n\n## Streaming path (`session.isStreaming === true`)\n\n- `prompt(...)` still runs extension/custom/file/template transforms first\n- then requires `streamingBehavior`:\n  - `\"steer\"` -> queue interrupt message (`agent.steer`)\n  - `\"followUp\"` -> queue post-turn message (`agent.followUp`)\n- if `streamingBehavior` is omitted, prompt throws an error\n\n### Important command-specific streaming behavior\n\n- Extension commands are executed immediately even during streaming (not queued as text).\n- `steer(...)`/`followUp(...)` helper methods reject extension commands (`#throwIfExtensionCommand`) to avoid queuing command text for handlers that must run synchronously.\n- Compaction queue replay uses `isKnownSlashCommand(...)` to decide whether queued entries should be replayed via `session.prompt(...)` (for known slash commands) vs raw steer/follow-up methods.\n\n## 9) Error handling and failure surfaces\n\n- Provider load failures are isolated; registry collects warnings and continues with other providers.\n- Invalid slash command items (missing name/path/content or invalid level) are dropped by capability validation.\n- Frontmatter parse failures:\n  - native commands: fatal parse error bubbles\n  - non-native commands: warning + fallback key/value parse\n- Extension/custom command handler exceptions are caught and reported via extension error channel (or logger fallback for custom commands without extension runner), and treated as handled (no unintended fallback execution).\n",
 	"task-agent-discovery.md": "# Task Agent Discovery and Selection\n\nThis document describes how the task subsystem discovers agent definitions, merges multiple sources, and resolves a requested agent at execution time.\n\nIt covers runtime behavior as implemented today, including precedence, invalid-definition handling, and spawn/depth constraints that can make an agent effectively unavailable.\n\n## Implementation files\n\n- [`src/task/discovery.ts`](../packages/coding-agent/src/task/discovery.ts)\n- [`src/task/agents.ts`](../packages/coding-agent/src/task/agents.ts)\n- [`src/task/types.ts`](../packages/coding-agent/src/task/types.ts)\n- [`src/task/index.ts`](../packages/coding-agent/src/task/index.ts)\n- [`src/task/commands.ts`](../packages/coding-agent/src/task/commands.ts)\n- [`src/prompts/agents/task.md`](../packages/coding-agent/src/prompts/agents/task.md)\n- [`src/prompts/tools/task.md`](../packages/coding-agent/src/prompts/tools/task.md)\n- [`src/discovery/helpers.ts`](../packages/coding-agent/src/discovery/helpers.ts)\n- [`src/config.ts`](../packages/coding-agent/src/config.ts)\n- [`src/task/executor.ts`](../packages/coding-agent/src/task/executor.ts)\n\n---\n\n## Agent definition shape\n\nTask agents normalize into `AgentDefinition` (`src/task/types.ts`):\n\n- `name`, `description`, `systemPrompt` (required for a valid loaded agent)\n- optional `tools`, `spawns`, `model`, `thinkingLevel`, `output`, `blocking`\n- `source`: `\"bundled\" | \"user\" | \"project\"`\n- optional `filePath`\n\nParsing comes from frontmatter via `parseAgentFields()` (`src/discovery/helpers.ts`):\n\n- missing `name` or `description` => invalid (`null`), caller treats as parse failure\n- `tools` accepts CSV or array; if provided, `yield` is auto-added\n- `spawns` accepts `*`, CSV, or array\n- backward-compat behavior: if `spawns` missing but `tools` includes `task`, `spawns` becomes `*`\n- `output` is passed through as opaque schema data\n\n## Bundled agents\n\nBundled agents are embedded at build time (`src/task/agents.ts`) using text imports.\n\n`EMBEDDED_AGENT_DEFS` defines:\n\n- `explore`, `plan`, `designer`, `reviewer` from prompt files\n- `task` and `quick_task` from shared `task.md` body plus injected frontmatter\n\nLoading path:\n\n1. `loadBundledAgents()` parses embedded markdown with `parseAgent(..., \"bundled\", \"fatal\")`\n2. results are cached in-memory (`bundledAgentsCache`)\n3. `clearBundledAgentsCache()` is test-only cache reset\n\nBecause bundled parsing uses `level: \"fatal\"`, malformed bundled frontmatter throws and can fail discovery entirely.\n\n## Filesystem and plugin discovery\n\n`discoverAgents(cwd, home)` (`src/task/discovery.ts`) merges agents from multiple places before appending bundled definitions.\n\n### Discovery inputs\n\n1. User config agent dirs from `getConfigDirs(\"agents\", { project: false })`\n2. Nearest project agent dirs from `findAllNearestProjectConfigDirs(\"agents\", cwd)`\n3. Claude plugin roots (`listClaudePluginRoots(home)`) with `agents/` subdirs\n4. Bundled agents (`loadBundledAgents()`)\n\n### Actual source order\n\nSource-family order comes from `getConfigDirs(\"\", { project: false })`, which is derived from `priorityList` in `src/config.ts`:\n\n1. `.omp`\n2. `.claude`\n3. `.codex`\n4. `.gemini`\n\nFor each source family, discovery order is:\n\n1. nearest project dir for that source (if found)\n2. user dir for that source\n\nAfter all source-family dirs, plugin `agents/` dirs are appended (project-scope plugins first, then user-scope).\n\nBundled agents are appended last.\n\n### Important caveat: stale comments vs current code\n\n`discovery.ts` header comments still mention `.pi` and do not mention `.codex`/`.gemini`. Actual runtime order is driven by `src/config.ts` and currently uses `.omp`, `.claude`, `.codex`, `.gemini`.\n\n## Merge and collision rules\n\nDiscovery uses first-wins dedup by exact `agent.name`:\n\n- A `Set<string>` tracks seen names.\n- Loaded agents are flattened in directory order and kept only if name unseen.\n- Bundled agents are filtered against the same set and only added if still unseen.\n\nImplications:\n\n- Project overrides user for same source family.\n- Higher-priority source family overrides lower (`.omp` before `.claude`, etc.).\n- Non-bundled agents override bundled agents with the same name.\n- Name matching is case-sensitive (`Task` and `task` are distinct).\n- Within one directory, markdown files are read in lexicographic filename order before dedup.\n\n## Invalid/missing agent file behavior\n\nPer directory (`loadAgentsFromDir`):\n\n- unreadable/missing directory: treated as empty (`readdir(...).catch(() => [])`)\n- file read or parse failure: warning logged, file skipped\n- parse path uses `parseAgent(..., level: \"warn\")`\n\nFrontmatter failure behavior comes from `parseFrontmatter`:\n\n- parse error at `warn` level logs warning\n- parser falls back to a simple `key: value` line parser\n- if required fields are still missing, `parseAgentFields` fails, then `AgentParsingError` is thrown and caught by caller (file skipped)\n\nNet effect: one bad custom agent file does not abort discovery of other files.\n\n## Agent lookup and selection\n\nLookup is exact-name linear search:\n\n- `getAgent(agents, name)` => `agents.find(a => a.name === name)`\n\nIn synchronous task execution (`TaskTool.#executeSync`):\n\n1. agents are rediscovered at execution time (`discoverAgents(this.session.cwd)`)\n2. requested `params.agent` is resolved through `getAgent`\n3. missing agent returns immediate tool response:\n   - `Unknown agent \"...\". Available: ...`\n   - no subprocess runs\n\n### Description vs execution-time discovery\n\n`TaskTool.create()` builds the tool description from discovery results at initialization time. `#executeSync` rediscovers agents, so the runtime set can differ from what was listed in the earlier tool description if agent files changed mid-session. The async entry path still uses the initialization-time list to decide whether an agent is marked `blocking` before scheduling.\n\n## Structured-output guardrails and schema precedence\n\nRuntime output schema precedence in `TaskTool.execute`:\n\n1. task call `params.schema` when `task.simple` allows custom schemas\n2. agent frontmatter `output`\n3. parent session `outputSchema`\n\n(`effectiveOutputSchema = outputSchema ?? effectiveAgent.output ?? this.session.outputSchema` when custom task schemas are enabled; otherwise task-call schema is skipped.)\n\nPrompt-time guardrail text in `src/prompts/tools/task.md` warns about mismatch behavior for structured-output agents (`explore`, `reviewer`): output-format instructions in prose can conflict with built-in schema and produce `null` outputs.\n\nThis is guidance, not hard runtime validation logic in `discoverAgents`.\n\n## Command discovery interaction\n\n`src/task/commands.ts` is parallel infrastructure for workflow commands (not agent definitions), but it follows the same overall pattern:\n\n- discover from capability providers first\n- deduplicate by name with first-wins\n- append bundled commands if still unseen\n- exact-name lookup via `getCommand`\n\nIn `src/task/index.ts`, command helpers are re-exported with agent discovery helpers. Agent discovery itself does not depend on command discovery at runtime.\n\n## Availability constraints beyond discovery\n\nAn agent can be discoverable but still unavailable to run because of execution guardrails.\n\n### Disabled-agent settings\n\n`TaskTool.#executeSync` checks `task.disabledAgents` after resolving the agent. If the requested name is disabled, execution returns an immediate error listing enabled alternatives when available.\n\n### Parent spawn policy\n\n`TaskTool.#executeSync` checks `session.getSessionSpawns()`:\n\n- `\"*\"` => allow any\n- `\"\"` => deny all\n- CSV list => allow only listed names\n\nIf denied: immediate `Cannot spawn '...'. Allowed: ...` response.\n\n### Blocked self-recursion env guard\n\n`PI_BLOCKED_AGENT` is read at tool construction. If request matches, execution is rejected with recursion-prevention message.\n\n### Recursion-depth gating (task tool availability inside child sessions)\n\nIn `runSubprocess` (`src/task/executor.ts`):\n\n- depth computed from `taskDepth`\n- `task.maxRecursionDepth` controls cutoff\n- when at max depth:\n  - `task` tool is removed from child tool list\n  - child `spawns` env is set to empty\n\nSo deeper levels cannot spawn further tasks even if the agent definition includes `spawns`.\n\n## Plan mode caveat (current implementation)\n\n`TaskTool.execute` computes an `effectiveAgent` for plan mode (prepends plan-mode prompt, forces read-only tool subset, clears spawns), but `runSubprocess` is called with `agent` rather than `effectiveAgent`.\n\nCurrent effect:\n\n- model override / thinking level / output schema are derived from `effectiveAgent`\n- system prompt and tool/spawn restrictions from `effectiveAgent` are not passed through in this call path\n\nThis is an implementation caveat worth knowing when reading plan-mode behavior expectations.\n",
 	"theme.md": "# Theming Reference\n\nThis document describes how theming works in the coding-agent today: schema, loading, runtime behavior, and failure modes.\n\n## What the theme system controls\n\nThe theme system drives:\n\n- foreground/background color tokens used across the TUI\n- markdown styling adapters (`getMarkdownTheme()`)\n- selector/editor/settings list adapters (`getSelectListTheme()`, `getEditorTheme()`, `getSettingsListTheme()`)\n- symbol preset + symbol overrides (`unicode`, `nerd`, `ascii`)\n- syntax highlighting colors used by native highlighter (`@oh-my-pi/pi-natives`)\n- status line segment colors\n\nPrimary implementation: `src/modes/theme/theme.ts`.\n\n## Theme JSON shape\n\nTheme files are JSON objects validated against the runtime schema in `theme.ts` (`ThemeJsonSchema`) and mirrored by `src/modes/theme/theme-schema.json`.\n\nTop-level fields:\n\n- `name` (required)\n- `colors` (required; all color tokens required)\n- `vars` (optional; reusable color variables)\n- `export` (optional; HTML export colors)\n- `symbols` (optional)\n  - `preset` (optional: `unicode | nerd | ascii`)\n  - `overrides` (optional: key/value overrides for `SymbolKey`)\n\nColor values accept:\n\n- hex string (`\"#RRGGBB\"`)\n- 256-color index (`0..255`)\n- variable reference string (resolved through `vars`)\n- empty string (`\"\"`) meaning terminal default (`\\x1b[39m` fg, `\\x1b[49m` bg)\n\n## Required color tokens (current)\n\nAll tokens below are required in `colors`.\n\n### Core text and borders (11)\n\n`accent`, `border`, `borderAccent`, `borderMuted`, `success`, `error`, `warning`, `muted`, `dim`, `text`, `thinkingText`\n\n### Background blocks (7)\n\n`selectedBg`, `userMessageBg`, `customMessageBg`, `toolPendingBg`, `toolSuccessBg`, `toolErrorBg`, `statusLineBg`\n\n### Message/tool text (5)\n\n`userMessageText`, `customMessageText`, `customMessageLabel`, `toolTitle`, `toolOutput`\n\n### Markdown (10)\n\n`mdHeading`, `mdLink`, `mdLinkUrl`, `mdCode`, `mdCodeBlock`, `mdCodeBlockBorder`, `mdQuote`, `mdQuoteBorder`, `mdHr`, `mdListBullet`\n\n### Tool diff + syntax highlighting (12)\n\n`toolDiffAdded`, `toolDiffRemoved`, `toolDiffContext`,\n`syntaxComment`, `syntaxKeyword`, `syntaxFunction`, `syntaxVariable`, `syntaxString`, `syntaxNumber`, `syntaxType`, `syntaxOperator`, `syntaxPunctuation`\n\n### Mode/thinking borders (8)\n\n`thinkingOff`, `thinkingMinimal`, `thinkingLow`, `thinkingMedium`, `thinkingHigh`, `thinkingXhigh`, `bashMode`, `pythonMode`\n\n### Status line segment colors (14)\n\n`statusLineSep`, `statusLineModel`, `statusLinePath`, `statusLineGitClean`, `statusLineGitDirty`, `statusLineContext`, `statusLineSpend`, `statusLineStaged`, `statusLineDirty`, `statusLineUntracked`, `statusLineOutput`, `statusLineCost`, `statusLineSubagents`\n\n## Optional tokens\n\n### `export` section (optional)\n\nUsed for HTML export theming helpers:\n\n- `export.pageBg`\n- `export.cardBg`\n- `export.infoBg`\n\nIf omitted, export code derives defaults from resolved theme colors.\n\n### `symbols` section (optional)\n\n- `symbols.preset` sets a theme-level default symbol set.\n- `symbols.overrides` can override individual `SymbolKey` values.\n\nRuntime precedence:\n\n1. settings `symbolPreset` override (if set)\n2. theme JSON `symbols.preset`\n3. fallback `\"unicode\"`\n\nInvalid override keys are ignored and logged (`logger.debug`).\n\n## Built-in vs custom theme sources\n\nTheme lookup order (`loadThemeJson`):\n\n1. built-in embedded themes (`dark.json`, `light.json`, and all `defaults/*.json` compiled into `defaultThemes`)\n2. custom theme file: `<customThemesDir>/<name>.json`\n\nCustom themes directory comes from `getCustomThemesDir()`:\n\n- default: `~/.omp/agent/themes`\n- overridden by `PI_CODING_AGENT_DIR` (`$PI_CODING_AGENT_DIR/themes`)\n\n`getAvailableThemes()` returns merged built-in + custom names, sorted, with built-ins taking precedence on name collision.\n\n## Loading, validation, and resolution\n\nFor custom theme files:\n\n1. read JSON\n2. parse JSON\n3. validate against `ThemeJsonSchema`\n4. resolve `vars` references recursively\n5. convert resolved values to ANSI by terminal capability mode\n\nValidation behavior:\n\n- missing required color tokens: explicit grouped error message\n- bad token types/values: validation errors with JSON path\n- unknown theme file: `Theme not found: <name>`\n\nVar reference behavior:\n\n- supports nested references\n- throws on missing variable reference\n- throws on circular references\n\n## Terminal color mode behavior\n\nColor mode detection (`detectColorMode`):\n\n- `COLORTERM=truecolor|24bit` => truecolor\n- `WT_SESSION` => truecolor\n- `TERM` in `dumb`, `linux`, or empty => 256color\n- otherwise => truecolor\n\nConversion behavior:\n\n- hex -> `Bun.color(..., \"ansi-16m\" | \"ansi-256\")`\n- numeric -> `38;5` / `48;5` ANSI\n- `\"\"` -> default fg/bg reset\n\n## Runtime switching behavior\n\n### Initial theme (`initTheme`)\n\n`main.ts` initializes theme with settings:\n\n- `symbolPreset`\n- `colorBlindMode`\n- `theme.dark`\n- `theme.light`\n\nAuto theme slot selection uses terminal appearance in this order:\n\n1. terminal-reported OSC 11 background luminance, unless the macOS/Zellij fallback path is active\n2. `COLORFGBG` background index (`< 8` => dark, `>= 8` => light)\n3. macOS appearance fallback only for the known-broken macOS/Zellij OSC 11 path\n4. dark slot fallback\n\nCurrent defaults from settings schema:\n\n- `theme.dark = \"titanium\"`\n- `theme.light = \"light\"`\n- `symbolPreset = \"unicode\"`\n- `colorBlindMode = false`\n\n### Explicit switching (`setTheme`)\n\n- loads selected theme\n- updates global `theme` singleton\n- optionally starts watcher\n- triggers `onThemeChange` callback\n\nOn failure:\n\n- falls back to built-in `dark`\n- returns `{ success: false, error }`\n\n### Preview switching (`previewTheme`)\n\n- applies temporary preview theme to global `theme`\n- does **not** change persisted settings by itself\n- returns success/error without fallback replacement\n\nSettings UI uses this for live preview and restores prior theme on cancel.\n\n## Watchers and live reload\n\nWhen watcher is enabled (`setTheme(..., true)` / interactive init):\n\n- watches `<customThemesDir>/<currentTheme>.json` only when that file exists\n- built-ins are effectively not watched; built-in theme lookup also takes precedence over same-name custom files\n- matching file changes schedule a debounced reload; reload errors or temporary file absence keep the last successfully loaded theme\n- the watcher does not perform a delete/rename fallback; it waits for a future successful reload or explicit theme switch\n\nAuto mode also reevaluates dark/light slot mapping from terminal appearance changes, `SIGWINCH`, and the macOS fallback observer when active.\n\n## Color-blind mode behavior\n\n`colorBlindMode` changes only one token at runtime:\n\n- `toolDiffAdded` is HSV-adjusted (green shifted toward blue)\n- adjustment is applied only when resolved value is a hex string\n\nOther tokens are unchanged.\n\n## Where theme settings are persisted\n\nTheme-related settings are persisted by `Settings` to global config YAML:\n\n- path: `<agentDir>/config.yml`\n- default agent dir: `~/.omp/agent`\n- effective default file: `~/.omp/agent/config.yml`\n\nPersisted keys:\n\n- `theme.dark`\n- `theme.light`\n- `symbolPreset`\n- `colorBlindMode`\n\nLegacy migration exists: old flat `theme: \"name\"` is migrated to nested `theme.dark` or `theme.light` based on luminance detection.\n\n## Creating a custom theme (practical)\n\n1. Create file in custom themes dir, e.g. `~/.omp/agent/themes/my-theme.json`.\n2. Include `name`, optional `vars`, and **all required** `colors` tokens.\n3. Optionally include `symbols` and `export`.\n4. Select the theme in Settings (`Display -> Dark theme` or `Display -> Light theme`) depending on which auto slot you want.\n\nMinimal skeleton:\n\n```json\n{\n  \"name\": \"my-theme\",\n  \"vars\": {\n    \"accent\": \"#7aa2f7\",\n    \"muted\": 244\n  },\n  \"colors\": {\n    \"accent\": \"accent\",\n    \"border\": \"#4c566a\",\n    \"borderAccent\": \"accent\",\n    \"borderMuted\": \"muted\",\n    \"success\": \"#9ece6a\",\n    \"error\": \"#f7768e\",\n    \"warning\": \"#e0af68\",\n    \"muted\": \"muted\",\n    \"dim\": 240,\n    \"text\": \"\",\n    \"thinkingText\": \"muted\",\n\n    \"selectedBg\": \"#2a2f45\",\n    \"userMessageBg\": \"#1f2335\",\n    \"userMessageText\": \"\",\n    \"customMessageBg\": \"#24283b\",\n    \"customMessageText\": \"\",\n    \"customMessageLabel\": \"accent\",\n    \"toolPendingBg\": \"#1f2335\",\n    \"toolSuccessBg\": \"#1f2d2a\",\n    \"toolErrorBg\": \"#2d1f2a\",\n    \"toolTitle\": \"\",\n    \"toolOutput\": \"muted\",\n\n    \"mdHeading\": \"accent\",\n    \"mdLink\": \"accent\",\n    \"mdLinkUrl\": \"muted\",\n    \"mdCode\": \"#c0caf5\",\n    \"mdCodeBlock\": \"#c0caf5\",\n    \"mdCodeBlockBorder\": \"muted\",\n    \"mdQuote\": \"muted\",\n    \"mdQuoteBorder\": \"muted\",\n    \"mdHr\": \"muted\",\n    \"mdListBullet\": \"accent\",\n\n    \"toolDiffAdded\": \"#9ece6a\",\n    \"toolDiffRemoved\": \"#f7768e\",\n    \"toolDiffContext\": \"muted\",\n\n    \"syntaxComment\": \"#565f89\",\n    \"syntaxKeyword\": \"#bb9af7\",\n    \"syntaxFunction\": \"#7aa2f7\",\n    \"syntaxVariable\": \"#c0caf5\",\n    \"syntaxString\": \"#9ece6a\",\n    \"syntaxNumber\": \"#ff9e64\",\n    \"syntaxType\": \"#2ac3de\",\n    \"syntaxOperator\": \"#89ddff\",\n    \"syntaxPunctuation\": \"#9aa5ce\",\n\n    \"thinkingOff\": 240,\n    \"thinkingMinimal\": 244,\n    \"thinkingLow\": \"#7aa2f7\",\n    \"thinkingMedium\": \"#2ac3de\",\n    \"thinkingHigh\": \"#bb9af7\",\n    \"thinkingXhigh\": \"#f7768e\",\n\n    \"bashMode\": \"#2ac3de\",\n    \"pythonMode\": \"#bb9af7\",\n\n    \"statusLineBg\": \"#16161e\",\n    \"statusLineSep\": 240,\n    \"statusLineModel\": \"#bb9af7\",\n    \"statusLinePath\": \"#7aa2f7\",\n    \"statusLineGitClean\": \"#9ece6a\",\n    \"statusLineGitDirty\": \"#e0af68\",\n    \"statusLineContext\": \"#2ac3de\",\n    \"statusLineSpend\": \"#7dcfff\",\n    \"statusLineStaged\": \"#9ece6a\",\n    \"statusLineDirty\": \"#e0af68\",\n    \"statusLineUntracked\": \"#f7768e\",\n    \"statusLineOutput\": \"#c0caf5\",\n    \"statusLineCost\": \"#ff9e64\",\n    \"statusLineSubagents\": \"#bb9af7\"\n  }\n}\n```\n\n## Testing custom themes\n\nUse this workflow:\n\n1. Start interactive mode (watcher enabled from startup).\n2. Open settings and preview theme values (live `previewTheme`).\n3. For custom theme files, edit the JSON while running and confirm auto-reload on save.\n4. Exercise critical surfaces:\n   - markdown rendering\n   - tool blocks (pending/success/error)\n   - diff rendering (added/removed/context)\n   - status line readability\n   - thinking level border changes\n   - bash/python mode border colors\n5. Validate both symbol presets if your theme depends on glyph width/appearance.\n\n## Real constraints and caveats\n\n- All `colors` tokens are required for custom themes.\n- `export` and `symbols` are optional.\n- `$schema` in theme JSON is informational; runtime validation is enforced by compiled TypeBox schema in code.\n- `setTheme` failure falls back to `dark`; `previewTheme` failure does not replace current theme.\n- File watcher reload errors or temporary missing files keep the current loaded theme until a successful reload or explicit theme switch.\n",
+	"tools/ask.md": "# ask\n\n> Prompts the interactive user for one or more choices or free-form answers.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ask.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ask.md`\n- Key collaborators:\n  - `packages/coding-agent/src/config/settings-schema.ts` — `ask.timeout` / `ask.notify` defaults\n  - `packages/coding-agent/src/modes/theme/theme.ts` — checkbox and tree glyphs for TUI rendering\n  - `packages/coding-agent/src/tui.ts` — status-line rendering\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `questions` | `Question[]` | Yes | One or more questions. Empty arrays are rejected by schema and also guarded at runtime. |\n\n### `Question`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `id` | `string` | Yes | Stable identifier used in multi-question results. |\n| `question` | `string` | Yes | Prompt text shown to the user. |\n| `options` | `{ label: string }[]` | Yes | Explicit options. The UI always appends `Other (type your own)`; callers must not include it. |\n| `multi` | `boolean` | No | Enables multi-select mode. Default: `false`. |\n| `recommended` | `number` | No | Zero-based recommended option index. In single-select mode the label gets ` (Recommended)` appended in the UI. |\n\n## Outputs\n- Single-shot result.\n- `content[0].text` is plain text:\n  - single question: `User selected: ...` and/or `User provided custom input: ...`\n  - multiple questions: `User answers:` followed by one line per `id`\n- `details`:\n  - single question: `{ question, options, multi, selectedOptions, customInput? }`\n  - multiple questions: `{ results: QuestionResult[] }`, where each item includes `id`, `question`, `options`, `multi`, `selectedOptions`, and optional `customInput`\n- Cancellation and headless cases throw instead of returning a structured success result.\n\n## Flow\n1. `AskTool.createIf()` only registers the tool when `session.hasUI` is true; headless sessions never get it.\n2. `execute()` requires `context.ui`; if missing it aborts the context and throws `ToolAbortError(\"Ask tool requires interactive mode\")`.\n3. It reads `ask.timeout` from settings, converts seconds to milliseconds, and disables timeout entirely while plan mode is enabled (`packages/coding-agent/src/tools/ask.ts`).\n4. If `ask.notify` is not `off`, it sends a terminal notification: `Waiting for input`.\n5. For each question, `askSingleQuestion()` drives either:\n   - single-select list + optional editor for `Other`\n   - multi-select checkbox loop + `Done selecting` sentinel + optional editor for `Other`\n6. In multi-question mode, left/right arrow handlers enable back/forward navigation between questions and preserve prior selections.\n7. If a timeout fires before any selection/custom input, the tool auto-selects the recommended option, or the first option when no valid `recommended` index exists.\n8. If the user cancels without timeout, `execute()` aborts the tool context and throws `ToolAbortError(\"Ask tool was cancelled by the user\")`.\n9. On success it formats human-readable text plus structured `details`; the TUI renderer uses `details` for rich display.\n\n## Modes / Variants\n- Single question: returns flattened `details` fields for one question.\n- Multiple questions: returns `details.results[]` and allows back/forward navigation across questions.\n- Single-select: one option or custom input.\n- Multi-select: toggled checkbox list, `Done selecting` sentinel only when forward navigation is not active.\n\n## Side Effects\n- User-visible prompts / interactive UI\n  - Opens a selection dialog via `context.ui.select(...)`.\n  - Opens a text editor dialog via `context.ui.editor(...)` for `Other`.\n  - Sends a terminal notification unless `ask.notify=off`.\n- Session state\n  - Reads plan-mode state to disable timeouts.\n  - Calls `context.abort()` on headless use or user cancellation.\n- Background work / cancellation\n  - Wraps UI waits in `untilAborted(...)` so abort signals interrupt pending dialogs.\n\n## Limits & Caps\n- `questions` must contain at least 1 item (`askSchema` in `packages/coding-agent/src/tools/ask.ts`).\n- `ask.timeout` default is `30` seconds; `0` disables timeout (`packages/coding-agent/src/config/settings-schema.ts`).\n- Prompt guidance says provide 2-5 options, but code does not enforce that (`packages/coding-agent/src/prompts/tools/ask.md`).\n- Timeout only applies to the option picker; once the user chooses `Other`, the editor has no timeout (`packages/coding-agent/src/prompts/tools/ask.md`).\n\n## Errors\n- Missing interactive UI: throws `ToolAbortError(\"Ask tool requires interactive mode\")`.\n- User cancels picker/editor without timeout: throws `ToolAbortError(\"Ask tool was cancelled by the user\")`.\n- Abort signal during input: converted to `ToolAbortError(\"Ask input was cancelled\")`.\n- Empty `questions` at runtime returns a text error payload instead of throwing: `Error: questions must not be empty`.\n\n## Notes\n- `recommended` is only a UI hint; invalid indexes are ignored.\n- In single-select mode the returned `selectedOptions` value strips the appended ` (Recommended)` suffix.\n- Multi-select results preserve selection order by `Set` insertion order, not original option order after arbitrary toggles.\n- Option labels and prompt text are returned verbatim in `details`; the tool does not interpret them beyond UI affordances like `Other` and ` (Recommended)`.\n",
+	"tools/ast-edit.md": "# ast_edit\n\n> Preview and apply structural rewrites over source files via native ast-grep.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ast-edit.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ast-edit.md`\n- Key collaborators:\n  - `crates/pi-natives/src/ast.rs` — native rewrite planning and file mutation\n  - `crates/pi-natives/src/language/mod.rs` — language aliases and extension inference\n  - `packages/coding-agent/src/tools/path-utils.ts` — path/glob parsing and multi-path resolution\n  - `packages/coding-agent/src/tools/resolve.ts` — preview/apply queueing\n  - `packages/coding-agent/src/tools/render-utils.ts` — parse-error dedupe and display caps\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — hashline vs line-number diff references\n  - `packages/coding-agent/src/hashline/hash.ts` — stable hashline diff anchors\n  - `packages/natives/native/index.d.ts` — JS-visible native binding contract\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `ops` | `{ pat: string; out: string }[]` | Yes | One or more rewrite rules. `pat` must be non-empty. Duplicate `pat` values fail before native execution. Empty `out` deletes the matched node. |\n| `paths` | `string[]` | Yes | One or more files, directories, globs, or internal URLs with backing files. Empty entries are rejected. Globs are forbidden for internal URLs. |\n\nShared AST pattern grammar and language catalog: see [`ast_grep`](./ast-grep.md#inputs).\n\n- `ast_edit` uses the same `$NAME`, `$_`, `$$$NAME`, and `$$$` metavariable semantics.\n- The tool prompt adds rewrite-specific constraints:\n  - metavariable names must be uppercase and must stand for whole AST nodes,\n  - captures from `pat` are substituted into `out`,\n  - each rewrite is a 1:1 structural substitution; one capture cannot expand into multiple sibling nodes unless the grammar itself permits that expansion at that position.\n\n## Outputs\n- Single-shot preview result from `ast_edit` itself.\n- Model-facing `content` is one text block showing proposed edits, grouped by file for directory/multi-file runs.\n  - Each change renders as two lines: `-REF|before` and `+REF|after` in hashline mode, or `-LINE:COLUMN before` / `+LINE:COLUMN after` when hashlines are off.\n  - Only the first line of each `before`/`after` snippet is shown, truncated to 120 characters in the wrapper.\n  - `Limit reached; narrow paths.` and formatted parse issues are appended when applicable.\n- If no rewrites match, text is `No replacements made` plus formatted parse issues when present.\n- `details` includes aggregate preview metadata:\n  - `totalReplacements`, `filesTouched`, `filesSearched`, `applied`, `limitReached`\n  - optional `parseErrors`, `scopePath`, `files`, `fileReplacements`, `displayContent`, `meta`\n- The tool always previews first (`applied: false` in the direct result). Actual file writes happen only later through `resolve(action: \"apply\", ...)`.\n- When preview produced replacements, `ast_edit` also queues a pending `resolve` action. Successful apply returns a separate `resolve` result, not another `ast_edit` result.\n\n## Flow\n1. `AstEditTool.execute()` validates each op in `packages/coding-agent/src/tools/ast-edit.ts`:\n   - empty `pat` fails,\n   - at least one op is required,\n   - duplicate `pat` values fail,\n   - ops are converted to a `Record<pattern, replacement>`.\n2. The wrapper reads `PI_MAX_AST_FILES` via `$envpos(..., 1000)` and uses that as the native `maxFiles` cap for both preview and apply.\n3. Path normalization, internal URL handling, missing-path partitioning, and multi-path resolution follow the same `path-utils.ts` flow as `ast_grep`.\n4. The wrapper stats the resolved base path to decide whether to render grouped directory output.\n5. `runAstEditOnce(...)` always runs native `astEdit(...)` with `dryRun: true` and `failOnParseError: false` on the first pass.\n6. Native `ast_edit` in `crates/pi-natives/src/ast.rs`:\n   - normalizes the rewrite map and sorts rules by pattern string,\n   - resolves strictness (`smart` by default),\n   - collects candidate files from a file or gitignore-aware directory scan,\n   - infers a single language for the whole call unless `lang` was supplied,\n   - compiles every rewrite pattern for that language,\n   - parses each file, skips files with syntax-error trees, collects `replace_by(...)` edits for every match, enforces replacement and file caps, and returns textual before/after slices plus source ranges.\n7. The TS wrapper deduplicates parse errors, groups changes by file, and renders preview diff lines.\n8. If preview found replacements and `applied` is false, `queueResolveHandler(...)` registers a forced `resolve` action and injects a `resolve-reminder` steering message.\n9. On `resolve(action: \"apply\")`, the queued callback reruns the same rewrite set with `dryRun: false`, recomputes counts, and rejects the apply as an error if the live result no longer matches the preview (`stalePreview`).\n10. On a non-stale apply, the callback returns `Applied N replacements in M files.`; on discard, `resolve` returns a discard message without mutating files.\n\n## Modes / Variants\n- Single file: preview or apply against one file.\n- Directory + optional glob: native scan walks the directory, then filters by compiled glob.\n- Multiple explicit paths/globs: wrapper unions them into one synthetic scope or runs per-target native calls when paths only meet at root.\n- Internal URL inputs: only supported when the router resolves them to a backing file path.\n- Preview mode: always the direct `ast_edit` tool result.\n- Apply mode: only reachable through the queued `resolve` callback after a preview.\n- Hashline output mode vs plain line/column mode: controlled by `resolveFileDisplayMode()`.\n\n## Side Effects\n- Filesystem\n  - Preview reads files and scans directories.\n  - Apply rewrites files in place with `std::fs::write(...)`, but only when the computed output differs from the original source.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Queues a one-shot forced `resolve` tool choice through `queueResolveHandler(...)`.\n  - Adds a `resolve-reminder` steering message.\n- User-visible prompts / interactive UI\n  - Direct `ast_edit` results are previews.\n  - Follow-up apply/discard is exposed through the hidden `resolve` tool.\n- Background work / cancellation\n  - Native preview/apply work runs on a blocking worker via `task::blocking(...)`.\n  - Cancellation and optional native timeout are cooperative through `CancelToken::heartbeat()`.\n\n## Limits & Caps\n- File cap exposed by the wrapper: `PI_MAX_AST_FILES`, default `1000`, in `packages/coding-agent/src/tools/ast-edit.ts`.\n- Native `maxFiles` and `maxReplacements` are both clamped to at least `1` when provided in `crates/pi-natives/src/ast.rs`.\n- The wrapper never sets `maxReplacements`; native behavior therefore defaults to effectively unbounded replacements for a run.\n- Parse issues are rendered with at most `PARSE_ERRORS_LIMIT = 20` lines in `packages/coding-agent/src/tools/render-utils.ts`; `details.parseErrors` is deduplicated but not capped.\n- Directory scans use `include_hidden: true`, `use_gitignore: true`, and skip `node_modules` unless the glob text explicitly mentions `node_modules` in `crates/pi-natives/src/ast.rs`.\n- No separate glob-expansion count cap exists. Candidate count is whatever the resolved path/glob expands to after gitignore filtering, then native `maxFiles` stops mutations after the configured number of touched files.\n- Preview text truncates each rendered `before` and `after` first line to 120 characters in `packages/coding-agent/src/tools/ast-edit.ts`.\n\n## Errors\n- TS wrapper throws `ToolError` for empty patterns, duplicate rewrite patterns, empty path entries, unsupported internal-URL globs, internal URLs without `sourcePath`, and missing paths.\n- Native code returns hard errors for:\n  - inability to infer one language across all candidates when `lang` is absent,\n  - unsupported explicit `lang`,\n  - bad glob compilation or unreadable search roots,\n  - overlapping computed edits (`Overlapping replacements detected; refine pattern to avoid ambiguous edits`),\n  - out-of-bounds edit ranges or non-UTF-8 replacement text,\n  - write failures during apply,\n  - cancellation or timeout.\n- With `failOnParseError: false` (the wrapper always uses this), pattern compile failures and file parse failures become `parseErrors` instead of aborting the whole run.\n- If every rewrite pattern fails to compile, native `ast_edit` returns a successful zero-replacement result with `parseErrors` populated.\n- Files containing tree-sitter error nodes are skipped for rewriting; they do not get partial edits.\n- Apply can fail after a successful preview if the preview becomes stale. The resolve callback compares replacement totals and per-file counts and returns an error result rather than applying a mismatched preview silently.\n\n## Notes\n- `ast_edit` does not expose the native `lang`, `strictness`, `selector`, `maxReplacements`, `failOnParseError`, or `timeoutMs` fields to the model. The runtime fixes the call shape to a preview-first, smart-strictness, best-effort parse mode.\n- Because the wrapper does not expose `lang`, mixed-language rewrites only succeed when every candidate infers to the same canonical language. This is stricter than `ast_grep`.\n- Idempotency is not enforced syntactically. A rewrite like `foo($A) -> foo($A)` previews zero changes because output equals input; a rewrite that keeps matching its own output may still produce replacements on repeated calls.\n- Rewrites are accumulated per file, then applied from the end of the file backward after an overlap check. Independent matches can coexist; overlapping matches abort the run.\n- Native rewrite rule order is by pattern-string sort, not by the original `ops` array order, because `normalize_rewrite_map(...)` sorts the `(pattern, rewrite)` pairs.\n- Preview/apply parity is validated only by totals and per-file counts, not by a byte-for-byte diff of every replacement payload.",
