@oh-my-pi/pi-coding-agent 15.5.0 → 15.5.2

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

@@ -5,7 +5,7 @@ export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.m
 export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"ERRATA-GPT5-HARMONY.md": "# ERRATA — GPT-5 Harmony-Header Leakage\n\n## 1. The problem\n\nOpenAI frames tool calls in the Harmony chat protocol:\n\n```\n<|start|>assistant<|channel|>commentary to=functions.<NAME><|message|>{ARGS}<|call|>\n```\n\n`<|channel|>commentary to=functions.NAME` is the **routing header** —\ncontrol tokens consumed by the runtime to dispatch the call. These\ntokens never appear as content under normal operation; the runtime\nstrips them.\n\nThe defect: gpt-5 models occasionally emit, **as ordinary content\ninside `{ARGS}`**, the **plain-text shadow** of these routing tokens —\nthe same characters without the `<|…|>` brackets — and continue\nproducing more pseudo-routing structure (channel name, body marker,\nmultilingual spam, fake tool-result framing). The contamination lives\ninside the visible tool argument and is dispatched to the tool as if it\nwere intended content.\n\n**Critical detail.** The actual `<|start|>` / `<|channel|>` /\n`<|message|>` / `<|call|>` special tokens almost never appear in tool\nargs. What leaks is the bracket-less spelling — `analysis to=functions.X\ncode …` — because OpenAI applies a logit mask suppressing the\ncontrol-token IDs inside the args region. The mass that would have gone\nto those special tokens redistributes onto the un-bracketed plain-text\nrepresentation the model also learned. This makes the leak structurally\ninvisible to the routing parser and lands it in the tool input verbatim.\n\nManifestation in tool args (real corpus example):\n\n```\n~      add_function(iso, ctx, ns, \"installSystemChangeObserver\",\n        os_install_system_change_observer);】【\"】【analysis to=functions.edit\n        code above เงินไทยฟรีuser to=functions.edit code …\n```\n\nThe leading code is real and intended. Everything after the first\nnon-Latin token through the next clean structural boundary is corruption.\n\n---\n\n## 2. Observed statistics & failure modes\n\nSource: `~/.omp/stats.db` (`ss_tool_calls`, `ss_assistant_msgs`), through\n2026-05-10. 1.05M tool calls scanned.\n\n### 2.1 Rate\n\n| Model            | Leaks in tool args | Calls   | per million |\n|------------------|-------------------:|--------:|------------:|\n| gpt-5.4          | 37                 | 226,957 | 163         |\n| gpt-5.3-codex    | 17                 | 112,243 | 151         |\n| gpt-5.5          | 2                  |  80,750 |  25         |\n| gpt-5.2-codex    | 0                  |    —    |   —         |\n\nPlus 15 hits in assistant visible text / thinking blobs.\n\n### 2.2 Tool distribution\n\n| Tool                | Hits |\n|---------------------|-----:|\n| `edit`              | 38   |\n| `eval`              | 11   |\n| `report_tool_issue` | 3    |\n| `grep`/`read`/`search`/`yield` | 1 each |\n\nConcentrated in tools with free-form (non-JSON-schema) argument formats.\n\n### 2.3 Leak shape (deterministic)\n\n```\nLEAK         ::= JUNK_PREFIX MARKER CHANNEL_BODY (LEAK)?\nMARKER       ::= \"to=functions.\" TOOL_NAME\nCHANNEL_BODY ::= \" code \" (SPAM | reasoning_prose | fake_tool_output)*\nJUNK_PREFIX  ::= (GLITCH_TOKEN | CHANNEL_WORD | NON_LATIN_RUN | \"}\" | \"】【\")+\n```\n\n**Cascading is common.** Of 96 marker occurrences across 71 contaminated\nrecords, 39 contain ≥2 markers and 7 contain ≥3 — the model emits\nmultiple fake `to=functions.X code …` blocks back-to-back, often with\nfake `code_output\\nCell N:\\n…` framing between them. Once the\nplain-text scaffolding is in the residual stream, the prefix now *looks\nlike* a fresh tool envelope start, so the macro prior over continuations\nkeeps voting for more scaffolding. Self-amplifying.\n\n### 2.4 Glitch tokens\n\nSingle-token identifiers in `o200k_base` whose embeddings appear to be\nnear-init from underrepresentation in post-training. ASCII residue\nimmediately before the marker in the natural corpus:\n\n| Surface string    | Single-token | Token ID | Hits in corpus |\n|-------------------|:-:|---------:|---:|\n| `Japgolly`        | ✅ | 199,745 | 1 |\n| `Jsii`            | ✅ | 114,318 | (subtoken of `Jsii_commentary`) |\n| `Jsii_commentary` | — (3 toks) | — | 2 |\n| `changedFiles`    | — (2 toks) | — | 8 |\n| `RTLU`            | — (2 toks) | — | 3 |\n\n`Japgolly` is in the last 0.13% of the vocabulary — the same family of\nGitHub-corpus residue that produced `SolidGoldMagikarp` in the 2023\nGPT-2 vocabulary (Rumbelow & Watkins). `SolidGoldMagikarp` itself\ntokenizes to 5 tokens in `o200k_base` — that specific token was retired,\nbut the class wasn't.\n\nFor the multi-token entries, the corpus-level signature is the surface\nstring; the underlying glitch trigger is a sub-token (e.g. `Jsii` inside\n`Jsii_commentary`). The detector list (`G` signal) keys on the surface\nstrings.\n\nStable across unrelated sessions. Treated as a high-precision detector\nsignal.\n\n### 2.5 Channel-word leakage\n\n`analysis` (5), `assistant` (5), `commentary` (3), `user` (1) appear\ndirectly preceding `to=`. Always bare words; never `<|channel|>analysis`\nor any other bracketed form. Consistent with §1 — the brackets are\nmasked, the words are not.\n\n### 2.6 Non-Latin spam residue\n\n96 marker hits, by script: CJK 40, Cyrillic 12, Telugu/Kannada/Malayalam\n18, Thai 8, Georgian 7, Armenian 7, Arabic 1. Recurring fragments are\nChinese gambling SEO (`大发时时彩`, `天天中彩票`), Georgian/Abkhaz junk,\nand Thai casino spam — well-known low-quality crawl residue.\n\nThis is the same script distribution observed in the controlled\nreproduction (§7.3), independent of the prompt's natural language.\n\n### 2.7 Failure-mode breakdown for the `edit` tool\n\nThe `edit` tool exists in two variants in the corpus:\n\n| Variant                  | Calls | Recovery |\n|--------------------------|------:|----------|\n| Patch-DSL (`§PATH`/anchor/`«»≔` ops) | 27 | **Recoverable** by op-truncation (§3.3) |\n| JSON-schema (`{path,edits:[…]}`)      | 11 | **Not recoverable** — contamination is escaped *inside* JSON strings, parser accepts it cleanly, content would be written verbatim into source files |\n\nFor Patch-DSL leaks specifically:\n\n- 20/27 cases: contamination on the last input line; nothing follows.\n- 7/27 cases: contamination mid-input; what follows is one of: a\n  duplicate replay of an earlier file/anchor, intended content for a\n  *different* tool call (the model started its next call inline), or\n  pure hallucination. Post-contamination content is never trustworthy.\n\n### 2.8 Mechanism (confirmed)\n\n**Prior collapse from null-embedding glitch tokens, into a\ncontrol-token-masked basin whose mass redistributes onto the\nplain-text shadow of the Harmony protocol.**\n\nStep by step:\n\n1. The model is mid-`{ARGS}` of a Harmony tool call. The runtime applies\n   a logit mask suppressing structural control tokens (`<|channel|>`,\n   `<|message|>`, `<|call|>`, `<|start|>`, `<|end|>`) inside the args\n   region. Without this mask, normal generation would constantly\n   hallucinate envelope-closes; with it, those token IDs have logit\n   `-∞` in args.\n2. A glitch token `g` is sampled. By construction `g` was in the BPE\n   merge corpus but barely in LM/RL training, so its **input embedding\n   `e_g` ≈ near-init noise of small norm**.\n3. At position t+1, the residual update `h_{t+1} ≈ LN(h_t + e_g + Attn +\n   MLP)` is dominated by the prefix-derived terms; the just-emitted-token\n   signal is effectively absent. Generation diversity normally comes\n   from `e_x` steering the residual into different sub-regions —\n   stripped here.\n4. The next-token distribution therefore collapses onto the **conditional\n   prior over continuations of the prefix, with local conditioning\n   removed**. In a tool-calling rollout context, that prior is sharply\n   peaked on Harmony scaffolding (control tokens + routing tokens) —\n   that's what RL trained.\n5. The mask zeros the control-token IDs. Mass redistributes onto the\n   **next-best continuation**: the un-bracketed surface-form spelling of\n   the same protocol (`analysis`, `commentary`, ` to=functions.X`,\n   ` code `). This spelling is unmasked because those characters are\n   ordinary tokens.\n6. Once a few tokens of plain-text scaffolding land in the residual\n   stream, the prefix now resembles a fresh envelope start. The macro\n   prior keeps voting for more scaffolding. Cascading (§2.3) follows.\n7. Multilingual spam after the marker is the same prior-collapse\n   continuation, drawn from the training neighborhood of the glitch\n   token (often ESL/auto-generated multilingual web junk — exactly the\n   crawl residue in §2.6).\n\n**Two corollaries the corpus data demanded but only the experiment\nexplained:**\n\n- **The brackets never appear** (§1, §2.5). The mask is what makes the\n  leak land in plain text instead of as a real envelope-close.\n- **Counterintuitive grammar dependency** (§7.4). The leak is *worse* in\n  formats closest to OpenAI's training distribution. Off-distribution\n  custom grammars dampen the macro-prior basin; the official\n  `*** Begin Patch` format is the strongest collapse target.\n\nThe 2023 SolidGoldMagikarp paper documented mechanism (1)+(2)+(4). The\nnew piece is (5): when constrained decoding masks the natural collapse\ntarget, the mass laundered through the un-masked plain-text shadow\nbecomes a structurally-invisible exfiltration channel.",
 	"ai-schema-normalize.md": "# AI tool-schema normalization\n\n`@oh-my-pi/pi-ai` exposes one unified schema normalizer that providers consume\nbefore tools are sent on the wire. All walkers live in\n`packages/ai/src/utils/schema/normalize.ts`; the operational contract is\n`packages/ai/src/utils/schema/CONSTRAINTS.md`.\n\nThere is no separate `strict-mode.ts` module any more — OpenAI strict-mode\nsanitization, OpenAI Responses `oneOf` rewriting, Google/Vertex/Gemini-CLI\nsanitization, Cloud Code Assist Claude sanitization, and MCP sanitization all\nshare the same option-driven walk.\n\n## Entry points\n\nAll exports live under `@oh-my-pi/pi-ai/utils/schema`:\n\n- `normalizeSchema(value, options)` — generic option-driven walker.\n- `normalizeSchemaForGoogle(value)` — Gemini / Vertex / Gemini CLI.\n- `normalizeSchemaForCCA(value)` — Cloud Code Assist Claude (Antigravity + GCA).\n- `normalizeSchemaForMCP(value)` — MCP inputSchemas before they enter the\n  custom-tool registry. `tool-bridge.ts` runs every MCP `inputSchema` through\n  this dispatcher.\n- `normalizeSchemaForOpenAIResponses(schema)` (alias\n  `sanitizeSchemaForOpenAIResponses`) — rewrites `oneOf` → `anyOf` for the\n  Responses family.\n- `sanitizeSchemaForStrictMode(schema)` and\n  `enforceStrictSchema(schema)` / `tryEnforceStrictSchema(schema)` — the\n  OpenAI strict-mode pipeline (sanitize → enforce). All three are exported\n  from `normalize.ts`.\n- `adaptSchemaForStrict(schema, strict)` from `./adapt` — thin composer that\n  wraps `tryEnforceStrictSchema` for provider call sites and consults\n  `PI_NO_STRICT` (env `PI_NO_STRICT`) for the global bypass.\n\nRemoved in the unified-flow refactor:\n\n- `strict-mode.ts` (merged into `normalize.ts`).\n- `sanitize-google.ts` and `normalize-cca.ts` (replaced by\n  `normalizeSchemaFor*` dispatchers).\n- `StringEnum` helper — use `z.enum([...])` directly; Zod's emitted JSON\n  Schema is already wire-compatible with Google and other providers.\n- `sanitizeSchemaFor{Google,CCA,MCP}` / `prepareSchemaForCCA` — renamed to\n  `normalizeSchemaFor{Google,CCA,MCP}`.\n\n## Dispatcher mapping\n\n| Provider transport(s)                                                | Dispatcher                                   |\n| -------------------------------------------------------------------- | -------------------------------------------- |\n| `openai-completions`, `openai-responses`, `openai-codex-responses`   | `adaptSchemaForStrict` (sanitize + enforce)  |\n| `openai-responses` family (`oneOf` → `anyOf` only)                   | `normalizeSchemaForOpenAIResponses`          |\n| `google-generative-ai`, `google-vertex`, Gemini CLI                  | `normalizeSchemaForGoogle`                   |\n| Cloud Code Assist Claude (Antigravity + GCA, `claude-*` model ids)   | `normalizeSchemaForCCA`                      |\n| MCP `inputSchema` ingestion                                          | `normalizeSchemaForMCP`                      |\n| `anthropic-messages` (native, not CCA)                               | per-provider whitelist in `anthropic.ts`     |\n\nGemini CLI / Antigravity CCA MUST run the full `normalizeSchemaForCCA`\npipeline (not just the first keyword-stripping pass) to keep parity with the\nshared Google Claude path.\n\n## Walk semantics\n\n`normalizeSchema` first upgrades the input to JSON Schema 2020-12, then\nwalks the tree with the option set pinned by the dispatcher. Each node:\n\n1. Inlines `$ref` (see \"Edge cases\" below).\n2. Renames `snake_case` combinator/property keys to camelCase\n   (`any_of` → `anyOf`, etc.; collisions follow python-genai\n   `pop(from)`/`set(to)` semantics — snake_case wins).\n3. Applies the `handle_null_fields` collapse for nullable unions before\n   recursing into children.\n4. Strips keys the target provider does not support, optionally lifting\n   human-meaningful keys (`pattern`, `format`, min/max, `default`,\n   `examples`, ...) into the sibling `description` via the spill formatter\n   (`spill.ts`). Structural/meta keys (`$ref`, `$defs`,\n   `additionalProperties`) are not spilled.\n5. Normalizes type unions (`type: [\"T\", \"null\"]` → `type: \"T\"` + nullable\n   marker on Google, plain `type: \"T\"` on CCA).\n6. Collapses object-only / same-type combiners, optionally lossy-collapses\n   mixed-type combiners (CCA only), and runs the residual-combiner fixpoint.\n7. Validates against AJV 2020 when `validateAndFallback` is set (CCA path)\n   and emits the per-tool fallback `{ \"type\": \"object\", \"properties\": {} }`\n   on residual incompatibility — `type` array, `type: \"null\"`, `nullable`\n   key, or any remaining `anyOf`/`oneOf`/`allOf`.\n\n## OpenAI strict-mode pipeline\n\n`adaptSchemaForStrict(schema, strict)` runs `tryEnforceStrictSchema`,\nwhich composes:\n\n1. **Sanitize** (`sanitizeSchemaForStrictMode`): strips non-structural\n   keywords (`format`, `pattern`, min/max, `examples`, `default`,\n   `if`/`then`/`else`, `not`, `unevaluated*`, `patternProperties`,\n   `dependent*`, `content*`, `min/maxProperties`, `$dynamicRef`, etc.). The\n   `default` value is inlined into the sibling `description` as\n   ` (default: X)` before being dropped, unless `description` already\n   contains `(default:` or no `description` exists.\n2. **Enforce** (`enforceStrictSchema`): every object node gets\n   `additionalProperties: false`, every property goes into `required`, and\n   optional properties become nullable unions\n   (`anyOf: [<original>, { \"type\": \"null\" }]`). Tuple `prefixItems` are\n   strictified recursively.\n\nThe two passes share node-level caches and the same epoch-based cycle\nguard, so a single walk on the wire path normalizes refs, allOf, and\nnullable wrapping consistently. `tryEnforceStrictSchema` is fail-open:\nif anything throws, it returns `{ strict: false, schema: original }` so\ncallers MUST emit `strict: true` only when enforcement actually succeeded.\n\n### Edge cases the strict-mode normalizer handles\n\n- **Local `$ref` inlining.** OpenAI strict mode rejects\n  `{ \"$ref\": \"...\", \"description\": \"...\" }` with sibling keys. The\n  sanitizer pre-resolves local `#/...` refs against the root and merges\n  with **sibling keys winning** over the resolved def — same precedence\n  as `openai-python`'s `_ensure_strict_json_schema`. Recursive refs are\n  guarded by the per-walk epoch.\n- **Single-item `allOf`.** A `{ \"allOf\": [X], ...siblings }` collapses to\n  `{ ...X, ...siblings }` with the inlined entry's keys winning over the\n  original siblings (matches `openai-python`'s `_pydantic.py:79-83`). Multi-\n  item `allOf` is left intact for the downstream validator to reject if\n  needed.\n- **Type-array branches and nullable unions.** When a node has\n  `type: [\"T\", \"U\"]`, the sanitizer emits one variant schema per type,\n  pruning type-specific keywords (e.g. `properties`/`required` only stay on\n  the `object` variant, `items` only on the `array` variant). The shared\n  `description` is **hoisted onto the `anyOf` wrapper** instead of being\n  duplicated on every branch — so a strict nullable union becomes\n  `{ anyOf: [T, { type: \"null\" }], description: \"...\" }`, not\n  `anyOf: [{ ..., description }, { ..., description }]`.\n- **Enum/const without a `type`.** Both sanitize and enforce paths call\n  `inferStrictPrimitiveTypeFromEnumOrConst` to infer the primitive `type`\n  from `enum` / `const` values. Mixed-primitive enums (`[1, \"two\", null]`),\n  enums containing objects/arrays, and non-primitive `const` values\n  (`{a:1}`, `[1,2,3]`) cannot be described by a single `type` keyword and\n  trigger the strict-mode fail-open path — emitting a typeless schema\n  would just be rejected on the wire by OpenAI.\n\n## Performance: static fingerprint cache\n\n`resolveProviderModels` in `packages/ai/src/model-manager.ts` and\n`readModelCache`/`writeModelCache` in `model-cache.ts` cooperate via a\nschema-v3 `static_fingerprint` column on the `model_cache` SQLite table.\n\n- `fingerprintStatic(staticModels)` hashes the static catalog slice\n  (`Bun.hash(JSON.stringify(models))` in base36) and memoizes the result\n  in a per-process `WeakMap` keyed by the array reference. Multiple\n  cold-start arms calling `resolveProviderModels` with the same\n  `staticModels` array pay the JSON+hash cost once.\n- On cache read, if the network fetch is being skipped, the cached row is\n  fresh + authoritative, and the cached `static_fingerprint` matches the\n  current one, `resolveProviderModels` returns the cached models verbatim\n  — the cache already incorporates the same static state, so re-running\n  `mergeDynamicModels(static, cache)` would just rebuild the same objects.\n- `mergeModelSources` and `mergeDynamicModels` short-circuit on\n  empty-source inputs (the common shape after `(static, [])` or for\n  providers without a static catalog), avoiding Map churn entirely.\n\nCache rows written before schema v3 are dropped by the cache-version\ncheck; the column defaults to `''` for any row that survives a version\nupgrade so the fingerprint-equality check naturally fails closed and the\nfull merge re-runs.\n\n## Related\n\n- `docs/models.md` — registry, equivalence, compat flags\n  (`supportsStrictMode`, `toolStrictMode`, `disableStrictTools`).\n- `docs/provider-streaming-internals.md` — how the normalized schemas are\n  used downstream during the provider stream loop.\n- `docs/mcp-server-tool-authoring.md` — MCP `inputSchema` ingestion via\n  `normalizeSchemaForMCP`.\n- `packages/ai/src/utils/schema/CONSTRAINTS.md` — operational contract for\n  every normalization rule.\n",
-	"approval-mode.md": "# Tool approval mode\n\nTool approval has two independent inputs:\n\n1. **Tool declaration** — every tool may declare an `approval` tier:\n   - `read`: reads data or updates UI-only session metadata.\n   - `write`: mutates workspace/session state but does not execute arbitrary code.\n   - `exec`: executes code, shells out, drives a browser, spawns agents, or performs similarly broad actions.\n2. **User policy** — `tools.approval.<toolName>: allow | deny | prompt` overrides the mode for that tool.\n\nTools without an `approval` declaration are treated as `exec`. This is the safe default for MCP and unknown custom tools.\n\n## Modes\n\nConfigure with `tools.approvalMode`:\n\n| Mode | Auto-approves | Prompts for |\n| --- | --- | --- |\n| `always-ask` | `read` | `write`, `exec` |\n| `write` | `read`, `write` | `exec` |\n| `yolo` (default) | `read`, `write`, `exec` | nothing unless a tool declares `override: true` |\n\n`--auto-approve` and `--yolo` force `tools.approvalMode: yolo` for the session. They do **not** bypass tool safety overrides.\n\n## User overrides\n\n`tools.approval` is honored in every mode:\n\n```yaml\ntools:\n  approvalMode: write\n  approval:\n    bash: prompt\n    read: allow\n    mcp__filesystem__delete: deny\n```\n\nResolution per tool call:\n\n1. Compute the tool's approval decision from `tool.approval(args)`; omitted means `exec`.\n2. If the decision has `override: true`:\n   - `tools.approval.<tool>: deny` blocks the call.\n   - every other policy prompts, even in `yolo`.\n3. Otherwise, a valid `tools.approval.<tool>` value wins.\n4. Otherwise, the active mode auto-approves or prompts by tier.\n\nInvalid policy values are ignored and fall back to the tool tier/mode decision.\n\n## Safety overrides\n\nA tool can force a prompt with object-form approval:\n\n```ts\napproval: { tier: \"exec\", override: true, reason: \"Critical pattern detected\" }\n```\n\n`bash` uses this for critical destructive patterns such as `rm -rf /`, fork bombs, remote-fetch-then-execute, writes to `/etc/passwd`, and host shutdown commands. These prompt even in `yolo`; in non-interactive/headless sessions they fail instead of running unattended.\n\n## Per-tool prompt details\n\nTools can add approval-prompt body lines with `formatApprovalDetails(args)`. The standard prompt includes:\n\n- `Allow tool: <name>`\n- `Origin: MCP server tool` for unannotated `mcp__...` tools\n- `Reason: <reason>` when the tool decision supplies one\n- tool-specific details such as command, path, code, browser action, or subagent assignment\n\n## Defining approval on tools\n\nBuilt-in and custom tools share the same shape:\n\n```ts\nexport type ToolTier = \"read\" | \"write\" | \"exec\";\nexport type ToolApprovalDecision = ToolTier | { tier: ToolTier; reason?: string; override?: boolean };\nexport type ToolApproval = ToolApprovalDecision | ((args: unknown) => ToolApprovalDecision);\n\napproval?: ToolApproval;\nformatApprovalDetails?: (args: unknown) => string | string[] | undefined;\n```\n\nExamples:\n\n```ts\napproval: \"read\"\n\napproval: args => LSP_READONLY_ACTIONS.has(args.action) ? \"read\" : \"write\"\n\napproval: args => isCritical(args.command)\n  ? { tier: \"exec\", override: true, reason: \"Critical pattern detected\" }\n  : \"exec\"\n```\n\n## Subagents\n\nSubagents run headless with `tools.approvalMode: yolo` so they do not stall waiting for UI. The parent `task` approval is the authorization boundary. Tool-level safety overrides still apply; a critical override inside a headless subagent fails rather than running without confirmation.\n",
