@oh-my-pi/pi-coding-agent 15.10.2 → 15.10.4

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

@@ -1,6 +1,6 @@
 // Auto-generated by scripts/generate-docs-index.ts - DO NOT EDIT
 
-export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","ai-schema-normalize.md","approval-mode.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","compaction.md","config-usage.md","custom-tools.md","environment-variables.md","extension-loading.md","extensions.md","fs-scan-cache-architecture.md","gemini-manifest-extensions.md","handoff-generation-pipeline.md","hooks.md","install-id.md","keybindings.md","local-models.md","lsp-config.md","marketplace.md","mcp-config.md","mcp-protocol-transports.md","mcp-runtime-lifecycle.md","mcp-server-tool-authoring.md","memory.md","mnemosyne-memory-backend.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","plugin-manager-installer-plumbing.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","skills.md","skills/authoring-extensions.md","skills/authoring-hooks.md","skills/authoring-marketplaces.md","skills/examples/hello-extension/README.md","skills/examples/mini-marketplace/README.md","skills/examples/safety-hook/README.md","slash-command-internals.md","system-prompt-customization.md","task-agent-discovery.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-core-renderer.md","tui-runtime-internals.md","tui.md"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","ai-schema-normalize.md","approval-mode.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","compaction.md","config-usage.md","custom-tools.md","environment-variables.md","extension-loading.md","extensions.md","fs-scan-cache-architecture.md","gemini-manifest-extensions.md","handoff-generation-pipeline.md","hooks.md","install-id.md","keybindings.md","local-models.md","lsp-config.md","macos-signing-notarization.md","marketplace.md","mcp-config.md","mcp-protocol-transports.md","mcp-runtime-lifecycle.md","mcp-server-tool-authoring.md","memory.md","mnemosyne-memory-backend.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","plugin-manager-installer-plumbing.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","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","system-prompt-customization.md","task-agent-discovery.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-core-renderer.md","tui-runtime-internals.md","tui.md"];
 
 export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"ERRATA-GPT5-HARMONY.md": "# ERRATA — GPT-5 Harmony-Header Leakage\n\nHistorical research note, not a current runtime contract. The statistics below\ncome from the named local stats database snapshot, not from checked-in tests or\nruntime code.\n\n## 1. The problem\n\nOpenAI frames tool calls in the Harmony chat protocol:\n\n```\n<|start|>assistant<|channel|>commentary to=functions.<NAME><|message|>{ARGS}<|call|>\n```\n\n`<|channel|>commentary to=functions.NAME` is the **routing header** —\ncontrol tokens consumed by the runtime to dispatch the call. These\ntokens never appear as content under normal operation; the runtime\nstrips them.\n\nThe defect: gpt-5 models occasionally emit, **as ordinary content\ninside `{ARGS}`**, the **plain-text shadow** of these routing tokens —\nthe same characters without the `<|…|>` brackets — and continue\nproducing more pseudo-routing structure (channel name, body marker,\nmultilingual spam, fake tool-result framing). The contamination lives\ninside the visible tool argument and is dispatched to the tool as if it\nwere intended content.\n\n**Critical detail.** The actual `<|start|>` / `<|channel|>` /\n`<|message|>` / `<|call|>` special tokens almost never appear in tool\nargs. What leaks is the bracket-less spelling — `analysis to=functions.X\ncode …` — because OpenAI applies a logit mask suppressing the\ncontrol-token IDs inside the args region. The mass that would have gone\nto those special tokens redistributes onto the un-bracketed plain-text\nrepresentation the model also learned. This makes the leak structurally\ninvisible to the routing parser and lands it in the tool input verbatim.\n\nManifestation in tool args (real corpus example):\n\n```\n~      add_function(iso, ctx, ns, \"installSystemChangeObserver\",\n        os_install_system_change_observer);】【\"】【analysis to=functions.edit\n        code above เงินไทยฟรีuser to=functions.edit code …\n```\n\nThe leading code is real and intended. Everything after the first\nnon-Latin token through the next clean structural boundary is corruption.\n\n---\n\n## 2. Observed statistics & failure modes\n\nSource: `~/.omp/stats.db` (`ss_tool_calls`, `ss_assistant_msgs`), through\n2026-05-10. 1.05M tool calls scanned.\n\n### 2.1 Rate\n\n| Model         | Leaks in tool args |   Calls | per million |\n| ------------- | -----------------: | ------: | ----------: |\n| gpt-5.4       |                 37 | 226,957 |         163 |\n| gpt-5.3-codex |                 17 | 112,243 |         151 |\n| gpt-5.5       |                  2 |  80,750 |          25 |\n| gpt-5.2-codex |                  0 |       — |           — |\n\nPlus 15 hits in assistant visible text / thinking blobs.\n\n### 2.2 Tool distribution\n\n| Tool                           |   Hits |\n| ------------------------------ | -----: |\n| `edit`                         |     38 |\n| `eval`                         |     11 |\n| `report_tool_issue`            |      3 |\n| `grep`/`read`/`search`/`yield` | 1 each |\n\nConcentrated in tools with free-form (non-JSON-schema) argument formats.\n\n### 2.3 Leak shape (deterministic)\n\n```\nLEAK         ::= JUNK_PREFIX MARKER CHANNEL_BODY (LEAK)?\nMARKER       ::= \"to=functions.\" TOOL_NAME\nCHANNEL_BODY ::= \" code \" (SPAM | reasoning_prose | fake_tool_output)*\nJUNK_PREFIX  ::= (GLITCH_TOKEN | CHANNEL_WORD | NON_LATIN_RUN | \"}\" | \"】【\")+\n```\n\n**Cascading is common.** Of 96 marker occurrences across 71 contaminated\nrecords, 39 contain ≥2 markers and 7 contain ≥3 — the model emits\nmultiple fake `to=functions.X code …` blocks back-to-back, often with\nfake `code_output\\nCell N:\\n…` framing between them. Once the\nplain-text scaffolding is in the residual stream, the prefix now _looks\nlike_ a fresh tool envelope start, so the macro prior over continuations\nkeeps voting for more scaffolding. Self-amplifying.\n\n### 2.4 Glitch tokens\n\nSingle-token identifiers in `o200k_base` whose embeddings appear to be\nnear-init from underrepresentation in post-training. ASCII residue\nimmediately before the marker in the natural corpus:\n\n| Surface string    | Single-token | Token ID |                  Hits in corpus |\n| ----------------- | :----------: | -------: | ------------------------------: |\n| `Japgolly`        |      ✅      |  199,745 |                               1 |\n| `Jsii`            |      ✅      |  114,318 | (subtoken of `Jsii_commentary`) |\n| `Jsii_commentary` |  — (3 toks)  |        — |                               2 |\n| `changedFiles`    |  — (2 toks)  |        — |                               8 |\n| `RTLU`            |  — (2 toks)  |        — |                               3 |\n\n`Japgolly` is in the last 0.13% of the vocabulary — the same family of\nGitHub-corpus residue that produced `SolidGoldMagikarp` in the 2023\nGPT-2 vocabulary (Rumbelow & Watkins). `SolidGoldMagikarp` itself\ntokenizes to 5 tokens in `o200k_base` — that specific token was retired,\nbut the class wasn't.\n\nFor the multi-token entries, the corpus-level signature is the surface\nstring; the underlying glitch trigger is a sub-token (e.g. `Jsii` inside\n`Jsii_commentary`). The detector list (`G` signal) keys on the surface\nstrings.\n\nStable across unrelated sessions. Treated as a high-precision detector\nsignal.\n\n### 2.5 Channel-word leakage\n\n`analysis` (5), `assistant` (5), `commentary` (3), `user` (1) appear\ndirectly preceding `to=`. Always bare words; never `<|channel|>analysis`\nor any other bracketed form. Consistent with §1 — the brackets are\nmasked, the words are not.\n\n### 2.6 Non-Latin spam residue\n\n96 marker hits, by script: CJK 40, Cyrillic 12, Telugu/Kannada/Malayalam\n18, Thai 8, Georgian 7, Armenian 7, Arabic 1. Recurring fragments are\nChinese gambling SEO (`大发时时彩`, `天天中彩票`), Georgian/Abkhaz junk,\nand Thai casino spam — well-known low-quality crawl residue.\n\nThis is the same script distribution observed in the controlled\nreproduction (§7.3), independent of the prompt's natural language.\n\n### 2.7 Failure-mode breakdown for the `edit` tool\n\nThe `edit` tool exists in two variants in the corpus:\n\n| Variant                              | Calls | Recovery                                                                                                                                             |\n| ------------------------------------ | ----: | ---------------------------------------------------------------------------------------------------------------------------------------------------- |\n| Patch-DSL (`§PATH`/anchor/`«»≔` ops) |    27 | **Recoverable** by op-truncation (§3.3)                                                                                                              |\n| JSON-schema (`{path,edits:[…]}`)     |    11 | **Not recoverable** — contamination is escaped _inside_ JSON strings, parser accepts it cleanly, content would be written verbatim into source files |\n\nFor Patch-DSL leaks specifically:\n\n- 20/27 cases: contamination on the last input line; nothing follows.\n- 7/27 cases: contamination mid-input; what follows is one of: a\n  duplicate replay of an earlier file/anchor, intended content for a\n  _different_ tool call (the model started its next call inline), or\n  pure hallucination. Post-contamination content is never trustworthy.\n\n### 2.8 Mechanism (confirmed)\n\n**Prior collapse from null-embedding glitch tokens, into a\ncontrol-token-masked basin whose mass redistributes onto the\nplain-text shadow of the Harmony protocol.**\n\nStep by step:\n\n1. The model is mid-`{ARGS}` of a Harmony tool call. The runtime applies\n   a logit mask suppressing structural control tokens (`<|channel|>`,\n   `<|message|>`, `<|call|>`, `<|start|>`, `<|end|>`) inside the args\n   region. Without this mask, normal generation would constantly\n   hallucinate envelope-closes; with it, those token IDs have logit\n   `-∞` in args.\n2. A glitch token `g` is sampled. By construction `g` was in the BPE\n   merge corpus but barely in LM/RL training, so its **input embedding\n   `e_g` ≈ near-init noise of small norm**.\n3. At position t+1, the residual update `h_{t+1} ≈ LN(h_t + e_g + Attn +\nMLP)` is dominated by the prefix-derived terms; the just-emitted-token\n   signal is effectively absent. Generation diversity normally comes\n   from `e_x` steering the residual into different sub-regions —\n   stripped here.\n4. The next-token distribution therefore collapses onto the **conditional\n   prior over continuations of the prefix, with local conditioning\n   removed**. In a tool-calling rollout context, that prior is sharply\n   peaked on Harmony scaffolding (control tokens + routing tokens) —\n   that's what RL trained.\n5. The mask zeros the control-token IDs. Mass redistributes onto the\n   **next-best continuation**: the un-bracketed surface-form spelling of\n   the same protocol (`analysis`, `commentary`, ` to=functions.X`,\n   `code`). This spelling is unmasked because those characters are\n   ordinary tokens.\n6. Once a few tokens of plain-text scaffolding land in the residual\n   stream, the prefix now resembles a fresh envelope start. The macro\n   prior keeps voting for more scaffolding. Cascading (§2.3) follows.\n7. Multilingual spam after the marker is the same prior-collapse\n   continuation, drawn from the training neighborhood of the glitch\n   token (often ESL/auto-generated multilingual web junk — exactly the\n   crawl residue in §2.6).\n\n**Two corollaries the corpus data demanded but only the experiment\nexplained:**\n\n- **The brackets never appear** (§1, §2.5). The mask is what makes the\n  leak land in plain text instead of as a real envelope-close.\n- **Counterintuitive grammar dependency** (§7.4). The leak is _worse_ in\n  formats closest to OpenAI's training distribution. Off-distribution\n  custom grammars dampen the macro-prior basin; the official\n  `*** Begin Patch` format is the strongest collapse target.\n\nThe 2023 SolidGoldMagikarp paper documented mechanism (1)+(2)+(4). The\nnew piece is (5): when constrained decoding masks the natural collapse\ntarget, the mass laundered through the un-masked plain-text shadow\nbecomes a structurally-invisible exfiltration channel.\n",
@@ -23,6 +23,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"keybindings.md": "# Keybindings\n\nRun `/hotkeys` inside an `omp` session to see the active chords for your current build. The list reflects any remaps loaded from disk and any bindings added by extensions.\n\n## Customize keybindings\n\nUser remaps live in `~/.omp/agent/keybindings.yml`. The file is a YAML mapping whose keys are keybinding action IDs and whose values are either one chord string or an array of chord strings. It is not read from `~/.omp/agent/config.yml`, and there is no nested `keybindings` object.\n\n```yaml\napp.model.cycleForward: Ctrl+P\napp.model.selectTemporary: Alt+P\napp.plan.toggle: Alt+Shift+P\n```\n\nChord names are case-insensitive and use the same notation shown in the UI, such as `Ctrl+P`, `Alt+Shift+P`, `Shift+Enter`, and `Ctrl+Backspace`.\n\nSet an action to an empty array to disable it:\n\n```yaml\napp.stt.toggle: []\n```\n\n## Common action IDs\n\n| Action ID                   | Default                                | Meaning                                       |\n| --------------------------- | -------------------------------------- | --------------------------------------------- |\n| `app.model.cycleForward`    | `Ctrl+P`                               | Cycle role models forward                     |\n| `app.model.cycleBackward`   | `Shift+Ctrl+P`                         | Cycle role models in temporary mode           |\n| `app.model.selectTemporary` | `Alt+P`                                | Pick a model temporarily for this session     |\n| `app.model.select`          | `Alt+M`                                | Open the model selector and set roles         |\n| `app.plan.toggle`           | `Alt+Shift+P`                          | Toggle plan mode                              |\n| `app.history.search`        | `Ctrl+R`                               | Search prompt history                         |\n| `app.tools.expand`          | `Ctrl+O`                               | Toggle tool-output expansion                  |\n| `app.thinking.toggle`       | `Ctrl+T`                               | Toggle thinking-block visibility              |\n| `app.thinking.cycle`        | `Shift+Tab`                            | Cycle thinking level                          |\n| `app.editor.external`       | `Ctrl+G`                               | Edit the draft in `$VISUAL` / `$EDITOR`       |\n| `app.message.followUp`      | `Ctrl+Q`, `Ctrl+Enter`                 | Queue a follow-up message                     |\n| `app.message.dequeue`       | `Alt+Up`                               | Dequeue a queued message back into the editor |\n| `app.display.reset`         | `Ctrl+L`                               | Reset terminal display                        |\n| `app.clipboard.copyLine`    | `Alt+Shift+L`                          | Copy the current line                         |\n| `app.clipboard.copyPrompt`  | `Alt+Shift+C`                          | Copy the whole prompt                         |\n| `app.clipboard.pasteImage`  | `Ctrl+V` (`Alt+V` fallback on Windows) | Paste an image from the clipboard             |\n| `app.stt.toggle`            | `Alt+H`                                | Toggle speech-to-text recording               |\n\nOn Windows Terminal, `Ctrl+V` may be handled by the terminal paste command before `omp` sees it; use the `Alt+V` fallback when clipboard image paste appears to do nothing. Windows Terminal also swallows `Ctrl+Enter`, so the follow-up shortcut also binds `Ctrl+Q` — the same chord GitHub Copilot CLI uses. If your existing `keybindings.yml` already assigns `Ctrl+Q` to another action, that user remap wins and follow-up keeps `Ctrl+Enter` unless you explicitly bind `app.message.followUp`.\n\nTerminals that implement OSC 5522 enhanced paste can send clipboard MIME data directly to `omp`; image pastes are attached as `[Image #N]`, while text/plain paste events keep normal paste behavior. When OSC 5522 is unavailable, bracketed paste still handles text, and a pasted single image-file path is loaded as an image when the file is readable from the `omp` host.\n\nOlder unqualified action names are migrated when `keybindings.yml` is loaded, but new docs and new configs should use the namespaced action IDs above. Existing `keybindings.json` files are still accepted and migrated to `keybindings.yml`; `keybindings.yaml` is also accepted.\n",
 	"local-models.md": "# Embedded Local Tiny-Model Experiments\n\nThis document summarizes the experiments behind the optional **local** tiny-model paths for\nsession-title generation (`providers.tinyModel`), Mnemopi memory extraction/consolidation\n(`providers.memoryModel`), and the `auto` thinking-level difficulty classifier\n(`providers.autoThinkingModel`, which reuses the memory-model registry). It is a factual engineering\nrecord for maintainers: what we measured, which recipes won, and which models we shipped. All three\nsettings default to `online`, so existing users incur no downloads or on-device inference cost unless\nthey opt in.\n\n## Runtime / environment findings\n\n- **Stack**: `@huggingface/transformers` (transformers.js) v4 running under Bun. In Bun the library\n  loads the **native `onnxruntime-node` backend** (not the WASM build).\n- **Device policy**: local tiny models default to CPU-only inference and retry once on CPU if an\n  explicit accelerated provider cannot initialize.\n  - Pick a provider persistently with the `providers.tinyModelDevice` setting (`default` keeps CPU),\n    or per-run with the `PI_TINY_DEVICE` env var (which overrides the setting).\n  - Accepted values are `cpu`, `gpu`, `metal`/`webgpu`, `auto`, `cuda`, `dml`, `coreml`, `wasm`,\n    `webnn`, `webnn-gpu`, `webnn-cpu`, and `webnn-npu`.\n  - Direct `coreml` remains opt-in via `PI_TINY_DEVICE=coreml`; it is not part of the default because\n    cached decoder-LLM ONNX loads can fail during session initialization.\n  - WebGPU/Metal works for the single-process eval harness, but the production worker forces\n    Darwin `gpu`/`webgpu`/`auto` requests back to CPU because ONNX Runtime/Bun currently\n    hard-crashes on worker teardown after WebGPU inference.\n  - Use `providers.tinyModelDevice` or `PI_TINY_DEVICE` only when explicitly opting out of the CPU\n    default.\n- **Quantization: q4 is the sweet spot** — smaller on disk, faster to load, and fast at inference.\n  q8/int8 loads slower _and_ infers slower on CPU. Every shipped model defaults to `q4`; override the\n  precision persistently with the `providers.tinyModelDtype` setting (`default` keeps `q4`, e.g. `fp16`\n  for higher fidelity), or per-run with `PI_TINY_DTYPE` (which overrides the setting). Accepts `auto`,\n  `fp32`, `fp16`, `q8`, `int8`, `uint8`, `q4`, `bnb4`, `q4f16`, `q2`, `q2f16`, `q1`, `q1f16`; an\n  unrecognized value fails loudly at worker startup.\n- **Load-time correction (important).** An earlier belief that \"q4 >=1B models take minutes to load\"\n  was a **measurement artifact** caused by running ~5 multi-GB HuggingFace downloads in parallel\n  (I/O saturation). Clean, isolated **warm** loads are all sub-3s:\n  - TinyLlama-1.1B q4: ~0.5s\n  - Llama-3.2-1B q4: ~2.8s (`graphOpt=all`) / ~0.5s (`disabled`)\n  - LFM2-1.2B q4: ~0.36s\n  - Qwen2.5-1.5B q4: ~1.5s\n  - Qwen3-1.7B q4: ~1.6s\n  - gemma-3-1b q4: ~1.1s\n  - Conclusion: **1B–1.7B models are viable on CPU.**\n- **`session_options.graphOptimizationLevel`** trades load vs inference speed: `disabled` = fastest\n  load, slightly slower inference; `all` = default.\n- **First run** downloads weights from the HF Hub to a cache dir (q4 weights ~200MB–1.1GB depending\n  on model); subsequent **warm** loads are sub-second to ~3s. Inference is async and\n  background-friendly for memory tasks; titles are semi-interactive.\n\n## Task 1: Session title generation (`providers.tinyModel`)\n\n**Task**: turn the first user message into a 3–6 word title. Tiny models (sub-1B) suffice.\n\n**Winning recipe**:\n\n- Plain system prompt (no few-shot).\n- **Prefill** the assistant turn with `<title>` and **stop at `</title>`**, then take the first line.\n- Greedy decoding (`do_sample:false`), `enable_thinking:false` in the chat template.\n\n**What we learned**:\n\n- **Few-shot examples HURT sub-0.6B models** for titles; the tag-prefill rescues even 270M models.\n- **Token biasing (`bad_words_ids`) is a confirmed no-op** here — the prefill already controls the\n  opener.\n\n**Leaderboard** (tag trick, CPU, warm):\n\n| Model         | Verdict                             |\n| ------------- | ----------------------------------- |\n| LFM2-350M     | Best speed/quality balance (~212MB) |\n| Qwen3-0.6B    | Most robust                         |\n| gemma-3-270m  | Smallest viable                     |\n| Qwen2.5-0.5B  | Acceptable                          |\n| SmolLM2-135M  | Too small                           |\n| flan-t5-small | Rejected — just echoes the input    |\n\n**Shipped local options**: `lfm2-350m`, `qwen3-0.6b`, `gemma-270m`, `qwen2.5-0.5b`, `lfm2-700m`.\n**Default**: `online` (pi/smol).\n\n## Task 2: Mnemopi memory (`providers.memoryModel`)\n\nMnemopi runs two small-LLM tasks:\n\n1. **Extraction** — pull durable, structured items from a single message.\n2. **Consolidation** — summarize a list of memories into 1–3 faithful sentences.\n\nThese need **bigger models than titles: 1B–1.7B**. We tested LFM2-1.2B, Qwen2.5-1.5B, Qwen3-1.7B,\nand gemma-3-1b (q4, CPU) via four parallel agents each running 27–31 experiments.\n\n### Extraction findings\n\nThe stock 5-category JSON prompt fails on small models in two ways:\n\n1. The all-empty example `{\"facts\":[],...}` gets **copied verbatim** → 0 facts extracted.\n2. Capable models emit **JSON objects inside arrays**, which Mnemopi's `String(item)` coerces into\n   the literal string `[object Object]`.\n\nThe robust fix is a **one-item-per-line output format** (consumed by Mnemopi's parser line-fallback)\nor a **flat JSON array of strings**. Every model also over-extracts pure small talk; an explicit\nchit-chat → NONE example is the best mitigation.\n\n### Technique polarity flips vs titles\n\n- At 1B+, **few-shot is the dominant quality lever**: e.g. Qwen2.5-1.5B extraction F1 0.52 → 0.83\n  going 1 → 3 shots; gemma recall 0.65 → 0.92 with 2 shots.\n- **Prefill HURTS extraction** — it forces output on small talk, producing false positives.\n- **System-split** (instructions in the system role) helps models that have a system role.\n- **Greedy >= temperature** for both tasks.\n- **Token biasing** is again a no-op.\n\n### Per-model verdicts (head-to-head, 16-fixture set)\n\n- **Qwen3-1.7B** — most disciplined extraction: returns empty on small talk, no buried-fact leak,\n  preserves language, clean flat JSON. Weaknesses: coarse granularity, missed a multi-turn value\n  update.\n- **Qwen2.5-1.5B** — best extraction granularity (atomic facts), caught the value update, zero\n  small-talk leakage. Weaknesses: weakest consolidation (run-on, no dedup) and one degenerate\n  buried-fact output.\n- **gemma-3-1b** — best consolidation (dedup works, faithful, clean single-memory). Weaknesses: leaks\n  small talk and translated German.\n- **LFM2-1.2B** — solid and fastest to load. Weaknesses: `Label: value` noise, small-talk + buried\n  leaks, a fluffy single-memory summary.\n\n### Recommendation\n\nExtraction favors **precision** (do not pollute long-term memory) → **Qwen3-1.7B is the best single\npick** (its consolidation is good enough). If running a second model for consolidation, **gemma-3-1b**\nwins that task.\n\n**Shipped local options**: `qwen3-1.7b` (recommended), `gemma-3-1b`, `qwen2.5-1.5b`, `lfm2-1.2b`.\n**Default**: `online` (the configured smol model).\n\n### Known Mnemopi parser bugs (surfaced by these experiments)\n\n- `String(item)` produces `[object Object]` on object array items.\n- The line-fallback drops items `<=10` chars, so a correct short fact like `Name: Can` is discarded.\n\n\n## Integration notes\n\n- `providers.tinyModel`, `providers.memoryModel`, and `providers.autoThinkingModel` default to\n  `online`, so existing users get **no downloads or on-device inference cost** unless they opt in.\n- Local inference runs **in a worker** (off the main thread); models are cached on disk and\n  downloaded on first use.\n- The memory local path applies the refined recipes (line-format + small-talk-guarded extraction\n  prompt, hardened consolidation prompt) via Mnemopi prompt overrides; the **online path is\n  unchanged**.\n- `providers.autoThinkingModel` uses the same shipped local options as `providers.memoryModel`.\n",
 	"lsp-config.md": "# LSP configuration in OMP\n\nThis guide explains how to configure language servers for the OMP coding agent.\n\nSource of truth in code:\n\n- Server config type: `packages/coding-agent/src/lsp/types.ts` (`ServerConfig`)\n- Config loader: `packages/coding-agent/src/lsp/config.ts`\n- Built-in server definitions: `packages/coding-agent/src/lsp/defaults.json`\n\n## Auto-detection\n\nWhen no LSP config file is present, OMP auto-detects servers by intersecting two conditions:\n\n1. The project directory contains at least one of the server's `rootMarkers`.\n2. The server binary is available — checked in project-local bin directories first (e.g., `node_modules/.bin/`, `.venv/bin/`), then `$PATH`.\n\nNo configuration is required for common setups. The built-in server list covers most popular languages; see [`defaults.json`](../packages/coding-agent/src/lsp/defaults.json) for the full set.\n\n## Config file locations\n\nOMP merges LSP config from multiple files, lowest to highest priority:\n\n| Priority    | Location                                                                                                                    |\n| ----------- | --------------------------------------------------------------------------------------------------------------------------- |\n| 5 (lowest)  | `~/lsp.json`, `~/.lsp.json`, `~/lsp.yaml`, `~/.lsp.yaml`, `~/lsp.yml`, `~/.lsp.yml`                                         |\n| 4           | Plugin LSP configs (marketplace / `--plugin-dir` roots)                                                                     |\n| 3           | User config dirs: `~/.omp/agent/lsp.*`, `~/.claude/lsp.*`, `~/.codex/lsp.*`, `~/.gemini/lsp.*`                              |\n| 2           | Project config dirs: `<project>/.omp/lsp.*`, `<project>/.claude/lsp.*`, `<project>/.codex/lsp.*`, `<project>/.gemini/lsp.*` |\n| 1 (highest) | Project root: `<project>/lsp.*` and `<project>/.lsp.*`                                                                      |\n\nEach location accepts `.json`, `.yaml`, and `.yml` variants, including hidden-file versions (`.lsp.json`, `.lsp.yaml`, `.lsp.yml`). Files are merged in order: higher-priority files override lower-priority fields for the same server. Servers not mentioned in any override file remain at their built-in defaults.\n\n**Recommended locations:**\n\n- User-wide preferences → `~/.omp/agent/lsp.json`\n- Project-specific overrides → `<project>/.omp/lsp.json`\n\n> **Note:** Auto-detection is skipped only when at least one config file contributes server overrides. A config file that only sets `idleTimeoutMs` still lets OMP auto-detect built-in servers. When server overrides exist, OMP merges them with defaults and then loads servers that have matching `rootMarkers`, an available binary, and are not explicitly `disabled`.\n\n## File shape\n\nBoth JSON and YAML are accepted. The top-level object can use either a `servers` wrapper key or a flat map directly:\n\n```json\n{\n  \"servers\": {\n    \"server-name\": { ... }\n  },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nor (flat, without the `servers` wrapper):\n\n```json\n{\n  \"server-name\": { ... },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nTop-level keys:\n\n- `servers` — map of server name to `ServerConfig` (optional wrapper; flat form is equivalent)\n- `idleTimeoutMs` — shut down idle language servers after this many milliseconds; disabled by default\n\n## ServerConfig fields\n\n| Field             | Type       | Required | Description                                                                                                      |\n| ----------------- | ---------- | -------- | ---------------------------------------------------------------------------------------------------------------- |\n| `command`         | `string`   | yes      | Binary name (resolved via PATH/local bins) or absolute path                                                      |\n| `args`            | `string[]` | no       | Arguments passed to the binary                                                                                   |\n| `fileTypes`       | `string[]` | yes      | File extensions this server handles, e.g. `[\".ts\", \".tsx\"]`                                                      |\n| `rootMarkers`     | `string[]` | yes      | Files/dirs that indicate a project root; glob patterns (e.g. `*.cabal`) are supported                            |\n| `initOptions`     | `object`   | no       | Sent as `initializationOptions` during LSP handshake                                                             |\n| `settings`        | `object`   | no       | Workspace settings pushed via `workspace/didChangeConfiguration`                                                 |\n| `disabled`        | `boolean`  | no       | Set to `true` to disable this server entirely                                                                    |\n| `warmupTimeoutMs` | `number`   | no       | Startup timeout in ms for this server (overrides the global default)                                             |\n| `isLinter`        | `boolean`  | no       | Mark server as linter/formatter only; excluded from type-intelligence operations (hover, go-to-definition, etc.) |\n| `capabilities`    | `object`   | no       | Opt-in server-specific features; see [Capabilities](#capabilities)                                               |\n\n`resolvedCommand` is populated automatically at runtime — do not set it manually.\n\n### Capabilities\n\nThe `capabilities` object enables optional server-specific features that OMP supports on a per-server basis:\n\n```json\n{\n  \"capabilities\": {\n    \"flycheck\": true,\n    \"ssr\": true,\n    \"expandMacro\": true,\n    \"runnables\": true,\n    \"relatedTests\": true\n  }\n}\n```\n\nAll fields are boolean and optional. They are currently used by `rust-analyzer`.\n\n## Common recipes\n\n### Override a built-in server's settings\n\nPartial overrides are merged onto the built-in defaults. You only need to specify the fields you want to change.\n\n```json\n{\n  \"servers\": {\n    \"typescript-language-server\": {\n      \"args\": [\"--stdio\", \"--log-level\", \"4\"]\n    }\n  }\n}\n```\n\n```yaml\nservers:\n  gopls:\n    settings:\n      gopls:\n        gofumpt: false\n        staticcheck: false\n```\n\n### Disable a built-in server\n\n```json\n{\n  \"servers\": {\n    \"eslint\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\n### Register a custom server\n\nNew servers require `command`, `fileTypes`, and `rootMarkers`. All other fields are optional.\n\n```json\n{\n  \"servers\": {\n    \"my-lsp\": {\n      \"command\": \"my-lsp-server\",\n      \"args\": [\"--stdio\"],\n      \"fileTypes\": [\".xyz\"],\n      \"rootMarkers\": [\".xyz-project\", \".git\"]\n    }\n  }\n}\n```\n\n### Set a global idle timeout\n\nShut down language servers that have been inactive for more than five minutes:\n\n```json\n{\n  \"idleTimeoutMs\": 300000\n}\n```\n\n### Disable a server for one project, keep it globally\n\nPlace the override in `<project>/.omp/lsp.json`:\n\n```json\n{\n  \"servers\": {\n    \"pylsp\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\nThe user-level config in `~/.omp/agent/lsp.json` is unaffected; pylsp is only suppressed in this project.\n\n## Built-in server list\n\nThe following servers ship in `defaults.json` and are eligible for auto-detection:\n\n| Server key                    | Language(s)                   | Binary                            |\n| ----------------------------- | ----------------------------- | --------------------------------- |\n| `rust-analyzer`               | Rust                          | `rust-analyzer`                   |\n| `clangd`                      | C, C++, ObjC                  | `clangd`                          |\n| `zls`                         | Zig                           | `zls`                             |\n| `gopls`                       | Go                            | `gopls`                           |\n| `typescript-language-server`  | TypeScript, JavaScript        | `typescript-language-server`      |\n| `denols`                      | TypeScript, JavaScript (Deno) | `deno`                            |\n| `biome`                       | TS/JS/JSON (linter)           | `biome`                           |\n| `eslint`                      | TS/JS/Vue/Svelte (linter)     | `vscode-eslint-language-server`   |\n| `vscode-html-language-server` | HTML                          | `vscode-html-language-server`     |\n| `vscode-css-language-server`  | CSS, SCSS, Less               | `vscode-css-language-server`      |\n| `vscode-json-language-server` | JSON                          | `vscode-json-language-server`     |\n| `tailwindcss`                 | HTML, CSS, TS/JS              | `tailwindcss-language-server`     |\n| `svelte`                      | Svelte                        | `svelteserver`                    |\n| `vue-language-server`         | Vue                           | `vue-language-server`             |\n| `astro`                       | Astro                         | `astro-ls`                        |\n| `pyright`                     | Python                        | `pyright-langserver`              |\n| `basedpyright`                | Python                        | `basedpyright-langserver`         |\n| `pylsp`                       | Python                        | `pylsp`                           |\n| `ruff`                        | Python (linter)               | `ruff`                            |\n| `jdtls`                       | Java                          | `jdtls`                           |\n| `kotlin-lsp`                  | Kotlin                        | `kotlin-lsp`                      |\n| `metals`                      | Scala                         | `metals`                          |\n| `hls`                         | Haskell                       | `haskell-language-server-wrapper` |\n| `ocamllsp`                    | OCaml                         | `ocamllsp`                        |\n| `elixirls`                    | Elixir                        | `elixir-ls`                       |\n| `erlangls`                    | Erlang                        | `erlang_ls`                       |\n| `gleam`                       | Gleam                         | `gleam`                           |\n| `solargraph`                  | Ruby                          | `solargraph`                      |\n| `ruby-lsp`                    | Ruby                          | `ruby-lsp`                        |\n| `rubocop`                     | Ruby (linter)                 | `rubocop`                         |\n| `bashls`                      | Bash, Zsh                     | `bash-language-server`            |\n| `lua-language-server`         | Lua                           | `lua-language-server`             |\n| `intelephense`                | PHP                           | `intelephense`                    |\n| `phpactor`                    | PHP                           | `phpactor`                        |\n| `omnisharp`                   | C#                            | `omnisharp`                       |\n| `yamlls`                      | YAML                          | `yaml-language-server`            |\n| `terraformls`                 | Terraform                     | `terraform-ls`                    |\n| `dockerls`                    | Dockerfile                    | `docker-langserver`               |\n| `helm-ls`                     | Helm                          | `helm_ls`                         |\n| `nixd`                        | Nix                           | `nixd`                            |\n| `nil`                         | Nix                           | `nil`                             |\n| `ols`                         | Odin                          | `ols`                             |\n| `dartls`                      | Dart                          | `dart`                            |\n| `marksman`                    | Markdown                      | `marksman`                        |\n| `texlab`                      | LaTeX                         | `texlab`                          |\n| `graphql`                     | GraphQL                       | `graphql-lsp`                     |\n| `prismals`                    | Prisma                        | `prisma-language-server`          |\n| `vimls`                       | Vim script                    | `vim-language-server`             |\n| `emmet-language-server`       | HTML, CSS, JSX                | `emmet-language-server`           |\n| `sourcekit-lsp`               | Swift                         | `sourcekit-lsp`                   |\n| `swiftlint`                   | Swift (linter)                | `swiftlint`                       |\n| `tlaplus`                     | TLA+                          | `tlapm_lsp`                       |\n",
+	"macos-signing-notarization.md": "# macOS signing & notarization\n\nThe compiled macOS `omp` binaries shipped on GitHub Releases are signed with a\n**Developer ID Application** certificate and **notarized** by Apple. This makes\nthem Gatekeeper-acceptable and is the prerequisite for an official Homebrew\nsubmission (see [#776](https://github.com/can1357/oh-my-pi/issues/776)).\n\nSigning happens in CI, in the `release_binary` job's darwin matrix legs\n(`.github/workflows/ci.yml`), via `scripts/ci-macos-sign.sh`. It **auto-skips**\nuntil the `APPLE_*` repository secrets below are configured, so releases keep\nworking (ad-hoc signed, as before) in the meantime.\n\n## How it works\n\n1. `ci:release:build-binaries` builds and **ad-hoc** signs the binary (so it can\n   run on the build runner).\n2. `scripts/ci-macos-sign.sh` then:\n   - imports the Developer ID cert into a throwaway keychain;\n   - re-signs with `--options runtime --timestamp` (hardened runtime + secure\n     timestamp) and `--entitlements scripts/macos-entitlements.plist`;\n   - runs `--version` and `--smoke-test` under the new signature to fail fast;\n   - notarizes the binary via `notarytool submit --wait`.\n3. `release_github_verify` re-downloads the published arm64 asset and asserts it\n   is **not** ad-hoc, passes `codesign --verify --strict`, and boots cleanly.\n\n### Why the entitlements are mandatory\n\nThe binary is a Bun single-file executable, so the hardened runtime needs:\n\n| Entitlement | Reason |\n| --- | --- |\n| `com.apple.security.cs.allow-jit` | JavaScriptCore JITs at runtime. |\n| `com.apple.security.cs.allow-unsigned-executable-memory` | JSC executable memory pages. |\n| `com.apple.security.cs.disable-library-validation` | omp extracts its native addon (`pi_natives.<triple>.node`) and other optional dylibs to a runtime cache and `dlopen()`s them. They do not share the main binary's Team ID, so without this the hardened runtime aborts with *\"mapping process and mapped file have different Team IDs\"* — breaking effectively every command. |\n\nWithout `disable-library-validation`, a signed+notarized binary signs and\nnotarizes fine but **fails at first real use**. `scripts/ci-macos-sign.sh` runs\n`--smoke-test` after signing specifically to catch this before notarizing.\n\n### Stapling limitation (important)\n\nA bare Mach-O executable **cannot be stapled** (`stapler` only supports\n`.app`/`.pkg`/`.dmg`). The binary is genuinely notarized — `notarytool` returns\n`Accepted` and the ticket exists on Apple's servers keyed to its cdhash — but\nbecause there is no *stapled* ticket, a direct `spctl -a -t exec` assessment\nreports `rejected / source=Unnotarized Developer ID`. This is expected and is\n**not** a signing or credential failure.\n\nWhat this means in practice:\n\n- `curl https://omp.sh/install | sh` — `curl` sets no quarantine bit, so\n  Gatekeeper is never consulted; the binary just runs. ✅\n- Homebrew **formula** installs — Homebrew does not quarantine formula files, so\n  Gatekeeper is never consulted. ✅\n- Anything that **quarantines** the binary (a browser download, or a Homebrew\n  **cask**) and is assessed offline will be blocked, because there is no stapled\n  ticket. For that route, wrap the binary in a stapleable, notarized **`.pkg` or\n  `.dmg`** (`xcrun stapler staple` works on those). That is a follow-up and is\n  **not** required for the `curl`/formula paths.\n\n## Required GitHub secrets\n\nAdd these under **Settings → Secrets and variables → Actions** (repo secrets).\nBoth the cert (`APPLE_CERTIFICATE_P12`) **and** the API key (`APPLE_API_KEY`)\nmust be present for signing to engage.\n\n| Secret | What it is |\n| --- | --- |\n| `APPLE_CERTIFICATE_P12` | base64 of the exported Developer ID Application `.p12` (cert + private key). |\n| `APPLE_CERTIFICATE_PASSWORD` | password you set when exporting the `.p12`. |\n| `APPLE_API_KEY_ID` | App Store Connect API **Key ID**. |\n| `APPLE_API_ISSUER_ID` | App Store Connect API **Issuer ID** (UUID). |\n| `APPLE_API_KEY` | base64 of the App Store Connect `.p8` private key. |\n\n### Producing the credential files\n\nDrop these into a working directory (default `~/omp-signing`):\n\n| File | How |\n| --- | --- |\n| `*.p12` | **Keychain Access** → right-click your *Developer ID Application: …* identity (the entry that expands to a cert **with** a private key) → **Export…** → save as `.p12` and set a password. |\n| `p12-password.txt` | the password you just set on the `.p12`. |\n| `AuthKey_<KEYID>.p8` | App Store Connect → **Users and Access → Integrations → App Store Connect API** → create a key (**Account Holder** role also allows API cert creation; **Developer** is enough for notarization) → **download once** (non-recoverable). |\n| `issuer-id.txt` | the **Issuer ID** (UUID) shown above the keys table. |\n| `key-id.txt` | *optional* — the Key ID; otherwise read from the `.p8` filename. |\n\nThe App Store Connect API key is the one credential that **cannot** be minted\nfrom a CLI — it is the bootstrap credential for the API itself, and the `.p8`\ndownloads exactly once. Everything else is local.\n\n### Uploading (no value leaves disk)\n\n`scripts/ci-macos-upload-secrets.sh` validates the files (opens the `.p12` with\nyour password, sanity-checks the `.p8`) and pipes each value to `gh secret set`\nover stdin — no secret is ever printed to the terminal, argv, or shell history:\n\n```sh\nscripts/ci-macos-upload-secrets.sh ~/omp-signing --dry-run   # validate first\nscripts/ci-macos-upload-secrets.sh ~/omp-signing             # upload all five\ngh secret list --repo can1357/oh-my-pi                       # confirm\n```\n\nRe-run it whenever the certificate is renewed.\n\n### Finding your signing identity / Team ID (sanity check)\n\n```sh\nsecurity find-identity -v -p codesigning\n# e.g. \"Developer ID Application: Your Name (TEAMID1234)\"\n```\n\nThe script selects the first `Developer ID Application` identity automatically;\nyou do not need to store the identity string or Team ID as a secret.\n\n## Local dry run\n\nYou can exercise the full sign+notarize path locally (real cert + API key) by\nexporting the five env vars and running:\n\n```sh\nRELEASE_TARGETS=darwin-arm64 bun run ci:release:build-binaries\nAPPLE_CERTIFICATE_P12=… APPLE_CERTIFICATE_PASSWORD=… \\\nAPPLE_API_KEY_ID=… APPLE_API_ISSUER_ID=… APPLE_API_KEY=… \\\n  bash scripts/ci-macos-sign.sh packages/coding-agent/binaries/omp-darwin-arm64\n```\n",
 	"marketplace.md": "# Marketplace plugin system\n\nThe marketplace system lets you discover, install, and manage plugins from Git, local, or direct-catalog sources. It is compatible with the Claude Code plugin registry format.\n\n## Quick start\n\n```\n/marketplace add anthropics/claude-plugins-official\n/marketplace install wordpress.com@claude-plugins-official\n```\n\nIn the TUI, `/marketplace` with no arguments opens the interactive plugin browser. In non-TUI command handling, `/marketplace` lists configured marketplaces; use `/marketplace discover` to browse.\n\n## Concepts\n\nA **marketplace** is a Git repository (or local directory) containing a catalog file at `.claude-plugin/marketplace.json`. The catalog lists available plugins with their sources, descriptions, and metadata.\n\nA **plugin** is a directory containing Claude/OMP plugin content such as skills, commands, hooks, tools, MCP servers, LSP servers, rules, prompts, or extension modules. Plugins are identified by `name@marketplace` (e.g. `code-review@claude-plugins-official`).\n\n**Scopes**: marketplace plugins can be installed at two scopes:\n\n- **user** (default) -- available in all projects, stored in `~/.omp/plugins/installed_plugins.json`\n- **project** -- available only in the active project, stored in the nearest project `.omp/plugins/installed_plugins.json`\n\nEnabled project-scoped installs shadow enabled user-scoped installs of the same plugin. A disabled project install does not shadow the user install.\n\n## Commands\n\n### Interactive mode\n\n| Command        | Effect                                    |\n| -------------- | ----------------------------------------- |\n| `/marketplace` | Open interactive plugin browser (install) |\n\n### Marketplace management\n\n| Command                      | Effect                                       |\n| ---------------------------- | -------------------------------------------- |\n| `/marketplace add <source>`  | Add a marketplace source                     |\n| `/marketplace remove <name>` | Remove a marketplace                         |\n| `/marketplace update [name]` | Re-fetch catalog(s); omit name to update all |\n| `/marketplace list`          | List configured marketplaces                 |\n\n### Plugin operations\n\n| Command                                                                   | Effect                                             |\n| ------------------------------------------------------------------------- | -------------------------------------------------- |\n| `/marketplace discover [marketplace]`                                     | Browse available plugins                           |\n| `/marketplace install [--force] [--scope user\\|project] name@marketplace` | Install a plugin                                   |\n| `/marketplace uninstall [--scope user\\|project] name@marketplace`         | Uninstall a plugin; no args opens the TUI selector |\n| `/marketplace installed`                                                  | List installed marketplace plugins                 |\n| `/marketplace upgrade [--scope user\\|project] [name@marketplace]`         | Upgrade one or all plugins                         |\n| `/plugins list`                                                           | List npm/link and marketplace plugins              |\n| `/plugins enable [--scope user\\|project] name@marketplace`                | Enable a marketplace plugin                        |\n| `/plugins disable [--scope user\\|project] name@marketplace`               | Disable a marketplace plugin                       |\n\n### CLI equivalents\n\nThe same operations are available from the command line:\n\n```\nomp plugin marketplace add <source>\nomp plugin marketplace remove <name>\nomp plugin marketplace update [name]\nomp plugin marketplace list\nomp plugin discover [marketplace]\nomp plugin install [--force] [--scope user|project] name@marketplace\nomp plugin uninstall [--scope user|project] name@marketplace\nomp plugin upgrade [--scope user|project] [name@marketplace]\nomp plugin enable [--scope user|project] name@marketplace\nomp plugin disable [--scope user|project] name@marketplace\n```\n\n## Marketplace sources\n\nWhen you run `/marketplace add <source>`, the system classifies the source:\n\n| Source format                   | Type                                               | Example                                |\n| ------------------------------- | -------------------------------------------------- | -------------------------------------- |\n| `owner/repo`                    | GitHub shorthand                                   | `anthropics/claude-plugins-official`   |\n| `https://...*.json`             | Direct catalog URL                                 | `https://example.com/marketplace.json` |\n| `https://...` / `http://...`    | Git repository unless the URL path ends in `.json` | `https://github.com/org/repo`          |\n| `git@...` / `ssh://...`         | Git repository                                     | `git@github.com:org/repo.git`          |\n| `./path` or `~/path` or `/path` | Local directory                                    | `./my-marketplace`                     |\n\nGit and local sources must contain `.claude-plugin/marketplace.json`. Direct catalog URLs cache only the JSON catalog; plugins in URL-sourced catalogs cannot use relative string sources like `\"./plugins/foo\"`.\n\n## Catalog format (marketplace.json)\n\nA marketplace catalog lives at `.claude-plugin/marketplace.json` in the repository root:\n\n```json\n{\n  \"$schema\": \"https://anthropic.com/claude-code/marketplace.schema.json\",\n  \"name\": \"my-marketplace\",\n  \"owner\": {\n    \"name\": \"Your Name\",\n    \"email\": \"you@example.com\"\n  },\n  \"metadata\": {\n    \"description\": \"A collection of plugins\",\n    \"version\": \"1.0.0\",\n    \"pluginRoot\": \"plugins\"\n  },\n  \"plugins\": [\n    {\n      \"name\": \"my-plugin\",\n      \"description\": \"What this plugin does\",\n      \"source\": \"./my-plugin\",\n      \"category\": \"development\",\n      \"homepage\": \"https://github.com/you/my-plugin\"\n    }\n  ]\n}\n```\n\n### Required fields\n\n| Field        | Description                                                                                                      |\n| ------------ | ---------------------------------------------------------------------------------------------------------------- |\n| `name`       | Marketplace name. Lowercase alphanumeric, hyphens, and dots. Must start and end with alphanumeric. Max 64 chars. |\n| `owner.name` | Marketplace owner name                                                                                           |\n| `plugins`    | Array of plugin entries                                                                                          |\n\nTop-level `metadata.description`, `metadata.version`, and `metadata.pluginRoot` are optional. When `metadata.pluginRoot` is set, it is prepended to relative plugin `source` paths.\n\n### Plugin entry fields\n\n| Field         | Required | Description                                                                             |\n| ------------- | -------- | --------------------------------------------------------------------------------------- |\n| `name`        | yes      | Plugin name (same rules as marketplace name)                                            |\n| `source`      | yes      | Where to find the plugin (see below)                                                    |\n| `description` | no       | Short description                                                                       |\n| `version`     | no       | Version string; install version falls back to plugin manifest, source SHA, then `0.0.0` |\n| `author`      | no       | `{ name, email? }`                                                                      |\n| `homepage`    | no       | URL                                                                                     |\n| `repository`  | no       | Repository URL/string                                                                   |\n| `license`     | no       | License string                                                                          |\n| `keywords`    | no       | Array of string keywords                                                                |\n| `category`    | no       | Category string (e.g. `development`, `productivity`, `security`)                        |\n| `tags`        | no       | Array of string tags                                                                    |\n| `strict`      | no       | Boolean                                                                                 |\n| `commands`    | no       | Slash commands provided                                                                 |\n| `agents`      | no       | Agents provided                                                                         |\n| `hooks`       | no       | Hook definitions                                                                        |\n| `mcpServers`  | no       | MCP server definitions                                                                  |\n| `lspServers`  | no       | LSP server definitions or path; copied to `.lsp.json` on install                        |\n\n### Plugin source formats\n\nThe `source` field supports these formats. String sources must start with `./` and are resolved inside the marketplace root, after optional `metadata.pluginRoot` is prepended:\n\n**Relative path** (within the marketplace repo):\n\n```json\n\"source\": \"./my-plugin\"\n```\n\n**Git repository URL**:\n\n```json\n\"source\": {\n  \"source\": \"url\",\n  \"url\": \"https://github.com/org/repo.git\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**GitHub shorthand**:\n\n```json\n\"source\": {\n  \"source\": \"github\",\n  \"repo\": \"org/repo\",\n  \"ref\": \"main\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**Git subdirectory** (monorepo):\n\n```json\n\"source\": {\n  \"source\": \"git-subdir\",\n  \"url\": \"https://github.com/org/monorepo.git\",\n  \"path\": \"plugins/my-plugin\",\n  \"ref\": \"main\",\n  \"sha\": \"abc123...\"\n}\n```\n\n**npm package** (parsed but not installable yet):\n\n```json\n\"source\": {\n  \"source\": \"npm\",\n  \"package\": \"@scope/my-plugin\",\n  \"version\": \"1.0.0\"\n}\n```\n\nCurrent installer behavior rejects npm marketplace sources with `npm plugin sources are not yet supported`; use relative, GitHub, URL, or git-subdir sources.\n\n## On-disk layout\n\n```\n~/.omp/\n  marketplaces.json              # Registry of added marketplaces\n  plugins/\n    installed_plugins.json       # User-scoped marketplace plugins (version: 2)\n    cache/\n      marketplaces/<name>/       # Cached marketplace clone/catalog\n      plugins/<marketplace>___<plugin>___<version>/  # Cached plugin directories\n\n<project>/.omp/\n  plugins/\n    installed_plugins.json       # Project-scoped marketplace plugins (version: 2)\n```\n\n## Naming rules\n\nMarketplace and plugin names must:\n\n- Start and end with a lowercase letter or digit\n- Contain only lowercase letters, digits, hyphens, and dots\n- Be at most 64 characters\n\nPlugin IDs (`name@marketplace`) must be at most 128 characters total.\n\nValid examples: `my-plugin`, `code-review`, `wordpress.com`, `ai-firstify`\nInvalid examples: `-bad`, `bad-`, `.bad`, `Bad`, `under_score`\n",
