@gajae-code/coding-agent 0.3.0 → 0.3.2

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

@@ -1,6 +1,6 @@
 // Auto-generated by scripts/generate-docs-index.ts - DO NOT EDIT
 
-export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","brand-assets.md","codebase-overview.md","compaction.md","environment-variables.md","fs-scan-cache-architecture.md","gjc-dogfood-skill-template.md","handoff-generation-pipeline.md","keybindings.md","lsp-config.md","memory.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","onboarding-packet.md","onboarding-receipt.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.md","tools/checkpoint.md","tools/cron.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/monitor.md","tools/read.md","tools/recall.md","tools/recipe.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","brand-assets.md","bridge.md","codebase-overview.md","compaction.md","environment-variables.md","fs-scan-cache-architecture.md","gjc-dogfood-skill-template.md","handoff-generation-pipeline.md","keybindings.md","lsp-config.md","memory.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","onboarding-packet.md","onboarding-receipt.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.md","tools/checkpoint.md","tools/cron.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/monitor.md","tools/read.md","tools/recipe.md","tools/render_mermaid.md","tools/resolve.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md"];
 
 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: `~/.gjc/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-openai-code    | 17                 | 112,243 | 151         |\n| gpt-5.5          | 2                  |  80,750 |  25         |\n| gpt-5.2-openai-code    | 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.",
@@ -10,16 +10,17 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"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- `GJC_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 `GJC_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",
 	"brand-assets.md": "# Brand assets\n\nGajae-Code uses the current GJC character and hero images in `assets/` for README and documentation surfaces.\n\n| Asset | Purpose |\n| --- | --- |\n| [`assets/hero.png`](../assets/hero.png) | Wide README/docs hero image for Gajae-Code. |\n| [`assets/character.png`](../assets/character.png) | Standalone Gajae-Code character mascot. |\n| [`assets/tool-image-fixture.webp`](../assets/tool-image-fixture.webp) | Minimal WebP fixture for terminal image rendering tests. Not a product brand asset. |\n\nThe old legacy demo artwork has been removed from the active asset set; new public surfaces should reference the Gajae-Code assets above.\n",
-	"codebase-overview.md": "# Codebase Overview\n\nThis document maps the main parts of the `gajae-code` repository. The root README stays intentionally small; this file is the architecture-oriented companion.\n\n## Product shape\n\nGajae-Code (`gjc`) is centered on `packages/coding-agent/`. The public workflow surface is intentionally fixed at four source-bundled skills and four public role subagents. Runtime state, specs, plans, goals, team state, and local overrides live under `.gjc/`.\n\nDefault workflow skills are embedded from:\n\n```text\npackages/coding-agent/src/defaults/gjc/skills/<name>/SKILL.md\n```\n\nPublic role subagent prompts are embedded from:\n\n```text\npackages/coding-agent/src/prompts/agents/<role>.md\n```\n\nThe runtime can still discover project/user overrides, but the bundled defaults are loaded from source so a missing project `.gjc` directory does not remove the default workflow surface.\n\n## Packages\n\n### `packages/coding-agent/`\n\nMain `gjc` CLI and product runtime.\n\n- `packages/coding-agent/package.json` exposes the `gjc` binary at `src/cli.ts` and the SDK/barrel entrypoint at `src/index.ts`.\n- `packages/coding-agent/src/cli.ts` is the executable bootstrap. It registers CLI commands such as `setup`, `deep-interview`, `ralplan`, `ultragoal`, `team`, and the default launch path.\n- `packages/coding-agent/src/main.ts` adapts CLI options into session creation and dispatches interactive, print, RPC, RPC-UI, and ACP modes.\n- `packages/coding-agent/src/sdk.ts` assembles settings, model registry, auth, workspace/context discovery, skills, rules, tools, system prompt, and the underlying `@gajae-code/agent-core` agent.\n- `packages/coding-agent/src/tools/index.ts` is the built-in tool registry for file/code/runtime tools such as read, bash, edit, AST tools, eval, find/search, LSP, browser, task/subagent, recipe, IRC, todo, web search, write, and memory tools.\n- `packages/coding-agent/src/defaults/gjc-defaults.ts` embeds and installs the default workflow skills.\n- `packages/coding-agent/src/task/agents.ts` embeds bundled task-agent prompts. The public contract is `executor`, `architect`, `planner`, and `critic`; other bundled prompts are internal/runtime utilities.\n\n### `packages/ai/`\n\nProvider/model boundary for LLM access.\n\n- `packages/ai/src/index.ts` exports model registry/resolution, provider implementations, auth broker/gateway/storage, streaming, usage, retry/overflow utilities, OAuth, discovery, and validation helpers.\n- `packages/ai/src/types.ts` defines provider, model, context, message, tool, usage, reasoning, and stream-event contracts.\n- `packages/ai/src/stream.ts` dispatches model-driven streams to the right provider/API implementation and normalizes streaming events.\n- `packages/ai/src/model-manager.ts` merges static, cached, dynamic, and remote model sources.\n- `packages/ai/README.md` documents tool calling, partial streaming tool calls, thinking/reasoning, provider configuration, context handoff, and OAuth flows.\n\n### `packages/agent/`\n\nStateful agent runtime built on `@gajae-code/ai`.\n\n- `packages/agent/src/index.ts` exports the `Agent`, loop APIs, append-only context, compaction, telemetry, proxy utilities, thinking helpers, and shared types.\n- `packages/agent/src/agent-loop.ts` owns the turn loop: transform context, call the model stream, execute tool calls, append tool results, and emit lifecycle events.\n- `packages/agent/src/agent.ts` wraps the loop with mutable state, subscriptions, prompt/continue/abort APIs, queues, provider session state, telemetry, and state mutation helpers.\n- `packages/agent/src/types.ts` defines `AgentMessage`, `AgentTool`, loop config, event, and runtime state contracts.\n\n### `packages/tui/`\n\nTerminal UI framework used by the CLI.\n\n- `packages/tui/src/index.ts` exports components, keybindings, autocomplete, terminal abstractions, image support, TUI core, and utilities.\n- `packages/tui/src/tui.ts` manages component rendering, focus, overlays, terminal dimensions, diff state, and synchronized output.\n- `packages/tui/src/terminal.ts` abstracts terminal lifecycle, dimensions, cursor controls, title/progress, Kitty protocol state, and appearance notifications.\n- `packages/tui/README.md` documents the component model and built-in components such as text, input, editor, markdown, loaders, select/settings lists, spacer, image, box, and container.\n\n### `packages/natives/` and Rust crates\n\nNative helper layer exposed through N-API.\n\n- `packages/natives/package.json` exports `native/index.js` and generated TypeScript definitions.\n- `packages/natives/native/loader-state.js` resolves platform/CPU-specific native binaries and validates package/native version alignment.\n- `crates/pi-natives/src/lib.rs` is the N-API root for appearance, AST search/editing, clipboard, filesystem scan/cache, grep/glob, syntax highlighting, HTML-to-Markdown, keyboard parsing, process/PTY/shell support, SIXEL, code summarization, token counting, text measurement/wrapping/truncation, workspace scanning, power assertions, and isolation helpers.\n- `crates/pi-shell/src/lib.rs` exposes brush-based shell execution primitives used by the native shell adapter.\n- `crates/pi-shell/src/shell.rs` implements persistent and one-shot shell execution, streaming, environment handling, cancellation, and output minimizer telemetry.\n- `crates/pi-shell/src/fixup.rs` performs conservative AST-based bash command fixups.\n- `crates/pi-natives/src/pty.rs` implements interactive PTY sessions.\n\n### `packages/utils/`\n\nShared TypeScript utilities.\n\n- `packages/utils/src/index.ts` exports abortable/async helpers, color/env/dir utilities, fetch retry, formatting, frontmatter, glob helpers, JSON helpers, logging, MIME detection, prompt rendering, process-tree helpers, sanitization, streams, temp files, tab spacing, type guards, and executable lookup.\n- `packages/utils/src/ptree.ts` and `packages/utils/src/procmgr.ts` wrap native process helpers for ergonomic TypeScript use.\n\n### `packages/stats/`\n\nLocal observability dashboard for session and model usage.\n\n- `packages/stats/src/index.ts` exposes the `gjc-stats` CLI entrypoint and exports aggregation/server APIs.\n- `packages/stats/src/aggregator.ts` parses session-derived request metrics and writes aggregated data through SQLite.\n- `packages/stats/src/server.ts` serves local dashboard API routes and static SPA assets.\n- `packages/stats/src/types.ts` and `packages/stats/src/shared-types.ts` define dashboard and aggregate metric shapes.\n\n### `packages/swarm-extension/`\n\nOptional YAML/DAG multi-agent extension outside the fixed default workflow surface.\n\n- `packages/swarm-extension/README.md` documents standalone `gjc-swarm` execution and in-TUI `/swarm` commands.\n- Swarm workflows define agents, tasks, dependency edges, waves, and shared workspace state under `.swarm_<name>/`.\n\n### `packages/typescript-edit-benchmark/`\n\nPrivate benchmark package for TypeScript edit tasks.\n\n- `packages/typescript-edit-benchmark/package.json` exposes `typescript-edit-benchmark` and depends on the coding-agent, agent-core, ai, tui, utils, diff, prettier, and Babel tooling.\n- `packages/typescript-edit-benchmark/src/index.ts` is the benchmark CLI: it resolves fixtures, loads tasks, runs edit attempts, records progress, and writes reports/conversation dumps under `runs/`.\n\n## Python packages\n\n### `python/gjc-rpc/`\n\nTyped Python client for `gjc --mode rpc`.\n\n- `python/gjc-rpc/pyproject.toml` packages `gjc-rpc` for Python 3.11+.\n- `python/gjc-rpc/README.md` documents the process-backed stdio client, typed command methods, startup flags, event listeners, todo seeding, host-owned tools, and host-owned URI schemes.\n\n### `python/robogjc/`\n\nSelf-hosted GitHub triage/fix bot that drives `gjc --mode rpc`.\n\n- `python/robogjc/AGENTS.md` is the authoritative local contract for this subtree.\n- `python/robogjc/pyproject.toml` packages `robogjc` for Python 3.11+ with FastAPI, httpx, pydantic settings, Click, and `gjc-rpc`.\n- `python/robogjc/README.md` documents the webhook-to-worktree-to-gjc flow, GitHub sidecar trust boundary, persistent per-issue sessions, and audit trail.\n- Important modules include `src/server.py`, `src/queue.py`, `src/tasks.py`, `src/worker.py`, `src/host_tools.py`, `src/sandbox.py`, `src/github_client.py`, `src/github_events.py`, `src/db.py`, and `src/config.py`.\n\n## Runtime flow\n\nA normal CLI session starts in `packages/coding-agent/src/cli.ts`, routes through command handling, then reaches `packages/coding-agent/src/main.ts`. `main.ts` converts CLI/runtime settings into `CreateAgentSessionOptions` and calls `createAgentSession()` in `packages/coding-agent/src/sdk.ts`.\n\nThe SDK builds the session context, loads the default skills, creates built-in tools, resolves model/auth state through `@gajae-code/ai`, constructs the system prompt, and instantiates `@gajae-code/agent-core`. The agent loop streams model events, executes tools, records tool results, and hands state back to the selected mode: interactive TUI, print, RPC, RPC-UI, or ACP.\n\n## Verification and gates\n\nPackage-local checks are defined in each `package.json`. For workflow-definition or default-surface changes, the focused gates are:\n\n```sh\nbun scripts/check-visible-definitions.ts\nbun scripts/verify-g002-gates.ts\nbun scripts/rebrand-inventory.ts --strict\nbun test packages/coding-agent/test/default-gjc-definitions.test.ts\n```\n\nFor broader TypeScript verification, use the root script:\n\n```sh\nbun run check:ts\n```\n\nDo not use `tsc` or `npx tsc` directly in this repository.\n",
+	"bridge.md": "# Bridge Protocol Reference (Experimental, Fail-Closed)\n\nBridge mode runs the coding agent as an experimental network control surface over\nHTTPS. For the 0.3.1 release train, the session-control surface is intentionally\n**fail-closed by default** while the bridge security model is hardened.\n\nDefault availability:\n\n- `GET /healthz` is available without auth and returns `{ \"status\": \"ok\" }`.\n- `GET /v1/help` is available without auth and reports the fail-closed endpoint\n  matrix.\n- `POST /v1/handshake` remains authenticated, but the default response advertises\n  no enabled session endpoints, no accepted capabilities, no accepted scopes, and\n  no frame types.\n- `GET /v1/sessions/{session_id}/events` fails closed with\n  `403 endpoint_disabled` after bearer auth succeeds.\n- `POST /v1/sessions/{session_id}/commands` fails closed with\n  `403 endpoint_disabled` after bearer auth succeeds and before body parsing,\n  command validation, scope checks, or dispatch.\n- `POST /v1/sessions/{session_id}/control:claim` and\n  `POST /v1/sessions/{session_id}/control:disconnect` fail closed with\n  `403 endpoint_disabled` after bearer auth succeeds.\n- `POST /v1/sessions/{session_id}/ui-responses/{correlation_id}` fails closed\n  with `403 endpoint_disabled` after bearer auth succeeds and before body parsing\n  or controller checks.\n- `POST /v1/sessions/{session_id}/host-tool-results/{correlation_id}` and\n  `POST /v1/sessions/{session_id}/host-uri-results/{correlation_id}` fail closed\n  with `403 endpoint_disabled` after bearer auth succeeds and before body parsing\n  or host callback handling.\n\nThe implementation still contains the v1 protocol scaffolding and internal tests\nfor the previously enabled surface, but external clients must treat events,\ncommands, controller ownership, UI responses, host tool results, and host URI\nresults as unavailable unless a future release explicitly re-enables them.\n\nPrimary implementation:\n\n- `src/modes/bridge/bridge-mode.ts`\n- `src/modes/bridge/auth.ts`\n- `src/modes/bridge/event-stream.ts`\n- `src/modes/bridge/bridge-client-bridge.ts`\n- `src/modes/bridge/bridge-ui-context.ts`\n- `src/modes/shared/agent-wire/*` (protocol, scopes, handshake, command dispatch/validation, host bridges)\n- `packages/bridge-client/src/*`\n\n## Startup\n\n```bash\ngjc --mode bridge [regular CLI options]\n```\n\nBehavior notes:\n\n- The bridge is served over **HTTPS only**. Startup refuses to bind without TLS\n  configured (see Security and TLS). There is no unencrypted startup path.\n- `@file` CLI arguments are rejected in bridge mode (as in RPC mode).\n- Bridge mode reuses the RPC default-setting overrides and suppresses automatic\n  session title generation.\n- One bridge process serves exactly **one live `AgentSession`**.\n- The default endpoint matrix disables session events, commands, controller\n  ownership, UI responses, host tool results, and host URI results.\n\n### Configuration (environment variables)\n\nSee `docs/environment-variables.md` for the authoritative table. Summary:\n\n| Variable | Required | Default | Notes |\n| --- | --- | --- | --- |\n| `GJC_BRIDGE_TOKEN` | Yes | — | Bearer token for authenticated endpoints. **Secret — never commit.** |\n| `GJC_BRIDGE_TLS_CERT` | Yes | — | Path to the TLS certificate (PEM). |\n| `GJC_BRIDGE_TLS_KEY` | Yes | — | Path to the TLS private key (PEM). **Secret — never commit.** |\n| `GJC_BRIDGE_HOST` | No | `127.0.0.1` | Bind hostname. |\n| `GJC_BRIDGE_PORT` | No | `4077` | Bind port (1–65535). |\n| `GJC_BRIDGE_SCOPES` | No | `prompt` | Parsed for internal compatibility, but default session endpoints are fail-closed. |\n\n## Security and TLS\n\nThe bridge is a network control surface, so it is **secure-by-default**:\n\n- **TLS is mandatory for every bind, including loopback.** Startup fails closed\n  with a clear error if `GJC_BRIDGE_TLS_CERT` and `GJC_BRIDGE_TLS_KEY` are not\n  both set. There is no plaintext fallback and no insecure/trust-bypass switch.\n- **Bearer token is mandatory** for every endpoint except `GET /healthz` and\n  `GET /v1/help`.\n- The TypeScript SDK refuses bearer-token clients over non-`https` URLs by\n  default. It allows plaintext only for `localhost`, `127.0.0.1`, or `[::1]`\n  when the caller explicitly passes the localhost/test opt-in.\n- Session endpoints fail closed by default even when bearer auth and scopes are\n  otherwise valid.\n\n## Handshake\n\n```\nPOST /v1/handshake   (authenticated)\n```\n\nThe client sends its supported protocol version range, requested capabilities,\nand requested scopes. Version mismatch returns `status: \"rejected\"`,\n`reason: \"incompatible_version\"`. Malformed request bodies return\n`400 invalid_request`.\n\nIn the default 0.3.1 fail-closed configuration, a successful authenticated\nhandshake returns:\n\n- `protocol_version` — the server protocol version (`BRIDGE_PROTOCOL_VERSION`, `1`).\n- `session_id` — the single session id this bridge serves.\n- `accepted_capabilities` — empty.\n- `accepted_scopes` — empty.\n- `unsupported` — every requested capability.\n- `endpoints` — all session endpoint descriptors present but empty strings.\n- `frame_types` — empty.\n\n## Fail-Closed Endpoint Matrix\n\nThe disabled endpoint matrix is:\n\n| Surface | Endpoint(s) | Default |\n| --- | --- | --- |\n| Events | `GET /v1/sessions/{session_id}/events?last_seq=<n>` | Disabled |\n| Commands | `POST /v1/sessions/{session_id}/commands` | Disabled |\n| Control | `POST /v1/sessions/{session_id}/control:claim`, `POST /v1/sessions/{session_id}/control:disconnect` | Disabled |\n| UI responses | `POST /v1/sessions/{session_id}/ui-responses/{correlation_id}` | Disabled |\n| Host tool results | `POST /v1/sessions/{session_id}/host-tool-results/{correlation_id}` | Disabled |\n| Host URI results | `POST /v1/sessions/{session_id}/host-uri-results/{correlation_id}` | Disabled |\n\nAuthenticated requests to disabled endpoints return:\n\n```json\n{ \"error\": \"endpoint_disabled\", \"endpoint\": \"commands\" }\n```\n\nThe `endpoint` value is one of `events`, `commands`, `control`, `uiResponses`,\n`hostToolResults`, or `hostUriResults`.\n\n## Protocol Catalog Kept for Internal Compatibility\n\nThe bridge protocol module still defines the v1 command and scope catalog so\nexisting internal tests can validate the dormant implementation and future\nre-enable work has a stable baseline.\n\nWhen internally enabled for compatibility tests, event replay still uses `last_seq` and the bounded replay reset marker `replay_window_exceeded`; command and UI response retries still use `Idempotency-Key`. These mechanisms are dormant for default external bridge clients because the endpoint matrix rejects the endpoints before they reach replay, body parsing, idempotency, scope, or dispatch logic.\n\n### Scopes\n\nThe configurable scope set (`BRIDGE_COMMAND_SCOPES`) is:\n\n- `prompt`\n- `control`\n- `bash`\n- `export`\n- `session`\n- `model`\n- `message:read`\n- `host_tools`\n- `host_uri`\n- `admin`\n\nThe mandatory compliance floor (`MANDATORY_FLOOR_COMMAND_SCOPES`) remains\n`prompt` for the dormant command surface. Because commands are disabled by the\nendpoint matrix, the default handshake advertises no accepted scopes.\n\n### Command catalog and scope mapping\n\n| Command | Scope |\n| --- | --- |\n| `prompt` | `prompt` |\n| `steer` | `prompt` |\n| `follow_up` | `prompt` |\n| `abort` | `prompt` |\n| `abort_and_prompt` | `prompt` |\n| `new_session` | `session` |\n| `get_state` | `message:read` |\n| `set_todos` | `control` |\n| `set_host_tools` | `host_tools` |\n| `set_host_uri_schemes` | `host_uri` |\n| `set_model` | `model` |\n| `cycle_model` | `model` |\n| `get_available_models` | `model` |\n| `set_thinking_level` | `model` |\n| `cycle_thinking_level` | `model` |\n| `set_steering_mode` | `control` |\n| `set_follow_up_mode` | `control` |\n| `set_interrupt_mode` | `control` |\n| `compact` | `control` |\n| `set_auto_compaction` | `control` |\n| `set_auto_retry` | `control` |\n| `abort_retry` | `control` |\n| `bash` | `bash` |\n| `abort_bash` | `bash` |\n| `get_session_stats` | `message:read` |\n| `export_html` | `export` |\n| `switch_session` | `session` |\n| `branch` | `session` |\n| `get_branch_messages` | `session` |\n| `get_last_assistant_text` | `message:read` |\n| `set_session_name` | `session` |\n| `handoff` | `admin` |\n| `get_messages` | `message:read` |\n| `get_login_providers` | `admin` |\n| `login` | `admin` |\n\n### Dormant capabilities and frame types\n\nThese names remain in the protocol code for future compatibility and internal\nconformance tests, but they are not advertised by the default fail-closed\nhandshake:\n\nCapabilities: `events`, `prompt`, `permission`, `elicitation`, `ui.declarative`,\n`host_tools`, `host_uri`.\n\nFrame types: `ready`, `event`, `response`, `ui_request`, `permission_request`,\n`host_tool_call`, `host_uri_request`, `reset`, `error`.\n\n## UI Capability Parity\n\nBridge UI parity remains **semantic, not pixel-perfect** when the dormant UI\nsurface is explicitly enabled for internal validation. Local-only UI capabilities\ncontinue to report typed unsupported results instead of silent defaults:\n\n- `ui.terminal_input`\n- `ui.widget.component`\n- `ui.footer.component`\n- `ui.header.component`\n- `ui.custom.component`\n- `ui.editor.get_text`\n- `ui.editor.component`\n- `ui.tools_expanded`\n- Theme switching is unsupported (`setTheme` returns `{ success: false }`).\n\n## SDK Usage\n\n`@gajae-code/bridge-client` exposes `BridgeClient` with handshake, command\nhelpers mirroring the full RPC command catalog, an `events()` async generator,\ncontroller/UI/host-callback helpers, and an idempotency-key helper. In 0.3.1,\nthose helpers should be expected to fail against the default bridge because the\nserver endpoint matrix disables the corresponding session endpoints.\n\n> Response typing: in this experimental version, `command()` and the typed\n> command helpers return `Promise<unknown>`. Callers narrow the response\n> themselves. Importing `@gajae-code/coding-agent` internal `rpc-types` into the\n> SDK is intentionally avoided to preserve the package boundary; stable shared\n> protocol response types are tracked as follow-up work.\n\n## Limitations\n\n- **Single session per process.** A bridge process serves exactly one live\n  `AgentSession`. The `session_id` is present in every frame and endpoint for\n  ordering and future additive multiplexing, but multi-session multiplexing is\n  **not** implemented in v1.\n- Session events, commands, controller ownership, UI responses, host tool\n  results, and host URI results are disabled by default in 0.3.1.\n- Coarse per-token scopes only (no fine-grained per-command policy yet).\n- UI parity is semantic, not pixel-perfect (see UI Capability Parity).\n\n## Hermes/Claw orchestration layering\n\nFor Hermes/Claw-style orchestration, treat `gjc` as an external runner. The orchestration agent should choose or create the repository checkout first, preferably a dedicated Git worktree for branch-local work, then launch or attach a leader session with `gjc --tmux` from that directory. GJC is not embedded runtime injection into Hermes, Claw Code, or another coding tool.\n\nPublic orchestration boundaries:\n\n1. Choose the repo/worktree and branch that will own changes, logs, and review evidence.\n2. Start or attach the GJC leader with `gjc --tmux` (or `gjc --tmux --worktree <path>` when the worktree path is part of the launch).\n3. Submit the workflow appropriate to the task: `/skill:deep-interview` for requirements discovery, `/skill:ralplan` for plan consensus, and `gjc ultragoal ...` for durable goal tracking through execution and verification.\n4. Use `gjc team ...` only when coordinated parallel tmux workers help with implementation or verification; single-lane work should stay in the leader session.\n5. Collect the handoff state: whether the session stopped cleanly, changed files, commands/checks run, failures, unresolved risks, and evidence summaries.\n\nBridge mode remains the public remote-control protocol for an already-running GJC session, but the session-control endpoints are fail-closed by default in 0.3.1. Keep lifecycle, worktree selection, and evidence policy above the bridge frames, and avoid documenting private deployment, routing, or credential internals. Introducing another authenticated remote-control protocol for the same purpose should require ADR-level rationale.\n\nThe same external-runner workflow is summarized in the README section [Using GJC with other coding agents](../README.md#using-gjc-with-other-coding-agents).\n",
+	"codebase-overview.md": "# Codebase Overview\n\nThis document maps the main parts of the `gajae-code` repository. The root README stays intentionally small; this file is the architecture-oriented companion.\n\n## Product shape\n\nGajae-Code (`gjc`) is centered on `packages/coding-agent/`. The public workflow surface is intentionally fixed at four source-bundled skills and four public role subagents. Runtime state, specs, plans, goals, team state, and local overrides live under `.gjc/`.\n\nDefault workflow skills are embedded from:\n\n```text\npackages/coding-agent/src/defaults/gjc/skills/<name>/SKILL.md\n```\n\nPublic role subagent prompts are embedded from:\n\n```text\npackages/coding-agent/src/prompts/agents/<role>.md\n```\n\nThe runtime can still discover project/user overrides, but the bundled defaults are loaded from source so a missing project `.gjc` directory does not remove the default workflow surface.\n\n## Packages\n\n### `packages/coding-agent/`\n\nMain `gjc` CLI and product runtime.\n\n- `packages/coding-agent/package.json` exposes the `gjc` binary at `src/cli.ts` and the SDK/barrel entrypoint at `src/index.ts`.\n- `packages/coding-agent/src/cli.ts` is the executable bootstrap. It registers CLI commands such as `setup`, `deep-interview`, `ralplan`, `ultragoal`, `team`, and the default launch path.\n- `packages/coding-agent/src/main.ts` adapts CLI options into session creation and dispatches interactive, print, RPC, RPC-UI, and ACP modes.\n- `packages/coding-agent/src/sdk.ts` assembles settings, model registry, auth, workspace/context discovery, skills, rules, tools, system prompt, and the underlying `@gajae-code/agent-core` agent.\n- `packages/coding-agent/src/tools/index.ts` is the built-in tool registry for file/code/runtime tools such as read, bash, edit, AST tools, eval, find/search, LSP, browser, task/subagent, recipe, IRC, todo, web search, and write. Memory backends are private integrations, not public coding-harness tools.\n- `packages/coding-agent/src/defaults/gjc-defaults.ts` embeds and installs the default workflow skills.\n- `packages/coding-agent/src/task/agents.ts` embeds bundled task-agent prompts. The public contract is `executor`, `architect`, `planner`, and `critic`; other bundled prompts are internal/runtime utilities.\n\n### `packages/ai/`\n\nProvider/model boundary for LLM access.\n\n- `packages/ai/src/index.ts` exports model registry/resolution, provider implementations, auth broker/gateway/storage, streaming, usage, retry/overflow utilities, OAuth, discovery, and validation helpers.\n- `packages/ai/src/types.ts` defines provider, model, context, message, tool, usage, reasoning, and stream-event contracts.\n- `packages/ai/src/stream.ts` dispatches model-driven streams to the right provider/API implementation and normalizes streaming events.\n- `packages/ai/src/model-manager.ts` merges static, cached, dynamic, and remote model sources.\n- `packages/ai/README.md` documents tool calling, partial streaming tool calls, thinking/reasoning, provider configuration, context handoff, and OAuth flows.\n\n### `packages/agent/`\n\nStateful agent runtime built on `@gajae-code/ai`.\n\n- `packages/agent/src/index.ts` exports the `Agent`, loop APIs, append-only context, compaction, telemetry, proxy utilities, thinking helpers, and shared types.\n- `packages/agent/src/agent-loop.ts` owns the turn loop: transform context, call the model stream, execute tool calls, append tool results, and emit lifecycle events.\n- `packages/agent/src/agent.ts` wraps the loop with mutable state, subscriptions, prompt/continue/abort APIs, queues, provider session state, telemetry, and state mutation helpers.\n- `packages/agent/src/types.ts` defines `AgentMessage`, `AgentTool`, loop config, event, and runtime state contracts.\n\n### `packages/tui/`\n\nTerminal UI framework used by the CLI.\n\n- `packages/tui/src/index.ts` exports components, keybindings, autocomplete, terminal abstractions, image support, TUI core, and utilities.\n- `packages/tui/src/tui.ts` manages component rendering, focus, overlays, terminal dimensions, diff state, and synchronized output.\n- `packages/tui/src/terminal.ts` abstracts terminal lifecycle, dimensions, cursor controls, title/progress, Kitty protocol state, and appearance notifications.\n- `packages/tui/README.md` documents the component model and built-in components such as text, input, editor, markdown, loaders, select/settings lists, spacer, image, box, and container.\n\n### `packages/natives/` and Rust crates\n\nNative helper layer exposed through N-API.\n\n- `packages/natives/package.json` exports `native/index.js` and generated TypeScript definitions.\n- `packages/natives/native/loader-state.js` resolves platform/CPU-specific native binaries and validates package/native version alignment.\n- `crates/pi-natives/src/lib.rs` is the N-API root for appearance, AST search/editing, clipboard, filesystem scan/cache, grep/glob, syntax highlighting, HTML-to-Markdown, keyboard parsing, process/PTY/shell support, SIXEL, code summarization, token counting, text measurement/wrapping/truncation, workspace scanning, power assertions, and isolation helpers.\n- `crates/pi-shell/src/lib.rs` exposes brush-based shell execution primitives used by the native shell adapter.\n- `crates/pi-shell/src/shell.rs` implements persistent and one-shot shell execution, streaming, environment handling, cancellation, and output minimizer telemetry.\n- `crates/pi-shell/src/fixup.rs` performs conservative AST-based bash command fixups.\n- `crates/pi-natives/src/pty.rs` implements interactive PTY sessions.\n\n### `packages/utils/`\n\nShared TypeScript utilities.\n\n- `packages/utils/src/index.ts` exports abortable/async helpers, color/env/dir utilities, fetch retry, formatting, frontmatter, glob helpers, JSON helpers, logging, MIME detection, prompt rendering, process-tree helpers, sanitization, streams, temp files, tab spacing, type guards, and executable lookup.\n- `packages/utils/src/ptree.ts` and `packages/utils/src/procmgr.ts` wrap native process helpers for ergonomic TypeScript use.\n\n### `packages/stats/`\n\nLocal observability dashboard for session and model usage.\n\n- `packages/stats/src/index.ts` exposes the `gjc-stats` CLI entrypoint and exports aggregation/server APIs.\n- `packages/stats/src/aggregator.ts` parses session-derived request metrics and writes aggregated data through SQLite.\n- `packages/stats/src/server.ts` serves local dashboard API routes and static SPA assets.\n- `packages/stats/src/types.ts` and `packages/stats/src/shared-types.ts` define dashboard and aggregate metric shapes.\n\n### `packages/swarm-extension/`\n\nOptional YAML/DAG multi-agent extension outside the fixed default workflow surface.\n\n- `packages/swarm-extension/README.md` documents standalone `gjc-swarm` execution and in-TUI `/swarm` commands.\n- Swarm workflows define agents, tasks, dependency edges, waves, and shared workspace state under `.swarm_<name>/`.\n\n### `packages/typescript-edit-benchmark/`\n\nPrivate benchmark package for TypeScript edit tasks.\n\n- `packages/typescript-edit-benchmark/package.json` exposes `typescript-edit-benchmark` and depends on the coding-agent, agent-core, ai, tui, utils, diff, prettier, and Babel tooling.\n- `packages/typescript-edit-benchmark/src/index.ts` is the benchmark CLI: it resolves fixtures, loads tasks, runs edit attempts, records progress, and writes reports/conversation dumps under `runs/`.\n\n## Python packages\n\n### `python/gjc-rpc/`\n\nTyped Python client for `gjc --mode rpc`.\n\n- `python/gjc-rpc/pyproject.toml` packages `gjc-rpc` for Python 3.11+.\n- `python/gjc-rpc/README.md` documents the process-backed stdio client, typed command methods, startup flags, event listeners, todo seeding, host-owned tools, and host-owned URI schemes.\n\n### `python/robogjc/`\n\nSelf-hosted GitHub triage/fix bot that drives `gjc --mode rpc`.\n\n- `python/robogjc/AGENTS.md` is the authoritative local contract for this subtree.\n- `python/robogjc/pyproject.toml` packages `robogjc` for Python 3.11+ with FastAPI, httpx, pydantic settings, Click, and `gjc-rpc`.\n- `python/robogjc/README.md` documents the webhook-to-worktree-to-gjc flow, GitHub sidecar trust boundary, persistent per-issue sessions, and audit trail.\n- Important modules include `src/server.py`, `src/queue.py`, `src/tasks.py`, `src/worker.py`, `src/host_tools.py`, `src/sandbox.py`, `src/github_client.py`, `src/github_events.py`, `src/db.py`, and `src/config.py`.\n\n## Runtime flow\n\nA normal CLI session starts in `packages/coding-agent/src/cli.ts`, routes through command handling, then reaches `packages/coding-agent/src/main.ts`. `main.ts` converts CLI/runtime settings into `CreateAgentSessionOptions` and calls `createAgentSession()` in `packages/coding-agent/src/sdk.ts`.\n\nThe SDK builds the session context, loads the default skills, creates built-in tools, resolves model/auth state through `@gajae-code/ai`, constructs the system prompt, and instantiates `@gajae-code/agent-core`. The agent loop streams model events, executes tools, records tool results, and hands state back to the selected mode: interactive TUI, print, RPC, RPC-UI, or ACP.\n\n## Verification and gates\n\nPackage-local checks are defined in each `package.json`. For workflow-definition or default-surface changes, the focused gates are:\n\n```sh\nbun scripts/check-visible-definitions.ts\nbun scripts/verify-g002-gates.ts\nbun scripts/rebrand-inventory.ts --strict\nbun test packages/coding-agent/test/default-gjc-definitions.test.ts\n```\n\nFor broader TypeScript verification, use the root script:\n\n```sh\nbun run check:ts\n```\n\nDo not use `tsc` or `npx tsc` directly in this repository.\n",
 	"compaction.md": "# Compaction and Branch Summaries\n\nCompaction and branch summaries are the two mechanisms that keep long sessions usable without losing prior work context.\n\n- **Compaction** rewrites old history into a summary on the current branch.\n- **Branch summary** captures abandoned branch context during `/tree` navigation.\n\nBoth are persisted as session entries and converted back into user-context messages when rebuilding LLM input.\n\n## Key implementation files\n\n- `packages/agent/src/compaction/compaction.ts` (context-full summarization and handoff generation)\n- `packages/agent/src/compaction/branch-summarization.ts`\n- `packages/agent/src/compaction/pruning.ts`\n- `packages/agent/src/compaction/utils.ts`\n- `packages/agent/src/compaction/openai.ts`\n- `packages/coding-agent/src/session/session-manager.ts`\n- `packages/coding-agent/src/session/agent-session.ts`\n- `packages/coding-agent/src/session/messages.ts`\n- `packages/coding-agent/src/extensibility/hooks/types.ts`\n- `packages/coding-agent/src/config/settings-schema.ts`\n\n## Session entry model\n\nCompaction and branch summaries are first-class session entries, not plain assistant/user messages.\n\n- `CompactionEntry`\n  - `type: \"compaction\"`\n  - `summary`, optional `shortSummary`\n  - `firstKeptEntryId` (compaction boundary)\n  - `tokensBefore`\n  - optional `details`, `preserveData`, `fromExtension`\n- `BranchSummaryEntry`\n  - `type: \"branch_summary\"`\n  - `fromId`, `summary`\n  - optional `details`, `fromExtension`\n\nWhen context is rebuilt (`buildSessionContext`):\n\n1. Latest compaction on the active path is converted to one `compactionSummary` message.\n2. Kept entries from `firstKeptEntryId` to the compaction point are re-included.\n3. Later entries on the path are appended.\n4. `branch_summary` entries are converted to `branchSummary` messages.\n5. `custom_message` entries are converted to `custom` messages.\n\nThose custom roles are then transformed into LLM-facing user messages in `convertToLlm()` using the static templates:\n\n- `packages/agent/src/compaction/prompts/compaction-summary-context.md`\n- `packages/agent/src/compaction/prompts/branch-summary-context.md`\n- `packages/agent/src/compaction/prompts/handoff-document.md`\n\n## Compaction pipeline\n\n### Triggers\n\nCompaction/context maintenance can run in four ways:\n\n1. **Manual context compaction**: `/compact [instructions]` calls `AgentSession.compact(...)`.\n2. **Automatic overflow recovery**: after a same-model assistant error that matches context overflow.\n3. **Automatic threshold maintenance**: after a successful turn when context exceeds the resolved threshold.\n4. **Idle maintenance**: `runIdleCompaction()` can invoke the same auto-maintenance path with reason `\"idle\"`.\n\n### Compaction shape (visual)\n\n```text\nBefore compaction:\n\n  entry:  0     1     2     3      4     5     6      7      8     9\n        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┐\n        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │\n        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┘\n                └────────┬───────┘ └──────────────┬──────────────┘\n               messagesToSummarize            kept messages\n                                   ↑\n                          firstKeptEntryId (entry 4)\n\nAfter compaction (new entry appended):\n\n  entry:  0     1     2     3      4     5     6      7      8     9      10\n        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┬─────┐\n        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │ cmp │\n        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┴─────┘\n               └──────────┬──────┘ └──────────────────────┬───────────────────┘\n                 not sent to LLM                    sent to LLM\n                                                         ↑\n                                              starts from firstKeptEntryId\n\nWhat the LLM sees:\n\n  ┌────────┬─────────┬─────┬─────┬──────┬──────┬─────┬──────┐\n  │ system │ summary │ usr │ ass │ tool │ tool │ ass │ tool │\n  └────────┴─────────┴─────┴─────┴──────┴──────┴─────┴──────┘\n       ↑         ↑      └─────────────────┬────────────────┘\n    prompt   from cmp          messages from firstKeptEntryId\n```\n\n### Overflow-retry vs threshold/idle maintenance\n\nThe automatic paths are intentionally different:\n\n- **Overflow recovery**\n  - Trigger: current-model assistant error is detected as context overflow and the error is not older than the latest compaction.\n  - The failing assistant error message is removed from active agent state before retry.\n  - Context promotion is tried first; if a configured larger model is available, the agent switches model and retries without compacting.\n  - If promotion is unavailable and compaction is enabled, context-full compaction runs with `reason: \"overflow\"` and `willRetry: true`; handoff strategy is not used for overflow.\n  - On success, agent auto-continues (`agent.continue()`) after compaction.\n\n- **Threshold maintenance**\n  - Trigger: successful, non-error assistant message whose adjusted context tokens exceed `resolveThresholdTokens(...)`.\n  - Tool-output pruning can reduce the measured token count before threshold comparison.\n  - Context promotion is tried before compaction.\n  - If promotion is unavailable, auto maintenance runs with `reason: \"threshold\"` and `willRetry: false`.\n  - With `compaction.strategy: \"handoff\"`, threshold maintenance starts a new handoff session instead of writing a compaction entry; if handoff returns no document without aborting, it falls back to context-full compaction.\n  - On success, if `compaction.autoContinue !== false`, schedules an agent-authored developer auto-continue prompt from `prompts/system/auto-continue.md`.\n\n- **Idle maintenance**\n  - Trigger: `runIdleCompaction()` when not streaming or already compacting.\n  - Uses `reason: \"idle\"` and does not auto-continue afterward.\n\n### Pre-compaction pruning\n\nBefore compaction checks, tool-result pruning may run (`pruneToolOutputs`).\n\nDefault prune policy:\n\n- Protect newest `40_000` tool-output tokens.\n- Require at least `20_000` total estimated savings.\n- Never prune tool results from `skill` or `read`.\n\nPruned tool results are replaced with:\n\n- `[Output truncated - N tokens]`\n\nIf pruning changes entries, session storage is rewritten and agent message state is refreshed before compaction decisions.\n\n### Boundary and cut-point logic\n\n`prepareCompaction()` only considers entries since the last compaction entry (if any).\n\n1. Find previous compaction index.\n2. Compute `boundaryStart = prevCompactionIndex + 1`.\n3. Adapt `keepRecentTokens` using measured usage ratio when available.\n4. Run `findCutPoint()` over the boundary window.\n\nValid cut points include:\n\n- message entries with roles: `user`, `assistant`, `bashExecution`, `hookMessage`, `branchSummary`, `compactionSummary`\n- `custom_message` entries\n- `branch_summary` entries\n\nHard rule: never cut at `toolResult`.\n\nIf there are non-message metadata entries immediately before the cut point (`model_change`, `thinking_level_change`, labels, etc.), they are pulled into the kept region by moving cut index backward until a message or compaction boundary is hit.\n\n### Split-turn handling\n\nIf cut point is not at a user-turn start, compaction treats it as a split turn.\n\nTurn start detection treats these as user-turn boundaries:\n\n- `message.role === \"user\"`\n- `message.role === \"bashExecution\"`\n- `custom_message` entry\n- `branch_summary` entry\n\nSplit-turn compaction generates two summaries:\n\n1. History summary (`messagesToSummarize`)\n2. Turn-prefix summary (`turnPrefixMessages`)\n\nFinal stored summary is merged as:\n\n```markdown\n<history summary>\n\n---\n\n**Turn Context (split turn):**\n\n<turn prefix summary>\n```\n\n### Summary generation\n\n`compact(...)` builds summaries from serialized conversation text:\n\n1. Convert messages via `convertToLlm()`.\n2. Serialize with `serializeConversation()`.\n3. Wrap in `<conversation>...</conversation>`.\n4. Optionally include `<previous-summary>...</previous-summary>`.\n5. Optionally inject hook context as `<additional-context>` list.\n6. Execute summarization prompt with `SUMMARIZATION_SYSTEM_PROMPT`.\n\nPrompt selection:\n\n- first compaction: `compaction-summary.md`\n- iterative compaction with prior summary: `compaction-update-summary.md`\n- split-turn second pass: `compaction-turn-prefix.md`\n- short UI summary: `compaction-short-summary.md`\n- handoff document: `handoff-document.md` (used by `generateHandoff(...)`, not serialized compaction)\n\nRemote summarization modes:\n\n- If `compaction.remoteEndpoint` is set and remote compaction is enabled, local summary generation POSTs:\n  - `{ systemPrompt, prompt }`\n- Expects JSON containing at least `{ summary }`.\n- For OpenAI/OpenAI code provider models, compaction first tries the provider-native `/responses/compact` endpoint when remote compaction is enabled. It preserves provider replacement history in `preserveData.openaiRemoteCompaction` and falls back to local summarization if that native request fails.\n\n### Handoff generation\n\n`packages/agent/src/compaction/compaction.ts` also exports `generateHandoff(...)`. Handoff generation uses the same `completeSimple(...)` oneshot style as summarization, but it preserves the live agent cache prefix by sending the active system prompt, tool array, and real LLM message history, then appending one agent-attributed `user` message containing the handoff prompt. It forces `toolChoice: \"none\"` and returns joined text blocks directly.\n\nHandoff does not write a `CompactionEntry`. `AgentSession.handoff()` owns the session transition: it starts a new session, injects the generated document as a visible `custom_message` with `customType: \"handoff\"`, and rebuilds agent messages from that new session.\n\n### File-operation context in summaries\n\nCompaction tracks cumulative file activity using assistant tool calls:\n\n- `read(path)` → read set\n- `write(path)` → modified set\n- `edit(path)` → modified set\n\nCumulative behavior:\n\n- Includes prior compaction details only when prior entry is pi-generated (`fromExtension !== true`).\n- In split turns, includes turn-prefix file ops too.\n- `readFiles` excludes files also modified.\n\nSummary text gets file tags appended via prompt template:\n\n```xml\n<read-files>\n...\n</read-files>\n<modified-files>\n...\n</modified-files>\n```\n\n### Persist and reload\n\nAfter summary generation (or hook-provided summary), agent session:\n\n1. Appends `CompactionEntry` with `appendCompaction(...)` for context-full maintenance; handoff strategy creates a new session and injects a handoff `custom_message` instead.\n2. Rebuilds display context from the active leaf via `buildDisplaySessionContext()`.\n3. Replaces live agent messages with rebuilt context.\n4. Emits `session_compact` hook event.\n\n## Branch summarization pipeline\n\nBranch summarization is tied to tree navigation, not token overflow.\n\n### Trigger\n\nDuring `navigateTree(...)`:\n\n1. Compute abandoned entries from old leaf to common ancestor using `collectEntriesForBranchSummary(...)`.\n2. If caller requested summary (`options.summarize`), generate summary before switching leaf.\n3. If summary exists, attach it at the navigation target using `branchWithSummary(...)`.\n\nOperationally this is commonly driven by `/tree` flow when `branchSummary.enabled` is enabled.\n\n### Branch switch shape (visual)\n\n```text\nTree before navigation:\n\n         ┌─ B ─ C ─ D (old leaf, being abandoned)\n    A ───┤\n         └─ E ─ F (target)\n\nCommon ancestor: A\nEntries to summarize: B, C, D\n\nAfter navigation with summary:\n\n         ┌─ B ─ C ─ D ─ [summary of B,C,D]\n    A ───┤\n         └─ E ─ F (new leaf)\n```\n\n### Preparation and token budget\n\n`generateBranchSummary(...)` computes budget as:\n\n- `tokenBudget = model.contextWindow - branchSummary.reserveTokens`\n\n`prepareBranchEntries(...)` then:\n\n1. First pass: collect cumulative file ops from all summarized entries, including prior pi-generated `branch_summary` details.\n2. Second pass: walk newest → oldest, adding messages until token budget is reached.\n3. Prefer preserving recent context.\n4. May still include large summary entries near budget edge for continuity.\n\nCompaction entries are included as messages (`compactionSummary`) during branch summarization input.\n\n### Summary generation and persistence\n\nBranch summarization:\n\n1. Converts and serializes selected messages.\n2. Wraps in `<conversation>`.\n3. Uses custom instructions if supplied, otherwise `branch-summary.md`.\n4. Calls summarization model with `SUMMARIZATION_SYSTEM_PROMPT`.\n5. Prepends `branch-summary-preamble.md`.\n6. Appends file-operation tags.\n\nResult is stored as `BranchSummaryEntry` with optional details (`readFiles`, `modifiedFiles`).\n\n## Extension and hook touchpoints\n\n### `session_before_compact`\n\nPre-compaction hook.\n\nCan:\n\n- cancel compaction (`{ cancel: true }`)\n- provide full custom compaction payload (`{ compaction: CompactionResult }`)\n\n### `session.compacting`\n\nPrompt/context customization hook for default compaction.\n\nCan return:\n\n- `prompt` (override base summary prompt)\n- `context` (extra context lines injected into `<additional-context>`)\n- `preserveData` (stored on compaction entry)\n\n### `session_compact`\n\nPost-compaction notification with saved `compactionEntry` and `fromExtension` flag.\n\n### `session_before_tree`\n\nRuns on tree navigation before default branch summary generation.\n\nCan:\n\n- cancel navigation\n- provide custom `{ summary: { summary, details } }` used when user requested summarization\n\n### `session_tree`\n\nPost-navigation event exposing new/old leaf and optional summary entry.\n\n## Runtime behavior and failure semantics\n\n- Manual compaction aborts current agent operation first.\n- `abortCompaction()` cancels both manual and auto-compaction controllers.\n- Auto compaction emits start/end session events for UI/state updates.\n- Auto compaction can try multiple model candidates and retry transient failures; long retry delays prefer the next candidate when one is available.\n- Overflow errors are excluded from generic retry path because they are handled by context promotion/compaction.\n- If auto-compaction fails:\n  - overflow path emits `Context overflow recovery failed: ...`\n  - threshold path emits `Auto-compaction failed: ...`\n- Branch summarization can be cancelled via abort signal (e.g., Escape), returning canceled/aborted navigation result.\n\n## Settings and defaults\n\nFrom `settings-schema.ts`:\n\n- `compaction.enabled` = `true`\n- `compaction.strategy` = `\"context-full\"` (`\"handoff\"` and `\"off\"` are also supported)\n- `compaction.reserveTokens` = `16384`\n- `compaction.keepRecentTokens` = `20000`\n- `compaction.autoContinue` = `true`\n- `compaction.remoteEnabled` = `true`\n- `compaction.remoteEndpoint` = `undefined`\n- `compaction.thresholdPercent` = `-1` and `compaction.thresholdTokens` = `-1`; when no positive override is set, the threshold is `contextWindow - max(15% of contextWindow, reserveTokens)`\n- `compaction.idleEnabled` = `true`\n- `branchSummary.enabled` = `false`\n- `branchSummary.reserveTokens` = `16384`\n\nThese values are consumed at runtime by `AgentSession` and compaction/branch summarization modules.\n",