+	"approval-mode.md": "# Tool approval mode\n\nTool approval has two independent inputs:\n\n1. **Tool declaration** — every tool may declare an `approval` tier:\n   - `read`: reads data or updates UI-only session metadata.\n   - `write`: mutates workspace/session state but does not execute arbitrary code.\n   - `exec`: executes code, shells out, drives a browser, spawns agents, or performs similarly broad actions.\n2. **User policy** — `tools.approval.<toolName>: allow | deny | prompt` overrides the mode for that tool.\n\nTools without an `approval` declaration are treated as `exec`. This is the safe default for MCP and unknown custom tools.\n\n## Modes\n\nConfigure with `tools.approvalMode`:\n\n## Modes\n\n| Mode | Auto-approves | Prompts for |\n| --- | --- | --- |\n| `always-ask` | `read` | `write`, `exec` |\n| `write` | `read`, `write` | `exec` |\n| `yolo` (default) | `read`, `write`, `exec` | none |\n\n`--auto-approve` and `--yolo` force `tools.approvalMode: yolo` for the session.\n\n## User overrides\n\n`tools.approval` is honored in every mode:\n\n```yaml\ntools:\n  approvalMode: write\n  approval:\n    bash: prompt\n    read: allow\n    mcp__filesystem__delete: deny\n```\n\nResolution per tool call:\n\n1. Compute the tool's approval decision from `tool.approval(args)`; omitted means `exec`.\n2. A user policy in `tools.approval.<tool>` is always applied.\n3. In `yolo` mode, with no user policy, the call is auto-approved.\n4. In non-yolo modes, if the tool sets `override: true`, `deny` is blocked and all other cases prompt.\n5. Otherwise, the active mode auto-approves or prompts by tier.\n\nInvalid policy values are ignored and fall back to the tool tier/mode decision.\n\n## Safety overrides\n\nA tool can force a prompt with object-form approval:\n\n```ts\napproval: { tier: \"exec\", override: true, reason: \"Critical pattern detected\" }\n```\n\n `bash` uses this for critical destructive patterns such as `rm -rf /`, fork bombs, remote-fetch-then-execute, writes to `/etc/passwd`, and host shutdown commands. These surface as `reason` in the approval prompt, but in `yolo` mode they are auto-approved unless a user policy for the tool is set to `prompt` or `deny`.\n\n## Per-tool prompt details\n\nTools can add approval-prompt body lines with `formatApprovalDetails(args)`. The standard prompt includes:\n\n- `Allow tool: <name>`\n- `Origin: MCP server tool` for unannotated `mcp__...` tools\n- `Reason: <reason>` when the tool decision supplies one\n- tool-specific details such as command, path, code, browser action, or subagent assignment\n\n## Defining approval on tools\n\nBuilt-in and custom tools share the same shape:\n\n```ts\nexport type ToolTier = \"read\" | \"write\" | \"exec\";\nexport type ToolApprovalDecision = ToolTier | { tier: ToolTier; reason?: string; override?: boolean };\nexport type ToolApproval = ToolApprovalDecision | ((args: unknown) => ToolApprovalDecision);\n\napproval?: ToolApproval;\nformatApprovalDetails?: (args: unknown) => string | string[] | undefined;\n```\n\nExamples:\n\n```ts\napproval: \"read\"\n\napproval: args => LSP_READONLY_ACTIONS.has(args.action) ? \"read\" : \"write\"\n\napproval: args => isCritical(args.command)\n  ? { tier: \"exec\", override: true, reason: \"Critical pattern detected\" }\n  : \"exec\"\n```\n\n## Subagents\n\nSubagents run headless with `tools.approvalMode: yolo` so they do not stall waiting for UI. The parent `task` approval is the authorization boundary. User `tools.approval.<tool>` settings continue to control whether a tool is allowed, prompted, or blocked.\n",
 	"auth-broker-gateway.md": "# Auth Broker and Auth Gateway\n\nThe auth broker and auth gateway are two cooperating HTTP services that move OAuth refresh tokens and provider access tokens off developer laptops and into a single broker host.\n\n- **`omp auth-broker serve`** holds the canonical SQLite credential vault, performs OAuth refreshes, and exposes a small REST API (`/v1/snapshot`, `/v1/credential/:id/refresh`, `/v1/credential/:id/disable`, `/v1/credential`, `/v1/usage`, `/v1/healthz`).\n- **`omp auth-gateway serve`** is a forward-proxy. It accepts OpenAI Chat Completions, Anthropic Messages, and OpenAI Responses requests, injects the broker-resolved access token, and forwards the bytes to the real provider. Clients (containerised omp, llm-git, the macOS usage widget, …) never see the access token.\n\nTransport security between operator, broker, and gateway is delegated to the operator (Tailscale / Wireguard / reverse proxy + TLS). Every endpoint except `/v1/healthz` (broker) and `/healthz` (gateway) requires a bearer token.\n\nSource: `packages/ai/src/auth-broker/`, `packages/ai/src/auth-gateway/`, `packages/coding-agent/src/cli/auth-broker-cli.ts`, `packages/coding-agent/src/cli/auth-gateway-cli.ts`, `packages/coding-agent/src/session/auth-broker-config.ts`.\n\n## Data flow\n\n```\n                ┌────────────────────────────────────────────────────────────┐\n                │ broker host                                                │\n                │                                                            │\n  developer ──▶ │  ┌──────────────────────────┐    ┌────────────────────┐    │\n  laptop /      │  │  omp auth-broker serve   │◀──▶│  SQLite agent.db    │    │\n  CI / robomp   │  │  - holds refresh tokens  │    │  (canonical writer)│    │\n                │  │  - background refresher  │    └────────────────────┘    │\n                │  │  /v1/{snapshot,refresh,…}│                              │\n                │  └─────────┬────────────────┘                              │\n                │            │  bearer ($CONFIG_DIR/auth-broker.token)       │\n                │            ▼                                               │\n                │  ┌──────────────────────────┐                              │\n                │  │  omp auth-gateway serve  │  RemoteAuthCredentialStore   │\n                │  │  /v1/{chat,messages,…}   │  pulls /v1/snapshot at boot, │\n                │  │  /v1/usage, /v1/models   │  refreshes credentials by id │\n                │  └─────────┬────────────────┘  via the broker on expiry    │\n                └────────────┼───────────────────────────────────────────────┘\n                             │  bearer ($CONFIG_DIR/auth-gateway.token)\n                             ▼\n                  unauthenticated clients\n                  (llm-git, macOS widget, robomp containers, IDE plugins, …)\n                                │\n                                ▼ same path is forwarded with Authorization\n                  api.anthropic.com / api.openai.com / …\n```\n\nThe broker is the only writer of OAuth refresh tokens. Clients (including the gateway itself) load a redacted snapshot in which every `refresh` field has been replaced with `REMOTE_REFRESH_SENTINEL`; when an access token expires the client calls `POST /v1/credential/:id/refresh` and the broker performs the refresh server-side. `RemoteAuthCredentialStore` rejects any local code path that tries to write through it, with an error pointing at `omp auth-broker login` / `omp auth-broker logout`.\n\n## auth-broker\n\n### CLI\n\n```\nomp auth-broker serve     [--bind=host:port]                    # boot the broker\nomp auth-broker token     [--regenerate] [--json]               # print or rotate the bearer token\nomp auth-broker login     [<provider>] [--via=user@host] [--dry-run]\nomp auth-broker logout    [<provider>]\nomp auth-broker list      [--json]\nomp auth-broker import    <file|dir> [--provider=<id>] [--include-disabled] [--dry-run] [--json]\nomp auth-broker migrate   --from-local [--dry-run] [--json]\nomp auth-broker status    [--json]\n```\n\n- `serve` opens the local SQLite store at `getAgentDbPath()` and binds an HTTP listener (default `127.0.0.1:8765`). On startup a token is ensured at `<config-dir>/auth-broker.token` (mode `0600`, `0700` parent dir). The background refresher refreshes any OAuth credential whose `expires - Date.now() < refreshSkewMs` (default 5 min) every `refreshIntervalMs` (default 60 s).\n- `token` prints the cached bearer or generates a new one. `--regenerate` rotates it.\n- `login [<provider>]` runs the per-provider OAuth flow locally — when no provider is supplied, it falls back to an interactive numbered picker. With `--via=user@host` it shells out `ssh -L <callback-port>:127.0.0.1:<callback-port> user@host omp auth-broker login <provider>` so the OAuth callback hits the local browser but the credential is written on the broker host (`--via` requires `<provider>`). Built-in callback ports: `anthropic:54545`, `openai-codex:1455`, `google-gemini-cli:8085`, `google-antigravity:51121`, `gitlab-duo:8080`. The OAuth dance is driven in-process via `AuthStorage.login()` — there is no longer a `pi-ai` bin to spawn.\n- `logout [<provider>]` deletes every credential row for `<provider>`. With no argument it shows an interactive numbered picker of currently-stored providers.\n- `list` enumerates every registered OAuth provider id/name (the union of built-ins + `registerOAuthProvider` custom providers). `--json` emits a machine-readable array.\n- `import <file|dir>` imports CLIProxyAPI-style JSON credentials into the local SQLite store. Maps `type` field → omp provider (`claude → anthropic`, `codex → openai-codex`, `gemini → google-gemini-cli`, `antigravity → google-antigravity`, `gemini-cli → google-gemini-cli`).\n- `migrate --from-local` walks the local SQLite store + env-derived credentials and idempotently uploads them to the configured broker (`POST /v1/credential`).\n- `status` health-pings the configured remote broker.\n\n### Endpoints\n\n| Method | Path | Auth | Purpose |\n| ------ | ---- | ---- | ------- |\n| `GET`  | `/v1/healthz` | none | Liveness + version |\n| `GET`  | `/v1/snapshot` | bearer | Redacted snapshot (refresh tokens replaced by sentinel) |\n| `POST` | `/v1/credential` | bearer | Upsert one OAuth or API-key credential |\n| `POST` | `/v1/credential/:id/refresh` | bearer | Force-refresh one OAuth credential |\n| `POST` | `/v1/credential/:id/disable` | bearer | Disable one credential with a recorded cause |\n| `GET`  | `/v1/usage` | bearer | Aggregate `UsageReport[]` across credentials |\n\nRequests use `Authorization: Bearer <token>`. The server compares against an in-memory token allow-list; the gateway’s implementation uses a timing-safe comparison.\n\n### Background refresher\n\n`AuthBrokerRefresher` iterates active OAuth credentials at `refreshIntervalMs` cadence and refreshes any within `refreshSkewMs` of expiry. Refreshes are single-flighted per credential id so a slow refresh cannot be retriggered. The refresher distinguishes:\n\n- **definitive failures** (`invalid_grant`, `invalid_token`, `revoked`, unauthorized refresh-token, 401/403 not from a network blip) — credentials are passed to `AuthStorage.disableCredentialById(id, cause)` so the next snapshot pull surfaces a clean delete on the client;\n- **transient failures** (timeout / ECONNREFUSED / fetch failed) — left in place for the next sweep.\n\n## auth-gateway\n\n### CLI\n\n```\nomp auth-gateway serve   [--bind=host:port] [--no-auth]\nomp auth-gateway token   [--regenerate] [--json]\nomp auth-gateway status  [--json]\n```\n\n- `serve` requires `OMP_AUTH_BROKER_URL` (or `auth.broker.url` in `config.yml`) — the gateway is itself a broker client. It calls `AuthBrokerClient.fetchSnapshot()`, wraps it in `RemoteAuthCredentialStore`, and constructs an `AuthStorage` that resolves access tokens through the broker. Default bind is `127.0.0.1:4000`. The gateway token is stored at `<config-dir>/auth-gateway.token` (`0600`); `--no-auth` disables the bearer check entirely (loopback-only use).\n- `token` / `status` mirror the broker’s equivalents.\n\n### Endpoints\n\n| Method | Path | Auth | Purpose |\n| ------ | ---- | ---- | ------- |\n| `GET`  | `/healthz` | none | Liveness + version |\n| `GET`  | `/v1/usage` | bearer | Aggregate `UsageReport[]` (proxied through `AuthStorage`) |\n| `GET`  | `/v1/models` | bearer | Bundled-model catalog filtered to providers with credentials |\n| `POST` | `/v1/chat/completions` | bearer | OpenAI Chat Completions wire format |\n| `POST` | `/v1/messages` | bearer | Anthropic Messages wire format |\n| `POST` | `/v1/responses` | bearer | OpenAI Responses wire format |\n\nThe model id is read from the top-level `model` field. The gateway picks the first bundled `Model<Api>` matching that id and:\n\n- **Passthrough fast-path** — when the inbound wire format matches the model’s native API (`openai-chat → openai-completions`, `anthropic-messages → anthropic-messages`, `openai-responses → openai-responses`), the request body is forwarded byte-for-byte with the client `Authorization`/`x-api-key` stripped and replaced by `Authorization: Bearer <resolved-access-token>`. Provider-specific fields (`cache_control`, `service_tier`, tool-choice extensions, …) flow through unmodified. Hop-by-hop headers (RFC 7230) plus `Content-Encoding`/`Content-Length` are stripped from the upstream response.\n- **Translate path** — when the inbound format and the resolved model’s API differ (e.g. `/v1/chat/completions` targeting an Anthropic model, or `/v1/responses` targeting `openai-codex-responses` which runs over a websocket transport), the request is parsed against the wire schema, rebuilt into an omp `Context`, dispatched through `streamSimple()`, and re-encoded back to the inbound format (SSE for streamed responses).\n\n`idleTimeout` on the underlying `Bun.serve` is set to `255 s` so long thinking-budget calls do not get killed by Bun’s default idle timeout.\n\n## Usage cache: server-side 5-min jitter + client-side 15 s single-flight\n\nTwo layers cache the aggregate provider-usage report. Both are intentional and stacked.\n\n### Server-side cache (broker `AuthStorage`)\n\n`AuthStorage` caches each credential’s `UsageReport` in the broker’s SQLite store at a **5-minute per-credential TTL with ±25 % jitter**. Anthropic and OpenAI rate-limit `/usage` aggressively per source IP, and a synchronized 5-credential fan-out trips 429s every cycle; the jitter decorrelates refresh times within a few cycles. On fetch failure the store keeps the **last-good** report for up to 24 h with a short jittered re-poll window — so a transient upstream blip never blanks out the widget.\n\nConstants: `USAGE_REPORT_TTL_MS = 5 * 60_000`, `USAGE_LAST_GOOD_RETENTION_MS = 24 * 60 * 60_000` (`packages/ai/src/auth-storage.ts`).\n\n### Client-side single-flight (`RemoteAuthCredentialStore`)\n\nWhen the gateway (or any other broker client) calls `fetchUsageReports()` / `getUsageReport(provider, credential)`, `RemoteAuthCredentialStore` coalesces concurrent calls into a single `GET /v1/usage` round-trip and caches the result for **15 s** in memory.\n\n- `USAGE_CACHE_TTL_MS = 15_000` (`packages/ai/src/auth-broker/remote-store.ts`).\n- A single `#usageInflight` promise is shared across all callers; a per-caller `AbortSignal` is **raced** against the shared promise, not threaded into it, so one caller’s abort never cascades into a peer’s in-flight request.\n- On fetch failure the rejected promise is logged and the awaited value is `null` — callers (`AuthStorage.fetchUsageReports`, `#getUsageReport`) treat a `null` report as \"no usage signal for this cycle\" and proceed without it. **This is the 15 s TTL fallback**: the client absorbs transient broker outages by suppressing the error, returning `null` to ranking, and re-attempting after the 15 s window.\n\nThe 15 s client window deliberately sits below the broker’s 5 min server cache, so almost every client poll is served from the broker’s already-cached value; the client cache exists to absorb the parallel fan-out generated by `AuthStorage.#rankOAuthSelections` into a single broker round-trip.\n\n## Operator opt-in\n\nThe broker is **off** unless `OMP_AUTH_BROKER_URL` (or `auth.broker.url` in `config.yml`) is set. When set, `discoverAuthStorage` in `packages/coding-agent/src/sdk.ts` swaps the local SQLite credential store for `RemoteAuthCredentialStore` and every API call resolves credentials through the broker.\n\n### Environment variables\n\n| Variable | Purpose | Required when |\n| -------- | ------- | ------------- |\n| `OMP_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`). Selecting this puts the client in broker mode — local SQLite is bypassed. | Any time the omp client should resolve credentials through a broker (and required by `omp auth-gateway serve`). |\n| `OMP_AUTH_BROKER_TOKEN` | Bearer token used for every broker endpoint except `/v1/healthz`. | When `OMP_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`. |\n\nResolution order in `resolveAuthBrokerConfig()`:\n\n1. `OMP_AUTH_BROKER_URL` env (else `auth.broker.url` from `config.yml`, with `$ENV_NAME` resolution);\n2. `OMP_AUTH_BROKER_TOKEN` env (else `auth.broker.token` from `config.yml`, else `<config-dir>/auth-broker.token`);\n3. URL set but no token resolvable → hard error pointing at the token file path.\n\nThe gateway has no dedicated env vars — it inherits `OMP_AUTH_BROKER_*` because it is itself a broker client.\n\n### `config.yml` keys\n\n| Key | Default | Purpose |\n| --- | ------- | ------- |\n| `auth.broker.url`   | unset | Same as `OMP_AUTH_BROKER_URL`; env wins. Hidden from the settings UI. |\n| `auth.broker.token` | unset | Same as `OMP_AUTH_BROKER_TOKEN`; env wins. Values may be the literal token or `$ENV_NAME` to indirect through env. |\n\n### Token files\n\n| Path | Owner | Mode |\n| ---- | ----- | ---- |\n| `<config-dir>/auth-broker.token`  | `omp auth-broker serve` (created at first start) | `0600` in a `0700` parent dir |\n| `<config-dir>/auth-gateway.token` | `omp auth-gateway serve` (skipped under `--no-auth`) | `0600` in a `0700` parent dir |\n\n`<config-dir>` resolves to `~/.omp/` (respecting `PI_CONFIG_DIR`).\n\n## Interaction with the local API-key resolution order\n\nThe broker only owns OAuth credentials and provider-API-key credentials that were uploaded to it. The standard credential ladder in `models.md` (`Auth and API key resolution order`) is preserved, with one addition committed alongside the gateway:\n\n- `AuthStorage.setConfigApiKey / removeConfigApiKey / clearConfigApiKeys` let a `models.yml` `apiKey` beat a stored OAuth token **without** overriding an explicit `--api-key`. This is what allows a broker-resolved OAuth credential to be reliably shadowed by a per-environment `models.yml` config key when both are present.\n\n## See also\n\n- [`secrets.md`](./secrets.md) — secret obfuscation around tokens that *do* leak through (e.g. `OMP_AUTH_BROKER_TOKEN` in shell output).\n- [`models.md`](./models.md) — provider auth resolution order; the broker plugs in at layers 2–3 (stored credentials).\n- [`environment-variables.md`](./environment-variables.md) — full env reference including `OMP_AUTH_BROKER_URL` / `OMP_AUTH_BROKER_TOKEN`.\n",
 	"bash-tool-runtime.md": "# Bash tool runtime\n\nThis document describes the **`bash` tool** runtime path used by agent tool calls, from command normalization to execution, truncation/artifacts, and rendering.\n\nIt also calls out where behavior diverges in interactive TUI, print mode, RPC mode, and user-initiated bang (`!`) shell execution.\n\n## Scope and runtime surfaces\n\nThere are two different bash execution surfaces in coding-agent:\n\n1. **Tool-call surface** (`toolName: \"bash\"`): used when the model calls the bash tool.\n   - Entry point: `BashTool.execute()`.\n   - Parameters include `command`, optional `env`, `timeout`, `cwd`, `head`, `tail`, `pty`, and, when `async.enabled` is true, `async`.\n2. **User bang-command surface** (`!cmd` from interactive input or RPC `bash` command): session-level helper path.\n   - Entry point: `AgentSession.executeBash()`.\n\nBoth eventually use `executeBash()` in `src/exec/bash-executor.ts` for non-PTY execution, but only the tool-call path runs normalization/interception, optional managed background-job handling, and tool renderer logic.\n\n## End-to-end tool-call pipeline\n\n## 1) Input handling and parameter merge\n\n`BashTool.execute()` currently handles input before execution as follows:\n\n- validates optional `env` names against shell-variable syntax,\n- extracts a leading `cd <path> && ...` into `cwd` when `cwd` was not supplied,\n- rejects `async: true` when `async.enabled` is false,\n- uses only explicit `head`/`tail` tool args for post-run filtering.\n\n`normalizeBashCommand()` still exists in `src/tools/bash-normalize.ts`, but `BashTool.execute()` does not call it in the current source. Trailing shell pipes such as `| head -n 50` remain part of the shell command unless the caller uses the structured `head`/`tail` args.\n\n## 2) Optional interception (blocked-command path)\n\nIf `bashInterceptor.enabled` is true, `BashTool` loads rules from settings and runs `checkBashInterception()` against the normalized command.\n\nInterception behavior:\n\n- command is blocked **only** when:\n  - regex rule matches, and\n  - the suggested tool is present in `ctx.toolNames`.\n- invalid regex rules are silently skipped.\n- on block, `BashTool` throws `ToolError` with message:\n  - `Blocked: ...`\n  - original command included.\n\nDefault rule patterns (defined in code) target common misuses:\n\n- file readers (`cat`, `head`, `tail`, ...)\n- search tools (`grep`, `rg`, ...)\n- file finders (`find`, `fd`, ...)\n- in-place editors (`sed -i`, `perl -i`, `awk -i inplace`)\n- shell redirection writes (`echo ... > file`, heredoc redirection)\n\n### Caveat\n\n`InterceptionResult` includes `suggestedTool`, but `BashTool` currently surfaces only the message text (no structured suggested-tool field in `details`).\n\n## 3) CWD validation and timeout clamping\n\n`cwd` is resolved relative to session cwd (`resolveToCwd`), then validated via `stat`:\n\n- missing path -> `ToolError(\"Working directory does not exist: ...\")`\n- non-directory -> `ToolError(\"Working directory is not a directory: ...\")`\n\nTimeout is clamped to `[1, 3600]` seconds and converted to milliseconds.\n\n## 4) Artifact allocation\n\nBefore execution, the tool allocates an artifact path/id (best-effort) for truncated output storage.\n\n- artifact allocation failure is non-fatal (execution continues without artifact spill file),\n- artifact id/path are passed into execution path for full-output persistence on truncation.\n\n## 5) PTY vs non-PTY execution selection\n\n`BashTool` chooses PTY execution only when all are true:\n\n- tool input `pty === true`\n- `PI_NO_PTY !== \"1\"`\n- tool context has UI (`ctx.hasUI === true` and `ctx.ui` set)\n\nOtherwise it uses non-interactive `executeBash()`.\n\nThat means print mode and non-UI RPC/tool contexts always use non-PTY.\n\n## Non-interactive execution engine (`executeBash`)\n\n## Shell session reuse model\n\n`executeBash()` caches native `Shell` instances in a process-global map keyed by:\n\n- shell path,\n- configured command prefix,\n- snapshot path,\n- serialized shell env,\n- optional agent session key.\n\nSession-level bang-command executions pass `sessionKey: this.sessionId`.\n\nTool-call executions pass `sessionKey: this.session.getSessionId?.()`, when available. In both surfaces, a session key isolates shell reuse per session; without one, reuse falls back to shell config/snapshot/env.