 	"mcp-config.md": "# MCP configuration in OMP\n\nThis guide explains how to add, edit, and validate MCP servers for the OMP coding agent.\n\nSource of truth in code:\n\n- Runtime config types: `packages/coding-agent/src/mcp/types.ts`\n- Config writer: `packages/coding-agent/src/mcp/config-writer.ts`\n- Loader + validation: `packages/coding-agent/src/mcp/config.ts`\n- Standalone `mcp.json` discovery: `packages/coding-agent/src/discovery/mcp-json.ts`\n- Schema: `packages/coding-agent/src/config/mcp-schema.json`\n\n## Preferred config locations\n\nOMP can discover MCP servers from multiple tools (`.claude/`, `.cursor/`, `.vscode/`, `opencode.json`, and more), but for OMP-native configuration you should usually use one of these primary files:\n\n- Project: `.omp/mcp.json`\n- User: `~/.omp/agent/mcp.json`\n\nThe native provider also reads `.omp/.mcp.json` and `~/.omp/agent/.mcp.json` for compatibility, but OMP writes to the primary `mcp.json` paths above.\n\nOMP also accepts fallback standalone files in the project root:\n\n- `mcp.json`\n- `.mcp.json`\n\nUse `.omp/mcp.json` or `~/.omp/agent/mcp.json` when you want OMP to own the configuration. Use root `mcp.json` / `.mcp.json` only when you want a portable fallback file that other MCP clients may also read.\n\n## Add a schema reference\n\nAdd this line at the top of the file for editor autocomplete and validation:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {}\n}\n```\n\nOMP now writes this automatically when `/mcp add`, `/mcp enable`, `/mcp disable`, `/mcp reauth`, or other config-writing flows create or update an OMP-managed MCP file.\n\n## File shape\n\nOMP supports this top-level structure:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"server-name\": {\n      \"type\": \"stdio\",\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"some-mcp-server\"]\n    }\n  },\n  \"disabledServers\": [\"server-name\"]\n}\n```\n\nTop-level keys:\n\n- `$schema` — optional JSON Schema URL for tooling\n- `mcpServers` — map of server name to server config\n- `disabledServers` — user-level denylist used to turn off discovered servers by name; runtime loading reads this list from `~/.omp/agent/mcp.json`\n\nServer names must match `^[a-zA-Z0-9_.-]{1,100}$`.\n\n## Supported server fields\n\nShared fields for every transport:\n\n- `enabled?: boolean` — skip this server when `false`\n- `timeout?: number` — MCP request timeout in milliseconds; `0` disables client-side MCP timeouts\n- `auth?: { ... }` — auth metadata used by OMP for OAuth/API-key flows\n- `oauth?: { ... }` — explicit OAuth client settings used during auth/reauth\n\nSet `OMP_MCP_TIMEOUT_MS=0` to disable the client-side timeout for every MCP server in the current process. Set it to a positive millisecond value, such as `OMP_MCP_TIMEOUT_MS=120000`, to apply one global timeout without editing each server entry.\n\n### `stdio` transport\n\n`stdio` is the default when `type` is omitted.\n\nRequired:\n\n- `command: string`\n\nOptional:\n\n- `type?: \"stdio\"`\n- `args?: string[]`\n- `env?: Record<string, string>`\n- `cwd?: string`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol/server-filesystem\",\n        \"/Users/alice/projects\",\n        \"/Users/alice/Documents\"\n      ]\n    }\n  }\n}\n```\n\nThis follows the official Filesystem MCP server package (`@modelcontextprotocol/server-filesystem`).\n\n### `http` transport\n\nRequired:\n\n- `type: \"http\"`\n- `url: string`\n\nOptional:\n\n- `headers?: Record<string, string>`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\"\n    }\n  }\n}\n```\n\nThis matches GitHub's hosted GitHub MCP server endpoint.\n\n### `sse` transport\n\nRequired:\n\n- `type: \"sse\"`\n- `url: string`\n\nOptional:\n\n- `headers?: Record<string, string>`\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"legacy-remote\": {\n      \"type\": \"sse\",\n      \"url\": \"https://example.com/mcp/sse\"\n    }\n  }\n}\n```\n\n`sse` is still supported for compatibility, but the MCP spec now prefers Streamable HTTP (`type: \"http\"`) for new servers.\n\n## Auth fields\n\nOMP understands two auth-related objects.\n\n### `auth`\n\n```json\n{\n  \"type\": \"oauth\" | \"apikey\",\n  \"credentialId\": \"optional-stored-credential-id\",\n  \"tokenUrl\": \"optional-token-endpoint\",\n  \"clientId\": \"optional-client-id\",\n  \"clientSecret\": \"optional-client-secret\"\n}\n```\n\nUse this when OMP should remember how to rehydrate credentials for a server.\n\n### `oauth`\n\n```json\n{\n  \"clientId\": \"...\",\n  \"clientSecret\": \"...\",\n  \"redirectUri\": \"...\",\n  \"callbackPort\": 3334,\n  \"callbackPath\": \"/oauth/callback\"\n}\n```\n\nUse this when the MCP server requires explicit OAuth client settings.\n\nSlack is the clearest current example. Slack's MCP server is hosted at `https://mcp.slack.com/mcp`, uses Streamable HTTP, and requires confidential OAuth with your Slack app's client credentials.\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"slack\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.slack.com/mcp\",\n      \"oauth\": {\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      },\n      \"auth\": {\n        \"type\": \"oauth\",\n        \"tokenUrl\": \"https://slack.com/api/oauth.v2.user.access\",\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      }\n    }\n  }\n}\n```\n\nRelevant Slack endpoints from Slack's docs:\n\n- MCP endpoint: `https://mcp.slack.com/mcp`\n- Authorization endpoint: `https://slack.com/oauth/v2_user/authorize`\n- Token endpoint: `https://slack.com/api/oauth.v2.user.access`\n\n## Common copy-paste examples\n\n### Filesystem server via stdio\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"filesystem\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@modelcontextprotocol/server-filesystem\",\n        \"/absolute/path/one\",\n        \"/absolute/path/two\"\n      ]\n    }\n  }\n}\n```\n\n### GitHub hosted server via HTTP\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\"\n    }\n  }\n}\n```\n\n### GitHub local server via Docker\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"github\": {\n      \"command\": \"docker\",\n      \"args\": [\n        \"run\",\n        \"-i\",\n        \"--rm\",\n        \"-e\",\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\",\n        \"ghcr.io/github/github-mcp-server\"\n      ],\n      \"env\": {\n        \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"\n      }\n    }\n  }\n}\n```\n\nThis matches GitHub's official local Docker image `ghcr.io/github/github-mcp-server`.\n\n### Slack hosted server via OAuth\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"mcpServers\": {\n    \"slack\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.slack.com/mcp\",\n      \"oauth\": {\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      },\n      \"auth\": {\n        \"type\": \"oauth\",\n        \"tokenUrl\": \"https://slack.com/api/oauth.v2.user.access\",\n        \"clientId\": \"YOUR_SLACK_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_SLACK_CLIENT_SECRET\"\n      }\n    }\n  }\n}\n```\n\n## Secrets and variable resolution\n\nThis is the part that usually trips people up.\n\n### Discovery-time `${...}` expansion\n\nOMP expands `${VAR}` and `${VAR:-default}` placeholders while discovering MCP configs from OMP-native files and standalone fallback files. Expansion applies recursively to string values in `command`, `args`, `env`, `cwd`, `url`, `headers`, `auth`, and `oauth`; unresolved placeholders remain literal strings.\n\nExample:\n\n```json\n{\n  \"mcpServers\": {\n    \"github\": {\n      \"type\": \"http\",\n      \"url\": \"https://api.githubcopilot.com/mcp/\",\n      \"headers\": {\n        \"Authorization\": \"Bearer ${GITHUB_TOKEN}\"\n      }\n    }\n  }\n}\n```\n\n### Pre-connect env/header resolution\n\nBefore OMP launches a stdio server or makes an HTTP/SSE request, it resolves stdio `env` values and HTTP/SSE `headers` values like this:\n\n1. If a value starts with `!`, OMP runs the rest as a shell command with a 10s timeout and uses trimmed stdout.\n2. If the command fails, times out, or prints only whitespace, that `env`/`headers` entry is omitted.\n3. Otherwise OMP checks whether the value names an environment variable.\n4. If that environment variable is set to a non-empty value, OMP uses the environment value; otherwise it uses the string literally.\n\nExamples:\n\n```json\n{\n  \"env\": {\n    \"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"\n  },\n  \"headers\": {\n    \"X-MCP-Insiders\": \"true\"\n  }\n}\n```\n\nThat means this is valid and convenient for local secrets:\n\n- `\"GITHUB_PERSONAL_ACCESS_TOKEN\": \"GITHUB_PERSONAL_ACCESS_TOKEN\"` → copy from the current shell environment\n- `\"Authorization\": \"Bearer hardcoded-token\"` → use the literal value\n- `\"Authorization\": \"!printf 'Bearer %s' \\\"$GITHUB_TOKEN\\\"\"` → build the header from a command\n\n## `disabledServers`\n\n`disabledServers` is read from the user config file (`~/.omp/agent/mcp.json`) when a server is discovered from any source and you want OMP to ignore it without editing that other tool's config.\n\nExample:\n\n```json\n{\n  \"$schema\": \"https://raw.githubusercontent.com/can1357/oh-my-pi/main/packages/coding-agent/src/config/mcp-schema.json\",\n  \"disabledServers\": [\"github\", \"slack\"]\n}\n```\n\n## `/mcp add` vs editing JSON directly\n\nUse `/mcp add` when you want guided setup.\n\nUse direct JSON editing when:\n\n- you need a transport or auth option the wizard does not prompt for yet\n- you want to paste a server definition from another MCP client\n- you want schema-backed validation in your editor\n\nAfter editing, use:\n\n- `/mcp reload` to rediscover and reconnect servers in the current session\n- `/mcp list` to see which config file a server came from\n- `/mcp test <name>` to test a single server\n- `/mcp reconnect <name>` to reconnect one server without rediscovering all configs\n- `/mcp resources`, `/mcp prompts`, and `/mcp notifications` to inspect non-tool MCP capabilities\n\n## Validation rules OMP enforces\n\nFrom `validateServerConfig()` in `packages/coding-agent/src/mcp/config.ts`:\n\n- `stdio` requires `command`\n- `http` and `sse` require `url`\n- a server cannot set both `command` and `url`\n- unknown `type` values are rejected\n\nPractical implications:\n\n- Omitting `type` means `stdio`\n- If you paste a remote server config and forget `\"type\": \"http\"`, OMP will treat it as `stdio` and complain that `command` is missing\n- `sse` remains valid for compatibility, but new hosted servers should usually be configured as `http`\n\n## Discovery and precedence\n\nOMP does not merge duplicate server definitions across files. Discovery providers are prioritized, and the higher-priority definition wins. Separately, `disabledServers` from `~/.omp/agent/mcp.json` can suppress a discovered server by name.\n\nIn practice:\n\n- prefer `.omp/mcp.json` or `~/.omp/agent/mcp.json` when you want an OMP-specific override\n- keep server names unique across tools when possible\n- use `disabledServers` in the user config when a third-party config keeps reintroducing a server you do not want\n\n## Troubleshooting\n\n### `Server \"name\": stdio server requires \"command\" field`\n\nYou probably omitted `type: \"http\"` on a remote server.\n\n### `Server \"name\": both \"command\" and \"url\" are set`\n\nPick one transport. OMP treats `command` as stdio and `url` as http/sse.\n\n### `/mcp add` worked but the server still does not connect\n\nThe JSON is valid, but the server may still be unreachable. Use `/mcp test <name>` and check whether:\n\n- the binary or Docker image exists\n- required environment variables are set\n- the remote URL is reachable\n- the OAuth or API token is valid\n\n### The server exists in another tool's config but not in OMP\n\nRun `/mcp list`. OMP discovers many third-party MCP files, but project-level loading can also be disabled via the `mcp.enableProjectConfig` setting, and a user-level `disabledServers` entry can suppress a server by name.\n\n## References\n\n- MCP transport spec: https://modelcontextprotocol.io/specification/2025-03-26/basic/transports\n- Filesystem server package: https://www.npmjs.com/package/@modelcontextprotocol/server-filesystem\n- GitHub MCP server: https://github.com/github/github-mcp-server\n- Slack MCP server docs: https://docs.slack.dev/ai/slack-mcp-server/\n",
 	"mcp-protocol-transports.md": "# MCP Protocol and Transport Internals\n\nThis document describes how coding-agent implements MCP JSON-RPC messaging and how protocol concerns are split from transport concerns.\n\n## Scope\n\nCovers:\n\n- JSON-RPC request/response and notification flow\n- Server-to-client request handling (`ping`, `roots/list`)\n- Request correlation and lifecycle for stdio and HTTP/SSE transports\n- Timeout, cancellation, and auth-refresh behavior\n- Error propagation and malformed payload handling\n- Transport selection boundaries (`stdio` vs `http`/`sse`)\n- Which reconnect/retry responsibilities are transport-level vs manager/tool-bridge-level\n\nDoes not cover extension authoring UX or command UI.\n\n## Implementation files\n\n- [`src/mcp/types.ts`](../packages/coding-agent/src/mcp/types.ts)\n- [`src/mcp/transports/stdio.ts`](../packages/coding-agent/src/mcp/transports/stdio.ts)\n- [`src/mcp/transports/http.ts`](../packages/coding-agent/src/mcp/transports/http.ts)\n- [`src/mcp/transports/index.ts`](../packages/coding-agent/src/mcp/transports/index.ts)\n- [`src/mcp/json-rpc.ts`](../packages/coding-agent/src/mcp/json-rpc.ts)\n- [`src/mcp/client.ts`](../packages/coding-agent/src/mcp/client.ts)\n- [`src/mcp/manager.ts`](../packages/coding-agent/src/mcp/manager.ts)\n\n## Layer boundaries\n\n### Protocol layer (JSON-RPC + MCP methods)\n\n- Message shapes are defined in `types.ts` (`JsonRpcRequest`, `JsonRpcNotification`, `JsonRpcResponse`, `JsonRpcMessage`).\n- MCP client logic (`client.ts`) decides method order and session handshake:\n  1. `initialize` request\n  2. for HTTP/SSE transports, start the optional background SSE listener after the initialize response has established any session id\n  3. `notifications/initialized` notification\n  4. method calls like `tools/list`, `tools/call`\n\n### Transport layer (`MCPTransport`)\n\n`MCPTransport` abstracts delivery and lifecycle:\n\n- `request(method, params, options?) -> Promise<T>`\n- `notify(method, params?) -> Promise<void>`\n- `close()`\n- `connected`\n- optional callbacks: `onClose`, `onError`, `onNotification`, `onRequest`\n\nTransport implementations own framing and I/O details:\n\n- `StdioTransport`: newline-delimited JSON over subprocess stdio\n- `HttpTransport`: JSON-RPC over HTTP POST, with optional SSE responses/listening\n\n### Manager/client wiring\n\n`connectToServer()` always installs an `onRequest` handler for standard server-to-client requests. `MCPManager` installs notification handlers, OAuth refresh hooks for HTTP OAuth servers, and `onClose` reconnect handling for managed connections.\n\n## Transport selection\n\n`client.ts:createTransport()` chooses transport from config:\n\n- `type` omitted or `\"stdio\"` -> `createStdioTransport`\n- `\"http\"` or `\"sse\"` -> `createHttpTransport`\n\n`\"sse\"` is treated as an HTTP transport variant (same class), not a separate transport implementation.\n\n## JSON-RPC message flow and correlation\n\n## Request IDs\n\nEach transport generates per-request IDs with `Snowflake.next()`. IDs are transport-local correlation tokens.\n\n## Stdio correlation path\n\n- Outbound request is serialized as one JSON object + `\\n`.\n- `#pendingRequests: Map<id, {resolve,reject}>` stores in-flight requests.\n- Read loop parses JSONL from stdout and calls `#handleMessage`.\n- If inbound message has matching `id`, request resolves/rejects.\n- If inbound message has `method` and no `id`, treated as notification and sent to `onNotification`.\n- If inbound message has both `method` and `id`, treated as a server-to-client request and answered through `onRequest`; without a handler the transport replies with JSON-RPC `-32601 Method not found`.\n\nUnknown response IDs are ignored (no rejection, no error callback).\n\n## HTTP correlation path\n\n- Outbound request is HTTP `POST` with JSON body and generated `id`.\n- Non-SSE response path: parse one JSON-RPC response and return `result`/throw on `error`.\n- SSE response path (`Content-Type: text/event-stream`): stream events, return first message whose `id` matches expected request ID and has `result` or `error`.\n- SSE messages with `method` and no `id` are treated as notifications.\n- SSE messages with both `method` and `id` are treated as server-to-client requests and answered with a POSTed JSON-RPC response.\n\nIf SSE stream ends before matching response, request fails with `No response received for request ID ...`. After the matching response is captured, the transport drains remaining SSE messages in the background.\n\n## Notifications\n\nClient emits JSON-RPC notifications via `transport.notify(...)`.\n\n- Stdio: writes notification frame to stdin (`jsonrpc`, `method`, optional `params`) plus newline.\n- HTTP: sends POST body without `id`; success accepts `2xx` or `202 Accepted`.\n\nServer-initiated notifications are surfaced through transport `onNotification`; `MCPManager` consumes known MCP list/update notifications and can forward all notifications through its own callback.\n\n## Stdio transport internals\n\n## Lifecycle and state transitions\n\n- Initial: `connected=false`, `process=null`, pending map empty\n- `connect()`:\n  - spawn subprocess with configured command/args/env/cwd\n  - mark connected\n  - start stdout read loop (`readJsonl`)\n  - start stderr loop (read/discard; currently silent)\n- `close()`:\n  - mark disconnected\n  - reject all pending requests (`Transport closed`)\n  - kill subprocess\n  - await read loop shutdown\n  - emit `onClose`\n\nIf read loop exits unexpectedly, `finally` triggers `#handleClose()` which performs the same pending-request rejection and close callback.\n\n## Timeout and cancellation\n\nPer request:\n\n- timeout defaults to `config.timeout ?? 30000`\n- optional `AbortSignal` from caller\n- abort and timeout both reject the pending promise and clean map entry\n\nCancellation is local only: transport does not send protocol-level cancellation notification to the server.\n\n## Malformed payload handling\n\nIn read loop:\n\n- each parsed JSONL line is passed to `#handleMessage` in `try/catch`\n- malformed/invalid message handling exceptions are dropped (`Skip malformed lines` comment)\n- loop continues, so one bad message does not kill the connection\n\nIf the underlying stream parser throws, `onError` is invoked (when still connected), then connection closes.\n\n## Disconnect/failure behavior\n\nWhen process exits or stream closes:\n\n- all in-flight requests are rejected with `Transport closed`\n- no automatic restart or reconnect\n- higher layers must reconnect by creating a new transport\n\n## Backpressure/streaming notes\n\n- Outbound writes use `stdin.write()` + `flush()` without awaiting drain semantics.\n- There is no explicit queue or high-watermark management in transport.\n- Inbound processing is stream-driven (`for await` over `readJsonl`), one parsed message at a time.\n\n## HTTP/SSE transport internals\n\n## Lifecycle and connection semantics\n\nHTTP transport has logical connection state, but request path is stateless per HTTP call:\n\n- `connect()` sets `connected=true` (no socket/session handshake)\n- optional server session tracking via `Mcp-Session-Id` header\n- `close()` optionally sends `DELETE` with `Mcp-Session-Id`, aborts SSE listener, emits `onClose`\n\nSo `connected` means \"transport usable\", not \"persistent stream established\".\n\n## Session header behavior\n\n- On POST response, if `Mcp-Session-Id` header is present, transport stores it.\n- Subsequent requests/notifications include `Mcp-Session-Id`.\n- `close()` tries to terminate server session with HTTP DELETE; termination failures are ignored.\n\n## Timeout, cancellation, and auth refresh\n\nFor `request()`:\n\n- timeout uses `AbortController` (`config.timeout ?? 30000`)\n- external signal, if provided, is merged via `AbortSignal.any([...])`\n- AbortError handling distinguishes caller abort vs timeout\n\nFor `notify()`:\n\n- timeout uses an internal `AbortController` (`config.timeout ?? 30000`)\n- there is no external abort option on the transport interface\n\nFor HTTP OAuth configs managed by `MCPManager`, outbound requests and best-effort server-request responses retry once on `HTTP 401`/`403` if token refresh returns replacement headers.\n\n## HTTP error propagation\n\nOn non-OK response:\n\n- response text is included in thrown error (`HTTP <status>: <text>`)\n- if present, auth hints from `WWW-Authenticate` and `Mcp-Auth-Server` are appended\n\nOn JSON-RPC error object:\n\n- throws `MCP error <code>: <message>`\n\nMalformed JSON body (`response.json()` failure) propagates as parse exception.\n\n## SSE behavior and modes\n\nTwo SSE paths exist:\n\n1. **Per-request SSE response** (`#parseSSEResponse`)\n   - used when POST response content type is `text/event-stream`\n   - consumes stream until matching response id found\n   - can process interleaved notifications during same stream\n\n2. **Background SSE listener** (`startSSEListener()`)\n   - optional GET listener for server-initiated notifications and server-to-client requests\n   - `connectToServer()` starts it for HTTP/SSE transports after `initialize` and before `notifications/initialized`\n   - listener startup waits up to one second, or less for very small request timeouts; `timeout: 0` / `OMP_MCP_TIMEOUT_MS=0` disables that startup deadline\n   - if GET returns `405`, another non-OK status, no body, or times out, listener silently disables itself\n\n## Malformed payload and disconnect handling\n\nSSE JSON parsing errors bubble out of `readSseJson` and reject request/listener.\n\n- Request SSE parse errors reject the active request.\n- Background listener errors trigger `onError` (except AbortError), and an established listener ending while still connected triggers `onClose` so the manager can reconnect.\n- Transport does not restart the listener itself; managed connections may reconnect through manager `onClose` handling.\n\n## `json-rpc.ts` utility vs transport abstraction\n\n`src/mcp/json-rpc.ts` provides `callMCP()` and `parseSSE()` helpers for direct HTTP MCP calls (used by Exa integration), not the `MCPTransport` abstraction used by `MCPClient`/`MCPManager`.\n\nNotable differences from `HttpTransport`:\n\n- parses entire response text first, then extracts first `data: ` line (`parseSSE`), with JSON fallback\n- no request timeout management, no abort API, no session-id handling, no transport lifecycle\n- returns raw JSON-RPC envelope object\n\nThis path is lightweight but less robust than full transport implementation.\n\n## Retry/reconnect responsibilities\n\n## Transport-level\n\nCurrent transport implementations do **not**:\n\n- retry ordinary failed requests, except the HTTP transport's single OAuth-refresh retry when `onAuthError` is wired\n- reconnect after stdio process exit\n- reconnect SSE listeners by themselves\n- resend in-flight requests after disconnect\n\nThey fail fast and propagate errors.\n\n## Manager/tool-bridge level\n\n`MCPManager` wires `transport.onClose` for managed connections and runs `reconnectServer(name)` when a transport closes unexpectedly. Reconnect tears down the stale connection, re-resolves auth/config values, retries with backoff (`500`, `1000`, `2000`, `4000` ms), reloads tools, and preserves stale tools while reconnecting.\n\n`MCPTool` and `DeferredMCPTool` also attempt one reconnect + retry for retriable connection errors during a tool call. This is tool availability recovery, not transport-level retry.\n\n## Failure scenarios summary\n\n- **Malformed stdio message line**: dropped; stream continues.\n- **Stdio stream/process ends**: transport closes; pending requests rejected as `Transport closed`; manager-managed connections trigger reconnect.\n- **HTTP non-2xx**: request/notify throws HTTP error; managed OAuth requests can refresh auth and retry once on 401/403.\n- **Invalid JSON response**: parse exception propagated.\n- **SSE ends without matching id**: request fails with `No response received for request ID ...`.\n- **Timeout**: transport-specific timeout error.\n- **Caller abort**: AbortError/reason propagated from caller signal where the method accepts one.\n\n## Practical boundary rule\n\nIf the concern is message shape, id correlation, or MCP method ordering, it belongs to protocol/client logic.\n\nIf the concern is framing (JSONL vs HTTP/SSE), stream parsing, fetch/spawn lifecycle, timeout clocks, or connection teardown, it belongs to transport implementation.\n",
@@ -45,7 +46,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"porting-from-pi-mono.md": "# Porting From pi-mono: A Practical Merge Guide\n\nThis guide is a repeatable checklist for porting changes from pi-mono into this repo.\nUse it for any merge: single file, feature branch, or full release sync.\n\n## Last Sync Point (historical upstream marker)\n\n**Commit:** `b21b42d032919de2f2e6920a76fa9a37c3920c0a`\n**Date:** 2026-03-22\n\nUpdate this section after each sync; do not reuse the previous range. This commit is an upstream pi-mono marker and may not exist in this repo's local object database.\n\nWhen starting a new sync, generate patches from this commit forward in a pi-mono checkout or remote that contains the commit:\n\n```bash\ngit format-patch b21b42d032919de2f2e6920a76fa9a37c3920c0a..HEAD --stdout > changes.patch\n```\n\n## 0) Define the scope\n\n- Identify the upstream reference (commit, tag, or PR).\n- List the packages or folders you plan to touch.\n- Decide which features are in-scope and which are intentionally skipped.\n\n## 1) Bring code over safely\n\n- Prefer a clean, focused diff rather than a wholesale copy.\n- Avoid copying built artifacts or generated files.\n- If upstream added new files, add them explicitly and review contents.\n\n## 2) Match import extension conventions\n\nMost runtime TypeScript sources omit `.js` in internal imports, but several current entrypoints and tool modules keep `.js` for ESM/runtime compatibility. Follow the surrounding file and package export style; do not blanket-strip or blanket-add extensions.\n\n- In `packages/coding-agent` runtime sources, prefer extensionless internal imports when the surrounding module does, but preserve existing `.js` imports in files that already require them.\n- In `packages/tui/test` and `packages/natives/bench`, keep `.js` where surrounding files already use it.\n- Keep real file extensions when required by tooling or import assertions (e.g., `.json`, `.css`, `.md` text embeds).\n- Example: `import { x } from \"./foo.js\";` → `import { x } from \"./foo\";` only when that package/file convention is extensionless.\n\n## 3) Replace import scopes\n\nUpstream uses different package scopes. Replace them consistently.\n\n- Replace old scopes with the local scope used here.\n- Examples (adjust to match the actual packages you are porting):\n  - `@mariozechner/pi-coding-agent` → `@oh-my-pi/pi-coding-agent`\n  - `@mariozechner/pi-agent-core` → `@oh-my-pi/pi-agent-core`\n  - `@mariozechner/pi-tui` → `@oh-my-pi/pi-tui`\n  - `@mariozechner/pi-ai` → `@oh-my-pi/pi-ai`\n  - `@mariozechner/pi-utils` → `@oh-my-pi/pi-utils`\n- Some upstream packages publish under the `@earendil-works/*` scope instead of `@mariozechner/*`. Map it the same way (`@earendil-works/pi-coding-agent` → `@oh-my-pi/pi-coding-agent`, and so on).\n- The bare `typebox` package is not an `@oh-my-pi/*` scope; do not rewrite it as one. See the Extensions divergence in section 15 for how tool-parameter schemas map.\n\n## 4) Use Bun APIs where they improve on Node\n\nWe run on Bun, but the current source intentionally mixes Bun APIs with small Node standard-library APIs. Replace Node APIs only when Bun provides a clearer, safer, or simpler implementation; do not mechanically rewrite every Node import.\n\n**Prefer replacing when porting new code:**\n\n- Process spawning: prefer Bun Shell `$` for simple commands; use `Bun.spawn`/`Bun.spawnSync` for streaming or process control. Keep existing `child_process` only where its exact semantics are needed.\n- HTTP clients: `node-fetch`, `axios` → native `fetch`\n- SQLite: `better-sqlite3` → `bun:sqlite`\n- Env loading: `dotenv` → Bun loads `.env` automatically\n- Runtime text/assets: prefer Bun imports such as `with { type: \"text\" }` or `Bun.file()` over copy steps or bundled fallback file reads.\n\n**DO NOT replace (these work fine in Bun):**\n\n- `os.homedir()` — do NOT replace with `Bun.env.HOME` or literal `\"~\"`\n- `os.tmpdir()` — do NOT replace with `Bun.env.TMPDIR || \"/tmp\"` or hardcoded paths\n- `fs.mkdtempSync()` — do NOT replace with manual path construction\n- `path.join()`, `path.resolve()`, etc. — these are fine\n\n**Import style:** Use the `node:` prefix for Node standard-library imports. Namespace imports are common, but named imports are acceptable where the surrounding code already uses them.\n\n**Additional Bun conventions:**\n\n- Prefer Bun Shell `$` for short, non-streaming commands; use `Bun.spawn` only when you need streaming I/O or process control.\n- Use `Bun.file()`/`Bun.write()` for simple files and `node:fs/promises` for directory-oriented operations. Existing synchronous `node:fs` calls are acceptable when the calling flow is intentionally synchronous.\n- Avoid `Bun.file().exists()` checks; use `isEnoent` handling in try/catch.\n- Prefer `Bun.sleep(ms)` over `setTimeout` wrappers.\n\n**Wrong:**\n\n```typescript\n// BROKEN: env vars may be undefined, \"~\" is not expanded\nconst home = Bun.env.HOME || \"~\";\nconst tmp = Bun.env.TMPDIR || \"/tmp\";\n```\n\n**Correct:**\n\n```typescript\nimport * as os from \"node:os\";\nimport * as fs from \"node:fs\";\nimport * as path from \"node:path\";\n\nconst configDir = path.join(os.homedir(), \".config\", \"myapp\");\nconst tempDir = fs.mkdtempSync(path.join(os.tmpdir(), \"myapp-\"));\n```\n\n## 5) Prefer Bun embeds (no copying)\n\nDo not add new runtime asset copy steps. Keep assets in repo and prefer Bun embeds/imports; preserve existing explicit generation workflows such as `packages/coding-agent/src/export/html/template.generated.ts`.\n\n- If upstream copies assets into a dist folder, replace with Bun-friendly embeds.\n- Prompts are static `.md` files; use Bun text imports (`with { type: \"text\" }`) and Handlebars instead of inline prompt strings.\n- Use `import.meta.dir` + `Bun.file` to load adjacent non-text resources.\n- Keep assets in-repo and let the bundler include them.\n- Eliminate copy scripts unless the user explicitly requests them or the package already has an intentional generation step.\n- If upstream reads a bundled fallback file at runtime, replace filesystem reads with a Bun text embed import unless the current package already uses a generated asset pipeline.\n  - Example (Codex instructions fallback):\n    - `const FALLBACK_PROMPT_PATH = join(import.meta.dir, \"codex-instructions.md\");` -> removed\n    - `import FALLBACK_INSTRUCTIONS from \"./codex-instructions.md\" with { type: \"text\" };`\n    - Use `return FALLBACK_INSTRUCTIONS;` instead of `readFileSync(FALLBACK_PROMPT_PATH, \"utf8\")`\n\n## 6) Port `package.json` carefully\n\nTreat `package.json` as a contract. Merge intentionally.\n\n- Keep existing `name`, `version`, `type`, `exports`, and `bin` unless the port requires changes.\n- Replace npm/node scripts with Bun equivalents (e.g., `bun check`, `bun test`).\n- Ensure dependencies use the correct scope.\n- Do not downgrade dependencies to fix type errors; upgrade instead.\n- Validate workspace package links and `peerDependencies`.\n\n## 7) Align code style and tooling\n\n- Keep existing formatting conventions.\n- Do not introduce `any` unless required.\n- Avoid dynamic imports unless they are required for optional dependencies, startup cost, or runtime-only modules; prefer top-level imports otherwise.\n- Never build prompts in code; prompts are static `.md` files rendered with Handlebars.\n- In `packages/coding-agent`, use `logger` from `@oh-my-pi/pi-utils` for internal/runtime logging; CLI command files may use `console.*` for intentional user-facing output.\n- Use `Promise.withResolvers()` instead of `new Promise((resolve, reject) => ...)`.\n- Prefer ES `#` private fields for new encapsulated state. Constructor parameter properties already exist in current code and are acceptable; do not churn unrelated access modifiers while porting.\n- Prefer existing helpers and utilities over new ad-hoc code.\n  Preserve Bun-first infrastructure changes already made in this repo:\n  - Runtime is Bun (no Node entry points for the main CLI).\n  - Package manager is Bun (no npm lockfiles).\n  - Heavy Node APIs should not be introduced casually; current source still uses selected Node APIs (`node:crypto`, `node:readline`, synchronous `node:fs`, and `child_process`) where they fit provider, CLI, or process-control semantics.\n  - Lightweight Node APIs (`os.homedir`, `os.tmpdir`, `fs.mkdtempSync`, `path.*`) are kept.\n  - CLI shebangs use `bun` (not `node`, not `tsx`).\n  - TypeScript packages generally use source files directly; `@oh-my-pi/pi-natives` exports generated native bindings from `packages/natives/native`.\n  - CI workflows run Bun for install/check/test.\n\n## 8) Remove old compatibility layers\n\nUnless requested, remove upstream compatibility shims.\n\n- Delete old APIs that were replaced.\n- Update all call sites to the new API directly.\n- Do not keep `*_v2` or parallel versions.\n\n## 9) Update docs and references\n\n- Replace pi-mono repo links where appropriate.\n- Update examples to use Bun and correct package scopes.\n- Ensure README instructions still match the current repo behavior.\n\n## 10) Validate the port\n\nRun the standard checks after changes:\n\n- `bun check`\n\nIf the repo already has failing checks unrelated to your changes, call that out.\nTests use Bun's runner (not Vitest), but only run `bun test` when explicitly requested.\n\n## 11) Protect improved features (regression trap list)\n\nIf you already improved behavior locally, treat those as **non‑negotiable**. Before porting, write down\nthe improvements and add explicit checks so they don’t get lost in the merge.\n\n- **Freeze the expected behavior**: add a short “before/after” note for each improvement (inputs, outputs,\n  defaults, edge cases). This prevents silent rollback.\n- **Map old → new APIs**: if upstream renamed concepts (hooks → extensions, custom tools → tools, etc.),\n  ensure every old entry point still wires through. One missed flag or export equals lost functionality.\n- **Verify exports**: check `package.json` `exports`, public types, and barrel files. Upstream ports often\n  forget to re-export local additions.\n- **Cover non‑happy paths**: if you fixed error handling, timeouts, or fallback logic, add a test or at\n  least a manual checklist that exercises those paths.\n- **Check defaults and config merge order**: improvements often live in defaults. Confirm new defaults\n  didn’t revert (e.g., new config precedence, disabled features, tool lists).\n- **Audit env/shell behavior**: if you fixed execution or sandboxing, verify the new path still uses your\n  sanitized env and does not reintroduce alias/function overrides.\n- **Re-run targeted samples**: keep a minimal set of \"known good\" examples and run them after the port\n  (CLI flags, extension registration, tool execution).\n\n## 12) Detect and handle reworked code\n\nBefore porting a file, check if upstream significantly refactored it:\n\n```bash\n# Compare the file you're about to port against what you have locally\ngit diff HEAD upstream/main -- path/to/file.ts\n```\n\nIf the diff shows the file was **reworked** (not just patched):\n\n- New abstractions, renamed concepts, merged modules, changed data flow\n\nThen you must **read the new implementation thoroughly** before porting. Blind merging of reworked code loses functionality because:\n\nNote: interactive mode was recently split into controllers/utils/types. When backporting related changes, port updates into the individual files we created and ensure `interactive-mode.ts` wiring stays in sync.\n\n1. **Defaults change silently** - A new variable `defaultFoo = [a, b]` may replace an old `getAllFoo()` that returned `[a, b, c, d, e]`.\n\n2. **API options get dropped** - When systems merge (e.g., `hooks` + `customTools` → `extensions`), old options may not wire through to the new implementation.\n\n3. **Code paths go stale** - A renamed concept (e.g., `hookMessage` → `custom`) needs updates in every switch statement, type guard, and handler—not just the definition.\n\n4. **Context/capabilities shrink** - Old APIs may have exposed `{ logger, typebox, pi }` that new APIs forgot to include.\n\n### Semantic porting process\n\nWhen upstream reworked a module:\n\n1. **Read the old implementation** - Understand what it did, what options it accepted, what it exposed.\n\n2. **Read the new implementation** - Understand the new abstractions and how they map to old behavior.\n\n3. **Verify feature parity** - For each capability in the old code, confirm the new code preserves it or explicitly removes it.\n\n4. **Grep for stragglers** - Search for old names/concepts that may have been missed in switch statements, handlers, UI components.\n\n5. **Test the boundaries** - CLI flags, SDK options, event handlers, default values—these are where regressions hide.\n\n### Quick checks\n\n```bash\n# Find all uses of an old concept that may need updating\nrg \"oldConceptName\" --type ts\n\n# Compare default values between versions\ngit show upstream/main:path/to/file.ts | rg \"default|DEFAULT\"\n\n# Check if all enum/union values have handlers\nrg \"case \\\"\" path/to/file.ts\n```\n\n## 13) Quick audit checklist\n\nUse this as a final pass before you finish:\n\n- [ ] Import extensions follow the local package convention (no blanket `.js` stripping)\n- [ ] No newly introduced Node-only APIs unless they match an existing justified pattern\n- [ ] All package scopes updated\n- [ ] `package.json` scripts use Bun\n- [ ] Prompts are `.md` text imports (no inline prompt strings)\n- [ ] No internal/runtime `console.*` in coding-agent; CLI user-facing output is intentional\n- [ ] Assets load via Bun embed/import patterns, or through an existing intentional generation pipeline\n- [ ] Tests or checks run (or explicitly noted as blocked)\n- [ ] No functionality regressions (see sections 11-12)\n\n## 14) Commit message format\n\nWhen committing a backport, follow the repo format `<type>(scope): <past-tense description>` and keep the commit\nrange in the title.\n\n```\nfix(coding-agent): backported pi-mono changes (<from>..<to>)\n\npackages/<package>:\n- <type>: <description>\n- <type>: <description> (#<issue> by @<contributor>)\n\npackages/<other-package>:\n- <type>: <description>\n```\n\n**Example:**\n\n```\nfix(coding-agent): backported pi-mono changes (9f3eef65f..52532c7c0)\n\npackages/ai:\n- fix: handle \"sensitive\" stop reason from Anthropic API\n- fix: normalize tool call IDs with special characters for Responses API\n- fix: add overflow detection for Bedrock, MiniMax, Kimi providers\n- fix: 429 status is rate limiting, not context overflow\n\npackages/tui:\n- fix: refactored autocomplete state tracking\n- fix: file autocomplete should not trigger on empty text\n- fix: configurable autocomplete max visible items\n- fix: improved table column width calculation with word-aware wrapping\n\npackages/coding-agent:\n- fix: preserve external config.yml edits on save (#1046 by @nicobailonMD)\n- fix: resolve macOS NFD and curly quote variants in file paths\n```\n\n**Rules:**\n\n- Group changes by package\n- Use conventional commit types (`fix`, `feat`, `refactor`, `perf`, `docs`)\n- Include upstream issue/PR numbers and contributor attribution for external contributions\n- The commit range in the title helps track sync points\n\n## 15) Intentional Divergences\n\nOur fork has architectural decisions that differ from upstream. **Do not port these upstream patterns:**\n\n### UI Architecture\n\n| Upstream                                    | Our Fork                                                  | Reason                                                                |\n| ------------------------------------------- | --------------------------------------------------------- | --------------------------------------------------------------------- |\n| `FooterDataProvider` class                  | `StatusLineComponent`                                     | Simpler, integrated status line                                       |\n| `ctx.ui.setHeader()` / `ctx.ui.setFooter()` | No-op stubs in current extension contexts                 | Not currently wired to replace the TUI status/header UI               |\n| `ctx.ui.setEditorComponent()`               | No-op stubs in current extension contexts                 | Custom editor replacement is not currently wired                      |\n| `InteractiveModeOptions` options object     | Positional constructor args (options type still exported) | Keep constructor signature; update the type when upstream adds fields |\n\n### Component Naming\n\n| Upstream                     | Our Fork                |\n| ---------------------------- | ----------------------- |\n| `extension-input.ts`         | `hook-input.ts`         |\n| `extension-selector.ts`      | `hook-selector.ts`      |\n| `ExtensionInputComponent`    | `HookInputComponent`    |\n| `ExtensionSelectorComponent` | `HookSelectorComponent` |\n\n### API Naming\n\n| Upstream                                 | Our Fork                                 | Notes                                     |\n| ---------------------------------------- | ---------------------------------------- | ----------------------------------------- |\n| `sessionManager.appendSessionInfo(name)` | `sessionManager.setSessionName(name)`    | We use `sessionName` throughout           |\n| `sessionManager.getSessionName()`        | `sessionManager.getSessionName()`        | Same (we unified to match upstream's RPC) |\n| `agent.sessionName` / `setSessionName()` | `agent.sessionName` / `setSessionName()` | Same                                      |\n\n### File Consolidation\n\n| Upstream                                           | Our Fork                                                  | Reason                                        |\n| -------------------------------------------------- | --------------------------------------------------------- | --------------------------------------------- |\n| `clipboard.ts` + `clipboard-image.ts` (tool files) | `src/utils/clipboard.ts` backed by `@oh-my-pi/pi-natives` | Native implementation with a small TS wrapper |\n\n### Test Framework\n\n| Upstream                  | Our Fork                      |\n| ------------------------- | ----------------------------- |\n| `vitest` with `vi.mock()` | `bun:test` with `vi` from bun |\n| `node:test` assertions    | `expect()` matchers           |\n\n### Tool Architecture\n\n| Upstream                            | Our Fork                                                                                                      | Notes                                                     |\n| ----------------------------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- |\n| `createTool(cwd: string, options?)` | `createTools(session: ToolSession)` via `BUILTIN_TOOLS` registry                                              | Tool factories accept `ToolSession` and can return `null` |\n| Per-tool `*Operations` interfaces   | Only current per-tool override interfaces remain (for example `FindOperations`)                               | Used for SSH/remote overrides where present               |\n| Node.js `fs/promises` everywhere    | Bun file APIs for simple file writes/reads, `node:fs/promises` for dirs, selected sync `node:fs` where needed | Prefer Bun APIs when they simplify                        |\n\n### Auth Storage\n\n| Upstream                        | Our Fork                                    | Notes                                        |\n| ------------------------------- | ------------------------------------------- | -------------------------------------------- |\n| `proper-lockfile` + `auth.json` | `agent.db` (bun:sqlite)                     | Credentials stored exclusively in `agent.db` |\n| Single credential per provider  | Multi-credential with round-robin selection | Session affinity and backoff logic preserved |\n\n### Extensions\n\n| Upstream                                                         | Our Fork                                                                                          |\n| ---------------------------------------------------------------- | ------------------------------------------------------------------------------------------------- |\n| `jiti` for TypeScript loading                                    | Native Bun `import()`                                                                              |\n| `pkg.pi` manifest field                                          | `pkg.omp` preferred; fallback to `pkg.pi` remains                                                  |\n| `StringEnum` from `pi-ai`                                        | `Type.Enum` from the `pi.typebox` shim (or author the schema with `pi.zod`); `pi-ai` no longer exports `StringEnum` |\n| `formatSize` from `pi-coding-agent`                              | `formatBytes` from `@oh-my-pi/pi-utils`                                                            |\n| `DefaultResourceLoader` / `DefaultPackageManager` / `SettingsManager` / `createEventBus` | Capability-based discovery (`loadCapability(...)`) plus the `Settings` singleton and `EventBus` |\n\n### Skip These Upstream Features\n\nWhen porting, **skip** these files/features entirely:\n\n- `footer-data-provider.ts` — we use StatusLineComponent\n- `clipboard-image.ts` — image clipboard support is exposed through `src/utils/clipboard.ts` backed by `@oh-my-pi/pi-natives`\n- GitHub workflow files — we have our own CI\n- `models.generated.ts` — auto-generated, regenerate locally (as models.json instead)\n\n### Features We Added (Preserve These)\n\nThese exist in our fork but not upstream. **Never overwrite:**\n\n- `StatusLineComponent` in interactive mode\n- Multi-credential auth with session affinity\n- Capability-based discovery system (`defineCapability`, `registerProvider`, `loadCapability`, `skillCapability`, etc.)\n- MCP/Exa/SSH integrations\n- LSP writethrough for format-on-save\n- Bash interception (`checkBashInterception`)\n- Fuzzy path suggestions in read tool\n",
