@gajae-code/coding-agent 0.8.0 → 0.8.2

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

@@ -12,7 +12,7 @@ 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",
 	"bot-integration.md": "# External controller integration guide\n\nThis guide is for authors of bots and orchestrators that want to drive Gajae-Code (`gjc`) without scraping terminal scrollback. Hermes, OpenClaw, GitHub bots, chatops bots, and custom schedulers are examples of external controllers; none of them need bespoke GJC behavior if they can speak the Coordinator MCP or RPC lifecycle below.\n\nGJC is an external runner. Your controller owns queueing, identity, policy, and credentials; GJC owns the coding-agent session, workflows, tools, artifacts, and evidence inside the selected repository or worktree.\n\n## Integration surfaces\n\nUse the smallest surface that fits your bot:\n\n| Surface | Best for | Command | Stability notes |\n| --- | --- | --- | --- |\n| Coordinator MCP | Any external controller that can call MCP tools to start/register tmux sessions, send turns, answer questions, and read artifacts. | `gjc mcp-serve coordinator` | Preferred orchestration surface. `gjc mcp-serve hermes` is a compatibility alias, not a separate contract. |\n| Setup adapter | Rendering a portable MCP config and operator instructions for a controller profile. | `gjc setup hermes --root /path/to/repo` | Compatibility-oriented config renderer; does not call an LLM or validate provider credentials. |\n| RPC stdio | A controller that embeds a single `gjc --mode rpc` subprocess and handles JSONL frames directly or through `python/gjc-rpc`. | `gjc --mode rpc` | Best for process-backed, single-session bot workers. |\n| Bridge HTTPS | Experimental remote control for an already-running session. | `gjc --mode bridge` | Session-control endpoints are fail-closed by default; do not use as the default bot lifecycle surface yet. |\n| Visible tmux fallback | Human-supervised lanes where an existing visible `gjc --tmux` pane should become coordinator-authoritative. | `gjc --tmux`, then `gjc_coordinator_register_session` | Use when an operator already opened a pane or wants direct terminal visibility. |\n\n## Recommended architecture\n\n```text\nexternal controller / bot\n  ├─ chooses repo/worktree and task policy\n  ├─ starts MCP server: gjc mcp-serve coordinator\n  ├─ starts or registers one GJC tmux session\n  ├─ sends one bounded turn at a time\n  ├─ answers structured questions explicitly\n  ├─ marks turn completion/failure with report_status\n  └─ reads artifacts/reports from allowlisted roots\n```\n\nDo not infer completion from terminal output. Treat durable turn state as authoritative and tmux tail output as advisory debug context only.\n\n## Coordinator MCP setup\n\nRender a non-mutating config preview:\n\n```sh\ngjc setup hermes --root /path/to/repo --profile my-bot --repo my-repo\n```\n\nInstall into a Hermes-compatible profile only when the target path is intentional:\n\n```sh\ngjc setup hermes \\\n  --root /path/to/repo \\\n  --profile my-bot \\\n  --repo my-repo \\\n  --mutation sessions,questions,reports \\\n  --profile-dir /path/to/hermes/profile \\\n  --install\n```\n\nRun provider-independent contract smokes before trying a live model:\n\n```sh\ngjc setup hermes --root /path/to/repo --smoke --json\ngjc mcp-serve coordinator --check --json\n```\n\nThe generated config uses these environment variables:\n\n| Variable | Purpose |\n| --- | --- |\n| `GJC_COORDINATOR_MCP_WORKDIR_ROOTS` | Required allowlist for workdirs and artifact paths. |\n| `GJC_COORDINATOR_MCP_MUTATIONS` | Startup opt-in for mutation classes: `sessions`, `questions`, `reports`, or `all`. |\n| `GJC_COORDINATOR_MCP_SESSION_COMMAND` | Command used to start real GJC sessions, defaulting to `gjc --worktree` in generated setup. |\n| `GJC_COORDINATOR_MCP_PROFILE` | Optional profile namespace so one bot cannot enumerate another profile's state. |\n| `GJC_COORDINATOR_MCP_REPO` | Optional repo namespace so one repo cannot enumerate another repo's state. |\n| `GJC_COORDINATOR_MCP_STATE_ROOT` | Optional coordination state root; defaults under `.gjc/state/coordinator-mcp`. |\n| `GJC_COORDINATOR_MCP_ARTIFACT_BYTE_CAP` | Maximum bytes returned by artifact reads. |\n\nMutating calls require both startup opt-in and per-call `allow_mutation: true`. Missing either one fails closed.\n\n## Generic smoke strategy\n\nUse three different smoke levels so CI does not depend on one operator's model, API key, tmux layout, or desktop:\n\n| Smoke | Required for CI | What it proves | Example |\n| --- | --- | --- | --- |\n| Contract smoke | Yes | MCP server metadata, tool discovery, exported tool names, input schemas, read-only default, and mutation-gate failures. No provider credentials or tmux pane required. | `gjc mcp-serve coordinator --check --json` and focused tests around `tools/list` plus mutation denial. |\n| Dry-run lifecycle smoke | Yes when changed behavior affects lifecycle state | A generic controller can start/register a mocked session, send a turn, observe active-turn protection, report terminal status, and read the completed turn without a real LLM. | `bun test packages/coding-agent/test/coordinator-mcp.test.ts` uses mocked coordinator services and temporary state roots. |\n| Optional live smoke | No | One operator's local provider/model/profile/tmux setup can run end-to-end in their chosen repo. Failure diagnoses that setup; it must not fail CI or PR validation. | Start `gjc mcp-serve coordinator` with local env, dispatch a tiny task, then report/read evidence. |\n\nA public bot integration change should at least preserve the contract smoke and local-leak docs test. Live smokes are diagnostics, not mandatory gates.\n\n## MCP tool contract\n\nRead-only tools:\n\n- `gjc_coordinator_list_sessions`\n- `gjc_coordinator_read_status`\n- `gjc_coordinator_read_tail`\n- `gjc_coordinator_read_turn`\n- `gjc_coordinator_await_turn`\n- `gjc_coordinator_list_questions`\n- `gjc_coordinator_list_artifacts`\n- `gjc_coordinator_read_artifact`\n- `gjc_coordinator_read_coordination_status`\n- `gjc_coordinator_watch_events`\n\nMutating tools:\n\n- `gjc_coordinator_start_session`\n- `gjc_coordinator_register_session`\n- `gjc_coordinator_send_prompt`\n- `gjc_coordinator_submit_question_answer`\n- `gjc_coordinator_report_status`\n\nHigh-level delegation tools:\n\n- `gjc_delegate_plan`\n- `gjc_delegate_execute`\n- `gjc_delegate_team`\n\nThe `gjc_delegate_*` tools package common GJC workflows for hosts that want to delegate an entire planning, execution, or team turn without manually composing `start_session` and `send_prompt`. They use the same coordinator mutation gates and workdir allowlists as the lower-level session tools.\n\n### Start a managed GJC session\n\nCall `gjc_coordinator_start_session` with a canonical workdir inside `GJC_COORDINATOR_MCP_WORKDIR_ROOTS`:\n\n```json\n{\n  \"cwd\": \"/path/to/repo\",\n  \"prompt\": \"Optional first bounded task prompt\",\n  \"allow_mutation\": true\n}\n```\n\nThe returned payload includes `session.session_id`, `session_state`, and, when a prompt is provided, `turn_id`, `status`, `delivery`, `queued`, and `delivered`.\n\n### Register a visible tmux fallback session\n\nIf an operator already started a visible session, register it instead of starting a hidden coordinator session:\n\n```sh\ngjc --tmux\n```\n\n```json\n{\n  \"session_id\": \"visible-gjc-1\",\n  \"cwd\": \"/path/to/repo\",\n  \"tmux_session\": \"visible-gjc-1\",\n  \"tmux_target\": \"visible-gjc-1:0.0\",\n  \"visible\": true,\n  \"source\": \"operator-visible-tmux\",\n  \"allow_mutation\": true\n}\n```\n\n`gjc_coordinator_register_session` validates safe ids, workdir allowlists, tmux target syntax, and liveness before writing coordinator state.\n\n### Send work as turns\n\nSend one bounded task prompt and persist the returned `turn_id`:\n\n```json\n{\n  \"session_id\": \"gjc-demo\",\n  \"prompt\": \"Use /skill:ralplan to build a plan for ...\",\n  \"allow_mutation\": true\n}\n```\n\nA session may have one active turn by default. A second prompt returns `active_turn_exists` unless the bot passes:\n\n- `queue: true` to enqueue a durable follow-up turn, or\n- `force: true` to supersede the previous active turn and audit the supersession.\n\n### Wait or watch for completion\n\nUse `gjc_coordinator_read_turn` for polling or `gjc_coordinator_await_turn` for bounded waiting:\n\n```json\n{\n  \"session_id\": \"gjc-demo\",\n  \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"timeout_ms\": 30000,\n  \"poll_interval_ms\": 1000,\n  \"lines\": 80\n}\n```\n\nTerminal turn statuses are `completed`, `failed`, `cancelled`, and `superseded`. Non-terminal statuses include `queued`, `delivering`, `active`, `waiting_for_answer`, and `completing`.\n\nWhen the work is done, your bot must call `gjc_coordinator_report_status` with the turn id. This writes the final response/error, evidence paths, and coordinator report that later reads consume:\n\n```json\n{\n  \"session_id\": \"gjc-demo\",\n  \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"status\": \"completed\",\n  \"summary\": \"Implemented the requested fix and ran focused tests.\",\n  \"evidence_paths\": [\"/path/to/repo/test-output.txt\"],\n  \"allow_mutation\": true\n}\n```\n\nUse `status: \"failed\"` plus `blocker` for provider failures, unrecoverable tool failures, missing credentials, policy denial, or task blockers.\nUse `status: \"cancelled\"` when the coordinator policy intentionally stops tracking an active turn, for example after an operator abort or a bot-side shutdown decision. This records the turn as terminal in coordinator state; it does not kill the underlying tmux process. To supersede one active turn with replacement work, send the replacement prompt with `force: true` and preserve the superseded turn id in your audit trail.\n\n### Forward finish/stop lifecycle notifications\n\nDiscord, Hermes, Clawhip, and similar external notifiers should be opt-in and should forward only the public lifecycle surface. Use one of these supported paths:\n\n- Coordinator controllers: watch or poll turn state with `gjc_coordinator_watch_events`, `gjc_coordinator_await_turn`, or `gjc_coordinator_read_turn`, then notify from the terminal turn status your controller records with `gjc_coordinator_report_status`.\n- In-process extensions or hooks: subscribe to the public lifecycle events `turn_end` and `agent_end` from the shared hook/extension event contract.