\n\n## Shell config and snapshot behavior\n\nAt each call, executor loads settings shell config (`shell`, `env`, optional `prefix`).\n\nIf selected shell includes `bash`, it attempts `getOrCreateSnapshot()`:\n\n- snapshot captures aliases/functions/options from user rc,\n- snapshot creation is best-effort,\n- failure falls back to no snapshot.\n\nIf `prefix` is configured, command becomes:\n\n```text\n<prefix> <command>\n```\n\n## Streaming and cancellation\n\n`Shell.run()` streams chunks to `OutputSink` and optional `onChunk` callback.\n\nCancellation:\n\n- aborted signal triggers `shellSession.abort(...)`,\n- timeout from native result is mapped to `cancelled: true` + annotation text,\n- explicit cancellation similarly returns `cancelled: true` + annotation.\n\nNo exception is thrown inside executor for timeout/cancel; it returns structured `BashResult` and lets caller map error semantics.\n\n## Interactive PTY path (`runInteractiveBashPty`)\n\nWhen PTY is enabled, tool runs `runInteractiveBashPty()` which opens an overlay console component and drives a native `PtySession`.\n\nBehavior highlights:\n\n- xterm-headless virtual terminal renders viewport in overlay,\n- keyboard input is normalized (including Kitty sequences and application cursor mode handling),\n- `esc` while running kills the PTY session,\n- terminal resize propagates to PTY (`session.resize(cols, rows)`).\n\nEnvironment hardening defaults are injected for unattended runs:\n\n- pagers disabled (`PAGER=cat`, `GIT_PAGER=cat`, etc.),\n- editor prompts disabled (`GIT_EDITOR=true`, `EDITOR=true`, ...),\n- terminal/auth prompts reduced (`GIT_TERMINAL_PROMPT=0`, `SSH_ASKPASS=/usr/bin/false`, `CI=1`),\n- package-manager/tool automation flags for non-interactive behavior.\n\nPTY output is normalized (`CRLF`/`CR` to `LF`, `sanitizeText`) and written into `OutputSink`, including artifact spill support.\n\nOn PTY startup/runtime error, sink receives `PTY error: ...` line and command finalizes with undefined exit code.\n\n## Output handling: streaming, truncation, artifact spill\n\nBoth PTY and non-PTY paths use `OutputSink`.\n\n## OutputSink semantics\n\n- keeps an in-memory UTF-8-safe tail buffer (`DEFAULT_MAX_BYTES`, currently 50KB),\n- tracks total bytes/lines seen,\n- if artifact path exists and output overflows (or file already active), writes full stream to artifact file,\n- when memory threshold overflows, trims in-memory buffer to tail (UTF-8 boundary safe),\n- marks `truncated` when overflow/file spill occurs.\n\n`dump()` returns:\n\n- `output` (possibly annotated prefix),\n- `truncated`,\n- `totalLines/totalBytes`,\n- `outputLines/outputBytes`,\n- `artifactId` if artifact file was active.\n\n### Long-output caveat\n\nRuntime truncation is byte-threshold based in `OutputSink` (50KB default). It does not enforce a hard 2000-line cap in this code path.\n\n## Live tool updates and async jobs\n\nFor non-PTY foreground execution, `BashTool` uses a separate `TailBuffer` for partial updates and emits `onUpdate` snapshots while command is running.\n\nFor PTY execution, live rendering is handled by custom UI overlay, not by `onUpdate` text chunks.\n\nWhen `async.enabled` is true and the call passes `async: true`, `BashTool` starts a managed bash job, returns a running job result with a job id, and stores completion through the session managed-job path. Auto-backgrounding can also start this path after `bash.autoBackground.thresholdMs`.\n\n## Result shaping, metadata, and error mapping\n\nAfter execution:\n\n1. `cancelled` handling:\n   - if abort signal is aborted -> throw `ToolAbortError` (abort semantics),\n   - else -> throw `ToolError` (treated as tool failure).\n2. PTY `timedOut` -> throw `ToolError`.\n3. apply head/tail filters to final output text (`applyHeadTail`, head then tail).\n4. empty output becomes `(no output)`.\n5. attach truncation metadata via `toolResult(...).truncationFromSummary(result, { direction: \"tail\" })`.\n6. exit-code mapping:\n   - missing exit code -> `ToolError(\"... missing exit status\")`\n   - non-zero exit -> `ToolError(\"... Command exited with code N\")`\n   - zero exit -> success result.\n\nSuccess payload structure:\n\n- `content`: text output,\n- `details.meta.truncation` when truncated, including:\n  - `direction`, `truncatedBy`, total/output line+byte counts,\n  - `shownRange`,\n  - `artifactId` when available.\n\nBecause built-in tools are wrapped with `wrapToolWithMetaNotice()`, truncation notice text is appended to final text content automatically (for example: `Full: artifact://<id>`).\n\n## Rendering paths\n\n## Tool-call renderer (`bashToolRenderer`)\n\n`bashToolRenderer` is used for tool-call messages (`toolCall` / `toolResult`):\n\n- collapsed mode shows visual-line-truncated preview,\n- expanded mode shows all currently available output text,\n- warning line includes truncation reason and `artifact://<id>` when truncated,\n- timeout value (from args) is shown in footer metadata line.\n\n### Caveat: full artifact expansion\n\n`BashRenderContext` has `isFullOutput`, but current renderer context builder does not set it for bash tool results. Expanded view still uses the text already in result content (tail/truncated output) unless another caller provides full artifact content.\n\n## User bang-command component (`BashExecutionComponent`)\n\n`BashExecutionComponent` is for user `!` commands in interactive mode (not model tool calls):\n\n- streams chunks live,\n- collapsed preview keeps last 20 logical lines,\n- line clamp at 4000 chars per line,\n- shows truncation + artifact warnings when metadata is present,\n- marks cancelled/error/exit state separately.\n\nThis component is wired by `CommandController.handleBashCommand()` and fed from `AgentSession.executeBash()`.\n\n## Mode-specific behavior differences\n\n| Surface                        | Entry path                                            | PTY eligible                                                         | Live output UX                                                           | Error surfacing                                  |\n| ------------------------------ | ----------------------------------------------------- | -------------------------------------------------------------------- | ------------------------------------------------------------------------ | ------------------------------------------------ |\n| Interactive tool call          | `BashTool.execute`                                    | Yes, when `pty=true` and UI exists and `PI_NO_PTY!=1`                | PTY overlay (interactive) or streamed tail updates                       | Tool errors become `toolResult.isError`          |\n| Print mode tool call           | `BashTool.execute`                                    | No (no UI context)                                                   | No TUI overlay; output appears in event stream/final assistant text flow | Same tool error mapping                          |\n| RPC tool call (agent tooling)  | `BashTool.execute`                                    | Usually no UI -> non-PTY                                             | Structured tool events/results                                           | Same tool error mapping                          |\n| Interactive bang command (`!`) | `AgentSession.executeBash` + `BashExecutionComponent` | No (uses executor directly)                                          | Dedicated bash execution component                                       | Controller catches exceptions and shows UI error |\n| RPC `bash` command             | `rpc-mode` -> `session.executeBash`                   | No                                                                   | Returns `BashResult` directly                                            | Consumer handles returned fields                 |\n\n## Operational caveats\n\n- Interceptor only blocks commands when suggested tool is currently available in context.\n- If artifact allocation fails, truncation still occurs but no `artifact://` back-reference is available.\n- Shell session cache has no explicit eviction in this module; lifetime is process-scoped.\n- PTY and non-PTY timeout surfaces differ:\n  - PTY exposes explicit `timedOut` result field,\n  - non-PTY maps timeout into `cancelled + annotation` summary.\n\n## Implementation files\n\n- [`src/tools/bash.ts`](../packages/coding-agent/src/tools/bash.ts) — tool entrypoint, input handling/interception, async and PTY/non-PTY selection, result/error mapping, bash tool renderer.\n- [`src/tools/bash-normalize.ts`](../packages/coding-agent/src/tools/bash-normalize.ts) — post-run head/tail filtering; also contains an unused command-normalization helper.\n- [`src/tools/bash-interceptor.ts`](../packages/coding-agent/src/tools/bash-interceptor.ts) — interceptor rule matching and blocked-command messages.\n- [`src/exec/bash-executor.ts`](../packages/coding-agent/src/exec/bash-executor.ts) — non-PTY executor, shell session reuse, cancellation wiring, output sink integration.\n- [`src/tools/bash-interactive.ts`](../packages/coding-agent/src/tools/bash-interactive.ts) — PTY runtime, overlay UI, input normalization, non-interactive env defaults.\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts) — `OutputSink`, `TailBuffer`, truncation/artifact spill, and summary metadata.\n- [`src/tools/output-meta.ts`](../packages/coding-agent/src/tools/output-meta.ts) — truncation metadata shape + notice injection wrapper.\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — session-level `executeBash`, message recording, abort lifecycle.\n- [`src/modes/components/bash-execution.ts`](../packages/coding-agent/src/modes/components/bash-execution.ts) — interactive `!` command execution component.\n- [`src/modes/controllers/command-controller.ts`](../packages/coding-agent/src/modes/controllers/command-controller.ts) — wiring for interactive `!` command UI stream/update completion.\n- [`src/modes/rpc/rpc-mode.ts`](../packages/coding-agent/src/modes/rpc/rpc-mode.ts) — RPC `bash` and `abort_bash` command surface.\n- [`src/internal-urls/artifact-protocol.ts`](../packages/coding-agent/src/internal-urls/artifact-protocol.ts) — `artifact://<id>` resolution.\n",
 	"blob-artifact-architecture.md": "# Blob and artifact storage architecture\n\nThis document describes how coding-agent stores large/binary payloads outside session JSONL, how truncated tool output is persisted, and how internal URLs (`artifact://`, `agent://`) resolve back to stored data.\n\n## Why two storage systems exist\n\nThe runtime uses two different persistence mechanisms for different data shapes:\n\n- **Content-addressed blobs** (`blob:sha256:<hash>`): global storage used to externalize large image base64 payloads and provider image data URLs from persisted session entries.\n- **Session-scoped artifacts** (files under `<sessionFile-without-.jsonl>/`): per-session text files used for full tool outputs and subagent outputs.\n\nThey are intentionally separate:\n\n- blob storage optimizes deduplication and stable references by content hash,\n- artifact storage optimizes append-only session tooling and human/tool retrieval by local IDs.\n\n## Storage boundaries and on-disk layout\n\n## Blob store boundary (global)\n\n`SessionManager` constructs `BlobStore(getBlobsDir())`, so blob files live in a shared global blob directory (not in a session folder).\n\nBlob file naming:\n\n- file path: `<blobsDir>/<sha256-hex>`\n- no extension\n- reference string stored in entries: `blob:sha256:<sha256-hex>`\n\nImplications:\n\n- same binary content across sessions resolves to the same hash/path,\n- writes are idempotent at the content level,\n- blobs can outlive any individual session file.\n\n## Artifact boundary (session-local)\n\n`ArtifactManager` derives artifact directory from session file path:\n\n- session file: `.../<timestamp>_<sessionId>.jsonl`\n- artifacts directory: `.../<timestamp>_<sessionId>/` (strip `.jsonl`)\n\nArtifact types share this directory:\n\n- truncated tool output files: `<numericId>.<toolType>.log` (for `artifact://`)\n- subagent output files: `<outputId>.md` (for `agent://`)\n\n## ID and name allocation schemes\n\n## Blob IDs: content hash\n\n`BlobStore.put()` computes SHA-256 over the bytes it is given and returns:\n\n- `hash`: hex digest,\n- `path`: `<blobsDir>/<hash>`,\n- `ref`: `blob:sha256:<hash>`.\n\nNo session-local counter is used.\n\n## Artifact IDs: session-local monotonic integer\n\n`ArtifactManager` scans existing `*.log` artifact files on first use to find max existing numeric ID and sets `nextId = max + 1`.\n\nAllocation behavior:\n\n- file format: `{id}.{toolType}.log`\n- IDs are sequential strings (`\"0\"`, `\"1\"`, ...)\n- resume does not overwrite existing artifacts because scan happens before allocation.\n\nIf artifact directory is missing, scanning yields empty list and allocation starts from `0`.\n\n## Agent output IDs (`agent://`)\n\n`AgentOutputManager` allocates IDs for subagent outputs as `<index>-<requestedId>` (optionally nested under parent prefix, e.g. `0-Parent.1-Child`). It scans existing `.md` files on initialization to continue from the next index on resume.\n\n## Persistence dataflow\n\n## 1) Session entry persistence rewrite path\n\nBefore session entries are written (`#rewriteFile` / incremental persist), `SessionManager` calls `prepareEntryForPersistence()` (via `truncateForPersistence`).\n\nKey behaviors:\n\n1. **Large string truncation**: oversized strings are cut and suffixed with `\"[Session persistence truncated large content]\"`; signature fields (`thinkingSignature`, `thoughtSignature`, `textSignature`) are cleared instead of truncated.\n2. **Transient field stripping**: `partialJson` and `jsonlEvents` are removed from persisted entries.\n3. **Image externalization to blobs**:\n   - image blocks in `content` arrays are externalized when `data` is not already a blob ref and base64 length is at least threshold (`BLOB_EXTERNALIZE_THRESHOLD = 1024`),\n   - provider-style `image_url` data URLs are externalized when they start with `data:image/` and contain `;base64,`,\n   - image block `data` is stored as decoded binary bytes,\n   - provider data URLs are stored as the original UTF-8 data URL string,\n   - persisted values are replaced with `blob:sha256:<hash>`.\n\nThis keeps session JSONL compact while preserving recoverability.\n\n## 2) Session load rehydration path\n\nWhen opening a session (`setSessionFile`), after migrations, `SessionManager` runs `resolveBlobRefsInEntries()`.\n\nFor message/custom-message image blocks with `blob:sha256:<hash>` and for persisted provider `image_url` fields with blob refs:\n\n- reads blob bytes from blob store,\n- converts image-block bytes back to base64,\n- converts provider `image_url` blobs back to the original string,\n- mutates in-memory entry fields for runtime consumers.\n\nIf blob is missing:\n\n- `resolveImageData()` logs warning,\n- returns original ref string unchanged,\n- load continues (no hard crash).\n\n## 3) Tool output spill/truncation path\n\n`OutputSink` powers streaming output in bash/python/ssh and related executors.\n\nBehavior:\n\n1. Every chunk is sanitized and appended to in-memory tail buffer.\n2. When in-memory bytes exceed spill threshold (`DEFAULT_MAX_BYTES`, 50KB), sink marks output truncated.\n3. If an artifact path is available, sink opens a file writer and writes:\n   - existing buffered content once,\n   - all subsequent chunks.\n4. In-memory buffer is always trimmed to tail window for display.\n5. `dump()` returns summary including `artifactId` only when file sink was successfully created.\n\nPractical effect:\n\n- UI/tool return shows truncated tail,\n- full output is preserved in artifact file and referenced as `artifact://<id>`.\n\nIf file sink creation fails (I/O error, missing path, etc.), sink silently falls back to in-memory truncation only; full output is not persisted.\n\n## URL access model\n\n## `blob:` references\n\n`blob:sha256:<hash>` is a persistence reference inside session entry payloads, not an internal URL scheme handled by the router. Resolution is done by `SessionManager` during session load.\n\n## `artifact://<id>`\n\nHandled by `ArtifactProtocolHandler`:\n\n- requires active session artifact directory,\n- ID must be numeric,\n- resolves by matching filename prefix `<id>.`,\n- returns raw text (`text/plain`) from the matched `.log` file,\n- when missing, error includes list of available artifact IDs.\n\nMissing directory behavior:\n\n- if artifacts directory does not exist, throws `No artifacts directory found`.\n\n## `agent://<id>`\n\nHandled by `AgentProtocolHandler` over `<artifactsDir>/<id>.md`:\n\n- plain form returns markdown text,\n- `/path` or `?q=` forms perform JSON extraction,\n- path and query extraction cannot be combined,\n- if extraction requested, file content must parse as JSON.\n\nMissing directory behavior:\n\n- throws `No artifacts directory found`.\n\nMissing output behavior:\n\n- throws `Not found: <id>` with available IDs from existing `.md` files.\n\nRead tool integration:\n\n- `read` supports offset/limit pagination for non-extraction internal URL reads,\n- rejects `offset/limit` when `agent://` extraction is used.\n\n## Resume, fork, and move semantics\n\n## Resume\n\n- `ArtifactManager` scans existing `{id}.*.log` files on first allocation and continues numbering.\n- `AgentOutputManager` scans existing `.md` output IDs and continues numbering.\n- `SessionManager` rehydrates blob refs to base64 on load.\n\n## Fork\n\n`SessionManager.fork()` creates a new session file with new session ID and `parentSession` link, then returns old/new file paths. Artifact copying is handled by `AgentSession.fork()`:\n\n- attempts recursive copy of old artifact directory to new artifact directory,\n- missing old directory is tolerated,\n- non-ENOENT copy errors are logged as warnings and fork still completes.\n\nID implications after fork:\n\n- if copy succeeded, artifact counters in new session continue after max copied ID,\n- if copy failed/skipped, new session artifact IDs start from `0`.\n\nBlob implications after fork:\n\n- blobs are global and content-addressed, so no blob directory copy is required.\n\n## Move to new cwd\n\n`SessionManager.moveTo()` renames both session file and artifact directory to the new default session directory, with rollback logic if a later step fails. This preserves artifact identity while relocating session scope.\n\n## Failure handling and fallback paths\n\n| Case                                                     | Behavior                                                              |\n| -------------------------------------------------------- | --------------------------------------------------------------------- |\n| Blob file missing during rehydration                     | Warn and keep `blob:sha256:` ref string in-memory                     |\n| Blob read ENOENT via `BlobStore.get`                     | Returns `null`                                                        |\n| Artifact directory missing (`ArtifactManager.listFiles`) | Returns empty list (allocation can start fresh)                       |\n| Artifact directory missing (`artifact://` / `agent://`)  | Throws explicit `No artifacts directory found`                        |\n| Artifact ID not found                                    | Throws with available IDs listing                                     |\n| OutputSink artifact writer init fails                    | Continues with tail-only truncation (no full-output artifact)         |\n| No session file (some task paths)                        | Task tool falls back to temp artifacts directory for subagent outputs |\n\n## Binary blob externalization vs text-output artifacts\n\n- **Blob externalization** is for image payloads inside persisted session entry content and provider image data URLs; it replaces inline payload strings in JSONL with stable content refs.\n- **Artifacts** are plain text files for execution output and subagent output; they are addressable by session-local IDs through internal URLs.\n\nThe two systems intersect only indirectly (both reduce session JSONL bloat) but have different identity, lifetime, and retrieval paths.\n\n## Implementation files\n\n- [`src/session/blob-store.ts`](../packages/coding-agent/src/session/blob-store.ts) — blob reference format, hashing, put/get, externalize/resolve helpers.\n- [`src/session/artifacts.ts`](../packages/coding-agent/src/session/artifacts.ts) — session artifact directory model and numeric artifact ID/path allocation.\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts) — `OutputSink` truncation/spill-to-file behavior and summary metadata.\n- [`src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts) — persistence transforms, blob rehydration on load, session fork/move interactions.\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — artifact directory copy during interactive fork.\n- [`src/internal-urls/artifact-protocol.ts`](../packages/coding-agent/src/internal-urls/artifact-protocol.ts) — `artifact://` resolver.\n- [`src/internal-urls/agent-protocol.ts`](../packages/coding-agent/src/internal-urls/agent-protocol.ts) — `agent://` resolver + JSON extraction.\n- [`src/sdk.ts`](../packages/coding-agent/src/sdk.ts) — internal URL router wiring and artifacts-dir resolver.\n- [`src/task/output-manager.ts`](../packages/coding-agent/src/task/output-manager.ts) — session-scoped agent output ID allocation for `agent://`.\n- [`src/task/executor.ts`](../packages/coding-agent/src/task/executor.ts) — subagent output artifact writes (`<id>.md`) and temp artifact directory fallback.\n",