 	"porting-to-natives.md": "# Porting to pi-natives (N-API) — Field Notes\n\nThis is a practical guide for moving hot paths into `crates/pi-natives` and wiring them through the generated native package entrypoint. It exists to avoid the same failures happening twice.\n\n## When to port\n\nPort when any of these are true:\n\n- The hot path runs in render loops, tight UI updates, or large batches.\n- JS allocations dominate (string churn, regex backtracking, large arrays).\n- You already have a JS baseline and can benchmark both versions side by side.\n- The work is CPU-bound or blocking I/O that can run on the libuv thread pool.\n- The work is async I/O that can run on Tokio's runtime (for example shell execution).\n\nAvoid ports that depend on JS-only state or dynamic imports. N-API exports should be data-in/data-out. Long-running work should go through `task::blocking` (CPU-bound/blocking I/O) or `task::future` (async I/O) with cancellation where the caller needs `timeoutMs` or `AbortSignal`.\n\n## Current package shape\n\n`@oh-my-pi/pi-natives` no longer has a `packages/natives/src/<module>` TypeScript wrapper layer. The package root points at generated native artifacts:\n\n- runtime entry/export wrapper: `packages/natives/native/index.js`\n- types entry: `packages/natives/native/index.d.ts`\n- loader helpers: `packages/natives/native/loader-state.js`\n- embedded manifest: `packages/natives/native/embedded-addon.js`\n\nConsumers import directly from `@oh-my-pi/pi-natives`. The generated declarations and explicit ESM exports are produced during `bun --cwd=packages/natives run build`.\n\n## Anatomy of a native export\n\n**Rust side:**\n\n- Implementation lives in `crates/pi-natives/src/<module>.rs`.\n- If you add a new module, register it in `crates/pi-natives/src/lib.rs`.\n- Export with `#[napi]`; snake_case exports are converted to camelCase automatically. Use explicit JS names only for true aliases/non-default names. Use `#[napi(object)]` for object-shaped structs.\n- For CPU-bound or blocking work, use `task::blocking(tag, cancel_token, work)`.\n- For async work that needs Tokio, use `task::future(env, tag, work)`.\n- Pass a `CancelToken` when the API exposes `timeoutMs` or `AbortSignal`, and call `heartbeat()` inside long loops.\n\n**Package/build side:**\n\n- `packages/natives/scripts/build-native.ts` runs napi-rs, installs the `.node` artifact, copies generated `index.d.ts`, and regenerates explicit ESM class/function exports plus enum runtime exports in the checked-in `native/index.js`.\n- `packages/natives/native/index.js` is the ESM entrypoint that calls the loader, exposes named exports, and rejects install/compiled `.node` files that do not expose the package-version sentinel.\n- `packages/natives/package.json` exposes only the package root (`@oh-my-pi/pi-natives`) as the import surface. At publish time the binaries are split out: the core ships the loader only (no `.node`), and each platform's `.node` is published as an optional-dependency leaf package `@oh-my-pi/pi-natives-<tag>` (`scripts/ci-release-publish.ts` + `packages/natives/scripts/gen-npm-packages.ts`). This is transparent to importers — you still `import` from `@oh-my-pi/pi-natives`.\n\n**Consumer side:**\n\n- Update direct imports/callsites in `packages/coding-agent` or `packages/tui` when the new export replaces a JS implementation.\n- Keep higher-level policy in consumers unless it belongs in the native primitive itself.\n\n## Porting checklist\n\n1. **Add the Rust implementation**\n\n- Put the core logic in a plain Rust function.\n- If it is a new module, add it to `crates/pi-natives/src/lib.rs`.\n- Expose it with `#[napi]` so the default snake_case -> camelCase mapping stays consistent.\n- Keep signatures owned and simple: `String`, `Vec<String>`, `Uint8Array`, `Either<JsString, Uint8Array>`, or `#[napi(object)]` structs.\n- For CPU-bound or blocking work, use `task::blocking`; for async work, use `task::future`.\n- If exposing cancellation, include `timeout_ms: Option<u32>` and `signal: Option<Unknown<'env>>` in options, create `CancelToken::new(...)`, and heartbeat in long loops.\n\n2. **Build generated bindings**\n\n- Run `bun --cwd=packages/natives run build`.\n- Confirm the generated `packages/natives/native/index.d.ts` includes the new export with the intended JS name/signature.\n- Confirm `packages/natives/native/index.js` has generated explicit ESM exports for the new class/function and enum objects when enum changes are involved.\n\n3. **Update consumers**\n\n- Import the new export directly from `@oh-my-pi/pi-natives`.\n- Replace only callsites where the native implementation is faster/equivalent and preserves behavior.\n- Remove obsolete JS implementation code in the same change when the native path becomes canonical.\n\n4. **Add benchmarks**\n\n- Put benchmarks next to the owning package (`packages/tui/bench`, `packages/natives/bench`, or `packages/coding-agent/bench`).\n- Include a JS baseline and native version in the same run.\n- Use `Bun.nanoseconds()` and a fixed iteration count.\n- Keep benchmark inputs realistic for the hot path.\n\n5. **Run focused verification**\n\n- Build the native package.\n- Run the benchmark.\n- Run the narrow tests or scenario covering the changed export/callsites.\n\n## Pain points and how to avoid them\n\n### 1) Stale platform/variant artifacts\n\nThe loader probes platform-tagged artifacts in deterministic order. For x64, selected variant candidates are tried before the unsuffixed default fallback:\n\n- `modern`: `pi_natives.<tag>-modern.node`, then `...-baseline.node`, then `pi_natives.<tag>.node`.\n- `baseline`: `pi_natives.<tag>-baseline.node`, then `pi_natives.<tag>.node`.\n\nNon-x64 uses `pi_natives.<tag>.node`.\n\nCompiled binaries also probe `<getNativesDir()>/<version>/...` and a legacy user-data directory before package/executable locations. Windows `node_modules` installs stage leaf/core addons into the same versioned directory before probing. If any earlier candidate is stale, a new export may appear missing unless the version sentinel rejects it first.\n\n**Fix:** remove stale candidate/cache files and rebuild.\n\n```bash\nrm packages/natives/native/pi_natives.<platform>-<arch>.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-modern.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-baseline.node\nbun --cwd=packages/natives run build\n```\n\nFor compiled binaries or Windows staging, delete the versioned addon cache shown in the loader error (normally under `~/.omp/natives/<version>` unless `$XDG_DATA_HOME/omp` is used).\n\n### 2) Generated types do not match loaded binary\n\nThis can happen when `native/index.d.ts` was regenerated but the `.node` file being loaded is stale, same-version incomplete, or from a different platform/variant. Different-version install/compiled binaries should be rejected by the version sentinel during loading.\n\nVerify the loaded export set from the actual candidate path reported by the loader:\n\n```bash\nbun -e 'import { createRequire } from \"node:module\"; const require = createRequire(import.meta.url); const mod = require(process.argv[2]); console.log(Object.keys(mod).sort())' -- /path/from/loader/error/pi_natives.<tag>[-variant].node\n```\n\nFix the build/candidate mismatch. Do not paper over it with optional consumer checks if the export is required.\n\n### 3) Rust signature mismatch\n\nKeep N-API signatures simple and owned. Avoid borrowed references like `&str` in public exports. If you need structured data, use `#[napi(object)]` structs. If you need callbacks, use napi-rs `ThreadsafeFunction` and keep callback error/value behavior explicit.\n\n### 4) Enum runtime exports and ESM named exports\n\nnapi-rs declarations alone are not enough for JS callers that import named symbols or use enum objects at runtime. `scripts/gen-enums.ts` reads `native/index.d.ts`, writes explicit `export const ... = nativeBindings...` entries for public classes/functions, and emits enum objects in `native/index.js`. If you add or change a native export, verify both `native/index.d.ts` and the generated export block in `native/index.js`.\n\n### 5) Benchmarking mistakes\n\n- Do not compare different inputs or allocations.\n- Keep JS and native using identical input arrays.\n- Run both in the same benchmark file to avoid skew.\n- Include enough iterations to smooth startup noise, but keep inputs realistic.\n\n## Benchmark template\n\n```ts\nconst ITERATIONS = 2000;\n\nfunction bench(name: string, fn: () => void): number {\n  const start = Bun.nanoseconds();\n  for (let i = 0; i < ITERATIONS; i++) fn();\n  const elapsed = (Bun.nanoseconds() - start) / 1e6;\n  console.log(\n    `${name}: ${elapsed.toFixed(2)}ms total (${(elapsed / ITERATIONS).toFixed(6)}ms/op)`,\n  );\n  return elapsed;\n}\n\nbench(\"feature/js\", () => {\n  jsImpl(sample);\n});\n\nbench(\"feature/native\", () => {\n  nativeImpl(sample);\n});\n```\n\n## Verification checklist\n\n- Generated `native/index.d.ts` includes the new export and intended TS signature.\n- `native/index.js` includes the generated named export; enum objects are present when the change adds/changes enums.\n- The loaded `.node` file's `Object.keys(require(candidate))` includes the new export and the package-version sentinel.\n- Bench numbers are recorded in the PR/notes.\n- Call sites are updated only if native is faster/equal and behavior-compatible.\n- Obsolete JS code is removed when the native implementation becomes canonical.\n\n## Rule of thumb\n\n- If native is slower, do not switch callsites. Keep or remove the export based on whether it has a near-term owner.\n- If native is faster and behavior-compatible, switch callsites and keep a benchmark to catch regressions.\n",
 	"provider-streaming-internals.md": "# Provider streaming internals\n\nThis document explains how token/tool streaming is normalized in `@oh-my-pi/pi-ai`, then propagated through `@oh-my-pi/pi-agent-core` and `coding-agent` session events.\n\n## End-to-end flow\n\n1. `streamSimple()` (`packages/ai/src/stream.ts`) maps generic options and dispatches to a provider stream function.\n2. Provider stream functions translate provider-native stream events into the unified `AssistantMessageEvent` sequence. Current built-ins include Anthropic, OpenAI Responses/Completions/Codex/Azure Responses, Google Gemini/Gemini CLI/Vertex, Bedrock Converse, Ollama, Cursor, pi-native gateway transport, plus GitLab Duo/Kimi/Synthetic wrappers and extension-registered custom APIs.\n3. Each provider pushes events into `AssistantMessageEventStream` (`packages/ai/src/utils/event-stream.ts`), which throttles delta events and exposes:\n   - async iteration for incremental updates\n   - `result()` for final `AssistantMessage`\n4. `agentLoop` (`packages/agent/src/agent-loop.ts`) consumes those events, mutates in-flight assistant state, and emits `message_update` events carrying the raw `assistantMessageEvent`.\n5. `AgentSession` (`packages/coding-agent/src/session/agent-session.ts`) subscribes to agent events, persists messages, drives extension hooks, and applies session behaviors (retry, compaction, TTSR, streaming-edit abort checks).\n\n## Unified stream contract in `@oh-my-pi/pi-ai`\n\nAll providers emit the same shape (`AssistantMessageEvent` in `packages/ai/src/types.ts`):\n\n- `start`\n- content block lifecycle triplets:\n  - text: `text_start` → `text_delta`\\* → `text_end`\n  - thinking: `thinking_start` → `thinking_delta`\\* → `thinking_end`\n  - tool call: `toolcall_start` → `toolcall_delta`\\* → `toolcall_end`\n- terminal event:\n  - `done` with `reason: \"stop\" | \"length\" | \"toolUse\"`\n  - or `error` with `reason: \"aborted\" | \"error\"`\n\n`AssistantMessageEventStream` guarantees:\n\n- final result is resolved by terminal event (`done` or `error`)\n- deltas are batched/throttled (~50ms)\n- buffered deltas are flushed before non-delta events and before completion\n\n## Delta throttling and harmonization behavior\n\n`AssistantMessageEventStream` treats `text_delta`, `thinking_delta`, and `toolcall_delta` as mergeable events:\n\n- buffered deltas are merged only when **type + contentIndex** match\n- merge keeps the latest `partial` snapshot\n- non-delta events force immediate flush\n\nThis smooths high-frequency provider streams for TUI/event consumers, but is not provider backpressure: providers still produce at full speed, while the local stream buffers.\n\n## Provider normalization details\n\n## Anthropic (`anthropic-messages`)\n\nSource: `packages/ai/src/providers/anthropic.ts`\n\nNormalization points:\n\n- `message_start` initializes usage (input/output/cache tokens)\n- `content_block_start` maps to text/thinking/toolcall starts\n- `content_block_delta` maps:\n  - `text_delta` → `text_delta`\n  - `thinking_delta` → `thinking_delta`\n  - `input_json_delta` → `toolcall_delta`\n  - `signature_delta` updates `thinkingSignature` only (no event)\n- `content_block_stop` emits corresponding `*_end`\n- `message_delta.stop_reason` maps via `mapStopReason()`\n\nTool-call argument streaming:\n\n- each tool block carries internal `partialJson`\n- every JSON delta appends to `partialJson`\n- `arguments` are reparsed on each delta via `parseStreamingJson()`\n- `toolcall_end` reparses once more, then strips `partialJson`\n\n## OpenAI Responses family (`openai-responses`, `openai-codex-responses`, `azure-openai-responses`)\n\nSources: `packages/ai/src/providers/openai-responses.ts`, `openai-codex-responses.ts`, and `azure-openai-responses.ts`\n\nNormalization points:\n\n- `response.output_item.added` starts reasoning/text/function-call/custom-tool blocks\n- reasoning summary events (`response.reasoning_summary_text.delta`) and raw reasoning events (`response.reasoning_text.delta`) become `thinking_delta`\n- output/refusal deltas become `text_delta`\n- `response.function_call_arguments.delta` and `response.custom_tool_call_input.delta` become `toolcall_delta`\n- `response.output_item.done` emits `thinking_end` / `text_end` / `toolcall_end`\n- `response.completed` maps status to stop reason and usage; `response.failed` / SDK `error` events throw into the wrapper's terminal `error` path\n\nTool-call argument streaming:\n\n- same `partialJson` accumulation pattern as Anthropic for function-call JSON arguments\n- custom tools stream raw string input and expose final arguments as `{ input: <raw> }`\n- providers that send only `response.function_call_arguments.done` still populate final args\n- tool call IDs are normalized as `\"<call_id>|<item_id>\"`\n\n## Google Generative AI (`google-generative-ai`)\n\nSource: `packages/ai/src/providers/google.ts`\n\nNormalization points:\n\n- iterates `candidate.content.parts`\n- text parts are split into thinking vs text by `isThinkingPart(part)`\n- block transitions close previous block before starting a new one\n- `part.functionCall` is treated as a complete tool call (start/delta/end emitted immediately)\n- finish reason mapped by `mapStopReason()` from `google-shared.ts`\n\nTool-call argument streaming:\n\n- function call args arrive as structured object, not incremental JSON text\n- implementation emits one synthetic `toolcall_delta` containing `JSON.stringify(arguments)`\n- no partial JSON parser needed for Google in this path\n\n## Partial tool-call JSON accumulation and recovery\n\nShared behavior for Anthropic/OpenAI Responses uses `parseStreamingJson()` (`packages/ai/src/utils/json-parse.ts`):\n\n1. try `JSON.parse`\n2. fallback to `partial-json` parser for incomplete fragments\n3. if both fail, return `{}`\n\nImplications:\n\n- malformed or truncated argument deltas do not crash stream processing immediately\n- in-progress `arguments` may temporarily be `{}`\n- later valid deltas can recover structured arguments because parsing is retried on every append\n- final `toolcall_end` performs one more parse attempt before emission\n\n## Stop reasons vs transport/runtime errors\n\nProvider stop reasons are mapped to normalized `stopReason`:\n\n- Anthropic: `end_turn`→`stop`, `max_tokens`→`length`, `tool_use`→`toolUse`, safety/refusal cases→`error`\n- OpenAI Responses: `completed`→`stop`, `incomplete`→`length`, `failed/cancelled`→`error`\n- Google: `STOP`→`stop`, `MAX_TOKENS`→`length`, safety/prohibited/malformed-function-call classes→`error`\n\nError semantics are split in two stages:\n\n1. **Model completion semantics** (provider reported finish reason/status)\n2. **Transport/runtime failure** (network/client/parser/abort exceptions)\n\nIf provider stream throws or signals failure, each provider wrapper catches and emits terminal `error` event with:\n\n- `stopReason = \"aborted\"` when abort signal is set\n- otherwise `stopReason = \"error\"`\n- `errorMessage = formatErrorMessageWithRetryAfter(error)`\n\n## Malformed chunk / SSE parse failure behavior\n\nMost provider paths delegate chunk/SSE framing to vendor SDK streams (Anthropic SDK, OpenAI SDK, Google SDK). The Codex SSE fallback uses `readSseJson()` directly, and websocket Codex frames are normalized through the same event handler.\n\nObserved behavior in current implementation:\n\n- malformed SDK stream parsing surfaces as an exception or stream `error` event\n- malformed Codex SSE JSON/framing throws from the local SSE reader\n- provider wrapper converts failures into unified terminal `error` events\n- no provider-specific resume/retry inside the stream function itself, except Codex websocket-to-SSE transport fallback before replay-unsafe output is emitted\n- higher-level retries are handled in `AgentSession` auto-retry logic (message-level retry, not stream-chunk replay)\n\n## Cancellation boundaries\n\nCancellation is layered:\n\n- AI provider request: `options.signal` is passed into provider client stream call.\n- Provider wrapper: after stream loop, aborted signal forces error path (`\"Request was aborted\"`).\n- Agent loop: checks `signal.aborted` before handling each provider event and can synthesize an aborted assistant message from the latest partial.\n- Session/agent controls: `AgentSession.abort()` -> `agent.abort()` -> shared abort controller cancellation.\n\nTool execution cancellation is separate from model stream cancellation:\n\n- tool runners use `AbortSignal.any([agentSignal, steeringAbortSignal])`\n- steering interrupts can abort remaining tool execution while preserving already-produced tool results\n\n## Backpressure boundaries\n\nThere is no hard backpressure mechanism between provider SDK stream and downstream consumers:\n\n- `EventStream` uses in-memory queues with no max size\n- throttling reduces UI update rate but does not slow provider intake\n- if consumers lag significantly, queued events can grow until completion\n\nCurrent design favors responsiveness and simple ordering over bounded-buffer flow control.\n\n## How stream events surface as agent/session events\n\n`agentLoop.streamAssistantResponse()` bridges `AssistantMessageEvent` to `AgentEvent`:\n\n- on `start`: pushes placeholder assistant message and emits `message_start`\n- on block events (`text_*`, `thinking_*`, `toolcall_*`): updates last assistant message, emits `message_update` with raw `assistantMessageEvent`\n- on terminal (`done`/`error`): resolves final message from `response.result()`, emits `message_end`\n\n`AgentSession` then consumes those events for session-level behaviors:\n\n- TTSR watches `message_update.assistantMessageEvent` for `text_delta`, `thinking_delta`, and `toolcall_delta`\n- streaming edit guard inspects `toolcall_delta`/`toolcall_end` on `edit` calls and can abort early\n- persistence writes finalized messages at `message_end`\n- auto-retry examines assistant `stopReason === \"error\"` plus `errorMessage` heuristics\n\n## Unified vs provider-specific responsibilities\n\nUnified (common contract):\n\n- event shape (`AssistantMessageEvent`)\n- final result extraction (`done`/`error`)\n- delta throttling + merge rules\n- agent/session event propagation model\n\nProvider-specific (not fully abstracted):\n\n- upstream event taxonomies and mapping logic\n- stop-reason translation tables\n- tool-call ID conventions\n- reasoning/thinking block semantics and signatures\n- usage token semantics and availability timing\n- message conversion constraints per API\n\n## Implementation files\n\n- [`../../ai/src/stream.ts`](../packages/ai/src/stream.ts) — provider dispatch, option mapping, API key/session plumbing, custom API dispatch, and provider-specific credential handling.\n- [`../../ai/src/utils/event-stream.ts`](../packages/ai/src/utils/event-stream.ts) — generic stream queue + assistant delta throttling.\n- [`../../ai/src/utils/json-parse.ts`](../packages/ai/src/utils/json-parse.ts) — partial JSON parsing for streamed tool arguments.\n- [`../../ai/src/providers/anthropic.ts`](../packages/ai/src/providers/anthropic.ts) — Anthropic event translation and tool JSON delta accumulation.\n- [`../../ai/src/providers/openai-responses.ts`](../packages/ai/src/providers/openai-responses.ts), [`openai-responses-shared.ts`](../packages/ai/src/providers/openai-responses-shared.ts), [`openai-codex-responses.ts`](../packages/ai/src/providers/openai-codex-responses.ts), [`azure-openai-responses.ts`](../packages/ai/src/providers/azure-openai-responses.ts) — Responses-family event translation and status mapping.\n- [`../../ai/src/providers/google.ts`](../packages/ai/src/providers/google.ts), [`google-gemini-cli.ts`](../packages/ai/src/providers/google-gemini-cli.ts), [`google-vertex.ts`](../packages/ai/src/providers/google-vertex.ts) — Gemini stream chunk-to-block translation variants.\n- [`../../ai/src/providers/google-shared.ts`](../packages/ai/src/providers/google-shared.ts) — Gemini finish-reason mapping and shared conversion rules.\n- [`../../ai/src/providers/amazon-bedrock.ts`](../packages/ai/src/providers/amazon-bedrock.ts), [`openai-completions.ts`](../packages/ai/src/providers/openai-completions.ts), [`ollama.ts`](../packages/ai/src/providers/ollama.ts), [`cursor.ts`](../packages/ai/src/providers/cursor.ts), [`pi-native-client.ts`](../packages/ai/src/providers/pi-native-client.ts) — additional built-in stream adapters using the same event contract.\n- [`../../agent/src/agent-loop.ts`](../packages/agent/src/agent-loop.ts) — provider stream consumption and `message_update` bridging.\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — session-level handling of streaming updates, abort, retry, and persistence.\n",
-	"python-repl.md": "# Eval Tool Python Backend\n\nThis document describes the Python execution stack in `packages/coding-agent`.\nIt covers tool behavior, runner lifecycle, environment handling, execution semantics, output rendering, supported magics, and operational failure modes.\n\n## Scope and Key Files\n\n- Tool surface: `src/tools/eval.ts`\n- Session/per-call kernel orchestration: `src/eval/py/executor.ts`\n- Subprocess kernel client: `src/eval/py/kernel.ts`\n- Python wrapper / NDJSON server: `src/eval/py/runner.py`\n- Prelude helpers loaded into every kernel: `src/eval/py/prelude.py`\n- Host-side subagent helper bridge: `src/eval/agent-bridge.ts`\n- MIME bundle renderer (text + structured outputs): `src/eval/py/display.ts`\n- Interactive-mode renderer for user-triggered Python runs: `src/modes/components/eval-execution.ts`\n- Runtime/env filtering and Python resolution: `src/eval/py/runtime.ts`\n\n## What eval's Python backend is\n\nThe `eval` tool executes one or more Python cells inside a retained `python` subprocess that speaks NDJSON over stdin/stdout. No Jupyter gateway and no extra pip dependencies are required — a vanilla Python 3.8+ interpreter is enough. Rich `display()` output (PIL, pandas, plotly, matplotlib figures) keeps working because the wrapper implements MIME-bundle dispatch.\n\nTool params:\n\n```ts\n{\n  cells: Array<{\n    language: \"py\" | \"js\";\n    code: string;\n    title?: string;\n    timeout?: number; // seconds, clamped to 1..600, default 30. Inactivity budget — see \"Cell timeout\".\n    reset?: boolean; // reset this cell's selected runtime before execution\n  }>;\n}\n```\n\nThe tool is `concurrency = \"exclusive\"` for a session, so calls do not overlap.\n\n## Kernel lifecycle\n\nEach Python kernel is a single subprocess: `<resolved-python> -u <runner.py>`. The runner is bundled with the host binary (Bun text import), written to an `omp-python-runner` cache under the OS temp directory once per script hash, and reused by subsequent spawns.\n\nKernel startup sequence:\n\n1. Availability check (`checkPythonKernelAvailability`) — verifies that a Python interpreter resolves and runs.\n2. Spawn `python -u runner.py` with filtered env and `cwd`.\n3. Send an init request that runs `os.chdir(cwd)`, injects env entries, and adds `cwd` to `sys.path`.\n4. Execute `PYTHON_PRELUDE` (idempotent — only initializes once per process).\n\nKernel shutdown:\n\n- Send `{\"type\": \"exit\"}` over stdin.\n- Wait for process exit with `SHUTDOWN_GRACE_MS` budget.\n- Escalate to `SIGTERM` and finally `SIGKILL` if the process does not exit in time.\n\n## Wire protocol (NDJSON, host ↔ runner)\n\nOne JSON object per line, UTF-8, `\\n` terminated.\n\nHost → runner:\n\n```jsonc\n{\"id\": \"<reqId>\", \"code\": \"<source>\", \"silent\": false, \"storeHistory\": true}\n{\"type\": \"exit\"}\n```\n\nRunner → host:\n\n```jsonc\n{\"type\": \"started\",  \"id\": \"<reqId>\"}\n{\"type\": \"stdout\",   \"id\": \"<reqId>\", \"data\": \"...\"}\n{\"type\": \"stderr\",   \"id\": \"<reqId>\", \"data\": \"...\"}\n{\"type\": \"display\",  \"id\": \"<reqId>\", \"bundle\": {<mime>: <value>}}\n{\"type\": \"result\",   \"id\": \"<reqId>\", \"bundle\": {<mime>: <value>}}\n{\"type\": \"error\",    \"id\": \"<reqId>\", \"ename\": \"...\", \"evalue\": \"...\", \"traceback\": [\"...\"]}\n{\"type\": \"done\",     \"id\": \"<reqId>\", \"status\": \"ok\"|\"error\", \"executionCount\": N, \"cancelled\": false}\n```\n\nStatus events the prelude emits (e.g. `_emit_status(\"find\", count=…)`) ship inside display bundles under `application/x-omp-status` so the existing TUI status renderer keeps working.\n\n## Magics\n\nThe runner's source transformer rewrites IPython-style magics to plain Python calls before parsing. Supported set:\n\n| Magic                             | Effect                                                                                                                                                      |\n| --------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `%pip <args>`                     | `python -m pip <args>` with live streaming output. Newly installed packages are evicted from `sys.modules` so the next `import` picks up the fresh install. |\n| `%cd <path>`                      | `os.chdir(path)` (with `~` expansion); emits status event.                                                                                                  |\n| `%pwd`                            | Returns `os.getcwd()`.                                                                                                                                      |\n| `%ls [path]`                      | Returns `sorted(os.listdir(path))`.                                                                                                                         |\n| `%env [KEY[=VAL]]`                | List, read, or set env vars (matches prelude `env()` semantics).                                                                                            |\n| `%set_env KEY VALUE`              | Set `os.environ[KEY]`.                                                                                                                                      |\n| `%time <expr>` / `%timeit <expr>` | Time the expression; emits status event with elapsed ms.                                                                                                    |\n| `%who` / `%whos`                  | List user-namespace names.                                                                                                                                  |\n| `%reset`                          | Clear user globals and re-inject prelude.                                                                                                                   |\n| `%load <path>`                    | Read a file into a fresh cell and execute.                                                                                                                  |\n| `%run <path>`                     | `runpy.run_path` and merge globals back.                                                                                                                    |\n| `%%bash` / `%%sh`                 | Run the cell body via `bash`/`sh`.                                                                                                                          |\n| `%%capture [name]`                | Run body with stdout/stderr captured into `name`.                                                                                                           |\n| `%%timeit`                        | Time the cell body.                                                                                                                                         |\n| `%%writefile <path>`              | Write body to file.                                                                                                                                         |\n| `!cmd` / `var = !cmd`             | Run command via subprocess shell; returns an SList-style result with `.n` / `.s` helpers.                                                                   |\n| `var = %name args`                | Assignment forms work for line magics and `!cmd`.                                                                                                           |\n\nUnknown magic names raise `NameError: UsageError: ...` inside the cell.\n\n## Session persistence semantics\n\n`python.kernelMode` controls retained kernel reuse:\n\n- `session` (default)\n  - Reuses kernel sessions keyed by namespaced eval session id plus cwd.\n  - Multiple owners can share the same retained kernel for that key.\n  - Calls through the tool are exclusive, so tool invocations do not overlap.\n  - A dead retained subprocess is replaced before execution.\n  - If the subprocess dies during execution, it is replaced and the cell is retried once.\n- `per-call`\n  - Spawns a fresh subprocess for each request.\n  - Shuts the subprocess down after the request.\n  - No cross-call state persistence.\n\n### Multi-cell behavior in a single tool call\n\nPython cells run sequentially in the same selected Python kernel instance for that tool call.\n\nIf an intermediate cell fails:\n\n- Earlier cell state remains in memory.\n- Tool returns a targeted error indicating which cell failed.\n- Later cells are not executed.\n\n`reset=true` is per cell and resets that language runtime before the cell executes.\n\n## Environment filtering and runtime resolution\n\nEnvironment is filtered before launching the runner:\n\n- Allowlist includes core vars like `PATH`, `HOME`, locale vars, `VIRTUAL_ENV`, `PYTHONPATH`, etc.\n- Allow-prefixes: `LC_`, `XDG_`, `PI_`\n- Denylist strips common API keys (OpenAI/Anthropic/Gemini/etc.)\n\nRuntime selection order:\n\n1. Active/located venv (`VIRTUAL_ENV`, then `<cwd>/.venv`, `<cwd>/venv`)\n2. Managed venv at `~/.omp/python-env`\n3. `python` or `python3` on PATH\n\nWhen a venv is selected, its bin/Scripts path is prepended to `PATH`.\n\nThe runner additionally receives `PYTHONUNBUFFERED=1` and `PYTHONIOENCODING=utf-8` so streamed output reaches the host promptly.\n\n## Tool availability and mode selection\n\n`eval.py` / `eval.js` (both default `true`) plus optional boolean env flags `PI_PY` / `PI_JS` control eval backend exposure:\n\n- Python backend only (`eval.py=true`, `eval.js=false`, or `PI_PY=1 PI_JS=0`)\n- JavaScript backend only (`eval.py=false`, `eval.js=true`, or `PI_PY=0 PI_JS=1`)\n- both backends (`eval.py=true`, `eval.js=true`, or `PI_PY=1 PI_JS=1`)\n\n`PI_PY` and `PI_JS` use normal boolean flag parsing. If either env var is set, the env pair overrides the per-key settings; an unset member of the pair defaults to enabled.\n\nIf Python preflight fails and `eval.js` is enabled, `eval` remains available for `js` cells; `py` cells fail with a Python-backend availability error.\n\nPython prelude helpers include `agent(prompt, *, agent_type=\"task\", model=None, context=None, label=None, schema=None)`. It synchronously calls the host bridge, runs one subagent through the task executor, and returns the final text. When `schema` is supplied, the helper parses the subagent's JSON output and returns the object.\n\n## Execution flow and cancellation/timeout\n\n### Cell timeout\n\nEach eval cell `timeout` is in seconds, defaults to 30, and is clamped to `1..600`. It is a **wall-clock budget on the cell's own work** that the watchdog (`IdleTimeout`, `src/eval/idle-timeout.ts`) enforces, **but it is paused while a host-side `agent()`/`parallel()`/`llm()` bridge call is in flight**: those calls pump a heartbeat (`withBridgeHeartbeat`, `src/eval/heartbeat.ts`) that re-arms the watchdog, so a long fanout or a slow completion runs to completion instead of being killed mid-stream.\n\nThe heartbeat is the **sole** signal that extends the budget. Everything else the cell does — compute, `stdout`/`stderr`, `log()`/`phase()`, and ordinary (non-agent) tool calls — counts against `timeout`, so a cell that is not delegating to an agent/llm is bounded by a plain wall-clock timeout. The tool combines the caller abort signal, the session abort signal, and the watchdog's signal with `AbortSignal.any(...)`; no wall-clock deadline is passed to the backend, so neither runtime arms a competing fixed timer.\n\n### Kernel execution cancellation\n\nOn abort/timeout:\n\n- The host sends `kill(\"SIGINT\")` to the runner subprocess.\n- The runner's exec-time signal handler raises `KeyboardInterrupt` inside the user code.\n- Result includes `cancelled=true`; the timeout path annotates output as `Command timed out after <n> seconds`.\n- Between requests the runner installs `SIG_IGN` for SIGINT so a stray cancel does not tear down the kernel.\n\nIf a second cancel is required (runner stuck in C code), the host escalates to `SIGTERM` and the session restarts on the next call.\n\n### stdin behavior\n\nInteractive stdin is not supported. The runner does not forward `input()` prompts; user code that calls `input()` blocks until cancellation.\n\n## Output capture and rendering\n\n### Captured output classes\n\nFrom runner frames:\n\n- `stdout` / `stderr` → plain text chunks\n- `display` / `result` → rich display handling (MIME bundle)\n- `error` → traceback text\n- `application/x-omp-status` MIME inside `display` → structured status events\n\nDisplay MIME precedence:\n\n1. `text/markdown`\n2. `text/plain`\n3. `text/html` (converted to basic markdown)\n\nAdditionally captured as structured outputs:\n\n- `application/json` → JSON tree data\n- `image/png` / `image/jpeg` → image payloads\n- `application/x-omp-status` → status events\n\n### Matplotlib\n\nThe runner sets `MPLBACKEND=Agg` as an environ default so figures render off-screen. After every cell, `pyplot.get_fignums()` is iterated; each figure is saved to PNG, emitted as an `image/png` display, and closed.\n\n### Storage and truncation\n\nOutput is streamed through `OutputSink` and may be persisted to artifact storage. Tool results can include truncation metadata and `artifact://<id>` for full output recovery.\n\n### Renderer behavior\n\n- Tool renderer (`eval.ts`):\n  - shows code-cell blocks with per-cell status\n  - collapsed preview defaults to 10 lines\n  - supports expanded mode for all output retained in the tool result\n- Interactive renderer (`eval-execution.ts`):\n  - used for user-triggered Python execution in TUI\n  - collapsed preview defaults to 20 lines\n  - clamps very long individual lines to 4000 chars for display safety\n  - shows cancellation/error/truncation notices\n\n## Operational troubleshooting\n\n- **Python backend not available** — Check `eval.py`, `PI_PY`, and that `python`/`python3` is on PATH. If preflight fails and `eval.js` is enabled, use a `js` cell.\n- **No Python on PATH** — Install a system Python 3.8+ or place a venv at `~/.omp/python-env`. `omp setup python --check` reports the resolved interpreter.\n- **Execution hangs then times out** — Increase tool `timeout` (max 600s) if workload is legitimate. For stuck native code, cancellation triggers `SIGINT` first then escalates; the session restarts on the next request.\n- **stdin/input prompts in Python code** — `input()` is not supported; pass data programmatically.\n- **Working directory errors** — Tool validates `cwd` exists and is a directory before execution.\n\n## Relevant environment variables\n\n- `PI_PY` / `PI_JS` — eval backend exposure overrides\n- `PI_PYTHON_SKIP_CHECK=1` — bypass Python preflight/warm checks\n- `PI_PYTHON_INTEGRATION=1` — enable gated integration tests that spawn a real Python\n- `PI_PYTHON_IPC_TRACE=1` — log NDJSON frames exchanged with the runner subprocess\n",
+	"python-repl.md": "# Eval Tool Python Backend\n\nThis document describes the Python execution stack in `packages/coding-agent`.\nIt covers tool behavior, runner lifecycle, environment handling, execution semantics, output rendering, supported magics, and operational failure modes.\n\n## Scope and Key Files\n\n- Tool surface: `src/tools/eval.ts`\n- Session/per-call kernel orchestration: `src/eval/py/executor.ts`\n- Subprocess kernel client: `src/eval/py/kernel.ts`\n- Python wrapper / NDJSON server: `src/eval/py/runner.py`\n- Prelude helpers loaded into every kernel: `src/eval/py/prelude.py`\n- Host-side subagent helper bridge: `src/eval/agent-bridge.ts`\n- MIME bundle renderer (text + structured outputs): `src/eval/py/display.ts`\n- Interactive-mode renderer for user-triggered Python runs: `src/modes/components/eval-execution.ts`\n- Runtime/env filtering and Python resolution: `src/eval/py/runtime.ts`\n\n## What eval's Python backend is\n\nThe `eval` tool executes one or more Python cells inside a retained `python` subprocess that speaks NDJSON over stdin/stdout. No Jupyter gateway and no extra pip dependencies are required — a vanilla Python 3.8+ interpreter is enough. Rich `display()` output (PIL, pandas, plotly, matplotlib figures) keeps working because the wrapper implements MIME-bundle dispatch.\n\nTool params:\n\n```ts\n{\n  cells: Array<{\n    language: \"py\" | \"js\";\n    code: string;\n    title?: string;\n    timeout?: number; // seconds, clamped to 1..600, default 30. Inactivity budget — see \"Cell timeout\".\n    reset?: boolean; // reset this cell's selected runtime before execution\n  }>;\n}\n```\n\nThe tool is `concurrency = \"exclusive\"` for a session, so calls do not overlap.\n\n## Kernel lifecycle\n\nEach Python kernel is a single subprocess: `<resolved-python> -u <runner.py>`. The runner is bundled with the host binary (Bun text import), written to an `omp-python-runner` cache under the OS temp directory once per script hash, and reused by subsequent spawns.\n\nKernel startup sequence:\n\n1. Availability check (`checkPythonKernelAvailability`) — verifies that a Python interpreter resolves and runs.\n2. Spawn `python -u runner.py` with filtered env and `cwd`.\n3. Send an init request that runs `os.chdir(cwd)`, injects env entries, and adds `cwd` to `sys.path`.\n4. Execute `PYTHON_PRELUDE` (idempotent — only initializes once per process).\n\nKernel shutdown:\n\n- Send `{\"type\": \"exit\"}` over stdin.\n- Wait for process exit with `SHUTDOWN_GRACE_MS` budget.\n- Escalate to `SIGTERM` and finally `SIGKILL` if the process does not exit in time.\n\n## Wire protocol (NDJSON, host ↔ runner)\n\nOne JSON object per line, UTF-8, `\\n` terminated.\n\nHost → runner:\n\n```jsonc\n{\"id\": \"<reqId>\", \"code\": \"<source>\", \"silent\": false, \"storeHistory\": true}\n{\"type\": \"exit\"}\n```\n\nRunner → host:\n\n```jsonc\n{\"type\": \"started\",  \"id\": \"<reqId>\"}\n{\"type\": \"stdout\",   \"id\": \"<reqId>\", \"data\": \"...\"}\n{\"type\": \"stderr\",   \"id\": \"<reqId>\", \"data\": \"...\"}\n{\"type\": \"display\",  \"id\": \"<reqId>\", \"bundle\": {<mime>: <value>}}\n{\"type\": \"result\",   \"id\": \"<reqId>\", \"bundle\": {<mime>: <value>}}\n{\"type\": \"error\",    \"id\": \"<reqId>\", \"ename\": \"...\", \"evalue\": \"...\", \"traceback\": [\"...\"]}\n{\"type\": \"done\",     \"id\": \"<reqId>\", \"status\": \"ok\"|\"error\", \"executionCount\": N, \"cancelled\": false}\n```\n\nStatus events the prelude emits (e.g. `_emit_status(\"find\", count=…)`) ship inside display bundles under `application/x-omp-status` so the existing TUI status renderer keeps working.\n\n## Magics\n\nThe runner's source transformer rewrites IPython-style magics to plain Python calls before parsing. Supported set:\n\n| Magic                             | Effect                                                                                                                                                      |\n| --------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `%pip <args>`                     | `python -m pip <args>` with live streaming output. Newly installed packages are evicted from `sys.modules` so the next `import` picks up the fresh install. |\n| `%cd <path>`                      | `os.chdir(path)` (with `~` expansion); emits status event.                                                                                                  |\n| `%pwd`                            | Returns `os.getcwd()`.                                                                                                                                      |\n| `%ls [path]`                      | Returns `sorted(os.listdir(path))`.                                                                                                                         |\n| `%env [KEY[=VAL]]`                | List, read, or set env vars (matches prelude `env()` semantics).                                                                                            |\n| `%set_env KEY VALUE`              | Set `os.environ[KEY]`.                                                                                                                                      |\n| `%time <expr>` / `%timeit <expr>` | Time the expression; emits status event with elapsed ms.                                                                                                    |\n| `%who` / `%whos`                  | List user-namespace names.                                                                                                                                  |\n| `%reset`                          | Clear user globals and re-inject prelude.                                                                                                                   |\n| `%load <path>`                    | Read a file into a fresh cell and execute.                                                                                                                  |\n| `%run <path>`                     | `runpy.run_path` and merge globals back.                                                                                                                    |\n| `%%bash` / `%%sh`                 | Run the cell body via `bash`/`sh`.                                                                                                                          |\n| `%%capture [name]`                | Run body with stdout/stderr captured into `name`.                                                                                                           |\n| `%%timeit`                        | Time the cell body.                                                                                                                                         |\n| `%%writefile <path>`              | Write body to file.                                                                                                                                         |\n| `!cmd` / `var = !cmd`             | Run command via subprocess shell; returns an SList-style result with `.n` / `.s` helpers.                                                                   |\n| `var = %name args`                | Assignment forms work for line magics and `!cmd`.                                                                                                           |\n\nUnknown magic names raise `NameError: UsageError: ...` inside the cell.\n\n## Session persistence semantics\n\n`python.kernelMode` controls retained kernel reuse:\n\n- `session` (default)\n  - Reuses kernel sessions keyed by namespaced eval session id plus cwd.\n  - Multiple owners can share the same retained kernel for that key.\n  - Calls through the tool are exclusive, so tool invocations do not overlap.\n  - A dead retained subprocess is replaced before execution.\n  - If the subprocess dies during execution, it is replaced and the cell is retried once.\n- `per-call`\n  - Spawns a fresh subprocess for each request.\n  - Shuts the subprocess down after the request.\n  - No cross-call state persistence.\n\n### Multi-cell behavior in a single tool call\n\nPython cells run sequentially in the same selected Python kernel instance for that tool call.\n\nIf an intermediate cell fails:\n\n- Earlier cell state remains in memory.\n- Tool returns a targeted error indicating which cell failed.\n- Later cells are not executed.\n\n`reset=true` is per cell and resets that language runtime before the cell executes.\n\n## Environment filtering and runtime resolution\n\nEnvironment is filtered before launching the runner:\n\n- Allowlist includes core vars like `PATH`, `HOME`, locale vars, `VIRTUAL_ENV`, `PYTHONPATH`, etc.\n- Allow-prefixes: `LC_`, `XDG_`, `PI_`\n- Denylist strips common API keys (OpenAI/Anthropic/Gemini/etc.)\n\nRuntime selection order:\n\n1. Active/located venv (`VIRTUAL_ENV`, then `<cwd>/.venv`, `<cwd>/venv`)\n2. Managed venv at `~/.omp/python-env`\n3. `python` or `python3` on PATH\n\nWhen a venv is selected, its bin/Scripts path is prepended to `PATH`.\n\nThe runner additionally receives `PYTHONUNBUFFERED=1` and `PYTHONIOENCODING=utf-8` so streamed output reaches the host promptly.\n\n## Tool availability and mode selection\n\n`eval.py` / `eval.js` (both default `true`) plus optional boolean env flags `PI_PY` / `PI_JS` control eval backend exposure:\n\n- Python backend only (`eval.py=true`, `eval.js=false`, or `PI_PY=1 PI_JS=0`)\n- JavaScript backend only (`eval.py=false`, `eval.js=true`, or `PI_PY=0 PI_JS=1`)\n- both backends (`eval.py=true`, `eval.js=true`, or `PI_PY=1 PI_JS=1`)\n\n`PI_PY` and `PI_JS` use normal boolean flag parsing. If either env var is set, the env pair overrides the per-key settings; an unset member of the pair defaults to enabled.\n\nIf Python preflight fails and `eval.js` is enabled, `eval` remains available for `js` cells; `py` cells fail with a Python-backend availability error.\n\nPython prelude helpers include `agent(prompt, *, agent_type=\"task\", model=None, context=None, label=None, schema=None)`. It synchronously calls the host bridge, runs one subagent through the task executor, and returns the final text. When `schema` is supplied, the helper parses the subagent's JSON output and returns the object.\n\n## Execution flow and cancellation/timeout\n\n### Cell timeout\n\nEach eval cell `timeout` is in seconds, defaults to 30, and is clamped to `1..600`. It is a **wall-clock budget on the cell's own work** that the watchdog (`IdleTimeout`, `src/eval/idle-timeout.ts`) enforces, **but it is paused while a host-side `agent()`/`parallel()`/`completion()` bridge call is in flight**: those calls pump a heartbeat (`withBridgeHeartbeat`, `src/eval/heartbeat.ts`) that re-arms the watchdog, so a long fanout or a slow completion runs to completion instead of being killed mid-stream.\n\nThe heartbeat is the **sole** signal that extends the budget. Everything else the cell does — compute, `stdout`/`stderr`, `log()`/`phase()`, and ordinary (non-agent) tool calls — counts against `timeout`, so a cell that is not delegating to an agent/completion is bounded by a plain wall-clock timeout. The tool combines the caller abort signal, the session abort signal, and the watchdog's signal with `AbortSignal.any(...)`; no wall-clock deadline is passed to the backend, so neither runtime arms a competing fixed timer.\n\n### Kernel execution cancellation\n\nOn abort/timeout:\n\n- The host sends `kill(\"SIGINT\")` to the runner subprocess.\n- The runner's exec-time signal handler raises `KeyboardInterrupt` inside the user code.\n- Result includes `cancelled=true`; the timeout path annotates output as `Command timed out after <n> seconds`.\n- Between requests the runner installs `SIG_IGN` for SIGINT so a stray cancel does not tear down the kernel.\n\nIf a second cancel is required (runner stuck in C code), the host escalates to `SIGTERM` and the session restarts on the next call.\n\n### stdin behavior\n\nInteractive stdin is not supported. The runner does not forward `input()` prompts; user code that calls `input()` blocks until cancellation.\n\n## Output capture and rendering\n\n### Captured output classes\n\nFrom runner frames:\n\n- `stdout` / `stderr` → plain text chunks\n- `display` / `result` → rich display handling (MIME bundle)\n- `error` → traceback text\n- `application/x-omp-status` MIME inside `display` → structured status events\n\nDisplay MIME precedence:\n\n1. `text/markdown`\n2. `text/plain`\n3. `text/html` (converted to basic markdown)\n\nAdditionally captured as structured outputs:\n\n- `application/json` → JSON tree data\n- `image/png` / `image/jpeg` → image payloads\n- `application/x-omp-status` → status events\n\n### Matplotlib\n\nThe runner sets `MPLBACKEND=Agg` as an environ default so figures render off-screen. After every cell, `pyplot.get_fignums()` is iterated; each figure is saved to PNG, emitted as an `image/png` display, and closed.\n\n### Storage and truncation\n\nOutput is streamed through `OutputSink` and may be persisted to artifact storage. Tool results can include truncation metadata and `artifact://<id>` for full output recovery.\n\n### Renderer behavior\n\n- Tool renderer (`eval.ts`):\n  - shows code-cell blocks with per-cell status\n  - collapsed preview defaults to 10 lines\n  - supports expanded mode for all output retained in the tool result\n- Interactive renderer (`eval-execution.ts`):\n  - used for user-triggered Python execution in TUI\n  - collapsed preview defaults to 20 lines\n  - clamps very long individual lines to 4000 chars for display safety\n  - shows cancellation/error/truncation notices\n\n## Operational troubleshooting\n\n- **Python backend not available** — Check `eval.py`, `PI_PY`, and that `python`/`python3` is on PATH. If preflight fails and `eval.js` is enabled, use a `js` cell.\n- **No Python on PATH** — Install a system Python 3.8+ or place a venv at `~/.omp/python-env`. `omp setup python --check` reports the resolved interpreter.\n- **Execution hangs then times out** — Increase tool `timeout` (max 600s) if workload is legitimate. For stuck native code, cancellation triggers `SIGINT` first then escalates; the session restarts on the next request.\n- **stdin/input prompts in Python code** — `input()` is not supported; pass data programmatically.\n- **Working directory errors** — Tool validates `cwd` exists and is a directory before execution.\n\n## Relevant environment variables\n\n- `PI_PY` / `PI_JS` — eval backend exposure overrides\n- `PI_PYTHON_SKIP_CHECK=1` — bypass Python preflight/warm checks\n- `PI_PYTHON_INTEGRATION=1` — enable gated integration tests that spawn a real Python\n- `PI_PYTHON_IPC_TRACE=1` — log NDJSON frames exchanged with the runner subprocess\n",
 	"render-mermaid.md": "# RenderMermaid\n\n`RenderMermaid` is an optional built-in tool that renders Mermaid source to terminal-friendly text.\n\n## Enable it\n\nDisabled by default. Turn it on in `/settings` under **Tools → Render Mermaid**, or in `~/.omp/agent/config.yml`:\n\n```yaml\nrenderMermaid:\n  enabled: true\n```\n\n## What it does\n\n- Tool name: `render_mermaid`\n- Input: Mermaid source in the required `mermaid` field\n- Output: rendered ASCII/Unicode text, not SVG or PNG\n- Storage: when artifact storage is available, the full render is also saved as an `artifact://...`\n\nThere are no model-specific or environment-variable prerequisites. Once enabled, any model that can call built-in tools can use it.\n\n## Parameters\n\n```json\n{\n  \"mermaid\": \"graph TD\\n  A[Start] --> B[Stop]\",\n  \"config\": {\n    \"useAscii\": false,\n    \"paddingX\": 2,\n    \"paddingY\": 2,\n    \"boxBorderPadding\": 0\n  }\n}\n```\n\nAvailable `config` fields:\n\n- `useAscii` — `true` for plain ASCII, `false` for Unicode box-drawing characters (default and usually more readable)\n- `paddingX` — horizontal spacing between nodes\n- `paddingY` — vertical spacing between nodes\n- `boxBorderPadding` — inner padding inside node boxes\n\n## Current limitations\n\n`RenderMermaid` uses the `beautiful-mermaid` ASCII renderer. It works best for flowcharts and small diagrams.\n\nComplex sequence diagrams, especially with `alt` / `else` blocks, can become very wide in a terminal. That is current renderer behavior, not a provider or model configuration problem.\n\nIf a sequence diagram is hard to read:\n\n1. Keep Unicode output (`useAscii: false`)\n2. Reduce spacing with a tighter config such as `paddingX: 2`, `paddingY: 2`, `boxBorderPadding: 0`\n3. Prefer smaller sub-diagrams over one large sequence diagram\n4. Open the saved artifact if the inline preview is truncated in the TUI\n\n## Example\n\nInput:\n\n```mermaid\ngraph TD\n  A[Start] --> B{Decision}\n  B -->|Yes| C[Action]\n  B -->|No| D[End]\n```\n\nTypical result:\n\n```text\n┌─────┐\n│Start│\n└─────┘\n   │\n   ▼\n┌────────┐\n│Decision│\n└────────┘\n```\n",
 	"resolve-tool-runtime.md": "# Resolve tool runtime internals\n\nThis document explains how preview/apply workflows are modeled in coding-agent and how built-in or custom tools can participate via the tool-choice queue and `pushPendingAction`.\n\n## Scope and key files\n\n- [`src/tools/resolve.ts`](../packages/coding-agent/src/tools/resolve.ts)\n- [`src/tools/ast-edit.ts`](../packages/coding-agent/src/tools/ast-edit.ts)\n- [`src/extensibility/custom-tools/types.ts`](../packages/coding-agent/src/extensibility/custom-tools/types.ts)\n- [`src/extensibility/custom-tools/loader.ts`](../packages/coding-agent/src/extensibility/custom-tools/loader.ts)\n- [`src/sdk.ts`](../packages/coding-agent/src/sdk.ts)\n\n## What `resolve` does\n\n`resolve` is a hidden tool that finalizes a pending preview action.\n\n- `action: \"apply\"` executes the queued action's `apply(reason, extra)` callback and returns that result with resolve metadata.\n- `action: \"discard\"` invokes `reject(reason, extra)` if provided; otherwise returns `Discarded: <label>. Reason: <reason>`.\n- `extra` is optional free-form metadata. Queue handlers receive it; producers decide whether it has meaning.\n\nIf no pending action exists, `resolve` fails with:\n\n- `No pending action to resolve. Nothing to apply or discard.`\n\n## Pending actions use the tool-choice queue\n\nPreview producers call `queueResolveHandler(...)`, which pushes a one-shot forced `resolve` directive onto the session tool-choice queue and adds a `resolve-reminder` steering message.\n\nRuntime behavior:\n\n- the queued handler owns the pending `apply`/`reject` callbacks,\n- `resolve` looks up the current queue invoker with `session.peekQueueInvoker()`,\n- if the model rejects the forced tool choice, the queue directive is requeued,\n- `resolve` does not maintain a separate pending-action stack.\n\n`resolve` also checks a standing resolve handler after the queue invoker; this is used by long-lived approval flows that are not ordinary preview tool calls.\n\nMultiple pending previews therefore follow the active tool-choice queue ordering, not an independent pending-action store. If an apply callback throws, the queued helper re-pushes the same resolve directive and reminder so the preview can still be discarded or retried.\n\n## Built-in producer example (`ast_edit`)\n\n`ast_edit` previews structural replacements first. When the preview has replacements and is not applied yet, it queues a resolve handler that contains:\n\n- label (human-readable summary)\n- `sourceToolName` (`ast_edit`)\n- `apply(reason: string, extra?: Record<string, unknown>)` callback that reruns AST edit with `dryRun: false`\n\n`resolve(action=\"apply\", reason=\"...\")` passes `reason` into this callback. `ast_edit` currently ignores `extra`.\n\n## Custom tools: `pushPendingAction`\n\nCustom tools can register resolve-compatible pending actions through `CustomToolAPI.pushPendingAction(...)`. The custom tool loader forwards these actions to `queueResolveHandler(...)` when that hook is available.\n\n`CustomToolPendingAction`:\n\n- `label: string` (required)\n- `apply(reason: string): Promise<AgentToolResult<unknown>>` (required) — invoked on apply; `reason` is the string passed to `resolve`\n- `reject?(reason: string): Promise<AgentToolResult<unknown> | undefined>` (optional) — invoked on discard; return value replaces the default \"Discarded\" message if provided\n- `details?: unknown` exists on the public custom-tool type but is not currently forwarded by the loader into resolve metadata\n- `sourceToolName?: string` (optional, defaults to `\"custom_tool\"`)\n\n### Minimal usage example\n\n```ts\nimport type { CustomToolFactory } from \"@oh-my-pi/pi-coding-agent\";\n\nconst factory: CustomToolFactory = (pi) => ({\n  name: \"batch_rename_preview\",\n  label: \"Batch Rename Preview\",\n  description: \"Previews renames and defers commit to resolve\",\n  parameters: pi.zod.object({\n    files: pi.zod.array(pi.zod.string()),\n  }),\n\n  async execute(_toolCallId, params) {\n    const previewSummary = `Prepared rename plan for ${params.files.length} files`;\n\n    pi.pushPendingAction({\n      label: `Batch rename: ${params.files.length} files`,\n      sourceToolName: \"batch_rename_preview\",\n      apply: async (reason) => {\n        // apply writes here\n        return {\n          content: [\n            { type: \"text\", text: `Applied batch rename. Reason: ${reason}` },\n          ],\n        };\n      },\n      reject: async (reason) => {\n        // optional: cleanup or notify on discard\n        return {\n          content: [\n            { type: \"text\", text: `Discarded batch rename. Reason: ${reason}` },\n          ],\n        };\n      },\n    });\n\n    return {\n      content: [\n        {\n          type: \"text\",\n          text: `${previewSummary}. Call resolve to apply or discard.`,\n        },\n      ],\n    };\n  },\n});\n\nexport default factory;\n```\n\n## Runtime availability and failures\n\n`pushPendingAction` is wired by the custom tool loader through the active session's resolve queue hook.\n\nIf the runtime did not provide the resolve queue hook, `pushPendingAction` throws:\n\n- `Pending action store unavailable for custom tools in this runtime.`\n\n## Tool-choice behavior\n\nWhen `queueResolveHandler(...)` registers a preview, the agent runtime forces a one-shot `resolve` tool choice so pending previews are explicitly finalized before normal tool flow continues.\n\n## Developer guidance\n\n- Use pending actions only for destructive or high-impact operations that should support explicit apply/discard.\n- Keep `label` concise and specific; it is shown in resolve renderer output.\n- Ensure `apply(reason)` is deterministic and idempotent enough for one-shot execution; `reason` is informational and should not change behavior.\n- Implement `reject(reason)` when the discard needs cleanup (temp state, locks, notifications); omit it for stateless previews where the default message suffices.\n- If your tool can stage multiple previews, remember they are mediated by the tool-choice queue rather than a separate pending-action stack.\n",