\n\nRecommended notification mapping:\n\n| Notification intent | Public surface | Safe meaning |\n| --- | --- | --- |\n| Turn finished | `turn_end` or terminal coordinator turn status `completed` | One LLM turn produced its final assistant message. |\n| Agent stopped / finished | `agent_end` | The agent loop ended for the submitted prompt. |\n| Waiting for user | Coordinator turn status `waiting_for_answer` | The agent is blocked on a structured question. |\n| Failed or blocked | Coordinator status `failed` with a public `blocker` summary | The controller recorded a terminal failure. |\n| Cancelled / superseded | Coordinator status `cancelled` or `superseded` | The controller intentionally stopped tracking or replaced the turn. |\n\nDo not forward raw prompts, transcripts, tool outputs, hidden instructions, private configs, host paths, channel ids, webhook URLs, or tokens. If your notifier needs a human-readable sentence, create a caller-supplied sanitized summary and keep provider/tool details out of the payload.\n\nExample public-safe extension event payloads:\n\n```json\n{ \"type\": \"turn_end\", \"turnIndex\": 2, \"summary\": \"Turn finished; review the local GJC session for details.\" }\n```\n\n```json\n{ \"type\": \"agent_end\", \"summary\": \"Agent loop ended; no raw transcript is included.\" }\n```\n\nExample opt-in forwarding policy:\n\n```json\n{\n  \"enabled\": true,\n  \"events\": [\"turn_end\", \"agent_end\"],\n  \"destination\": \"external-notifier-profile\",\n  \"redaction\": \"metadata-only\"\n}\n```\n\nGJC does not currently expose a structured stop-reason field on `agent_end`; integrators that need `waiting_for_answer`, `failed`, `cancelled`, or `superseded` should prefer the Coordinator MCP turn status because it is explicit, terminal-state oriented, and safe to relay after controller-side redaction.\n\n### Answer structured questions\n\nList pending questions:\n\n```json\n{\n  \"session_id\": \"gjc-demo\",\n  \"status\": \"pending\"\n}\n```\n\nThen answer by id:\n\n```json\n{\n  \"session_id\": \"gjc-demo\",\n  \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"question_id\": \"question-1\",\n  \"answer\": { \"decision\": \"approve\" },\n  \"allow_mutation\": true\n}\n```\n\nAlways answer the advertised shape. Do not synthesize approvals for destructive actions unless your bot policy explicitly permits that action.\n\n### Read artifacts and reports\n\nUse `gjc_coordinator_list_artifacts` to inspect safe roots and `gjc_coordinator_read_artifact` to read a bounded artifact:\n\n```json\n{ \"path\": \"/path/to/repo/.gjc/ultragoal/ledger.jsonl\" }\n```\n\nArtifact paths are canonicalized, symlink escapes are rejected, and output is byte-capped. Use `gjc_coordinator_read_coordination_status` for status reports written through `gjc_coordinator_report_status`.\n\n## RPC stdio integration\n\nUse RPC when your bot owns a single worker subprocess rather than an MCP coordinator. The wire protocol is JSONL over stdio:\n\n```sh\ngjc --mode rpc --provider anthropic --model claude-sonnet-4-5\n```\n\nRecommended Python client:\n\n```python\nfrom gjc_rpc import RpcClient, WorkflowGate\n\nwith RpcClient(no_session=True, no_rules=True) as client:\n    client.install_headless_ui()\n\n    def on_gate(gate: WorkflowGate) -> None:\n        if gate.kind == \"approval\":\n            client.respond_gate(gate.gate_id, {\"decision\": \"approve\"})\n\n    client.on_workflow_gate(on_gate)\n    turn = client.prompt_and_wait(\"Inspect this repo and report the integration contract.\")\n    print(turn.require_assistant_text())\n```\n\nRPC hosts can also expose host-owned tools and URI schemes. Use these to give GJC controlled access to your bot's issue tracker, queue, database rows, or artifact store without leaking long-lived credentials into the GJC process.\n\nKey RPC lifecycle facts:\n\n- `{ \"type\": \"ready\" }` means the subprocess is ready for commands.\n- `prompt` is acknowledged immediately; completion is observed through `agent_end` or `RpcClient.prompt_and_wait()`.\n- `workflow_gate` frames are answered with `workflow_gate_response`.\n- `extension_ui_request` frames are answered with `extension_ui_response` or a headless policy.\n- Host tool calls and host URI requests are explicit callback frames that must be completed or rejected by the host.\n- `RpcClient` enforces single-flight prompt lifecycle collection; use one client per concurrent worker.\n- `abort` and `abort_and_prompt` are the RPC cancellation commands for subprocess workers; coordinator MCP cancellation is recorded through terminal turn status instead.\n\n## Error handling playbook\n\n| Situation | Bot behavior |\n| --- | --- |\n| `coordinator_mutation_class_disabled:*` | Re-render setup with the required mutation class, or keep the bot in read-only mode. |\n| `coordinator_mutation_call_not_allowed:*` | Add `allow_mutation: true` only after policy approval for that specific call. |\n| `unknown_session` | Re-list sessions; start a new managed session or register the visible tmux fallback. |\n| `active_turn_exists` | Poll the active turn, send with `queue: true`, or use `force: true` only when supersession is intentional. |\n| `timeout` from `await_turn` | Treat as non-terminal. Poll again or inspect `read_status`/`read_tail`; do not mark failure solely from a bounded wait timeout. |\n| Coordinator cancellation | Use `gjc_coordinator_report_status` with `status: \"cancelled\"` for an intentionally stopped turn, or send replacement work with `force: true` when supersession is policy-approved. This is coordinator state, not a tmux process kill. |\n| Stale tmux/session state | Check `read_status.session_state` and advisory liveness. Register a new visible session or report the turn failed with a recoverable blocker. |\n| Provider/auth failure | Capture the model/provider error in `report_status` with `status: \"failed\"`; do not retry forever without a policy budget. |\n| Artifact denied | Keep the artifact inside allowlisted roots and avoid symlink escapes. |\n| Malformed or invalid question answer | Re-read the question/gate schema and submit a value matching the advertised shape. |\n| Bot shutdown | Persist `session_id` and active `turn_id`; on restart use `read_turn` and `read_status` before sending more work. |\n\n## Controller examples\n\nGeneric MCP controller config:\n\n```json\n{\n  \"mcp_servers\": {\n    \"gjc_coordinator\": {\n      \"command\": \"gjc\",\n      \"args\": [\"mcp-serve\", \"coordinator\"],\n      \"env\": {\n        \"GJC_COORDINATOR_MCP_WORKDIR_ROOTS\": \"/home/bot/src/project:/home/bot/src/worktrees\",\n        \"GJC_COORDINATOR_MCP_MUTATIONS\": \"sessions,questions,reports\",\n        \"GJC_COORDINATOR_MCP_PROFILE\": \"controller-prod\",\n        \"GJC_COORDINATOR_MCP_REPO\": \"project\",\n        \"GJC_COORDINATOR_MCP_SESSION_COMMAND\": \"gjc --worktree\"\n      },\n      \"enabled\": true\n    }\n  }\n}\n```\n\nExample controller loop:\n\n```text\n1. Start `gjc mcp-serve coordinator` with repo/worktree roots allowlisted.\n2. Call `gjc_coordinator_start_session` for a GJC-managed worktree session.\n3. Send `/skill:deep-interview`, `/skill:ralplan`, or an approved `gjc ultragoal ...` task as one turn.\n4. Await the turn; answer `gjc_coordinator_list_questions` entries using bot policy.\n5. Report terminal status with evidence paths.\n6. Read artifacts/reports for the user-facing bot response.\n```\n\nHermes and OpenClaw can use the same MCP tool contract. Their names here are examples of controller products, not privileged integration modes.\n\n## Security and credential boundaries\n\n- Do not put provider API keys, GitHub tokens, or bot secrets in prompts.\n- Prefer host tools, host URI schemes, or bot-side sidecars for credentialed external writes.\n- Keep `GJC_COORDINATOR_MCP_WORKDIR_ROOTS` narrow; do not allow `/`, `/home`, or broad parent directories.\n- Use namespaces for multi-tenant bots.\n- Keep mutation classes minimal: read-only for dashboards, `sessions` for work dispatch, `questions` for answering questions, and `reports` for final state.\n- Treat `.gjc/` as local runtime state and evidence. Do not expose it wholesale to untrusted users.\n\n## Related references\n\n- [`docs/hermes-mcp-bridge.md`](./hermes-mcp-bridge.md) — coordinator MCP details and setup adapter behavior.\n- [`docs/rpc.md`](./rpc.md) — JSONL RPC protocol, event frames, workflow gates, host tools, and host URI schemes.\n- [`docs/bridge.md`](./bridge.md) — experimental HTTPS bridge and fail-closed endpoint matrix.\n- [`python/gjc-rpc/README.md`](../python/gjc-rpc/README.md) — typed Python RPC client examples.\n- [`python/robogjc/README.md`](../python/robogjc/README.md) — example self-hosted GitHub bot using `gjc --mode rpc`.\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/logo-vertical.png`](../assets/logo-vertical.png) | Vertical README/docs logo lockup for Gajae-Code. |\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/rlm.png`](../assets/rlm.png) | Feature card for the `rlm` research/REPL mode (scientist mascot). |\n| [`assets/computer-use.png`](../assets/computer-use.png) | Feature card for the `computer-use` desktop-control surface (operator mascot). |\n| [`assets/telegram-mobile-hero.png`](../assets/telegram-mobile-hero.png) | Feature card for the 0.7.0 Telegram/mobile notifications flow. |\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",
+	"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/logo-vertical.png`](../assets/logo-vertical.png) | Vertical README/docs logo lockup for Gajae-Code. |\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/rlm.png`](../assets/rlm.png) | Feature card for the `rlm` research/REPL mode (scientist mascot). |\n| [`assets/computer-use.png`](../assets/computer-use.png) | Feature card for the `computer-use` desktop-control surface (operator mascot). |\n| [`assets/telegram-mobile-hero.png`](../assets/telegram-mobile-hero.png) | Feature card for the Telegram/mobile notifications flow. |\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",