+	"tools/ast-grep.md": "# ast_grep\n\n> Structural code search over supported source files via native ast-grep.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ast-grep.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ast-grep.md`\n- Key collaborators:\n  - `crates/pi-natives/src/ast.rs` — native scan, parse, match engine\n  - `crates/pi-natives/src/language/mod.rs` — language aliases and extension inference\n  - `packages/coding-agent/src/tools/path-utils.ts` — path/glob parsing and multi-path resolution\n  - `packages/coding-agent/src/tools/render-utils.ts` — parse-error dedupe and display caps\n  - `packages/coding-agent/src/tools/match-line-format.ts` — anchor-prefixed match rendering\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — hashline vs line-number output mode\n  - `packages/natives/native/index.d.ts` — JS-visible native binding contract\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `pat` | `string` | Yes | Single AST pattern. The wrapper trims it and rejects empty strings. |\n| `paths` | `string[]` | Yes | One or more files, directories, globs, or internal URLs with backing files. Empty entries are rejected. Globs are forbidden for internal URLs. |\n| `skip` | `number` | No | Match offset. Defaults to `0`, then `Math.floor(...)`; negatives and non-finite values fail. |\n\nPattern grammar and language support exposed to the model:\n- `$NAME` — capture one AST node.\n- `$_` — match one AST node without binding.\n- `$$$NAME` — capture zero or more AST nodes; ast-grep stops lazily at the next satisfiable node.\n- `$$$` — match zero or more AST nodes without binding.\n- Metavariable names must be uppercase and must stand for whole AST nodes, not partial tokens or string fragments.\n- Reusing the same metavariable requires identical code at each occurrence.\n- Patterns must parse as one valid AST node for the inferred target language.\n- Supported canonical languages come from `SupportLang::all_langs()` in `crates/pi-natives/src/language/mod.rs`: `astro`, `bash`, `c`, `cmake`, `cpp`, `csharp`, `dart`, `clojure`, `css`, `diff`, `dockerfile`, `elixir`, `erlang`, `go`, `graphql`, `haskell`, `hcl`, `html`, `ini`, `java`, `javascript`, `json`, `just`, `julia`, `kotlin`, `lua`, `make`, `markdown`, `nix`, `objc`, `ocaml`, `odin`, `perl`, `php`, `powershell`, `protobuf`, `python`, `r`, `regex`, `ruby`, `rust`, `scala`, `solidity`, `sql`, `starlark`, `svelte`, `swift`, `toml`, `tlaplus`, `tsx`, `typescript`, `verilog`, `vue`, `xml`, `yaml`, `zig`.\n\n## Outputs\n- Single-shot tool result.\n- Model-facing `content` is one text block:\n  - grouped by file for directory/multi-file searches,\n  - match lines rendered as `*LINE+HASH|text` in hashline mode or `*LINE|text` otherwise,\n  - continuation lines for multi-line matches rendered with a leading space,\n  - optional `meta: NAME=value` lines when ast-grep captured metavariables.\n- If no matches are found, text is `No matches found` or `No matches found. Parse issues mean the query may be mis-scoped; narrow paths before concluding absence.` plus formatted parse issues.\n- If the wrapper truncates visible results, the text ends with `Result limit reached; narrow paths or increase limit.`\n- `details` includes counts and metadata, not full match payloads:\n  - `matchCount`, `fileCount`, `filesSearched`, `limitReached`\n  - optional `parseErrors`, `scopePath`, `files`, `fileMatches`, `displayContent`, `meta`\n- Native ranges (`byteStart`, `byteEnd`, `startLine`, `startColumn`, `endLine`, `endColumn`) exist only inside the native result; the wrapper does not emit them directly to the model.\n\n## Flow\n1. `AstGrepTool.execute()` validates `pat`, normalizes `skip`, and normalizes each `paths` entry in `packages/coding-agent/src/tools/ast-grep.ts`.\n2. Internal URLs are resolved through `session.internalRouter`; entries without `sourcePath` fail, and internal-URL globs fail early.\n3. For multiple path inputs, `partitionExistingPaths()` drops missing bases only when at least one surviving base remains; if all bases are missing the call fails.\n4. `parseSearchPath()` splits a single path into `basePath` plus optional `glob`. `resolveExplicitSearchPaths()` collapses multiple inputs into a common base plus a brace-union glob, or separate `targets` when the only common base is a filesystem root.\n5. The wrapper stats the resolved base path to decide whether output should be grouped as a directory result.\n6. Execution dispatches to either:\n   - one native `astGrep(...)` call for a single resolved base, or\n   - `runMultiTargetAstGrep(...)`, which calls the native binding once per target, rebases paths back to the common root, sorts globally, then applies `skip` and the wrapper limit.\n7. Native `ast_grep` in `crates/pi-natives/src/ast.rs`:\n   - normalizes and deduplicates patterns,\n   - resolves a `MatchStrictness` (`smart` by default),\n   - collects candidate files from a file or gitignore-aware directory scan,\n   - infers language per candidate from extension unless `lang` was provided,\n   - compiles the pattern separately for each language present,\n   - reads each file, reports syntax-error trees as parse issues, runs `find_all`, and optionally captures metavariable bindings.\n8. Native results are sorted by path and source position, then paged by `offset`/`limit`.\n9. The TS wrapper normalizes parse-error strings, deduplicates them, groups matches by formatted path, renders anchor lines, appends limit/parse notices, and returns `toolResult(...).text(...).done()`.\n\n## Modes / Variants\n- Single file: native path is the file; output is a flat list of rendered match lines.\n- Directory + optional glob: native scan walks the directory, then filters by compiled glob.\n- Multiple explicit paths/globs: wrapper unions them into one synthetic scope or runs per-target native calls when paths only meet at root.\n- Internal URL inputs: only supported when the router can resolve them to a backing file path.\n- Hashline output mode vs plain line-number mode: controlled by `resolveFileDisplayMode()`; hashline mode requires the edit tool and non-raw, mutable sources.\n\n## Side Effects\n- Filesystem\n  - Stats input paths in the TS wrapper.\n  - Native code reads matched files and scans directories through `fs_cache`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - None beyond normal tool transcript/result metadata.\n- Background work / cancellation\n  - Native work runs on a blocking worker via `task::blocking(...)`.\n  - Cancellation and optional native timeout are cooperative through `CancelToken::heartbeat()`.\n\n## Limits & Caps\n- Wrapper-visible result cap: `DEFAULT_AST_LIMIT = 50` in `packages/coding-agent/src/tools/ast-grep.ts`.\n  - Single-target calls rely on the native default limit of 50 in `crates/pi-natives/src/ast.rs`.\n  - Multi-target calls fetch `skip + 50 + 1` matches per target, then re-page after global sort.\n- Native `limit` is clamped to at least `1`; omitted `offset` defaults to `0` in `crates/pi-natives/src/ast.rs`.\n- Parse issues are rendered with at most `PARSE_ERRORS_LIMIT = 20` lines in `packages/coding-agent/src/tools/render-utils.ts`; `details.parseErrors` itself is only deduplicated, not capped.\n- Directory scans use `include_hidden: true`, `use_gitignore: true`, and skip `node_modules` unless the glob text explicitly mentions `node_modules` in `crates/pi-natives/src/ast.rs`.\n- No hard file-count cap is applied by the wrapper or native `ast_grep`; candidate count is whatever the resolved path/glob expands to after gitignore filtering.\n- Multi-path union deduplicates identical path inputs before resolution in `resolveExplicitSearchPaths()`.\n\n## Errors\n- TS wrapper throws `ToolError` for empty patterns, invalid `skip`, empty path entries, unsupported internal-URL globs, internal URLs without `sourcePath`, and missing paths.\n- Native code returns hard errors for:\n  - unsupported explicit `lang`,\n  - inability to infer language for a candidate when `lang` is not supplied,\n  - invalid AST pattern compilation for every relevant language,\n  - unreadable search roots or bad glob compilation,\n  - cancellation (`Aborted: Signal`) or timeout (`Aborted: Timeout`).\n- File-level parse failures and many per-language pattern compile failures are non-fatal: they are accumulated in `parseErrors` and surfaced alongside successful matches.\n- `no matches` is not an error, even when parse issues were recorded.\n\n## Notes\n- `pat` is always wrapped into a one-element `patterns` array by the TS tool; the model cannot send multiple patterns through `ast_grep` even though the native binding supports it.\n- `ast_grep` can search mixed-language trees because native compilation happens per discovered language, but the prompt still tells the model to keep calls single-language when possible to reduce parse noise.\n- Pattern compilation is per language present in the candidate set. One pattern can succeed for some languages and generate per-file parse errors for others in the same run.\n- A file with tree-sitter error nodes still gets searched; the syntax warning is additive, not a skip condition.\n- For glob semantics, `*.ts` matches only direct children while `**/*.ts` recurses; this is covered by native tests in `crates/pi-natives/src/ast.rs`.\n- Output anchors are intended for follow-up tools, but the exact anchor format depends on session edit mode (`hashline` vs line-number mode).",
+	"tools/bash.md": "# bash\n\n> Execute a shell command in the session workspace, with optional PTY or background-job handling.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/bash.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/bash.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/bash-interactive.ts` — PTY/TUI execution path.\n  - `packages/coding-agent/src/tools/bash-interceptor.ts` — blocks tool-better shell patterns.\n  - `packages/coding-agent/src/tools/bash-skill-urls.ts` — expands internal URLs to paths.\n  - `packages/coding-agent/src/exec/bash-executor.ts` — non-PTY shell execution.\n  - `packages/coding-agent/src/session/streaming-output.ts` — tail buffer, truncation, artifact spill.\n  - `packages/coding-agent/src/tools/tool-timeouts.ts` — timeout clamp bounds.\n  - `packages/coding-agent/src/config/settings-schema.ts` — default interceptor rules.\n  - `docs/bash-tool-runtime.md` — deeper executor/runtime notes; use as the companion doc for shell-session internals.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `command` | `string` | Yes | Shell command text to execute. A leading `cd <path> && ...` is rewritten into `cwd` only when `cwd` was omitted. |\n| `env` | `Record<string, string>` | No | Extra environment variables. Keys must match `^[A-Za-z_][A-Za-z0-9_]*$` or the tool throws. Values also go through internal-URL expansion. |\n| `timeout` | `number` | No | Timeout in seconds. Default `300`; clamped to `1..3600` by `clampTimeout(\"bash\", ...)`. |\n| `cwd` | `string` | No | Working directory, resolved against `session.cwd` via `resolveToCwd`. Must exist and be a directory. |\n| `pty` | `boolean` | No | Request PTY mode. Default `false`. PTY is used only when `pty: true`, `PI_NO_PTY !== \"1\"`, and the tool context has a UI. |\n| `async` | `boolean` | No | Background execution request. Present only when `async.enabled` is true for the session. Returns immediately with a job id instead of waiting. |\n\n## Outputs\nThe tool returns a single `text` content block plus optional `details`.\n\n- Success, foreground:\n  - `content[0].text`: command output, or `(no output)` when the command produced nothing.\n  - `details.timeoutSeconds`: effective timeout after clamping.\n  - `details.requestedTimeoutSeconds`: only present when the requested timeout was clamped.\n  - `details.meta.truncation`: present when output was truncated in memory; includes `artifactId` when full output spilled to an artifact.\n- Success, background start (`async: true` or auto-background):\n  - `content[0].text`: optional preview tail, timeout notice if any, then `Background job <id> started: <label>` with follow-up instructions.\n  - `details.async`: `{ state: \"running\", jobId, type: \"bash\" }`.\n- Background progress / completion:\n  - delivered through `onUpdate` / async job manager, not the initial return.\n  - running updates contain tail text and `details.async.state: \"running\"` only after the job is considered backgrounded.\n  - completion/failure updates carry final text and `details.async.state: \"completed\" | \"failed\"`.\n- Failure:\n  - the tool throws `ToolError` / `ToolAbortError`; non-zero exits are surfaced as errors, not success results.\n\nStdout and stderr are merged before the model sees them. Non-zero exit codes are appended to the thrown error text as `Command exited with code <n>`.\n\n## Flow\n1. `BashTool.execute()` in `packages/coding-agent/src/tools/bash.ts` reads `command`, normalizes `env`, and defaults `timeout` to `300`.\n2. If `cwd` is absent, it rewrites a leading `cd <path> && ...` into the structured `cwd` field and strips that prefix from `command`.\n3. If `async: true` is requested while `async.enabled` is off, it throws `ToolError` before any execution.\n4. If `bashInterceptor.enabled` is on, `checkBashInterception()` runs against both the original command and the `cd`-stripped command. A matching enabled rule throws before URL expansion or execution.\n5. `expandInternalUrls()` rewrites supported internal URLs inside `command`, each `env` value, and protocol-looking `cwd` values. Command/env replacements are shell-escaped unless `noEscape` is requested by the caller path.\n6. `resolveToCwd()` resolves `cwd` against `session.cwd`; `fs.stat()` verifies that the target exists and is a directory.\n7. `clampTimeout(\"bash\", requestedTimeoutSec)` enforces `TOOL_TIMEOUTS.bash` (`default: 300`, `min: 1`, `max: 3600`). When clamped, `#buildCompletedResult()` / `#buildBackgroundStartResult()` append a notice line.\n8. Execution path splits:\n   1. `async: true` -> `#startManagedBashJob()` registers a session async job and returns immediately.\n   2. Non-PTY with `bash.autoBackground.enabled` and an async job manager -> starts a managed job, waits up to `min(thresholdMs, timeoutMs - 1000)`, and either returns the completed result or converts the run into a background job.\n   3. Otherwise runs foreground execution.\n9. Foreground non-PTY calls `executeBash()` from `packages/coding-agent/src/exec/bash-executor.ts`.\n10. Foreground PTY calls `runInteractiveBashPty()` from `packages/coding-agent/src/tools/bash-interactive.ts`.\n11. Both paths allocate an output artifact first when `session.allocateOutputArtifact` is available. The artifact path/id are passed into the sink so large output can spill to disk.\n12. `executeBash()` loads shell settings, optional shell snapshot, and shell minimizer settings, then runs via a persistent native `Shell` session or one-shot `executeShell()`. `docs/bash-tool-runtime.md` covers that path in detail.\n13. `runInteractiveBashPty()` creates a `PtySession`, overlays an xterm-backed console UI, forwards user key input into the PTY, captures output through `OutputSink`, and kills the PTY on dismiss/dispose.\n14. On completion, `#buildCompletedResult()` formats `(no output)` when needed, attaches truncation metadata from the `OutputSink` summary, and re-checks exit status / timeout / cancellation before returning.\n15. On non-zero exit, timeout, missing exit status, or cancellation, `#buildResultText()` throws with the captured output included in the error message.\n\n## Modes / Variants\n1. Foreground non-PTY\n   - Default path.\n   - Uses `executeBash()`.\n   - Streams tail-only updates through `streamTailUpdates()` and `TailBuffer(DEFAULT_MAX_BYTES)`.\n2. Foreground PTY\n   - Requires `pty: true`, UI context, and `PI_NO_PTY !== \"1\"`.\n   - Uses `runInteractiveBashPty()` and a `PtySession` overlay.\n   - Supports interactive input; `Esc` kills the session from the overlay.\n3. Explicit background job\n   - Requires `async: true` and `async.enabled`.\n   - Registers a job with `session.asyncJobManager` and returns `{ state: \"running\", jobId }` immediately.\n4. Auto-backgrounded non-PTY job\n   - Requires `bash.autoBackground.enabled`, no PTY, and an async job manager.\n   - Starts like a foreground managed job, then backgrounds it when it outlives the wait window.\n5. Intercepted command\n   - No subprocess created.\n   - Returns a `ToolError` pointing the model at `read`, `search`, `find`, `edit`, or `write`.\n\n## Side Effects\n- Filesystem\n  - Validates `cwd` with `fs.stat()`.\n  - May allocate and write artifact files for full output (`bash`) and minimizer-preserved raw output (`bash-original`).\n  - `expandInternalUrls(..., { ensureLocalParentDirs: true })` creates parent directories for `local://` paths before execution.\n- Subprocesses / native bindings\n  - Non-PTY uses native shell execution via `@oh-my-pi/pi-natives` (`Shell.run()` or `executeShell()`).\n  - PTY uses native `PtySession.start()`.\n- Session state\n  - Reads session settings for async, auto-background, interceptor, tool availability, and shell configuration.\n  - Registers jobs with `session.asyncJobManager` for explicit/auto background runs.\n  - Uses `session.getSessionId()` to isolate shell reuse and async session keys.\n  - Uses `session.allocateOutputArtifact()` for spill files.\n- User-visible prompts / interactive UI\n  - PTY mode opens a TUI overlay titled `Console` and forwards input to the PTY.\n  - Background start messages direct the agent to `job` and `read jobs://<id>`.\n- Background work / cancellation\n  - Async and auto-background jobs continue after the initial tool return.\n  - Cancellation aborts the native run; PTY overlay dismissal also kills the PTY.\n\n## Limits & Caps\n- Default timeout: `300s` (`TOOL_TIMEOUTS.bash.default` in `packages/coding-agent/src/tools/tool-timeouts.ts`).\n- Timeout clamp: `1..3600s` (`TOOL_TIMEOUTS.bash.min/max`).\n- Auto-background default threshold: `60_000ms` (`DEFAULT_AUTO_BACKGROUND_THRESHOLD_MS` in `packages/coding-agent/src/tools/bash.ts`), further capped to `timeoutMs - 1000` by `#resolveAutoBackgroundWaitMs()`.\n- Hard kill grace beyond requested timeout in non-PTY executor: `5_000ms` (`HARD_TIMEOUT_GRACE_MS` in `packages/coding-agent/src/exec/bash-executor.ts`).\n- In-memory output tail cap: `50 * 1024` bytes (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`). Once exceeded, the sink keeps only the tail window in memory.\n- Streaming callback throttle in `executeBash()`: `50ms` between `onChunk` calls when streaming is enabled.\n- TUI collapsed preview: `10` visual lines (`BASH_DEFAULT_PREVIEW_LINES`) when rendered inline in the agent UI; this is a renderer cap, not a tool output cap.\n\n## Errors\n- Input validation:\n  - invalid env key -> `ToolError(\"Invalid bash env name: <key>\")`.\n  - async requested while disabled -> `ToolError(\"Async bash execution is disabled...\")`.\n  - missing async job manager -> `ToolError(\"Async job manager unavailable for this session.\")`.\n  - missing/bad `cwd` -> `ToolError(\"Working directory does not exist: ...\")` or `ToolError(\"Working directory is not a directory: ...\")`.\n- Interceptor:\n  - matched command -> `ToolError` with `Blocked: <rule.message>` and the original command.\n  - invalid interceptor regexes are silently skipped by `compileRules()`.\n- Internal URL expansion:\n  - unsupported scheme, unknown skill, path traversal, missing router support, or router resolution failures all throw `ToolError` from `packages/coding-agent/src/tools/bash-skill-urls.ts`.\n- Execution:\n  - non-zero exit -> thrown `ToolError` containing captured output plus `Command exited with code <n>`.\n  - missing exit code -> thrown `ToolError` with `Command failed: missing exit status`.\n  - timeout -> thrown `ToolError`; PTY uses `Command timed out after <n> seconds`, non-PTY executor returns cancelled output that `BashTool` converts to an error.\n  - user abort -> `ToolAbortError` when the caller signal is aborted.\n- Artifact allocation / artifact save failures are swallowed in `saveBashOriginalArtifact()` and `OutputSink.#createFileSink()`; execution continues without that artifact.\n\n## Notes\n- `strict = true` and `concurrency = \"exclusive\"` are set on `BashTool`; the tool does not run concurrently with another bash tool call in the same session.\n- `command` and `env` URL expansions shell-escape replacements; `cwd` expansion uses `noEscape: true` because it becomes a filesystem path argument, not shell text.\n- `checkBashInterception()` blocks only when the matching rule's `tool` name is present in `ctx.toolNames`; missing tools disable their corresponding rule.\n- Default interceptor rules come from `DEFAULT_BASH_INTERCEPTOR_RULES` in `packages/coding-agent/src/config/settings-schema.ts`:\n  - `cat|head|tail|less|more` -> `read`\n  - `grep|rg|ripgrep|ag|ack` -> `search`\n  - `find|fd|locate` with name/type/glob flags -> `find`\n  - `sed -i`, `perl -i`, `awk -i inplace` -> `edit`\n  - `echo|printf|cat <<` with redirection -> `write`\n- PTY mode is ignored in non-UI contexts and when `PI_NO_PTY=1`; the tool silently falls back to non-PTY execution.\n- Non-PTY runs merge `NON_INTERACTIVE_ENV` with `env`; PTY runs also prepend `NON_INTERACTIVE_ENV` before custom env values.\n- When the shell minimizer rewrites output inside `executeBash()`, the visible output is replaced with minimized text and a `[raw output: artifact://<id>]` footer may be appended if `onMinimizedSave` persisted the original text.\n- The TUI renderer parses partial JSON to recover `env` assignments early in streaming previews; that behavior is display-only.\n- For executor internals that are not tool-specific — shell session reuse keys, snapshots, prefix handling, and native timeout behavior — see `docs/bash-tool-runtime.md`.\n",
+	"tools/browser.md": "# browser\n\n> Open, reuse, close, and script Puppeteer tabs against headless Chromium or CDP-attached apps.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/browser.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/browser.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/browser/tab-supervisor.ts` — global tab registry; worker lifecycle; run/close coordination.\n  - `packages/coding-agent/src/tools/browser/tab-worker.ts` — executes `run` code; implements the `tab` helper API.\n  - `packages/coding-agent/src/tools/browser/tab-worker-entry.ts` — worker-thread transport bootstrap.\n  - `packages/coding-agent/src/tools/browser/registry.ts` — browser-handle registry keyed by browser kind.\n  - `packages/coding-agent/src/tools/browser/launch.ts` — Puppeteer loading, Chromium resolution/download, headless launch, stealth injection.\n  - `packages/coding-agent/src/tools/browser/attach.ts` — CDP attach/reuse, target picking, spawned-app process handling.\n  - `packages/coding-agent/src/tools/browser/tab-protocol.ts` — worker init/run/result message schema.\n  - `packages/coding-agent/src/tools/browser/readable.ts` — `tab.extract()` readability extraction.\n  - `packages/coding-agent/src/tools/browser/render.ts` — TUI rendering for `open`/`close` status lines and `run` JS cells.\n  - `packages/coding-agent/src/tools/puppeteer/00_stealth_tampering.txt` — mask patched functions/descriptors as native.\n  - `packages/coding-agent/src/tools/puppeteer/01_stealth_activity.txt` — synthesize visibility/focus/scroll activity.\n  - `packages/coding-agent/src/tools/puppeteer/02_stealth_hairline.txt` — fix Modernizr hairline detection.\n  - `packages/coding-agent/src/tools/puppeteer/03_stealth_botd.txt` — spoof `navigator.webdriver`, `window.chrome`, and Chrome fingerprint surfaces.\n  - `packages/coding-agent/src/tools/puppeteer/04_stealth_iframe.txt` — patch iframe `contentWindow`/`srcdoc` behavior.\n  - `packages/coding-agent/src/tools/puppeteer/05_stealth_webgl.txt` — spoof WebGL vendor/renderer/precision.\n  - `packages/coding-agent/src/tools/puppeteer/06_stealth_screen.txt` — normalize screen/viewport/device-pixel-ratio values.\n  - `packages/coding-agent/src/tools/puppeteer/07_stealth_fonts.txt` — spoof local fonts and perturb canvas text rendering.\n  - `packages/coding-agent/src/tools/puppeteer/08_stealth_audio.txt` — spoof audio latency/sample-rate and perturb offline rendering.\n  - `packages/coding-agent/src/tools/puppeteer/09_stealth_locale.txt` — force locale/languages/timezone/date strings.\n  - `packages/coding-agent/src/tools/puppeteer/10_stealth_plugins.txt` — synthesize `navigator.plugins`/`navigator.mimeTypes`.\n  - `packages/coding-agent/src/tools/puppeteer/11_stealth_hardware.txt` — spoof `navigator.hardwareConcurrency`.\n  - `packages/coding-agent/src/tools/puppeteer/12_stealth_codecs.txt` — spoof media codec support.\n  - `packages/coding-agent/src/tools/puppeteer/13_stealth_worker.txt` — carry UA/platform spoofing into `Worker`/`SharedWorker`.\n\n## Inputs\n\n### Shared fields\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | `\"open\" \\| \"close\" \\| \"run\"` | Yes | Dispatches to the open/close/run path. |\n| `name` | `string` | No | Tab id. Defaults to `\"main\"`. Tabs live in a process-global map, so the same name is reused across later calls and in-process subagents until closed. |\n| `timeout` | `number` | No | Tool wall-clock timeout in seconds. Defaults to `30`; clamped to the browser tool range before execution. |\n\n### `action: \"open\"`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `url` | `string` | No | Navigate after the tab is ready. Existing reusable tabs also navigate when `url` is supplied. |\n| `viewport` | `{ width: number; height: number; scale?: number }` | No | Requested viewport. For headless launch this becomes the initial viewport; for a page it is applied with `page.setViewport()`. `scale` maps to Puppeteer `deviceScaleFactor`. |\n| `wait_until` | `\"load\" \\| \"domcontentloaded\" \\| \"networkidle0\" \\| \"networkidle2\"` | No | Navigation wait condition. Defaults to `\"networkidle2\"` where omitted. |\n| `dialogs` | `\"accept\" \\| \"dismiss\"` | No | Installs a page `dialog` handler that auto-accepts or auto-dismisses dialogs. Omitted means no handler. |\n| `app` | `{ path?: string; cdp_url?: string; args?: string[]; target?: string }` | No | Selects browser kind. No `app` uses the session `browser.headless` setting. `app.path` is resolved against the session cwd and used as the executable path for spawn/attach reuse. `app.cdp_url` connects to an existing CDP endpoint. `args` are appended only when spawning `app.path`. `target` is only used for attached/spawned-app page selection. |\n\n### `action: \"close\"`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `all` | `boolean` | No | Close every known tab. Omitted closes only `name`. |\n| `kill` | `boolean` | No | When a tab release drops a spawned-app browser handle to refcount 0, also terminate its process tree. Has no effect on headless shutdown and only disconnects connected CDP browsers. |\n\n### `action: \"run\"`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `code` | `string` | Yes | Async-function body executed in a VM context with `page`, `browser`, `tab`, `display`, `assert`, `wait`, `console`, timers, `URL`, `TextEncoder`, `TextDecoder`, and `Buffer` in scope. |\n\n## Outputs\nThe tool returns one result per call; no streaming partial output is emitted from the browser implementation itself.\n\n- `open`: text content with `Opened` or `Reused`, browser description, URL, and optional title. `details` includes `action`, `name`, `browser`, `url`, `viewport`, and the same text in `details.result`.\n- `close`: text content with either `Closed ...` or `No tab named ...`. `details` includes `action`, `name`, and `details.result`.\n- `run`: ordered `content` array built as:\n  1. every `display(value)` call in execution order,\n  2. final return value, JSON-stringified unless already a string,\n  3. or `Ran code on tab \"...\"` if nothing else was produced.\n- `display(value)` coercion in `packages/coding-agent/src/tools/browser/tab-worker.ts`:\n  - `{ type: \"image\", data: string, mimeType: string }` becomes image content,\n  - `string` becomes text content,\n  - other values become pretty JSON text when serializable, else `String(value)`.\n- `tab.screenshot()` also appends text plus an image content item unless `silent: true`; `details.screenshots` records persisted screenshot metadata `{ dest, mimeType, bytes, width, height }`.\n- `run` `details` includes `action`, `name`, current `browser`/`url` when the tab exists, optional `screenshots`, and `details.result` containing only the concatenated text outputs.\n\n## Flow\n1. `BrowserTool.execute()` (`packages/coding-agent/src/tools/browser.ts`) abort-checks, clamps `timeout` via `clampTimeout(\"browser\", ...)`, defaults `name` to `\"main\"`, and dispatches on `action`.\n2. `open` resolves browser kind with `resolveBrowserKind()`:\n   - `app.cdp_url` → `{ kind: \"connected\" }` after trimming trailing slashes.\n   - `app.path` → `{ kind: \"spawned\" }` after resolving against session cwd.\n   - otherwise → `{ kind: \"headless\", headless: session.settings.get(\"browser.headless\") }`.\n3. `open` rejects reusing the same tab name across different browser kinds (`sameBrowserKind()`); callers must close first.\n4. `open` acquires a browser handle through `acquireBrowser()` (`packages/coding-agent/src/tools/browser/registry.ts`):\n   - existing connected handle is reused by browser-kind key;\n   - stale disconnected handles are disposed and recreated;\n   - headless launches via `launchHeadlessBrowser()`;\n   - `connected` waits for `${cdpUrl}/json/version`, then `puppeteer.connect()`;\n   - `spawned` first tries `findReusableCdp()`, else kills same-path processes, allocates a free loopback port, spawns the executable with `--remote-debugging-port=<port>`, waits for CDP, then connects.\n5. `open` acquires a tab through `acquireTab()` (`packages/coding-agent/src/tools/browser/tab-supervisor.ts`):\n   - same-name + same-browser + alive tab is reused unless `dialogs` changed;\n   - same-name but different browser handle, dead state, or changed dialog policy forces release and recreation;\n   - reusing with a new `url` navigates by issuing `await tab.goto(...)` through the worker.\n6. New tabs build a `WorkerInitPayload` in `buildInitPayload()`:\n   - headless mode sends `url`, `waitUntil`, `viewport`, `dialogs`, and timeout;\n   - attach mode resolves a page with `pickElectronTarget()`, gets its target id, and sends `targetId` plus `dialogs`.\n7. `acquireTab()` spawns a dedicated Bun `Worker` from `tab-worker-entry.ts`; if that fails it falls back to inline execution in the main thread (`spawnInlineWorker()`), preserving behavior but losing protection against synchronous infinite loops.\n8. `WorkerCore.#init()` (`packages/coding-agent/src/tools/browser/tab-worker.ts`) connects back to the browser websocket endpoint. Headless mode opens a new page, applies stealth patches, applies viewport, installs dialog handling if requested, and optionally navigates. Attach mode resolves the requested target page and optionally installs dialog handling.\n9. On success the worker sends `ready` with `{ url, title, viewport, targetId }`; the supervisor stores a `TabSession`, increments browser-handle refcount with `holdBrowser()`, and keeps the tab in a process-global `Map<string, TabSession>`.\n10. `run` requires non-empty `code`, looks up the tab with `getTab()`, then delegates to `runInTab()`.\n11. `runInTabWithSnapshot()` rejects dead tabs and concurrent runs (`Tab ... is busy`), captures session cwd plus optional `browser.screenshotDir`, registers an abort hook, sends a `run` message to the worker, and races the result against `timeoutMs + 750` ms. Timeouts force-kill the tab worker and, for headless tabs, close the orphaned page target.\n12. `WorkerCore.#run()` creates a VM context, exposes the raw Puppeteer `page`/`browser` plus a synthetic `tab` API, and executes `(async () => { ...code... })()` via `vm.runInContext()`.\n13. The `tab` helper API implemented in `#createTabApi()` is:\n   - `tab.name: string`\n   - `tab.page: Page`\n   - `tab.signal?: AbortSignal`\n   - `tab.url(): string`\n   - `tab.title(): Promise<string>`\n   - `tab.goto(url, { waitUntil? })`\n   - `tab.observe({ includeAll?, viewportOnly? })`\n   - `tab.screenshot({ selector?, fullPage?, save?, silent? })`\n   - `tab.extract(format = \"markdown\")`\n   - `tab.click(selector)`\n   - `tab.type(selector, text)`\n   - `tab.fill(selector, value)`\n   - `tab.press(key, { selector? })`\n   - `tab.scroll(deltaX, deltaY)`\n   - `tab.drag(from, to)`\n   - `tab.waitFor(selector)`\n   - `tab.evaluate(fn, ...args)`\n   - `tab.scrollIntoView(selector)`\n   - `tab.select(selector, ...values)`\n   - `tab.uploadFile(selector, ...filePaths)`\n   - `tab.waitForUrl(pattern, { timeout? })`\n   - `tab.waitForResponse(pattern, { timeout? })`\n   - `tab.id(n)`\n14. Selector handling in `normalizeSelector()` accepts plain CSS and Puppeteer query handlers, and rewrites legacy Playwright-style prefixes `p-text/`, `p-xpath/`, `p-pierce/`, `p-aria/`; other `p-*` prefixes throw a `ToolError`.\n15. `tab.observe()` clears the element cache, takes a Puppeteer accessibility snapshot, filters to interactive nodes unless `includeAll`, optionally filters to viewport-visible nodes, assigns numeric ids, caches `ElementHandle`s, and returns URL/title/viewport/scroll metadata plus `elements`.\n16. `tab.id(n)` resolves the cached `ElementHandle`, verifies `el.isConnected`, and throws a stale-id error after cache invalidation if the DOM changed or the cache was cleared.\n17. `tab.goto()` clears the cached element ids before navigating. Any new `tab.observe()` also clears and rebuilds the cache.\n18. `tab.click()` uses a custom retry loop for `text/...` selectors to find an actionable visible match; other selectors use `page.locator(...).click()` with the run timeout.\n19. `tab.screenshot()` captures either the whole page or a selector PNG, downsizes a copy for model output, chooses a persistence path, writes the image to disk, records metadata, and optionally emits text + image display entries.\n20. `display()` calls accumulate in an array. After code finishes, the worker posts `{ displays, returnValue, screenshots }`; `BrowserTool.#run()` appends the return value as trailing text content when not `undefined`.\n21. `close` releases one tab or all tabs via `releaseTab()` / `releaseAllTabs()`. Each tab aborts pending runs, asks the worker to close, waits up to `750` ms for a `closed` ack, terminates the worker, decrements browser refcount, and disposes the browser handle when refcount reaches zero.\n\n## Modes / Variants\n- **Action dispatch**\n  - `open` — acquire/reuse browser + tab.\n  - `close` — release one tab or all tabs.\n  - `run` — execute JS inside the tab worker.\n- **Browser kind**\n  - **Headless**: launches local Chromium with Puppeteer, applies stealth patches, and creates a fresh page per tab.\n  - **Spawned app (`app.path`)**: reuses an existing CDP-enabled process for that executable when possible; otherwise kills same-path processes, spawns the executable with remote debugging enabled, then attaches. No stealth patches are injected.\n  - **Connected browser (`app.cdp_url`)**: attaches to an already-running CDP endpoint. No process ownership; close only disconnects.\n- **Target selection for attached/spawned browsers**\n  - With `app.target`, `pickElectronTarget()` returns the first page whose URL or title contains the case-insensitive substring.\n  - Without `app.target`, it skips titles/URLs matching `request handler|devtools|background page|background host|service worker` and otherwise falls back to the first page.\n- **Worker mode**\n  - **Dedicated worker**: normal path; user code runs off the main thread and can be aborted even when it blocks synchronously.\n  - **Inline fallback**: activated when Bun worker spawn fails; behavior matches, but synchronous infinite loops on user code cannot be interrupted.\n- **Dialog policy**\n  - No `dialogs` field: no auto-handler.\n  - `accept`/`dismiss`: page `dialog` events are handled automatically.\n  - Changing dialog policy on an existing live tab forces tab recreation instead of mutating the worker in place.\n- **Screenshot persistence**\n  - `save` provided: persist full-resolution PNG at the resolved cwd-relative or absolute path.\n  - `browser.screenshotDir` session setting set: persist full-resolution PNG under that directory with a timestamped filename.\n  - Neither set: persist the resized image to a temp-file path under the OS temp dir.\n\n## Side Effects\n- Filesystem\n  - `loadPuppeteer()` writes `{}` to `<puppeteer-safe-dir>/package.json` before importing `puppeteer-core`.\n  - First headless launch may download Chromium into the Puppeteer cache directory returned by `getPuppeteerDir()`.\n  - `tab.screenshot()` creates parent directories and writes image files.\n  - `tab.uploadFile()` resolves supplied paths against the session cwd.\n- Network\n  - CDP attach paths poll `http://127.0.0.1:<port>/json/version` or the supplied `cdp_url` `/json/version`.\n  - Headless/browser-attach sessions create CDP websocket connections.\n  - Headless first-use Chromium download uses `@puppeteer/browsers`.\n  - User `page` / `tab` operations perform normal browser network traffic.\n- Subprocesses / native bindings\n  - Headless mode launches Chromium through Puppeteer.\n  - `app.path` mode may spawn the target executable via `Bun.spawn()`.\n  - `killExistingByPath()` / `gracefulKillTreeOnce()` use `@oh-my-pi/pi-natives` process inspection/termination.\n  - Worker mode uses Bun `Worker`; fallback mode does not.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Browser handles are cached in a process-global `Map` keyed by browser kind in `packages/coding-agent/src/tools/browser/registry.ts`.\n  - Tabs are cached in a process-global `Map` keyed by `name` in `packages/coding-agent/src/tools/browser/tab-supervisor.ts`.\n  - `run` captures session cwd and optional `browser.screenshotDir` for screenshot/save path resolution.\n  - `restartForModeChange()` drops only headless tabs.\n- User-visible prompts / interactive UI\n  - None beyond normal tool output. Dialog auto-handling is invisible unless it fails and emits debug logs.\n- Background work / cancellation\n  - `open`, `run`, CDP waits, and browser actions thread through abort signals.\n  - A timed-out `run` aborts the worker execution path and can tear down the tab.\n\n## Limits & Caps\n- Tool timeout clamp: default `30` s, min `1` s, max `30` s (`TOOL_TIMEOUTS.browser` in `packages/coding-agent/src/tools/tool-timeouts.ts`).\n- Supervisor grace period around init/run/close: `750` ms (`GRACE_MS` in `packages/coding-agent/src/tools/browser/tab-supervisor.ts`).\n- Puppeteer protocol timeout for launch/connect operations: `60_000` ms (`BROWSER_PROTOCOL_TIMEOUT_MS` in `packages/coding-agent/src/tools/browser/launch.ts`).\n- Connected-browser CDP readiness wait: `5_000` ms before `puppeteer.connect()` (`packages/coding-agent/src/tools/browser/registry.ts`).\n- Spawned-app CDP readiness wait after spawn: `30_000` ms (`packages/coding-agent/src/tools/browser/registry.ts`).\n- CDP polling cadence: 150 ms in `waitForCdp()` (`packages/coding-agent/src/tools/browser/attach.ts`).\n- Headless default viewport: `1365x768` at `deviceScaleFactor: 1.25` (`DEFAULT_VIEWPORT` in `packages/coding-agent/src/tools/browser/launch.ts`).\n- Screenshot model-attachment resize cap: `maxWidth 1024`, `maxHeight 1024`, `maxBytes 150 * 1024`, `jpegQuality 70` (`packages/coding-agent/src/tools/browser/tab-worker.ts`).\n- `tab.waitForUrl()` polling interval: `200` ms (`packages/coding-agent/src/tools/browser/tab-worker.ts`).\n- Drag simulation uses `12` mouse-move steps (`packages/coding-agent/src/tools/browser/tab-worker.ts`).\n\n## Errors\n- `BrowserTool.execute()` converts DOM-style `AbortError` into `ToolAbortError`; other errors propagate.\n- `run` hard-fails on missing code: `Missing required parameter 'code' for action 'run'.`\n- `open` fails when reusing a name across browser kinds: `Tab \"...\" is bound to a different browser (...). Close it first.`\n- `runInTabWithSnapshot()` fails when the tab is absent/dead (`Tab \"...\" is not alive. Reopen it.`) or already running (`Tab \"...\" is busy`).\n- Worker init failures and run failures are serialized through `RunErrorPayload`; `ToolError` and abort state are reconstructed on the host side by `errorFromPayload()`.\n- Attached-target mismatches surface as:\n  - `No page targets available on the attached browser`\n  - `No page target matched \"...\". Available pages:\\n...`\n  - `Target ... is no longer available on the attached browser`\n- Spawned-app path validation requires an absolute executable path, not an app bundle path.\n- Spawn/attach failures are wrapped into `ToolError`s such as `Timed out waiting for CDP endpoint ...`, `Failed to attach to ...`, or `Connected to ... but puppeteer.connect failed: ...`.\n- `tab` helper errors are user-visible `ToolError`s, including unsupported selector prefix, stale/unknown element id, invalid drag target, missing upload files, non-`<select>` for `tab.select()`, non-file-input for `tab.uploadFile()`, and screenshot selector misses.\n- On run timeout, the worker reports `Browser code execution timed out after <ms>ms`; the supervisor may escalate to `Browser code execution hung past grace; tab killed` if the worker does not respond after the grace window.\n\n## Notes\n- `loadPuppeteer()` and `loadPuppeteerInWorker()` temporarily redirect `cwd` to a safe Puppeteer directory before importing `puppeteer-core`, because Puppeteer probes the current working directory during module load.\n- Headless launch prefers a detected system Chrome/Chromium, then `PUPPETEER_EXECUTABLE_PATH`, and only then downloads Chromium.\n- Headless launch always passes `--no-sandbox`, `--disable-setuid-sandbox`, `--disable-blink-features=AutomationControlled`, and a `--window-size=...` matching the initial viewport. It also ignores Puppeteer default args `--disable-extensions`, `--disable-default-apps`, and `--disable-component-extensions-with-background-pages`.\n- Proxy-related env vars only affect headless launch: `PUPPETEER_PROXY`, `PUPPETEER_PROXY_BYPASS_LOOPBACK`, and `PUPPETEER_PROXY_IGNORE_CERT_ERRORS`.\n- Stealth patches are applied only in headless mode. Spawned or externally connected browsers are intentionally left untouched.\n- `applyStealthPatches()` also strips Puppeteer's `//# sourceURL=__puppeteer_evaluation_script__` suffix from CDP `Runtime.evaluate` / `Runtime.callFunctionOn` payloads.\n- `tab.extract()` reads `page.content()`, runs Readability first, then falls back to `main article`/`article`/`main`/`[role='main']`/`body`, and returns `null` if neither extraction path yields content.\n- `close(all: true, kill: false)` disconnects from spawned/connected browsers when the last tab closes but leaves spawned app processes running.\n- Headless orphan cleanup is best-effort: if a worker dies before closing its page, the supervisor searches browser targets by `targetId` and closes that page.\n- Console methods inside `run` do not appear in tool output; they are forwarded as debug/warn/error logs through the worker transport.",