 	"rpc.md": "# RPC Protocol Reference\n\nRPC mode runs the coding agent as a newline-delimited JSON protocol over stdio.\n\n- **stdin**: commands (`RpcCommand`), extension UI responses, and host-tool updates/results\n- **stdout**: a ready frame, command responses (`RpcResponse`), session/agent events, extension UI requests, host-tool requests/cancellations\n\nPrimary implementation:\n\n- `src/modes/rpc/rpc-mode.ts`\n- `src/modes/rpc/rpc-types.ts`\n- `src/session/agent-session.ts`\n- `packages/agent/src/agent.ts`\n- `packages/agent/src/agent-loop.ts`\n\n## Startup\n\n```bash\nomp --mode rpc [regular CLI options]\n```\n\nBehavior notes:\n\n- `@file` CLI arguments are rejected in RPC mode.\n- RPC mode disables automatic session title generation by default to avoid an extra model call.\n- RPC mode resets workflow-altering `todo.*`, `task.*`, `async.*`, and `bash.autoBackground.*` settings to their built-in defaults instead of inheriting user overrides.\n- The process reads stdin as JSONL (`readJsonl(Bun.stdin.stream())`).\n- At startup it writes `{ \"type\": \"ready\" }` before processing commands.\n- When stdin closes, pending host-tool calls are rejected and the process exits with code `0`.\n- Responses/events are written as one JSON object per line.\n\n## Transport and Framing\n\nEach frame is a single JSON object followed by `\\n`.\n\nThere is no envelope beyond the object shape itself.\n\n### Outbound frame categories (stdout)\n\n1. Ready frame (`{ type: \"ready\" }`)\n2. `RpcResponse` (`{ type: \"response\", ... }`)\n3. `AgentSessionEvent` objects (`agent_start`, `message_update`, etc.)\n4. `RpcExtensionUIRequest` (`{ type: \"extension_ui_request\", ... }`)\n5. Host tool requests/cancellations (`host_tool_call`, `host_tool_cancel`)\n6. Host URI requests/cancellations (`host_uri_request`, `host_uri_cancel`)\n7. Extension errors (`{ type: \"extension_error\", extensionPath, event, error }`)\n\n### Inbound frame categories (stdin)\n\n1. `RpcCommand`\n2. `RpcExtensionUIResponse` (`{ type: \"extension_ui_response\", ... }`)\n3. Host tool updates/results (`host_tool_update`, `host_tool_result`)\n4. Host URI results (`host_uri_result`)\n\n## Request/Response Correlation\n\nAll commands accept optional `id?: string`.\n\n- If provided, normal command responses echo the same `id`.\n- `RpcClient` relies on this for pending-request resolution.\n\nImportant edge behavior from runtime:\n\n- Unknown command responses are emitted with `id: undefined` (even if the request had an `id`).\n- Parse/handler exceptions in the input loop emit `command: \"parse\"` with `id: undefined`.\n- `prompt` and `abort_and_prompt` return immediate success, then may emit a later error response with the **same** id if async prompt scheduling fails.\n\n## Command Schema (canonical)\n\n`RpcCommand` is defined in `src/modes/rpc/rpc-types.ts`:\n\n### Prompting\n\n- `{ id?, type: \"prompt\", message: string, images?: ImageContent[], streamingBehavior?: \"steer\" | \"followUp\" }`\n- `{ id?, type: \"steer\", message: string, images?: ImageContent[] }`\n- `{ id?, type: \"follow_up\", message: string, images?: ImageContent[] }`\n- `{ id?, type: \"abort\" }`\n- `{ id?, type: \"abort_and_prompt\", message: string, images?: ImageContent[] }`\n- `{ id?, type: \"new_session\", parentSession?: string }`\n\n### State\n\n- `{ id?, type: \"get_state\" }`\n- `{ id?, type: \"set_todos\", phases: TodoPhase[] }`\n- `{ id?, type: \"set_host_tools\", tools: RpcHostToolDefinition[] }`\n- `{ id?, type: \"set_host_uri_schemes\", schemes: RpcHostUriSchemeDefinition[] }`\n\n### Model\n\n- `{ id?, type: \"set_model\", provider: string, modelId: string }`\n- `{ id?, type: \"cycle_model\" }`\n- `{ id?, type: \"get_available_models\" }`\n\n### Thinking\n\n- `{ id?, type: \"set_thinking_level\", level: ThinkingLevel }`\n- `{ id?, type: \"cycle_thinking_level\" }`\n\n### Queue modes\n\n- `{ id?, type: \"set_steering_mode\", mode: \"all\" | \"one-at-a-time\" }`\n- `{ id?, type: \"set_follow_up_mode\", mode: \"all\" | \"one-at-a-time\" }`\n- `{ id?, type: \"set_interrupt_mode\", mode: \"immediate\" | \"wait\" }`\n\n### Compaction\n\n- `{ id?, type: \"compact\", customInstructions?: string }`\n- `{ id?, type: \"set_auto_compaction\", enabled: boolean }`\n\n### Retry\n\n- `{ id?, type: \"set_auto_retry\", enabled: boolean }`\n- `{ id?, type: \"abort_retry\" }`\n\n### Bash\n\n- `{ id?, type: \"bash\", command: string }`\n- `{ id?, type: \"abort_bash\" }`\n\n### Session\n\n- `{ id?, type: \"get_session_stats\" }`\n- `{ id?, type: \"export_html\", outputPath?: string }`\n- `{ id?, type: \"switch_session\", sessionPath: string }`\n- `{ id?, type: \"branch\", entryId: string }`\n- `{ id?, type: \"get_branch_messages\" }`\n- `{ id?, type: \"get_last_assistant_text\" }`\n- `{ id?, type: \"set_session_name\", name: string }`\n- `{ id?, type: \"handoff\", customInstructions?: string }`\n\n### Messages\n\n- `{ id?, type: \"get_messages\" }`\n\n### Login\n\n- `{ id?, type: \"get_login_providers\" }`\n- `{ id?, type: \"login\", providerId: string }`\n\n## Response Schema\n\nAll command results use `RpcResponse`:\n\n- Success: `{ id?, type: \"response\", command: <command>, success: true, data?: ... }`\n- Failure: `{ id?, type: \"response\", command: string, success: false, error: string }`\n\nData payloads are command-specific and defined in `rpc-types.ts`.\n\n### `get_state` payload\n\n```json\n{\n  \"model\": { \"provider\": \"...\", \"id\": \"...\" },\n  \"thinkingLevel\": \"off|minimal|low|medium|high|xhigh\",\n  \"isStreaming\": false,\n  \"isCompacting\": false,\n  \"steeringMode\": \"all|one-at-a-time\",\n  \"followUpMode\": \"all|one-at-a-time\",\n  \"interruptMode\": \"immediate|wait\",\n  \"sessionFile\": \"...\",\n  \"sessionId\": \"...\",\n  \"sessionName\": \"...\",\n  \"autoCompactionEnabled\": true,\n  \"messageCount\": 0,\n  \"queuedMessageCount\": 0,\n  \"todoPhases\": [\n    {\n      \"id\": \"phase-1\",\n      \"name\": \"Todos\",\n      \"tasks\": [\n        {\n          \"id\": \"task-1\",\n          \"content\": \"Map the tool surface\",\n          \"status\": \"in_progress\"\n        }\n      ]\n    }\n  ],\n  \"systemPrompt\": [\"...\"],\n  \"dumpTools\": [\n    {\n      \"name\": \"read\",\n      \"description\": \"Read files and URLs\",\n      \"parameters\": {}\n    }\n  ],\n  \"contextUsage\": {\n    \"tokens\": 1100,\n    \"contextWindow\": 200000,\n    \"percent\": 0.55\n  }\n}\n```\n\n### `set_todos` payload\n\nReplaces the in-memory todo state for the current session and returns the normalized phase list:\n\n```json\n{\n  \"id\": \"req_2\",\n  \"type\": \"set_todos\",\n  \"phases\": [\n    {\n      \"id\": \"phase-1\",\n      \"name\": \"Evaluation\",\n      \"tasks\": [\n        {\n          \"id\": \"task-1\",\n          \"content\": \"Map the read tool surface\",\n          \"status\": \"in_progress\"\n        },\n        {\n          \"id\": \"task-2\",\n          \"content\": \"Exercise edit operations\",\n          \"status\": \"pending\"\n        }\n      ]\n    }\n  ]\n}\n```\n\nThis is useful for hosts that want to pre-seed a plan before the first prompt.\n\n### `set_host_tools` payload\n\nReplaces the current set of host-owned tools that the RPC server may call back\ninto over stdio:\n\n```json\n{\n  \"id\": \"req_3\",\n  \"type\": \"set_host_tools\",\n  \"tools\": [\n    {\n      \"name\": \"echo_host\",\n      \"label\": \"Echo Host\",\n      \"description\": \"Echo a value from the embedding host\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"message\": { \"type\": \"string\" }\n        },\n        \"required\": [\"message\"],\n        \"additionalProperties\": false\n      }\n    }\n  ]\n}\n```\n\nThe response payload is:\n\n```json\n{\n  \"toolNames\": [\"echo_host\"]\n}\n```\n\nThese tools are added to the active session tool registry before the next model\ncall. Re-sending `set_host_tools` replaces the previous host-owned set.\n\n### `set_host_uri_schemes` payload\n\nReplaces the current set of host-owned URL schemes the RPC server should\ndispatch reads/writes through:\n\n```json\n{\n  \"id\": \"req_4\",\n  \"type\": \"set_host_uri_schemes\",\n  \"schemes\": [\n    {\n      \"scheme\": \"db\",\n      \"description\": \"Virtual db row files\",\n      \"writable\": true,\n      \"immutable\": false\n    }\n  ]\n}\n```\n\nThe response payload is:\n\n```json\n{\n  \"schemes\": [\"db\"]\n}\n```\n\nSchemes are case-insensitive on the wire and normalized to lowercase before\nthe response is sent. Re-sending `set_host_uri_schemes` replaces the entire\nprevious set — schemes missing from the new list are unregistered.\n\n## Event Stream Schema\n\nRPC mode forwards `AgentSessionEvent` objects from `AgentSession.subscribe(...)`.\n\nCommon event types:\n\n- `agent_start`, `agent_end`\n- `turn_start`, `turn_end`\n- `message_start`, `message_update`, `message_end`\n- `tool_execution_start`, `tool_execution_update`, `tool_execution_end`\n- `auto_compaction_start`, `auto_compaction_end`\n- `auto_retry_start`, `auto_retry_end`\n- `ttsr_triggered`\n- `todo_reminder`\n- `todo_auto_clear`\n\nExtension runner errors are emitted separately as:\n\n```json\n{\n  \"type\": \"extension_error\",\n  \"extensionPath\": \"...\",\n  \"event\": \"...\",\n  \"error\": \"...\"\n}\n```\n\n`message_update` includes streaming deltas in `assistantMessageEvent` (text/thinking/toolcall deltas).\n\n## Prompt/Queue Concurrency and Ordering\n\nThis is the most important operational behavior.\n\n### Immediate ack vs completion\n\n`prompt` and `abort_and_prompt` are **acknowledged immediately**:\n\n```json\n{ \"id\": \"req_1\", \"type\": \"response\", \"command\": \"prompt\", \"success\": true }\n```\n\nThat means:\n\n- command acceptance != run completion\n- final completion is observed via `agent_end`\n\n### While streaming\n\n`AgentSession.prompt()` requires `streamingBehavior` during active streaming:\n\n- `\"steer\"` => queued steering message (interrupt path)\n- `\"followUp\"` => queued follow-up message (post-turn path)\n\nIf omitted during streaming, prompt fails.\n\n### Queue defaults\n\nFrom `packages/agent/src/agent.ts` defaults:\n\n- `steeringMode`: `\"one-at-a-time\"`\n- `followUpMode`: `\"one-at-a-time\"`\n- `interruptMode`: `\"immediate\"`\n\n### Mode semantics\n\n- `set_steering_mode` / `set_follow_up_mode`\n  - `\"one-at-a-time\"`: dequeue one queued message per turn\n  - `\"all\"`: dequeue entire queue at once\n- `set_interrupt_mode`\n  - `\"immediate\"`: tool execution checks steering between tool calls; pending steering can abort remaining tool calls in the turn\n  - `\"wait\"`: defer steering until turn completion\n\n## Extension UI Sub-Protocol\n\nExtensions in RPC mode use request/response UI frames.\n\n### Outbound request\n\n`RpcExtensionUIRequest` (`type: \"extension_ui_request\"`) methods:\n\n- `select`, `confirm`, `input`, `editor`, `cancel`\n- `notify`, `setStatus`, `setWidget`, `setTitle`, `set_editor_text`\n- `open_url` (emitted by RPC login flows)\n\nRuntime note:\n\n- Automatic session title generation is disabled in RPC mode, and `setTitle` UI\n  requests are also suppressed by default because most hosts do not have a\n  meaningful terminal-title surface. Set `PI_RPC_EMIT_TITLE=1` to opt back in to\n  the UI event only.\n\nExample:\n\n```json\n{\n  \"type\": \"extension_ui_request\",\n  \"id\": \"123\",\n  \"method\": \"confirm\",\n  \"title\": \"Confirm\",\n  \"message\": \"Continue?\",\n  \"timeout\": 30000\n}\n```\n\n### Inbound response\n\n`RpcExtensionUIResponse` (`type: \"extension_ui_response\"`):\n\n- `{ type: \"extension_ui_response\", id: string, value: string }`\n- `{ type: \"extension_ui_response\", id: string, confirmed: boolean }`\n- `{ type: \"extension_ui_response\", id: string, cancelled: true, timedOut?: boolean }`\n\nIf a dialog has a timeout, RPC mode resolves to a default value when timeout/abort fires.\n\n## Host Tool Sub-Protocol\n\nRPC hosts can expose custom tools to the agent by sending `set_host_tools`, then\nserving execution requests over the same transport.\n\n### Outbound request\n\nWhen the agent wants the host to execute one of those tools, RPC mode emits:\n\n```json\n{\n  \"type\": \"host_tool_call\",\n  \"id\": \"host_1\",\n  \"toolCallId\": \"toolu_123\",\n  \"toolName\": \"echo_host\",\n  \"arguments\": { \"message\": \"hello\" }\n}\n```\n\nIf the tool execution is later aborted, RPC mode emits:\n\n```json\n{\n  \"type\": \"host_tool_cancel\",\n  \"id\": \"host_cancel_1\",\n  \"targetId\": \"host_1\"\n}\n```\n\n### Inbound updates and completion\n\nHosts can optionally stream progress:\n\n```json\n{\n  \"type\": \"host_tool_update\",\n  \"id\": \"host_1\",\n  \"partialResult\": {\n    \"content\": [{ \"type\": \"text\", \"text\": \"working\" }]\n  }\n}\n```\n\nCompletion uses:\n\n```json\n{\n  \"type\": \"host_tool_result\",\n  \"id\": \"host_1\",\n  \"result\": {\n    \"content\": [{ \"type\": \"text\", \"text\": \"done\" }]\n  }\n}\n```\n\nSet top-level `isError: true` on `host_tool_result` to reject the pending host tool call and surface the returned text content as a tool error.\n\n## Host URI Sub-Protocol\n\nRPC hosts can also own custom URL schemes (virtual files). After\n`set_host_uri_schemes`, every read of `<scheme>://…` and write of\n`<scheme>://…` (when registered as `writable`) is bounced back to the host\nover the same transport.\n\n### Outbound request\n\nWhen a session tool resolves a host-owned URL, RPC mode emits:\n\n```json\n{\n  \"type\": \"host_uri_request\",\n  \"id\": \"uri_1\",\n  \"operation\": \"read\",\n  \"url\": \"db://users/42\"\n}\n```\n\nWrites look the same with `\"operation\": \"write\"` and an additional\n`\"content\": \"...\"` field carrying the full replacement bytes.\n\nIf the request is later aborted (caller cancels, session ends), RPC mode\nemits:\n\n```json\n{\n  \"type\": \"host_uri_cancel\",\n  \"id\": \"uri_cancel_1\",\n  \"targetId\": \"uri_1\"\n}\n```\n\n### Inbound result\n\nFor successful reads:\n\n```json\n{\n  \"type\": \"host_uri_result\",\n  \"id\": \"uri_1\",\n  \"content\": \"id=42\\nname=Alice\\n\",\n  \"contentType\": \"text/plain\",\n  \"notes\": [\"fresh from cache\"],\n  \"immutable\": false\n}\n```\n\nFor successful writes, omit content:\n\n```json\n{ \"type\": \"host_uri_result\", \"id\": \"uri_1\" }\n```\n\nTo reject the request, set `isError: true` and either populate `error` with\na message or fall back to `content` for textual error surfacing:\n\n```json\n{\n  \"type\": \"host_uri_result\",\n  \"id\": \"uri_1\",\n  \"isError\": true,\n  \"error\": \"row 42 not found\"\n}\n```\n\n### Constraints\n\n- The agent's `edit` tool does not target host URIs. Hosts that want to\n  mutate virtual files expose `write` and let the model use the `write` tool\n  with replacement content.\n- Schemes are global to the process; `set_host_uri_schemes` replaces the\n  previous set, unregistering anything not in the new list.\n- Schemes are normalized to lowercase before registration.\n\n## Error Model and Recoverability\n\n### Command-level failures\n\nFailures are `success: false` with string `error`.\n\n```json\n{\n  \"id\": \"req_2\",\n  \"type\": \"response\",\n  \"command\": \"set_model\",\n  \"success\": false,\n  \"error\": \"Model not found: provider/model\"\n}\n```\n\n### Recoverability expectations\n\n- Most command failures are recoverable; process remains alive.\n- Malformed JSONL / parse-loop exceptions emit a `parse` error response and continue reading subsequent lines.\n- Empty `set_session_name` is rejected (`Session name cannot be empty`).\n- Extension UI responses with unknown `id` are ignored.\n- Process termination conditions are stdin close or explicit extension-triggered shutdown after the current command.\n\n## Compact Command Flows\n\n### 1) Prompt and stream\n\nstdin:\n\n```json\n{ \"id\": \"req_1\", \"type\": \"prompt\", \"message\": \"Summarize this repo\" }\n```\n\nstdout sequence (typical):\n\n```json\n{ \"id\": \"req_1\", \"type\": \"response\", \"command\": \"prompt\", \"success\": true }\n{ \"type\": \"agent_start\" }\n{ \"type\": \"message_update\", \"assistantMessageEvent\": { \"type\": \"text_delta\", \"delta\": \"...\" }, \"message\": { \"role\": \"assistant\", \"content\": [] } }\n{ \"type\": \"agent_end\", \"messages\": [] }\n```\n\n### 2) Prompt during streaming with explicit queue policy\n\nstdin:\n\n```json\n{\n  \"id\": \"req_2\",\n  \"type\": \"prompt\",\n  \"message\": \"Also include risks\",\n  \"streamingBehavior\": \"followUp\"\n}\n```\n\n### 3) Inspect and tune queue behavior\n\nstdin:\n\n```json\n{ \"id\": \"q1\", \"type\": \"get_state\" }\n{ \"id\": \"q2\", \"type\": \"set_steering_mode\", \"mode\": \"all\" }\n{ \"id\": \"q3\", \"type\": \"set_interrupt_mode\", \"mode\": \"wait\" }\n```\n\n### 4) Extension UI round trip\n\nstdout:\n\n```json\n{\n  \"type\": \"extension_ui_request\",\n  \"id\": \"ui_7\",\n  \"method\": \"input\",\n  \"title\": \"Branch name\",\n  \"placeholder\": \"feature/...\"\n}\n```\n\nstdin:\n\n```json\n{ \"type\": \"extension_ui_response\", \"id\": \"ui_7\", \"value\": \"feature/rpc-host\" }\n```\n\n## Notes on `RpcClient` helper\n\n`src/modes/rpc/rpc-client.ts` is a convenience wrapper, not the protocol definition.\n\nCurrent helper characteristics:\n\n- Spawns `bun <cliPath> --mode rpc`\n- Correlates responses by generated `req_<n>` ids\n- Dispatches recognized core `AgentEvent` types to listeners\n- Supports host-owned custom tools via `setCustomTools()` and automatic handling of `host_tool_call` / `host_tool_cancel`\n- Wraps common protocol commands including OAuth `getLoginProviders()` / `login(...)`; use raw protocol frames for any surface not wrapped by the helper.\n\nUse raw protocol frames if you need complete surface coverage.\n",
@@ -74,15 +75,15 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"tools/browser.md": "# browser\n\n> Open, reuse, close, and script Puppeteer tabs against headless Chromium or CDP-attached apps.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/browser.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/browser.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/browser/tab-supervisor.ts` — global tab registry; worker lifecycle; run/close coordination.\n  - `packages/coding-agent/src/tools/browser/tab-worker.ts` — executes `run` code; implements the `tab` helper API.\n  - `packages/coding-agent/src/tools/browser/tab-worker-entry.ts` — worker-thread transport bootstrap.\n  - `packages/coding-agent/src/tools/browser/registry.ts` — browser-handle registry keyed by browser kind.\n  - `packages/coding-agent/src/tools/browser/launch.ts` — Puppeteer loading, Chromium resolution/download, headless launch, stealth injection.\n  - `packages/coding-agent/src/tools/browser/attach.ts` — CDP attach/reuse, target picking, spawned-app process handling.\n  - `packages/coding-agent/src/tools/browser/tab-protocol.ts` — worker init/run/result message schema.\n  - `packages/coding-agent/src/tools/browser/readable.ts` — `tab.extract()` readability extraction.\n  - `packages/coding-agent/src/tools/browser/render.ts` — TUI rendering for `open`/`close` status lines and `run` JS cells.\n  - `packages/coding-agent/src/tools/puppeteer/00_stealth_tampering.txt` — mask patched functions/descriptors as native.\n  - `packages/coding-agent/src/tools/puppeteer/01_stealth_activity.txt` — synthesize visibility/focus/scroll activity.\n  - `packages/coding-agent/src/tools/puppeteer/02_stealth_hairline.txt` — fix Modernizr hairline detection.\n  - `packages/coding-agent/src/tools/puppeteer/03_stealth_botd.txt` — spoof `navigator.webdriver`, `window.chrome`, and Chrome fingerprint surfaces.\n  - `packages/coding-agent/src/tools/puppeteer/04_stealth_iframe.txt` — patch iframe `contentWindow`/`srcdoc` behavior.\n  - `packages/coding-agent/src/tools/puppeteer/05_stealth_webgl.txt` — spoof WebGL vendor/renderer/precision.\n  - `packages/coding-agent/src/tools/puppeteer/06_stealth_screen.txt` — normalize screen/viewport/device-pixel-ratio values.\n  - `packages/coding-agent/src/tools/puppeteer/07_stealth_fonts.txt` — spoof local fonts and perturb canvas text rendering.\n  - `packages/coding-agent/src/tools/puppeteer/08_stealth_audio.txt` — spoof audio latency/sample-rate and perturb offline rendering.\n  - `packages/coding-agent/src/tools/puppeteer/09_stealth_locale.txt` — force locale/languages/timezone/date strings.\n  - `packages/coding-agent/src/tools/puppeteer/10_stealth_plugins.txt` — synthesize `navigator.plugins`/`navigator.mimeTypes`.\n  - `packages/coding-agent/src/tools/puppeteer/11_stealth_hardware.txt` — spoof `navigator.hardwareConcurrency`.\n  - `packages/coding-agent/src/tools/puppeteer/12_stealth_codecs.txt` — spoof media codec support.\n  - `packages/coding-agent/src/tools/puppeteer/13_stealth_worker.txt` — carry UA/platform spoofing into `Worker`/`SharedWorker`.\n\n## Inputs\n\n### Shared fields\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | `\"open\" \\| \"close\" \\| \"run\"` | Yes | Dispatches to the open/close/run path. |\n| `name` | `string` | No | Tab id. Defaults to `\"main\"`. Tabs live in a process-global map, so the same name is reused across later calls and in-process subagents until closed. |\n| `timeout` | `number` | No | Tool wall-clock timeout in seconds. Defaults to `30`; clamped to the browser tool range before execution. |\n\n### `action: \"open\"`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `url` | `string` | No | Navigate after the tab is ready. Existing reusable tabs also navigate when `url` is supplied. |\n| `viewport` | `{ width: number; height: number; scale?: number }` | No | Requested viewport. For headless launch this becomes the initial viewport; for a page it is applied with `page.setViewport()`. `scale` maps to Puppeteer `deviceScaleFactor`. |\n| `wait_until` | `\"load\" \\| \"domcontentloaded\" \\| \"networkidle0\" \\| \"networkidle2\"` | No | Navigation wait condition. Defaults to `\"load\"` where omitted, including `open` navigation and later `tab.goto(...)`. |\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, defaulting to `waitUntil: \"load\"` when `wait_until` is omitted.\n6. New tabs build a `WorkerInitPayload` in `buildInitPayload()`:\n   - headless mode sends `url`, `waitUntil`, `viewport`, `dialogs`, and timeout; the worker defaults missing `waitUntil` to `\"load\"`.\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 `300` 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 after cwd resolution, not an app bundle directory path.\n- Spawn/attach failures are wrapped into `ToolError`s such as `Timed out waiting for CDP endpoint ...`, `Failed to attach to ...`, or `Connected to ... but puppeteer.connect failed: ...`.\n- `tab` helper errors are user-visible `ToolError`s, including unsupported selector prefix, stale/unknown element id, invalid drag target, missing upload files, non-`<select>` for `tab.select()`, non-file-input for `tab.uploadFile()`, and screenshot selector misses.\n- On run timeout, the worker reports `Browser code execution timed out after <ms>ms`; the supervisor may escalate to `Browser code execution hung past grace; tab killed` if the worker does not respond after the grace window.\n\n## Notes\n- `loadPuppeteer()` and `loadPuppeteerInWorker()` temporarily redirect `cwd` to a safe Puppeteer directory before importing `puppeteer-core`, because Puppeteer probes the current working directory during module load.\n- Headless launch prefers a detected system Chrome/Chromium, then `PUPPETEER_EXECUTABLE_PATH`, and only then downloads Chromium.\n- Headless launch always passes `--no-sandbox`, `--disable-setuid-sandbox`, `--disable-blink-features=AutomationControlled`, and a `--window-size=...` matching the initial viewport. It also ignores Puppeteer default args `--disable-extensions`, `--disable-default-apps`, and `--disable-component-extensions-with-background-pages`.\n- Proxy-related env vars only affect headless launch: `PUPPETEER_PROXY`, `PUPPETEER_PROXY_BYPASS_LOOPBACK`, and `PUPPETEER_PROXY_IGNORE_CERT_ERRORS`.\n- Stealth patches are applied only in headless mode. Spawned or externally connected browsers are intentionally left untouched.\n- `applyStealthPatches()` also strips Puppeteer's `//# sourceURL=__puppeteer_evaluation_script__` suffix from CDP `Runtime.evaluate` / `Runtime.callFunctionOn` payloads.\n- `tab.extract()` reads `page.content()`, runs Readability first, then falls back to `main article`/`article`/`main`/`[role='main']`/`body`, and returns `null` if neither extraction path yields content.\n- `close(all: true, kill: false)` disconnects from spawned/connected browsers when the last tab closes but leaves spawned app processes running.\n- Headless orphan cleanup is best-effort: if a worker dies before closing its page, the supervisor searches browser targets by `targetId` and closes that page.\n- Console methods inside `run` do not appear in tool output; they are forwarded as debug/warn/error logs through the worker transport.",
 	"tools/checkpoint.md": "# checkpoint\n\n> Mark the current top-level conversation state so later `rewind` can collapse exploratory context into a report.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/checkpoint.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/checkpoint.md`\n- Key collaborators:\n  - `packages/coding-agent/src/session/agent-session.ts` — captures the active checkpoint after tool success.\n  - `packages/coding-agent/src/session/session-manager.ts` — persists the normal session entry stream; not the active checkpoint marker.\n  - `packages/coding-agent/src/tools/index.ts` — registers the tool and gates it behind `checkpoint.enabled`.\n  - `packages/coding-agent/src/config/settings-schema.ts` — defines the disabled-by-default feature flag.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `goal` | `string` | Yes | Investigation goal. Required by the schema and echoed in the tool result. |\n\n## Outputs\nThe tool returns a single text result plus structured details:\n\n- text body:\n  - `Checkpoint created.`\n  - `Goal: <goal>`\n  - `Run your investigation, then call rewind with a concise report.`\n- `details`:\n  - `goal: string`\n  - `startedAt: string` — ISO timestamp created inside `CheckpointTool.execute()`\n\nNo checkpoint ID, artifact URI, job handle, file path, or restore token is returned.\n\n## Flow\n1. `CheckpointTool.createIf()` in `packages/coding-agent/src/tools/checkpoint.ts` returns `null` for subagents by checking `session.taskDepth`; only top-level sessions can see the tool.\n2. `CheckpointTool.execute()` rejects subagent calls again with `ToolError(\"Checkpoint not available in subagents.\")`.\n3. It rejects nested checkpoints with `ToolError(\"Checkpoint already active.\")` when `session.getCheckpointState?.()` is already set.\n4. It creates `startedAt = new Date().toISOString()` and returns a normal `toolResult()` payload. The tool itself does not persist anything.\n5. On the later `tool_execution_end` event, `AgentSession` in `packages/coding-agent/src/session/agent-session.ts` detects successful `checkpoint` execution and captures three in-memory fields:\n   - `checkpointMessageCount` — current `agent.state.messages.length`, after the checkpoint tool result has already been appended\n   - `checkpointEntryId` — `sessionManager.getEntries().at(-1)?.id ?? null`, i.e. the last persisted session entry ID at checkpoint time\n   - `startedAt` — copied from tool details or regenerated\n6. `AgentSession` stores that object in its private `#checkpointState` field and clears `#pendingRewindReport`.\n\n## Side Effects\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Sets `AgentSession.#checkpointState` in memory.\n  - Records the checkpoint boundary as a message count plus a session entry ID.\n  - Enables the later yield guard: if a checkpoint is active and no rewind report is pending, `#enforceRewindBeforeYield()` injects a developer-role warning and schedules another turn.\n- User-visible prompts / interactive UI\n  - The tool result tells the model to call `rewind` after the investigation.\n  - If the agent tries to `yield` first, `AgentSession` injects:\n\n```text\n<system-warning>\nYou are in an active checkpoint. You MUST call rewind with your investigation findings before yielding. Do NOT yield without completing the checkpoint.\n</system-warning>\n```\n\n## Limits & Caps\n- Availability is gated by `checkpoint.enabled`, default `false`, in `packages/coding-agent/src/config/settings-schema.ts`.\n- The tool is registered as discoverable in `packages/coding-agent/src/tools/index.ts`.\n- Only one active checkpoint is allowed per top-level session.\n- Checkpoint state is not persisted as a dedicated session entry. If the process exits, a resumed session can reload the conversation history, but not the live `#checkpointState` guard.\n- Session persistence still applies to the ordinary checkpoint tool call message. Global session persistence truncation is `MAX_PERSIST_CHARS = 500_000` in `packages/coding-agent/src/session/session-manager.ts`.\n\n## Errors\n- `ToolError(\"Checkpoint not available in subagents.\")` — thrown for subagent sessions.\n- `ToolError(\"Checkpoint already active.\")` — thrown when a prior checkpoint has not been rewound or cleared.\n- The tool body has no local `try/catch`; unexpected exceptions propagate.\n\n## Notes\n- Despite the summary string `Create a git-based checkpoint to save and restore session state`, the implementation does not call git and does not snapshot filesystem state.\n- Captured state is conversation/session metadata only:\n  - in-memory message count\n  - session entry ID in the session tree\n  - timestamp\n- Not captured:\n  - working tree contents\n  - staged changes\n  - artifacts\n  - blob-store contents\n  - SQLite history rows from `packages/coding-agent/src/session/history-storage.ts`\n  - auth or agent records from `packages/coding-agent/src/session/agent-storage.ts`\n",
 	"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` uses this when provided; otherwise it falls back to the current stopped location's instruction-pointer reference if the adapter supplied one. |\n| `instruction_reference` | `string` | No | Instruction breakpoint reference; required for instruction breakpoint actions. Not used by `disassemble`. |\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`, and either `memory_reference` or a current stopped location with `instructionPointerReference`\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- Approval is action-sensitive: read-only actions (`output`, `threads`, `stack_trace`, `scopes`, `variables`, `disassemble`, `read_memory`, `loaded_sources`, `modules`, `sessions`) request read approval; all other actions request exec approval.\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 `memory_reference`, or around the current stopped instruction pointer when no memory reference is supplied.\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  - `instruction_count is required for disassemble`\n  - `disassemble requires memory_reference unless the current stop location has an instruction pointer reference`\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 the current stopped session's `instructionPointerReference`; it throws if neither is present.\n- `RawSseDebugBuffer.recordEvent()` increments `totalEvents` before bounded retention. A snapshot can therefore show fewer retained records than total observed events.\n- Raw SSE buffer listener failures are swallowed so viewer bugs do not break capture.\n- `createDebugLogSource()` walks daily log files newest-first, but `loadOlderLogs()` reverses each requested slice before concatenation so older chunks prepend in chronological order.\n- `clearArtifactCache()` deletes directories by directory mtime, not per-file age.\n- `addDirectoryToArchive()` reads artifact files as text with `Bun.file(...).text()`. Binary artifact contents are not preserved byte-for-byte in the report bundle.\n- The tool renderer truncates displayed output for the TUI preview, but the underlying text result still contains the full returned string.\n",
-	"tools/edit.md": "# edit\n\n> Applies source edits; default mode is the hashline patch language consumed from a single `input` string.\n\n## Source\n- Entry: `packages/coding-agent/src/edit/index.ts`\n- Model-facing prompt: `packages/hashline/src/prompt.md`\n- Key collaborators:\n  - `packages/coding-agent/src/utils/edit-mode.ts` — selects active edit mode\n  - `packages/hashline/src/grammar.lark` — canonical constrained-decoding grammar\n  - `packages/hashline/src/format.ts` — sigils and header constants (`¶`, `#`, `+`, `replace`, `delete`, `insert`)\n  - `packages/hashline/src/input.ts` — parses `¶PATH#TAG` sections\n  - `packages/hashline/src/tokenizer.ts` / `packages/hashline/src/parser.ts` — tokenizes and parses ops\n  - `packages/hashline/src/apply.ts` — applies parsed edits to file text\n  - `packages/hashline/src/mismatch.ts` — stale-anchor mismatch formatting\n  - `packages/hashline/src/recovery.ts` — snapshot-based stale-anchor recovery\n  - `packages/hashline/src/snapshots.ts` — mints and resolves per-path opaque snapshot tags\n\n## Inputs\n\n### Hashline mode (default)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `input` | `string` | Yes | One or more file sections. Anchored sections must start with `¶PATH#TAG`; `TAG` is the four-hex snapshot tag emitted by the latest `read`/`search`/`write`/successful `edit`. Optional `*** Begin Patch` / `*** End Patch` envelope is ignored if present. |\n\nPatch language inside `input`:\n\n- **File header**: `¶PATH#TAG`. `TAG` is four uppercase-hex chars minted by the session snapshot store.\n- **Operations**:\n  - `replace N..M:` — replace original lines N..M with the body rows below.\n  - `replace block N:` — replace the whole tree-sitter block beginning on line N (its header line through its closing line) with the body rows. The line span is resolved at apply time from the file's parse tree; point N at the line that opens the construct. Errors (and steers to `replace N..M:`) when the language is unsupported, line N is blank or a closing delimiter, no node begins there, or the resolved block has a syntax error.\n  - `delete N..M` — delete original lines N..M. No body.\n  - `delete block N` — delete the whole tree-sitter block beginning on line N (resolved like `replace block N`). No body. Same resolution failure modes and `delete N..M` fallback.\n  - `insert before N:` — insert body rows immediately before line N.\n  - `insert after N:` — insert body rows immediately after line N.\n  - `insert head:` — insert body rows at the start of the file.\n  - `insert tail:` — insert body rows at the end of the file.\n- **Body rows**:\n  - Only body-bearing headers end in `:`.\n  - Every body row is `+TEXT`; `+` alone adds a blank line.\n  - `delete` never has body rows.\n  - There is no repeat row kind. To keep a line, leave it out of every range; split edits into multiple hunks when needed.\n  - `-` rows are invalid. Literal text beginning with `-` or `+` must be written as `+-text` / `++text`.\n\nAnchors come from `read`/`search` output. `read` emits a `¶PATH#TAG` header from the session snapshot store and lines as `LINE:TEXT`; copy the header into the edit section and copy only the line number into hunk headers.\n\n### Tolerated input shapes (lenient parsing)\n\nThe canonical grammar is strict, but the hand parser accepts a few non-dangerous variants:\n\n- `replace N:` — accepted as `replace N..N:`.\n- `delete N` — accepted as single-line delete.\n- Missing trailing colon on `replace` or `insert` — accepted.\n- `replace N-M:`, `replace N…M:`, and `replace N M:` — accepted as `replace N..M:`.\n- Bare body rows with no `+` prefix are auto-prepended with `+` and a `BARE_BODY_AUTO_PIPED_WARNING` is appended.\n- `*** Begin Patch` / `*** End Patch` envelopes are silently consumed. `*** Abort` terminates parsing silently — ops parsed before the marker still apply, no warning surfaced.\n- Some malformed `¶` headers are recovered after stripping apply-patch path noise such as `Update File:` / `Add File:` and extra `***`, but the recovered header still needs a valid four-hex tag for the patcher to apply it.\n- `*** Update File:` / `*** Add File:` / `*** Delete File:` / `*** Move to:` apply_patch sentinels inside the diff body throw an `apply_patch sentinel … is not valid in hashline` error.\n- `@@`-bracketed hunk headers are rejected with guidance to write a verb header.\n- Bare `N` and bare `N M` / `N..M` headers are rejected with guidance to write `replace` or `delete`.\n- `delete N..M:` and any body rows under `delete` / `delete block` are rejected.\n- Empty `replace` / `insert` / `replace block` hunks are rejected.\n- `-` body rows are rejected with `MINUS_ROW_REJECTED`.\n- `replace block N:` / `delete block N` require a wired tree-sitter resolver; `replace block` additionally needs at least one `+TEXT` body row, while `delete block` takes none. An unresolvable block (unsupported language, blank/closing-delimiter line, no node beginning on N, or a syntax error in the resolved block) is rejected on the apply/final-preview path; the streaming preview silently drops it instead.\n\n## Outputs\n- Single-shot tool result; hashline mode does not use a `resolve` preview/apply handshake.\n- `content` contains one text block per call. For a successful single-file edit it is either:\n  - `<path>:` plus a compact diff preview from `packages/hashline/src/diff-preview.ts`, or\n  - `Updated <path>` / `Created <path>` when no compact preview text is emitted.\n- Parse, apply, or recovery warnings are appended as:\n\n```text\nWarnings:\n...\n```\n\n- `details` is `EditToolDetails` from `packages/coding-agent/src/edit/renderer.ts`:\n  - `diff`: unified diff string\n  - `firstChangedLine`: first changed post-edit line\n  - `diagnostics`: LSP/format result if available\n  - `op`: `\"create\"` or `\"update\"` for hashline mode\n  - `meta`: output metadata\n  - `perFileResults`: present for multi-section input\n- Multi-section input returns one aggregated result with combined text and per-file details.\n\n## Worked examples\n\nReference file (the exact shape `read` returns):\n\n```text\n¶a.ts#0A3B\n1:const X = \"a\";\n2:const Y = X;\n3:\n4:console.log(X);\n5:console.log(Y);\n6:export { X, Y };\n```\n\nReplace line 1 with two lines:\n\n```text\n¶a.ts#0A3B\nreplace 1..1:\n+const X = \"b\";\n+export const Y = X;\n```\n\nInsert below line 5:\n\n```text\n¶a.ts#0A3B\ninsert after 5:\n+console.log(X + Y);\n```\n\nInsert above line 5:\n\n```text\n¶a.ts#0A3B\ninsert before 5:\n+console.log(X + Y);\n```\n\nDelete lines 4..5 entirely:\n\n```text\n¶a.ts#0A3B\ndelete 4..5\n```\n\nInsert at start and end of file:\n\n```text\n¶a.ts#0A3B\ninsert head:\n+// header\ninsert tail:\n+// trailer\n```\n\nMulti-file:\n\n```text\n¶src/a.ts#0A3B\nreplace 4..4:\n+const enabled = true;\n¶src/b.ts#1F7C\ndelete 20\n```\n\n## Limits & Caps\n- File snapshot tags are exactly four uppercase-hex chars minted by the per-session snapshot store.\n- The visible mismatch report shows 2 lines of context on each side (`MISMATCH_CONTEXT`) in `packages/hashline/src/messages.ts`.\n- Stale-anchor recovery uses `fuzzFactor: 0` in `packages/hashline/src/recovery.ts`.\n- `HL_FILE_PREFIX` is `¶`, `HL_PAYLOAD_REPLACE` is `+`, `HL_RANGE_SEP` is `..`, `HL_FILE_HASH_SEP` is `#`, and hunk keyword constants are `replace` / `delete` / `insert` (`packages/hashline/src/format.ts`).\n\n## Errors\n- Missing section header:\n  - `input must begin with \"¶PATH#HASH\" on the first non-blank line for anchored edits; got: ...`\n- Missing tag for any section:\n  - `Missing hashline snapshot tag for anchored edit to <path>; use ¶<path>#tag from your latest read/search output.`\n- Stray payload line:\n  - `line N: payload line has no preceding hunk header. Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` above the body. Got \"...\".`\n- Minus row:\n  - ``line N: `-` rows are not valid; hashline ranges already name the lines being changed. To insert a literal line starting with `-`, write `+-…`.``\n- Empty body-bearing hunk:\n  - `line N: \\`replace N..M:\\` needs at least one \\`+TEXT\\` body row. To delete lines, use \\`delete N..M\\`.`\n  - `line N: \\`insert\\` needs at least one \\`+TEXT\\` body row.`\n  - `line N: \\`replace block N:\\` needs at least one \\`+TEXT\\` body row. To delete a block, use \\`delete N..M\\` with the block's line range.`\n- Unresolvable `replace block N:` (apply / final-preview path only):\n  - `line N: \\`replace block X:\\` could not resolve a syntactic block beginning on line X. The language may be unsupported, the line may be blank or a closing delimiter, or the block may not parse. Use \\`replace X..M:\\` with the block's explicit end line instead.`\n- Delete with body:\n  - `line N: \\`delete N..M\\` does not take body rows. Remove the body, or use \\`replace N..M:\\`.`\n  - `line N: \\`delete block N\\` does not take body rows. Remove the body, or use \\`replace block N:\\` to replace the block.`\n- Range out of order:\n  - `line N: range A..B ends before it starts.`\n- Overlapping hunks on the same anchor:\n  - `line N: anchor line X is already targeted by another hunk on line Y. Issue ONE hunk per range; payload is only the final desired content, never a before/after pair.`\n- apply_patch / unified-diff contamination:\n  - `line N: apply_patch sentinel \"*** …\" is not valid in hashline. File sections start with \\`¶path#HASH\\` (no \\`Update File:\\` / \\`Add File:\\` keyword). Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` ops.`\n  - `line N: unified-diff hunk header (\\`@@ -N,M +N,M @@\\`) is not valid in hashline. Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` ops.`\n  - `line N: \\`@@\\`-bracketed hunk header \"@@ …\" is not valid in hashline. Drop the \\`@@ ... @@\\` brackets and write a verb header such as \\`replace N..M:\\`.`\n  - `line N: hunk headers need a verb. Use \\`replace N..N:\\` to replace, or \\`delete N\\` to delete.`\n  - `line N: bare range hunk header \"N M\" is not valid. Hunk headers need a verb: write \\`replace N..M:\\` or \\`delete N..M\\`.`\n- Out-of-range anchor:\n  - `Line N does not exist (file has M lines)`\n- Stale snapshot tag: the `Patcher` first attempts snapshot-based recovery. When recovery cannot prove a valid result it throws `MismatchError`, which distinguishes recognized-but-drifted hashes from never-recorded hashes. The error includes the current file hash plus context around each anchor.\n- No-op edit:\n  - `Edits to <path> parsed and applied cleanly, but produced no change: your body row(s) are byte-identical to the file at the targeted lines. The bug is somewhere else — re-read the file before issuing another edit. Do NOT widen the payload or add lines; verify the anchor first.`\n- Recovery failure is silent internally: if cache-based merge cannot prove a valid result, the mismatch error is surfaced unchanged.\n\n## Warnings\n- `Auto-prefixed bare body row(s) with +. Body rows must be +TEXT literal lines …` (`BARE_BODY_AUTO_PIPED_WARNING`)\n- Recovery banners: `RECOVERY_EXTERNAL_WARNING`, `RECOVERY_SESSION_CHAIN_WARNING`, `RECOVERY_SESSION_REPLAY_WARNING` (`packages/hashline/src/messages.ts`).\n",
-	"tools/eval.md": "# eval\n\n> Execute Python or JavaScript code in persistent cell-based runtimes.\n\n> **Notice:** Do not shell out to `python -c`/`python -e`, `bun -e`, or `node -e` via the `bash` tool for ad-hoc code execution. Use this tool instead — it gives you persistent state across cells, structured `display()` output, image/JSON capture, and proper cancellation/timeout handling that one-shot `-e`/`-c` invocations cannot provide.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/eval.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/eval.md`\n- Key collaborators:\n  - `packages/coding-agent/src/eval/backend.ts` — backend execution contract\n  - `packages/coding-agent/src/eval/agent-bridge.ts` — host-side `agent()` bridge into the subagent executor\n  - `packages/coding-agent/src/eval/js/executor.ts` — JS backend adapter\n  - `packages/coding-agent/src/eval/js/worker-core.ts` — JS execution, VM context, display/log capture\n  - `packages/coding-agent/src/eval/js/shared/prelude.txt` — JS global helper installer\n  - `packages/coding-agent/src/eval/js/shared/helpers.ts` — JS filesystem/text/env helper implementations\n  - `packages/coding-agent/src/eval/py/index.ts` — Python backend adapter\n  - `packages/coding-agent/src/eval/py/executor.ts` — kernel session retention, reset, cleanup\n  - `packages/coding-agent/src/eval/py/kernel.ts` — Jupyter gateway/kernel protocol, display capture\n  - `packages/coding-agent/src/eval/py/prelude.py` — Python helper functions and status events\n  - `packages/coding-agent/src/session/streaming-output.ts` — truncation, artifacts, streamed chunks\n  - `docs/python-repl.md` — Python kernel/gateway internals\n\n## Inputs\n\nTool parameters are a JSON object with a single `cells` field — an ordered array of cell objects. Each cell is a structured record; there is no `*** Cell` header parsing, no language sniffing, and no implicit single-cell fallback. Cells run in array order; state persists within each language across cells and across tool calls.\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `cells` | `EvalCellInput[]` | Yes | Cells executed in order. At least one cell is required (`.min(1)`). |\n\nEach `EvalCellInput` (from `evalCellSchema` in `packages/coding-agent/src/tools/eval.ts`):\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `language` | `\"py\" \\| \"js\"` | Yes | Backend selector. `\"py\"` maps to the IPython/Jupyter kernel (`python` backend); `\"js\"` maps to the persistent JavaScript VM. |\n| `code` | `string` | Yes | Cell body, verbatim. JSON-encoded — embed newlines, quotes, and indentation directly; no fences, no headers. |\n| `title` | `string` | No | Short label rendered in the transcript (e.g. `\"imports\"`, `\"load config\"`). |\n| `timeout` | `integer` | No | Per-cell timeout in seconds, clamped to `1..600`. Defaults to 30 when omitted. |\n| `reset` | `boolean` | No | Wipe this cell's language kernel before running. Reset is per-language: a `py` cell's reset does not touch the JS VM and vice versa. Defaults to `false`. |\n\nMinimal example matching the live schema:\n\n```json\n{\n  \"cells\": [\n    { \"language\": \"py\", \"title\": \"imports\", \"timeout\": 10, \"code\": \"import json\\nfrom pathlib import Path\" },\n    { \"language\": \"py\", \"title\": \"load config\", \"code\": \"data = json.loads(read('package.json'))\\ndisplay(data)\" },\n    { \"language\": \"js\", \"title\": \"summary\", \"reset\": true, \"code\": \"const data = JSON.parse(await read('package.json'));\\ndisplay(data);\\nreturn data.name;\" }\n  ]\n}\n```\n\n## Outputs\n\nFinal result from `EvalTool.execute()` is single-shot, but `onUpdate` streams partial text and `details` while cells run.\n\nReturned shape:\n\n- `content`: one text block containing combined cell output, `(displayed N image(s); no text output)` when only images exist, or `(no output)` when nothing visible was produced; image outputs are appended as additional image content blocks.\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  - `statusEvents`: aggregated helper/tool status events\n  - `notice`: backend fallback notice (currently unused; reserved for future per-cell notices)\n  - `meta`: truncation metadata\n  - `isError`: set on cell failure or cancellation\n\nRenderer behavior in `packages/coding-agent/src/tools/eval.ts`:\n\n- call preview renders each cell's `code` with syntax highlighting based on its declared `language`\n- result view renders each cell separately, including status, duration, and output\n- markdown outputs are rendered with the Markdown component instead of plain text\n- `jsonOutputs` render as a tree, collapsed or expanded depending on UI state\n- timeout / truncation notices render as dim metadata lines\n- images are returned as content image blocks; live updates may also carry `details.images` while execution is in progress\n\nSide-channel artifacts:\n\n- `session.allocateOutputArtifact?.(\"eval\")` may allocate an `artifact://...` backing store for spilled output.\n- Truncated output metadata points at that artifact when available.\n\n## Flow\n\n1. `EvalTool.execute()` in `packages/coding-agent/src/tools/eval.ts` receives `params.cells` already validated by the Zod schema — no string parsing step.\n2. For each cell, `execute()` maps `cell.language` to an `EvalLanguage` (`\"py\"` → `\"python\"`, `\"js\"` → `\"js\"`) and calls `resolveBackend(session, language)`:\n   - `python` is gated on `eval.py !== false` and `pythonBackend.isAvailable(session)`.\n   - `js` is gated on `eval.js !== false`.\n   - A disabled or unavailable requested backend throws `ToolError`; there is no auto-fallback or sniffing.\n3. The tool allocates an `OutputSink`, a `TailBuffer`, per-cell result objects, and a `sessionAbortController`. `session.trackEvalExecution?.(...)` can wrap the whole run for external cancellation tracking.\n4. It resolves the executor session id from `session.getEvalSessionId?.()`, falling back to `defaultEvalSessionId(session)`. Subagents inherit the parent's id so both sides share the same JS VM and Python kernel for each backend.\n5. Cells execute sequentially within one eval tool call. For each cell, `execute()`:\n   - clamps `cell.timeout ?? 30` seconds through `clampTimeout(\"eval\", ...)`\n   - builds a combined abort signal from the tool signal, the timeout, and the session abort controller\n   - marks the cell `running` and emits an update\n   - calls the backend’s `execute()` with `cwd`, `sessionId`, `sessionFile`, `kernelOwnerId`, `deadlineMs`, `reset` (defaults to `false`), artifact info, and chunk callback\n6. JS cells dispatch through `packages/coding-agent/src/eval/js/index.ts` into `executeJs()`; Python cells dispatch through `packages/coding-agent/src/eval/py/index.ts` into `executePython()`.\n7. Backend text chunks stream into the shared `OutputSink`; rich outputs are accumulated separately as JSON, images, markdown markers, and status events.\n8. After each cell:\n   - text output is trimmed and stored on that cell result\n   - multi-cell runs prefix text with `[i/n]` and the optional title\n   - cancellations return early with `isError: true` and a cell-specific abort message\n   - non-zero exit codes return early with `isError: true` and a message naming the failed cell\n   - later cells are skipped after the first error, but earlier cell state persists in the underlying runtime\n9. On success, the tool joins all cell outputs, synthesizes `(no text output)` or `(no output)` when needed, and attaches truncation metadata from `summarizeFinal()`.\n10. The renderer uses `details.cells`, `details.jsonOutputs`, and `details.statusEvents` to build notebook-style output. `mergeCallAndResult = true` and `inline = true`, so call and result render together in the transcript.\n\n## Modes / Variants\n\n### Backend selection\n\nBackend choice is **explicit per cell** — there is no auto-detection.\n\n- `language: \"py\"` → Python (IPython/Jupyter) backend\n- `language: \"js\"` → JavaScript VM backend\n\nIf the requested backend is disabled or unavailable, the tool throws `ToolError` for that cell. The caller chooses; the tool does not silently substitute.\n\n### JavaScript runtime\n\nImplemented in `packages/coding-agent/src/eval/js/worker-core.ts`, `packages/coding-agent/src/eval/js/shared/prelude.txt`, and `packages/coding-agent/src/eval/js/shared/helpers.ts`.