@gajae-code/coding-agent 0.4.3 → 0.4.5

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

@@ -1,6 +1,6 @@
 // Auto-generated by scripts/generate-docs-index.ts - DO NOT EDIT
 
-export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","brand-assets.md","bridge.md","codebase-overview.md","compaction.md","environment-variables.md","fs-scan-cache-architecture.md","gjc-dogfood-skill-template.md","handoff-generation-pipeline.md","keybindings.md","lsp-config.md","memory.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","onboarding-packet.md","onboarding-receipt.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.md","tools/checkpoint.md","tools/cron.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/monitor.md","tools/read.md","tools/recipe.md","tools/render_mermaid.md","tools/resolve.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","brand-assets.md","bridge.md","codebase-overview.md","compaction.md","environment-variables.md","fs-scan-cache-architecture.md","gjc-dogfood-skill-template.md","grok-build-provider-design.md","handoff-generation-pipeline.md","hermes-mcp-bridge.md","keybindings.md","lsp-config.md","memory.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","onboarding-packet.md","onboarding-receipt.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.md","tools/checkpoint.md","tools/cron.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/monitor.md","tools/read.md","tools/recipe.md","tools/render_mermaid.md","tools/resolve.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md"];
 
 export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"ERRATA-GPT5-HARMONY.md": "# ERRATA — GPT-5 Harmony-Header Leakage\n\n## 1. The problem\n\nOpenAI frames tool calls in the Harmony chat protocol:\n\n```\n<|start|>assistant<|channel|>commentary to=functions.<NAME><|message|>{ARGS}<|call|>\n```\n\n`<|channel|>commentary to=functions.NAME` is the **routing header** —\ncontrol tokens consumed by the runtime to dispatch the call. These\ntokens never appear as content under normal operation; the runtime\nstrips them.\n\nThe defect: gpt-5 models occasionally emit, **as ordinary content\ninside `{ARGS}`**, the **plain-text shadow** of these routing tokens —\nthe same characters without the `<|…|>` brackets — and continue\nproducing more pseudo-routing structure (channel name, body marker,\nmultilingual spam, fake tool-result framing). The contamination lives\ninside the visible tool argument and is dispatched to the tool as if it\nwere intended content.\n\n**Critical detail.** The actual `<|start|>` / `<|channel|>` /\n`<|message|>` / `<|call|>` special tokens almost never appear in tool\nargs. What leaks is the bracket-less spelling — `analysis to=functions.X\ncode …` — because OpenAI applies a logit mask suppressing the\ncontrol-token IDs inside the args region. The mass that would have gone\nto those special tokens redistributes onto the un-bracketed plain-text\nrepresentation the model also learned. This makes the leak structurally\ninvisible to the routing parser and lands it in the tool input verbatim.\n\nManifestation in tool args (real corpus example):\n\n```\n~      add_function(iso, ctx, ns, \"installSystemChangeObserver\",\n        os_install_system_change_observer);】【\"】【analysis to=functions.edit\n        code above เงินไทยฟรีuser to=functions.edit code …\n```\n\nThe leading code is real and intended. Everything after the first\nnon-Latin token through the next clean structural boundary is corruption.\n\n---\n\n## 2. Observed statistics & failure modes\n\nSource: `~/.gjc/stats.db` (`ss_tool_calls`, `ss_assistant_msgs`), through\n2026-05-10. 1.05M tool calls scanned.\n\n### 2.1 Rate\n\n| Model            | Leaks in tool args | Calls   | per million |\n|------------------|-------------------:|--------:|------------:|\n| gpt-5.4          | 37                 | 226,957 | 163         |\n| gpt-5.3-openai-code    | 17                 | 112,243 | 151         |\n| gpt-5.5          | 2                  |  80,750 |  25         |\n| gpt-5.2-openai-code    | 0                  |    —    |   —         |\n\nPlus 15 hits in assistant visible text / thinking blobs.\n\n### 2.2 Tool distribution\n\n| Tool                | Hits |\n|---------------------|-----:|\n| `edit`              | 38   |\n| `eval`              | 11   |\n| `report_tool_issue` | 3    |\n| `grep`/`read`/`search`/`yield` | 1 each |\n\nConcentrated in tools with free-form (non-JSON-schema) argument formats.\n\n### 2.3 Leak shape (deterministic)\n\n```\nLEAK         ::= JUNK_PREFIX MARKER CHANNEL_BODY (LEAK)?\nMARKER       ::= \"to=functions.\" TOOL_NAME\nCHANNEL_BODY ::= \" code \" (SPAM | reasoning_prose | fake_tool_output)*\nJUNK_PREFIX  ::= (GLITCH_TOKEN | CHANNEL_WORD | NON_LATIN_RUN | \"}\" | \"】【\")+\n```\n\n**Cascading is common.