 	"bridge.md": "# Bridge Protocol Reference (Experimental, Fail-Closed)\n\nBridge mode runs the coding agent as an experimental network control surface over\nHTTPS. The session-control surface is intentionally **fail-closed by default**\nwhile 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 fail-closed configuration, a successful authenticated\nhandshake returns:\n\n- `protocol_version` — the server protocol version (`BRIDGE_PROTOCOL_VERSION`, `2`).\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\nWorkflow-gate responses are part of the UI-response surface, not the dormant command surface: when internally enabled, an answerer responds to `workflow_gate` frame `wg_...` by posting `{ \"gate_id\": \"wg_...\", \"answer\": ... }` to `POST /v1/sessions/{session_id}/ui-responses/{gate_id}`. Gate answers are authorized by bearer auth, the `control` scope on this (default-disabled) endpoint, and the currently claimed controller owner token. `X-GJC-Bridge-Owner-Token` must match the claimed controller token; mismatches return `403 not_controller` and do not resolve the gate. `Idempotency-Key` is optional and is also forwarded as `idempotency_key` when supplied by SDK helpers.\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| `get_pending_workflow_gates` | `message:read` |\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| `negotiate_unattended` | `control` |\n| `workflow_gate_response` | `control` |\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`, `workflow_gate`.\n\nFrame types: `ready`, `event`, `response`, `ui_request`, `permission_request`,\n`host_tool_call`, `host_uri_request`, `reset`, `workflow_gate`, `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. The bridge\nsession-control surface remains fail-closed by default, so against an\nunconfigured bridge those helpers should be expected to fail because the server\nendpoint matrix disables the corresponding session endpoints until they are\nexplicitly enabled.\n\n`BridgeClient.respondGate(sessionId, gateId, ownerToken, answer, options)` posts to the fail-closed UI-response endpoint and returns the gate resolution envelope emitted by the bridge. It deliberately does not send `workflow_gate_response` through `/commands`. Gate answers are authorized by bearer auth, the `control` scope on the (by-default-disabled) `ui-responses` endpoint, and the current controller owner token; unauthorized owner-token attempts return `403 not_controller` without resolving the gate.\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.\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` from that directory. If you want GJC to create the sibling worktree, use `gjc --tmux --worktree <branch-like-name>`; the argument is a worktree/branch name, not a filesystem path.\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. 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, ACP, and Bridge 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- `packages/coding-agent/src/coordinator/contract.ts` defines the transport-neutral third-party coordinator contract used by `gjc mcp-serve coordinator`, `gjc coordinator`, and `gjc setup hermes`.\n- `packages/coding-agent/src/coordinator-mcp/server.ts` implements the outward MCP adapter for bot/coordinator integrations, including session start/register, turn state, question answering, status reports, and artifact reads.\n- `docs/external-control-readiness.md` classifies the public external-control surfaces: Coordinator MCP for multi-session control planes, RPC stdio for subprocess workers, ACP for editor/ACP clients, and Bridge HTTPS as experimental/fail-closed protocol scaffolding.\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/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- `docs/bot-integration.md` is the practical entry guide for generic external controller and bot authors; it ties together coordinator MCP, RPC stdio, bridge limitations, visible tmux fallback, provider-independent smokes, errors, and artifact/report consumption.\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, ACP, or Bridge.\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",
 	"codegraph-custom-tool.md": "# CodeGraph as a custom tool\n\n[CodeGraph](https://github.com/colbymchenry/codegraph) is a local, language-agnostic\ncode knowledge graph for AI agents. It pre-indexes symbols, call edges, and\ndependencies in a project so an agent can answer structural questions (\"how does X\nwork\", \"who calls X\", \"what breaks if I change X\") in a few graph queries instead\nof crawling files with `search`/`read`.\n\nThis guide shows how to wire CodeGraph into GJC through the **custom-tool extension\npath** — no core changes, no built-in provider. GJC intentionally keeps third-party\nCLI integrations like this in the user/project extension layer rather than bundling\nthem, so you own the integration and its lifecycle.\n\n> CodeGraph integrates with other agents over MCP, but this guide wires it as a GJC\n> custom tool around CodeGraph's local **CLI** — it does not add an MCP server or a\n> built-in provider. For how GJC treats MCP servers in standalone sessions, see\n> [`standalone-mcp.md`](standalone-mcp.md).\n\n## 1. Install and index\n\n```bash\n# Install the CodeGraph CLI (or use the install script from CodeGraph's README).\nnpm i -g @colbymchenry/codegraph\n\n# Build the local index for a project.\ncd your-project\ncodegraph init\n```\n\n`codegraph init` creates a local `.codegraph/` directory. No data leaves your\nmachine — it is a local SQLite index.\n\n## 2. Add the custom tool\n\nGJC discovers custom tools from a `tools/` directory in its config dirs:\n\n- **Project-scoped**: `<project>/.gjc/tools/`\n- **User-scoped (all projects)**: `~/.gjc/agent/tools/`\n\nA `*.ts` tool file's default export is a factory `(pi) => CustomTool`. The factory\nreceives an API (`pi`) with members such as `exec`, `cwd`, `zod`, and `logger` — so\nthe tool needs no imports from GJC internals.\n\nSave the following as `.gjc/tools/codegraph.ts` (project) or\n`~/.gjc/agent/tools/codegraph.ts` (user):\n\n```typescript\n/**\n * CodeGraph custom tool for gajae-code (GJC).\n *\n * Wraps the local CodeGraph CLI (https://github.com/colbymchenry/codegraph) so the\n * agent can query a project's code knowledge graph instead of crawling files.\n *\n * It only runs CodeGraph's query-style (read-only) subcommands and never edits your\n * source files. It does not run indexing or sync commands. (CodeGraph maintains its\n * own local `.codegraph/` index via its own CLI; this tool only reads from it.)\n *\n * Prereqs: `npm i -g @colbymchenry/codegraph` and `codegraph init` in the project.\n */\nimport type { CustomToolFactory } from \"@gajae-code/coding-agent\"; // optional: editor types only\n\nconst CODEGRAPH_CLI = \"codegraph\";\nconst TIMEOUT_MS = 60_000;\nconst SEARCH_LIMIT_DEFAULT = 10;\nconst MAX = 100;\n\nconst codegraph: CustomToolFactory = (pi) => {\n\tconst z = pi.zod;\n\n\tconst parameters = z\n\t\t.object({\n\t\t\top: z\n\t\t\t\t.enum([\"explore\", \"search\", \"callers\", \"callees\", \"impact\", \"status\"])\n\t\t\t\t.describe(\n\t\t\t\t\t\"explore: context (relevant source + call paths) for a natural-language query — prefer for 'how does X work'; search: full-text symbol search (target=query); callers: who calls target; callees: what target calls; impact: blast radius of changing target; status: index health (no target).\",\n\t\t\t\t),\n\t\t\ttarget: z\n\t\t\t\t.string()\n\t\t\t\t.optional()\n\t\t\t\t.describe(\n\t\t\t\t\t\"For explore: a natural-language query or symbol(s). For callers/callees/impact: a symbol name. For search: the query. Omit for status.\",\n\t\t\t\t),\n\t\t\tlimit: z.number().int().min(1).max(MAX).optional().describe(`Max search results (default ${SEARCH_LIMIT_DEFAULT}).`),\n\t\t\tmaxFiles: z.number().int().min(1).max(MAX).optional().describe(\"For explore: cap files whose source is included.\"),\n\t\t})\n\t\t.strict();\n\n\ttype Params = import(\"zod/v4\").infer<typeof parameters>;\n\n\tfunction buildArgs(params: Params): string[] {\n\t\tif (params.op === \"status\") return [\"status\", pi.cwd, \"--json\"];\n\t\tconst target = params.target?.trim();\n\t\tif (!target) throw new Error(`codegraph ${params.op} requires a non-empty \"target\".`);\n\t\tif (params.op === \"search\") {\n\t\t\tconst limit = Math.min(params.limit ?? SEARCH_LIMIT_DEFAULT, MAX);\n\t\t\treturn [\"query\", target, \"--json\", \"--limit\", String(limit), \"--path\", pi.cwd];\n\t\t}\n\t\tif (params.op === \"explore\") {\n\t\t\tconst args = [\"explore\", target, \"--path\", pi.cwd];\n\t\t\tif (params.maxFiles !== undefined) args.push(\"--max-files\", String(params.maxFiles));\n\t\t\treturn args;\n\t\t}\n\t\treturn [params.op, target, \"--json\", \"--path\", pi.cwd];\n\t}\n\n\tfunction ref(r: { name: string; kind: string; filePath: string; startLine: number }): string {\n\t\treturn `  - ${r.name} (${r.kind}) — ${r.filePath}:${r.startLine}`;\n\t}\n\n\tfunction render(params: Params, stdout: string): string {\n\t\tif (params.op === \"explore\") return stdout.trim() || `No exploration results for \"${params.target?.trim() ?? \"\"}\".`;\n\t\tlet data: any;\n\t\ttry {\n\t\t\tdata = JSON.parse(stdout);\n\t\t} catch {\n\t\t\tthrow new Error(`codegraph ${params.op} returned unparseable output.`);\n\t\t}\n\t\tif (params.op === \"search\") {\n\t\t\tconst hits = data as Array<{ node: any }>;\n\t\t\tif (hits.length === 0) return `No symbols matched \"${params.target?.trim() ?? \"\"}\".`;\n\t\t\treturn [\n\t\t\t\t`${hits.length} symbol(s) matching \"${params.target?.trim() ?? \"\"}\":`,\n\t\t\t\t...hits.map(({ node }) => {\n\t\t\t\t\tconst exp = node.isExported ? \" [exported]\" : \"\";\n\t\t\t\t\tconst sig = node.signature ? ` ${node.signature}` : \"\";\n\t\t\t\t\treturn `  - ${node.name} (${node.kind})${sig}${exp} — ${node.filePath}:${node.startLine}`;\n\t\t\t\t}),\n\t\t\t].join(\"\\n\");\n\t\t}\n\t\tif (params.op === \"callers\") {\n\t\t\tconst list = data.callers ?? [];\n\t\t\treturn list.length === 0\n\t\t\t\t? `No callers found for \"${data.symbol}\".`\n\t\t\t\t: [`${list.length} caller(s) of \"${data.symbol}\":`, ...list.map(ref)].join(\"\\n\");\n\t\t}\n\t\tif (params.op === \"callees\") {\n\t\t\tconst list = data.callees ?? [];\n\t\t\treturn list.length === 0\n\t\t\t\t? `\"${data.symbol}\" has no recorded callees.`\n\t\t\t\t: [`${list.length} callee(s) of \"${data.symbol}\":`, ...list.map(ref)].join(\"\\n\");\n\t\t}\n\t\tif (params.op === \"impact\") {\n\t\t\tconst header = `Impact of changing \"${data.symbol}\" (depth ${data.depth}): ${data.nodeCount} node(s), ${data.edgeCount} edge(s) affected.`;\n\t\t\tconst list = data.affected ?? [];\n\t\t\treturn list.length === 0 ? header : [header, \"Affected:\", ...list.map(ref)].join(\"\\n\");\n\t\t}\n\t\t// status\n\t\tif (!data.initialized) return `CodeGraph is not initialized for ${data.projectPath}. Run \\`codegraph init\\`.