\n\n- Persistent worker-backed VM sessions keyed by `js:${sessionId}`\n- `reset: true` calls `resetVmContext(sessionKey)` before the cell executes; reset is destructive for all live runs on that JS session\n- Top-level `await` and bare `return` are supported by wrapping code in an async IIFE when `wrapCode()` sees `await` or `return`\n- Top-level static `import ... from ...` and dynamic `import(...)` calls are routed through `rewriteImports()`, which sends them via `__omp_import__` so the specifier resolves against the session cwd\n- Module cache is busted for **local** imports between cells so edits to source files are picked up without restarting the runtime. `__omp_import__` deletes `require.cache[absPath]` before re-importing whenever the original specifier is a filesystem path: relative (`./x`, `../x`, `.`, `..`), POSIX-absolute (`/...`), home-prefixed (`~/...`), or Windows drive-letter (`C:\\...` / `C:/...`). Bare specifiers (`react`, `lodash/x`) and URL/scheme specifiers (`node:fs`, `file://...`, `https://...`) are left in cache so package identity stays stable across cells. The cache-bust only fires when the resolved target is an absolute path — unresolved bare-package fallbacks (`resolveImportSpecifier()` returning the original specifier) skip it.\n- The prelude installs globals:\n  - `display`, `print`\n  - `read`, `write`, `append`, `sort`, `uniq`, `counter`, `diff`, `tree`, `env`, `output`\n  - `tool.<name>(args)` proxy for arbitrary session tool calls\n  - `llm(prompt, opts?)` for oneshot, stateless LLM calls (see _Oneshot LLM helper_ below)\n  - `agent(prompt, opts?)` for a single subagent call, plus `parallel()` / `pipeline()` bounded-pool helpers (see _Subagent helper_ below)\n- JS helpers that touch the host/runtime boundary are async and `await`able; pure text helpers (`sort`, `uniq`, `counter`) return synchronously but may still be safely awaited.\n- JS helper signatures use a trailing options object rather than Python keyword arguments:\n  - `await read(path, { offset?, limit? })`\n  - `await tree(path = \".\", { maxDepth?, hidden? })`\n  - `sort(text, { reverse?, unique? })`, `uniq(text, { count? })`, `counter(items, { limit?, reverse? })`\n  - `await agent(prompt, { agentType?, model?, context?, label?, schema? })`\n  - `await parallel([() => agent(\"a\"), () => agent(\"b\")])`\n  - `await pipeline(items, stage1, stage2)`\n- `display(value)` behavior:\n  - plain objects/arrays become JSON outputs\n  - `{ type: \"image\", data, mimeType }` becomes an image output\n  - scalars become text\n- The VM exposes a restricted `process` subset plus `Buffer`, `fetch`, `Blob`, `File`, `Headers`, `Request`, `Response`, `fs`, `require`, and browser-style globals\n- Concurrent runs on the same VM are not queued end-to-end. Synchronous JS still runs on the single event loop; awaited regions can interleave with sibling runs.\n\n### Python runtime\n\nImplemented in `packages/coding-agent/src/eval/py/executor.ts`, `packages/coding-agent/src/eval/py/kernel.ts`, and `packages/coding-agent/src/eval/py/prelude.py`. See `docs/python-repl.md` for gateway and kernel details.\n\n- Default mode is retained `session` kernels keyed by `python:${sessionId}`\n- Optional `python.kernelMode = \"per-call\"` creates a fresh kernel for each cell and shuts it down afterward\n- `reset: true` disposes the retained kernel for that session before the cell runs; later Python cells in the same tool call reuse the fresh kernel\n- Startup path:\n  - availability check\n  - create/connect kernel\n  - initialize cwd / env / `sys.path`\n  - execute `PYTHON_PRELUDE`\n- Python cells run in the runner's persistent asyncio event loop, so top-level `await` works; the prompt warns not to use `asyncio.run(...)`\n- The Python prelude defines helpers with the same surface as JS where practical, including `tool.<name>(args)`, `llm(...)`, and `agent(...)` through a per-run loopback bridge\n- Synchronous statement blocks run in the default executor with ContextVar state copied in; the GIL still serializes bytecode execution, but awaited regions can interleave with sibling cells\n- Kernel `display_data` / `execute_result` messages map to:\n  - `application/x-omp-status` → status event\n  - `image/png` → image output\n  - `application/json` → JSON output\n  - `text/markdown` → markdown output\n  - `text/plain` → text output\n  - `text/html` → HTML converted to markdown with `htmlToBasicMarkdown()`\n- Interactive stdin is rejected: `input_request` sends an empty reply, marks `stdinRequested`, and the executor returns exit code `1`\n\n### Oneshot LLM helper (`llm`)\n\nBoth runtimes expose `llm()` — a single stateless completion against a model tier. It is intentionally minimal: no conversation history, no agent-visible tools, pure text in / text (or object) out. Implemented host-side in `packages/coding-agent/src/eval/llm-bridge.ts` and routed through the existing tool bridge under the reserved name `__llm__`.\n\n- Signatures:\n  - JS: `await llm(prompt, { model?, system?, schema? })`\n  - Python: `llm(prompt, *, model=\"default\", system=None, schema=None)`\n- `model` selects a tier (default `\"default\"`):\n  - `\"smol\"` → `pi/smol` role (fast / cheap)\n  - `\"default\"` → the session's active model, falling back to the `pi/default` role\n  - `\"slow\"` → `pi/slow` role; requests high reasoning effort only on reasoning-capable models\n- `system` (optional) supplies a system prompt.\n- `schema` (optional) is a plain JSON-Schema object. When present, the model is forced to call a single synthetic `respond` tool with that schema (loose, non-strict), and the helper returns the parsed object. When absent, the helper returns the completion string.\n- Errors surface as exceptions: unresolved tier, missing API key, an `error`/`aborted` stop reason, or empty output each raise.\n\n### Subagent helper (`agent`)\n\nBoth runtimes expose `agent()` — a single subagent invocation routed through `packages/coding-agent/src/eval/agent-bridge.ts` into the same `runSubprocess(...)` path used by the `task` tool. It uses the current eval session's spawn policy and inherits the parent eval executor id, so parent and subagent code share JS/Python runtime state.\n\n- Signatures:\n  - JS: `await agent(prompt, { agentType?, model?, context?, label?, schema? })`\n  - Python: `agent(prompt, *, agent_type=\"task\", model=None, context=None, label=None, schema=None)`\n- `agentType` / `agent_type` defaults to the bundled `task` agent and resolves through normal agent discovery, so project and user agents work.\n- `model` overrides the selected agent's model. Without it, normal per-agent settings and the agent frontmatter model apply.\n- `context` supplies shared background; `label` controls the `agent://<id>` output label prefix.\n- `schema` passes a JSON Schema to the subagent structured-output path. When present, the helper parses the final JSON text and returns an object.\n- Spawn restrictions use `session.getSessionSpawns()` exactly like the `task` tool. Eval-driven subagent recursion is capped at depth 3.\n- JS and Python both expose `parallel(thunks)` and `pipeline(items, ...stages)`; both use a bounded async/threaded pool whose width tracks the `task.maxConcurrency` setting (the same ceiling the `task` tool uses; `0` = run every item at once), preserve item order, and propagate rejections. The width is fetched live from the host via the `__concurrency__` bridge, so the helpers no longer take a `concurrency` argument.\n- Errors surface as exceptions: unknown or disabled agent, disallowed spawn, recursion cap, subagent failure, or invalid structured output all fail the eval cell.\n\n### Multi-language call behavior\n\nA single tool call can mix Python and JS cells. Persistence is per language runtime:\n\n- `reset: true` on a Python cell does not touch JS state\n- `reset: true` on a JS cell does not touch Python state\n- each backend keeps its own retained session keyed from the same session-derived ID\n\n## Side Effects\n\n- Filesystem\n  - JS/Python prelude helpers can read, write, append, diff, and traverse filesystem paths under the session cwd or absolute paths.\n  - JS helper `read()` rejects protocol URIs (`://`) and directory paths; use `tool.read(...)` for internal URLs or reader-mode behavior.\n  - Output may spill to an artifact file via `OutputSink`.\n- Network\n  - Python backend speaks NDJSON to a local `python3` subprocess over stdin/stdout (no network).\n  - JS runtime exposes `fetch` and `tool.<name>()`; those tools may perform additional network I/O.\n- Subprocesses / native bindings\n  - Python availability check runs `<python> -c ...`.\n  - Python backend spawns one `python -u runner.py` subprocess per kernel; cancellation sends `SIGINT`. Details in `docs/python-repl.md`.\n  - `agent()` runs one in-process subagent via the task executor; that subagent may use its configured tools.\n- Session state\n  - `session.assertEvalExecutionAllowed?.()` can block execution.\n  - `session.trackEvalExecution?.(...)` can register cancellable eval work.\n  - `session.getSessionFile?.()`, `session.getEvalSessionId?.()`, and `session.getEvalKernelOwnerId?.()` influence VM/kernel reuse and artifact lookup.\n  - JS VM contexts persist across eval calls until reset/disposal.\n  - Python retained kernels persist until reset, owner cleanup, or process exit.\n  - `agent()` allocates `agent://<id>` output artifacts and reuses the parent's eval executor id.\n- User-visible prompts / interactive UI\n  - none; stdin requests are rejected programmatically\n- Background work / cancellation\n  - Python retained kernels have heartbeat and idle cleanup timers.\n  - Cancellation hard-kills/resets the shared executor for that backend: JS terminates the worker, Python sends SIGINT and may escalate to subprocess shutdown.\n\n## Limits & Caps\n\n- Per-cell timeout default: 30s (applied when `timeout` is omitted in `EvalTool.execute()`; clamped through `TOOL_TIMEOUTS.eval.default` in `packages/coding-agent/src/tools/tool-timeouts.ts`)\n- Schema-level `timeout` range: integer `1..600` seconds (enforced by Zod on the cell schema)\n- Timeout clamp at runtime: 1s minimum, 600s maximum (`TOOL_TIMEOUTS.eval` in `packages/coding-agent/src/tools/tool-timeouts.ts`)\n- Transcript code/output preview: 10 lines by default (`EVAL_DEFAULT_PREVIEW_LINES` in `packages/coding-agent/src/tools/eval.ts`)\n- Output truncation window: 50KB default (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`)\n- Output line cap inside truncation helpers: 3000 lines (`DEFAULT_MAX_LINES` in `packages/coding-agent/src/session/streaming-output.ts`)\n- Streaming tail buffer for live updates: `DEFAULT_MAX_BYTES * 2` = 100KB (`packages/coding-agent/src/tools/eval.ts`)\n- JS/Python `parallel()` / `pipeline()` helper pool width: the `task.maxConcurrency` setting (default 32; `0` = unbounded), resolved live via the `__concurrency__` bridge (`packages/coding-agent/src/eval/concurrency-bridge.ts`)\n- Eval-driven `agent()` recursion cap: task depth 3 (`EVAL_AGENT_MAX_DEPTH`)\n- Python retained kernel idle timeout: 5 minutes (`IDLE_TIMEOUT_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python retained kernel cap: 4 sessions (`MAX_KERNEL_SESSIONS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python retained kernel cleanup sweep: every 30s (`CLEANUP_INTERVAL_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python owner-cleanup shutdown wait: 2000ms (`OWNER_CLEANUP_KERNEL_SHUTDOWN_TIMEOUT_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python heartbeat interval: 5s (`ensureKernelHeartbeat()` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python external gateway availability check timeout: 5s (`AbortSignal.timeout(5000)` in `packages/coding-agent/src/eval/py/kernel.ts`)\n- Python auto-restart budget: one restart per retained session before hard failure (`restartCount > 1` in `packages/coding-agent/src/eval/py/executor.ts`)\n\n## Errors\n\n- Zod validation rejects malformed `cells` arrays before `execute()` runs (missing `language`/`code`, out-of-range `timeout`, empty `cells`).\n- Missing session without proxy executor throws `ToolError(\"Eval tool requires a session when not using proxy executor\")`.\n- Disabled/unavailable backends throw `ToolError` from `resolveBackend()`:\n  - `eval.py = false` and a `py` cell is requested\n  - `eval.js = false` and a `js` cell is requested\n  - Python kernel unavailable and a `py` cell is requested\n- JS runtime exceptions are converted into text output plus `exitCode: 1`; cancellations return `cancelled: true` and may append `Command timed out`.\n- Python execution errors from the kernel become text output and `exitCode: 1`; later cells are skipped.\n- Python stdin requests are treated as errors with the message `Kernel requested stdin; interactive input is not supported.`\n- Cancellation is returned, not thrown, once backend execution has started. The tool formats it as a cell failure and sets `details.isError = true`.\n- If output truncates, the tool still succeeds; truncation is surfaced through `details.meta` and artifact-backed full output when available.\n\n## Shared executor trade-offs\n\n- Parent agents and subagents share eval state bidirectionally when a subagent inherits the parent's executor id. Mutations in either direction are visible to the other participant.\n- Async regions of concurrent runs can interleave. Synchronous JS still blocks the VM event loop; synchronous Python still contends on the GIL.\n- Cancelling one run is destructive to the shared backend executor. This is intentional: JS worker termination and Python SIGINT/subprocess shutdown are the only reliable way to interrupt arbitrary user code.\n- `reset: true` is destructive for every live run on that backend session id. New starts on that backend are rejected while reset is in flight.\n\n## Notes\n\n- Backend selection is strictly explicit per cell: `language` must be `\"py\"` or `\"js\"`. The previous `*** Cell` header parser, the `eval.lark` constrained grammar, and the sniffer-based fallback have all been removed.\n- `EvalTool.customFormat` no longer exists. Tool calls flow through the standard JSON schema; there is no Lark-constrained sampling path.\n- `tool.<name>()` exists in both JS and Python. Python calls route through a per-run loopback bridge keyed by the current cell id.\n- JS helper paths reject protocol URIs (`://`) in `resolveRegularFile()` for `read()`, and resolve other paths against the session cwd or absolute filesystem path. Use `tool.read(...)` or another tool explicitly for internal URLs.\n- Python helper `output(...)` depends on `PI_ARTIFACTS_DIR` or `PI_SESSION_FILE`; it fails outside a session-backed run.\n- `display()` can produce text and structured outputs from the same value; the renderer prefers markdown over `text/plain` when both exist.\n- JS static imports are rewritten only at top level. Nested imports stay invalid and surface normal JS syntax/runtime errors.\n- `EvalTool` is `concurrency = \"exclusive\"` within one agent session, but parent and subagent sessions can run eval concurrently when they share an inherited executor id.\n- The tool description shown to the model is templated by backend availability (`getEvalToolDescription()`); if Python is unavailable, the prompt omits Python-specific instructions.\n",
+	"tools/edit.md": "# edit\n\n> Applies source edits; default mode is the hashline patch language consumed from a single `input` string.\n\n## Source\n- Entry: `packages/coding-agent/src/edit/index.ts`\n- Model-facing prompt: `packages/hashline/src/prompt.md`\n- Key collaborators:\n  - `packages/coding-agent/src/utils/edit-mode.ts` — selects active edit mode\n  - `packages/hashline/src/grammar.lark` — canonical constrained-decoding grammar\n  - `packages/hashline/src/format.ts` — sigils and header constants (`¶`, `#`, `+`, `replace`, `delete`, `insert`)\n  - `packages/hashline/src/input.ts` — parses `¶PATH#TAG` sections\n  - `packages/hashline/src/tokenizer.ts` / `packages/hashline/src/parser.ts` — tokenizes and parses ops\n  - `packages/hashline/src/apply.ts` — applies parsed edits to file text\n  - `packages/hashline/src/mismatch.ts` — stale-anchor mismatch formatting\n  - `packages/hashline/src/recovery.ts` — snapshot-based stale-anchor recovery\n  - `packages/hashline/src/snapshots.ts` — mints and resolves per-path opaque snapshot tags\n\n## Inputs\n\n### Hashline mode (default)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `input` | `string` | Yes | One or more file sections. Anchored sections must start with `¶PATH#TAG`; `TAG` is the four-hex snapshot tag emitted by the latest `read`/`search`/`write`/successful `edit`. Optional `*** Begin Patch` / `*** End Patch` envelope is ignored if present. |\n\nPatch language inside `input`:\n\n- **File header**: `¶PATH#TAG`. `TAG` is four uppercase-hex chars minted by the session snapshot store.\n- **Operations**:\n  - `replace N..M:` — replace original lines N..M with the body rows below.\n  - `replace block N:` — replace the whole tree-sitter block beginning on line N (its header line through its closing line) with the body rows. The line span is resolved at apply time from the file's parse tree; point N at the line that opens the construct. The resolved span is exactly the node that begins on line N — a leading decorator, attribute, or doc-comment is a separate node and is not included; point N at the first decorator line (Python wraps `@dec` + `def` as one block) or fall back to `replace N..M:` to take a leading line-comment that parses as its own node (e.g. Rust `///`). On success the result echoes the matched span (`replace block N → resolved lines A-B`). Errors (and steers to `replace N..M:`) when the language is unsupported, line N is blank or a closing delimiter, no node begins there, or the resolved block has a syntax error.\n  - `delete N..M` — delete original lines N..M. No body.\n  - `delete block N` — delete the whole tree-sitter block beginning on line N (resolved like `replace block N`, with the same decorator/comment caveat). No body. On success the result echoes the matched span (`delete block N → resolved lines A-B`). Same resolution failure modes and `delete N..M` fallback.\n  - `insert before N:` — insert body rows immediately before line N.\n  - `insert after N:` — insert body rows immediately after line N.\n  - `insert head:` — insert body rows at the start of the file.\n  - `insert tail:` — insert body rows at the end of the file.\n- **Body rows**:\n  - Only body-bearing headers end in `:`.\n  - Every body row is `+TEXT`; `+` alone adds a blank line.\n  - `delete` never has body rows.\n  - There is no repeat row kind. To keep a line, leave it out of every range; split edits into multiple hunks when needed.\n  - `-` rows are invalid. Literal text beginning with `-` or `+` must be written as `+-text` / `++text`.\n\nAnchors come from `read`/`search` output. `read` emits a `¶PATH#TAG` header from the session snapshot store and lines as `LINE:TEXT`; copy the header into the edit section and copy only the line number into hunk headers.\n\n### Tolerated input shapes (lenient parsing)\n\nThe canonical grammar is strict, but the hand parser accepts a few non-dangerous variants:\n\n- `replace N:` — accepted as `replace N..N:`.\n- `delete N` — accepted as single-line delete.\n- Missing trailing colon on `replace` or `insert` — accepted.\n- `replace N-M:`, `replace N…M:`, and `replace N M:` — accepted as `replace N..M:`.\n- Bare body rows with no `+` prefix are auto-prepended with `+` and a `BARE_BODY_AUTO_PIPED_WARNING` is appended.\n- `*** Begin Patch` / `*** End Patch` envelopes are silently consumed. `*** Abort` terminates parsing silently — ops parsed before the marker still apply, no warning surfaced.\n- Some malformed `¶` headers are recovered after stripping apply-patch path noise such as `Update File:` / `Add File:` and extra `***`, but the recovered header still needs a valid four-hex tag for the patcher to apply it.\n- `*** Update File:` / `*** Add File:` / `*** Delete File:` / `*** Move to:` apply_patch sentinels inside the diff body throw an `apply_patch sentinel … is not valid in hashline` error.\n- `@@`-bracketed hunk headers are rejected with guidance to write a verb header.\n- Bare `N` and bare `N M` / `N..M` headers are rejected with guidance to write `replace` or `delete`.\n- `delete N..M:` and any body rows under `delete` / `delete block` are rejected.\n- Empty `replace` / `insert` / `replace block` hunks are rejected.\n- `-` body rows are rejected with `MINUS_ROW_REJECTED`.\n- `replace block N:` / `delete block N` require a wired tree-sitter resolver; `replace block` additionally needs at least one `+TEXT` body row, while `delete block` takes none. An unresolvable block (unsupported language, blank/closing-delimiter line, no node beginning on N, or a syntax error in the resolved block) is rejected on the apply/final-preview path; the streaming preview silently drops it instead.\n\n## Outputs\n- Single-shot tool result; hashline mode does not use a `resolve` preview/apply handshake.\n- `content` contains one text block per call. For a successful single-file edit it is either:\n  - `<path>:` plus a compact diff preview from `packages/hashline/src/diff-preview.ts`, or\n  - `Updated <path>` / `Created <path>` when no compact preview text is emitted.\n- When the patch used `replace block`/`delete block` ops (and the apply matched the tagged content), one `replace block N → resolved lines A-B (K lines)` line per block op is inserted between the `¶PATH#TAG` header and the diff preview, so the caller can confirm tree-sitter resolved the construct it intended.\n- Parse, apply, or recovery warnings are appended as:\n\n```text\nWarnings:\n...\n```\n\n- `details` is `EditToolDetails` from `packages/coding-agent/src/edit/renderer.ts`:\n  - `diff`: unified diff string\n  - `firstChangedLine`: first changed post-edit line\n  - `diagnostics`: LSP/format result if available\n  - `op`: `\"create\"` or `\"update\"` for hashline mode\n  - `meta`: output metadata\n  - `perFileResults`: present for multi-section input\n- Multi-section input returns one aggregated result with combined text and per-file details.\n\n## Worked examples\n\nReference file (the exact shape `read` returns):\n\n```text\n¶a.ts#0A3B\n1:const X = \"a\";\n2:const Y = X;\n3:\n4:console.log(X);\n5:console.log(Y);\n6:export { X, Y };\n```\n\nReplace line 1 with two lines:\n\n```text\n¶a.ts#0A3B\nreplace 1..1:\n+const X = \"b\";\n+export const Y = X;\n```\n\nInsert below line 5:\n\n```text\n¶a.ts#0A3B\ninsert after 5:\n+console.log(X + Y);\n```\n\nInsert above line 5:\n\n```text\n¶a.ts#0A3B\ninsert before 5:\n+console.log(X + Y);\n```\n\nDelete lines 4..5 entirely:\n\n```text\n¶a.ts#0A3B\ndelete 4..5\n```\n\nInsert at start and end of file:\n\n```text\n¶a.ts#0A3B\ninsert head:\n+// header\ninsert tail:\n+// trailer\n```\n\nMulti-file:\n\n```text\n¶src/a.ts#0A3B\nreplace 4..4:\n+const enabled = true;\n¶src/b.ts#1F7C\ndelete 20\n```\n\n## Limits & Caps\n- File snapshot tags are exactly four uppercase-hex chars minted by the per-session snapshot store.\n- The visible mismatch report shows 2 lines of context on each side (`MISMATCH_CONTEXT`) in `packages/hashline/src/messages.ts`.\n- Stale-anchor recovery uses `fuzzFactor: 0` in `packages/hashline/src/recovery.ts`.\n- `HL_FILE_PREFIX` is `¶`, `HL_PAYLOAD_REPLACE` is `+`, `HL_RANGE_SEP` is `..`, `HL_FILE_HASH_SEP` is `#`, and hunk keyword constants are `replace` / `delete` / `insert` (`packages/hashline/src/format.ts`).\n\n## Errors\n- Missing section header:\n  - `input must begin with \"¶PATH#HASH\" on the first non-blank line for anchored edits; got: ...`\n- Missing tag for any section:\n  - `Missing hashline snapshot tag for anchored edit to <path>; use ¶<path>#tag from your latest read/search output.`\n- Stray payload line:\n  - `line N: payload line has no preceding hunk header. Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` above the body. Got \"...\".`\n- Minus row:\n  - ``line N: `-` rows are not valid; hashline ranges already name the lines being changed. To insert a literal line starting with `-`, write `+-…`.``\n- Empty body-bearing hunk:\n  - `line N: \\`replace N..M:\\` needs at least one \\`+TEXT\\` body row. To delete lines, use \\`delete N..M\\`.`\n  - `line N: \\`insert\\` needs at least one \\`+TEXT\\` body row.`\n  - `line N: \\`replace block N:\\` needs at least one \\`+TEXT\\` body row. To delete a block, use \\`delete N..M\\` with the block's line range.`\n- Unresolvable `replace block N:` (apply / final-preview path only):\n  - `line N: \\`replace block X:\\` could not resolve a syntactic block beginning on line X. The language may be unsupported, the line may be blank or a closing delimiter, or the block may not parse. Use \\`replace X..M:\\` with the block's explicit end line instead.`\n- Delete with body:\n  - `line N: \\`delete N..M\\` does not take body rows. Remove the body, or use \\`replace N..M:\\`.`\n  - `line N: \\`delete block N\\` does not take body rows. Remove the body, or use \\`replace block N:\\` to replace the block.`\n- Range out of order:\n  - `line N: range A..B ends before it starts.`\n- Overlapping hunks on the same anchor:\n  - `line N: anchor line X is already targeted by another hunk on line Y. Issue ONE hunk per range; payload is only the final desired content, never a before/after pair.`\n- apply_patch / unified-diff contamination:\n  - `line N: apply_patch sentinel \"*** …\" is not valid in hashline. File sections start with \\`¶path#HASH\\` (no \\`Update File:\\` / \\`Add File:\\` keyword). Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` ops.`\n  - `line N: unified-diff hunk header (\\`@@ -N,M +N,M @@\\`) is not valid in hashline. Use \\`replace N..M:\\`, \\`delete N..M\\`, or \\`insert before|after|head|tail:\\` ops.`\n  - `line N: \\`@@\\`-bracketed hunk header \"@@ …\" is not valid in hashline. Drop the \\`@@ ... @@\\` brackets and write a verb header such as \\`replace N..M:\\`.`\n  - `line N: hunk headers need a verb. Use \\`replace N..N:\\` to replace, or \\`delete N\\` to delete.`\n  - `line N: bare range hunk header \"N M\" is not valid. Hunk headers need a verb: write \\`replace N..M:\\` or \\`delete N..M\\`.`\n- Out-of-range anchor:\n  - `Line N does not exist (file has M lines)`\n- Stale snapshot tag: the `Patcher` first attempts snapshot-based recovery. When recovery cannot prove a valid result it throws `MismatchError`, which distinguishes recognized-but-drifted hashes from never-recorded hashes. The error includes the current file hash plus context around each anchor.\n- No-op edit:\n  - `Edits to <path> parsed and applied cleanly, but produced no change: your body row(s) are byte-identical to the file at the targeted lines. The bug is somewhere else — re-read the file before issuing another edit. Do NOT widen the payload or add lines; verify the anchor first.`\n- Recovery failure is silent internally: if cache-based merge cannot prove a valid result, the mismatch error is surfaced unchanged.\n\n## Warnings\n- `Auto-prefixed bare body row(s) with +. Body rows must be +TEXT literal lines …` (`BARE_BODY_AUTO_PIPED_WARNING`)\n- Recovery banners: `RECOVERY_EXTERNAL_WARNING`, `RECOVERY_SESSION_CHAIN_WARNING`, `RECOVERY_SESSION_REPLAY_WARNING` (`packages/hashline/src/messages.ts`).\n",
+	"tools/eval.md": "# eval\n\n> Execute Python or JavaScript code in persistent cell-based runtimes.\n\n> **Notice:** Do not shell out to `python -c`/`python -e`, `bun -e`, or `node -e` via the `bash` tool for ad-hoc code execution. Use this tool instead — it gives you persistent state across cells, structured `display()` output, image/JSON capture, and proper cancellation/timeout handling that one-shot `-e`/`-c` invocations cannot provide.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/eval.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/eval.md`\n- Key collaborators:\n  - `packages/coding-agent/src/eval/backend.ts` — backend execution contract\n  - `packages/coding-agent/src/eval/agent-bridge.ts` — host-side `agent()` bridge into the subagent executor\n  - `packages/coding-agent/src/eval/js/executor.ts` — JS backend adapter\n  - `packages/coding-agent/src/eval/js/worker-core.ts` — JS execution, VM context, display/log capture\n  - `packages/coding-agent/src/eval/js/shared/prelude.txt` — JS global helper installer\n  - `packages/coding-agent/src/eval/js/shared/helpers.ts` — JS filesystem/text/env helper implementations\n  - `packages/coding-agent/src/eval/py/index.ts` — Python backend adapter\n  - `packages/coding-agent/src/eval/py/executor.ts` — kernel session retention, reset, cleanup\n  - `packages/coding-agent/src/eval/py/kernel.ts` — Jupyter gateway/kernel protocol, display capture\n  - `packages/coding-agent/src/eval/py/prelude.py` — Python helper functions and status events\n  - `packages/coding-agent/src/session/streaming-output.ts` — truncation, artifacts, streamed chunks\n  - `docs/python-repl.md` — Python kernel/gateway internals\n\n## Inputs\n\nTool parameters are a JSON object with a single `cells` field — an ordered array of cell objects. Each cell is a structured record; there is no `*** Cell` header parsing, no language sniffing, and no implicit single-cell fallback. Cells run in array order; state persists within each language across cells and across tool calls.\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `cells` | `EvalCellInput[]` | Yes | Cells executed in order. At least one cell is required (`.min(1)`). |\n\nEach `EvalCellInput` (from `evalCellSchema` in `packages/coding-agent/src/tools/eval.ts`):\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `language` | `\"py\" \\| \"js\"` | Yes | Backend selector. `\"py\"` maps to the IPython/Jupyter kernel (`python` backend); `\"js\"` maps to the persistent JavaScript VM. |\n| `code` | `string` | Yes | Cell body, verbatim. JSON-encoded — embed newlines, quotes, and indentation directly; no fences, no headers. |\n| `title` | `string` | No | Short label rendered in the transcript (e.g. `\"imports\"`, `\"load config\"`). |\n| `timeout` | `integer` | No | Per-cell timeout in seconds, clamped to `1..600`. Defaults to 30 when omitted. |\n| `reset` | `boolean` | No | Wipe this cell's language kernel before running. Reset is per-language: a `py` cell's reset does not touch the JS VM and vice versa. Defaults to `false`. |\n\nMinimal example matching the live schema:\n\n```json\n{\n  \"cells\": [\n    { \"language\": \"py\", \"title\": \"imports\", \"timeout\": 10, \"code\": \"import json\\nfrom pathlib import Path\" },\n    { \"language\": \"py\", \"title\": \"load config\", \"code\": \"data = json.loads(read('package.json'))\\ndisplay(data)\" },\n    { \"language\": \"js\", \"title\": \"summary\", \"reset\": true, \"code\": \"const data = JSON.parse(await read('package.json'));\\ndisplay(data);\\nreturn data.name;\" }\n  ]\n}\n```\n\n## Outputs\n\nFinal result from `EvalTool.execute()` is single-shot, but `onUpdate` streams partial text and `details` while cells run.\n\nReturned shape:\n\n- `content`: one text block containing combined cell output, `(displayed N image(s); no text output)` when only images exist, or `(no output)` when nothing visible was produced; image outputs are appended as additional image content blocks.\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  - `statusEvents`: aggregated helper/tool status events\n  - `notice`: backend fallback notice (currently unused; reserved for future per-cell notices)\n  - `meta`: truncation metadata\n  - `isError`: set on cell failure or cancellation\n\nRenderer behavior in `packages/coding-agent/src/tools/eval.ts`:\n\n- call preview renders each cell's `code` with syntax highlighting based on its declared `language`\n- result view renders each cell separately, including status, duration, and output\n- markdown outputs are rendered with the Markdown component instead of plain text\n- `jsonOutputs` render as a tree, collapsed or expanded depending on UI state\n- timeout / truncation notices render as dim metadata lines\n- images are returned as content image blocks; live updates may also carry `details.images` while execution is in progress\n\nSide-channel artifacts:\n\n- `session.allocateOutputArtifact?.(\"eval\")` may allocate an `artifact://...` backing store for spilled output.\n- Truncated output metadata points at that artifact when available.\n\n## Flow\n\n1. `EvalTool.execute()` in `packages/coding-agent/src/tools/eval.ts` receives `params.cells` already validated by the Zod schema — no string parsing step.\n2. For each cell, `execute()` maps `cell.language` to an `EvalLanguage` (`\"py\"` → `\"python\"`, `\"js\"` → `\"js\"`) and calls `resolveBackend(session, language)`:\n   - `python` is gated on `eval.py !== false` and `pythonBackend.isAvailable(session)`.\n   - `js` is gated on `eval.js !== false`.\n   - A disabled or unavailable requested backend throws `ToolError`; there is no auto-fallback or sniffing.\n3. The tool allocates an `OutputSink`, a `TailBuffer`, per-cell result objects, and a `sessionAbortController`. `session.trackEvalExecution?.(...)` can wrap the whole run for external cancellation tracking.\n4. It resolves the executor session id from `session.getEvalSessionId?.()`, falling back to `defaultEvalSessionId(session)`. Subagents inherit the parent's id so both sides share the same JS VM and Python kernel for each backend.\n5. Cells execute sequentially within one eval tool call. For each cell, `execute()`:\n   - clamps `cell.timeout ?? 30` seconds through `clampTimeout(\"eval\", ...)`\n   - builds a combined abort signal from the tool signal, the timeout, and the session abort controller\n   - marks the cell `running` and emits an update\n   - calls the backend’s `execute()` with `cwd`, `sessionId`, `sessionFile`, `kernelOwnerId`, `deadlineMs`, `reset` (defaults to `false`), artifact info, and chunk callback\n6. JS cells dispatch through `packages/coding-agent/src/eval/js/index.ts` into `executeJs()`; Python cells dispatch through `packages/coding-agent/src/eval/py/index.ts` into `executePython()`.\n7. Backend text chunks stream into the shared `OutputSink`; rich outputs are accumulated separately as JSON, images, markdown markers, and status events.\n8. After each cell:\n   - text output is trimmed and stored on that cell result\n   - multi-cell runs prefix text with `[i/n]` and the optional title\n   - cancellations return early with `isError: true` and a cell-specific abort message\n   - non-zero exit codes return early with `isError: true` and a message naming the failed cell\n   - later cells are skipped after the first error, but earlier cell state persists in the underlying runtime\n9. On success, the tool joins all cell outputs, synthesizes `(no text output)` or `(no output)` when needed, and attaches truncation metadata from `summarizeFinal()`.\n10. The renderer uses `details.cells`, `details.jsonOutputs`, and `details.statusEvents` to build notebook-style output. `mergeCallAndResult = true` and `inline = true`, so call and result render together in the transcript.\n\n## Modes / Variants\n\n### Backend selection\n\nBackend choice is **explicit per cell** — there is no auto-detection.\n\n- `language: \"py\"` → Python (IPython/Jupyter) backend\n- `language: \"js\"` → JavaScript VM backend\n\nIf the requested backend is disabled or unavailable, the tool throws `ToolError` for that cell. The caller chooses; the tool does not silently substitute.\n\n### JavaScript runtime\n\nImplemented in `packages/coding-agent/src/eval/js/worker-core.ts`, `packages/coding-agent/src/eval/js/shared/prelude.txt`, and `packages/coding-agent/src/eval/js/shared/helpers.ts`.\n\n- Persistent worker-backed VM sessions keyed by `js:${sessionId}`\n- `reset: true` calls `resetVmContext(sessionKey)` before the cell executes; reset is destructive for all live runs on that JS session\n- Top-level `await` and bare `return` are supported by wrapping code in an async IIFE when `wrapCode()` sees `await` or `return`\n- Top-level static `import ... from ...` and dynamic `import(...)` calls are routed through `rewriteImports()`, which sends them via `__omp_import__` so the specifier resolves against the session cwd\n- Module cache is busted for **local** imports between cells so edits to source files are picked up without restarting the runtime. `__omp_import__` deletes `require.cache[absPath]` before re-importing whenever the original specifier is a filesystem path: relative (`./x`, `../x`, `.`, `..`), POSIX-absolute (`/...`), home-prefixed (`~/...`), or Windows drive-letter (`C:\\...` / `C:/...`). Bare specifiers (`react`, `lodash/x`) and URL/scheme specifiers (`node:fs`, `file://...`, `https://...`) are left in cache so package identity stays stable across cells. The cache-bust only fires when the resolved target is an absolute path — unresolved bare-package fallbacks (`resolveImportSpecifier()` returning the original specifier) skip it.\n- The prelude installs globals:\n  - `display`, `print`\n  - `read`, `write`, `append`, `sort`, `uniq`, `counter`, `diff`, `tree`, `env`, `output`\n  - `tool.<name>(args)` proxy for arbitrary session tool calls\n  - `completion(prompt, opts?)` for oneshot, stateless model calls (see _Oneshot completion helper_ below)\n  - `agent(prompt, opts?)` for a single subagent call, plus `parallel()` / `pipeline()` bounded-pool helpers (see _Subagent helper_ below)\n- JS helpers that touch the host/runtime boundary are async and `await`able; pure text helpers (`sort`, `uniq`, `counter`) return synchronously but may still be safely awaited.\n- JS helper signatures use a trailing options object rather than Python keyword arguments:\n  - `await read(path, { offset?, limit? })`\n  - `await tree(path = \".\", { maxDepth?, hidden? })`\n  - `sort(text, { reverse?, unique? })`, `uniq(text, { count? })`, `counter(items, { limit?, reverse? })`\n  - `await agent(prompt, { agentType?, model?, context?, label?, schema? })`\n  - `await parallel([() => agent(\"a\"), () => agent(\"b\")])`\n  - `await pipeline(items, stage1, stage2)`\n- `display(value)` behavior:\n  - plain objects/arrays become JSON outputs\n  - `{ type: \"image\", data, mimeType }` becomes an image output\n  - scalars become text\n- The VM exposes a restricted `process` subset plus `Buffer`, `fetch`, `Blob`, `File`, `Headers`, `Request`, `Response`, `fs`, `require`, and browser-style globals\n- Concurrent runs on the same VM are not queued end-to-end. Synchronous JS still runs on the single event loop; awaited regions can interleave with sibling runs.\n\n### Python runtime\n\nImplemented in `packages/coding-agent/src/eval/py/executor.ts`, `packages/coding-agent/src/eval/py/kernel.ts`, and `packages/coding-agent/src/eval/py/prelude.py`. See `docs/python-repl.md` for gateway and kernel details.\n\n- Default mode is retained `session` kernels keyed by `python:${sessionId}`\n- Optional `python.kernelMode = \"per-call\"` creates a fresh kernel for each cell and shuts it down afterward\n- `reset: true` disposes the retained kernel for that session before the cell runs; later Python cells in the same tool call reuse the fresh kernel\n- Startup path:\n  - availability check\n  - create/connect kernel\n  - initialize cwd / env / `sys.path`\n  - execute `PYTHON_PRELUDE`\n- Python cells run in the runner's persistent asyncio event loop, so top-level `await` works; the prompt warns not to use `asyncio.run(...)`\n- The Python prelude defines helpers with the same surface as JS where practical, including `tool.<name>(args)`, `completion(...)`, and `agent(...)` through a per-run loopback bridge\n- Synchronous statement blocks run in the default executor with ContextVar state copied in; the GIL still serializes bytecode execution, but awaited regions can interleave with sibling cells\n- Kernel `display_data` / `execute_result` messages map to:\n  - `application/x-omp-status` → status event\n  - `image/png` → image output\n  - `application/json` → JSON output\n  - `text/markdown` → markdown output\n  - `text/plain` → text output\n  - `text/html` → HTML converted to markdown with `htmlToBasicMarkdown()`\n- Interactive stdin is rejected: `input_request` sends an empty reply, marks `stdinRequested`, and the executor returns exit code `1`\n\n### Oneshot completion helper (`completion`)\n\nBoth runtimes expose `completion()` — a single stateless completion against a model tier. It is intentionally minimal: no conversation history, no agent-visible tools, pure text in / text (or object) out. Implemented host-side in `packages/coding-agent/src/eval/completion-bridge.ts` and routed through the existing tool bridge under the reserved name `__completion__`.\n\n- Signatures:\n  - JS: `await completion(prompt, { model?, system?, schema? })`\n  - Python: `completion(prompt, *, model=\"default\", system=None, schema=None)`\n- `model` selects a tier (default `\"default\"`):\n  - `\"smol\"` → `pi/smol` role (fast / cheap)\n  - `\"default\"` → the session's active model, falling back to the `pi/default` role\n  - `\"slow\"` → `pi/slow` role; requests high reasoning effort only on reasoning-capable models\n- `system` (optional) supplies a system prompt.\n- `schema` (optional) is a plain JSON-Schema object. When present, the model is forced to call a single synthetic `respond` tool with that schema (loose, non-strict), and the helper returns the parsed object. When absent, the helper returns the completion string.\n- Errors surface as exceptions: unresolved tier, missing API key, an `error`/`aborted` stop reason, or empty output each raise.\n\n### Subagent helper (`agent`)\n\nBoth runtimes expose `agent()` — a single subagent invocation routed through `packages/coding-agent/src/eval/agent-bridge.ts` into the same `runSubprocess(...)` path used by the `task` tool. It uses the current eval session's spawn policy and inherits the parent eval executor id, so parent and subagent code share JS/Python runtime state.\n\n- Signatures:\n  - JS: `await agent(prompt, { agentType?, model?, context?, label?, schema? })`\n  - Python: `agent(prompt, *, agent_type=\"task\", model=None, context=None, label=None, schema=None)`\n- `agentType` / `agent_type` defaults to the bundled `task` agent and resolves through normal agent discovery, so project and user agents work.\n- `model` overrides the selected agent's model. Without it, normal per-agent settings and the agent frontmatter model apply.\n- `context` supplies shared background; `label` controls the `agent://<id>` output label prefix.\n- `schema` passes a JSON Schema to the subagent structured-output path. When present, the helper parses the final JSON text and returns an object.\n- Spawn restrictions use `session.getSessionSpawns()` exactly like the `task` tool. Eval-driven subagent recursion is capped at depth 3.\n- JS and Python both expose `parallel(thunks)` and `pipeline(items, ...stages)`; both use a bounded async/threaded pool whose width tracks the `task.maxConcurrency` setting (the same ceiling the `task` tool uses; `0` = run every item at once), preserve item order, and propagate rejections. The width is fetched live from the host via the `__concurrency__` bridge, so the helpers no longer take a `concurrency` argument.\n- Errors surface as exceptions: unknown or disabled agent, disallowed spawn, recursion cap, subagent failure, or invalid structured output all fail the eval cell.\n\n### Multi-language call behavior\n\nA single tool call can mix Python and JS cells. Persistence is per language runtime:\n\n- `reset: true` on a Python cell does not touch JS state\n- `reset: true` on a JS cell does not touch Python state\n- each backend keeps its own retained session keyed from the same session-derived ID\n\n## Side Effects\n\n- Filesystem\n  - JS/Python prelude helpers can read, write, append, diff, and traverse filesystem paths under the session cwd or absolute paths.\n  - JS helper `read()` rejects protocol URIs (`://`) and directory paths; use `tool.read(...)` for internal URLs or reader-mode behavior.\n  - Output may spill to an artifact file via `OutputSink`.\n- Network\n  - Python backend speaks NDJSON to a local `python3` subprocess over stdin/stdout (no network).\n  - JS runtime exposes `fetch` and `tool.<name>()`; those tools may perform additional network I/O.\n- Subprocesses / native bindings\n  - Python availability check runs `<python> -c ...`.\n  - Python backend spawns one `python -u runner.py` subprocess per kernel; cancellation sends `SIGINT`. Details in `docs/python-repl.md`.\n  - `agent()` runs one in-process subagent via the task executor; that subagent may use its configured tools.\n- Session state\n  - `session.assertEvalExecutionAllowed?.()` can block execution.\n  - `session.trackEvalExecution?.(...)` can register cancellable eval work.\n  - `session.getSessionFile?.()`, `session.getEvalSessionId?.()`, and `session.getEvalKernelOwnerId?.()` influence VM/kernel reuse and artifact lookup.\n  - JS VM contexts persist across eval calls until reset/disposal.\n  - Python retained kernels persist until reset, owner cleanup, or process exit.\n  - `agent()` allocates `agent://<id>` output artifacts and reuses the parent's eval executor id.\n- User-visible prompts / interactive UI\n  - none; stdin requests are rejected programmatically\n- Background work / cancellation\n  - Python retained kernels have heartbeat and idle cleanup timers.\n  - Cancellation hard-kills/resets the shared executor for that backend: JS terminates the worker, Python sends SIGINT and may escalate to subprocess shutdown.\n\n## Limits & Caps\n\n- Per-cell timeout default: 30s (applied when `timeout` is omitted in `EvalTool.execute()`; clamped through `TOOL_TIMEOUTS.eval.default` in `packages/coding-agent/src/tools/tool-timeouts.ts`)\n- Schema-level `timeout` range: integer `1..600` seconds (enforced by Zod on the cell schema)\n- Timeout clamp at runtime: 1s minimum, 600s maximum (`TOOL_TIMEOUTS.eval` in `packages/coding-agent/src/tools/tool-timeouts.ts`)\n- Transcript code/output preview: 10 lines by default (`EVAL_DEFAULT_PREVIEW_LINES` in `packages/coding-agent/src/tools/eval.ts`)\n- Output truncation window: 50KB default (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`)\n- Output line cap inside truncation helpers: 3000 lines (`DEFAULT_MAX_LINES` in `packages/coding-agent/src/session/streaming-output.ts`)\n- Streaming tail buffer for live updates: `DEFAULT_MAX_BYTES * 2` = 100KB (`packages/coding-agent/src/tools/eval.ts`)\n- JS/Python `parallel()` / `pipeline()` helper pool width: the `task.maxConcurrency` setting (default 32; `0` = unbounded), resolved live via the `__concurrency__` bridge (`packages/coding-agent/src/eval/concurrency-bridge.ts`)\n- Eval-driven `agent()` recursion cap: task depth 3 (`EVAL_AGENT_MAX_DEPTH`)\n- Python retained kernel idle timeout: 5 minutes (`IDLE_TIMEOUT_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python retained kernel cap: 4 sessions (`MAX_KERNEL_SESSIONS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python retained kernel cleanup sweep: every 30s (`CLEANUP_INTERVAL_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python owner-cleanup shutdown wait: 2000ms (`OWNER_CLEANUP_KERNEL_SHUTDOWN_TIMEOUT_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python heartbeat interval: 5s (`ensureKernelHeartbeat()` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python external gateway availability check timeout: 5s (`AbortSignal.timeout(5000)` in `packages/coding-agent/src/eval/py/kernel.ts`)\n- Python auto-restart budget: one restart per retained session before hard failure (`restartCount > 1` in `packages/coding-agent/src/eval/py/executor.ts`)\n\n## Errors\n\n- Zod validation rejects malformed `cells` arrays before `execute()` runs (missing `language`/`code`, out-of-range `timeout`, empty `cells`).\n- Missing session without proxy executor throws `ToolError(\"Eval tool requires a session when not using proxy executor\")`.\n- Disabled/unavailable backends throw `ToolError` from `resolveBackend()`:\n  - `eval.py = false` and a `py` cell is requested\n  - `eval.js = false` and a `js` cell is requested\n  - Python kernel unavailable and a `py` cell is requested\n- JS runtime exceptions are converted into text output plus `exitCode: 1`; cancellations return `cancelled: true` and may append `Command timed out`.\n- Python execution errors from the kernel become text output and `exitCode: 1`; later cells are skipped.\n- Python stdin requests are treated as errors with the message `Kernel requested stdin; interactive input is not supported.`\n- Cancellation is returned, not thrown, once backend execution has started. The tool formats it as a cell failure and sets `details.isError = true`.\n- If output truncates, the tool still succeeds; truncation is surfaced through `details.meta` and artifact-backed full output when available.\n\n## Shared executor trade-offs\n\n- Parent agents and subagents share eval state bidirectionally when a subagent inherits the parent's executor id. Mutations in either direction are visible to the other participant.\n- Async regions of concurrent runs can interleave. Synchronous JS still blocks the VM event loop; synchronous Python still contends on the GIL.\n- Cancelling one run is destructive to the shared backend executor. This is intentional: JS worker termination and Python SIGINT/subprocess shutdown are the only reliable way to interrupt arbitrary user code.\n- `reset: true` is destructive for every live run on that backend session id. New starts on that backend are rejected while reset is in flight.\n\n## Notes\n\n- Backend selection is strictly explicit per cell: `language` must be `\"py\"` or `\"js\"`. The previous `*** Cell` header parser, the `eval.lark` constrained grammar, and the sniffer-based fallback have all been removed.\n- `EvalTool.customFormat` no longer exists. Tool calls flow through the standard JSON schema; there is no Lark-constrained sampling path.\n- `tool.<name>()` exists in both JS and Python. Python calls route through a per-run loopback bridge keyed by the current cell id.\n- JS helper paths reject protocol URIs (`://`) in `resolveRegularFile()` for `read()`, and resolve other paths against the session cwd or absolute filesystem path. Use `tool.read(...)` or another tool explicitly for internal URLs.\n- Python helper `output(...)` depends on `PI_ARTIFACTS_DIR` or `PI_SESSION_FILE`; it fails outside a session-backed run.\n- `display()` can produce text and structured outputs from the same value; the renderer prefers markdown over `text/plain` when both exist.\n- JS static imports are rewritten only at top level. Nested imports stay invalid and surface normal JS syntax/runtime errors.\n- `EvalTool` is `concurrency = \"exclusive\"` within one agent session, but parent and subagent sessions can run eval concurrently when they share an inherited executor id.\n- The tool description shown to the model is templated by backend availability (`getEvalToolDescription()`); if Python is unavailable, the prompt omits Python-specific instructions.\n",
 	"tools/find.md": "# find\n\n> Find filesystem paths by glob; use `search` when you need content matches instead of path matches.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/find.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/find.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/path-utils.ts` — normalize inputs; split base path vs glob.\n  - `packages/coding-agent/src/tools/list-limit.ts` — apply result-count caps.\n  - `packages/coding-agent/src/session/streaming-output.ts` — truncate text output at byte cap.\n  - `packages/coding-agent/src/tools/tool-result.ts` — build `content` and `details.meta`.\n  - `packages/coding-agent/src/tools/output-meta.ts` — encode limit / truncation metadata.\n  - `packages/coding-agent/src/tools/tool-errors.ts` — map user-facing tool errors.\n  - `packages/coding-agent/src/tools/index.ts` — register the built-in local implementation.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `paths` | `string[]` | Yes | One or more globs, files, directories, or internal URLs with backing files. Empty strings are rejected. Single entries accidentally joined with comma, semicolon, or whitespace are expanded only after existence validation; existing paths containing delimiters stay intact. 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| `gitignore` | `boolean` | No | Whether `.gitignore` is respected during local native globbing. Defaults to `true`; set `false` to include gitignored files. |\n| `limit` | `number` | No | Max returned paths. Defaults to `200`; finite positive inputs are floored then clamped to `1..200`. |\n| `timeout` | `number` | No | Timeout in seconds. Defaults to `5`; clamped to `0.5..60`. On timeout, returns partial matches collected so far with a timeout notice and `truncated: true`. |\n\n## Outputs\nThe tool returns a single text block plus structured `details`.\n\n- Success text: matching paths grouped by directory. Each non-root group starts with `# <dir>/` and then lists basenames; root-level matches are listed without a header. Directory matches carry a trailing `/`. Exact file inputs return that file path as one line.\n- Empty result text: `No files found matching pattern`, optionally followed by a timeout or missing-path notice.\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. Final output is grouped; streaming snapshots are not.\n\n## Flow\n\n1. `FindTool.execute()` expands delimiter-flattened local `paths` entries with `expandDelimitedPathEntries(..., parseFindPattern)` unless custom operations are injected. The splitter validates candidate parts by statting their parsed base paths, keeps existing delimiter-containing paths intact, accepts comma/semicolon splits when at least one part resolves, and accepts whitespace splits only when every part resolves.\n2. The tool normalizes each resulting 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 ``.\n3. 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.\n4. 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()`.\n5. `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.\n6. `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`.\n7. `limit` defaults to `DEFAULT_LIMIT` (`200`), must be positive and finite, is floored, then clamped to `MAX_LIMIT` (`200`). `hidden` and `gitignore` both default to `true`. `timeout` is converted to milliseconds and clamped to `500..60_000` before building an `AbortSignal.timeout(...)`.\n8. 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 `hidden`, `maxResults: effectiveLimit`, `sortByMtime: true`, `gitignore: useGitignore`, and the combined abort signal.\n9. In the local branch, optional `onMatch` callbacks convert each match to a cwd-relative display path and emit throttled progress updates.\n10. After native glob returns, JS sorts `result.matches` by `mtime` descending (`(b.mtime ?? 0) - (a.mtime ?? 0)`) before formatting paths.\n11. `buildResult()` applies `applyListLimit()` to cap the array again at `effectiveLimit`, formats paths with `formatFindGroupedOutput()`, appends notices, 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.\n12. `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- **Internal URL input**: supported when the internal router resolves the URL to a backing file. Internal URL globs are rejected.\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 the configured internal timeout.\n\n## Limits & Caps\n- Default result limit: `200` (`DEFAULT_LIMIT` in `packages/coding-agent/src/tools/find.ts`).\n- Maximum result limit: `200` (`MAX_LIMIT`); larger inputs are clamped.\n- Local glob timeout: default `5000` ms, clamped to `500..60_000` ms.\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  - timeout result text is `find timed out after <seconds>s; returning <N> partial matches — increase timeout or narrow pattern` and is returned as a successful, truncated partial result rather than an error.\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` defaults to enabled in the built-in local branch. Use `gitignore: false` to disable it for native traversal.\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 does not force `fileType: File`; it can return files and directories from native glob. Directory outputs also occur through exact-path passthrough or custom delegates that return them.",