+	"tools/calc.md": "# calc\n\n> Evaluates one or more arithmetic expressions and returns formatted numeric results.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/calculator.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/calculator.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tui.ts` — status lines and tree-list rendering\n  - `packages/coding-agent/src/tools/render-utils.ts` — preview limits and formatting helpers\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `calculations` | `Calculation[]` | Yes | Batch of expressions to evaluate in order. |\n\n### `Calculation`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `expression` | `string` | Yes | Arithmetic expression string. |\n| `prefix` | `string` | Yes | Prepended verbatim to the rendered numeric result. |\n| `suffix` | `string` | Yes | Appended verbatim to the rendered numeric result. |\n\n## Outputs\n- Single-shot result.\n- `content[0].text` is the newline-joined `prefix + value + suffix` string for each calculation.\n- `details.results` is an array of `{ expression, value, output }`.\n- On renderer fallback, if `details` is missing but `content[0].text` exists, the TUI tries to pair each output line with the original expressions from call args.\n\n## Flow\n1. `execute()` wraps evaluation in `untilAborted(...)`.\n2. For each entry, `evaluateExpression(...)` tokenizes the expression, parses it with a recursive-descent parser, rejects non-finite outputs, and normalizes `-0` to `0`.\n3. `tokenizeExpression(...)` accepts whitespace, parentheses, operators, and number literals; any other character throws immediately.\n4. `ExpressionParser` applies precedence in this order: `+ -`, `* / %`, unary `+ -`, exponentiation `**`, parentheses/literals.\n5. Exponentiation is right-associative (`2 ** 3 ** 2` parses as `2 ** (3 ** 2)`).\n6. Each numeric result is formatted with `String(value)` and wrapped with the provided `prefix` and `suffix`.\n7. The tool returns text output plus structured `details`.\n\n## Side Effects\n- Background work / cancellation\n  - Supports abort via `untilAborted(...)`.\n- Session state\n  - None.\n- Filesystem / Network / Subprocesses\n  - None.\n\n## Limits & Caps\n- Supported operators: `+`, `-`, `*`, `/`, `%`, `**` (`packages/coding-agent/src/tools/calculator.ts`).\n- Supported numeric literals:\n  - decimal integers/floats, including leading-dot forms like `.5`\n  - scientific notation like `1e10`, `2.5E-3`\n  - hexadecimal `0x...`\n  - binary `0b...`\n  - octal `0o...`\n- Results must be finite; `Infinity` and `NaN` are rejected.\n- The renderer collapses long result lists using `PREVIEW_LIMITS.COLLAPSED_ITEMS` from `packages/coding-agent/src/tools/render-utils.ts`.\n\n## Errors\n- Invalid characters: e.g. `Invalid character \"x\" in expression`.\n- Malformed numbers: invalid prefixed literal, invalid exponent, invalid number.\n- Syntax errors: `Unexpected token in expression`, `Unexpected end of expression`, `Missing closing parenthesis`, `Expression is empty`.\n- Non-finite arithmetic: `Expression result is not a finite number`.\n- Any evaluation error aborts the whole batch; the tool does not return partial successes.\n\n## Notes\n- Despite the schema example showing `sqrt(16)`, the parser does not support functions, identifiers, units, or constants; only numeric literals, operators, and parentheses are accepted.\n- Precision is plain JavaScript `number` semantics throughout, including floating-point rounding behavior.\n- `/` and `%` use JavaScript numeric operators directly; there is no integer-only mode or unit handling.\n- Unary operators bind tighter than `*`/`/`/`%` but looser than exponentiation because unary parsing delegates to `#parsePower()`.\n",
+	"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/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",
+	"tools/inspect_image.md": "# inspect_image\n\n> Send a local image file to a vision-capable model and return text analysis.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/inspect-image.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/inspect-image.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/inspect-image-renderer.ts` — TUI call/result rendering.\n  - `packages/coding-agent/src/utils/image-loading.ts` — path resolution, type detection, size gate, optional resize.\n  - `packages/coding-agent/src/utils/image-resize.ts` — downscale and recompress oversized images.\n  - `packages/coding-agent/src/tools/path-utils.ts` — resolve input path relative to session cwd.\n  - `packages/utils/src/mime.ts` — detect supported image formats from file bytes.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `path` | `string` | Yes | Image path passed to `loadImageInput`; resolved relative to `session.cwd` by `resolveReadPath(...)`. |\n| `question` | `string` | Yes | User prompt sent as a text content block alongside the image. |\n\n## Outputs\nThe tool returns a single `AgentToolResult`:\n\n- `content`: one text block, `[{ type: \"text\", text }]`, where `text` is the concatenated assistant text content from the model response.\n- `details`:\n  - `model`: `<provider>/<id>` of the selected model.\n  - `imagePath`: resolved filesystem path returned by `loadImageInput(...)`.\n  - `mimeType`: MIME type actually sent to the model after optional resize/re-encode.\n\nModel-visible output is single-shot, not streamed by this tool.\n\nTUI rendering adds presentation-only truncation from `packages/coding-agent/src/tools/inspect-image-renderer.ts`:\n\n- call preview truncates `question` to 100 columns,\n- result view shows 4 lines collapsed or 16 lines expanded,\n- each rendered output line is truncated to 120 columns,\n- footer metadata shows `model · mimeType` when present.\n\n## Flow\n1. `InspectImageTool.execute(...)` rejects immediately if `images.blockImages` is enabled in session settings.\n2. It reads `session.modelRegistry`; missing registry, empty registry, missing API key, or unresolved model each raise `ToolError` from `packages/coding-agent/src/tools/inspect-image.ts`.\n3. Model selection tries, in order, `pi/vision`, `pi/default`, the active model string from the session, then `availableModels[0]`. `expandRoleAlias(...)` and `resolveModelFromString(...)` handle each lookup.\n4. The chosen model must advertise `input.includes(\"image\")`; otherwise execution fails before reading the file.\n5. `loadImageInput(...)` in `packages/coding-agent/src/utils/image-loading.ts` resolves the path with `resolveReadPath(...)`, detects MIME type with `readImageMetadata(...)`, and rejects files larger than `MAX_IMAGE_INPUT_BYTES` (`20 * 1024 * 1024`, 20 MiB) using `ImageInputTooLargeError`.\n6. `readImageMetadata(...)` in `packages/utils/src/mime.ts` inspects file headers only. Supported detected MIME types are `image/png`, `image/jpeg`, `image/gif`, and `image/webp`.\n7. If `images.autoResize` is true, `loadImageInput(...)` calls `resizeImage(...)`. Resize failures are swallowed there and the original bytes are kept.\n8. If MIME detection returned no supported image type, `execute(...)` throws `ToolError(\"inspect_image only supports PNG, JPEG, GIF, and WEBP files detected by file content.\")`.\n9. The tool calls `completeSimple(...)` with one user message containing two content parts in order:\n   - `{ type: \"image\", data: imageInput.data, mimeType: imageInput.mimeType }`\n   - `{ type: \"text\", text: params.question }`\n10. `systemPrompt` is a one-element array rendered from `packages/coding-agent/src/prompts/tools/inspect-image-system.md`.\n11. If the model response stop reason is `error` or `aborted`, the tool maps that to `ToolError`.\n12. `extractResponseText(...)` concatenates only `text` content blocks from the assistant message, trims the result, and fails if nothing remains.\n13. Success returns the text plus `details`; `inspectImageToolRenderer` formats the result for the TUI.\n\n## Modes / Variants\n- **Original image path**: `images.autoResize` disabled. The original file bytes are base64-encoded and sent with the detected MIME type.\n- **Auto-resized path**: `images.autoResize` enabled. `resizeImage(...)` may downscale and re-encode the image before upload.\n- **Unsupported image path**: file exists but header sniffing does not identify PNG/JPEG/GIF/WEBP. The tool returns a `ToolError` before any model call.\n- **Oversize image path**: file size exceeds 20 MiB before upload. The tool returns a `ToolError` before any model call.\n\n## Side Effects\n- Filesystem\n  - Resolves and reads the target image from disk.\n  - Stats the file once with `Bun.file(...).stat()` and reads it fully with `fs.readFile(...)`.\n- Network\n  - Sends the final base64 image payload plus question text to the selected model through `completeSimple(...)`.\n- Session state\n  - Reads session settings, active model preferences, cwd, and model registry.\n- Background work / cancellation\n  - Passes the caller `AbortSignal` into `completeSimple(...)`.\n  - Image preprocessing is local and not cancellation-aware in these helpers.\n\n## Limits & Caps\n- Supported detected input formats: `image/png`, `image/jpeg`, `image/gif`, `image/webp` (`SUPPORTED_IMAGE_MIME_TYPES` in `packages/utils/src/mime.ts`).\n- Metadata sniff cap: `DEFAULT_IMAGE_METADATA_HEADER_BYTES = 256 * 1024` bytes. Format detection only reads up to 256 KiB from the file header.\n- Upload input cap: `MAX_IMAGE_INPUT_BYTES = 20 * 1024 * 1024` bytes (20 MiB) in `packages/coding-agent/src/utils/image-loading.ts`.\n- Auto-resize defaults in `packages/coding-agent/src/utils/image-resize.ts`:\n  - `maxWidth: 1568`\n  - `maxHeight: 1568`\n  - `maxBytes: 500 * 1024` bytes (500 KiB target)\n  - `jpegQuality: 75`\n- Resize fast path: if the original image is already within `1568x1568` and within `maxBytes / 4` (125 KiB by default), `resizeImage(...)` returns the original bytes unchanged.\n- Resize quality ladder: after the first encode pass, lossy retries use qualities `[70, 60, 50, 40]`.\n- Resize dimension ladder: if quality reduction still misses the byte target, retries scale dimensions by `[1.0, 0.75, 0.5, 0.35, 0.25]` and stop if either dimension would fall below `100` pixels.\n- First resize pass encodes PNG, JPEG, and WebP, then keeps the smallest encoded buffer. Fallback passes encode JPEG and WebP only, again keeping the smaller output.\n- Renderer caps:\n  - `INSPECT_QUESTION_PREVIEW_WIDTH = 100`\n  - `INSPECT_OUTPUT_COLLAPSED_LINES = 4`\n  - `INSPECT_OUTPUT_EXPANDED_LINES = 16`\n  - `INSPECT_OUTPUT_LINE_WIDTH = 120`\n\n## Errors\n- Settings gate:\n  - `Image submission is disabled by settings (images.blockImages=true). Disable it to use inspect_image.`\n- Model resolution / capability:\n  - `Model registry is unavailable for inspect_image.`\n  - `No models available for inspect_image.`\n  - `Unable to resolve a model for inspect_image.`\n  - `Resolved model <provider>/<id> does not support image input. Configure a vision-capable model for modelRoles.vision.`\n  - `No API key available for <provider>/<id>. Configure credentials for this provider or choose another vision-capable model.`\n- Input file:\n  - `Image file too large: <size> exceeds <limit> limit.` from `ImageInputTooLargeError`, remapped to `ToolError`.\n  - `inspect_image only supports PNG, JPEG, GIF, and WEBP files detected by file content.` when header sniffing fails.\n- Model call:\n  - `inspect_image request failed.` if the response stop reason is `error` without a provider message.\n  - Provider `errorMessage` is passed through when present.\n  - `inspect_image request aborted.` on aborted responses.\n  - `inspect_image model returned no text output.` when the assistant message contains no text blocks after filtering.\n\nFailures surface as thrown `ToolError`s from `execute(...)`; the normal success return shape is not used for error reporting.\n\n## Notes\n- The model-facing prompt path on disk is `packages/coding-agent/src/prompts/tools/inspect-image.md`; the assignment's underscore form does not exist.\n- Format support is based on file content, not filename extension. Renaming a non-image file to `.png` does not make it valid.\n- `resolveReadPath(...)` tries macOS-specific path variants: shell-unescaped spaces, AM/PM narrow no-break-space filenames, NFD normalization, and curly-quote variants.\n- `loadImageInput(...)` also computes `textNote`, `dimensionNote`, and final `bytes`, but `inspect_image` does not include those in tool output.\n- Auto-resize can change the MIME type sent to the model. A JPEG or GIF input may be uploaded as PNG, JPEG, or WebP depending on which encoder output is smallest.\n- If `resizeImage(...)` throws or cannot decode the image, `loadImageInput(...)` silently keeps the original base64 payload instead of failing.\n",
+	"tools/irc.md": "# irc\n\n> Send short prose messages to other live agents in the current process.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/irc.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/irc.md`\n- Key collaborators:\n  - `packages/coding-agent/src/registry/agent-registry.ts` — process-global live agent directory.\n  - `packages/coding-agent/src/session/agent-session.ts` — side-channel reply generation and history injection.\n  - `packages/coding-agent/src/prompts/system/irc-incoming.md` — no-tools auto-reply prompt.\n  - `packages/coding-agent/src/tools/index.ts` — tool availability gating.\n  - `packages/coding-agent/src/config/settings-schema.ts` — `irc.enabled` default.\n  - `packages/coding-agent/src/modes/controllers/event-controller.ts` — renders IRC events into chat UI.\n  - `packages/coding-agent/src/modes/utils/ui-helpers.ts` — formats `[IRC]` transcript lines.\n  - `packages/coding-agent/src/task/executor.ts` — carries `irc.enabled` into subagents.\n\n## Inputs\n\n### `op: \"list\"`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `\"list\"` | Yes | Lists peers visible to the caller. |\n\n### `op: \"send\"`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `\"send\"` | Yes | Sends one message to one peer or to `\"all\"`. |\n| `to` | `string` | Yes | Peer id such as `0-Main`, or `\"all\"` for broadcast. Whitespace is trimmed. |\n| `message` | `string` | Yes | Message body. Whitespace is trimmed; empty-after-trim is rejected. |\n| `awaitReply` | `boolean` | No | Wait for prose replies. Defaults to `true` for direct messages and `false` for `to: \"all\"`. |\n\n## Outputs\n- Single-shot `AgentToolResult`; no streaming updates.\n- `content` is one text block.\n  - `list` returns either `No other live agents.` or a bullet list headed by `<n> peer(s):`.\n  - `send` returns delivery summary text, then optional `## Replies`, `## Failed`, and `Unknown / unavailable peers:` sections.\n- `details` is structured metadata:\n  - `list`: `{ op, from, peers, channels }`\n  - `send`: `{ op, from, to, delivered, replies?, failed?, notFound? }`\n- The tool does not return raw IRC frames, message ids, or a transcript object.\n\n## Flow\n1. `IrcTool.createIf` only constructs the tool when `irc.enabled` is on and the session has both an `AgentRegistry` and `getAgentId` (`packages/coding-agent/src/tools/irc.ts`).\n2. Tool discovery adds another gate in `packages/coding-agent/src/tools/index.ts`: if the caller is `0-Main` and `async.enabled` is off, `irc` is hidden because the main agent cannot talk to concurrent peers in sync mode.\n3. `execute` resolves the process-global registry and sender id. Missing either returns a text error result instead of throwing.\n4. `op: \"list\"` calls `registry.listVisibleTo(senderId)`, which exposes every other agent in flat namespace whose status is `running` or `idle` (`packages/coding-agent/src/registry/agent-registry.ts`).\n5. `list` formats human-readable lines and returns `channels` as `['all', ...peerIds]`. These are logical targets only; there is no channel join state.\n6. `op: \"send\"` trims `to` and `message`; missing values produce text errors.\n7. `send` resolves targets:\n   - `to === \"all\"`: all visible peers.\n   - otherwise: one exact registry id, excluding self and excluding peers not in `running`/`idle`.\n8. `send` chooses `awaitReply = params.awaitReply ?? !isBroadcast`.\n9. Each target is dispatched in parallel via `target.session.respondAsBackground(...)`. One slow or failing peer does not block dispatch to the others.\n10. `respondAsBackground` emits an `irc_message` session event, forwards a display-only relay to the main session UI, and either:\n    - queues just the incoming message for later history injection when `awaitReply === false`, or\n    - renders `packages/coding-agent/src/prompts/system/irc-incoming.md`, runs `runEphemeralTurn` with `toolChoice: \"none\"`, emits an auto-reply event, then queues both incoming and reply messages for history injection.\n11. Deferred injection waits until the recipient is no longer streaming; `#flushPendingBackgroundExchanges` appends the custom messages through normal `message_start`/`message_end` external events so persistence and listeners see them.\n12. `send` aggregates `delivered`, `replies`, `failed`, and `notFound`, then returns one text summary plus matching `details`.\n\n## Modes / Variants\n- `list`: enumerate visible peers and logical channels.\n- `send` direct message: one exact peer id, default synchronous auto-reply.\n- `send` broadcast: `to: \"all\"`, default fire-and-forget (`awaitReply: false`) to every visible peer.\n- `send` with `awaitReply: false`: recipient records the incoming message but does not generate a reply.\n- `send` with `awaitReply: true`: recipient performs a no-tools ephemeral LLM turn and returns prose.\n\n## Side Effects\n- Session state\n  - Reads from the process-global `AgentRegistry`.\n  - Emits `irc_message` session events on recipient sessions.\n  - Queues IRC custom messages into recipient persisted history after the current stream finishes.\n  - For non-main recipients, forwards display-only relay observations into the main session UI; these relays are not persisted to the main agent history.\n  - Subagents inherit `irc.enabled` from task executor settings.\n- User-visible prompts / interactive UI\n  - IRC events render as `[IRC]` transcript lines in the TUI.\n  - Auto-replies are generated from `packages/coding-agent/src/prompts/system/irc-incoming.md` and explicitly forbid tool use.\n- Background work / cancellation\n  - `send` starts one background `respondAsBackground` call per target.\n  - The caller's `AbortSignal` is forwarded into each background reply turn.\n- Network\n  - No IRC server connection.\n  - When `awaitReply: true`, the recipient may make model-provider API calls through `runEphemeralTurn`.\n- Filesystem\n  - No direct filesystem writes in the tool itself.\n\n## Limits & Caps\n- Availability gates:\n  - `irc.enabled` defaults to `true` in `packages/coding-agent/src/config/settings-schema.ts`.\n  - Main agent tool discovery suppresses `irc` when `async.enabled` is off (`packages/coding-agent/src/tools/index.ts`).\n- Visibility scope: only peers in status `running` or `idle` are addressable via `listVisibleTo`.\n- Reply execution:\n  - No tools are available in auto-reply turns (`toolChoice: \"none\"` in `runEphemeralTurn`).\n  - No internal timeout, retry, backoff, rate limit, or reply length cap is defined in `irc.ts`; behavior relies on the underlying model stream and any upstream API limits.\n- Flush scheduling: deferred history injection polls every `50` ms while the recipient is still streaming (`#scheduleBackgroundExchangeFlush` in `packages/coding-agent/src/session/agent-session.ts`).\n\n## Errors\n- The tool returns text errors, not thrown exceptions, for:\n  - missing registry: `IRC is unavailable in this session.`\n  - missing sender id: `IRC is unavailable: caller has no agent id.`\n  - missing `to`: `` `to` is required for op=\"send\". ``\n  - missing `message`: `` `message` is required for op=\"send\". ``\n  - unknown op: `Unknown irc op.`\n- Unknown, self-addressed, non-running, and non-idle direct targets are reported under `details.notFound` and in the text footer `Unknown / unavailable peers:`.\n- If a target has no attached session, it is treated as not found.\n- Exceptions thrown by `respondAsBackground` or `runEphemeralTurn` are caught per-target and surfaced under `details.failed` as `{ id, error }`; other recipients still complete.\n- If no target succeeds, `send` still returns normally with `No recipients received the message.` and optional `failed`/`notFound` metadata.\n\n## Notes\n- This is IRC-like naming only. There are no servers, sockets, nick registration, auth handshakes, channels beyond `all`, or commands such as join/part/topic.\n- Addressing is by exact agent id from the registry; there is no fuzzy lookup or aliasing.\n- `channels` in `list` is synthetic output: `all` plus visible peer ids. Nothing is persisted across calls as channel membership.\n- Persistence is per recipient history, not per sender history. The sender gets the tool result; the recipient later sees injected custom messages on its next turn.\n- The main UI may show IRC relays for conversations it was not part of, but those relay records are explicitly display-only.\n- Because reply generation snapshots in-flight assistant text, a recipient can answer based on partially streamed context.\n- Direct self-messaging is rejected by resolving the target as unavailable.",
+	"tools/job.md": "# job\n\n> Wait for or cancel background jobs managed by the session async runtime.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/job.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/job.md`\n- Key collaborators:\n  - `packages/coding-agent/src/async/job-manager.ts` — job registry, cancellation, delivery suppression.\n  - `packages/coding-agent/src/async/support.ts` — feature gating for background jobs.\n  - `packages/coding-agent/src/internal-urls/jobs-protocol.ts` — `jobs://` listing and per-job detail.\n  - `packages/coding-agent/src/tools/bash.ts` — explicit async bash and auto-backgrounded bash jobs.\n  - `packages/coding-agent/src/task/index.ts` — async task-job scheduling.\n  - `packages/coding-agent/src/sdk.ts` — automatic follow-up delivery for unsuppressed completions.\n  - `packages/coding-agent/src/config/settings-schema.ts` — `async.pollWaitDuration` options.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `poll` | `string[]` | No | Job ids to watch. If omitted and `cancel` is also omitted, the tool watches all running jobs. If provided, missing ids are silently filtered out before waiting. |\n| `cancel` | `string[]` | No | Job ids to cancel before any polling. Missing ids are reported as `not_found`; non-running ids as `already_completed`. |\n\n## Outputs\nThe tool returns one text block plus `details`.\n\n- `content[0].text`: markdown-like plain text sections assembled by `#buildResult(...)`:\n  - `## Cancelled (N)` for cancel outcomes.\n  - `## Completed (N)` for non-running jobs, including stored `resultText` and `errorText`.\n  - `## Still Running (N)` for jobs still in `running`.\n- `details.jobs`: array of snapshots:\n  - `id: string`\n  - `type: \"bash\" | \"task\"`\n  - `status: \"running\" | \"completed\" | \"failed\" | \"cancelled\"`\n  - `label: string`\n  - `durationMs: number`\n  - optional `resultText`, `errorText`\n- `details.cancelled` appears only when `cancel` was passed; each item is `{ id, status }` where status is `\"cancelled\" | \"not_found\" | \"already_completed\"`.\n\nStreaming behavior:\n- During a polling wait, `execute(...)` emits `onUpdate(...)` every 500 ms with an empty text block and fresh `details.jobs` snapshots.\n- Final return is single-shot after a completion, timeout, abort, or immediate fast path.\n\nRelated read path:\n- `read jobs://` lists all current jobs.\n- `read jobs://<id>` renders one job with status, label, start time, duration, and stored result/error text.\n\n## Flow\n1. `JobTool.createIf(...)` in `packages/coding-agent/src/tools/job.ts` only exposes the tool when `isBackgroundJobSupportEnabled(...)` returns true for either `async.enabled` or `bash.autoBackground.enabled`.\n2. `execute(...)` fetches `session.asyncJobManager`. If absent, it returns `Async execution is disabled; no background jobs are available.`\n3. `cancel` ids are processed first:\n   - `manager.getJob(id)` missing → `not_found`.\n   - existing job with `status !== \"running\"` → `already_completed`.\n   - running job → `manager.cancel(id)`, which sets `job.status = \"cancelled\"`, aborts the controller, and schedules eviction.\n4. Polling mode is chosen with `const shouldPoll = requestedPollIds !== undefined || cancelIds.length === 0`:\n   - only `cancel` present → return immediately, no wait.\n   - explicit `poll`, or no args at all → proceed to watch jobs.\n5. Watch set resolution:\n   - explicit `poll` → map ids through `manager.getJob(...)` and drop missing ones.\n   - no `poll` and no `cancel` → `manager.getRunningJobs()`.\n6. Empty watch set returns immediately:\n   - if cancellations happened, return snapshots for the cancelled ids that still exist.\n   - else return either `No matching jobs found for IDs: ...` or `No running background jobs to wait for.`\n7. If every watched job is already non-running, `#buildResult(...)` returns immediately without waiting.\n8. Otherwise the tool waits on `Promise.race(...)` across:\n   - every watched running job's `job.promise`,\n   - a timeout promise for `async.pollWaitDuration`,\n   - the tool-call abort signal when present.\n9. Before waiting, it calls `manager.watchJobs(watchedJobIds)`. This suppresses automatic completion delivery for those ids while they are being watched.\n10. If `onUpdate` exists, a 500 ms interval sends progress snapshots from `#snapshotJobs(...)`; one snapshot is emitted immediately before entering the race.\n11. In `finally`, the tool always calls `manager.unwatchJobs(...)`, clears the timeout, and stops the progress interval.\n12. `#buildResult(...)` deduplicates jobs, snapshots current manager state, then calls `manager.acknowledgeDeliveries(...)` for every non-running job in the result. That suppresses later automatic follow-up delivery for the same completions and removes queued deliveries for those ids.\n13. The final text groups jobs by non-running vs still-running state. A timeout is not an error path; it simply returns the current snapshot.\n\n## Modes / Variants\n- Poll all running jobs: call with neither `poll` nor `cancel`.\n- Poll explicit ids: call with `poll` only.\n- Cancel only: call with `cancel` only; cancellations happen and the tool returns immediately.\n- Cancel then poll: call with both. Cancellations are applied first, then the tool watches the remaining resolved `poll` ids.\n- Read-only inspection outside the tool: `jobs://` and `jobs://<id>` expose the same manager state without waiting.\n\nSpawn paths that produce jobs:\n- `packages/coding-agent/src/tools/bash.ts`\n  - `async: true` always registers a `type: \"bash\"` job with `AsyncJobManager.register(...)` and returns a start message.\n  - auto-background mode (`bash.autoBackground.enabled`) starts the same managed job path for non-PTY commands, waits up to `min(bash.autoBackground.thresholdMs, timeoutMs - 1000)`, and if the command is still running returns a background-job start result instead of inline command output.\n- `packages/coding-agent/src/task/index.ts`\n  - when `async.enabled` is on, the chosen agent is not blocking, and `tasks.length > 0`, each task item is registered as a `type: \"task\"` job.\n\nLifecycle and exact state names:\n- Conceptual scheduling path: `pending` (only task-progress bookkeeping before work starts) → `running` → `completed` / `failed`; cancellation changes a running async job to `cancelled`.\n- Exact `AsyncJob.status` values in `packages/coding-agent/src/async/job-manager.ts`: `\"running\" | \"completed\" | \"failed\" | \"cancelled\"`.\n- Exact per-task progress values in `packages/coding-agent/src/task/types.ts`: `\"pending\" | \"running\" | \"completed\" | \"failed\" | \"aborted\"`.\n\n## Side Effects\n- Filesystem\n  - None in `job.ts` itself.\n  - Jobs being observed may already have written artifacts/results through their own tool runtimes.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Reads and mutates `session.asyncJobManager` state.\n  - `watchJobs(...)` / `unwatchJobs(...)` toggle delivery suppression for the watched ids.\n  - `acknowledgeDeliveries(...)` marks completed ids as suppressed and removes queued deliveries for them.\n  - `cancel(...)` aborts running jobs through each job's `AbortController`.\n- User-visible prompts / interactive UI\n  - Polling emits periodic `onUpdate` snapshots every 500 ms.\n  - Automatic job completion follow-ups are generated by `packages/coding-agent/src/sdk.ts` only for unsuppressed deliveries.\n- Background work / cancellation\n  - Waiting uses a timeout plus optional tool-call abort signal.\n  - Cancelling a job does not synchronously await teardown; it flips state, aborts, and returns control to the manager/job promise.\n\n## Limits & Caps\n- Poll wait duration comes from `async.pollWaitDuration` in `packages/coding-agent/src/config/settings-schema.ts`:\n  - allowed values: `5s`, `10s`, `30s`, `1m`, `5m`\n  - default: `30s`\n- Progress update cadence while polling: `PROGRESS_INTERVAL_MS = 500` in `packages/coding-agent/src/tools/job.ts`.\n- Async job retention default: `DEFAULT_RETENTION_MS = 5 * 60 * 1000` in `packages/coding-agent/src/async/job-manager.ts`.\n- Manager fallback max-running limit: `DEFAULT_MAX_RUNNING_JOBS = 15` in `packages/coding-agent/src/async/job-manager.ts`.\n- Session wiring clamps `async.maxJobs` to `1..100` before constructing the manager in `packages/coding-agent/src/sdk.ts`; settings default is `100` in `packages/coding-agent/src/config/settings-schema.ts`.\n- Async completion delivery retry backoff in `packages/coding-agent/src/async/job-manager.ts`:\n  - base `500` ms\n  - max `30_000` ms\n  - jitter `< 200` ms\n  - exponent capped at 8 doublings\n\n## Errors\n- Tool-disabled path is returned as normal text, not thrown: `Async execution is disabled; no background jobs are available.`\n- Polling a nonexistent id is not an exception:\n  - with `poll` only, missing ids are dropped; if none remain the tool returns `No matching jobs found for IDs: ...`.\n  - with `cancel`, each missing id is reported as `not_found` in `details.cancelled` and text.\n- Cancelling a non-running job is not an exception; it reports `already_completed` even if the actual status is `completed`, `failed`, or `cancelled`.\n- Tool-call abort during polling stops waiting and returns a final snapshot through `#buildResult(...)`; it does not cancel watched jobs.\n- Failures inside the underlying async work are stored on the job (`status: \"failed\"`, `errorText`) and reported in normal tool output, not rethrown by `job`.\n- `read jobs://<id>` missing job returns markdown content headed `# Job Not Found` rather than throwing.\n\n## Notes\n- `job` waits for the first watched running job to settle, not for all watched jobs. If others remain `running`, they are reported under `## Still Running`; the caller must invoke `job` again to continue waiting.\n- Delivery suppression is the key difference between snapshot and automatic delivery:\n  - snapshots (`job`, `read jobs://`) read current manager state;\n  - follow-up delivery comes from `AsyncJobManager.#enqueueDelivery(...)` and `sdk.ts` `onJobComplete`;\n  - watched or acknowledged ids are suppressed via `isDeliverySuppressed(...)`.\n- `manager.cancel(id)` sets `status = \"cancelled\"` before the underlying promise settles. The job function may later populate `resultText` or `errorText`; `job-manager.ts` preserves that text but does not transition the status away from `cancelled`.\n- `jobs://` is implemented by `JobsProtocolHandler` with `immutable = true`, but each resolve call reads live manager state at access time.\n- `jobs://<id>` shows a cancellation section only when a cancelled job has `errorText`; cancelled jobs with `resultText` are not rendered with a result section there.\n- Retention eviction removes the job record, suppression flags, and watch flag together. After eviction, both `job` and `read jobs://<id>` behave as if the id never existed.\n",
+	"tools/lsp.md": "# lsp\n\n> Query language servers for diagnostics, navigation, symbols, renames, code actions, capabilities, and raw requests.\n\n## Source\n- Entry: `packages/coding-agent/src/lsp/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/lsp.md`\n- Key collaborators:\n  - `packages/coding-agent/src/lsp/client.ts` — client process lifecycle and JSON-RPC\n  - `packages/coding-agent/src/lsp/config.ts` — config loading, auto-detect, server selection\n  - `packages/coding-agent/src/lsp/lspmux.ts` — optional `lspmux` command wrapping\n  - `packages/coding-agent/src/lsp/edits.ts` — apply `WorkspaceEdit` and text edits\n  - `packages/coding-agent/src/lsp/utils.ts` — URI conversion, symbol resolution, formatting, glob expansion\n  - `packages/coding-agent/src/lsp/types.ts` — tool schema and protocol types\n  - `packages/coding-agent/src/lsp/clients/index.ts` — custom linter client cache/factory\n  - `packages/coding-agent/src/lsp/clients/lsp-linter-client.ts` — LSP-backed linter adapter\n  - `packages/coding-agent/src/lsp/clients/biome-client.ts` — Biome CLI diagnostics/formatting adapter\n  - `packages/coding-agent/src/lsp/clients/swiftlint-client.ts` — SwiftLint CLI diagnostics adapter\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and `lsp.enabled` gating\n  - `packages/coding-agent/src/tools/tool-timeouts.ts` — timeout defaults and clamping\n  - `packages/coding-agent/src/lsp/defaults.json` — built-in server definitions for auto-detect\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | string enum | Yes | One of `diagnostics`, `definition`, `references`, `hover`, `symbols`, `rename`, `rename_file`, `code_actions`, `type_definition`, `implementation`, `status`, `reload`, `capabilities`, `request`. |\n| `file` | string | No | File path; for `diagnostics` also a glob; for workspace forms use `\"*\"`; for `rename_file` this is the source path. |\n| `line` | number | No | 1-indexed line number for position-based actions. Defaults to `1` on the single-file action path. |\n| `symbol` | string | No | Substring used to resolve the column on `line`. Supports `name#N` occurrence selectors; `N` is 1-indexed and defaults to `1`. |\n| `query` | string | No | Workspace symbol query, code-action selector/filter, or LSP method name for `action=request`. |\n| `new_name` | string | No | Required for `rename` and `rename_file`. |\n| `apply` | boolean | No | For `rename`/`rename_file`, apply unless explicitly `false`. For `code_actions`, list unless explicitly `true`. |\n| `timeout` | number | No | Seconds, clamped by `clampTimeout(\"lsp\", ...)` to `5..60`, default `20`. |\n| `payload` | string | No | JSON string for `action=request`; overrides auto-built params. |\n\n## Outputs\n- Single-shot `AgentToolResult`.\n- `content` is always one text block: `[{ type: \"text\", text: string }]`.\n- `details` is `LspToolDetails`: `action`, `success`, optional `serverName`, optional original `request`.\n- No streaming updates.\n- No artifact URIs or background jobs.\n- Many validation failures are returned as ordinary text results with `details.success: false`; aborts throw `ToolAbortError` instead.\n\n## Flow\n1. `packages/coding-agent/src/tools/index.ts` registers `lsp: LspTool.createIf`; session creation also gates it behind `session.enableLsp !== false` and `settings.get(\"lsp.enabled\")`.\n2. `LspTool.execute()` in `packages/coding-agent/src/lsp/index.ts` clamps `timeout` with `clampTimeout(\"lsp\", ...)`, builds an `AbortSignal.timeout(...)`, and combines it with the caller signal.\n3. `getConfig()` loads and caches `LspConfig` per cwd, applies idle-timeout config via `setIdleTimeout()`, and reuses the cached config on later calls.\n4. Config loading in `packages/coding-agent/src/lsp/config.ts` merges `defaults.json` with JSON/YAML overrides from project, project config dirs, user config dirs, plugin roots, and home; if there are no overrides it auto-detects servers from root markers plus executable discovery.\n5. Server routing uses `getServersForFile()` / `getServerForFile()` from `config.ts`: extension or basename match, then sort primary servers before linters. `index.ts` further filters custom linter clients out of navigation/refactor paths with `getLspServersForFile()` / `getLspServerForFile()`.\n6. `getOrCreateClient()` in `client.ts` creates one process per `command:cwd`, optionally wraps supported commands with `lspmux`, spawns the server, starts the background message reader, sends `initialize`, stores server capabilities, then sends `initialized`.\n7. The message reader in `client.ts` parses LSP frames, resolves pending requests, caches `publishDiagnostics`, tracks `$/progress` tokens for project-load completion, answers `workspace/configuration`, and applies `workspace/applyEdit` requests through `applyWorkspaceEdit()`.\n8. File-scoped actions call `ensureFileOpen()` before requests. Column resolution uses `resolveSymbolColumn()` from `utils.ts`: read the target file, pick first non-whitespace when `symbol` is omitted, otherwise find the exact or case-insensitive match on the target line and honor `#N` occurrence selectors.\n9. Actions dispatch in `LspTool.execute()` through dedicated branches: workspace-only branches (`status`, some `diagnostics`, workspace `symbols`, workspace `reload`, `capabilities`, `request`) run before the single-file switch; all other single-file actions share one client lookup and `switch(action)`.\n10. Requests go through `sendRequest()` in `client.ts`, which allocates an incrementing JSON-RPC id, installs abort and timeout handling, sends `$/cancelRequest` on abort, and rejects on timeout or process exit.\n11. Actions that return edits either preview with `formatWorkspaceEdit()` or apply with `applyWorkspaceEdit()` from `edits.ts`; `rename_file` also performs the filesystem rename and then sends `workspace/didRenameFiles`.\n12. Non-abort failures inside the single-file action block are converted to `LSP error: ...`; many precondition failures return explicit text without throwing.\n\n## Modes / Variants\n### Routing and workspace scope\n- `file: \"*\"` is only special for `diagnostics`, `symbols`, and `reload`.\n- `status` ignores `file`.\n- `capabilities` with omitted `file` or `\"*\"` inspects all non-custom LSP servers; with a concrete file it scopes to matching non-custom servers.\n- `request` with omitted `file` or `\"*\"` chooses the first available non-custom LSP server; with a concrete file it chooses that file's primary non-linter server.\n- `rename_file` sends `workspace/willRenameFiles` and `workspace/didRenameFiles` to every non-custom LSP server from `getLspServers(config)`, not just one file-scoped server.\n- Diagnostics are the only tool action that queries both normal LSP servers and custom linter clients (`BiomeClient`, `SwiftLintClient`, or `LspLinterClient`).\n\n### `diagnostics`\n**Inputs**\n- Required: `file`, unless using workspace mode with `file: \"*\"`.\n- Optional: `timeout`.\n\n**Execution**\n- `file: \"*\"`: `runWorkspaceDiagnostics()` detects project type from root markers and runs one subprocess command: Rust `cargo check --message-format=short`, TypeScript `npx tsc --noEmit`, Go `go build ./...`, Python `pyright`.\n- Concrete file or glob: `resolveDiagnosticTargets()` treats non-globs as one target, otherwise expands a `Bun.Glob` up to `MAX_GLOB_DIAGNOSTIC_TARGETS`.\n- Per file, every matching server runs: custom clients call `lint(file)`; real LSP servers optionally wait for project load, capture `diagnosticsVersion`, `refreshFile()`, then `waitForDiagnostics()` for fresh `publishDiagnostics`.