-	"environment-variables.md": "# Environment Variables (Current Runtime Reference)\n\nThis reference is derived from current code paths in:\n\n- `packages/coding-agent/src/**`\n- `packages/ai/src/**` (provider/auth resolution used by coding-agent)\n- `packages/utils/src/**` and `packages/tui/src/**` where those vars directly affect coding-agent runtime\n\nIt documents only active behavior.\n\n## Resolution model and precedence\n\nMost runtime lookups use `$env` from `@gajae-code/utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Agent `.env` (`~/.gjc/agent/.env`, respecting `GJC_CONFIG_DIR` / `GJC_CODING_AGENT_DIR`) for keys not already set\n4. Config-root `.env` (`~/.gjc/.env`, respecting `GJC_CONFIG_DIR`) for keys not already set\n5. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule inside each `.env` file: `GJC_*` keys are mirrored to `GJC_*` keys in that parsed file.\n\n---\n\n## 1) Model/provider authentication\n\nThese are consumed via `getEnvApiKey()` (`packages/ai/src/stream.ts`) unless noted otherwise.\n\n### Core provider credentials\n\n| Variable                        | Used for                                         | Required when                                                  | Notes / precedence                                                                                  |\n| ------------------------------- | ------------------------------------------------ | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- |\n| `ANTHROPIC_OAUTH_TOKEN`         | Anthropic API auth                               | Using Anthropic with OAuth token auth                          | Takes precedence over `ANTHROPIC_API_KEY` for provider auth resolution                              |\n| `ANTHROPIC_API_KEY`             | Anthropic API auth                               | Using Anthropic without OAuth token                            | Fallback after `ANTHROPIC_OAUTH_TOKEN`                                                              |\n| `ANTHROPIC_FOUNDRY_API_KEY`     | Anthropic via Azure Foundry / enterprise gateway | `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` enabled                              | Takes precedence over `ANTHROPIC_OAUTH_TOKEN` and `ANTHROPIC_API_KEY` when Foundry mode is enabled  |\n| `OPENAI_API_KEY`                | OpenAI auth                                      | Using OpenAI-family providers without explicit apiKey argument | Used by OpenAI Completions/Responses providers                                                      |\n| `GEMINI_API_KEY`                | Google Gemini auth                               | Using `google` provider models                                 | Primary key for Gemini provider mapping                                                             |\n| `GOOGLE_API_KEY`                | Gemini image tool auth fallback                  | Using `gemini_image` tool without `GEMINI_API_KEY`             | Used by coding-agent image tool fallback path                                                       |\n| `GROQ_API_KEY`                  | Groq auth                                        | Using Groq models                                              |                                                                                                     |\n| `CEREBRAS_API_KEY`              | Cerebras auth                                    | Using Cerebras models                                          |                                                                                                     |\n| `FIREWORKS_API_KEY`             | Fireworks auth                                   | Using Fireworks models                                         |                                                                                                     |\n| `TOGETHER_API_KEY`              | Together auth                                    | Using `together` provider                                      |                                                                                                     |\n| `HUGGINGFACE_HUB_TOKEN`         | Hugging Face auth                                | Using `huggingface` provider                                   | Primary Hugging Face token env var                                                                  |\n| `HF_TOKEN`                      | Hugging Face auth                                | Using `huggingface` provider                                   | Fallback when `HUGGINGFACE_HUB_TOKEN` is unset                                                      |\n| `SYNTHETIC_API_KEY`             | Synthetic auth                                   | Using Synthetic models                                         |                                                                                                     |\n| `NVIDIA_API_KEY`                | NVIDIA auth                                      | Using `nvidia` provider                                        |                                                                                                     |\n| `NANO_GPT_API_KEY`              | NanoGPT auth                                     | Using `nanogpt` provider                                       |                                                                                                     |\n| `VENICE_API_KEY`                | Venice auth                                      | Using `venice` provider                                        |                                                                                                     |\n| `LITELLM_API_KEY`               | LiteLLM auth                                     | Using `litellm` provider                                       | OpenAI-compatible LiteLLM proxy key                                                                 |\n| `LM_STUDIO_API_KEY`             | LM Studio auth (optional)                        | Using `lm-studio` provider with authenticated hosts            | Local LM Studio usually runs without auth; any non-empty token works when a key is required         |\n| `OLLAMA_API_KEY`                | Ollama auth (optional)                           | Using `ollama` provider with authenticated hosts               | Local Ollama usually runs without auth; any non-empty token works when a key is required            |\n| `LLAMA_CPP_API_KEY`             | llama.cpp auth (optional)                        | Using `llama.cpp` provider with authenticated hosts            | Local llama.cpp usually runs without auth; any non-empty token works when a key is configured       |\n| `XIAOMI_API_KEY`                | Xiaomi MiMo auth                                 | Using `xiaomi` provider                                        |                                                                                                     |\n| `MOONSHOT_API_KEY`              | Moonshot auth                                    | Using `moonshot` provider                                      |                                                                                                     |\n| `XAI_API_KEY`                   | xAI auth                                         | Using xAI models                                               |                                                                                                     |\n| `OPENROUTER_API_KEY`            | OpenRouter auth                                  | Using OpenRouter models                                        | Also used by image tool when preferred/auto provider is OpenRouter                                  |\n| `MISTRAL_API_KEY`               | Mistral auth                                     | Using Mistral models                                           |                                                                                                     |\n| `ZAI_API_KEY`                   | z.ai auth                                        | Using z.ai models                                              | Also used by z.ai web search provider                                                               |\n| `MINIMAX_API_KEY`               | MiniMax auth                                     | Using `minimax` provider                                       |                                                                                                     |\n| `AZURE_OPENAI_API_KEY`          | Azure OpenAI auth                               | Using `azure-openai` / `azure-openai-responses` models         | Pair with `AZURE_OPENAI_BASE_URL` or `AZURE_OPENAI_RESOURCE_NAME`                                   |\n| `MINIMAX_CODE_API_KEY`          | MiniMax Code auth                                | Using `minimax-code` provider                                  |                                                                                                     |\n| `MINIMAX_CODE_CN_API_KEY`       | MiniMax Code CN auth                             | Using `minimax-code-cn` provider                               |                                                                                                     |\n| `OPENCODE_API_KEY`              | OpenCode auth                                    | Using `opencode-go` / `opencode-zen` models                    |                                                                                                     |\n| `QIANFAN_API_KEY`               | Qianfan auth                                     | Using `qianfan` provider                                       |                                                                                                     |\n| `QWEN_OAUTH_TOKEN`              | Qwen Portal auth                                 | Using `qwen-portal` with OAuth token                           | Takes precedence over `QWEN_PORTAL_API_KEY`                                                         |\n| `QWEN_PORTAL_API_KEY`           | Qwen Portal auth                                 | Using `qwen-portal` with API key                               | Fallback after `QWEN_OAUTH_TOKEN`                                                                   |\n| `ZENMUX_API_KEY`                | ZenMux auth                                      | Using `zenmux` provider                                        | Used for ZenMux OpenAI and Anthropic-compatible routes                                              |\n| `VLLM_API_KEY`                  | vLLM auth/discovery opt-in                       | Using `vllm` provider (local OpenAI-compatible servers)        | Any non-empty value works for no-auth local servers                                                 |\n| `CURSOR_ACCESS_TOKEN`           | Cursor provider auth                             | Using Cursor provider                                          |                                                                                                     |\n| `AI_GATEWAY_API_KEY`            | Vercel AI Gateway auth                           | Using `vercel-ai-gateway` provider                             |                                                                                                     |\n| `CLOUDFLARE_AI_GATEWAY_API_KEY` | Cloudflare AI Gateway auth                       | Using `cloudflare-ai-gateway` provider                         | Base URL must be configured as `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic` |\n| `ALIBABA_CODING_PLAN_API_KEY`   | Alibaba Coding Plan auth                         | Using `alibaba-coding-plan` provider                           |                                                                                                     |\n| `DEEPSEEK_API_KEY`              | DeepSeek auth                                    | Using DeepSeek models                                          |                                                                                                     |\n| `KILO_API_KEY`                  | Kilo auth                                        | Using Kilo models                                              |                                                                                                     |\n| `OLLAMA_CLOUD_API_KEY`          | Ollama Cloud auth                                | Using `ollama-cloud` provider                                  |                                                                                                     |\n| `GITLAB_TOKEN`                  | GitLab Duo auth                                  | Using `gitlab-duo` provider                                    |                                                                                                     |\n\n### GitHub/Copilot token chains\n\n| Variable               | Used for                                         | Chain                                                |\n| ---------------------- | ------------------------------------------------ | ---------------------------------------------------- |\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth                     | `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` |\n| `GH_TOKEN`             | Copilot fallback; GitHub API auth in web scraper | In web scraper: `GITHUB_TOKEN` → `GH_TOKEN`          |\n| `GITHUB_TOKEN`         | Copilot fallback; GitHub API auth in web scraper | In web scraper: checked before `GH_TOKEN`            |\n\n### Auth broker / auth gateway (remote credential vault)\n\nWhen the broker is enabled, the local SQLite credential store is bypassed and all OAuth refresh / access tokens live on the broker host. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full protocol, CLI surface, and 5-min/15-s usage cache layering.\n\n| Variable                | Used for                                                                                          | Required when                                                                                                          | Notes / precedence                                                                                                                                                                                  |\n| ----------------------- | ------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `GJC_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`); selects broker mode      | Resolving credentials through a broker; also required by `gjc auth-gateway serve` (the gateway is itself a broker client) | Wins over `auth.broker.url` in `config.yml`. When set with no resolvable token, `resolveAuthBrokerConfig()` hard-errors instead of falling back to local SQLite.                                    |\n| `GJC_AUTH_BROKER_TOKEN` | Bearer token sent on every broker endpoint except `/v1/healthz`                                   | `GJC_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`     | Resolution: this env → `auth.broker.token` (`$ENV_NAME` indirection supported) → `<config-dir>/auth-broker.token` (mode `0600`). `<config-dir>` is `~/.gjc/` (respecting `GJC_CONFIG_DIR`).         |\n\nThe gateway has no dedicated env vars — it inherits `GJC_AUTH_BROKER_*`. Its own inbound bearer token lives at `<config-dir>/auth-gateway.token` and is managed via `gjc auth-gateway token`.\n\n---\n\n## 2) Provider-specific runtime configuration\n\n### Anthropic Foundry Gateway (Azure / enterprise proxy)\n\nWhen `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled, Anthropic requests switch to Foundry mode:\n\n- Base URL resolves from `FOUNDRY_BASE_URL` (fallback remains model/default base URL if unset).\n- API key resolution for provider `anthropic` becomes:\n  `ANTHROPIC_FOUNDRY_API_KEY` → `ANTHROPIC_OAUTH_TOKEN` → `ANTHROPIC_API_KEY`.\n- `ANTHROPIC_CUSTOM_HEADERS` is parsed as comma/newline-separated `key: value` pairs and merged into request headers.\n- TLS client/server material can be injected from env values:\n  `NODE_EXTRA_CA_CERTS`, `ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`.\n  Each accepts either:\n  - a filesystem path to PEM content, or\n  - inline PEM (including escaped `\\n` sequences).\n\n| Variable                    | Value type                                     | Behavior                                                                      |\n| --------------------------- | ---------------------------------------------- | ----------------------------------------------------------------------------- |\n| `ANTHROPIC_MODEL_CODE_USE_FOUNDRY`   | Boolean-like string (`1`, `true`, `yes`, `on`) | Enables Foundry mode for Anthropic provider                                   |\n| `FOUNDRY_BASE_URL`          | URL string                                     | Anthropic endpoint base URL in Foundry mode                                   |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Token string                                   | Used for `Authorization: Bearer <token>`                                      |\n| `ANTHROPIC_CUSTOM_HEADERS`  | Header list string                             | Extra headers; format `header-a: value, header-b: value` or newline-separated |\n| `NODE_EXTRA_CA_CERTS`       | PEM path or inline PEM                         | Extra CA chain for server certificate validation                              |\n| `ANTHROPIC_MODEL_CODE_CLIENT_CERT`   | PEM path or inline PEM                         | mTLS client certificate                                                       |\n| `ANTHROPIC_MODEL_CODE_CLIENT_KEY`    | PEM path or inline PEM                         | mTLS client private key (must be paired with cert)                            |\n\n### Amazon Bedrock\n\n| Variable                                                                        | Default / behavior                                                                            |\n| ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `AWS_REGION`                                                                    | Primary region source                                                                         |\n| `AWS_DEFAULT_REGION`                                                            | Fallback if `AWS_REGION` unset                                                                |\n| `AWS_PROFILE`                                                                   | Enables named profile auth path                                                               |\n| `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`                                   | Enables IAM key auth path                                                                     |\n| `AWS_BEARER_TOKEN_BEDROCK`                                                      | Enables bearer token auth path                                                                |\n| `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI` / `AWS_CONTAINER_CREDENTIALS_FULL_URI` | Enables ECS task credential path                                                              |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN`                                  | Enables web identity auth path                                                                |\n| `AWS_BEDROCK_SKIP_AUTH`                                                         | If `1`, injects dummy credentials (proxy/non-auth scenarios)                                  |\n| `AWS_BEDROCK_FORCE_HTTP1`                                                       | If `1`, forces Node HTTP/1 request handler                                                    |\n| `HTTPS_PROXY` / `HTTP_PROXY` / `ALL_PROXY`                                      | Routes Bedrock runtime and AWS SSO credential calls through the configured proxy using HTTP/1 |\n| `NO_PROXY`                                                                      | Excludes matching hosts from proxy routing when a proxy variable is configured                |\n\nRegion fallback in provider code: `options.region` → `AWS_REGION` → `AWS_DEFAULT_REGION` → `us-east-1`.\n\nCredential fallback order is static env (`AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY` plus optional `AWS_SESSION_TOKEN`), named profile / SSO / `credential_process`, then EC2 IMDSv2. `models.yml` Bedrock entries use `api: bedrock-converse-stream` and do not require `apiKey` or `apiKeyEnv` because the provider signs requests from this AWS chain.\n\n### Azure OpenAI Responses\n\n| Variable                           | Default / behavior                                                          |\n| ---------------------------------- | --------------------------------------------------------------------------- |\n| `AZURE_OPENAI_API_KEY`             | Required unless API key passed as option                                    |\n| `AZURE_OPENAI_API_VERSION`         | Default `v1`                                                                |\n| `AZURE_OPENAI_BASE_URL`            | Direct base URL override                                                    |\n| `AZURE_OPENAI_RESOURCE_NAME`       | Used to construct base URL: `https://<resource>.openai.azure.com/openai/v1` |\n| `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` | Optional mapping string: `modelId=deploymentName,model2=deployment2`        |\n\nBase URL resolution: option `azureBaseUrl` → env `AZURE_OPENAI_BASE_URL` → option/env resource name → `model.baseUrl`.\n\n### Model provider base URL overrides\n\nBuilt-in model provider base URLs resolve with this precedence:\n\n1. `models.yml` / model config provider `baseUrl`\n2. provider-specific base URL environment variable\n3. bundled provider default\n\nSupported aliases:\n\n| Provider | Variables |\n| --- | --- |\n| OpenAI | `OPENAI_BASE_URL` |\n| Anthropic | `ANTHROPIC_BASE_URL` |\n| Google Gemini | `GOOGLE_BASE_URL`, `GEMINI_BASE_URL` |\n| Google Antigravity | `GOOGLE_ANTIGRAVITY_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Gemini CLI | `GOOGLE_GEMINI_CLI_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Vertex | `GOOGLE_VERTEX_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Any provider id | derived `<PROVIDER_ID>_BASE_URL`, uppercased with non-alphanumerics converted to `_` (for example `my-proxy` → `MY_PROXY_BASE_URL`) |\n\nOpenAI-compatible proxy note: the built-in `openai` provider keeps its bundled API transport (`openai-responses`). Setting `OPENAI_BASE_URL` changes the host but still calls `<baseUrl>/responses`. If your proxy only supports Chat Completions, configure a custom `models.yml` provider with `api: openai-completions` instead of using the built-in OpenAI provider override:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKey: OPENAI_API_KEY\n    api: openai-completions\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        api: openai-completions\n```\n\nFor OpenRouter traffic, GJC explicitly sends `User-Agent: Gajae-Code/<package version>` plus OpenRouter attribution headers. For the built-in OpenAI Responses transport and generic OpenAI-compatible Chat Completions transport, GJC passes model/provider headers through the OpenAI JavaScript SDK and does not set a GJC user-agent unless the provider-specific code adds one.\n\n### OpenAI-compatible proxy provider config\n\nFor OpenAI-compatible proxies that only implement Chat Completions, prefer a custom `models.yml` provider over `OPENAI_BASE_URL`:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        reasoning: false\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n```\n\n`models.yml` is strict: unsupported provider/model keys fail validation before the provider request is dispatched.\n\n### GJC workflow bridge commands\n\n`gjc ralplan`, `gjc deep-interview`, and `gjc state` are private runtime bridge commands. They require `GJC_RUNTIME_BINARY` (or legacy `GJC_LEGACY_RUNTIME_BINARY`) to point at the private runtime executable; public bundled workflow use remains through `/skill:ralplan` and `/skill:deep-interview` inside a GJC session.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_RUNTIME_BINARY` | Private runtime bridge binary for `gjc ralplan`, `gjc deep-interview`, and `gjc state` |\n| `GJC_LEGACY_RUNTIME_BINARY` | Legacy fallback bridge binary name |\n\n### Team tmux backend, dry-run, and state paths\n\n`gjc team ...` starts tmux worker panes from the current tmux-backed leader session. Start that leader with `gjc --tmux` first; `gjc team` intentionally does not create or attach the leader session itself.\n\n`gjc team ... --dry-run --json` creates the same machine-readable state tree as a team launch without starting tmux panes. By default that state is written under `<cwd>/.gjc/state/team/<team>/`; treat it as ephemeral smoke-test/review state. Do not commit generated `.gjc/state/team` contents. Remove the generated team directory after a dry-run when the harness no longer needs it.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_TEAM_STATE_ROOT` | Overrides the team state root (default `<cwd>/.gjc/state/team`) |\n| `GJC_TEAM_TMUX_COMMAND` | tmux binary/command override for team launch |\n| `GJC_TEAM_WORKER_COMMAND` | Worker GJC command override |\n| `GJC_TEAM_WORKER_CLI` | Team worker CLI selector; accepted values are `auto` or `gjc` |\n| `GJC_TEAM_WORKER_CLI_MAP` | Comma-separated worker CLI selector map; entries must be `auto` or `gjc` |\n\n### Google Vertex AI\n\n| Variable                         | Required?                      | Notes                                                                                                                     |\n| -------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |\n| `GOOGLE_CLOUD_PROJECT`           | Yes (unless passed in options) | Fallback: `GCLOUD_PROJECT`                                                                                                |\n| `GCLOUD_PROJECT`                 | Fallback                       | Used as alternate project ID source                                                                                       |\n| `GOOGLE_CLOUD_PROJECT_ID`        | OAuth login helper only        | Used by Gemini CLI OAuth project discovery                                                                                |\n| `GOOGLE_CLOUD_LOCATION`          | Yes (unless passed in options) | No default in provider                                                                                                    |\n| `GOOGLE_CLOUD_API_KEY`           | Conditional                    | Direct Vertex API-key auth; otherwise ADC fallback can authenticate when project and location are set                     |\n| `GOOGLE_APPLICATION_CREDENTIALS` | Conditional                    | If set, file must exist; otherwise ADC fallback path is checked (`~/.config/gcloud/application_default_credentials.json`) |\n\n### Kimi\n\n| Variable               | Default / behavior                                       |\n| ---------------------- | -------------------------------------------------------- |\n| `KIMI_CODE_OAUTH_HOST` | Primary OAuth host override                              |\n| `KIMI_OAUTH_HOST`      | Fallback OAuth host override                             |\n| `KIMI_CODE_BASE_URL`   | Overrides Kimi usage endpoint base URL (`usage/kimi.ts`) |\n\nOAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth.kimi.com`.\n\n### Gemini CLI compatibility\n\n| Variable                   | Default / behavior                                              |\n| -------------------------- | --------------------------------------------------------------- |\n| `GJC_AI_GEMINI_CLI_VERSION` | Overrides Gemini CLI user-agent version tag (`0.35.3` if unset) |\n\n### OpenAI code provider responses (feature/debug controls)\n\n| Variable                             | Behavior                                             |\n| ------------------------------------ | ---------------------------------------------------- |\n| `GJC_OPENAI_CODE_DEBUG`                     | `1`/`true` enables OpenAI code provider debug logging      |\n| `GJC_OPENAI_CODE_WEBSOCKET`                 | `1`/`true` enables websocket transport preference    |\n| `GJC_OPENAI_CODE_WEBSOCKET_V2`              | `1`/`true` enables websocket v2 path                 |\n| `GJC_OPENAI_CODE_WEBSOCKET_IDLE_TIMEOUT_MS` | Positive integer override (default 300000)           |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_BUDGET`    | Non-negative integer override (default 5)            |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_DELAY_MS`  | Positive integer base backoff override (default 500) |\n| `GJC_OPENAI_STREAM_IDLE_TIMEOUT_MS`   | Positive integer OpenAI stream idle timeout override |\n\n### Cursor provider debug\n\n| Variable           | Behavior                                                                 |\n| ------------------ | ------------------------------------------------------------------------ |\n| `DEBUG_CURSOR`     | Enables provider debug logs; `2`/`verbose` for detailed payload snippets |\n| `DEBUG_CURSOR_LOG` | Optional file path for JSONL debug log output                            |\n\n### Prompt cache compatibility switch\n\n| Variable             | Behavior                                                                                                          |\n| -------------------- | ----------------------------------------------------------------------------------------------------------------- |\n| `GJC_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution) |\n\n---\n\n## 3) Web search subsystem\n\n### Search provider credentials\n\n| Variable                                            | Used by                                                       |\n| --------------------------------------------------- | ------------------------------------------------------------- |\n| `EXA_API_KEY`                                       | Exa search provider                         |\n| `BRAVE_API_KEY`                                     | Brave search provider                                         |\n| `PERPLEXITY_API_KEY`                                | Perplexity search provider API-key mode                       |\n| `PERPLEXITY_COOKIES`                                | Perplexity cookie-auth search mode                            |\n| `TAVILY_API_KEY`                                    | Tavily search provider                                        |\n| `ZAI_API_KEY`                                       | z.ai search provider (also checks stored OAuth in `agent.db`) |\n| `OPENAI_API_KEY` / OpenAI code OAuth in DB                | OpenAI code search provider availability/auth                       |\n| `GJC_OPENAI_CODE_WEB_SEARCH_MODEL`                         | OpenAI code search provider model override                          |\n| `MOONSHOT_SEARCH_API_KEY` / `KIMI_SEARCH_API_KEY`   | Kimi/Moonshot search provider env auth                        |\n| `MOONSHOT_SEARCH_BASE_URL` / `KIMI_SEARCH_BASE_URL` | Kimi/Moonshot search endpoint override                        |\n| `KAGI_API_KEY`                                      | Kagi search provider                                          |\n| `JINA_API_KEY`                                      | Jina search provider                                          |\n| `PARALLEL_API_KEY`                                  | Parallel search provider                                      |\n| `SEARXNG_ENDPOINT`, `SEARXNG_TOKEN`                 | SearXNG endpoint and optional bearer token                    |\n| `SEARXNG_BASIC_USERNAME`, `SEARXNG_BASIC_PASSWORD`  | SearXNG HTTP Basic Auth credentials                           |\n\nSearXNG also reads the equivalent `searxng.endpoint`, `searxng.token`, `searxng.basicUsername`, and `searxng.basicPassword` settings from `~/.gjc/agent/config.yml`; environment variables are fallbacks.\n\n### Anthropic web search auth chain\n\nAnthropic web search uses `findAnthropicAuth()` from `packages/ai/src/utils/anthropic-auth.ts` in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY` (+ optional `ANTHROPIC_SEARCH_BASE_URL`)\n2. `ANTHROPIC_FOUNDRY_API_KEY` when `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled\n3. Anthropic OAuth credentials from `agent.db` (must not expire within 5-minute buffer)\n4. Anthropic API-key credentials from `agent.db`\n5. Generic Anthropic env fallback: provider key (`ANTHROPIC_FOUNDRY_API_KEY` in Foundry mode, otherwise `ANTHROPIC_OAUTH_TOKEN`/`ANTHROPIC_API_KEY`) + optional `ANTHROPIC_BASE_URL` (`FOUNDRY_BASE_URL` when Foundry mode is enabled)\n\nRelated vars:\n\n| Variable                    | Default / behavior                                   |\n| --------------------------- | ---------------------------------------------------- |\n| `ANTHROPIC_SEARCH_API_KEY`  | Highest-priority explicit search key                 |\n| `ANTHROPIC_SEARCH_BASE_URL` | Defaults to `https://api.anthropic.com` when omitted |\n| `ANTHROPIC_SEARCH_MODEL`    | Defaults to `anthropic-model-haiku-4-5`                       |\n| `ANTHROPIC_BASE_URL`        | Generic fallback base URL for tier-4 auth path       |\n\n### Perplexity OAuth flow behavior flag\n\n| Variable            | Behavior                                                                        |\n| ------------------- | ------------------------------------------------------------------------------- |\n| `GJC_AUTH_NO_BORROW` | If set, disables macOS native-app token borrowing path in Perplexity login flow |\n\n---\n\n## 4) Python tooling and kernel runtime\n\n| Variable                  | Default / behavior                                                                                                  |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------- |\n| `GJC_PY`                   | Eval backend override: `0`/`bash`=JavaScript only, `1`/`py`=Python only, `mix`/`both`=both; invalid values ignored |\n| `GJC_PYTHON_SKIP_CHECK`    | If `1`, skips Python interpreter availability checks (subprocess runner still starts on demand)                     |\n| `GJC_PYTHON_INTEGRATION`   | If `1`, opts gated integration tests in (e.g. `python-runner.integration.test.ts`) into running against real Python |\n| `GJC_PYTHON_IPC_TRACE`     | If `1`, logs NDJSON frames exchanged with the Python runner subprocess                                              |\n| `VIRTUAL_ENV`             | Highest-priority venv path for Python runtime resolution                                                            |\n\nExtra conditional behavior:\n\n- If `BUN_ENV=test` or `NODE_ENV=test`, Python availability checks are treated as OK and warming is skipped.\n- Python env filtering denies common API keys and allows safe base vars + `LC_`, `XDG_`, `GJC_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable                     | Default / behavior                                                                                 |\n| ---------------------------- | -------------------------------------------------------------------------------------------------- |\n| `GJC_SMOL_MODEL`              | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence)                           |\n| `GJC_SLOW_MODEL`              | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence)                           |\n| `GJC_PLAN_MODEL`              | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence)                           |\n| `GJC_NO_TITLE`                | If set (any non-empty value), disables auto session title generation on first user message         |\n| `NULL_PROMPT`                | If `true`, system prompt builder returns empty string                                              |\n| `GJC_BLOCKED_AGENT`           | Blocks a specific subagent type in task tool                                                       |\n| `GJC_SUBPROCESS_CMD`          | Overrides subagent spawn command (`gjc` / `gjc.cmd` resolution bypass)                             |\n| `GJC_TASK_MAX_OUTPUT_BYTES`   | Max captured output bytes per subagent (default `500000`)                                          |\n| `GJC_TASK_MAX_OUTPUT_LINES`   | Max captured output lines per subagent (default `5000`)                                            |\n| `GJC_TIMING`                  | If set (any non-empty value), prints a hierarchical timing-span tree to **stderr** via `logger.printTimings()`. In interactive mode the tree prints once the agent is ready (before the TUI starts); in print mode it prints after the whole prompt batch completes. Print-mode prompts are wrapped in `print:prompt:initial` / `print:prompt:next` spans so each user message shows up as its own row. `GJC_TIMING=x` exits the process with code 0 right after printing in interactive mode (use to measure cold startup only). `GJC_TIMING=full` lists every module-load entry instead of just the top N. |\n| `GJC_PACKAGE_DIR`             | Overrides package asset base dir resolution (docs/examples/changelog path lookup)                  |\n| `GJC_DISABLE_LSPMUX`          | If `1`, disables lspmux detection/integration and forces direct LSP server spawning                |\n| `GJC_RPC_EMIT_TITLE`          | Boolean-like flag enabling title events in RPC mode                                                |\n| `SMITHERY_URL`               | Smithery web URL override (default `https://smithery.ai`)                                          |\n| `SMITHERY_API_URL`           | Smithery API base URL override (default `https://api.smithery.ai`)                                 |\n| `PUPPETEER_EXECUTABLE_PATH`  | Browser tool Chromium executable override                                                          |\n| `LM_STUDIO_BASE_URL`         | Default implicit LM Studio discovery base URL override (`http://127.0.0.1:1234/v1` if unset)       |\n| `OLLAMA_BASE_URL`            | Default implicit Ollama discovery base URL override (`http://127.0.0.1:11434` if unset)            |\n| `LLAMA_CPP_BASE_URL`         | Default implicit Llama.cpp discovery base URL override (`http://127.0.0.1:8080` if unset)          |\n| `GJC_EDIT_VARIANT`            | Forces edit tool variant when valid (`patch`, `replace`, `hashline`, `atom`, `vim`, `apply_patch`) |\n| `GJC_FORCE_IMAGE_PROTOCOL`    | Forces supported image protocol (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) where used            |\n| `GJC_ALLOW_SIXEL_PASSTHROUGH` | Allows SIXEL passthrough when `GJC_FORCE_IMAGE_PROTOCOL=sixel`                                      |\n| `GJC_NO_PTY`                  | If `1`, disables interactive PTY path for bash tool                                                |\n\n`GJC_NO_PTY` is also set internally when CLI `--no-pty` is used.\n\n---\n\n## 6) Storage and config root paths\n\nThese are consumed via `@gajae-code/utils/dirs` and affect where coding-agent stores data.\n\n| Variable              | Default / behavior                                                            |\n| --------------------- | ----------------------------------------------------------------------------- |\n| `GJC_CONFIG_DIR`       | Config root dirname under home (default `.gjc`)                               |\n| `GJC_CODING_AGENT_DIR` | Full override for agent directory (default `~/<GJC_CONFIG_DIR or .gjc>/agent`) |\n| `PWD`                 | Used when matching canonical current working directory in path helpers        |\n\n---\n\n## 7) Shell/tool execution environment\n\n(From `packages/utils/src/procmgr.ts` and coding-agent bash tool integration.)\n\n| Variable                   | Behavior                                                                       |\n| -------------------------- | ------------------------------------------------------------------------------ |\n| `GJC_BASH_NO_CI`            | Suppresses automatic `CI=true` injection into spawned shell env                |\n| `ANTHROPIC_MODEL_BASH_NO_CI`        | Legacy alias fallback for `GJC_BASH_NO_CI`                                      |\n| `GJC_BASH_NO_LOGIN`         | Disables login-shell mode; shell args become `['-c']` instead of `['-l','-c']` |\n| `ANTHROPIC_MODEL_BASH_NO_LOGIN`     | Legacy alias fallback for `GJC_BASH_NO_LOGIN`                                   |\n| `GJC_SHELL_PREFIX`          | Optional command prefix wrapper                                                |\n| `ANTHROPIC_MODEL_CODE_SHELL_PREFIX` | Legacy alias fallback for `GJC_SHELL_PREFIX`                                    |\n| `VISUAL`                   | Preferred external editor command                                              |\n| `EDITOR`                   | Fallback external editor command                                               |\n\nCurrent implementation: `GJC_BASH_NO_LOGIN`/`ANTHROPIC_MODEL_BASH_NO_LOGIN` are active; when either is set, `getShellArgs()` returns `['-c']`.\n\n---\n\n## 8) UI/theme/session detection (auto-detected env)\n\nThese are read as runtime signals; they are usually set by the terminal/OS rather than manually configured.\n\n| Variable                                                                                                           | Used for                                                  |\n| ------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------- |\n| `COLORTERM`, `TERM`, `WT_SESSION`                                                                                  | Color capability detection (theme color mode)             |\n| `COLORFGBG`                                                                                                        | Terminal background light/dark auto-detection             |\n| `TERM_PROGRAM`, `TERM_PROGRAM_VERSION`, `TERMINAL_EMULATOR`                                                        | Terminal identity in system prompt/context                |\n| `KDE_FULL_SESSION`, `XDG_CURRENT_DESKTOP`, `DESKTOP_SESSION`, `XDG_SESSION_DESKTOP`, `GDMSESSION`, `WINDOWMANAGER` | Desktop/window-manager detection in system prompt/context |\n| `KITTY_WINDOW_ID`, `TMUX_PANE`, `TERM_SESSION_ID`, `WT_SESSION`                                                    | Stable per-terminal session breadcrumb IDs                |\n| `SHELL`, `ComSpec`, `TERM_PROGRAM`, `TERM`                                                                         | System info diagnostics                                   |\n| `APPDATA`, `XDG_CONFIG_HOME`                                                                                       | lspmux config path resolution                             |\n| `HOME`                                                                                                             | Path shortening in command UI                         |\n\n---\n\n## 9) TUI runtime flags (shared package, affects coding-agent UX)\n\n| Variable                  | Behavior                                                                              |\n| ------------------------- | ------------------------------------------------------------------------------------- |\n| `GJC_NOTIFICATIONS`        | `off` / `0` / `false` suppress desktop notifications                                  |\n| `GJC_TUI_WRITE_LOG`        | If set, logs TUI writes to file                                                       |\n| `GJC_HARDWARE_CURSOR`      | If `1`, enables hardware cursor mode                                                  |\n| `GJC_CLEAR_ON_SHRINK`      | If `1`, clears empty rows when content shrinks                                        |\n| `GJC_DEBUG_REDRAW`         | If `1`, enables redraw debug logging                                                  |\n| `GJC_TUI_DEBUG`            | If `1`, enables deep TUI debug dump path                                              |\n| `GJC_FORCE_IMAGE_PROTOCOL` | Forces terminal image protocol detection (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) |\n\n---\n\n## 10) Commit generation controls\n\n| Variable                  | Behavior                                                            |\n| ------------------------- | ------------------------------------------------------------------- |\n| `GJC_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `GJC_COMMIT_NO_FALLBACK`   | If `true`, disables fallback when agent returns no proposal         |\n| `GJC_COMMIT_MAP_REDUCE`    | If `false`, disables map-reduce commit analysis path                |\n| `DEBUG`                   | If set, commit agent error stack traces are printed                 |\n\n---\n\n## Security-sensitive variables\n\nTreat these as secrets; do not log or commit them:\n\n- Provider/API keys and OAuth/bearer credentials (all `*_API_KEY`, `*_TOKEN`, OAuth access/refresh tokens)\n- Cloud credentials (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS` path may expose service-account material)\n- Search/provider auth vars (`EXA_API_KEY`, `BRAVE_API_KEY`, `PERPLEXITY_API_KEY`, Anthropic search keys)\n- Foundry mTLS material (`ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`, `NODE_EXTRA_CA_CERTS` when it points to private CA bundles)\n\nPython runtime also explicitly strips many common key vars before spawning kernel subprocesses (`packages/coding-agent/src/eval/py/runtime.ts`).\n",
+	"environment-variables.md": "# Environment Variables (Current Runtime Reference)\n\nThis reference is derived from current code paths in:\n\n- `packages/coding-agent/src/**`\n- `packages/ai/src/**` (provider/auth resolution used by coding-agent)\n- `packages/utils/src/**` and `packages/tui/src/**` where those vars directly affect coding-agent runtime\n\nIt documents only active behavior.\n\n## Resolution model and precedence\n\nMost runtime lookups use `$env` from `@gajae-code/utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Agent `.env` (`~/.gjc/agent/.env`, respecting `GJC_CONFIG_DIR` / `GJC_CODING_AGENT_DIR`) for keys not already set\n4. Config-root `.env` (`~/.gjc/.env`, respecting `GJC_CONFIG_DIR`) for keys not already set\n5. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule inside each `.env` file: `GJC_*` keys are mirrored to `GJC_*` keys in that parsed file.\n\n---\n\n## 1) Model/provider authentication\n\nThese are consumed via `getEnvApiKey()` (`packages/ai/src/stream.ts`) unless noted otherwise.\n\n### Core provider credentials\n\n| Variable                        | Used for                                         | Required when                                                  | Notes / precedence                                                                                  |\n| ------------------------------- | ------------------------------------------------ | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- |\n| `ANTHROPIC_OAUTH_TOKEN`         | Anthropic API auth                               | Using Anthropic with OAuth token auth                          | Takes precedence over `ANTHROPIC_API_KEY` for provider auth resolution                              |\n| `ANTHROPIC_API_KEY`             | Anthropic API auth                               | Using Anthropic without OAuth token                            | Fallback after `ANTHROPIC_OAUTH_TOKEN`                                                              |\n| `ANTHROPIC_FOUNDRY_API_KEY`     | Anthropic via Azure Foundry / enterprise gateway | `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` enabled                              | Takes precedence over `ANTHROPIC_OAUTH_TOKEN` and `ANTHROPIC_API_KEY` when Foundry mode is enabled  |\n| `OPENAI_API_KEY`                | OpenAI auth                                      | Using OpenAI-family providers without explicit apiKey argument | Used by OpenAI Completions/Responses providers                                                      |\n| `GEMINI_API_KEY`                | Google Gemini auth                               | Using `google` provider models                                 | Primary key for Gemini provider mapping                                                             |\n| `GOOGLE_API_KEY`                | Gemini image tool auth fallback                  | Using `gemini_image` tool without `GEMINI_API_KEY`             | Used by coding-agent image tool fallback path                                                       |\n| `GROQ_API_KEY`                  | Groq auth                                        | Using Groq models                                              |                                                                                                     |\n| `CEREBRAS_API_KEY`              | Cerebras auth                                    | Using Cerebras models                                          |                                                                                                     |\n| `FIREWORKS_API_KEY`             | Fireworks auth                                   | Using Fireworks models                                         |                                                                                                     |\n| `TOGETHER_API_KEY`              | Together auth                                    | Using `together` provider                                      |                                                                                                     |\n| `HUGGINGFACE_HUB_TOKEN`         | Hugging Face auth                                | Using `huggingface` provider                                   | Primary Hugging Face token env var                                                                  |\n| `HF_TOKEN`                      | Hugging Face auth                                | Using `huggingface` provider                                   | Fallback when `HUGGINGFACE_HUB_TOKEN` is unset                                                      |\n| `SYNTHETIC_API_KEY`             | Synthetic auth                                   | Using Synthetic models                                         |                                                                                                     |\n| `NVIDIA_API_KEY`                | NVIDIA auth                                      | Using `nvidia` provider                                        |                                                                                                     |\n| `NANO_GPT_API_KEY`              | NanoGPT auth                                     | Using `nanogpt` provider                                       |                                                                                                     |\n| `VENICE_API_KEY`                | Venice auth                                      | Using `venice` provider                                        |                                                                                                     |\n| `LITELLM_API_KEY`               | LiteLLM auth                                     | Using `litellm` provider                                       | OpenAI-compatible LiteLLM proxy key                                                                 |\n| `LM_STUDIO_API_KEY`             | LM Studio auth (optional)                        | Using `lm-studio` provider with authenticated hosts            | Local LM Studio usually runs without auth; any non-empty token works when a key is required         |\n| `OLLAMA_API_KEY`                | Ollama auth (optional)                           | Using `ollama` provider with authenticated hosts               | Local Ollama usually runs without auth; any non-empty token works when a key is required            |\n| `LLAMA_CPP_API_KEY`             | llama.cpp auth (optional)                        | Using `llama.cpp` provider with authenticated hosts            | Local llama.cpp usually runs without auth; any non-empty token works when a key is configured       |\n| `XIAOMI_API_KEY`                | Xiaomi MiMo auth                                 | Using `xiaomi` provider                                        |                                                                                                     |\n| `MOONSHOT_API_KEY`              | Moonshot auth                                    | Using `moonshot` provider                                      |                                                                                                     |\n| `XAI_API_KEY`                   | xAI auth                                         | Using xAI models                                               |                                                                                                     |\n| `OPENROUTER_API_KEY`            | OpenRouter auth                                  | Using OpenRouter models                                        | Also used by image tool when preferred/auto provider is OpenRouter                                  |\n| `MISTRAL_API_KEY`               | Mistral auth                                     | Using Mistral models                                           |                                                                                                     |\n| `ZAI_API_KEY`                   | z.ai auth                                        | Using z.ai models                                              | Also used by z.ai web search provider                                                               |\n| `MINIMAX_API_KEY`               | MiniMax auth                                     | Using `minimax` provider                                       |                                                                                                     |\n| `AZURE_OPENAI_API_KEY`          | Azure OpenAI auth                               | Using `azure-openai` / `azure-openai-responses` models         | Pair with `AZURE_OPENAI_BASE_URL` or `AZURE_OPENAI_RESOURCE_NAME`                                   |\n| `MINIMAX_CODE_API_KEY`          | MiniMax Code auth                                | Using `minimax-code` provider                                  |                                                                                                     |\n| `MINIMAX_CODE_CN_API_KEY`       | MiniMax Code CN auth                             | Using `minimax-code-cn` provider                               |                                                                                                     |\n| `OPENCODE_API_KEY`              | OpenCode auth                                    | Using `opencode-go` / `opencode-zen` models                    |                                                                                                     |\n| `QIANFAN_API_KEY`               | Qianfan auth                                     | Using `qianfan` provider                                       |                                                                                                     |\n| `QWEN_OAUTH_TOKEN`              | Qwen Portal auth                                 | Using `qwen-portal` with OAuth token                           | Takes precedence over `QWEN_PORTAL_API_KEY`                                                         |\n| `QWEN_PORTAL_API_KEY`           | Qwen Portal auth                                 | Using `qwen-portal` with API key                               | Fallback after `QWEN_OAUTH_TOKEN`                                                                   |\n| `ZENMUX_API_KEY`                | ZenMux auth                                      | Using `zenmux` provider                                        | Used for ZenMux OpenAI and Anthropic-compatible routes                                              |\n| `VLLM_API_KEY`                  | vLLM auth/discovery opt-in                       | Using `vllm` provider (local OpenAI-compatible servers)        | Any non-empty value works for no-auth local servers                                                 |\n| `CURSOR_ACCESS_TOKEN`           | Cursor provider auth                             | Using Cursor provider                                          |                                                                                                     |\n| `AI_GATEWAY_API_KEY`            | Vercel AI Gateway auth                           | Using `vercel-ai-gateway` provider                             |                                                                                                     |\n| `CLOUDFLARE_AI_GATEWAY_API_KEY` | Cloudflare AI Gateway auth                       | Using `cloudflare-ai-gateway` provider                         | Base URL must be configured as `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic` |\n| `ALIBABA_CODING_PLAN_API_KEY`   | Alibaba Coding Plan auth                         | Using `alibaba-coding-plan` provider                           |                                                                                                     |\n| `DEEPSEEK_API_KEY`              | DeepSeek auth                                    | Using DeepSeek models                                          |                                                                                                     |\n| `KILO_API_KEY`                  | Kilo auth                                        | Using Kilo models                                              |                                                                                                     |\n| `OLLAMA_CLOUD_API_KEY`          | Ollama Cloud auth                                | Using `ollama-cloud` provider                                  |                                                                                                     |\n| `GITLAB_TOKEN`                  | GitLab Duo auth                                  | Using `gitlab-duo` provider                                    |                                                                                                     |\n\n### GitHub/Copilot token chains\n\n| Variable               | Used for                                         | Chain                                                |\n| ---------------------- | ------------------------------------------------ | ---------------------------------------------------- |\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth                     | `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` |\n| `GH_TOKEN`             | Copilot fallback; GitHub API auth in web scraper | In web scraper: `GITHUB_TOKEN` → `GH_TOKEN`          |\n| `GITHUB_TOKEN`         | Copilot fallback; GitHub API auth in web scraper | In web scraper: checked before `GH_TOKEN`            |\n\n### Auth broker / auth gateway (remote credential vault)\n\nWhen the broker is enabled, the local SQLite credential store is bypassed and all OAuth refresh / access tokens live on the broker host. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full protocol, CLI surface, and 5-min/15-s usage cache layering.\n\n| Variable                | Used for                                                                                          | Required when                                                                                                          | Notes / precedence                                                                                                                                                                                  |\n| ----------------------- | ------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `GJC_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`); selects broker mode      | Resolving credentials through a broker; also required by `gjc auth-gateway serve` (the gateway is itself a broker client) | Wins over `auth.broker.url` in `config.yml`. When set with no resolvable token, `resolveAuthBrokerConfig()` hard-errors instead of falling back to local SQLite.                                    |\n| `GJC_AUTH_BROKER_TOKEN` | Bearer token sent on every broker endpoint except `/v1/healthz`                                   | `GJC_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`     | Resolution: this env → `auth.broker.token` (`$ENV_NAME` indirection supported) → `<config-dir>/auth-broker.token` (mode `0600`). `<config-dir>` is `~/.gjc/` (respecting `GJC_CONFIG_DIR`).         |\n\nThe gateway has no dedicated env vars — it inherits `GJC_AUTH_BROKER_*`. Its own inbound bearer token lives at `<config-dir>/auth-gateway.token` and is managed via `gjc auth-gateway token`.\n\n---\n\n## 2) Provider-specific runtime configuration\n\n### Anthropic Foundry Gateway (Azure / enterprise proxy)\n\nWhen `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled, Anthropic requests switch to Foundry mode:\n\n- Base URL resolves from `FOUNDRY_BASE_URL` (fallback remains model/default base URL if unset).\n- API key resolution for provider `anthropic` becomes:\n  `ANTHROPIC_FOUNDRY_API_KEY` → `ANTHROPIC_OAUTH_TOKEN` → `ANTHROPIC_API_KEY`.\n- `ANTHROPIC_CUSTOM_HEADERS` is parsed as comma/newline-separated `key: value` pairs and merged into request headers.\n- TLS client/server material can be injected from env values:\n  `NODE_EXTRA_CA_CERTS`, `ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`.\n  Each accepts either:\n  - a filesystem path to PEM content, or\n  - inline PEM (including escaped `\\n` sequences).\n\n| Variable                    | Value type                                     | Behavior                                                                      |\n| --------------------------- | ---------------------------------------------- | ----------------------------------------------------------------------------- |\n| `ANTHROPIC_MODEL_CODE_USE_FOUNDRY`   | Boolean-like string (`1`, `true`, `yes`, `on`) | Enables Foundry mode for Anthropic provider                                   |\n| `FOUNDRY_BASE_URL`          | URL string                                     | Anthropic endpoint base URL in Foundry mode                                   |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Token string                                   | Used for `Authorization: Bearer <token>`                                      |\n| `ANTHROPIC_CUSTOM_HEADERS`  | Header list string                             | Extra headers; format `header-a: value, header-b: value` or newline-separated |\n| `NODE_EXTRA_CA_CERTS`       | PEM path or inline PEM                         | Extra CA chain for server certificate validation                              |\n| `ANTHROPIC_MODEL_CODE_CLIENT_CERT`   | PEM path or inline PEM                         | mTLS client certificate                                                       |\n| `ANTHROPIC_MODEL_CODE_CLIENT_KEY`    | PEM path or inline PEM                         | mTLS client private key (must be paired with cert)                            |\n\n### Amazon Bedrock\n\n| Variable                                                                        | Default / behavior                                                                            |\n| ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `AWS_REGION`                                                                    | Primary region source                                                                         |\n| `AWS_DEFAULT_REGION`                                                            | Fallback if `AWS_REGION` unset                                                                |\n| `AWS_PROFILE`                                                                   | Enables named profile auth path                                                               |\n| `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`                                   | Enables IAM key auth path                                                                     |\n| `AWS_BEARER_TOKEN_BEDROCK`                                                      | Enables bearer token auth path                                                                |\n| `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI` / `AWS_CONTAINER_CREDENTIALS_FULL_URI` | Enables ECS task credential path                                                              |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN`                                  | Enables web identity auth path                                                                |\n| `AWS_BEDROCK_SKIP_AUTH`                                                         | If `1`, injects dummy credentials (proxy/non-auth scenarios)                                  |\n| `AWS_BEDROCK_FORCE_HTTP1`                                                       | If `1`, forces Node HTTP/1 request handler                                                    |\n| `HTTPS_PROXY` / `HTTP_PROXY` / `ALL_PROXY`                                      | Routes Bedrock runtime and AWS SSO credential calls through the configured proxy using HTTP/1 |\n| `NO_PROXY`                                                                      | Excludes matching hosts from proxy routing when a proxy variable is configured                |\n\nRegion fallback in provider code: `options.region` → `AWS_REGION` → `AWS_DEFAULT_REGION` → `us-east-1`.\n\nCredential fallback order is static env (`AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY` plus optional `AWS_SESSION_TOKEN`), named profile / SSO / `credential_process`, then EC2 IMDSv2. `models.yml` Bedrock entries use `api: bedrock-converse-stream` and do not require `apiKey` or `apiKeyEnv` because the provider signs requests from this AWS chain.\n\n### Azure OpenAI Responses\n\n| Variable                           | Default / behavior                                                          |\n| ---------------------------------- | --------------------------------------------------------------------------- |\n| `AZURE_OPENAI_API_KEY`             | Required unless API key passed as option                                    |\n| `AZURE_OPENAI_API_VERSION`         | Default `v1`                                                                |\n| `AZURE_OPENAI_BASE_URL`            | Direct base URL override                                                    |\n| `AZURE_OPENAI_RESOURCE_NAME`       | Used to construct base URL: `https://<resource>.openai.azure.com/openai/v1` |\n| `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` | Optional mapping string: `modelId=deploymentName,model2=deployment2`        |\n\nBase URL resolution: option `azureBaseUrl` → env `AZURE_OPENAI_BASE_URL` → option/env resource name → `model.baseUrl`.