 	"tools/github.md": "# github\n\n> Dispatch GitHub CLI operations for repositories, issues, pull requests, search, and Actions run watching.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/gh.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/github.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/gh-format.ts` — shorten commit SHAs for summaries.\n  - `packages/coding-agent/src/tools/gh-renderer.ts` — TUI rendering, especially `run_watch` live/result views.\n  - `packages/coding-agent/src/utils/git.ts` — `gh`/`git` process wrappers, repo locking, branch config writes.\n  - `packages/utils/src/dirs.ts` — base directory for dedicated PR worktrees.\n  - `packages/coding-agent/src/sdk.ts` — session artifact allocation hook.\n  - `packages/coding-agent/src/session/artifacts.ts` — artifact filename format `<id>.<toolType>.log`.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `\"repo_view\" \\| \"pr_create\" \\| \"pr_checkout\" \\| \"pr_push\" \\| \"search_issues\" \\| \"search_prs\" \\| \"search_code\" \\| \"search_commits\" \\| \"search_repos\" \\| \"run_watch\"` | Yes | Dispatch selector. `GithubTool.execute()` switches only on this field. |\n| `repo` | `string` | No | `owner/repo` override. Ignored when the identifier argument is already a full GitHub URL. For `search_issues`/`search_prs`/`search_code`/`search_commits`, defaults to the current checkout's `owner/repo` when omitted (skipped when the query already contains a `repo:`/`org:`/`user:`/`owner:` qualifier or when current-repo resolution fails). Required in practice when `gh` cannot infer repo context from the current checkout. |\n| `branch` | `string` | No | Used by `repo_view`, `pr_push`, and `run_watch`. `run_watch` falls back to current git branch when `run` is omitted; `pr_push` falls back to current branch. |\n| `pr` | `string \\| string[]` | No | Used by `pr_checkout`. Each item may be a PR number, branch name, or GitHub PR URL. Array form enables batching. Omitted means current branch PR. |\n| `force` | `boolean` | No | Used only by `pr_checkout`. Defaults to `false`; allows resetting an existing `pr-<number>` local branch to the PR head commit. |\n| `forceWithLease` | `boolean` | No | Used only by `pr_push`; passed through to git push. |\n| `title` | `string` | No | Used only by `pr_create`. Required unless `fill` is `true`. |\n| `body` | `string` | No | Used only by `pr_create`. Mutually exclusive with `fill`. Empty/omitted body becomes `--body \"\"` to suppress the interactive editor. Non-empty body is written to a temp file and passed as `--body-file`. |\n| `base` | `string` | No | Used only by `pr_create`; passed as `--base`. |\n| `head` | `string` | No | Used only by `pr_create`; passed as `--head`. |\n| `draft` | `boolean` | No | Used only by `pr_create`. Defaults to `false`. |\n| `fill` | `boolean` | No | Used only by `pr_create`. Defaults to `false`. Mutually exclusive with `title` and `body`. |\n| `reviewer` | `string[]` | No | Used only by `pr_create`; each entry becomes `--reviewer`. |\n| `assignee` | `string[]` | No | Used only by `pr_create`; each entry becomes `--assignee`. |\n| `label` | `string[]` | No | Used only by `pr_create`; each entry becomes `--label`. |\n| `query` | `string` | No | Used by all `search_*` ops. Required by local validation only for `search_code`; the other search ops compose it with optional date/repo/type qualifiers and send the result to GitHub. |\n| `since` | `string` | No | Lower date bound for `search_issues`, `search_prs`, `search_commits`, and `search_repos`. Accepts relative durations (`3d`, `12h`, `2w`, `2mo`, `1y`), `YYYY-MM-DD`, or an ISO datetime. Rejected for `search_code`. |\n| `until` | `string` | No | Upper date bound for `search_issues`, `search_prs`, `search_commits`, and `search_repos`. Same formats as `since`. Rejected for `search_code`. |\n| `dateField` | `\"created\" \\| \"updated\"` | No | Date qualifier field for issue/PR/repo search. Defaults to `created`; repo search maps `updated` to GitHub's `pushed:` qualifier. Ignored for commit search, which always uses `committer-date:`. |\n| `limit` | `number` | No | Used by all `search_*` ops. Defaults to `10`, floored, clamped to `50`, and must be `> 0`. |\n| `run` | `string` | No | Used only by `run_watch`. Must be a numeric run ID or full GitHub Actions run URL. |\n| `tail` | `number` | No | Used only by `run_watch`. Defaults to `15`, floored, clamped to `200`, and must be `> 0`. |\n\n## Outputs\nThe tool returns a single text result built by `buildTextResult()` in `packages/coding-agent/src/tools/gh.ts`.\n\n- `content`: one text block. Multi-item ops join sections with blank lines and `---` separators.\n- `sourceUrl`: set for single repo/PR/run results when a canonical URL is known.\n- `details`: optional structured metadata used by the TUI renderer.\n  - Common fields: `artifactId`, `repo`, `branch`, `worktreePath`, `remote`, `remoteBranch`, `headSha`, `runId`, `runIds`, `status`, `conclusion`, `failedJobs`.\n  - `pr_checkout` adds `checkouts: GhPrCheckoutSummary[]`.\n  - `run_watch` adds `watch: GhRunWatchViewDetails`, which drives the custom live/result renderer in `packages/coding-agent/src/tools/gh-renderer.ts`.\n- Artifact trailer: when `artifactId` is present, the text body gets an appended line like `Full failed-job logs: artifact://<id>`.\n  - `run_watch` allocates artifacts with `session.allocateOutputArtifact(\"github\")`; persistent sessions therefore save failed-log bodies as `<artifact-dir>/<id>.github.log`.\n\n`run_watch` is the only streaming op. It emits `onUpdate` snapshots while polling, then returns one final text result.\n\n## Flow\n1. `GithubTool.createIf()` exposes the tool only when `git.github.available()` finds `gh` on `PATH`.\n2. `GithubTool.execute()` wraps dispatch in `untilAborted()` and switches on `params.op`.\n3. Each op normalizes optional strings, arrays, booleans, and numeric caps locally in `packages/coding-agent/src/tools/gh.ts`.\n4. CLI execution goes through `git.github.run/json/text()` in `packages/coding-agent/src/utils/git.ts`:\n   - spawns `gh ...` with `Bun.spawn()`;\n   - trims stdout/stderr unless `trimOutput: false`;\n   - maps common auth/repo-context failures into tool-facing `ToolError` messages;\n   - `json()` rejects empty or invalid JSON.\n5. Read-style ops (`repo_view`, `search_*`) fetch JSON and format Markdown-like text summaries. Single-issue and single-PR views were moved out of the tool and now resolve through the `issue://` / `pr://` internal URL schemes, which share the same SQLite cache.\n6. PR diffs moved out of the tool. `pr://<N>/diff` lists changed files, `pr://<N>/diff/<i>` slices a single file, and `pr://<N>/diff/all` returns the full unified diff — see `docs/tools/read.md`. All three variants share one `gh pr diff` invocation through the `pr-diff` cache row.\n7. `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.\n8. `pr_push` reads PR head metadata back from git branch config, derives a refspec, then pushes with `git.push()`.\n9. `pr_create` shells out once, then best-effort re-reads the created PR for a richer summary.\n10. `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.\n11. Final text goes through `toolResult().text(...)`; if `session.allocateOutputArtifact()` returns a slot, failed-log text is persisted with `Bun.write()`.\n\n## Modes / Variants\n\n### `repo_view`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `branch` |\n| `gh` command | `gh repo view [<repo>] [--branch <branch>] --json <GH_REPO_FIELDS>` |\n| Batching | None |\n| Output | `# <owner/repo>` header, description, URL, default branch, requested branch, visibility, permission, primary language, stars, forks, archive/fork flags, updated timestamp, homepage, topics. `sourceUrl = data.url`. |\n\nIf `repo` is omitted, `gh` repository resolution is used.\n\nSingle-issue and single-PR reads live in the `issue://<N>` / `pr://<N>` URL schemes (see `docs/tools/read.md`). They share `~/.omp/cache/github-cache.db` (override via `OMP_GITHUB_CACHE_DB`) and the `github.cache.softTtlSec` / `github.cache.hardTtlSec` / `github.cache.enabled` settings. The cache retains rendered Markdown plus the raw JSON payload returned by `gh`, including private bodies, comments, reviews, and review comments when comments are enabled; rows are scoped by the local GitHub credential fingerprint. Root and repo-scoped reads (`issue://`, `pr://owner/repo`) issue a live `gh issue list` / `gh pr list` for browsing; query params `state`, `limit`, `author`, `label` pass through to `gh` (`issue://` accepts `state=open|closed|all`; `pr://` also accepts `merged`). PR diffs ride the same cache under `pr://<N>/diff[/…]`: the listing, full diff, and per-file slices all share one `pr-diff` row keyed by repo and PR number.\n\n### `pr_create`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` plus either `fill=true` or `title` |\n| Optional fields | `repo`, `title`, `body`, `base`, `head`, `draft`, `fill`, `reviewer[]`, `assignee[]`, `label[]` |\n| `gh` command | `gh pr create ...` with flags assembled from provided fields |\n| Batching | None |\n| Output | `# Created Pull Request ...` summary with URL, state, draft flag, base/head, author, created time, labels, optional body. `sourceUrl` is the created PR URL. |\n\nBranches:\n- `fill && (title || body !== undefined)` throws.\n- Non-empty `body` is written under a temp dir `gh-pr-body-*` in `os.tmpdir()`, passed as `--body-file`, then removed in `finally`.\n- After creation, the tool parses the returned URL and best-effort runs `gh pr view <number> --repo <repo> --json <GH_PR_FIELDS_NO_COMMENTS>`; failures there are swallowed.\n\n### `pr_checkout`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `pr`, `force` |\n| `gh` command | For each requested PR: `gh pr view [<pr>] [--repo <repo>] --json <GH_PR_CHECKOUT_FIELDS>`; cross-repo PRs may also call `gh repo view <headRepository> --json <GH_REPO_CLONE_FIELDS>`. |\n| Batching | Yes. `pr` may be `string[]`; each PR is resolved in parallel, but git mutations are serialized per primary repo by `git.withRepoLock()`. |\n| Output | Single PR: checkout/worktree summary plus `details.repo`, `details.branch`, `details.worktreePath`, `details.remote`, `details.remoteBranch`, `details.checkouts`. Batched: `# <n> Pull Request Worktrees (...)` plus one section per PR and aggregated `details.checkouts`. |\n\nWorktree and metadata behavior:\n- Local branch name is always `pr-<number>`.\n- Worktree path is `path.join(getWorktreesDir(), encodeRepoPathForFilesystem(primaryRepoRoot), localBranch)`, where `getWorktreesDir()` is `~/.omp/wt`; effective path is `~/.omp/wt/<encoded-primary-repo-root>/pr-<number>`.\n- Existing worktree detection is by branch ref `refs/heads/pr-<number>` from `git.worktree.list()`.\n- New worktree creation calls `git.worktree.add(repoRoot, finalWorktreePath, localBranch, { signal })` after verifying the path is neither already registered nor already present on disk.\n- For same-repo PRs, remote is `origin`. For cross-repo PRs, the tool resolves a clone URL for the head repo, reuses an existing remote with the same URL when possible, or creates `fork-<owner>` / `fork-<owner>-<n>`.\n- The branch push metadata is persisted with `git config` under the repository's shared `.git/config` as:\n  - `branch.pr-<number>.remote`\n  - `branch.pr-<number>.merge`\n  - `branch.pr-<number>.pushRemote`\n  - `branch.pr-<number>.ompPrHeadRef`\n  - `branch.pr-<number>.ompPrUrl`\n  - `branch.pr-<number>.ompPrIsCrossRepository`\n  - `branch.pr-<number>.ompPrMaintainerCanModify`\n- If `refs/heads/pr-<number>` already exists at a different commit, checkout fails unless `force=true`, in which case `git branch --force` resets it to the fetched PR head.\n- If a matching worktree already exists, the tool reuses it and reports `reused: true`.\n\n### `pr_push`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `branch`, `forceWithLease` |\n| `gh` command | None. This path uses git, not `gh`. |\n| Batching | None |\n| Output | `# Pushed Pull Request Branch` summary with local branch, remote, remote branch, remote URL, PR URL, and force-with-lease flag. `sourceUrl = prUrl` when known. |\n\nPush target resolution reads the `branch.<name>.ompPrHeadRef`, `pushRemote`/`remote`, `ompPrUrl`, `ompPrMaintainerCanModify`, and `ompPrIsCrossRepository` git-config keys written by `pr_checkout`. If the current checked-out branch matches the target branch, the source ref is `HEAD`; otherwise it pushes `refs/heads/<branch>`. The refspec is `HEAD:refs/heads/<headRef>` or `refs/heads/<branch>:refs/heads/<headRef>`.\n\n### `search_issues`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `query`, `limit`, `since`, `until`, `dateField` |\n| `gh` command | `gh api -X GET /search/issues -f q=\"<query> [date qualifier] [repo:<repo>] is:issue\" -F per_page=<limit>` |\n| Batching | None |\n| Output | `# GitHub issues search`, echoed query, optional repo, result count, then one bullet per issue with repo/state/author/labels/timestamps/URL. |\n\n`repo` defaults to the current checkout's `owner/repo` via `resolveSearchRepoScope()` when omitted. The default is suppressed when the composed query already contains a leading `repo:`/`org:`/`user:`/`owner:` qualifier or when `gh repo view` fails to resolve the current checkout (e.g. outside a github remote).\n\n### `search_prs`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `query`, `limit`, `since`, `until`, `dateField` |\n| `gh` command | `gh api -X GET /search/issues -f q=\"<query> [date qualifier] [repo:<repo>] is:pr\" -F per_page=<limit>` |\n| Batching | None |\n| Output | Same shape as `search_issues`, labeled as pull requests. |\n\n`repo` defaults to the current checkout's `owner/repo` as in `search_issues`.\n\n### `search_code`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh api -X GET /search/code -f q=\"<query> [repo:<repo>]\" -F per_page=<limit> -H \"Accept: application/vnd.github.text-match+json\"` |\n| Batching | None |\n| Output | `# GitHub code search`, result count, then one bullet per match with path, repo, short commit SHA, URL, and first normalized text-match fragment line when present. |\n\n`repo` defaults to the current checkout's `owner/repo` as in `search_issues`. `since` and `until` are explicitly rejected for this op because GitHub code search has no supported date qualifier.\n\n### `search_commits`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `query`, `limit`, `since`, `until`, `dateField` (accepted but ignored; commit searches use `committer-date`) |\n| `gh` command | `gh api -X GET /search/commits -f q=\"<query> [committer-date qualifier] [repo:<repo>]\" -F per_page=<limit>` |\n| Batching | None |\n| Output | `# GitHub commits search`, result count, then one bullet per commit: short SHA + first commit-message line, repo, author, date, URL. |\n\n`repo` defaults to the current checkout's `owner/repo` as in `search_issues`.\n\n### `search_repos`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `query`, `limit`, `since`, `until`, `dateField` |\n| `gh` command | `gh api -X GET /search/repositories -f q=\"<query> [date qualifier]\" -F per_page=<limit>` |\n| Batching | None |\n| Output | `# GitHub repositories search`, result count, then one bullet per repo with first description line, language, stars, forks, open issues, visibility, archive/fork flags, updated time, URL. |\n\n`repo` is intentionally not used for this op. If `query`, `since`, and `until` are all omitted, the tool sends an empty GitHub repository-search query and the GitHub API may reject it.\n\n### `run_watch`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `branch`, `run`, `tail` |\n| `gh` command | Repo resolution: `gh repo view --json nameWithOwner -q .nameWithOwner` when `repo` and run URL repo are both absent. Single-run mode uses `gh api --method GET /repos/<repo>/actions/runs/<runId>` and `gh api --method GET /repos/<repo>/actions/runs/<runId>/jobs`. Commit mode uses `gh api --method GET /repos/<repo>/branches/<branch>`, `gh api --method GET /repos/<repo>/actions/runs`, `gh api --method GET /repos/<repo>/actions/runs/<runId>/jobs`, and `gh api /repos/<repo>/actions/jobs/<jobId>/logs` for failed jobs. |\n| Batching | Implicit batching only in commit mode: all workflow runs for one commit are tracked together. |\n| Output | Streaming watch snapshots via `onUpdate`, then a final text report. On failure, appends `Full failed-job logs: artifact://<id>` and sets `details.artifactId`. |\n\nWatch flow:\n- `run` parsing accepts either a decimal run ID or a full run URL. URL repo must match explicit `repo` when both are given.\n- Poll interval is fixed at 3 seconds (`RUN_WATCH_INTERVAL_DEFAULT`).\n- Failure grace period is fixed at 5 seconds (`RUN_WATCH_GRACE_DEFAULT`). When any failed job appears before completion, the tool emits a note, waits once, re-fetches state, then collects logs so concurrent failures are included.\n- Failed-job logs are fetched with `gh api /repos/<repo>/actions/jobs/<jobId>/logs` via `git.github.run()`, not `json()`. Non-zero exit leaves `available: false` instead of failing the whole watch.\n- Inline result includes only the last `tail` lines per failed job. The saved artifact contains full logs (`mode: \"full\"`).\n- In commit mode, success is intentionally double-checked: once all known runs are successful, the tool waits one more poll interval and succeeds only if the set of run IDs is unchanged. This avoids returning before late workflow runs appear for the same commit.\n- `details.watch` drives a specialized renderer in `packages/coding-agent/src/tools/gh-renderer.ts`; non-watch results fall back to generic text rendering.\n\n## Side Effects\n- Filesystem\n  - `pr_create` may create a temp dir under `os.tmpdir()` named `gh-pr-body-*`, write `body.md`, then remove the dir in `finally`.\n  - `pr_checkout` may create directories under `~/.omp/wt/<encoded-primary-repo-root>/` and add git worktrees there.\n  - `run_watch` may write a session artifact with full failed-job logs.\n- Network\n  - Every op shells out to `gh`, which then talks to GitHub APIs except `pr_push`.\n  - `pr_push` uses git network transport to the configured remote.\n- Subprocesses / native bindings\n  - All `gh` calls use `Bun.spawn([\"gh\", ...args])`.\n  - `pr_checkout` and `pr_push` also invoke git helpers from `packages/coding-agent/src/utils/git.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - `run_watch` consumes `session.allocateOutputArtifact()` when failed-job logs are persisted.\n  - Returned `details` objects carry run/checkouts metadata for the renderer/UI.\n- User-visible prompts / interactive UI\n  - `gh` interactive editor fallback is suppressed for `pr_create` by forcing either `--body-file` or `--body \"\"`.\n  - `gh-renderer` provides compact headers for all ops and a custom live watch view for `run_watch`.\n- Background work / cancellation\n  - `run_watch` loops until success/failure and uses `scheduler.wait()` between polls.\n  - `GithubTool.execute()` is wrapped in `untilAborted()`; `git.github.run()` forwards the abort signal into `Bun.spawn()`.\n\n## Limits & Caps\n- Search result default: `10` (`SEARCH_LIMIT_DEFAULT` in `packages/coding-agent/src/tools/gh.ts`).\n- Search result max: `50` (`SEARCH_LIMIT_MAX`).\n- PR file preview inside the `pr://` view: first `50` files only (`FILE_PREVIEW_LIMIT` in `gh.ts`).\n- Run-watch poll interval: `3s` (`RUN_WATCH_INTERVAL_DEFAULT`).\n- Run-watch failure grace period: `5s` (`RUN_WATCH_GRACE_DEFAULT`).\n- Run-watch failed-log tail default: `15` lines (`RUN_WATCH_TAIL_DEFAULT`).\n- Run-watch failed-log tail max: `200` lines (`RUN_WATCH_TAIL_MAX`).\n- PR review comments page size: `100` (`REVIEW_COMMENTS_PAGE_SIZE`).\n- Actions jobs page size: `100` (`RUN_JOBS_PAGE_SIZE`).\n- Search and tail numeric inputs are floored with `Math.floor()`, clamped to the max, and rejected when non-finite or `<= 0`.\n- `pr_checkout` batch fan-out is unbounded in tool code; all requested PRs are launched with `Promise.all()`.\n\n## Errors\n- Tool creation is skipped entirely when `gh` is not installed.\n- `git.github.run()` throws `ToolError(\"GitHub CLI (gh) is not installed...\")` if `gh` is missing at execution time.\n- `git.github.text/json()` map common failures to model-facing messages:\n  - not authenticated → `GitHub CLI is not authenticated. Run \\`gh auth login\\`.`\n  - missing repo context without explicit `repo` → `GitHub repository context is unavailable. Pass \\`repo\\` explicitly or run the tool inside a GitHub checkout.`\n  - otherwise stderr/stdout text, or fallback `GitHub CLI command failed: gh ...`\n- `json()` also throws on empty stdout or invalid JSON.\n- Local validation errors throw `ToolError`, including:\n  - missing required per-op fields (`query` for `search_code`, `title unless fill=true`)\n  - invalid numeric `limit` / `tail`\n  - invalid `since` / `until` date bound\n  - invalid `run` format\n  - `fill` combined with `title` or `body`\n  - missing git repo / branch / HEAD context for checkout, push, or watch\n  - `pr_push` on a branch without `ompPrHeadRef` metadata\n  - conflicting existing worktree path or branch without `force`\n- `run_watch` treats failed-job log fetches specially: missing log content does not fail the watch; it marks that log `available: false` and prints `Log tail unavailable.` / `Full log unavailable.`.\n- `pr_create` swallows only the post-create best-effort `gh pr view` refresh; the create step itself still fails normally.\n\n## Notes\n- `appendRepoFlag()` intentionally skips `--repo` when the identifier argument is already a full GitHub URL; that lets `gh` derive repo/number from the URL.\n- `normalizePrIdentifierList()` accepts `reviewer`, `assignee`, and `label` arrays too; the helper name is broader than its callers.\n- `pr_push` depends on `pr_checkout` having run first for that local branch; there is no alternate metadata source.\n- `pr_checkout` stores push metadata in branch config, not in the worktree directory. Reusing the same `pr-<number>` branch reuses those config keys.\n- Worktree write serialization is keyed by the primary repo root, not the current worktree path, because git worktrees share `.git/config`, `packed-refs`, commit-graph, and worktree metadata files.\n- `search_repos` is the only search op that never forwards `repo`; repository scoping must be expressed in the query itself.\n- `run_watch` success on commit mode means “all observed runs succeeded and no additional runs appeared one poll later”, not merely “latest poll looked green”.\n- The TUI renderer collapses failed log previews unless the result view is expanded; the underlying text result still contains the same tailed lines plus any artifact reference.\n",
 	"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 `instrumentedCompleteSimple(...)` 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`; telemetry is tagged with oneshot kind `inspect_image`.\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 `instrumentedCompleteSimple(...)` / the configured simple completion implementation.\n- Session state\n  - Reads session settings, active model preferences, cwd, and model registry.\n- Background work / cancellation\n  - Passes the caller `AbortSignal` into `instrumentedCompleteSimple(...)` and the configured simple completion implementation.\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 tool schema is not marked strict in `InspectImageTool`; callers should still treat only `path` and `question` as supported inputs because the implementation reads no other fields.\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 `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 `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. Dispatch waits are bounded by `irc.timeoutMs` (default `120_000` ms). A value of `0` disables the local timeout; parent aborts still abort the dispatch.\n13. `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. `irc.timeoutMs` creates a per-recipient `AbortController` and reports timeout failures per target.\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  - `irc.timeoutMs` defaults to `120_000`; `0` disables the timeout, non-finite values fall back to the default, and positive values are truncated and clamped to at least `1` ms.\n  - No retry, backoff, rate limit, or reply length cap is defined in `irc.ts`; behavior otherwise 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`, `runEphemeralTurn`, abort handling, or timeout handling 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/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. Cannot be combined with `list`. 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| `list` | `boolean` | No | Return an immediate snapshot of every job spawned by the calling agent (running + completed within retention) without waiting. Read-only — cannot be combined with `poll` or `cancel`. |\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\nRead-only snapshot path:\n- Calling `job` with `list: true` returns a markdown summary of every job spawned by the calling agent (running + completed within retention) without waiting.\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: call with `list: true` for the same snapshot data without waiting on completion.\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- Calling `list: true` against an empty manager returns a normal empty-list result rather than throwing; missing ids passed to `poll` are silently filtered.\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` calls with `poll` or `list: true`) 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- Retention eviction removes the job record, suppression flags, and watch flag together. After eviction, both `job` calls and `list: true` snapshots 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- Startup LSP warmup (`discoverStartupLspServers(cwd)` in `sdk.ts`) is gated on `enableLsp && options.hasUI && settings.get(\"lsp.diagnosticsOnWrite\")` — print/RPC/ACP/script sessions skip it and let `getOrCreateClient()` cold-start servers on demand. See `docs/sdk.md` § Startup performance.\n- `configCache` is per-process and never auto-invalidated; config changes require a fresh process to be observed by `getConfig()` callers.",
-	"tools/read.md": "# read\n\n> Read files, directories, archives, SQLite databases, internal resources, images, documents, and URLs through one `path` string.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/read.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/read.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/path-utils.ts` — split `path` from trailing selectors; normalize local paths.\n  - `packages/coding-agent/src/tools/archive-reader.ts` — detect `archive.ext:inner/path`, index archives, list/read entries.\n  - `packages/coding-agent/src/tools/sqlite-reader.ts` — detect SQLite targets, parse selectors, render tables.\n  - `packages/coding-agent/src/tools/fetch.ts` — URL parsing, fetch/render pipeline, URL cache/artifacts.\n  - `packages/coding-agent/src/internal-urls/router.ts` — resolve `agent://`, `artifact://`, `local://`, `mcp://`, `memory://`, `omp://`, `rule://`, `skill://`.\n  - `packages/coding-agent/src/edit/notebook.ts` — convert `.ipynb` to editable `# %% [...] cell:N` text.\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — decide hashline vs line-number vs raw display.\n  - `packages/coding-agent/src/workspace-tree.ts` — render directory trees.\n  - `packages/coding-agent/src/edit/file-snapshot-store.ts` — stores read lines for later hashline edit verification/recovery.\n  - `packages/coding-agent/src/tools/index.ts` — registers `read: s => new ReadTool(s)`.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `path` | `string` | Yes | Filesystem path, internal URL, or web URL. May end with a trailing selector such as `:50-100` or `:raw`. |\n\n### Selector grammar\n\nFor normal file-like reads, `splitPathAndSel()` in `packages/coding-agent/src/tools/path-utils.ts` recognizes the final suffix only when it matches one of these forms:\n\n| Suffix | Meaning |\n| --- | --- |\n| `:raw` | Raw/verbatim mode. Disables structural summaries and line prefixes. |\n| `:conflicts` | Render unresolved Git merge-conflict regions for a local file. |\n| `:N` / `:LN` / `:N-` | 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| `:R1,R2,...` | Multiple ranges, sorted and merged before reading (for example `:5-16,960-973`). |\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`, but use the same line-range parser for `:raw`, `:N`, `:A-B`, `:A+C`, `:5-10,20-30`, and `:range:raw` / `:raw:range`. Because URL ports also use `:`, add a trailing slash before a selector on a host/port URL, e.g. `https://example.com/:80`.\n\n## Outputs\n- Single-shot `AgentToolResult` built through `toolResult()` in `packages/coding-agent/src/tools/tool-result.ts`.\n- `content` is usually one text block. Image reads may return `[text, image]`.\n- `details` is path-dependent. `ReadToolDetails` may include:\n  - `kind: \"file\" | \"url\"` (URL path uses `kind: \"url\"`; file reads usually omit `kind`)\n  - `isDirectory`\n  - `resolvedPath`\n  - `suffixResolution`\n  - URL fields: `url`, `finalUrl`, `contentType`, `method`, `notes`\n  - `truncation`\n  - `displayContent` (unprefixed text + starting line for TUI rendering)\n  - `summary` (`lines`, `elidedSpans`, `elidedLines`) for structural summaries\n  - `meta` from `packages/coding-agent/src/tools/output-meta.ts`\n- `details.meta.source` is set to the backing path, URL, or internal URL.\n- `details.meta.truncation` carries shown range, total lines/bytes, next offset, and optional `artifactId` for cached URL output.\n- Directory/archive listings and SQLite table lists also set `details.meta.limits` when list limits trigger.\n\n## Flow\n1. `ReadTool.execute()` accepts `{ path }`. `file://...` inputs are expanded first with `expandPath()`.\n2. It tries URL handling first via `parseReadUrlTarget()` from `packages/coding-agent/src/tools/fetch.ts`.\n   - Plain URL reads call `executeReadUrl()`.\n   - URL reads with line selectors load or refresh the URL cache with `loadReadUrlCacheEntry()` and paginate the cached text locally with `#buildInMemoryTextResult()`.\n3. If not a web URL, it checks `session.internalRouter.canHandle(...)`.\n   - Internal URLs are resolved with `internalRouter.resolve()`.\n   - `agent://` query extraction (`/path` or `?q=`) bypasses pagination and returns the extracted content directly.\n   - Other internal resources are paginated in-memory by `#buildInMemoryTextResult()`.\n4. It tries archive resolution next with `#resolveArchiveReadPath()`.\n   - `parseArchivePathCandidates()` scans for `.tar`, `.tar.gz`, `.tgz`, or `.zip` anywhere before `:sub/path`.\n   - On success, `#readArchive()` either lists a directory or decodes an entry as UTF-8 text.\n5. It tries SQLite resolution with `#resolveSqliteReadPath()`.\n   - `parseSqlitePathCandidates()` scans for `.sqlite`, `.sqlite3`, `.db`, `.db3` before any `:table`, `:key`, or `?query` suffix.\n   - `#readSqlite()` dispatches on `parseSqliteSelector()`.\n6. Otherwise it treats the input as a local filesystem path.\n   - `resolveReadPath()` expands `~`, resolves relative to session cwd, treats bare `/` as session cwd, and retries macOS screenshot/NFD/curly-quote variants.\n   - If the path does not exist, `findUniqueSuffixMatch()` does a workspace glob-based unique suffix lookup (skipped for remote mounts).\n7. Directories go through `#readDirectory()`.\n8. Non-directories branch by content type:\n   - image metadata / inline image\n   - editable notebook text\n   - markit-converted document\n   - structural summary for parseable code/prose\n   - streamed text/line-range read\n9. Local text reads are streamed by `streamLinesFromFile()` rather than loading the whole file. The tool adds up to 3 lines of context before/after explicit bounded ranges.\n10. Non-empty contiguous local reads are recorded into `getFileReadCache(session)` for later hashline edit recovery.\n11. If suffix resolution happened, the first text block is prefixed with `[Path '...' not found; resolved to '...' via suffix match]`.\n\n## Modes / Variants\n\n### Local text files\n- No selector: if summarization is enabled and the file is small enough, `#trySummarize()` calls `summarizeCode()`.\n  - Guards: file size `<= 2 MiB` (`MAX_SUMMARY_BYTES`), line count `<= 20_000` (`MAX_SUMMARY_LINES`).\n  - Summary output keeps selected declarations and replaces elided spans with `...` or merged brace-pair lines containing `..`. When at least one span is elided, the text content ends with a footer like `[NN lines elided; re-read needed ranges, e.g. <path>:5-16,40-80]` using concrete ranges from the actual elisions.\n  - When an elided block sits between matching brace lines, `#renderSummary()` may merge them into one anchored line rather than emitting separate opener/closer lines.\n- Explicit selector or summarization miss: streamed text read.\n  - Default open-ended limit is `min(session setting read.defaultLimit, DEFAULT_MAX_LINES)`.\n  - Explicit ranges expand by `RANGE_LEADING_CONTEXT_LINES = 1` / `RANGE_TRAILING_CONTEXT_LINES = 3` on the constrained sides only.\n  - Non-raw output uses `resolveFileDisplayMode()`:\n    - hashline numbered output when edit mode is hashline, read is not raw, source is mutable, edit tool exists, and `readHashLines !== false`\n    - otherwise optional line numbers when `readLineNumbers === true`\n    - raw mode suppresses both\n- Prefix format in hashline mode is a `¶PATH#TAG` header followed by `LINE:TEXT`, e.g. `¶src/foo.ts#0A1B` and `41:def alpha():`, from the session snapshot store plus `formatNumberedLine()` / `formatHashlineHeader()`.\n- The `edit`/hashline path consumes that header plus bare line numbers later; the four-hex tag is opaque and only meaningful in the session snapshot store that minted it. Immutable sources and `:raw` intentionally suppress hashline headers.\n\n### Directory listings\n- `#readDirectory()` calls `buildDirectoryTree()` with:\n  - `maxDepth = 2`\n  - `perDirLimit = 12`\n  - `rootLimit = null`\n  - `lineCap = limit` when a line selector was present, else unlimited at this layer\n- `buildDirectoryTree()` sorts siblings by recency, shows file sizes and relative ages, and may mark `limits.resultLimit` when the tree truncates.\n- Empty directories render as `(empty directory)`.\n\n### Archives\n- Supported archive containers: `.tar`, `.tar.gz`, `.tgz`, `.zip`.\n- Syntax: `archive.ext`, `archive.ext:path/inside`, `archive.ext:path/inside:50-60`.\n- `openArchive()` reads the whole archive into memory, then:\n  - tar/tgz uses `new Bun.Archive(bytes)`\n  - zip uses `fflate.unzipSync()`\n- Archive paths normalize `/`, drop `.` segments, and reject `..`.\n- Directory reads list immediate children; files show `name` plus ` (size)` when size > 0.\n- Directory listing default limit is `500` entries in `#readArchiveDirectory()`.\n- File entries are UTF-8 decoded. Non-UTF-8 entries return `[Cannot read binary archive entry '...' (...)]` instead of bytes.\n- Text archive entries reuse the normal in-memory pagination/anchoring path.\n\n### SQLite databases\n- Database detection requires both a matching extension and a valid SQLite file header (`isSqliteFile()`).\n- Selector forms from `parseSqliteSelector()`:\n\n#### `db.sqlite`\n- `kind: \"list\"`\n- Lists non-`sqlite_%` tables with row counts.\n- `#readSqlite()` caps the rendered list to `500` tables via `applyListLimit()`.\n\n#### `db.sqlite:table`\n- `kind: \"schema\"`\n- Returns `sqlite_master.sql` plus sample rows.\n- Sample size is `DEFAULT_SCHEMA_SAMPLE_LIMIT = 5`.\n\n#### `db.sqlite:table:key`\n- `kind: \"row\"`\n- Resolves by primary key when the table has exactly one PK column; otherwise falls back to `rowid` lookup.\n- No query parameters allowed on row lookups.\n\n#### `db.sqlite:table?limit=...&offset=...&order=...&where=...`\n- `kind: \"query\"`\n- Defaults: `limit = 20`, `offset = 0`.\n- `limit` is capped at `500`.\n- `order` accepts `column` or `column:asc|desc` and must name an existing column.\n- `where` is accepted only after `validateWhereClause()` rejects comments, semicolons, and control keywords like `LIMIT`, `OFFSET`, `UNION`, `ATTACH`, `PRAGMA`.\n- Unknown query parameters throw.\n\n#### `db.sqlite?q=SELECT ...`\n- `kind: \"raw\"`\n- Cannot be combined with table selectors or any other query param.\n- Empty `q` throws.\n- `executeReadQuery()` runs `db.prepare(sql).all()` and rejects bound parameters; it does not verify that the SQL starts with `SELECT`.\n\n- Rendering caps in `packages/coding-agent/src/tools/sqlite-reader.ts`:\n  - ASCII table width `120` (`MAX_RENDER_WIDTH`)\n  - per-column width `40` (`MAX_COLUMN_WIDTH`)\n- `#readSqlite()` opens Bun SQLite in `{ readonly: true, strict: true }` and sets `PRAGMA busy_timeout = 3000`.\n\n### Documents\n- `CONVERTIBLE_EXTENSIONS` in `packages/coding-agent/src/tools/read.ts` covers `.pdf`, `.doc`, `.docx`, `.ppt`, `.pptx`, `.xls`, `.xlsx`, `.rtf`, `.epub`.\n- `convertFileWithMarkit()` converts the file to text/markdown.\n- Converted output is then head-truncated with normal shared limits; there is no line selector support inside the source document before conversion.\n- Conversion failures return a text block like `[Cannot read .pdf file: ...]`.\n\n### Jupyter notebooks\n- `.ipynb` goes through `readEditableNotebookText()` unless `:raw` was requested.\n- Output is editable plain text with markers like:\n\n```text\n# %% [code] cell:0\n...\n```\n\n- Raw mode bypasses that conversion and falls back to file-text reading.\n\n### Images\n- Image detection is metadata-based (`readImageMetadata()`).\n- Max accepted image size is `20 MiB` (`MAX_IMAGE_INPUT_BYTES`, re-exported as `MAX_IMAGE_SIZE`). Larger files throw.\n- If `inspect_image.enabled` is true, `read` returns metadata only (MIME, bytes, dimensions, channels, alpha) plus a suggestion to call `inspect_image`.\n- Otherwise it calls `loadImageInput()` and returns:\n  - a text note from the image loader\n  - an inline image block\n- Unsupported/undecodable image formats throw a `ToolError`.\n\n### Internal URLs\n- `read` does not resolve these itself; it delegates to `session.internalRouter.resolve()`.\n- Registered protocols are outside this file, but the router in `packages/coding-agent/src/internal-urls/router.ts` is built for `agent://`, `artifact://`, `issue://`, `local://`, `mcp://`, `memory://`, `omp://`, `pr://`, `rule://`, and `skill://`.\n- `#handleInternalUrl()` behavior:\n  - parses the URL with `parseInternalUrl()` so colons inside the host segment are legal\n  - for `agent://`, treats non-root path extraction or `?q=` extraction as a special no-pagination mode\n  - otherwise paginates the resolved text in memory\n  - passes `immutable` through to `resolveFileDisplayMode()` so anchors are suppressed for immutable resources such as artifacts, skills, memory, and agent outputs\n  - sets `ignoreResultLimits: true` for `skill://` so the full skill text is paginated only by explicit selectors, not by the normal default line limit\n- `issue://<N>` / `pr://<N>` (and the long form `issue://<owner>/<repo>/<N>` / `pr://<owner>/<repo>/<N>`) route through the same SQLite cache the `github` tool writes to; `?comments=0` selects the no-comments rendering. Bare `issue://` / `pr://` (and `issue://<owner>/<repo>` / `pr://<owner>/<repo>`) issue a live `gh issue list` / `gh pr list` for browsing, accepting `?state=`, `?limit=`, `?author=`, `?label=`. PR diffs share the same cache through `pr://<N>/diff` (numbered file listing with per-file hints), `pr://<N>/diff/<i>` (single file slice; 1-indexed), and `pr://<N>/diff/all` (verbatim unified diff); the listing and per-file slices are reconstructed from the cached unified-diff payload, so all three variants share one `gh pr diff` invocation per PR. Diff content is served as `text/plain`. Soft TTL `github.cache.softTtlSec` (default 5 minutes), hard TTL `github.cache.hardTtlSec` (default 7 days). Stale-hit returns the cached row and schedules a background refresh.\n\n### Web URLs\n- `parseReadUrlTarget()` accepts `http://`, `https://`, or `www.` targets.\n- Plain URL reads call `executeReadUrl()` in `packages/coding-agent/src/tools/fetch.ts`.\n- `:raw` means raw HTML/body fallback path; plain URL reads prefer rendered/reader-friendly output.\n- `:N`, `:A-B`, `:A+C`, and comma-separated multi-ranges do not refetch when cached output is usable. They page over cached output from the prior or current URL render.\n- URL render pipeline in `renderUrl()`:\n  1. normalize scheme (`https://` added for bare `www.`)\n  2. try special handlers for known sites unless raw\n  3. fetch with `loadPage()`\n  4. if content is image/PDF/DOCX/etc., try binary fetch + markit/image handling\n  5. handle JSON directly, feeds via feed parser, plain text directly\n  6. for HTML and non-raw mode, try markdown alternates, `URL.md`, content negotiation, feed alternates, HTML-to-text renderers, extracted linked documents, then `llms.txt`\n  7. fall back to raw body text/html\n- URL output is wrapped with a small header:\n\n```text\nURL: ...\nContent-Type: ...\nMethod: ...\nNotes: ...\n\n---\n```\n\n- `method` records the winning path (`json`, `feed`, `text`, `alternate-markdown`, `md-suffix`, `content-negotiation`, `image`, `markit`, `llms.txt`, `raw`, `raw-html`, etc.).\n- URL reads may return an inline image block when the fetched resource is a supported image and survives resizing.\n\n## Side Effects\n- Filesystem\n  - Opens and streams local files.\n  - Reads entire archives into memory before indexing.\n  - May read URL-cache artifact files from the session artifacts directory.\n  - Writes URL output artifacts when URL output is truncated or when line-range pagination needs a persisted cache body.\n- Network\n  - URL mode performs HTTP fetches, binary refetches, and alternate-endpoint probes.\n- Subprocesses / native bindings\n  - Uses Bun SQLite for `.db`/`.sqlite*`.\n  - Uses `Bun.Archive` for tar/tgz and `fflate` for zip.\n  - URL HTML rendering can delegate into site handlers and HTML-to-text backends from `packages/coding-agent/src/tools/fetch.ts`.\n- Session state\n  - Records local text lines into `session.fileReadCache` for later stale-anchor recovery.\n  - Uses `session.internalRouter` for internal URLs.\n  - Uses `session.allocateOutputArtifact()` for cached/truncated URL output.\n- Background work / cancellation\n  - Most branches honor `AbortSignal`; the tool itself is marked `nonAbortable = true`, but helper paths still call `throwIfAborted(signal)`.\n\n## Limits & Caps\n- Shared text truncation defaults from `packages/coding-agent/src/session/streaming-output.ts`:\n  - `DEFAULT_MAX_LINES = 3000`\n  - `DEFAULT_MAX_BYTES = 50 * 1024`\n- Local text open-ended default line limit: `read.defaultLimit`, clamped to `[1, DEFAULT_MAX_LINES]`.\n- Explicit line ranges add `1` leading and `3` trailing context lines on the constrained sides (`RANGE_LEADING_CONTEXT_LINES` / `RANGE_TRAILING_CONTEXT_LINES`).\n- File streaming chunk size: `8 * 1024` bytes (`READ_CHUNK_SIZE`).\n- Local streamed byte budget for line reads: `max(DEFAULT_MAX_BYTES, maxLinesToCollect * 512)`.\n- Structural summaries only run when file size `<= 2 MiB` and line count `<= 20_000`.\n- Image input max: `20 MiB`.\n- Directory tree caps for local directories: depth `2`, per-directory children `12`.\n- Archive directory default list cap: `500` entries.\n- SQLite:\n  - default row query limit `20`\n  - schema sample limit `5`\n  - max query limit `500`\n  - table list cap `500`\n  - render width `120`, column width `40`\n  - busy timeout `3000` ms\n- URL read result shown to the model is truncated to `300` lines and `50 KiB` in `executeReadUrl()`; full cached output can be attached as an artifact.\n- Inline fetched URL images:\n  - source bytes cap `20 MiB`\n  - post-resize inline output cap `300 KiB`\n- Unique suffix auto-resolution glob timeout: `5000` ms.\n- File-read cache holds `30` paths per session.\n\n## Errors\n- Validation and operational failures surface as `ToolError`.\n- Selector errors include:\n  - `Line selector 0 is invalid; lines are 1-indexed. Use :1.`\n  - invalid `A+B` / `A-B` shapes\n  - `Cannot combine query extraction with offset/limit` for `agent://.../path:50`\n- Missing local/archive/sqlite paths first attempt unique suffix resolution; if no unique match exists they error.\n- Out-of-bounds line reads do not throw. They return explanatory text with a suggestion such as `Use :1 ...` or `Use :<last line> ...`.\n- Binary archive entries do not throw; they return a text notice.\n- Document conversion failure returns a text notice.\n- Image oversize/unsupported/invalid cases throw.\n- SQLite parser rejects unsupported parameter combinations early; DB/runtime errors are caught and rethrown as `ToolError(message)`.\n- URL fetch failure does not throw when HTTP fetch succeeds but `response.ok === false`; it returns a failed URL read with `method: \"failed\"` and explanatory notes.\n\n## Notes\n- 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/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` (settles on the latest publish; exact-version match accepted immediately).\n- Results are deduplicated by range+message and severity-sorted.\n\n**Output text**\n- Single target with no issues: `OK`.\n- Single target with issues: `<summary>:\\n<grouped diagnostics>`.\n- Batch/glob target: one section per file, plus an initial truncation warning when the glob exceeds the file cap.\n- Workspace mode: `Workspace diagnostics (<detected description>):\\n<command output>`.\n\n### `definition`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/definition` with `{ textDocument, position }`.\n- Accepts `Location`, `Location[]`, `LocationLink`, or `LocationLink[]`; `normalizeLocationResult()` converts `LocationLink` to `targetSelectionRange ?? targetRange`.\n- Waits for project load before the request.\n\n**Output text**\n- `No definition found` or `Found N definition(s):` followed by `file:line:col` and one context line above/below each location.\n\n### `type_definition`\nSame as `definition`, but sends `textDocument/typeDefinition` and reports `type definition(s)`.\n\n### `implementation`\nSame as `definition`, but sends `textDocument/implementation` and reports `implementation(s)`.\n\n### `references`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/references` with `includeDeclaration: true`.\n- For project-aware servers, retries up to `REFERENCES_RETRY_COUNT` times when the only hit is the queried declaration; between retries it waits for project load and sleeps `REFERENCES_RETRY_DELAY_MS`.\n- First `REFERENCE_CONTEXT_LIMIT` references include surrounding context; the rest are location-only.\n\n**Output text**\n- `No references found` or `Found N reference(s):` with contextual entries first, then `... M additional reference(s) shown without context` when truncated.\n\n### `hover`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/hover`.\n- `extractHoverText()` flattens strings, markup content, marked-string objects, or arrays into plain text.\n\n**Output text**\n- `No hover information` or the extracted hover text.\n\n### `symbols`\n**Inputs**\n- Workspace mode: `file: \"*\"` or omitted file on the early workspace branch, plus required `query`.\n- Document mode: required `file`.\n- Optional: `timeout`.\n\n**Execution**\n- Workspace mode sends `workspace/symbol` to every non-custom LSP server, post-filters matches with `filterWorkspaceSymbols()`, deduplicates with `dedupeWorkspaceSymbols()`, then truncates to `WORKSPACE_SYMBOL_LIMIT`.\n- Document mode sends `textDocument/documentSymbol` to the primary server. If the first item has `selectionRange`, it formats hierarchical `DocumentSymbol`s; otherwise it formats flat `SymbolInformation`s.\n\n**Output text**\n- Workspace mode: `Found N symbol(s) matching \"query\":` plus formatted `name @ file:line:col`, with an omission line when over the limit.\n- Document mode: `Symbols in <file>:` plus hierarchical or flat symbol lines.\n\n### `rename`\n**Inputs**\n- Required: `file`, `new_name`.\n- Optional: `line`, `symbol`, `apply`, `timeout`.\n\n**Execution**\n- Waits for project load, sends `textDocument/rename`, receives a `WorkspaceEdit`.\n- `apply !== false` applies edits immediately with `applyWorkspaceEdit()`.\n- `apply === false` renders a preview with `formatWorkspaceEdit()`.\n\n**Output text**\n- `Rename returned no edits`, `Applied rename:` plus applied change lines, or `Rename preview:` plus summarized edits.\n\n### `rename_file`\n**Inputs**\n- Required: `file` source path, `new_name` destination path.\n- Optional: `apply`, `timeout`.\n\n**Execution**\n- Resolves absolute source and destination, rejects identical paths, missing source, existing destination, empty rename set, or directories with more than `MAX_RENAME_PAIRS` files.\n- `enumerateRenamePairs()` returns one `{oldUri,newUri}` pair for a file or walks every regular file in a directory tree.\n- Sends `workspace/willRenameFiles` with `{ files: pairs }` to every non-custom LSP server; collects returned `WorkspaceEdit`s and server notes.\n- Preview mode (`apply === false`) only formats those edits.\n- Apply mode runs each returned `WorkspaceEdit`, renames the source path on disk, sends `textDocument/didClose` for every renamed open file, deletes those `openFiles` entries, then sends `workspace/didRenameFiles`.\n\n**Output text**\n- Preview: `Rename preview: <file-count label> → <dest>` plus per-server edit summaries and optional server notes.\n- Apply: `Renamed <file-count label> → <dest>` plus applied edit summaries, filesystem rename line, and optional server notes.\n\n### `code_actions`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `query`, `apply`, `timeout`.\n\n**Execution**\n- Reads cached diagnostics for the open URI from `client.diagnostics` and sends `textDocument/codeAction` for a zero-width range at the resolved position.\n- When `apply !== true`, `query` is passed as `context.only: [query]`; this is a server-side kind filter.\n- When `apply === true`, `query` becomes a required client-side selector: either a zero-based numeric index or a case-insensitive substring of the action title.\n- Applying a `CodeAction` uses `applyCodeAction()`: optionally `codeAction/resolve`, then `applyWorkspaceEdit(edit)`, then optional `workspace/executeCommand`.\n- Applying a bare `Command` only runs `workspace/executeCommand`.\n\n**Output text**\n- List mode: `N code action(s):` plus `index: [kind] title` lines.\n- Apply mode success: `Applied \"title\":` plus `Workspace edit:` and/or `Executed command(s):` sections.\n- Apply mode miss: `No code action matches \"query\". Available actions:`.\n- Apply mode with no edit/command: `Action \"title\" has no workspace edit or command to apply`.\n\n### `status`\n**Inputs**\n- None.\n\n**Execution**\n- Reads configured servers from cached `LspConfig`, not `getActiveClients()`.\n- Calls `detectLspmux()` and appends status text when `lspmux` is installed.\n\n**Output text**\n- `Active language servers: ...` or `No language servers configured for this project`, optionally followed by `lspmux: active (multiplexing enabled)` or `lspmux: installed but server not running`.\n\n### `reload`\n**Inputs**\n- Workspace mode: `file: \"*\"` or omitted `file`.\n- Single-file mode: required `file`.\n- Optional: `timeout`.\n\n**Execution**\n- Workspace mode reloads every non-custom LSP server.\n- Single-file mode reloads the primary server for that file.\n- `reloadServer()` tries `rust-analyzer/reloadWorkspace`, then `workspace/didChangeConfiguration` with `{ settings: {} }`; if neither works it kills the process so the next request cold-starts a new client.\n\n**Output text**\n- One line per server: `Reloaded <server>`, `Restarted <server>`, or `Failed to reload <server>: ...`.\n\n### `capabilities`\n**Inputs**\n- Optional: `file`, `timeout`.\n\n**Execution**\n- With a concrete `file`, inspects matching non-custom servers for that file.\n- With omitted `file` or `\"*\"`, inspects every non-custom configured server.\n- Starts servers as needed and dumps `client.serverCapabilities ?? {}` as pretty JSON.\n\n**Output text**\n- Per server: `<server>:` followed by indented `capabilities: { ... }`, or `<server>: failed to start (...)`.\n\n### `request`\n**Inputs**\n- Required: `query` method name.\n- Optional: `file`, `line`, `symbol`, `payload`, `timeout`.\n\n**Execution**\n- Chooses one non-custom server: file-scoped primary server, otherwise the first configured non-custom server.\n- Param building precedence:\n  1. If `payload` is present, parse JSON and use it verbatim.\n  2. Else if `file` is concrete and `line` is present, build `{ textDocument: { uri }, position: { line: line - 1, character } }` using `resolveSymbolColumn()`.\n  3. Else if `file` is concrete, build `{ textDocument: { uri } }`.\n  4. Else use `{}`.\n- Opens the file first when `file` is concrete.\n\n**Output text**\n- Success: `<server> ← <method>:\\n<formatted result>`, where non-string results are `JSON.stringify(..., null, 2)` and nullish values become `null`.\n- Failure: `LSP error from <server> on <method>: ...`.\n\n## Side Effects\n- Filesystem\n  - Reads config files, target files, and root markers.\n  - `rename` and `code_actions` may edit/create/delete/rename files via `applyWorkspaceEdit()`.\n  - `rename_file` always renames the source path on disk in apply mode.\n  - Server-initiated `workspace/applyEdit` requests also mutate files through `applyWorkspaceEdit()`.\n- Network\n  - None directly; communication is local stdio JSON-RPC to subprocesses.\n- Subprocesses / native bindings\n  - Spawns language servers with `ptree.spawn()`.\n  - Workspace diagnostics spawns `cargo`, `npx`, `go`, or `pyright`.\n  - `BiomeClient` and `SwiftLintClient` spawn CLI tools.\n  - Optional `lspmux` detection spawns `lspmux status`; supported servers may be wrapped through `lspmux client`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Caches config per cwd in `configCache`.\n  - Caches LSP clients per `command:cwd`, with `pendingRequests`, `diagnostics`, `openFiles`, `serverCapabilities`, and project-load state.\n  - Caches custom linter clients by `serverName:cwd`.\n  - Updates client `lastActivity`; optional idle-timeout cleanup is driven by `setIdleTimeout()`.\n- Background work / cancellation\n  - Every request has an abortable timeout signal.\n  - Aborting an in-flight LSP request sends `$/cancelRequest`.\n  - Background message readers persist for each live client until process exit/shutdown.\n\n## Limits & Caps\n- Tool timeout clamp: default `20`, min `5`, max `60` seconds — `TOOL_TIMEOUTS.lsp` in `packages/coding-agent/src/tools/tool-timeouts.ts`.\n- LSP request default timeout inside `sendRequest()`: `30_000ms` — `DEFAULT_REQUEST_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Warmup initialize timeout default: `5_000ms` — `WARMUP_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Project-load wait fallback: `15_000ms` — `PROJECT_LOAD_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Idle-client sweep interval when enabled: `60_000ms` — `IDLE_CHECK_INTERVAL_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Diagnostic message output cap: first `50` messages — `DIAGNOSTIC_MESSAGE_LIMIT` in `packages/coding-agent/src/lsp/index.ts`.\n- Single-file diagnostics wait: `3_000ms` — `SINGLE_DIAGNOSTICS_WAIT_TIMEOUT_MS`.\n- Batch/glob diagnostics wait per file: `400ms` — `BATCH_DIAGNOSTICS_WAIT_TIMEOUT_MS`.\n- Glob diagnostic target cap: first `20` matches — `MAX_GLOB_DIAGNOSTIC_TARGETS`.\n- Workspace symbol cap: first `200` entries — `WORKSPACE_SYMBOL_LIMIT`.\n- Reference context cap: first `50` references include source context — `REFERENCE_CONTEXT_LIMIT`.\n- References retry count: `2` retries, `250ms` backoff — `REFERENCES_RETRY_COUNT`, `REFERENCES_RETRY_DELAY_MS`.\n- Directory rename cap: `1_000` file pairs — `MAX_RENAME_PAIRS`.\n- `detectLspmux()` state cache TTL: `5 * 60 * 1000ms`; liveness check timeout: `1_000ms` — `STATE_CACHE_TTL_MS`, `LIVENESS_TIMEOUT_MS` in `packages/coding-agent/src/lsp/lspmux.ts`.\n- Workspace diagnostics output cap: first `50` lines from the subprocess.\n\n## Errors\n- Missing or invalid inputs are usually returned as text with `details.success: false`, not thrown:\n  - missing `file`/`query`/`new_name`\n  - invalid JSON in `payload`\n  - no matching server\n  - invalid `rename_file` source/destination conditions\n- `resolveSymbolColumn()` throws explicit errors for missing files, missing symbols, and out-of-bounds `#N` selectors; these surface as `LSP error: ...` or request-specific error text.\n- `sendRequest()` rejects on timeout with `LSP request <method> timed out after <ms>ms`.\n- Client process exit rejects all pending requests with an exit-code/stderr error assembled in `getOrCreateClient()`.\n- Single-file action failures inside the main `try` become `LSP error: <message>`.\n- `request` has its own error envelope: `LSP error from <server> on <method>: <message>`.\n- Some server failures are intentionally softened:\n  - diagnostics continue when one server fails\n  - `rename_file` suppresses `workspace/willRenameFiles` “method not found” errors and records other server errors as notes\n  - `code_actions` ignores `codeAction/resolve` failures and applies unresolved actions when possible\n- Aborts are not converted to text: `ToolAbortError` is rethrown.\n\n## Notes\n- `status` reports configured/available servers from `LspConfig`, not currently active client processes from `getActiveClients()`.\n- `getLspServerForFile()` excludes `createClient` adapters and linter-only servers; navigation/refactor actions never target Biome/SwiftLint custom clients.\n- `getServersForFile()` matches both file extensions and exact basenames from `fileTypes`; config can target names like `Dockerfile` if present.\n- `symbol` matching is exact first, then case-insensitive, and falls back to the Nth occurrence on the specified line only; it never scans other lines.\n- `code_actions` uses `query` in two different ways: server-side `context.only` filter in list mode, client-side title/index selector in apply mode.\n- `rename` and `rename_file` default to apply. Preview requires `apply: false`.\n- `request` with `file: \"*\"` is treated the same as omitted `file`: it does not build workspace-specific params.\n- `reload` does not recreate a client immediately after killing it; the next request triggers reinitialization.\n- `workspace/applyEdit` can apply edits initiated by the server outside the direct tool action result path.\n- `detectLspmux()` can be disabled with `PI_DISABLE_LSPMUX=1`; only `rust-analyzer` is in `DEFAULT_SUPPORTED_SERVERS`.\n- Startup LSP warmup (`discoverStartupLspServers(cwd)` in `sdk.ts`) is gated on `enableLsp && options.hasUI && settings.get(\"lsp.diagnosticsOnWrite\")` — print/RPC/ACP/script sessions skip it and let `getOrCreateClient()` cold-start servers on demand. See `docs/sdk.md` § Startup performance.\n- `configCache` is per-process and never auto-invalidated; config changes require a fresh process to be observed by `getConfig()` callers.",