@@ -72,7 +72,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"tools/calc.md": "# calc\n\n> Evaluates one or more arithmetic expressions and returns formatted numeric results.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/calculator.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/calculator.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tui.ts` — status lines and tree-list rendering\n  - `packages/coding-agent/src/tools/render-utils.ts` — preview limits and formatting helpers\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `calculations` | `Calculation[]` | Yes | Batch of expressions to evaluate in order. |\n\n### `Calculation`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `expression` | `string` | Yes | Arithmetic expression string. |\n| `prefix` | `string` | Yes | Prepended verbatim to the rendered numeric result. |\n| `suffix` | `string` | Yes | Appended verbatim to the rendered numeric result. |\n\n## Outputs\n- Single-shot result.\n- `content[0].text` is the newline-joined `prefix + value + suffix` string for each calculation.\n- `details.results` is an array of `{ expression, value, output }`.\n- On renderer fallback, if `details` is missing but `content[0].text` exists, the TUI tries to pair each output line with the original expressions from call args.\n\n## Flow\n1. `execute()` wraps evaluation in `untilAborted(...)`.\n2. For each entry, `evaluateExpression(...)` tokenizes the expression, parses it with a recursive-descent parser, rejects non-finite outputs, and normalizes `-0` to `0`.\n3. `tokenizeExpression(...)` accepts whitespace, parentheses, operators, and number literals; any other character throws immediately.\n4. `ExpressionParser` applies precedence in this order: `+ -`, `* / %`, unary `+ -`, exponentiation `**`, parentheses/literals.\n5. Exponentiation is right-associative (`2 ** 3 ** 2` parses as `2 ** (3 ** 2)`).\n6. Each numeric result is formatted with `String(value)` and wrapped with the provided `prefix` and `suffix`.\n7. The tool returns text output plus structured `details`.\n\n## Side Effects\n- Background work / cancellation\n  - Supports abort via `untilAborted(...)`.\n- Session state\n  - None.\n- Filesystem / Network / Subprocesses\n  - None.\n\n## Limits & Caps\n- Supported operators: `+`, `-`, `*`, `/`, `%`, `**` (`packages/coding-agent/src/tools/calculator.ts`).\n- Supported numeric literals:\n  - decimal integers/floats, including leading-dot forms like `.5`\n  - scientific notation like `1e10`, `2.5E-3`\n  - hexadecimal `0x...`\n  - binary `0b...`\n  - octal `0o...`\n- Results must be finite; `Infinity` and `NaN` are rejected.\n- The renderer collapses long result lists using `PREVIEW_LIMITS.COLLAPSED_ITEMS` from `packages/coding-agent/src/tools/render-utils.ts`.\n\n## Errors\n- Invalid characters: e.g. `Invalid character \"x\" in expression`.\n- Malformed numbers: invalid prefixed literal, invalid exponent, invalid number.\n- Syntax errors: `Unexpected token in expression`, `Unexpected end of expression`, `Missing closing parenthesis`, `Expression is empty`.\n- Non-finite arithmetic: `Expression result is not a finite number`.\n- Any evaluation error aborts the whole batch; the tool does not return partial successes.\n\n## Notes\n- Despite the schema example showing `sqrt(16)`, the parser does not support functions, identifiers, units, or constants; only numeric literals, operators, and parentheses are accepted.\n- Precision is plain JavaScript `number` semantics throughout, including floating-point rounding behavior.\n- `/` and `%` use JavaScript numeric operators directly; there is no integer-only mode or unit handling.\n- Unary operators bind tighter than `*`/`/`/`%` but looser than exponentiation because unary parsing delegates to `#parsePower()`.\n",
 	"tools/checkpoint.md": "# checkpoint\n\n> Mark the current top-level conversation state so later `rewind` can collapse exploratory context into a report.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/checkpoint.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/checkpoint.md`\n- Key collaborators:\n  - `packages/coding-agent/src/session/agent-session.ts` — captures the active checkpoint after tool success.\n  - `packages/coding-agent/src/session/session-manager.ts` — persists the normal session entry stream; not the active checkpoint marker.\n  - `packages/coding-agent/src/tools/index.ts` — registers the tool and gates it behind `checkpoint.enabled`.\n  - `packages/coding-agent/src/config/settings-schema.ts` — defines the disabled-by-default feature flag.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `goal` | `string` | Yes | Investigation goal. Required by the schema and echoed in the tool result. |\n\n## Outputs\nThe tool returns a single text result plus structured details:\n\n- text body:\n  - `Checkpoint created.`\n  - `Goal: <goal>`\n  - `Run your investigation, then call rewind with a concise report.`\n- `details`:\n  - `goal: string`\n  - `startedAt: string` — ISO timestamp created inside `CheckpointTool.execute()`\n\nNo checkpoint ID, artifact URI, job handle, file path, or restore token is returned.\n\n## Flow\n1. `CheckpointTool.createIf()` in `packages/coding-agent/src/tools/checkpoint.ts` returns `null` for subagents by checking `session.taskDepth`; only top-level sessions can see the tool.\n2. `CheckpointTool.execute()` rejects subagent calls again with `ToolError(\"Checkpoint not available in subagents.\")`.\n3. It rejects nested checkpoints with `ToolError(\"Checkpoint already active.\")` when `session.getCheckpointState?.()` is already set.\n4. It creates `startedAt = new Date().toISOString()` and returns a normal `toolResult()` payload. The tool itself does not persist anything.\n5. On the later `tool_execution_end` event, `AgentSession` in `packages/coding-agent/src/session/agent-session.ts` detects successful `checkpoint` execution and captures three in-memory fields:\n   - `checkpointMessageCount` — current `agent.state.messages.length`, after the checkpoint tool result has already been appended\n   - `checkpointEntryId` — `sessionManager.getEntries().at(-1)?.id ?? null`, i.e. the last persisted session entry ID at checkpoint time\n   - `startedAt` — copied from tool details or regenerated\n6. `AgentSession` stores that object in its private `#checkpointState` field and clears `#pendingRewindReport`.\n\n## Side Effects\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Sets `AgentSession.#checkpointState` in memory.\n  - Records the checkpoint boundary as a message count plus a session entry ID.\n  - Enables the later yield guard: if a checkpoint is active and no rewind report is pending, `#enforceRewindBeforeYield()` injects a developer-role warning and schedules another turn.\n- User-visible prompts / interactive UI\n  - The tool result tells the model to call `rewind` after the investigation.\n  - If the agent tries to `yield` first, `AgentSession` injects:\n\n```text\n<system-warning>\nYou are in an active checkpoint. You MUST call rewind with your investigation findings before yielding. Do NOT yield without completing the checkpoint.\n</system-warning>\n```\n\n## Limits & Caps\n- Availability is gated by `checkpoint.enabled`, default `false`, in `packages/coding-agent/src/config/settings-schema.ts`.\n- The tool is registered as discoverable in `packages/coding-agent/src/tools/index.ts`.\n- Only one active checkpoint is allowed per top-level session.\n- Checkpoint state is not persisted as a dedicated session entry. If the process exits, a resumed session can reload the conversation history, but not the live `#checkpointState` guard.\n- Session persistence still applies to the ordinary checkpoint tool call message. Global session persistence truncation is `MAX_PERSIST_CHARS = 500_000` in `packages/coding-agent/src/session/session-manager.ts`.\n\n## Errors\n- `ToolError(\"Checkpoint not available in subagents.\")` — thrown for subagent sessions.\n- `ToolError(\"Checkpoint already active.\")` — thrown when a prior checkpoint has not been rewound or cleared.\n- The tool body has no local `try/catch`; unexpected exceptions propagate.\n\n## Notes\n- Despite the summary string `Create a git-based checkpoint to save and restore session state`, the implementation does not call git and does not snapshot filesystem state.\n- Captured state is conversation/session metadata only:\n  - in-memory message count\n  - session entry ID in the session tree\n  - timestamp\n- Not captured:\n  - working tree contents\n  - staged changes\n  - artifacts\n  - blob-store contents\n  - SQLite history rows from `packages/coding-agent/src/session/history-storage.ts`\n  - auth or agent records from `packages/coding-agent/src/session/agent-storage.ts`\n- If the turn ends with `stopReason === \"aborted\"` while a checkpoint is active, `AgentSession` clears `#checkpointState` and `#pendingRewindReport` instead of preserving a half-finished checkpoint.\n",
 	"tools/debug.md": "# debug\n\n> Drive one DAP debug session; adjacent debug UI code reuses the same subsystem for logs, raw SSE capture, reports, profiling, and system diagnostics.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/debug.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/debug.md`\n- Key collaborators:\n  - `packages/coding-agent/src/dap/session.ts` — session lifecycle, breakpoint/state cache\n  - `packages/coding-agent/src/dap/client.ts` — adapter process/socket transport, DAP message loop\n  - `packages/coding-agent/src/dap/config.ts` — adapter resolution and auto-selection\n  - `packages/coding-agent/src/dap/defaults.json` — built-in adapter definitions\n  - `packages/coding-agent/src/dap/types.ts` — request/response/capability shapes\n  - `packages/coding-agent/src/tools/tool-timeouts.ts` — per-tool timeout clamp\n  - `packages/coding-agent/src/debug/index.ts` — interactive debug selector menu\n  - `packages/coding-agent/src/debug/log-viewer.ts` — recent-log TUI viewer\n  - `packages/coding-agent/src/debug/raw-sse.ts` — raw SSE TUI viewer\n  - `packages/coding-agent/src/debug/raw-sse-buffer.ts` — bounded SSE capture buffer\n  - `packages/coding-agent/src/debug/profiler.ts` — CPU/heap profiling helpers\n  - `packages/coding-agent/src/debug/report-bundle.ts` — `.tar.gz` report bundling, log source, cache cleanup\n  - `packages/coding-agent/src/debug/system-info.ts` — system snapshot collection and env redaction\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | `\"launch\" \\| \"attach\" \\| \"set_breakpoint\" \\| \"remove_breakpoint\" \\| \"set_instruction_breakpoint\" \\| \"remove_instruction_breakpoint\" \\| \"data_breakpoint_info\" \\| \"set_data_breakpoint\" \\| \"remove_data_breakpoint\" \\| \"continue\" \\| \"step_over\" \\| \"step_in\" \\| \"step_out\" \\| \"pause\" \\| \"evaluate\" \\| \"stack_trace\" \\| \"threads\" \\| \"scopes\" \\| \"variables\" \\| \"disassemble\" \\| \"read_memory\" \\| \"write_memory\" \\| \"modules\" \\| \"loaded_sources\" \\| \"custom_request\" \\| \"output\" \\| \"terminate\" \\| \"sessions\"` | Yes | Dispatch key for the tool switch in `packages/coding-agent/src/tools/debug.ts`. |\n| `program` | `string` | No | Launch target path. Required for `launch`. Resolved relative to `cwd` if provided, otherwise session cwd. |\n| `args` | `string[]` | No | Program argv for `launch`. |\n| `adapter` | `string` | No | Explicit adapter name. Otherwise `selectLaunchAdapter()` / `selectAttachAdapter()` auto-pick from `packages/coding-agent/src/dap/config.ts`. |\n| `cwd` | `string` | No | Launch/attach working directory. Defaults to session cwd. |\n| `file` | `string` | No | Source file path for source breakpoints. |\n| `line` | `number` | No | Source line for source breakpoints. |\n| `function` | `string` | No | Function breakpoint name. Mutually exclusive with `file`+`line` in breakpoint actions. |\n| `name` | `string` | No | Data breakpoint info target name. Required for `data_breakpoint_info`. |\n| `condition` | `string` | No | Conditional expression for source/function/instruction/data breakpoints. |\n| `hit_condition` | `string` | No | Hit-count condition for instruction/data breakpoints. |\n| `expression` | `string` | No | Expression or raw debugger command. Required for `evaluate`. |\n| `context` | `string` | No | Evaluate context. Defaults to `\"repl\"`. Passed through as DAP evaluate context. |\n| `frame_id` | `number` | No | Frame selector for `evaluate`, `scopes`, `data_breakpoint_info`. `scopes` and `evaluate` default to the current stopped frame when omitted. |\n| `scope_id` | `number` | No | Variables reference from a scope. Accepted by `variables`; also used as a fallback variables reference for `data_breakpoint_info`. |\n| `variable_ref` | `number` | No | Variables reference for `variables`; preferred over `scope_id` when both are present. |\n| `pid` | `number` | No | Local process id for `attach`. `attach` requires `pid` or `port`. |\n| `port` | `number` | No | Remote attach port. If no adapter is forced, attach prefers `debugpy` when `port` is present. |\n| `host` | `string` | No | Remote attach host for `attach`. |\n| `levels` | `number` | No | Max stack frames for `stack_trace`. |\n| `memory_reference` | `string` | No | Memory reference/address for `disassemble`, `read_memory`, `write_memory`. `disassemble` also accepts it via `instruction_reference` fallback logic in `resolveDisassemblyReference()`. |\n| `instruction_reference` | `string` | No | Instruction breakpoint reference; required for instruction breakpoint actions. |\n| `instruction_count` | `number` | No | Required for `disassemble`. |\n| `instruction_offset` | `number` | No | Instruction offset for `disassemble`. |\n| `count` | `number` | No | Byte count for `read_memory`. Required there. |\n| `data` | `string` | No | Base64 payload for `write_memory`. Required there. |\n| `data_id` | `string` | No | Data breakpoint id. Required for `set_data_breakpoint` / `remove_data_breakpoint`. |\n| `access_type` | `\"read\" \\| \"write\" \\| \"readWrite\"` | No | Access filter for `set_data_breakpoint`. |\n| `command` | `string` | No | Custom DAP request command. Required for `custom_request`. |\n| `arguments` | `Record<string, unknown>` | No | Custom DAP request body for `custom_request`. |\n| `offset` | `number` | No | Offset for instruction breakpoints, disassembly, memory read, memory write. |\n| `resolve_symbols` | `boolean` | No | `disassemble` symbol-resolution flag. |\n| `allow_partial` | `boolean` | No | `write_memory` partial-write allowance. |\n| `start_module` | `number` | No | Modules pagination start index for `modules`. |\n| `module_count` | `number` | No | Modules pagination count for `modules`. |\n| `timeout` | `number` | No | Per-request timeout in seconds. Default `30`, clamped to `5..300`. |\n\n### Action-specific requirements\n- `launch`: `program`\n- `attach`: `pid` or `port`\n- `set_breakpoint` / `remove_breakpoint`: `function`, or `file` + `line`\n- `set_instruction_breakpoint` / `remove_instruction_breakpoint`: `instruction_reference`\n- `data_breakpoint_info`: `name`\n- `set_data_breakpoint` / `remove_data_breakpoint`: `data_id`\n- `evaluate`: `expression`\n- `variables`: `variable_ref` or `scope_id`\n- `disassemble`: capability `supportsDisassembleRequest`, plus `instruction_count`\n- `read_memory`: capability `supportsReadMemoryRequest`, plus `memory_reference` and `count`\n- `write_memory`: capability `supportsWriteMemoryRequest`, plus `memory_reference` and `data`\n- `modules`: capability `supportsModulesRequest`\n- `loaded_sources`: capability `supportsLoadedSourcesRequest`\n- `custom_request`: `command`\n\n### Interactive selector values\n`packages/coding-agent/src/debug/index.ts` also exposes a fixed UI-only selector with values `open-artifacts`, `performance`, `work`, `dump`, `memory`, `logs`, `system`, `raw-sse`, `transcript`, `clear-cache`. These are not model-callable through `debugSchema`; they are local TUI menu routes.\n\n## Outputs\nThe agent tool returns a standard `toolResult()` payload from `packages/coding-agent/src/tools/debug.ts`:\n- `content`: one text block. Every action renders human-readable text; there is no structured JSON block in `content`.\n- `details.action`: echoed action.\n- `details.success`: always initialized `true`; failures surface by throwing before a result is returned.\n- `details.snapshot`: present for actions that operate on or create a session, using `DapSessionSummary` from `packages/coding-agent/src/dap/types.ts`.\n- Action-specific `details` fields:\n  - `launch` / `attach`: `adapter`\n  - breakpoint actions: `breakpoints`, `functionBreakpoints`, `instructionBreakpoints`, `dataBreakpoints`\n  - `data_breakpoint_info`: `dataBreakpointInfo`\n  - `continue` / `step_*`: `state`, `timedOut`\n  - `threads`: `threads`\n  - `stack_trace`: `stackFrames`\n  - `scopes`: `scopes`\n  - `variables`: `variables`\n  - `evaluate`: `evaluation`\n  - `disassemble`: `disassembly`\n  - `read_memory`: `memoryAddress`, `memoryData`, `unreadableBytes`\n  - `write_memory`: `bytesWritten`\n  - `modules`: `modules`\n  - `loaded_sources`: `sources`\n  - `custom_request`: `customBody`\n  - `output`: `output`\n  - `sessions`: `sessions`\n\nStreaming/UI behavior:\n- The tool renderer merges call and result (`mergeCallAndResult: true`) and renders inline.\n- `debug.ts` itself does not emit progress updates through `_onUpdate`; result delivery is single-shot.\n- The interactive selector is UI-driven instead of model-driven. It swaps TUI components, appends status lines to the chat pane, opens files in external viewers, or writes archives/temp files.\n\nSide-channel artifacts outside the model tool result:\n- `createReportBundle()` writes `omp-report-<timestamp>.tar.gz` under the reports dir and returns the filesystem path to the UI handler.\n- `#handleWorkReport()` writes `/tmp/work-profile-<Date.now()>.svg` before opening it.\n- `RawSseViewerComponent` and `DebugLogViewerComponent` can copy captured text to the clipboard.\n\n## Flow\n1. Tool registration is conditional: `DebugTool.createIf()` in `packages/coding-agent/src/tools/debug.ts` returns `null` unless `session.settings.get(\"debug.enabled\")` is true. `packages/coding-agent/src/tools/index.ts` wires the factory and rechecks the same setting in tool filtering.\n2. `DebugTool.execute()` clamps `params.timeout` through `clampTimeout(\"debug\", params.timeout)` and composes the caller `AbortSignal` with `AbortSignal.timeout(...)`.\n3. `launch` and `attach` resolve cwd/program paths, select an adapter in `packages/coding-agent/src/dap/config.ts`, then delegate to `dapSessionManager.launch()` / `.attach()`.\n4. `DapSessionManager.launch()` / `.attach()` enforce the single-session rule with `#ensureLaunchSlot()`, spawn the adapter through `DapClient.spawn()`, register listeners, send `initialize`, cache capabilities, start listening for an initial stop event before sending `launch`/`attach`, then complete the `initialized` → `configurationDone` handshake in `#completeConfigurationHandshake()`.\n5. `DapClient.spawn()` starts the adapter detached with `NON_INTERACTIVE_ENV`. Most adapters use stdio; socket-mode adapters (`dlv`) use `#spawnSocketUnix()` on Linux or `#spawnSocketClientAddr()` on macOS/other.\n6. `#registerSession()` in `packages/coding-agent/src/dap/session.ts` installs reverse-request handlers:\n   - `runInTerminal`: spawns the requested debuggee command detached via `ptree.spawn()` and returns `{ processId }`\n   - `startDebugging`: logs the child-session request and returns `{}`; it does not create nested sessions\n   - events: `output`, `initialized`, `stopped`, `continued`, `exited`, `terminated` update cached session state\n7. Operational actions (`set_breakpoint`, `evaluate`, `threads`, `read_memory`, `custom_request`, and similar) call `dapSessionManager` methods. Most flow through `#sendRequestWithConfig()`, which first sends `configurationDone` when required, then sends the DAP request, then updates `lastUsedAt`.\n8. Breakpoint actions maintain local cached breakpoint sets in `DapSessionManager` and remap adapter responses back onto those cached records.\n9. `continue` and the three step actions clear cached stop state, subscribe for `stopped`/`terminated`/`exited` before sending the DAP request, then `#awaitStopOutcome()` either returns the new stopped location or reports that the program is still running after timeout.\n10. `pause` sends DAP `pause`, waits for a stopped event if needed, and reuses cached stop state if the program was already stopped.\n11. `stack_trace`, `scopes`, `variables`, and `evaluate` default to the current stopped thread/frame when the caller omits ids and cached state is available.\n12. `output` reads the in-memory output ring from `DapSessionManager.getOutput()`. `terminate` sends `terminate` when supported, always attempts `disconnect`, marks the session terminated, and disposes the client.\n13. `sessions` reads the manager’s current map and formats all summaries. Although the manager stores a map, only one active session can exist because new launch/attach calls are blocked until the active one is terminated or cleaned up.\n14. The interactive selector in `packages/coding-agent/src/debug/index.ts` builds a `SelectList` of fixed values and dispatches each to a handler:\n   - `performance`: `startCpuProfile()`, wait for Enter/Escape, stop profiling, read a 30-second work profile with `getWorkProfile(30)`, then bundle via `createReportBundle()`\n   - `work`: read `getWorkProfile(30)`, write a temp SVG, open it externally\n   - `dump`: create a report bundle immediately\n   - `memory`: force GC, call `Bun.generateHeapSnapshot(\"v8\")`, then bundle\n   - `logs`: build a `DebugLogSource` and mount `DebugLogViewerComponent`\n   - `raw-sse`: resolve a `RawSseDebugBuffer` from the session and mount `RawSseViewerComponent`\n   - `system`: call `collectSystemInfo()` and render `formatSystemInfo()` into the chat pane\n   - `open-artifacts`: open the current session artifact directory if it exists\n   - `transcript`: delegates to `ctx.handleDebugTranscriptCommand()`\n   - `clear-cache`: show confirmation, then remove artifact directories older than 30 days with `clearArtifactCache()`\n\n## Modes / Variants\n- **Availability gate**\n  - Tool hidden when `debug.enabled` is false.\n- **Adapter selection**\n  - `launch`: explicit `adapter` wins; otherwise `selectLaunchAdapter()` ranks available adapters by extension match, root-marker match, then native-debugger preference (`gdb`, `lldb-dap`) for extensionless binaries.\n  - `attach`: explicit `adapter` wins; otherwise remote `port` prefers `debugpy`, then native debuggers, then first available adapter.\n- **Transport**\n  - stdio adapters: direct `stdin`/`stdout` framing.\n  - socket adapters: Unix domain socket on Linux; TCP callback on macOS/other.\n- **DAP agent-tool actions**\n  - `launch` — spawn adapter, initialize session, maybe stop on entry; returns formatted session snapshot and `details.adapter`.\n  - `attach` — connect to a live process or remote port; same output shape as `launch`.\n  - `set_breakpoint` — source or function breakpoint add/update; returns the current breakpoint list for that target.\n  - `remove_breakpoint` — source or function breakpoint removal; returns the remaining breakpoint list.\n  - `set_instruction_breakpoint` / `remove_instruction_breakpoint` — require `supportsInstructionBreakpoints`; return current instruction breakpoint list.\n  - `data_breakpoint_info` — require `supportsDataBreakpoints`; asks the adapter for a `dataId`, access types, and description for `name`.\n  - `set_data_breakpoint` / `remove_data_breakpoint` — require `supportsDataBreakpoints`; return the cached data-breakpoint list.\n  - `continue` / `step_over` / `step_in` / `step_out` — return text describing whether execution stopped, terminated, or kept running, plus `details.state` and `details.timedOut`.\n  - `pause` — interrupts a running target and returns a stopped snapshot.\n  - `evaluate` — adapter expression evaluation; defaults context to `repl`.\n  - `stack_trace` — fetches frames for the resolved thread.\n  - `threads` — fetches current threads.\n  - `scopes` — frame scopes for an explicit `frame_id` or the current stopped frame.\n  - `variables` — variables for `variable_ref` or `scope_id`.\n  - `disassemble` — require `supportsDisassembleRequest`; disassembles around a memory reference.\n  - `read_memory` — require `supportsReadMemoryRequest`; returns address, base64 data, unreadable-byte count.