\n\n### Model provider base URL overrides\n\nBuilt-in model provider base URLs resolve with this precedence:\n\n1. `models.yml` / model config provider `baseUrl`\n2. provider-specific base URL environment variable\n3. bundled provider default\n\nSupported aliases:\n\n| Provider | Variables |\n| --- | --- |\n| OpenAI | `OPENAI_BASE_URL` |\n| Anthropic | `ANTHROPIC_BASE_URL` |\n| Google Gemini | `GOOGLE_BASE_URL`, `GEMINI_BASE_URL` |\n| Google Antigravity | `GOOGLE_ANTIGRAVITY_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Gemini CLI | `GOOGLE_GEMINI_CLI_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Vertex | `GOOGLE_VERTEX_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Any provider id | derived `<PROVIDER_ID>_BASE_URL`, uppercased with non-alphanumerics converted to `_` (for example `my-proxy` → `MY_PROXY_BASE_URL`) |\n\nOpenAI-compatible proxy note: the built-in `openai` provider keeps its bundled API transport (`openai-responses`). Setting `OPENAI_BASE_URL` changes the host but still calls `<baseUrl>/responses`. If your proxy only supports Chat Completions, configure a custom `models.yml` provider with `api: openai-completions` instead of using the built-in OpenAI provider override:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKey: OPENAI_API_KEY\n    api: openai-completions\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        api: openai-completions\n```\n\nFor OpenRouter traffic, GJC explicitly sends `User-Agent: Gajae-Code/<package version>` plus OpenRouter attribution headers. For the built-in OpenAI Responses transport and generic OpenAI-compatible Chat Completions transport, GJC passes model/provider headers through the OpenAI JavaScript SDK and does not set a GJC user-agent unless the provider-specific code adds one.\n\n### OpenAI-compatible proxy provider config\n\nFor OpenAI-compatible proxies that only implement Chat Completions, prefer a custom `models.yml` provider over `OPENAI_BASE_URL`:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        reasoning: false\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n```\n\n`models.yml` is strict: unsupported provider/model keys fail validation before the provider request is dispatched.\n\n### GJC workflow bridge commands\n\n`gjc ralplan`, `gjc deep-interview`, and `gjc state` are private runtime bridge commands. They require `GJC_RUNTIME_BINARY` (or legacy `GJC_LEGACY_RUNTIME_BINARY`) to point at the private runtime executable; public bundled workflow use remains through `/skill:ralplan` and `/skill:deep-interview` inside a GJC session.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_RUNTIME_BINARY` | Private runtime bridge binary for `gjc ralplan`, `gjc deep-interview`, and `gjc state` |\n| `GJC_LEGACY_RUNTIME_BINARY` | Legacy fallback bridge binary name |\n\n### Team tmux backend, dry-run, and state paths\n\n`gjc team ...` starts tmux worker panes from the current tmux-backed leader session. Start that leader with `gjc --tmux` first; `gjc team` intentionally does not create or attach the leader session itself.\n\n`gjc team ... --dry-run --json` creates the same machine-readable state tree as a team launch without starting tmux panes. By default that state is written under `<cwd>/.gjc/state/team/<team>/`; treat it as ephemeral smoke-test/review state. Do not commit generated `.gjc/state/team` contents. Remove the generated team directory after a dry-run when the harness no longer needs it.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_TEAM_STATE_ROOT` | Overrides the team state root (default `<cwd>/.gjc/state/team`) |\n| `GJC_TEAM_TMUX_COMMAND` | tmux binary/command override for team launch |\n| `GJC_TEAM_WORKER_COMMAND` | Worker GJC command override |\n| `GJC_TEAM_WORKER_CLI` | Team worker CLI selector; accepted values are `auto` or `gjc` |\n| `GJC_TEAM_WORKER_CLI_MAP` | Comma-separated worker CLI selector map; entries must be `auto` or `gjc` |\n\n### Google Vertex AI\n\n| Variable                         | Required?                      | Notes                                                                                                                     |\n| -------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |\n| `GOOGLE_CLOUD_PROJECT`           | Yes (unless passed in options) | Fallback: `GCLOUD_PROJECT`                                                                                                |\n| `GCLOUD_PROJECT`                 | Fallback                       | Used as alternate project ID source                                                                                       |\n| `GOOGLE_CLOUD_PROJECT_ID`        | OAuth login helper only        | Used by Gemini CLI OAuth project discovery                                                                                |\n| `GOOGLE_CLOUD_LOCATION`          | Yes (unless passed in options) | No default in provider                                                                                                    |\n| `GOOGLE_CLOUD_API_KEY`           | Conditional                    | Direct Vertex API-key auth; otherwise ADC fallback can authenticate when project and location are set                     |\n| `GOOGLE_APPLICATION_CREDENTIALS` | Conditional                    | If set, file must exist; otherwise ADC fallback path is checked (`~/.config/gcloud/application_default_credentials.json`) |\n\n### Kimi\n\n| Variable               | Default / behavior                                       |\n| ---------------------- | -------------------------------------------------------- |\n| `KIMI_CODE_OAUTH_HOST` | Primary OAuth host override                              |\n| `KIMI_OAUTH_HOST`      | Fallback OAuth host override                             |\n| `KIMI_CODE_BASE_URL`   | Overrides Kimi usage endpoint base URL (`usage/kimi.ts`) |\n\nOAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth.kimi.com`.\n\n### Gemini CLI compatibility\n\n| Variable                   | Default / behavior                                              |\n| -------------------------- | --------------------------------------------------------------- |\n| `GJC_AI_GEMINI_CLI_VERSION` | Overrides Gemini CLI user-agent version tag (`0.35.3` if unset) |\n\n### OpenAI code provider responses (feature/debug controls)\n\n| Variable                             | Behavior                                             |\n| ------------------------------------ | ---------------------------------------------------- |\n| `GJC_OPENAI_CODE_DEBUG`                     | `1`/`true` enables OpenAI code provider debug logging      |\n| `GJC_OPENAI_CODE_WEBSOCKET`                 | `1`/`true` enables websocket transport preference    |\n| `GJC_OPENAI_CODE_WEBSOCKET_V2`              | `1`/`true` enables websocket v2 path                 |\n| `GJC_OPENAI_CODE_WEBSOCKET_IDLE_TIMEOUT_MS` | Positive integer override (default 300000)           |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_BUDGET`    | Non-negative integer override (default 5)            |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_DELAY_MS`  | Positive integer base backoff override (default 500) |\n| `GJC_OPENAI_STREAM_IDLE_TIMEOUT_MS`   | Positive integer OpenAI stream idle timeout override |\n\n### Cursor provider debug\n\n| Variable           | Behavior                                                                 |\n| ------------------ | ------------------------------------------------------------------------ |\n| `DEBUG_CURSOR`     | Enables provider debug logs; `2`/`verbose` for detailed payload snippets |\n| `DEBUG_CURSOR_LOG` | Optional file path for JSONL debug log output                            |\n\n### Prompt cache compatibility switch\n\n| Variable             | Behavior                                                                                                          |\n| -------------------- | ----------------------------------------------------------------------------------------------------------------- |\n| `GJC_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution) |\n\n---\n\n## 3) Web search subsystem\n\n### Search provider credentials\n\n| Variable                                            | Used by                                                       |\n| --------------------------------------------------- | ------------------------------------------------------------- |\n| `EXA_API_KEY`                                       | Exa search provider                         |\n| `BRAVE_API_KEY`                                     | Brave search provider                                         |\n| `PERPLEXITY_API_KEY`                                | Perplexity search provider API-key mode                       |\n| `PERPLEXITY_COOKIES`                                | Perplexity cookie-auth search mode                            |\n| `TAVILY_API_KEY`                                    | Tavily search provider                                        |\n| `ZAI_API_KEY`                                       | z.ai search provider (also checks stored OAuth in `agent.db`) |\n| `OPENAI_API_KEY` / OpenAI code OAuth in DB                | OpenAI code search provider availability/auth                       |\n| `GJC_OPENAI_CODE_WEB_SEARCH_MODEL`                         | OpenAI code search provider model override                          |\n| `MOONSHOT_SEARCH_API_KEY` / `KIMI_SEARCH_API_KEY`   | Kimi/Moonshot search provider env auth                        |\n| `MOONSHOT_SEARCH_BASE_URL` / `KIMI_SEARCH_BASE_URL` | Kimi/Moonshot search endpoint override                        |\n| `KAGI_API_KEY`                                      | Kagi search provider                                          |\n| `JINA_API_KEY`                                      | Jina search provider                                          |\n| `PARALLEL_API_KEY`                                  | Parallel search provider                                      |\n| `SEARXNG_ENDPOINT`, `SEARXNG_TOKEN`                 | SearXNG endpoint and optional bearer token                    |\n| `SEARXNG_BASIC_USERNAME`, `SEARXNG_BASIC_PASSWORD`  | SearXNG HTTP Basic Auth credentials                           |\n\nSearXNG also reads the equivalent `searxng.endpoint`, `searxng.token`, `searxng.basicUsername`, and `searxng.basicPassword` settings from `~/.gjc/agent/config.yml`; environment variables are fallbacks.\n\n### Anthropic web search auth chain\n\nAnthropic web search uses `findAnthropicAuth()` from `packages/ai/src/utils/anthropic-auth.ts` in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY` (+ optional `ANTHROPIC_SEARCH_BASE_URL`)\n2. `ANTHROPIC_FOUNDRY_API_KEY` when `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled\n3. Anthropic OAuth credentials from `agent.db` (must not expire within 5-minute buffer)\n4. Anthropic API-key credentials from `agent.db`\n5. Generic Anthropic env fallback: provider key (`ANTHROPIC_FOUNDRY_API_KEY` in Foundry mode, otherwise `ANTHROPIC_OAUTH_TOKEN`/`ANTHROPIC_API_KEY`) + optional `ANTHROPIC_BASE_URL` (`FOUNDRY_BASE_URL` when Foundry mode is enabled)\n\nRelated vars:\n\n| Variable                    | Default / behavior                                   |\n| --------------------------- | ---------------------------------------------------- |\n| `ANTHROPIC_SEARCH_API_KEY`  | Highest-priority explicit search key                 |\n| `ANTHROPIC_SEARCH_BASE_URL` | Defaults to `https://api.anthropic.com` when omitted |\n| `ANTHROPIC_SEARCH_MODEL`    | Defaults to `anthropic-model-haiku-4-5`                       |\n| `ANTHROPIC_BASE_URL`        | Generic fallback base URL for tier-4 auth path       |\n\n### Perplexity OAuth flow behavior flag\n\n| Variable            | Behavior                                                                        |\n| ------------------- | ------------------------------------------------------------------------------- |\n| `GJC_AUTH_NO_BORROW` | If set, disables macOS native-app token borrowing path in Perplexity login flow |\n\n---\n\n## 4) Python tooling and kernel runtime\n\n| Variable                  | Default / behavior                                                                                                  |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------- |\n| `GJC_PY`                   | Eval backend override: `0`/`bash`=JavaScript only, `1`/`py`=Python only, `mix`/`both`=both; invalid values ignored |\n| `GJC_PYTHON_SKIP_CHECK`    | If `1`, skips Python interpreter availability checks (subprocess runner still starts on demand)                     |\n| `GJC_PYTHON_INTEGRATION`   | If `1`, opts gated integration tests in (e.g. `python-runner.integration.test.ts`) into running against real Python |\n| `GJC_PYTHON_IPC_TRACE`     | If `1`, logs NDJSON frames exchanged with the Python runner subprocess                                              |\n| `VIRTUAL_ENV`             | Highest-priority venv path for Python runtime resolution                                                            |\n\nExtra conditional behavior:\n\n- If `BUN_ENV=test` or `NODE_ENV=test`, Python availability checks are treated as OK and warming is skipped.\n- Python env filtering denies common API keys and allows safe base vars + `LC_`, `XDG_`, `GJC_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable                     | Default / behavior                                                                                 |\n| ---------------------------- | -------------------------------------------------------------------------------------------------- |\n| `GJC_SMOL_MODEL`              | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence)                           |\n| `GJC_SLOW_MODEL`              | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence)                           |\n| `GJC_PLAN_MODEL`              | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence)                           |\n| `GJC_NO_TITLE`                | If set (any non-empty value), disables auto session title generation on first user message         |\n| `NULL_PROMPT`                | If `true`, system prompt builder returns empty string                                              |\n| `GJC_BLOCKED_AGENT`           | Blocks a specific subagent type in task tool                                                       |\n| `GJC_SUBPROCESS_CMD`          | Overrides subagent spawn command (`gjc` / `gjc.cmd` resolution bypass)                             |\n| `GJC_TASK_MAX_OUTPUT_BYTES`   | Max captured output bytes per subagent (default `500000`)                                          |\n| `GJC_TASK_MAX_OUTPUT_LINES`   | Max captured output lines per subagent (default `5000`)                                            |\n| `GJC_TIMING`                  | If set (any non-empty value), prints a hierarchical timing-span tree to **stderr** via `logger.printTimings()`. In interactive mode the tree prints once the agent is ready (before the TUI starts); in print mode it prints after the whole prompt batch completes. Print-mode prompts are wrapped in `print:prompt:initial` / `print:prompt:next` spans so each user message shows up as its own row. `GJC_TIMING=x` exits the process with code 0 right after printing in interactive mode (use to measure cold startup only). `GJC_TIMING=full` lists every module-load entry instead of just the top N. |\n| `GJC_PACKAGE_DIR`             | Overrides package asset base dir resolution (docs/examples/changelog path lookup)                  |\n| `GJC_DISABLE_LSPMUX`          | If `1`, disables lspmux detection/integration and forces direct LSP server spawning                |\n| `GJC_RPC_EMIT_TITLE`          | Boolean-like flag enabling title events in RPC mode                                                |\n| `SMITHERY_URL`               | Smithery web URL override (default `https://smithery.ai`)                                          |\n| `SMITHERY_API_URL`           | Smithery API base URL override (default `https://api.smithery.ai`)                                 |\n| `PUPPETEER_EXECUTABLE_PATH`  | Browser tool Chromium executable override                                                          |\n| `LM_STUDIO_BASE_URL`         | Default implicit LM Studio discovery base URL override (`http://127.0.0.1:1234/v1` if unset)       |\n| `OLLAMA_BASE_URL`            | Default implicit Ollama discovery base URL override (`http://127.0.0.1:11434` if unset)            |\n| `LLAMA_CPP_BASE_URL`         | Default implicit Llama.cpp discovery base URL override (`http://127.0.0.1:8080` if unset)          |\n| `GJC_EDIT_VARIANT`            | Forces edit tool variant when valid (`patch`, `replace`, `hashline`, `atom`, `vim`, `apply_patch`) |\n| `GJC_FORCE_IMAGE_PROTOCOL`    | Forces supported image protocol (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) where used            |\n| `GJC_ALLOW_SIXEL_PASSTHROUGH` | Allows SIXEL passthrough when `GJC_FORCE_IMAGE_PROTOCOL=sixel`                                      |\n| `GJC_NO_PTY`                  | If `1`, disables interactive PTY path for bash tool                                                |\n\n`GJC_NO_PTY` is also set internally when CLI `--no-pty` is used.\n\n---\n\n## 6) Storage and config root paths\n\nThese are consumed via `@gajae-code/utils/dirs` and affect where coding-agent stores data.\n\n| Variable              | Default / behavior                                                            |\n| --------------------- | ----------------------------------------------------------------------------- |\n| `GJC_CONFIG_DIR`       | Config root dirname under home (default `.gjc`)                               |\n| `GJC_CODING_AGENT_DIR` | Full override for agent directory (default `~/<GJC_CONFIG_DIR or .gjc>/agent`) |\n| `PWD`                 | Used when matching canonical current working directory in path helpers        |\n\n---\n\n## 7) Shell/tool execution environment\n\n(From `packages/utils/src/procmgr.ts` and coding-agent bash tool integration.)\n\n| Variable                   | Behavior                                                                       |\n| -------------------------- | ------------------------------------------------------------------------------ |\n| `GJC_BASH_NO_CI`            | Suppresses automatic `CI=true` injection into spawned shell env                |\n| `ANTHROPIC_MODEL_BASH_NO_CI`        | Legacy alias fallback for `GJC_BASH_NO_CI`                                      |\n| `GJC_BASH_NO_LOGIN`         | Disables login-shell mode; shell args become `['-c']` instead of `['-l','-c']` |\n| `ANTHROPIC_MODEL_BASH_NO_LOGIN`     | Legacy alias fallback for `GJC_BASH_NO_LOGIN`                                   |\n| `GJC_SHELL_PREFIX`          | Optional command prefix wrapper                                                |\n| `ANTHROPIC_MODEL_CODE_SHELL_PREFIX` | Legacy alias fallback for `GJC_SHELL_PREFIX`                                    |\n| `VISUAL`                   | Preferred external editor command                                              |\n| `EDITOR`                   | Fallback external editor command                                               |\n\nCurrent implementation: `GJC_BASH_NO_LOGIN`/`ANTHROPIC_MODEL_BASH_NO_LOGIN` are active; when either is set, `getShellArgs()` returns `['-c']`.\n\n---\n\n## 8) UI/theme/session detection (auto-detected env)\n\nThese are read as runtime signals; they are usually set by the terminal/OS rather than manually configured.\n\n| Variable                                                                                                           | Used for                                                  |\n| ------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------- |\n| `COLORTERM`, `TERM`, `WT_SESSION`                                                                                  | Color capability detection (theme color mode)             |\n| `COLORFGBG`                                                                                                        | Terminal background light/dark auto-detection             |\n| `TERM_PROGRAM`, `TERM_PROGRAM_VERSION`, `TERMINAL_EMULATOR`                                                        | Terminal identity in system prompt/context                |\n| `KDE_FULL_SESSION`, `XDG_CURRENT_DESKTOP`, `DESKTOP_SESSION`, `XDG_SESSION_DESKTOP`, `GDMSESSION`, `WINDOWMANAGER` | Desktop/window-manager detection in system prompt/context |\n| `KITTY_WINDOW_ID`, `TMUX_PANE`, `TERM_SESSION_ID`, `WT_SESSION`                                                    | Stable per-terminal session breadcrumb IDs                |\n| `SHELL`, `ComSpec`, `TERM_PROGRAM`, `TERM`                                                                         | System info diagnostics                                   |\n| `APPDATA`, `XDG_CONFIG_HOME`                                                                                       | lspmux config path resolution                             |\n| `HOME`                                                                                                             | Path shortening in command UI                         |\n\n---\n\n## 9) TUI runtime flags (shared package, affects coding-agent UX)\n\n| Variable                  | Behavior                                                                              |\n| ------------------------- | ------------------------------------------------------------------------------------- |\n| `GJC_NOTIFICATIONS`        | `off` / `0` / `false` suppress desktop notifications                                  |\n| `GJC_TUI_WRITE_LOG`        | If set, logs TUI writes to file                                                       |\n| `GJC_HARDWARE_CURSOR`      | If `1`, enables hardware cursor mode                                                  |\n| `GJC_CLEAR_ON_SHRINK`      | If `1`, clears empty rows when content shrinks                                        |\n| `GJC_DEBUG_REDRAW`         | If `1`, enables redraw debug logging                                                  |\n| `GJC_TUI_DEBUG`            | If `1`, enables deep TUI debug dump path                                              |\n| `GJC_FORCE_IMAGE_PROTOCOL` | Forces terminal image protocol detection (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) |\n\n---\n\n## 10) Commit generation controls\n\n| Variable                  | Behavior                                                            |\n| ------------------------- | ------------------------------------------------------------------- |\n| `GJC_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `GJC_COMMIT_NO_FALLBACK`   | If `true`, disables fallback when agent returns no proposal         |\n| `GJC_COMMIT_MAP_REDUCE`    | If `false`, disables map-reduce commit analysis path                |\n| `DEBUG`                   | If set, commit agent error stack traces are printed                 |\n\n---\n\n## 11) Bridge mode (`--mode bridge`)\n\nConsumed by `packages/coding-agent/src/modes/bridge/*`. The bridge is a\nnetwork-reachable control surface and is **secure-by-default**: it refuses to\nstart without TLS and a bearer token, and the 0.3.1 default endpoint matrix\nfail-closes session events, commands, controller ownership, UI responses, host\ntool results, and host URI results. See `docs/bridge.md` for protocol details.\n\n| Variable | Required | Default | Behavior |\n| --- | --- | --- | --- |\n| `GJC_BRIDGE_TOKEN` | Yes | — | Bearer token required on authenticated endpoints. **Secret — never commit.** |\n| `GJC_BRIDGE_TLS_CERT` | Yes | — | Path to the TLS certificate (PEM). Startup fails closed if cert/key are missing (TLS is mandatory, including loopback). |\n| `GJC_BRIDGE_TLS_KEY` | Yes | — | Path to the TLS private key (PEM). **Secret — never commit; `chmod 600`.** |\n| `GJC_BRIDGE_HOST` | No | `127.0.0.1` | Bind hostname. |\n| `GJC_BRIDGE_PORT` | No | `4077` | Bind port (1–65535). |\n| `GJC_BRIDGE_SCOPES` | No | `prompt` | Parsed for dormant command-surface compatibility. Valid scopes: `prompt`, `control`, `bash`, `export`, `session`, `model`, `message:read`, `host_tools`, `host_uri`, `admin`. The default endpoint matrix still advertises no accepted scopes and rejects commands before scope checks. |\n\nLocal development with a self-signed certificate must add the local CA to the\nclient trust store; there is no plaintext or certificate-verification-bypass mode.\n\n---\n\n## Security-sensitive variables\n\nTreat these as secrets; do not log or commit them:\n\n- Provider/API keys and OAuth/bearer credentials (all `*_API_KEY`, `*_TOKEN`, OAuth access/refresh tokens)\n- Cloud credentials (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS` path may expose service-account material)\n- Search/provider auth vars (`EXA_API_KEY`, `BRAVE_API_KEY`, `PERPLEXITY_API_KEY`, Anthropic search keys)\n- Foundry mTLS material (`ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`, `NODE_EXTRA_CA_CERTS` when it points to private CA bundles)\n- Bridge auth/TLS material (`GJC_BRIDGE_TOKEN` and the `GJC_BRIDGE_TLS_KEY` private key; never commit cert/key/token material)\n\nPython runtime also explicitly strips many common key vars before spawning kernel subprocesses (`packages/coding-agent/src/eval/py/runtime.ts`).\n",
 	"fs-scan-cache-architecture.md": "# Filesystem Scan Cache Architecture Contract\n\nThis document defines the current contract for the shared filesystem scan cache implemented in Rust (`crates/pi-natives/src/fs_cache.rs`) and consumed by native discovery/search APIs exposed to `packages/coding-agent`.\n\n## What this cache is\n\nThe cache stores full directory-scan entry lists (`GlobMatch[]`) keyed by scan scope and traversal policy, then lets higher-level operations (glob filtering, fuzzy scoring, grep file selection) run against those cached entries.\n\nPrimary goals:\n\n- avoid repeated filesystem walks for repeated discovery/search calls\n- keep consistency across `glob`, `fuzzyFind`, and `grep` when they share the same scan policy\n- allow explicit staleness recovery for empty results and explicit invalidation after file mutations\n\n## Ownership and public surface\n\n- Cache implementation and policy: `crates/pi-natives/src/fs_cache.rs`\n- Native consumers:\n  - `crates/pi-natives/src/glob.rs`\n  - `crates/pi-natives/src/fd.rs` (`fuzzyFind`)\n  - `crates/pi-natives/src/grep.rs`\n- JS binding/export:\n  - `packages/natives/src/glob/index.ts` (`invalidateFsScanCache`)\n  - `packages/natives/src/glob/types.ts`\n  - `packages/natives/src/grep/types.ts`\n- Coding-agent mutation invalidation helpers:\n  - `packages/coding-agent/src/tools/fs-cache-invalidation.ts`\n\n## Cache key partitioning (hard contract)\n\nEach entry is keyed by:\n\n- canonicalized `root` directory path\n- `include_hidden` boolean\n- `use_gitignore` boolean\n- `skip_node_modules` boolean\n\nImplications:\n\n- Hidden and non-hidden scans do **not** share entries.\n- Gitignore-respecting and ignore-disabled scans do **not** share entries.\n- Scans that prune `node_modules` do **not** share entries with scans that include it.\n- Consumers must pass stable semantics for hidden/gitignore/node_modules behavior; changing any flag creates a different cache partition.\n\n## Scan collection behavior\n\nCache population uses a deterministic walker (`ignore::WalkBuilder`) configured by `include_hidden`, `use_gitignore`, and `skip_node_modules`:\n\n- `follow_links(false)`\n- sorted by file path\n- `.git` is always skipped\n- `node_modules` is pruned at traversal time when `skip_node_modules=true`\n- entry file type + `mtime` are captured via `symlink_metadata`\n\nSearch roots are resolved by `resolve_search_path`:\n\n- relative paths are resolved against current cwd\n- target must be an existing directory\n- root is canonicalized when possible\n\n## Freshness and eviction policy\n\nGlobal policy (environment-overridable):\n\n- `FS_SCAN_CACHE_TTL_MS` (default `1000`)\n- `FS_SCAN_EMPTY_RECHECK_MS` (default `200`)\n- `FS_SCAN_CACHE_MAX_ENTRIES` (default `16`)\n\nBehavior:\n\n- `get_or_scan(...)`\n  - if TTL is `0`: bypass cache entirely, always fresh scan (`cache_age_ms = 0`)\n  - on cache hit within TTL: return cached entries + non-zero `cache_age_ms`\n  - on expired hit: evict key, rescan, store fresh entry\n- max entry enforcement is oldest-first eviction by `created_at`\n\n## Empty-result fast recheck (separate from normal hits)\n\nNormal cache hit:\n\n- a cache hit inside TTL returns cached entries and does nothing else.\n\nEmpty-result fast recheck:\n\n- this is a **caller-side** policy using `ScanResult.cache_age_ms`\n- if filtered/query result is empty and cached scan age is at least `empty_recheck_ms()`, caller performs one `force_rescan(...)` and retries\n- intended to reduce stale-negative results when files were recently added but cache is still within TTL\n\nCurrent consumers:\n\n- `glob`: rechecks when filtered matches are empty and scan age exceeds threshold\n- `fuzzyFind` (`fd.rs`): rechecks only when query is non-empty and scored matches are empty\n- `grep`: rechecks when selected candidate file list is empty\n\n## Consumer defaults and cache usage\n\nCache is opt-in on all exposed APIs (`cache?: boolean`, default `false`).\n\nCurrent defaults in native APIs:\n\n- `glob`: `hidden=false`, `gitignore=true`, `cache=false`, and `node_modules` included only when the pattern mentions `node_modules`\n- `fuzzyFind`: `hidden=false`, `gitignore=true`, `cache=false`, and `node_modules` is skipped\n- `grep`: `hidden=true`, `gitignore=true`, `cache=false`, and `node_modules` included only when the glob mentions `node_modules`\n\nCoding-agent callers today:\n\n- High-volume mention candidate discovery enables cache:\n  - `packages/coding-agent/src/utils/file-mentions.ts`\n  - profile: `hidden=true`, `gitignore=true`, `includeNodeModules=true`, `cache=true`\n- Tool-level `grep` integration currently disables scan cache (`cache: false`):\n  - `packages/coding-agent/src/tools/grep.ts`\n\n## Invalidation contract\n\nNative invalidation entrypoint:\n\n- `invalidateFsScanCache(path?: string)`\n  - with `path`: remove cache entries whose root is a prefix of target path\n  - without path: clear all scan cache entries\n\nPath handling details:\n\n- relative invalidation paths are resolved against cwd\n- invalidation attempts canonicalization\n- if target does not exist (e.g., delete), fallback canonicalizes parent and reattaches filename when possible\n- this preserves invalidation behavior for create/delete/rename where one side may not exist\n\n## Coding-agent mutation flow responsibilities\n\nCoding-agent code must invalidate after successful filesystem mutations.\n\nCentral helpers:\n\n- `invalidateFsScanAfterWrite(path)`\n- `invalidateFsScanAfterDelete(path)`\n- `invalidateFsScanAfterRename(oldPath, newPath)` (invalidates both sides when paths differ)\n\nCurrent mutation tool callsites:\n\n- `packages/coding-agent/src/tools/write.ts`\n- `packages/coding-agent/src/patch/index.ts` (hashline/patch/replace flows)\n\nRule: if a flow mutates filesystem content or location and bypasses these helpers, cache staleness bugs are expected.\n\n## Adding a new cache consumer safely\n\nWhen introducing cache use in a new scanner/search path:\n\n1. **Use stable scan policy inputs**\n   - decide hidden/gitignore/node_modules semantics first\n   - pass them consistently to `get_or_scan`/`force_rescan` so cache partitions are intentional\n\n2. **Treat cache data as pre-filtered only by traversal policy**\n   - apply tool-specific filtering (glob patterns, type filters, scoring) after retrieval\n   - never assume cached entries already reflect your higher-level filters\n\n3. **Implement empty-result fast recheck only for stale-negative risk**\n   - use `scan.cache_age_ms >= empty_recheck_ms()`\n   - retry once with `force_rescan(..., store=true, ...)`\n   - keep this path separate from normal cache-hit logic\n\n4. **Respect no-cache mode explicitly**\n   - when caller disables cache, call `force_rescan(..., store=false, ...)`\n   - do not populate shared cache in a no-cache request path\n\n5. **Wire mutation invalidation for any new write path**\n   - after successful write/edit/delete/rename, call the coding-agent invalidation helper\n   - for rename/move, invalidate both old and new paths\n\n6. **Do not add per-call TTL knobs**\n   - current contract is global policy only (env-configured), no per-request TTL override\n\n## Known boundaries\n\n- Cache scope is process-local in-memory (`DashMap`), not persisted across process restarts.\n- Cache stores scan entries, not final tool results.\n- `glob`/`fuzzyFind`/`grep` share scan entries only when key dimensions (`root`, `hidden`, `gitignore`, `skip_node_modules`) match.\n- `.git` is always excluded at scan collection time regardless of caller options.\n",
 	"gjc-dogfood-skill-template.md": "# GJC dogfood local skill template\n\nIssue #93 requested a gaebal-gajae/operator dogfood skill. The live issue has no comment approving a fifth bundled default workflow skill, so this stays a local template instead of changing the default workflow surface. Operators can copy it into a user or project override when they want GJC-first session guidance:\n\n```sh\nmkdir -p ~/.gjc/skills/gjc-dogfood\ncp docs/gjc-dogfood-skill-template.md ~/.gjc/skills/gjc-dogfood/SKILL.md\n```\n\nFor a single project, copy it to `<project>/.gjc/skills/gjc-dogfood/SKILL.md` instead. Do not commit that project `.gjc` copy unless the project explicitly wants a local override.\n\n---\nname: gjc-dogfood\ndescription: Use when running or reviewing work through GJC sessions, dogfooding Gajae-Code, or migrating an operator workflow from OMX to GJC.\n---\n\n# GJC Dogfood Operator Workflow\n\nUse GJC first for coding, review, planning, and follow-up sessions. Treat OMX as a fallback only when GJC is unavailable, broken, or missing a required capability.\n\n## Locate and launch GJC\n\n- Installed CLI: run `command -v gjc` and then launch with `gjc --tmux`.\n- Repository checkout: from the gajae-code repo, prefer `bun packages/coding-agent/src/cli.ts --tmux` when testing source changes before install.\n- Worktree isolation: for branch-specific work, launch from or point at the branch worktree with `gjc --tmux --worktree <path>`.\n- Name sessions explicitly with the project and issue, for example `gajae-code-93-dogfood-skill`, so tmux panes, logs, and exports remain traceable.\n\n## Start the session\n\n- Put git operations inside the GJC session: fetch, branch/worktree setup, focused commits, pushes, and PR creation should be visible in-session.\n- Submit the initial prompt with the issue URL, target branch, acceptance criteria, verification limits, and any existing plan/spec link.\n- Verify the prompt was accepted: the TUI should show the user prompt, an active assistant turn, or a tool/action request. If the session silently idles, resend once with a shorter prompt and capture the failure.\n- Verify working state before leaving the session unattended: confirm the target cwd/worktree, branch, and issue scope are visible in the transcript or command output.\n\n## During work\n\n- Keep session names and branch names issue-scoped.\n- Prefer GJC workflow skills only when they fit: `deep-interview` for unclear requirements, `ralplan` for planning, `ultragoal` for durable ledgers, and `team` for coordinated tmux execution.\n- Keep evidence in the session: issue reads, focused tests/checks, screenshots only when visual behavior matters, and PR URLs.\n- When GJC is weaker than OMX, finish the urgent work with the smallest safe fallback and file a gajae-code follow-up issue with the missing capability, exact command/session context, expected behavior, and evidence.\n\n## Fallback policy\n\nUse OMX or another operator path only when:\n\n- `gjc` cannot be located or launched after checking installed and repo-local commands;\n- authentication, model routing, tmux, or prompt submission is broken;\n- GJC lacks a required capability that OMX already has;\n- an urgent production/review deadline would be missed by debugging GJC first.\n\nRecord the fallback reason and create or link the gajae-code issue that would make GJC sufficient next time.\n\n## Evidence checklist\n\nReport:\n\n- project, issue, branch/worktree, and session name;\n- whether GJC was installed or repo-local;\n- prompt acceptance and working-state evidence;\n- git operations performed in-session;\n- focused verification commands and results;\n- PR/issue URLs;\n- follow-up gajae-code issues for any GJC gap or fallback.\n",
 	"handoff-generation-pipeline.md": "# `/handoff` generation pipeline\n\nThis document describes how the coding-agent implements `/handoff`: trigger path, oneshot generation, session switch, context reinjection, persistence, and UI behavior.\n\n## Scope\n\nCovers:\n\n- Interactive `/handoff` command dispatch\n- `AgentSession.handoff()` lifecycle and state transitions\n- `generateHandoff(...)` request shape\n- How old/new sessions persist handoff data differently\n- UI behavior for success, cancel, and failure\n\nDoes not cover:\n\n- Generic tree navigation/branch internals\n- Non-handoff session commands (`/new`, `/fork`, `/resume`)\n\n## Implementation files\n\n- [`../src/modes/controllers/input-controller.ts`](../packages/coding-agent/src/modes/controllers/input-controller.ts)\n- [`../src/modes/controllers/command-controller.ts`](../packages/coding-agent/src/modes/controllers/command-controller.ts)\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`packages/agent/src/compaction/compaction.ts`](../packages/agent/src/compaction/compaction.ts)\n- [`../src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts)\n- [`../src/extensibility/slash-commands.ts`](../packages/coding-agent/src/extensibility/slash-commands.ts)\n\n## Trigger path\n\n1. `/handoff` is declared in builtin slash command metadata (`slash-commands.ts`) with optional inline hint: `[focus instructions]`.\n2. In interactive input handling (`InputController`), submit text matching `/handoff` or `/handoff ...` is intercepted before normal prompt submission.\n3. The editor is cleared and `handleHandoffCommand(customInstructions?)` is called.\n4. `CommandController.handleHandoffCommand` performs a preflight guard using current entries:\n   - Counts `type === \"message\"` entries.\n   - If `< 2`, it warns: `Nothing to hand off (no messages yet)` and returns.\n\nThe same minimum-content guard exists again inside `AgentSession.handoff()` and throws if violated. This duplicates safety at both UI and session layers.\n\n## End-to-end lifecycle\n\n### 1) Start handoff generation\n\n`AgentSession.handoff(customInstructions?)`:\n\n- Reads current branch entries (`sessionManager.getBranch()`).\n- Validates minimum message count (`>= 2`).\n- Creates `#handoffAbortController` and links any caller-provided abort signal to it.\n- Resolves the current model API key through `ModelRegistry`.\n- Calls `generateHandoff(...)` with:\n  - live agent messages (`agent.state.messages`),\n  - the current model and API key,\n  - the base system prompt (`#baseSystemPrompt`),\n  - the live tool array (`agent.state.tools`),\n  - optional focus instructions,\n  - coding-agent message conversion (`convertToLlm`),\n  - provider metadata and `initiatorOverride: \"agent\"`.\n\n`generateHandoff(...)` lives in `packages/agent/src/compaction/compaction.ts` next to summarization. It renders `packages/agent/src/compaction/prompts/handoff-document.md` via `renderHandoffPrompt(...)` with optional `additionalFocus`.\n\n### 2) Generate and capture output\n\n`generateHandoff(...)` converts the existing `AgentMessage[]` history to real LLM `Message[]` history, then appends one trailing agent-attributed `user` message containing the rendered handoff prompt.\n\nThe request uses `completeSimple(...)` directly:\n\n```ts\nawait completeSimple(\n  model,\n  {\n    systemPrompt,\n    messages: requestMessages,\n    tools,\n  },\n  {\n    apiKey,\n    signal,\n    reasoning: Effort.High,\n    toolChoice: \"none\",\n    initiatorOverride,\n    metadata,\n  },\n);\n```\n\nImportant generation properties:\n\n- The request preserves the live provider cache prefix by reusing the same system prompt, tool definitions, and real message history shape as the active agent.\n- The handoff instruction is a trailing `user` message, not a developer message, so the cached prefix remains aligned with the prior turn.\n- `toolChoice: \"none\"` prevents intentional tool dispatch.\n- The returned assistant content is filtered to text blocks and joined with `\\n`; stray tool-call blocks are ignored if a provider does not honor `toolChoice: \"none\"`.\n- `stopReason === \"error\"` throws a generation error.\n\nNo agent-loop events are used for capture. The handoff path no longer waits for `agent_end` and no longer scans the latest assistant message.\n\n### 3) Cancellation checks\n\nCancellation throws `Error(\"Handoff cancelled\")`; a completed generation with no text returns `undefined`.\n\n- caller signal aborts `#handoffAbortController`\n- `completeSimple(...)` receives the abort signal\n- aborted handoff signal or provider `AbortError` is normalized to `Error(\"Handoff cancelled\")`\n- empty generated text returns `undefined`\n\n`AgentSession.handoff()` always clears `#handoffAbortController` in `finally`.\n\n### 4) New session creation\n\nIf text was generated and not aborted:\n\n1. Flush current session writer (`sessionManager.flush()`).\n2. Cancel session-owned async jobs.\n3. Start a brand-new session with `parentSession` pointing at the previous session file when one exists.\n4. Reset in-memory agent state (`agent.reset()`).\n5. Rebind `agent.sessionId` to the new session id.\n6. Rekey/reset hindsight state for the new session.\n7. Clear queued context arrays (`#steeringMessages`, `#followUpMessages`, `#pendingNextTurnMessages`) and any scheduled hidden next-turn generation.\n8. Reset todo reminder counter.\n\n### 5) Handoff-context injection\n\nThe generated handoff document is wrapped by coding-agent session glue and appended to the new session as a `custom_message` entry:\n\n```text\n<handoff-context>\n...handoff text...\n</handoff-context>\n\nThe above is a handoff document from a previous session. Use this context to continue the work seamlessly.\n```\n\nInsertion call:\n\n```ts\nthis.sessionManager.appendCustomMessageEntry(\"handoff\", handoffContent, true, undefined, \"agent\");\n```\n\nSemantics:\n\n- `customType`: `\"handoff\"`\n- `display`: `true` (visible in TUI rebuild)\n- attribution: `\"agent\"`\n- Entry type: `custom_message` (participates in LLM context)\n\n### 6) Rebuild active agent context\n\nAfter injection:\n\n1. `buildDisplaySessionContext()` resolves message list for current leaf.\n2. `agent.replaceMessages(sessionContext.messages)` makes the injected handoff message active context.\n3. Todo phases are synchronized from the new branch.\n4. Method returns `{ document: handoffText, savedPath? }`.\n\nAt this point, the active LLM context in the new session contains the injected handoff message, not the old transcript.\n\n## Persistence model: old session vs new session\n\n### Old session\n\nHandoff generation is a oneshot request, not a visible agent turn. The generated handoff text is not appended to the old session as an assistant message.\n\nResult: the original session keeps its prior transcript unchanged except for data already persisted before handoff began.\n\n### New session\n\nAfter session reset, handoff is persisted as `custom_message` with `customType: \"handoff\"`.\n\n`buildSessionContext()` converts this entry into a runtime custom/user-context message via `createCustomMessage(...)`, so it is included in future prompts from the new session.\n\nAuto-triggered handoffs can additionally write a timestamped `handoff-*.md` artifact under the session artifacts directory when `compaction.handoffSaveToDisk` is enabled. Manual `/handoff` does not write that artifact.\n\n## Controller/UI behavior\n\n`CommandController.handleHandoffCommand` behavior:\n\n- Shows a status loader: `Generating handoff… (esc to cancel)`.\n- Calls `await session.handoff(customInstructions)`.\n- If result is `undefined`: `showError(\"Handoff cancelled\")`.\n- On success:\n  - `rebuildChatFromMessages()` (loads new session context, including injected handoff)\n  - invalidates status line and editor top border\n  - reloads todos\n  - appends success chat line: `New session started with handoff context`\n- On exception:\n  - if message is `\"Handoff cancelled\"` or error name is `AbortError`: `showError(\"Handoff cancelled\")`\n  - otherwise: `showError(\"Handoff failed: <message>\")`\n- Stops the loader, restores the previous Escape handler, and requests render at end.\n\nManual `/handoff` no longer streams the generated document into chat. A cancellable loader remains visible while the oneshot request runs, and the chat is rebuilt after generation completes.\n\n## Cancellation semantics\n\n### Session-level cancellation primitive\n\n`AgentSession` exposes:\n\n- `abortHandoff()` → aborts `#handoffAbortController`\n- `isGeneratingHandoff` → true while controller exists\n\nWhen this abort path is used, the abort signal is passed to `completeSimple(...)`; `handoff()` normalizes the cancellation to `Error(\"Handoff cancelled\")`, and command controller maps it to cancellation UI.\n\n### Interactive `/handoff` path\n\nThe command controller installs a temporary Escape handler for `/handoff` while the loader is visible. Pressing Escape calls `session.abortHandoff()`, which aborts the `completeSimple(...)` request through `#handoffAbortController`.\n\n## Aborted vs failed handoff\n\nCurrent UI classification:\n\n- **Aborted/cancelled**\n  - `abortHandoff()` path triggers `\"Handoff cancelled\"`, or\n  - thrown `AbortError`\n  - UI shows `Handoff cancelled`\n- **Failed**\n  - any other thrown error from `handoff()` / `generateHandoff()` / provider request path\n  - UI shows `Handoff failed: ...`\n\nAdditional nuance: if generation completes but no text is returned, `handoff()` returns `undefined` and controller currently reports **cancelled**, not **failed**.\n\n## Short-session and minimum-content guardrails\n\nTwo guards prevent low-signal handoffs:\n\n- UI layer (`handleHandoffCommand`): warns and returns early for `< 2` message entries\n- Session layer (`handoff()`): throws the same condition as an error\n\nThis avoids creating a new session with empty/near-empty handoff context.\n\n## State transition summary\n\nHigh-level state flow:\n\n1. Interactive slash command intercepted.\n2. Preflight message-count guard.\n3. `#handoffAbortController` created (`isGeneratingHandoff = true`).\n4. `generateHandoff(...)` issues one `completeSimple(...)` request with live system prompt, tools, message history, and trailing handoff prompt.\n5. Assistant response text blocks are joined; tool-call blocks are discarded.\n6. If missing text → return `undefined`; if aborted → cancellation error path.\n7. If present:\n   - flush old session\n   - cancel async jobs\n   - create new empty session with previous session as parent\n   - reset runtime queues/counters\n   - append `custom_message(handoff)`\n   - optionally save an auto-triggered handoff document under the session artifacts directory when `compaction.handoffSaveToDisk` is enabled\n8. Controller rebuilds chat UI and announces success.\n9. `#handoffAbortController` cleared (`isGeneratingHandoff = false`).\n\n## Known assumptions and limitations\n\n- No structural validation checks that generated markdown follows the requested section format.\n- Missing generated text is reported as cancellation in controller UX.\n- Manual handoff has no streaming visibility; a cancellable loader is shown until the UI updates after generation completes.\n- Auto-triggered handoffs can write a timestamped `handoff-*.md` artifact when `compaction.handoffSaveToDisk` is enabled; write failure is logged and does not fail the handoff.\n",
 	"keybindings.md": "# Keybindings\n\nRun `/hotkeys` inside an `gjc` session to see the active chords for your current build. The list reflects any remaps loaded from disk and any bindings added by extensions.\n\n## Customize keybindings\n\nUser remaps live in `~/.gjc/agent/keybindings.json`. The file is a JSON object whose keys are keybinding action IDs and whose values are either one chord string or an array of chord strings. It is not read from `~/.gjc/agent/config.yml`, and there is no nested `keybindings` object.\n\n```json\n{\n  \"app.model.cycleForward\": \"Ctrl+P\",\n  \"app.model.selectTemporary\": \"Alt+P\",\n  \"app.plan.toggle\": \"Alt+Shift+P\"\n}\n```\n\nChord names are case-insensitive and use the same notation shown in the UI, such as `Ctrl+P`, `Alt+Shift+P`, `Shift+Enter`, and `Ctrl+Backspace`.\n\nSet an action to an empty array to disable it:\n\n```json\n{\n  \"app.stt.toggle\": []\n}\n```\n\n## Common action IDs\n\n| Action ID | Default | Meaning |\n| --- | --- | --- |\n| `app.model.cycleForward` | `Ctrl+P` | Cycle role models forward |\n| `app.model.cycleBackward` | `Shift+Ctrl+P` | Cycle role models backward |\n| `app.model.selectTemporary` | `Alt+P` | Pick a model temporarily for this session |\n| `app.model.select` | `Ctrl+L` | Open the model selector and set roles |\n| `app.plan.toggle` | `Alt+Shift+P` | Toggle plan mode |\n| `app.history.search` | `Ctrl+R` | Search prompt history |\n| `app.tools.expand` | `Ctrl+O` | Toggle tool-output expansion |\n| `app.thinking.toggle` | `Ctrl+T` | Toggle thinking-block visibility |\n| `app.thinking.cycle` | `Shift+Tab` | Cycle thinking level |\n| `app.editor.external` | `Ctrl+G` | Edit the draft in `$VISUAL` / `$EDITOR` |\n| `app.message.followUp` | `Ctrl+Enter` | Queue a follow-up message |\n| `app.message.dequeue` | `Alt+Up` | Dequeue a queued message back into the editor |\n| `app.clipboard.copyLine` | `Alt+Shift+L` | Copy the current line |\n| `app.clipboard.copyPrompt` | `Alt+Shift+C` | Copy the whole prompt |\n| `app.stt.toggle` | `Alt+H` | Toggle speech-to-text recording |\n\nOlder unqualified action names are migrated when `keybindings.json` is loaded, but new docs and new configs should use the namespaced action IDs above.\n",
 	"lsp-config.md": "# LSP configuration in GJC\n\nThis guide explains how to configure language servers for the GJC coding agent.\n\nSource of truth in code:\n\n- Server config type: `packages/coding-agent/src/lsp/types.ts` (`ServerConfig`)\n- Config loader: `packages/coding-agent/src/lsp/config.ts`\n- Built-in server definitions: `packages/coding-agent/src/lsp/defaults.json`\n\n## Auto-detection\n\nWhen no LSP config file is present, GJC auto-detects servers by intersecting two conditions:\n\n1. The project directory contains at least one of the server's `rootMarkers`.\n2. The server binary is available — checked in project-local bin directories first (e.g., `node_modules/.bin/`, `.venv/bin/`), then `$PATH`.\n\nNo configuration is required for common setups. The built-in server list covers most popular languages; see [`defaults.json`](../packages/coding-agent/src/lsp/defaults.json) for the full set.\n\n## Config file locations\n\nGJC merges LSP config from multiple files, lowest to highest priority:\n\n| Priority | Location |\n|----------|----------|\n| 5 (lowest) | `~/lsp.json`, `~/.lsp.json`, `~/lsp.yaml`, `~/.lsp.yaml` |\n| 3 | `~/.gjc/agent/lsp.json`, `~/.gjc/agent/lsp.yaml`, `~/.gemini/lsp.*` |\n| 2 | `<project>/.gjc/lsp.json`, `<project>/.gjc/lsp.yaml`, `<project>/.gemini/lsp.*` |\n| 1 (highest) | `<project>/lsp.json`, `<project>/.lsp.json`, `<project>/lsp.yaml` |\n\nEach location accepts both `.json` and `.yaml` / `.yml` variants, as well as hidden-file versions (`.lsp.json`, `.lsp.yaml`). Files are merged in order: higher-priority files override lower-priority fields for the same server. Servers not mentioned in any override file remain at their built-in defaults.\n\n**Recommended locations:**\n\n- User-wide preferences → `~/.gjc/agent/lsp.json`\n- Project-specific overrides → `<project>/.gjc/lsp.json`\n\n> **Note:** The presence of any LSP config file disables auto-detection. When at least one file is found, GJC skips the binary-scan phase and loads all servers that have matching `rootMarkers`, an available binary, and are not explicitly `disabled`.\n\n## File shape\n\nBoth JSON and YAML are accepted. The top-level object can use either a `servers` wrapper key or a flat map directly:\n\n```json\n{\n  \"servers\": {\n    \"server-name\": { ... }\n  },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nor (flat, without the `servers` wrapper):\n\n```json\n{\n  \"server-name\": { ... },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nTop-level keys:\n\n- `servers` — map of server name to `ServerConfig` (optional wrapper; flat form is equivalent)\n- `idleTimeoutMs` — shut down idle language servers after this many milliseconds; disabled by default\n\n## ServerConfig fields\n\n| Field | Type | Required | Description |\n|-------|------|----------|-------------|\n| `command` | `string` | yes | Binary name (resolved via PATH/local bins) or absolute path |\n| `args` | `string[]` | no | Arguments passed to the binary |\n| `fileTypes` | `string[]` | yes | File extensions this server handles, e.g. `[\".ts\", \".tsx\"]` |\n| `rootMarkers` | `string[]` | yes | Files/dirs that indicate a project root; glob patterns (e.g. `*.cabal`) are supported |\n| `initOptions` | `object` | no | Sent as `initializationOptions` during LSP handshake |\n| `settings` | `object` | no | Workspace settings pushed via `workspace/didChangeConfiguration` |\n| `disabled` | `boolean` | no | Set to `true` to disable this server entirely |\n| `warmupTimeoutMs` | `number` | no | Startup timeout in ms for this server (overrides the global default) |\n| `isLinter` | `boolean` | no | Mark server as linter/formatter only; excluded from type-intelligence operations (hover, go-to-definition, etc.) |\n| `capabilities` | `object` | no | Opt-in server-specific features; see [Capabilities](#capabilities) |\n\n`resolvedCommand` is populated automatically at runtime — do not set it manually.\n\n### Capabilities\n\nThe `capabilities` object enables optional server-specific features that GJC supports on a per-server basis:\n\n```json\n{\n  \"capabilities\": {\n    \"flycheck\": true,\n    \"ssr\": true,\n    \"expandMacro\": true,\n    \"runnables\": true,\n    \"relatedTests\": true\n  }\n}\n```\n\nAll fields are boolean and optional. They are currently used by `rust-analyzer`.\n\n## Common recipes\n\n### Override a built-in server's settings\n\nPartial overrides are merged onto the built-in defaults. You only need to specify the fields you want to change.\n\n```json\n{\n  \"servers\": {\n    \"typescript-language-server\": {\n      \"args\": [\"--stdio\", \"--log-level\", \"4\"]\n    }\n  }\n}\n```\n\n```yaml\nservers:\n  gopls:\n    settings:\n      gopls:\n        gofumpt: false\n        staticcheck: false\n```\n\n### Disable a built-in server\n\n```json\n{\n  \"servers\": {\n    \"eslint\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\n### Register a custom server\n\nNew servers require `command`, `fileTypes`, and `rootMarkers`. All other fields are optional.\n\n```json\n{\n  \"servers\": {\n    \"my-lsp\": {\n      \"command\": \"my-lsp-server\",\n      \"args\": [\"--stdio\"],\n      \"fileTypes\": [\".xyz\"],\n      \"rootMarkers\": [\".xyz-project\", \".git\"]\n    }\n  }\n}\n```\n\n### Set a global idle timeout\n\nShut down language servers that have been inactive for more than five minutes:\n\n```json\n{\n  \"idleTimeoutMs\": 300000\n}\n```\n\n### Disable a server for one project, keep it globally\n\nPlace the override in `<project>/.gjc/lsp.json`:\n\n```json\n{\n  \"servers\": {\n    \"pylsp\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\nThe user-level config in `~/.gjc/agent/lsp.json` is unaffected; pylsp is only suppressed in this project.\n\n## Built-in server list\n\nThe following servers ship in `defaults.json` and are eligible for auto-detection:\n\n| Server key | Language(s) | Binary |\n|---|---|---|\n| `rust-analyzer` | Rust | `rust-analyzer` |\n| `clangd` | C, C++, ObjC | `clangd` |\n| `zls` | Zig | `zls` |\n| `gopls` | Go | `gopls` |\n| `typescript-language-server` | TypeScript, JavaScript | `typescript-language-server` |\n| `denols` | TypeScript, JavaScript (Deno) | `deno` |\n| `biome` | TS/JS/JSON (linter) | `biome` |\n| `eslint` | TS/JS/Vue/Svelte (linter) | `vscode-eslint-language-server` |\n| `vscode-html-language-server` | HTML | `vscode-html-language-server` |\n| `vscode-css-language-server` | CSS, SCSS, Less | `vscode-css-language-server` |\n| `vscode-json-language-server` | JSON | `vscode-json-language-server` |\n| `tailwindcss` | HTML, CSS, TS/JS | `tailwindcss-language-server` |\n| `svelte` | Svelte | `svelteserver` |\n| `vue-language-server` | Vue | `vue-language-server` |\n| `astro` | Astro | `astro-ls` |\n| `pyright` | Python | `pyright-langserver` |\n| `basedpyright` | Python | `basedpyright-langserver` |\n| `pylsp` | Python | `pylsp` |\n| `ruff` | Python (linter) | `ruff` |\n| `jdtls` | Java | `jdtls` |\n| `kotlin-lsp` | Kotlin | `kotlin-lsp` |\n| `metals` | Scala | `metals` |\n| `hls` | Haskell | `haskell-language-server-wrapper` |\n| `ocamllsp` | OCaml | `ocamllsp` |\n| `elixirls` | Elixir | `elixir-ls` |\n| `erlangls` | Erlang | `erlang_ls` |\n| `gleam` | Gleam | `gleam` |\n| `solargraph` | Ruby | `solargraph` |\n| `ruby-lsp` | Ruby | `ruby-lsp` |\n| `rubocop` | Ruby (linter) | `rubocop` |\n| `bashls` | Bash, Zsh | `bash-language-server` |\n| `lua-language-server` | Lua | `lua-language-server` |\n| `intelephense` | PHP | `intelephense` |\n| `phpactor` | PHP | `phpactor` |\n| `omnisharp` | C# | `omnisharp` |\n| `yamlls` | YAML | `yaml-language-server` |\n| `terraformls` | Terraform | `terraform-ls` |\n| `dockerls` | Dockerfile | `docker-langserver` |\n| `helm-ls` | Helm | `helm_ls` |\n| `nixd` | Nix | `nixd` |\n| `nil` | Nix | `nil` |\n| `ols` | Odin | `ols` |\n| `dartls` | Dart | `dart` |\n| `marksman` | Markdown | `marksman` |\n| `texlab` | LaTeX | `texlab` |\n| `graphql` | GraphQL | `graphql-lsp` |\n| `prismals` | Prisma | `prisma-language-server` |\n| `vimls` | Vim script | `vim-language-server` |\n| `emmet-language-server` | HTML, CSS, JSX | `emmet-language-server` |\n| `sourcekit-lsp` | Swift | `sourcekit-lsp` |\n| `swiftlint` | Swift (linter) | `swiftlint` |\n| `tlaplus` | TLA+ | `tlapm_lsp` |\n",