+	"tools/read.md": "# read\n\n> Read files, directories, archives, SQLite databases, internal resources, images, documents, and URLs through one `path` string.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/read.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/read.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/path-utils.ts` — split `path` from trailing selectors; normalize local paths.\n  - `packages/coding-agent/src/tools/archive-reader.ts` — detect `archive.ext:inner/path`, index archives, list/read entries.\n  - `packages/coding-agent/src/tools/sqlite-reader.ts` — detect SQLite targets, parse selectors, render tables.\n  - `packages/coding-agent/src/tools/fetch.ts` — URL parsing, fetch/render pipeline, URL cache/artifacts.\n  - `packages/coding-agent/src/internal-urls/router.ts` — resolve `agent://`, `artifact://`, `local://`, `mcp://`, `memory://`, `omp://`, `rule://`, `skill://`.\n  - `packages/coding-agent/src/edit/notebook.ts` — convert `.ipynb` to editable `# %% [...] cell:N` text.\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — decide hashline vs line-number vs raw display.\n  - `packages/coding-agent/src/workspace-tree.ts` — render directory trees.\n  - `packages/coding-agent/src/edit/file-snapshot-store.ts` — stores read lines for later hashline edit verification/recovery.\n  - `packages/coding-agent/src/tools/index.ts` — registers `read: s => new ReadTool(s)`.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `path` | `string` | Yes | Filesystem path, internal URL, or web URL. May end with a trailing selector such as `:50-100` or `:raw`. |\n\n### Selector grammar\n\nFor normal file-like reads, `splitPathAndSel()` in `packages/coding-agent/src/tools/path-utils.ts` recognizes the final suffix only when it matches one of these forms:\n\n| Suffix | Meaning |\n| --- | --- |\n| `:raw` | Raw/verbatim mode. Disables structural summaries and line prefixes. |\n| `:conflicts` | Render unresolved Git merge-conflict regions for a local file. |\n| `:N` / `:LN` / `:N-` | 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| `:R1,R2,...` | Multiple ranges, sorted and merged before reading (for example `:5-16,960-973`). |\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`, but use the same line-range parser for `:raw`, `:N`, `:A-B`, `:A+C`, `:5-10,20-30`, and `:range:raw` / `:raw:range`. Because URL ports also use `:`, add a trailing slash before a selector on a host/port URL, e.g. `https://example.com/:80`.\n\n## Outputs\n- Single-shot `AgentToolResult` built through `toolResult()` in `packages/coding-agent/src/tools/tool-result.ts`.\n- `content` is usually one text block. Image reads may return `[text, image]`.\n- `details` is path-dependent. `ReadToolDetails` may include:\n  - `kind: \"file\" | \"url\"` (URL path uses `kind: \"url\"`; file reads usually omit `kind`)\n  - `isDirectory`\n  - `resolvedPath`\n  - `suffixResolution`\n  - URL fields: `url`, `finalUrl`, `contentType`, `method`, `notes`\n  - `truncation`\n  - `displayContent` (unprefixed text + starting line for TUI rendering)\n  - `summary` (`lines`, `elidedSpans`, `elidedLines`) for structural summaries\n  - `meta` from `packages/coding-agent/src/tools/output-meta.ts`\n- `details.meta.source` is set to the backing path, URL, or internal URL.\n- `details.meta.truncation` carries shown range, total lines/bytes, next offset, and optional `artifactId` for cached URL output.\n- Directory/archive listings and SQLite table lists also set `details.meta.limits` when list limits trigger.\n\n## Flow\n1. `ReadTool.execute()` accepts `{ path }`. `file://...` inputs are expanded first with `expandPath()`.\n2. It tries URL handling first via `parseReadUrlTarget()` from `packages/coding-agent/src/tools/fetch.ts`.\n   - Plain URL reads call `executeReadUrl()`.\n   - URL reads with line selectors load or refresh the URL cache with `loadReadUrlCacheEntry()` and paginate the cached text locally with `#buildInMemoryTextResult()`.\n3. If not a web URL, it checks `session.internalRouter.canHandle(...)`.\n   - Internal URLs are resolved with `internalRouter.resolve()`.\n   - `agent://` query extraction (`/path` or `?q=`) bypasses pagination and returns the extracted content directly.\n   - Other internal resources are paginated in-memory by `#buildInMemoryTextResult()`.\n4. It tries archive resolution next with `#resolveArchiveReadPath()`.\n   - `parseArchivePathCandidates()` scans for `.tar`, `.tar.gz`, `.tgz`, or `.zip` anywhere before `:sub/path`.\n   - On success, `#readArchive()` either lists a directory or decodes an entry as UTF-8 text.\n5. It tries SQLite resolution with `#resolveSqliteReadPath()`.\n   - `parseSqlitePathCandidates()` scans for `.sqlite`, `.sqlite3`, `.db`, `.db3` before any `:table`, `:key`, or `?query` suffix.\n   - `#readSqlite()` dispatches on `parseSqliteSelector()`.\n6. Otherwise it treats the input as a local filesystem path.\n   - `resolveReadPath()` expands `~`, resolves relative to session cwd, treats bare `/` as session cwd, and retries macOS screenshot/NFD/curly-quote variants.\n   - If the path does not exist, `findUniqueSuffixMatch()` does a workspace glob-based unique suffix lookup (skipped for remote mounts).\n7. Directories go through `#readDirectory()`.\n8. Non-directories branch by content type:\n   - image metadata / inline image\n   - editable notebook text\n   - markit-converted document\n   - structural summary for parseable code/prose\n   - streamed text/line-range read\n9. Local text reads are streamed by `streamLinesFromFile()` rather than loading the whole file. The tool adds up to 3 lines of context before/after explicit bounded ranges.\n10. Non-empty contiguous local reads are recorded into `getFileReadCache(session)` for later hashline edit recovery.\n11. If suffix resolution happened, the first text block is prefixed with `[Path '...' not found; resolved to '...' via suffix match]`.\n\n## Modes / Variants\n\n### Local text files\n- No selector: if summarization is enabled and the file is small enough, `#trySummarize()` calls `summarizeCode()`.\n  - Guards: file size `<= 2 MiB` (`MAX_SUMMARY_BYTES`), line count `<= 20_000` (`MAX_SUMMARY_LINES`).\n  - Summary output keeps selected declarations and replaces elided spans with `...` or merged brace-pair lines containing `..`. When at least one span is elided, the text content ends with a footer like `[NN lines elided; re-read needed ranges, e.g. <path>:5-16,40-80]` using concrete ranges from the actual elisions.\n  - When an elided block sits between matching brace lines, `#renderSummary()` may merge them into one anchored line rather than emitting separate opener/closer lines.\n- Explicit selector or summarization miss: streamed text read.\n  - Default open-ended limit is `min(session setting read.defaultLimit, DEFAULT_MAX_LINES)`.\n  - Explicit ranges expand by `RANGE_LEADING_CONTEXT_LINES = 1` / `RANGE_TRAILING_CONTEXT_LINES = 3` on the constrained sides only.\n  - Non-raw output uses `resolveFileDisplayMode()`:\n    - hashline numbered output when edit mode is hashline, read is not raw, source is mutable, edit tool exists, and `readHashLines !== false`\n    - otherwise optional line numbers when `readLineNumbers === true`\n    - raw mode suppresses both\n- Prefix format in hashline mode is a `¶PATH#TAG` header followed by `LINE:TEXT`, e.g. `¶src/foo.ts#0A1B` and `41:def alpha():`, from the session snapshot store plus `formatNumberedLine()` / `formatHashlineHeader()`.\n- The `edit`/hashline path consumes that header plus bare line numbers later; the four-hex tag is opaque and only meaningful in the session snapshot store that minted it. Immutable sources and `:raw` intentionally suppress hashline headers.\n\n### Directory listings\n- `#readDirectory()` calls `buildDirectoryTree()` with:\n  - `maxDepth = 2`\n  - `perDirLimit = 12`\n  - `rootLimit = null`\n  - `lineCap = limit` when a line selector was present, else unlimited at this layer\n- `buildDirectoryTree()` sorts siblings by recency, shows file sizes and relative ages, and may mark `limits.resultLimit` when the tree truncates.\n- Empty directories render as `(empty directory)`.\n\n### Archives\n- Supported archive containers: `.tar`, `.tar.gz`, `.tgz`, `.zip`.\n- Syntax: `archive.ext`, `archive.ext:path/inside`, `archive.ext:path/inside:50-60`.\n- `openArchive()` reads the whole archive into memory, then:\n  - tar/tgz uses `new Bun.Archive(bytes)`\n  - zip uses `fflate.unzipSync()`\n- Archive paths normalize `/`, drop `.` segments, and reject `..`.\n- Directory reads list immediate children; files show `name` plus ` (size)` when size > 0.\n- Directory listing default limit is `500` entries in `#readArchiveDirectory()`.\n- File entries are UTF-8 decoded. Non-UTF-8 entries return `[Cannot read binary archive entry '...' (...)]` instead of bytes.\n- Text archive entries reuse the normal in-memory pagination/anchoring path.\n\n### SQLite databases\n- Database detection requires both a matching extension and a valid SQLite file header (`isSqliteFile()`).\n- Selector forms from `parseSqliteSelector()`:\n\n#### `db.sqlite`\n- `kind: \"list\"`\n- Lists non-`sqlite_%` tables with row counts.\n- `#readSqlite()` caps the rendered list to `500` tables via `applyListLimit()`.\n\n#### `db.sqlite:table`\n- `kind: \"schema\"`\n- Returns `sqlite_master.sql` plus sample rows.\n- Sample size is `DEFAULT_SCHEMA_SAMPLE_LIMIT = 5`.\n\n#### `db.sqlite:table:key`\n- `kind: \"row\"`\n- Resolves by primary key when the table has exactly one PK column; otherwise falls back to `rowid` lookup.\n- No query parameters allowed on row lookups.\n\n#### `db.sqlite:table?limit=...&offset=...&order=...&where=...`\n- `kind: \"query\"`\n- Defaults: `limit = 20`, `offset = 0`.\n- `limit` is capped at `500`.\n- `order` accepts `column` or `column:asc|desc` and must name an existing column.\n- `where` is accepted only after `validateWhereClause()` rejects comments, semicolons, and control keywords like `LIMIT`, `OFFSET`, `UNION`, `ATTACH`, `PRAGMA`.\n- Unknown query parameters throw.\n\n#### `db.sqlite?q=SELECT ...`\n- `kind: \"raw\"`\n- Cannot be combined with table selectors or any other query param.\n- Empty `q` throws.\n- `executeReadQuery()` runs `db.prepare(sql).all()` and rejects bound parameters; it does not verify that the SQL starts with `SELECT`.\n\n- Rendering caps in `packages/coding-agent/src/tools/sqlite-reader.ts`:\n  - ASCII table width `120` (`MAX_RENDER_WIDTH`)\n  - per-column width `40` (`MAX_COLUMN_WIDTH`)\n- `#readSqlite()` opens Bun SQLite in `{ readonly: true, strict: true }` and sets `PRAGMA busy_timeout = 3000`.\n\n### Documents\n- `CONVERTIBLE_EXTENSIONS` in `packages/coding-agent/src/tools/read.ts` covers `.pdf`, `.doc`, `.docx`, `.ppt`, `.pptx`, `.xls`, `.xlsx`, `.rtf`, `.epub`.\n- `convertFileWithMarkit()` converts the file to text/markdown.\n- Converted output is then head-truncated with normal shared limits; there is no line selector support inside the source document before conversion.\n- Conversion failures return a text block like `[Cannot read .pdf file: ...]`.\n\n### Jupyter notebooks\n- `.ipynb` goes through `readEditableNotebookText()` unless `:raw` was requested.\n- Output is editable plain text with markers like:\n\n```text\n# %% [code] cell:0\n...\n```\n\n- Raw mode bypasses that conversion and falls back to file-text reading.\n\n### Images\n- Image detection is metadata-based (`readImageMetadata()`).\n- Max accepted image size is `20 MiB` (`MAX_IMAGE_INPUT_BYTES`, re-exported as `MAX_IMAGE_SIZE`). Larger files throw.\n- If `inspect_image.enabled` is true, `read` returns metadata only (MIME, bytes, dimensions, channels, alpha) plus a suggestion to call `inspect_image`.\n- Otherwise it calls `loadImageInput()` and returns:\n  - a text note from the image loader\n  - an inline image block\n- Unsupported/undecodable image formats throw a `ToolError`.\n\n### Internal URLs\n- `read` does not resolve these itself; it delegates to `session.internalRouter.resolve()`.\n- Registered protocols are outside this file, but the router in `packages/coding-agent/src/internal-urls/router.ts` is built for `agent://`, `artifact://`, `issue://`, `local://`, `mcp://`, `memory://`, `omp://`, `pr://`, `rule://`, and `skill://`.\n- `#handleInternalUrl()` behavior:\n  - parses the URL with `parseInternalUrl()` so colons inside the host segment are legal\n  - for `agent://`, treats non-root path extraction or `?q=` extraction as a special no-pagination mode\n  - otherwise paginates the resolved text in memory\n  - passes `immutable` through to `resolveFileDisplayMode()` so anchors are suppressed for immutable resources such as artifacts, skills, memory, and agent outputs\n  - sets `ignoreResultLimits: true` for `skill://` so the full skill text is paginated only by explicit selectors, not by the normal default line limit\n- `issue://<N>` / `pr://<N>` (and the long form `issue://<owner>/<repo>/<N>` / `pr://<owner>/<repo>/<N>`) route through the same SQLite cache the `github` tool writes to; `?comments=0` selects the no-comments rendering. Bare `issue://` / `pr://` (and `issue://<owner>/<repo>` / `pr://<owner>/<repo>`) issue a live `gh issue list` / `gh pr list` for browsing, accepting `?state=`, `?limit=`, `?author=`, `?label=`. PR diffs share the same cache through `pr://<N>/diff` (numbered file listing with per-file hints), `pr://<N>/diff/<i>` (single file slice; 1-indexed), and `pr://<N>/diff/all` (verbatim unified diff); the listing and per-file slices are reconstructed from the cached unified-diff payload, so all three variants share one `gh pr diff` invocation per PR. Diff content is served as `text/plain`. Soft TTL `github.cache.softTtlSec` (default 5 minutes), hard TTL `github.cache.hardTtlSec` (default 7 days). Stale-hit returns the cached row and schedules a background refresh.\n\n### Web URLs\n- `parseReadUrlTarget()` accepts `http://`, `https://`, or `www.` targets.\n- Plain URL reads call `executeReadUrl()` in `packages/coding-agent/src/tools/fetch.ts`.\n- `:raw` means raw HTML/body fallback path; plain URL reads prefer rendered/reader-friendly output.\n- `:N`, `:A-B`, `:A+C`, and comma-separated multi-ranges do not refetch when cached output is usable. 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  - Only the deterministic disk reads are non-abortable: plain-file line/range reads (`streamLinesFromFile`, multi-range) and directory listings (`#readDirectory`) are called with `undefined` instead of the `AbortSignal`, so an interrupt mid-read can't surface a misleading \"Operation aborted\" on a read that would have finished instantly. Every other branch keeps the signal and its helpers call `throwIfAborted(signal)` to stop promptly: URL/internal-URL reads (network), archive, sqlite, document conversion, image decode, structural summary, conflict scan, and the suffix-glob path resolution.\n\n## Limits & Caps\n- Shared text truncation defaults from `packages/coding-agent/src/session/streaming-output.ts`:\n  - `DEFAULT_MAX_LINES = 3000`\n  - `DEFAULT_MAX_BYTES = 50 * 1024`\n- Local text open-ended default line limit: `read.defaultLimit`, clamped to `[1, DEFAULT_MAX_LINES]`.\n- Explicit line ranges add `1` leading and `3` trailing context lines on the constrained sides (`RANGE_LEADING_CONTEXT_LINES` / `RANGE_TRAILING_CONTEXT_LINES`).\n- File streaming chunk size: `8 * 1024` bytes (`READ_CHUNK_SIZE`).\n- Local streamed byte budget for line reads: `max(DEFAULT_MAX_BYTES, maxLinesToCollect * 512)`.\n- Structural summaries only run when file size `<= 2 MiB` and line count `<= 20_000`.\n- Image input max: `20 MiB`.\n- Directory tree caps for local directories: depth `2`, per-directory children `12`.\n- Archive directory default list cap: `500` entries.\n- SQLite:\n  - default row query limit `20`\n  - schema sample limit `5`\n  - max query limit `500`\n  - table list cap `500`\n  - render width `120`, column width `40`\n  - busy timeout `3000` ms\n- URL read result shown to the model is truncated to `300` lines and `50 KiB` in `executeReadUrl()`; full cached output can be attached as an artifact.\n- Inline fetched URL images:\n  - source bytes cap `20 MiB`\n  - post-resize inline output cap `300 KiB`\n- Unique suffix auto-resolution glob timeout: `5000` ms.\n- File-read cache holds `30` paths per session.\n\n## Errors\n- Validation and operational failures surface as `ToolError`.\n- Selector errors include:\n  - `Line selector 0 is invalid; lines are 1-indexed. Use :1.`\n  - invalid `A+B` / `A-B` shapes\n  - `Cannot combine query extraction with offset/limit` for `agent://.../path:50`\n- Missing local/archive/sqlite paths first attempt unique suffix resolution; if no unique match exists they error.\n- Out-of-bounds line reads do not throw. They return explanatory text with a suggestion such as `Use :1 ...` or `Use :<last line> ...`.\n- Binary archive entries do not throw; they return a text notice.\n- Document conversion failure returns a text notice.\n- Image oversize/unsupported/invalid cases throw.\n- SQLite parser rejects unsupported parameter combinations early; DB/runtime errors are caught and rethrown as `ToolError(message)`.\n- URL fetch failure does not throw when HTTP fetch succeeds but `response.ok === false`; it returns a failed URL read with `method: \"failed\"` and explanatory notes.\n\n## Notes\n- 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 long-term memory backend and return matching memories.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/memory-recall.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/recall.md`\n- Hindsight 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- Mnemopi collaborators:\n  - `packages/coding-agent/src/mnemopi/state.ts` — scoped local recall and result formatting with ids.\n  - `packages/coding-agent/src/mnemopi/config.ts` — local bank scoping and recall limits.\n  - `docs/tools/retain.md` — shared backend, storage, scoping, and retention behavior.\n\n## Inputs\n\n| Field | Type | Required | Description |\n|---|---|---:|---|\n| `query` | `string` | Yes | Natural-language search query. The tool passes it through unchanged except Mnemopi `per-project-tagged` may run an internal shared-bank fallback query. |\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 memory/memories (as of YYYY-MM-DD HH:MM UTC):\\n\\n<bullet list>\"`\n- `details = {}`\n\nHindsight bullet format comes from `formatMemories(...)`:\n- each bullet is `- <text> [<type>] (<mentioned_at>)`; the type and timestamp suffixes appear only when those fields are present.\n\nMnemopi bullet format comes from `formatScopedRecallWithIds(...)`:\n- each bullet is `- <content> (id: <id>|id unavailable) [<source>] (<YYYY-MM-DD>) c:<score>`; optional source, date, and score suffixes appear only when present.\n\nWhen no matches exist:\n- `content[0].text = \"No relevant memories found.\"`\n- `details = {}`\n\n## Flow\n1. `MemoryRecallTool.createIf(...)` exposes the tool when `memory.backend` is either `\"hindsight\"` or `\"mnemopi\"`.\n2. `execute(...)` wraps the operation in `untilAborted(...)`.\n3. If the backend is `mnemopi`:\n   - it reads `session.getMnemopiSessionState()` and throws if the backend was not started;\n   - it calls `state.recallResultsScoped(params.query)`;\n   - scoped recall queries each configured recall bank with `recallEnhanced(query, recallLimit, { includeFacts: true, channelId: bank })`, merges/deduplicates results by id/content, sorts them, and truncates to `recallLimit`;\n   - in `per-project-tagged`, the shared bank may receive one extra fallback query with project-bank literal tokens stripped so broad global memories still match;\n   - results are formatted with ids for later `memory_edit` use.\n4. If the backend is `hindsight`:\n   - it reads `session.getHindsightSessionState()` and throws if the backend was not started;\n   - it calls `state.client.recall(...)` with `bankId`, query, configured `budget`, `maxTokens`, `types`, and bank-scope tag filters;\n   - `HindsightApi.recall(...)` POSTs `/v1/default/banks/{bank_id}/memories/recall`;\n   - results are formatted into a plain-text list with `formatMemories(...)`.\n5. Backend failures are logged with `logger.warn(\"recall failed\", ...)` and rethrown as `Error` instances when needed.\n\n## Modes / Variants\n- Tool path: explicit query-only recall. It does not compose context from recent turns.\n- Backend auto-recall has a richer query-composition path in `HindsightSessionState.beforeAgentStartPrompt(...)` / `maybeRecallOnAgentStart(...)` and `MnemopiSessionState.beforeAgentStartPrompt(...)` / `maybeRecallOnAgentStart(...)`.\n- Hindsight bank scoping:\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- Mnemopi bank scoping:\n  - `global` — recall reads the shared bank.\n  - `per-project` — recall reads the project bank.\n  - `per-project-tagged` — recall reads the project bank and shared bank, then merges results.\n- Session scope: reads cross-session memory data, using the active session's cached config and scope.\n\n## Side Effects\n- Network\n  - Hindsight: `POST /v1/default/banks/{bank_id}/memories/recall`.\n  - Mnemopi: none unless configured local runtime providers perform embedding/LLM work during recall.\n- Session state\n  - None on success for the explicit tool path. 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- Tool availability requires `memory.backend` to be `\"hindsight\"` or `\"mnemopi\"`; default `memory.backend` is `\"off\"`.\n- Hindsight client default budget for raw `HindsightApi.recall(...)` is `\"mid\"`; this tool overrides from config.\n- Hindsight recall settings:\n  - `hindsight.recallBudget = \"mid\"`\n  - `hindsight.recallMaxTokens = 1024`\n  - `hindsight.recallTypes = [\"world\", \"experience\"]`\n- Mnemopi recall settings:\n  - `mnemopi.recallLimit = 8`\n  - `mnemopi.scoping` selects which local bank(s) are searched\n- The explicit tool path does not apply `hindsight.recallContextTurns`, `hindsight.recallMaxQueryChars`, `mnemopi.recallContextTurns`, or `mnemopi.recallMaxQueryChars`; those caps only affect backend auto-recall query composition.\n\n## Errors\n- Throws `Mnemopi backend is not initialised for this session.` when `memory.backend == \"mnemopi\"` but no state exists.\n- Throws `Hindsight backend is not initialised for this session.` when `memory.backend == \"hindsight\"` but no state exists.\n- Hindsight HTTP and fetch failures become `HindsightError` with `statusCode` and parsed `details` when available.\n- Mnemopi recall target failures inside `collectScopedRecallResults(...)` are caught per bank and logged only when `mnemopi.debug` is enabled; if all targets fail, the tool can return `No relevant memories found.`\n- Non-`Error` failures caught by the tool are normalized to `new Error(String(err))` before rethrow.\n\n## Notes\n- Shared backend details are in `docs/tools/retain.md`: storage, subagent aliasing, bank scoping, mission setup, and mental-model behavior.\n- Hindsight mental models are not fetched by this tool. They may already be present in the agent's developer instructions because the backend caches a `<mental_models>` block separately from recall results.\n- Mnemopi developer instructions may include a `<memories>` block from auto-recall; this explicit tool does not update that block.\n- The tool returns memory hits; it does not synthesize across them. Use `reflect` for that path.\n",
 	"tools/reflect.md": "# reflect\n\n> Synthesize an answer over the active long-term memory backend.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/memory-reflect.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/reflect.md`\n- Hindsight 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- Mnemopi collaborators:\n  - `packages/coding-agent/src/mnemopi/state.ts` — scoped local recall and context formatting.\n  - `docs/tools/retain.md` — shared backend, storage, scoping, and mental-model behavior.\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. Hindsight sends it as `context`; Mnemopi appends trimmed context to the recall query under `Additional context:`. |\n\n## Outputs\nReturns a single-shot tool result.\n\nHindsight:\n- `content[0].type = \"text\"`\n- `content[0].text = response.text?.trim() || \"No relevant information found to reflect on.\"`\n- `details = {}`\n- The tool returns the Hindsight server's synthesized text directly; it does not expose raw recall hits.\n\nMnemopi:\n- if no scoped recall results exist: `content[0].text = \"No relevant information found to reflect on.\"`\n- otherwise: `content[0].text = \"Based on recalled memories:\\n\\n<formatted context>\"`\n- `details = {}`\n- The local path performs recall plus formatting; it does not call a separate synthesis endpoint.\n\n## Flow\n1. `MemoryReflectTool.createIf(...)` exposes the tool when `memory.backend` is either `\"hindsight\"` or `\"mnemopi\"`.\n2. `execute(...)` runs under `untilAborted(...)`.\n3. If the backend is `mnemopi`:\n   - it reads `session.getMnemopiSessionState()` and throws if the backend was not started;\n   - if `context` has non-whitespace content, it recalls with `<query>\\n\\nAdditional context:\\n<context>`; otherwise it recalls with `query`;\n   - it calls `state.recallResultsScoped(...)` using the same local scoping and merge behavior as `recall`;\n   - if results exist, it renders them through `state.formatContextScoped(...)` and prefixes `Based on recalled memories:`.\n4. If the backend is `hindsight`:\n   - it reads `session.getHindsightSessionState()` and throws if the backend was not started;\n   - it calls `ensureBankMission(...)` with the current `bankId`, config, and process-local `missionsSet`;\n   - `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;\n   - it calls `state.client.reflect(...)` with `query`, optional `context`, configured recall budget, and bank-scope tag filters;\n   - `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;\n   - blank or whitespace-only responses are replaced with `No relevant information found to reflect on.`\n5. Backend failures are logged with `logger.warn(\"reflect failed\", ...)` and rethrown as `Error` instances when needed.\n\n## Modes / Variants\n- Hindsight tool path: one remote reflect request, optionally focused by `context`.\n- Mnemopi tool path: one local scoped recall followed by context formatting.\n- Hindsight bank scoping:\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- Mnemopi bank scoping:\n  - `global` — reads the shared bank.\n  - `per-project` — reads the project bank.\n  - `per-project-tagged` — reads the project bank and shared bank, then merges results.\n- Session scope: reads cross-session memory data, but does not persist local output.\n\n## Side Effects\n- Network\n  - Hindsight: optional `PUT /v1/default/banks/{bank_id}` from `ensureBankMission(...)`, then `POST /v1/default/banks/{bank_id}/reflect`.\n  - Mnemopi: none unless configured embedding or LLM providers are used by the local runtime during recall.\n- Session state\n  - Reads session-held backend scope and config only. Does not update `lastRecallSnippet`, Hindsight mental-model cache, or retain queues.\n- Background work / cancellation\n  - Aborts through `untilAborted(...)` if the tool call signal is cancelled.\n\n## Limits & Caps\n- Tool availability requires `memory.backend` to be `\"hindsight\"` or `\"mnemopi\"`; default `memory.backend` is `\"off\"`.\n- Tool-level params: only `query` is required; `context` is optional.\n- Hindsight budget setting comes from `hindsight.recallBudget`, default `\"mid\"`.\n- Hindsight `reflect` has no client-side token cap parameter here; unlike `recall`, the tool does not pass `maxTokens`.\n- Hindsight mission initialization tracks up to `MISSION_SET_CAP = 10_000` bank ids, then drops the oldest half of the sorted set.\n- Mnemopi result count is capped by `mnemopi.recallLimit`, default `8`.\n\n## Errors\n- Throws `Mnemopi backend is not initialised for this session.` when `memory.backend == \"mnemopi\"` but no state exists.\n- Throws `Hindsight backend is not initialised for this session.` when `memory.backend == \"hindsight\"` but no state exists.\n- Hindsight HTTP and fetch failures become `HindsightError` with `statusCode` and parsed `details` when available.\n- Hindsight `ensureBankMission(...)` failures are silent to the tool caller; only the later reflect request can fail visibly.\n- Mnemopi recall target failures inside `collectScopedRecallResults(...)` are caught per bank and logged only when `mnemopi.debug` is enabled; if all targets fail, the tool can return the no-information text.\n- Non-`Error` failures caught by the tool are normalized to `new Error(String(err))` before rethrow.\n\n## Notes\n- Shared backend details are in `docs/tools/retain.md`: storage, subagent aliasing, bank scoping, seed mental models, and prompt injection.\n- Hindsight `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- Hindsight 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- Mnemopi `reflect` is local recall plus formatting, so its output shape differs from Hindsight's remote synthesized answer.\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",
@@ -95,7 +96,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"tools/task.md": "# task\n\n> Launch subagents for parallel, optionally isolated work.\n\n## Source\n- Entry: `packages/coding-agent/src/task/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/task.md`\n- Key collaborators:\n  - `packages/coding-agent/src/task/types.ts` — dynamic schema, progress/result types, output caps.\n  - `packages/coding-agent/src/task/discovery.ts` — discover project/user/plugin/bundled agents.\n  - `packages/coding-agent/src/task/agents.ts` — bundled agent definitions and frontmatter parsing.\n  - `packages/coding-agent/src/task/executor.ts` — create child sessions, run subagents, collect output.\n  - `packages/coding-agent/src/task/parallel.ts` — concurrency-limited scheduling and async semaphore.\n  - `packages/coding-agent/src/task/isolation-backend.ts` — isolation backend resolution and platform fallback.\n  - `packages/coding-agent/src/task/worktree.ts` — worktree / FUSE / ProjFS setup, patch capture, branch merge.\n  - `packages/coding-agent/src/task/output-manager.ts` — session-scoped `agent://` id allocation.\n  - `packages/coding-agent/src/task/simple-mode.ts` — `default` / `schema-free` / `independent` field gating.\n  - `packages/coding-agent/src/internal-urls/agent-protocol.ts` — resolve `agent://<id>` to saved subagent output.\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and recursion-depth gating.\n  - `packages/coding-agent/src/sdk.ts` — child-session router/tool wiring and per-subagent `AgentOutputManager`.\n  - `docs/task-agent-discovery.md` — deeper discovery and precedence notes.\n  - `docs/handoff-generation-pipeline.md` — session artifact/handoff persistence patterns used by the wider session layer.\n\n## Inputs\n\n### Default mode (`task.simple = \"default\"`)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `agent` | `string` | Yes | Exact agent name for every task item. Resolved at execution time through `discoverAgents(...)`. |\n| `tasks` | `Array<{ id: string; description: string; assignment: string }>` | Yes | Batch of small, self-contained task items. `id` max length 48 in schema; duplicate ids are rejected case-insensitively at runtime. |\n| `context` | `string` | No | Shared background prepended to every subagent system prompt. Trimmed before use. |\n| `schema` | `string` | No | JSON-encoded JTD schema. Overrides agent/session output schema when this mode allows task-level schemas. |\n| `isolated` | `boolean` | No | Only present when the tool is created with isolation enabled. Requests isolated execution for the whole batch. |\n\n`tasks[].description` is UI-only. `tasks[].assignment` is the actual per-task instruction.\n\n### Schema-free mode (`task.simple = \"schema-free\"`)\n\nSame as default, except `schema` is rejected by `validateTaskModeParams(...)` in `packages/coding-agent/src/task/index.ts`.\n\n### Independent mode (`task.simple = \"independent\"`)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `agent` | `string` | Yes | Exact agent name. |\n| `tasks` | `Array<{ id: string; description: string; assignment: string }>` | Yes | Same item shape, but each `assignment` must carry all required background because shared `context` is disabled. |\n| `isolated` | `boolean` | No | Same conditional field as above. |\n\nIn this mode both `context` and `schema` are rejected.\n\n## Outputs\nThe tool returns one text block plus `details: TaskToolDetails`.\n\n`details` fields:\n- `projectAgentsDir: string | null` — nearest discovered project `agents/` dir.\n- `results: SingleResult[]` — one entry per task in input order for synchronous execution; empty for async-launch responses.\n- `totalDurationMs: number`\n- `usage?: Usage` — sum of per-subagent assistant-message usage.\n- `outputPaths?: string[]` — written `.md` artifact paths for completed subagent outputs.\n- `progress?: AgentProgress[]` — live or final per-task progress snapshots.\n- `async?: { state: \"running\" | \"completed\" | \"failed\"; jobId: string; type: \"task\" }` — present for background execution updates/results.\n\n`SingleResult` includes:\n- identity: `index`, `id`, `agent`, `agentSource`, `description`, optional `assignment`\n- status: `exitCode`, optional `error`, optional `aborted`, optional `abortReason`\n- output: `output`, `stderr`, `truncated`, `durationMs`, `tokens`\n- artifact metadata: `outputPath?`, `patchPath?`, `branchName?`, `nestedPatches?`, `outputMeta?`\n- extracted tool data: `extractedToolData?` from registered subprocess tool handlers such as `yield` and `report_finding`\n\nArtifacts and side channels:\n- Every subagent with an artifacts dir writes `<id>.md`; `agent://<id>` resolves to that file.\n- If the output file is JSON, `agent://<id>/<path>` and `agent://<id>?q=<query>` perform JSON extraction in `packages/coding-agent/src/internal-urls/agent-protocol.ts`.\n- When the parent session persists artifacts, each subagent also gets `<id>.jsonl` session history.\n- Isolated patch mode writes `<id>.patch` per successful task before merge.\n- Async mode returns immediately after job registration, then emits `onUpdate(...)` progress snapshots and later hands completion to the session async-job pipeline.\n\n## Flow\n1. `TaskTool.create(...)` in `packages/coding-agent/src/task/index.ts` calls `discoverAgents(session.cwd)` once to build the dynamic prompt description from current agents and `task.simple` capabilities.\n2. `execute(...)` validates mode-gated fields with `validateTaskModeParams(...)`.\n3. It decides async vs sync:\n   - sync when `async.enabled` is false\n   - sync when the selected cached agent has `blocking === true`\n   - sync when `tasks.length === 0`\n   - otherwise async job scheduling\n4. Async path:\n   - allocate unique output ids with `AgentOutputManager.allocateBatch(...)`\n   - create one async job per task through `session.asyncJobManager.register(...)`\n   - limit concurrent job bodies with `Semaphore(task.maxConcurrency)` from `packages/coding-agent/src/task/parallel.ts`\n   - each job body calls `#executeSync(...)` with a one-task batch and the preallocated id\n   - `onUpdate(...)` emits aggregate `progress` snapshots and `details.async`\n5. Sync path (`#executeSync(...)`) rediscovers agents from disk via `discoverAgents(...)`, so runtime resolution can differ from the earlier prompt description.\n6. It resolves the requested agent with `getAgent(...)`, rejects unknown or disabled agents, and enforces parent spawn policy plus `PI_BLOCKED_AGENT` self-recursion prevention.\n7. It derives the effective output schema in priority order: task call `schema` (if allowed) → agent frontmatter `output` → inherited parent session schema.\n8. It validates task ids: missing ids and case-insensitive duplicates are immediate errors.\n9. If `isolated` was requested, it requires a git repo (`getRepoRoot(...)` / `captureBaseline(...)`) and resolves the actual backend through `resolveIsolationBackendForTaskExecution(...)`.\n10. It chooses an artifacts dir from the parent session when available, otherwise a temp dir, and writes `context.md` there when `session.getCompactContext?.()` returns content.\n11. It allocates unique ids again if the caller did not preallocate them, then builds `tasksWithUniqueIds`.\n12. For each task, it seeds an `AgentProgress` entry and runs `runTask(...)` through `mapWithConcurrencyLimit(...)` using `task.maxConcurrency`.\n13. Non-isolated `runTask(...)` calls `runSubprocess(...)` directly with parent cwd.\n14. Isolated `runTask(...)`:\n   - creates an isolation workspace (`ensureWorktree(...)`, `ensureFuseOverlay(...)`, or `ensureProjfsOverlay(...)`)\n   - applies the captured baseline for worktrees\n   - runs `runSubprocess(...)` inside that workspace\n   - on success, either commits to a per-task branch (`mergeMode === \"branch\"`) or captures a patch with `captureDeltaPatch(...)`\n   - always cleans up the isolation workspace/backend\n15. `runSubprocess(...)` in `packages/coding-agent/src/task/executor.ts` creates a child agent session with:\n   - isolated settings snapshot via `Settings.isolated(...)`, forcing `async.enabled = false` and `bash.autoBackground.enabled = false`\n   - child `agentId` / `parentTaskPrefix` equal to the allocated task id\n   - child internal URL router and `AgentOutputManager` from `packages/coding-agent/src/sdk.ts`\n   - the shared `context`, optional `context.md` reference, optional isolation worktree path, output schema, and IRC peer roster in the system prompt template\n16. Child tool availability is derived from the agent definition plus runtime guards:\n   - explicit `agent.tools` if provided\n   - auto-add `task` when the agent has `spawns` and recursion depth allows it\n   - remove `task` at or past `task.maxRecursionDepth`\n   - expand `exec` to `eval` and `bash`\n   - strip parent-owned `todo` after session creation\n17. `runSubprocess(...)` subscribes to child agent events, coalesces progress updates every 150 ms, forwards lifecycle/progress events on the parent event bus, and extracts tool data through `subprocessToolRegistry`.\n18. The child must finish through the hidden `yield` tool. If it does not, `runSubprocess(...)` sends up to 3 reminder prompts; the last reminder forces `toolChoice = yield` when supported.\n19. Finalization uses `finalizeSubprocessOutput(...)` to reconcile raw assistant text, `yield` payloads, structured schemas, `report_finding` data, and abort states. Output is truncated with `MAX_OUTPUT_BYTES` / `MAX_OUTPUT_LINES` before returning to the parent, but the full raw output is still written to `<id>.md`.\n20. After all sync tasks finish, `#executeSync(...)` aggregates usage, collects artifact paths, and if isolation was used merges results back:\n   - branch mode: cherry-pick per-task branches with `mergeTaskBranches(...)`, then delete merged branches with `cleanupTaskBranches(...)`\n   - patch mode: combine non-empty patch artifacts, dry-check with `git.patch.canApplyText(...)`, then apply or leave manual artifacts\n   - nested repo patches are applied separately with `applyNestedPatches(...)`\n21. The final text summary is rendered from `packages/coding-agent/src/prompts/tools/task-summary.md` and includes `agent://<id>` handles for outputs that exist.\n\n## Modes / Variants\n- Execution mode\n  - Sync inline execution — default path.\n  - Async background execution — one async job per task item when `async.enabled` is on and the chosen agent is not marked `blocking`.\n- Simple mode\n  - `default` — accepts shared `context` and per-call `schema`.\n  - `schema-free` — accepts `context`, rejects `schema`.\n  - `independent` — rejects `context` and `schema`; each assignment stands alone.\n- Isolation backend\n  - `none` — no isolation.\n  - `worktree` — detached git worktree plus baseline replay.\n  - `fuse-overlay` — Unix FUSE overlay mount.\n  - `fuse-projfs` — Windows ProjFS overlay.\n- Isolation merge strategy\n  - Patch mode — capture/apply root patches, keep patch artifacts when application fails.\n  - Branch mode — commit each task onto `omp/task/<id>` branch, cherry-pick into parent, preserve failed branches for manual resolution.\n- Agent source\n  - Project custom agents — nearest project config/plugin agent directories, first by source-family precedence.\n  - User custom agents — user config/plugin agent directories after project dirs of the same source family.\n  - Bundled agents — appended last from `packages/coding-agent/src/task/agents.ts`.\n- Bundled agent types\n  - `explore` — read-only scout with structured handoff output.\n  - `plan` — architecture/planning agent; may spawn `explore`.\n  - `designer` — UI/UX specialist.\n  - `reviewer` — review agent with `report_finding` extraction.\n  - `task` — general-purpose worker with full capabilities.\n  - `quick_task` — low-reasoning mechanical worker using the same task prompt body.\n  - `librarian` — source-grounded external API/library researcher.\n  - `oracle` — senior-engineer implementation/debugging/general consultation agent.\n\n## Side Effects\n- Filesystem\n  - Writes `context.md`, `<id>.jsonl`, and `<id>.md` under the session artifacts dir or a temp task dir.\n  - In isolated patch mode writes `<id>.patch` artifacts.\n  - Creates/removes worktrees or overlay mount directories.\n  - In branch mode creates temporary worktrees and task branches.\n- Network\n  - Child sessions may use whichever networked tools/models their active tool set permits.\n  - MCP proxy tools can call existing parent MCP connections with a 60_000 ms timeout.\n- Subprocesses / native bindings\n  - `fuse-overlayfs` and `fusermount`/`fusermount3` for FUSE isolation.\n  - ProjFS native bindings via `@oh-my-pi/pi-natives` on Windows.\n  - Git operations for baseline capture, patch apply, worktrees, branches, stash, cherry-pick, commits.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Creates child `AgentSession` instances with isolated settings snapshots.\n  - Registers async jobs in `session.asyncJobManager` for background task mode.\n  - Emits `task:subagent:event`, `task:subagent:progress`, and `task:subagent:lifecycle` on the parent event bus.\n  - Allocates session-scoped output ids through `AgentOutputManager` so `agent://` remains unique across invocations and resumes.\n  - Shares the parent `local://` root with subagents by passing `localProtocolOptions` through `createAgentSession(...)`.\n- User-visible prompts / interactive UI\n  - Async mode streams aggregate progress updates.\n  - Missing-`yield` recovery sends up to three internal reminder prompts to the child session.\n  - Final summaries include `<system-notification>` blocks for isolation fallbacks or merge failures.\n- Background work / cancellation\n  - Parent abort stops scheduling new work, aborts active child sessions, and marks unscheduled tasks as skipped.\n  - Async jobs keep their own cancellation via `AsyncJobManager`.\n\n## Limits & Caps\n- Per-subagent output truncation: `MAX_OUTPUT_BYTES = 500_000` and `MAX_OUTPUT_LINES = 5000` in `packages/coding-agent/src/task/types.ts`. Full raw output is still written to `<id>.md` before truncation is returned to the caller.\n- Progress coalescing in child execution: `PROGRESS_COALESCE_MS = 150` in `packages/coding-agent/src/task/executor.ts`.\n- Recent output tail for progress: `RECENT_OUTPUT_TAIL_BYTES = 8 * 1024` and `recentOutput` keeps the last 8 non-empty lines in `packages/coding-agent/src/task/executor.ts`.\n- Missing-`yield` reminder retries: `MAX_YIELD_RETRIES = 3` in `packages/coding-agent/src/task/executor.ts`.\n- MCP proxy timeout: `MCP_CALL_TIMEOUT_MS = 60_000` in `packages/coding-agent/src/task/executor.ts`.\n- Task id schema cap: `tasks[].id` `maxLength: 48` in `packages/coding-agent/src/task/types.ts`.\n- Prompt text says ids should be `≤32` chars, but the runtime schema allows 48; this mismatch is real.\n- Async/full sync parallelism both use `task.maxConcurrency` from settings:\n  - sync path: `mapWithConcurrencyLimit(...)`\n  - async path: `Semaphore(...)` around job bodies\n- Recursion depth gate: `task.maxRecursionDepth` from settings; `packages/coding-agent/src/tools/index.ts` hides the `task` tool at or beyond the limit, and `runSubprocess(...)` also strips child `task` access at max depth.\n- Final inline summary preview per task uses `fullOutputThreshold = 5000` chars in `packages/coding-agent/src/task/index.ts`; longer outputs are summarized while `agent://<id>` points to the full artifact.\n\n## Errors\n- Most validation failures are returned as normal tool text with empty `results`, not thrown:\n  - invalid simple-mode fields\n  - unknown/disabled agent\n  - missing tasks\n  - missing/duplicate task ids\n  - spawn-policy denial\n  - requesting `isolated` while isolation mode is `none`\n- Isolated execution without a git repo returns `Isolated task execution requires a git repository. ...`.\n- Backend resolution can return a hard error (`ProjFS isolation initialization failed...`) or a non-fatal warning with fallback to `worktree`.\n- `mapWithConcurrencyLimit(...)` fails fast on non-abort worker exceptions; already completed results are preserved only in the thrown path’s local state, not surfaced unless the caller catches and converts them.\n- Child-session failures surface as `SingleResult.exitCode = 1` with `stderr`/`error` populated.\n- If the child omits `yield`, `finalizeSubprocessOutput(...)` injects warnings such as `SYSTEM WARNING: Subagent exited without calling yield tool after 3 reminders.`\n- Async scheduling failures are accumulated per task; if no jobs start, the tool returns `Failed to start background task jobs: ...`.\n- `agent://<id>` resolution errors are model-visible when another tool reads them: no session, no artifacts dir, missing id, conflicting extraction syntax, or invalid JSON for extraction.\n\n## Notes\n- Agent discovery precedence is first-wins by exact name: project dirs before user dirs within a source family, plugin agent dirs after config dirs, bundled agents last. See `packages/coding-agent/src/task/discovery.ts` and `docs/task-agent-discovery.md`.\n- `TaskTool.create(...)` caches discovered agents only for description rendering and the async blocking-agent decision. `#executeSync(...)` rediscovers agents each call.\n- Custom agent frontmatter can override bundled agents by name. Bundled definitions are embedded at build time in `packages/coding-agent/src/task/agents.ts`.\n- Child sessions do not inherit conversation history automatically. The only built-in carry-over is shared `context`, optional `context.md`, workspace tree/skills/context files, and shared `local://` root.\n- `Settings.isolated(...)` gives each child a session-isolated settings snapshot; tool enablement is recomputed inside the child session rather than sharing mutable parent tool state.\n- When the parent passes `mcpManager`, child sessions disable standalone MCP discovery and instead get proxy tools that reuse the parent connections.\n- Plan mode mutates an `effectiveAgent` with a read-only tool subset and plan-mode prompt text, but `runSubprocess(...)` is still invoked with `agent` rather than `effectiveAgent`. Model/thinking/schema overrides use the effective agent; prompt/tool/spawn restrictions do not fully flow through this call path.\n- Branch-mode merge temporarily stashes the parent repo before cherry-picking task branches. A stash-pop conflict is treated as merge failure and leaves recovery state behind.\n- Patch-mode only applies combined root patches if every successful task produced a patch and `git.patch.canApplyText(...)` succeeds.\n- Nested git repos are handled separately from the root repo. They are copied into isolated worktrees, diffed independently, and merged later with `applyNestedPatches(...)` because parent git cannot track their file-level changes.\n- `agent://` ids are name-based (`Task` first, `Task-2`/`Task-3` only when the name repeats, nested like `Parent.Child`) by `AgentOutputManager`; this is what prevents artifact collisions across repeated or nested task invocations.\n",