\n  - `write_memory` — require `supportsWriteMemoryRequest`; writes base64 data and reports bytes written.\n  - `modules` — require `supportsModulesRequest`; optional pagination via `start_module` / `module_count`.\n  - `loaded_sources` — require `supportsLoadedSourcesRequest`; returns loaded source descriptors.\n  - `custom_request` — sends any DAP request name with arbitrary arguments.\n  - `output` — dumps captured stdout/stderr/console text from the session cache.\n  - `terminate` — disconnects and disposes the active session; returns `No debug session to terminate.` when none exists.\n  - `sessions` — lists all cached session summaries.\n- **Interactive selector routes (UI-only)**\n  - `logs` — loads today’s log tail and optional older daily log files into `DebugLogViewerComponent`; supports copy, range selection, pid filtering, load-older.\n  - `raw-sse` — live view over the session’s `RawSseDebugBuffer`; supports tail-follow, scrolling, copy-all.\n  - `performance` — CPU profile + 30-second work profile + report bundle.\n  - `memory` — heap snapshot + report bundle.\n  - `dump` — report bundle without profiler artifacts.\n  - `work` — standalone work-profile flamegraph export/open.\n  - `system` — formatted OS/arch/CPU/memory/version/cwd/shell/terminal dump.\n  - `open-artifacts` / `transcript` / `clear-cache` — artifact directory open, transcript export, artifact-cache pruning.\n\n## Side Effects\n- Filesystem\n  - Resolves program/file/cwd paths against the session cwd.\n  - Report creation writes `.tar.gz` bundles and may read the session JSONL, artifact files, subagent session JSONLs, and log files.\n  - Work-profile export writes `/tmp/work-profile-<timestamp>.svg`.\n  - Log source reads daily log files from the logs dir.\n  - Artifact-cache cleanup removes session artifact directories older than the cutoff.\n  - `resolveRawSseDebugBuffer()` may attach a non-enumerable `rawSseDebugBuffer` property to the owner object.\n- Network\n  - Socket-mode adapters bind/connect local sockets.\n  - Remote attach may connect through the adapter to a remote debug port.\n- Subprocesses / native bindings\n  - Spawns debugger adapters (`gdb`, `lldb-dap`, `python -m debugpy.adapter`, `dlv`, and others from `defaults.json`) detached.\n  - Reverse DAP `runInTerminal` requests spawn the debuggee detached via `ptree.spawn()`.\n  - `getWorkProfile(30)` comes from `@oh-my-pi/pi-natives`.\n  - CPU profiling uses `node:inspector/promises`; heap snapshots use `Bun.generateHeapSnapshot(\"v8\")`; raw/log viewers sanitize text via `@oh-my-pi/pi-natives`.\n  - `openPath()` launches the OS default file/browser handler for artifact dirs and SVGs.\n  - Log/raw-SSE viewers can call `copyToClipboard()`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - `DapSessionManager` keeps session summaries, breakpoints, threads, stack frames, stop location, output capture, capabilities, and last-used timestamps in memory.\n  - Active-session id is global to the singleton `dapSessionManager`.\n  - `RawSseDebugBuffer` stores recent SSE events per owner/session.\n  - The tool is `exclusive`; concurrent debug tool calls are blocked by the scheduler.\n- User-visible prompts / interactive UI\n  - Debug selector shows confirmation before cache deletion.\n  - Performance profiling temporarily hijacks editor Enter/Escape handlers until profiling stops.\n  - Log/raw-SSE viewers replace the editor pane with custom components.\n- Background work / cancellation\n  - Every DAP request accepts an `AbortSignal`; timeouts and caller cancellation abort the active request, not the whole session lifetime.\n  - `DapSessionManager` runs a background cleanup loop every 30 seconds.\n  - Raw SSE viewers subscribe to buffer updates until closed.\n\n## Limits & Caps\n- Tool timeout clamp: `default=30`, `min=5`, `max=300` in `packages/coding-agent/src/tools/tool-timeouts.ts`.\n- Per-request DAP default timeout: `DEFAULT_REQUEST_TIMEOUT_MS = 30_000` in `packages/coding-agent/src/dap/client.ts`.\n- Single active session: enforced by `#ensureLaunchSlot()` in `packages/coding-agent/src/dap/session.ts`.\n- Idle session cleanup: `IDLE_TIMEOUT_MS = 10 * 60 * 1000`, checked every `CLEANUP_INTERVAL_MS = 30 * 1000`.\n- Adapter liveness heartbeat: `HEARTBEAT_INTERVAL_MS = 5 * 1000`.\n- Output capture cap: `MAX_OUTPUT_BYTES = 128 * 1024`; older text is trimmed in ~1 KiB slices and `outputTruncated` is recorded.\n- Initial stop capture timeout after launch/attach: `STOP_CAPTURE_TIMEOUT_MS = 5_000`.\n- Socket-mode adapter readiness timeout: `10_000` ms in `waitForCondition()` and TCP connect timeout logic in `packages/coding-agent/src/dap/client.ts`.\n- Raw SSE buffer caps in `packages/coding-agent/src/debug/raw-sse-buffer.ts`:\n  - `MAX_RAW_SSE_EVENTS = 1_000`\n  - `MAX_RAW_SSE_CHARS = 512_000`\n  - `MAX_RAW_SSE_EVENT_CHARS = 64_000` per event, with `: omp-debug-truncated ...` marker appended on trim\n- Log viewer window in `packages/coding-agent/src/debug/log-viewer.ts`:\n  - `INITIAL_LOG_CHUNK = 50`\n  - `LOAD_OLDER_CHUNK = 50`\n- Report/log ingestion caps in `packages/coding-agent/src/debug/report-bundle.ts`:\n  - `MAX_LOG_LINES = 5000` for interactive log reading\n  - `MAX_LOG_BYTES = 2 * 1024 * 1024` tail-read ceiling\n  - report bundles include only the last `1000` log lines\n  - subagent session inclusion is capped at the most recent `10` JSONL files\n- Interactive profiling windows in `packages/coding-agent/src/debug/index.ts`: both performance and work reports request `getWorkProfile(30)`.\n- Artifact cache pruning default: `30` days in `clearArtifactCache()` and the selector confirmation text.\n\n## Errors\n- Parameter validation in `packages/coding-agent/src/tools/debug.ts` throws `ToolError` with explicit messages such as:\n  - `program is required for launch`\n  - `attach requires pid or port`\n  - `set_breakpoint requires file+line or function`\n  - `variables requires variable_ref or scope_id`\n  - `memory_reference is required for read_memory`\n  - `count is required for read_memory`\n  - `data is required for write_memory`\n  - `command is required for custom_request`\n- Adapter selection failure throws `No debugger adapter available. Installed adapters: ...`.\n- Capability-gated actions throw from `requireCapability(...)`, e.g. `Active adapter does not support memory reads.`\n- No-session and state errors come from `DapSessionManager`, e.g. `No active debug session. Launch or attach first.`, `No active stack frame. Run stack_trace first or supply frame_id.`, `Debugger reported no threads.`\n- Launching a second live session throws `Debug session <id> is still active. Terminate it before launching another.`\n- DAP transport/request failures surface as thrown errors from `DapClient`:\n  - `DAP request <command> timed out after <ms>ms`\n  - `DAP event <event> timed out after <ms>ms`\n  - `DAP adapter <name> is not running`\n  - `DAP adapter exited (code N): <stderr>` or `DAP adapter exited unexpectedly (code N)`\n  - adapter response `message` when a DAP request fails\n- `continue` / `step_*` are intentionally non-fatal when the target stays running past the timeout: they return `details.timedOut = true` and `state: \"running\"` instead of throwing.\n- `terminate` suppresses adapter errors while sending `terminate`/`disconnect`; it still disposes the client and returns the last summary when possible.\n- Interactive selector handlers report UI errors instead of throwing:\n  - profiler start/stop, report bundling, log reading, system-info collection, cache clearing, and artifact opening use `ctx.showError(...)` / `ctx.showWarning(...)`\n  - empty logs and empty artifact caches are warnings/status messages, not failures\n  - copy failures in log/raw-SSE viewers become status/error text in the UI\n- Report-bundle helpers are intentionally best-effort for many file reads: missing session files, missing artifact dirs, unreadable artifact files, missing log dirs, inaccessible cache dirs, and missing subagent files are skipped silently.\n- `collectSystemInfo()` is best-effort for CPU probing; failure there falls back to `Unknown CPU`.\n\n## Notes\n- `packages/coding-agent/src/prompts/tools/debug.md` tells the model only one active session is supported; that is not advisory, it is enforced in code.\n- `configurationDone` is sent automatically both during launch/attach handshake and lazily before later requests if the adapter required it and the initial handshake did not complete.\n- `startDebugging` reverse requests are acknowledged but not implemented; child debug sessions are not spawned.\n- `output` exposes the merged `output` event stream only; the tool does not distinguish stdout, stderr, and console categories.\n- Session summaries expose `needsConfigurationDone`; this is derived from adapter capabilities and whether `configurationDone` has been sent.\n- Source breakpoint file paths are normalized with `path.resolve()` before caching and sending to the adapter.\n- `evaluate` defaults to `repl`, so the tool can forward raw debugger commands when the adapter supports them.\n- `disassemble` resolves its target from `memory_reference` first, then `instruction_reference`; it throws if neither is present.\n- `RawSseDebugBuffer.recordEvent()` increments `totalEvents` before bounded retention. A snapshot can therefore show fewer retained records than total observed events.\n- Raw SSE buffer listener failures are swallowed so viewer bugs do not break capture.\n- `createDebugLogSource()` walks daily log files newest-first, but `loadOlderLogs()` reverses each requested slice before concatenation so older chunks prepend in chronological order.\n- `clearArtifactCache()` deletes directories by directory mtime, not per-file age.\n- `addDirectoryToArchive()` reads artifact files as text with `Bun.file(...).text()`. Binary artifact contents are not preserved byte-for-byte in the report bundle.\n- The tool renderer truncates displayed output for the TUI preview, but the underlying text result still contains the full returned string.\n",
-	"tools/edit.md": "# edit\n\n> Applies source edits; default mode is the hashline patch language consumed from a single `input` string.\n\n## Source\n- Entry: `packages/coding-agent/src/edit/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/hashline.md`\n- Key collaborators:\n  - `packages/coding-agent/src/utils/edit-mode.ts` — selects active edit mode\n  - `packages/coding-agent/src/hashline/grammar.lark` — custom-tool grammar for hashline mode\n  - `packages/coding-agent/src/hashline/input.ts` — splits `¶PATH` sections\n  - `packages/coding-agent/src/hashline/parser.ts` — parses op-prefixed edits and verbatim payload lines\n  - `packages/coding-agent/src/hashline/apply.ts` — validates anchors and applies edits\n  - `packages/coding-agent/src/hashline/anchors.ts` — stale-anchor mismatch formatting\n  - `packages/coding-agent/src/hashline/recovery.ts` — cache-based stale-anchor recovery\n  - `packages/coding-agent/src/hashline/hash.ts` — computes 4-hex file hashes and `LINE:TEXT` display lines shared with `read`/`search`\n  - `packages/coding-agent/src/edit/file-read-cache.ts` — per-session read snapshot cache\n  - `packages/coding-agent/src/tools/read.ts` — emits anchored lines and records read snapshots\n  - `packages/coding-agent/src/tools/search.ts` — records sparse snapshots from matches/context\n  - `packages/coding-agent/src/tools/fs-cache-invalidation.ts` — invalidates FS scan caches after writes\n  - `packages/coding-agent/src/edit/streaming.ts` — computes in-flight diff previews for the TUI\n\n## Inputs\n\n### Hashline mode (default)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `input` | `string` | Yes | One or more edit sections. Anchored sections must start with `¶PATH#HASH`; unbound `¶PATH` is allowed only for new-file / `BOF` / `EOF` boundary inserts. Optional `*** Begin Patch` / `*** End Patch` envelope is ignored if present. |\n\nPatch language inside `input`:\n\n- Section header: `¶PATH#HASH` for anchored edits, `¶PATH` for BOF/EOF-only inserts\n- Insert after: `LINE↓[payload]`\n- Insert before: `LINE↑[payload]`\n- Replace range: `A-B:[payload]`\n- Single-line replace sugar: `A:[payload]` means `A-A:[payload]`\n- Delete range: `A-B!`\n- Single-line delete sugar: `A!` means `A-A!`\n- **Payload semantics:** the first payload line is whatever follows the sigil on the op line itself; additional payload lines follow on subsequent lines and append after the inline first line. An empty inline (just the sigil followed by a newline) means the first payload line is empty. So bare `A↑` / `A↓` insert one blank line, and bare `A:` / `A-B:` replace the line/range with one blank line. But `A↓\\nfoo` inserts blank-then-`foo`, not just `foo` — for a single-line insert, put `foo` inline as `A↓foo`.\n- `!` deletes and forbids payload.\n- Read lines like `84:content` are already valid single-line replacements.\n- Special anchors: `BOF`, `EOF` (both support inline payload, e.g. `BOF↓export const done = true;`).\n- Anchor token: bare line number, for example `41`\n- File binding: 4-hex hash in the section header, for example `¶src/a.ts#1a2b`\n\nAnchors come from `read`/`search` output. `read` emits a `¶PATH#HASH` header and lines as `LINE:TEXT`; copy the header into the edit section and copy only the line number into op lines.\n\nOther edit modes exist (`replace`, `patch`, `apply_patch`) and are selected outside the tool payload by `resolveEditMode()` in `packages/coding-agent/src/utils/edit-mode.ts`. Their schemas are different; this document covers the default hashline mode.\n\n## Outputs\n- Single-shot tool result; hashline mode does not use a `resolve` preview/apply handshake.\n- `content` contains one text block per call. For a successful single-file edit it is either:\n  - `<path>:` plus a compact diff preview from `packages/coding-agent/src/hashline/diff-preview.ts`, or\n  - `Updated <path>` / `Created <path>` when no compact preview text is emitted.\n- Parse or recovery warnings are appended as:\n\n```text\nWarnings:\n...\n```\n\n- `details` is `EditToolDetails` from `packages/coding-agent/src/edit/renderer.ts`:\n  - `diff`: unified diff string\n  - `firstChangedLine`: first changed post-edit line\n  - `diagnostics`: LSP/format result if available\n  - `op`: `\"create\"` or `\"update\"` for hashline mode\n  - `meta`: output metadata\n  - `perFileResults`: present for multi-section input\n- Multi-section input returns one aggregated result with combined text and per-file details.\n- While the model is still typing arguments, the TUI can compute a diff preview with `packages/coding-agent/src/edit/streaming.ts`; that preview is not a deferred action and does not block execution.\n\n## Flow\n1. `EditTool.execute()` in `packages/coding-agent/src/edit/index.ts` resolves the active mode. Default is `hashline`; `customFormat` exposes `packages/coding-agent/src/hashline/grammar.lark` with `$HFILE_HASH$` / `$HOP_INSERT_BEFORE$` / `$HOP_INSERT_AFTER$` / `$HOP_REPLACE$` / `$HOP_CHARS$` / `$HFILE$` placeholders filled from `packages/coding-agent/src/hashline/hash.ts`.\n2. `executeHashlineSingle()` in `packages/coding-agent/src/hashline/execute.ts` splits the raw `input` into `¶PATH#HASH` / `¶PATH` sections with `splitHashlineInputs()`.\n3. If multiple sections target the same path, `mergeSamePathSections()` concatenates them before execution so every op still refers to the original file snapshot.\n4. Multi-section calls run a preflight pass (`preflightHashlineSection()`): parse ops, enforce plan-mode write rules, load the current file, reject anchor-scoped edits against missing files, reject auto-generated files, apply edits in memory, and fail if the result is a no-op. This prevents partial batches.\n5. `parseHashlineWithWarnings()` in `packages/coding-agent/src/hashline/parser.ts` tokenizes the diff body:\n   - ignores blank lines and optional `*** Begin Patch`\n   - stops at `*** End Patch`\n   - stops at `*** Abort` and emits `ABORT_WARNING`\n   - turns `↓` / `↑` payload runs (inline plus subsequent lines) into one `insert` edit per payload line\n   - turns `A-B:` with payload into inserts before `A`, then deletes for `A-B`\n   - turns `A-B!` into one `delete` edit per line in the range; payload is forbidden\n6. `executeHashlineSingle()` computes the current file hash before applying anchored edits. If it differs from the section `#HASH`, recovery tries the read/search snapshot cache before any write.\n7. `applyHashlineEdits()` validates only line bounds, then applies the already hash-bound line-number edits.\n8. Recovery replays the edits against the cached snapshot for the section hash (`packages/coding-agent/src/edit/file-read-cache.ts`), then 3-way merges the result onto current disk content using `Diff.applyPatch(..., { fuzzFactor: 0 })` in `packages/coding-agent/src/hashline/recovery.ts`. On success the edit proceeds with a warning; on failure a `HashlineMismatchError` is surfaced.\n9. Before splicing lines, `absorbReplacementBoundaryDuplicates()` normalizes some malformed-but-recoverable ranges:\n   - duplicate prefix/suffix lines adjacent to a replacement can be absorbed by widening the delete range\n   - pure inserts can auto-drop duplicated leading/trailing payload lines when `edit.hashlineAutoDropPureInsertDuplicates` is enabled\n   - all such fixes append warnings\n10. `after_anchor` inserts are normalized to `before_anchor` of the next line, or `EOF` if the anchor was the last line.\n11. Anchor-targeted edits are bucketed by target line and applied bottom-up so earlier splices do not invalidate later original line numbers. `BOF` and `EOF` inserts are applied after that.\n12. The edited text is restored to the original BOM and line ending style with helpers from `packages/coding-agent/src/edit/normalize.ts` and persisted via `serializeEditFileText()` in `packages/coding-agent/src/edit/read-file.ts`.\n13. The writethrough callback from `createLspWritethrough()` may format the file and fetch diagnostics. Late diagnostics are queued back into session state as a hidden deferred message by `EditTool.#injectLateDiagnostics()` in `packages/coding-agent/src/edit/index.ts`.\n14. `invalidateFsScanAfterWrite()` calls `invalidateFsScanCache(path)` so filesystem-backed tools do not serve stale scan results.\n15. The session file-read cache is refreshed with the post-edit file text via `recordContiguous()`, making the just-written content the new recovery base for subsequent stale-anchor merges.\n16. The final response is built from a unified diff (`generateDiffString()`), a compact preview, and any accumulated warnings.\n\n## Modes / Variants\n- `hashline` — default mode; line-anchored patch language described here (`packages/coding-agent/src/utils/edit-mode.ts`).\n- `replace` — exact/fuzzy old/new text replacement (`packages/coding-agent/src/edit/modes/replace.ts`).\n- `patch` — structured JSON diff-hunk mode (`packages/coding-agent/src/edit/modes/patch.ts`).\n- `apply_patch` — freeform Codex-style `*** Begin Patch` envelope, internally expanded into patch-mode entries (`packages/coding-agent/src/edit/modes/apply-patch.ts`).\n\nHashline op examples (single-line payloads are inline; multi-line payloads continue on subsequent lines):\n\n```text\n¶src/a.ts#1a2b\n4↓const added = true;\n```\n\n```text\n¶src/a.ts#1a2b\n4↑const addedBefore = true;\n```\n\n```text\n¶src/a.ts#1a2b\n4-6:const replacement = true;\n```\n\n```text\n¶src/a.ts#1a2b\n4-5:const clean = (name || DEF).trim();\nreturn clean.length === 0 ? DEF : clean.toUpperCase();\n```\n\n```text\n¶src/a.ts#1a2b\n4:const clean = (name || DEF).trim();\n```\n\nBOF/EOF examples:\n\n```text\n¶src/a.ts\nBOF↓const HEADER = true;\n```\n\n```text\n¶src/a.ts\nEOF↓export const done = true;\n```\n\nDelete / blank examples:\n\n```text\n¶src/a.ts#1a2b\n4!\n```\n\n```text\n¶src/a.ts#1a2b\n4:\n```\n\n```text\n¶src/a.ts#1a2b\n4-6!\n```\n\nMulti-file example:\n\n```text\n¶src/a.ts#1a2b\n4:const enabled = true;\n¶src/b.ts#3c4d\n20!\n```\n\n## Side Effects\n- Filesystem\n  - Reads target files with `readEditFileText()`.\n  - Writes full updated file contents with `serializeEditFileText()`.\n  - Preserves BOM and original line-ending style.\n- Subprocesses / native bindings\n  - `createLspWritethrough()` may trigger formatter / diagnostics work through the LSP subsystem.\n  - `invalidateFsScanAfterWrite()` calls native `invalidateFsScanCache()` from `@oh-my-pi/pi-natives`.\n- Session state\n  - Reads and updates the per-session `FileReadCache` used for stale-anchor recovery.\n  - Stores pending deferred-diagnostics abort controllers per path inside `EditTool`.\n  - Queues late diagnostics back into the session transcript as a hidden custom message.\n- Background work / cancellation\n  - A new edit to the same path aborts the prior deferred diagnostics fetch for that path (`packages/coding-agent/src/edit/index.ts`).\n  - The tool itself is marked `nonAbortable = true` and `concurrency = \"exclusive\"` in `packages/coding-agent/src/edit/index.ts`.\n\n## Limits & Caps\n- Default mode is `hashline` (`DEFAULT_EDIT_MODE`) in `packages/coding-agent/src/utils/edit-mode.ts`.\n- File hashes are 4 lowercase hex chars from `computeFileHash()` in `packages/coding-agent/src/hashline/hash.ts`.\n- The visible mismatch report shows 2 lines of context on each side (`MISMATCH_CONTEXT`) in `packages/coding-agent/src/hashline/constants.ts`.\n- Stale-anchor recovery uses `fuzzFactor: 0` (`HASHLINE_RECOVERY_FUZZ_FACTOR`) in `packages/coding-agent/src/hashline/recovery.ts`.\n- The per-session read cache keeps at most 30 paths (`MAX_PATHS_PER_SESSION`) in `packages/coding-agent/src/edit/file-read-cache.ts`.\n- Hashline streaming chunk defaults are 200 lines or 64 KiB per chunk (`packages/coding-agent/src/hashline/types.ts`, consumed by `packages/coding-agent/src/hashline/stream.ts`).\n- `HL_OP_INSERT_BEFORE` is `↑`, `HL_OP_INSERT_AFTER` is `↓`, `HL_OP_REPLACE` is `:`, `HL_OP_DELETE` is `!`, `HL_OP_CHARS` is `↑↓:!`, `HL_FILE_PREFIX` is `¶`, `HL_FILE_HASH_SEP` is `#`, and `HL_LINE_BODY_SEP` is `:` (`packages/coding-agent/src/hashline/hash.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- Empty header:\n  - `Input header \"¶\" is empty; provide a file path.`\n- Missing hash for anchored edit:\n  - `Missing hashline file hash for anchored edit to <path>; use ¶<path>#hash from your latest read.`\n- Line-hash anchors in edit ops:\n  - `line N: edit ops use bare line numbers. Copy the ¶PATH#hash header, then use anchors like 42, 42-45, BOF, or EOF.`\n- Bad anchor token:\n  - `line N: expected a line number such as \"119\"; got \"...\".`\n- Bad range syntax:\n  - `line N: range must be LINE or LINE-LINE (one dash, no spaces); got ...`\n  - `line N: range A-B ends before it starts.`\n- Payload forbidden for `!`:\n  - `line N: ! deletes only. Payload is forbidden after !; use : to replace.`\n- Stray payload line:\n  - `line N: payload line has no preceding ↑, ↓, :, or ! operation.`\n- Unknown op:\n  - `line N: unrecognized op. Use LINE↑ (insert before), LINE↓ (insert after), LINE: / A-B: (replace), or LINE! / A-B! (delete).`\n- Missing file for anchor-scoped edits:\n  - `File not found: <path>`\n- Out-of-range anchor:\n  - `Line N does not exist (file has M lines)`\n- Stale file hash throws `HashlineMismatchError`. The error contains both hashes, re-read guidance, and nearby current file lines as `*LINE:TEXT` / ` LINE:TEXT`.\n- No-op edit:\n  - `Edits to <path> resulted in no changes being made.`\n- Recovery failure is silent internally: if cache-based merge cannot prove a valid result, the mismatch error is surfaced unchanged.\n\n## Notes\n- `read` and `search` are the authoritative source of section hashes. Copy `¶PATH#HASH`; op lines use bare line numbers and do not want the trailing `:TEXT`.\n- Multi-op patches are parsed against the original file snapshot. Do not renumber later anchors after earlier ops; `applyHashlineEdits()` buckets and applies them bottom-up.\n- Failed hand-edits often come from sequentially shifting later anchors inside the same patch. Treat every op as using the line numbers from the original section header.\n- `A-B:` is not a primitive replace in the parser. With payload, it expands to inserts before `A` plus deletes for `A-B`. `A-B!` is the direct delete form. Bare `A:` / `A-B:` (no payload) replaces with a single blank line; bare `↑` / `↓` insert a blank line.\n- Inline payload tip: trailing whitespace on the op line is trimmed. To preserve trailing spaces in the inserted/replacement content, put that content on the next line instead of inline.\n- `computeFileHash()` normalizes CR characters and trailing whitespace before hashing. The section survives line-ending and trailing-space-only changes, but not substantive file edits.\n- `splitHashlineInputs()` normalizes absolute `¶PATH#HASH` headers back to a cwd-relative path when the file is inside the current working tree. Headers with any run of leading `¶` chars (e.g. `¶foo.ts`, `¶¶foo.ts`, `¶¶¶foo.ts`) are accepted; the canonical form is `¶PATH#HASH` for anchored edits.\n- Optional `*** Begin Patch` / `*** End Patch` markers are accepted in hashline mode, but the file sections are still `¶PATH#HASH`-based, not Codex `*** Update File:` hunks.\n- `*** Abort` terminates parsing early and returns `ABORT_WARNING`; ops parsed before the marker still apply.\n- File-read cache invalidation is conflict-based, not write-through invalidation. If `read` later records content for a line that disagrees with the cached snapshot, the entire snapshot for that path is replaced with the newly observed lines (`packages/coding-agent/src/edit/file-read-cache.ts`).\n- There is no resolve-style apply/discard phase for hashline edits. The only preview path is the transient TUI diff preview in `packages/coding-agent/src/edit/streaming.ts`.\n",