-	"memory.md": "# Autonomous Memory\n\nWhen enabled, the agent automatically extracts durable knowledge from past sessions and injects a compact summary into each new session. Over time it builds a project-scoped memory store — technical decisions, recurring workflows, pitfalls — that carries forward without manual effort.\n\nDisabled by default. Enable via `/settings` or `config.yml`:\n\n```yaml\nmemories:\n  enabled: true\n```\n\n## Usage\n\n### What gets injected\n\nAt session start, if a memory summary exists for the current project, it is injected into the system prompt as a **Memory Guidance** block. The agent is instructed to:\n\n- Treat memory as heuristic context — useful for process and prior decisions, not authoritative on current repo state.\n- Cite the memory artifact path when memory changes the plan, and pair it with current-repo evidence before acting.\n- Prefer repo state and user instruction when they conflict with memory; treat conflicting memory as stale.\n\n### Reading memory artifacts\n\nThe agent can read memory files directly using `memory://` URLs with the `read` tool:\n\n| URL                                    | Content                             |\n| -------------------------------------- | ----------------------------------- |\n| `memory://root`                        | Compact summary injected at startup |\n| `memory://root/MEMORY.md`              | Full long-term memory document      |\n| `memory://root/skills/<name>/SKILL.md` | A generated skill playbook          |\n\n### `/memory` slash command\n\n| Subcommand            | Effect                                         |\n| --------------------- | ---------------------------------------------- |\n| `view`                | Show the current memory injection payload      |\n| `clear` / `reset`     | Delete all memory data and generated artifacts |\n| `enqueue` / `rebuild` | Force consolidation to run at next startup     |\n\n## How it works\n\nMemories are built by a background pipeline that runs at startup or when manually triggered via slash command.\n\n**Phase 1 — per-session extraction:** For each past session that has changed since it was last processed, a model reads the session history and extracts durable signal: technical decisions, constraints, resolved failures, recurring workflows. Sessions that are too recent, too old, or currently active are skipped. Each extraction produces a raw memory block and a short synopsis for that session.\n\n**Phase 2 — consolidation:** After extraction, a second model pass reads all per-session extractions and produces three outputs written to disk:\n\n- `MEMORY.md` — a curated long-term memory document\n- `memory_summary.md` — the compact text injected at session start\n- `skills/` — reusable procedural playbooks, each in its own subdirectory\n\nPhase 2 uses a lease to prevent double-running when multiple processes start simultaneously. Stale skill directories from prior runs are pruned automatically.\n\nAll output is scanned for secrets before being written to disk.\n\n### Extraction behavior\n\nMemory extraction and consolidation behavior is driven by static prompt files in `packages/coding-agent/src/prompts/memories/`.\n\n| File                  | Purpose                                     | Variables                                   |\n| --------------------- | ------------------------------------------- | ------------------------------------------- |\n| `stage_one_system.md` | System prompt for per-session extraction    | —                                           |\n| `stage_one_input.md`  | User-turn template wrapping session content | `{{thread_id}}`, `{{response_items_json}}`  |\n| `consolidation.md`    | Prompt for cross-session consolidation      | `{{raw_memories}}`, `{{rollout_summaries}}` |\n| `read_path.md`        | Memory guidance injected into live sessions | `{{memory_summary}}`                        |\n\n### Model selection\n\nMemory piggybacks on the model role system.\n\n| Phase                   | Role                                                                | Purpose                          |\n| ----------------------- | ------------------------------------------------------------------- | -------------------------------- |\n| Phase 1 (extraction)    | `default`                                                           | Per-session knowledge extraction |\n| Phase 2 (consolidation) | `smol` (falls back to `default`, then current/first registry model) | Cross-session synthesis          |\n\nIf the requested memory role is not configured, memory model resolution falls back to the `default` role, then the active session model, then the first model in the registry.\n\n## Configuration\n\n| Setting                               | Default | Description                                               |\n| ------------------------------------- | ------- | --------------------------------------------------------- |\n| `memories.enabled`                    | `false` | Master switch                                             |\n| `memories.maxRolloutAgeDays`          | `30`    | Sessions older than this are not processed                |\n| `memories.minRolloutIdleHours`        | `12`    | Sessions active more recently than this are skipped       |\n| `memories.maxRolloutsPerStartup`      | `64`    | Cap on sessions processed in a single startup             |\n| `memories.summaryInjectionTokenLimit` | `5000`  | Max tokens of the summary injected into the system prompt |\n\nAdditional tuning knobs (concurrency, lease durations, token budgets) are available in config for advanced use.\n\n## Key files\n\n- `packages/coding-agent/src/memories/index.ts` — pipeline orchestration, injection, slash command handling\n- `packages/coding-agent/src/memories/storage.ts` — SQLite-backed job queue and thread registry\n- `packages/coding-agent/src/prompts/memories/` — memory prompt templates\n- `packages/coding-agent/src/internal-urls/memory-protocol.ts` — `memory://` URL handler\n",
-	"models.md": "# Model and Provider Configuration (`models.yml`)\n\nThis document describes how the coding-agent currently loads models, applies overrides, resolves credentials, and chooses models at runtime.\n\n## What controls model behavior\n\nPrimary implementation files:\n\n- `src/config/model-registry.ts` — loads built-in + custom models, provider overrides, runtime discovery, auth integration\n- `src/config/model-resolver.ts` — parses model patterns and selects initial/smol/slow models\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.gjc/agent/models.yml`\n\nLegacy behavior still present:\n\n- If `models.yml` is missing and `models.json` exists at the same location, it is migrated to `models.yml`.\n- Explicit `.json` / `.jsonc` config paths are still supported when passed programmatically to `ModelRegistry`.\n\n## `models.yml` shape\n\n```yaml\nproviders:\n  <provider-id>:\n    # provider-level config\nequivalence:\n  overrides:\n    <provider-id>/<model-id>: <canonical-model-id>\n  exclude:\n    - <provider-id>/<model-id>\n```\n\n`provider-id` is the canonical provider key used across selection and auth lookup.\n\n`equivalence` is optional and configures canonical model grouping on top of concrete provider models:\n\n- `overrides` maps an exact concrete selector (`provider/modelId`) to an official upstream canonical id\n- `exclude` opts a concrete selector out of canonical grouping\n\n## Provider-level fields\n\n```yaml\nproviders:\n  my-provider:\n    baseUrl: https://api.example.com/v1\n    apiKey: MY_PROVIDER_API_KEY\n    api: openai-completions\n    headers:\n      X-Team: platform\n    authHeader: true\n    auth: apiKey\n    disableStrictTools: false  # set true for Anthropic-compatible endpoints that reject the strict field\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\nmodelBindings:\n  modelRoles:\n    default: my-provider/some-model-id:high\n  agentModelOverrides:\n    executor: my-provider/some-model-id\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `bedrock-converse-stream`\n- `anthropic-messages`\n- `bedrock-converse-stream`\n- `google-generative-ai`\n- `google-vertex`\n- `google-gemini-cli`\n- `ollama-chat`\n- `cursor-agent`\n\n\n### First-class Azure OpenAI and Amazon Bedrock examples\n\nAzure OpenAI uses canonical OpenAI model IDs in GJC and resolves those IDs to Azure deployment names at request time. Set `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` to avoid assuming model id equals deployment name:\n\n```yaml\nproviders:\n  azure-openai:\n    baseUrl: https://my-resource.openai.azure.com/openai/v1\n    apiKeyEnv: AZURE_OPENAI_API_KEY\n    api: azure-openai-responses\n    models:\n      - id: gpt-4.1\n      - id: o3\n```\n\n```sh\nexport AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-4.1=gpt-41-prod,o3=o3-reasoning-prod'\n```\n\nAmazon Bedrock uses the native `bedrock-converse-stream` transport and AWS credential chain auth. Do not put AWS access keys in `models.yml`; configure `AWS_REGION` / `AWS_PROFILE` or standard static AWS credential environment variables instead:\n\n```yaml\nproviders:\n  amazon-bedrock:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com\n    api: bedrock-converse-stream\n    models:\n      - id: us.anthropic.claude-opus-4-6-v1\n      - id: anthropic.claude-3-5-sonnet-20241022-v2:0\n```\n\n### MiniMax and GLM custom provider examples\n\nFor common MiniMax and GLM/zAI setup, prefer the provider presets so the OpenAI-compatible API, base URL, env var, model id, and compatibility flags are written together:\n\n```sh\ngjc setup provider --preset minimax\ngjc setup provider --preset minimax-cn\ngjc setup provider --preset glm\n```\n\nThe same presets are available inside the TUI:\n\n```text\n/provider add --preset minimax\n/provider add --preset glm\n/provider add zai\n```\n\nPresets only write `models.yml` entries that reference documented environment variable names (`MINIMAX_CODE_API_KEY`, `MINIMAX_CODE_CN_API_KEY`, or `ZAI_API_KEY`); they do not store or validate real credentials. The GLM preset aliases (`glm`, `zai`, `z-ai`) write an OpenAI-compatible custom provider named `glm-proxy` and do not replace the first-class `zai` provider.\n\nMiniMax's OpenAI-compatible endpoint rejects multiple system messages and emits thinking in `reasoning_content`, so pin the public-safe compatibility fields when hand-authoring a custom provider:\n\n```yaml\nproviders:\n  minimax-custom:\n    baseUrl: https://api.minimax.io/v1\n    apiKeyEnv: MINIMAX_API_KEY\n    api: openai-completions\n    compat:\n      supportsStore: false\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n      reasoningContentField: reasoning_content\n    models:\n      - id: MiniMax-M2.5\n```\n\nGLM via z.ai is available as the first-class `zai` provider. For a private GLM-compatible proxy, keep secrets in an env var and disable OpenAI-only request fields as needed:\n\n```yaml\nproviders:\n  glm-proxy:\n    baseUrl: https://api.z.ai/api/paas/v4\n    apiKeyEnv: ZAI_API_KEY\n    api: openai-completions\n    compat:\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n    models:\n      - id: glm-4.6\n```\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `models.yml` is strict: unknown provider/model keys fail validation before provider dispatch, so stale keys such as `requestTransform` or `wireModelId` only work where this document lists them.\n- `discovery.type`: `ollama`, `llama.cpp`, or `lm-studio`\n\n## OpenAI-compatible proxy configuration\n\nOpenAI-compatible proxy providers should use schema-supported provider keys first:\n\n```yaml\nproviders:\n  proxy-provider:\n    baseUrl: https://api.proxy.example/v1\n    apiKeyEnv: PROXY_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: local-gpt\n        name: Local GPT\n        reasoning: true\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n```\n\nUse provider-level `headers` for proxy-required headers. Keep the provider `api` set to `openai-completions` when the proxy exposes Chat Completions-compatible `/v1/chat/completions` semantics. `auth: apiKey` sends the resolved token as bearer auth; use `auth: none` only for trusted local/no-auth endpoints.\n\n`requestTransform` and `wireModelId` remain supported for request-body shaping, but they are not needed for ordinary OpenAI-compatible proxies whose local model id is already the upstream wire id. Unknown config keys fail validation before a provider request is sent.\n\nWhen request shaping is needed:\n\n- `requestTransform.profile: openai-proxy` strips OpenAI SDK/Stainless telemetry headers at final fetch time and sets a generic GJC user agent.\n- `stripHeaders` replaces the preset strip list when provided.\n- `setHeaders` is applied after stripping; use `null` to remove a header.\n- `extraBody` is shallow-merged into the JSON request body after provider compatibility fields; core transport keys such as `model`, `messages`/`input`, `stream`, `tools`, and `tool_choice` are protected and ignored.\n- Model-level `requestTransform` overrides provider-level fields and shallow-merges `setHeaders`/`extraBody`.\n- `wireModelId` changes only the upstream request body model id; local selection still uses `provider/id`.\n\n### Layofflabs-style proxy example\n\n```yaml\nproviders:\n  layofflabs:\n    baseUrl: https://api.layofflabs.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-5.5\n        name: GPT 5.5 via Layofflabs\n        reasoning: true\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n\nmodelBindings:\n  modelRoles:\n    default: layofflabs/gpt-5.5:high\n  agentModelOverrides:\n    executor: layofflabs/gpt-5.5:high\n```\n\n## Validation rules (current)\n\n### Full custom provider (`models` is non-empty)\n\nRequired:\n\n- `baseUrl`\n- `apiKey` unless `auth: none`\n- `api` at provider level or each model\n\n### Override-only provider (`models` missing or empty)\n\nMust define at least one of:\n\n- `baseUrl`\n- `headers`\n- `compat`\n- `requestTransform`\n- `disableStrictTools`\n- `modelOverrides`\n- `discovery`\n\n### Discovery\n\n- `discovery` requires provider-level `api`.\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\n- unknown provider, model, override, and request-transform keys fail schema validation; remove stale keys instead of relying on them being ignored.\n\n## Merge and override order\n\nModelRegistry pipeline (on refresh):\n\n1. Load built-in providers/models from `@gajae-code/ai`.\n2. Load `models.yml` custom config.\n3. Apply provider overrides (`baseUrl`, `headers`, `requestTransform`, `disableStrictTools`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (schema v3) with a `static_fingerprint` column that hashes the\nstatic catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process via a WeakMap keyed by the static-models array\nreference, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `anthropic-model-opus-4-6`\n- `anthropic-model-haiku-4-5`\n- `gpt-5.3-openai-code`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: openai-code\n        name: Zenmux OpenAI code\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/openai-code: gpt-5.3-openai-code\n    p-openai-code/openai-code: gpt-5.3-openai-code\n  exclude:\n    - demo/openai-code-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `input`, `cost`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL` or `http://127.0.0.1:11434`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `GJC_AUTH_BROKER_URL` (or `auth.broker.url`) is set, the local SQLite credential store is replaced by `RemoteAuthCredentialStore`. Layers 2 and 3 above (stored API key / OAuth in `agent.db`) are served from a broker-supplied snapshot whose `refresh` tokens are redacted; expiry triggers `POST /v1/credential/:id/refresh` on the broker rather than a local refresh.\n\n`AuthStorage.setConfigApiKey` lets a `models.yml` `apiKey` win over a broker-resolved OAuth token without overriding a runtime `--api-key`. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full broker / gateway design and env surface (`GJC_AUTH_BROKER_URL`, `GJC_AUTH_BROKER_TOKEN`, `auth.broker.url`, `auth.broker.token`).\n\n## Model availability vs all models\n\n- `getAll()` returns the loaded model registry (built-in + merged custom + discovered).\n- `getAvailable()` filters to models that are keyless or have resolvable auth.\n\nSo a model can exist in registry but not be selectable until auth is available.\n\n## Runtime model resolution\n\n### CLI and pattern parsing\n\n`model-resolver.ts` supports:\n\n- exact `provider/modelId`\n- exact canonical model id\n- exact model id (provider inferred)\n- fuzzy/substring matching\n- glob scope patterns in `--models` (e.g. `openai/*`, `*sonnet*`)\n- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh`)\n\n`--provider` is legacy; `--model` is preferred.\n\nResolution precedence for exact selectors:\n\n1. exact `provider/modelId` bypasses coalescing\n2. exact canonical id resolves through the canonical index\n3. exact bare concrete id still works\n4. fuzzy and glob matching run after the exact paths\n\n### Initial model selection priority\n\n`findInitialModel(...)` uses this order:\n\n1. explicit CLI provider+model\n2. first scoped model (if not resuming)\n3. saved default provider/model\n4. known provider defaults (e.g. OpenAI/Anthropic/etc.) among available models\n5. first available model\n\n### Role aliases and settings\n\nSupported model roles:\n\n- `default`, `smol`, `slow`, `vision`, `plan`, `designer`, `commit`, `task`\n\nRole aliases like `pi/smol` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI code provider transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-openai-code` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - anthropic-model-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/anthropic-model-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `--list-models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `--list-models` prints a canonical section plus the concrete provider rows\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI code provider websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for Spark -> non-Spark on the same provider:\n\n```yaml\nproviders:\n  openai-code:\n    modelOverrides:\n      gpt-5.3-openai-code-spark:\n        contextPromotionTarget: openai-code/gpt-5.3-openai-code\n```\n\nThe built-in model generator also assigns this automatically for `*-spark` models when a same-provider base model exists.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/ai/src/providers/openai-completions-compat.ts`. It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/model-registry.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/ai/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok and zAI).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true  # if the proxy doesn't support strict tool schemas\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/anthropic-model-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.gjc/agent/models.yml`.\n\n## Failure mode\n\nIf `models.yml` fails schema or validation checks:\n\n- registry keeps operating with built-in models\n- error is exposed via `ModelRegistry.getError()` and surfaced in UI/notifications\n",
+	"memory.md": "# Autonomous Memory\n\nWhen enabled, the agent automatically extracts durable knowledge from past sessions and injects a compact summary into each new session. Over time it builds a project-scoped memory store — technical decisions, recurring workflows, pitfalls — that carries forward without manual effort.\n\nDisabled by default. Enable via `/settings` or `config.yml`:\n\n```yaml\nmemories:\n  enabled: true\n```\n\n## Usage\n\n### What gets injected\n\nAt session start, if a memory summary exists for the current project, it is injected into the system prompt as a **Memory Guidance** block. The agent is instructed to:\n\n- Treat memory as heuristic context — useful for process and prior decisions, not authoritative on current repo state.\n- Pair memory-influenced decisions with current-repo evidence before acting.\n- Prefer repo state and user instruction when they conflict with memory; treat conflicting memory as stale.\n\n### Memory artifacts\n\nGenerated local-memory artifacts are private runtime state, not a public tool or URI surface. They may be summarized into the system prompt when local memory is enabled, but users and model-facing tool docs should not rely on direct `memory://` reads. The legacy internal `memory://` resolver remains only for compatibility with existing persisted guidance and is not part of the public coding harness contract; remove it after legacy local-memory prompts no longer reference it.\n### `/memory` slash command\n\n| Subcommand            | Effect                                         |\n| --------------------- | ---------------------------------------------- |\n| `view`                | Show the current memory injection payload      |\n| `clear` / `reset`     | Delete all memory data and generated artifacts |\n| `enqueue` / `rebuild` | Force consolidation to run at next startup     |\n\n## How it works\n\nMemories are built by a background pipeline that runs at startup or when manually triggered via slash command.\n\n**Phase 1 — per-session extraction:** For each past session that has changed since it was last processed, a model reads the session history and extracts durable signal: technical decisions, constraints, resolved failures, recurring workflows. Sessions that are too recent, too old, or currently active are skipped. Each extraction produces a raw memory block and a short synopsis for that session.\n\n**Phase 2 — consolidation:** After extraction, a second model pass reads all per-session extractions and produces three outputs written to disk:\n\n- `MEMORY.md` — a curated long-term memory document\n- `memory_summary.md` — the compact text injected at session start\n- `skills/` — reusable procedural playbooks, each in its own subdirectory\n\nPhase 2 uses a lease to prevent double-running when multiple processes start simultaneously. Stale skill directories from prior runs are pruned automatically.\n\nAll output is scanned for secrets before being written to disk.\n\n### Extraction behavior\n\nMemory extraction and consolidation behavior is driven by static prompt files in `packages/coding-agent/src/prompts/memories/`.\n\n| File                  | Purpose                                     | Variables                                   |\n| --------------------- | ------------------------------------------- | ------------------------------------------- |\n| `stage_one_system.md` | System prompt for per-session extraction    | —                                           |\n| `stage_one_input.md`  | User-turn template wrapping session content | `{{thread_id}}`, `{{response_items_json}}`  |\n| `consolidation.md`    | Prompt for cross-session consolidation      | `{{raw_memories}}`, `{{rollout_summaries}}` |\n| `read_path.md`        | Memory guidance injected into live sessions | `{{memory_summary}}`                        |\n\n### Model selection\n\nMemory piggybacks on the model role system.\n\n| Phase                   | Role                                                                | Purpose                          |\n| ----------------------- | ------------------------------------------------------------------- | -------------------------------- |\n| Phase 1 (extraction)    | `default`                                                           | Per-session knowledge extraction |\n| Phase 2 (consolidation) | `smol` (falls back to `default`, then current/first registry model) | Cross-session synthesis          |\n\nIf the requested memory role is not configured, memory model resolution falls back to the `default` role, then the active session model, then the first model in the registry.\n\n## Configuration\n\n| Setting                               | Default | Description                                               |\n| ------------------------------------- | ------- | --------------------------------------------------------- |\n| `memories.enabled`                    | `false` | Master switch                                             |\n| `memories.maxRolloutAgeDays`          | `30`    | Sessions older than this are not processed                |\n| `memories.minRolloutIdleHours`        | `12`    | Sessions active more recently than this are skipped       |\n| `memories.maxRolloutsPerStartup`      | `64`    | Cap on sessions processed in a single startup             |\n| `memories.summaryInjectionTokenLimit` | `5000`  | Max tokens of the summary injected into the system prompt |\n\nAdditional tuning knobs (concurrency, lease durations, token budgets) are available in config for advanced use.\n\n## Key files\n\n- `packages/coding-agent/src/memories/index.ts` — pipeline orchestration, injection, slash command handling\n- `packages/coding-agent/src/memories/storage.ts` — SQLite-backed job queue and thread registry\n- `packages/coding-agent/src/prompts/memories/` — memory prompt templates\n- `packages/coding-agent/src/internal-urls/memory-protocol.ts` — legacy non-public `memory://` compatibility handler\n",
+	"models.md": "# Model and Provider Configuration (`models.yml`)\n\nThis document describes how the coding-agent currently loads models, applies overrides, resolves credentials, and chooses models at runtime.\n\n## What controls model behavior\n\nPrimary implementation files:\n\n- `src/config/model-registry.ts` — loads built-in + custom models, provider overrides, runtime discovery, auth integration\n- `src/config/model-resolver.ts` — parses model patterns and selects initial/smol/slow models\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.gjc/agent/models.yml`\n\nLegacy behavior still present:\n\n- If `models.yml` is missing and `models.json` exists at the same location, it is migrated to `models.yml`.\n- Explicit `.json` / `.jsonc` config paths are still supported when passed programmatically to `ModelRegistry`.\n\n## `models.yml` shape\n\n```yaml\nproviders:\n  <provider-id>:\n    # provider-level config\nequivalence:\n  overrides:\n    <provider-id>/<model-id>: <canonical-model-id>\n  exclude:\n    - <provider-id>/<model-id>\n```\n\n`provider-id` is the canonical provider key used across selection and auth lookup.\n\n`equivalence` is optional and configures canonical model grouping on top of concrete provider models:\n\n- `overrides` maps an exact concrete selector (`provider/modelId`) to an official upstream canonical id\n- `exclude` opts a concrete selector out of canonical grouping\n\n## Provider-level fields\n\n```yaml\nproviders:\n  my-provider:\n    baseUrl: https://api.example.com/v1\n    apiKey: MY_PROVIDER_API_KEY\n    api: openai-completions\n    headers:\n      X-Team: platform\n    authHeader: true\n    auth: apiKey\n    disableStrictTools: false  # set true for Anthropic-compatible endpoints that reject the strict field\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\nmodelBindings:\n  modelRoles:\n    default: my-provider/some-model-id:high\n  agentModelOverrides:\n    executor: my-provider/some-model-id\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `bedrock-converse-stream`\n- `anthropic-messages`\n- `bedrock-converse-stream`\n- `google-generative-ai`\n- `google-vertex`\n- `google-gemini-cli`\n- `ollama-chat`\n- `cursor-agent`\n\n\n### First-class Azure OpenAI and Amazon Bedrock examples\n\nAzure OpenAI uses canonical OpenAI model IDs in GJC and resolves those IDs to Azure deployment names at request time. Set `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` to avoid assuming model id equals deployment name:\n\n```yaml\nproviders:\n  azure-openai:\n    baseUrl: https://my-resource.openai.azure.com/openai/v1\n    apiKeyEnv: AZURE_OPENAI_API_KEY\n    api: azure-openai-responses\n    models:\n      - id: gpt-4.1\n      - id: o3\n```\n\n```sh\nexport AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-4.1=gpt-41-prod,o3=o3-reasoning-prod'\n```\n\nAmazon Bedrock uses the native `bedrock-converse-stream` transport and AWS credential chain auth. Do not put AWS access keys in `models.yml`; configure `AWS_REGION` / `AWS_PROFILE` or standard static AWS credential environment variables instead:\n\n```yaml\nproviders:\n  amazon-bedrock:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com\n    api: bedrock-converse-stream\n    models:\n      - id: us.anthropic.claude-opus-4-6-v1\n      - id: anthropic.claude-3-5-sonnet-20241022-v2:0\n```\n\n### MiniMax and GLM custom provider examples\n\nFor common MiniMax and GLM/zAI setup, prefer the provider presets so the OpenAI-compatible API, base URL, env var, model id, and compatibility flags are written together:\n\n```sh\ngjc setup provider --preset minimax\ngjc setup provider --preset minimax-cn\ngjc setup provider --preset glm\n```\n\nThe same presets are available inside the TUI:\n\n```text\n/provider add --preset minimax\n/provider add --preset glm\n/provider add zai\n```\n\nPresets only write `models.yml` entries that reference documented environment variable names (`MINIMAX_CODE_API_KEY`, `MINIMAX_CODE_CN_API_KEY`, or `ZAI_API_KEY`); they do not store or validate real credentials. The GLM preset aliases (`glm`, `zai`, `z-ai`) write an OpenAI-compatible custom provider named `glm-proxy` and do not replace the first-class `zai` provider.\n\n## Model profiles (`--mpreset`)\n\nModel profiles are optional top-level `profiles:` entries in `~/.gjc/agent/models.yml`. A profile can require provider credentials before activation and can map one or more model roles; omitted roles inherit from the active defaults.\n\n```yaml\nprofiles:\n  team-standard:\n    required_providers: [openai, anthropic]\n    model_mapping:\n      default: openai/gpt-5.2\n      executor: anthropic/claude-sonnet-4-6:medium\n      architect: openai/o3:high\n      planner: openai/o3:high\n      critic: openai/o3:high\n```\n\n`model_mapping` keys are role names (`default`, `executor`, `architect`, `planner`, `critic`). Each role maps to exactly one model selector in the form `provider/modelId[:effort]`; comma-separated fallback chains are not supported in a single role value.\n`required_providers` is the aggregate set of providers required across the profile's mapped roles, not a per-role fallback chain.\n\nBuilt-in profiles are grouped by provider mix and tier:\n\n- `opencode-go-{eco,standard,pro}`\n- `codex-{eco,standard,pro}`\n- `opencode-go-codex-{eco,standard,pro}`\n\nThe `eco` tier favors cheaper/faster defaults, `standard` matches normal production defaults (`codex-standard` is the current OpenAI Codex default set), and `pro` raises reasoning for architect, critic, and planner roles. User-defined profiles override built-ins by exact profile name.\n\nUse `gjc --mpreset <name>` to activate a profile for the current session only. Activation hard-blocks when any provider listed in `required_providers` lacks credentials. Add `--default` to persist the selected profile as `modelProfile.default` in `config.yml`, so it applies at startup:\n\n```sh\ngjc --mpreset codex-standard\ngjc --mpreset opencode-go-pro --default\n```\n\nThe `/model` command shows a `Profiles` section above model selection. In `/login`, `Add custom provider` is the first option for configuring credentials needed by custom or profile-required providers.\n\nMiniMax's OpenAI-compatible endpoint rejects multiple system messages and emits thinking in `reasoning_content`, so pin the public-safe compatibility fields when hand-authoring a custom provider:\n\n```yaml\nproviders:\n  minimax-custom:\n    baseUrl: https://api.minimax.io/v1\n    apiKeyEnv: MINIMAX_API_KEY\n    api: openai-completions\n    compat:\n      supportsStore: false\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n      reasoningContentField: reasoning_content\n    models:\n      - id: MiniMax-M2.5\n```\n\nGLM via z.ai is available as the first-class `zai` provider. For a private GLM-compatible proxy, keep secrets in an env var and disable OpenAI-only request fields as needed:\n\n```yaml\nproviders:\n  glm-proxy:\n    baseUrl: https://api.z.ai/api/paas/v4\n    apiKeyEnv: ZAI_API_KEY\n    api: openai-completions\n    compat:\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n    models:\n      - id: glm-4.6\n```\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `models.yml` is strict: unknown provider/model keys fail validation before provider dispatch, so stale keys such as `requestTransform` or `wireModelId` only work where this document lists them.\n- `discovery.type`: `ollama`, `llama.cpp`, or `lm-studio`\n\n## OpenAI-compatible proxy configuration\n\nOpenAI-compatible proxy providers should use schema-supported provider keys first:\n\n```yaml\nproviders:\n  proxy-provider:\n    baseUrl: https://api.proxy.example/v1\n    apiKeyEnv: PROXY_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: local-gpt\n        name: Local GPT\n        reasoning: true\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n```\n\nUse provider-level `headers` for proxy-required headers. Keep the provider `api` set to `openai-completions` when the proxy exposes Chat Completions-compatible `/v1/chat/completions` semantics. `auth: apiKey` sends the resolved token as bearer auth; use `auth: none` only for trusted local/no-auth endpoints.\n\n`requestTransform` and `wireModelId` remain supported for request-body shaping, but they are not needed for ordinary OpenAI-compatible proxies whose local model id is already the upstream wire id. Unknown config keys fail validation before a provider request is sent.\n\nWhen request shaping is needed:\n\n- `requestTransform.profile: openai-proxy` strips OpenAI SDK/Stainless telemetry headers at final fetch time and sets a generic GJC user agent.\n- `stripHeaders` replaces the preset strip list when provided.\n- `setHeaders` is applied after stripping; use `null` to remove a header.\n- `extraBody` is shallow-merged into the JSON request body after provider compatibility fields; core transport keys such as `model`, `messages`/`input`, `stream`, `tools`, and `tool_choice` are protected and ignored.\n- Model-level `requestTransform` overrides provider-level fields and shallow-merges `setHeaders`/`extraBody`.\n- `wireModelId` changes only the upstream request body model id; local selection still uses `provider/id`.\n\n### Layofflabs-style proxy example\n\n```yaml\nproviders:\n  layofflabs:\n    baseUrl: https://api.layofflabs.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-5.5\n        name: GPT 5.5 via Layofflabs\n        reasoning: true\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n\nmodelBindings:\n  modelRoles:\n    default: layofflabs/gpt-5.5:high\n  agentModelOverrides:\n    executor: layofflabs/gpt-5.5:high\n```\n\n## Validation rules (current)\n\n### Full custom provider (`models` is non-empty)\n\nRequired:\n\n- `baseUrl`\n- `apiKey` unless `auth: none`\n- `api` at provider level or each model\n\n### Override-only provider (`models` missing or empty)\n\nMust define at least one of:\n\n- `baseUrl`\n- `headers`\n- `compat`\n- `requestTransform`\n- `disableStrictTools`\n- `modelOverrides`\n- `discovery`\n\n### Discovery\n\n- `discovery` requires provider-level `api`.\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\n- unknown provider, model, override, and request-transform keys fail schema validation; remove stale keys instead of relying on them being ignored.\n\n## Merge and override order\n\nModelRegistry pipeline (on refresh):\n\n1. Load built-in providers/models from `@gajae-code/ai`.\n2. Load `models.yml` custom config.\n3. Apply provider overrides (`baseUrl`, `headers`, `requestTransform`, `disableStrictTools`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (schema v3) with a `static_fingerprint` column that hashes the\nstatic catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process via a WeakMap keyed by the static-models array\nreference, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `anthropic-model-opus-4-6`\n- `anthropic-model-haiku-4-5`\n- `gpt-5.3-openai-code`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: openai-code\n        name: Zenmux OpenAI code\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/openai-code: gpt-5.3-openai-code\n    p-openai-code/openai-code: gpt-5.3-openai-code\n  exclude:\n    - demo/openai-code-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `input`, `cost`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL` or `http://127.0.0.1:11434`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `GJC_AUTH_BROKER_URL` (or `auth.broker.url`) is set, the local SQLite credential store is replaced by `RemoteAuthCredentialStore`. Layers 2 and 3 above (stored API key / OAuth in `agent.db`) are served from a broker-supplied snapshot whose `refresh` tokens are redacted; expiry triggers `POST /v1/credential/:id/refresh` on the broker rather than a local refresh.\n\n`AuthStorage.setConfigApiKey` lets a `models.yml` `apiKey` win over a broker-resolved OAuth token without overriding a runtime `--api-key`. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full broker / gateway design and env surface (`GJC_AUTH_BROKER_URL`, `GJC_AUTH_BROKER_TOKEN`, `auth.broker.url`, `auth.broker.token`).\n\n## Model availability vs all models\n\n- `getAll()` returns the loaded model registry (built-in + merged custom + discovered).\n- `getAvailable()` filters to models that are keyless or have resolvable auth.\n\nSo a model can exist in registry but not be selectable until auth is available.\n\n## Runtime model resolution\n\n### CLI and pattern parsing\n\n`model-resolver.ts` supports:\n\n- exact `provider/modelId`\n- exact canonical model id\n- exact model id (provider inferred)\n- fuzzy/substring matching\n- glob scope patterns in `--models` (e.g. `openai/*`, `*sonnet*`)\n- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh`)\n\n`--provider` is legacy; `--model` is preferred.\n\nResolution precedence for exact selectors:\n\n1. exact `provider/modelId` bypasses coalescing\n2. exact canonical id resolves through the canonical index\n3. exact bare concrete id still works\n4. fuzzy and glob matching run after the exact paths\n\n### Initial model selection priority\n\n`findInitialModel(...)` uses this order:\n\n1. explicit CLI provider+model\n2. first scoped model (if not resuming)\n3. saved default provider/model\n4. known provider defaults (e.g. OpenAI/Anthropic/etc.) among available models\n5. first available model\n\n### Role aliases and settings\n\nSupported model roles:\n\n- `default`, `smol`, `slow`, `vision`, `plan`, `designer`, `commit`, `task`\n\nRole aliases like `pi/smol` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI code provider transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-openai-code` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - anthropic-model-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/anthropic-model-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `--list-models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `--list-models` prints a canonical section plus the concrete provider rows\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI code provider websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for Spark -> non-Spark on the same provider:\n\n```yaml\nproviders:\n  openai-code:\n    modelOverrides:\n      gpt-5.3-openai-code-spark:\n        contextPromotionTarget: openai-code/gpt-5.3-openai-code\n```\n\nThe built-in model generator also assigns this automatically for `*-spark` models when a same-provider base model exists.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/ai/src/providers/openai-completions-compat.ts`. It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/model-registry.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/ai/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok and zAI).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true  # if the proxy doesn't support strict tool schemas\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/anthropic-model-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.gjc/agent/models.yml`.\n\n## Failure mode\n\nIf `models.yml` fails schema or validation checks:\n\n- registry keeps operating with built-in models\n- error is exposed via `ModelRegistry.getError()` and surfaced in UI/notifications\n",
 	"natives-addon-loader-runtime.md": "# Natives Addon Loader Runtime\n\nThis document covers the runtime loader shipped by `@gajae-code/natives`: how `native/index.js` decides which `.node` file to require, how compiled-binary embedded payloads are extracted, and what startup failures report.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/package.json`\n\n## Scope and responsibility\n\nThe loader is intentionally narrow:\n\n- Build a platform/CPU-aware candidate list for addon filenames and directories.\n- Treat an embedded-addon manifest as the authoritative compiled-binary signal when present.\n- Optionally materialize an embedded addon into a versioned per-user cache directory.\n- Attempt candidates in deterministic order and return the first addon that `require(...)` loads.\n\nThe current loader does **not** run a separate `validateNative(...)` export-presence gate. API shape is provided by the generated N-API binding file (`native/index.d.ts`) and the loaded addon itself. A stale binary therefore normally fails as a missing property or native load error rather than as a custom \"missing exports\" validation error.\n\n## Runtime inputs and derived state\n\nAt module initialization, `native/index.js` computes:\n\n- **Platform tag**: `${process.platform}-${process.arch}` (for example `darwin-arm64`).\n- **Package version**: from `packages/natives/package.json`.\n- **Core directories**:\n  - `nativeDir`: package-local `packages/natives/native`.\n  - `execDir`: directory containing `process.execPath`.\n  - `versionedDir`: `<getNativesDir()>/<packageVersion>`.\n  - `userDataDir` fallback:\n    - Windows: `%LOCALAPPDATA%/gjc` or `%USERPROFILE%/AppData/Local/gjc`.\n    - Non-Windows: `~/.local/bin`.\n- **Natives cache root** (`getNativesDir()`):\n  - if `$XDG_DATA_HOME/gjc` exists, `$XDG_DATA_HOME/gjc/natives`;\n  - otherwise `~/.gjc/natives`.\n- **Compiled-binary mode** (`detectCompiledBinary`): true if any of:\n  - embedded-addon manifest is non-null,\n  - `GJC_COMPILED` env var is set,\n  - `import.meta.url` contains Bun embedded markers (`$bunfs`, `~BUN`, `%7EBUN`).\n- **Variant override**: `GJC_NATIVE_VARIANT` (`modern`/`baseline` only; invalid values ignored).\n- **Selected variant**: explicit override, otherwise runtime AVX2 detection on x64 (`modern` if AVX2, else `baseline`).\n\n## Platform support and tag resolution\n\n`SUPPORTED_PLATFORMS` is fixed to:\n\n- `linux-x64`\n- `linux-arm64`\n- `darwin-x64`\n- `darwin-arm64`\n- `win32-x64`\n\nUnsupported platforms are not rejected before probing. The loader first tries the computed candidate paths. If all fail and `platformTag` is unsupported, it throws an unsupported-platform error listing supported tags.\n\n## Variant selection (`modern` / `baseline` / default)\n\n### x64 behavior\n\n1. `GJC_NATIVE_VARIANT=modern|baseline` wins when valid.\n2. Otherwise AVX2 support is detected:\n   - Linux: scan `/proc/cpuinfo` for `avx2`.\n   - macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`.\n   - Windows: PowerShell `[System.Runtime.Intrinsics.X86.Avx2]::IsSupported`.\n3. AVX2 selects `modern`; unavailable or undetectable AVX2 selects `baseline`.\n\n### Non-x64 behavior\n\nNo variant suffix is used; the filename is `pi_natives.<platform>-<arch>.node`.\n\n### Filename construction\n\n`loader-state.js#getAddonFilenames` returns:\n\n- Non-x64 or no variant: `pi_natives.<tag>.node`\n- x64 + `modern`:\n  1. `pi_natives.<tag>-modern.node`\n  2. `pi_natives.<tag>-baseline.node`\n  3. `pi_natives.<tag>.node`\n- x64 + `baseline`:\n  1. `pi_natives.<tag>-baseline.node`\n  2. `pi_natives.<tag>.node`\n\nThe default unsuffixed fallback remains part of the x64 candidate list.\n\n## Candidate path construction and fallback ordering\n\n`resolveLoaderCandidates(...)` expands every filename across directories, then de-duplicates while preserving first occurrence order.\n\n### Non-compiled runtime\n\nFor each filename, candidates are:\n\n1. `<nativeDir>/<filename>`\n2. `<execDir>/<filename>`\n\n### Compiled runtime\n\nFor each filename, candidates are:\n\n1. `<versionedDir>/<filename>`\n2. `<userDataDir>/<filename>`\n3. `<nativeDir>/<filename>`\n4. `<execDir>/<filename>`\n\nAt load time, an extracted embedded candidate, when produced, is prepended ahead of these de-duplicated candidates.\n\n## Embedded addon extraction lifecycle\n\n`embedded-addon.js` is generated by `scripts/embed-native.ts`. The reset stub exports `embeddedAddon = null`. A populated manifest has:\n\n- `platformTag`\n- `version`\n- `files[]` entries with `variant`, `filename`, and `filePath`\n\nExtraction (`maybeExtractEmbeddedAddon`) runs only when:\n\n1. compiled-binary mode is true,\n2. `embeddedAddon` is non-null,\n3. manifest `platformTag` equals the runtime platform tag,\n4. manifest `version` equals the package version,\n5. a variant-appropriate embedded file exists.\n\nVariant file selection:\n\n- Non-x64: prefer `default`, then first available file.\n- x64 + `modern`: prefer `modern`, fallback to `baseline`.\n- x64 + `baseline`: require `baseline`.\n\nMaterialization:\n\n1. Ensure `<versionedDir>` exists.\n2. Reuse `<versionedDir>/<selected filename>` if it already exists.\n3. Otherwise read `selectedEmbeddedFile.filePath` and write the target path.\n4. Return the target path as the first candidate.\n\nDirectory creation or write failures are appended to the loader error list; probing continues through normal candidates.\n\n## Lifecycle and state transitions\n\n```text\nInit\n  -> Load package metadata and embedded-addon manifest\n  -> Compute platform/version/variant/filenames/candidate paths\n  -> (compiled + embedded manifest matches?)\n       yes -> try extract to versionedDir (record errors, continue)\n       no  -> skip extraction\n  -> For each runtime candidate in order:\n       require(candidate)\n       -> success: return addon exports (READY)\n       -> failure: record error, continue\n  -> none loaded:\n       if unsupported platform tag -> throw Unsupported platform\n       else -> throw Failed to load (tried-path diagnostics + hints)\n```\n\n## Failure behavior and diagnostics\n\n### Unsupported platform\n\nIf all candidates fail and `platformTag` is not supported, the loader throws:\n\n- `Unsupported platform: <tag>`\n- supported platform list\n- issue-reporting guidance\n\n### No loadable candidate\n\nIf the platform is supported but no candidate can be loaded, the final error includes:\n\n- `Failed to load pi_natives native addon for <platformTag>` or `<platformTag> (<variant>)`\n- every attempted path with the corresponding `require(...)` error\n- mode-specific remediation hints\n\n### Compiled-binary startup failures\n\nCompiled mode diagnostics include:\n\n- expected versioned cache target paths (`<versionedDir>/<filename>`),\n- remediation to delete the versioned cache and rerun,\n- direct release download `curl` commands for each expected filename.\n\n### Non-compiled startup failures\n\nNormal package/runtime diagnostics include:\n\n- reinstall hint (`bun install @gajae-code/natives`),\n- local rebuild command (`bun --cwd=packages/natives run build`),\n- optional x64 variant build hint (`TARGET_VARIANT=baseline|modern bun --cwd=packages/natives run build`).\n",
 	"natives-architecture.md": "# Natives Architecture\n\n`@gajae-code/natives` is now a two-layer package around a loader:\n\n1. **CommonJS loader/package entrypoint** resolves and loads the correct `.node` addon and patches generated enum objects onto the export object.\n2. **Rust N-API module layer** implements the exported functions/classes and emits the generated TypeScript declarations.\n\nThis document is the foundation for deeper module-level docs.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n\n## Package entrypoint and public surface\n\n`packages/natives/package.json` points directly at generated native bindings:\n\n- `main`: `./native/index.js`\n- `types`: `./native/index.d.ts`\n- `exports[\".\"].types`: `./native/index.d.ts`\n- `exports[\".\"].import`: `./native/index.js`\n\nThere is no current `packages/natives/src` TypeScript wrapper layer. Consumers import functions/classes/enums directly from `@gajae-code/natives`; the type contract is the generated `native/index.d.ts` plus enum exports appended by `scripts/gen-enums.ts`.\n\nCurrent capability groups in the generated API include:\n\n- **Search/text/code primitives**: `grep`, `search`, `hasMatch`, `fuzzyFind`, `glob`, `astGrep`, `astEdit`, text width/slicing/wrapping/sanitization, syntax highlighting, token counting.\n- **Execution/process/terminal primitives**: `executeShell`, `Shell`, `PtySession`, process-tree helpers, key parsing.\n- **System/media/conversion primitives**: clipboard, image resize/encode/SIXEL, HTML-to-Markdown, macOS appearance/power helpers, work profiling, Windows ProjFS overlay helpers.\n\n## Loader layer\n\n`packages/natives/native/index.js` owns runtime addon selection and optional embedded extraction.\n\n### Candidate resolution model\n\n- Platform tag is `${process.platform}-${process.arch}`.\n- Supported tags are currently:\n  - `linux-x64`\n  - `linux-arm64`\n  - `darwin-x64`\n  - `darwin-arm64`\n  - `win32-x64`\n- x64 can use CPU variants:\n  - `modern` (AVX2-capable)\n  - `baseline` (fallback)\n- Non-x64 uses the default filename without a variant suffix.\n\nFilename strategy:\n\n- Default: `pi_natives.<platform>-<arch>.node`\n- x64 variant: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- x64 runtime fallback includes the unsuffixed default filename after variant candidates.\n\n### Platform-specific variant detection\n\nFor x64, variant selection uses:\n\n- Linux: `/proc/cpuinfo`\n- macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`\n- Windows: PowerShell check for `System.Runtime.Intrinsics.X86.Avx2`\n\n`GJC_NATIVE_VARIANT` can force `modern` or `baseline`; invalid values are ignored.\n\n### Binary distribution and extraction model\n\n`packages/natives/package.json` publishes `native/`, which contains the loader, generated declarations, generated enum patch, embedded-addon manifest stub, and prebuilt `.node` artifacts.\n\nFor compiled binaries, loader behavior is:\n\n1. Check versioned user cache path: `<getNativesDir()>/<packageVersion>/...`.\n2. Check legacy compiled-binary location:\n   - Windows: `%LOCALAPPDATA%/gjc` (fallback `%USERPROFILE%/AppData/Local/gjc`)\n   - non-Windows: `~/.local/bin`\n3. Fall back to packaged `native/` and executable directory candidates.\n\n`getNativesDir()` uses `$XDG_DATA_HOME/gjc/natives` when `$XDG_DATA_HOME/gjc` exists; otherwise it uses `~/.gjc/natives`.\n\nIf a populated embedded addon manifest is present, it is also treated as a compiled-binary signal. The loader can extract the matching embedded `.node` into the versioned cache directory before candidate probing.\n\n### Failure modes\n\nLoader failures are explicit:\n\n- **Unsupported platform tag**: after failed probing, throws with supported platform list.\n- **No loadable candidate**: throws with all attempted paths and remediation hints.\n- **Embedded extraction errors**: directory/write failures are recorded and included in final load diagnostics if no candidate loads.\n\nThe current loader does not perform a separate post-`require` export validation pass.\n\n## Rust N-API module layer\n\n`crates/pi-natives/src/lib.rs` declares exported module ownership:\n\n- `appearance`\n- `ast`\n- `clipboard`\n- `fd`\n- `fs_cache`\n- `glob`\n- `glob_util`\n- `grep`\n- `highlight`\n- `html`\n- `image`\n- `keys`\n- `language`\n- `power`\n- `prof`\n- `projfs_overlay`\n- `ps`\n- `pty`\n- `shell`\n- `task`\n- `text`\n- `tokens`\n- `utils` (crate-private helpers)\n\nN-API exports are generated from Rust `#[napi]` functions/classes/objects/enums. Snake_case Rust names are exposed as camelCase JavaScript names unless explicitly configured by napi-rs.\n\n## Ownership boundaries\n\n- **Loader/package ownership (`packages/natives/native`, `packages/natives/scripts`)**\n  - runtime binary selection\n  - CPU variant selection and override handling\n  - compiled-binary embedded extraction\n  - generated TypeScript declarations and enum export patching\n- **Rust ownership (`crates/pi-natives/src`)**\n  - algorithmic and system-level implementation\n  - platform-native behavior and performance-sensitive logic\n  - N-API symbol implementation consumed directly by package callers\n- **Consumer ownership (`packages/coding-agent`, `packages/tui`)**\n  - user-facing policy and fallbacks that are not built into the native API\n  - higher-level rendering, artifact, shell-session, and command behavior\n\n## Runtime flow (high level)\n\n1. Consumer imports from `@gajae-code/natives`.\n2. `native/index.js` computes platform/arch/variant and candidate paths.\n3. Optional embedded binary extraction occurs for compiled distributions.\n4. The first `require(candidate)` that succeeds becomes the exported addon object.\n5. Generated enum objects are appended to `module.exports`.\n6. Caller invokes generated N-API functions/classes directly.\n\n## Glossary\n\n- **Native addon**: A `.node` binary loaded via Node-API (N-API).\n- **Platform tag**: Runtime tuple `platform-arch` (for example `darwin-arm64`).\n- **Variant**: x64 CPU-specific build flavor (`modern` AVX2, `baseline` fallback).\n- **Generated binding declaration**: `native/index.d.ts` emitted by napi-rs during `build-native.ts`.\n- **Compiled binary mode**: Runtime mode where the CLI is bundled and native addons are resolved from embedded/cache paths before package-local paths.\n- **Embedded addon**: Build artifact metadata and file references generated into `native/embedded-addon.js` so compiled binaries can extract matching `.node` payloads.\n",