\n- Results are deduplicated by range+message and severity-sorted.\n\n**Output text**\n- Single target with no issues: `OK`.\n- Single target with issues: `<summary>:\\n<grouped diagnostics>`.\n- Batch/glob target: one section per file, plus an initial truncation warning when the glob exceeds the file cap.\n- Workspace mode: `Workspace diagnostics (<detected description>):\\n<command output>`.\n\n### `definition`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/definition` with `{ textDocument, position }`.\n- Accepts `Location`, `Location[]`, `LocationLink`, or `LocationLink[]`; `normalizeLocationResult()` converts `LocationLink` to `targetSelectionRange ?? targetRange`.\n- Waits for project load before the request.\n\n**Output text**\n- `No definition found` or `Found N definition(s):` followed by `file:line:col` and one context line above/below each location.\n\n### `type_definition`\nSame as `definition`, but sends `textDocument/typeDefinition` and reports `type definition(s)`.\n\n### `implementation`\nSame as `definition`, but sends `textDocument/implementation` and reports `implementation(s)`.\n\n### `references`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/references` with `includeDeclaration: true`.\n- For project-aware servers, retries up to `REFERENCES_RETRY_COUNT` times when the only hit is the queried declaration; between retries it waits for project load and sleeps `REFERENCES_RETRY_DELAY_MS`.\n- First `REFERENCE_CONTEXT_LIMIT` references include surrounding context; the rest are location-only.\n\n**Output text**\n- `No references found` or `Found N reference(s):` with contextual entries first, then `... M additional reference(s) shown without context` when truncated.\n\n### `hover`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/hover`.\n- `extractHoverText()` flattens strings, markup content, marked-string objects, or arrays into plain text.\n\n**Output text**\n- `No hover information` or the extracted hover text.\n\n### `symbols`\n**Inputs**\n- Workspace mode: `file: \"*\"` or omitted file on the early workspace branch, plus required `query`.\n- Document mode: required `file`.\n- Optional: `timeout`.\n\n**Execution**\n- Workspace mode sends `workspace/symbol` to every non-custom LSP server, post-filters matches with `filterWorkspaceSymbols()`, deduplicates with `dedupeWorkspaceSymbols()`, then truncates to `WORKSPACE_SYMBOL_LIMIT`.\n- Document mode sends `textDocument/documentSymbol` to the primary server. If the first item has `selectionRange`, it formats hierarchical `DocumentSymbol`s; otherwise it formats flat `SymbolInformation`s.\n\n**Output text**\n- Workspace mode: `Found N symbol(s) matching \"query\":` plus formatted `name @ file:line:col`, with an omission line when over the limit.\n- Document mode: `Symbols in <file>:` plus hierarchical or flat symbol lines.\n\n### `rename`\n**Inputs**\n- Required: `file`, `new_name`.\n- Optional: `line`, `symbol`, `apply`, `timeout`.\n\n**Execution**\n- Waits for project load, sends `textDocument/rename`, receives a `WorkspaceEdit`.\n- `apply !== false` applies edits immediately with `applyWorkspaceEdit()`.\n- `apply === false` renders a preview with `formatWorkspaceEdit()`.\n\n**Output text**\n- `Rename returned no edits`, `Applied rename:` plus applied change lines, or `Rename preview:` plus summarized edits.\n\n### `rename_file`\n**Inputs**\n- Required: `file` source path, `new_name` destination path.\n- Optional: `apply`, `timeout`.\n\n**Execution**\n- Resolves absolute source and destination, rejects identical paths, missing source, existing destination, empty rename set, or directories with more than `MAX_RENAME_PAIRS` files.\n- `enumerateRenamePairs()` returns one `{oldUri,newUri}` pair for a file or walks every regular file in a directory tree.\n- Sends `workspace/willRenameFiles` with `{ files: pairs }` to every non-custom LSP server; collects returned `WorkspaceEdit`s and server notes.\n- Preview mode (`apply === false`) only formats those edits.\n- Apply mode runs each returned `WorkspaceEdit`, renames the source path on disk, sends `textDocument/didClose` for every renamed open file, deletes those `openFiles` entries, then sends `workspace/didRenameFiles`.\n\n**Output text**\n- Preview: `Rename preview: <file-count label> → <dest>` plus per-server edit summaries and optional server notes.\n- Apply: `Renamed <file-count label> → <dest>` plus applied edit summaries, filesystem rename line, and optional server notes.\n\n### `code_actions`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `query`, `apply`, `timeout`.\n\n**Execution**\n- Reads cached diagnostics for the open URI from `client.diagnostics` and sends `textDocument/codeAction` for a zero-width range at the resolved position.\n- When `apply !== true`, `query` is passed as `context.only: [query]`; this is a server-side kind filter.\n- When `apply === true`, `query` becomes a required client-side selector: either a zero-based numeric index or a case-insensitive substring of the action title.\n- Applying a `CodeAction` uses `applyCodeAction()`: optionally `codeAction/resolve`, then `applyWorkspaceEdit(edit)`, then optional `workspace/executeCommand`.\n- Applying a bare `Command` only runs `workspace/executeCommand`.\n\n**Output text**\n- List mode: `N code action(s):` plus `index: [kind] title` lines.\n- Apply mode success: `Applied \"title\":` plus `Workspace edit:` and/or `Executed command(s):` sections.\n- Apply mode miss: `No code action matches \"query\". Available actions:`.\n- Apply mode with no edit/command: `Action \"title\" has no workspace edit or command to apply`.\n\n### `status`\n**Inputs**\n- None.\n\n**Execution**\n- Reads configured servers from cached `LspConfig`, not `getActiveClients()`.\n- Calls `detectLspmux()` and appends status text when `lspmux` is installed.\n\n**Output text**\n- `Active language servers: ...` or `No language servers configured for this project`, optionally followed by `lspmux: active (multiplexing enabled)` or `lspmux: installed but server not running`.\n\n### `reload`\n**Inputs**\n- Workspace mode: `file: \"*\"` or omitted `file`.\n- Single-file mode: required `file`.\n- Optional: `timeout`.\n\n**Execution**\n- Workspace mode reloads every non-custom LSP server.\n- Single-file mode reloads the primary server for that file.\n- `reloadServer()` tries `rust-analyzer/reloadWorkspace`, then `workspace/didChangeConfiguration` with `{ settings: {} }`; if neither works it kills the process so the next request cold-starts a new client.\n\n**Output text**\n- One line per server: `Reloaded <server>`, `Restarted <server>`, or `Failed to reload <server>: ...`.\n\n### `capabilities`\n**Inputs**\n- Optional: `file`, `timeout`.\n\n**Execution**\n- With a concrete `file`, inspects matching non-custom servers for that file.\n- With omitted `file` or `\"*\"`, inspects every non-custom configured server.\n- Starts servers as needed and dumps `client.serverCapabilities ?? {}` as pretty JSON.\n\n**Output text**\n- Per server: `<server>:` followed by indented `capabilities: { ... }`, or `<server>: failed to start (...)`.\n\n### `request`\n**Inputs**\n- Required: `query` method name.\n- Optional: `file`, `line`, `symbol`, `payload`, `timeout`.\n\n**Execution**\n- Chooses one non-custom server: file-scoped primary server, otherwise the first configured non-custom server.\n- Param building precedence:\n  1. If `payload` is present, parse JSON and use it verbatim.\n  2. Else if `file` is concrete and `line` is present, build `{ textDocument: { uri }, position: { line: line - 1, character } }` using `resolveSymbolColumn()`.\n  3. Else if `file` is concrete, build `{ textDocument: { uri } }`.\n  4. Else use `{}`.\n- Opens the file first when `file` is concrete.\n\n**Output text**\n- Success: `<server> ← <method>:\\n<formatted result>`, where non-string results are `JSON.stringify(..., null, 2)` and nullish values become `null`.\n- Failure: `LSP error from <server> on <method>: ...`.\n\n## Side Effects\n- Filesystem\n  - Reads config files, target files, and root markers.\n  - `rename` and `code_actions` may edit/create/delete/rename files via `applyWorkspaceEdit()`.\n  - `rename_file` always renames the source path on disk in apply mode.\n  - Server-initiated `workspace/applyEdit` requests also mutate files through `applyWorkspaceEdit()`.\n- Network\n  - None directly; communication is local stdio JSON-RPC to subprocesses.\n- Subprocesses / native bindings\n  - Spawns language servers with `ptree.spawn()`.\n  - Workspace diagnostics spawns `cargo`, `npx`, `go`, or `pyright`.\n  - `BiomeClient` and `SwiftLintClient` spawn CLI tools.\n  - Optional `lspmux` detection spawns `lspmux status`; supported servers may be wrapped through `lspmux client`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Caches config per cwd in `configCache`.\n  - Caches LSP clients per `command:cwd`, with `pendingRequests`, `diagnostics`, `openFiles`, `serverCapabilities`, and project-load state.\n  - Caches custom linter clients by `serverName:cwd`.\n  - Updates client `lastActivity`; optional idle-timeout cleanup is driven by `setIdleTimeout()`.\n- Background work / cancellation\n  - Every request has an abortable timeout signal.\n  - Aborting an in-flight LSP request sends `$/cancelRequest`.\n  - Background message readers persist for each live client until process exit/shutdown.\n\n## Limits & Caps\n- Tool timeout clamp: default `20`, min `5`, max `60` seconds — `TOOL_TIMEOUTS.lsp` in `packages/coding-agent/src/tools/tool-timeouts.ts`.\n- LSP request default timeout inside `sendRequest()`: `30_000ms` — `DEFAULT_REQUEST_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Warmup initialize timeout default: `5_000ms` — `WARMUP_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Project-load wait fallback: `15_000ms` — `PROJECT_LOAD_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Idle-client sweep interval when enabled: `60_000ms` — `IDLE_CHECK_INTERVAL_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Diagnostic message output cap: first `50` messages — `DIAGNOSTIC_MESSAGE_LIMIT` in `packages/coding-agent/src/lsp/index.ts`.\n- Single-file diagnostics wait: `3_000ms` — `SINGLE_DIAGNOSTICS_WAIT_TIMEOUT_MS`.\n- Batch/glob diagnostics wait per file: `400ms` — `BATCH_DIAGNOSTICS_WAIT_TIMEOUT_MS`.\n- Glob diagnostic target cap: first `20` matches — `MAX_GLOB_DIAGNOSTIC_TARGETS`.\n- Workspace symbol cap: first `200` entries — `WORKSPACE_SYMBOL_LIMIT`.\n- Reference context cap: first `50` references include source context — `REFERENCE_CONTEXT_LIMIT`.\n- References retry count: `2` retries, `250ms` backoff — `REFERENCES_RETRY_COUNT`, `REFERENCES_RETRY_DELAY_MS`.\n- Directory rename cap: `1_000` file pairs — `MAX_RENAME_PAIRS`.\n- `detectLspmux()` state cache TTL: `5 * 60 * 1000ms`; liveness check timeout: `1_000ms` — `STATE_CACHE_TTL_MS`, `LIVENESS_TIMEOUT_MS` in `packages/coding-agent/src/lsp/lspmux.ts`.\n- Workspace diagnostics output cap: first `50` lines from the subprocess.\n\n## Errors\n- Missing or invalid inputs are usually returned as text with `details.success: false`, not thrown:\n  - missing `file`/`query`/`new_name`\n  - invalid JSON in `payload`\n  - no matching server\n  - invalid `rename_file` source/destination conditions\n- `resolveSymbolColumn()` throws explicit errors for missing files, missing symbols, and out-of-bounds `#N` selectors; these surface as `LSP error: ...` or request-specific error text.\n- `sendRequest()` rejects on timeout with `LSP request <method> timed out after <ms>ms`.\n- Client process exit rejects all pending requests with an exit-code/stderr error assembled in `getOrCreateClient()`.\n- Single-file action failures inside the main `try` become `LSP error: <message>`.\n- `request` has its own error envelope: `LSP error from <server> on <method>: <message>`.\n- Some server failures are intentionally softened:\n  - diagnostics continue when one server fails\n  - `rename_file` suppresses `workspace/willRenameFiles` “method not found” errors and records other server errors as notes\n  - `code_actions` ignores `codeAction/resolve` failures and applies unresolved actions when possible\n- Aborts are not converted to text: `ToolAbortError` is rethrown.\n\n## Notes\n- `status` reports configured/available servers from `LspConfig`, not currently active client processes from `getActiveClients()`.\n- `getLspServerForFile()` excludes `createClient` adapters and linter-only servers; navigation/refactor actions never target Biome/SwiftLint custom clients.\n- `getServersForFile()` matches both file extensions and exact basenames from `fileTypes`; config can target names like `Dockerfile` if present.\n- `symbol` matching is exact first, then case-insensitive, and falls back to the Nth occurrence on the specified line only; it never scans other lines.\n- `code_actions` uses `query` in two different ways: server-side `context.only` filter in list mode, client-side title/index selector in apply mode.\n- `rename` and `rename_file` default to apply. Preview requires `apply: false`.\n- `request` with `file: \"*\"` is treated the same as omitted `file`: it does not build workspace-specific params.\n- `reload` does not recreate a client immediately after killing it; the next request triggers reinitialization.\n- `workspace/applyEdit` can apply edits initiated by the server outside the direct tool action result path.\n- `detectLspmux()` can be disabled with `PI_DISABLE_LSPMUX=1`; only `rust-analyzer` is in `DEFAULT_SUPPORTED_SERVERS`.\n- `configCache` is per-process and never auto-invalidated; config changes require a fresh process to be observed by `getConfig()` callers.",
+	"tools/read.md": "# read\n\n> Read files, directories, archives, SQLite databases, internal resources, images, documents, and URLs through one `path` string.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/read.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/read.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/path-utils.ts` — split `path` from trailing selectors; normalize local paths.\n  - `packages/coding-agent/src/tools/archive-reader.ts` — detect `archive.ext:inner/path`, index archives, list/read entries.\n  - `packages/coding-agent/src/tools/sqlite-reader.ts` — detect SQLite targets, parse selectors, render tables.\n  - `packages/coding-agent/src/tools/fetch.ts` — URL parsing, fetch/render pipeline, URL cache/artifacts.\n  - `packages/coding-agent/src/internal-urls/router.ts` — resolve `agent://`, `artifact://`, `jobs://`, `local://`, `mcp://`, `memory://`, `pi://`, `rule://`, `skill://`.\n  - `packages/coding-agent/src/edit/notebook.ts` — convert `.ipynb` to editable `# %% [...] cell:N` text.\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — decide hashline vs line-number vs raw display.\n  - `packages/coding-agent/src/workspace-tree.ts` — render directory trees.\n  - `packages/coding-agent/src/edit/file-read-cache.ts` — cache read lines for later hashline edit recovery.\n  - `packages/coding-agent/src/tools/index.ts` — registers `read: s => new ReadTool(s)`.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `path` | `string` | Yes | Filesystem path, internal URL, or web URL. May end with a trailing selector such as `:50-100` or `:raw`. |\n\n### Selector grammar\n\nFor normal file-like reads, `splitPathAndSel()` in `packages/coding-agent/src/tools/path-utils.ts` recognizes the final suffix only when it matches one of these forms:\n\n| Suffix | Meaning |\n| --- | --- |\n| `:raw` | Raw/verbatim mode. Disables structural summaries and line prefixes. |\n| `:N` / `:LN` | Start at 1-indexed line `N`, open-ended. |\n| `:A-B` / `:LA-LB` | Inclusive 1-indexed line range. |\n| `:A+C` / `:LA+LC` | `C` lines starting at `A`; tool converts this to end line `A + C - 1`. |\n| `:range:raw` or `:raw:range` | Same line selection, but raw output. |\n\nValidation in `parseLineRangeChunk()`:\n- line numbers are 1-indexed; `:0` throws.\n- `+` counts must be `>= 1`.\n- `-` end must be `>= start`.\n\nSelector parsing intentionally falls through for unrecognized trailing `:...`; archive and SQLite paths consume their own colon syntax.\n\nURL selectors are parsed separately in `packages/coding-agent/src/tools/fetch.ts` and support only `:raw`, `:N`, `:A-B`, and `:A+C` — no optional `L` prefix there.\n\n## Outputs\n- Single-shot `AgentToolResult` built through `toolResult()` in `packages/coding-agent/src/tools/tool-result.ts`.\n- `content` is usually one text block. Image reads may return `[text, image]`.\n- `details` is path-dependent. `ReadToolDetails` may include:\n  - `kind: \"file\" | \"url\"` (URL path uses `kind: \"url\"`; file reads usually omit `kind`)\n  - `isDirectory`\n  - `resolvedPath`\n  - `suffixResolution`\n  - URL fields: `url`, `finalUrl`, `contentType`, `method`, `notes`\n  - `truncation`\n  - `displayContent` (unprefixed text + starting line for TUI rendering)\n  - `summary` (`lines`, `elidedSpans`) for structural summaries\n  - `meta` from `packages/coding-agent/src/tools/output-meta.ts`\n- `details.meta.source` is set to the backing path, URL, or internal URL.\n- `details.meta.truncation` carries shown range, total lines/bytes, next offset, and optional `artifactId` for cached URL output.\n- Directory/archive listings and SQLite table lists also set `details.meta.limits` when list limits trigger.\n\n## Flow\n1. `ReadTool.execute()` accepts `{ path }`. `file://...` inputs are expanded first with `expandPath()`.\n2. It tries URL handling first via `parseReadUrlTarget()` from `packages/coding-agent/src/tools/fetch.ts`.\n   - Plain URL reads call `executeReadUrl()`.\n   - URL reads with line selectors load or refresh the URL cache with `loadReadUrlCacheEntry()` and paginate the cached text locally with `#buildInMemoryTextResult()`.\n3. If not a web URL, it checks `session.internalRouter.canHandle(...)`.\n   - Internal URLs are resolved with `internalRouter.resolve()`.\n   - `agent://` query extraction (`/path` or `?q=`) bypasses pagination and returns the extracted content directly.\n   - Other internal resources are paginated in-memory by `#buildInMemoryTextResult()`.\n4. It tries archive resolution next with `#resolveArchiveReadPath()`.\n   - `parseArchivePathCandidates()` scans for `.tar`, `.tar.gz`, `.tgz`, or `.zip` anywhere before `:sub/path`.\n   - On success, `#readArchive()` either lists a directory or decodes an entry as UTF-8 text.\n5. It tries SQLite resolution with `#resolveSqliteReadPath()`.\n   - `parseSqlitePathCandidates()` scans for `.sqlite`, `.sqlite3`, `.db`, `.db3` before any `:table`, `:key`, or `?query` suffix.\n   - `#readSqlite()` dispatches on `parseSqliteSelector()`.\n6. Otherwise it treats the input as a local filesystem path.\n   - `resolveReadPath()` expands `~`, resolves relative to session cwd, treats bare `/` as session cwd, and retries macOS screenshot/NFD/curly-quote variants.\n   - If the path does not exist, `findUniqueSuffixMatch()` does a workspace glob-based unique suffix lookup (skipped for remote mounts).\n7. Directories go through `#readDirectory()`.\n8. Non-directories branch by content type:\n   - image metadata / inline image\n   - editable notebook text\n   - markit-converted document\n   - structural summary for parseable code/prose\n   - streamed text/line-range read\n9. Local text reads are streamed by `streamLinesFromFile()` rather than loading the whole file. The tool adds up to 3 lines of context before/after explicit bounded ranges.\n10. Non-empty contiguous local reads are recorded into `getFileReadCache(session)` for later hashline edit recovery.\n11. If suffix resolution happened, the first text block is prefixed with `[Path '...' not found; resolved to '...' via suffix match]`.\n\n## Modes / Variants\n\n### Local text files\n- No selector: if summarization is enabled and the file is small enough, `#trySummarize()` calls `summarizeCode()`.\n  - Guards: file size `<= 2 MiB` (`MAX_SUMMARY_BYTES`), line count `<= 20_000` (`MAX_SUMMARY_LINES`).\n  - Summary output keeps selected declarations and replaces elided spans with `...`.\n  - When an elided block sits between matching brace lines, `#renderSummary()` may merge them into one anchored line rather than emitting separate opener/closer lines.\n- Explicit selector or summarization miss: streamed text read.\n  - Default open-ended limit is `min(session setting read.defaultLimit, DEFAULT_MAX_LINES)`.\n  - Explicit ranges expand by `RANGE_CONTEXT_LINES = 3` on the constrained sides only.\n  - Non-raw output uses `resolveFileDisplayMode()`:\n    - hashline anchors when edit mode is hashline, read is not raw, source is mutable, edit tool exists, and `readHashLines !== false`\n    - otherwise optional line numbers when `readLineNumbers === true`\n    - raw mode suppresses both\n- Prefix format in hashline mode is `lineNumber + 2-char line hash + \"|\"`, e.g. `41th|def alpha():`, from `formatHashLine()` in `packages/coding-agent/src/hashline/hash.ts`.\n- Those anchors are what the `edit`/hashline path consumes later; immutable sources and `:raw` intentionally suppress them.\n\n### Directory listings\n- `#readDirectory()` calls `buildDirectoryTree()` with:\n  - `maxDepth = 2`\n  - `perDirLimit = 12`\n  - `rootLimit = null`\n  - `lineCap = limit` when a line selector was present, else unlimited at this layer\n- `buildDirectoryTree()` sorts siblings by recency, shows file sizes and relative ages, and may mark `limits.resultLimit` when the tree truncates.\n- Empty directories render as `(empty directory)`.\n\n### Archives\n- Supported archive containers: `.tar`, `.tar.gz`, `.tgz`, `.zip`.\n- Syntax: `archive.ext`, `archive.ext:path/inside`, `archive.ext:path/inside:50-60`.\n- `openArchive()` reads the whole archive into memory, then:\n  - tar/tgz uses `new Bun.Archive(bytes)`\n  - zip uses `fflate.unzipSync()`\n- Archive paths normalize `/`, drop `.` segments, and reject `..`.\n- Directory reads list immediate children; files show `name` plus ` (size)` when size > 0.\n- Directory listing default limit is `500` entries in `#readArchiveDirectory()`.\n- File entries are UTF-8 decoded. Non-UTF-8 entries return `[Cannot read binary archive entry '...' (...)]` instead of bytes.\n- Text archive entries reuse the normal in-memory pagination/anchoring path.\n\n### SQLite databases\n- Database detection requires both a matching extension and a valid SQLite file header (`isSqliteFile()`).\n- Selector forms from `parseSqliteSelector()`:\n\n#### `db.sqlite`\n- `kind: \"list\"`\n- Lists non-`sqlite_%` tables with row counts.\n- `#readSqlite()` caps the rendered list to `500` tables via `applyListLimit()`.\n\n#### `db.sqlite:table`\n- `kind: \"schema\"`\n- Returns `sqlite_master.sql` plus sample rows.\n- Sample size is `DEFAULT_SCHEMA_SAMPLE_LIMIT = 5`.\n\n#### `db.sqlite:table:key`\n- `kind: \"row\"`\n- Resolves by primary key when the table has exactly one PK column; otherwise falls back to `rowid` lookup.\n- No query parameters allowed on row lookups.\n\n#### `db.sqlite:table?limit=...&offset=...&order=...&where=...`\n- `kind: \"query\"`\n- Defaults: `limit = 20`, `offset = 0`.\n- `limit` is capped at `500`.\n- `order` accepts `column` or `column:asc|desc` and must name an existing column.\n- `where` is accepted only after `validateWhereClause()` rejects comments, semicolons, and control keywords like `LIMIT`, `OFFSET`, `UNION`, `ATTACH`, `PRAGMA`.\n- Unknown query parameters throw.\n\n#### `db.sqlite?q=SELECT ...`\n- `kind: \"raw\"`\n- Cannot be combined with table selectors or any other query param.\n- Empty `q` throws.\n- `executeReadQuery()` runs `db.prepare(sql).all()` and rejects bound parameters; it does not verify that the SQL starts with `SELECT`.\n\n- Rendering caps in `packages/coding-agent/src/tools/sqlite-reader.ts`:\n  - ASCII table width `120` (`MAX_RENDER_WIDTH`)\n  - per-column width `40` (`MAX_COLUMN_WIDTH`)\n- `#readSqlite()` opens Bun SQLite in `{ readonly: true, strict: true }` and sets `PRAGMA busy_timeout = 3000`.\n\n### Documents\n- `CONVERTIBLE_EXTENSIONS` in `packages/coding-agent/src/tools/read.ts` covers `.pdf`, `.doc`, `.docx`, `.ppt`, `.pptx`, `.xls`, `.xlsx`, `.rtf`, `.epub`.\n- `convertFileWithMarkit()` converts the file to text/markdown.\n- Converted output is then head-truncated with normal shared limits; there is no line selector support inside the source document before conversion.\n- Conversion failures return a text block like `[Cannot read .pdf file: ...]`.\n\n### Jupyter notebooks\n- `.ipynb` goes through `readEditableNotebookText()` unless `:raw` was requested.\n- Output is editable plain text with markers like:\n\n```text\n# %% [code] cell:0\n...\n```\n\n- Raw mode bypasses that conversion and falls back to file-text reading.\n\n### Images\n- Image detection is metadata-based (`readImageMetadata()`).\n- Max accepted image size is `20 MiB` (`MAX_IMAGE_INPUT_BYTES`, re-exported as `MAX_IMAGE_SIZE`). Larger files throw.\n- If `inspect_image.enabled` is true, `read` returns metadata only (MIME, bytes, dimensions, channels, alpha) plus a suggestion to call `inspect_image`.\n- Otherwise it calls `loadImageInput()` and returns:\n  - a text note from the image loader\n  - an inline image block\n- Unsupported/undecodable image formats throw a `ToolError`.\n\n### Internal URLs\n- `read` does not resolve these itself; it delegates to `session.internalRouter.resolve()`.\n- Registered protocols are outside this file, but the router in `packages/coding-agent/src/internal-urls/router.ts` is built for `agent://`, `artifact://`, `jobs://`, `local://`, `mcp://`, `memory://`, `pi://`, `rule://`, and `skill://`.\n- `#handleInternalUrl()` behavior:\n  - parses the URL with `parseInternalUrl()` so colons inside the host segment are legal\n  - for `agent://`, treats non-root path extraction or `?q=` extraction as a special no-pagination mode\n  - otherwise paginates the resolved text in memory\n  - passes `immutable` through to `resolveFileDisplayMode()` so anchors are suppressed for immutable resources such as artifacts, skills, memory, and agent outputs\n  - sets `ignoreResultLimits: true` for `skill://` so the full skill text is paginated only by explicit selectors, not by the normal default line limit\n\n### Web URLs\n- `parseReadUrlTarget()` accepts `http://`, `https://`, or `www.` targets.\n- Plain URL reads call `executeReadUrl()` in `packages/coding-agent/src/tools/fetch.ts`.\n- `:raw` means raw HTML/body fallback path; plain URL reads prefer rendered/reader-friendly output.\n- `:N`, `:A-B`, `:A+C` do not refetch. They page over cached output from the prior or current URL render.\n- URL render pipeline in `renderUrl()`:\n  1. normalize scheme (`https://` added for bare `www.`)\n  2. try special handlers for known sites unless raw\n  3. fetch with `loadPage()`\n  4. if content is image/PDF/DOCX/etc., try binary fetch + markit/image handling\n  5. handle JSON directly, feeds via feed parser, plain text directly\n  6. for HTML and non-raw mode, try markdown alternates, `URL.md`, content negotiation, feed alternates, HTML-to-text renderers, extracted linked documents, then `llms.txt`\n  7. fall back to raw body text/html\n- URL output is wrapped with a small header:\n\n```text\nURL: ...\nContent-Type: ...\nMethod: ...\nNotes: ...\n\n---\n```\n\n- `method` records the winning path (`json`, `feed`, `text`, `alternate-markdown`, `md-suffix`, `content-negotiation`, `image`, `markit`, `llms.txt`, `raw`, `raw-html`, etc.).\n- URL reads may return an inline image block when the fetched resource is a supported image and survives resizing.\n\n## Side Effects\n- Filesystem\n  - Opens and streams local files.\n  - Reads entire archives into memory before indexing.\n  - May read URL-cache artifact files from the session artifacts directory.\n  - Writes URL output artifacts when URL output is truncated or when line-range pagination needs a persisted cache body.\n- Network\n  - URL mode performs HTTP fetches, binary refetches, and alternate-endpoint probes.\n- Subprocesses / native bindings\n  - Uses Bun SQLite for `.db`/`.sqlite*`.\n  - Uses `Bun.Archive` for tar/tgz and `fflate` for zip.\n  - URL HTML rendering can delegate into site handlers and HTML-to-text backends from `packages/coding-agent/src/tools/fetch.ts`.\n- Session state\n  - Records local text lines into `session.fileReadCache` for later stale-anchor recovery.\n  - Uses `session.internalRouter` for internal URLs.\n  - Uses `session.allocateOutputArtifact()` for cached/truncated URL output.\n- Background work / cancellation\n  - Most branches honor `AbortSignal`; the tool itself is marked `nonAbortable = true`, but helper paths still call `throwIfAborted(signal)`.\n\n## Limits & Caps\n- Shared text truncation defaults from `packages/coding-agent/src/session/streaming-output.ts`:\n  - `DEFAULT_MAX_LINES = 3000`\n  - `DEFAULT_MAX_BYTES = 50 * 1024`\n- Local text open-ended default line limit: `read.defaultLimit`, clamped to `[1, DEFAULT_MAX_LINES]`.\n- Explicit line ranges add `3` context lines on each constrained side (`RANGE_CONTEXT_LINES`).\n- File streaming chunk size: `8 * 1024` bytes (`READ_CHUNK_SIZE`).\n- Local streamed byte budget for line reads: `max(DEFAULT_MAX_BYTES, maxLinesToCollect * 512)`.\n- Structural summaries only run when file size `<= 2 MiB` and line count `<= 20_000`.\n- Image input max: `20 MiB`.\n- Directory tree caps for local directories: depth `2`, per-directory children `12`.\n- Archive directory default list cap: `500` entries.\n- SQLite:\n  - default row query limit `20`\n  - schema sample limit `5`\n  - max query limit `500`\n  - table list cap `500`\n  - render width `120`, column width `40`\n  - busy timeout `3000` ms\n- URL read result shown to the model is truncated to `300` lines and `50 KiB` in `executeReadUrl()`; full cached output can be attached as an artifact.\n- Inline fetched URL images:\n  - source bytes cap `20 MiB`\n  - post-resize inline output cap `300 KiB`\n- Unique suffix auto-resolution glob timeout: `5000` ms.\n- File-read cache holds `30` paths per session.\n\n## Errors\n- Validation and operational failures surface as `ToolError`.\n- Selector errors include:\n  - `Line selector 0 is invalid; lines are 1-indexed. Use :1.`\n  - invalid `A+B` / `A-B` shapes\n  - `Cannot combine query extraction with offset/limit` for `agent://.../path:50`\n- Missing local/archive/sqlite paths first attempt unique suffix resolution; if no unique match exists they error.\n- Out-of-bounds line reads do not throw. They return explanatory text with a suggestion such as `Use :1 ...` or `Use :<last line> ...`.\n- Binary archive entries do not throw; they return a text notice.\n- Document conversion failure returns a text notice.\n- Image oversize/unsupported/invalid cases throw.\n- SQLite parser rejects unsupported parameter combinations early; DB/runtime errors are caught and rethrown as `ToolError(message)`.\n- URL fetch failure does not throw when HTTP fetch succeeds but `response.ok === false`; it returns a failed URL read with `method: \"failed\"` and explanatory notes.\n\n## Notes\n- `readSchema` examples include `https://example.com:L1-L40`, but URL selector parsing in `packages/coding-agent/src/tools/fetch.ts` does not accept `L` prefixes.\n- Hashline anchors are suppressed for raw reads and immutable internal resources because there is no editable backing target for later `edit` consumption.\n- `splitPathAndSel()` intentionally treats unknown trailing `:...` as part of the path so `archive.zip:inner/file` and `db.sqlite:table:key` still work.\n- `resolveReadPath()` contains macOS-specific filename fallbacks for screenshot timestamps, NFD Unicode normalization, and curly apostrophes.\n- A bare `/` resolves to the session cwd, not the filesystem root.\n- URL cache keys are session-scoped and normalized by requested URL + raw/rendered mode; both requested URL and final redirected URL are cached.\n- URL line-range reads request `ensureArtifact: true, preferCached: true` so a later paginated read can reopen the same rendered body from artifact storage.\n- Raw SQLite `q=` execution is not keyword-restricted beyond “no bound parameters”; the read tool relies on the surrounding contract to keep it read-only.\n- The file-read cache is not a read acceleration cache. It exists to recover hashline edits when the file changed after the read.",
+	"tools/recall.md": "# recall\n\n> Search the active Hindsight bank and return raw matching memories.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/hindsight-recall.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/recall.md`\n- Key collaborators:\n  - `packages/coding-agent/src/hindsight/state.ts` — session state, recall query defaults, prompt-side auto-recall.\n  - `packages/coding-agent/src/hindsight/content.ts` — result formatting and UTC timestamp formatting.\n  - `packages/coding-agent/src/hindsight/client.ts` — HTTP `recall` call and error mapping.\n  - `packages/coding-agent/src/hindsight/bank.ts` — bank id and tag-filter scoping.\n  - `docs/tools/retain.md` — shared backend, storage, seeding, and mental-model bootstrap.\n\n## Inputs\n\n| Field | Type | Required | Description |\n|---|---|---:|---|\n| `query` | `string` | Yes | Natural-language search query. The tool passes it through unchanged. |\n\n## Outputs\nReturns a single-shot tool result.\n\nWhen matches exist:\n- `content[0].type = \"text\"`\n- `content[0].text = \"Found <n> relevant memories (as of YYYY-MM-DD HH:MM UTC):\\n\\n<bullet list>\"`\n- each bullet is `- <text> [<type>] (<mentioned_at>)`; the type and timestamp suffixes appear only when those fields are present\n- `details = {}`\n\nWhen no matches exist:\n- `content[0].text = \"No relevant memories found.\"`\n- `details = {}`\n\n## Flow\n1. `HindsightRecallTool.createIf(...)` only exposes the tool when `memory.backend == \"hindsight\"`.\n2. `execute(...)` wraps the whole operation in `untilAborted(...)` from `@oh-my-pi/pi-utils`.\n3. It reads the active `HindsightSessionState`; missing state throws `Hindsight backend is not initialised for this session.`\n4. It calls `state.client.recall(...)` with:\n   - `bankId` from session bootstrap,\n   - the model-supplied `query`,\n   - `budget`, `maxTokens`, and `types` from `HindsightConfig`,\n   - tag filters from the bank scope (`recallTags`, `recallTagsMatch`).\n5. `HindsightApi.recall(...)` POSTs `/v1/default/banks/{bank_id}/memories/recall`.\n6. Results are formatted into a plain-text list with `formatMemories(...)`; empty results map to the fixed no-match string.\n7. Failures are logged with `logger.warn(\"recall failed\", ...)` and rethrown.\n\n## Modes / Variants\n- Tool path: explicit query-only recall. The tool does not compose context from recent turns; that richer path is reserved for backend auto-recall in `HindsightSessionState.beforeAgentStartPrompt(...)` / `maybeRecallOnAgentStart(...)`.\n- Bank scoping is inherited from the active `HindsightSessionState`:\n  - `global` — no tag filter.\n  - `per-project` — separate bank id per cwd basename.\n  - `per-project-tagged` — shared bank id plus `project:<cwd basename>` filter with `tagsMatch = \"any\"`, so project-tagged and untagged global memories can both surface.\n- Session scope: reads cross-session server-side memories, but uses per-session cached config and scope.\n\n## Side Effects\n- Network\n  - `POST /v1/default/banks/{bank_id}/memories/recall` via `packages/coding-agent/src/hindsight/client.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - None on success. Unlike backend auto-recall, this tool does not update `lastRecallSnippet` or refresh the system prompt.\n- Background work / cancellation\n  - Aborts through `untilAborted(...)` if the tool call signal is cancelled.\n\n## Limits & Caps\n- Client default budget for raw `HindsightApi.recall(...)` is `\"mid\"`; this tool overrides from config in `packages/coding-agent/src/hindsight/state.ts`.\n- Default recall settings from `packages/coding-agent/src/config/settings-schema.ts`:\n  - `hindsight.recallBudget = \"mid\"`\n  - `hindsight.recallMaxTokens = 1024`\n  - `hindsight.recallTypes = [\"world\", \"experience\"]`\n- The explicit tool path does not apply `hindsight.recallContextTurns` or `hindsight.recallMaxQueryChars`; those caps only affect backend auto-recall query composition.\n\n## Errors\n- Throws `Hindsight backend is not initialised for this session.` when no state exists.\n- HTTP and fetch failures become `HindsightError` from `packages/coding-agent/src/hindsight/client.ts` with `statusCode` and parsed `details` when available.\n- Non-`Error` failures are normalized to `new Error(String(err))` before rethrow.\n\n## Notes\n- Shared backend details are in `docs/tools/retain.md`: server-side storage, subagent aliasing, bank scoping, mission setup, and mental-model bootstrap.\n- Mental models are not fetched by this tool. They may still already be present in the agent's developer instructions because the backend caches a `<mental_models>` block separately from recall results.\n- The tool returns raw memory hits; it does not synthesize across them. Use `reflect` for that path.\n",