`;\n\t\tconst lines = [\n\t\t\t`CodeGraph index for ${data.projectPath}:`,\n\t\t\t`  files: ${data.fileCount}, nodes: ${data.nodeCount}, edges: ${data.edgeCount}`,\n\t\t];\n\t\tif (data.languages?.length) lines.push(`  languages: ${data.languages.join(\", \")}`);\n\t\tconst p = data.pendingChanges;\n\t\tif (p && (p.added || p.modified || p.removed)) lines.push(`  pending sync: +${p.added} ~${p.modified} -${p.removed}`);\n\t\treturn lines.join(\"\\n\");\n\t}\n\n\treturn {\n\t\tname: \"codegraph\",\n\t\tlabel: \"CodeGraph\",\n\t\tdescription:\n\t\t\t\"Query the project's CodeGraph code knowledge graph (symbols, callers, callees, impact, and an 'explore' context query) via the local codegraph CLI. Read-only with respect to your source. Prefer over search/read for structural questions. Requires `codegraph init` to have been run in the project.\",\n\t\tparameters,\n\t\tstrict: true,\n\t\tasync execute(_id: string, params: Params, _onUpdate: unknown, _ctx: unknown, signal?: AbortSignal) {\n\t\t\tlet result: { stdout: string; stderr: string; code: number };\n\t\t\ttry {\n\t\t\t\tresult = await pi.exec(CODEGRAPH_CLI, buildArgs(params), { cwd: pi.cwd, signal, timeout: TIMEOUT_MS });\n\t\t\t} catch (e) {\n\t\t\t\tconst msg = e instanceof Error ? e.message : String(e);\n\t\t\t\tif (/not found|enoent/i.test(msg)) {\n\t\t\t\t\tthrow new Error(\"The `codegraph` CLI is not installed. Install it: npm i -g @colbymchenry/codegraph\");\n\t\t\t\t}\n\t\t\t\tthrow e;\n\t\t\t}\n\t\t\tif (result.code !== 0) {\n\t\t\t\tconst err = result.stderr.toLowerCase();\n\t\t\t\tif (err.includes(\"not initialized\") || err.includes(\".codegraph\") || err.includes(\"no index\")) {\n\t\t\t\t\tthrow new Error(\"CodeGraph is not initialized for this project. Run `codegraph init` in the project root.\");\n\t\t\t\t}\n\t\t\t\tthrow new Error(result.stderr.trim() || \"codegraph failed with no diagnostic output.\");\n\t\t\t}\n\t\t\treturn { content: [{ type: \"text\", text: render(params, result.stdout) }] };\n\t\t},\n\t};\n};\n\nexport default codegraph;\n```\n\nThe `import type` line is optional — it only provides editor types when GJC is\nresolvable from your tool file. It is erased at runtime, so the tool loads fine\nwithout it.\n\n## 3. Use it\n\nStart GJC in the project. The `codegraph` tool is now available to the model. Ask\na structural question and it will call the tool, for example:\n\n- `codegraph` with `{ \"op\": \"explore\", \"target\": \"how requests are routed\" }` can\n  return relevant source plus graph context in one call.\n- `{ \"op\": \"callers\", \"target\": \"MyClass.handle\" }` lists callers.\n- `{ \"op\": \"impact\", \"target\": \"parseConfig\" }` shows what a change would affect.\n- `{ \"op\": \"status\" }` reports index health.\n\n## Operations\n\n| `op` | `target` | Description |\n| --- | --- | --- |\n| `explore` | natural-language query | Context query: relevant symbols' source plus graph context (CodeGraph's `explore`). `maxFiles` caps included source. |\n| `search` | query | Full-text symbol search (`limit`, default 10). |\n| `callers` | symbol | Functions/methods that call the symbol, including dynamic dispatch. |\n| `callees` | symbol | Functions/methods the symbol calls. |\n| `impact` | symbol | Blast radius of changing the symbol. |\n| `status` | — | Index health: file/node/edge counts, languages, pending sync. |\n\n## Notes\n\n- **Read-only with respect to your code.** The tool only runs CodeGraph's\n  query-style subcommands; it never edits your files and does not run indexing or\n  sync commands. CodeGraph maintains its own local `.codegraph/` index via its CLI.\n  If results look stale or `status` reports pending changes, refresh the index with\n  CodeGraph's CLI (e.g. `codegraph sync`) outside GJC.\n- **Safe argument handling.** The example spawns CodeGraph with argv arrays via\n  `pi.exec` (no shell), `op` is constrained to a fixed enum, and numeric inputs are\n  capped — there is no shell interpolation of model-provided values.\n- **Scope.** Use a project-scoped file to limit the tool to one repo, or a\n  user-scoped file to make it available everywhere `codegraph init` has been run.\n- **Naming.** The tool registers as `codegraph`; rename it in the file if it\n  collides with another tool in your setup.\n- **Fallback.** If the graph reports a symbol is missing, a file is flagged as\n  pending sync, or you need a non-structural text search, refresh the CodeGraph\n  index outside GJC or fall back to `read`/`search`.\n- For background on how GJC treats external tools and MCP servers in standalone\n  sessions, see [`standalone-mcp.md`](standalone-mcp.md).\n",
@@ -48,7 +48,7 @@ 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` remains available as a compatibility alias routing to `o200k_base` in default builds.\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",
-	"notifications-sdk.md": "# Notifications SDK\n\n<p align=\"center\">\n  <img src=\"../assets/telegram-mobile-hero.png\" alt=\"Gajae Code 0.7.0 mobile answers for coding agents hero illustration\" width=\"100%\" />\n</p>\n\nA small, transport-agnostic way to get **action-needed** signals out of a GJC\nsession and deliver **replies** back — without scraping the terminal and without\nthe depth of the RPC / Coordinator / Bridge surfaces.\n\nThe stable contract is deliberately generic: every running session exposes one\nloopback WebSocket endpoint, and integrations are user-written clients that\nconnect to that endpoint. Telegram, Discord, Slack, mobile apps, and local tools\nall use the same JSON protocol. No upstream Rust, N-API, or wire-protocol change\nis required for a new integration.\n\n> Status: the Rust core (`crates/gjc-notifications`) provides the wire protocol,\n> action lifecycle, loopback WebSocket server, and endpoint discovery file. The\n> bundled Telegram daemon is a reference client layered on top of this SDK; it is\n> not the upstream topology.\n\n## Architecture\n\n```\nGJC session (upstream)                          your client (anywhere)\n┌───────────────────────────────┐               ┌──────────────────────────┐\n│ ask-tool fires / agent idle    │  action_needed │ Telegram / Discord / ... │\n│   → notifications core         │ ─────────────▶ │  render + collect reply  │\n│ ws://127.0.0.1:<port> (+token) │ ◀───────────── │                          │\n│   reply → resolve ask gate     │     reply       │                          │\n└───────────────────────────────┘               └──────────────────────────┘\n```\n\n- **One endpoint per session.** Each session runs its own loopback WebSocket\n  server. Upstream does not maintain a shared daemon, singleton, or\n  chat-to-session registry; multiplexing many sessions into one integration is a\n  client-side concern.\n- **Integrations are clients.** A client discovers endpoint files, connects to\n  one or more WebSockets, renders `action_needed`, and sends `reply` messages.\n- **Zero upstream change.** New transports do not require changes to\n  `crates/gjc-notifications` or the JSON protocol.\n- **Off unless configured.** No endpoint exists unless notifications are enabled\n  and a token is present.\n- **tmux-agnostic.** The endpoint behaves identically with or without tmux.\n\n## Endpoint discovery\n\nA running session writes a discovery file at:\n\n```\n<repo>/.gjc/state/notifications/<sessionId>.json\n```\n\n(`.gjc/state/` is git-ignored.) Shape:\n\n```json\n{\n  \"version\": 1,\n  \"sessionId\": \"019edd41-...\",\n  \"pid\": 12345,\n  \"host\": \"127.0.0.1\",\n  \"port\": 53124,\n  \"url\": \"ws://127.0.0.1:53124\",\n  \"token\": \"<per-session token>\",\n  \"startedAt\": 1718760000000,\n  \"updatedAt\": 1718760000000,\n  \"stale\": false\n}\n```\n\n- The file is created `0700`/`0600` (unix) and written atomically.\n- The **token is in the file** because clients need it; never log it raw.\n  Stale files (dead PID, past TTL, or explicitly marked) are cleaned up on the\n  next start.\n\nConnect with the token as a query parameter:\n\n```\nws://127.0.0.1:<port>/?token=<token>\n```\n\nA wrong/missing token is rejected at the handshake with HTTP `401`.\n\n## Protocol\n\nJSON text frames. Field names are `camelCase`; the `type` discriminator is\n`snake_case`.\n\n### Server → client\n\n`action_needed` — something needs attention:\n\n```json\n{ \"type\": \"action_needed\", \"id\": \"wg_run_stage_1\", \"kind\": \"ask\",\n  \"sessionId\": \"sess-1\", \"question\": \"Proceed?\", \"options\": [\"Yes\", \"No\"] }\n```\n\n```json\n{ \"type\": \"action_needed\", \"id\": \"idle-sess-1-7\", \"kind\": \"idle\",\n  \"sessionId\": \"sess-1\", \"summary\": \"finished refactor; awaiting next step\" }\n```\n\n- `kind: \"ask\"` is answerable in both interactive/TUI and unattended/RPC modes.\n  The `id` is the real workflow-gate id.\n- `kind: \"idle\"` is notify-only and ephemeral (not replayed to clients that\n  connect later).\n\n`action_resolved` — a pending action is now terminal and **non-repliable**:\n\n```json\n{ \"type\": \"action_resolved\", \"id\": \"wg_run_stage_1\", \"resolvedBy\": \"local\" }\n```\n\n`resolvedBy` is `local` (answered in the CLI/TUI), `client` (a remote reply won),\nor `timeout`.\n\n`reply_rejected` — sent only to the client whose reply failed:\n\n```json\n{ \"type\": \"reply_rejected\", \"id\": \"wg_run_stage_1\", \"reason\": \"already_answered\" }\n```\n\nReasons: `already_answered`, `unknown_action`, `invalid_answer`,\n`resolver_unavailable`, `idempotency_conflict`, `unauthorized`.\n\nThe frames above are the minimal contract every client implements. Threaded\nclients (like the managed Telegram daemon) may also receive optional\nserver → client frames they can render or ignore: `identity_header` (one-time\nper-session repo/branch/machine header), `context_update` (last message, task,\ngoal, token usage, model, diff), `turn_stream` (live/finalized turn output),\n`image_attachment` (agent-produced images), `activity` (busy/idle, drives the\ntyping indicator), `inbound_ack` (delivery state of an injected user message),\n`session_closed` (endpoint teardown; threaded clients may delete/archive the\nremote conversation), `config_update` (current verbosity/redact), `hello`\n(server capability/version), and `pong`. A minimal client only needs\n`action_needed`, `action_resolved`, and `reply_rejected`.