 	"natives-binding-contract.md": "# Natives Binding Contract (JavaScript/TypeScript Side)\n\nThis document defines the JS/TS contract between `@gajae-code/natives` callers and the loaded N-API addon.\n\nCurrent package shape is direct-to-native: there is no `packages/natives/src/<module>` TypeScript wrapper layer. The public API is the generated `packages/natives/native/index.d.ts` declaration file, the CommonJS loader in `packages/natives/native/index.js`, and the Rust `#[napi]` exports in `crates/pi-natives/src`.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n- Rust modules under `crates/pi-natives/src/*.rs`\n\n## Contract model\n\nThe contract has three parts:\n\n1. **Generated runtime loader** (`native/index.js`)\n   - computes candidates and `require(...)`s the `.node` addon;\n   - exports the loaded addon object directly;\n   - appends enum objects generated by `scripts/gen-enums.ts`.\n2. **Generated TypeScript declarations** (`native/index.d.ts`)\n   - generated by napi-rs during `scripts/build-native.ts`;\n   - declares exported functions, classes, object interfaces, and native enums;\n   - is the package `types` entry.\n3. **Rust N-API exports** (`crates/pi-natives/src`)\n   - `#[napi]` functions/classes/objects/enums are the source of generated declarations and runtime symbols;\n   - snake_case Rust names become camelCase JavaScript names by napi-rs convention.\n\nThere is no current `NativeBindings` declaration-merging lifecycle and no `validateNative(...)` required-export list in the loader.\n\n## Public export surface organization\n\n`packages/natives/package.json` exposes the package root only:\n\n```json\n{\n  \"main\": \"./native/index.js\",\n  \"types\": \"./native/index.d.ts\",\n  \"exports\": {\n    \".\": {\n      \"types\": \"./native/index.d.ts\",\n      \"import\": \"./native/index.js\"\n    }\n  }\n}\n```\n\nConsumers in `packages/coding-agent` and `packages/tui` import directly from `@gajae-code/natives`.\n\n## JS API ↔ native export mapping (representative)\n\n| Category          | Public JS API                                                                                              | Rust source                                                 | Return style                  |\n| ----------------- | ---------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- | ----------------------------- |\n| Grep              | `grep(options, onMatch?)`                                                                                  | `grep.rs`                                                   | `Promise<GrepResult>`         |\n| Grep              | `search(content, options)`                                                                                 | `grep.rs`                                                   | `SearchResult`                |\n| Grep              | `hasMatch(content, pattern, ignoreCase?, multiline?)`                                                      | `grep.rs`                                                   | `boolean`                     |\n| Fuzzy path search | `fuzzyFind(options)`                                                                                       | `fd.rs`                                                     | `Promise<FuzzyFindResult>`    |\n| Glob              | `glob(options, onMatch?)`                                                                                  | `glob.rs`                                                   | `Promise<GlobResult>`         |\n| Glob cache        | `invalidateFsScanCache(path?)`                                                                             | `fs_cache.rs`                                               | `void`                        |\n| AST search/edit   | `astGrep(options)`, `astEdit(options)`                                                                     | `ast.rs`                                                    | `Promise<...>`                |\n| Shell             | `executeShell(options, onChunk?)`                                                                          | `shell.rs`                                                  | `Promise<ShellExecuteResult>` |\n| Shell             | `new Shell(options?)`, `shell.run(...)`, `shell.abort()`                                                   | `shell.rs`                                                  | class / promises              |\n| PTY               | `new PtySession()`, `start/write/resize/kill`                                                              | `pty.rs`                                                    | class / promises              |\n| Process           | `killTree(pid, signal)`, `listDescendants(pid)`                                                            | `ps.rs`                                                     | sync                          |\n| Keys              | `parseKey`, `matchesKey`, Kitty/legacy helpers                                                             | `keys.rs`                                                   | sync                          |\n| Text              | `wrapTextWithAnsi`, `truncateToWidth`, `sliceWithWidth`, `extractSegments`, `visibleWidth`                 | `text.rs`                                                   | sync                          |\n| Highlight         | `highlightCode`, `supportsLanguage`, `getSupportedLanguages`                                               | `highlight.rs`                                              | sync                          |\n| HTML              | `htmlToMarkdown(html, options?)`                                                                           | `html.rs`                                                   | `Promise<string>`             |\n| Image             | `PhotonImage`, `encodeSixel`                                                                               | `image.rs`                                                  | class / sync / promises       |\n| Clipboard         | `copyToClipboard`, `readImageFromClipboard`                                                                | `clipboard.rs`                                              | sync / promise                |\n| Tokens            | `countTokens(input, encoding?)`                                                                            | `tokens.rs`                                                 | sync                          |\n| System            | `detectMacOSAppearance`, `MacAppearanceObserver`, `MacOSPowerAssertion`, `getWorkProfile`, ProjFS helpers  | `appearance.rs`, `power.rs`, `prof.rs`, `projfs_overlay.rs` | mixed                         |\n\n## Sync vs async contract differences\n\nThe contract preserves Rust/N-API call style:\n\n- **Promise-returning exports** for worker-thread or async runtime work (`grep`, `glob`, `fuzzyFind`, `astGrep`, `astEdit`, `htmlToMarkdown`, shell/PTY runs, image parse/resize/encode, clipboard image read).\n- **Synchronous exports** for deterministic in-memory transforms/parsers or direct system calls (`search`, `hasMatch`, highlighting, text utilities, token counting, process queries, `copyToClipboard`, `encodeSixel`).\n- **Constructor exports** for stateful runtime objects (`Shell`, `PtySession`, `PhotonImage`, macOS observer/power handles).\n\nChanging sync ↔ async for an existing export is a breaking public API change because consumers call these exports directly.\n\n## Object and enum typing patterns\n\n### Object patterns\n\n`#[napi(object)]` Rust structs become TS interfaces, for example:\n\n- `GrepResult`, `SearchResult`, `GlobResult`, `FuzzyFindResult`\n- `ShellRunResult`, `ShellExecuteResult`, `PtyRunResult`, `MinimizerResult`\n- `AstFindResult`, `AstReplaceResult`\n- `System`/media payloads such as `ClipboardImage`, `WorkProfile`, `ParsedKittyResult`\n\nRuntime shape correctness is owned by napi-rs and the Rust implementation.\n\n### Enum patterns\n\nNative enums are represented in generated declarations and also appended to `module.exports` by `scripts/gen-enums.ts`, because the loader is hand-maintained CommonJS around the generated addon. Current enum objects include:\n\n- `AstMatchStrictness`\n- `Ellipsis`\n- `Encoding`\n- `FileType`\n- `GrepOutputMode`\n- `ImageFormat`\n- `KeyEventType`\n- `MacOSAppearance`\n- `SamplingFilter`\n\n## Error behavior and caveats\n\n- Addon load failure or unsupported platform throws during package import from `native/index.js`.\n- The loader does not verify the full export set after `require(...)`; stale or mismatched binaries surface as native load errors or missing members at use sites.\n- N-API conversion validates basic argument conversion, but TS optional fields do not guarantee semantic validity for untyped callers.\n- Numeric enum declarations do not prevent out-of-range numeric values from untyped callers unless the Rust function rejects them during conversion.\n- Callback exports use napi-rs `ThreadsafeFunction` shape: `(error: Error | null, value) => void`. Native code generally emits successful values; hard failures reject/throw through the owning call.\n\n## Maintainer checklist for binding changes\n\nWhen adding/changing an export, update all of:\n\n1. Rust `#[napi]` implementation in the owning `crates/pi-natives/src/<module>.rs`.\n2. `crates/pi-natives/src/lib.rs` if a new module is added.\n3. Any consumer imports/callsites in `packages/coding-agent` or `packages/tui`.\n4. Build output by running the natives build so `native/index.d.ts` and `native/index.js` stay in sync.\n5. `scripts/gen-enums.ts` if enum runtime export patching needs to change.\n\nDo not add a parallel TS wrapper convention unless the package design intentionally moves back to wrappers; current consumers depend on the direct generated API.\n",
@@ -30,7 +31,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"natives-text-search-pipeline.md": "# Natives Text/Search Pipeline\n\nThis document maps the `@gajae-code/natives` text/search/code surface from generated JS/TS exports to Rust N-API modules and back to JS result objects.\n\nTerminology follows `docs/natives-architecture.md`:\n\n- **Generated binding**: public API in `packages/natives/native/index.d.ts`.\n- **Rust module layer**: N-API exports in `crates/pi-natives/src/*`.\n- **Shared scan cache**: `fs_cache`-backed directory-entry cache used by discovery/search flows.\n\n## Implementation files\n\n- `packages/natives/native/index.d.ts`\n- `crates/pi-natives/src/grep.rs`\n- `crates/pi-natives/src/glob.rs`\n- `crates/pi-natives/src/glob_util.rs`\n- `crates/pi-natives/src/fs_cache.rs`\n- `crates/pi-natives/src/fd.rs`\n- `crates/pi-natives/src/ast.rs`\n- `crates/pi-natives/src/text.rs`\n- `crates/pi-natives/src/highlight.rs`\n- `crates/pi-natives/src/tokens.rs`\n\n## JS API ↔ Rust export mapping\n\n| JS API                                                                          | Rust export (`#[napi]`, snake_case -> camelCase) | Rust module    |\n| ------------------------------------------------------------------------------- | ------------------------------------------------ | -------------- |\n| `grep(options, onMatch?)`                                                       | `grep`                                           | `grep.rs`      |\n| `search(content, options)`                                                      | `search`                                         | `grep.rs`      |\n| `hasMatch(content, pattern, ignoreCase?, multiline?)`                           | `hasMatch`                                       | `grep.rs`      |\n| `fuzzyFind(options)`                                                            | `fuzzyFind`                                      | `fd.rs`        |\n| `glob(options, onMatch?)`                                                       | `glob`                                           | `glob.rs`      |\n| `invalidateFsScanCache(path?)`                                                  | `invalidateFsScanCache`                          | `fs_cache.rs`  |\n| `astGrep(options)`                                                              | `astGrep`                                        | `ast.rs`       |\n| `astEdit(options)`                                                              | `astEdit`                                        | `ast.rs`       |\n| `wrapTextWithAnsi(text, width, tabWidth)`                                       | `wrapTextWithAnsi`                               | `text.rs`      |\n| `truncateToWidth(text, maxWidth, ellipsis, pad, tabWidth)`                      | `truncateToWidth`                                | `text.rs`      |\n| `sliceWithWidth(line, startCol, length, strict, tabWidth)`                      | `sliceWithWidth`                                 | `text.rs`      |\n| `extractSegments(line, beforeEnd, afterStart, afterLen, strictAfter, tabWidth)` | `extractSegments`                                | `text.rs`      |\n| `visibleWidth(text, tabWidth)`                                                  | `visibleWidth`                                   | `text.rs`      |\n| `highlightCode(code, lang, colors)`                                             | `highlightCode`                                  | `highlight.rs` |\n| `supportsLanguage(lang)`                                                        | `supportsLanguage`                               | `highlight.rs` |\n| `getSupportedLanguages()`                                                       | `getSupportedLanguages`                          | `highlight.rs` |\n| `countTokens(input, encoding?)`                                                 | `countTokens`                                    | `tokens.rs`    |\n\n## Pipeline overview by subsystem\n\n## 1) Regex search (`grep`, `search`, `hasMatch`)\n\n### Input/options flow\n\n1. Callers invoke generated native exports directly; there is no package-local TS wrapper that renames `search` to `searchContent`.\n2. Rust option structs in `grep.rs` deserialize camelCase fields (`ignoreCase`, `maxCount`, `contextBefore`, `contextAfter`, `maxColumns`, `timeoutMs`).\n3. `grep` creates `CancelToken` from `timeoutMs` + `AbortSignal` and runs inside `task::blocking(\"grep\", ...)`.\n4. `search` and `hasMatch` operate on provided string/`Uint8Array` content and do not scan the filesystem.\n\n### Execution branches\n\n- **In-memory branch**\n  - `search` -> `search_sync` / search helpers over provided content bytes.\n  - `hasMatch` compiles/checks pattern against provided content and returns a boolean.\n  - No filesystem scan, no `fs_cache`.\n- **Single-file branch**\n  - `grep` resolves path, checks metadata is file, and searches that file.\n- **Directory branch**\n  - Optional cache lookup via `fs_cache::get_or_scan` when `cache: true`.\n  - Fresh scan via `fs_cache::force_rescan` when `cache: false`.\n  - Optional empty-result recheck when cached results are older than the empty-result recheck threshold.\n  - Entry filtering: file-only + optional glob filter (`glob_util`) + optional type filter mapping (`js`, `ts`, `rust`, etc.).\n\n### Search/collection semantics\n\n- Regex engine: `grep_regex::RegexMatcherBuilder` with `ignoreCase` and `multiline`.\n- Context resolution:\n  - `contextBefore/contextAfter` override legacy `context`.\n  - Non-content modes do not collect context.\n- Output modes:\n  - `content` -> one `GrepMatch` per hit.\n  - `count` and `filesWithMatches` map to count-style entries (`lineNumber=0`, `line=\"\"`, `matchCount` set).\n- Limits:\n  - Global `offset` and `maxCount` apply across files.\n  - Parallel path is used only when `maxCount` is unset and `offset == 0`; otherwise sequential path preserves deterministic global offset/limit semantics.\n\n### Result shaping back to JS\n\n- Rust `SearchResult`/`GrepResult` fields map to TS interfaces via N-API object conversion.\n- Counters are clamped before crossing N-API where needed.\n- `GrepResult.limitReached` is optional and emitted when true.\n- Streaming callback receives each shaped `GrepMatch` for content or count-style entries.\n\n### Failure behavior\n\n- `search` returns `SearchResult.error` for regex/search failures instead of throwing.\n- `grep` rejects on hard errors such as invalid path, invalid glob/regex, or cancellation timeout/abort.\n- `hasMatch` returns a boolean on success and throws on invalid pattern/UTF-8 conversion errors.\n- File open/search errors in multi-file scans are skipped per-file; scan continues.\n\n### Malformed regex handling\n\n`grep.rs` sanitizes braces before regex compile:\n\n- Invalid repetition-like braces are escaped (`{`/`}` -> `\\{`/`\\}`) when they cannot form `{N}`, `{N,}`, `{N,M}`.\n- This prevents common literal-template fragments (for example `${platform}`) from failing as malformed repetition.\n- Remaining invalid regex syntax still returns a regex error.\n\n## 2) File discovery (`glob`) and fuzzy path search (`fuzzyFind`)\n\n`glob` and `fuzzyFind` share `fs_cache` scans; matching logic differs.\n\n### `glob` flow\n\n1. Caller passes `GlobOptions` directly. `pattern` and `path` are required in the generated type.\n2. Rust resolves the search path and compiles pattern via `glob_util::compile_glob`.\n3. Entry source:\n   - `cache=true` -> `get_or_scan` + optional stale-empty `force_rescan`.\n   - `cache=false` -> `force_rescan(..., store=false)` (fresh only).\n4. Filtering:\n   - skip `.git` always;\n   - skip `node_modules` unless requested (`includeNodeModules`) or pattern mentions `node_modules`;\n   - apply glob match;\n   - apply file-type filter; symlink `file`/`dir` filters resolve target metadata.\n5. Optional sort by mtime descending (`sortByMtime`) before truncating to `maxResults`.\n\n### `fuzzyFind` flow\n\n1. Rust implementation lives in `fd.rs`; generated export is `fuzzyFind`.\n2. Shared scan source from `fs_cache` with the same cache/no-cache split and stale-empty recheck policy.\n3. Scoring:\n   - exact / starts-with / contains / subsequence-based fuzzy score;\n   - separator/punctuation-normalized scoring path;\n   - directory bonus and deterministic tie-break (`score desc`, then `path asc`).\n4. Symlink entries are excluded from fuzzy results.\n\n### Failure behavior\n\n- Invalid glob pattern returns an error from `glob_util::compile_glob`.\n- Search root must resolve to an existing directory for directory discovery flows.\n- Cancellation/timeouts propagate as abort errors via `CancelToken::heartbeat()` checks in loops.\n\n### Malformed glob handling\n\n`glob_util::build_glob_pattern` is tolerant:\n\n- normalizes `\\` to `/`,\n- auto-prefixes simple recursive patterns with `**/` when `recursive=true`,\n- auto-closes unbalanced `{...` alternation groups before compile.\n\n## 3) AST search/edit (`astGrep`, `astEdit`)\n\n`ast.rs` exposes syntax-aware code search and rewrite operations.\n\n- `astGrep(options)` returns matches with byte/line/column coordinates and optional metavariable bindings.\n- `astEdit(options)` returns replacement changes, per-file counts, searched/touched file counts, parse errors, and whether edits were applied.\n- `dryRun` defaults to true for edit options in the generated documentation.\n- Options include language override, path/glob/selector, strictness, limits, parse-error policy, `signal`, and `timeoutMs`.\n\nThese exports are direct native APIs used by tooling; they are not mediated by a TS wrapper in `packages/natives`.\n\n## 4) Shared scan/cache lifecycle (`fs_cache`)\n\n`fs_cache` stores scan results as normalized relative entries (`path`, `fileType`, optional `mtime`) keyed by:\n\n- canonical search root,\n- `include_hidden`,\n- `use_gitignore`.\n\n### Cache state transitions\n\n1. **Miss / disabled**\n   - TTL is `0` or key absent/expired -> fresh collection.\n2. **Hit**\n   - Entry age is within TTL -> return cached entries + `cache_age_ms`.\n3. **Stale-empty recheck**\n   - If query yields zero matches and cache age exceeds the empty-result threshold, force one rescan.\n4. **Invalidation**\n   - `invalidateFsScanCache(path?)`:\n     - no arg: clear all keys;\n     - path arg: remove keys for roots affected by that path.\n\n### Stale-result tradeoff\n\n- Cache favors low-latency repeated scans over immediate consistency.\n- TTL window can return stale positives/negatives.\n- Empty-result recheck reduces stale negatives for older cached scans at the cost of one extra scan.\n- Explicit invalidation is the intended correctness hook after file mutations.\n\n## 5) ANSI text utilities (`text`)\n\nThese are pure, in-memory utilities.\n\n### Boundaries and responsibilities\n\n- `text.rs` owns terminal-cell semantics:\n  - ANSI sequence parsing,\n  - grapheme-aware width and slicing,\n  - wrap/truncate/sanitize behavior,\n  - explicit tab-width parameter on width-sensitive APIs.\n- `grep.rs` line truncation (`maxColumns`) is separate:\n  - simple character-boundary truncation of matched lines with `...`,\n  - not ANSI-state-preserving and not terminal-cell width aware.\n\n### Key behaviors\n\n- `wrapTextWithAnsi`: wraps by visible width, carries active SGR codes across wrapped lines.\n- `truncateToWidth`: visible-cell truncation with ellipsis policy (`Unicode`, `Ascii`, `Omit`), optional right padding.\n- `sliceWithWidth`: column slicing with optional strict width enforcement.\n- `extractSegments`: extracts before/after segments around an overlay while restoring ANSI state for the `after` segment.\n- `sanitizeText` (ANSI/control/surrogate stripping with line-ending normalization) no longer lives in `text.rs`; it moved to `@gajae-code/utils` as a pure-JS implementation in `packages/utils/src/sanitize-text.ts`. The native binding was removed in the same change because the JS version was competitive on the benchmarked workloads, and keeping a Rust copy forced every caller (including `pi-utils`) to pull in `@gajae-code/natives`.\n- `visibleWidth`: counts visible terminal cells using caller-supplied tab width.\n\n### Failure behavior\n\nText functions generally return deterministic transformed output; errors are limited to N-API argument/string conversion boundaries.\n\n## 6) Syntax highlighting (`highlight`)\n\n`highlight.rs` is pure transformation; it does not use the filesystem scan cache.\n\n### Flow\n\n1. Caller passes `code`, optional `lang`, and ANSI color palette.\n2. Rust resolves syntax by token/name lookup, extension lookup, alias table fallback, then plain-text fallback.\n3. Each line is parsed with syntect `ParseState` and scope stack.\n4. Scopes map to semantic color categories and ANSI color codes are injected/reset.\n\n### Failure behavior\n\n- Per-line parse failure does not fail the call: that line is appended unhighlighted and processing continues.\n- Unknown/unsupported language falls back to plain text syntax.\n\n## 7) Token counting (`tokens`)\n\n`countTokens(input, encoding?)` is an in-memory utility.\n\n- `input` may be a single string or an array of strings.\n- Arrays return one aggregate count and are encoded in parallel in Rust.\n- Default encoding is `O200kBase`; `Cl100kBase` is also available.\n- The implementation uses ordinary tokenization, not special-token handling.\n\n## Pure utility vs filesystem-dependent flows\n\n| Flow                         | Filesystem access | Shared cache         | Notes                                         |\n| ---------------------------- | ----------------- | -------------------- | --------------------------------------------- |\n| `search` / `hasMatch`        | No                | No                   | regex on provided bytes/string only           |\n| `text` module functions      | No                | No                   | ANSI/width/sanitization only                  |\n| `highlight` module functions | No                | No                   | syntax + ANSI coloring only                   |\n| `countTokens`                | No                | No                   | tokenization only                             |\n| `astGrep` / `astEdit`        | Yes               | No                   | syntax-aware file search/edit                 |\n| `glob`                       | Yes               | Optional             | directory scans + glob filtering              |\n| `fuzzyFind`                  | Yes               | Optional             | directory scans + fuzzy scoring               |\n| `grep` (file/dir path)       | Yes               | Optional in dir mode | ripgrep over files, optional filters/callback |\n\n## End-to-end lifecycle summary\n\n1. Caller invokes generated native export with typed options.\n2. Rust validates/normalizes options and builds matcher/search config.\n3. For filesystem flows, entries are scanned (cache hit/miss/rescan where applicable) then filtered/scored/searched.\n4. Worker loops periodically call cancel heartbeat; timeout/abort can terminate execution.\n5. Rust shapes outputs into N-API objects (`lineNumber`, `matchCount`, `limitReached`, etc.).\n6. Generated bindings return typed JS objects and optional per-match callbacks for `grep`/`glob`.\n",
 	"non-compaction-retry-policy.md": "# Non-compaction auto-retry policy\n\nThis document describes the standard API-error retry path in `AgentSession`.\n\nIt explicitly excludes context-overflow recovery via auto-compaction. Overflow is handled by compaction logic and is documented separately in [`compaction.md`](../docs/compaction.md).\n\n## Implementation files\n\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`../src/config/settings-schema.ts`](../packages/coding-agent/src/config/settings-schema.ts)\n- [`../src/modes/controllers/event-controller.ts`](../packages/coding-agent/src/modes/controllers/event-controller.ts)\n- [`../src/modes/rpc/rpc-mode.ts`](../packages/coding-agent/src/modes/rpc/rpc-mode.ts)\n- [`../src/modes/rpc/rpc-client.ts`](../packages/coding-agent/src/modes/rpc/rpc-client.ts)\n- [`../src/modes/rpc/rpc-types.ts`](../packages/coding-agent/src/modes/rpc/rpc-types.ts)\n\n## Scope boundary vs compaction\n\nRetry and compaction are checked from the same `agent_end` path, but they are intentionally separated:\n\n1. `agent_end` inspects the last assistant message.\n2. `#isRetryableError(...)` runs first.\n3. If retry is initiated, compaction checks are skipped for that turn.\n4. Context-overflow errors are hard-excluded from retry classification (`isContextOverflow(...)` short-circuits retry).\n5. Overflow therefore falls through to `#checkCompaction(...)` instead of standard retry.\n\nSo: overload/rate/server/network-style failures use this retry policy; context-window overflow uses compaction recovery.\n\n## Retry classification\n\n`#isRetryableError(...)` requires all of the following:\n\n- assistant `stopReason === \"error\"`\n- `errorMessage` exists\n- message is **not** context overflow\n- `errorMessage` matches transient transport/envelope patterns or `isUsageLimitError(...)`\n\nCurrent retryable inputs are regex/string-classified:\n\n- transient transport/envelope failures, including Anthropic stream-envelope failures before `message_start`\n- overloaded/provider-returned-error wording\n- rate limit / usage limit / too many requests\n- HTTP-like server classes: 429, 500, 502, 503, 504\n- service unavailable / server/internal error\n- provider-suggested retry wording, including OpenAI `retry your request` failures\n- network/connection/socket failures, refused/closed connections, upstream connect/reset-before-headers, socket hang up, timeout/timed out, fetch failed, terminated, retry delay wording, and unexpected socket close messages\n\nThis is string-pattern classification, not typed provider error codes.\n\n## Retry lifecycle and state transitions\n\nSession state used by retry:\n\n- `#retryAttempt: number` (`0` means idle)\n- `#retryPromise: Promise<void> | undefined` (tracks in-progress retry lifecycle)\n- `#retryResolve: (() => void) | undefined` (resolves `#retryPromise`)\n- `#retryAbortController: AbortController | undefined` (cancels backoff sleep)\n\nFlow (`#handleRetryableError`):\n\n1. Read `retry` settings group.\n2. If `retry.enabled === false`, stop immediately (`false`, no retry started).\n3. Increment `#retryAttempt`.\n4. Create `#retryPromise` once (first attempt in a chain).\n5. If attempt exceeded `retry.maxRetries`, emit final failure event and stop.\n6. Compute base delay: `retry.baseDelayMs * 2^(attempt-1)`.\n7. For usage-limit errors, parse retry hints and call auth storage (`markUsageLimitReached(...)`); if credential switching succeeds, force delay to `0`, otherwise use a larger retry-after/backoff hint when present.\n8. If no credential switch occurred, suppress the current model selector for cooldown, try configured retry model fallback chains, and force delay to `0` on model switch.\n9. Emit `auto_retry_start`.\n10. Remove the trailing assistant error message from agent runtime state (kept in persisted session history).\n11. Sleep with abort support.\n12. Schedule `agent.continue()` through the post-prompt task scheduler (`delayMs: 1`) for the same prompt generation.\n\n### What resets retry counters\n\n`#retryAttempt` resets to `0` in these cases:\n\n- first successful non-error, non-aborted assistant message after retries started (emits `auto_retry_end { success: true }`)\n- retry cancellation during backoff sleep\n- max retries exceeded path\n\n`#retryPromise` resolves/clears when retry chain ends (success, cancellation, or max-exceeded), via `#resolveRetry()`.\n\n## Backoff and max-attempt semantics\n\nSettings:\n\n- `retry.enabled` (default `true`)\n- `retry.maxRetries` (default `3`)\n- `retry.baseDelayMs` (default `2000`)\n- `retry.maxDelayMs` (default `300000`)\n- `retry.requestMaxRetries` (default `5`) — provider request retries before a stream is established; counts retries, not the initial request\n- `retry.streamMaxRetries` (default `5`) — provider stream replay retries for replay-safe transient stream failures; counts retries, not the initial stream attempt\n\nAttempt numbering:\n\n- attempt counter is incremented before max-check\n- start events use current attempt (1-based)\n- max-exceeded end event reports `attempt: this.#retryAttempt - 1` (last attempted retry count)\n\nBackoff sequence with default settings:\n\n- attempt 1: 2000 ms\n- attempt 2: 4000 ms\n- attempt 3: 8000 ms\n\nDelay override inputs can come from parsed retry headers (`retry-after-ms`, `retry-after`, `x-ratelimit-reset-ms`, `x-ratelimit-reset`) or usage-limit backoff. Credential/model fallback switches set delay to `0`; otherwise parsed hints can extend the exponential local delay.\n\n## Abort mechanics\n\n### Explicit retry abort\n\n`abortRetry()`:\n\n- aborts `#retryAbortController` (if present)\n- resolves retry promise (`#resolveRetry()`) so awaiters are unblocked\n\nIf abort hits while sleeping, catch path emits:\n\n- `auto_retry_end { success: false, finalError: \"Retry cancelled\" }`\n- resets attempt/controller\n\n### Global operation abort interaction\n\n`abort()` calls `abortRetry()` before aborting the active agent stream. This guarantees retry backoff is cancelled when user issues a general abort.\n\n### TUI interaction\n\nOn `auto_retry_start`, EventController:\n\n- swaps `Esc` handler to `session.abortRetry()`\n- renders loader text: `Retrying (attempt/maxAttempts) in Ns… (esc to cancel)`\n\nOn `auto_retry_end`, it restores prior `Esc` handler and clears loader state.\n\n## Streaming and prompt completion behavior\n\n`prompt()` ultimately waits on `#waitForRetry()` after `agent.prompt(...)` returns.\n\nEffect:\n\n- a prompt call does not fully resolve until any started retry chain finishes (success/failure/cancel)\n- retry lifecycle is part of one logical prompt execution boundary\n\nThis prevents callers from treating a retrying turn as complete too early.\n\n## Controls: settings and RPC\n\n### Configuration knobs\n\nDefined in settings schema under retry group:\n\n- `retry.enabled`\n- `retry.maxRetries`\n- `retry.baseDelayMs`\n- `retry.fallbackChains`\n- `retry.fallbackRevertPolicy` (`\"cooldown-expiry\"` by default; `\"never\"` disables automatic restoration)\n\nProgrammatic toggles in session:\n\n- `setAutoRetryEnabled(enabled)` writes `retry.enabled`\n- `autoRetryEnabled` reads `retry.enabled`\n- `isRetrying` reports whether retry lifecycle promise is active\n\n### RPC controls\n\nRPC command surface:\n\n- `set_auto_retry` → `session.setAutoRetryEnabled(command.enabled)`\n- `abort_retry` → `session.abortRetry()`\n\nClient helpers:\n\n- `RpcClient.setAutoRetry(enabled)`\n- `RpcClient.abortRetry()`\n\nBoth commands return success responses; retry progress/failure details come from streamed session events, not command response payloads.\n\n## Event emission and failure surfacing\n\nSession-level retry events:\n\n- `auto_retry_start { attempt, maxAttempts, delayMs, errorMessage }`\n- `auto_retry_end { success, attempt, finalError? }`\n- `retry_fallback_applied { from, to, role }`\n- `retry_fallback_succeeded { model, role }`\n\nPropagation:\n\n- emitted through `AgentSession.subscribe(...)`\n- forwarded to extension runner as extension events\n- in RPC mode, forwarded directly as JSON event objects (`session.subscribe(event => output(event))`)\n- in TUI, consumed by `EventController` for loader/error UI\n\nFinal failure surfacing:\n\n- On max-exceeded or cancellation, `auto_retry_end.success === false`\n- TUI shows: `Retry failed after N attempts: <finalError>`\n- Extensions/hooks receive `auto_retry_end` with same fields\n- RPC consumers receive same event object on stdout stream\n\n## Permanent stop conditions\n\nRetry stops and will not auto-continue when any of these occur:\n\n- `retry.enabled` is false\n- error is not retry-classified\n- error is context overflow (delegated to compaction path)\n- max retries exceeded\n- user cancels retry (`abort_retry` or `Esc` during retry loader)\n- global abort (`abort`) cancels retry first\n\nA new retry chain can still start later on a future retryable error after counters reset.\n\n## Operational caveats\n\n- Classification is regex text matching; provider-specific structured errors are not used here.\n- Retry strips the failing assistant error from **runtime context** before re-continue, but session history still keeps that error entry.\n- `RpcSessionState` currently exposes `autoCompactionEnabled` but not an `autoRetryEnabled` field; RPC callers must track their own toggle state or query settings through other APIs.\n- Model fallback changes append temporary `model_change` entries and may later restore the primary model when its cooldown expires, depending on `retry.fallbackRevertPolicy`.\n\n## Provider request/stream retry budgets\n\nThe provider budgets are deliberately separate from session auto-retry:\n\n```yaml\nretry:\n  requestMaxRetries: 4\n  streamMaxRetries: 100\n```\n\n`requestMaxRetries` maps to provider SDK/fetch retry counts for request setup failures such as retryable 5xx/408/429/network errors. `streamMaxRetries` maps to provider-specific stream replay loops that are safe to repeat without duplicating visible assistant output. Providers that cannot safely replay a stream continue to surface the terminal error so the session-level auto-retry layer can decide whether to retry the turn.\n\nFail-fast cases stay fail-fast: invalid credentials (after any credential-refresh path is exhausted), unsupported model/provider configuration, malformed requests, context overflow, explicit user aborts, and permanent quota failures are not treated as transient provider budget candidates.\n",
 	"notebook-tool-runtime.md": "# Notebook tool runtime internals\n\nThis document describes the current `notebook` tool implementation and its relationship to the kernel-backed Python runtime.\n\nThe critical distinction: **`notebook` is a JSON notebook editor, not a notebook executor**. It edits `.ipynb` cell sources directly; it does not start or talk to a Python kernel.\n\n## Implementation files\n\n- [`src/tools/notebook.ts`](../packages/coding-agent/src/tools/notebook.ts)\n- [`src/eval/py/executor.ts`](../packages/coding-agent/src/eval/py/executor.ts)\n- [`src/eval/py/kernel.ts`](../packages/coding-agent/src/eval/py/kernel.ts)\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts)\n- [`src/tools/eval.ts`](../packages/coding-agent/src/tools/eval.ts)\n\n## 1) Runtime boundary: editing vs executing\n\n## `notebook` tool (`src/tools/notebook.ts`)\n\n- Supports `action: edit | insert | delete` on a `.ipynb` file.\n- Resolves path relative to session CWD (`resolveToCwd`).\n- Loads notebook JSON, validates `cells` array, validates `cell_index` bounds.\n- Applies source edits in-memory and writes full notebook JSON back with `JSON.stringify(notebook, null, 1)`.\n- Returns textual summary + structured `details` (`action`, `cellIndex`, `cellType`, `totalCells`, `cellSource`).\n\nNo kernel lifecycle exists in this tool:\n\n- no gateway acquisition\n- no kernel session ID\n- no `execute_request`\n- no stream chunks from kernel channels\n- no rich display capture (`image/png`, JSON display, status MIME)\n\n## Notebook-like execution path (`src/tools/eval.ts` + `src/eval/py/*`)\n\nWhen the agent needs to run cell-style Python code (sequential cells, persistent state, rich displays), that goes through the **`eval` tool** with `language: \"python\"`, not `notebook`.\n\nThat path is where kernel modes, restart/cancel behavior, chunk streaming, and output artifact truncation live.\n\n## 2) Notebook cell handling semantics (`notebook` tool)\n\n## Source normalization\n\n`content` is split into `source: string[]` with newline preservation:\n\n- each non-final line keeps trailing `\\n`\n- final line has no forced trailing newline\n\nThis mirrors notebook JSON conventions and avoids accidental line concatenation on later edits.\n\n## Action behavior\n\n- `edit`\n  - replaces `cells[cell_index].source`\n  - preserves existing `cell_type`\n- `insert`\n  - inserts at `[0..cellCount]`\n  - `cell_type` defaults to `code`\n  - code cells initialize `execution_count: null` and `outputs: []`\n  - markdown cells initialize only `metadata` + `source`\n- `delete`\n  - removes `cells[cell_index]`\n  - returns removed `source` in details for renderer preview\n\n## Error surfaces\n\nHard failures are thrown for:\n\n- missing notebook file\n- invalid JSON\n- missing/non-array `cells`\n- out-of-range index (insert and non-insert have different valid ranges)\n- missing `content` for `edit`/`insert`\n\nThese become `Error:` tool responses upstream; renderer uses notebook path + formatted error text.\n\n## 3) Kernel session semantics (where they actually exist)\n\nKernel semantics are implemented in `executePython` / `PythonKernel` and apply to the Python backend of the `eval` tool.\n\n## Modes\n\n`PythonKernelMode`:\n\n- `session` (default)\n  - kernels cached in `kernelSessions` map\n  - max 4 sessions; oldest evicted on overflow\n  - idle/dead cleanup every 30s, timeout after 5 minutes\n  - per-session queue serializes execution (`session.queue`)\n- `per-call`\n  - creates kernel for request\n  - executes\n  - always shuts down kernel in `finally`\n\n## Reset behavior\n\n`eval` passes `reset` only for the first cell in a multi-cell Python call; later cells always run with `reset: false`.\n\n## Kernel death / restart / retry\n\nIn session mode (`withKernelSession`):\n\n- dead kernel detected by heartbeat (`kernel.isAlive()` check every 5s) or execute failure.\n- pre-run dead state triggers `restartKernelSession`.\n- execute-time crash path retries once: restart kernel, rerun handler.\n- `restartCount > 1` in same session throws `Python kernel restarted too many times in this session`.\n\nStartup retry behavior:\n\n- shared gateway kernel creation retries once on `SharedGatewayCreateError` with HTTP 5xx.\n\nResource exhaustion recovery:\n\n- detects `EMFILE`/`ENFILE`/\"Too many open files\" style failures\n- clears tracked sessions\n- calls `shutdownSharedGateway()`\n- retries kernel session creation once\n\n## 4) Environment/session variable injection\n\nKernel startup receives the optional session file path from executor:\n\n- `GJC_SESSION_FILE` (session state file path)\n\n`PythonKernel.#initializeKernelEnvironment(...)` then runs init script inside kernel to:\n\n- `os.chdir(cwd)`\n- inject env entries into `os.environ`\n- prepend cwd to `sys.path` if missing\n\nImplication:\n\n- prelude helpers that read session context rely on this env var in Python process state.\n\n## 5) Streaming/chunk and display handling (kernel-backed path)\n\nThe kernel client processes Jupyter protocol messages per execution:\n\n- `stream` -> text chunk to `onChunk`\n- `execute_result` / `display_data` ->\n  - display text chosen by MIME precedence: `text/markdown` > `text/plain` > converted `text/html`\n  - structured outputs captured separately:\n    - `application/json` -> `{ type: \"json\" }`\n    - `image/png` -> `{ type: \"image\" }`\n    - `application/x-gjc-status` -> `{ type: \"status\" }` (no text emission)\n- `error` -> traceback text pushed to chunk stream + structured error metadata\n- `input_request` -> emits stdin warning text, sends empty `input_reply`, marks stdin requested\n- completion waits for both `execute_reply` and kernel `status=idle`\n\nCancellation/timeout:\n\n- abort signal triggers `interrupt()` (REST `/interrupt` + control-channel `interrupt_request`)\n- result marks `cancelled=true`\n- timeout path annotates output with `Command timed out after <n> seconds`\n\n## 6) Truncation and artifact behavior\n\n`OutputSink` in `src/session/streaming-output.ts` is used by kernel execution paths (`executeWithKernel`):\n\n- sanitizes every chunk (`sanitizeText`)\n- tracks total/output lines and bytes\n- optional artifact spill file (`artifactPath`, `artifactId`)\n- when in-memory buffer exceeds threshold (`DEFAULT_MAX_BYTES` unless overridden):\n  - marks truncated\n  - keeps tail bytes in memory (UTF-8 safe boundary)\n  - can spill full stream to artifact sink\n\n`dump()` returns:\n\n- visible output text (possibly tail-truncated)\n- truncation flag + counts\n- artifact ID (for `artifact://<id>` references)\n\n`eval` converts this metadata into result truncation notices and TUI warnings.\n\n`notebook` tool does **not** use `OutputSink`; it has no stream/artifact truncation pipeline because it does not execute code.\n\n## 7) Renderer assumptions and formatting\n\n## Notebook renderer (`notebookToolRenderer`)\n\n- call view: status line with action + notebook path + cell/type metadata\n- result view:\n  - success summary derived from `details`\n  - `cellSource` rendered via `renderCodeCell`\n  - markdown cells set language hint `markdown`; other cells have no explicit language override\n  - collapsed code preview limit is `PREVIEW_LIMITS.COLLAPSED_LINES * 2`\n  - supports expanded mode via shared render options\n  - uses render cache keyed by width + expanded state\n\nError rendering assumption:\n\n- if first text content starts with `Error:`, renderer formats as notebook error block.\n\n## Python renderer (for actual execution output)\n\nKernel-backed execution rendering expects:\n\n- per-cell status transitions (`pending/running/complete/error`)\n- optional structured status event section\n- optional JSON output trees\n- truncation warnings + optional `artifact://<id>` pointer\n\nThis renderer behavior is unrelated to `notebook` JSON editing results except that both reuse shared TUI primitives.\n\n## 8) Divergence from eval Python backend behavior\n\nIf \"plain Python execution\" means the `eval` tool with `language: \"python\"`:\n\n- `eval` executes code in a kernel, persists state by mode, streams chunks, captures rich displays, handles interrupts/timeouts, and supports output truncation/artifacts.\n- `notebook` performs deterministic notebook JSON mutations only; no execution, no kernel state, no chunk stream, no display outputs, no artifact pipeline.\n\nIf a workflow needs both:\n\n1. edit notebook source with `notebook`\n2. execute code cells via `eval` with `language: \"python\"` (manually passing code), not through `notebook`\n\nCurrent implementation does not provide a single tool that both mutates `.ipynb` and executes notebook cells through kernel context.\n",
-	"onboarding-packet.md": "# Gajae-Code Onboarding Packet\n\nThis packet is a docs-only, public-safe context seed for the `gajae-code` repository as inspected on 2026-06-01. It is intentionally a no-new-skill artifact: not a new workflow skill, command, agent, configuration surface, issue template, or runtime behavior.\n\n## Purpose in one paragraph\n\nGajae-Code is the `gjc` coding-agent CLI and supporting monorepo. The product centers on a small public workflow loop: clarify with `deep-interview`, plan with `ralplan`, execute and verify through `ultragoal`, and use `team` only when parallel tmux workers are useful. The main product package is `packages/coding-agent/`; supporting packages provide LLM/provider access, agent runtime, TUI rendering, native helpers, stats, utilities, benchmarks, and Python RPC/bot integrations.\n\n## Fixed public surface\n\nKeep this invariant front-and-center when onboarding to the repo:\n\n- Default workflow skills: `deep-interview`, `ralplan`, `team`, `ultragoal`.\n- Public role agents: `executor`, `architect`, `planner`, `critic`.\n- Bundled default workflow skill sources live under `packages/coding-agent/src/defaults/gjc/skills/`.\n- Bundled role-agent prompt sources live under `packages/coding-agent/src/prompts/agents/`.\n- Runtime state, specs, plans, goals, team state, and local overrides belong under `.gjc/` for the product and `.omx/` only for this agent-run orchestration.\n\nDo not add a fifth default skill, fifth public role agent, new command, new config surface, or feature-intake behavior unless that product decision has already been made and the default-surface gates are updated.\n\n## Primary entrypoints\n\n| Area             | Repo-relative path                                   | Why it matters                                                                                    |\n| ---------------- | ---------------------------------------------------- | ------------------------------------------------------------------------------------------------- |\n| CLI bootstrap    | `packages/coding-agent/src/cli.ts`                   | Registers top-level CLI commands and routes default launch behavior.                              |\n| Session launch   | `packages/coding-agent/src/main.ts`                  | Converts CLI/runtime settings into agent-session creation and mode dispatch.                      |\n| Agent assembly   | `packages/coding-agent/src/sdk.ts`                   | Loads settings, default skills, rules, tools, auth/model state, system prompt, and agent runtime. |\n| Built-in tools   | `packages/coding-agent/src/tools/index.ts`           | Registers file, shell, edit, search, browser, task/subagent, memory, and related tools.           |\n| Default skills   | `packages/coding-agent/src/defaults/gjc-defaults.ts` | Embeds and installs the four default workflow skills plus deep-interview fragments.               |\n| Role agents      | `packages/coding-agent/src/task/agents.ts`           | Embeds bundled task-agent prompts; tests enforce public role-agent expectations.                  |\n| Product overview | `README.md`                                          | Explains installation, product story, fixed workflow surface, and development entry commands.     |\n| Architecture map | `docs/codebase-overview.md`                          | Public package map and runtime-flow reference.                                                    |\n\n## Package map\n\n- `packages/coding-agent/` — main `gjc` CLI, workflows, session runtime, tool registry, discovery, settings, prompts, and tests.\n- `packages/ai/` — provider/model boundary, streaming, auth, model registry, retries, and provider integrations.\n- `packages/agent/` — stateful agent loop and append-only context runtime.\n- `packages/tui/` — terminal UI framework and rendering primitives.\n- `packages/natives/` plus `crates/*` — native helpers, Rust/N-API bindings, shell/PTY, text search, AST, filesystem, and media utilities.\n- `packages/utils/` — shared TypeScript utilities, logging, formatting, process helpers, JSON/frontmatter, and sanitization.\n- `packages/stats/` — local observability dashboard and session/model usage aggregation.\n- `packages/swarm-extension/` — optional YAML/DAG multi-agent extension outside the fixed default workflow surface.\n- `packages/typescript-edit-benchmark/` — TypeScript edit benchmark tooling.\n- `python/gjc-rpc/` — Python client for `gjc --mode rpc`.\n- `python/robogjc/` — GitHub triage/fix bot that drives `gjc --mode rpc`; this subtree has its own `AGENTS.md`.\n\n## Build, test, and validation commands\n\nPrefer targeted checks first, then broader checks when code changes justify them. For this docs-only packet, lightweight validation is enough.\n\n| Command                                                               | Scope                               | When to use                                                                 |\n| --------------------------------------------------------------------- | ----------------------------------- | --------------------------------------------------------------------------- |\n| `bun install`                                                         | Workspace dependencies              | Initial local setup.                                                        |\n| `bun run install:defaults`                                            | Local default install               | Installs source-bundled default workflow definitions for local development. |\n| `bun packages/coding-agent/src/cli.ts --help`                         | CLI smoke/discovery                 | Fast source checkout CLI sanity check.                                      |\n| `bun run check:ts`                                                    | Type/lint/default UI checks         | Broad TypeScript validation; heavier than docs-only changes.                |\n| `bun run test`                                                        | Full TS + Rust tests                | Broad regression check; use for runtime/product changes.                    |\n| `bun run ci:test:smoke`                                               | CLI version/help/stats worker smoke | Useful before release/install changes.                                      |\n| `bun scripts/check-visible-definitions.ts`                            | Default surface gate                | Required after workflow-definition changes.                                 |\n| `bun scripts/verify-g002-gates.ts`                                    | Rebrand/default-surface gate        | Required after workflow-definition or public-surface changes.               |\n| `bun scripts/rebrand-inventory.ts --strict`                           | Rebrand inventory gate              | Required after workflow-definition or public-surface changes.               |\n| `bun test packages/coding-agent/test/default-gjc-definitions.test.ts` | Four-skills/four-agents contract    | Required after default workflow/agent surface changes.                      |\n\nRepository rule: do not run `tsc` or `npx tsc`; use the Bun scripts above.\n\n## Danger zones\n\n- **Default surface expansion:** `packages/coding-agent/src/defaults/gjc/skills/`, `packages/coding-agent/src/defaults/gjc-defaults.ts`, `packages/coding-agent/src/prompts/agents/`, and model-assignment tests are contract-heavy. Changes here can accidentally alter the fixed four-skills/four-agents shape.\n- **CLI commands:** `packages/coding-agent/src/cli.ts` and `packages/coding-agent/src/commands/` define visible behavior. Adding commands or aliases is a product-surface change.\n- **Runtime/session assembly:** `packages/coding-agent/src/main.ts`, `packages/coding-agent/src/sdk.ts`, discovery, settings, tools, and system-prompt paths can affect every session.\n- **TUI/logging:** Avoid `console.log`, `console.warn`, or `console.error` inside `packages/coding-agent/`; use the centralized logger to avoid corrupting TUI rendering.\n- **Secrets/auth/config:** Keep `docs/secrets.md`, auth broker/gateway code, settings, and environment-variable docs public-safe. Do not expose tokens or private infrastructure.\n- **Native/Rust build:** `packages/natives/` and `crates/*` can require platform-specific toolchains and CI artifact behavior.\n- **Python bot subtree:** `python/robogjc/` has its own local instructions and trust boundaries.\n- **Generated model data:** Do not edit `packages/ai/src/models.json` directly; update generators/descriptors/resolvers and regenerate with `bun --cwd=packages/ai run generate-models`.\n\n## Unknowns worth preserving\n\n- Which onboarding packet shape will be most useful for future `gjc` context ingestion is still an experiment, not a product contract.\n- Public issue #158 / `gajae-deep-onboarding` context is summarized only from the user-provided prompt in this run; this packet does not add issue intake or feature workflow behavior.\n- Full CI may depend on runner/system dependencies and native artifacts; docs-only changes usually do not need the full matrix locally.\n- Some packages contain internal or hidden utility prompts/agents beyond the four public role agents. Public-facing docs should keep the four-role contract clear.\n\n## First safe tasks for a new contributor or agent\n\n1. Read `README.md`, `docs/codebase-overview.md`, and this packet.\n2. Run `bun packages/coding-agent/src/cli.ts --help` for a fast CLI surface check after dependencies are installed.\n3. For docs-only edits, run formatting/check commands that do not mutate runtime behavior.\n4. For default-surface edits, run the four required gates listed in the command table before claiming completion.\n5. For package code edits, start with the nearest package test, then escalate to `bun run check:ts` or `bun run test` as risk increases.\n6. Before changing `packages/coding-agent/src/defaults/gjc/skills/`, `packages/coding-agent/src/prompts/agents/`, `packages/coding-agent/src/commands/`, or config/settings paths, write down whether the change alters public surface area.\n\n## Context seed checklist\n\nA future agent can use this packet as context if it preserves these constraints:\n\n- Keep changes public-safe and repo-relative.\n- Prefer docs and tests over new runtime abstractions for onboarding experiments.\n- Treat the fixed four-skills/four-agents shape as a product constraint.\n- Verify claims with repo files before summarizing them.\n- Report validation evidence and caveats instead of implying hidden automation.\n",
+	"onboarding-packet.md": "# Gajae-Code Onboarding Packet\n\nThis packet is a docs-only, public-safe context seed for the `gajae-code` repository as inspected on 2026-06-01. It is intentionally a no-new-skill artifact: not a new workflow skill, command, agent, configuration surface, issue template, or runtime behavior.\n\n## Purpose in one paragraph\n\nGajae-Code is the `gjc` coding-agent CLI and supporting monorepo. The product centers on a small public workflow loop: clarify with `deep-interview`, plan with `ralplan`, execute and verify through `ultragoal`, and use `team` only when parallel tmux workers are useful. The main product package is `packages/coding-agent/`; supporting packages provide LLM/provider access, agent runtime, TUI rendering, native helpers, stats, utilities, benchmarks, and Python RPC/bot integrations.\n\n## Fixed public surface\n\nKeep this invariant front-and-center when onboarding to the repo:\n\n- Default workflow skills: `deep-interview`, `ralplan`, `team`, `ultragoal`.\n- Public role agents: `executor`, `architect`, `planner`, `critic`.\n- Bundled default workflow skill sources live under `packages/coding-agent/src/defaults/gjc/skills/`.\n- Bundled role-agent prompt sources live under `packages/coding-agent/src/prompts/agents/`.\n- Runtime state, specs, plans, goals, team state, and local overrides belong under `.gjc/` for the product and `.omx/` only for this agent-run orchestration.\n\nDo not add a fifth default skill, fifth public role agent, new command, new config surface, or feature-intake behavior unless that product decision has already been made and the default-surface gates are updated.\n\n## Primary entrypoints\n\n| Area             | Repo-relative path                                   | Why it matters                                                                                    |\n| ---------------- | ---------------------------------------------------- | ------------------------------------------------------------------------------------------------- |\n| CLI bootstrap    | `packages/coding-agent/src/cli.ts`                   | Registers top-level CLI commands and routes default launch behavior.                              |\n| Session launch   | `packages/coding-agent/src/main.ts`                  | Converts CLI/runtime settings into agent-session creation and mode dispatch.                      |\n| Agent assembly   | `packages/coding-agent/src/sdk.ts`                   | Loads settings, default skills, rules, tools, auth/model state, system prompt, and agent runtime. |\n| Built-in tools   | `packages/coding-agent/src/tools/index.ts`           | Registers file, shell, edit, search, browser, task/subagent, and related public coding-harness tools. Memory backends are private integrations, not public tools. |\n| Default skills   | `packages/coding-agent/src/defaults/gjc-defaults.ts` | Embeds and installs the four default workflow skills plus deep-interview fragments.               |\n| Role agents      | `packages/coding-agent/src/task/agents.ts`           | Embeds bundled task-agent prompts; tests enforce public role-agent expectations.                  |\n| Product overview | `README.md`                                          | Explains installation, product story, fixed workflow surface, and development entry commands.     |\n| Architecture map | `docs/codebase-overview.md`                          | Public package map and runtime-flow reference.                                                    |\n\n## Package map\n\n- `packages/coding-agent/` — main `gjc` CLI, workflows, session runtime, tool registry, discovery, settings, prompts, and tests.\n- `packages/ai/` — provider/model boundary, streaming, auth, model registry, retries, and provider integrations.\n- `packages/agent/` — stateful agent loop and append-only context runtime.\n- `packages/tui/` — terminal UI framework and rendering primitives.\n- `packages/natives/` plus `crates/*` — native helpers, Rust/N-API bindings, shell/PTY, text search, AST, filesystem, and media utilities.\n- `packages/utils/` — shared TypeScript utilities, logging, formatting, process helpers, JSON/frontmatter, and sanitization.\n- `packages/stats/` — local observability dashboard and session/model usage aggregation.\n- `packages/swarm-extension/` — optional YAML/DAG multi-agent extension outside the fixed default workflow surface.\n- `packages/typescript-edit-benchmark/` — TypeScript edit benchmark tooling.\n- `python/gjc-rpc/` — Python client for `gjc --mode rpc`.\n- `python/robogjc/` — GitHub triage/fix bot that drives `gjc --mode rpc`; this subtree has its own `AGENTS.md`.\n\n## Build, test, and validation commands\n\nPrefer targeted checks first, then broader checks when code changes justify them. For this docs-only packet, lightweight validation is enough.\n\n| Command                                                               | Scope                               | When to use                                                                 |\n| --------------------------------------------------------------------- | ----------------------------------- | --------------------------------------------------------------------------- |\n| `bun install`                                                         | Workspace dependencies              | Initial local setup.                                                        |\n| `bun run install:defaults`                                            | Local default install               | Installs source-bundled default workflow definitions for local development. |\n| `bun packages/coding-agent/src/cli.ts --help`                         | CLI smoke/discovery                 | Fast source checkout CLI sanity check.                                      |\n| `bun run check:ts`                                                    | Type/lint/default UI checks         | Broad TypeScript validation; heavier than docs-only changes.                |\n| `bun run test`                                                        | Full TS + Rust tests                | Broad regression check; use for runtime/product changes.                    |\n| `bun run ci:test:smoke`                                               | CLI version/help/stats worker smoke | Useful before release/install changes.                                      |\n| `bun scripts/check-visible-definitions.ts`                            | Default surface gate                | Required after workflow-definition changes.                                 |\n| `bun scripts/verify-g002-gates.ts`                                    | Rebrand/default-surface gate        | Required after workflow-definition or public-surface changes.               |\n| `bun scripts/rebrand-inventory.ts --strict`                           | Rebrand inventory gate              | Required after workflow-definition or public-surface changes.               |\n| `bun test packages/coding-agent/test/default-gjc-definitions.test.ts` | Four-skills/four-agents contract    | Required after default workflow/agent surface changes.                      |\n\nRepository rule: do not run `tsc` or `npx tsc`; use the Bun scripts above.\n\n## Danger zones\n\n- **Default surface expansion:** `packages/coding-agent/src/defaults/gjc/skills/`, `packages/coding-agent/src/defaults/gjc-defaults.ts`, `packages/coding-agent/src/prompts/agents/`, and model-assignment tests are contract-heavy. Changes here can accidentally alter the fixed four-skills/four-agents shape.\n- **CLI commands:** `packages/coding-agent/src/cli.ts` and `packages/coding-agent/src/commands/` define visible behavior. Adding commands or aliases is a product-surface change.\n- **Runtime/session assembly:** `packages/coding-agent/src/main.ts`, `packages/coding-agent/src/sdk.ts`, discovery, settings, tools, and system-prompt paths can affect every session.\n- **TUI/logging:** Avoid `console.log`, `console.warn`, or `console.error` inside `packages/coding-agent/`; use the centralized logger to avoid corrupting TUI rendering.\n- **Secrets/auth/config:** Keep `docs/secrets.md`, auth broker/gateway code, settings, and environment-variable docs public-safe. Do not expose tokens or private infrastructure.\n- **Native/Rust build:** `packages/natives/` and `crates/*` can require platform-specific toolchains and CI artifact behavior.\n- **Python bot subtree:** `python/robogjc/` has its own local instructions and trust boundaries.\n- **Generated model data:** Do not edit `packages/ai/src/models.json` directly; update generators/descriptors/resolvers and regenerate with `bun --cwd=packages/ai run generate-models`.\n\n## Unknowns worth preserving\n\n- Which onboarding packet shape will be most useful for future `gjc` context ingestion is still an experiment, not a product contract.\n- Public issue #158 / `gajae-deep-onboarding` context is summarized only from the user-provided prompt in this run; this packet does not add issue intake or feature workflow behavior.\n- Full CI may depend on runner/system dependencies and native artifacts; docs-only changes usually do not need the full matrix locally.\n- Some packages contain internal or hidden utility prompts/agents beyond the four public role agents. Public-facing docs should keep the four-role contract clear.\n\n## First safe tasks for a new contributor or agent\n\n1. Read `README.md`, `docs/codebase-overview.md`, and this packet.\n2. Run `bun packages/coding-agent/src/cli.ts --help` for a fast CLI surface check after dependencies are installed.\n3. For docs-only edits, run formatting/check commands that do not mutate runtime behavior.\n4. For default-surface edits, run the four required gates listed in the command table before claiming completion.\n5. For package code edits, start with the nearest package test, then escalate to `bun run check:ts` or `bun run test` as risk increases.\n6. Before changing `packages/coding-agent/src/defaults/gjc/skills/`, `packages/coding-agent/src/prompts/agents/`, `packages/coding-agent/src/commands/`, or config/settings paths, write down whether the change alters public surface area.\n\n## Context seed checklist\n\nA future agent can use this packet as context if it preserves these constraints:\n\n- Keep changes public-safe and repo-relative.\n- Prefer docs and tests over new runtime abstractions for onboarding experiments.\n- Treat the fixed four-skills/four-agents shape as a product constraint.\n- Verify claims with repo files before summarizing them.\n- Report validation evidence and caveats instead of implying hidden automation.\n",