+	"tools/edit.md": "# edit\n\n> Applies source edits; default mode is the hashline patch language consumed from a single `input` string.\n\n## Source\n- Entry: `packages/coding-agent/src/edit/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/hashline.md`\n- Key collaborators:\n  - `packages/coding-agent/src/utils/edit-mode.ts` — selects active edit mode\n  - `packages/coding-agent/src/hashline/grammar.lark` — custom-tool grammar for hashline mode\n  - `packages/coding-agent/src/hashline/input.ts` — splits `¶PATH` sections\n  - `packages/coding-agent/src/hashline/executor.ts` / `tokenizer.ts` — parses op-prefixed edits and `+`-prefixed payload continuation lines\n  - `packages/coding-agent/src/hashline/apply.ts` — validates anchors and applies edits\n  - `packages/coding-agent/src/hashline/anchors.ts` — stale-anchor mismatch formatting\n  - `packages/coding-agent/src/hashline/recovery.ts` — cache-based stale-anchor recovery\n  - `packages/coding-agent/src/hashline/hash.ts` — computes 4-hex file hashes and `LINE:TEXT` display lines shared with `read`/`search`\n  - `packages/coding-agent/src/edit/file-read-cache.ts` — per-session read snapshot cache\n  - `packages/coding-agent/src/tools/read.ts` — emits anchored lines and records read snapshots\n  - `packages/coding-agent/src/tools/search.ts` — records sparse snapshots from matches/context\n  - `packages/coding-agent/src/tools/fs-cache-invalidation.ts` — invalidates FS scan caches after writes\n  - `packages/coding-agent/src/edit/streaming.ts` — computes in-flight diff previews for the TUI\n\n## Inputs\n\n### Hashline mode (default)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `input` | `string` | Yes | One or more edit sections. Anchored sections must start with `¶PATH#HASH`; unbound `¶PATH` is allowed only for new-file / `BOF` / `EOF` boundary inserts. Optional `*** Begin Patch` / `*** End Patch` envelope is ignored if present. |\n\nPatch language inside `input`:\n\n- Section header: `¶PATH#HASH` for anchored edits, `¶PATH` for BOF/EOF-only inserts\n- Insert after: `LINE↓[payload]`\n- Insert before: `LINE↑[payload]`\n- Replace range: `A-B:[payload]`\n- Single-line replace sugar: `A:[payload]` means `A-A:[payload]`\n- Delete range: `A-B!`\n- Single-line delete sugar: `A!` means `A-A!`\n- **Payload semantics:** the first payload line may follow the sigil on the op line itself. Additional payload lines must be on subsequent lines prefixed with `+`; that delimiter is stripped before writing. Use `+` alone for an empty payload line, and `++text` to write a payload line that begins with `+text`. Bare `A↑` / `A↓` insert one blank line, and bare `A:` / `A-B:` replace the line/range with one blank line.\n- `!` deletes and forbids payload.\n- Read lines like `84:content` are already valid single-line replacements.\n- Special anchors: `BOF`, `EOF` (both support inline payload, e.g. `BOF↓export const done = true;`).\n- Anchor token: bare line number, for example `41`\n- File binding: 4-hex hash in the section header, for example `¶src/a.ts#1a2b`\n\nAnchors come from `read`/`search` output. `read` emits a `¶PATH#HASH` header and lines as `LINE:TEXT`; copy the header into the edit section and copy only the line number into op lines.\n\nOther edit modes exist (`replace`, `patch`, `apply_patch`) and are selected outside the tool payload by `resolveEditMode()` in `packages/coding-agent/src/utils/edit-mode.ts`. Their schemas are different; this document covers the default hashline mode.\n\n## Outputs\n- Single-shot tool result; hashline mode does not use a `resolve` preview/apply handshake.\n- `content` contains one text block per call. For a successful single-file edit it is either:\n  - `<path>:` plus a compact diff preview from `packages/coding-agent/src/hashline/diff-preview.ts`, or\n  - `Updated <path>` / `Created <path>` when no compact preview text is emitted.\n- Parse or recovery warnings are appended as:\n\n```text\nWarnings:\n...\n```\n\n- `details` is `EditToolDetails` from `packages/coding-agent/src/edit/renderer.ts`:\n  - `diff`: unified diff string\n  - `firstChangedLine`: first changed post-edit line\n  - `diagnostics`: LSP/format result if available\n  - `op`: `\"create\"` or `\"update\"` for hashline mode\n  - `meta`: output metadata\n  - `perFileResults`: present for multi-section input\n- Multi-section input returns one aggregated result with combined text and per-file details.\n- While the model is still typing arguments, the TUI can compute a diff preview with `packages/coding-agent/src/edit/streaming.ts`; that preview is not a deferred action and does not block execution.\n\n## Flow\n1. `EditTool.execute()` in `packages/coding-agent/src/edit/index.ts` resolves the active mode. Default is `hashline`; `customFormat` exposes `packages/coding-agent/src/hashline/grammar.lark` with `$HFILE_HASH$` / `$HOP_INSERT_BEFORE$` / `$HOP_INSERT_AFTER$` / `$HOP_REPLACE$` / `$HOP_CHARS$` / `$HFILE$` placeholders filled from `packages/coding-agent/src/hashline/hash.ts`.\n2. `executeHashlineSingle()` in `packages/coding-agent/src/hashline/execute.ts` splits the raw `input` into `¶PATH#HASH` / `¶PATH` sections with `splitHashlineInputs()`.\n3. If multiple sections target the same path, `mergeSamePathSections()` concatenates them before execution so every op still refers to the original file snapshot.\n4. Multi-section calls run a preflight pass (`preflightHashlineSection()`): parse ops, enforce plan-mode write rules, load the current file, reject anchor-scoped edits against missing files, reject auto-generated files, apply edits in memory, and fail if the result is a no-op. This prevents partial batches.\n5. `parseHashline()` in `packages/coding-agent/src/hashline/executor.ts` tokenizes the diff body:\n   - ignores raw blank lines and optional `*** Begin Patch`\n   - stops at `*** End Patch`\n   - stops at `*** Abort` and emits `ABORT_WARNING`\n   - turns `↓` / `↑` payload runs (inline plus `+`-prefixed subsequent lines) into one `insert` edit per payload line\n   - turns `A-B:` with payload into inserts before `A`, then deletes for `A-B`\n   - turns `A-B!` into one `delete` edit per line in the range; payload is forbidden\n6. `executeHashlineSingle()` computes the current file hash before applying anchored edits. If it differs from the section `#HASH`, recovery tries the read/search snapshot cache before any write.\n7. `applyHashlineEdits()` validates only line bounds, then applies the already hash-bound line-number edits.\n8. Recovery replays the edits against the cached snapshot for the section hash (`packages/coding-agent/src/edit/file-read-cache.ts`), then 3-way merges the result onto current disk content using `Diff.applyPatch(..., { fuzzFactor: 0 })` in `packages/coding-agent/src/hashline/recovery.ts`. On success the edit proceeds with a warning; on failure a `HashlineMismatchError` is surfaced.\n9. Before splicing lines, `absorbReplacementBoundaryDuplicates()` normalizes some malformed-but-recoverable ranges:\n   - duplicate prefix/suffix lines adjacent to a replacement can be absorbed by widening the delete range\n   - pure inserts can auto-drop duplicated leading/trailing payload lines when `edit.hashlineAutoDropPureInsertDuplicates` is enabled\n   - all such fixes append warnings\n10. `after_anchor` inserts are normalized to `before_anchor` of the next line, or `EOF` if the anchor was the last line.\n11. Anchor-targeted edits are bucketed by target line and applied bottom-up so earlier splices do not invalidate later original line numbers. `BOF` and `EOF` inserts are applied after that.\n12. The edited text is restored to the original BOM and line ending style with helpers from `packages/coding-agent/src/edit/normalize.ts` and persisted via `serializeEditFileText()` in `packages/coding-agent/src/edit/read-file.ts`.\n13. The writethrough callback from `createLspWritethrough()` may format the file and fetch diagnostics. Late diagnostics are queued back into session state as a hidden deferred message by `EditTool.#injectLateDiagnostics()` in `packages/coding-agent/src/edit/index.ts`.\n14. `invalidateFsScanAfterWrite()` calls `invalidateFsScanCache(path)` so filesystem-backed tools do not serve stale scan results.\n15. The session file-read cache is refreshed with the post-edit file text via `recordContiguous()`, making the just-written content the new recovery base for subsequent stale-anchor merges.\n16. The final response is built from a unified diff (`generateDiffString()`), a compact preview, and any accumulated warnings.\n\n## Modes / Variants\n- `hashline` — default mode; line-anchored patch language described here (`packages/coding-agent/src/utils/edit-mode.ts`).\n- `replace` — exact/fuzzy old/new text replacement (`packages/coding-agent/src/edit/modes/replace.ts`).\n- `patch` — structured JSON diff-hunk mode (`packages/coding-agent/src/edit/modes/patch.ts`).\n- `apply_patch` — freeform Codex-style `*** Begin Patch` envelope, internally expanded into patch-mode entries (`packages/coding-agent/src/edit/modes/apply-patch.ts`).\n\nHashline op examples (single-line payloads are inline; multi-line payloads continue on `+`-prefixed subsequent lines):\n\n```text\n¶src/a.ts#1a2b\n4↓const added = true;\n```\n\n```text\n¶src/a.ts#1a2b\n4↑const addedBefore = true;\n```\n\n```text\n¶src/a.ts#1a2b\n4-6:const replacement = true;\n```\n\n```text\n¶src/a.ts#1a2b\n4-5:const clean = (name || DEF).trim();\n+return clean.length === 0 ? DEF : clean.toUpperCase();\n```\n\n```text\n¶src/a.ts#1a2b\n4:const clean = (name || DEF).trim();\n```\n\nBOF/EOF examples:\n\n```text\n¶src/a.ts\nBOF↓const HEADER = true;\n```\n\n```text\n¶src/a.ts\nEOF↓export const done = true;\n```\n\nDelete / blank examples:\n\n```text\n¶src/a.ts#1a2b\n4!\n```\n\n```text\n¶src/a.ts#1a2b\n4:\n```\n\n```text\n¶src/a.ts#1a2b\n4-6!\n```\n\nMulti-file example:\n\n```text\n¶src/a.ts#1a2b\n4:const enabled = true;\n¶src/b.ts#3c4d\n20!\n```\n\n## Side Effects\n- Filesystem\n  - Reads target files with `readEditFileText()`.\n  - Writes full updated file contents with `serializeEditFileText()`.\n  - Preserves BOM and original line-ending style.\n- Subprocesses / native bindings\n  - `createLspWritethrough()` may trigger formatter / diagnostics work through the LSP subsystem.\n  - `invalidateFsScanAfterWrite()` calls native `invalidateFsScanCache()` from `@oh-my-pi/pi-natives`.\n- Session state\n  - Reads and updates the per-session `FileReadCache` used for stale-anchor recovery.\n  - Stores pending deferred-diagnostics abort controllers per path inside `EditTool`.\n  - Queues late diagnostics back into the session transcript as a hidden custom message.\n- Background work / cancellation\n  - A new edit to the same path aborts the prior deferred diagnostics fetch for that path (`packages/coding-agent/src/edit/index.ts`).\n  - The tool itself is marked `nonAbortable = true` and `concurrency = \"exclusive\"` in `packages/coding-agent/src/edit/index.ts`.\n\n## Limits & Caps\n- Default mode is `hashline` (`DEFAULT_EDIT_MODE`) in `packages/coding-agent/src/utils/edit-mode.ts`.\n- File hashes are 4 lowercase hex chars from `computeFileHash()` in `packages/coding-agent/src/hashline/hash.ts`.\n- The visible mismatch report shows 2 lines of context on each side (`MISMATCH_CONTEXT`) in `packages/coding-agent/src/hashline/constants.ts`.\n- Stale-anchor recovery uses `fuzzFactor: 0` (`HASHLINE_RECOVERY_FUZZ_FACTOR`) in `packages/coding-agent/src/hashline/recovery.ts`.\n- The per-session read cache keeps at most 30 paths (`MAX_PATHS_PER_SESSION`) in `packages/coding-agent/src/edit/file-read-cache.ts`.\n- Hashline streaming chunk defaults are 200 lines or 64 KiB per chunk (`packages/coding-agent/src/hashline/types.ts`, consumed by `packages/coding-agent/src/hashline/stream.ts`).\n- `HL_OP_INSERT_BEFORE` is `↑`, `HL_OP_INSERT_AFTER` is `↓`, `HL_OP_REPLACE` is `:`, `HL_OP_DELETE` is `!`, `HL_OP_CHARS` is `↑↓:!`, `HL_FILE_PREFIX` is `¶`, `HL_FILE_HASH_SEP` is `#`, and `HL_LINE_BODY_SEP` is `:` (`packages/coding-agent/src/hashline/hash.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- Empty header:\n  - `Input header \"¶\" is empty; provide a file path.`\n- Missing hash for anchored edit:\n  - `Missing hashline file hash for anchored edit to <path>; use ¶<path>#hash from your latest read.`\n- Line-hash anchors in edit ops:\n  - `line N: edit ops use bare line numbers. Copy the ¶PATH#hash header, then use anchors like 42, 42-45, BOF, or EOF.`\n- Bad anchor token:\n  - `line N: expected a line number such as \"119\"; got \"...\".`\n- Bad range syntax:\n  - `line N: range must be LINE or LINE-LINE (one dash, no spaces); got ...`\n  - `line N: range A-B ends before it starts.`\n- Payload forbidden for `!`:\n  - `line N: ! deletes only. Payload is forbidden after !; use : to replace.`\n- Missing `+` on a continuation line:\n  - `line N: payload continuation lines must start with +.`\n- Stray payload line:\n  - `line N: payload line has no preceding ↑, ↓, :, or ! operation.`\n- Unknown op:\n  - `line N: unrecognized op. Use LINE↑ (insert before), LINE↓ (insert after), LINE: / A-B: (replace), or LINE! / A-B! (delete).`\n- Missing file for anchor-scoped edits:\n  - `File not found: <path>`\n- Out-of-range anchor:\n  - `Line N does not exist (file has M lines)`\n- Stale file hash throws `HashlineMismatchError`. The error contains both hashes, re-read guidance, and nearby current file lines as `*LINE:TEXT` / ` LINE:TEXT`.\n- No-op edit:\n  - `Edits to <path> resulted in no changes being made.`\n- Recovery failure is silent internally: if cache-based merge cannot prove a valid result, the mismatch error is surfaced unchanged.\n\n## Notes\n- `read` and `search` are the authoritative source of section hashes. Copy `¶PATH#HASH`; op lines use bare line numbers and do not want the trailing `:TEXT`.\n- Multi-op patches are parsed against the original file snapshot. Do not renumber later anchors after earlier ops; `applyHashlineEdits()` buckets and applies them bottom-up.\n- Failed hand-edits often come from sequentially shifting later anchors inside the same patch. Treat every op as using the line numbers from the original section header.\n- Two consecutive `A-B:` ops on the *identical* range in the same hunk are coalesced: the second op's payload wins and the first is dropped (a \"Detected an identical-range before/after replace pair\" warning is appended). Other overlap shapes — different ranges, `A-B:` overlapping a `N!`/`N:`, or two `!` deletes on the same line — still throw `line N: anchor line X is already targeted by the :/! op on line Y`. The coalesce only fires while the first op is still pending; cross-hunk duplicates still throw.\n- `A-B:` is not a primitive replace in the parser. With payload, it expands to inserts before `A` plus deletes for `A-B`. `A-B!` is the direct delete form. Bare `A:` / `A-B:` (no payload) replaces with a single blank line; bare `↑` / `↓` insert a blank line.\n- Inline payload tip: trailing whitespace on the op line is trimmed. To preserve trailing spaces in the inserted/replacement content, put that content on the next line instead of inline.\n- `computeFileHash()` normalizes CR characters and trailing whitespace before hashing. The section survives line-ending and trailing-space-only changes, but not substantive file edits.\n- `splitHashlineInputs()` normalizes absolute `¶PATH#HASH` headers back to a cwd-relative path when the file is inside the current working tree. Headers with any run of leading `¶` chars (e.g. `¶foo.ts`, `¶¶foo.ts`, `¶¶¶foo.ts`) are accepted; the canonical form is `¶PATH#HASH` for anchored edits.\n- Optional `*** Begin Patch` / `*** End Patch` markers are accepted in hashline mode, but the file sections are still `¶PATH#HASH`-based, not Codex `*** Update File:` hunks.\n- `*** Abort` terminates parsing early and returns `ABORT_WARNING`; ops parsed before the marker still apply.\n- File-read cache invalidation is conflict-based, not write-through invalidation. If `read` later records content for a line that disagrees with the cached snapshot, the entire snapshot for that path is replaced with the newly observed lines (`packages/coding-agent/src/edit/file-read-cache.ts`).\n- There is no resolve-style apply/discard phase for hashline edits. The only preview path is the transient TUI diff preview in `packages/coding-agent/src/edit/streaming.ts`.\n",
 	"tools/eval.md": "# eval\n\n> Execute Python or JavaScript code in persistent cell-based runtimes.\n\n> **Notice:** Do not shell out to `python -c`/`python -e`, `bun -e`, or `node -e` via the `bash` tool for ad-hoc code execution. Use this tool instead — it gives you persistent state across cells, structured `display()` output, image/JSON capture, and proper cancellation/timeout handling that one-shot `-e`/`-c` invocations cannot provide.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/eval.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/eval.md`\n- Key collaborators:\n  - `packages/coding-agent/src/eval/backend.ts` — backend execution contract\n  - `packages/coding-agent/src/eval/js/index.ts` — JS backend adapter\n  - `packages/coding-agent/src/eval/js/executor.ts` — JS execution + output sink\n  - `packages/coding-agent/src/eval/js/context-manager.ts` — persistent VM contexts, prelude, tool bridge\n  - `packages/coding-agent/src/eval/js/prelude.txt` — JS global helpers\n  - `packages/coding-agent/src/eval/py/index.ts` — Python backend adapter\n  - `packages/coding-agent/src/eval/py/executor.ts` — kernel session retention, reset, cleanup\n  - `packages/coding-agent/src/eval/py/kernel.ts` — Jupyter gateway/kernel protocol, display capture\n  - `packages/coding-agent/src/eval/py/prelude.py` — Python helper functions and status events\n  - `packages/coding-agent/src/session/streaming-output.ts` — truncation, artifacts, streamed chunks\n  - `docs/python-repl.md` — Python kernel/gateway internals\n\n## Inputs\n\nTool parameters are a JSON object with a single `cells` field — an ordered array of cell objects. Each cell is a structured record; there is no `*** Cell` header parsing, no language sniffing, and no implicit single-cell fallback. Cells run in array order; state persists within each language across cells and across tool calls.\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `cells` | `EvalCellInput[]` | Yes | Cells executed in order. At least one cell is required (`.min(1)`). |\n\nEach `EvalCellInput` (from `evalCellSchema` in `packages/coding-agent/src/tools/eval.ts`):\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `language` | `\"py\" \\| \"js\"` | Yes | Backend selector. `\"py\"` maps to the IPython/Jupyter kernel (`python` backend); `\"js\"` maps to the persistent JavaScript VM. |\n| `code` | `string` | Yes | Cell body, verbatim. JSON-encoded — embed newlines, quotes, and indentation directly; no fences, no headers. |\n| `title` | `string` | No | Short label rendered in the transcript (e.g. `\"imports\"`, `\"load config\"`). |\n| `timeout` | `integer` | No | Per-cell timeout in seconds, clamped to `1..600`. Defaults to 30 when omitted. |\n| `reset` | `boolean` | No | Wipe this cell's language kernel before running. Reset is per-language: a `py` cell's reset does not touch the JS VM and vice versa. Defaults to `false`. |\n\nMinimal example matching the live schema:\n\n```json\n{\n  \"cells\": [\n    { \"language\": \"py\", \"title\": \"imports\", \"timeout\": 10, \"code\": \"import json\\nfrom pathlib import Path\" },\n    { \"language\": \"py\", \"title\": \"load config\", \"code\": \"data = json.loads(read('package.json'))\\ndisplay(data)\" },\n    { \"language\": \"js\", \"title\": \"summary\", \"reset\": true, \"code\": \"const data = JSON.parse(await read('package.json'));\\ndisplay(data);\\nreturn data.name;\" }\n  ]\n}\n```\n\n## Outputs\n\nFinal result from `EvalTool.execute()` is single-shot, but `onUpdate` streams partial text and `details` while cells run.\n\nReturned shape:\n\n- `content`: one text block containing combined cell output, or `(no text output)` / `(no output)` when only rich outputs exist.\n- `details` (`EvalToolDetails` from `packages/coding-agent/src/eval/types.ts`):\n  - `cells`: per-cell code, status (`pending`/`running`/`complete`/`error`), output, duration, exit code, status events, markdown flag\n  - `language`: first backend used\n  - `languages`: distinct backends used, in first-use order\n  - `jsonOutputs`: structured values emitted via `display(...)