\n\n### Client → server\n\n`reply` — answer a pending `ask`:\n\n```json\n{ \"type\": \"reply\", \"id\": \"wg_run_stage_1\", \"answer\": 0, \"token\": \"<token>\" }\n```\n\n`answer` accepts:\n\n- a number — zero-based option index (`0` = first option);\n- a string — an option label, or free text;\n- an object — `{ \"selected\": [0, \"Maybe\"], \"custom\": \"...\" }` for multi-select.\n\nOptional `idempotencyKey` makes retries safe: the same key + same body re-acks;\nthe same key + different body is rejected with `idempotency_conflict`.\n\nThreaded clients may also send optional client → server frames: `user_message`\n(inject/steer a turn with free text), `config_command` (toggle verbosity/redact\nin-thread), `hello` (capability/version), and `ping`. A minimal client only\nneeds `reply`.\n\n## Answer semantics\n\nA remote reply answers a pending ask in **both** modes — RPC is not required:\n\n- **Interactive / TUI mode:** the ask tool races the local selector against the\n  remote reply (first valid answer wins). If you tap a button in the client, the\n  ask resolves with that option; if you answer locally, the client receives\n  `action_resolved` (`resolvedBy: \"local\"`) and the action becomes non-repliable.\n- **Unattended / RPC mode:** the reply resolves the real workflow-gate, driving\n  the session the same way a local answer would.\n\nIn both modes the first valid reply wins; later replies get `already_answered`.\nIdle pings are notify-only.\n\n## Minimal client example\n\n```js\nimport { readFileSync } from \"node:fs\";\nimport WebSocket from \"ws\";\n\nconst { url, token } = JSON.parse(\n  readFileSync(`.gjc/state/notifications/${sessionId}.json`, \"utf8\"),\n);\n\nconst ws = new WebSocket(`${url}/?token=${encodeURIComponent(token)}`);\n\nws.on(\"message\", (data) => {\n  const msg = JSON.parse(data.toString());\n  if (msg.type === \"action_needed\" && msg.kind === \"ask\") {\n    // present msg.question / msg.options to the human, then:\n    ws.send(JSON.stringify({ type: \"reply\", id: msg.id, answer: 0, token }));\n  } else if (msg.type === \"action_resolved\") {\n    // mark this action as no longer answerable in your UI\n  } else if (msg.type === \"reply_rejected\") {\n    // e.g. reason === \"already_answered\" → the ask was answered elsewhere\n  }\n});\n```\n\nSwap `ws` for a Telegram bot's long-poll loop, a Discord gateway client, or a\nSlack socket-mode app — the contract above is all you implement.\n\n## Managed notification adapters\n\nFor the exact user setup flow (`gjc notify setup`, BotFather token, private-chat pairing, status, and troubleshooting), see [Telegram notification onboarding](./telegram-onboarding.md).\n\n## Managed Telegram daemon (bundled reference client)\n\nGJC also ships a managed Telegram reference client for the common phone-notify\nworkflow. It remains a client of the generic SDK: it scans session discovery\nfiles, opens each session WebSocket, and routes Telegram replies back to the\nmatching endpoint.\n\nThe daemon/session engine is shared. Session discovery, WebSocket protocol,\nredaction decisions, rate-limit pooling, reply routing, singleton ownership, and\nlifecycle control are not reimplemented by each chat surface. Telegram, Discord,\nand Slack adapters are thin presentation layers: they render internal notification\nevents into transport payloads and map transport interactions back to `{sessionId,\nactionId,answer}` replies.\n\n### Setup and auto-connect\n\nRun the setup command once:\n\n```sh\ngjc notify setup\n```\n\nThe wizard validates the bot token with Telegram, verifies private-chat Threaded\nMode capability via `getMe.has_topics_enabled`, waits for a private DM to the bot,\nand writes canonical global Settings under `config.yml` in the GJC agent\ndirectory. It enables:\n\n- `notifications.enabled`\n- `notifications.telegram.botToken`\n- `notifications.telegram.chatId`\n- `notifications.redact` (optional; default false)\n- `notifications.discord.botToken` / `notifications.discord.channelId` (optional Discord adapter)\n- `notifications.slack.botToken` / `notifications.slack.channelId` (optional Slack adapter)\n\nAfter setup, sessions auto-connect when notifications are enabled. Each session\nstill publishes its own loopback endpoint; the daemon is only the Telegram-side\nmultiplexer.\n\nFor Telegram forum topics, the daemon deletes the per-session topic when the local\nnotification endpoint shuts down, so it disappears from the topic list. A resumed\nsession creates a fresh topic before sending again. The bot must be allowed to\ndelete messages in that chat; without that permission, deletion is best-effort and\ndelivery continues.\n\n### Singleton poller and trust model\n\nTelegram `getUpdates` allows only one active long-poll owner per bot token. The\nmanaged daemon enforces **one bot token = one getUpdates poller** with a local\nlock/state file under the agent directory. New sessions attach to the existing\nfresh daemon owner instead of starting another poller, preventing Telegram 409\nconflicts.\n\nThe trust model is intentionally strict:\n\n- setup pairs exactly one private Telegram chat;\n- runtime accepts updates only from that paired chat id;\n- groups, supergroups, channels, and unpaired users never receive session names,\n  action ids, pending status, or configuration hints;\n- daemon state stores a token fingerprint, not the raw bot token.\n\n### Routing in private-chat topics\n\nThe paired private chat prefers per-session Telegram topics (Threaded Mode). The\ndaemon tags messages by session, stores compact callback aliases for inline\nbuttons, and routes replies back to the exact session/action. A forum-enabled\nsupergroup is no longer required: when the bot owner enables Threaded Mode in\n@BotFather, the daemon creates one topic per session in the paired private chat.\nGJC cannot enable Threaded Mode through the Bot API; setup only verifies the\ncapability and guides the manual BotFather toggle.\n\nIf BotFather's per-bot **Bot Settings** menu does not show **Threads Settings**\nor **Threaded Mode**, the supported fallback is the normal private-chat pairing.\nSetup can be saved as `threaded=unverified`/`threaded=unknown`, and the daemon\nstill tries topics when Telegram allows them. When `createForumTopic` is refused,\nthe daemon does not drop the send: it routes the notification to the normal\n(flat) paired private chat and posts a one-time `turn on threaded mode from\nbotfather miniapp to receive gjc notification!` nudge. Pairing is private-only,\nso flat delivery stays within the user's own private DM.\n\nSupported reply paths:\n\n- tap an inline button on an ask notification;\n- reply inside the session's thread/topic (replies are thread-native; the\n  topic identifies the session, so no session tag is needed).\n\nIn threaded mode the user can also adjust per-session behaviour with in-thread\nconfig commands: `/verbose`, `/lean`, `/verbosity <lean|verbose>`, and\n`/redact <on|off>`. The legacy `/answer <session-tag> <answer>` command is\nremoved — replies are routed by the topic they arrive in.\n\nFlat fallback keeps outbound notifications and inline-button answers working,\nbut free-text replies and `/verbose`/`/lean`/`/verbosity`/`/redact` commands are\nthread-native and require topic routing. Do not pair a group, supergroup, or\nchannel to work around a missing BotFather menu; the bundled setup flow is\nprivate-chat only, and non-private chat ids remain fail-closed to avoid session\ndata leaks.\n\nUnknown, expired, or restart-unvalidated callback aliases fail closed: the daemon\nsends guidance and does not guess a target session or action.\n\n### Discord and Slack setup\n\nDiscord and Slack use the same internal notification events and reply protocol as\nTelegram. Store only runtime credentials in local GJC settings or environment;\nnever paste bot tokens, webhook URLs, transcripts, prompts, host paths, or raw logs\ninto docs, tests, issues, or PR comments.\n\nConfiguration keys:\n\n```yaml\nnotifications:\n  enabled: true\n  discord:\n    botToken: \"<local Discord bot token>\"\n    channelId: \"<Discord channel id>\"\n  slack:\n    botToken: \"<local Slack bot token>\"\n    channelId: \"<Slack channel id>\"\n  redact: true\n```\n\nThe bundled adapters intentionally render public-safe message bodies and return\nroute metadata only for pending internal actions. They do not own polling,\nsession scans, daemon locks, rate limits, or SDK lifecycle. Production transport\nsenders should consume the adapter payloads and keep all credential-bearing HTTP\nor gateway details outside logged payloads.\n### Redaction\n\n`notifications.redact` strips sensitive content before remote delivery, but\n**asks are exempt**: an ask is an interactive prompt the human must read and\nanswer remotely, so its `question` and `options` are always sent unredacted\n(otherwise it would be unanswerable). When redaction is enabled, `idle`\nsummaries are removed and streamed content frames (`turn_stream`,\n`context_update`, `image_attachment`) are suppressed at their emit sites. When\nredaction is disabled, all content is delivered unchanged.\n\n### Local `/notify`\n\nInside a GJC session, `/notify` controls the current session only:\n\n- `/notify status` reports enabled/disabled state, daemon observation when known,\n  and redaction state without printing secrets;\n- `/notify off` disables the current session's notification endpoint and removes\n  its discovery record without mutating global Settings;\n- `/notify on` re-enables the current session when global setup is complete and\n  `GJC_NOTIFICATIONS=0` is not forcing opt-out.\n\n### Manual Telegram CLI is for debugging\n\n`packages/coding-agent/src/notifications/telegram-cli.ts` remains as a manual\nreference/debug client and template for other integrations. It is not the primary\nTelegram UX.\n\n```sh\nbun run packages/coding-agent/src/notifications/telegram-cli.ts --bot-token \"$BOT_TOKEN\"\n```\n\nBy default it refuses to start when a fresh managed daemon already owns the same\nbot token for the same paired chat, because a second poller will cause Telegram\n409 conflicts. Use `--force` only for deliberate debugging when you have stopped\nor intentionally want to override the daemon guard.\n## Two client surfaces: per-session vs daemon-owned lifecycle control\n\nThe SDK now exposes **two distinct surfaces**. Do not confuse them:\n\n1. **Per-session notification clients (the normal, documented contract above).