+	"tools/recipe.md": "# recipe\n\n> Run a task exposed by a detected project task runner.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/recipe/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/recipe.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/recipe/runner.ts` — op parsing, task resolution, prompt model.\n  - `packages/coding-agent/src/tools/recipe/render.ts` — shell-style call/result rendering.\n  - `packages/coding-agent/src/tools/recipe/runners/index.ts` — runner registration order.\n  - `packages/coding-agent/src/tools/recipe/runners/just.ts` — detect `just` recipes from justfiles.\n  - `packages/coding-agent/src/tools/recipe/runners/pkg.ts` — detect `package.json` scripts and workspaces.\n  - `packages/coding-agent/src/tools/recipe/runners/cargo.ts` — detect Cargo run/test targets.\n  - `packages/coding-agent/src/tools/recipe/runners/make.ts` — parse make targets from makefiles.\n  - `packages/coding-agent/src/tools/recipe/runners/task.ts` — detect Taskfile tasks via `task --list-all`.\n  - `packages/coding-agent/src/tools/bash.ts` — actual command execution, truncation, cwd/env handling.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `string` | Yes | Single string containing the task selector plus trailing arguments. The first whitespace-delimited token selects the task; the remainder is appended verbatim to the resolved runner command. Examples from schema/prompt: `test`, `build --release`, `pkg-a/test`, `crate/bin/server`, `pkg:test --watch`. |\n\n### `op` grammar\n\n```text\nop          := S* head (S+ tail)?\nhead        := explicit-runner / implicit-task\nexplicit-runner := runner-id \":\" task-token\nimplicit-task   := task-token\nrunner-id   := detected runner id (`just` | `pkg` | `cargo` | `make` | `task`)\ntask-token  := first non-whitespace token; may contain `/`\ntail        := remaining characters after the first whitespace run\n```\n\nResolution rules from `resolveRunnerAndTask()`:\n- Leading whitespace is ignored; an empty `op` throws `ToolError` with the available task list.\n- Only the first token is parsed structurally. Everything after the first whitespace run becomes `tail` and is appended to the command unchanged.\n- If `head` contains `:` and the prefix matches a detected runner id, the suffix must exactly match a task in that runner.\n- Otherwise `head` is treated as a task name and matched across all detected runners.\n- If exactly one runner has that task, it is used.\n- If multiple runners have that task, the call is rejected and the error tells the model to use `<runner-id>:<task>`.\n- Namespaced task names generated by runners use `/`, not `:`. `/` is part of the task name, not a parser separator.\n\n## Outputs\n- Delegates directly to `BashTool.execute()` and returns the same `AgentToolResult<BashToolDetails>` shape.\n- Success path: one text content block containing merged command output (`result.output` from bash execution, or `(no output)`), plus any timeout clamp notice appended after a blank line.\n- Recipe does not return separate `stdout`, `stderr`, or `exitCode` fields. `stdout`/`stderr` are already merged into the text block by bash execution; `exitCode` is only observed indirectly (success requires `0`, non-zero becomes an error).\n- Error path: throws `ToolError`; for non-zero exits the message is the merged output followed by `Command exited with code <n>`.\n- `details` may include:\n  - `timeoutSeconds`: effective timeout used by bash.\n  - `requestedTimeoutSeconds`: only when bash clamped a requested timeout; recipe never sets one itself.\n  - `meta`: output truncation metadata from bash execution.\n  - `async`: defined by bash background execution paths, but recipe does not expose an `async` input.\n- When bash output is truncated, the full text is stored in an artifact and referenced via bash truncation metadata.\n- Call/result rendering in the TUI uses bash shell rendering with a resolved title, command preview, and optional task cwd.\n\n## Flow\n1. `RecipeTool.createIf()` in `packages/coding-agent/src/tools/recipe/index.ts` checks `session.settings.get(\"recipe.enabled\")`; disabled returns `null`.\n2. It probes every runner in `RUNNERS` from `packages/coding-agent/src/tools/recipe/runners/index.ts` with `Promise.all(...)` in this order: `just`, `pkg`, `cargo`, `make`, `task`.\n3. Each runner returns either `null` or a `DetectedRunner { id, label, commandPrefix, tasks }`; runners with zero tasks are discarded.\n4. If no runners remain, the tool is not registered.\n5. Constructor stores detected runners, instantiates `BashTool`, renders the model-facing description by passing `buildPromptModel(runners)` into `packages/coding-agent/src/prompts/tools/recipe.md`, and builds shell renderers from `createRecipeToolRenderer()`.\n6. On execution, `RecipeTool.execute()` calls `resolveCommand(op, this.#runners)`.\n7. `resolveCommand()` in `packages/coding-agent/src/tools/recipe/runner.ts`:\n   1. `parseOp()` trims only leading whitespace, extracts the first non-whitespace token as `head`, and keeps the remainder as `tail`.\n   2. `resolveRunnerAndTask()` resolves `head` either as `runnerId:taskName` or as an unqualified task name.\n   3. It throws `ToolError` for empty ops, missing explicit tasks, ambiguous task names, or unknown tasks; all error variants include the available task list.\n   4. It builds the final shell command with `buildCommand(commandPrefix, commandName, tail)`, joining non-empty parts with spaces.\n   5. If the task defines `cwd`, that relative path is returned alongside the command.\n8. `RecipeTool.execute()` forwards `{ command, cwd }` into `BashTool.execute()`; recipe does not pass timeout, env, async, or pty options.\n9. `BashTool.execute()` resolves internal URLs, validates/normalizes cwd against `session.cwd`, clamps timeout, applies bash interception rules, runs the command, and formats the final result.\n\n## Modes / Variants\n- Tool enablement:\n  - Disabled by `recipe.enabled` setting: tool is absent.\n  - Enabled but no detected tasks: tool is absent.\n- Task selection:\n  - Unqualified task name: succeeds only when exactly one detected runner owns that task.\n  - Explicit runner-qualified task: `<runner-id>:<task>`.\n- Runner detection paths:\n  - `just`: requires `just` on `PATH`, a justfile, and successful `just --dump --dump-format=json`.\n  - `pkg`: requires a readable root `package.json`; picks a package manager command from lockfiles or `bun` availability; discovers root scripts and workspace package scripts.\n  - `cargo`: requires `cargo` on `PATH`, `Cargo.toml`, and successful `cargo metadata --no-deps --format-version=1`.\n  - `make`: requires `make` on `PATH` and a makefile; parses targets statically.\n  - `task`: requires `task` on `PATH`, a Taskfile, and successful `task --list-all --json`.\n- Execution path:\n  - Always the synchronous `bash` call surface from recipe inputs.\n  - Bash may still auto-background long-running work if `bash.autoBackground.enabled` and session async job support are enabled.\n\n## Side Effects\n- Filesystem\n  - Reads manifests from the session cwd during detection: justfiles, `package.json`, workspace `package.json` files, `Cargo.toml`, makefiles, `Taskfile.yml` / `Taskfile.yaml`.\n  - Command execution runs in `session.cwd` or a task-specific relative cwd resolved under it.\n  - Bash may allocate output artifacts for truncated command output.\n- Subprocesses / native bindings\n  - Detection may spawn `just --dump --dump-format=json`, `cargo metadata --no-deps --format-version=1`, and `task --list-all --json`.\n  - Execution spawns the resolved shell command through `BashTool` / `executeBash()`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Tool availability depends on session settings.\n  - Constructor prompt text is specialized to detected runners/tasks.\n  - Bash execution may create async job records and output artifacts if bash auto-background triggers.\n- User-visible prompts / interactive UI\n  - The model-facing tool description lists detected runners and up to 20 tasks per runner.\n  - TUI rendering shows a shell-style preview using the resolved title/command/cwd.\n- Background work / cancellation\n  - Detection is parallelized across runners.\n  - Runtime command execution honors the passed abort signal through `BashTool`.\n\n## Limits & Caps\n- Prompt task listing is capped at `PROMPT_TASK_LIMIT = 20` per runner in `packages/coding-agent/src/tools/recipe/runner.ts`; this affects the rendered tool description, not execution.\n- Recipe itself defines no timeout input; delegated bash execution therefore uses bash's default `timeout = 300` seconds from `packages/coding-agent/src/tools/bash.ts`.\n- Bash clamps timeouts to the configured bash range (`clampTimeout(\"bash\", ...)` in `packages/coding-agent/src/tools/bash.ts`), but recipe cannot request a custom value.\n- `pkg` workspace discovery normalizes workspace globs to `.../package.json` and sorts matched package files lexicographically before task generation.\n- `cargo` deduplicates generated task names with a `Set`, so duplicate targets collapse to one recipe task.\n\n## Errors\n- Detection failures in runner modules are mostly soft-failed:\n  - Missing binaries, missing manifests, parse failures, or non-zero probe exits usually return `null` and log with `logger.debug(...)`.\n  - Result: the affected runner disappears instead of surfacing an error to the model.\n- Invocation failures are hard errors from `resolveRunnerAndTask()`:\n  - Empty `op`.\n  - Explicit runner prefix with missing/empty task.\n  - Ambiguous unqualified task name across runners.\n  - Unknown task name.\n- Execution failures come from `BashTool.execute()`:\n  - Invalid cwd.\n  - Bash interceptor blocks.\n  - Aborts/timeouts.\n  - Non-zero exit codes.\n  - Missing exit status.\n- All `resolveRunnerAndTask()` errors include the current available task list to help the model retry.\n\n## Notes\n- `RecipeTool` sets `concurrency = \"exclusive\"`; calls do not run concurrently with other exclusive tools.\n- Tool registration is all-or-nothing per runner: a detected runner with zero tasks is dropped.\n- Runner ids are fixed string literals from the runner modules: `just`, `pkg`, `cargo`, `make`, `task`.\n- `buildPromptModel()` includes each task's rendered command (`commandPrefix` + `commandName`) and relative cwd when present; the prompt therefore exposes the exact shell form recipe will run.\n- `pkg` task names:\n  - Root `package.json` scripts keep bare names like `test`.\n  - Workspace scripts are always namespaced as `<package-name-or-dir>/<script>` and set `cwd` to that package directory.\n  - Script names are shell-quoted into `commandName`, so a task like `build` becomes `bun run 'build'` / `npm run 'build'` / similar.\n- `pkg` command prefix selection prefers lockfiles in this order: `bun.lock`/`bun.lockb`, `pnpm-lock.yaml`, `yarn.lock`, `package-lock.json`/`npm-shrinkwrap.json`; otherwise it falls back to `bun run` if `bun` exists, else `npm run`.\n- `cargo` task names are generated from metadata targets:\n  - Single-package manifests: `bin/<name>`, `example/<name>`, `test/<name>`.\n  - Multi-package workspaces: `<package>/bin/<name>`, `<package>/example/<name>`, `<package>/test/<name>`.\n  - Each task overrides `commandPrefix` to the full `cargo run ... --bin|--example` or `cargo test ... --test` prefix, and `commandName` to the quoted target name.\n- `make` target parsing is static text parsing, not `make -qp` output:\n  - Recognizes makefiles named `Makefile`, `makefile`, `GNUmakefile`.\n  - Uses `.PHONY` lines to decide whether to include undocumented file targets; without any `.PHONY`, all parsed targets are exposed.\n  - If `.PHONY` exists, documented non-phony targets are kept with ` (file target)` appended to `doc`.\n- `just` detection ignores private recipes and preserves declared parameter names only for prompt display; execution still accepts arbitrary `tail` text.\n- `task` detection uses `desc` first, then `summary`, for task documentation.\n- Recipe has no env input of its own. Commands inherit whatever environment `BashTool` supplies for normal bash execution in the session.",
+	"tools/reflect.md": "# reflect\n\n> Ask the Hindsight server to synthesize an answer over the active memory bank.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/hindsight-reflect.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/reflect.md`\n- Key collaborators:\n  - `packages/coding-agent/src/hindsight/bank.ts` — best-effort bank mission initialization.\n  - `packages/coding-agent/src/hindsight/state.ts` — session state, shared bank scope, recall/reflect config.\n  - `packages/coding-agent/src/hindsight/client.ts` — HTTP `reflect` call and error mapping.\n  - `docs/tools/retain.md` — shared backend, storage, seeding, and mental-model bootstrap.\n\n## Inputs\n\n| Field | Type | Required | Description |\n|---|---|---:|---|\n| `query` | `string` | Yes | Question to answer from long-term memory. |\n| `context` | `string` | No | Extra guidance sent to the Hindsight reflect endpoint. |\n\n## Outputs\nReturns a single-shot tool result:\n\n- `content[0].type = \"text\"`\n- `content[0].text = response.text?.trim() || \"No relevant information found to reflect on.\"`\n- `details = {}`\n\nThe tool returns the Hindsight server's synthesized text directly; it does not expose raw recall hits.\n\n## Flow\n1. `HindsightReflectTool.createIf(...)` only exposes the tool when `memory.backend == \"hindsight\"`.\n2. `execute(...)` runs under `untilAborted(...)`.\n3. It reads the active `HindsightSessionState`; missing state throws `Hindsight backend is not initialised for this session.`\n4. Before reflecting, it calls `ensureBankMission(...)` with the current `bankId`, config, and process-local `missionsSet`.\n5. `ensureBankMission(...)` best-effort `PUT`s `/v1/default/banks/{bank_id}` with `reflect_mission` and optional `retain_mission` exactly once per bank/process; failures are swallowed.\n6. It calls `state.client.reflect(...)` with the model `query`, optional `context`, configured recall budget, and bank-scope tag filters.\n7. `HindsightApi.reflect(...)` POSTs `/v1/default/banks/{bank_id}/reflect` and defaults its own budget to `\"low\"` when callers omit one; this tool always passes the configured budget.\n8. Blank or whitespace-only responses are replaced with `No relevant information found to reflect on.`\n9. Failures are logged with `logger.warn(\"reflect failed\", ...)` and rethrown.\n\n## Modes / Variants\n- Tool path: one reflect request, optionally focused by `context`.\n- Bank scoping is inherited from the active `HindsightSessionState`:\n  - `global` — no tag filter.\n  - `per-project` — separate bank id per cwd basename.\n  - `per-project-tagged` — shared bank id plus `project:<cwd basename>` filter with `tagsMatch = \"any\"`.\n- Session scope: reads cross-session server-side memories, but does not persist local output.\n\n## Side Effects\n- Network\n  - Optional `PUT /v1/default/banks/{bank_id}` from `ensureBankMission(...)`.\n  - `POST /v1/default/banks/{bank_id}/reflect` via `packages/coding-agent/src/hindsight/client.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Reads session-held bank scope and config only. Does not update `lastRecallSnippet`, the mental-model cache, or the retain queue.\n- Background work / cancellation\n  - Aborts through `untilAborted(...)` if the tool call signal is cancelled.\n\n## Limits & Caps\n- Tool-level params: only `query` is required; `context` is optional.\n- Default budget setting comes from `hindsight.recallBudget` in `packages/coding-agent/src/config/settings-schema.ts`; default `\"mid\"`.\n- `reflect` itself has no client-side token cap parameter here; unlike `recall`, the tool does not pass `maxTokens`.\n- Mission initialization tracks up to `MISSION_SET_CAP = 10_000` bank ids in `packages/coding-agent/src/hindsight/bank.ts`, then drops the oldest half of the sorted set.\n\n## Errors\n- Throws `Hindsight backend is not initialised for this session.` when no state exists.\n- HTTP and fetch failures become `HindsightError` from `packages/coding-agent/src/hindsight/client.ts` with `statusCode` and parsed `details` when available.\n- `ensureBankMission(...)` failures are silent to the tool caller; only the later reflect request can fail visibly.\n- Non-`Error` failures are normalized to `new Error(String(err))` before rethrow.\n\n## Notes\n- Shared backend details are in `docs/tools/retain.md`: server-side storage, subagent aliasing, bank scoping, seed mental models from `packages/coding-agent/src/hindsight/seeds.json`, and mental-model prompt injection.\n- `reflect` does not read the cached `<mental_models>` block directly. It queries the Hindsight server over the bank contents. The same session may also have separate mental-model context injected into its developer instructions.\n- Reflect mission and retain mission are bank-level server settings, not per-request payload. The tool just ensures they are present best-effort before reflecting.\n",
+	"tools/render_mermaid.md": "# render_mermaid\n\n> Convert Mermaid source into terminal-friendly ASCII/Unicode text.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/render-mermaid.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/render-mermaid.md`\n- Key collaborators:\n  - `packages/utils/src/mermaid-ascii.ts` — thin wrapper over renderer package.\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and enablement gate.\n  - `packages/coding-agent/src/sdk.ts` — session-facing artifact allocation hook.\n  - `packages/coding-agent/src/session/session-manager.ts` — persistent-session artifact path allocation.\n  - `packages/coding-agent/src/session/artifacts.ts` — artifact filename generation and writes.\n- Related user/runtime doc: `docs/render-mermaid.md`\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `mermaid` | `string` | Yes | Mermaid source text. Schema example: `graph TD; A-->B`. |\n| `config` | `object` | No | Optional renderer options. Sanitized before rendering; numeric fields are floored and clamped to `>= 0`. |\n\n`config` fields:\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `useAscii` | `boolean` | No | `true` for plain ASCII, `false`/omitted for Unicode box-drawing output. Passed through unchanged. |\n| `paddingX` | `number` | No | Horizontal spacing. `Math.floor`, then `Math.max(0, value)`. |\n| `paddingY` | `number` | No | Vertical spacing. `Math.floor`, then `Math.max(0, value)`. |\n| `boxBorderPadding` | `number` | No | Inner box padding. `Math.floor`, then `Math.max(0, value)`. |\n\n## Outputs\nThe tool returns a single text content block:\n\n- inline body: rendered diagram text\n- optional trailer: `Saved artifact: artifact://<id>` when artifact storage is available\n\n`details` may include:\n\n- `artifactId?: string`\n\nNo image path, SVG, PNG, or binary payload is returned. Stored artifacts are plain text `.log` files; artifact filenames are allocated as `<id>.render_mermaid.log` by `packages/coding-agent/src/session/artifacts.ts`.\n\n## Flow\n1. `RenderMermaidTool.execute()` in `packages/coding-agent/src/tools/render-mermaid.ts` receives `mermaid` and optional `config`.\n2. `sanitizeRenderConfig()` normalizes `paddingX`, `paddingY`, and `boxBorderPadding` to non-negative integers; `useAscii` is passed through.\n3. The tool calls `renderMermaidAscii()` from `@oh-my-pi/pi-utils`.\n4. `packages/utils/src/mermaid-ascii.ts` forwards directly to `renderMermaidASCII()` from the `beautiful-mermaid` package.\n5. The tool optionally asks the session for an artifact slot with `allocateOutputArtifact(\"render_mermaid\")`.\n6. If a path is returned, `Bun.write()` persists the full rendered text to that file.\n7. The tool returns the rendered text, plus an `artifact://` line and `details.artifactId` when persistence succeeded.\n\n## Modes / Variants\n- Default render: Unicode box-drawing output when `config.useAscii` is omitted or false.\n- ASCII render: plain ASCII output when `config.useAscii` is true.\n- Persistent-session path: artifact text is written when `allocateOutputArtifact()` returns a path.\n- Ephemeral-session path: no artifact is written; the inline text result is still returned.\n\n## Side Effects\n- Filesystem\n  - May write one session artifact via `Bun.write()`.\n  - Artifact filename format is `<id>.render_mermaid.log`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Consumes the session artifact allocator hook.\n  - Returns `details.artifactId` for the tool result.\n\n## Limits & Caps\n- No tool-local timeout, retry, truncation, or streaming path.\n- Numeric config fields are quantized to integers with `Math.floor()` and clamped to `0` minimum in `sanitizeRenderConfig()`.\n- Renderer engine is `beautiful-mermaid@1.1.3` per root `package.json` / `bun.lock`.\n- The tool is registered as discoverable and gated by `renderMermaid.enabled` in `packages/coding-agent/src/tools/index.ts`.\n\n## Errors\n- `renderMermaidAscii()` is not wrapped in a local `try/catch`; renderer exceptions propagate out of `execute()`.\n- Invalid Mermaid syntax therefore fails the tool call rather than returning partial output.\n- Artifact allocation failures inside the SDK hook are swallowed there and converted to `{}` in `packages/coding-agent/src/sdk.ts`; rendering still succeeds, just without a saved artifact.\n- Artifact write failures from `Bun.write()` are not caught in the tool and will fail the call.\n\n## Notes\n- The tool summary string says `Render a Mermaid diagram to an image`, but the implementation and prompt both produce text, not images.\n- Despite the name, this tool does not use Puppeteer, browser rendering, Mermaid CLI, or native bindings; rendering stays in-process through the JS package wrapper.\n- `docs/render-mermaid.md` covers operator-facing behavior and enablement; keep this file focused on the tool contract and runtime path.\n",
+	"tools/resolve.md": "# resolve\n\n> Finalizes a queued preview action by applying or discarding it.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/resolve.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/resolve.md`\n- Key collaborators:\n  - `docs/resolve-tool-runtime.md` — preview/apply runtime reference\n  - `packages/coding-agent/src/extensibility/custom-tools/loader.ts` — forwards custom pending actions into the queue\n  - `packages/coding-agent/src/tools/ast-edit.ts` — built-in preview producer example\n  - `packages/coding-agent/src/session/agent-session.ts` — tool-choice queue and invoker access\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | `\"apply\" | \"discard\"` | Yes | Whether to commit or reject the queued preview. |\n| `reason` | `string` | Yes | Required explanation passed through to the queued callback. |\n\n## Outputs\n- Single-shot result.\n- `execute()` returns whatever the queued invoker returns, with `details` wrapped/augmented to include:\n  - `action`\n  - `reason`\n  - `sourceToolName?`\n  - `label?`\n  - `sourceResultDetails?` — original `result.details` from the apply/reject callback when present\n- If `discard` has no custom reject callback, the default success payload is `Discarded: <label>. Reason: <reason>`.\n- The TUI renderer is inline and merges call+result into one block.\n\n## Flow\n1. Preview-producing code calls `queueResolveHandler(...)` with a label, source tool name, and `apply(reason)` callback, plus optional `reject(reason)`.\n2. `queueResolveHandler(...)` asks the session for a forced `resolve` tool choice and pushes it into the tool-choice queue with `pushOnce(...)`.\n3. The queued entry is marked `now: true`; if the model rejects that forced tool choice, `onRejected` returns `requeue`, so the reminder comes back.\n4. `queueResolveHandler(...)` also injects a `resolve-reminder` steering message: `This is a preview. Call the resolve tool to apply or discard these changes.`\n5. When `resolve.execute()` runs, it wraps the call in `untilAborted(...)` and fetches the current queue invoker with `session.peekQueueInvoker()`.\n6. If no invoker exists, it throws `ToolError(\"No pending action to resolve. Nothing to apply or discard.\")`.\n7. Otherwise it invokes the queued callback with `{ action, reason }`.\n8. For `apply`, it always executes the producer's `apply(reason)` callback.\n9. For `discard`, it executes `reject(reason)` when provided; if that callback is absent or returns `undefined`, `resolve` fabricates the default discard message.\n10. Before returning, it merges resolve metadata into `result.details` so renderer/UI code can show the action, label, and originating tool.\n\n## Modes / Variants\n- `apply`: runs the queued `apply(reason)` callback and returns its content.\n- `discard` with reject callback: runs `reject(reason)` and returns that callback's content.\n- `discard` without reject callback: returns the built-in `Discarded: ...` text payload.\n\n## Side Effects\n- Session state\n  - Consumes the current pending preview through the session tool-choice queue; there is no separate pending-action stack.\n  - Adds a `resolve-reminder` steering message when a preview is queued.\n- User-visible prompts / interactive UI\n  - No direct prompt. The visible effect depends on the preview-producing tool and the resolve renderer.\n- Background work / cancellation\n  - `untilAborted(...)` lets abort signals interrupt resolution before invoking the callback completes.\n\n## Limits & Caps\n- Hidden tool: not discoverable in the normal tool index (`packages/coding-agent/src/tools/resolve.ts`, `packages/coding-agent/src/session/agent-session.ts`).\n- Exactly one active queue invoker is consulted per call via `session.peekQueueInvoker()`.\n- There is no independent queue depth cap in this tool; ordering follows the shared tool-choice queue (`docs/resolve-tool-runtime.md`).\n\n## Errors\n- No pending preview: throws `ToolError(\"No pending action to resolve. Nothing to apply or discard.\")`.\n- Any exception from the queued `apply` / `reject` callback propagates through `resolve`.\n- Aborts during `untilAborted(...)` surface as the underlying abort error from the utility.\n\n## Notes\n- `reason` is informational; `resolve` passes it through but does not interpret it.\n- `queueResolveHandler(...)` is the canonical built-in integration point; custom tools use `pushPendingAction(...)`, which the loader forwards into the same mechanism.\n- The tool only works because another tool already staged a preview and forced a one-shot `resolve` choice.\n- `sourceResultDetails` is added only when the apply/reject callback returned a non-null `details` field; custom pending-action `details` are not forwarded automatically by the loader.\n",
+	"tools/retain.md": "# retain\n\n> Queue durable facts for asynchronous write into the active Hindsight bank.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/hindsight-retain.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/retain.md`\n- Key collaborators:\n  - `packages/coding-agent/src/hindsight/state.ts` — per-session queue, flush, auto-retain.\n  - `packages/coding-agent/src/hindsight/backend.ts` — session bootstrap, prompt injection, subagent aliasing.\n  - `packages/coding-agent/src/hindsight/bank.ts` — bank id derivation, tag scoping, mission setup.\n  - `packages/coding-agent/src/hindsight/client.ts` — HTTP `retain` / `retainBatch` calls.\n  - `packages/coding-agent/src/hindsight/content.ts` — retention transcript shaping, memory-tag stripping.\n  - `packages/coding-agent/src/hindsight/mental-models.ts` — bank-scoped mental-model seeding and cache rendering.\n  - `packages/coding-agent/src/hindsight/seeds.json` — built-in mental-model seed definitions.\n  - `packages/coding-agent/src/hindsight/transcript.ts` — extracts user/assistant turns for auto-retain.\n\n## Inputs\n\n| Field | Type | Required | Description |\n|---|---|---:|---|\n| `items` | `Array<{ content: string; context?: string }>` | Yes | One or more memories to queue. `minItems: 1`. Each item must be self-contained; `context` is optional per-item provenance. |\n\n## Outputs\nReturns a single-shot tool result:\n\n- `content[0].type = \"text\"`\n- `content[0].text = \"<count> memory queued.\"` or `\"<count> memories queued.\"`\n- `details = { count: number }`\n\nThe write is not confirmed before the tool returns. The queue flushes later; flush failures emit a session warning notice and are not returned to the model.\n\n## Flow\n1. `HindsightRetainTool.createIf(...)` only exposes the tool when `memory.backend == \"hindsight\"` in `packages/coding-agent/src/tools/hindsight-retain.ts`.\n2. `execute(...)` fetches `session.getHindsightSessionState()` and throws if the Hindsight backend was not started.\n3. Each input item is handed to `HindsightSessionState.enqueueRetain(...)` in `packages/coding-agent/src/hindsight/state.ts`.\n4. `HindsightRetainQueue.enqueue(...)` appends the item and either:\n   - flushes immediately when the queue reaches `RETAIN_FLUSH_BATCH_SIZE`, or\n   - starts a debounce timer for `RETAIN_FLUSH_INTERVAL_MS`.\n5. On flush, `HindsightRetainQueue.#doFlush(...)`:\n   - verifies the session still owns this state,\n   - calls `ensureBankMission(...)` once per bank/process before writing,\n   - maps queued items to `MemoryItemInput` with `context ?? config.retainContext`, `metadata.session_id`, and bank-scope tags,\n   - sends one async `retainBatch(...)` request.\n6. The tool returns immediately after enqueueing; it does not await the HTTP write.\n\n## Modes / Variants\n- Tool path: queued batch write only.\n- Bank scoping comes from `computeBankScope(...)` in `packages/coding-agent/src/hindsight/bank.ts`:\n  - `global` — one shared bank, no project tags.\n  - `per-project` — bank id gets `-<cwd basename>` appended.\n  - `per-project-tagged` — shared bank plus `project:<cwd basename>` tags on retained memories.\n- Session scope:\n  - tool-called retains are per-session queued work in `HindsightSessionState`,\n  - persisted memories are cross-session server-side bank data,\n  - subagents alias the parent `HindsightSessionState`, so their `retain` calls write into the same bank and queue.\n\n## Side Effects\n- Filesystem\n  - None for retained memories. No local memory file is written.\n- Network\n  - `POST /v1/default/banks/{bank_id}/memories` via `retainBatch(...)` in `packages/coding-agent/src/hindsight/client.ts`.\n  - Optional `PUT /v1/default/banks/{bank_id}` via `ensureBankMission(...)` before first write per bank/process.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Appends to the in-memory `HindsightRetainQueue` on the active `HindsightSessionState`.\n  - Includes `metadata.session_id` on each retained item.\n  - Shares parent state for subagents (`aliasOf` path in `packages/coding-agent/src/hindsight/backend.ts`).\n- User-visible prompts / interactive UI\n  - On async flush failure, emits `session.emitNotice(\"warning\", ...)`; the model is not told.\n- Background work / cancellation\n  - Flush runs later on timer, queue-size threshold, `agent_end`, backend `enqueue(...)`, or backend `clear(...)`.\n\n## Limits & Caps\n- Input schema requires `items.length >= 1` in `packages/coding-agent/src/tools/hindsight-retain.ts`.\n- Queue flush threshold: `RETAIN_FLUSH_BATCH_SIZE = 16` in `packages/coding-agent/src/hindsight/state.ts`.\n- Queue debounce: `RETAIN_FLUSH_INTERVAL_MS = 5_000` in `packages/coding-agent/src/hindsight/state.ts`.\n- Queue writes use `retainBatch(..., { async: true })`; the client does not wait for server-side consolidation.\n- Shared auto-retain settings on the same backend:\n  - `hindsight.retainEveryNTurns` default `3`\n  - `hindsight.retainOverlapTurns` default `2`\n  - `hindsight.retainContext` default `\"omp\"`\n  - `hindsight.retainMode` default `\"full-session\"`\n  from `packages/coding-agent/src/config/settings-schema.ts`.\n\n## Errors\n- Throws `Hindsight backend is not initialised for this session.` when no state exists.\n- Queue enqueue on disposed state throws `Hindsight retain queue is closed.`\n- Flush-time API failures are caught in `HindsightRetainQueue.#doFlush(...)`, logged, and converted into a warning notice instead of a tool error.\n- Mission creation failures are swallowed in `ensureBankMission(...)`; writes continue.\n\n## Notes\n- Storage is server-side. `hindsightBackend.clear(...)` only clears local cache/state and warns that upstream deletion must happen in Hindsight UI or `deleteBank`; see `packages/coding-agent/src/hindsight/backend.ts`.\n- Auto-retain uses the same bank but a different path than this tool: `retainSession(...)` extracts plain user/assistant transcript from `packages/coding-agent/src/hindsight/transcript.ts`, strips `<memories>` / `<mental_models>` blocks via `stripMemoryTags(...)`, and calls single-item `retain(...)`.\n- `retain` itself does not seed or read mental models. Mental-model bootstrap lives in the shared backend: `HindsightSessionState.runMentalModelLoad(...)` optionally resolves seeds from `packages/coding-agent/src/hindsight/seeds.json`, creates missing models with `ensureMentalModels(...)`, then caches a rendered `<mental_models>` block for prompt injection.\n- Built-in seeds are `user-preferences`, `project-conventions`, and `project-decisions`. `projectTagged: true` seeds inherit the active scope's retain tags; untagged seeds read the whole bank.\n- Mental-model defaults from `packages/coding-agent/src/config/settings-schema.ts`: `hindsight.mentalModelsEnabled = true`, `hindsight.mentalModelAutoSeed = true`, `hindsight.mentalModelRefreshIntervalMs = 5 * 60 * 1000`, `hindsight.mentalModelMaxRenderChars = 16_000`. First-turn loading waits up to `MENTAL_MODEL_FIRST_TURN_DEADLINE_MS = 1500` in `packages/coding-agent/src/hindsight/mental-models.ts`.\n- Seed lifecycle is create-only. Changing `packages/coding-agent/src/hindsight/seeds.json` does not mutate existing server-side models.\n- `recall.md` and `reflect.md` rely on the same bank, scoping, and mental-model bootstrap; refer back here for the shared backend behavior.\n",
+	"tools/rewind.md": "# rewind\n\n> End an active checkpoint by pruning exploratory context and retaining a concise report.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/checkpoint.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/rewind.md`\n- Key collaborators:\n  - `packages/coding-agent/src/session/agent-session.ts` — validates pending rewind state, applies the actual rewind, and injects the retained report.\n  - `packages/coding-agent/src/session/session-manager.ts` — branches the persisted session tree and appends persisted summary/report entries.\n  - `packages/coding-agent/src/session/messages.ts` — converts persisted `branch_summary` entries into LLM-visible branch-summary messages on rebuilt context.\n  - `packages/coding-agent/src/tools/index.ts` — registers the tool and shares the `checkpoint.enabled` gate.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `report` | `string` | Yes | Investigation findings. `execute()` trims it and rejects the empty result. |\n\n## Outputs\nThe tool returns a single text result plus structured details:\n\n- text body:\n  - `Rewind requested.`\n  - `Report captured for context replacement.`\n- `details`:\n  - `report: string` — trimmed report text\n  - `rewound: true`\n\nThe returned tool result is not the final rewind. `AgentSession` waits until `turn_end`, then applies the rewind side effects asynchronously.\n\n## Flow\n1. `RewindTool.createIf()` in `packages/coding-agent/src/tools/checkpoint.ts` hides the tool from subagents.\n2. `RewindTool.execute()` rejects subagent calls with `ToolError(\"Checkpoint not available in subagents.\")`.\n3. It rejects calls with no active checkpoint using `ToolError(\"No active checkpoint.\")`.\n4. It trims `params.report`; if empty, it throws `ToolError(\"Report cannot be empty.\")`.\n5. It returns a `toolResult()` with `details.report` and `details.rewound = true`.\n6. On `tool_execution_end`, `AgentSession` extracts the report from `details.report` or the first text content block and stores it in `#pendingRewindReport`.\n7. On `turn_end`, if `#pendingRewindReport` is set, `AgentSession.#applyRewind()` runs.\n8. `#applyRewind()` computes `safeCount = clamp(checkpointMessageCount, 0, agent.state.messages.length)` and calls `agent.replaceMessages(agent.state.messages.slice(0, safeCount))`.\n9. It then calls `sessionManager.branchWithSummary(checkpointEntryId, report, { startedAt })`. That moves the persisted session leaf back to the checkpoint entry and appends a new `branch_summary` entry whose `summary` is the rewind report.\n10. If `checkpointEntryId` no longer resolves, it logs a warning and falls back to `branchWithSummary(null, report, { startedAt })`, branching from root instead.\n11. `#applyRewind()` appends a hidden in-memory custom message `{ customType: \"rewind-report\", content: report, display: false }` and persists the same payload through `sessionManager.appendCustomMessageEntry(\"rewind-report\", ...)` with `details = { startedAt, rewoundAt }`.\n12. Finally it clears `#checkpointState` and `#pendingRewindReport`.\n\n## Modes / Variants\n- Normal rewind: checkpoint entry exists; session history branches from that exact entry.\n- Fallback rewind: checkpoint entry ID is missing from the current session tree; rewind branches from root and logs a warning.\n- Immediate turn-end apply: rewind side effects happen only after the surrounding assistant turn finishes, not inside `RewindTool.execute()`.\n\n## Side Effects\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Replaces in-memory conversation history with the prefix ending at the checkpoint tool result.\n  - Adds a hidden custom message `rewind-report` carrying the retained report.\n  - Clears the active checkpoint state and pending rewind report.\n  - Repositions the persisted session leaf to the checkpoint branch point and appends new session entries.\n- Filesystem\n  - Persists the new `branch_summary` and `custom_message` entries into the session `.jsonl` file through normal `SessionManager` append persistence.\n  - Session files are named `<ISO-timestamp-with-:-and-.-replaced>_<uuidv7>.jsonl` in the session directory; default directory selection is documented in `SessionManager.create()` as `~/.omp/agent/sessions/<encoded-cwd>/` when no override is passed.\n- User-visible prompts / interactive UI\n  - The tool result itself is visible.\n  - The persisted `branch_summary` becomes an LLM-visible `branchSummary` message when context is rebuilt from `SessionManager.buildSessionContext()`; `messages.ts` renders it as a user-role text message using `prompts/compaction/branch-summary-context.md`.\n  - The persisted `rewind-report` custom message also participates in rebuilt LLM context because `custom_message` entries are converted through `createCustomMessage()`.\n- Background work / cancellation\n  - Rewind application is deferred to `turn_end`. There is no separate job object or cancel handle.\n\n## Limits & Caps\n- Availability is gated by `checkpoint.enabled`, default `false`, in `packages/coding-agent/src/config/settings-schema.ts`.\n- Top-level sessions only.\n- Requires exactly one active checkpoint; there is no path to name or choose among multiple checkpoints.\n- Report text must be non-empty after `trim()`.\n- Rewind restores only the message prefix recorded by `checkpointMessageCount`; there is no file restore, artifact restore, blob restore, or process restore path.\n- Persisted report/summary content is still subject to the global session persistence cap `MAX_PERSIST_CHARS = 500_000` in `packages/coding-agent/src/session/session-manager.ts`.\n\n## Errors\n- `ToolError(\"Checkpoint not available in subagents.\")` — thrown for subagent sessions.\n- `ToolError(\"No active checkpoint.\")` — thrown when no checkpoint state is present.\n- `ToolError(\"Report cannot be empty.\")` — thrown when the trimmed report is empty.\n- Missing checkpoint entry IDs during apply do not fail the tool call; `#applyRewind()` catches the error, logs `Rewind branch checkpoint missing, falling back to root`, and branches from root.\n- If the agent turn is aborted while a checkpoint is active, `AgentSession` clears checkpoint state rather than applying a delayed rewind.\n\n## Notes\n- Checkpoint selection is implicit. `rewind` always targets the single `#checkpointState` captured by the last successful `checkpoint`; there is no checkpoint list, label, or ID parameter.\n- Restored state is transcript/session-tree state only:\n  - in-memory `agent.state.messages` prefix up to `checkpointMessageCount`\n  - persisted session leaf reset to `checkpointEntryId` or root fallback\n  - retained rewind report as `branch_summary` and hidden `rewind-report` custom message\n- Not restored:\n  - filesystem contents\n  - git state\n  - artifacts under `packages/coding-agent/src/session/artifacts.ts`\n  - blob-store payloads under `packages/coding-agent/src/session/blob-store.ts`\n  - prompt history rows in `packages/coding-agent/src/session/history-storage.ts`\n  - auth or other agent storage in `packages/coding-agent/src/session/agent-storage.ts`\n- There is no concurrent-edit reconciliation. If code or session-adjacent state changes during the checkpoint window, rewind does not merge or revert them; it only drops conversation context and rewires the session branch.\n- Rewind is not destructive to persisted session history. `branchWithSummary()` appends a new `branch_summary` entry and moves the leaf; it does not delete the abandoned path from the `.jsonl` session log. The active context is cut over to the new branch, but the old entries remain in session storage.\n",