 	"onboarding-receipt.md": "# Onboarding Packet Receipt\n\n- Date: 2026-06-01\n- Scope: docs-only no-new-skill onboarding packet experiment for this repository.\n- Output files:\n  - `docs/onboarding-packet.md`\n  - `docs/onboarding-receipt.md`\n- Public-safe boundary: no secrets, tokens, hidden prompts, private infrastructure, internal ops, or private paths beyond repo-relative paths.\n- Product boundary: no new skill, command, agent slot, issue, config, or runtime behavior.\n\n## Evidence inspected\n\n- `README.md`\n- `docs/codebase-overview.md`\n- `package.json`\n- `packages/coding-agent/package.json`\n- `packages/coding-agent/src/cli.ts`\n- `packages/coding-agent/src/main.ts`\n- `packages/coding-agent/src/sdk.ts`\n- `packages/coding-agent/src/defaults/gjc-defaults.ts`\n- `packages/coding-agent/src/task/agents.ts`\n- `packages/coding-agent/test/default-gjc-definitions.test.ts`\n- `.github/workflows/ci.yml`\n- `.github/workflows/dev-ci.yml`\n\n## Result\n\nThe packet records repo purpose, package layout, main entrypoints, build/test commands, danger zones, unknowns, and first safe tasks without changing the product surface. It is suitable as a public context seed for future onboarding experiments, not as a feature intake mechanism.\n\n## Caveats\n\n- The attempted `omx question --input '<json>' --json` interview round failed before user input because the runtime reported no attached tmux client; no human answer was inferred from that failed call.\n- Public issue context is limited to the user-provided prompt summary for this run.\n- Full CI was not required for the docs-only artifact unless later code/runtime files change.\n",
 	"porting-from-pi-mono.md": "# Porting From pi-mono: A Practical Merge Guide\n\nThis guide is a repeatable checklist for porting changes from pi-mono into this repo.\nUse it for any merge: single file, feature branch, or full release sync.\n\n## Last Sync Point (historical upstream marker)\n\n**Commit:** `b21b42d032919de2f2e6920a76fa9a37c3920c0a`\n**Date:** 2026-03-22\n\nUpdate this section after each sync; do not reuse the previous range. This commit is an upstream pi-mono marker and may not exist in this repo's local object database.\n\nWhen starting a new sync, generate patches from this commit forward in a pi-mono checkout or remote that contains the commit:\n\n```bash\ngit format-patch b21b42d032919de2f2e6920a76fa9a37c3920c0a..HEAD --stdout > changes.patch\n```\n\n## 0) Define the scope\n\n- Identify the upstream reference (commit, tag, or PR).\n- List the packages or folders you plan to touch.\n- Decide which features are in-scope and which are intentionally skipped.\n\n## 1) Bring code over safely\n\n- Prefer a clean, focused diff rather than a wholesale copy.\n- Avoid copying built artifacts or generated files.\n- If upstream added new files, add them explicitly and review contents.\n\n## 2) Match import extension conventions\n\nMost runtime TypeScript sources omit `.js` in internal imports, but several current entrypoints and tool modules keep `.js` for ESM/runtime compatibility. Follow the surrounding file and package export style; do not blanket-strip or blanket-add extensions.\n\n- In `packages/coding-agent` runtime sources, prefer extensionless internal imports when the surrounding module does, but preserve existing `.js` imports in files that already require them.\n- In `packages/tui/test` and `packages/natives/bench`, keep `.js` where surrounding files already use it.\n- Keep real file extensions when required by tooling or import assertions (e.g., `.json`, `.css`, `.md` text embeds).\n- Example: `import { x } from \"./foo.js\";` → `import { x } from \"./foo\";` only when that package/file convention is extensionless.\n\n## 3) Replace import scopes\n\nUpstream uses different package scopes. Replace them consistently.\n\n- Replace old scopes with the local scope used here.\n- Examples (adjust to match the actual packages you are porting):\n  - `@mariozechner/gajae-code` → `@gajae-code/coding-agent`\n  - `@mariozechner/pi-agent-core` → `@gajae-code/agent-core`\n  - `@mariozechner/pi-tui` → `@gajae-code/tui`\n  - `@mariozechner/pi-ai` → `@gajae-code/ai`\n\n## 4) Use Bun APIs where they improve on Node\n\nWe run on Bun, but the current source intentionally mixes Bun APIs with small Node standard-library APIs. Replace Node APIs only when Bun provides a clearer, safer, or simpler implementation; do not mechanically rewrite every Node import.\n\n**Prefer replacing when porting new code:**\n\n- Process spawning: prefer Bun Shell `$` for simple commands; use `Bun.spawn`/`Bun.spawnSync` for streaming or process control. Keep existing `child_process` only where its exact semantics are needed.\n- HTTP clients: `node-fetch`, `axios` → native `fetch`\n- SQLite: `better-sqlite3` → `bun:sqlite`\n- Env loading: `dotenv` → Bun loads `.env` automatically\n- Runtime text/assets: prefer Bun imports such as `with { type: \"text\" }` or `Bun.file()` over copy steps or bundled fallback file reads.\n\n**DO NOT replace (these work fine in Bun):**\n\n- `os.homedir()` — do NOT replace with `Bun.env.HOME` or literal `\"~\"`\n- `os.tmpdir()` — do NOT replace with `Bun.env.TMPDIR || \"/tmp\"` or hardcoded paths\n- `fs.mkdtempSync()` — do NOT replace with manual path construction\n- `path.join()`, `path.resolve()`, etc. — these are fine\n\n**Import style:** Use the `node:` prefix for Node standard-library imports. Namespace imports are common, but named imports are acceptable where the surrounding code already uses them.\n\n**Additional Bun conventions:**\n\n- Prefer Bun Shell `$` for short, non-streaming commands; use `Bun.spawn` only when you need streaming I/O or process control.\n- Use `Bun.file()`/`Bun.write()` for simple files and `node:fs/promises` for directory-oriented operations. Existing synchronous `node:fs` calls are acceptable when the calling flow is intentionally synchronous.\n- Avoid `Bun.file().exists()` checks; use `isEnoent` handling in try/catch.\n- Prefer `Bun.sleep(ms)` over `setTimeout` wrappers.\n\n**Wrong:**\n\n```typescript\n// BROKEN: env vars may be undefined, \"~\" is not expanded\nconst home = Bun.env.HOME || \"~\";\nconst tmp = Bun.env.TMPDIR || \"/tmp\";\n```\n\n**Correct:**\n\n```typescript\nimport * as os from \"node:os\";\nimport * as fs from \"node:fs\";\nimport * as path from \"node:path\";\n\nconst configDir = path.join(os.homedir(), \".config\", \"myapp\");\nconst tempDir = fs.mkdtempSync(path.join(os.tmpdir(), \"myapp-\"));\n```\n\n## 5) Prefer Bun embeds (no copying)\n\nDo not add new runtime asset copy steps. Keep assets in repo and prefer Bun embeds/imports; preserve existing explicit generation workflows such as `packages/coding-agent/src/export/html/template.generated.ts`.\n\n- If upstream copies assets into a dist folder, replace with Bun-friendly embeds.\n- Prompts are static `.md` files; use Bun text imports (`with { type: \"text\" }`) and Handlebars instead of inline prompt strings.\n- Use `import.meta.dir` + `Bun.file` to load adjacent non-text resources.\n- Keep assets in-repo and let the bundler include them.\n- Eliminate copy scripts unless the user explicitly requests them or the package already has an intentional generation step.\n- If upstream reads a bundled fallback file at runtime, replace filesystem reads with a Bun text embed import unless the current package already uses a generated asset pipeline.\n  - Example (provider instructions fallback):\n    - `const FALLBACK_PROMPT_PATH = join(import.meta.dir, \"openai-code-instructions.md\");` -> removed\n    - `import FALLBACK_INSTRUCTIONS from \"./openai-code-instructions.md\" with { type: \"text\" };`\n    - Use `return FALLBACK_INSTRUCTIONS;` instead of `readFileSync(FALLBACK_PROMPT_PATH, \"utf8\")`\n\n## 6) Port `package.json` carefully\n\nTreat `package.json` as a contract. Merge intentionally.\n\n- Keep existing `name`, `version`, `type`, `exports`, and `bin` unless the port requires changes.\n- Replace npm/node scripts with Bun equivalents (e.g., `bun check`, `bun test`).\n- Ensure dependencies use the correct scope.\n- Do not downgrade dependencies to fix type errors; upgrade instead.\n- Validate workspace package links and `peerDependencies`.\n\n## 7) Align code style and tooling\n\n- Keep existing formatting conventions.\n- Do not introduce `any` unless required.\n- Avoid dynamic imports unless they are required for optional dependencies, startup cost, or runtime-only modules; prefer top-level imports otherwise.\n- Never build prompts in code; prompts are static `.md` files rendered with Handlebars.\n- In `packages/coding-agent`, use `logger` from `@gajae-code/utils` for internal/runtime logging; CLI command files may use `console.*` for intentional user-facing output.\n- Use `Promise.withResolvers()` instead of `new Promise((resolve, reject) => ...)`.\n- Prefer ES `#` private fields for new encapsulated state. Constructor parameter properties already exist in current code and are acceptable; do not churn unrelated access modifiers while porting.\n- Prefer existing helpers and utilities over new ad-hoc code.\n  Preserve Bun-first infrastructure changes already made in this repo:\n  - Runtime is Bun (no Node entry points for the main CLI).\n  - Package manager is Bun (no npm lockfiles).\n  - Heavy Node APIs should not be introduced casually; current source still uses selected Node APIs (`node:crypto`, `node:readline`, synchronous `node:fs`, and `child_process`) where they fit provider, CLI, or process-control semantics.\n  - Lightweight Node APIs (`os.homedir`, `os.tmpdir`, `fs.mkdtempSync`, `path.*`) are kept.\n  - CLI shebangs use `bun` (not `node`, not `tsx`).\n  - TypeScript packages generally use source files directly; `@gajae-code/natives` exports generated native bindings from `packages/natives/native`.\n  - CI workflows run Bun for install/check/test.\n\n## 8) Remove old compatibility layers\n\nUnless requested, remove upstream compatibility shims.\n\n- Delete old APIs that were replaced.\n- Update all call sites to the new API directly.\n- Do not keep `*_v2` or parallel versions.\n\n## 9) Update docs and references\n\n- Replace pi-mono repo links where appropriate.\n- Update examples to use Bun and correct package scopes.\n- Ensure README instructions still match the current repo behavior.\n\n## 10) Validate the port\n\nRun the standard checks after changes:\n\n- `bun check`\n\nIf the repo already has failing checks unrelated to your changes, call that out.\nTests use Bun's runner (not Vitest), but only run `bun test` when explicitly requested.\n\n## 11) Protect improved features (regression trap list)\n\nIf you already improved behavior locally, treat those as **non‑negotiable**. Before porting, write down\nthe improvements and add explicit checks so they don’t get lost in the merge.\n\n- **Freeze the expected behavior**: add a short “before/after” note for each improvement (inputs, outputs,\n  defaults, edge cases). This prevents silent rollback.\n- **Map old → new APIs**: if upstream renamed concepts (hooks → extensions, custom tools → tools, etc.),\n  ensure every old entry point still wires through. One missed flag or export equals lost functionality.\n- **Verify exports**: check `package.json` `exports`, public types, and barrel files. Upstream ports often\n  forget to re-export local additions.\n- **Cover non‑happy paths**: if you fixed error handling, timeouts, or fallback logic, add a test or at\n  least a manual checklist that exercises those paths.\n- **Check defaults and config merge order**: improvements often live in defaults. Confirm new defaults\n  didn’t revert (e.g., new config precedence, disabled features, tool lists).\n- **Audit env/shell behavior**: if you fixed execution or sandboxing, verify the new path still uses your\n  sanitized env and does not reintroduce alias/function overrides.\n- **Re-run targeted samples**: keep a minimal set of \"known good\" examples and run them after the port\n  (CLI flags, extension registration, tool execution).\n\n## 12) Detect and handle reworked code\n\nBefore porting a file, check if upstream significantly refactored it:\n\n```bash\n# Compare the file you're about to port against what you have locally\ngit diff HEAD upstream/main -- path/to/file.ts\n```\n\nIf the diff shows the file was **reworked** (not just patched):\n\n- New abstractions, renamed concepts, merged modules, changed data flow\n\nThen you must **read the new implementation thoroughly** before porting. Blind merging of reworked code loses functionality because:\n\nNote: interactive mode was recently split into controllers/utils/types. When backporting related changes, port updates into the individual files we created and ensure `interactive-mode.ts` wiring stays in sync.\n\n1. **Defaults change silently** - A new variable `defaultFoo = [a, b]` may replace an old `getAllFoo()` that returned `[a, b, c, d, e]`.\n\n2. **API options get dropped** - When systems merge (e.g., `hooks` + `customTools` → `extensions`), old options may not wire through to the new implementation.\n\n3. **Code paths go stale** - A renamed concept (e.g., `hookMessage` → `custom`) needs updates in every switch statement, type guard, and handler—not just the definition.\n\n4. **Context/capabilities shrink** - Old APIs may have exposed `{ logger, typebox, pi }` that new APIs forgot to include.\n\n### Semantic porting process\n\nWhen upstream reworked a module:\n\n1. **Read the old implementation** - Understand what it did, what options it accepted, what it exposed.\n\n2. **Read the new implementation** - Understand the new abstractions and how they map to old behavior.\n\n3. **Verify feature parity** - For each capability in the old code, confirm the new code preserves it or explicitly removes it.\n\n4. **Grep for stragglers** - Search for old names/concepts that may have been missed in switch statements, handlers, UI components.\n\n5. **Test the boundaries** - CLI flags, SDK options, event handlers, default values—these are where regressions hide.\n\n### Quick checks\n\n```bash\n# Find all uses of an old concept that may need updating\nrg \"oldConceptName\" --type ts\n\n# Compare default values between versions\ngit show upstream/main:path/to/file.ts | rg \"default|DEFAULT\"\n\n# Check if all enum/union values have handlers\nrg \"case \\\"\" path/to/file.ts\n```\n\n## 13) Quick audit checklist\n\nUse this as a final pass before you finish:\n\n- [ ] Import extensions follow the local package convention (no blanket `.js` stripping)\n- [ ] No newly introduced Node-only APIs unless they match an existing justified pattern\n- [ ] All package scopes updated\n- [ ] `package.json` scripts use Bun\n- [ ] Prompts are `.md` text imports (no inline prompt strings)\n- [ ] No internal/runtime `console.*` in coding-agent; CLI user-facing output is intentional\n- [ ] Assets load via Bun embed/import patterns, or through an existing intentional generation pipeline\n- [ ] Tests or checks run (or explicitly noted as blocked)\n- [ ] No functionality regressions (see sections 11-12)\n\n## 14) Commit message format\n\nWhen committing a backport, follow the repo format `<type>(scope): <past-tense description>` and keep the commit\nrange in the title.\n\n```\nfix(coding-agent): backported pi-mono changes (<from>..<to>)\n\npackages/<package>:\n- <type>: <description>\n- <type>: <description> (#<issue> by @<contributor>)\n\npackages/<other-package>:\n- <type>: <description>\n```\n\n**Example:**\n\n```\nfix(coding-agent): backported pi-mono changes (9f3eef65f..52532c7c0)\n\npackages/ai:\n- fix: handle \"sensitive\" stop reason from Anthropic API\n- fix: normalize tool call IDs with special characters for Responses API\n- fix: add overflow detection for Bedrock, MiniMax, Kimi providers\n- fix: 429 status is rate limiting, not context overflow\n\npackages/tui:\n- fix: refactored autocomplete state tracking\n- fix: file autocomplete should not trigger on empty text\n- fix: configurable autocomplete max visible items\n- fix: improved table column width calculation with word-aware wrapping\n\npackages/coding-agent:\n- fix: preserve external config.yml edits on save (#1046 by @nicobailonMD)\n- fix: resolve macOS NFD and curly quote variants in file paths\n```\n\n**Rules:**\n\n- Group changes by package\n- Use conventional commit types (`fix`, `feat`, `refactor`, `perf`, `docs`)\n- Include upstream issue/PR numbers and contributor attribution for external contributions\n- The commit range in the title helps track sync points\n\n## 15) Intentional Divergences\n\nOur fork has architectural decisions that differ from upstream. **Do not port these upstream patterns:**\n\n### UI Architecture\n\n| Upstream                                    | Our Fork                                                  | Reason                                                                |\n| ------------------------------------------- | --------------------------------------------------------- | --------------------------------------------------------------------- |\n| `FooterDataProvider` class                  | `StatusLineComponent`                                     | Simpler, integrated status line                                       |\n| `ctx.ui.setHeader()` / `ctx.ui.setFooter()` | No-op stubs in current extension contexts                 | Not currently wired to replace the TUI status/header UI               |\n| `ctx.ui.setEditorComponent()`               | No-op stubs in current extension contexts                 | Custom editor replacement is not currently wired                      |\n| `InteractiveModeOptions` options object     | Positional constructor args (options type still exported) | Keep constructor signature; update the type when upstream adds fields |\n\n### Component Naming\n\n| Upstream                     | Our Fork                |\n| ---------------------------- | ----------------------- |\n| `extension-input.ts`         | `hook-input.ts`         |\n| `extension-selector.ts`      | `hook-selector.ts`      |\n| `ExtensionInputComponent`    | `HookInputComponent`    |\n| `ExtensionSelectorComponent` | `HookSelectorComponent` |\n\n### API Naming\n\n| Upstream                                 | Our Fork                                 | Notes                                     |\n| ---------------------------------------- | ---------------------------------------- | ----------------------------------------- |\n| `sessionManager.appendSessionInfo(name)` | `sessionManager.setSessionName(name)`    | We use `sessionName` throughout           |\n| `sessionManager.getSessionName()`        | `sessionManager.getSessionName()`        | Same (we unified to match upstream's RPC) |\n| `agent.sessionName` / `setSessionName()` | `agent.sessionName` / `setSessionName()` | Same                                      |\n\n### File Consolidation\n\n| Upstream                                           | Our Fork                                                  | Reason                                        |\n| -------------------------------------------------- | --------------------------------------------------------- | --------------------------------------------- |\n| `clipboard.ts` + `clipboard-image.ts` (tool files) | `src/utils/clipboard.ts` backed by `@gajae-code/natives` | Native implementation with a small TS wrapper |\n\n### Test Framework\n\n| Upstream                  | Our Fork                      |\n| ------------------------- | ----------------------------- |\n| `vitest` with `vi.mock()` | `bun:test` with `vi` from bun |\n| `node:test` assertions    | `expect()` matchers           |\n\n### Tool Architecture\n\n| Upstream                            | Our Fork                                                                                                      | Notes                                                     |\n| ----------------------------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- |\n| `createTool(cwd: string, options?)` | `createTools(session: ToolSession)` via `BUILTIN_TOOLS` registry                                              | Tool factories accept `ToolSession` and can return `null` |\n| Per-tool `*Operations` interfaces   | Only current per-tool override interfaces remain (for example `FindOperations`)                               | Used for SSH/remote overrides where present               |\n| Node.js `fs/promises` everywhere    | Bun file APIs for simple file writes/reads, `node:fs/promises` for dirs, selected sync `node:fs` where needed | Prefer Bun APIs when they simplify                        |\n\n### Auth Storage\n\n| Upstream                        | Our Fork                                    | Notes                                        |\n| ------------------------------- | ------------------------------------------- | -------------------------------------------- |\n| `proper-lockfile` + `auth.json` | `agent.db` (bun:sqlite)                     | Credentials stored exclusively in `agent.db` |\n| Single credential per provider  | Multi-credential with round-robin selection | Session affinity and backoff logic preserved |\n\n### Extensions\n\n| Upstream                      | Our Fork                                          |\n| ----------------------------- | ------------------------------------------------- |\n| `jiti` for TypeScript loading | Native Bun `import()`                             |\n| `pkg.pi` manifest field       | `pkg.gjc` preferred; fallback to `pkg.pi` remains |\n\n### Skip These Upstream Features\n\nWhen porting, **skip** these files/features entirely:\n\n- `footer-data-provider.ts` — we use StatusLineComponent\n- `clipboard-image.ts` — image clipboard support is exposed through `src/utils/clipboard.ts` backed by `@gajae-code/natives`\n- GitHub workflow files — we have our own CI\n- `models.generated.ts` — auto-generated, regenerate locally (as models.json instead)\n\n### Features We Added (Preserve These)\n\nThese exist in our fork but not upstream. **Never overwrite:**\n\n- `StatusLineComponent` in interactive mode\n- Multi-credential auth with session affinity\n- Capability-based discovery system (`defineCapability`, `registerProvider`, `loadCapability`, `skillCapability`, etc.)\n- MCP/Exa/SSH integrations\n- LSP writethrough for format-on-save\n- Bash interception (`checkBashInterception`)\n- Fuzzy path suggestions in read tool\n",
 	"porting-to-natives.md": "# Porting to pi-natives (N-API) — Field Notes\n\nThis is a practical guide for moving hot paths into `crates/pi-natives` and wiring them through the generated native package entrypoint. It exists to avoid the same failures happening twice.\n\n## When to port\n\nPort when any of these are true:\n\n- The hot path runs in render loops, tight UI updates, or large batches.\n- JS allocations dominate (string churn, regex backtracking, large arrays).\n- You already have a JS baseline and can benchmark both versions side by side.\n- The work is CPU-bound or blocking I/O that can run on the libuv thread pool.\n- The work is async I/O that can run on Tokio's runtime (for example shell execution).\n\nRust is reserved for native bindings, native OS/process/filesystem integration, and measured hot paths. New crates or Rust source trees must have an explicit native/performance rationale in `scripts/check-rust-scope.ts`; keep product policy, orchestration, and glue code in TypeScript unless the benchmark or native boundary justifies moving it.\n\nAvoid ports that depend on JS-only state or dynamic imports. N-API exports should be data-in/data-out. Long-running work should go through `task::blocking` (CPU-bound/blocking I/O) or `task::future` (async I/O) with cancellation where the caller needs `timeoutMs` or `AbortSignal`.\n\n## Current package shape\n\n`@gajae-code/natives` no longer has a `packages/natives/src/<module>` TypeScript wrapper layer. The package root points at generated native artifacts:\n\n- runtime entry: `packages/natives/native/index.js`\n- types entry: `packages/natives/native/index.d.ts`\n- loader helpers: `packages/natives/native/loader-state.js`\n- embedded manifest: `packages/natives/native/embedded-addon.js`\n\nConsumers import directly from `@gajae-code/natives`. The generated declarations are produced during `bun --cwd=packages/natives run build`.\n\n## Anatomy of a native export\n\n**Rust side:**\n\n- Implementation lives in `crates/pi-natives/src/<module>.rs`.\n- If you add a new module, register it in `crates/pi-natives/src/lib.rs`.\n- Export with `#[napi]`; snake_case exports are converted to camelCase automatically. Use explicit JS names only for true aliases/non-default names. Use `#[napi(object)]` for object-shaped structs.\n- For CPU-bound or blocking work, use `task::blocking(tag, cancel_token, work)`.\n- For async work that needs Tokio, use `task::future(env, tag, work)`.\n- Pass a `CancelToken` when the API exposes `timeoutMs` or `AbortSignal`, and call `heartbeat()` inside long loops.\n\n**Package/build side:**\n\n- `packages/natives/scripts/build-native.ts` runs napi-rs, installs the `.node` artifact, copies generated `index.js`/`index.d.ts`, and appends enum runtime exports.\n- `packages/natives/native/index.js` is the loader that chooses a candidate `.node` file and returns the loaded addon.\n- `packages/natives/package.json` exposes only the package root (`@gajae-code/natives`).\n\n**Consumer side:**\n\n- Update direct imports/callsites in `packages/coding-agent` or `packages/tui` when the new export replaces a JS implementation.\n- Keep higher-level policy in consumers unless it belongs in the native primitive itself.\n\n## Porting checklist\n\n1. **Add the Rust implementation**\n\n- Put the core logic in a plain Rust function.\n- If it is a new module, add it to `crates/pi-natives/src/lib.rs`.\n- Expose it with `#[napi]` so the default snake_case -> camelCase mapping stays consistent.\n- Keep signatures owned and simple: `String`, `Vec<String>`, `Uint8Array`, `Either<JsString, Uint8Array>`, or `#[napi(object)]` structs.\n- For CPU-bound or blocking work, use `task::blocking`; for async work, use `task::future`.\n- If exposing cancellation, include `timeout_ms: Option<u32>` and `signal: Option<Unknown<'env>>` in options, create `CancelToken::new(...)`, and heartbeat in long loops.\n\n2. **Build generated bindings**\n\n- Run `bun --cwd=packages/natives run build`.\n- Confirm the generated `packages/natives/native/index.d.ts` includes the new export with the intended JS name/signature.\n- Confirm `packages/natives/native/index.js` still has generated enum exports appended when enum changes are involved.\n\n3. **Update consumers**\n\n- Import the new export directly from `@gajae-code/natives`.\n- Replace only callsites where the native implementation is faster/equivalent and preserves behavior.\n- Remove obsolete JS implementation code in the same change when the native path becomes canonical.\n\n4. **Add benchmarks**\n\n- Put benchmarks next to the owning package (`packages/tui/bench`, `packages/natives/bench`, or `packages/coding-agent/bench`).\n- Include a JS baseline and native version in the same run.\n- Use `Bun.nanoseconds()` and a fixed iteration count.\n- Keep benchmark inputs realistic for the hot path.\n\n5. **Run focused verification**\n\n- Build the native package.\n- Run the benchmark.\n- Run the narrow tests or scenario covering the changed export/callsites.\n\n## Pain points and how to avoid them\n\n### 1) Stale platform/variant artifacts\n\nThe loader probes platform-tagged artifacts in deterministic order. For x64, selected variant candidates are tried before the unsuffixed default fallback:\n\n- `modern`: `pi_natives.<tag>-modern.node`, then `...-baseline.node`, then `pi_natives.<tag>.node`.\n- `baseline`: `pi_natives.<tag>-baseline.node`, then `pi_natives.<tag>.node`.\n\nNon-x64 uses `pi_natives.<tag>.node`.\n\nCompiled binaries also probe `<getNativesDir()>/<version>/...` and a legacy user-data directory before package/executable locations. If any earlier candidate is stale, a new export may appear missing.\n\n**Fix:** remove stale candidate/cache files and rebuild.\n\n```bash\nrm packages/natives/native/pi_natives.<platform>-<arch>.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-modern.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-baseline.node\nbun --cwd=packages/natives run build\n```\n\nFor compiled binaries, delete the versioned addon cache shown in the loader error (normally under `~/.gjc/natives/<version>` unless `$XDG_DATA_HOME/gjc` is used).\n\n### 2) Generated types do not match loaded binary\n\nThis can happen when `native/index.d.ts` was regenerated but the `.node` file being loaded is stale or from a different platform/variant.\n\nVerify the loaded export set from the actual candidate path:\n\n```bash\nbun -e 'const tag = `${process.platform}-${process.arch}`; const mod = require(`./packages/natives/native/pi_natives.${tag}.node`); console.log(Object.keys(mod).sort())'\n```\n\nFix the build/candidate mismatch. Do not paper over it with optional consumer checks if the export is required.\n\n### 3) Rust signature mismatch\n\nKeep N-API signatures simple and owned. Avoid borrowed references like `&str` in public exports. If you need structured data, use `#[napi(object)]` structs. If you need callbacks, use napi-rs `ThreadsafeFunction` and keep callback error/value behavior explicit.\n\n### 4) Enum runtime exports\n\nnapi-rs declarations alone are not enough for JS callers that use enum objects at runtime. `scripts/gen-enums.ts` appends enum objects to `native/index.js`. If you add or change a native enum, verify both `native/index.d.ts` and the generated enum export block in `native/index.js`.\n\n### 5) Benchmarking mistakes\n\n- Do not compare different inputs or allocations.\n- Keep JS and native using identical input arrays.\n- Run both in the same benchmark file to avoid skew.\n- Include enough iterations to smooth startup noise, but keep inputs realistic.\n\n## Benchmark template\n\n```ts\nconst ITERATIONS = 2000;\n\nfunction bench(name: string, fn: () => void): number {\n  const start = Bun.nanoseconds();\n  for (let i = 0; i < ITERATIONS; i++) fn();\n  const elapsed = (Bun.nanoseconds() - start) / 1e6;\n  console.log(\n    `${name}: ${elapsed.toFixed(2)}ms total (${(elapsed / ITERATIONS).toFixed(6)}ms/op)`,\n  );\n  return elapsed;\n}\n\nbench(\"feature/js\", () => {\n  jsImpl(sample);\n});\n\nbench(\"feature/native\", () => {\n  nativeImpl(sample);\n});\n```\n\n## Verification checklist\n\n- Generated `native/index.d.ts` includes the new export and intended TS signature.\n- The loaded `.node` file's `Object.keys(require(candidate))` includes the new export.\n- Runtime enum objects are present when the change adds/changes enums.\n- Bench numbers are recorded in the PR/notes.\n- Call sites are updated only if native is faster/equal and behavior-compatible.\n- Obsolete JS code is removed when the native implementation becomes canonical.\n\n## Rule of thumb\n\n- If native is slower, do not switch callsites. Keep or remove the export based on whether it has a near-term owner.\n- If native is faster and behavior-compatible, switch callsites and keep a benchmark to catch regressions.\n",
@@ -65,13 +66,10 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"tools/job.md": "# job\n\n> Wait for or cancel background jobs managed by the session async runtime.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/job.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/job.md`\n- Key collaborators:\n  - `packages/coding-agent/src/async/job-manager.ts` — job registry, cancellation, delivery suppression.\n  - `packages/coding-agent/src/async/support.ts` — feature gating for background jobs.\n  - `packages/coding-agent/src/tools/bash.ts` — explicit async bash and auto-backgrounded bash jobs.\n  - `packages/coding-agent/src/task/index.ts` — async task-job scheduling.\n  - `packages/coding-agent/src/sdk.ts` — automatic follow-up delivery for unsuppressed completions.\n  - `packages/coding-agent/src/config/settings-schema.ts` — `async.pollWaitDuration` options.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `poll` | `string[]` | No | Job ids to watch. Cannot be combined with `list`. If omitted (and `cancel` is also omitted), the tool watches all running jobs. If provided, missing ids are silently filtered out before waiting. |\n| `cancel` | `string[]` | No | Job ids to cancel before any polling. Missing ids are reported as `not_found`; non-running ids as `already_completed`. |\n| `list` | `boolean` | No | Return an immediate snapshot of every job spawned by the calling agent (running + completed within retention) without waiting. Read-only — cannot be combined with `poll` or `cancel`. |\n\n## Outputs\nThe tool returns one text block plus `details`.\n\n- `content[0].text`: markdown-like plain text sections assembled by `#buildResult(...)`:\n  - `## Cancelled (N)` for cancel outcomes.\n  - `## Completed (N)` for non-running jobs, including stored `resultText` and `errorText`.\n  - `## Still Running (N)` for jobs still in `running`.\n- `details.jobs`: array of snapshots:\n  - `id: string`\n  - `type: \"bash\" | \"task\"`\n  - `status: \"running\" | \"completed\" | \"failed\" | \"cancelled\"`\n  - `label: string`\n  - `durationMs: number`\n  - optional `resultText`, `errorText`\n- `details.cancelled` appears only when `cancel` was passed; each item is `{ id, status }` where status is `\"cancelled\" | \"not_found\" | \"already_completed\"`.\n\nStreaming behavior:\n- During a polling wait, `execute(...)` emits `onUpdate(...)` every 500 ms with an empty text block and fresh `details.jobs` snapshots.\n- Final return is single-shot after a completion, timeout, abort, or immediate fast path.\n\nRead-only snapshot path:\n- Calling `job` with `list: true` returns a markdown summary of every job spawned by the calling agent (running + completed within retention) without waiting.\n\n## Flow\n1. `JobTool.createIf(...)` in `packages/coding-agent/src/tools/job.ts` only exposes the tool when `isBackgroundJobSupportEnabled(...)` returns true for either `async.enabled` or `bash.autoBackground.enabled`.\n2. `execute(...)` fetches `session.asyncJobManager`. If absent, it returns `Async execution is disabled; no background jobs are available.`\n3. `cancel` ids are processed first:\n   - `manager.getJob(id)` missing → `not_found`.\n   - existing job with `status !== \"running\"` → `already_completed`.\n   - running job → `manager.cancel(id)`, which sets `job.status = \"cancelled\"`, aborts the controller, and schedules eviction.\n4. Polling mode is chosen with `const shouldPoll = requestedPollIds !== undefined || cancelIds.length === 0`:\n   - only `cancel` present → return immediately, no wait.\n   - explicit `poll`, or no args at all → proceed to watch jobs.\n5. Watch set resolution:\n   - explicit `poll` → map ids through `manager.getJob(...)` and drop missing ones.\n   - no `poll` and no `cancel` → `manager.getRunningJobs()`.\n6. Empty watch set returns immediately:\n   - if cancellations happened, return snapshots for the cancelled ids that still exist.\n   - else return either `No matching jobs found for IDs: ...` or `No running background jobs to wait for.`\n7. If every watched job is already non-running, `#buildResult(...)` returns immediately without waiting.\n8. Otherwise the tool waits on `Promise.race(...)` across:\n   - every watched running job's `job.promise`,\n   - a timeout promise for `async.pollWaitDuration`,\n   - the tool-call abort signal when present.\n9. Before waiting, it calls `manager.watchJobs(watchedJobIds)`. This suppresses automatic completion delivery for those ids while they are being watched.\n10. If `onUpdate` exists, a 500 ms interval sends progress snapshots from `#snapshotJobs(...)`; one snapshot is emitted immediately before entering the race.\n11. In `finally`, the tool always calls `manager.unwatchJobs(...)`, clears the timeout, and stops the progress interval.\n12. `#buildResult(...)` deduplicates jobs, snapshots current manager state, then calls `manager.acknowledgeDeliveries(...)` for every non-running job in the result. That suppresses later automatic follow-up delivery for the same completions and removes queued deliveries for those ids.\n13. The final text groups jobs by non-running vs still-running state. A timeout is not an error path; it simply returns the current snapshot.\n\n## Modes / Variants\n- Poll all running jobs: call with neither `poll` nor `cancel`.\n- Poll explicit ids: call with `poll` only.\n- Cancel only: call with `cancel` only; cancellations happen and the tool returns immediately.\n- Cancel then poll: call with both. Cancellations are applied first, then the tool watches the remaining resolved `poll` ids.\n- Read-only inspection: call with `list: true` for the same snapshot data without waiting on completion.\n\nSpawn paths that produce jobs:\n- `packages/coding-agent/src/tools/bash.ts`\n  - `async: true` always registers a `type: \"bash\"` job with `AsyncJobManager.register(...)` and returns a start message.\n  - auto-background mode (`bash.autoBackground.enabled`) starts the same managed job path for non-PTY commands, waits up to `min(bash.autoBackground.thresholdMs, timeoutMs - 1000)`, and if the command is still running returns a background-job start result instead of inline command output.\n- `packages/coding-agent/src/task/index.ts`\n  - when `async.enabled` is on, the chosen agent is not blocking, and `tasks.length > 0`, each task item is registered as a `type: \"task\"` job.\n\nLifecycle and exact state names:\n- Conceptual scheduling path: `pending` (only task-progress bookkeeping before work starts) → `running` → `completed` / `failed`; cancellation changes a running async job to `cancelled`.\n- Exact `AsyncJob.status` values in `packages/coding-agent/src/async/job-manager.ts`: `\"running\" | \"completed\" | \"failed\" | \"cancelled\"`.\n- Exact per-task progress values in `packages/coding-agent/src/task/types.ts`: `\"pending\" | \"running\" | \"completed\" | \"failed\" | \"aborted\"`.\n\n## Side Effects\n- Filesystem\n  - None in `job.ts` itself.\n  - Jobs being observed may already have written artifacts/results through their own tool runtimes.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Reads and mutates `session.asyncJobManager` state.\n  - `watchJobs(...)` / `unwatchJobs(...)` toggle delivery suppression for the watched ids.\n  - `acknowledgeDeliveries(...)` marks completed ids as suppressed and removes queued deliveries for them.\n  - `cancel(...)` aborts running jobs through each job's `AbortController`.\n- User-visible prompts / interactive UI\n  - Polling emits periodic `onUpdate` snapshots every 500 ms.\n  - Automatic job completion follow-ups are generated by `packages/coding-agent/src/sdk.ts` only for unsuppressed deliveries.\n- Background work / cancellation\n  - Waiting uses a timeout plus optional tool-call abort signal.\n  - Cancelling a job does not synchronously await teardown; it flips state, aborts, and returns control to the manager/job promise.\n\n## Limits & Caps\n- Poll wait duration comes from `async.pollWaitDuration` in `packages/coding-agent/src/config/settings-schema.ts`:\n  - allowed values: `5s`, `10s`, `30s`, `1m`, `5m`\n  - default: `30s`\n- Progress update cadence while polling: `PROGRESS_INTERVAL_MS = 500` in `packages/coding-agent/src/tools/job.ts`.\n- Async job retention default: `DEFAULT_RETENTION_MS = 5 * 60 * 1000` in `packages/coding-agent/src/async/job-manager.ts`.\n- Manager fallback max-running limit: `DEFAULT_MAX_RUNNING_JOBS = 15` in `packages/coding-agent/src/async/job-manager.ts`.\n- Session wiring clamps `async.maxJobs` to `1..100` before constructing the manager in `packages/coding-agent/src/sdk.ts`; settings default is `100` in `packages/coding-agent/src/config/settings-schema.ts`.\n- Async completion delivery retry backoff in `packages/coding-agent/src/async/job-manager.ts`:\n  - base `500` ms\n  - max `30_000` ms\n  - jitter `< 200` ms\n  - exponent capped at 8 doublings\n\n## Errors\n- Tool-disabled path is returned as normal text, not thrown: `Async execution is disabled; no background jobs are available.`\n- Polling a nonexistent id is not an exception:\n  - with `poll` only, missing ids are dropped; if none remain the tool returns `No matching jobs found for IDs: ...`.\n  - with `cancel`, each missing id is reported as `not_found` in `details.cancelled` and text.\n- Cancelling a non-running job is not an exception; it reports `already_completed` even if the actual status is `completed`, `failed`, or `cancelled`.\n- Tool-call abort during polling stops waiting and returns a final snapshot through `#buildResult(...)`; it does not cancel watched jobs.\n- Failures inside the underlying async work are stored on the job (`status: \"failed\"`, `errorText`) and reported in normal tool output, not rethrown by `job`.\n- Calling `list: true` against an empty manager returns a normal empty-list result rather than throwing; missing ids passed to `poll` are silently filtered.\n\n## Notes\n- `job` waits for the first watched running job to settle, not for all watched jobs. If others remain `running`, they are reported under `## Still Running`; the caller must invoke `job` again to continue waiting.\n- Delivery suppression is the key difference between snapshot and automatic delivery:\n  - snapshots (`job` calls with `poll` or `list: true`) read current manager state;\n  - follow-up delivery comes from `AsyncJobManager.#enqueueDelivery(...)` and `sdk.ts` `onJobComplete`;\n  - watched or acknowledged ids are suppressed via `isDeliverySuppressed(...)`.\n- `manager.cancel(id)` sets `status = \"cancelled\"` before the underlying promise settles. The job function may later populate `resultText` or `errorText`; `job-manager.ts` preserves that text but does not transition the status away from `cancelled`.\n- Retention eviction removes the job record, suppression flags, and watch flag together. After eviction, both `job` calls and `list: true` snapshots behave as if the id never existed.\n",
 	"tools/lsp.md": "# lsp\n\n> Query language servers for diagnostics, navigation, symbols, renames, code actions, capabilities, and raw requests.\n\n## Source\n- Entry: `packages/coding-agent/src/lsp/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/lsp.md`\n- Key collaborators:\n  - `packages/coding-agent/src/lsp/client.ts` — client process lifecycle and JSON-RPC\n  - `packages/coding-agent/src/lsp/config.ts` — config loading, auto-detect, server selection\n  - `packages/coding-agent/src/lsp/lspmux.ts` — optional `lspmux` command wrapping\n  - `packages/coding-agent/src/lsp/edits.ts` — apply `WorkspaceEdit` and text edits\n  - `packages/coding-agent/src/lsp/utils.ts` — URI conversion, symbol resolution, formatting, glob expansion\n  - `packages/coding-agent/src/lsp/types.ts` — tool schema and protocol types\n  - `packages/coding-agent/src/lsp/clients/index.ts` — custom linter client cache/factory\n  - `packages/coding-agent/src/lsp/clients/lsp-linter-client.ts` — LSP-backed linter adapter\n  - `packages/coding-agent/src/lsp/clients/biome-client.ts` — Biome CLI diagnostics/formatting adapter\n  - `packages/coding-agent/src/lsp/clients/swiftlint-client.ts` — SwiftLint CLI diagnostics adapter\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and `lsp.enabled` gating\n  - `packages/coding-agent/src/tools/tool-timeouts.ts` — timeout defaults and clamping\n  - `packages/coding-agent/src/lsp/defaults.json` — built-in server definitions for auto-detect\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | string enum | Yes | One of `diagnostics`, `definition`, `references`, `hover`, `symbols`, `rename`, `rename_file`, `code_actions`, `type_definition`, `implementation`, `status`, `reload`, `capabilities`, `request`. |\n| `file` | string | No | File path; for `diagnostics` also a glob; for workspace forms use `\"*\"`; for `rename_file` this is the source path. |\n| `line` | number | No | 1-indexed line number for position-based actions. Defaults to `1` on the single-file action path. |\n| `symbol` | string | No | Substring used to resolve the column on `line`. Supports `name#N` occurrence selectors; `N` is 1-indexed and defaults to `1`. |\n| `query` | string | No | Workspace symbol query, code-action selector/filter, or LSP method name for `action=request`. |\n| `new_name` | string | No | Required for `rename` and `rename_file`. |\n| `apply` | boolean | No | For `rename`/`rename_file`, apply unless explicitly `false`. For `code_actions`, list unless explicitly `true`. |\n| `timeout` | number | No | Seconds, clamped by `clampTimeout(\"lsp\", ...)` to `5..60`, default `20`. |\n| `payload` | string | No | JSON string for `action=request`; overrides auto-built params. |\n\n## Outputs\n- Single-shot `AgentToolResult`.\n- `content` is always one text block: `[{ type: \"text\", text: string }]`.\n- `details` is `LspToolDetails`: `action`, `success`, optional `serverName`, optional original `request`.\n- No streaming updates.\n- No artifact URIs or background jobs.\n- Many validation failures are returned as ordinary text results with `details.success: false`; aborts throw `ToolAbortError` instead.\n\n## Flow\n1. `packages/coding-agent/src/tools/index.ts` registers `lsp: LspTool.createIf`; session creation also gates it behind `session.enableLsp !== false` and `settings.get(\"lsp.enabled\")`.\n2. `LspTool.execute()` in `packages/coding-agent/src/lsp/index.ts` clamps `timeout` with `clampTimeout(\"lsp\", ...)`, builds an `AbortSignal.timeout(...)`, and combines it with the caller signal.\n3. `getConfig()` loads and caches `LspConfig` per cwd, applies idle-timeout config via `setIdleTimeout()`, and reuses the cached config on later calls.\n4. Config loading in `packages/coding-agent/src/lsp/config.ts` merges `defaults.json` with JSON/YAML overrides from project, project config dirs, user config dirs, plugin roots, and home; if there are no overrides it auto-detects servers from root markers plus executable discovery.\n5. Server routing uses `getServersForFile()` / `getServerForFile()` from `config.ts`: extension or basename match, then sort primary servers before linters. `index.ts` further filters custom linter clients out of navigation/refactor paths with `getLspServersForFile()` / `getLspServerForFile()`.\n6. `getOrCreateClient()` in `client.ts` creates one process per `command:cwd`, optionally wraps supported commands with `lspmux`, spawns the server, starts the background message reader, sends `initialize`, stores server capabilities, then sends `initialized`.\n7. The message reader in `client.ts` parses LSP frames, resolves pending requests, caches `publishDiagnostics`, tracks `$/progress` tokens for project-load completion, answers `workspace/configuration`, and applies `workspace/applyEdit` requests through `applyWorkspaceEdit()`.\n8. File-scoped actions call `ensureFileOpen()` before requests. Column resolution uses `resolveSymbolColumn()` from `utils.ts`: read the target file, pick first non-whitespace when `symbol` is omitted, otherwise find the exact or case-insensitive match on the target line and honor `#N` occurrence selectors.\n9. Actions dispatch in `LspTool.execute()` through dedicated branches: workspace-only branches (`status`, some `diagnostics`, workspace `symbols`, workspace `reload`, `capabilities`, `request`) run before the single-file switch; all other single-file actions share one client lookup and `switch(action)`.\n10. Requests go through `sendRequest()` in `client.ts`, which allocates an incrementing JSON-RPC id, installs abort and timeout handling, sends `$/cancelRequest` on abort, and rejects on timeout or process exit.\n11. Actions that return edits either preview with `formatWorkspaceEdit()` or apply with `applyWorkspaceEdit()` from `edits.ts`; `rename_file` also performs the filesystem rename and then sends `workspace/didRenameFiles`.\n12. Non-abort failures inside the single-file action block are converted to `LSP error: ...`; many precondition failures return explicit text without throwing.\n\n## Modes / Variants\n### Routing and workspace scope\n- `file: \"*\"` is only special for `diagnostics`, `symbols`, and `reload`.\n- `status` ignores `file`.\n- `capabilities` with omitted `file` or `\"*\"` inspects all non-custom LSP servers; with a concrete file it scopes to matching non-custom servers.\n- `request` with omitted `file` or `\"*\"` chooses the first available non-custom LSP server; with a concrete file it chooses that file's primary non-linter server.\n- `rename_file` sends `workspace/willRenameFiles` and `workspace/didRenameFiles` to every non-custom LSP server from `getLspServers(config)`, not just one file-scoped server.\n- Diagnostics are the only tool action that queries both normal LSP servers and custom linter clients (`BiomeClient`, `SwiftLintClient`, or `LspLinterClient`).\n\n### `diagnostics`\n**Inputs**\n- Required: `file`, unless using workspace mode with `file: \"*\"`.\n- Optional: `timeout`.\n\n**Execution**\n- `file: \"*\"`: `runWorkspaceDiagnostics()` detects project type from root markers and runs one subprocess command: Rust `cargo check --message-format=short`, TypeScript `npx tsc --noEmit`, Go `go build ./...`, Python `pyright`.\n- Concrete file or glob: `resolveDiagnosticTargets()` treats non-globs as one target, otherwise expands a `Bun.Glob` up to `MAX_GLOB_DIAGNOSTIC_TARGETS`.\n- Per file, every matching server runs: custom clients call `lint(file)`; real LSP servers optionally wait for project load, capture `diagnosticsVersion`, `refreshFile()`, then `waitForDiagnostics()` for fresh `publishDiagnostics`.\n- Results are deduplicated by range+message and severity-sorted.\n\n**Output text**\n- Single target with no issues: `OK`.\n- Single target with issues: `<summary>:\\n<grouped diagnostics>`.\n- Batch/glob target: one section per file, plus an initial truncation warning when the glob exceeds the file cap.\n- Workspace mode: `Workspace diagnostics (<detected description>):\\n<command output>`.\n\n### `definition`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/definition` with `{ textDocument, position }`.\n- Accepts `Location`, `Location[]`, `LocationLink`, or `LocationLink[]`; `normalizeLocationResult()` converts `LocationLink` to `targetSelectionRange ?? targetRange`.\n- Waits for project load before the request.\n\n**Output text**\n- `No definition found` or `Found N definition(s):` followed by `file:line:col` and one context line above/below each location.\n\n### `type_definition`\nSame as `definition`, but sends `textDocument/typeDefinition` and reports `type definition(s)`.\n\n### `implementation`\nSame as `definition`, but sends `textDocument/implementation` and reports `implementation(s)`.\n\n### `references`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/references` with `includeDeclaration: true`.\n- For project-aware servers, retries up to `REFERENCES_RETRY_COUNT` times when the only hit is the queried declaration; between retries it waits for project load and sleeps `REFERENCES_RETRY_DELAY_MS`.\n- First `REFERENCE_CONTEXT_LIMIT` references include surrounding context; the rest are location-only.\n\n**Output text**\n- `No references found` or `Found N reference(s):` with contextual entries first, then `... M additional reference(s) shown without context` when truncated.\n\n### `hover`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `timeout`.\n\n**Execution**\n- Sends `textDocument/hover`.\n- `extractHoverText()` flattens strings, markup content, marked-string objects, or arrays into plain text.\n\n**Output text**\n- `No hover information` or the extracted hover text.\n\n### `symbols`\n**Inputs**\n- Workspace mode: `file: \"*\"` or omitted file on the early workspace branch, plus required `query`.\n- Document mode: required `file`.\n- Optional: `timeout`.\n\n**Execution**\n- Workspace mode sends `workspace/symbol` to every non-custom LSP server, post-filters matches with `filterWorkspaceSymbols()`, deduplicates with `dedupeWorkspaceSymbols()`, then truncates to `WORKSPACE_SYMBOL_LIMIT`.\n- Document mode sends `textDocument/documentSymbol` to the primary server. If the first item has `selectionRange`, it formats hierarchical `DocumentSymbol`s; otherwise it formats flat `SymbolInformation`s.\n\n**Output text**\n- Workspace mode: `Found N symbol(s) matching \"query\":` plus formatted `name @ file:line:col`, with an omission line when over the limit.\n- Document mode: `Symbols in <file>:` plus hierarchical or flat symbol lines.\n\n### `rename`\n**Inputs**\n- Required: `file`, `new_name`.\n- Optional: `line`, `symbol`, `apply`, `timeout`.\n\n**Execution**\n- Waits for project load, sends `textDocument/rename`, receives a `WorkspaceEdit`.\n- `apply !== false` applies edits immediately with `applyWorkspaceEdit()`.\n- `apply === false` renders a preview with `formatWorkspaceEdit()`.\n\n**Output text**\n- `Rename returned no edits`, `Applied rename:` plus applied change lines, or `Rename preview:` plus summarized edits.\n\n### `rename_file`\n**Inputs**\n- Required: `file` source path, `new_name` destination path.\n- Optional: `apply`, `timeout`.\n\n**Execution**\n- Resolves absolute source and destination, rejects identical paths, missing source, existing destination, empty rename set, or directories with more than `MAX_RENAME_PAIRS` files.\n- `enumerateRenamePairs()` returns one `{oldUri,newUri}` pair for a file or walks every regular file in a directory tree.\n- Sends `workspace/willRenameFiles` with `{ files: pairs }` to every non-custom LSP server; collects returned `WorkspaceEdit`s and server notes.\n- Preview mode (`apply === false`) only formats those edits.\n- Apply mode runs each returned `WorkspaceEdit`, renames the source path on disk, sends `textDocument/didClose` for every renamed open file, deletes those `openFiles` entries, then sends `workspace/didRenameFiles`.\n\n**Output text**\n- Preview: `Rename preview: <file-count label> → <dest>` plus per-server edit summaries and optional server notes.\n- Apply: `Renamed <file-count label> → <dest>` plus applied edit summaries, filesystem rename line, and optional server notes.\n\n### `code_actions`\n**Inputs**\n- Required: `file`.\n- Optional: `line`, `symbol`, `query`, `apply`, `timeout`.\n\n**Execution**\n- Reads cached diagnostics for the open URI from `client.diagnostics` and sends `textDocument/codeAction` for a zero-width range at the resolved position.\n- When `apply !== true`, `query` is passed as `context.only: [query]`; this is a server-side kind filter.\n- When `apply === true`, `query` becomes a required client-side selector: either a zero-based numeric index or a case-insensitive substring of the action title.\n- Applying a `CodeAction` uses `applyCodeAction()`: optionally `codeAction/resolve`, then `applyWorkspaceEdit(edit)`, then optional `workspace/executeCommand`.\n- Applying a bare `Command` only runs `workspace/executeCommand`.\n\n**Output text**\n- List mode: `N code action(s):` plus `index: [kind] title` lines.\n- Apply mode success: `Applied \"title\":` plus `Workspace edit:` and/or `Executed command(s):` sections.\n- Apply mode miss: `No code action matches \"query\". Available actions:`.\n- Apply mode with no edit/command: `Action \"title\" has no workspace edit or command to apply`.\n\n### `status`\n**Inputs**\n- None.\n\n**Execution**\n- Reads configured servers from cached `LspConfig`, not `getActiveClients()`.\n- Calls `detectLspmux()` and appends status text when `lspmux` is installed.\n\n**Output text**\n- `Active language servers: ...` or `No language servers configured for this project`, optionally followed by `lspmux: active (multiplexing enabled)` or `lspmux: installed but server not running`.\n\n### `reload`\n**Inputs**\n- Workspace mode: `file: \"*\"` or omitted `file`.\n- Single-file mode: required `file`.\n- Optional: `timeout`.\n\n**Execution**\n- Workspace mode reloads every non-custom LSP server.\n- Single-file mode reloads the primary server for that file.\n- `reloadServer()` tries `rust-analyzer/reloadWorkspace`, then `workspace/didChangeConfiguration` with `{ settings: {} }`; if neither works it kills the process so the next request cold-starts a new client.\n\n**Output text**\n- One line per server: `Reloaded <server>`, `Restarted <server>`, or `Failed to reload <server>: ...`.\n\n### `capabilities`\n**Inputs**\n- Optional: `file`, `timeout`.\n\n**Execution**\n- With a concrete `file`, inspects matching non-custom servers for that file.\n- With omitted `file` or `\"*\"`, inspects every non-custom configured server.\n- Starts servers as needed and dumps `client.serverCapabilities ?? {}` as pretty JSON.\n\n**Output text**\n- Per server: `<server>:` followed by indented `capabilities: { ... }`, or `<server>: failed to start (...)`.\n\n### `request`\n**Inputs**\n- Required: `query` method name.\n- Optional: `file`, `line`, `symbol`, `payload`, `timeout`.\n\n**Execution**\n- Chooses one non-custom server: file-scoped primary server, otherwise the first configured non-custom server.\n- Param building precedence:\n  1. If `payload` is present, parse JSON and use it verbatim.\n  2. Else if `file` is concrete and `line` is present, build `{ textDocument: { uri }, position: { line: line - 1, character } }` using `resolveSymbolColumn()`.\n  3. Else if `file` is concrete, build `{ textDocument: { uri } }`.\n  4. Else use `{}`.\n- Opens the file first when `file` is concrete.\n\n**Output text**\n- Success: `<server> ← <method>:\\n<formatted result>`, where non-string results are `JSON.stringify(..., null, 2)` and nullish values become `null`.\n- Failure: `LSP error from <server> on <method>: ...`.\n\n## Side Effects\n- Filesystem\n  - Reads config files, target files, and root markers.\n  - `rename` and `code_actions` may edit/create/delete/rename files via `applyWorkspaceEdit()`.\n  - `rename_file` always renames the source path on disk in apply mode.\n  - Server-initiated `workspace/applyEdit` requests also mutate files through `applyWorkspaceEdit()`.\n- Network\n  - None directly; communication is local stdio JSON-RPC to subprocesses.\n- Subprocesses / native bindings\n  - Spawns language servers with `ptree.spawn()`.\n  - Workspace diagnostics spawns `cargo`, `npx`, `go`, or `pyright`.\n  - `BiomeClient` and `SwiftLintClient` spawn CLI tools.\n  - Optional `lspmux` detection spawns `lspmux status`; supported servers may be wrapped through `lspmux client`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Caches config per cwd in `configCache`.\n  - Caches LSP clients per `command:cwd`, with `pendingRequests`, `diagnostics`, `openFiles`, `serverCapabilities`, and project-load state.\n  - Caches custom linter clients by `serverName:cwd`.\n  - Updates client `lastActivity`; optional idle-timeout cleanup is driven by `setIdleTimeout()`.\n- Background work / cancellation\n  - Every request has an abortable timeout signal.\n  - Aborting an in-flight LSP request sends `$/cancelRequest`.\n  - Background message readers persist for each live client until process exit/shutdown.\n\n## Limits & Caps\n- Tool timeout clamp: default `20`, min `5`, max `60` seconds — `TOOL_TIMEOUTS.lsp` in `packages/coding-agent/src/tools/tool-timeouts.ts`.\n- LSP request default timeout inside `sendRequest()`: `30_000ms` — `DEFAULT_REQUEST_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Warmup initialize timeout default: `5_000ms` — `WARMUP_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Project-load wait fallback: `15_000ms` — `PROJECT_LOAD_TIMEOUT_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Idle-client sweep interval when enabled: `60_000ms` — `IDLE_CHECK_INTERVAL_MS` in `packages/coding-agent/src/lsp/client.ts`.\n- Diagnostic message output cap: first `50` messages — `DIAGNOSTIC_MESSAGE_LIMIT` in `packages/coding-agent/src/lsp/index.ts`.\n- Single-file diagnostics wait: `3_000ms` — `SINGLE_DIAGNOSTICS_WAIT_TIMEOUT_MS`.\n- Batch/glob diagnostics wait per file: `400ms` — `BATCH_DIAGNOSTICS_WAIT_TIMEOUT_MS`.\n- Glob diagnostic target cap: first `20` matches — `MAX_GLOB_DIAGNOSTIC_TARGETS`.\n- Workspace symbol cap: first `200` entries — `WORKSPACE_SYMBOL_LIMIT`.\n- Reference context cap: first `50` references include source context — `REFERENCE_CONTEXT_LIMIT`.\n- References retry count: `2` retries, `250ms` backoff — `REFERENCES_RETRY_COUNT`, `REFERENCES_RETRY_DELAY_MS`.\n- Directory rename cap: `1_000` file pairs — `MAX_RENAME_PAIRS`.\n- `detectLspmux()` state cache TTL: `5 * 60 * 1000ms`; liveness check timeout: `1_000ms` — `STATE_CACHE_TTL_MS`, `LIVENESS_TIMEOUT_MS` in `packages/coding-agent/src/lsp/lspmux.ts`.\n- Workspace diagnostics output cap: first `50` lines from the subprocess.\n\n## Errors\n- Missing or invalid inputs are usually returned as text with `details.success: false`, not thrown:\n  - missing `file`/`query`/`new_name`\n  - invalid JSON in `payload`\n  - no matching server\n  - invalid `rename_file` source/destination conditions\n- `resolveSymbolColumn()` throws explicit errors for missing files, missing symbols, and out-of-bounds `#N` selectors; these surface as `LSP error: ...` or request-specific error text.\n- `sendRequest()` rejects on timeout with `LSP request <method> timed out after <ms>ms`.\n- Client process exit rejects all pending requests with an exit-code/stderr error assembled in `getOrCreateClient()`.\n- Single-file action failures inside the main `try` become `LSP error: <message>`.\n- `request` has its own error envelope: `LSP error from <server> on <method>: <message>`.\n- Some server failures are intentionally softened:\n  - diagnostics continue when one server fails\n  - `rename_file` suppresses `workspace/willRenameFiles` “method not found” errors and records other server errors as notes\n  - `code_actions` ignores `codeAction/resolve` failures and applies unresolved actions when possible\n- Aborts are not converted to text: `ToolAbortError` is rethrown.\n\n## Notes\n- `status` reports configured/available servers from `LspConfig`, not currently active client processes from `getActiveClients()`.\n- `getLspServerForFile()` excludes `createClient` adapters and linter-only servers; navigation/refactor actions never target Biome/SwiftLint custom clients.\n- `getServersForFile()` matches both file extensions and exact basenames from `fileTypes`; config can target names like `Dockerfile` if present.\n- `symbol` matching is exact first, then case-insensitive, and falls back to the Nth occurrence on the specified line only; it never scans other lines.\n- `code_actions` uses `query` in two different ways: server-side `context.only` filter in list mode, client-side title/index selector in apply mode.\n- `rename` and `rename_file` default to apply. Preview requires `apply: false`.\n- `request` with `file: \"*\"` is treated the same as omitted `file`: it does not build workspace-specific params.\n- `reload` does not recreate a client immediately after killing it; the next request triggers reinitialization.\n- `workspace/applyEdit` can apply edits initiated by the server outside the direct tool action result path.\n- `detectLspmux()` can be disabled with `GJC_DISABLE_LSPMUX=1`; only `rust-analyzer` is in `DEFAULT_SUPPORTED_SERVERS`.\n- Startup LSP warmup (`discoverStartupLspServers(cwd)` in `sdk.ts`) is gated on `enableLsp && options.hasUI && settings.get(\"lsp.diagnosticsOnWrite\")` — print/RPC/ACP/script sessions skip it and let `getOrCreateClient()` cold-start servers on demand. See `docs/sdk.md` § Startup performance.\n- `configCache` is per-process and never auto-invalidated; config changes require a fresh process to be observed by `getConfig()` callers.",