**\n   A client discovers `<repo>/.gjc/state/notifications/<sessionId>.json`, connects\n   to that session's loopback WebSocket, and handles `action_needed`,\n   `action_resolved`, `reply_rejected`, and the optional threaded frames. This is\n   all an ordinary integration (Telegram, Discord, Slack, mobile, local tools)\n   needs. It requires **zero** upstream changes.\n\n2. **The daemon-owned session *lifecycle* control endpoint (privileged).**\n   A separate, **session-independent**, loopback-only, authenticated control\n   endpoint that accepts `session_create` / `session_close` / `session_resume`\n   frames. It exists because creating a session cannot use a per-session socket\n   (none exists before the session does). It is **not** part of the normal\n   integration contract: ordinary clients never implement it. Only the bundled,\n   trusted daemon (e.g. the managed Telegram daemon) speaks it.\n\n### Lifecycle control endpoint\n\n- **Discovery:** `<agentDir>/notifications/control.json` (daemon-owned, mode\n  `0600`), distinct from per-session endpoint files. It carries only non-secret\n  endpoint metadata (url/host/port/pid/owner). The control token is held **in\n  memory** by the daemon (the sole client) and is **never** written to disk.\n- **Auth:** loopback-only bind (a non-loopback bind is refused). The WebSocket\n  upgrade requires `?token=<control-token>` (HTTP `401` otherwise), and every\n  lifecycle frame's `token` is re-checked (`unauthorized` on mismatch). The Rust\n  ingress authenticates and forwards; it never spawns or applies policy.\n- **Frames:** `session_create` (target `existing_path` | `worktree` |\n  `plain_dir`), `session_close` (hard-kill, history preserved, recoverable),\n  `session_resume` (reattach if alive, else cold-restart from history); responses\n  `session_create_response` / `session_close_response` / `session_resume_response`\n  / `session_lifecycle_error`. The protocol also defines a replayable\n  `session_ready` per-session frame for readiness-gated creates; the current MVP\n  daemon replies once the tmux launch is requested (see the phone guide) rather\n  than waiting on it. Inline prompt text (`-- <prompt>`) is rejected in the MVP.\n\n### Trust model and hardening (daemon side)\n\nThe control endpoint trusts the configured paired chat for any path (an accepted\nrisk). It is hardened around that boundary:\n\n- **Strict paired-chat gating** — non-paired chats are rejected *before* any path\n  parsing, filesystem, or process action.\n- **Durable idempotency** — a locked, atomic, fsynced ledger keyed by\n  `chatId:updateId` + request hash (`telegram-lifecycle-idempotency.json`).\n  Duplicate updates never repeat side effects, including across daemon restart; a\n  duplicate while in-progress reports pending (never a second spawn); a same id\n  with a different body is `duplicate_conflict`; an effect failure is recorded\n  `terminal_uncertain` (never auto-respawned).\n- **Per-chat create rate limit.**\n- **Audit log** — append-only `telegram-lifecycle-audit.jsonl` (`0600`) recording\n  every accept/reject/duplicate/rate-limit/spawn/success/failure. Raw control\n  tokens and raw prompts are never logged (prompt hash + byte length only).\n- **Inline prompts rejected (MVP)** — `session_create` with `-- <prompt>` text is\n  rejected with usage; no prompt is ever placed in argv, audit, or responses. (A\n  redacted prompt-ref flow is reserved for a future revision.)\n- **GJC-managed-only close** — force-close re-reads the exact `@gjc-profile`\n  immediately before kill and requires the `@gjc-session-id` (and optional\n  `@gjc-session-state-file`) tag to match; it never touches non-GJC tmux.\n- **Recent-activity picker** — sessions are ranked by history-file mtime and\n  enriched with terminal breadcrumbs so the operator picks a recent repo/session\n  instead of typing raw paths. Ambiguous resumes fail closed with candidates.\n### Phone test guide (create / close / resume from Telegram)\n\nEnd-to-end manual check once `gjc notify setup` has paired your private chat:\n\n1. **Pair + start.** Run `gjc notify setup` (BotFather token, DM the bot to pair).\n   Start any GJC session with notifications enabled so the daemon owner is\n   running (`gjc launch` in a repo, or `GJC_NOTIFICATIONS=1`). The owner starts\n   the loopback control endpoint and accepts `/session_*` while running; with zero\n   active sessions it still idle-exits after the inactivity timeout.\n2. **Create.** From your paired chat, pick `/session_create` from the Telegram\n   command menu or send `/session_create path <repo-dir>` (or\n   `/session_create worktree <repo> <branch>`, or `/session_create dir <newdir>`).\n   `<repo-dir>`, `<repo>`, and `<newdir>` may use `~`/`~/...` for your own home\n   directory; named-user forms such as `~alice/repo` are rejected. The bot replies\n   once the tmux launch is requested; the session shows up in `/session_recent`\n   once it is ready. (Inline prompts via `-- <text>` are rejected for now with\n   usage text.)\n3. **List.** `/session_recent` shows recent sessions (most-recent first) to copy\n   an id from.\n4. **Close.** `/session_close <sessionId>` hard-kills the GJC-managed session\n   (history is preserved); the bot confirms.\n5. **Resume.** `/session_resume <sessionId|prefix>` reattaches if it is still\n   alive, otherwise cold-restarts it from saved history. An ambiguous prefix\n   replies with the matching candidates instead of guessing.\n\nCommands are accepted **only** from the paired chat; **create** is rate-limited,\nand all lifecycle commands are idempotent per Telegram update id and audited (no\ntokens or prompts are logged).\nFor an automated proof of the wire path without a real bot, see\n`packages/coding-agent/scripts/g011-daemon-path-smoke.ts` (real native control\nendpoint + loopback WebSocket).\n",
+	"notifications-sdk.md": "# Notifications SDK\n\n<p align=\"center\">\n  <img src=\"../assets/telegram-mobile-hero.png\" alt=\"Gajae Code mobile answers for coding agents hero illustration\" width=\"100%\" />\n</p>\n\nA small, transport-agnostic way to get **action-needed** signals out of a GJC\nsession and deliver **replies** back — without scraping the terminal and without\nthe depth of the RPC / Coordinator / Bridge surfaces.\n\nThe stable contract is deliberately generic: every running session exposes one\nloopback WebSocket endpoint, and integrations are user-written clients that\nconnect to that endpoint. Telegram, Discord, Slack, mobile apps, and local tools\nall use the same JSON protocol. No upstream Rust, N-API, or wire-protocol change\nis required for a new integration.\n\n> Status: the Rust core (`crates/gjc-notifications`) provides the wire protocol,\n> action lifecycle, loopback WebSocket server, and endpoint discovery file. The\n> bundled Telegram daemon is a reference client layered on top of this SDK; it is\n> not the upstream topology.\n\n## Architecture\n\n```\nGJC session (upstream)                          your client (anywhere)\n┌───────────────────────────────┐               ┌──────────────────────────┐\n│ ask-tool fires / agent idle    │  action_needed │ Telegram / Discord / ... │\n│   → notifications core         │ ─────────────▶ │  render + collect reply  │\n│ ws://127.0.0.1:<port> (+token) │ ◀───────────── │                          │\n│   reply → resolve ask gate     │     reply       │                          │\n└───────────────────────────────┘               └──────────────────────────┘\n```\n\n- **One endpoint per session.** Each session runs its own loopback WebSocket\n  server. Upstream does not maintain a shared daemon, singleton, or\n  chat-to-session registry; multiplexing many sessions into one integration is a\n  client-side concern.\n- **Integrations are clients.** A client discovers endpoint files, connects to\n  one or more WebSockets, renders `action_needed`, and sends `reply` messages.\n- **Zero upstream change.** New transports do not require changes to\n  `crates/gjc-notifications` or the JSON protocol.\n- **Off unless configured.** No endpoint exists unless notifications are enabled\n  and a token is present.\n- **tmux-agnostic.** The endpoint behaves identically with or without tmux.\n\n## Endpoint discovery\n\nA running session writes a discovery file at:\n\n```\n<repo>/.gjc/state/notifications/<sessionId>.json\n```\n\n(`.gjc/state/` is git-ignored.) Shape:\n\n```json\n{\n  \"version\": 1,\n  \"sessionId\": \"019edd41-...\",\n  \"pid\": 12345,\n  \"host\": \"127.0.0.1\",\n  \"port\": 53124,\n  \"url\": \"ws://127.0.0.1:53124\",\n  \"token\": \"<per-session token>\",\n  \"startedAt\": 1718760000000,\n  \"updatedAt\": 1718760000000,\n  \"stale\": false\n}\n```\n\n- The file is created `0700`/`0600` (unix) and written atomically.\n- The **token is in the file** because clients need it; never log it raw.\n  Stale files (dead PID, past TTL, or explicitly marked) are cleaned up on the\n  next start.\n\nConnect with the token as a query parameter:\n\n```\nws://127.0.0.1:<port>/?token=<token>\n```\n\nA wrong/missing token is rejected at the handshake with HTTP `401`.\n\n## Protocol\n\nJSON text frames. Field names are `camelCase`; the `type` discriminator is\n`snake_case`.\n\n### Server → client\n\n`action_needed` — something needs attention:\n\n```json\n{ \"type\": \"action_needed\", \"id\": \"wg_run_stage_1\", \"kind\": \"ask\",\n  \"sessionId\": \"sess-1\", \"question\": \"Proceed?\", \"options\": [\"Yes\", \"No\"] }\n```\n\n```json\n{ \"type\": \"action_needed\", \"id\": \"idle-sess-1-7\", \"kind\": \"idle\",\n  \"sessionId\": \"sess-1\", \"summary\": \"finished refactor; awaiting next step\" }\n```\n\n- `kind: \"ask\"` is answerable in both interactive/TUI and unattended/RPC modes.\n  The `id` is the real workflow-gate id.\n- `kind: \"idle\"` is notify-only and ephemeral (not replayed to clients that\n  connect later).\n\n`action_resolved` — a pending action is now terminal and **non-repliable**:\n\n```json\n{ \"type\": \"action_resolved\", \"id\": \"wg_run_stage_1\", \"resolvedBy\": \"local\" }\n```\n\n`resolvedBy` is `local` (answered in the CLI/TUI), `client` (a remote reply won),\nor `timeout`.\n\n`reply_rejected` — sent only to the client whose reply failed:\n\n```json\n{ \"type\": \"reply_rejected\", \"id\": \"wg_run_stage_1\", \"reason\": \"already_answered\" }\n```\n\nReasons: `already_answered`, `unknown_action`, `invalid_answer`,\n`resolver_unavailable`, `idempotency_conflict`, `unauthorized`.