+	"tools/search.md": "# search\n\n> Search file contents with a regex across files, directories, globs, and internal URLs.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/search.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/search.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/match-line-format.ts` — model-facing anchor formatting.\n  - `packages/coding-agent/src/tools/path-utils.ts` — path normalization, glob splitting, internal URL resolution.\n  - `packages/coding-agent/src/tools/file-recorder.ts` — file ordering for grouped output.\n  - `packages/coding-agent/src/tools/grouped-file-output.ts` — grouped per-file text layout.\n  - `packages/coding-agent/src/session/streaming-output.ts` — line truncation and final byte truncation.\n  - `packages/coding-agent/src/config/settings-schema.ts` — default context lines.\n  - `packages/natives/native/index.d.ts` — native `grep()` types exposed to TS.\n  - `crates/pi-natives/src/grep.rs` — native regex/file search implementation.\n  - `docs/natives-text-search-pipeline.md` — native search pipeline overview.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `pattern` | `string` | Yes | Regex pattern. `search.ts` trims it and rejects empty input. The native matcher enables multiline only when the pattern text contains a literal newline or the two-character sequence `\\\\n`. The model prompt explicitly documents literal-brace escaping such as ``interface\\\\{\\\\}``, although the native layer also auto-escapes braces that cannot be valid repetition quantifiers. |\n| `paths` | `string[]` | Yes | One or more file paths, directory paths, glob-like paths, or internal URLs. Empty strings are rejected after trimming/quote stripping. Internal URLs must resolve to a backing file and cannot contain glob characters. |\n| `i` | `boolean` | No | Case-insensitive search. Defaults to `false`. Passed to native `ignoreCase`. |\n| `gitignore` | `boolean` | No | Respect `.gitignore` during directory scans. Defaults to `true`. Passed to native `gitignore`. |\n| `skip` | `number` | No | Global match offset. Defaults to `0`. `search.ts` floors finite numbers and rejects negative or non-finite values. |\n\n## Outputs\nThe tool returns a single text block in `content[0].text` plus structured `details`.\n\n- Match lines are formatted by `formatMatchLine()` as `*<anchor>|<line>` for matches and ` <anchor>|<line>` for context.\n  - Hashline mode: `*5th|content`, ` 9x}|content`.\n  - Plain mode: `*5|content`, ` 9|content`.\n- Directory results are grouped by file, with `# <path>` headings and blank lines between groups.\n- `details` may include:\n  - `scopePath` — formatted search scope.\n  - `matchCount`, `fileCount`, `files`, `fileMatches` — counts for the returned page, not necessarily total corpus counts.\n  - `matchLimitReached` — visible-page limit hit (`100`).\n  - `resultLimitReached` — native preselection limit hit (`500`).\n  - `linesTruncated` — one or more matched lines were shortened to `1024` chars plus `…`.\n  - `truncated` and `meta.truncation` — final text output was head-truncated by `truncateHead()`.\n  - `displayContent` — TUI-only rendering text with `│` gutters instead of model anchors.\n  - `missingPaths` — multi-path entries skipped because their base path did not exist.\n- No-match result text is `No matches found`, optionally followed by `Skipped missing paths: ...`.\n\n## Flow\n1. `SearchTool.execute()` validates and normalizes input in `packages/coding-agent/src/tools/search.ts`:\n   - trims `pattern`, rejects empty patterns;\n   - normalizes `skip` to a non-negative integer;\n   - reads `search.contextBefore` and `search.contextAfter` from session settings (`1` and `3` by default);\n   - enables multiline only when `pattern` contains `\\n` or an actual newline.\n2. Each `paths` entry is normalized with `normalizePathLikeInput()`.\n3. Internal URLs are resolved through `session.internalRouter`:\n   - glob metacharacters (`*`, `?`, `[`, `{`) are rejected for internal URLs;\n   - URLs without `resource.sourcePath` fail;\n   - immutable sources are tracked so output can suppress editable hashline anchors per file.\n4. For multi-path calls, `partitionExistingPaths()` skips only ENOENT entries. If every entry is missing, the tool errors.\n5. Path resolution branches:\n   - one entry: `parseSearchPath()` splits `basePath` and optional glob;\n   - multiple entries: `resolveExplicitSearchPaths()` computes a common base directory, brace-union glob, exact-file list, or degenerate-root target list.\n6. `search.ts` stats the resolved base path to decide file vs directory behavior.\n7. It calls native `grep()` from `@oh-my-pi/pi-natives` with:\n   - `pattern`, `ignoreCase`, `multiline`, `gitignore`;\n   - `hidden: true`;\n   - `cache: false`;\n   - `contextBefore` / `contextAfter` from settings;\n   - `maxColumns: 1024`;\n   - `mode: content`.\n8. Native execution happens in `crates/pi-natives/src/grep.rs`:\n   - `build_matcher()` sanitizes non-quantifier braces before regex compile;\n   - if compile fails with unopened/unclosed-group errors, it retries after escaping previously unescaped parentheses;\n   - directory scans use the grep pipeline described in `docs/natives-text-search-pipeline.md`.\n9. Search dispatch differs by resolved path set:\n   - exact explicit files or degenerate-root multi-targets: JS loops over targets and merges `grep()` results itself;\n   - single file/directory base: one `grep()` call handles offset/limit natively.\n10. JS output shaping then:\n   - round-robins directory matches down to `100` visible matches so one file does not monopolize the page;\n   - keeps the first `100` file matches for single-file searches;\n   - formats lines through `formatMatchLine()` for the model and `formatCodeFrameLine()` for TUI;\n   - records non-truncated matched/context lines into the session file-read cache with `recordSparse()`.\n11. Final text is passed through `truncateHead(rawOutput, { maxLines: Number.MAX_SAFE_INTEGER })`, so the effective cap is the default byte cap from `streaming-output.ts`, not the default line cap.\n12. `toolResult()` attaches text plus limit/truncation metadata.\n\n## Modes / Variants\n1. **Single file path**\n   - `grep()` searches one file.\n   - Output is a flat list of match/context lines.\n   - Visible limit is the first `100` matches after native offset handling.\n2. **Single directory path or single glob-like path**\n   - `parseSearchPath()` may split the input into `path` + `glob`.\n   - One native `grep()` scans the directory tree with `gitignore` and `hidden:true`.\n   - Native `offset` handles `skip` globally across files.\n   - JS round-robins the returned matches to `100` visible rows.\n3. **Multiple explicit paths/globs**\n   - `resolveExplicitSearchPaths()` collapses them into a common base and either a brace-union glob, an explicit file list, or per-target searches when the only common base is the filesystem root.\n   - Missing entries are skipped non-fatally unless all are missing.\n4. **Internal URL paths**\n   - Supported only when the internal resource resolves to a real backing file.\n   - No internal-URL globbing.\n   - Immutable sources switch to the immutable display mode when formatting anchors.\n\n## Side Effects\n- Filesystem\n  - Stats resolved search roots and input paths.\n  - Reads matched files through native `grep()`.\n  - Records sparse matched/context lines into the session file-read cache via `getFileReadCache(...).recordSparse(...)`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Reads session settings for context defaults.\n  - Uses `session.internalRouter` to resolve internal URLs.\n  - Populates tool `details.meta` with truncation/limit metadata.\n- Background work / cancellation\n  - Wrapped in `untilAborted(signal, ...)` at the JS level.\n  - `search.ts` does not pass `signal` or `timeoutMs` into native `grep()`, so native grep cancellation/timeouts are not used by this tool.\n\n## Limits & Caps\n- Visible page limit: `100` matches (`DEFAULT_MATCH_LIMIT` in `packages/coding-agent/src/tools/search.ts`).\n- Native preselection limit: `500` matches (`internalLimit = Math.min(DEFAULT_MATCH_LIMIT * 5, 2000)` in `packages/coding-agent/src/tools/search.ts`).\n- Line truncation: `1024` characters per emitted line (`DEFAULT_MAX_COLUMN` in `packages/coding-agent/src/session/streaming-output.ts`). Native grep marks truncated lines; JS reports `linesTruncated`.\n- Final text truncation: `truncateHead()` default byte cap `50 * 1024` bytes (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`). `search.ts` overrides `maxLines` to `Number.MAX_SAFE_INTEGER`, so normal search output is byte-capped, not line-capped.\n- Context defaults: `search.contextBefore = 1`, `search.contextAfter = 3` in `packages/coding-agent/src/config/settings-schema.ts`.\n- Pagination: `skip` is a global match offset. In single-base searches it is pushed into native `offset`; in exact-file/multi-target aggregation it is applied in JS with `matches.slice(skip)`.\n- Native directory-scan cache: available in `grep.rs`, but this tool always sets `cache: false`.\n\n## Errors\n- `Pattern must not be empty` when trimmed `pattern` is empty.\n- `Skip must be a non-negative number` for negative or non-finite `skip`.\n- `` `paths` must contain non-empty paths or globs `` when any normalized path is empty.\n- `Glob patterns are not supported for internal URLs: ...` for internal URL + glob metacharacters.\n- `Cannot search internal URL without a backing file: ...` when the router resolves a virtual resource without `sourcePath`.\n- `Path not found: ...` when the resolved base path is missing, or when every multi-path entry is missing.\n- Regex compile failures bubble from native `grep()` as tool errors. `search.ts` has a special catch for messages beginning with `regex parse error`, then otherwise rethrows.\n- Multi-file native scans skip per-file open/search failures inside `grep.rs`; the scan continues with surviving files.\n\n## Notes\n- The model-facing prompt documents standard regex syntax plus two search-specific rules: escape literal braces, and use `\\n` or a literal newline for cross-line matching.\n- Native `build_matcher()` already auto-escapes braces that cannot be valid quantifiers, so patterns like `${platform}` become searchable instead of failing. Valid quantifiers like `a{2,4}` remain unchanged.\n- Native compile retry also escapes unescaped literal parentheses only after an unopened/unclosed-group parse error. It is a fallback, not a general parser mode.\n- Internal URLs are resolved before path existence checks. After resolution, the native layer sees ordinary filesystem paths.\n- `hidden:true` is hard-coded in `search.ts`; there is no model-facing flag to exclude dotfiles.\n- `gitignore:false` only affects native directory traversal. It does not disable the tool's own path normalization or explicit-file handling.\n- When `paths` resolves to multiple exact files, `search.ts` does not apply the native `500` match cap and reports `totalMatches` internally as the post-skip length for that branch.\n- The anchor suffix in hashline mode comes from `computeLineHash()` in `packages/coding-agent/src/hashline/hash.ts`; `search` itself only formats it.\n",
+	"tools/search_tool_bm25.md": "# search_tool_bm25\n\n> Search the hidden tool-discovery index and activate the top matches for the current session.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/search-tool-bm25.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/search-tool-bm25.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tool-discovery/tool-index.ts` — discoverable-tool metadata and BM25 index/search.\n  - `packages/coding-agent/src/session/agent-session.ts` — session discovery mode, corpus assembly, activation, cache invalidation.\n  - `packages/coding-agent/src/sdk.ts` — initial hiding of discoverable built-ins and prompt-time discoverable summary.\n  - `packages/coding-agent/src/tools/index.ts` — tool-session discovery hooks, essential/discoverable load modes, registry wiring.\n  - `packages/coding-agent/src/config/settings-schema.ts` — `tools.discoveryMode` and legacy `mcp.discoveryMode` settings.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `query` | `string` | Yes | Natural-language or keyword query. Trimmed before search; empty-after-trim is rejected. |\n| `limit` | `integer` | No | Max matches to return and activate. Minimum `1`. Defaults to `8` (`DEFAULT_LIMIT`). |\n\n## Outputs\n- Single-shot `AgentToolResult`.\n- Model-visible `content` is one text part containing JSON with:\n\n```json\n{\"query\":\"...\",\"activated_tools\":[\"...\"],\"match_count\":2,\"total_tools\":17}\n```\n\n- Runtime-only `details` carries the ranked matches used by the TUI renderer:\n  - `query`, `limit`, `total_tools`\n  - `activated_tools`: tool names activated by this call\n  - `active_selected_tools`: cumulative discovered-tool selections still active\n  - `tools`: array of match objects with\n    - `name`\n    - `label`\n    - `description` (`tool.summary`; this is the only snippet-like field)\n    - optional `server_name`\n    - optional `mcp_tool_name`\n    - `schema_keys`\n    - `score` rounded to 6 decimals\n- The renderer shows a status line plus up to 5 collapsed tree items by default (`COLLAPSED_MATCH_LIMIT`), each with label, optional server name, score to 3 decimals, and truncated description. The ranked match list is not serialized into `content`.\n\n## Flow\n1. `SearchToolBm25Tool.createIf()` in `packages/coding-agent/src/tools/search-tool-bm25.ts` exposes the tool only when `tools.discoveryMode !== \"off\"` or legacy `mcp.discoveryMode === true`, and only if the session implements the discovery hooks.\n2. `description` is rendered from `packages/coding-agent/src/prompts/tools/search-tool-bm25.md` via `renderSearchToolBm25Description()`, using the current discoverable-tool list plus per-server summary/count.\n3. `execute()` re-checks capability and settings:\n   - missing discovery hooks -> `ToolError(\"Tool discovery is unavailable in this session.\")`\n   - discovery disabled -> `ToolError(\"Tool discovery is disabled. Enable tools.discoveryMode or mcp.discoveryMode to use search_tool_bm25.\")`\n4. `query` is trimmed and validated; `limit` is defaulted/validated.\n5. `getDiscoverableToolSearchIndexForExecution()` fetches the cached generic search index from the session when available, otherwise falls back to the legacy MCP cache, otherwise rebuilds an index from the current discoverable-tool list.\n6. `getSelectedToolNames()` reads the current discovered selections so already-selected tools can be excluded from fresh results.\n7. `searchDiscoverableTools()` in `packages/coding-agent/src/tool-discovery/tool-index.ts` tokenizes the query, scores every document with BM25, sorts by descending score then `tool.name`, and returns up to `searchIndex.documents.length` results; `execute()` then filters already-selected names and slices to `limit`.\n8. If any matches remain, `activateTools()` activates all matched tool names through `session.activateDiscoveredTools()` or legacy `activateDiscoveredMCPTools()`.\n9. `details` is assembled from the activated names, current selected names, corpus size, and formatted matches; `content` is reduced to the compact JSON summary from `buildSearchToolBm25Content()`.\n10. `searchToolBm25Renderer` renders either:\n   - the structured `details` view, or\n   - a fallback text-only warning block if `details` is absent.\n\n## Modes / Variants\n- Discovery-mode gating:\n  - `tools.discoveryMode = \"all\"`: searches hidden discoverable built-ins plus hidden MCP tools.\n  - `tools.discoveryMode = \"mcp-only\"`: searches hidden MCP tools only.\n  - legacy `mcp.discoveryMode = true` with `tools.discoveryMode = \"off\"`: same as MCP-only.\n- Search-index source:\n  - generic cached discoverable index from the session\n  - legacy cached MCP index, cast to the generic shape\n  - rebuilt ad hoc from the current discoverable-tool list if neither cache path works\n- Activation backend:\n  - generic `activateDiscoveredTools()`\n  - legacy `activateDiscoveredMCPTools()` fallback\n\n## Side Effects\n- Session state\n  - Adds matched tools to the active session tool set through `activateDiscoveredTools()` / `activateDiscoveredMCPTools()`.\n  - Updates discovered-tool selection state so repeated searches accumulate selections instead of replacing them.\n  - Invalidates the cached discoverable search index when newly activated built-ins change the hidden corpus (`packages/coding-agent/src/session/agent-session.ts`).\n  - Tool availability changes before the next model call in the same turn; the prompt text says this explicitly.\n- User-visible prompts / interactive UI\n  - The tool description includes discoverable server summaries and total discoverable-tool count.\n  - The TUI renderer shows ranked matches, but the model-visible text summary does not.\n\n## Limits & Caps\n- Default result cap: `8` (`DEFAULT_LIMIT` in `packages/coding-agent/src/tools/search-tool-bm25.ts`).\n- `limit` must be a positive integer; no tool-level upper bound beyond corpus size.\n- Renderer collapsed list cap: `5` (`COLLAPSED_MATCH_LIMIT`).\n- Renderer truncation widths:\n  - label: `72` chars (`MATCH_LABEL_LEN`)\n  - description: `96` chars (`MATCH_DESCRIPTION_LEN`)\n- BM25 parameters in `packages/coding-agent/src/tool-discovery/tool-index.ts`:\n  - `BM25_K1 = 1.2`\n  - `BM25_B = 0.75`\n- Weighted corpus fields (`FIELD_WEIGHTS`):\n  - `name`: `6`\n  - `label`: `4`\n  - `mcpToolName`: `4`\n  - `serverName`: `2`\n  - `summary`: `2`\n  - each `schemaKey`: `1`\n- Summary fallback length for discoverable metadata: first `200` chars of `description` when no explicit summary exists (`getDiscoverableTool()` in `packages/coding-agent/src/tool-discovery/tool-index.ts`).\n\n## Errors\n- `execute()` throws `ToolError` for unavailable discovery hooks, disabled discovery mode, empty trimmed query, and non-positive/non-integer `limit`.\n- `searchDiscoverableTools()` throws `Error(\"Query must contain at least one letter or number.\")` if tokenization produces no alphanumeric tokens; `execute()` catches `Error` and rethrows `ToolError(error.message)`.\n- Empty corpus is not an error; search returns `[]`, activation is skipped, and the renderer message becomes either `No discoverable tools are currently loaded.` or `No matching tools found.`\n- `getDiscoverableToolsForDescription()` and `getDiscoverableToolSearchIndexForExecution()` swallow discovery-hook/cache errors and fall back to an empty corpus or rebuilt index.\n\n## Notes\n- The tool wire name stays `search_tool_bm25` for persisted-session back-compat, even though the source file is `search-tool-bm25.ts`.\n- Corpus composition is session-dependent and excludes already-active tools:\n  - MCP entries come from `#discoverableMCPTools`, filtered to names not currently active, mapped with `summary = description`.\n  - Built-in entries appear only in `\"all\"` mode and only for registry tools whose `loadMode === \"discoverable\"` and are not currently active.\n  - Hidden/internal built-ins are intentionally excluded from the built-in corpus: `resolve`, `yield`, `exit_plan_mode`, `report_finding`, `report_tool_issue` are called out in the `#collectDiscoverableBuiltinTools()` comment.\n- `DiscoverableToolSource` includes `\"extension\"` and `\"custom\"`, but `AgentSession.getDiscoverableTools()` currently assembles only built-in and MCP sources.\n- On startup, `packages/coding-agent/src/sdk.ts` hides non-essential discoverable built-ins in `tools.discoveryMode = \"all\"`; defaults are `read`, `bash`, and `edit` unless `tools.essentialOverride` changes them.\n- Query tokenization is simple and deterministic: camelCase is split, non-alphanumerics become spaces, tokens are lowercased, and only non-empty alphanumeric tokens survive.\n- Scores are rounded differently by surface: `details.tools[].score` keeps 6 decimals; the TUI line renders 3.\n",
+	"tools/ssh.md": "# ssh\n\n> Execute one remote command on a discovered SSH host.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ssh.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ssh.md`\n- Key collaborators:\n  - `packages/coding-agent/src/ssh/ssh-executor.ts` — runs `ssh`, captures output\n  - `packages/coding-agent/src/ssh/connection-manager.ts` — master-connection reuse, host probing\n  - `packages/coding-agent/src/ssh/sshfs-mount.ts` — optional `sshfs` mount side effect\n  - `packages/coding-agent/src/discovery/ssh.ts` — discovers host configs\n  - `packages/coding-agent/src/capability/ssh.ts` — canonical host shape\n  - `packages/coding-agent/src/session/streaming-output.ts` — tail streaming, truncation, artifacts\n  - `packages/coding-agent/src/tools/tool-timeouts.ts` — timeout clamp rules\n  - `packages/utils/src/dirs.ts` — user/project ssh config paths\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `host` | `string` | Yes | Host name key from discovered SSH config entries, not an arbitrary hostname/IP. |\n| `command` | `string` | Yes | Remote command string passed to `ssh` as the remote command. |\n| `cwd` | `string` | No | Remote working directory. The tool prepends a shell-specific `cd`/`Set-Location` wrapper. |\n| `timeout` | `number` | No | Timeout in seconds. Default `60`; clamped to `1..3600`. |\n\n## Outputs\nThe tool returns a standard text tool result built in `packages/coding-agent/src/tools/ssh.ts`:\n\n- `content`: one text block containing combined remote stdout+stderr, or `\"(no output)\"` when empty.\n- `details.meta.truncation`: present when output exceeded the in-memory tail window; derived from the executor summary.\n\nStreaming behavior:\n\n- While the command runs, `onUpdate` receives tail-only text snapshots built from `TailBuffer` in `packages/coding-agent/src/session/streaming-output.ts`.\n- Final output is single-shot after process exit.\n\nSide-channel artifacts:\n\n- When session artifact allocation is available and output exceeds the spill threshold, full output is written to a session artifact file and the returned summary carries its `artifactId` internally.\n- The ssh tool itself does not print the `artifact://...` URI into the result text.\n\nFailure behavior:\n\n- Unknown host, missing host config, timeout, cancellation, SSH startup failure, key validation failure, or non-zero remote exit all surface as thrown `ToolError`s.\n- Non-zero remote exit includes captured output plus `Command exited with code N`.\n\n## Flow\n1. `loadSshTool()` in `packages/coding-agent/src/tools/ssh.ts` calls `loadCapability(sshCapability.id, { cwd: session.cwd })` to discover hosts.\n2. `packages/coding-agent/src/discovery/ssh.ts` loads host entries from, in this order: project managed ssh config, user managed ssh config, `ssh.json` in the repo root, `.ssh.json` in the repo root.\n3. `getSSHConfigPath(\"project\")` and `getSSHConfigPath(\"user\")` in `packages/utils/src/dirs.ts` resolve those managed files to `.omp/ssh.json` in the project and `~/.omp/agent/ssh.json` in the user config dir. This tool does not read `~/.ssh/config`.\n4. Capability loading deduplicates by host name with first item winning; provider order is priority-sorted and the SSH JSON provider registers at priority `5`.\n5. `loadHosts()` in `packages/coding-agent/src/tools/ssh.ts` builds `hostsByName` and drops later duplicates again with `if (!hostsByName.has(host.name))`.\n6. Tool description text is built from `packages/coding-agent/src/prompts/tools/ssh.md` plus an `Available hosts:` list. Each host entry calls `getHostInfoForHost()` to show detected shell/OS when cached; otherwise it renders `detecting...`.\n7. On execute, `SshTool.execute()` rejects any `host` not in the discovered host-name set.\n8. `ensureHostInfo()` in `packages/coding-agent/src/ssh/connection-manager.ts` ensures an SSH master connection exists, loads cached host info from disk if present, and probes remote OS/shell when cache is missing or stale.\n9. `buildRemoteCommand()` in `packages/coding-agent/src/tools/ssh.ts` prepends a cwd change when `cwd` is provided:\n   - Unix-like or Windows compat shells: `cd -- '<cwd>' && <command>`\n   - Windows PowerShell: `Set-Location -Path '<cwd>'; <command>`\n   - Windows cmd: `cd /d \"<cwd>\" && <command>`\n10. `clampTimeout(\"ssh\", rawTimeout)` applies the `1..3600` second clamp from `packages/coding-agent/src/tools/tool-timeouts.ts`.\n11. `executeSSH()` in `packages/coding-agent/src/ssh/ssh-executor.ts` calls `ensureConnection(host)` again, opportunistically mounts the remote host root with `sshfs` if available, optionally wraps the command in `bash -c` or `sh -c` for Windows compat mode, then spawns `ssh` with `ptree.spawn`.\n12. Output from both stdout and stderr is piped into one `OutputSink`; chunks are sanitized and forwarded to streaming updates through `streamTailUpdates()`.\n13. On normal exit, the sink returns combined output plus truncation counters. On timeout or abort, `executeSSH()` returns `cancelled: true` and prefixes the output with a notice line such as `[SSH: ...]` or `[Command aborted: ...]`.\n14. `SshTool.execute()` converts `cancelled: true` into `ToolError`, converts non-zero exit codes into `ToolError`, otherwise returns the text result with truncation metadata.\n\n## Modes / Variants\n- **Tool unavailable**: `loadSshTool()` returns `null` when discovery finds no hosts, so the tool is not registered for that session.\n- **Unix-like target**: remote command is passed through directly, with optional `cd -- ... &&` prefix.\n- **Windows native shell**: cwd wrapper uses PowerShell `Set-Location` or cmd `cd /d`; command otherwise runs in the remote default Windows shell.\n- **Windows compat shell**: if host probing finds `bash` or `sh` on Windows, `executeSSH()` wraps the remote command as `bash -c '...'` or `sh -c '...'`. Host config can force compat on/off with `compat`.\n- **Cached vs probed host info**: shell/OS detection comes from in-memory cache, persisted JSON under the remote-host dir, or a fresh probe over SSH.\n- **Truncated vs untruncated output**: small output stays in memory; large output keeps only the last 50 KiB in memory and may spill full output to an artifact file.\n\n## Side Effects\n- Filesystem\n  - Reads managed SSH config JSON plus legacy `ssh.json` / `.ssh.json`.\n  - Validates private-key path existence and permissions before connecting.\n  - Persists probed host info as JSON under the remote-host cache dir via `persistHostInfo()`.\n  - May create the SSH control socket dir and, when `sshfs` exists, remote mount dirs.\n  - May write full command output to a session artifact file.\n- Network\n  - Opens SSH connections to the selected host.\n  - May issue extra probe commands to detect OS/shell and compat shells.\n- Subprocesses / native bindings\n  - Requires `ssh` on `PATH`; spawns it for connection checks, master startup, probing, and command execution.\n  - May call `sshfs`, `mountpoint`, `fusermount`/`fusermount3`, or `umount`.\n  - Sanitizes streamed text with `@oh-my-pi/pi-natives` text sanitization.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Uses session artifact allocation when available.\n  - Registers postmortem cleanup hooks for SSH master connections and sshfs mounts.\n  - Tool concurrency is `exclusive`, so the agent scheduler should not run multiple ssh tool calls concurrently.\n- Background work / cancellation\n  - Process spawn receives the tool `AbortSignal`.\n  - Cancellation/timeout ends the running ssh process and returns a cancelled result that the tool turns into an error.\n\n## Limits & Caps\n- Timeout defaults/clamps: `default=60`, `min=1`, `max=3600` in `packages/coding-agent/src/tools/tool-timeouts.ts`.\n- Output tail window: `DEFAULT_MAX_BYTES = 50 * 1024` in `packages/coding-agent/src/session/streaming-output.ts`.\n- Output sink spill threshold defaults to the same `50 KiB`; once exceeded, only the tail remains in memory.\n- SSH master reuse persistence: `ControlPersist=3600` in `packages/coding-agent/src/ssh/connection-manager.ts` and `packages/coding-agent/src/ssh/sshfs-mount.ts`.\n- SSH host info schema version: `HOST_INFO_VERSION = 2` in `packages/coding-agent/src/ssh/connection-manager.ts`; stale cache entries are reprobed.\n- Streaming tail buffer compacts after more than `10` pending chunks (`MAX_PENDING`) before trimming.\n\n## Errors\n- `Unknown SSH host: ... Available hosts: ...` when the model passes a host name not present in discovery.\n- `SSH host not loaded: ...` if the discovered-name set and `hostsByName` map diverge.\n- `ssh binary not found on PATH` when `ssh` is unavailable.\n- `SSH key not found: ...`, `SSH key is not a file: ...`, or `SSH key permissions must be 600 or stricter: ...` from key validation.\n- `Failed to start SSH master for <target>: <stderr>` when control-master startup fails.\n- Non-zero remote command exit becomes `ToolError` with captured output and `Command exited with code N`.\n- Timeout becomes a cancelled result with output notice `[SSH: <timeout message>]`, then `ToolError`.\n- Abort becomes a cancelled result with output notice `[Command aborted: <message>]`, then `ToolError`.\n- `sshfs` mount failures are logged and ignored in `executeSSH()`; they do not fail the tool call.\n- Discovery parse problems do not fail tool loading; they become capability warnings. If all sources are empty/invalid, the tool simply does not load.\n\n## Notes\n- Host discovery is JSON-based only. The tool does not parse OpenSSH config files.\n- Discovery expands environment variables recursively in the parsed JSON and expands `~` in `key`/`keyPath`.\n- Host names are capability keys; the model must pass the config key, not the raw hostname.\n- Commands run without a PTY. `executeSSH()` uses `ptree.spawn(..., { stdin: \"pipe\", stderr: \"full\" })` and does not request an interactive terminal.\n- The tool exposes `cwd` but no `env`, `pty`, upload, download, or explicit file-transfer fields.\n- Lower layers support an `artifactId` for full output and a `remotePath` mount target, but `SshTool.execute()` does not expose those knobs.\n- Both stdout and stderr are merged into one output stream; ordering is whatever arrives through the two streams.\n- `StrictHostKeyChecking=accept-new` and `BatchMode=yes` are always set for connection checks, master startup, and command runs.\n- Connection reuse is keyed by discovered host name, not by raw target tuple alone.\n- `closeAllConnections()` and sshfs unmount cleanup run through postmortem hooks, not per-call teardown.\n",
+	"tools/task.md": "# task\n\n> Launch subagents for parallel, optionally isolated work.\n\n## Source\n- Entry: `packages/coding-agent/src/task/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/task.md`\n- Key collaborators:\n  - `packages/coding-agent/src/task/types.ts` — dynamic schema, progress/result types, output caps.\n  - `packages/coding-agent/src/task/discovery.ts` — discover project/user/plugin/bundled agents.\n  - `packages/coding-agent/src/task/agents.ts` — bundled agent definitions and frontmatter parsing.\n  - `packages/coding-agent/src/task/executor.ts` — create child sessions, run subagents, collect output.\n  - `packages/coding-agent/src/task/parallel.ts` — concurrency-limited scheduling and async semaphore.\n  - `packages/coding-agent/src/task/isolation-backend.ts` — isolation backend resolution and platform fallback.\n  - `packages/coding-agent/src/task/worktree.ts` — worktree / FUSE / ProjFS setup, patch capture, branch merge.\n  - `packages/coding-agent/src/task/output-manager.ts` — session-scoped `agent://` id allocation.\n  - `packages/coding-agent/src/task/simple-mode.ts` — `default` / `schema-free` / `independent` field gating.\n  - `packages/coding-agent/src/internal-urls/agent-protocol.ts` — resolve `agent://<id>` to saved subagent output.\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and recursion-depth gating.\n  - `packages/coding-agent/src/sdk.ts` — child-session router/tool wiring and per-subagent `AgentOutputManager`.\n  - `docs/task-agent-discovery.md` — deeper discovery and precedence notes.\n  - `docs/handoff-generation-pipeline.md` — session artifact/handoff persistence patterns used by the wider session layer.\n\n## Inputs\n\n### Default mode (`task.simple = \"default\"`)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `agent` | `string` | Yes | Exact agent name for every task item. Resolved at execution time through `discoverAgents(...)`. |\n| `tasks` | `Array<{ id: string; description: string; assignment: string }>` | Yes | Batch of small, self-contained task items. `id` max length 48 in schema; duplicate ids are rejected case-insensitively at runtime. |\n| `context` | `string` | No | Shared background prepended to every subagent system prompt. Trimmed before use. |\n| `schema` | `string` | No | JSON-encoded JTD schema. Overrides agent/session output schema when this mode allows task-level schemas. |\n| `isolated` | `boolean` | No | Only present when the tool is created with isolation enabled. Requests isolated execution for the whole batch. |\n\n`tasks[].description` is UI-only. `tasks[].assignment` is the actual per-task instruction.\n\n### Schema-free mode (`task.simple = \"schema-free\"`)\n\nSame as default, except `schema` is rejected by `validateTaskModeParams(...)` in `packages/coding-agent/src/task/index.ts`.\n\n### Independent mode (`task.simple = \"independent\"`)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `agent` | `string` | Yes | Exact agent name. |\n| `tasks` | `Array<{ id: string; description: string; assignment: string }>` | Yes | Same item shape, but each `assignment` must carry all required background because shared `context` is disabled. |\n| `isolated` | `boolean` | No | Same conditional field as above. |\n\nIn this mode both `context` and `schema` are rejected.\n\n## Outputs\nThe tool returns one text block plus `details: TaskToolDetails`.\n\n`details` fields:\n- `projectAgentsDir: string | null` — nearest discovered project `agents/` dir.\n- `results: SingleResult[]` — one entry per task in input order for synchronous execution; empty for async-launch responses.\n- `totalDurationMs: number`\n- `usage?: Usage` — sum of per-subagent assistant-message usage.\n- `outputPaths?: string[]` — written `.md` artifact paths for completed subagent outputs.\n- `progress?: AgentProgress[]` — live or final per-task progress snapshots.\n- `async?: { state: \"running\" | \"completed\" | \"failed\"; jobId: string; type: \"task\" }` — present for background execution updates/results.\n\n`SingleResult` includes:\n- identity: `index`, `id`, `agent`, `agentSource`, `description`, optional `assignment`\n- status: `exitCode`, optional `error`, optional `aborted`, optional `abortReason`\n- output: `output`, `stderr`, `truncated`, `durationMs`, `tokens`\n- artifact metadata: `outputPath?`, `patchPath?`, `branchName?`, `nestedPatches?`, `outputMeta?`\n- extracted tool data: `extractedToolData?` from registered subprocess tool handlers such as `yield` and `report_finding`\n\nArtifacts and side channels:\n- Every subagent with an artifacts dir writes `<id>.md`; `agent://<id>` resolves to that file.\n- If the output file is JSON, `agent://<id>/<path>` and `agent://<id>?q=<query>` perform JSON extraction in `packages/coding-agent/src/internal-urls/agent-protocol.ts`.\n- When the parent session persists artifacts, each subagent also gets `<id>.jsonl` session history.\n- Isolated patch mode writes `<id>.patch` per successful task before merge.\n- Async mode returns immediately after job registration, then emits `onUpdate(...)` progress snapshots and later hands completion to the session async-job pipeline.\n\n## Flow\n1. `TaskTool.create(...)` in `packages/coding-agent/src/task/index.ts` calls `discoverAgents(session.cwd)` once to build the dynamic prompt description from current agents and `task.simple` capabilities.\n2. `execute(...)` validates mode-gated fields with `validateTaskModeParams(...)`.\n3. It decides async vs sync:\n   - sync when `async.enabled` is false\n   - sync when the selected cached agent has `blocking === true`\n   - sync when `tasks.length === 0`\n   - otherwise async job scheduling\n4. Async path:\n   - allocate unique output ids with `AgentOutputManager.allocateBatch(...)`\n   - create one async job per task through `session.asyncJobManager.register(...)`\n   - limit concurrent job bodies with `Semaphore(task.maxConcurrency)` from `packages/coding-agent/src/task/parallel.ts`\n   - each job body calls `#executeSync(...)` with a one-task batch and the preallocated id\n   - `onUpdate(...)` emits aggregate `progress` snapshots and `details.async`\n5. Sync path (`#executeSync(...)`) rediscovers agents from disk via `discoverAgents(...)`, so runtime resolution can differ from the earlier prompt description.\n6. It resolves the requested agent with `getAgent(...)`, rejects unknown or disabled agents, and enforces parent spawn policy plus `PI_BLOCKED_AGENT` self-recursion prevention.\n7. It derives the effective output schema in priority order: task call `schema` (if allowed) → agent frontmatter `output` → inherited parent session schema.\n8. It validates task ids: missing ids and case-insensitive duplicates are immediate errors.\n9. If `isolated` was requested, it requires a git repo (`getRepoRoot(...)` / `captureBaseline(...)`) and resolves the actual backend through `resolveIsolationBackendForTaskExecution(...)`.\n10. It chooses an artifacts dir from the parent session when available, otherwise a temp dir, and writes `context.md` there when `session.getCompactContext?.()` returns content.\n11. It allocates unique ids again if the caller did not preallocate them, then builds `tasksWithUniqueIds`.\n12. For each task, it seeds an `AgentProgress` entry and runs `runTask(...)` through `mapWithConcurrencyLimit(...)` using `task.maxConcurrency`.\n13. Non-isolated `runTask(...)` calls `runSubprocess(...)` directly with parent cwd.\n14. Isolated `runTask(...)`:\n   - creates an isolation workspace (`ensureWorktree(...)`, `ensureFuseOverlay(...)`, or `ensureProjfsOverlay(...)`)\n   - applies the captured baseline for worktrees\n   - runs `runSubprocess(...)` inside that workspace\n   - on success, either commits to a per-task branch (`mergeMode === \"branch\"`) or captures a patch with `captureDeltaPatch(...)`\n   - always cleans up the isolation workspace/backend\n15. `runSubprocess(...)` in `packages/coding-agent/src/task/executor.ts` creates a child agent session with:\n   - isolated settings snapshot via `Settings.isolated(...)`, forcing `async.enabled = false` and `bash.autoBackground.enabled = false`\n   - child `agentId` / `parentTaskPrefix` equal to the allocated task id\n   - child internal URL router and `AgentOutputManager` from `packages/coding-agent/src/sdk.ts`\n   - the shared `context`, optional `context.md` reference, optional isolation worktree path, output schema, and IRC peer roster in the system prompt template\n16. Child tool availability is derived from the agent definition plus runtime guards:\n   - explicit `agent.tools` if provided\n   - auto-add `task` when the agent has `spawns` and recursion depth allows it\n   - remove `task` at or past `task.maxRecursionDepth`\n   - expand `exec` to `eval` and `bash`\n   - strip parent-owned `todo_write` after session creation\n17. `runSubprocess(...)` subscribes to child agent events, coalesces progress updates every 150 ms, forwards lifecycle/progress events on the parent event bus, and extracts tool data through `subprocessToolRegistry`.\n18. The child must finish through the hidden `yield` tool. If it does not, `runSubprocess(...)` sends up to 3 reminder prompts; the last reminder forces `toolChoice = yield` when supported.\n19. Finalization uses `finalizeSubprocessOutput(...)` to reconcile raw assistant text, `yield` payloads, structured schemas, `report_finding` data, and abort states. Output is truncated with `MAX_OUTPUT_BYTES` / `MAX_OUTPUT_LINES` before returning to the parent, but the full raw output is still written to `<id>.md`.\n20. After all sync tasks finish, `#executeSync(...)` aggregates usage, collects artifact paths, and if isolation was used merges results back:\n   - branch mode: cherry-pick per-task branches with `mergeTaskBranches(...)`, then delete merged branches with `cleanupTaskBranches(...)`\n   - patch mode: combine non-empty patch artifacts, dry-check with `git.patch.canApplyText(...)`, then apply or leave manual artifacts\n   - nested repo patches are applied separately with `applyNestedPatches(...)`\n21. The final text summary is rendered from `packages/coding-agent/src/prompts/tools/task-summary.md` and includes `agent://<id>` handles for outputs that exist.\n\n## Modes / Variants\n- Execution mode\n  - Sync inline execution — default path.\n  - Async background execution — one async job per task item when `async.enabled` is on and the chosen agent is not marked `blocking`.\n- Simple mode\n  - `default` — accepts shared `context` and per-call `schema`.\n  - `schema-free` — accepts `context`, rejects `schema`.\n  - `independent` — rejects `context` and `schema`; each assignment stands alone.\n- Isolation backend\n  - `none` — no isolation.\n  - `worktree` — detached git worktree plus baseline replay.\n  - `fuse-overlay` — Unix FUSE overlay mount.\n  - `fuse-projfs` — Windows ProjFS overlay.\n- Isolation merge strategy\n  - Patch mode — capture/apply root patches, keep patch artifacts when application fails.\n  - Branch mode — commit each task onto `omp/task/<id>` branch, cherry-pick into parent, preserve failed branches for manual resolution.\n- Agent source\n  - Project custom agents — nearest project config/plugin agent directories, first by source-family precedence.\n  - User custom agents — user config/plugin agent directories after project dirs of the same source family.\n  - Bundled agents — appended last from `packages/coding-agent/src/task/agents.ts`.