`\n  - `images`: image payloads emitted by Python rich display or JS `display({ type: \"image\", ... })`\n  - `statusEvents`: aggregated helper/tool status events\n  - `notice`: backend fallback notice (currently unused; reserved for future per-cell notices)\n  - `meta`: truncation metadata\n  - `isError`: set on cell failure or cancellation\n\nRenderer behavior in `packages/coding-agent/src/tools/eval.ts`:\n\n- call preview renders each cell's `code` with syntax highlighting based on its declared `language`\n- result view renders each cell separately, including status, duration, and output\n- markdown outputs are rendered with the Markdown component instead of plain text\n- `jsonOutputs` render as a tree, collapsed or expanded depending on UI state\n- timeout / truncation notices render as dim metadata lines\n- images are carried in `details.images`; generic tool UI image handling renders them outside the text block\n\nSide-channel artifacts:\n\n- `session.allocateOutputArtifact?.(\"eval\")` may allocate an `artifact://...` backing store for spilled output.\n- Truncated output metadata points at that artifact when available.\n\n## Flow\n\n1. `EvalTool.execute()` in `packages/coding-agent/src/tools/eval.ts` receives `params.cells` already validated by the Zod schema — no string parsing step.\n2. For each cell, `execute()` maps `cell.language` to an `EvalLanguage` (`\"py\"` → `\"python\"`, `\"js\"` → `\"js\"`) and calls `resolveBackend(session, language)`:\n   - `python` is gated on `eval.py !== false` and `pythonBackend.isAvailable(session)`.\n   - `js` is gated on `eval.js !== false`.\n   - A disabled or unavailable requested backend throws `ToolError`; there is no auto-fallback or sniffing.\n3. The tool allocates an `OutputSink`, a `TailBuffer`, per-cell result objects, and a `sessionAbortController`. `session.trackEvalExecution?.(...)` can wrap the whole run for external cancellation tracking.\n4. It resolves the executor session id from `session.getEvalSessionId?.()`, falling back to `defaultEvalSessionId(session)`. Subagents inherit the parent's id so both sides share the same JS VM and Python kernel for each backend.\n5. Cells execute sequentially within one eval tool call. For each cell, `execute()`:\n   - clamps `(cell.timeout ?? 30) * 1000` ms through `clampTimeout(\"eval\", ...)`\n   - builds a combined abort signal from the tool signal, the timeout, and the session abort controller\n   - marks the cell `running` and emits an update\n   - calls the backend’s `execute()` with `cwd`, `sessionId`, `sessionFile`, `kernelOwnerId`, `deadlineMs`, `reset` (defaults to `false`), artifact info, and chunk callback\n6. JS cells dispatch through `packages/coding-agent/src/eval/js/index.ts` into `executeJs()`; Python cells dispatch through `packages/coding-agent/src/eval/py/index.ts` into `executePython()`.\n7. Backend text chunks stream into the shared `OutputSink`; rich outputs are accumulated separately as JSON, images, markdown markers, and status events.\n8. After each cell:\n   - text output is trimmed and stored on that cell result\n   - multi-cell runs prefix text with `[i/n]` and the optional title\n   - cancellations return early with `isError: true` and a cell-specific abort message\n   - non-zero exit codes return early with `isError: true` and a message naming the failed cell\n   - later cells are skipped after the first error, but earlier cell state persists in the underlying runtime\n9. On success, the tool joins all cell outputs, synthesizes `(no text output)` or `(no output)` when needed, and attaches truncation metadata from `summarizeFinal()`.\n10. The renderer uses `details.cells`, `details.jsonOutputs`, and `details.statusEvents` to build notebook-style output. `mergeCallAndResult = true` and `inline = true`, so call and result render together in the transcript.\n\n## Modes / Variants\n\n### Backend selection\n\nBackend choice is **explicit per cell** — there is no auto-detection.\n\n- `language: \"py\"` → Python (IPython/Jupyter) backend\n- `language: \"js\"` → JavaScript VM backend\n\nIf the requested backend is disabled or unavailable, the tool throws `ToolError` for that cell. The caller chooses; the tool does not silently substitute.\n\n### JavaScript runtime\n\nImplemented in `packages/coding-agent/src/eval/js/context-manager.ts` and `packages/coding-agent/src/eval/js/prelude.txt`.\n\n- Persistent worker-backed VM sessions keyed by `js:${sessionId}`\n- `reset: true` calls `resetVmContext(sessionKey)` before the cell executes; reset is destructive for all live runs on that JS session\n- Top-level `await` and bare `return` are supported by wrapping code in an async IIFE when `wrapCode()` sees `await` or `return`\n- Top-level static `import ... from ...` and dynamic `import(...)` calls are routed through `rewriteImports()`, which sends them via `__omp_import__` so the specifier resolves against the session cwd\n- Module cache is busted for **local** imports between cells so edits to source files are picked up without restarting the runtime. `__omp_import__` deletes `require.cache[absPath]` before re-importing whenever the original specifier is a filesystem path: relative (`./x`, `../x`, `.`, `..`), POSIX-absolute (`/...`), home-prefixed (`~/...`), or Windows drive-letter (`C:\\...` / `C:/...`). Bare specifiers (`react`, `lodash/x`) and URL/scheme specifiers (`node:fs`, `file://...`, `https://...`) are left in cache so package identity stays stable across cells. The cache-bust only fires when the resolved target is an absolute path — unresolved bare-package fallbacks (`resolveImportSpecifier()` returning the original specifier) skip it.\n- The prelude installs globals:\n  - `display`, `print`\n  - `read`, `write`, `append`, `sort`, `uniq`, `counter`, `diff`, `tree`, `env`, `output`\n  - `tool.<name>(args)` proxy for arbitrary session tool calls\n- JS helpers are async because they cross the VM/tool boundary\n- `display(value)` behavior:\n  - plain objects/arrays become JSON outputs\n  - `{ type: \"image\", data, mimeType }` becomes an image output\n  - scalars become text\n- The VM exposes a restricted `process` subset plus `Buffer`, `fetch`, `Blob`, `File`, `Headers`, `Request`, `Response`, `fs`, `require`, and browser-style globals\n- Concurrent runs on the same VM are not queued end-to-end. Synchronous JS still runs on the single event loop; awaited regions can interleave with sibling runs.\n\n### Python runtime\n\nImplemented in `packages/coding-agent/src/eval/py/executor.ts`, `packages/coding-agent/src/eval/py/kernel.ts`, and `packages/coding-agent/src/eval/py/prelude.py`. See `docs/python-repl.md` for gateway and kernel details.\n\n- Default mode is retained `session` kernels keyed by `python:${sessionId}`\n- Optional `python.kernelMode = \"per-call\"` creates a fresh kernel for each cell and shuts it down afterward\n- `reset: true` disposes the retained kernel for that session before the cell runs; later Python cells in the same tool call reuse the fresh kernel\n- Startup path:\n  - availability check\n  - create/connect kernel\n  - initialize cwd / env / `sys.path`\n  - execute `PYTHON_PRELUDE`\n- Python cells run in the runner's persistent asyncio event loop, so top-level `await` works; the prompt warns not to use `asyncio.run(...)`\n- The Python prelude defines helpers with the same surface as JS where practical, including `tool.<name>(args)` through a per-run loopback bridge\n- Synchronous statement blocks run in the default executor with ContextVar state copied in; the GIL still serializes bytecode execution, but awaited regions can interleave with sibling cells\n- Kernel `display_data` / `execute_result` messages map to:\n  - `application/x-omp-status` → status event\n  - `image/png` → image output\n  - `application/json` → JSON output\n  - `text/markdown` → markdown output\n  - `text/plain` → text output\n  - `text/html` → HTML converted to markdown with `htmlToBasicMarkdown()`\n- Interactive stdin is rejected: `input_request` sends an empty reply, marks `stdinRequested`, and the executor returns exit code `1`\n\n### Multi-language call behavior\n\nA single tool call can mix Python and JS cells. Persistence is per language runtime:\n\n- `reset: true` on a Python cell does not touch JS state\n- `reset: true` on a JS cell does not touch Python state\n- each backend keeps its own retained session keyed from the same session-derived ID\n\n## Side Effects\n\n- Filesystem\n  - JS/Python prelude helpers can read, write, append, diff, and traverse files under the session cwd or absolute paths.\n  - Output may spill to an artifact file via `OutputSink`.\n- Network\n  - Python backend speaks NDJSON to a local `python3` subprocess over stdin/stdout (no network).\n  - JS runtime exposes `fetch` and `tool.<name>()`; those tools may perform additional network I/O.\n- Subprocesses / native bindings\n  - Python availability check runs `<python> -c ...`.\n  - Python backend spawns one `python -u runner.py` subprocess per kernel; cancellation sends `SIGINT`. Details in `docs/python-repl.md`.\n- Session state\n  - `session.assertEvalExecutionAllowed?.()` can block execution.\n  - `session.trackEvalExecution?.(...)` can register cancellable eval work.\n  - `session.getSessionFile?.()`, `session.getEvalSessionId?.()`, and `session.getEvalKernelOwnerId?.()` influence VM/kernel reuse and artifact lookup.\n  - JS VM contexts persist across eval calls until reset/disposal.\n  - Python retained kernels persist until reset, owner cleanup, or process exit.\n- User-visible prompts / interactive UI\n  - none; stdin requests are rejected programmatically\n- Background work / cancellation\n  - Python retained kernels have heartbeat and idle cleanup timers.\n  - Cancellation hard-kills/resets the shared executor for that backend: JS terminates the worker, Python sends SIGINT and may escalate to subprocess shutdown.\n\n## Limits & Caps\n\n- Per-cell timeout default: 30s (applied when `timeout` is omitted in `EvalTool.execute()`; clamped through `TOOL_TIMEOUTS.eval.default` in `packages/coding-agent/src/tools/tool-timeouts.ts`)\n- Schema-level `timeout` range: integer `1..600` seconds (enforced by Zod on the cell schema)\n- Timeout clamp at runtime: 1s minimum, 600s maximum (`TOOL_TIMEOUTS.eval` in `packages/coding-agent/src/tools/tool-timeouts.ts`)\n- Transcript code/output preview: 10 lines by default (`EVAL_DEFAULT_PREVIEW_LINES` in `packages/coding-agent/src/tools/eval.ts`)\n- Output truncation window: 50KB default (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`)\n- Output line cap inside truncation helpers: 3000 lines (`DEFAULT_MAX_LINES` in `packages/coding-agent/src/session/streaming-output.ts`)\n- Streaming tail buffer for live updates: `DEFAULT_MAX_BYTES * 2` = 100KB (`packages/coding-agent/src/tools/eval.ts`)\n- Python retained kernel idle timeout: 5 minutes (`IDLE_TIMEOUT_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python retained kernel cap: 4 sessions (`MAX_KERNEL_SESSIONS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python retained kernel cleanup sweep: every 30s (`CLEANUP_INTERVAL_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python owner-cleanup shutdown wait: 2000ms (`OWNER_CLEANUP_KERNEL_SHUTDOWN_TIMEOUT_MS` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python heartbeat interval: 5s (`ensureKernelHeartbeat()` in `packages/coding-agent/src/eval/py/executor.ts`)\n- Python external gateway availability check timeout: 5s (`AbortSignal.timeout(5000)` in `packages/coding-agent/src/eval/py/kernel.ts`)\n- Python auto-restart budget: one restart per retained session before hard failure (`restartCount > 1` in `packages/coding-agent/src/eval/py/executor.ts`)\n\n## Errors\n\n- Zod validation rejects malformed `cells` arrays before `execute()` runs (missing `language`/`code`, out-of-range `timeout`, empty `cells`).\n- Missing session without proxy executor throws `ToolError(\"Eval tool requires a session when not using proxy executor\")`.\n- Disabled/unavailable backends throw `ToolError` from `resolveBackend()`:\n  - `eval.py = false` and a `py` cell is requested\n  - `eval.js = false` and a `js` cell is requested\n  - Python kernel unavailable and a `py` cell is requested\n- JS runtime exceptions are converted into text output plus `exitCode: 1`; cancellations return `cancelled: true` and may append `Command timed out`.\n- Python execution errors from the kernel become text output and `exitCode: 1`; later cells are skipped.\n- Python stdin requests are treated as errors with the message `Kernel requested stdin; interactive input is not supported.`\n- Cancellation is returned, not thrown, once backend execution has started. The tool formats it as a cell failure and sets `details.isError = true`.\n- If output truncates, the tool still succeeds; truncation is surfaced through `details.meta` and artifact-backed full output when available.\n\n## Shared executor trade-offs\n\n- Parent agents and subagents share eval state bidirectionally when a subagent inherits the parent's executor id. Mutations in either direction are visible to the other participant.\n- Async regions of concurrent runs can interleave. Synchronous JS still blocks the VM event loop; synchronous Python still contends on the GIL.\n- Cancelling one run is destructive to the shared backend executor. This is intentional: JS worker termination and Python SIGINT/subprocess shutdown are the only reliable way to interrupt arbitrary user code.\n- `reset: true` is destructive for every live run on that backend session id. New starts on that backend are rejected while reset is in flight.\n\n## Notes\n\n- Backend selection is now strictly explicit per cell: `language` must be `\"py\"` or `\"js\"`. The previous `*** Cell` header parser, the `eval.lark` constrained grammar, and the sniffer-based fallback have all been removed.\n- `EvalTool.customFormat` no longer exists. Tool calls flow through the standard JSON schema; there is no Lark-constrained sampling path.\n- `tool.<name>()` exists in both JS and Python. Python calls route through a per-run loopback bridge keyed by the current cell id.\n- JS helper paths reject protocol URIs (`://`) in `resolvePath()`; the JS prelude is filesystem-only unless the code calls `tool.read(...)` or another tool explicitly.\n- Python helper `output(...)` depends on `PI_SESSION_FILE`; it fails outside a session-backed run.\n- `display()` can produce text and structured outputs from the same value; the renderer prefers markdown over `text/plain` when both exist.\n- JS static imports are rewritten only at top level. Nested imports stay invalid and surface normal JS syntax/runtime errors.\n- `EvalTool` is `concurrency = \"exclusive\"` within one agent session, but parent and subagent sessions can run eval concurrently when they share an inherited executor id.\n- The tool description shown to the model is templated by backend availability (`getEvalToolDescription()`); if Python is unavailable, the prompt omits Python-specific instructions.\n",
 	"tools/find.md": "# find\n\n> Find filesystem paths by glob; use `search` when you need content matches instead of path matches.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/find.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/find.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/path-utils.ts` — normalize inputs; split base path vs glob.\n  - `packages/coding-agent/src/tools/list-limit.ts` — apply result-count caps.\n  - `packages/coding-agent/src/session/streaming-output.ts` — truncate text output at byte cap.\n  - `packages/coding-agent/src/tools/tool-result.ts` — build `content` and `details.meta`.\n  - `packages/coding-agent/src/tools/output-meta.ts` — encode limit / truncation metadata.\n  - `packages/coding-agent/src/tools/tool-errors.ts` — map user-facing tool errors.\n  - `packages/coding-agent/src/tools/index.ts` — register the built-in local implementation.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `paths` | `string[]` | Yes | One or more globs, files, or directories. Empty strings are rejected. Multiple entries may be merged into one brace-union search when their base paths can be resolved together. |\n| `hidden` | `boolean` | No | Whether hidden files are included. Defaults to `true` (`hidden ?? true`). |\n| `limit` | `number` | No | Max returned paths. Defaults to `1000`. Must be a finite positive number; non-integers are floored. |\n\n## Outputs\nThe tool returns a single text block plus structured `details`.\n\n- Success text: newline-delimited paths, one per line, relative to the session cwd when possible; absolute when outside cwd. Exact file inputs return that file path as one line.\n- Empty result text: `No files found matching pattern`.\n- Multi-path partial miss: appends `Skipped missing paths: ...` after the result block, or after the empty-result line.\n- `details` may include:\n  - `scopePath`: display form of the searched root or merged roots.\n  - `fileCount`: number of paths returned after result limiting.\n  - `files`: returned paths as an array.\n  - `truncated`: whether result count or byte truncation occurred.\n  - `resultLimitReached`: reached result limit.\n  - `missingPaths`: skipped missing inputs in multi-path calls.\n  - `truncation` / `meta.limits`: structured truncation and limit metadata for renderers.\n- Streaming: when the runtime supplies `onUpdate`, the local implementation emits incremental newline-delimited text snapshots during globbing, throttled to 200 ms.\n\n## Flow\n1. `FindTool.execute()` normalizes each `paths` entry with `normalizePathLikeInput()` and `/\\\\/g -> \"/\"` (`packages/coding-agent/src/tools/find.ts`). Empty normalized entries fail with `` `paths` must contain non-empty globs or paths ``.\n2. For multi-path local calls, `partitionExistingPaths(..., parseFindPattern)` (`packages/coding-agent/src/tools/path-utils.ts`) stats each base path. Missing entries are skipped; if all are missing, the tool throws `Path not found: ...`. Single missing paths still hard-fail.\n3. The tool tries `resolveExplicitFindPatterns()` to merge multiple inputs into one search rooted at a common base path. If that does not apply, it parses one input with `parseFindPattern()`.\n4. `parseFindPattern()` determines `(basePath, globPattern, hasGlob)`:\n   - no glob chars (`*`, `?`, `[`, `{`) => search that path with implicit `**/*`.\n   - glob in the first segment => search from `.` and, unless the pattern already starts with `**/`, prefix it with `**/`.\n   - glob later in the path => split at the first glob-bearing segment.\n5. `resolveToCwd()` converts the base path to an absolute path under the session cwd. A resolved `/` is rejected with `Searching from root directory '/' is not allowed`.\n6. `limit` is defaulted to `DEFAULT_LIMIT` (`1000`) and validated as a positive finite integer. `hidden` defaults to `true`. The tool also creates a 5 s timeout via `AbortSignal.timeout(GLOB_TIMEOUT_MS)`.\n7. Execution then branches:\n   - **Custom operations branch**: if `FindToolOptions.operations.glob` exists, the tool checks existence with `operations.exists()`, short-circuits exact-file inputs via `operations.stat()` when available, then calls `operations.glob(globPattern, searchPath, { ignore: [\"**/node_modules/**\", \"**/.git/**\"], limit })`.\n   - **Built-in local branch**: the tool stats `searchPath`. Exact-file inputs return immediately. Directory inputs call `natives.glob()` with `fileType: File`, `hidden`, `maxResults: limit`, `sortByMtime: true`, `gitignore: true`, and the combined abort signal.\n8. In the local branch, optional `onMatch` callbacks convert each match to a cwd-relative display path and emit throttled progress updates.\n9. After native glob returns, JS sorts `result.matches` by `mtime` descending (`(b.mtime ?? 0) - (a.mtime ?? 0)`) before formatting paths.\n10. `buildResult()` applies `applyListLimit()` to cap the array again at `limit`, joins paths with `\\n`, then runs `truncateHead()` with `maxLines: Number.MAX_SAFE_INTEGER`. In practice this leaves the 50 KB byte cap in place while disabling the default 3000-line cap.\n11. `toolResult()` packages text plus `details`, and records result-limit / truncation metadata for renderers.\n\n## Modes / Variants\n- **Exact file path**: if the parsed input has no glob and the resolved path stats as a file, output is that one path.\n- **Directory path**: if the parsed input has no glob and stats as a directory, the tool searches it with implicit `**/*`.\n- **Single glob path**: one input parsed by `parseFindPattern()`.\n- **Merged multi-path search**: multiple inputs resolved by `resolveExplicitFindPatterns()` into one brace-union glob rooted at a common base path.\n- **Partial multi-path search with missing inputs**: local multi-path calls skip missing base paths and surface them as `missingPaths` / `Skipped missing paths: ...`.\n- **Custom delegated search**: uses injected `FindOperations` instead of local fs + native glob.\n\n## Side Effects\n- Filesystem\n  - Stats the resolved base path, and in local multi-path mode stats every candidate base path up front.\n  - Does not write files.\n- Subprocesses / native bindings\n  - Built-in local mode calls the native `@oh-my-pi/pi-natives` glob implementation.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Emits structured progress updates when `onUpdate` is provided.\n  - Adds truncation / limit metadata to the tool result.\n- Background work / cancellation\n  - Local globbing is cancellable through the caller abort signal plus an internal 5 s timeout.\n\n## Limits & Caps\n- Default result limit: `1000` (`DEFAULT_LIMIT` in `packages/coding-agent/src/tools/find.ts`).\n- Local glob timeout: `5000` ms (`GLOB_TIMEOUT_MS` in `packages/coding-agent/src/tools/find.ts`).\n- Output byte cap: `50 * 1024` bytes (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`).\n- Default generic line cap in `truncateHead()` is `3000`, but `find` overrides `maxLines` to `Number.MAX_SAFE_INTEGER`, so byte size — not line count — is the practical output truncation cap.\n- Streaming update throttle: `200` ms between `onUpdate` emissions.\n- Sort order: most recent `mtime` first in the built-in local branch and promised in the prompt. The tool re-sorts in JS even though native glob receives `sortByMtime: true` so native code can still stop early at `maxResults`.\n\n## Errors\n- User-facing `ToolError`s from `FindTool.execute()` include:\n  - `` `paths` must contain non-empty globs or paths ``\n  - `Path not found: ...`\n  - `Searching from root directory '/' is not allowed`\n  - `Limit must be a positive number`\n  - `Path is not a directory: ...`\n  - `find timed out after 5s`\n- If the caller aborts, the local branch converts `AbortError` into `ToolAbortError`.\n- Non-`ENOENT` stat failures and other unexpected errors are rethrown.\n- Empty matches are not errors; they return the no-files text result.\n\n## Notes\n- Reach for `find` for filename / path discovery. Reach for `search` when the selection criterion is file contents or regex matches; `search` takes a `pattern` and returns anchored content matches, while `find` only returns matching paths (`packages/coding-agent/src/prompts/tools/find.md`, `packages/coding-agent/src/prompts/tools/search.md`).\n- Bare top-level globs are made recursive. `*.ts` is parsed as base `.` plus glob `**/*.ts`; `src/*.ts` stays rooted at `src` with a non-recursive `*.ts` segment; `src/**/*.ts` preserves explicit recursion.\n- `.gitignore` is always enabled in the built-in local branch (`gitignore: true`). There is no model-facing flag to disable it.\n- `hidden` defaults to `true`; hidden-file exclusion is opt-out, not opt-in.\n- Multi-path missing-input tolerance only applies in the built-in local branch. The custom-operations branch hard-fails the first missing `searchPath` it checks.\n- The custom `FindOperations.glob()` hook receives `ignore` and `limit`, but not the `hidden` flag or an explicit `.gitignore` toggle. A remote delegate must account for that itself if it wants parity with the local branch.\n- Built-in local globbing asks the native layer for `fileType: File`, so recursive directory searches yield files, not directories. Directory outputs are only possible through exact-path passthrough or custom delegates that return them.\n",