 	"tools/todo.md": "# todo\n\n> Applies ordered mutations to the session todo list and returns a text summary plus the full phase/task state.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/todo.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/todo.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/index.ts` — registers tool, exposes session hooks, gates availability.\n  - `packages/coding-agent/src/modes/controllers/event-controller.ts` — updates the visible todo UI on tool completion.\n  - `packages/coding-agent/src/session/agent-session.ts` — stores cached phases, auto-clears done/dropped tasks, emits failure reminders.\n  - `packages/coding-agent/src/modes/controllers/todo-command-controller.ts` — `/todo` command path, custom-entry persistence, transcript reminder injection.\n  - `packages/coding-agent/src/tools/render-utils.ts` — collapsed-preview cap for renderer trees.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `ops` | `TodoOpEntry[]` | Yes | Ordered operations to apply. `minItems: 1`.\n\n### `TodoOpEntry`\n\n| Op | Required fields | Optional fields | Effect |\n| --- | --- | --- | --- |\n| `init` | `list` | None of the other fields are used | Replaces the entire list with `list`; every new task starts `pending` before normalization. |\n| `start` | `task` | None | Marks one task `in_progress`; any other `in_progress` task is demoted to `pending`. |\n| `done` | `task` or `phase` or neither | None | Marks the target task, phase, or all tasks `completed`. |\n| `drop` | `task` or `phase` or neither | None | Marks the target task, phase, or all tasks `abandoned`. |\n| `rm` | `task` or `phase` or neither | None | Removes the target task, clears the phase's task list, or clears all task lists. |\n| `append` | `phase`, `items` | None | Appends new `pending` tasks to a phase; creates the phase if missing. |\n| `note` | `task`, `text` | None | Appends one trimmed note string to the task's `notes` array. |\n\n### Fields used inside ops\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `\"init\" | \"start\" | \"done\" | \"rm\" | \"drop\" | \"append\" | \"note\"` | Yes | Operation discriminator. |\n| `list` | `{ phase: string; items: string[] }[]` | For `init` | Full replacement payload. Each `items` array has `minItems: 1`. |\n| `task` | `string` | For `start`; for task-targeted `done`/`drop`/`rm`/`note` | Exact task content match. |\n| `phase` | `string` | For `append`; for phase-targeted `done`/`drop`/`rm` | Exact phase name match, except `append` lazily creates a missing phase. |\n| `items` | `string[]` | For `append` | Tasks to append. `minItems: 1`. |\n| `text` | `string` | For `note` | Note text; trailing whitespace is stripped before storing. Empty-after-trim is rejected. |\n\n## Outputs\nThe tool returns a single-shot `AgentToolResult`:\n\n- `content`: one text part containing the summary from `formatSummary(...)`.\n  - Empty final state with no errors: `Todo list cleared.`\n  - Non-empty final state: remaining-item list, current phase progress, then a per-phase tree.\n  - If the active `in_progress` task has notes, the summary includes the note bodies inline.\n  - If any op produced validation/runtime errors, the summary starts with `Errors: ...`; the returned tool result is marked `isError: true` and still includes the mutated state.\n- `details`:\n  - `phases: TodoPhase[]`\n  - `storage: \"session\" | \"memory\"`\n  - `completedTasks?: TodoCompletionTransition[]` when a task changed from non-completed to `completed` during the batch\n\n`TodoPhase` / `TodoItem` state model:\n\n- `TodoPhase`: `{ name: string, tasks: TodoItem[] }`\n- `TodoItem`: `{ content: string, status: \"pending\" | \"in_progress\" | \"completed\" | \"abandoned\", notes?: string[] }`\n\nThe TUI renderer (`todoToolRenderer`) merges call and result into one transcript block, renders phases as a tree, shows note counts as superscripts, and renders the note bodies only for the current `in_progress` task. Collapsed transcript previews cap tree items at `PREVIEW_LIMITS.COLLAPSED_ITEMS` (`8`).\n\n## Flow\n1. `TodoTool.execute(...)` clones the current cached phases from `session.getTodoPhases?.() ?? []` (`packages/coding-agent/src/tools/todo.ts`).\n2. `applyParams(...)` walks `params.ops` in order and applies each entry with `applyEntry(...)`.\n3. Each op mutates the working phase array:\n   - `initPhases(...)` rebuilds the list from scratch.\n   - `start` resolves a task by exact `content`, demotes every other `in_progress` task to `pending`, then marks the target `in_progress`.\n   - `done` / `drop` use `getTaskTargets(...)` to target one task, one phase, or every task.\n   - `rm` removes one task, clears one phase's `tasks`, or clears all phases' task arrays.\n   - `appendItems(...)` resolves or creates the target phase and pushes new `pending` tasks unless the same task content already exists anywhere.\n   - `note` trims trailing whitespace, rejects empty text, and appends the note to `task.notes`.\n4. Missing task/phase references are recorded in an `errors` array by `resolveTaskOrError(...)` / `resolvePhaseOrError(...)`; execution continues through the rest of the batch.\n5. After the full batch, `normalizeInProgressTask(...)` enforces the single-active-task invariant:\n   - if multiple tasks are `in_progress`, only the first stays active and the rest become `pending`;\n   - if none are `in_progress`, the first `pending` task in phase/task order is auto-promoted to `in_progress`.\n6. `execute(...)` stores the normalized phases with `session.setTodoPhases?.(...)` and reports `storage` as `\"session\"` when `session.getSessionFile()` exists, else `\"memory\"`.\n7. `getCompletionTransitions(...)` compares the previous and updated phases; newly completed tasks are returned in `details.completedTasks`.\n8. The agent runtime also watches `todo` tool results in `packages/coding-agent/src/session/agent-session.ts`; successful results refresh cached todos, failed results inject a hidden next-turn reminder telling the model that todo progress is not visible until it retries.\n9. The event controller updates the visible todo UI from `result.details.phases` on success, or shows a warning on error (`packages/coding-agent/src/modes/controllers/event-controller.ts`).\n\n## Modes / Variants\n### State transitions\n\n| Current status | `start` | `done` | `drop` | `rm` | `append` | `note` |\n| --- | --- | --- | --- | --- | --- | --- |\n| `pending` | `in_progress` on target | `completed` | `abandoned` | Removed | New tasks enter as `pending` | No status change |\n| `in_progress` | Target stays `in_progress`; non-target active tasks become `pending` | `completed` | `abandoned` | Removed | No status change | No status change |\n| `completed` | Can be set back to `in_progress` if targeted | Stays `completed` | Becomes `abandoned` if targeted | Removed | No status change | No status change |\n| `abandoned` | Can be set back to `in_progress` if targeted | Becomes `completed` if targeted | Stays `abandoned` | Removed | No status change | No status change |\n\nNormalization then re-applies the single-active-task rule after the full op batch.\n\n### Op targeting rules\n- `done`, `drop`, `rm`:\n  - `task` set: affect one exact-content task.\n  - else `phase` set: affect every task in that exact-name phase.\n  - else: affect every task in every phase.\n- `append` is the only op that creates a missing phase.\n- `note` only targets a single task.\n- `init` discards previous phases entirely.\n\n### Markdown round-trip helpers\nThe same file also exposes non-tool helpers used by `/todo`:\n- `phasesToMarkdown(...)` serializes phases as headings plus checklist items (`[ ]`, `[/]`, `[x]`, `[-]`) with blockquote note bodies.\n- `markdownToPhases(...)` parses that format, defaults orphan tasks into a `Todos` phase, accepts `>` as an `in_progress` marker and `~` as `abandoned`, and runs the same normalization step.\n\n## Side Effects\n- Filesystem\n  - None in the tool itself.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Mutates the session todo cache through `setTodoPhases`.\n  - `storage` reports whether the session has a backing session file, but the tool does not append a custom session entry itself.\n  - Successful tool-result messages carry `details.phases`; `getLatestTodoPhasesFromEntries(...)` can reconstruct state later from those transcript entries.\n  - Failed `todo` results cause `agent-session` to enqueue a hidden next-turn reminder (`customType: \"todo-error-reminder\"`).\n- User-visible prompts / interactive UI\n  - Transcript block is rendered by `todoToolRenderer` and merged with the call line.\n  - `event-controller` updates the visible todo panel from successful results.\n  - On error, `event-controller` shows `Todo update failed...`; the visible panel may stay stale until a later successful call.\n- Background work / cancellation\n  - `AgentSession.setTodoPhases(...)` schedules auto-clear timers for `completed` / `abandoned` tasks via `tasks.todoClearDelay`.\n\n## Limits & Caps\n- `ops` array: `minItems: 1` (`todoSchema`).\n- `init.list[*].items`: `minItems: 1`.\n- `append.items`: `minItems: 1`.\n- Renderer collapsed preview: `PREVIEW_LIMITS.COLLAPSED_ITEMS = 8` (`packages/coding-agent/src/tools/render-utils.ts`).\n- Auto-clear delay: `tasks.todoClearDelay` default `60` seconds; `< 0` disables auto-clear, `0` clears on the next microtask (`packages/coding-agent/src/session/agent-session.ts`).\n- Tool execution mode: `concurrency = \"exclusive\"`, `strict = true`, `loadMode = \"discoverable\"`.\n\n## Errors\n- Ordinary bad op payloads are accumulated as human-readable strings in `errors`; the tool still returns the mutated state, but marks the result `isError: true`.\n- Error strings come from the helpers in `packages/coding-agent/src/tools/todo.ts`, including:\n  - `Missing list for init operation`\n  - `Missing task content`\n  - `Task \"...\" not found` with an extra empty-list hint when applicable\n  - `Missing phase name`\n  - `Phase \"...\" not found`\n  - `Missing phase name for append operation`\n  - `Missing items for append operation`\n  - `Task \"...\" already exists`\n  - `Missing text for note operation`\n- Because ops are processed in order, earlier errors do not roll back later ops.\n- Runtime-level tool failure is handled outside the tool body: `agent-session` injects a hidden reminder and the event controller warns the user that visible progress may be stale.\n- Idempotency is op-specific:\n  - `init` is a full replacement; replaying the same payload yields the same state.\n  - `start`, `done`, and `drop` are effectively idempotent on an existing target state, but `start` also demotes any other active task.\n  - `rm` is not idempotent for targeted removals: the second call errors because the task or phase is gone.\n  - `append` is not idempotent: duplicate task content is rejected with `Task \"...\" already exists`.\n  - `note` is append-only and never idempotent; replaying it adds another note entry.\n\n## Notes\n- Task lookup is exact string equality inside the tool. The model-facing prompt says task content and phase names are identifiers and should stay unique; `append` enforces task uniqueness globally, but `init` does not validate duplicate task or phase names.\n- `findTaskByContent(...)` returns the first matching task across phases. Duplicate task contents make later targeted ops ambiguous.\n- `normalizeInProgressTask(...)` runs after the whole batch, not after each op. A single call can intentionally build an intermediate invalid state and rely on final normalization.\n- `storage: \"session\"` means the session has a session-file backing; it does not mean this tool wrote a durable custom entry.\n- Reload persistence differs by path:\n  - plain `todo` calls survive in transcript tool-result details;\n  - `/todo` command edits additionally append `customType: \"user_todo_edit\"` entries and inject a visible-to-model `<system-reminder>` developer message describing the manual edit.\n- On session resume, `AgentSession.#syncTodoPhasesFromBranch()` strips `completed` and `abandoned` tasks before restoring the cached list. The `/todo` command works around that by reading the latest transcript/custom-entry state so historical done/dropped tasks still appear to the user.\n- Tool availability is gated by `todo.enabled`, and the registry excludes it when `includeYield` is enabled (`packages/coding-agent/src/tools/index.ts`).\n- Subagents do not inherit `todo`; `packages/coding-agent/src/task/executor.ts` filters it out as a parent-owned tool.\n",
 	"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 providers are unavailable or provider attempts fail. 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()` forwards its `AbortSignal` into `executeSearch()`, and `executeSearch()` passes it to providers. If the signal is aborted during fallback handling, `throwIfAborted(signal)` rethrows the cancellation instead of returning an `\"Error: ...\"` text result.\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 each 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: <provider/error>; ...`; 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/types.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: `ANTHROPIC_SEARCH_API_KEY` env var, otherwise `authStorage.hasAuth(\"anthropic\")`; search credentials come from `authStorage.getApiKey(\"anthropic\")` when no search-specific key is set.\n    - Env overrides specific to search (do not affect chat completions):\n      - `ANTHROPIC_SEARCH_API_KEY` — highest-priority search auth; overrides `ANTHROPIC_API_KEY` / OAuth / `ANTHROPIC_FOUNDRY_API_KEY` for the search call only.\n      - `ANTHROPIC_SEARCH_BASE_URL` — search-only base URL for either `ANTHROPIC_SEARCH_API_KEY` or fallback Anthropic credentials; overrides `ANTHROPIC_BASE_URL` (and `FOUNDRY_BASE_URL` in Foundry mode); defaults to `https://api.anthropic.com`.\n      - `ANTHROPIC_SEARCH_MODEL` — search model; defaults to `claude-haiku-4-5`.\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: env or `agent.db` credential for `exa` admits Exa to the auto chain; settings must not explicitly disable `exa.enabled` or `exa.enableSearch`. Explicit selection (`providers.webSearch: exa`) reaches Exa even without a credential and falls back to public MCP.\n    - Querying: POST `https://api.exa.ai/search` with the resolved Exa API key, otherwise JSON-RPC `tools/call` against `https://mcp.exa.ai/mcp` for remote 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: POST `https://kagi.com/api/v1/search` with `Authorization: Bearer <key>` and JSON body `{ query, workflow: \"search\", limit, filters?: { after } }`. `recency` maps to `filters.after` as a UTC `YYYY-MM-DD` string (`day`/`week`/`month`/`year`).\n    - `limit` and `num_search_results` are collapsed together before dispatch, clamped to `1..40`, default `10`.\n    - Output: `sources` (concatenated `data.search` + `data.video` + `data.news` + `data.infobox`, with video/news/infobox results tagged in the title), `relatedQuestions` (`data.adjacent_question` + `data.related_search` `props.question`), `answer` (`data.direct_answer[0].snippet ?? title`), `requestId` (`meta.trace`).\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`; `WebSearchTool.execute()` passes the tool call signal into `executeSearch()`, which forwards it as `params.signal` to providers and rethrows cancellation during fallback.\n\n## Limits & Caps\n- Provider auto-order length: 14 providers (`SEARCH_PROVIDER_ORDER` in `packages/coding-agent/src/web/search/types.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: ...`; the message is either the single normalized provider error or a semicolon-separated summary of all failed providers.\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` uses the shared `SEARCH_PROVIDER_PREFERENCES` / `SEARCH_PROVIDER_OPTIONS` metadata, so the settings selector and setup wizard expose `auto` plus every provider in the auto chain.\n- Exa uses `authStorage.getApiKey(\"exa\")`, then `EXA_API_KEY`, then unauthenticated `https://mcp.exa.ai/mcp` fallback.\n",
-	"tools/write.md": "# write\n\n> Create or overwrite a file, writable internal resource, archive entry, SQLite row, or merge-conflict resolution.\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. Writable internal URLs are delegated to their handler. `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. `conflict://<id>` resolves a recorded merge conflict. |\n| `content` | `string` | Yes | Full replacement file content, archive entry content, internal-resource content, conflict replacement, 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 <chars> bytes to <relative-path>` (the count is `cleanContent.length`, not encoded byte length).\n  - Internal URL write: `Successfully wrote <chars> bytes to <url>`.\n  - Archive write: `Successfully wrote <chars> 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  - Conflict resolution: conflict-specific success text, with fresh hashline snapshot headers when applicable.\n- If hashline prefixes were copied from `read` output and stripped first, the first text block gets an extra note.\n- In hashline display mode, plain file writes (including ACP bridge writes) and conflict resolutions prepend a fresh `¶<relative-path>#TAG` header so the next `edit` has a current snapshot tag without an extra `read`. Bulk conflict resolutions append a `Snapshots:` block listing one header per successfully written file.\n- Plain file writes may also return `details.diagnostics` plus `details.meta.diagnostics` when LSP diagnostics-on-write is enabled, and `details.madeExecutable` when a newly written shebang file is chmodded executable.\n- SQLite writes use `toolResult(...).sourcePath(...)`, so `details.meta.sourcePath` points at the database file.\n- Archive and internal URL writes return empty `details`.\n\n## Flow\n1. `WriteTool.execute()` in `packages/coding-agent/src/tools/write.ts` strips pasted `¶PATH#HASH` headers and `LINE:` hashline prefixes from `content` when the session is in hashline display mode.\n2. If `path` is an internal URL whose handler exposes `write`, the tool delegates directly to `handler.write(...)` and returns.\n3. `conflict://...` paths are handled next by the merge-conflict resolver. Scope reads such as `conflict://<id>/ours` are rejected as read-only; writable conflict URIs must omit the scope.\n4. It calls `#resolveArchiveWritePath()` next. 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.\n5. 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.\n6. 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.\n7. 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`.\n8. 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   - ACP bridge writeTextFile is tried first when available; otherwise 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   - `maybeMarkExecutableForShebang()` may chmod the file executable when content starts with `#!`.\n   - `invalidateFsScanAfterWrite()` runs on the file path.\n9. The tool returns a text result and optional diagnostics / executable 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  - Resolves conflict markers in files for `conflict://...` writes.\n  - May chmod a shebang file executable after a successful plain-file write.\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- Shebang executable handling depends on host filesystem chmod support.\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- Conflict scope writes such as `conflict://<id>/ours` are rejected as read-only; invalid conflict IDs or missing conflict history surface as `ToolError`s from the conflict resolver.\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 and internal URL writes report `cleanContent.length` as “bytes”, 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",
+	"tools/write.md": "# write\n\n> Create or overwrite a file, writable internal resource, archive entry, SQLite row, or merge-conflict resolution.\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. Writable internal URLs are delegated to their handler. `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. `conflict://<id>` resolves a recorded merge conflict. |\n| `content` | `string` | Yes | Full replacement file content, archive entry content, internal-resource content, conflict replacement, 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 <chars> bytes to <relative-path>` (the count is `cleanContent.length`, not encoded byte length).\n  - Internal URL write: `Successfully wrote <chars> bytes to <url>`.\n  - Archive write: `Successfully wrote <chars> 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  - Conflict resolution: conflict-specific success text, with fresh hashline snapshot headers when applicable.\n- If hashline prefixes were copied from `read` output and stripped first, the first text block gets an extra note.\n- In hashline display mode, plain file writes (including ACP bridge writes) and conflict resolutions prepend a fresh `¶<relative-path>#TAG` header so the next `edit` has a current snapshot tag without an extra `read`. Bulk conflict resolutions append a `Snapshots:` block listing one header per successfully written file.\n- Plain file writes may also return `details.diagnostics` plus `details.meta.diagnostics` when LSP diagnostics-on-write is enabled, and `details.madeExecutable` when a newly written shebang file is chmodded executable.\n- SQLite writes use `toolResult(...).sourcePath(...)`, so `details.meta.sourcePath` points at the database file.\n- Archive and internal URL writes return empty `details`.\n\n## Flow\n1. `WriteTool.execute()` in `packages/coding-agent/src/tools/write.ts` strips pasted `¶PATH#HASH` headers and `LINE:` hashline prefixes from `content` when the session is in hashline display mode.\n2. If `path` is an internal URL whose handler exposes `write`, the tool delegates directly to `handler.write(...)` and returns.\n3. `conflict://...` paths are handled next by the merge-conflict resolver. Scope reads such as `conflict://<id>/ours` are rejected as read-only; writable conflict URIs must omit the scope.\n4. It calls `#resolveArchiveWritePath()` next. 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.\n5. 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.\n6. 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.\n7. 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`.\n8. 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   - ACP bridge writeTextFile is tried first when available; otherwise 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   - `maybeMarkExecutableForShebang()` may chmod the file executable when content starts with `#!`.\n   - `invalidateFsScanAfterWrite()` runs on the file path.\n9. The tool returns a text result and optional diagnostics / executable 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  - Resolves conflict markers in files for `conflict://...` writes.\n  - May chmod a shebang file executable after a successful plain-file write.\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 `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- Shebang executable handling depends on host filesystem chmod support.\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- Conflict scope writes such as `conflict://<id>/ours` are rejected as read-only; invalid conflict IDs or missing conflict history surface as `ToolError`s from the conflict resolver.\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 and internal URL writes report `cleanContent.length` as “bytes”, 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 conversational nodes plus any entry types not explicitly suppressed. It hides these setting/bookkeeping entry types:\n\n- `label`\n- `custom`\n- `model_change`\n- `thinking_level_change`\n\nOther internal entry types that are not rendered specially may appear as blank rows in current code.\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, constructs a `TtsrManager`, and buckets rules through `bucketRules(...)`:\n\n```ts\nconst ttsrSettings = settings.getGroup(\"ttsr\");\nconst ttsrManager = new TtsrManager(ttsrSettings);\nconst rulesResult = await loadCapability<Rule>(ruleCapability.id, { cwd });\nconst { rulebookRules, alwaysApplyRules } = bucketRules(\n  rulesResult.items,\n  ttsrManager,\n  {\n    builtinRules: ttsrSettings.builtinRules,\n    disabledRules: ttsrSettings.disabledRules,\n  },\n);\n```\n\n`bucketRules(...)` drops names listed in `ttsr.disabledRules`, drops embedded `builtin-defaults` rules when `ttsr.builtinRules === false`, registers accepted TTSR rules, and then routes the remaining rules to always-apply/rulebook buckets.\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. If a TTSR rule defines `globs`, those globs are compiled as a global file-path gate for matching.\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-glob, 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\nNon-interrupting matches split by `matchContext.source`:\n\n- **`source === \"tool\"` (tool-source match).** The rule is bucketed into `#perToolTtsrInjections`, keyed by the matched tool call's `id`. There is **no** deferred follow-up turn and the stream is not aborted. When the tool actually produces a result, the `afterToolCall` hook prepends a rendered `ttsr-tool-reminder.md` block to `ctx.result.content` (a single `text` block inserted ahead of the tool's own content), and persists a `ttsr_injection` entry with the consumed rule names. The template payload is:\n\n  ```xml\n  <system-reminder reason=\"rule_violation\" rule=\"{{name}}\" path=\"{{path}}\">\n  ...\n  {{content}}\n  </system-reminder>\n  ```\n\n- **`source === \"text\"` / `\"thinking\"` (prose-source match).** Behavior is unchanged: the rule is queued in `#pendingTtsrInjections` and, 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\nWithin a single matching batch, each rule is attached to exactly one sibling tool call — if multiple sibling tool calls would satisfy the same rule, deduplication picks one and the others are left untouched. Multiple distinct rules can still fold onto the same tool call.\n\n#### Implications for tool authors and transcript readers\n\n- The tool's own `toolResult` content is preserved verbatim; the reminder is **prepended** as an additional leading text block. Renderers that assume `content[0]` is the tool's primary output must scan past any block whose text begins with `<system-reminder reason=\"rule_violation\"` (or filter on the wrapper tag) to find the real payload.\n- The reminder is in-band on the tool result, not a separate `custom_message`/`ttsr-injection` entry. Transcript readers looking for non-interrupting TTSR activity on tool-source rules MUST inspect tool results (and the persisted `ttsr_injection` entry list), not just synthetic injection entries.\n- A single tool result may carry reminders for several rules concatenated with a blank line between rendered templates.\n- If the assistant message ends with `stopReason === \"aborted\"` or `\"error\"` before the matched tools run, the pending per-tool buckets are cleared — those rules are **not** persisted as injected and remain eligible to re-trigger on a future turn (subject to repeat policy).\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 prose-source injections are marked/persisted when their queued custom message reaches `message_end`\n- non-interrupting tool-source injections are marked at match time and persisted via `appendTtsrInjection(...)` from the `afterToolCall` hook when the matched tool's result is produced\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- `ttsr.disabledRules`: listed names are dropped before TTSR registration and are not surfaced through always-apply/rulebook buckets.\n- `ttsr.builtinRules: false`: embedded `builtin-defaults` rules are dropped before TTSR registration; user/project rules still load.\n- `globs` on a TTSR rule require the stream match context to include at least one matching file path.\n- `contextMode: \"keep\"`: partial violating output can remain in context before reminder retry.\n- `interruptMode: \"never\"`: prose-source matches queue a deferred hidden injection after a successful assistant message; tool-source matches fold an in-band `<system-reminder>` into the matched tool call's `toolResult` content via the `afterToolCall` hook (no mid-stream abort, no separate follow-up turn).\n- Tool-source non-interrupting buckets are cleared when the parent assistant message ends with `stopReason === \"aborted\"` or `\"error\"`, so rules whose target tool never produced a result remain eligible to re-trigger.\n- Repeat-after-gap depends on turn count increments at `turn_end`; mid-turn chunks do not advance gap counters.\n",
 	"tui-core-renderer.md": "# TUI core renderer — invariants & failure modes\n\nWhat you are dealing with before you touch the rendering engine. This is the\ncompanion to [`tui-runtime-internals.md`](./tui-runtime-internals.md): that doc\nmaps the *flow* (input → component tree → render); this doc explains what\n**does not work, why it keeps breaking, and the invariants you must not\nviolate**. Scope is the core engine only:\n\n- [`packages/tui/src/tui.ts`](../packages/tui/src/tui.ts) — render planner, intent emitters, native-scrollback bookkeeping, cursor placement.\n- [`packages/tui/src/terminal.ts`](../packages/tui/src/terminal.ts) — `ProcessTerminal`, capability probes, private-CSI reassembly.\n- [`packages/tui/src/terminal-capabilities.ts`](../packages/tui/src/terminal-capabilities.ts) — `TERMINAL` profile, ED3 risk / sync-output / DECCARA / image detection.\n- [`packages/tui/src/stdin-buffer.ts`](../packages/tui/src/stdin-buffer.ts) — escape-sequence reassembly.\n- [`packages/tui/src/utils.ts`](../packages/tui/src/utils.ts) — width/slice/wrap (the width model).\n- [`packages/tui/src/kitty-graphics.ts`](../packages/tui/src/kitty-graphics.ts) + [`components/image.ts`](../packages/tui/src/components/image.ts) — inline images.\n- [`packages/tui/src/deccara.ts`](../packages/tui/src/deccara.ts) — rectangular-fill optimizer.\n\nApplication-layer renderers (transcript, tool calls, session tree, editor,\nwidgets) are **out of scope** — they live in `packages/coding-agent`.\n\n---\n\n## 1. The one thing to understand first\n\n> **The renderer cannot observe the terminal's scroll position on most hosts it\n> runs on.** Every decision about rewriting native scrollback is therefore a\n> *guess*, and the guess has two opposite failure modes that cannot both be\n> avoided by a single policy.\n\nWe keep our transcript on the **normal screen**. We deliberately have not moved\nthe engine to the alternate screen: alt-screen would make the terminal handle\nviewport isolation, but the transcript/resume affordances would disappear with\nthe alternate buffer. Keeping the normal screen means\n*we* own native scrollback, which means we must decide, per frame, whether it is\nsafe to rebuild it. To rebuild history we emit xterm **ED3** (`CSI 3 J`, erase\nsaved lines). Deciding when ED3 is safe requires knowing whether the user has\nscrolled up — and we usually can't:\n\n- **ConPTY hosts** (Windows Terminal, Tabby, Hyper, VS Code, conhost): the\n  pseudo-console buffer is pinned to the visible grid, so any \"am I at the\n  bottom?\" console query answers \"yes\" even when the reader scrolled up. The\n  probe *lies*.\n- **POSIX terminals**: there is no scroll-position API at all. The probe is\n  *absent*.\n\nSo `Terminal.isNativeViewportAtBottom()` returns `true` / `false` / **`undefined`**,\nand `undefined` (\"unknown\") is the common case. The whole renderer is built\naround not trusting `undefined`.\n\n### The two-way bind\n\n| If you guess… | …and you're wrong | Symptom |\n|---|---|---|\n| **Eager** (rebuild now → emit `CSI 3 J`) | reader was scrolled up | **YANK** to top + **FLASH** on terminals that snap scroll on ED3 |\n| **Defer** (emit nothing, reconcile later) | viewport really was at the bottom | **CORRUPTION** (stale/duplicated rows) + **invisible-until-resize** |\n\nYank, flash, and buffer corruption are **the same bug wearing three masks.**\nHistorically, every fix that suppressed one mask for one terminal class\nre-enabled the opposite mask for a neighbouring class, and the follow-on\ncomplaint landed within a day. If you \"fix flashing\" by making rebuilds more\neager, you will reintroduce yank. If you \"fix yank\" by deferring more, you will\nreintroduce corruption / invisibility. **Do not move this lever without the\nfidelity harness (§9) green.**\n\n---\n\n## 2. The render-intent planner (what you are editing)\n\n`#doRender` is split into a **planner** (`#planRender`) that classifies a frame\ninto exactly one `RenderIntent`, and one `#emit*` method per intent that owns\nthe bytes written and the state update. All state flows through a single\n`#commit` checkpoint at the end of every emitter. The intent union\n(`tui.ts`, search `type RenderIntent`):\n\n| Intent | Emits | When |\n|---|---|---|\n| `noop` | cursor only | nothing visible changed |\n| `initial` | clear viewport, paint transcript, **keep** prior shell scrollback | first paint after `start()` |\n| `sessionReplace` | clear viewport **+ ED3** (outside multiplexers) | caller forced `{ clearScrollback: true }` (switch/branch/reload/resume) |\n| `historyRebuild` | clear viewport **+ ED3** (outside multiplexers) | geometry change rewrapped history, or a proven-at-tail rebuild |\n| `overlayRebuild` | rebuild viewport with overlay composite | overlay visibility changed |\n| `liveRegionPinned` | relative moves + per-row rewrite/suffix-clear + `\\r\\n` | foreground streaming on an ED3-risk host, commit-as-you-go |\n| `viewportRepaint` | rewrite the visible viewport in place (optional `appendFrom` tail first) | safe non-destructive repaint |\n| `deferredShrink` | padded viewport repaint, history left dirty | bottom-anchored shrink, viewport unobservable |\n| `deferredMutation` | **zero bytes**, history left dirty | row-reindexing edit while possibly scrolled |\n| `shrink` / `diff` | trailing-row clear / changed-line diff | ordinary in-place updates |\n\n**ED3 (`CSI 3 J`) is emitted in exactly one place** — `#emitFullPaint` when\n`clearScrollback: true` (`\\x1b[2J\\x1b[H\\x1b[3J`). The ordinary clear is\n**non-destructive**: `\\x1b[22J` (copy-screen-to-scrollback, only when\n`TERMINAL.supportsScreenToScrollback`) then `\\x1b[2J\\x1b[H`, **no `3J`**. ED3 is\nreached only by `sessionReplace`/`historyRebuild`/`overlayRebuild`, and those\nsuppress the scrollback clear inside multiplexers (`isMultiplexerSession()` =\n`TMUX || STY || ZELLIJ`).\n\n### The predicate gates\n\nThree private predicates encode the guessing policy. Do not \"simplify\" them —\neach branch is load-bearing:\n\n- `#canReplayNativeScrollbackAtCheckpoint(atBottom)` → `atBottom === true`. A\n  rebuild at a **keystroke checkpoint** (prompt submit) is allowed only with a\n  *positive* at-tail proof. A prompt submit is **no longer** treated as implicit\n  proof for an unobservable host.\n- `#canRebuildNativeScrollbackLive(atBottom, allowUnknown)` → `true` iff\n  `atBottom === true`, **or** (`atBottom === undefined && allowUnknown &&\n  platform !== \"win32\"`). i.e. live ED3 during streaming requires either proof\n  or an explicit direct-user-input opt-in, and **never** on win32.\n- `#nativeViewportIsScrolled(atBottom, allowUnknown)` → `true` if\n  `atBottom === false`, or (`undefined && win32 && !allowUnknown`). Used to\n  decide deferral.\n\n`allowUnknownViewportMutation` is the **direct-user-input opt-in** (autocomplete\n/ IME / a keystroke the user just typed). A keystroke pins the host viewport to\nthe bottom, so it is safe to repaint live then. It is **not** set by passive\nstreaming. `setEagerNativeScrollbackRebuild(true)` is the streaming opt-in; on\nED3-risk hosts it is downgraded so it never promotes to a live ED3 clear.\n\n### Deferral + checkpoint discipline\n\nWhen the viewport is unobservable during **passive streaming**, the planner\ndefers (`deferredMutation`/`deferredShrink`/`viewportRepaint`) and marks native\nscrollback dirty (`#markNativeScrollbackDirty()`). Reconciliation happens later\nat a checkpoint via `refreshNativeScrollbackIfDirty()` — and only if\n`#canReplayNativeScrollbackAtCheckpoint` proves at-tail. The streaming-defer +\nlive-region-pin seam (`NativeScrollbackLiveRegion`,\n`getNativeScrollbackLiveRegionStart` / `getNativeScrollbackCommitSafeEnd`) is the\n**actively-churning** part of the engine; if you change how transient rows are\ncommitted, every structural-mutation branch (shrink **and** grow/offscreen-edit)\nmust defer **symmetrically**, or you reopen the corruption family.\n\n---\n\n## 3. The five fault families\n\n### YANK — viewport snapped to top — NOT fully converged\n- **Mechanism:** a live `historyRebuild` fires `CSI 3 J` while the reader is\n  scrolled up; ED3-snap terminals reset the visible viewport to the top of the\n  (now-erased) scrollback.\n- **Trigger to avoid:** treating an unobservable probe as \"at bottom\" during\n  *passive* streaming, or OR-ing an eager-streaming flag into the live ED3 path.\n- **Current stance:** never emit ED3 on an unobservable host during passive\n  streaming; defer and reconcile at a keystroke checkpoint. ConPTY/win32 never\n  trust the probe at all.\n\n### CORRUPTION — duplicated / stale rows — NOT fully converged\n- **Mechanism:** the flip side of the yank fix. A deferred/repainted frame\n  leaves rows already committed to native scrollback out of sync with the live\n  viewport; the scrollback↔viewport seam duplicates (e.g. a 2-row dup, a\n  streaming-tail dup, or an async-expansion dup).\n- **Trigger to avoid:** repainting the viewport over scrollback that still holds\n  the old copy; a frozen/deferred block whose snapshot no longer matches after\n  the region above it reflowed; one mutation branch deferring while its mirror\n  branch repaints.\n- **Current stance:** commit only the **stable prefix** line-count to native\n  history; keep unstable rows out; reconcile drift at the checkpoint; park the\n  hardware cursor at real content bottom, not padded bottom.\n\n### FLASH (and invisible-until-resize) — NOT fully converged\n- **Two distinct causes, one symptom:**\n  - *Flash* = eager ED3 rebuild wrapped in DEC 2026 BSU/ESU fired per streaming\n    frame on a terminal that clamps scroll on ED3 (VTE/GNOME family).\n  - *Invisible-until-resize* = the defer fix over-firing, so a structural frame\n    emits **zero bytes** (`deferredMutation` returns nothing) until a resize\n    forces a repaint.\n- **Trigger to avoid:** env-detection that misses a flashing terminal (SSH\n  strips `VTE_VERSION`; some hosts set no distinguishing var); collapsing an\n  `undefined` probe into a definite scrolled/at-bottom verdict.\n- **Current stance:** confine ED3 to the destructive path; auto-disable DEC 2026\n  at runtime when the terminal reports it unsupported (DECRQM), with\n  `PI_NO_SYNC_OUTPUT` as a manual hatch; keep autowrap discipline regardless.\n\n### WIDTH — measurement crashes / fidelity — crash class dead, accuracy unproven\n- **Mechanism:** the measured column width of a line disagreed with the\n  terminal's painted cells (emoji, wide graphemes, combining marks, Hangul\n  jamo), and the old render loop **threw** on any mismatch — a 1-cell cosmetic\n  error became a fatal whole-agent crash.\n- **Current stance:** **never throw in the render hot path — clamp.** The loop\n  truncates over-wide lines with `truncateToWidth`/`sliceByColumn` and logs\n  (under debug) instead of dying. Width is owned end-to-end by one native UAX#11\n  engine shared by measure/slice/wrap (see §6). Accuracy across all scripts\n  (e.g. RTL/combining marks) is still not proven by a green gate.\n\n### PROBE — stray bytes injected as keystrokes — RESOLVED\n- **Mechanism:** a private-CSI probe reply (DA1 / kitty / mode 2031) split\n  across a stdin flush; the unmatched prefix was dropped and the continuation\n  bytes were forwarded as keystrokes.\n- **Current stance:** buffer-and-reassemble partial CSI responses; give each\n  probe a typed sentinel owner. This is the **one cleanly-closed family** —\n  because its contract is *bounded and observable* (bytes in = bytes out),\n  unlike the unobservable-viewport families. See §7.\n\n---\n\n## 4. Invariants — MUST / NEVER\n\nThese are the rules the recurrence taught us. Treat them as load-bearing.\n\n1. **NEVER add a new `CSI 3 J` (ED3) callsite.** ED3 must flow only through\n   `#emitFullPaint({ clearScrollback: true })`, for the existing destructive\n   intents (`sessionReplace`, proven/safe `historyRebuild`, `overlayRebuild`).\n   Ordinary redraws use the non-destructive `\\x1b[22J` + `\\x1b[2J\\x1b[H` clear.\n2. **NEVER trust an unobservable viewport probe (`undefined`) for *passive*\n   streaming.** Only a positive at-tail proof, or a direct-user-input opt-in\n   (`allowUnknownViewportMutation`), authorizes a live rebuild — and never on\n   win32/ConPTY.\n3. **NEVER throw in the render hot path.** Clamp over-wide lines; a width\n   mismatch is cosmetic, not fatal.\n4. **NEVER let a defer path emit a structurally-changed frame as zero bytes\n   while at the bottom** — that is invisible-until-resize. `deferredMutation`/\n   `deferredShrink` are only safe when the viewport is (or may be) scrolled.\n5. **Defer symmetrically.** If one structural-mutation branch (shrink) defers on\n   an unobservable ED3-risk host, the mirror branch (grow / offscreen-edit) must\n   too. Asymmetry reopens corruption.\n6. **Commit only the stable prefix to native history.** Transient/unsettled rows\n   stay out of scrollback until a checkpoint; reconcile drift at the checkpoint.\n7. **Park the hardware cursor at real content bottom**, not the padded viewport\n   bottom, or height shrinks scroll live rows into scrollback and duplicate them\n   per resize step.\n8. **Cursor writes live *inside* the synchronized-output frame**, before ESU —\n   never as a second frame after it (that teleports/blinks the caret).\n9. **Detect terminal *risk*, not terminal *brand*, and default unknown to\n   risky.** Env sniffing is necessarily incomplete (see §5); never assume an\n   un-enumerated host is safe.\n10. **Multiplexers (tmux/screen/zellij) get no destructive scrollback clear and\n    no viewport probe.** ED3 is a no-op there and a full replay duplicates the\n    transcript; repaint in place and rely on the pinned/commit-as-you-go path.\n11. **Any change to the eager/defer lever, the predicates, or the live-region\n    seam must be validated by the render-stress fidelity harness (§9)** across\n    `{win32, POSIX} × {unknown, scrolled, at-bottom}`, not by a single-terminal\n    smoke test.\n\n---\n\n## 5. Terminal capability detection (and why it is fragile)\n\n`TERMINAL` (`terminal-capabilities.ts`) is resolved once at import from\n`TERMINAL_ID` plus environment sniffing. The detection helpers are pure and\nparameterized over `(env, platform)` so they are unit-testable:\n\n- `detectTerminalEagerEraseScrollbackRisk(env, platform)` → is a live ED3\n  rebuild unsafe here? Current policy: `false` on win32 (dedicated ConPTY\n  deferral paths handle it) and when `PI_TUI_ED3_SAFE=1`; otherwise **`true`**\n  for `WT_SESSION` (WT fronting WSL), SSH/tmux/screen/zellij, known\n  ED3-snap/scrollback-clearing terminals (WezTerm, kitty, ghostty, alacritty,\n  VTE, iTerm2, Apple Terminal, GNOME Terminal, Ptyxis, xfce4-terminal), Linux\n  truecolor, **and every other unknown POSIX terminal**. The default is *risky*\n  on purpose.\n- `shouldEnableSynchronizedOutputByDefault(env, id)` → DEC 2026 default. Precedence:\n  user opt-out (`PI_NO_SYNC_OUTPUT`/`PI_TUI_SYNC_OUTPUT=0`) → user force-on\n  (`PI_FORCE_SYNC_OUTPUT=1`/`PI_TUI_SYNC_OUTPUT=1`) → `TERM_FEATURES` advertises\n  `Sy` → `WT_SESSION` (WT/WSL) → known direct terminals\n  (kitty/ghostty/wezterm/iterm2/alacritty/vscode; SSH passes through) → off for\n  risky multiplexers and everything else (VTE-family, GNU screen, Apple Terminal,\n  legacy conhost, unknown). Reconciled at runtime by the DECRQM mode-2026 report:\n  a positive report **enables** sync (upgrading default-off muxes like\n  zellij/tmux-master), a negative one disables it; a user override still wins.\n  `synchronizedOutputUserOverride(env)` is the shared opt-out/force resolver.\n- `detectRectangularSgrSupport(id, env)` → DECCARA fills: **kitty only**\n  (ghostty does not implement the SGR-background extension), off in multiplexers\n  and under `PI_NO_DECCARA`.\n\n**Why this keeps leaking:** terminal class is inferred from env vars that are\n**not durable**. `VTE_VERSION` is stripped by `sshd` (default `AcceptEnv`);\n`COLORTERM` is also not in default `AcceptEnv`; some hosts (Tabby) set no\ndistinguishing var; WSL-fronting-WT is neither pure win32 nor pure POSIX. Every\nmissed env var is a missed terminal class is a new complaint. The mitigations\nare: (a) **default unknown to risky** rather than safe, and (b) detect by\n*behavior/handshake* (DECRQM) where possible rather than a host allow-list. When\nyou add a terminal, add it to the pure detector and add the **SSH-stripped env\nshape** to the test, not just the env-present shape.\n\n---\n\n## 6. Width model\n\n`visibleWidth` / `truncateToWidth` / `sliceByColumn` / `wrapTextWithAnsi`\n(`utils.ts`) all route through **one native UAX#11 engine** (`@oh-my-pi/pi-natives`,\nRust `unicode-width`). We deliberately dropped `Bun.stringWidth` because it\ndisagreed with the engine on combining marks and jamo, and mixing two width\nmodels in measure-vs-slice produced the crashes.\n\n- Fast path: printable ASCII is one cell per code unit.\n- ZWJ pictographic emoji take the `visibleWidthByGrapheme` override (ANSI spans\n  excised first, then `Intl.Segmenter`), because the native scanner double-counts\n  SGR bytes when a sequence is split by the segmenter.\n- OSC 66 sized text (`\\x1b]66;…`) takes the native path.\n\n**Rule:** if you add a code path that measures width, route it through these\nhelpers. Never reintroduce `Bun.stringWidth` or a parallel width table — the\nmeasure model and the slice/wrap model must agree, or you get over-wide lines\nthat the hot-path clamp silently truncates (cosmetic loss) or, worse, seam\nduplication.\n\n---\n\n## 7. Capability probes & stdin reassembly\n\n`ProcessTerminal` fuses capability queries with a bare DA1 (`CSI c`) sentinel so\na non-answering terminal is detected when DA1 returns first. Replies can arrive\n**split across a stdin flush**, so:\n\n- `#privateCsiResponseBuffer` accumulates `\\x1b[?…` partials while a sentinel is\n  outstanding, rejoins on the terminator byte (0x40–0x7e), then runs the\n  DA1/kitty/mode-2031 handlers on the **complete** reply. A new `\\x1b`\n  mid-reassembly or >256 bytes abandons the partial so real keys (e.g. arrow\n  `\\x1b[A`) still reach input.\n- `#da1SentinelOwners` is a **typed FIFO** discriminated by `kind` (`keyboard`,\n  `osc11`, `privateMode`, `kittyGraphicsProbe`, `osc99Probe`) so a keyboard DA1\n  cannot be mistaken for an OSC 11 / DECRQM / graphics-probe sentinel.\n- DECRQM probes (`#queryPrivateMode(2026/2048/2031)`) record support via DECRPM\n  and drive runtime feature gating (e.g. auto-disabling DEC 2026 sync output).\n\n**Rule:** any new probe must own a typed sentinel and survive a split reply. The\ncontract is bytes-in = bytes-out; it is testable, so test it (feed the reply\nbyte-by-byte and assert nothing leaks to the input handler).\n\n---\n\n## 8. Inline images & memory\n\nKitty images are **transmit-once, place-many** (`kitty-graphics.ts`):\n`encodeKittyTransmit` (`a=t`, keyed by a stable `i=`) writes the base64 a single\ntime; repaints emit only `encodeKittyPlacement` (`a=p`). Text clears\n(`CSI 2 J` / `CSI 3 J`) do **not** purge the terminal's image store — only\n`encodeKittyDeleteImage` (`a=d,d=I`) does. `ImageBudget` (`components/image.ts`)\nkeeps only the most-recent N images live; demoted images render their text\nfallback and are explicitly purged.\n\n**Rule:** never re-emit full base64 per frame (it pegged RAM and pinned the UI\nthread). Kitty Unicode placeholders are default-on only for kitty/ghostty\n(`PI_NO_KITTY_PLACEHOLDERS` / `PI_KITTY_PLACEHOLDERS`); other Kitty-protocol\nhosts render placeholder cells as literal PUA glyphs, so they fall back to\ndirect `a=p` placement.\n\n---\n\n## 9. The fidelity gate (use it)\n\n`packages/tui/test/render-stress-harness.ts` renders the renderer's **real emitted ANSI** into\na ghostty-web `VirtualTerminal` and asserts viewport fidelity (a scrolled reader\nstays put), background-column fidelity, and scrollback-buffer fidelity, across\nparameterized terminal shapes and randomized op sequences.\n\nThis harness is the structural fix for the whole recurrence: every guess-flip and\nsniffing-gap regression historically **shipped blind and was caught by a user**,\nbecause no automated \"a scrolled-up reader stays pinned across kitty/WT/WSL/\nConPTY\" assertion gated CI. **Before you change the eager/defer lever, a\npredicate, the live-region seam, or width math, run the stress harness and the\ntargeted repro tests** (`packages/tui/test/render-regressions.test.ts`,\n`packages/tui/test/streaming-scrollback-defer.test.ts`, the `issue-*-repro.test.ts` files).\nA change that passes one terminal and one seed is not verified.\n\n---\n\n## 10. Escape hatches (env vars)\n\n| Var | Effect |\n|---|---|\n| `PI_NO_SYNC_OUTPUT=1` | Disable DEC 2026 BSU/ESU wrappers (autowrap discipline stays on). For terminals that advertise but mishandle mode 2026. |\n| `PI_TUI_SYNC_OUTPUT=0\\|1` / `PI_FORCE_SYNC_OUTPUT=1` | Force sync output off / on. |\n| `PI_TUI_ED3_SAFE=1` | Declare the terminal safe for live ED3 (disables `eagerEraseScrollbackRisk`). |\n| `PI_NO_DECCARA` | Disable Kitty DECCARA rectangular-fill optimization (force padded-string fills). |\n| `PI_FORCE_IMAGE_PROTOCOL=kitty\\|iterm2\\|sixel\\|off` | Override image protocol detection. |\n| `PI_NO_KITTY_PLACEHOLDERS=1` / `PI_KITTY_PLACEHOLDERS=1` | Force Kitty Unicode placeholders off / on. |\n| `PI_CLEAR_ON_SHRINK=1` | Clear empty rows when content shrinks (default off). |\n| `PI_HARDWARE_CURSOR=1` | Show the real hardware cursor instead of a rendered one. |\n| `PI_NOTIFICATIONS=off\\|0\\|false` | Suppress terminal notifications. |\n| `PI_DEBUG_REDRAW=1` | Log the chosen render intent per frame to the debug log. |\n| `PI_TUI_DEBUG=1` | Dump per-render diff state under `/tmp/tui`. |\n\n---\n\n## 11. Before you touch the render core — checklist\n\n- [ ] Are you about to emit `CSI 3 J` anywhere other than the destructive\n      `clearScrollback` path? **Stop.**\n- [ ] Does your change trust `isNativeViewportAtBottom() === undefined` as\n      \"at bottom\" during passive streaming? **Stop.**\n- [ ] Did you change one structural-mutation branch without mirroring its\n      sibling (shrink ↔ grow)? **Defer symmetrically.**\n- [ ] Could any frame now emit zero bytes while the viewport is at the bottom?\n      That's invisible-until-resize.\n- [ ] Did you add a terminal by brand instead of by behavior, or skip the\n      SSH-stripped env shape in the test?\n- [ ] Did you run `packages/tui/test/render-stress-harness.ts` + the repro suite across\n      win32/POSIX × unknown/scrolled/at-bottom — not just one terminal?\n- [ ] New probe? Typed sentinel owner + split-reply test.\n- [ ] New width path? Routed through the shared native engine, clamped (never\n      thrown) in the hot path.\n",