\n- Bundled agent types\n  - `explore` — read-only scout with structured handoff output.\n  - `plan` — architecture/planning agent; may spawn `explore`.\n  - `designer` — UI/UX specialist.\n  - `reviewer` — review agent with `report_finding` extraction.\n  - `task` — general-purpose worker with full capabilities.\n  - `quick_task` — low-reasoning mechanical worker using the same task prompt body.\n  - `librarian` — source-grounded external API/library researcher.\n\n## Side Effects\n- Filesystem\n  - Writes `context.md`, `<id>.jsonl`, and `<id>.md` under the session artifacts dir or a temp task dir.\n  - In isolated patch mode writes `<id>.patch` artifacts.\n  - Creates/removes worktrees or overlay mount directories.\n  - In branch mode creates temporary worktrees and task branches.\n- Network\n  - Child sessions may use whichever networked tools/models their active tool set permits.\n  - MCP proxy tools can call existing parent MCP connections with a 60_000 ms timeout.\n- Subprocesses / native bindings\n  - `fuse-overlayfs` and `fusermount`/`fusermount3` for FUSE isolation.\n  - ProjFS native bindings via `@oh-my-pi/pi-natives` on Windows.\n  - Git operations for baseline capture, patch apply, worktrees, branches, stash, cherry-pick, commits.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Creates child `AgentSession` instances with isolated settings snapshots.\n  - Registers async jobs in `session.asyncJobManager` for background task mode.\n  - Emits `task:subagent:event`, `task:subagent:progress`, and `task:subagent:lifecycle` on the parent event bus.\n  - Allocates session-scoped output ids through `AgentOutputManager` so `agent://` remains unique across invocations and resumes.\n  - Shares the parent `local://` root with subagents by passing `localProtocolOptions` through `createAgentSession(...)`.\n- User-visible prompts / interactive UI\n  - Async mode streams aggregate progress updates.\n  - Missing-`yield` recovery sends up to three internal reminder prompts to the child session.\n  - Final summaries include `<system-notification>` blocks for isolation fallbacks or merge failures.\n- Background work / cancellation\n  - Parent abort stops scheduling new work, aborts active child sessions, and marks unscheduled tasks as skipped.\n  - Async jobs keep their own cancellation via `AsyncJobManager`.\n\n## Limits & Caps\n- Per-subagent output truncation: `MAX_OUTPUT_BYTES = 500_000` and `MAX_OUTPUT_LINES = 5000` in `packages/coding-agent/src/task/types.ts`. Full raw output is still written to `<id>.md` before truncation is returned to the caller.\n- Progress coalescing in child execution: `PROGRESS_COALESCE_MS = 150` in `packages/coding-agent/src/task/executor.ts`.\n- Recent output tail for progress: `RECENT_OUTPUT_TAIL_BYTES = 8 * 1024` and `recentOutput` keeps the last 8 non-empty lines in `packages/coding-agent/src/task/executor.ts`.\n- Missing-`yield` reminder retries: `MAX_YIELD_RETRIES = 3` in `packages/coding-agent/src/task/executor.ts`.\n- MCP proxy timeout: `MCP_CALL_TIMEOUT_MS = 60_000` in `packages/coding-agent/src/task/executor.ts`.\n- Task id schema cap: `tasks[].id` `maxLength: 48` in `packages/coding-agent/src/task/types.ts`.\n- Prompt text says ids should be `≤32` chars, but the runtime schema allows 48; this mismatch is real.\n- Async/full sync parallelism both use `task.maxConcurrency` from settings:\n  - sync path: `mapWithConcurrencyLimit(...)`\n  - async path: `Semaphore(...)` around job bodies\n- Recursion depth gate: `task.maxRecursionDepth` from settings; `packages/coding-agent/src/tools/index.ts` hides the `task` tool at or beyond the limit, and `runSubprocess(...)` also strips child `task` access at max depth.\n- Final inline summary preview per task uses `fullOutputThreshold = 5000` chars in `packages/coding-agent/src/task/index.ts`; longer outputs are summarized while `agent://<id>` points to the full artifact.\n\n## Errors\n- Most validation failures are returned as normal tool text with empty `results`, not thrown:\n  - invalid simple-mode fields\n  - unknown/disabled agent\n  - missing tasks\n  - missing/duplicate task ids\n  - spawn-policy denial\n  - requesting `isolated` while isolation mode is `none`\n- Isolated execution without a git repo returns `Isolated task execution requires a git repository. ...`.\n- Backend resolution can return a hard error (`ProjFS isolation initialization failed...`) or a non-fatal warning with fallback to `worktree`.\n- `mapWithConcurrencyLimit(...)` fails fast on non-abort worker exceptions; already completed results are preserved only in the thrown path’s local state, not surfaced unless the caller catches and converts them.\n- Child-session failures surface as `SingleResult.exitCode = 1` with `stderr`/`error` populated.\n- If the child omits `yield`, `finalizeSubprocessOutput(...)` injects warnings such as `SYSTEM WARNING: Subagent exited without calling yield tool after 3 reminders.`\n- Async scheduling failures are accumulated per task; if no jobs start, the tool returns `Failed to start background task jobs: ...`.\n- `agent://<id>` resolution errors are model-visible when another tool reads them: no session, no artifacts dir, missing id, conflicting extraction syntax, or invalid JSON for extraction.\n\n## Notes\n- Agent discovery precedence is first-wins by exact name: project dirs before user dirs within a source family, plugin agent dirs after config dirs, bundled agents last. See `packages/coding-agent/src/task/discovery.ts` and `docs/task-agent-discovery.md`.\n- `TaskTool.create(...)` caches discovered agents only for description rendering and the async blocking-agent decision. `#executeSync(...)` rediscovers agents each call.\n- Custom agent frontmatter can override bundled agents by name. Bundled definitions are embedded at build time in `packages/coding-agent/src/task/agents.ts`.\n- Child sessions do not inherit conversation history automatically. The only built-in carry-over is shared `context`, optional `context.md`, workspace tree/skills/context files, and shared `local://` root.\n- `Settings.isolated(...)` gives each child a session-isolated settings snapshot; tool enablement is recomputed inside the child session rather than sharing mutable parent tool state.\n- When the parent passes `mcpManager`, child sessions disable standalone MCP discovery and instead get proxy tools that reuse the parent connections.\n- Plan mode mutates an `effectiveAgent` with a read-only tool subset and plan-mode prompt text, but `runSubprocess(...)` is still invoked with `agent` rather than `effectiveAgent`. Model/thinking/schema overrides use the effective agent; prompt/tool/spawn restrictions do not fully flow through this call path.\n- Branch-mode merge temporarily stashes the parent repo before cherry-picking task branches. A stash-pop conflict is treated as merge failure and leaves recovery state behind.\n- Patch-mode only applies combined root patches if every successful task produced a patch and `git.patch.canApplyText(...)` succeeds.\n- Nested git repos are handled separately from the root repo. They are copied into isolated worktrees, diffed independently, and merged later with `applyNestedPatches(...)` because parent git cannot track their file-level changes.\n- `agent://` ids are numeric-prefixed (`0-Task`, `1-Task`, nested like `0-Parent.0-Child`) by `AgentOutputManager`; this is what prevents artifact collisions across repeated or nested task invocations.\n",
+	"tools/todo_write.md": "# todo_write\n\n> Applies ordered mutations to the session todo list and returns a text summary plus the full phase/task state.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/todo-write.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/todo-write.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/index.ts` — registers tool, exposes session hooks, gates availability.\n  - `packages/coding-agent/src/modes/controllers/event-controller.ts` — updates the visible todo UI on tool completion.\n  - `packages/coding-agent/src/session/agent-session.ts` — stores cached phases, auto-clears done/dropped tasks, emits failure reminders.\n  - `packages/coding-agent/src/modes/controllers/todo-command-controller.ts` — `/todo` command path, custom-entry persistence, transcript reminder injection.\n  - `packages/coding-agent/src/tools/render-utils.ts` — collapsed-preview cap for renderer trees.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `ops` | `TodoOpEntry[]` | Yes | Ordered operations to apply. `minItems: 1`.\n\n### `TodoOpEntry`\n\n| Op | Required fields | Optional fields | Effect |\n| --- | --- | --- | --- |\n| `init` | `list` | None of the other fields are used | Replaces the entire list with `list`; every new task starts `pending` before normalization. |\n| `start` | `task` | None | Marks one task `in_progress`; any other `in_progress` task is demoted to `pending`. |\n| `done` | `task` or `phase` or neither | None | Marks the target task, phase, or all tasks `completed`. |\n| `drop` | `task` or `phase` or neither | None | Marks the target task, phase, or all tasks `abandoned`. |\n| `rm` | `task` or `phase` or neither | None | Removes the target task, clears the phase's task list, or clears all task lists. |\n| `append` | `phase`, `items` | None | Appends new `pending` tasks to a phase; creates the phase if missing. |\n| `note` | `task`, `text` | None | Appends one trimmed note string to the task's `notes` array. |\n\n### Fields used inside ops\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `\"init\" | \"start\" | \"done\" | \"rm\" | \"drop\" | \"append\" | \"note\"` | Yes | Operation discriminator. |\n| `list` | `{ phase: string; items: string[] }[]` | For `init` | Full replacement payload. Each `items` array has `minItems: 1`. |\n| `task` | `string` | For `start`; for task-targeted `done`/`drop`/`rm`/`note` | Exact task content match. |\n| `phase` | `string` | For `append`; for phase-targeted `done`/`drop`/`rm` | Exact phase name match, except `append` lazily creates a missing phase. |\n| `items` | `string[]` | For `append` | Tasks to append. `minItems: 1`. |\n| `text` | `string` | For `note` | Note text; trailing whitespace is stripped before storing. Empty-after-trim is rejected. |\n\n## Outputs\nThe tool returns a single-shot `AgentToolResult`:\n\n- `content`: one text part containing the summary from `formatSummary(...)`.\n  - Empty final state with no errors: `Todo list cleared.`\n  - Non-empty final state: remaining-item list, current phase progress, then a per-phase tree.\n  - If the active `in_progress` task has notes, the summary includes the note bodies inline.\n  - If any op produced validation/runtime errors, the summary starts with `Errors: ...` but still returns the mutated state.\n- `details`:\n  - `phases: TodoPhase[]`\n  - `storage: \"session\" | \"memory\"`\n\n`TodoPhase` / `TodoItem` state model:\n\n- `TodoPhase`: `{ name: string, tasks: TodoItem[] }`\n- `TodoItem`: `{ content: string, status: \"pending\" | \"in_progress\" | \"completed\" | \"abandoned\", notes?: string[] }`\n\nThe TUI renderer (`todoWriteToolRenderer`) merges call and result into one transcript block, renders phases as a tree, shows note counts as superscripts, and renders the note bodies only for the current `in_progress` task. Collapsed transcript previews cap tree items at `PREVIEW_LIMITS.COLLAPSED_ITEMS` (`8`).\n\n## Flow\n1. `TodoWriteTool.execute(...)` clones the current cached phases from `session.getTodoPhases?.() ?? []` (`packages/coding-agent/src/tools/todo-write.ts`).\n2. `applyParams(...)` walks `params.ops` in order and applies each entry with `applyEntry(...)`.\n3. Each op mutates the working phase array:\n   - `initPhases(...)` rebuilds the list from scratch.\n   - `start` resolves a task by exact `content`, demotes every other `in_progress` task to `pending`, then marks the target `in_progress`.\n   - `done` / `drop` use `getTaskTargets(...)` to target one task, one phase, or every task.\n   - `rm` removes one task, clears one phase's `tasks`, or clears all phases' task arrays.\n   - `appendItems(...)` resolves or creates the target phase and pushes new `pending` tasks unless the same task content already exists anywhere.\n   - `note` trims trailing whitespace, rejects empty text, and appends the note to `task.notes`.\n4. Missing task/phase references are recorded in an `errors` array by `resolveTaskOrError(...)` / `resolvePhaseOrError(...)`; execution continues through the rest of the batch.\n5. After the full batch, `normalizeInProgressTask(...)` enforces the single-active-task invariant:\n   - if multiple tasks are `in_progress`, only the first stays active and the rest become `pending`;\n   - if none are `in_progress`, the first `pending` task in phase/task order is auto-promoted to `in_progress`.\n6. `execute(...)` stores the normalized phases with `session.setTodoPhases?.(...)` and reports `storage` as `\"session\"` when `session.getSessionFile()` exists, else `\"memory\"`.\n7. The agent runtime also watches `todo_write` tool results in `packages/coding-agent/src/session/agent-session.ts`; successful results refresh cached todos, failed results inject a hidden next-turn reminder telling the model that todo progress is not visible until it retries.\n8. The event controller updates the visible todo UI from `result.details.phases` on success, or shows a warning on error (`packages/coding-agent/src/modes/controllers/event-controller.ts`).\n\n## Modes / Variants\n### State transitions\n\n| Current status | `start` | `done` | `drop` | `rm` | `append` | `note` |\n| --- | --- | --- | --- | --- | --- | --- |\n| `pending` | `in_progress` on target | `completed` | `abandoned` | Removed | New tasks enter as `pending` | No status change |\n| `in_progress` | Target stays `in_progress`; non-target active tasks become `pending` | `completed` | `abandoned` | Removed | No status change | No status change |\n| `completed` | Can be set back to `in_progress` if targeted | Stays `completed` | Becomes `abandoned` if targeted | Removed | No status change | No status change |\n| `abandoned` | Can be set back to `in_progress` if targeted | Becomes `completed` if targeted | Stays `abandoned` | Removed | No status change | No status change |\n\nNormalization then re-applies the single-active-task rule after the full op batch.\n\n### Op targeting rules\n- `done`, `drop`, `rm`:\n  - `task` set: affect one exact-content task.\n  - else `phase` set: affect every task in that exact-name phase.\n  - else: affect every task in every phase.\n- `append` is the only op that creates a missing phase.\n- `note` only targets a single task.\n- `init` discards previous phases entirely.\n\n### Markdown round-trip helpers\nThe same file also exposes non-tool helpers used by `/todo`:\n- `phasesToMarkdown(...)` serializes phases as headings plus checklist items (`[ ]`, `[/]`, `[x]`, `[-]`) with blockquote note bodies.\n- `markdownToPhases(...)` parses that format, defaults orphan tasks into a `Todos` phase, accepts `>` as an `in_progress` marker and `~` as `abandoned`, and runs the same normalization step.\n\n## Side Effects\n- Filesystem\n  - None in the tool itself.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Mutates the session todo cache through `setTodoPhases`.\n  - `storage` reports whether the session has a backing session file, but the tool does not append a custom session entry itself.\n  - Successful tool-result messages carry `details.phases`; `getLatestTodoPhasesFromEntries(...)` can reconstruct state later from those transcript entries.\n  - Failed `todo_write` results cause `agent-session` to enqueue a hidden next-turn reminder (`customType: \"todo-write-error-reminder\"`).\n- User-visible prompts / interactive UI\n  - Transcript block is rendered by `todoWriteToolRenderer` and merged with the call line.\n  - `event-controller` updates the visible todo panel from successful results.\n  - On error, `event-controller` shows `Todo update failed...`; the visible panel may stay stale until a later successful call.\n- Background work / cancellation\n  - `AgentSession.setTodoPhases(...)` schedules auto-clear timers for `completed` / `abandoned` tasks via `tasks.todoClearDelay`.\n\n## Limits & Caps\n- `ops` array: `minItems: 1` (`todoWriteSchema`).\n- `init.list[*].items`: `minItems: 1`.\n- `append.items`: `minItems: 1`.\n- Renderer collapsed preview: `PREVIEW_LIMITS.COLLAPSED_ITEMS = 8` (`packages/coding-agent/src/tools/render-utils.ts`).\n- Auto-clear delay: `tasks.todoClearDelay` default `60` seconds; `< 0` disables auto-clear, `0` clears on the next microtask (`packages/coding-agent/src/session/agent-session.ts`).\n- Tool execution mode: `concurrency = \"exclusive\"`, `strict = true`, `loadMode = \"discoverable\"`.\n\n## Errors\n- The tool does not throw for ordinary bad op payloads; it accumulates human-readable strings in `errors` and still returns success with the mutated state.\n- Error strings come from the helpers in `packages/coding-agent/src/tools/todo-write.ts`, including:\n  - `Missing list for init operation`\n  - `Missing task content`\n  - `Task \"...\" not found` with an extra empty-list hint when applicable\n  - `Missing phase name`\n  - `Phase \"...\" not found`\n  - `Missing phase name for append operation`\n  - `Missing items for append operation`\n  - `Task \"...\" already exists`\n  - `Missing text for note operation`\n- Because ops are processed in order, earlier errors do not roll back later ops.\n- Runtime-level tool failure is handled outside the tool body: `agent-session` injects a hidden reminder and the event controller warns the user that visible progress may be stale.\n- Idempotency is op-specific:\n  - `init` is a full replacement; replaying the same payload yields the same state.\n  - `start`, `done`, and `drop` are effectively idempotent on an existing target state, but `start` also demotes any other active task.\n  - `rm` is not idempotent for targeted removals: the second call errors because the task or phase is gone.\n  - `append` is not idempotent: duplicate task content is rejected with `Task \"...\" already exists`.\n  - `note` is append-only and never idempotent; replaying it adds another note entry.\n\n## Notes\n- Task lookup is exact string equality inside the tool. The model-facing prompt says task content and phase names are identifiers and should stay unique; `append` enforces task uniqueness globally, but `init` does not validate duplicate task or phase names.\n- `findTaskByContent(...)` returns the first matching task across phases. Duplicate task contents make later targeted ops ambiguous.\n- `normalizeInProgressTask(...)` runs after the whole batch, not after each op. A single call can intentionally build an intermediate invalid state and rely on final normalization.\n- `storage: \"session\"` means the session has a session-file backing; it does not mean this tool wrote a durable custom entry.\n- Reload persistence differs by path:\n  - plain `todo_write` calls survive in transcript tool-result details;\n  - `/todo` command edits additionally append `customType: \"user_todo_edit\"` entries and inject a visible-to-model `<system-reminder>` developer message describing the manual edit.\n- On session resume, `AgentSession.#syncTodoPhasesFromBranch()` strips `completed` and `abandoned` tasks before restoring the cached list. The `/todo` command works around that by reading the latest transcript/custom-entry state so historical done/dropped tasks still appear to the user.\n- Tool availability is gated by `todo.enabled`, and the registry excludes it when `includeYield` is enabled (`packages/coding-agent/src/tools/index.ts`).\n- Subagents do not inherit `todo_write`; `packages/coding-agent/src/task/executor.ts` filters it out as a parent-owned tool.\n",
+	"tools/web_search.md": "# web_search\n\n> Run one web query through the first available search provider and return LLM-formatted answer, source URLs, and optional citations.\n\n## Source\n- Entry: `packages/coding-agent/src/web/search/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/web-search.md`\n- Key collaborators:\n  - `packages/coding-agent/src/web/search/provider.ts` — lazy provider registry; availability chain.\n  - `packages/coding-agent/src/web/search/types.ts` — unified `SearchResponse` / `SearchProviderError` types.\n  - `packages/coding-agent/src/web/search/render.ts` — TUI renderer details type.\n  - `packages/coding-agent/src/web/search/providers/base.ts` — provider interface and shared params contract.\n  - `packages/coding-agent/src/web/search/providers/utils.ts` — credential lookup; source normalization.\n  - `packages/coding-agent/src/web/search/providers/anthropic.ts` — Claude web-search provider.\n  - `packages/coding-agent/src/web/search/providers/brave.ts` — Brave Search API adapter.\n  - `packages/coding-agent/src/web/search/providers/codex.ts` — OpenAI Codex SSE adapter.\n  - `packages/coding-agent/src/web/search/providers/exa.ts` — Exa API or MCP adapter.\n  - `packages/coding-agent/src/web/search/providers/gemini.ts` — Gemini grounding SSE adapter.\n  - `packages/coding-agent/src/web/search/providers/jina.ts` — Jina Reader search adapter.\n  - `packages/coding-agent/src/web/search/providers/kagi.ts` — Kagi provider wrapper.\n  - `packages/coding-agent/src/web/search/providers/kimi.ts` — Kimi search adapter.\n  - `packages/coding-agent/src/web/search/providers/parallel.ts` — Parallel provider wrapper.\n  - `packages/coding-agent/src/web/search/providers/perplexity.ts` — Perplexity API / OAuth adapter.\n  - `packages/coding-agent/src/web/search/providers/searxng.ts` — self-hosted SearXNG adapter.\n  - `packages/coding-agent/src/web/search/providers/synthetic.ts` — Synthetic search adapter.\n  - `packages/coding-agent/src/web/search/providers/tavily.ts` — Tavily search adapter.\n  - `packages/coding-agent/src/web/search/providers/zai.ts` — Z.AI remote MCP adapter.\n  - `packages/coding-agent/src/web/parallel.ts` — Parallel search/extract HTTP client.\n  - `packages/coding-agent/src/web/kagi.ts` — Kagi HTTP client.\n  - `packages/coding-agent/src/tools/index.ts` — built-in tool registration and enable flag.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `query` | `string` | Yes | Search query. `executeSearch()` rewrites any `2020`-`2029` substring to the current year before dispatch. |\n| `recency` | `\"day\" \\| \"week\" \\| \"month\" \\| \"year\"` | No | Time filter. Only providers that implement it use it. Prompt text says Brave and Perplexity; code also maps it for Tavily and SearXNG. |\n| `limit` | `number` | No | Max results to return. Usually becomes the provider request's result-count parameter when `num_search_results` is absent. |\n| `max_tokens` | `number` | No | Passed through as `maxOutputTokens` / `max_tokens` only by Anthropic, Gemini, and Perplexity API-key mode. Ignored by the other providers. |\n| `temperature` | `number` | No | Passed through only by Anthropic, Gemini, and Perplexity API-key mode. Ignored by the other providers. |\n| `num_search_results` | `number` | No | Requested upstream search breadth. For most providers this is the same count used for returned sources. Perplexity is the only adapter that keeps it distinct from `limit`. |\n\n## Outputs\nThe tool returns a single text content block plus structured `details`.\n\n- `content`: `[{ type: \"text\", text: string }]`\n- `details`: `SearchRenderDetails` from `packages/coding-agent/src/web/search/render.ts`\n  - `response: SearchResponse`\n  - `error?: string`\n\n`text` is produced by `formatForLLM()` in `packages/coding-agent/src/web/search/index.ts`:\n\n- If `response.answer` exists, it is emitted first.\n- If sources exist, a `## Sources` section follows with a source count, then one entry per source:\n  - `[n] <title> (<formatted age or published date>)`\n  - `    <url>`\n  - optional snippet line truncated to 240 chars.\n- If citations exist, a `## Citations` section follows with URL/title plus optional cited text truncated to 240 chars.\n- If related questions exist, a `## Related` bullet list follows.\n- If search queries exist, a `Search queries: <n>` section follows, capped to the first 3 queries and 120 chars each.\n\nFailure output is not thrown at the tool boundary when at least one provider was attempted. Instead the tool returns:\n\n- `content[0].text = \"Error: ...\"`\n- `details.response.provider = <last attempted provider> | \"none\"`\n- `details.error = ...`\n\nStreaming: none. `WebSearchTool.execute()` does not forward its `_signal` argument into `executeSearch()`, so provider cancellation is only available to internal callers that place `signal` inside `SearchQueryParams`.\n\n## Flow\n1. `WebSearchTool.execute()` in `packages/coding-agent/src/web/search/index.ts` delegates directly to `executeSearch()`.\n2. `executeSearch()` chooses a provider list:\n   - if `params.provider` is set and not `\"auto\"`, it loads that provider with `getSearchProvider()`; if `isAvailable()` returns true, the list is `[that provider]`, otherwise it falls back to `resolveProviderChain(\"auto\")`.\n   - otherwise it calls `resolveProviderChain()` with the module-global preferred provider from `packages/coding-agent/src/web/search/provider.ts`.\n3. `resolveProviderChain()` lazily loads each provider module on demand, checks `isAvailable()`, and returns only available providers. If a preferred provider is set, it is tried first, then the static `SEARCH_PROVIDER_ORDER` excluding that provider.\n4. If no providers are available, `executeSearch()` returns `Error: No web search provider configured.` with `details.response.provider = \"none\"`.\n5. For each provider in order, `executeSearch()` calls `provider.search()` with:\n   - `query` after year-rewrite,\n   - `limit`, `recency`, `temperature`, `maxOutputTokens`, `numSearchResults`,\n   - `systemPrompt` from `packages/coding-agent/src/prompts/tools/web-search.md`.\n6. On the first successful `SearchResponse`, `formatForLLM()` renders answer/sources/citations/related/search-queries into one text block and returns it with `details.response`.\n7. If a provider throws, `executeSearch()` records the error and tries the next provider. There is no provider-level parallel fan-out; fallback is sequential.\n8. After all candidates fail, `formatProviderError()` normalizes the last error:\n   - Anthropic `404` becomes `Anthropic web search returned 404 (model or endpoint not found).`\n   - `401`/`403` become `<Provider> authorization failed ...` except Z.AI, which preserves its raw message.\n   - other `SearchProviderError`s surface `error.message`.\n9. If more than one provider was attempted, the final message is `All web search providers failed (<labels>). Last error: <message>`; otherwise it is just the normalized last error.\n\n## Modes / Variants\n- **Provider selection**\n  - **Forced provider**: internal callers may pass `provider`; unavailable forced providers fall back to the auto chain instead of hard-failing (`packages/coding-agent/src/web/search/index.ts`). This field is not in the model-facing schema.\n  - **Preferred provider**: `setPreferredSearchProvider()` sets a module-global default used by `resolveProviderChain()`. `packages/coding-agent/src/sdk.ts` and `packages/coding-agent/src/modes/controllers/selector-controller.ts` wire this from settings.\n  - **Auto chain order**: `tavily`, `perplexity`, `brave`, `jina`, `kimi`, `anthropic`, `gemini`, `codex`, `zai`, `exa`, `parallel`, `kagi`, `synthetic`, `searxng` (`SEARCH_PROVIDER_ORDER` in `packages/coding-agent/src/web/search/provider.ts`).\n- **Provider adapters**\n  - **Tavily** — `packages/coding-agent/src/web/search/providers/tavily.ts`\n    - Availability: API key from env or `agent.db` via `findCredential()`.\n    - Querying: POST `https://api.tavily.com/search`.\n    - `recency` maps to Tavily `time_range`; code explicitly keeps `topic` at default general scope instead of narrowing to news.\n    - `limit` / `num_search_results`: adapter uses `params.numSearchResults ?? params.limit`, clamped to `5..20` with default `5`.\n    - Output: `answer`, `sources`, `requestId`, `authMode: \"api_key\"`.\n  - **Perplexity** — `packages/coding-agent/src/web/search/providers/perplexity.ts`\n    - Availability: auth precedence is `PERPLEXITY_COOKIES` -> OAuth token in `agent.db` -> `PERPLEXITY_API_KEY` / `PPLX_API_KEY`.\n    - OAuth/cookie mode: POSTs to `https://www.perplexity.ai/rest/sse/perplexity_ask`, consumes SSE, merges partial events, extracts answer and source URLs, sets `authMode: \"oauth\"`.\n    - API-key mode: POSTs to `https://api.perplexity.ai/chat/completions` with `model: \"sonar-pro\"`, `search_mode: \"web\"`, `num_search_results`, optional `search_recency_filter`, `max_tokens`, `temperature`.\n    - `num_search_results` controls upstream API breadth only in API-key mode. `limit` is preserved separately as `num_results` and slices returned `sources` after parsing in both auth modes.\n    - Output may include `answer`, `sources`, `citations`, `usage`, `model`, `requestId`, `authMode`.\n  - **Brave** — `packages/coding-agent/src/web/search/providers/brave.ts`\n    - Availability: `BRAVE_API_KEY` only.\n    - Querying: GET `https://api.search.brave.com/res/v1/web/search` with `count`, `extra_snippets=true`, and `freshness=pd|pw|pm|py` for `recency`.\n    - `limit` / `num_search_results`: `params.numSearchResults ?? params.limit`, clamped to `1..20`, default `10`.\n    - Output: `sources`, `requestId`.\n  - **Jina** — `packages/coding-agent/src/web/search/providers/jina.ts`\n    - Availability: `JINA_API_KEY` only.\n    - Querying: GET-like fetch to `https://s.jina.ai/<encoded query>` with bearer auth.\n    - Ignores `recency`, `max_tokens`, and `temperature`.\n    - `limit` / `num_search_results`: adapter slices sources to `params.numSearchResults ?? params.limit` when provided; otherwise returns all payload items.\n    - Output: `sources` only.\n  - **Kimi** — `packages/coding-agent/src/web/search/providers/kimi.ts`\n    - Availability: `MOONSHOT_SEARCH_API_KEY`, `KIMI_SEARCH_API_KEY`, `MOONSHOT_API_KEY`, or `agent.db` credentials for `moonshot` / `kimi-code`.\n    - Querying: POST to `MOONSHOT_SEARCH_BASE_URL` / `KIMI_SEARCH_BASE_URL` / default `https://api.kimi.com/coding/v1/search` with `text_query`, `limit`, `enable_page_crawling`, `timeout_seconds: 30`.\n    - `limit` / `num_search_results`: `params.numSearchResults ?? params.limit`, clamped to `1..20`, default `10`.\n    - Output: `sources`, `requestId`.\n  - **Anthropic** — `packages/coding-agent/src/web/search/providers/anthropic.ts`\n    - Availability: `findAnthropicAuth()` from `@oh-my-pi/pi-ai`.\n    - Querying: Claude Messages API with web-search tool enabled.\n    - `max_tokens` and `temperature` pass through.\n    - `limit` and `num_search_results` are collapsed together before dispatch: `num_results = params.numSearchResults ?? params.limit`.\n    - Output may include `answer`, `sources`, `citations`, `searchQueries`, `usage.searchRequests`, `model`, `requestId`.\n  - **Gemini** — `packages/coding-agent/src/web/search/providers/gemini.ts`\n    - Availability: OAuth credentials in `agent.db` for `google-gemini-cli` or `google-antigravity`.\n    - Querying: SSE `streamGenerateContent` call with Google Search grounding enabled. Antigravity auth tries two fallback endpoints and retries `401/403/400 invalid auth` once after token refresh; `429/5xx` retry with exponential backoff and server-provided retry delay, capped by a `5 * 60 * 1000` ms rate-limit budget.\n    - `max_tokens` and `temperature` pass through as `generationConfig.maxOutputTokens` / `generationConfig.temperature`.\n    - `limit` and `num_search_results` are collapsed together before dispatch.\n    - Output may include `answer`, `sources`, `citations`, `searchQueries`, `usage`, `model`.\n  - **Codex** — `packages/coding-agent/src/web/search/providers/codex.ts`\n    - Availability: non-expired OAuth credential for `openai-codex` in `agent.db`.\n    - Querying: SSE POST to `https://chatgpt.com/backend-api/codex/responses` with `tool_choice: { type: \"web_search\" }` and `search_context_size: \"high\"` by default.\n    - Ignores `recency`, `max_tokens`, and `temperature` in this tool path.\n    - `limit` and `num_search_results` are collapsed together before dispatch.\n    - Output may include `answer`, `sources`, `usage`, `model`, `requestId`. If the streamed response has no `url_citation` annotations, the adapter falls back to scraping markdown links and bare URLs from the answer text.\n  - **Z.AI** — `packages/coding-agent/src/web/search/providers/zai.ts`\n    - Availability: env or `agent.db` credential for `zai`.\n    - Querying: JSON-RPC `tools/call` against `https://api.z.ai/api/mcp/web_search_prime/mcp` for remote MCP tool `web_search_prime`.\n    - Fallback chain inside the provider: tries `{query,count}`, then `{search_query,count}`, then `{search_query, search_engine:\"search-prime\", count}` when earlier attempts fail with argument-shape errors.\n    - `limit` and `num_search_results` are collapsed together before dispatch.\n    - Output may include parsed free-text `answer`, `sources`, `requestId`.\n  - **Exa** — `packages/coding-agent/src/web/search/providers/exa.ts`\n    - Availability: always true unless settings explicitly disable `exa.enabled` or `exa.enableSearch`; the adapter can use public MCP even without `EXA_API_KEY`.\n    - Querying: with `EXA_API_KEY`, POST `https://api.exa.ai/search`; otherwise call MCP tool `web_search_exa`.\n    - `limit` and `num_search_results` are collapsed together before dispatch.\n    - Output: synthesized `answer` from up to 3 result summaries, `sources`, `requestId`.\n  - **Parallel** — `packages/coding-agent/src/web/search/providers/parallel.ts`, `packages/coding-agent/src/web/parallel.ts`\n    - Availability: env or `agent.db` credential for `parallel`.\n    - Querying: POST `https://api.parallel.ai/v1beta/search` with `objective=query`, `search_queries=[query]`, `mode:\"fast\"`, `max_chars_per_result: 10000`, beta header `search-extract-2025-10-10`.\n    - There is no provider fan-out here despite the name; the current adapter always sends a one-element `search_queries` array.\n    - `limit` and `num_search_results` are collapsed together before dispatch, clamped to `1..40`, default `10`.\n    - Output: `sources`, `requestId`.\n  - **Kagi** — `packages/coding-agent/src/web/search/providers/kagi.ts`, `packages/coding-agent/src/web/kagi.ts`\n    - Availability: env or `agent.db` credential for `kagi`.\n    - Querying: GET `https://kagi.com/api/v0/search?q=<query>&limit=<n>` with `Authorization: Bot <key>`.\n    - `limit` and `num_search_results` are collapsed together before dispatch, clamped to `1..40`, default `10`.\n    - Output: `sources`, `relatedQuestions`, `requestId`.\n  - **Synthetic** — `packages/coding-agent/src/web/search/providers/synthetic.ts`\n    - Availability: env or `agent.db` credential for `synthetic`.\n    - Querying: POST `https://api.synthetic.new/v2/search` with `{ query }`.\n    - Ignores `recency`, `max_tokens`, and `temperature`.\n    - `limit` and `num_search_results` are collapsed together before dispatch.\n    - Output: `sources` only.\n  - **SearXNG** — `packages/coding-agent/src/web/search/providers/searxng.ts`\n    - Availability: endpoint from `searxng.endpoint` setting or `SEARXNG_ENDPOINT` env.\n    - Querying: GET `<endpoint>/search?format=json&q=...`; optional settings add `categories` and `language`.\n    - Auth precedence: Basic auth (`searxng.basicUsername` / `searxng.basicPassword` or env equivalents) over bearer token (`searxng.token` / `SEARXNG_TOKEN`). Basic credentials are validated for RFC 7617 restrictions.\n    - `recency` maps to `time_range`; `week` is downgraded to `month` because SearXNG does not support week.\n    - `limit` and `num_search_results` are collapsed together before dispatch, clamped to `1..20`, default `10`.\n    - Output: `sources`, `relatedQuestions` from `suggestions`.\n\n## Side Effects\n- Network\n  - Calls one or more external search providers over HTTPS until one succeeds or all fail.\n  - Provider-specific transports include JSON POST, JSON GET, SSE streaming (Perplexity OAuth/API, Gemini, Codex), and JSON-RPC over HTTP (Z.AI).\n- Subprocesses / native bindings\n  - None.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Uses a module-global provider-instance cache in `packages/coding-agent/src/web/search/provider.ts`.\n  - Uses a module-global preferred-provider setting in the same file.\n  - `packages/coding-agent/src/tools/index.ts` gates tool availability behind `session.settings.get(\"web_search.enabled\")`.\n- Background work / cancellation\n  - Many provider adapters accept `AbortSignal`, but `WebSearchTool.execute()` does not pass its `_signal` into `executeSearch()`. Internal callers can still use cancellation by calling `runSearchQuery()` / `executeSearch()` with `signal` embedded in params.\n\n## Limits & Caps\n- Provider auto-order length: 14 providers (`SEARCH_PROVIDER_ORDER` in `packages/coding-agent/src/web/search/provider.ts`).\n- `formatForLLM()` truncates source snippets and citation text to 240 chars (`packages/coding-agent/src/web/search/index.ts`).\n- `formatForLLM()` emits at most 3 search queries, each truncated to 120 chars (`packages/coding-agent/src/web/search/index.ts`).\n- Brave result count: default `10`, max `20` (`DEFAULT_NUM_RESULTS`, `MAX_NUM_RESULTS` in `packages/coding-agent/src/web/search/providers/brave.ts`).\n- Tavily result count: default `5`, max `20` (`packages/coding-agent/src/web/search/providers/tavily.ts`).\n- Kimi result count: default `10`, max `20`; request timeout field fixed to `30` seconds (`packages/coding-agent/src/web/search/providers/kimi.ts`).\n- Parallel result count: default `10`, max `40`; per-result excerpt cap `10_000` chars (`packages/coding-agent/src/web/search/providers/parallel.ts`, `packages/coding-agent/src/web/parallel.ts`).\n- Kagi result count: default `10`, max `40` (`packages/coding-agent/src/web/search/providers/kagi.ts`).\n- SearXNG result count: default `10`, max `20` (`packages/coding-agent/src/web/search/providers/searxng.ts`).\n- Perplexity API-key mode defaults: `max_tokens = 8192`, `temperature = 0.2`, `num_search_results = 10` (`packages/coding-agent/src/web/search/providers/perplexity.ts`).\n- Anthropic defaults: model `claude-haiku-4-5`, `DEFAULT_MAX_TOKENS = 4096` when the provider omits `max_tokens` (`packages/coding-agent/src/web/search/providers/anthropic.ts`).\n- Gemini retries: up to `3` retries per endpoint, base delay `1000` ms, rate-limit delay budget `5 * 60 * 1000` ms (`packages/coding-agent/src/web/search/providers/gemini.ts`).\n\n## Errors\n- Tool-level no-provider case returns a normal tool result with `Error: No web search provider configured.`; it does not throw.\n- Tool-level all-failed case also returns a normal tool result with `Error: ...`; failures are summarized from the last attempted provider.\n- Provider adapters usually throw `SearchProviderError(provider, message, status)` for HTTP or protocol failures.\n- Availability probes intentionally swallow lookup errors and report `false` in many providers via `isApiKeyAvailable()`.\n- Per-provider notable failures:\n  - Anthropic: missing credentials throw a plain `Error`; a `404` is remapped to a special final message by `formatProviderError()`.\n  - Perplexity: missing auth throws a plain `Error`; OAuth stream `error_code` events become `SearchProviderError(\"perplexity\", ...)`.\n  - Gemini: auth refresh, endpoint fallback, and retry logic are internal; final exhausted failures surface as `SearchProviderError(\"gemini\", ...)`.\n  - Codex and Gemini both fail if the HTTP response has no body after a `200`.\n  - Z.AI treats malformed SSE/JSON-RPC payloads as provider errors and retries only argument-shape failures across request variants.\n  - SearXNG `findAuth()` can throw configuration errors before any HTTP call if Basic auth fields are incomplete or invalid.\n\n## Notes\n- The model-facing schema does not expose `provider`, but internal callers can force one through `SearchQueryParams`.\n- `resolveProviderChain()` lazily imports provider modules and caches singleton instances. Just asking for labels via `getSearchProviderLabel()` does not trigger those imports.\n- Most providers treat `limit` and `num_search_results` as the same number because adapters pass `params.numSearchResults ?? params.limit`. Perplexity is the only implementation that preserves both concepts.\n- The prompt says `recency` is for Brave and Perplexity, but code also implements it for Tavily and SearXNG.\n- The year rewrite in `executeSearch()` is blunt: any `2020`-`2029` substring is replaced with the current year.\n- `packages/coding-agent/src/config/settings-schema.ts` exposes provider preferences for `auto`, `exa`, `brave`, `jina`, `kimi`, `perplexity`, `anthropic`, `zai`, `tavily`, `kagi`, `synthetic`, `parallel`, and `searxng`. Gemini and Codex are in the registry and auto chain but not in that settings enum.\n- Exa availability is optimistic. Unless settings disable it, the provider stays in the chain even without an API key because it can fall back to MCP.\n",