 	"tools/github.md": "# github\n\n> Dispatch GitHub CLI operations for repositories, issues, pull requests, search, and Actions run watching.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/gh.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/github.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/gh-format.ts` — shorten commit SHAs for summaries.\n  - `packages/coding-agent/src/tools/gh-renderer.ts` — TUI rendering, especially `run_watch` live/result views.\n  - `packages/coding-agent/src/utils/git.ts` — `gh`/`git` process wrappers, repo locking, branch config writes.\n  - `packages/utils/src/dirs.ts` — base directory for dedicated PR worktrees.\n  - `packages/coding-agent/src/sdk.ts` — session artifact allocation hook.\n  - `packages/coding-agent/src/session/artifacts.ts` — artifact filename format `<id>.<toolType>.log`.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `\"repo_view\" \\| \"pr_create\" \\| \"pr_checkout\" \\| \"pr_push\" \\| \"search_issues\" \\| \"search_prs\" \\| \"search_code\" \\| \"search_commits\" \\| \"search_repos\" \\| \"run_watch\"` | Yes | Dispatch selector. `GithubTool.execute()` switches only on this field. |\n| `repo` | `string` | No | `owner/repo` override. Ignored when the identifier argument is already a full GitHub URL. For `search_issues`/`search_prs`/`search_code`/`search_commits`, defaults to the current checkout's `owner/repo` when omitted (skipped when the query already contains a `repo:`/`org:`/`user:`/`owner:` qualifier or when current-repo resolution fails). Required in practice when `gh` cannot infer repo context from the current checkout. |\n| `branch` | `string` | No | Used by `repo_view`, `pr_push`, and `run_watch`. `run_watch` falls back to current git branch when `run` is omitted; `pr_push` falls back to current branch. |\n| `pr` | `string \\| string[]` | No | Used by `pr_checkout`. Each item may be a PR number, branch name, or GitHub PR URL. Array form enables batching. Omitted means current branch PR. |\n| `force` | `boolean` | No | Used only by `pr_checkout`. Defaults to `false`; allows resetting an existing `pr-<number>` local branch to the PR head commit. |\n| `forceWithLease` | `boolean` | No | Used only by `pr_push`; passed through to git push. |\n| `title` | `string` | No | Used only by `pr_create`. Required unless `fill` is `true`. |\n| `body` | `string` | No | Used only by `pr_create`. Mutually exclusive with `fill`. Empty/omitted body becomes `--body \"\"` to suppress the interactive editor. Non-empty body is written to a temp file and passed as `--body-file`. |\n| `base` | `string` | No | Used only by `pr_create`; passed as `--base`. |\n| `head` | `string` | No | Used only by `pr_create`; passed as `--head`. |\n| `draft` | `boolean` | No | Used only by `pr_create`. Defaults to `false`. |\n| `fill` | `boolean` | No | Used only by `pr_create`. Defaults to `false`. Mutually exclusive with `title` and `body`. |\n| `reviewer` | `string[]` | No | Used only by `pr_create`; each entry becomes `--reviewer`. |\n| `assignee` | `string[]` | No | Used only by `pr_create`; each entry becomes `--assignee`. |\n| `label` | `string[]` | No | Used only by `pr_create`; each entry becomes `--label`. |\n| `query` | `string` | No | Used by all `search_*` ops. Required there. |\n| `limit` | `number` | No | Used by all `search_*` ops. Defaults to `10`, floored, clamped to `50`, and must be `> 0`. |\n| `run` | `string` | No | Used only by `run_watch`. Must be a numeric run ID or full GitHub Actions run URL. |\n| `tail` | `number` | No | Used only by `run_watch`. Defaults to `15`, floored, clamped to `200`, and must be `> 0`. |\n\n## Outputs\nThe tool returns a single text result built by `buildTextResult()` in `packages/coding-agent/src/tools/gh.ts`.\n\n- `content`: one text block. Multi-item ops join sections with blank lines and `---` separators.\n- `sourceUrl`: set for single repo/PR/run results when a canonical URL is known.\n- `details`: optional structured metadata used by the TUI renderer.\n  - Common fields: `artifactId`, `repo`, `branch`, `worktreePath`, `remote`, `remoteBranch`, `headSha`, `runId`, `runIds`, `status`, `conclusion`, `failedJobs`.\n  - `pr_checkout` adds `checkouts: GhPrCheckoutSummary[]`.\n  - `run_watch` adds `watch: GhRunWatchViewDetails`, which drives the custom live/result renderer in `packages/coding-agent/src/tools/gh-renderer.ts`.\n- Artifact trailer: when `artifactId` is present, the text body gets an appended line like `Full failed-job logs: artifact://<id>`.\n  - `run_watch` allocates artifacts with `session.allocateOutputArtifact(\"github\")`; persistent sessions therefore save failed-log bodies as `<artifact-dir>/<id>.github.log`.\n\n`run_watch` is the only streaming op. It emits `onUpdate` snapshots while polling, then returns one final text result.\n\n## Flow\n1. `GithubTool.createIf()` exposes the tool only when `git.github.available()` finds `gh` on `PATH`.\n2. `GithubTool.execute()` wraps dispatch in `untilAborted()` and switches on `params.op`.\n3. Each op normalizes optional strings, arrays, booleans, and numeric caps locally in `packages/coding-agent/src/tools/gh.ts`.\n4. CLI execution goes through `git.github.run/json/text()` in `packages/coding-agent/src/utils/git.ts`:\n   - spawns `gh ...` with `Bun.spawn()`;\n   - trims stdout/stderr unless `trimOutput: false`;\n   - maps common auth/repo-context failures into tool-facing `ToolError` messages;\n   - `json()` rejects empty or invalid JSON.\n5. Read-style ops (`repo_view`, `search_*`) fetch JSON and format Markdown-like text summaries. Single-issue and single-PR views were moved out of the tool and now resolve through the `issue://` / `pr://` internal URL schemes, which share the same SQLite cache.\n7. PR diffs moved out of the tool. `pr://<N>/diff` lists changed files, `pr://<N>/diff/<i>` slices a single file, and `pr://<N>/diff/all` returns the full unified diff — see `docs/tools/read.md`. All three variants share one `gh pr diff` invocation through the `pr-diff` cache row.\n8. `pr_checkout` resolves PR metadata first, then enters `git.withRepoLock()` before any git mutation so parallel checkout calls for the same primary repo do not race on shared `.git` state.\n9. `pr_push` reads PR head metadata back from git branch config, derives a refspec, then pushes with `git.push()`.\n10. `pr_create` shells out once, then best-effort re-reads the created PR for a richer summary.\n11. `run_watch` chooses either run mode (`run` supplied) or commit mode (`run` omitted), polls GitHub Actions APIs every 3 seconds, emits streaming updates, and may save a full failed-log artifact before returning.\n12. Final text goes through `toolResult().text(...)`; if `session.allocateOutputArtifact()` returns a slot, failed-log text is persisted with `Bun.write()`.\n\n## Modes / Variants\n\n### `repo_view`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `branch` |\n| `gh` command | `gh repo view [<repo>] [--branch <branch>] --json <GH_REPO_FIELDS>` |\n| Batching | None |\n| Output | `# <owner/repo>` header, description, URL, default branch, requested branch, visibility, permission, primary language, stars, forks, archive/fork flags, updated timestamp, homepage, topics. `sourceUrl = data.url`. |\n\nIf `repo` is omitted, `gh` repository resolution is used.\n\nSingle-issue and single-PR reads live in the `issue://<N>` / `pr://<N>` URL schemes (see `docs/tools/read.md`). They share `~/.omp/cache/github-cache.db` (override via `OMP_GITHUB_CACHE_DB`) and the `github.cache.softTtlSec` / `github.cache.hardTtlSec` / `github.cache.enabled` settings. The cache retains rendered Markdown plus the raw JSON payload returned by `gh`, including private bodies, comments, reviews, and review comments when comments are enabled; rows are scoped by the local GitHub credential fingerprint. Root and repo-scoped reads (`issue://`, `pr://owner/repo`) issue a live `gh issue list` / `gh pr list` for browsing; query params `state`, `limit`, `author`, `label` pass through to `gh` (`issue://` accepts `state=open|closed|all`; `pr://` also accepts `merged`). PR diffs ride the same cache under `pr://<N>/diff[/…]`: the listing, full diff, and per-file slices all share one `pr-diff` row keyed by repo and PR number.\n\n### `pr_create`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` plus either `fill=true` or `title` |\n| Optional fields | `repo`, `title`, `body`, `base`, `head`, `draft`, `fill`, `reviewer[]`, `assignee[]`, `label[]` |\n| `gh` command | `gh pr create ...` with flags assembled from provided fields |\n| Batching | None |\n| Output | `# Created Pull Request ...` summary with URL, state, draft flag, base/head, author, created time, labels, optional body. `sourceUrl` is the created PR URL. |\n\nBranches:\n- `fill && (title || body !== undefined)` throws.\n- Non-empty `body` is written under a temp dir `gh-pr-body-*` in `os.tmpdir()`, passed as `--body-file`, then removed in `finally`.\n- After creation, the tool parses the returned URL and best-effort runs `gh pr view <number> --repo <repo> --json <GH_PR_FIELDS_NO_COMMENTS>`; failures there are swallowed.\n\n### `pr_checkout`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `pr`, `force` |\n| `gh` command | For each requested PR: `gh pr view [<pr>] [--repo <repo>] --json <GH_PR_CHECKOUT_FIELDS>`; cross-repo PRs may also call `gh repo view <headRepository> --json <GH_REPO_CLONE_FIELDS>`. |\n| Batching | Yes. `pr` may be `string[]`; each PR is resolved in parallel, but git mutations are serialized per primary repo by `git.withRepoLock()`. |\n| Output | Single PR: checkout/worktree summary plus `details.repo`, `details.branch`, `details.worktreePath`, `details.remote`, `details.remoteBranch`, `details.checkouts`. Batched: `# <n> Pull Request Worktrees (...)` plus one section per PR and aggregated `details.checkouts`. |\n\nWorktree and metadata behavior:\n- Local branch name is always `pr-<number>`.\n- Worktree path is `path.join(getWorktreesDir(), encodeRepoPathForFilesystem(primaryRepoRoot), localBranch)`, where `getWorktreesDir()` is `~/.omp/wt`; effective path is `~/.omp/wt/<encoded-primary-repo-root>/pr-<number>`.\n- Existing worktree detection is by branch ref `refs/heads/pr-<number>` from `git.worktree.list()`.\n- New worktree creation calls `git.worktree.add(repoRoot, finalWorktreePath, localBranch, { signal })` after verifying the path is neither already registered nor already present on disk.\n- For same-repo PRs, remote is `origin`. For cross-repo PRs, the tool resolves a clone URL for the head repo, reuses an existing remote with the same URL when possible, or creates `fork-<owner>` / `fork-<owner>-<n>`.\n- The branch push metadata is persisted with `git config` under the repository's shared `.git/config` as:\n  - `branch.pr-<number>.remote`\n  - `branch.pr-<number>.merge`\n  - `branch.pr-<number>.pushRemote`\n  - `branch.pr-<number>.ompPrHeadRef`\n  - `branch.pr-<number>.ompPrUrl`\n  - `branch.pr-<number>.ompPrIsCrossRepository`\n  - `branch.pr-<number>.ompPrMaintainerCanModify`\n- If `refs/heads/pr-<number>` already exists at a different commit, checkout fails unless `force=true`, in which case `git branch --force` resets it to the fetched PR head.\n- If a matching worktree already exists, the tool reuses it and reports `reused: true`.\n\n### `pr_push`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `branch`, `forceWithLease` |\n| `gh` command | None. This path uses git, not `gh`. |\n| Batching | None |\n| Output | `# Pushed Pull Request Branch` summary with local branch, remote, remote branch, remote URL, PR URL, and force-with-lease flag. `sourceUrl = prUrl` when known. |\n\nPush target resolution reads the `branch.<name>.ompPrHeadRef`, `pushRemote`/`remote`, `ompPrUrl`, `ompPrMaintainerCanModify`, and `ompPrIsCrossRepository` git-config keys written by `pr_checkout`. If the current checked-out branch matches the target branch, the source ref is `HEAD`; otherwise it pushes `refs/heads/<branch>`. The refspec is `HEAD:refs/heads/<headRef>` or `refs/heads/<branch>:refs/heads/<headRef>`.\n\n### `search_issues`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh api -X GET /search/issues -f q=\"<query> [repo:<repo>] is:issue\" -F per_page=<limit>` |\n| Batching | None |\n| Output | `# GitHub issues search`, echoed query, optional repo, result count, then one bullet per issue with repo/state/author/labels/timestamps/URL. |\n\n`repo` defaults to the current checkout's `owner/repo` via `resolveSearchRepoScope()` when omitted. The default is suppressed when the query already contains a leading `repo:`/`org:`/`user:`/`owner:` qualifier or when `gh repo view` fails to resolve the current checkout (e.g. outside a github remote).\n\n### `search_prs`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh api -X GET /search/issues -f q=\"<query> [repo:<repo>] is:pr\" -F per_page=<limit>` |\n| Batching | None |\n| Output | Same shape as `search_issues`, labeled as pull requests. |\n\n`repo` defaults to the current checkout's `owner/repo` as in `search_issues`.\n\n### `search_code`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh api -X GET /search/code -f q=\"<query> [repo:<repo>]\" -F per_page=<limit> -H \"Accept: application/vnd.github.text-match+json\"` |\n| Batching | None |\n| Output | `# GitHub code search`, result count, then one bullet per match with path, repo, short commit SHA, URL, and first normalized text-match fragment line when present. |\n\n`repo` defaults to the current checkout's `owner/repo` as in `search_issues`.\n\n### `search_commits`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `repo`, `limit` |\n| `gh` command | `gh api -X GET /search/commits -f q=\"<query> [repo:<repo>]\" -F per_page=<limit>` |\n| Batching | None |\n| Output | `# GitHub commits search`, result count, then one bullet per commit: short SHA + first commit-message line, repo, author, date, URL. |\n\n`repo` defaults to the current checkout's `owner/repo` as in `search_issues`.\n\n### `search_repos`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op`, `query` |\n| Optional fields | `limit` |\n| `gh` command | `gh api -X GET /search/repositories -f q=\"<query>\" -F per_page=<limit>` |\n| Batching | None |\n| Output | `# GitHub repositories search`, result count, then one bullet per repo with first description line, language, stars, forks, open issues, visibility, archive/fork flags, updated time, URL. |\n\n`repo` is intentionally not used for this op.\n\n### `run_watch`\n\n| Aspect | Value |\n| --- | --- |\n| Required fields | `op` |\n| Optional fields | `repo`, `branch`, `run`, `tail` |\n| `gh` command | Repo resolution: `gh repo view --json nameWithOwner -q .nameWithOwner` when `repo` and run URL repo are both absent. Single-run mode uses `gh api --method GET /repos/<repo>/actions/runs/<runId>` and `gh api --method GET /repos/<repo>/actions/runs/<runId>/jobs`. Commit mode uses `gh api --method GET /repos/<repo>/branches/<branch>`, `gh api --method GET /repos/<repo>/actions/runs`, `gh api --method GET /repos/<repo>/actions/runs/<runId>/jobs`, and `gh api /repos/<repo>/actions/jobs/<jobId>/logs` for failed jobs. |\n| Batching | Implicit batching only in commit mode: all workflow runs for one commit are tracked together. |\n| Output | Streaming watch snapshots via `onUpdate`, then a final text report. On failure, appends `Full failed-job logs: artifact://<id>` and sets `details.artifactId`. |\n\nWatch flow:\n- `run` parsing accepts either a decimal run ID or a full run URL. URL repo must match explicit `repo` when both are given.\n- Poll interval is fixed at 3 seconds (`RUN_WATCH_INTERVAL_DEFAULT`).\n- Failure grace period is fixed at 5 seconds (`RUN_WATCH_GRACE_DEFAULT`). When any failed job appears before completion, the tool emits a note, waits once, re-fetches state, then collects logs so concurrent failures are included.\n- Failed-job logs are fetched with `gh api /repos/<repo>/actions/jobs/<jobId>/logs` via `git.github.run()`, not `json()`. Non-zero exit leaves `available: false` instead of failing the whole watch.\n- Inline result includes only the last `tail` lines per failed job. The saved artifact contains full logs (`mode: \"full\"`).\n- In commit mode, success is intentionally double-checked: once all known runs are successful, the tool waits one more poll interval and succeeds only if the set of run IDs is unchanged. This avoids returning before late workflow runs appear for the same commit.\n- `details.watch` drives a specialized renderer in `packages/coding-agent/src/tools/gh-renderer.ts`; non-watch results fall back to generic text rendering.\n\n## Side Effects\n- Filesystem\n  - `pr_create` may create a temp dir under `os.tmpdir()` named `gh-pr-body-*`, write `body.md`, then remove the dir in `finally`.\n  - `pr_checkout` may create directories under `~/.omp/wt/<encoded-primary-repo-root>/` and add git worktrees there.\n  - `run_watch` may write a session artifact with full failed-job logs.\n- Network\n  - Every op shells out to `gh`, which then talks to GitHub APIs except `pr_push`.\n  - `pr_push` uses git network transport to the configured remote.\n- Subprocesses / native bindings\n  - All `gh` calls use `Bun.spawn([\"gh\", ...args])`.\n  - `pr_checkout` and `pr_push` also invoke git helpers from `packages/coding-agent/src/utils/git.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - `run_watch` consumes `session.allocateOutputArtifact()` when failed-job logs are persisted.\n  - Returned `details` objects carry run/checkouts metadata for the renderer/UI.\n- User-visible prompts / interactive UI\n  - `gh` interactive editor fallback is suppressed for `pr_create` by forcing either `--body-file` or `--body \"\"`.\n  - `gh-renderer` provides compact headers for all ops and a custom live watch view for `run_watch`.\n- Background work / cancellation\n  - `run_watch` loops until success/failure and uses `scheduler.wait()` between polls.\n  - `GithubTool.execute()` is wrapped in `untilAborted()`; `git.github.run()` forwards the abort signal into `Bun.spawn()`.\n\n## Limits & Caps\n- Search result default: `10` (`SEARCH_LIMIT_DEFAULT` in `packages/coding-agent/src/tools/gh.ts`).\n- Search result max: `50` (`SEARCH_LIMIT_MAX`).\n- PR file preview inside the `pr://` view: first `50` files only (`FILE_PREVIEW_LIMIT` in `gh.ts`).\n- Run-watch poll interval: `3s` (`RUN_WATCH_INTERVAL_DEFAULT`).\n- Run-watch failure grace period: `5s` (`RUN_WATCH_GRACE_DEFAULT`).\n- Run-watch failed-log tail default: `15` lines (`RUN_WATCH_TAIL_DEFAULT`).\n- Run-watch failed-log tail max: `200` lines (`RUN_WATCH_TAIL_MAX`).\n- PR review comments page size: `100` (`REVIEW_COMMENTS_PAGE_SIZE`).\n- Actions jobs page size: `100` (`RUN_JOBS_PAGE_SIZE`).\n- Search and tail numeric inputs are floored with `Math.floor()`, clamped to the max, and rejected when non-finite or `<= 0`.\n- `pr_checkout` batch fan-out is unbounded in tool code; all requested PRs are launched with `Promise.all()`.\n\n## Errors\n- Tool creation is skipped entirely when `gh` is not installed.\n- `git.github.run()` throws `ToolError(\"GitHub CLI (gh) is not installed...\")` if `gh` is missing at execution time.\n- `git.github.text/json()` map common failures to model-facing messages:\n  - not authenticated → `GitHub CLI is not authenticated. Run \\`gh auth login\\`.`\n  - missing repo context without explicit `repo` → `GitHub repository context is unavailable. Pass \\`repo\\` explicitly or run the tool inside a GitHub checkout.`\n  - otherwise stderr/stdout text, or fallback `GitHub CLI command failed: gh ...`\n- `json()` also throws on empty stdout or invalid JSON.\n- Local validation errors throw `ToolError`, including:\n  - missing required per-op fields (`query`, `title unless fill=true`)\n  - invalid numeric `limit` / `tail`\n  - invalid `run` format\n  - `fill` combined with `title` or `body`\n  - missing git repo / branch / HEAD context for checkout, push, or watch\n  - `pr_push` on a branch without `ompPrHeadRef` metadata\n  - conflicting existing worktree path or branch without `force`\n- `run_watch` treats failed-job log fetches specially: missing log content does not fail the watch; it marks that log `available: false` and prints `Log tail unavailable.` / `Full log unavailable.`.\n- `pr_create` swallows only the post-create best-effort `gh pr view` refresh; the create step itself still fails normally.\n\n## Notes\n- `appendRepoFlag()` intentionally skips `--repo` when the identifier argument is already a full GitHub URL; that lets `gh` derive repo/number from the URL.\n- `normalizePrIdentifierList()` accepts `reviewer`, `assignee`, and `label` arrays too; the helper name is broader than its callers.\n- `pr_push` depends on `pr_checkout` having run first for that local branch; there is no alternate metadata source.\n- `pr_checkout` stores push metadata in branch config, not in the worktree directory. Reusing the same `pr-<number>` branch reuses those config keys.\n- Worktree write serialization is keyed by the primary repo root, not the current worktree path, because git worktrees share `.git/config`, `packed-refs`, commit-graph, and worktree metadata files.\n- `search_repos` is the only search op that never forwards `repo`; repository scoping must be expressed in the query itself.\n- `run_watch` success on commit mode means “all observed runs succeeded and no additional runs appeared one poll later”, not merely “latest poll looked green”.\n- The TUI renderer collapses failed log previews unless the result view is expanded; the underlying text result still contains the same tailed lines plus any artifact reference.\n",