\n\nThe frames above are the minimal contract every client implements. Threaded\nclients (like the managed Telegram daemon) may also receive optional\nserver → client frames they can render or ignore: `identity_header` (one-time\nper-session repo/branch/machine header), `context_update` (last message, task,\ngoal, token usage, model, diff), `turn_stream` (live/finalized turn output),\n`image_attachment` (agent-produced images), `activity` (busy/idle, drives the\ntyping indicator), `inbound_ack` (delivery state of an injected user message),\n`session_closed` (endpoint teardown; threaded clients may delete/archive the\nremote conversation), `config_update` (current verbosity/redact), `hello`\n(server capability/version), and `pong`. A minimal client only needs\n`action_needed`, `action_resolved`, and `reply_rejected`.\n\n### Client → server\n\n`reply` — answer a pending `ask`:\n\n```json\n{ \"type\": \"reply\", \"id\": \"wg_run_stage_1\", \"answer\": 0, \"token\": \"<token>\" }\n```\n\n`answer` accepts:\n\n- a number — zero-based option index (`0` = first option);\n- a string — an option label, or free text;\n- an object — `{ \"selected\": [0, \"Maybe\"], \"custom\": \"...\" }` for multi-select.\n\nOptional `idempotencyKey` makes retries safe: the same key + same body re-acks;\nthe same key + different body is rejected with `idempotency_conflict`.\n\nThreaded clients may also send optional client → server frames: `user_message`\n(inject/steer a turn with free text), `config_command` (toggle verbosity/redact\nin-thread), `hello` (capability/version), and `ping`. A minimal client only\nneeds `reply`.\n\n## Answer semantics\n\nA remote reply answers a pending ask in **both** modes — RPC is not required:\n\n- **Interactive / TUI mode:** the ask tool races the local selector against the\n  remote reply (first valid answer wins). If you tap a button in the client, the\n  ask resolves with that option; if you answer locally, the client receives\n  `action_resolved` (`resolvedBy: \"local\"`) and the action becomes non-repliable.\n- **Unattended / RPC mode:** the reply resolves the real workflow-gate, driving\n  the session the same way a local answer would.\n\nIn both modes the first valid reply wins; later replies get `already_answered`.\nIdle pings are notify-only.\n\n## Minimal client example\n\n```js\nimport { readFileSync } from \"node:fs\";\nimport WebSocket from \"ws\";\n\nconst { url, token } = JSON.parse(\n  readFileSync(`.gjc/state/notifications/${sessionId}.json`, \"utf8\"),\n);\n\nconst ws = new WebSocket(`${url}/?token=${encodeURIComponent(token)}`);\n\nws.on(\"message\", (data) => {\n  const msg = JSON.parse(data.toString());\n  if (msg.type === \"action_needed\" && msg.kind === \"ask\") {\n    // present msg.question / msg.options to the human, then:\n    ws.send(JSON.stringify({ type: \"reply\", id: msg.id, answer: 0, token }));\n  } else if (msg.type === \"action_resolved\") {\n    // mark this action as no longer answerable in your UI\n  } else if (msg.type === \"reply_rejected\") {\n    // e.g. reason === \"already_answered\" → the ask was answered elsewhere\n  }\n});\n```\n\nSwap `ws` for a Telegram bot's long-poll loop, a Discord gateway client, or a\nSlack socket-mode app — the contract above is all you implement.\n\n## Managed notification adapters\n\nFor the exact user setup flow (`gjc notify setup`, BotFather token, private-chat pairing, status, and troubleshooting), see [Telegram notification onboarding](./telegram-onboarding.md).\n\n## Managed Telegram daemon (bundled reference client)\n\nGJC also ships a managed Telegram reference client for the common phone-notify\nworkflow. It remains a client of the generic SDK: it scans session discovery\nfiles, opens each session WebSocket, and routes Telegram replies back to the\nmatching endpoint.\n\nThe daemon/session engine is shared. Session discovery, WebSocket protocol,\nredaction decisions, rate-limit pooling, reply routing, singleton ownership, and\nlifecycle control are not reimplemented by each chat surface. Telegram, Discord,\nand Slack adapters are thin presentation layers: they render internal notification\nevents into transport payloads and map transport interactions back to `{sessionId,\nactionId,answer}` replies.\n\n### Setup and auto-connect\n\nRun the setup command once:\n\n```sh\ngjc notify setup\n```\n\nThe wizard validates the bot token with Telegram, verifies private-chat Threaded\nMode capability via `getMe.has_topics_enabled`, waits for a private DM to the bot,\nand writes canonical global Settings under `config.yml` in the GJC agent\ndirectory. It enables:\n\n- `notifications.enabled`\n- `notifications.telegram.botToken`\n- `notifications.telegram.chatId`\n- `notifications.redact` (optional; default false)\n- `notifications.discord.botToken` / `notifications.discord.channelId` (optional Discord adapter)\n- `notifications.slack.botToken` / `notifications.slack.channelId` (optional Slack adapter)\n\nAfter setup, sessions auto-connect when notifications are enabled. Each session\nstill publishes its own loopback endpoint; the daemon is only the Telegram-side\nmultiplexer.\n\nFor Telegram forum topics, the daemon deletes the per-session topic when the local\nnotification endpoint shuts down, so it disappears from the topic list. A resumed\nsession creates a fresh topic before sending again. The bot must be allowed to\ndelete messages in that chat; without that permission, deletion is best-effort and\ndelivery continues.\n\n### Singleton poller and trust model\n\nTelegram `getUpdates` allows only one active long-poll owner per bot token. The\nmanaged daemon enforces **one bot token = one getUpdates poller** with a local\nlock/state file under the agent directory. New sessions attach to the existing\nfresh daemon owner instead of starting another poller, preventing Telegram 409\nconflicts.\n\nThe trust model is intentionally strict:\n\n- setup pairs exactly one private Telegram chat;\n- runtime accepts updates only from that paired chat id;\n- groups, supergroups, channels, and unpaired users never receive session names,\n  action ids, pending status, or configuration hints;\n- daemon state stores a token fingerprint, not the raw bot token.\n\n### Routing in private-chat topics\n\nThe paired private chat prefers per-session Telegram topics (Threaded Mode). The\ndaemon tags messages by session, stores compact callback aliases for inline\nbuttons, and routes replies back to the exact session/action. A forum-enabled\nsupergroup is no longer required: when the bot owner enables Threaded Mode in\n@BotFather, the daemon creates one topic per session in the paired private chat.\nGJC cannot enable Threaded Mode through the Bot API; setup only verifies the\ncapability and guides the manual BotFather toggle.\n\nIf BotFather's per-bot **Bot Settings** menu does not show **Threads Settings**\nor **Threaded Mode**, the supported fallback is the normal private-chat pairing.\nSetup can be saved as `threaded=unverified`/`threaded=unknown`, and the daemon\nstill tries topics when Telegram allows them. When `createForumTopic` is refused,\nthe daemon does not drop the send: it routes the notification to the normal\n(flat) paired private chat and posts a one-time `turn on threaded mode from\nbotfather miniapp to receive gjc notification!` nudge. Pairing is private-only,\nso flat delivery stays within the user's own private DM.\n\nSupported reply paths:\n\n- tap an inline button on an ask notification;\n- reply inside the session's thread/topic (replies are thread-native; the\n  topic identifies the session, so no session tag is needed).\n\nIn threaded mode the user can also adjust per-session behaviour with in-thread\nconfig commands: `/verbose`, `/lean`, `/verbosity <lean|verbose>`, and\n`/redact <on|off>`. The legacy `/answer <session-tag> <answer>` command is\nremoved — replies are routed by the topic they arrive in.\n\nFlat fallback keeps outbound notifications and inline-button answers working,\nbut plain free-text never guesses from the global pending-ask set. Free-text\nreplies and `/verbose`/`/lean`/`/verbosity`/`/redact` commands are\nthread-native and require topic routing. Do not pair a group, supergroup, or\nchannel to work around a missing BotFather menu; the bundled setup flow is\nprivate-chat only, and non-private chat ids remain fail-closed to avoid session\ndata leaks.\n\nUnknown, expired, or restart-unvalidated callback aliases fail closed: the daemon\nsends guidance and does not guess a target session or action.\n\n### Discord and Slack setup\n\nDiscord and Slack use the same internal notification events and reply protocol as\nTelegram. Store only runtime credentials in local GJC settings or environment;\nnever paste bot tokens, webhook URLs, transcripts, prompts, host paths, or raw logs\ninto docs, tests, issues, or PR comments.\n\nConfiguration keys:\n\n```yaml\nnotifications:\n  enabled: true\n  discord:\n    botToken: \"<local Discord bot token>\"\n    channelId: \"<Discord channel id>\"\n  slack:\n    botToken: \"<local Slack bot token>\"\n    channelId: \"<Slack channel id>\"\n  redact: true\n```\n\nThe bundled adapters intentionally render public-safe message bodies and return\nroute metadata only for pending internal actions. They do not own polling,\nsession scans, daemon locks, rate limits, or SDK lifecycle. Production transport\nsenders should consume the adapter payloads and keep all credential-bearing HTTP\nor gateway details outside logged payloads.\n### Redaction\n\n`notifications.redact` strips sensitive content before remote delivery, but\n**asks are exempt**: an ask is an interactive prompt the human must read and\nanswer remotely, so its `question` and `options` are always sent unredacted\n(otherwise it would be unanswerable). When redaction is enabled, `idle`\nsummaries are removed and streamed content frames (`turn_stream`,\n`context_update`, `image_attachment`) are suppressed at their emit sites. When\nredaction is disabled, all content is delivered unchanged.\n\n### Local `/notify`\n\nInside a GJC session, `/notify` controls the current session only:\n\n- `/notify status` reports enabled/disabled state, daemon observation when known,\n  and redaction state without printing secrets;\n- `/notify off` disables the current session's notification endpoint and removes\n  its discovery record without mutating global Settings;\n- `/notify on` re-enables the current session when global setup is complete and\n  `GJC_NOTIFICATIONS=0` is not forcing opt-out.