+	"tools/write.md": "# write\n\n> Create or overwrite a file, archive entry, or SQLite row.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/write.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/write.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/archive-reader.ts` — parse `archive.ext:entry` selectors.\n  - `packages/coding-agent/src/tools/sqlite-reader.ts` — detect SQLite paths and perform row insert/update/delete.\n  - `packages/coding-agent/src/lsp/index.ts` — format-on-write and diagnostics writethrough.\n  - `packages/coding-agent/src/tools/auto-generated-guard.ts` — block overwriting generated files.\n  - `packages/coding-agent/src/tools/fs-cache-invalidation.ts` — invalidate shared FS scan caches after writes.\n  - `packages/coding-agent/src/tools/plan-mode-guard.ts` — resolve paths and enforce plan-mode write policy.\n\n## Inputs\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `path` | `string` | Yes | Target path. Plain file path writes a filesystem file. `archive.ext:inner/path` writes an archive entry for `.tar`, `.tar.gz`, `.tgz`, or `.zip`. `db.sqlite:table` inserts a row. `db.sqlite:table:key` updates or deletes a row. |\n| `content` | `string` | Yes | Full replacement file content, archive entry content, or SQLite row payload. SQLite non-delete writes must parse as a JSON5 object. Empty or whitespace-only content deletes a SQLite row when `path` includes a row key. |\n\nWorked examples:\n\n```text\npath: \"src/generated/config.json\"\ncontent: \"{\\n  \\\"enabled\\\": true\\n}\\n\"\n```\n\n```text\npath: \"fixtures/archive.zip:templates/email.txt\"\ncontent: \"hello\\n\"\n```\n\n```text\npath: \"data/app.sqlite:users:42\"\ncontent: \"{name: 'Ada', active: true}\"\n```\n\n## Outputs\nSingle-shot result.\n\n- Success always returns a text block.\n  - Plain file write: `Successfully wrote <bytes> bytes to <relative-path>`.\n  - Archive write: `Successfully wrote <bytes> bytes to <relative-archive-path>:<entry-path>`.\n  - SQLite write: one of `Inserted row into <table>`, `Updated row '<key>' in <table>`, `No row updated ...`, `Deleted row ...`, `No row deleted ...`.\n- If hashline prefixes were copied from `read` output and stripped first, the first text block gets an extra note.\n- Plain file writes may also return `details.diagnostics` plus `details.meta.diagnostics` when LSP diagnostics-on-write is enabled.\n- SQLite writes use `toolResult(...).sourcePath(...)`, so `details.meta.sourcePath` points at the database file.\n- Archive writes return empty `details`.\n\n## Flow\n1. `WriteTool.execute()` in `packages/coding-agent/src/tools/write.ts` strips `LINE+ID|` hashline prefixes from `content` when the session is in hashline display mode.\n2. It calls `#resolveArchiveWritePath()` first. That uses `parseArchivePathCandidates()` from `packages/coding-agent/src/tools/archive-reader.ts`, checks candidate archive files on disk, and falls back to the longest matching archive suffix even when the archive file does not exist yet.\n3. Archive writes call `enforcePlanModeWrite(..., { op: exists ? \"update\" : \"create\" })`, then `#writeArchiveEntry()`.\n   - The parent directory of the archive file is created with `fs.mkdir(..., { recursive: true })`.\n   - `.zip` archives are read with `fflate.unzipSync()`, the target entry is replaced in an in-memory map, and the archive is rewritten with `fflate.zipSync()` + `Bun.write()`.\n   - `.tar`, `.tar.gz`, and `.tgz` archives are read with `Bun.Archive`, existing entries are copied into an object map, the target entry is replaced, and `Bun.Archive.write()` rewrites the archive.\n   - `invalidateFsScanAfterWrite()` runs on the archive file path.\n4. If the path is not treated as an archive, `execute()` calls `#resolveSqliteWritePath()`. That uses `parseSqlitePathCandidates()` and `isSqliteFile()` from `packages/coding-agent/src/tools/sqlite-reader.ts`. Existing non-SQLite files suppress the SQLite path interpretation.\n5. SQLite writes call `enforcePlanModeWrite(..., { op: \"update\" })`, then `#writeSqliteRow()`.\n   - The database must already exist; missing DBs throw `SQLite database '<path>' not found`.\n   - The tool opens `new Database(..., { create: false, strict: true })` and sets `PRAGMA busy_timeout = 3000`.\n   - Whitespace-only `content` with a row key deletes a row.\n   - Non-empty `content` is parsed with `Bun.JSON5.parse()`, must be a JSON object, and is routed to insert/update helpers from `packages/coding-agent/src/tools/sqlite-reader.ts`.\n   - `invalidateFsScanAfterWrite()` runs on the DB path and the connection is closed in `finally`.\n6. Otherwise the tool treats `path` as a plain filesystem file.\n   - `enforcePlanModeWrite(..., { op: \"create\" })` runs before path resolution.\n   - Existing files are checked by `assertEditableFile()` to block overwriting detected generated files.\n   - The session’s writethrough callback writes content. With LSP enabled and `lsp.formatOnWrite` / `lsp.diagnosticsOnWrite` settings on, `createLspWritethrough()` may format content, sync it through LSP servers, save it, and collect diagnostics. Otherwise `writethroughNoop()` writes directly with `Bun.write()` or `file.write()`.\n   - `invalidateFsScanAfterWrite()` runs on the file path.\n7. The tool returns a text result and optional diagnostics metadata.\n\n## Modes / Variants\n### Plain file path\n- Target is any path that does not resolve as an archive selector and does not resolve as an existing-or-new SQLite selector.\n- Existing files are overwritten.\n- `write.ts` does not call `fs.mkdir()` on this path; parent-directory creation is only implemented in the archive branch.\n\nExample:\n\n```text\npath: \"tmp/output.txt\"\ncontent: \"hello\\n\"\n```\n\n### Archive entry write\n- Selector syntax: `archive.ext:inner/path`.\n- Supported archive suffixes come from `parseArchivePathCandidates()`: `.tar`, `.tar.gz`, `.tgz`, `.zip`.\n- The inner path is normalized to `/`, strips empty and `.` segments, rejects `..`, and rejects directory targets ending in `/`.\n- Rewrites the whole archive file after replacing one entry.\n- Creates the parent directory for the archive file if needed.\n\nExample:\n\n```text\npath: \"build/assets.tar.gz:css/app.css\"\ncontent: \"body { color: black; }\\n\"\n```\n\n### SQLite table insert\n- Selector syntax: `db.sqlite:table`.\n- `content` must parse as a JSON5 object.\n- Empty object is allowed and becomes `INSERT INTO <table> DEFAULT VALUES`.\n- Query parameters are rejected for SQLite writes.\n\nExample:\n\n```text\npath: \"data/app.db:users\"\ncontent: \"{name: 'Ada', active: true}\"\n```\n\n### SQLite row update / delete\n- Selector syntax: `db.sqlite:table:key`.\n- Non-empty `content` updates the row.\n- Empty or whitespace-only `content` deletes the row.\n- Row lookup uses the single-column primary key if present; otherwise it falls back to `rowid`. Composite primary keys and `WITHOUT ROWID` tables are rejected for key-based writes.\n\nExample update:\n\n```text\npath: \"data/app.sqlite:users:42\"\ncontent: \"{email: 'ada@example.com'}\"\n```\n\nExample delete:\n\n```text\npath: \"data/app.sqlite:users:42\"\ncontent: \"\"\n```\n\n## Side Effects\n- Filesystem\n  - Creates or overwrites plain files.\n  - Rewrites entire archive files when writing an archive entry.\n  - Creates parent directories for archive files only.\n  - Mutates existing SQLite databases; never creates a new SQLite DB.\n- Subprocesses / native bindings\n  - Uses Bun SQLite bindings via `bun:sqlite`.\n  - Uses Bun archive APIs and lazily imports `fflate` for ZIP reads/writes.\n  - May talk to configured LSP servers through `packages/coding-agent/src/lsp/index.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Invalidates shared filesystem scan cache entries through `invalidateFsScanAfterWrite()`.\n  - Enforces plan-mode write restrictions before mutating the target.\n- Background work / cancellation\n  - Marks the tool `nonAbortable = true` and `concurrency = \"exclusive\"` in `WriteTool`.\n  - LSP writethrough can schedule deferred diagnostics fetches after a timeout, but plain `write.ts` only consumes the immediate return value.\n\n## Limits & Caps\n- `WriteTool` itself exposes no byte cap beyond storing `content` in memory and, for archives, rebuilding the archive in memory.\n- Generated-file detection reads at most `CHECK_BYTE_COUNT = 1024` bytes and `HEADER_LINE_LIMIT = 40` header lines from an existing file in `packages/coding-agent/src/tools/auto-generated-guard.ts`.\n- SQLite writes set `PRAGMA busy_timeout = 3000`.\n- LSP writethrough uses a `5_000` ms operation timeout in `runLspWritethrough()` and may schedule a deferred diagnostics fetch with `AbortSignal.timeout(25_000)` in `scheduleDeferredDiagnosticsFetch()`.\n\n## Errors\n- Invalid archive subpaths throw `ToolError` with messages such as:\n  - `Archive write path must target a file inside the archive`\n  - `Archive write path must target a file, not a directory`\n  - `Archive path cannot contain '..'`\n- SQLite path parsing throws on unsupported forms:\n  - `SQLite write paths do not support query parameters`\n  - `SQLite write path must target a table`\n  - `SQLite row writes require a non-empty row key`\n- Missing SQLite DBs surface as `SQLite database '<path>' not found`.\n- SQLite content errors are model-visible `ToolError`s, including invalid JSON5, non-object payloads, unknown columns, non-scalar values, empty update objects, composite primary keys, and `WITHOUT ROWID` tables.\n- Existing plain files may be rejected by `assertEditableFile()` when they look generated.\n- Archive read/write failures and unexpected SQLite exceptions are wrapped in `ToolError(error.message)`.\n- If no LSP server matches or LSP formatting/diagnostics times out, file writes still fall back to writing content; diagnostics may be omitted.\n\n## Notes\n- Archive path detection runs before SQLite detection. A path that matches an archive selector is never treated as SQLite.\n- SQLite detection declines when an existing file with a `.sqlite` / `.db` suffix is present but does not have SQLite magic bytes; then the path falls back to a plain file write.\n- ZIP entry content is encoded with `new TextEncoder().encode(content)` in `#writeArchiveEntry()`. Non-ZIP archive writes pass the string directly to `Bun.Archive.write()`.\n- The prompt forbids two common anti-patterns: using `write` for routine edits that should use `edit`, and creating `*.md` / `README` files unless explicitly requested. It also forbids emojis unless requested.\n- Plain file writes report byte count using `cleanContent.length`, which is UTF-16 code units in JS, not an on-disk byte measurement.\n- `stripWriteContent()` only removes hashline prefixes when the session’s file display mode has `hashLines` enabled; otherwise content is written unchanged.\n",
 	"tree.md": "# `/tree` Command Reference\n\n`/tree` opens the interactive **Session Tree** navigator. It lets you jump to any entry in the current session file and continue from that point.\n\nThis is an in-file leaf move, not a new session export.\n\n## What `/tree` does\n\n- Builds a tree from current session entries (`SessionManager.getTree()`)\n- Opens `TreeSelectorComponent` with keyboard navigation, filters, and search\n- On selection, calls `AgentSession.navigateTree(targetId, { summarize, customInstructions })`\n- Rebuilds visible chat from the new leaf path\n- Optionally prefills editor text when selecting a user/custom message\n\nPrimary implementation:\n\n- `src/modes/controllers/input-controller.ts` (`/tree`, keybinding wiring, double-escape behavior)\n- `src/modes/controllers/selector-controller.ts` (tree UI launch + summary prompt flow)\n- `src/modes/components/tree-selector.ts` (navigation, filters, search, labels, rendering)\n- `src/session/agent-session.ts` (`navigateTree` leaf switching + optional summary)\n- `src/session/session-manager.ts` (`getTree`, `branch`, `branchWithSummary`, `resetLeaf`, label persistence)\n\n## How to open it\n\nAny of the following opens the same selector:\n\n- `/tree`\n- configured keybinding action `tree`\n- double-escape on empty editor when `doubleEscapeAction = \"tree\"` (default)\n- `/branch` when `doubleEscapeAction = \"tree\"` (routes to tree selector instead of user-only branch picker)\n\n## Tree UI model\n\nThe tree is rendered from session entry parent pointers (`id` / `parentId`).\n\n- Children are sorted by timestamp ascending (older first, newer lower)\n- Active branch (path from root to current leaf) is marked with a bullet\n- Labels (if present) render as `[label]` before node text\n- If multiple roots exist (orphaned/broken parent chains), they are shown under a virtual branching root\n\n```text\nExample tree view (active path marked with •):\n\n├─ user: \"Start task\"\n│  └─ assistant: \"Plan\"\n│     ├─ • user: \"Try approach A\"\n│     │  └─ • assistant: \"A result\"\n│     │     └─ • [milestone] user: \"Continue A\"\n│     └─ user: \"Try approach B\"\n│        └─ assistant: \"B result\"\n```\n\nThe selector recenters around current selection and shows up to:\n\n- `max(5, floor(terminalHeight / 2))` rows\n\n## Keybindings inside tree selector\n\n- `Up` / `Down`: move selection (wraps)\n- `Left` / `Right`: page up / page down\n- `Enter`: select node\n- `Esc`: clear search if active; otherwise close selector\n- `Ctrl+C`: close selector\n- `Type`: append to search query\n- `Backspace`: delete search character\n- `Shift+L`: edit/clear label on selected entry\n- `Ctrl+O`: cycle filter forward\n- `Shift+Ctrl+O`: cycle filter backward\n- `Alt+D/T/U/L/A`: jump directly to specific filter mode\n\n## Filters and search semantics\n\nFilter modes (`TreeList`):\n\n1. `default`\n2. `no-tools`\n3. `user-only`\n4. `labeled-only`\n5. `all`\n\n### `default`\n\nShows most conversational nodes, but hides bookkeeping entry types:\n\n- `label`\n- `custom`\n- `model_change`\n- `thinking_level_change`\n\n### `no-tools`\n\nSame as `default`, plus hides `toolResult` messages.\n\n### `user-only`\n\nOnly `message` entries where role is `user`.\n\n### `labeled-only`\n\nOnly entries that currently resolve to a label.\n\n### `all`\n\nEverything in the session tree, including bookkeeping/custom entries.\n\n### Tool-only assistant node behavior\n\nAssistant messages that contain **only tool calls** (no text) are hidden by default in all filtered views unless:\n\n- message is error/aborted (`stopReason` not `stop`/`toolUse`), or\n- it is the current leaf (always kept visible)\n\n### Search behavior\n\n- Query is tokenized by spaces\n- Matching is case-insensitive\n- All tokens must match (AND semantics)\n- Searchable text includes label, role, and type-specific content (message text, branch summary text, custom type, tool command snippets, etc.)\n\n## Selection outcomes (important)\n\n`navigateTree` computes new leaf behavior from selected entry type:\n\n### Selecting `user` message\n\n- New leaf becomes selected entry’s `parentId`\n- If parent is `null` (root user message), leaf resets to root (`resetLeaf()`)\n- Selected message text is copied to editor for editing/resubmit\n\n### Selecting `custom_message`\n\n- Same leaf rule as user messages (`parentId`)\n- Text content is extracted and copied to editor\n\n### Selecting non-user node (assistant/tool/summary/compaction/custom bookkeeping/etc.)\n\n- New leaf becomes selected node id\n- Editor is not prefilled\n\n### Selecting current leaf\n\n- No-op; selector closes with “Already at this point”\n\n```text\nSelection decision (simplified):\n\nselected node\n   │\n   ├─ is current leaf? ── yes ──> close selector (no-op)\n   │\n   ├─ is user/custom_message? ── yes ──> leaf := parentId (or resetLeaf for root)\n   │                                     + prefill editor text\n   │\n   └─ otherwise ──> leaf := selected node id\n                    + no editor prefill\n```\n\n## Summary-on-switch flow\n\nSummary prompt is controlled by `branchSummary.enabled` (default: `false`).\n\nWhen enabled, after picking a node the UI asks:\n\n- `No summary`\n- `Summarize`\n- `Summarize with custom prompt`\n\nFlow details:\n\n- Escape in summary prompt reopens tree selector\n- Custom prompt cancellation returns to summary choice loop\n- During summarization, UI shows loader and binds `Esc` to `abortBranchSummary()`\n- If summarization aborts, tree selector reopens and no move is applied\n\n`navigateTree` internals:\n\n- Collects abandoned-branch entries from old leaf to common ancestor\n- Emits `session_before_tree` (extensions can cancel or inject summary)\n- Uses default summarizer only if requested and needed\n- Applies move with:\n  - `branchWithSummary(...)` when summary exists\n  - `branch(newLeafId)` for non-root move without summary\n  - `resetLeaf()` for root move without summary\n- Replaces agent conversation with rebuilt session context\n- Emits `session_tree`\n\nNote: if user requests summary but there is nothing to summarize, navigation proceeds without creating a summary entry.\n\n## Labels\n\nLabel edits in tree UI call `appendLabelChange(targetId, label)`.\n\n- non-empty label sets/updates resolved label\n- empty label clears it\n- labels are stored as append-only `label` entries\n- tree nodes display resolved label state, not raw label-entry history\n\n## `/tree` vs adjacent operations\n\n| Operation | Scope                                            | Result                                                                                                                                                   |\n| --------- | ------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `/tree`   | Current session file                             | Moves leaf to selected point (same file)                                                                                                                 |\n| `/branch` | Usually current session file -> new session file | By default branches from selected **user** message into a new session file; if `doubleEscapeAction = \"tree\"`, `/branch` opens tree navigation UI instead |\n| `/fork`   | Whole current session                            | Duplicates session into a new persisted session file                                                                                                     |\n| `/resume` | Session list                                     | Switches to another session file                                                                                                                         |\n\nKey distinction: `/tree` is a navigation/repositioning tool inside one session file. `/branch`, `/fork`, and `/resume` all change session-file context.\n\n## Operator workflows\n\n### Re-run from an earlier user prompt without losing current branch\n\n1. `/tree`\n2. search/select earlier user message\n3. choose `No summary` (or summarize if needed)\n4. edit prefilled text in editor\n5. submit\n\nEffect: new branch grows from selected point within same session file.\n\n### Leave current branch with context breadcrumb\n\n1. enable `branchSummary.enabled`\n2. `/tree` and select target node\n3. choose `Summarize` (or custom prompt)\n\nEffect: a `branch_summary` entry is appended at the target position before continuing.\n\n### Investigate hidden bookkeeping entries\n\n1. `/tree`\n2. press `Alt+A` (all)\n3. search for `model`, `thinking`, `custom`, or labels\n\nEffect: inspect full internal timeline, not just conversational nodes.\n\n### Bookmark pivot points for later jumps\n\n1. `/tree`\n2. move to entry\n3. `Shift+L` and set label\n4. later use `Alt+L` (`labeled-only`) to jump quickly\n\nEffect: fast navigation among durable branch landmarks.\n",
 	"ttsr-injection-lifecycle.md": "# TTSR Injection Lifecycle\n\nThis document covers the current Time Traveling Stream Rules (TTSR) runtime path from rule discovery to stream interruption, retry injection, extension notifications, and session-state handling.\n\n## Implementation files\n\n- [`../src/sdk.ts`](../packages/coding-agent/src/sdk.ts)\n- [`../src/export/ttsr.ts`](../packages/coding-agent/src/export/ttsr.ts)\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`../src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts)\n- [`../src/prompts/system/ttsr-interrupt.md`](../packages/coding-agent/src/prompts/system/ttsr-interrupt.md)\n- [`../src/capability/index.ts`](../packages/coding-agent/src/capability/index.ts)\n- [`../src/extensibility/extensions/types.ts`](../packages/coding-agent/src/extensibility/extensions/types.ts)\n- [`../src/extensibility/hooks/types.ts`](../packages/coding-agent/src/extensibility/hooks/types.ts)\n- [`../src/extensibility/custom-tools/types.ts`](../packages/coding-agent/src/extensibility/custom-tools/types.ts)\n- [`../src/modes/controllers/event-controller.ts`](../packages/coding-agent/src/modes/controllers/event-controller.ts)\n\n## 1. Discovery feed and rule registration\n\nAt session creation, `createAgentSession()` loads discovered rules and constructs a `TtsrManager`:\n\n```ts\nconst ttsrSettings = settings.getGroup(\"ttsr\");\nconst ttsrManager = new TtsrManager(ttsrSettings);\nconst rulesResult = await loadCapability<Rule>(ruleCapability.id, { cwd });\nfor (const rule of rulesResult.items) {\n  if (rule.condition?.length && ttsrManager.addRule(rule)) continue;\n  // non-TTSR rules continue through normal rule handling\n}\n```\n\n### Pre-registration dedupe behavior\n\n`loadCapability(\"rules\")` deduplicates by `rule.name` with first-wins semantics (higher provider priority first). Shadowed duplicates are removed before TTSR registration.\n\n### `TtsrManager.addRule()` behavior\n\nRegistration is skipped when:\n\n- `rule.condition` is absent or all condition regexes fail to compile\n- a rule with the same `rule.name` was already registered in this manager\n- the rule scope excludes all monitored streams\n\nInvalid regex conditions and unreachable scopes are logged as warnings and ignored; session startup continues.\n\n### Setting caveat\n\n`TtsrSettings.enabled` is loaded into the manager but is not currently checked in runtime gating. If TTSR rules exist, matching still runs.\n\n## 2. Streaming monitor lifecycle\n\nTTSR detection runs inside `AgentSession.#handleAgentEvent`.\n\n### Turn start\n\nOn `turn_start`, the stream buffer is reset:\n\n- `ttsrManager.resetBuffer()`\n\n### During stream (`message_update`)\n\nWhen assistant updates arrive and rules exist:\n\n- monitor `text_delta`, `thinking_delta`, and `toolcall_delta`\n- append delta into a source/tool scoped manager buffer\n- call `checkDelta(delta, matchContext)`\n\n`checkDelta()` iterates registered rules and returns all matching rules that pass scope, global-path, condition, and repeat policy checks.\n\n## 3. Trigger decision and immediate abort path\n\nWhen one or more rules match and at least one matched rule allows interruption:\n\n1. Matched rules are deduplicated into `#pendingTtsrInjections`.\n2. `#ttsrAbortPending = true` and a TTSR resume gate is created.\n3. `agent.abort()` is called immediately.\n4. `ttsr_triggered` event is emitted asynchronously (fire-and-forget).\n5. retry work is scheduled via the post-prompt task scheduler with a 50ms delay.\n\nAbort is not blocked on extension callbacks.\n\n## 4. Retry scheduling, context mode, and reminder injection\n\nAfter the 50ms timeout:\n\n1. `#ttsrAbortPending = false`\n2. read `ttsrManager.getSettings().contextMode`\n3. if `contextMode === \"discard\"`, drop the targeted partial assistant output with `agent.replaceMessages(...slice(0, targetAssistantIndex))`\n4. build injection content from pending rules using `ttsr-interrupt.md` template\n5. append and persist a hidden `custom_message`/runtime custom message with `customType: \"ttsr-injection\"` and `details.rules`\n6. mark those rule names injected, persist a `ttsr_injection` entry, and call `agent.continue()` to retry generation\n\nTemplate payload is:\n\n```xml\n<system-interrupt reason=\"rule_violation\" rule=\"{{name}}\" path=\"{{path}}\">\n...\n{{content}}\n</system-interrupt>\n```\n\nPending injections are cleared after content generation.\n\n### `contextMode` behavior on partial output\n\n- `discard`: partial/aborted assistant message is removed before retry.\n- `keep`: partial assistant output remains in conversation state; reminder is appended after it.\n\n### Non-interrupting matches\n\nIf matched rules do not permit interruption (`interruptMode: \"never\"`, or source-specific `prose-only`/`tool-only` mismatch), they are still queued. After a successful non-error, non-aborted assistant message, `AgentSession` injects the hidden `ttsr-injection` custom message as a follow-up and schedules continuation.\n\n## 5. Repeat policy and gap logic\n\n`TtsrManager` tracks `#messageCount` and per-rule `lastInjectedAt`.\n\n### `repeatMode: \"once\"`\n\nA rule can trigger only once after it has an injection record.\n\n### `repeatMode: \"after-gap\"`\n\nA rule can re-trigger only when:\n\n- `messageCount - lastInjectedAt >= repeatGap`\n\n`messageCount` increments on `turn_end`, so gap is measured in completed turns, not stream chunks.\n\n## 6. Event emission and extension/hook surfaces\n\n### Session event\n\n`AgentSessionEvent` includes:\n\n```ts\n{ type: \"ttsr_triggered\"; rules: Rule[] }\n```\n\n### Extension runner\n\n`#emitSessionEvent()` routes the event to:\n\n- extension listeners (`ExtensionRunner.emit({ type: \"ttsr_triggered\", rules })`)\n- local session subscribers\n\n### Hook and custom-tool typing\n\n- extension API exposes `on(\"ttsr_triggered\", ...)`\n- hook API exposes `on(\"ttsr_triggered\", ...)`\n- custom tools receive `onSession({ reason: \"ttsr_triggered\", rules })`\n\n### Interactive-mode rendering difference\n\nInteractive mode uses `session.isTtsrAbortPending` to suppress showing the aborted assistant stop reason as a visible failure during TTSR interruption, and renders a `TtsrNotificationComponent` when the event arrives.\n\n## 7. Persistence and resume state (current implementation)\n\n`SessionManager` persists injected-rule state:\n\n- entry type: `ttsr_injection`\n- append API: `appendTtsrInjection(ruleNames)`\n- query API: `getInjectedTtsrRules()`\n- context reconstruction includes `SessionContext.injectedTtsrRules`\n\n`TtsrManager` supports restoration via `restoreInjected(ruleNames)`.\n\n### Current wiring status\n\nIn the current runtime path:\n\n- interrupted injections append a hidden `custom_message` with `customType: \"ttsr-injection\"` and append a `ttsr_injection` entry via `appendTtsrInjection(...)`\n- deferred non-interrupting injections are marked/persisted when their queued custom message reaches `message_end`\n- `createAgentSession()` restores `existingSession.injectedTtsrRules` into `ttsrManager`\n\nNet effect: injected-rule suppression is persisted/restored across session reload/resume for the current branch path.\n\n## 8. Race boundaries and ordering guarantees\n\n### Abort vs retry callback\n\n- abort is synchronous from TTSR handler perspective (`agent.abort()` called immediately)\n- retry is deferred by timer (`50ms`)\n- extension notification is asynchronous and intentionally not awaited before abort/retry scheduling\n\n### Multiple matches in same stream window\n\n`checkDelta()` returns all currently matching eligible rules for that scoped buffer. Pending injections are deduplicated by rule name before injection.\n\n### Between abort and continue\n\nDuring the timer window, state can change (user interruption, mode actions, additional events). The retry call is best-effort: `agent.continue().catch(() => {})` swallows follow-up errors.\n\n## 9. Edge cases summary\n\n- Invalid `condition` regex: skipped with warning; other conditions/rules continue.\n- Duplicate rule names at capability layer: lower-priority duplicates are shadowed before registration.\n- Duplicate names at manager layer: second registration is ignored.\n- `contextMode: \"keep\"`: partial violating output can remain in context before reminder retry.\n- `interruptMode: \"never\"` queues a deferred hidden injection after a successful assistant message rather than aborting mid-stream.\n- Repeat-after-gap depends on turn count increments at `turn_end`; mid-turn chunks do not advance gap counters.\n",
 	"tui-runtime-internals.md": "# TUI runtime internals\n\nThis document maps the non-theme runtime path from terminal input to rendered output in interactive mode. It focuses on behavior in `packages/tui` and its integration from `packages/coding-agent` controllers.\n\n## Runtime layers and ownership\n\n- **`packages/tui` engine**: terminal lifecycle, stdin normalization, focus routing, render scheduling, differential painting, overlay composition, hardware cursor placement.\n- **`packages/coding-agent` interactive mode**: builds component tree, binds editor callbacks and keymaps, reacts to agent/session events, and translates domain state (streaming, tool execution, retries, plan mode) into UI components.\n\nBoundary rule: the TUI engine is message-agnostic. It only knows `Component.render(width)`, `handleInput(data)`, focus, and overlays. Agent semantics stay in interactive controllers.\n\n## Implementation files\n\n- [`../src/modes/interactive-mode.ts`](../packages/coding-agent/src/modes/interactive-mode.ts)\n- [`../src/modes/controllers/event-controller.ts`](../packages/coding-agent/src/modes/controllers/event-controller.ts)\n- [`../src/modes/controllers/input-controller.ts`](../packages/coding-agent/src/modes/controllers/input-controller.ts)\n- [`../src/modes/components/custom-editor.ts`](../packages/coding-agent/src/modes/components/custom-editor.ts)\n- [`../../tui/src/tui.ts`](../packages/tui/src/tui.ts)\n- [`../../tui/src/terminal.ts`](../packages/tui/src/terminal.ts)\n- [`../../tui/src/editor-component.ts`](../packages/tui/src/editor-component.ts)\n- [`../../tui/src/stdin-buffer.ts`](../packages/tui/src/stdin-buffer.ts)\n- [`../../tui/src/components/loader.ts`](../packages/tui/src/components/loader.ts)\n\n## Boot and component tree assembly\n\n`InteractiveMode` constructs `TUI(new ProcessTerminal(), settings.get(\"showHardwareCursor\"))`, applies `settings.get(\"clearOnShrink\")`, and creates persistent containers:\n\n- `chatContainer`\n- `pendingMessagesContainer`\n- `statusContainer`\n- `todoContainer`\n- `btwContainer`\n- `statusLine`\n- `hookWidgetContainerAbove`\n- `editorContainer` (holds `CustomEditor`)\n- `hookWidgetContainerBelow`\n\n`init()` wires the tree in that order, focuses the editor, registers input handlers via `InputController`, subscribes terminal appearance changes into theme auto-detection, starts TUI, and requests a forced render.\nA forced render (`requestRender(true)`) resets previous-line caches and cursor bookkeeping before repainting.\n\n## Terminal lifecycle and stdin normalization\n\n`ProcessTerminal.start()`:\n\n1. Enables raw mode and bracketed paste.\n2. Attaches resize handler.\n3. Creates a `StdinBuffer` to split partial escape chunks into complete sequences.\n4. Queries Kitty keyboard protocol support (`CSI ? u`), then enables protocol flags if supported; otherwise enables modifyOtherKeys fallback after a short timeout.\n5. Queries OSC 11 background color and enables Mode 2031 appearance notifications for dark/light theme detection.\n6. On Windows, attempts VT input enablement via `kernel32` mode flags.\n   `StdinBuffer` behavior:\n\n- Buffers fragmented escape sequences (CSI/OSC/DCS/APC/SS3).\n- Emits `data` only when a sequence is complete or timeout-flushed.\n- Detects bracketed paste and emits a `paste` event with raw pasted text.\n\nThis prevents partial escape chunks from being misinterpreted as normal keypresses.\n\n## Input routing and focus model\n\nInput path:\n\n`stdin -> ProcessTerminal -> StdinBuffer -> TUI.#handleInput -> focusedComponent.handleInput`\n\nRouting details:\n\n1. TUI runs registered input listeners first (`addInputListener`), allowing consume/transform behavior.\n2. TUI handles global debug shortcut (`shift+ctrl+d`) before component dispatch.\n3. If focused component belongs to an overlay that is now hidden/invisible, TUI reassigns focus to next visible overlay or saved pre-overlay focus.\n4. Key release events are filtered unless focused component sets `wantsKeyRelease = true`.\n5. After dispatch, TUI schedules render.\n\n`setFocus()` also toggles `Focusable.focused`, which controls whether components emit `CURSOR_MARKER` for hardware cursor placement.\n\n## Key handling split: editor vs controller\n\n`CustomEditor` intercepts high-priority combos first (escape, ctrl-c/d/z, ctrl-v, ctrl-p variants, ctrl-t, alt-up, extension custom keys) and delegates the rest to base `Editor` behavior (text editing, history, autocomplete, cursor movement).\n\n`InputController.setupKeyHandlers()` then binds editor callbacks to mode actions:\n\n- cancellation / mode exits on `Escape`\n- shutdown on double `Ctrl+C` or empty-editor `Ctrl+D`\n- suspend/resume on `Ctrl+Z`\n- slash-command and selector hotkeys\n- follow-up/dequeue toggles and expansion toggles\n\nThis keeps key parsing/editor mechanics in `packages/tui` and mode semantics in coding-agent controllers.\n\n## Render loop and diffing strategy\n\n`TUI.requestRender()` is debounced to one render per tick using `process.nextTick`. Multiple state changes in the same turn coalesce.\n\n`#doRender()` pipeline:\n\n1. Render root component tree to `newLines`.\n2. Composite visible overlays (if any).\n3. Extract and strip `CURSOR_MARKER` from visible viewport lines.\n4. Append segment reset suffixes for non-image lines.\n5. Choose full repaint vs differential patch:\n   - first frame\n   - width change\n   - shrink with `clearOnShrink` enabled and no overlays\n   - edits above previous viewport\n6. For differential updates, patch only changed line range and clear stale trailing lines when needed.\n7. Reposition hardware cursor for IME support.\n\nRender writes use synchronized output mode (`CSI ? 2026 h/l`) to reduce flicker/tearing.\n\n## Render safety constraints\n\nCritical safety checks in `TUI`:\n\n- Non-image rendered lines are expected to fit terminal width; the differential path truncates overwide lines as a last-resort guard and can write debug diagnostics when redraw debugging is enabled.\n- Overlay compositing includes defensive truncation and post-composite width guarding.\n- Width changes force full redraw because wrapping semantics change.\n- Cursor position is clamped before movement.\n\nThese constraints are runtime guards plus component conventions; renderers should still return width-safe lines rather than rely on truncation.\n\n## Resize handling\n\nResize events are event-driven from `ProcessTerminal` to `TUI.requestRender()`.\n\nEffects:\n\n- Width changes trigger full redraw.\n- Height changes trigger full redraw except in Termux and terminal multiplexers, where the renderer avoids scrollback-hostile full replays.\n- Viewport/top tracking (`#previousViewportTop`, `#maxLinesRendered`) avoids invalid relative cursor math when content or terminal size changes.\n- Overlay visibility can depend on terminal dimensions (`OverlayOptions.visible`); focus is corrected when overlays become non-visible after resize.\n\n## Streaming and incremental UI updates\n\n`EventController` subscribes to `AgentSessionEvent` and updates UI incrementally:\n\n- `agent_start`: starts loader in `statusContainer`.\n- `message_start` assistant: creates `streamingComponent` and mounts it.\n- `message_update`: updates streaming assistant content; creates/updates tool execution components as tool calls appear.\n- `tool_execution_update/end`: updates tool result components and completion state.\n- `message_end`: finalizes assistant stream, handles aborted/error annotations, marks pending tool args complete on normal stop.\n- `agent_end`: stops loaders, clears transient stream state, flushes deferred model switch, issues completion notification if backgrounded.\n\nRead-tool grouping is intentionally stateful (`#lastReadGroup`) to coalesce consecutive read tool calls into one visual block until a non-read break occurs.\n\n## Status and loader orchestration\n\nStatus lane ownership:\n\n- `statusContainer` holds transient loaders (`loadingAnimation`, `autoCompactionLoader`, `retryLoader`).\n- `statusLine` renders persistent status/hooks/plan indicators and drives editor top border updates.\n\nLoader behavior:\n\n- `Loader` updates every 80ms via interval and requests render each frame.\n- Escape handlers are temporarily overridden during auto-compaction and auto-retry to cancel those operations.\n- On end/cancel paths, controllers restore prior escape handlers and stop/clear loader components.\n\n## Mode transitions and backgrounding\n\n### Bash/Python input modes\n\nInput text prefixes toggle editor border mode flags:\n\n- `!` -> bash mode\n- `$` (non-template literal prefix) -> python mode\n\nEscape exits inactive mode by clearing editor text and restoring border color; when execution is active, escape aborts the running task instead.\n\n### Plan mode\n\n`InteractiveMode` tracks plan mode flags, status-line state, active tools, and model switching. Enter/exit updates session mode entries and status/UI state, including deferred model switch if streaming is active.\n\n### Suspend/resume (`Ctrl+Z`)\n\n`InputController.handleCtrlZ()`:\n\n1. Registers one-shot `SIGCONT` handler to restart TUI and force render.\n2. Stops TUI before suspend.\n3. Sends `SIGTSTP` to process group.\n\n### Background mode (`/background` or `/bg`)\n\n`handleBackgroundCommand()`:\n\n- Rejects when idle.\n- Switches tool UI context to non-interactive (`hasUI=false`) so interactive UI tools fail fast.\n- Stops loaders/status line and unsubscribes foreground event handler.\n- Subscribes background event handler (primarily waits for `agent_end`).\n- Stops TUI and sends `SIGTSTP` (POSIX job control path).\n\nOn `agent_end` in background with no queued work, controller sends completion notification and shuts down.\n\n## Cancellation paths\n\nPrimary cancellation inputs:\n\n- `Escape` during active stream loader: restores queued messages to editor and aborts agent.\n- `Escape` during bash/python execution: aborts running command.\n- `Escape` during auto-compaction/retry: invokes dedicated abort methods through temporary escape handlers.\n- `Ctrl+C` single press: clear editor; double press within 500ms: shutdown.\n\nCancellation is state-conditional; same key can mean abort, mode-exit, selector trigger, or no-op depending on runtime state.\n\n## Event-driven vs throttled behavior\n\nEvent-driven updates:\n\n- Agent session events (`EventController`)\n- Key input callbacks (`InputController`)\n- terminal resize callback\n- terminal appearance callbacks, SIGWINCH theme reevaluation, and git branch watchers in `InteractiveMode`\n\nThrottled/debounced paths:\n\n- TUI rendering is tick-debounced (`requestRender` coalescing).\n- Loader animation is fixed-interval (80ms), each frame requesting render.\n- Editor autocomplete updates (inside `Editor`) use debounce timers, reducing recompute churn during typing.\n\nThe runtime therefore mixes event-driven state transitions with bounded render cadence to keep interactivity responsive without repaint storms.\n",