 	"tools/monitor.md": "# monitor\n\n> Start a background monitor that streams stdout lines as task notifications. Mirrors Claude Code's `Monitor` tool surface.\n\n## Source\n\n- Entry: `packages/coding-agent/src/tools/monitor.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/monitor.md`\n- Key collaborators:\n  - `packages/coding-agent/src/async/job-manager.ts` — stores the captured stream via `appendOutput`/`readOutputSince` and delivers the final background-job result.\n  - `packages/coding-agent/src/exec/bash-executor.ts` and `packages/coding-agent/src/session/streaming-output.ts` — provide the unthrottled `onRawChunk` capture hook that feeds the manager.\n  - `packages/coding-agent/src/tools/bash.ts` — exposes `BashTool.startMonitorJob(...)`, a Bash-aligned helper that preserves interception, cwd/env expansion, artifacts, timeouts, and raw stream capture.\n  - `packages/coding-agent/src/tools/job.ts` — polls/cancels the monitor task by id; there is no sibling `MonitorKill` tool.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `command` | `string` | Yes | Shell command to run as a background monitor. Each sanitized stdout line is delivered as a task-notification. |\n| `kind` | `\"log\" \\| \"poll\" \\| \"watch\" \\| \"other\"` | Yes | Category of monitor. Surfaces in listings. |\n| `description` | `string` | Yes | Short human-readable summary of what is being monitored. |\n| `timeout` | `number` | No | Maximum wall-clock seconds the monitor may run before automatic shutdown. Omit for session lifetime. |\n| `persistent` | `boolean` | No | Keep the monitor running after its first emitted event. Persistent monitors survive until session end, timeout, or explicit cancel via `job`. Defaults to `false`. |\n\n## Outputs\n\nThe tool returns one text block plus `details`:\n\n- `content[0].text`: `Monitor started · task <task_id> · persistent: true|false`.\n- `details`: `{ taskId, kind, description, command, persistent }`.\n\nEach newline-terminated stdout line is appended to the manager-owned cursor and sent to the agent as a `<task-notification>` custom message between turns. Use `job` with the returned `taskId` to inspect completion state or terminate the monitor.\n\n## Behavior / Lifecycle\n\n1. `MonitorTool.createIf(session)` gates the tool on `isBackgroundJobSupportEnabled(session.settings)` — identical to `JobTool`'s gate.\n2. `execute(...)` delegates to `BashTool.startMonitorJob(...)`, so Monitor inherits Bash's interception rules, cwd normalization, internal URL expansion, environment construction, artifact allocation, timeout clamping, and unthrottled raw capture.\n3. The helper mirrors every sanitized raw chunk to `manager.appendOutput(jobId, chunk)` and line-buffers the stream so each stdout line dispatches one `<task-notification>` event.\n4. Non-persistent monitors auto-cancel after delivering their first stdout-line notification. Persistent monitors terminate when the underlying command exits, `timeout` elapses, the calling agent is torn down, or the user cancels the returned background task via `job`.\n\n## Errors\n\n- `ToolError`: `Async execution is disabled; the monitor tool is unavailable in this session.` — emitted when `AsyncJobManager.instance()` returns `undefined`.\n- Invalid parameter shapes are rejected by zod with the project's standard validation error path.\n\n## Examples\n\nTail an error log and react when lines appear:\n\n```jsonc\n{\n  \"command\": \"tail -F /var/log/app.log | grep -i error\",\n  \"kind\": \"log\",\n  \"description\": \"Tail app.log for errors\"\n}\n```\n\nPoll CI status until the build completes (15-minute timeout):\n\n```jsonc\n{\n  \"command\": \"while true; do gh run view --json status,conclusion --jq .status; sleep 30; done\",\n  \"kind\": \"poll\",\n  \"description\": \"Watch CI build status\",\n  \"timeout\": 900,\n  \"persistent\": false\n}\n```\n\n## Parity oracle\n\nThe schema and behavior captured in this doc are pinned by the fixture at\n`packages/coding-agent/test/fixtures/claude-code-tools/monitor.schema.json`,\ncaptured from the upstream Claude Code CLI (`claude --version 2.1.152`). Any\ndeviation from that fixture is a parity bug.\n",
-	"tools/read.md": "# read\n\n> Read files, directories, archives, SQLite databases, internal resources, images, documents, and URLs through one `path` string.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/read.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/read.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/path-utils.ts` — split `path` from trailing selectors; normalize local paths.\n  - `packages/coding-agent/src/tools/archive-reader.ts` — detect `archive.ext:inner/path`, index archives, list/read entries.\n  - `packages/coding-agent/src/tools/sqlite-reader.ts` — detect SQLite targets, parse selectors, render tables.\n  - `packages/coding-agent/src/tools/fetch.ts` — URL parsing, fetch/render pipeline, URL cache/artifacts.\n  - `packages/coding-agent/src/internal-urls/router.ts` — resolve `agent://`, `artifact://`, `local://`, `memory://`, `gjc://`, and `rule://`.\n  - `packages/coding-agent/src/edit/notebook.ts` — convert `.ipynb` to editable `# %% [...] cell:N` text.\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — decide hashline vs line-number vs raw display.\n  - `packages/coding-agent/src/workspace-tree.ts` — render directory trees.\n  - `packages/coding-agent/src/edit/file-read-cache.ts` — cache read lines for later hashline edit recovery.\n  - `packages/coding-agent/src/tools/index.ts` — registers `read: s => new ReadTool(s)`.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `path` | `string` | Yes | Filesystem path, internal URL, or web URL. May end with a trailing selector such as `:50-100` or `:raw`. |\n\n### Selector grammar\n\nFor normal file-like reads, `splitPathAndSel()` in `packages/coding-agent/src/tools/path-utils.ts` recognizes the final suffix only when it matches one of these forms:\n\n| Suffix | Meaning |\n| --- | --- |\n| `:raw` | Raw/verbatim mode. Disables structural summaries and line prefixes. |\n| `:N` / `:LN` | Start at 1-indexed line `N`, open-ended. |\n| `:A-B` / `:LA-LB` | Inclusive 1-indexed line range. |\n| `:A+C` / `:LA+LC` | `C` lines starting at `A`; tool converts this to end line `A + C - 1`. |\n| `:range:raw` or `:raw:range` | Same line selection, but raw output. |\n\nValidation in `parseLineRangeChunk()`:\n- line numbers are 1-indexed; `:0` throws.\n- `+` counts must be `>= 1`.\n- `-` end must be `>= start`.\n\nSelector parsing intentionally falls through for unrecognized trailing `:...`; archive and SQLite paths consume their own colon syntax.\n\nURL selectors are parsed separately in `packages/coding-agent/src/tools/fetch.ts` and support only `:raw`, `:N`, `:A-B`, and `:A+C` — no optional `L` prefix there.\n\n## Outputs\n- Single-shot `AgentToolResult` built through `toolResult()` in `packages/coding-agent/src/tools/tool-result.ts`.\n- `content` is usually one text block. Image reads may return `[text, image]`.\n- `details` is path-dependent. `ReadToolDetails` may include:\n  - `kind: \"file\" | \"url\"` (URL path uses `kind: \"url\"`; file reads usually omit `kind`)\n  - `isDirectory`\n  - `resolvedPath`\n  - `suffixResolution`\n  - URL fields: `url`, `finalUrl`, `contentType`, `method`, `notes`\n  - `truncation`\n  - `displayContent` (unprefixed text + starting line for TUI rendering)\n  - `summary` (`lines`, `elidedSpans`, `elidedLines`) for structural summaries\n  - `meta` from `packages/coding-agent/src/tools/output-meta.ts`\n- `details.meta.source` is set to the backing path, URL, or internal URL.\n- `details.meta.truncation` carries shown range, total lines/bytes, next offset, and optional `artifactId` for cached URL output.\n- Directory/archive listings and SQLite table lists also set `details.meta.limits` when list limits trigger.\n\n## Flow\n1. `ReadTool.execute()` accepts `{ path }`. `file://...` inputs are expanded first with `expandPath()`.\n2. It tries URL handling first via `parseReadUrlTarget()` from `packages/coding-agent/src/tools/fetch.ts`.\n   - Plain URL reads call `executeReadUrl()`.\n   - URL reads with line selectors load or refresh the URL cache with `loadReadUrlCacheEntry()` and paginate the cached text locally with `#buildInMemoryTextResult()`.\n3. If not a web URL, it checks `session.internalRouter.canHandle(...)`.\n   - Internal URLs are resolved with `internalRouter.resolve()`.\n   - `agent://` query extraction (`/path` or `?q=`) bypasses pagination and returns the extracted content directly.\n   - Other internal resources are paginated in-memory by `#buildInMemoryTextResult()`.\n4. It tries archive resolution next with `#resolveArchiveReadPath()`.\n   - `parseArchivePathCandidates()` scans for `.tar`, `.tar.gz`, `.tgz`, or `.zip` anywhere before `:sub/path`.\n   - On success, `#readArchive()` either lists a directory or decodes an entry as UTF-8 text.\n5. It tries SQLite resolution with `#resolveSqliteReadPath()`.\n   - `parseSqlitePathCandidates()` scans for `.sqlite`, `.sqlite3`, `.db`, `.db3` before any `:table`, `:key`, or `?query` suffix.\n   - `#readSqlite()` dispatches on `parseSqliteSelector()`.\n6. Otherwise it treats the input as a local filesystem path.\n   - `resolveReadPath()` expands `~`, resolves relative to session cwd, treats bare `/` as session cwd, and retries macOS screenshot/NFD/curly-quote variants.\n   - If the path does not exist, `findUniqueSuffixMatch()` does a workspace glob-based unique suffix lookup (skipped for remote mounts).\n7. Directories go through `#readDirectory()`.\n8. Non-directories branch by content type:\n   - image metadata / inline image\n   - editable notebook text\n   - markit-converted document\n   - structural summary for parseable code/prose\n   - streamed text/line-range read\n9. Local text reads are streamed by `streamLinesFromFile()` rather than loading the whole file. The tool adds up to 3 lines of context before/after explicit bounded ranges.\n10. Non-empty contiguous local reads are recorded into `getFileReadCache(session)` for later hashline edit recovery.\n11. If suffix resolution happened, the first text block is prefixed with `[Path '...' not found; resolved to '...' via suffix match]`.\n\n## Modes / Variants\n\n### Local text files\n- No selector: if summarization is enabled and the file is small enough, `#trySummarize()` calls `summarizeCode()`.\n  - Guards: file size `<= 2 MiB` (`MAX_SUMMARY_BYTES`), line count `<= 20_000` (`MAX_SUMMARY_LINES`).\n  - Summary output keeps selected declarations and replaces elided spans with `...`. When at least one span is elided, the text content ends with a footer like `[NN lines across MM elided regions; read <path>:raw or a line range like <path>:1-9999 for verbatim content]` so the agent has a concrete recovery selector instead of a bare marker.\n  - When an elided block sits between matching brace lines, `#renderSummary()` may merge them into one anchored line rather than emitting separate opener/closer lines.\n- Explicit selector or summarization miss: streamed text read.\n  - Default open-ended limit is `min(session setting read.defaultLimit, DEFAULT_MAX_LINES)`.\n  - Explicit ranges expand by `RANGE_LEADING_CONTEXT_LINES = 1` / `RANGE_TRAILING_CONTEXT_LINES = 3` on the constrained sides only.\n  - Non-raw output uses `resolveFileDisplayMode()`:\n    - hashline anchors when edit mode is hashline, read is not raw, source is mutable, edit tool exists, and `readHashLines !== false`\n    - otherwise optional line numbers when `readLineNumbers === true`\n    - raw mode suppresses both\n- Prefix format in hashline mode is `lineNumber + 2-char line hash + \"|\"`, e.g. `41th|def alpha():`, from `formatHashLine()` in `packages/coding-agent/src/hashline/hash.ts`.\n- Those anchors are what the `edit`/hashline path consumes later; immutable sources and `:raw` intentionally suppress them.\n\n### Directory listings\n- `#readDirectory()` calls `buildDirectoryTree()` with:\n  - `maxDepth = 2`\n  - `perDirLimit = 12`\n  - `rootLimit = null`\n  - `lineCap = limit` when a line selector was present, else unlimited at this layer\n- `buildDirectoryTree()` sorts siblings by recency, shows file sizes and relative ages, and may mark `limits.resultLimit` when the tree truncates.\n- Empty directories render as `(empty directory)`.\n\n### Archives\n- Supported archive containers: `.tar`, `.tar.gz`, `.tgz`, `.zip`.\n- Syntax: `archive.ext`, `archive.ext:path/inside`, `archive.ext:path/inside:50-60`.\n- `openArchive()` reads the whole archive into memory, then:\n  - tar/tgz uses `new Bun.Archive(bytes)`\n  - zip uses `fflate.unzipSync()`\n- Archive paths normalize `/`, drop `.` segments, and reject `..`.\n- Directory reads list immediate children; files show `name` plus ` (size)` when size > 0.\n- Directory listing default limit is `500` entries in `#readArchiveDirectory()`.\n- File entries are UTF-8 decoded. Non-UTF-8 entries return `[Cannot read binary archive entry '...' (...)]` instead of bytes.\n- Text archive entries reuse the normal in-memory pagination/anchoring path.\n\n### SQLite databases\n- Database detection requires both a matching extension and a valid SQLite file header (`isSqliteFile()`).\n- Selector forms from `parseSqliteSelector()`:\n\n#### `db.sqlite`\n- `kind: \"list\"`\n- Lists non-`sqlite_%` tables with row counts.\n- `#readSqlite()` caps the rendered list to `500` tables via `applyListLimit()`.\n\n#### `db.sqlite:table`\n- `kind: \"schema\"`\n- Returns `sqlite_master.sql` plus sample rows.\n- Sample size is `DEFAULT_SCHEMA_SAMPLE_LIMIT = 5`.\n\n#### `db.sqlite:table:key`\n- `kind: \"row\"`\n- Resolves by primary key when the table has exactly one PK column; otherwise falls back to `rowid` lookup.\n- No query parameters allowed on row lookups.\n\n#### `db.sqlite:table?limit=...&offset=...&order=...&where=...`\n- `kind: \"query\"`\n- Defaults: `limit = 20`, `offset = 0`.\n- `limit` is capped at `500`.\n- `order` accepts `column` or `column:asc|desc` and must name an existing column.\n- `where` is accepted only after `validateWhereClause()` rejects comments, semicolons, and control keywords like `LIMIT`, `OFFSET`, `UNION`, `ATTACH`, `PRAGMA`.\n- Unknown query parameters throw.\n\n#### `db.sqlite?q=SELECT ...`\n- `kind: \"raw\"`\n- Cannot be combined with table selectors or any other query param.\n- Empty `q` throws.\n- `executeReadQuery()` runs `db.prepare(sql).all()` and rejects bound parameters; it does not verify that the SQL starts with `SELECT`.\n\n- Rendering caps in `packages/coding-agent/src/tools/sqlite-reader.ts`:\n  - ASCII table width `120` (`MAX_RENDER_WIDTH`)\n  - per-column width `40` (`MAX_COLUMN_WIDTH`)\n- `#readSqlite()` opens Bun SQLite in `{ readonly: true, strict: true }` and sets `PRAGMA busy_timeout = 3000`.\n\n### Documents\n- `CONVERTIBLE_EXTENSIONS` in `packages/coding-agent/src/tools/read.ts` covers `.pdf`, `.doc`, `.docx`, `.ppt`, `.pptx`, `.xls`, `.xlsx`, `.rtf`, `.epub`.\n- `convertFileWithMarkit()` converts the file to text/markdown.\n- Converted output is then head-truncated with normal shared limits; there is no line selector support inside the source document before conversion.\n- Conversion failures return a text block like `[Cannot read .pdf file: ...]`.\n\n### Jupyter notebooks\n- `.ipynb` goes through `readEditableNotebookText()` unless `:raw` was requested.\n- Output is editable plain text with markers like:\n\n```text\n# %% [code] cell:0\n...\n```\n\n- Raw mode bypasses that conversion and falls back to file-text reading.\n\n### Images\n- Image detection is metadata-based (`readImageMetadata()`).\n- Max accepted image size is `20 MiB` (`MAX_IMAGE_INPUT_BYTES`, re-exported as `MAX_IMAGE_SIZE`). Larger files throw.\n- If `inspect_image.enabled` is true, `read` returns metadata only (MIME, bytes, dimensions, channels, alpha) plus a suggestion to call `inspect_image`.\n- Otherwise it calls `loadImageInput()` and returns:\n  - a text note from the image loader\n  - an inline image block\n- Unsupported/undecodable image formats throw a `ToolError`.\n\n### Internal URLs\n- `read` does not resolve these itself; it delegates to `session.internalRouter.resolve()`.\n- Registered protocols are outside this file, but the router in `packages/coding-agent/src/internal-urls/router.ts` is built for `agent://`, `artifact://`, `issue://`, `local://`, `memory://`, `gjc://`, `pr://`, and `rule://`.\n- `#handleInternalUrl()` behavior:\n  - parses the URL with `parseInternalUrl()` so colons inside the host segment are legal\n  - for `agent://`, treats non-root path extraction or `?q=` extraction as a special no-pagination mode\n  - otherwise paginates the resolved text in memory\n  - passes `immutable` through to `resolveFileDisplayMode()` so anchors are suppressed for immutable resources such as artifacts, memory, and agent outputs\n- `issue://<N>` / `pr://<N>` (and the long form `issue://<owner>/<repo>/<N>` / `pr://<owner>/<repo>/<N>`) route through the same SQLite cache the `github` tool writes to; `?comments=0` selects the no-comments rendering. Bare `issue://` / `pr://` (and `issue://<owner>/<repo>` / `pr://<owner>/<repo>`) issue a live `gh issue list` / `gh pr list` for browsing, accepting `?state=`, `?limit=`, `?author=`, `?label=`. PR diffs share the same cache through `pr://<N>/diff` (numbered file listing with per-file hints), `pr://<N>/diff/<i>` (single file slice; 1-indexed), and `pr://<N>/diff/all` (verbatim unified diff); the listing and per-file slices are reconstructed from the cached unified-diff payload, so all three variants share one `gh pr diff` invocation per PR. Diff content is served as `text/plain`. Soft TTL `github.cache.softTtlSec` (default 5 minutes), hard TTL `github.cache.hardTtlSec` (default 7 days). Stale-hit returns the cached row and schedules a background refresh.\n\n### Web URLs\n- `parseReadUrlTarget()` accepts `http://`, `https://`, or `www.` targets.\n- Plain URL reads call `executeReadUrl()` in `packages/coding-agent/src/tools/fetch.ts`.\n- `:raw` means raw HTML/body fallback path; plain URL reads prefer rendered/reader-friendly output.\n- `:N`, `:A-B`, `:A+C` do not refetch. They page over cached output from the prior or current URL render.\n- URL render pipeline in `renderUrl()`:\n  1. normalize scheme (`https://` added for bare `www.`)\n  2. try special handlers for known sites unless raw\n  3. fetch with `loadPage()`\n  4. if content is image/PDF/DOCX/etc., try binary fetch + markit/image handling\n  5. handle JSON directly, feeds via feed parser, plain text directly\n  6. for HTML and non-raw mode, try markdown alternates, `URL.md`, content negotiation, feed alternates, HTML-to-text renderers, extracted linked documents, then `llms.txt`\n  7. fall back to raw body text/html\n- URL output is wrapped with a small header:\n\n```text\nURL: ...\nContent-Type: ...\nMethod: ...\nNotes: ...\n\n---\n```\n\n- `method` records the winning path (`json`, `feed`, `text`, `alternate-markdown`, `md-suffix`, `content-negotiation`, `image`, `markit`, `llms.txt`, `raw`, `raw-html`, etc.).\n- URL reads may return an inline image block when the fetched resource is a supported image and survives resizing.\n\n## Side Effects\n- Filesystem\n  - Opens and streams local files.\n  - Reads entire archives into memory before indexing.\n  - May read URL-cache artifact files from the session artifacts directory.\n  - Writes URL output artifacts when URL output is truncated or when line-range pagination needs a persisted cache body.\n- Network\n  - URL mode performs HTTP fetches, binary refetches, and alternate-endpoint probes.\n- Subprocesses / native bindings\n  - Uses Bun SQLite for `.db`/`.sqlite*`.\n  - Uses `Bun.Archive` for tar/tgz and `fflate` for zip.\n  - URL HTML rendering can delegate into site handlers and HTML-to-text backends from `packages/coding-agent/src/tools/fetch.ts`.\n- Session state\n  - Records local text lines into `session.fileReadCache` for later stale-anchor recovery.\n  - Uses `session.internalRouter` for internal URLs.\n  - Uses `session.allocateOutputArtifact()` for cached/truncated URL output.\n- Background work / cancellation\n  - Most branches honor `AbortSignal`; the tool itself is marked `nonAbortable = true`, but helper paths still call `throwIfAborted(signal)`.\n\n## Limits & Caps\n- Shared text truncation defaults from `packages/coding-agent/src/session/streaming-output.ts`:\n  - `DEFAULT_MAX_LINES = 3000`\n  - `DEFAULT_MAX_BYTES = 50 * 1024`\n- Local text open-ended default line limit: `read.defaultLimit`, clamped to `[1, DEFAULT_MAX_LINES]`.\n- Explicit line ranges add `1` leading and `3` trailing context lines on the constrained sides (`RANGE_LEADING_CONTEXT_LINES` / `RANGE_TRAILING_CONTEXT_LINES`).\n- File streaming chunk size: `8 * 1024` bytes (`READ_CHUNK_SIZE`).\n- Local streamed byte budget for line reads: `max(DEFAULT_MAX_BYTES, maxLinesToCollect * 512)`.\n- Structural summaries only run when file size `<= 2 MiB` and line count `<= 20_000`.\n- Image input max: `20 MiB`.\n- Directory tree caps for local directories: depth `2`, per-directory children `12`.\n- Archive directory default list cap: `500` entries.\n- SQLite:\n  - default row query limit `20`\n  - schema sample limit `5`\n  - max query limit `500`\n  - table list cap `500`\n  - render width `120`, column width `40`\n  - busy timeout `3000` ms\n- URL read result shown to the model is truncated to `300` lines and `50 KiB` in `executeReadUrl()`; full cached output can be attached as an artifact.\n- Inline fetched URL images:\n  - source bytes cap `20 MiB`\n  - post-resize inline output cap `300 KiB`\n- Unique suffix auto-resolution glob timeout: `5000` ms.\n- File-read cache holds `30` paths per session.\n\n## Errors\n- Validation and operational failures surface as `ToolError`.\n- Selector errors include:\n  - `Line selector 0 is invalid; lines are 1-indexed. Use :1.`\n  - invalid `A+B` / `A-B` shapes\n  - `Cannot combine query extraction with offset/limit` for `agent://.../path:50`\n- Missing local/archive/sqlite paths first attempt unique suffix resolution; if no unique match exists they error.\n- Out-of-bounds line reads do not throw. They return explanatory text with a suggestion such as `Use :1 ...` or `Use :<last line> ...`.\n- Binary archive entries do not throw; they return a text notice.\n- Document conversion failure returns a text notice.\n- Image oversize/unsupported/invalid cases throw.\n- SQLite parser rejects unsupported parameter combinations early; DB/runtime errors are caught and rethrown as `ToolError(message)`.\n- URL fetch failure does not throw when HTTP fetch succeeds but `response.ok === false`; it returns a failed URL read with `method: \"failed\"` and explanatory notes.\n\n## Notes\n- `readSchema` examples include `https://example.com:L1-L40`, but URL selector parsing in `packages/coding-agent/src/tools/fetch.ts` does not accept `L` prefixes.\n- Hashline anchors are suppressed for raw reads and immutable internal resources because there is no editable backing target for later `edit` consumption.\n- `splitPathAndSel()` intentionally treats unknown trailing `:...` as part of the path so `archive.zip:inner/file` and `db.sqlite:table:key` still work.\n- `resolveReadPath()` contains macOS-specific filename fallbacks for screenshot timestamps, NFD Unicode normalization, and curly apostrophes.\n- A bare `/` resolves to the session cwd, not the filesystem root.\n- URL cache keys are session-scoped and normalized by requested URL + raw/rendered mode; both requested URL and final redirected URL are cached.\n- URL line-range reads request `ensureArtifact: true, preferCached: true` so a later paginated read can reopen the same rendered body from artifact storage.\n- Raw SQLite `q=` execution is not keyword-restricted beyond “no bound parameters”; the read tool relies on the surrounding contract to keep it read-only.\n- The file-read cache is not a read acceleration cache. It exists to recover hashline edits when the file changed after the read.",
-	"tools/recall.md": "# recall\n\n> Search the active Hindsight bank and return raw matching memories.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/hindsight-recall.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/recall.md`\n- Key collaborators:\n  - `packages/coding-agent/src/hindsight/state.ts` — session state, recall query defaults, prompt-side auto-recall.\n  - `packages/coding-agent/src/hindsight/content.ts` — result formatting and UTC timestamp formatting.\n  - `packages/coding-agent/src/hindsight/client.ts` — HTTP `recall` call and error mapping.\n  - `packages/coding-agent/src/hindsight/bank.ts` — bank id and tag-filter scoping.\n  - `docs/tools/retain.md` — shared backend, storage, seeding, and mental-model bootstrap.\n\n## Inputs\n\n| Field | Type | Required | Description |\n|---|---|---:|---|\n| `query` | `string` | Yes | Natural-language search query. The tool passes it through unchanged. |\n\n## Outputs\nReturns a single-shot tool result.\n\nWhen matches exist:\n- `content[0].type = \"text\"`\n- `content[0].text = \"Found <n> relevant memories (as of YYYY-MM-DD HH:MM UTC):\\n\\n<bullet list>\"`\n- each bullet is `- <text> [<type>] (<mentioned_at>)`; the type and timestamp suffixes appear only when those fields are present\n- `details = {}`\n\nWhen no matches exist:\n- `content[0].text = \"No relevant memories found.\"`\n- `details = {}`\n\n## Flow\n1. `HindsightRecallTool.createIf(...)` only exposes the tool when `memory.backend == \"hindsight\"`.\n2. `execute(...)` wraps the whole operation in `untilAborted(...)` from `@gajae-code/utils`.\n3. It reads the active `HindsightSessionState`; missing state throws `Hindsight backend is not initialised for this session.`\n4. It calls `state.client.recall(...)` with:\n   - `bankId` from session bootstrap,\n   - the model-supplied `query`,\n   - `budget`, `maxTokens`, and `types` from `HindsightConfig`,\n   - tag filters from the bank scope (`recallTags`, `recallTagsMatch`).\n5. `HindsightApi.recall(...)` POSTs `/v1/default/banks/{bank_id}/memories/recall`.\n6. Results are formatted into a plain-text list with `formatMemories(...)`; empty results map to the fixed no-match string.\n7. Failures are logged with `logger.warn(\"recall failed\", ...)` and rethrown.\n\n## Modes / Variants\n- Tool path: explicit query-only recall. The tool does not compose context from recent turns; that richer path is reserved for backend auto-recall in `HindsightSessionState.beforeAgentStartPrompt(...)` / `maybeRecallOnAgentStart(...)`.\n- Bank scoping is inherited from the active `HindsightSessionState`:\n  - `global` — no tag filter.\n  - `per-project` — separate bank id per cwd basename.\n  - `per-project-tagged` — shared bank id plus `project:<cwd basename>` filter with `tagsMatch = \"any\"`, so project-tagged and untagged global memories can both surface.\n- Session scope: reads cross-session server-side memories, but uses per-session cached config and scope.\n\n## Side Effects\n- Network\n  - `POST /v1/default/banks/{bank_id}/memories/recall` via `packages/coding-agent/src/hindsight/client.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - None on success. Unlike backend auto-recall, this tool does not update `lastRecallSnippet` or refresh the system prompt.\n- Background work / cancellation\n  - Aborts through `untilAborted(...)` if the tool call signal is cancelled.\n\n## Limits & Caps\n- Client default budget for raw `HindsightApi.recall(...)` is `\"mid\"`; this tool overrides from config in `packages/coding-agent/src/hindsight/state.ts`.\n- Default recall settings from `packages/coding-agent/src/config/settings-schema.ts`:\n  - `hindsight.recallBudget = \"mid\"`\n  - `hindsight.recallMaxTokens = 1024`\n  - `hindsight.recallTypes = [\"world\", \"experience\"]`\n- The explicit tool path does not apply `hindsight.recallContextTurns` or `hindsight.recallMaxQueryChars`; those caps only affect backend auto-recall query composition.\n\n## Errors\n- Throws `Hindsight backend is not initialised for this session.` when no state exists.\n- HTTP and fetch failures become `HindsightError` from `packages/coding-agent/src/hindsight/client.ts` with `statusCode` and parsed `details` when available.\n- Non-`Error` failures are normalized to `new Error(String(err))` before rethrow.\n\n## Notes\n- Shared backend details are in `docs/tools/retain.md`: server-side storage, subagent aliasing, bank scoping, mission setup, and mental-model bootstrap.\n- Mental models are not fetched by this tool. They may still already be present in the agent's developer instructions because the backend caches a `<mental_models>` block separately from recall results.\n- The tool returns raw memory hits; it does not synthesize across them. Use `reflect` for that path.\n",
+	"tools/read.md": "# read\n\n> Read files, directories, archives, SQLite databases, internal resources, images, documents, and URLs through one `path` string.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/read.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/read.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/path-utils.ts` — split `path` from trailing selectors; normalize local paths.\n  - `packages/coding-agent/src/tools/archive-reader.ts` — detect `archive.ext:inner/path`, index archives, list/read entries.\n  - `packages/coding-agent/src/tools/sqlite-reader.ts` — detect SQLite targets, parse selectors, render tables.\n  - `packages/coding-agent/src/tools/fetch.ts` — URL parsing, fetch/render pipeline, URL cache/artifacts.\n  - `packages/coding-agent/src/internal-urls/router.ts` — resolve public internal URLs (`agent://`, `artifact://`, `local://`, `gjc://`, and `rule://`) plus legacy non-public compatibility handlers.\n  - `packages/coding-agent/src/edit/notebook.ts` — convert `.ipynb` to editable `# %% [...] cell:N` text.\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — decide hashline vs line-number vs raw display.\n  - `packages/coding-agent/src/workspace-tree.ts` — render directory trees.\n  - `packages/coding-agent/src/edit/file-read-cache.ts` — cache read lines for later hashline edit recovery.\n  - `packages/coding-agent/src/tools/index.ts` — registers `read: s => new ReadTool(s)`.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `path` | `string` | Yes | Filesystem path, internal URL, or web URL. May end with a trailing selector such as `:50-100` or `:raw`. |\n\n### Selector grammar\n\nFor normal file-like reads, `splitPathAndSel()` in `packages/coding-agent/src/tools/path-utils.ts` recognizes the final suffix only when it matches one of these forms:\n\n| Suffix | Meaning |\n| --- | --- |\n| `:raw` | Raw/verbatim mode. Disables structural summaries and line prefixes. |\n| `:N` / `:LN` | Start at 1-indexed line `N`, open-ended. |\n| `:A-B` / `:LA-LB` | Inclusive 1-indexed line range. |\n| `:A+C` / `:LA+LC` | `C` lines starting at `A`; tool converts this to end line `A + C - 1`. |\n| `:range:raw` or `:raw:range` | Same line selection, but raw output. |\n\nValidation in `parseLineRangeChunk()`:\n- line numbers are 1-indexed; `:0` throws.\n- `+` counts must be `>= 1`.\n- `-` end must be `>= start`.\n\nSelector parsing intentionally falls through for unrecognized trailing `:...`; archive and SQLite paths consume their own colon syntax.\n\nURL selectors are parsed separately in `packages/coding-agent/src/tools/fetch.ts` and support only `:raw`, `:N`, `:A-B`, and `:A+C` — no optional `L` prefix there.\n\n## Outputs\n- Single-shot `AgentToolResult` built through `toolResult()` in `packages/coding-agent/src/tools/tool-result.ts`.\n- `content` is usually one text block. Image reads may return `[text, image]`.\n- `details` is path-dependent. `ReadToolDetails` may include:\n  - `kind: \"file\" | \"url\"` (URL path uses `kind: \"url\"`; file reads usually omit `kind`)\n  - `isDirectory`\n  - `resolvedPath`\n  - `suffixResolution`\n  - URL fields: `url`, `finalUrl`, `contentType`, `method`, `notes`\n  - `truncation`\n  - `displayContent` (unprefixed text + starting line for TUI rendering)\n  - `summary` (`lines`, `elidedSpans`, `elidedLines`) for structural summaries\n  - `meta` from `packages/coding-agent/src/tools/output-meta.ts`\n- `details.meta.source` is set to the backing path, URL, or internal URL.\n- `details.meta.truncation` carries shown range, total lines/bytes, next offset, and optional `artifactId` for cached URL output.\n- Directory/archive listings and SQLite table lists also set `details.meta.limits` when list limits trigger.\n\n## Flow\n1. `ReadTool.execute()` accepts `{ path }`. `file://...` inputs are expanded first with `expandPath()`.\n2. It tries URL handling first via `parseReadUrlTarget()` from `packages/coding-agent/src/tools/fetch.ts`.\n   - Plain URL reads call `executeReadUrl()`.\n   - URL reads with line selectors load or refresh the URL cache with `loadReadUrlCacheEntry()` and paginate the cached text locally with `#buildInMemoryTextResult()`.\n3. If not a web URL, it checks `session.internalRouter.canHandle(...)`.\n   - Internal URLs are resolved with `internalRouter.resolve()`.\n   - `agent://` query extraction (`/path` or `?q=`) bypasses pagination and returns the extracted content directly.\n   - Other internal resources are paginated in-memory by `#buildInMemoryTextResult()`.\n4. It tries archive resolution next with `#resolveArchiveReadPath()`.\n   - `parseArchivePathCandidates()` scans for `.tar`, `.tar.gz`, `.tgz`, or `.zip` anywhere before `:sub/path`.\n   - On success, `#readArchive()` either lists a directory or decodes an entry as UTF-8 text.\n5. It tries SQLite resolution with `#resolveSqliteReadPath()`.\n   - `parseSqlitePathCandidates()` scans for `.sqlite`, `.sqlite3`, `.db`, `.db3` before any `:table`, `:key`, or `?query` suffix.\n   - `#readSqlite()` dispatches on `parseSqliteSelector()`.\n6. Otherwise it treats the input as a local filesystem path.\n   - `resolveReadPath()` expands `~`, resolves relative to session cwd, treats bare `/` as session cwd, and retries macOS screenshot/NFD/curly-quote variants.\n   - If the path does not exist, `findUniqueSuffixMatch()` does a workspace glob-based unique suffix lookup (skipped for remote mounts).\n7. Directories go through `#readDirectory()`.\n8. Non-directories branch by content type:\n   - image metadata / inline image\n   - editable notebook text\n   - markit-converted document\n   - structural summary for parseable code/prose\n   - streamed text/line-range read\n9. Local text reads are streamed by `streamLinesFromFile()` rather than loading the whole file. The tool adds up to 3 lines of context before/after explicit bounded ranges.\n10. Non-empty contiguous local reads are recorded into `getFileReadCache(session)` for later hashline edit recovery.\n11. If suffix resolution happened, the first text block is prefixed with `[Path '...' not found; resolved to '...' via suffix match]`.\n\n## Modes / Variants\n\n### Local text files\n- No selector: if summarization is enabled and the file is small enough, `#trySummarize()` calls `summarizeCode()`.\n  - Guards: file size `<= 2 MiB` (`MAX_SUMMARY_BYTES`), line count `<= 20_000` (`MAX_SUMMARY_LINES`).\n  - Summary output keeps selected declarations and replaces elided spans with `...`. When at least one span is elided, the text content ends with a footer like `[NN lines across MM elided regions; read <path>:raw or a line range like <path>:1-9999 for verbatim content]` so the agent has a concrete recovery selector instead of a bare marker.\n  - When an elided block sits between matching brace lines, `#renderSummary()` may merge them into one anchored line rather than emitting separate opener/closer lines.\n- Explicit selector or summarization miss: streamed text read.\n  - Default open-ended limit is `min(session setting read.defaultLimit, DEFAULT_MAX_LINES)`.\n  - Explicit ranges expand by `RANGE_LEADING_CONTEXT_LINES = 1` / `RANGE_TRAILING_CONTEXT_LINES = 3` on the constrained sides only.\n  - Non-raw output uses `resolveFileDisplayMode()`:\n    - hashline anchors when edit mode is hashline, read is not raw, source is mutable, edit tool exists, and `readHashLines !== false`\n    - otherwise optional line numbers when `readLineNumbers === true`\n    - raw mode suppresses both\n- Prefix format in hashline mode is `lineNumber + 2-char line hash + \"|\"`, e.g. `41th|def alpha():`, from `formatHashLine()` in `packages/coding-agent/src/hashline/hash.ts`.\n- Those anchors are what the `edit`/hashline path consumes later; immutable sources and `:raw` intentionally suppress them.\n\n### Directory listings\n- `#readDirectory()` calls `buildDirectoryTree()` with:\n  - `maxDepth = 2`\n  - `perDirLimit = 12`\n  - `rootLimit = null`\n  - `lineCap = limit` when a line selector was present, else unlimited at this layer\n- `buildDirectoryTree()` sorts siblings by recency, shows file sizes and relative ages, and may mark `limits.resultLimit` when the tree truncates.\n- Empty directories render as `(empty directory)`.\n\n### Archives\n- Supported archive containers: `.tar`, `.tar.gz`, `.tgz`, `.zip`.\n- Syntax: `archive.ext`, `archive.ext:path/inside`, `archive.ext:path/inside:50-60`.\n- `openArchive()` reads the whole archive into memory, then:\n  - tar/tgz uses `new Bun.Archive(bytes)`\n  - zip uses `fflate.unzipSync()`\n- Archive paths normalize `/`, drop `.` segments, and reject `..`.\n- Directory reads list immediate children; files show `name` plus ` (size)` when size > 0.\n- Directory listing default limit is `500` entries in `#readArchiveDirectory()`.\n- File entries are UTF-8 decoded. Non-UTF-8 entries return `[Cannot read binary archive entry '...' (...)]` instead of bytes.\n- Text archive entries reuse the normal in-memory pagination/anchoring path.\n\n### SQLite databases\n- Database detection requires both a matching extension and a valid SQLite file header (`isSqliteFile()`).\n- Selector forms from `parseSqliteSelector()`:\n\n#### `db.sqlite`\n- `kind: \"list\"`\n- Lists non-`sqlite_%` tables with row counts.\n- `#readSqlite()` caps the rendered list to `500` tables via `applyListLimit()`.\n\n#### `db.sqlite:table`\n- `kind: \"schema\"`\n- Returns `sqlite_master.sql` plus sample rows.\n- Sample size is `DEFAULT_SCHEMA_SAMPLE_LIMIT = 5`.\n\n#### `db.sqlite:table:key`\n- `kind: \"row\"`\n- Resolves by primary key when the table has exactly one PK column; otherwise falls back to `rowid` lookup.\n- No query parameters allowed on row lookups.\n\n#### `db.sqlite:table?limit=...&offset=...&order=...&where=...`\n- `kind: \"query\"`\n- Defaults: `limit = 20`, `offset = 0`.\n- `limit` is capped at `500`.\n- `order` accepts `column` or `column:asc|desc` and must name an existing column.\n- `where` is accepted only after `validateWhereClause()` rejects comments, semicolons, and control keywords like `LIMIT`, `OFFSET`, `UNION`, `ATTACH`, `PRAGMA`.\n- Unknown query parameters throw.\n\n#### `db.sqlite?q=SELECT ...`\n- `kind: \"raw\"`\n- Cannot be combined with table selectors or any other query param.\n- Empty `q` throws.\n- `executeReadQuery()` runs `db.prepare(sql).all()` and rejects bound parameters; it does not verify that the SQL starts with `SELECT`.\n\n- Rendering caps in `packages/coding-agent/src/tools/sqlite-reader.ts`:\n  - ASCII table width `120` (`MAX_RENDER_WIDTH`)\n  - per-column width `40` (`MAX_COLUMN_WIDTH`)\n- `#readSqlite()` opens Bun SQLite in `{ readonly: true, strict: true }` and sets `PRAGMA busy_timeout = 3000`.\n\n### Documents\n- `CONVERTIBLE_EXTENSIONS` in `packages/coding-agent/src/tools/read.ts` covers `.pdf`, `.doc`, `.docx`, `.ppt`, `.pptx`, `.xls`, `.xlsx`, `.rtf`, `.epub`.\n- `convertFileWithMarkit()` converts the file to text/markdown.\n- Converted output is then head-truncated with normal shared limits; there is no line selector support inside the source document before conversion.\n- Conversion failures return a text block like `[Cannot read .pdf file: ...]`.\n\n### Jupyter notebooks\n- `.ipynb` goes through `readEditableNotebookText()` unless `:raw` was requested.\n- Output is editable plain text with markers like:\n\n```text\n# %% [code] cell:0\n...\n```\n\n- Raw mode bypasses that conversion and falls back to file-text reading.\n\n### Images\n- Image detection is metadata-based (`readImageMetadata()`).\n- Max accepted image size is `20 MiB` (`MAX_IMAGE_INPUT_BYTES`, re-exported as `MAX_IMAGE_SIZE`). Larger files throw.\n- If `inspect_image.enabled` is true, `read` returns metadata only (MIME, bytes, dimensions, channels, alpha) plus a suggestion to call `inspect_image`.\n- Otherwise it calls `loadImageInput()` and returns:\n  - a text note from the image loader\n  - an inline image block\n- Unsupported/undecodable image formats throw a `ToolError`.\n\n### Internal URLs\n- `read` does not resolve these itself; it delegates to `session.internalRouter.resolve()`.\n- Registered public protocols include `agent://`, `artifact://`, `issue://`, `local://`, `gjc://`, `pr://`, and `rule://`. Non-public compatibility handlers may exist in the router for legacy persisted guidance, but they are not part of the public coding-harness URI contract and must not be documented as user/model-facing read targets.\n- `#handleInternalUrl()` behavior:\n  - parses the URL with `parseInternalUrl()` so colons inside the host segment are legal\n  - for `agent://`, treats non-root path extraction or `?q=` extraction as a special no-pagination mode\n  - otherwise paginates the resolved text in memory\n  - passes `immutable` through to `resolveFileDisplayMode()` so anchors are suppressed for immutable resources such as artifacts and agent outputs\n- `issue://<N>` / `pr://<N>` (and the long form `issue://<owner>/<repo>/<N>` / `pr://<owner>/<repo>/<N>`) route through the same SQLite cache the `github` tool writes to; `?comments=0` selects the no-comments rendering. Bare `issue://` / `pr://` (and `issue://<owner>/<repo>` / `pr://<owner>/<repo>`) issue a live `gh issue list` / `gh pr list` for browsing, accepting `?state=`, `?limit=`, `?author=`, `?label=`. PR diffs share the same cache through `pr://<N>/diff` (numbered file listing with per-file hints), `pr://<N>/diff/<i>` (single file slice; 1-indexed), and `pr://<N>/diff/all` (verbatim unified diff); the listing and per-file slices are reconstructed from the cached unified-diff payload, so all three variants share one `gh pr diff` invocation per PR. Diff content is served as `text/plain`. Soft TTL `github.cache.softTtlSec` (default 5 minutes), hard TTL `github.cache.hardTtlSec` (default 7 days). Stale-hit returns the cached row and schedules a background refresh.\n\n### Web URLs\n- `parseReadUrlTarget()` accepts `http://`, `https://`, or `www.` targets.\n- Plain URL reads call `executeReadUrl()` in `packages/coding-agent/src/tools/fetch.ts`.\n- `:raw` means raw HTML/body fallback path; plain URL reads prefer rendered/reader-friendly output.\n- `:N`, `:A-B`, `:A+C` do not refetch. They page over cached output from the prior or current URL render.\n- URL render pipeline in `renderUrl()`:\n  1. normalize scheme (`https://` added for bare `www.`)\n  2. try special handlers for known sites unless raw\n  3. fetch with `loadPage()`\n  4. if content is image/PDF/DOCX/etc., try binary fetch + markit/image handling\n  5. handle JSON directly, feeds via feed parser, plain text directly\n  6. for HTML and non-raw mode, try markdown alternates, `URL.md`, content negotiation, feed alternates, HTML-to-text renderers, extracted linked documents, then `llms.txt`\n  7. fall back to raw body text/html\n- URL output is wrapped with a small header:\n\n```text\nURL: ...\nContent-Type: ...\nMethod: ...\nNotes: ...\n\n---\n```\n\n- `method` records the winning path (`json`, `feed`, `text`, `alternate-markdown`, `md-suffix`, `content-negotiation`, `image`, `markit`, `llms.txt`, `raw`, `raw-html`, etc.).\n- URL reads may return an inline image block when the fetched resource is a supported image and survives resizing.\n\n## Side Effects\n- Filesystem\n  - Opens and streams local files.\n  - Reads entire archives into memory before indexing.\n  - May read URL-cache artifact files from the session artifacts directory.\n  - Writes URL output artifacts when URL output is truncated or when line-range pagination needs a persisted cache body.\n- Network\n  - URL mode performs HTTP fetches, binary refetches, and alternate-endpoint probes.\n- Subprocesses / native bindings\n  - Uses Bun SQLite for `.db`/`.sqlite*`.\n  - Uses `Bun.Archive` for tar/tgz and `fflate` for zip.\n  - URL HTML rendering can delegate into site handlers and HTML-to-text backends from `packages/coding-agent/src/tools/fetch.ts`.\n- Session state\n  - Records local text lines into `session.fileReadCache` for later stale-anchor recovery.\n  - Uses `session.internalRouter` for internal URLs.\n  - Uses `session.allocateOutputArtifact()` for cached/truncated URL output.\n- Background work / cancellation\n  - Most branches honor `AbortSignal`; the tool itself is marked `nonAbortable = true`, but helper paths still call `throwIfAborted(signal)`.\n\n## Limits & Caps\n- Shared text truncation defaults from `packages/coding-agent/src/session/streaming-output.ts`:\n  - `DEFAULT_MAX_LINES = 3000`\n  - `DEFAULT_MAX_BYTES = 50 * 1024`\n- Local text open-ended default line limit: `read.defaultLimit`, clamped to `[1, DEFAULT_MAX_LINES]`.\n- Explicit line ranges add `1` leading and `3` trailing context lines on the constrained sides (`RANGE_LEADING_CONTEXT_LINES` / `RANGE_TRAILING_CONTEXT_LINES`).\n- File streaming chunk size: `8 * 1024` bytes (`READ_CHUNK_SIZE`).\n- Local streamed byte budget for line reads: `max(DEFAULT_MAX_BYTES, maxLinesToCollect * 512)`.\n- Structural summaries only run when file size `<= 2 MiB` and line count `<= 20_000`.\n- Image input max: `20 MiB`.\n- Directory tree caps for local directories: depth `2`, per-directory children `12`.\n- Archive directory default list cap: `500` entries.\n- SQLite:\n  - default row query limit `20`\n  - schema sample limit `5`\n  - max query limit `500`\n  - table list cap `500`\n  - render width `120`, column width `40`\n  - busy timeout `3000` ms\n- URL read result shown to the model is truncated to `300` lines and `50 KiB` in `executeReadUrl()`; full cached output can be attached as an artifact.\n- Inline fetched URL images:\n  - source bytes cap `20 MiB`\n  - post-resize inline output cap `300 KiB`\n- Unique suffix auto-resolution glob timeout: `5000` ms.\n- File-read cache holds `30` paths per session.\n\n## Errors\n- Validation and operational failures surface as `ToolError`.\n- Selector errors include:\n  - `Line selector 0 is invalid; lines are 1-indexed. Use :1.`\n  - invalid `A+B` / `A-B` shapes\n  - `Cannot combine query extraction with offset/limit` for `agent://.../path:50`\n- Missing local/archive/sqlite paths first attempt unique suffix resolution; if no unique match exists they error.\n- Out-of-bounds line reads do not throw. They return explanatory text with a suggestion such as `Use :1 ...` or `Use :<last line> ...`.\n- Binary archive entries do not throw; they return a text notice.\n- Document conversion failure returns a text notice.\n- Image oversize/unsupported/invalid cases throw.\n- SQLite parser rejects unsupported parameter combinations early; DB/runtime errors are caught and rethrown as `ToolError(message)`.\n- URL fetch failure does not throw when HTTP fetch succeeds but `response.ok === false`; it returns a failed URL read with `method: \"failed\"` and explanatory notes.\n\n## Notes\n- `readSchema` examples include `https://example.com:L1-L40`, but URL selector parsing in `packages/coding-agent/src/tools/fetch.ts` does not accept `L` prefixes.\n- Hashline anchors are suppressed for raw reads and immutable internal resources because there is no editable backing target for later `edit` consumption.\n- `splitPathAndSel()` intentionally treats unknown trailing `:...` as part of the path so `archive.zip:inner/file` and `db.sqlite:table:key` still work.\n- `resolveReadPath()` contains macOS-specific filename fallbacks for screenshot timestamps, NFD Unicode normalization, and curly apostrophes.\n- A bare `/` resolves to the session cwd, not the filesystem root.\n- URL cache keys are session-scoped and normalized by requested URL + raw/rendered mode; both requested URL and final redirected URL are cached.\n- URL line-range reads request `ensureArtifact: true, preferCached: true` so a later paginated read can reopen the same rendered body from artifact storage.\n- Raw SQLite `q=` execution is not keyword-restricted beyond “no bound parameters”; the read tool relies on the surrounding contract to keep it read-only.\n- The file-read cache is not a read acceleration cache. It exists to recover hashline edits when the file changed after the read.",