\n\n### Manual Telegram CLI is for debugging\n\n`packages/coding-agent/src/notifications/telegram-cli.ts` remains as a manual\nreference/debug client and template for other integrations. It is not the primary\nTelegram UX.\n\n```sh\nbun run packages/coding-agent/src/notifications/telegram-cli.ts --bot-token \"$BOT_TOKEN\"\n```\n\nBy default it refuses to start when a fresh managed daemon already owns the same\nbot token for the same paired chat, because a second poller will cause Telegram\n409 conflicts. Use `--force` only for deliberate debugging when you have stopped\nor intentionally want to override the daemon guard.\n## Two client surfaces: per-session vs daemon-owned lifecycle control\n\nThe SDK now exposes **two distinct surfaces**. Do not confuse them:\n\n1. **Per-session notification clients (the normal, documented contract above).**\n   A client discovers `<repo>/.gjc/state/notifications/<sessionId>.json`, connects\n   to that session's loopback WebSocket, and handles `action_needed`,\n   `action_resolved`, `reply_rejected`, and the optional threaded frames. This is\n   all an ordinary integration (Telegram, Discord, Slack, mobile, local tools)\n   needs. It requires **zero** upstream changes.\n\n2. **The daemon-owned session *lifecycle* control endpoint (privileged).**\n   A separate, **session-independent**, loopback-only, authenticated control\n   endpoint that accepts `session_create` / `session_close` / `session_resume`\n   frames. It exists because creating a session cannot use a per-session socket\n   (none exists before the session does). It is **not** part of the normal\n   integration contract: ordinary clients never implement it. Only the bundled,\n   trusted daemon (e.g. the managed Telegram daemon) speaks it.\n\n### Lifecycle control endpoint\n\n- **Discovery:** `<agentDir>/notifications/control.json` (daemon-owned, mode\n  `0600`), distinct from per-session endpoint files. It carries only non-secret\n  endpoint metadata (url/host/port/pid/owner). The control token is held **in\n  memory** by the daemon (the sole client) and is **never** written to disk.\n- **Auth:** loopback-only bind (a non-loopback bind is refused). The WebSocket\n  upgrade requires `?token=<control-token>` (HTTP `401` otherwise), and every\n  lifecycle frame's `token` is re-checked (`unauthorized` on mismatch). The Rust\n  ingress authenticates and forwards; it never spawns or applies policy.\n- **Frames:** `session_create` (target `existing_path` | `worktree` |\n  `plain_dir`), `session_close` (hard-kill, history preserved, recoverable),\n  `session_resume` (reattach if alive, else cold-restart from history); responses\n  `session_create_response` / `session_close_response` / `session_resume_response`\n  / `session_lifecycle_error`. The protocol also defines a replayable\n  `session_ready` per-session frame for readiness-gated creates; the current MVP\n  daemon replies once the tmux launch is requested (see the phone guide) rather\n  than waiting on it. Inline prompt text (`-- <prompt>`) is rejected in the MVP.\n\n### Trust model and hardening (daemon side)\n\nThe control endpoint trusts the configured paired chat for any path (an accepted\nrisk). It is hardened around that boundary:\n\n- **Strict paired-chat gating** — non-paired chats are rejected *before* any path\n  parsing, filesystem, or process action.\n- **Durable idempotency** — a locked, atomic, fsynced ledger keyed by\n  `chatId:updateId` + request hash (`telegram-lifecycle-idempotency.json`).\n  Duplicate updates never repeat side effects, including across daemon restart; a\n  duplicate while in-progress reports pending (never a second spawn); a same id\n  with a different body is `duplicate_conflict`; an effect failure is recorded\n  `terminal_uncertain` (never auto-respawned).\n- **Per-chat create rate limit.**\n- **Audit log** — append-only `telegram-lifecycle-audit.jsonl` (`0600`) recording\n  every accept/reject/duplicate/rate-limit/spawn/success/failure. Raw control\n  tokens and raw prompts are never logged (prompt hash + byte length only).\n- **Inline prompts rejected (MVP)** — `session_create` with `-- <prompt>` text is\n  rejected with usage; no prompt is ever placed in argv, audit, or responses. (A\n  redacted prompt-ref flow is reserved for a future revision.)\n- **GJC-managed-only close** — force-close re-reads the exact `@gjc-profile`\n  immediately before kill and requires the `@gjc-session-id` (and optional\n  `@gjc-session-state-file`) tag to match; it never touches non-GJC tmux.\n- **Recent-activity picker** — sessions are ranked by history-file mtime and\n  enriched with terminal breadcrumbs so the operator picks a recent repo/session\n  instead of typing raw paths. Ambiguous resumes fail closed with candidates.\n### Phone test guide (create / close / resume from Telegram)\n\nEnd-to-end manual check once `gjc notify setup` has paired your private chat:\n\n1. **Pair + start.** Run `gjc notify setup` (BotFather token, DM the bot to pair).\n   Start any GJC session with notifications enabled so the daemon owner is\n   running (`gjc launch` in a repo, or `GJC_NOTIFICATIONS=1`). The owner starts\n   the loopback control endpoint and accepts `/session_*` while running; with zero\n   active sessions it still idle-exits after the inactivity timeout.\n2. **Create.** From your paired chat, pick `/session_create` from the Telegram\n   command menu or send `/session_create path <repo-dir>` (or\n   `/session_create worktree <repo> <branch>`, or `/session_create dir <newdir>`).\n   `<repo-dir>`, `<repo>`, and `<newdir>` may use `~`/`~/...` for your own home\n   directory; named-user forms such as `~alice/repo` are rejected. The bot replies\n   once the tmux launch is requested; the session shows up in `/session_recent`\n   once it is ready. (Inline prompts via `-- <text>` are rejected for now with\n   usage text.)\n3. **List.** `/session_recent` shows recent sessions (most-recent first) to copy\n   an id from.\n4. **Close.** `/session_close <sessionId>` hard-kills the GJC-managed session\n   (history is preserved); the bot confirms.\n5. **Resume.** `/session_resume <sessionId|prefix>` reattaches if it is still\n   alive, otherwise cold-restarts it from saved history. An ambiguous prefix\n   replies with the matching candidates instead of guessing.\n\nCommands are accepted **only** from the paired chat; **create** is rate-limited,\nand all lifecycle commands are idempotent per Telegram update id and audited (no\ntokens or prompts are logged).\nFor an automated proof of the wire path without a real bot, see\n`packages/coding-agent/scripts/g011-daemon-path-smoke.ts` (real native control\nendpoint + loopback WebSocket).\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/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",
 	"ooo-bridge-extension-contract.md": "# Ouroboros `ooo` bridge extension contract\n\nGJC exposes the `ooo` bridge through the existing extension input-event surface. It is not a default workflow skill, hook, slash command, or built-in agent.\n\n## Interception surface\n\nExtensions register an `input` handler:\n\n```ts\nimport { createOuroborosOooBridge } from \"@gajae-code/coding-agent/extensibility/extensions\";\n\nexport default function activate(gjc) {\n  gjc.on(\"input\", createOuroborosOooBridge());\n}\n```\n\nThe handler matches only the bare exact prefix:\n\n- `ooo`\n- `ooo ...`\n\nIt does not match embedded or longer-token text such as `please ooo status`, `oooo`, or `/ooo`.\n\nThe extension runner already treats `InputEventResult.handled === true` as terminal: the input is not sent through normal model flow. An empty result (`{}`) means continue/pass-through, preserving existing chained input handlers and normal prompt handling.\n\n## Dispatch and result semantics\n\n`createOuroborosOooBridge()` is a small specialization of `createExactPrefixCommandBridge()`:\n\n- command: `ouroboros`\n- arguments: `dispatch`, then the full submitted input text\n- recursion guard variable: `_OUROBOROS_GJC_BRIDGE_DEPTH`\n- continue/pass-through exit code: `78`\n\nExit-code mapping:\n\n| Dispatch result | GJC input result |\n| --- | --- |\n| `0` | `{ handled: true }`; do not send input to the model. |\n| `78` | `{}`; continue/pass-through so GJC processes the input normally. |\n| any other non-zero | Surface an extension error notification using stderr, then stdout, then a generic exit-code message, and return `{ handled: true }`; the failed `ooo` command is terminal and is not sent to the model. |\n\n## Recursion guard\n\nBefore dispatch, the helper sets `_OUROBOROS_GJC_BRIDGE_DEPTH` to the next numeric depth and restores the previous value after dispatch finishes. A current numeric depth of `0` or `1` is dispatchable, which preserves concurrent independent interactive inputs while marking child dispatcher processes with depth `1`. A current numeric depth greater than `1`, or any non-empty non-numeric value, returns `{}` without dispatching.\n\nThis means the bridge allows exactly one inherited bridge-marked dispatcher level and blocks recursive re-entry from deeper bridge-marked children. The guard also passes through `event.source === \"extension\"` to avoid extension-originated messages re-entering the bridge.\n\n## Installation and discovery\n\nThe canonical install location is the agent extensions directory discovered by the native GJC provider:\n\n- user-level: `${GJC_CODING_AGENT_DIR:-$HOME/.gjc/agent}/extensions`\n- project-level: `<cwd>/${GJC_CONFIG_DIR:-.gjc}/extensions`\n\nFor native discovery, install one of:\n\n- `extensions/<name>.ts` or `extensions/<name>.js`\n- `extensions/<name>/index.ts` or `extensions/<name>/index.js`\n- `extensions/<name>/package.json` declaring extension entries\n\nThe loader scans one level under each `extensions` directory. Complex packages should use a package manifest instead of relying on recursive discovery.\n\n`GJC_CONFIG_DIR` selects the project config directory name. `GJC_CODING_AGENT_DIR` selects the user agent directory name under `$HOME`. The native provider resolves those locations before loading extension modules, skills, rules, hooks, and related capabilities.\n\nHooks are not the input bridge surface: `packages/coding-agent/src/capability/hook.ts` defines pre/post tool hooks only.\n",