 	"tools/recipe.md": "# recipe\n\n> Run a task exposed by a detected project task runner.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/recipe/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/recipe.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/recipe/runner.ts` — op parsing, task resolution, prompt model.\n  - `packages/coding-agent/src/tools/recipe/render.ts` — shell-style call/result rendering.\n  - `packages/coding-agent/src/tools/recipe/runners/index.ts` — runner registration order.\n  - `packages/coding-agent/src/tools/recipe/runners/just.ts` — detect `just` recipes from justfiles.\n  - `packages/coding-agent/src/tools/recipe/runners/pkg.ts` — detect `package.json` scripts and workspaces.\n  - `packages/coding-agent/src/tools/recipe/runners/cargo.ts` — detect Cargo run/test targets.\n  - `packages/coding-agent/src/tools/recipe/runners/make.ts` — parse make targets from makefiles.\n  - `packages/coding-agent/src/tools/recipe/runners/task.ts` — detect Taskfile tasks via `task --list-all`.\n  - `packages/coding-agent/src/tools/bash.ts` — actual command execution, truncation, cwd/env handling.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `string` | Yes | Single string containing the task selector plus trailing arguments. The first whitespace-delimited token selects the task; the remainder is appended verbatim to the resolved runner command. Examples from schema/prompt: `test`, `build --release`, `pkg-a/test`, `crate/bin/server`, `pkg:test --watch`. |\n\n### `op` grammar\n\n```text\nop          := S* head (S+ tail)?\nhead        := explicit-runner / implicit-task\nexplicit-runner := runner-id \":\" task-token\nimplicit-task   := task-token\nrunner-id   := detected runner id (`just` | `pkg` | `cargo` | `make` | `task`)\ntask-token  := first non-whitespace token; may contain `/`\ntail        := remaining characters after the first whitespace run\n```\n\nResolution rules from `resolveRunnerAndTask()`:\n- Leading whitespace is ignored; an empty `op` throws `ToolError` with the available task list.\n- Only the first token is parsed structurally. Everything after the first whitespace run becomes `tail` and is appended to the command unchanged.\n- If `head` contains `:` and the prefix matches a detected runner id, the suffix must exactly match a task in that runner.\n- Otherwise `head` is treated as a task name and matched across all detected runners.\n- If exactly one runner has that task, it is used.\n- If multiple runners have that task, the call is rejected and the error tells the model to use `<runner-id>:<task>`.\n- Namespaced task names generated by runners use `/`, not `:`. `/` is part of the task name, not a parser separator.\n\n## Outputs\n- Delegates directly to `BashTool.execute()` and returns the same `AgentToolResult<BashToolDetails>` shape.\n- Success path: one text content block containing merged command output (`result.output` from bash execution, or `(no output)`), plus any timeout clamp notice appended after a blank line.\n- Recipe does not return separate `stdout`, `stderr`, or `exitCode` fields. `stdout`/`stderr` are already merged into the text block by bash execution; `exitCode` is only observed indirectly (success requires `0`, non-zero becomes an error).\n- Error path: throws `ToolError`; for non-zero exits the message is the merged output followed by `Command exited with code <n>`.\n- `details` may include:\n  - `timeoutSeconds`: effective timeout used by bash.\n  - `requestedTimeoutSeconds`: only when bash clamped a requested timeout; recipe never sets one itself.\n  - `meta`: output truncation metadata from bash execution.\n  - `async`: defined by bash background execution paths, but recipe does not expose an `async` input.\n- When bash output is truncated, the full text is stored in an artifact and referenced via bash truncation metadata.\n- Call/result rendering in the TUI uses bash shell rendering with a resolved title, command preview, and optional task cwd.\n\n## Flow\n1. `RecipeTool.createIf()` in `packages/coding-agent/src/tools/recipe/index.ts` checks `session.settings.get(\"recipe.enabled\")`; disabled returns `null`.\n2. It probes every runner in `RUNNERS` from `packages/coding-agent/src/tools/recipe/runners/index.ts` with `Promise.all(...)` in this order: `just`, `pkg`, `cargo`, `make`, `task`.\n3. Each runner returns either `null` or a `DetectedRunner { id, label, commandPrefix, tasks }`; runners with zero tasks are discarded.\n4. If no runners remain, the tool is not registered.\n5. Constructor stores detected runners, instantiates `BashTool`, renders the model-facing description by passing `buildPromptModel(runners)` into `packages/coding-agent/src/prompts/tools/recipe.md`, and builds shell renderers from `createRecipeToolRenderer()`.\n6. On execution, `RecipeTool.execute()` calls `resolveCommand(op, this.#runners)`.\n7. `resolveCommand()` in `packages/coding-agent/src/tools/recipe/runner.ts`:\n   1. `parseOp()` trims only leading whitespace, extracts the first non-whitespace token as `head`, and keeps the remainder as `tail`.\n   2. `resolveRunnerAndTask()` resolves `head` either as `runnerId:taskName` or as an unqualified task name.\n   3. It throws `ToolError` for empty ops, missing explicit tasks, ambiguous task names, or unknown tasks; all error variants include the available task list.\n   4. It builds the final shell command with `buildCommand(commandPrefix, commandName, tail)`, joining non-empty parts with spaces.\n   5. If the task defines `cwd`, that relative path is returned alongside the command.\n8. `RecipeTool.execute()` forwards `{ command, cwd }` into `BashTool.execute()`; recipe does not pass timeout, env, async, or pty options.\n9. `BashTool.execute()` resolves internal URLs, validates/normalizes cwd against `session.cwd`, clamps timeout, applies bash interception rules, runs the command, and formats the final result.\n\n## Modes / Variants\n- Tool enablement:\n  - Disabled by `recipe.enabled` setting: tool is absent.\n  - Enabled but no detected tasks: tool is absent.\n- Task selection:\n  - Unqualified task name: succeeds only when exactly one detected runner owns that task.\n  - Explicit runner-qualified task: `<runner-id>:<task>`.\n- Runner detection paths:\n  - `just`: requires `just` on `PATH`, a justfile, and successful `just --dump --dump-format=json`.\n  - `pkg`: requires a readable root `package.json`; picks a package manager command from lockfiles or `bun` availability; discovers root scripts and workspace package scripts.\n  - `cargo`: requires `cargo` on `PATH`, `Cargo.toml`, and successful `cargo metadata --no-deps --format-version=1`.\n  - `make`: requires `make` on `PATH` and a makefile; parses targets statically.\n  - `task`: requires `task` on `PATH`, a Taskfile, and successful `task --list-all --json`.\n- Execution path:\n  - Always the synchronous `bash` call surface from recipe inputs.\n  - Bash may still auto-background long-running work if `bash.autoBackground.enabled` and session async job support are enabled.\n\n## Side Effects\n- Filesystem\n  - Reads manifests from the session cwd during detection: justfiles, `package.json`, workspace `package.json` files, `Cargo.toml`, makefiles, `Taskfile.yml` / `Taskfile.yaml`.\n  - Command execution runs in `session.cwd` or a task-specific relative cwd resolved under it.\n  - Bash may allocate output artifacts for truncated command output.\n- Subprocesses / native bindings\n  - Detection may spawn `just --dump --dump-format=json`, `cargo metadata --no-deps --format-version=1`, and `task --list-all --json`.\n  - Execution spawns the resolved shell command through `BashTool` / `executeBash()`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Tool availability depends on session settings.\n  - Constructor prompt text is specialized to detected runners/tasks.\n  - Bash execution may create async job records and output artifacts if bash auto-background triggers.\n- User-visible prompts / interactive UI\n  - The model-facing tool description lists detected runners and up to 20 tasks per runner.\n  - TUI rendering shows a shell-style preview using the resolved title/command/cwd.\n- Background work / cancellation\n  - Detection is parallelized across runners.\n  - Runtime command execution honors the passed abort signal through `BashTool`.\n\n## Limits & Caps\n- Prompt task listing is capped at `PROMPT_TASK_LIMIT = 20` per runner in `packages/coding-agent/src/tools/recipe/runner.ts`; this affects the rendered tool description, not execution.\n- Recipe itself defines no timeout input; delegated bash execution therefore uses bash's default `timeout = 300` seconds from `packages/coding-agent/src/tools/bash.ts`.\n- Bash clamps timeouts to the configured bash range (`clampTimeout(\"bash\", ...)` in `packages/coding-agent/src/tools/bash.ts`), but recipe cannot request a custom value.\n- `pkg` workspace discovery normalizes workspace globs to `.../package.json` and sorts matched package files lexicographically before task generation.\n- `cargo` deduplicates generated task names with a `Set`, so duplicate targets collapse to one recipe task.\n\n## Errors\n- Detection failures in runner modules are mostly soft-failed:\n  - Missing binaries, missing manifests, parse failures, or non-zero probe exits usually return `null` and log with `logger.debug(...)`.\n  - Result: the affected runner disappears instead of surfacing an error to the model.\n- Invocation failures are hard errors from `resolveRunnerAndTask()`:\n  - Empty `op`.\n  - Explicit runner prefix with missing/empty task.\n  - Ambiguous unqualified task name across runners.\n  - Unknown task name.\n- Execution failures come from `BashTool.execute()`:\n  - Invalid cwd.\n  - Bash interceptor blocks.\n  - Aborts/timeouts.\n  - Non-zero exit codes.\n  - Missing exit status.\n- All `resolveRunnerAndTask()` errors include the current available task list to help the model retry.\n\n## Notes\n- `RecipeTool` sets `concurrency = \"exclusive\"`; calls do not run concurrently with other exclusive tools.\n- Tool registration is all-or-nothing per runner: a detected runner with zero tasks is dropped.\n- Runner ids are fixed string literals from the runner modules: `just`, `pkg`, `cargo`, `make`, `task`.\n- `buildPromptModel()` includes each task's rendered command (`commandPrefix` + `commandName`) and relative cwd when present; the prompt therefore exposes the exact shell form recipe will run.\n- `pkg` task names:\n  - Root `package.json` scripts keep bare names like `test`.\n  - Workspace scripts are always namespaced as `<package-name-or-dir>/<script>` and set `cwd` to that package directory.\n  - Script names are shell-quoted into `commandName`, so a task like `build` becomes `bun run 'build'` / `npm run 'build'` / similar.\n- `pkg` command prefix selection prefers lockfiles in this order: `bun.lock`/`bun.lockb`, `pnpm-lock.yaml`, `yarn.lock`, `package-lock.json`/`npm-shrinkwrap.json`; otherwise it falls back to `bun run` if `bun` exists, else `npm run`.\n- `cargo` task names are generated from metadata targets:\n  - Single-package manifests: `bin/<name>`, `example/<name>`, `test/<name>`.\n  - Multi-package workspaces: `<package>/bin/<name>`, `<package>/example/<name>`, `<package>/test/<name>`.\n  - Each task overrides `commandPrefix` to the full `cargo run ... --bin|--example` or `cargo test ... --test` prefix, and `commandName` to the quoted target name.\n- `make` target parsing is static text parsing, not `make -qp` output:\n  - Recognizes makefiles named `Makefile`, `makefile`, `GNUmakefile`.\n  - Uses `.PHONY` lines to decide whether to include undocumented file targets; without any `.PHONY`, all parsed targets are exposed.\n  - If `.PHONY` exists, documented non-phony targets are kept with ` (file target)` appended to `doc`.\n- `just` detection ignores private recipes and preserves declared parameter names only for prompt display; execution still accepts arbitrary `tail` text.\n- `task` detection uses `desc` first, then `summary`, for task documentation.\n- Recipe has no env input of its own. Commands inherit whatever environment `BashTool` supplies for normal bash execution in the session.",
-	"tools/reflect.md": "# reflect\n\n> Ask the Hindsight server to synthesize an answer over the active memory bank.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/hindsight-reflect.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/reflect.md`\n- Key collaborators:\n  - `packages/coding-agent/src/hindsight/bank.ts` — best-effort bank mission initialization.\n  - `packages/coding-agent/src/hindsight/state.ts` — session state, shared bank scope, recall/reflect config.\n  - `packages/coding-agent/src/hindsight/client.ts` — HTTP `reflect` call and error mapping.\n  - `docs/tools/retain.md` — shared backend, storage, seeding, and mental-model bootstrap.\n\n## Inputs\n\n| Field | Type | Required | Description |\n|---|---|---:|---|\n| `query` | `string` | Yes | Question to answer from long-term memory. |\n| `context` | `string` | No | Extra guidance sent to the Hindsight reflect endpoint. |\n\n## Outputs\nReturns a single-shot tool result:\n\n- `content[0].type = \"text\"`\n- `content[0].text = response.text?.trim() || \"No relevant information found to reflect on.\"`\n- `details = {}`\n\nThe tool returns the Hindsight server's synthesized text directly; it does not expose raw recall hits.\n\n## Flow\n1. `HindsightReflectTool.createIf(...)` only exposes the tool when `memory.backend == \"hindsight\"`.\n2. `execute(...)` runs under `untilAborted(...)`.\n3. It reads the active `HindsightSessionState`; missing state throws `Hindsight backend is not initialised for this session.`\n4. Before reflecting, it calls `ensureBankMission(...)` with the current `bankId`, config, and process-local `missionsSet`.\n5. `ensureBankMission(...)` best-effort `PUT`s `/v1/default/banks/{bank_id}` with `reflect_mission` and optional `retain_mission` exactly once per bank/process; failures are swallowed.\n6. It calls `state.client.reflect(...)` with the model `query`, optional `context`, configured recall budget, and bank-scope tag filters.\n7. `HindsightApi.reflect(...)` POSTs `/v1/default/banks/{bank_id}/reflect` and defaults its own budget to `\"low\"` when callers omit one; this tool always passes the configured budget.\n8. Blank or whitespace-only responses are replaced with `No relevant information found to reflect on.`\n9. Failures are logged with `logger.warn(\"reflect failed\", ...)` and rethrown.\n\n## Modes / Variants\n- Tool path: one reflect request, optionally focused by `context`.\n- Bank scoping is inherited from the active `HindsightSessionState`:\n  - `global` — no tag filter.\n  - `per-project` — separate bank id per cwd basename.\n  - `per-project-tagged` — shared bank id plus `project:<cwd basename>` filter with `tagsMatch = \"any\"`.\n- Session scope: reads cross-session server-side memories, but does not persist local output.\n\n## Side Effects\n- Network\n  - Optional `PUT /v1/default/banks/{bank_id}` from `ensureBankMission(...)`.\n  - `POST /v1/default/banks/{bank_id}/reflect` via `packages/coding-agent/src/hindsight/client.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Reads session-held bank scope and config only. Does not update `lastRecallSnippet`, the mental-model cache, or the retain queue.\n- Background work / cancellation\n  - Aborts through `untilAborted(...)` if the tool call signal is cancelled.\n\n## Limits & Caps\n- Tool-level params: only `query` is required; `context` is optional.\n- Default budget setting comes from `hindsight.recallBudget` in `packages/coding-agent/src/config/settings-schema.ts`; default `\"mid\"`.\n- `reflect` itself has no client-side token cap parameter here; unlike `recall`, the tool does not pass `maxTokens`.\n- Mission initialization tracks up to `MISSION_SET_CAP = 10_000` bank ids in `packages/coding-agent/src/hindsight/bank.ts`, then drops the oldest half of the sorted set.\n\n## Errors\n- Throws `Hindsight backend is not initialised for this session.` when no state exists.\n- HTTP and fetch failures become `HindsightError` from `packages/coding-agent/src/hindsight/client.ts` with `statusCode` and parsed `details` when available.\n- `ensureBankMission(...)` failures are silent to the tool caller; only the later reflect request can fail visibly.\n- Non-`Error` failures are normalized to `new Error(String(err))` before rethrow.\n\n## Notes\n- Shared backend details are in `docs/tools/retain.md`: server-side storage, subagent aliasing, bank scoping, seed mental models from `packages/coding-agent/src/hindsight/seeds.json`, and mental-model prompt injection.\n- `reflect` does not read the cached `<mental_models>` block directly. It queries the Hindsight server over the bank contents. The same session may also have separate mental-model context injected into its developer instructions.\n- Reflect mission and retain mission are bank-level server settings, not per-request payload. The tool just ensures they are present best-effort before reflecting.\n",
 	"tools/render_mermaid.md": "# render_mermaid\n\n> Convert Mermaid source into terminal-friendly ASCII/Unicode text.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/render-mermaid.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/render-mermaid.md`\n- Key collaborators:\n  - `packages/utils/src/mermaid-ascii.ts` — thin wrapper over renderer package.\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and enablement gate.\n  - `packages/coding-agent/src/sdk.ts` — session-facing artifact allocation hook.\n  - `packages/coding-agent/src/session/session-manager.ts` — persistent-session artifact path allocation.\n  - `packages/coding-agent/src/session/artifacts.ts` — artifact filename generation and writes.\n- Related user/runtime doc: `docs/render-mermaid.md`\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `mermaid` | `string` | Yes | Mermaid source text. Schema example: `graph TD; A-->B`. |\n| `config` | `object` | No | Optional renderer options. Sanitized before rendering; numeric fields are floored and clamped to `>= 0`. |\n\n`config` fields:\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `useAscii` | `boolean` | No | `true` for plain ASCII, `false`/omitted for Unicode box-drawing output. Passed through unchanged. |\n| `paddingX` | `number` | No | Horizontal spacing. `Math.floor`, then `Math.max(0, value)`. |\n| `paddingY` | `number` | No | Vertical spacing. `Math.floor`, then `Math.max(0, value)`. |\n| `boxBorderPadding` | `number` | No | Inner box padding. `Math.floor`, then `Math.max(0, value)`. |\n\n## Outputs\nThe tool returns a single text content block:\n\n- inline body: rendered diagram text\n- optional trailer: `Saved artifact: artifact://<id>` when artifact storage is available\n\n`details` may include:\n\n- `artifactId?: string`\n\nNo image path, SVG, PNG, or binary payload is returned. Stored artifacts are plain text `.log` files; artifact filenames are allocated as `<id>.render_mermaid.log` by `packages/coding-agent/src/session/artifacts.ts`.\n\n## Flow\n1. `RenderMermaidTool.execute()` in `packages/coding-agent/src/tools/render-mermaid.ts` receives `mermaid` and optional `config`.\n2. `sanitizeRenderConfig()` normalizes `paddingX`, `paddingY`, and `boxBorderPadding` to non-negative integers; `useAscii` is passed through.\n3. The tool calls `renderMermaidAscii()` from `@gajae-code/utils`.\n4. `packages/utils/src/mermaid-ascii.ts` forwards directly to `renderMermaidASCII()` from the `beautiful-mermaid` package.\n5. The tool optionally asks the session for an artifact slot with `allocateOutputArtifact(\"render_mermaid\")`.\n6. If a path is returned, `Bun.write()` persists the full rendered text to that file.\n7. The tool returns the rendered text, plus an `artifact://` line and `details.artifactId` when persistence succeeded.\n\n## Modes / Variants\n- Default render: Unicode box-drawing output when `config.useAscii` is omitted or false.\n- ASCII render: plain ASCII output when `config.useAscii` is true.\n- Persistent-session path: artifact text is written when `allocateOutputArtifact()` returns a path.\n- Ephemeral-session path: no artifact is written; the inline text result is still returned.\n\n## Side Effects\n- Filesystem\n  - May write one session artifact via `Bun.write()`.\n  - Artifact filename format is `<id>.render_mermaid.log`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Consumes the session artifact allocator hook.\n  - Returns `details.artifactId` for the tool result.\n\n## Limits & Caps\n- No tool-local timeout, retry, truncation, or streaming path.\n- Numeric config fields are quantized to integers with `Math.floor()` and clamped to `0` minimum in `sanitizeRenderConfig()`.\n- Renderer engine is `beautiful-mermaid@1.1.3` per root `package.json` / `bun.lock`.\n- The tool is registered as discoverable and gated by `renderMermaid.enabled` in `packages/coding-agent/src/tools/index.ts`.\n\n## Errors\n- `renderMermaidAscii()` is not wrapped in a local `try/catch`; renderer exceptions propagate out of `execute()`.\n- Invalid Mermaid syntax therefore fails the tool call rather than returning partial output.\n- Artifact allocation failures inside the SDK hook are swallowed there and converted to `{}` in `packages/coding-agent/src/sdk.ts`; rendering still succeeds, just without a saved artifact.\n- Artifact write failures from `Bun.write()` are not caught in the tool and will fail the call.\n\n## Notes\n- The tool summary string says `Render a Mermaid diagram to an image`, but the implementation and prompt both produce text, not images.\n- Despite the name, this tool does not use Puppeteer, browser rendering, Mermaid CLI, or native bindings; rendering stays in-process through the JS package wrapper.\n- `docs/render-mermaid.md` covers operator-facing behavior and enablement; keep this file focused on the tool contract and runtime path.\n",
 	"tools/resolve.md": "# resolve\n\n> Finalizes a queued preview action by applying or discarding it.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/resolve.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/resolve.md`\n- Key collaborators:\n  - `docs/resolve-tool-runtime.md` — preview/apply runtime reference\n  - `packages/coding-agent/src/extensibility/custom-tools/loader.ts` — forwards custom pending actions into the queue\n  - `packages/coding-agent/src/tools/ast-edit.ts` — built-in preview producer example\n  - `packages/coding-agent/src/session/agent-session.ts` — tool-choice queue and invoker access\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | `\"apply\" | \"discard\"` | Yes | Whether to commit or reject the queued preview. |\n| `reason` | `string` | Yes | Required explanation passed through to the queued callback. |\n\n## Outputs\n- Single-shot result.\n- `execute()` returns whatever the queued invoker returns, with `details` wrapped/augmented to include:\n  - `action`\n  - `reason`\n  - `sourceToolName?`\n  - `label?`\n  - `sourceResultDetails?` — original `result.details` from the apply/reject callback when present\n- If `discard` has no custom reject callback, the default success payload is `Discarded: <label>. Reason: <reason>`.\n- The TUI renderer is inline and merges call+result into one block.\n\n## Flow\n1. Preview-producing code calls `queueResolveHandler(...)` with a label, source tool name, and `apply(reason)` callback, plus optional `reject(reason)`.\n2. `queueResolveHandler(...)` asks the session for a forced `resolve` tool choice and pushes it into the tool-choice queue with `pushOnce(...)`.\n3. The queued entry is marked `now: true`; if the model rejects that forced tool choice, `onRejected` returns `requeue`, so the reminder comes back.\n4. `queueResolveHandler(...)` also injects a `resolve-reminder` steering message: `This is a preview. Call the resolve tool to apply or discard these changes.`\n5. When `resolve.execute()` runs, it wraps the call in `untilAborted(...)` and fetches the current queue invoker with `session.peekQueueInvoker()`.\n6. If no invoker exists, it throws `ToolError(\"No pending action to resolve. Nothing to apply or discard.\")`.\n7. Otherwise it invokes the queued callback with `{ action, reason }`.\n8. For `apply`, it always executes the producer's `apply(reason)` callback.\n9. For `discard`, it executes `reject(reason)` when provided; if that callback is absent or returns `undefined`, `resolve` fabricates the default discard message.\n10. Before returning, it merges resolve metadata into `result.details` so renderer/UI code can show the action, label, and originating tool.\n\n## Modes / Variants\n- `apply`: runs the queued `apply(reason)` callback and returns its content.\n- `discard` with reject callback: runs `reject(reason)` and returns that callback's content.\n- `discard` without reject callback: returns the built-in `Discarded: ...` text payload.\n\n## Side Effects\n- Session state\n  - Consumes the current pending preview through the session tool-choice queue; there is no separate pending-action stack.\n  - Adds a `resolve-reminder` steering message when a preview is queued.\n- User-visible prompts / interactive UI\n  - No direct prompt. The visible effect depends on the preview-producing tool and the resolve renderer.\n- Background work / cancellation\n  - `untilAborted(...)` lets abort signals interrupt resolution before invoking the callback completes.\n\n## Limits & Caps\n- Hidden tool: not discoverable in the normal tool index (`packages/coding-agent/src/tools/resolve.ts`, `packages/coding-agent/src/session/agent-session.ts`).\n- Exactly one active queue invoker is consulted per call via `session.peekQueueInvoker()`.\n- There is no independent queue depth cap in this tool; ordering follows the shared tool-choice queue (`docs/resolve-tool-runtime.md`).\n\n## Errors\n- No pending preview: throws `ToolError(\"No pending action to resolve. Nothing to apply or discard.\")`.\n- Any exception from the queued `apply` / `reject` callback propagates through `resolve`.\n- Aborts during `untilAborted(...)` surface as the underlying abort error from the utility.\n\n## Notes\n- `reason` is informational; `resolve` passes it through but does not interpret it.\n- `queueResolveHandler(...)` is the canonical built-in integration point; custom tools use `pushPendingAction(...)`, which the loader forwards into the same mechanism.\n- The tool only works because another tool already staged a preview and forced a one-shot `resolve` choice.\n- `sourceResultDetails` is added only when the apply/reject callback returned a non-null `details` field; custom pending-action `details` are not forwarded automatically by the loader.\n",
-	"tools/retain.md": "# retain\n\n> Queue durable facts for asynchronous write into the active Hindsight bank.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/hindsight-retain.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/retain.md`\n- Key collaborators:\n  - `packages/coding-agent/src/hindsight/state.ts` — per-session queue, flush, auto-retain.\n  - `packages/coding-agent/src/hindsight/backend.ts` — session bootstrap, prompt injection, subagent aliasing.\n  - `packages/coding-agent/src/hindsight/bank.ts` — bank id derivation, tag scoping, mission setup.\n  - `packages/coding-agent/src/hindsight/client.ts` — HTTP `retain` / `retainBatch` calls.\n  - `packages/coding-agent/src/hindsight/content.ts` — retention transcript shaping, memory-tag stripping.\n  - `packages/coding-agent/src/hindsight/mental-models.ts` — bank-scoped mental-model seeding and cache rendering.\n  - `packages/coding-agent/src/hindsight/seeds.json` — built-in mental-model seed definitions.\n  - `packages/coding-agent/src/hindsight/transcript.ts` — extracts user/assistant turns for auto-retain.\n\n## Inputs\n\n| Field | Type | Required | Description |\n|---|---|---:|---|\n| `items` | `Array<{ content: string; context?: string }>` | Yes | One or more memories to queue. `minItems: 1`. Each item must be self-contained; `context` is optional per-item provenance. |\n\n## Outputs\nReturns a single-shot tool result:\n\n- `content[0].type = \"text\"`\n- `content[0].text = \"<count> memory queued.\"` or `\"<count> memories queued.\"`\n- `details = { count: number }`\n\nThe write is not confirmed before the tool returns. The queue flushes later; flush failures emit a session warning notice and are not returned to the model.\n\n## Flow\n1. `HindsightRetainTool.createIf(...)` only exposes the tool when `memory.backend == \"hindsight\"` in `packages/coding-agent/src/tools/hindsight-retain.ts`.\n2. `execute(...)` fetches `session.getHindsightSessionState()` and throws if the Hindsight backend was not started.\n3. Each input item is handed to `HindsightSessionState.enqueueRetain(...)` in `packages/coding-agent/src/hindsight/state.ts`.\n4. `HindsightRetainQueue.enqueue(...)` appends the item and either:\n   - flushes immediately when the queue reaches `RETAIN_FLUSH_BATCH_SIZE`, or\n   - starts a debounce timer for `RETAIN_FLUSH_INTERVAL_MS`.\n5. On flush, `HindsightRetainQueue.#doFlush(...)`:\n   - verifies the session still owns this state,\n   - calls `ensureBankMission(...)` once per bank/process before writing,\n   - maps queued items to `MemoryItemInput` with `context ?? config.retainContext`, `metadata.session_id`, and bank-scope tags,\n   - sends one async `retainBatch(...)` request.\n6. The tool returns immediately after enqueueing; it does not await the HTTP write.\n\n## Modes / Variants\n- Tool path: queued batch write only.\n- Bank scoping comes from `computeBankScope(...)` in `packages/coding-agent/src/hindsight/bank.ts`:\n  - `global` — one shared bank, no project tags.\n  - `per-project` — bank id gets `-<cwd basename>` appended.\n  - `per-project-tagged` — shared bank plus `project:<cwd basename>` tags on retained memories.\n- Session scope:\n  - tool-called retains are per-session queued work in `HindsightSessionState`,\n  - persisted memories are cross-session server-side bank data,\n  - subagents alias the parent `HindsightSessionState`, so their `retain` calls write into the same bank and queue.\n\n## Side Effects\n- Filesystem\n  - None for retained memories. No local memory file is written.\n- Network\n  - `POST /v1/default/banks/{bank_id}/memories` via `retainBatch(...)` in `packages/coding-agent/src/hindsight/client.ts`.\n  - Optional `PUT /v1/default/banks/{bank_id}` via `ensureBankMission(...)` before first write per bank/process.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Appends to the in-memory `HindsightRetainQueue` on the active `HindsightSessionState`.\n  - Includes `metadata.session_id` on each retained item.\n  - Shares parent state for subagents (`aliasOf` path in `packages/coding-agent/src/hindsight/backend.ts`).\n- User-visible prompts / interactive UI\n  - On async flush failure, emits `session.emitNotice(\"warning\", ...)`; the model is not told.\n- Background work / cancellation\n  - Flush runs later on timer, queue-size threshold, `agent_end`, backend `enqueue(...)`, or backend `clear(...)`.\n\n## Limits & Caps\n- Input schema requires `items.length >= 1` in `packages/coding-agent/src/tools/hindsight-retain.ts`.\n- Queue flush threshold: `RETAIN_FLUSH_BATCH_SIZE = 16` in `packages/coding-agent/src/hindsight/state.ts`.\n- Queue debounce: `RETAIN_FLUSH_INTERVAL_MS = 5_000` in `packages/coding-agent/src/hindsight/state.ts`.\n- Queue writes use `retainBatch(..., { async: true })`; the client does not wait for server-side consolidation.\n- Shared auto-retain settings on the same backend:\n  - `hindsight.retainEveryNTurns` default `3`\n  - `hindsight.retainOverlapTurns` default `2`\n  - `hindsight.retainContext` default `\"gjc\"`\n  - `hindsight.retainMode` default `\"full-session\"`\n  from `packages/coding-agent/src/config/settings-schema.ts`.\n\n## Errors\n- Throws `Hindsight backend is not initialised for this session.` when no state exists.\n- Queue enqueue on disposed state throws `Hindsight retain queue is closed.`\n- Flush-time API failures are caught in `HindsightRetainQueue.#doFlush(...)`, logged, and converted into a warning notice instead of a tool error.\n- Mission creation failures are swallowed in `ensureBankMission(...)`; writes continue.\n\n## Notes\n- Storage is server-side. `hindsightBackend.clear(...)` only clears local cache/state and warns that upstream deletion must happen in Hindsight UI or `deleteBank`; see `packages/coding-agent/src/hindsight/backend.ts`.\n- Auto-retain uses the same bank but a different path than this tool: `retainSession(...)` extracts plain user/assistant transcript from `packages/coding-agent/src/hindsight/transcript.ts`, strips `<memories>` / `<mental_models>` blocks via `stripMemoryTags(...)`, and calls single-item `retain(...)`.\n- `retain` itself does not seed or read mental models. Mental-model bootstrap lives in the shared backend: `HindsightSessionState.runMentalModelLoad(...)` optionally resolves seeds from `packages/coding-agent/src/hindsight/seeds.json`, creates missing models with `ensureMentalModels(...)`, then caches a rendered `<mental_models>` block for prompt injection.\n- Built-in seeds are `user-preferences`, `project-conventions`, and `project-decisions`. `projectTagged: true` seeds inherit the active scope's retain tags; untagged seeds read the whole bank.\n- Mental-model defaults from `packages/coding-agent/src/config/settings-schema.ts`: `hindsight.mentalModelsEnabled = true`, `hindsight.mentalModelAutoSeed = true`, `hindsight.mentalModelRefreshIntervalMs = 5 * 60 * 1000`, `hindsight.mentalModelMaxRenderChars = 16_000`. First-turn loading waits up to `MENTAL_MODEL_FIRST_TURN_DEADLINE_MS = 1500` in `packages/coding-agent/src/hindsight/mental-models.ts`.\n- Seed lifecycle is create-only. Changing `packages/coding-agent/src/hindsight/seeds.json` does not mutate existing server-side models.\n- `recall.md` and `reflect.md` rely on the same bank, scoping, and mental-model bootstrap; refer back here for the shared backend behavior.\n",
 	"tools/rewind.md": "# rewind\n\n> End an active checkpoint by pruning exploratory context and retaining a concise report.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/checkpoint.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/rewind.md`\n- Key collaborators:\n  - `packages/coding-agent/src/session/agent-session.ts` — validates pending rewind state, applies the actual rewind, and injects the retained report.\n  - `packages/coding-agent/src/session/session-manager.ts` — branches the persisted session tree and appends persisted summary/report entries.\n  - `packages/coding-agent/src/session/messages.ts` — converts persisted `branch_summary` entries into LLM-visible branch-summary messages on rebuilt context.\n  - `packages/coding-agent/src/tools/index.ts` — registers the tool and shares the `checkpoint.enabled` gate.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `report` | `string` | Yes | Investigation findings. `execute()` trims it and rejects the empty result. |\n\n## Outputs\nThe tool returns a single text result plus structured details:\n\n- text body:\n  - `Rewind requested.`\n  - `Report captured for context replacement.`\n- `details`:\n  - `report: string` — trimmed report text\n  - `rewound: true`\n\nThe returned tool result is not the final rewind. `AgentSession` waits until `turn_end`, then applies the rewind side effects asynchronously.\n\n## Flow\n1. `RewindTool.createIf()` in `packages/coding-agent/src/tools/checkpoint.ts` hides the tool from subagents.\n2. `RewindTool.execute()` rejects subagent calls with `ToolError(\"Checkpoint not available in subagents.\")`.\n3. It rejects calls with no active checkpoint using `ToolError(\"No active checkpoint.\")`.\n4. It trims `params.report`; if empty, it throws `ToolError(\"Report cannot be empty.\")`.\n5. It returns a `toolResult()` with `details.report` and `details.rewound = true`.\n6. On `tool_execution_end`, `AgentSession` extracts the report from `details.report` or the first text content block and stores it in `#pendingRewindReport`.\n7. On `turn_end`, if `#pendingRewindReport` is set, `AgentSession.#applyRewind()` runs.\n8. `#applyRewind()` computes `safeCount = clamp(checkpointMessageCount, 0, agent.state.messages.length)` and calls `agent.replaceMessages(agent.state.messages.slice(0, safeCount))`.\n9. It then calls `sessionManager.branchWithSummary(checkpointEntryId, report, { startedAt })`. That moves the persisted session leaf back to the checkpoint entry and appends a new `branch_summary` entry whose `summary` is the rewind report.\n10. If `checkpointEntryId` no longer resolves, it logs a warning and falls back to `branchWithSummary(null, report, { startedAt })`, branching from root instead.\n11. `#applyRewind()` appends a hidden in-memory custom message `{ customType: \"rewind-report\", content: report, display: false }` and persists the same payload through `sessionManager.appendCustomMessageEntry(\"rewind-report\", ...)` with `details = { startedAt, rewoundAt }`.\n12. Finally it clears `#checkpointState` and `#pendingRewindReport`.\n\n## Modes / Variants\n- Normal rewind: checkpoint entry exists; session history branches from that exact entry.\n- Fallback rewind: checkpoint entry ID is missing from the current session tree; rewind branches from root and logs a warning.\n- Immediate turn-end apply: rewind side effects happen only after the surrounding assistant turn finishes, not inside `RewindTool.execute()`.\n\n## Side Effects\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Replaces in-memory conversation history with the prefix ending at the checkpoint tool result.\n  - Adds a hidden custom message `rewind-report` carrying the retained report.\n  - Clears the active checkpoint state and pending rewind report.\n  - Repositions the persisted session leaf to the checkpoint branch point and appends new session entries.\n- Filesystem\n  - Persists the new `branch_summary` and `custom_message` entries into the session `.jsonl` file through normal `SessionManager` append persistence.\n  - Session files are named `<ISO-timestamp-with-:-and-.-replaced>_<uuidv7>.jsonl` in the session directory; default directory selection is documented in `SessionManager.create()` as `~/.gjc/agent/sessions/<encoded-cwd>/` when no override is passed.\n- User-visible prompts / interactive UI\n  - The tool result itself is visible.\n  - The persisted `branch_summary` becomes an LLM-visible `branchSummary` message when context is rebuilt from `SessionManager.buildSessionContext()`; `messages.ts` renders it as a user-role text message using `packages/agent/src/compaction/prompts/branch-summary-context.md`.\n  - The persisted `rewind-report` custom message also participates in rebuilt LLM context because `custom_message` entries are converted through `createCustomMessage()`.\n- Background work / cancellation\n  - Rewind application is deferred to `turn_end`. There is no separate job object or cancel handle.\n\n## Limits & Caps\n- Availability is gated by `checkpoint.enabled`, default `false`, in `packages/coding-agent/src/config/settings-schema.ts`.\n- Top-level sessions only.\n- Requires exactly one active checkpoint; there is no path to name or choose among multiple checkpoints.\n- Report text must be non-empty after `trim()`.\n- Rewind restores only the message prefix recorded by `checkpointMessageCount`; there is no file restore, artifact restore, blob restore, or process restore path.\n- Persisted report/summary content is still subject to the global session persistence cap `MAX_PERSIST_CHARS = 500_000` in `packages/coding-agent/src/session/session-manager.ts`.\n\n## Errors\n- `ToolError(\"Checkpoint not available in subagents.\")` — thrown for subagent sessions.\n- `ToolError(\"No active checkpoint.\")` — thrown when no checkpoint state is present.\n- `ToolError(\"Report cannot be empty.\")` — thrown when the trimmed report is empty.\n- Missing checkpoint entry IDs during apply do not fail the tool call; `#applyRewind()` catches the error, logs `Rewind branch checkpoint missing, falling back to root`, and branches from root.\n- If the agent turn is aborted while a checkpoint is active, `AgentSession` clears checkpoint state rather than applying a delayed rewind.\n\n## Notes\n- Checkpoint selection is implicit. `rewind` always targets the single `#checkpointState` captured by the last successful `checkpoint`; there is no checkpoint list, label, or ID parameter.\n- Restored state is transcript/session-tree state only:\n  - in-memory `agent.state.messages` prefix up to `checkpointMessageCount`\n  - persisted session leaf reset to `checkpointEntryId` or root fallback\n  - retained rewind report as `branch_summary` and hidden `rewind-report` custom message\n- Not restored:\n  - filesystem contents\n  - git state\n  - artifacts under `packages/coding-agent/src/session/artifacts.ts`\n  - blob-store payloads under `packages/coding-agent/src/session/blob-store.ts`\n  - prompt history rows in `packages/coding-agent/src/session/history-storage.ts`\n  - auth or other agent storage in `packages/coding-agent/src/session/agent-storage.ts`\n- There is no concurrent-edit reconciliation. If code or session-adjacent state changes during the checkpoint window, rewind does not merge or revert them; it only drops conversation context and rewires the session branch.\n- Rewind is not destructive to persisted session history. `branchWithSummary()` appends a new `branch_summary` entry and moves the leaf; it does not delete the abandoned path from the `.jsonl` session log. The active context is cut over to the new branch, but the old entries remain in session storage.\n",
 	"tools/search.md": "# search\n\n> Search file contents with a regex across files, directories, globs, and internal URLs.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/search.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/search.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/match-line-format.ts` — model-facing anchor formatting.\n  - `packages/coding-agent/src/tools/path-utils.ts` — path normalization, glob splitting, internal URL resolution.\n  - `packages/coding-agent/src/tools/file-recorder.ts` — file ordering for grouped output.\n  - `packages/coding-agent/src/tools/grouped-file-output.ts` — grouped per-file text layout.\n  - `packages/coding-agent/src/session/streaming-output.ts` — line truncation and final byte truncation.\n  - `packages/coding-agent/src/config/settings-schema.ts` — default context lines.\n  - `packages/natives/native/index.d.ts` — native `grep()` types exposed to TS.\n  - `crates/pi-natives/src/grep.rs` — native regex/file search implementation.\n  - `docs/natives-text-search-pipeline.md` — native search pipeline overview.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `pattern` | `string` | Yes | Regex pattern. `search.ts` trims it and rejects empty input. The native matcher enables multiline only when the pattern text contains a literal newline or the two-character sequence `\\\\n`. The model prompt explicitly documents literal-brace escaping such as ``interface\\\\{\\\\}``, although the native layer also auto-escapes braces that cannot be valid repetition quantifiers. |\n| `paths` | `string[]` | Yes | One or more file paths, directory paths, glob-like paths, or internal URLs. Empty strings are rejected after trimming/quote stripping. Internal URLs must resolve to a backing file and cannot contain glob characters. |\n| `i` | `boolean` | No | Case-insensitive search. Defaults to `false`. Passed to native `ignoreCase`. |\n| `gitignore` | `boolean` | No | Respect `.gitignore` during directory scans. Defaults to `true`. Passed to native `gitignore`. |\n| `skip` | `number` | No | Global match offset. Defaults to `0`. `search.ts` floors finite numbers and rejects negative or non-finite values. |\n\n## Outputs\nThe tool returns a single text block in `content[0].text` plus structured `details`.\n\n- Match lines are formatted by `formatMatchLine()` as `*<anchor>|<line>` for matches and ` <anchor>|<line>` for context.\n  - Hashline mode: `*5th|content`, ` 9x}|content`.\n  - Plain mode: `*5|content`, ` 9|content`.\n- Directory results are grouped by file, with `# <path>` headings and blank lines between groups.\n- `details` may include:\n  - `scopePath` — formatted search scope.\n  - `matchCount`, `fileCount`, `files`, `fileMatches` — counts for the returned page, not necessarily total corpus counts.\n  - `matchLimitReached` — visible-page limit hit (`100`).\n  - `resultLimitReached` — native preselection limit hit (`500`).\n  - `linesTruncated` — one or more matched lines were shortened to `1024` chars plus `…`.\n  - `truncated` and `meta.truncation` — final text output was head-truncated by `truncateHead()`.\n  - `displayContent` — TUI-only rendering text with `│` gutters instead of model anchors.\n  - `missingPaths` — multi-path entries skipped because their base path did not exist.\n- No-match result text is `No matches found`, optionally followed by `Skipped missing paths: ...`.\n\n## Flow\n1. `SearchTool.execute()` validates and normalizes input in `packages/coding-agent/src/tools/search.ts`:\n   - trims `pattern`, rejects empty patterns;\n   - normalizes `skip` to a non-negative integer;\n   - reads `search.contextBefore` and `search.contextAfter` from session settings (`1` and `3` by default);\n   - enables multiline only when `pattern` contains `\\n` or an actual newline.\n2. Each `paths` entry is normalized with `normalizePathLikeInput()`.\n3. Internal URLs are resolved through `session.internalRouter`:\n   - glob metacharacters (`*`, `?`, `[`, `{`) are rejected for internal URLs;\n   - URLs without `resource.sourcePath` fail;\n   - immutable sources are tracked so output can suppress editable hashline anchors per file.\n4. For multi-path calls, `partitionExistingPaths()` skips only ENOENT entries. If every entry is missing, the tool errors.\n5. Path resolution branches:\n   - one entry: `parseSearchPath()` splits `basePath` and optional glob;\n   - multiple entries: `resolveExplicitSearchPaths()` computes a common base directory, brace-union glob, exact-file list, or degenerate-root target list.\n6. `search.ts` stats the resolved base path to decide file vs directory behavior.\n7. It calls native `grep()` from `@gajae-code/natives` with:\n   - `pattern`, `ignoreCase`, `multiline`, `gitignore`;\n   - `hidden: true`;\n   - `cache: false`;\n   - `contextBefore` / `contextAfter` from settings;\n   - `maxColumns: 1024`;\n   - `mode: content`.\n8. Native execution happens in `crates/pi-natives/src/grep.rs`:\n   - `build_matcher()` sanitizes non-quantifier braces before regex compile;\n   - if compile fails with unopened/unclosed-group errors, it retries after escaping previously unescaped parentheses;\n   - directory scans use the grep pipeline described in `docs/natives-text-search-pipeline.md`.\n9. Search dispatch differs by resolved path set:\n   - exact explicit files or degenerate-root multi-targets: JS loops over targets and merges `grep()` results itself;\n   - single file/directory base: one `grep()` call handles offset/limit natively.\n10. JS output shaping then:\n   - round-robins directory matches down to `100` visible matches so one file does not monopolize the page;\n   - keeps the first `100` file matches for single-file searches;\n   - formats lines through `formatMatchLine()` for the model and `formatCodeFrameLine()` for TUI;\n   - records non-truncated matched/context lines into the session file-read cache with `recordSparse()`.\n11. Final text is passed through `truncateHead(rawOutput, { maxLines: Number.MAX_SAFE_INTEGER })`, so the effective cap is the default byte cap from `streaming-output.ts`, not the default line cap.\n12. `toolResult()` attaches text plus limit/truncation metadata.\n\n## Modes / Variants\n1. **Single file path**\n   - `grep()` searches one file.\n   - Output is a flat list of match/context lines.\n   - Visible limit is the first `100` matches after native offset handling.\n2. **Single directory path or single glob-like path**\n   - `parseSearchPath()` may split the input into `path` + `glob`.\n   - One native `grep()` scans the directory tree with `gitignore` and `hidden:true`.\n   - Native `offset` handles `skip` globally across files.\n   - JS round-robins the returned matches to `100` visible rows.\n3. **Multiple explicit paths/globs**\n   - `resolveExplicitSearchPaths()` collapses them into a common base and either a brace-union glob, an explicit file list, or per-target searches when the only common base is the filesystem root.\n   - Missing entries are skipped non-fatally unless all are missing.\n4. **Internal URL paths**\n   - Supported only when the internal resource resolves to a real backing file.\n   - No internal-URL globbing.\n   - Immutable sources switch to the immutable display mode when formatting anchors.\n\n## Side Effects\n- Filesystem\n  - Stats resolved search roots and input paths.\n  - Reads matched files through native `grep()`.\n  - Records sparse matched/context lines into the session file-read cache via `getFileReadCache(...).recordSparse(...)`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Reads session settings for context defaults.\n  - Uses `session.internalRouter` to resolve internal URLs.\n  - Populates tool `details.meta` with truncation/limit metadata.\n- Background work / cancellation\n  - Wrapped in `untilAborted(signal, ...)` at the JS level.\n  - `search.ts` does not pass `signal` or `timeoutMs` into native `grep()`, so native grep cancellation/timeouts are not used by this tool.\n\n## Limits & Caps\n- Visible page limit: `100` matches (`DEFAULT_MATCH_LIMIT` in `packages/coding-agent/src/tools/search.ts`).\n- Native preselection limit: `500` matches (`internalLimit = Math.min(DEFAULT_MATCH_LIMIT * 5, 2000)` in `packages/coding-agent/src/tools/search.ts`).\n- Line truncation: `1024` characters per emitted line (`DEFAULT_MAX_COLUMN` in `packages/coding-agent/src/session/streaming-output.ts`). Native grep marks truncated lines; JS reports `linesTruncated`.\n- Final text truncation: `truncateHead()` default byte cap `50 * 1024` bytes (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`). `search.ts` overrides `maxLines` to `Number.MAX_SAFE_INTEGER`, so normal search output is byte-capped, not line-capped.\n- Context defaults: `search.contextBefore = 1`, `search.contextAfter = 3` in `packages/coding-agent/src/config/settings-schema.ts`.\n- Pagination: `skip` is a global match offset. In single-base searches it is pushed into native `offset`; in exact-file/multi-target aggregation it is applied in JS with `matches.slice(skip)`.\n- Native directory-scan cache: available in `grep.rs`, but this tool always sets `cache: false`.\n\n## Errors\n- `Pattern must not be empty` when trimmed `pattern` is empty.\n- `Skip must be a non-negative number` for negative or non-finite `skip`.\n- `` `paths` must contain non-empty paths or globs `` when any normalized path is empty.\n- `Glob patterns are not supported for internal URLs: ...` for internal URL + glob metacharacters.\n- `Cannot search internal URL without a backing file: ...` when the router resolves a virtual resource without `sourcePath`.\n- `Path not found: ...` when the resolved base path is missing, or when every multi-path entry is missing.\n- Regex compile failures bubble from native `grep()` as tool errors. `search.ts` has a special catch for messages beginning with `regex parse error`, then otherwise rethrows.\n- Multi-file native scans skip per-file open/search failures inside `grep.rs`; the scan continues with surviving files.\n\n## Notes\n- The model-facing prompt documents standard regex syntax plus two search-specific rules: escape literal braces, and use `\\n` or a literal newline for cross-line matching.\n- Native `build_matcher()` already auto-escapes braces that cannot be valid quantifiers, so patterns like `${platform}` become searchable instead of failing. Valid quantifiers like `a{2,4}` remain unchanged.\n- Native compile retry also escapes unescaped literal parentheses only after an unopened/unclosed-group parse error. It is a fallback, not a general parser mode.\n- Internal URLs are resolved before path existence checks. After resolution, the native layer sees ordinary filesystem paths.\n- `hidden:true` is hard-coded in `search.ts`; there is no model-facing flag to exclude dotfiles.\n- `gitignore:false` only affects native directory traversal. It does not disable the tool's own path normalization or explicit-file handling.\n- When `paths` resolves to multiple exact files, `search.ts` does not apply the native `500` match cap and reports `totalMatches` internally as the post-skip length for that branch.\n- The anchor suffix in hashline mode comes from `computeLineHash()` in `packages/coding-agent/src/hashline/hash.ts`; `search` itself only formats it.\n",
 	"tools/search_tool_bm25.md": "# search_tool_bm25\n\n> Search the hidden tool-discovery index and activate the top matches for the current session.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/search-tool-bm25.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/search-tool-bm25.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tool-discovery/tool-index.ts` — discoverable-tool metadata and BM25 index/search.\n  - `packages/coding-agent/src/session/agent-session.ts` — session discovery mode, corpus assembly, activation, cache invalidation.\n  - `packages/coding-agent/src/sdk.ts` — initial hiding of discoverable built-ins and prompt-time discoverable summary.\n  - `packages/coding-agent/src/tools/index.ts` — tool-session discovery hooks, essential/discoverable load modes, registry wiring.\n  - `packages/coding-agent/src/config/settings-schema.ts` — `tools.discoveryMode` and legacy `mcp.discoveryMode` settings.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `query` | `string` | Yes | Natural-language or keyword query. Trimmed before search; empty-after-trim is rejected. |\n| `limit` | `integer` | No | Max matches to return and activate. Minimum `1`. Defaults to `8` (`DEFAULT_LIMIT`). |\n\n## Outputs\n- Single-shot `AgentToolResult`.\n- Model-visible `content` is one text part containing JSON with:\n\n```json\n{\"query\":\"...\",\"activated_tools\":[\"...\"],\"match_count\":2,\"total_tools\":17}\n```\n\n- Runtime-only `details` carries the ranked matches used by the TUI renderer:\n  - `query`, `limit`, `total_tools`\n  - `activated_tools`: tool names activated by this call\n  - `active_selected_tools`: cumulative discovered-tool selections still active\n  - `tools`: array of match objects with\n    - `name`\n    - `label`\n    - `description` (`tool.summary`; this is the only snippet-like field)\n    - optional `server_name`\n    - optional `mcp_tool_name`\n    - `schema_keys`\n    - `score` rounded to 6 decimals\n- The renderer shows a status line plus up to 5 collapsed tree items by default (`COLLAPSED_MATCH_LIMIT`), each with label, optional server name, score to 3 decimals, and truncated description. The ranked match list is not serialized into `content`.\n\n## Flow\n1. `SearchToolBm25Tool.createIf()` in `packages/coding-agent/src/tools/search-tool-bm25.ts` exposes the tool only when `tools.discoveryMode !== \"off\"` and the session implements discovery hooks.\n2. `description` is rendered from `packages/coding-agent/src/prompts/tools/search-tool-bm25.md` via `renderSearchToolBm25Description()`, using the current discoverable-tool list plus per-server summary/count.\n3. `execute()` re-checks capability and settings:\n   - missing discovery hooks -> `ToolError(\"Tool discovery is unavailable in this session.\")`\n   - discovery disabled -> `ToolError(\"Tool discovery is disabled. Enable tools.discoveryMode or mcp.discoveryMode to use search_tool_bm25.\")`\n4. `query` is trimmed and validated; `limit` is defaulted/validated.\n5. `getDiscoverableToolSearchIndexForExecution()` fetches the cached generic search index from the session when available, otherwise rebuilds an index from the current discoverable-tool list.\n6. `getSelectedToolNames()` reads the current discovered selections so already-selected tools can be excluded from fresh results.\n7. `searchDiscoverableTools()` in `packages/coding-agent/src/tool-discovery/tool-index.ts` tokenizes the query, scores every document with BM25, sorts by descending score then `tool.name`, and returns up to `searchIndex.documents.length` results; `execute()` then filters already-selected names and slices to `limit`.\n8. If any matches remain, `activateTools()` activates all matched tool names through `session.activateDiscoveredTools()`.\n9. `details` is assembled from the activated names, current selected names, corpus size, and formatted matches; `content` is reduced to the compact JSON summary from `buildSearchToolBm25Content()`.\n10. `searchToolBm25Renderer` renders either:\n   - the structured `details` view, or\n   - a fallback text-only warning block if `details` is absent.\n\n## Modes / Variants\n- Discovery-mode gating:\n  - `tools.discoveryMode = \"all\"`: searches hidden discoverable built-ins.\n- Search-index source:\n  - generic cached discoverable index from the session\n  - rebuilt ad hoc from the current discoverable-tool list if neither cache path works\n- Activation backend:\n  - generic `activateDiscoveredTools()`\n  - legacy `activateDiscoveredMCPTools()` fallback\n\n## Side Effects\n- Session state\n  - Adds matched tools to the active session tool set through `activateDiscoveredTools()`.\n  - Updates discovered-tool selection state so repeated searches accumulate selections instead of replacing them.\n  - Invalidates the cached discoverable search index when newly activated built-ins change the hidden corpus (`packages/coding-agent/src/session/agent-session.ts`).\n  - Tool availability changes before the next model call in the same turn; the prompt text says this explicitly.\n- User-visible prompts / interactive UI\n  - The tool description includes discoverable server summaries and total discoverable-tool count.\n  - The TUI renderer shows ranked matches, but the model-visible text summary does not.\n\n## Limits & Caps\n- Default result cap: `8` (`DEFAULT_LIMIT` in `packages/coding-agent/src/tools/search-tool-bm25.ts`).\n- `limit` must be a positive integer; no tool-level upper bound beyond corpus size.\n- Renderer collapsed list cap: `5` (`COLLAPSED_MATCH_LIMIT`).\n- Renderer truncation widths:\n  - label: `72` chars (`MATCH_LABEL_LEN`)\n  - description: `96` chars (`MATCH_DESCRIPTION_LEN`)\n- BM25 parameters in `packages/coding-agent/src/tool-discovery/tool-index.ts`:\n  - `BM25_K1 = 1.2`\n  - `BM25_B = 0.75`\n- Weighted corpus fields (`FIELD_WEIGHTS`):\n  - `name`: `6`\n  - `label`: `4`\n  - `mcpToolName`: `4`\n  - `serverName`: `2`\n  - `summary`: `2`\n  - each `schemaKey`: `1`\n- Summary fallback length for discoverable metadata: first `200` chars of `description` when no explicit summary exists (`getDiscoverableTool()` in `packages/coding-agent/src/tool-discovery/tool-index.ts`).\n\n## Errors\n- `execute()` throws `ToolError` for unavailable discovery hooks, disabled discovery mode, empty trimmed query, and non-positive/non-integer `limit`.\n- `searchDiscoverableTools()` throws `Error(\"Query must contain at least one letter or number.\")` if tokenization produces no alphanumeric tokens; `execute()` catches `Error` and rethrows `ToolError(error.message)`.\n- Empty corpus is not an error; search returns `[]`, activation is skipped, and the renderer message becomes either `No discoverable tools are currently loaded.` or `No matching tools found.`\n- `getDiscoverableToolsForDescription()` and `getDiscoverableToolSearchIndexForExecution()` swallow discovery-hook/cache errors and fall back to an empty corpus or rebuilt index.\n\n## Notes\n- The tool wire name stays `search_tool_bm25` for persisted-session back-compat, even though the source file is `search-tool-bm25.ts`.\n- Corpus composition is session-dependent and excludes already-active tools:\n  - Built-in entries appear only in `\"all\"` mode and only for registry tools whose `loadMode === \"discoverable\"` and are not currently active.\n  - Hidden/internal built-ins are intentionally excluded from the built-in corpus: `resolve`, `yield`, `report_finding`, `report_tool_issue` are called out in the `#collectDiscoverableBuiltinTools()` comment.\n- `AgentSession.getDiscoverableTools()` currently assembles built-in discoverable tools.\n- On startup, `packages/coding-agent/src/sdk.ts` hides non-essential discoverable built-ins in `tools.discoveryMode = \"all\"`; defaults are `read`, `bash`, and `edit` unless `tools.essentialOverride` changes them.\n- Query tokenization is simple and deterministic: camelCase is split, non-alphanumerics become spaces, tokens are lowercased, and only non-empty alphanumeric tokens survive.\n- Scores are rounded differently by surface: `details.tools[].score` keeps 6 decimals; the TUI line renders 3.\n",