** Of 96 marker occurrences across 71 contaminated\nrecords, 39 contain ≥2 markers and 7 contain ≥3 — the model emits\nmultiple fake `to=functions.X code …` blocks back-to-back, often with\nfake `code_output\\nCell N:\\n…` framing between them. Once the\nplain-text scaffolding is in the residual stream, the prefix now *looks\nlike* a fresh tool envelope start, so the macro prior over continuations\nkeeps voting for more scaffolding. Self-amplifying.\n\n### 2.4 Glitch tokens\n\nSingle-token identifiers in `o200k_base` whose embeddings appear to be\nnear-init from underrepresentation in post-training. ASCII residue\nimmediately before the marker in the natural corpus:\n\n| Surface string    | Single-token | Token ID | Hits in corpus |\n|-------------------|:-:|---------:|---:|\n| `Japgolly`        | ✅ | 199,745 | 1 |\n| `Jsii`            | ✅ | 114,318 | (subtoken of `Jsii_commentary`) |\n| `Jsii_commentary` | — (3 toks) | — | 2 |\n| `changedFiles`    | — (2 toks) | — | 8 |\n| `RTLU`            | — (2 toks) | — | 3 |\n\n`Japgolly` is in the last 0.13% of the vocabulary — the same family of\nGitHub-corpus residue that produced `SolidGoldMagikarp` in the 2023\nGPT-2 vocabulary (Rumbelow & Watkins). `SolidGoldMagikarp` itself\ntokenizes to 5 tokens in `o200k_base` — that specific token was retired,\nbut the class wasn't.\n\nFor the multi-token entries, the corpus-level signature is the surface\nstring; the underlying glitch trigger is a sub-token (e.g. `Jsii` inside\n`Jsii_commentary`). The detector list (`G` signal) keys on the surface\nstrings.\n\nStable across unrelated sessions. Treated as a high-precision detector\nsignal.\n\n### 2.5 Channel-word leakage\n\n`analysis` (5), `assistant` (5), `commentary` (3), `user` (1) appear\ndirectly preceding `to=`. Always bare words; never `<|channel|>analysis`\nor any other bracketed form. Consistent with §1 — the brackets are\nmasked, the words are not.\n\n### 2.6 Non-Latin spam residue\n\n96 marker hits, by script: CJK 40, Cyrillic 12, Telugu/Kannada/Malayalam\n18, Thai 8, Georgian 7, Armenian 7, Arabic 1. Recurring fragments are\nChinese gambling SEO (`大发时时彩`, `天天中彩票`), Georgian/Abkhaz junk,\nand Thai casino spam — well-known low-quality crawl residue.\n\nThis is the same script distribution observed in the controlled\nreproduction (§7.3), independent of the prompt's natural language.\n\n### 2.7 Failure-mode breakdown for the `edit` tool\n\nThe `edit` tool exists in two variants in the corpus:\n\n| Variant                  | Calls | Recovery |\n|--------------------------|------:|----------|\n| Patch-DSL (`§PATH`/anchor/`«»≔` ops) | 27 | **Recoverable** by op-truncation (§3.3) |\n| JSON-schema (`{path,edits:[…]}`)      | 11 | **Not recoverable** — contamination is escaped *inside* JSON strings, parser accepts it cleanly, content would be written verbatim into source files |\n\nFor Patch-DSL leaks specifically:\n\n- 20/27 cases: contamination on the last input line; nothing follows.\n- 7/27 cases: contamination mid-input; what follows is one of: a\n  duplicate replay of an earlier file/anchor, intended content for a\n  *different* tool call (the model started its next call inline), or\n  pure hallucination. Post-contamination content is never trustworthy.\n\n### 2.8 Mechanism (confirmed)\n\n**Prior collapse from null-embedding glitch tokens, into a\ncontrol-token-masked basin whose mass redistributes onto the\nplain-text shadow of the Harmony protocol.**\n\nStep by step:\n\n1. The model is mid-`{ARGS}` of a Harmony tool call. The runtime applies\n   a logit mask suppressing structural control tokens (`<|channel|>`,\n   `<|message|>`, `<|call|>`, `<|start|>`, `<|end|>`) inside the args\n   region. Without this mask, normal generation would constantly\n   hallucinate envelope-closes; with it, those token IDs have logit\n   `-∞` in args.\n2. A glitch token `g` is sampled. By construction `g` was in the BPE\n   merge corpus but barely in LM/RL training, so its **input embedding\n   `e_g` ≈ near-init noise of small norm**.\n3. At position t+1, the residual update `h_{t+1} ≈ LN(h_t + e_g + Attn +\n   MLP)` is dominated by the prefix-derived terms; the just-emitted-token\n   signal is effectively absent. Generation diversity normally comes\n   from `e_x` steering the residual into different sub-regions —\n   stripped here.\n4. The next-token distribution therefore collapses onto the **conditional\n   prior over continuations of the prefix, with local conditioning\n   removed**. In a tool-calling rollout context, that prior is sharply\n   peaked on Harmony scaffolding (control tokens + routing tokens) —\n   that's what RL trained.\n5. The mask zeros the control-token IDs. Mass redistributes onto the\n   **next-best continuation**: the un-bracketed surface-form spelling of\n   the same protocol (`analysis`, `commentary`, ` to=functions.X`,\n   ` code `). This spelling is unmasked because those characters are\n   ordinary tokens.\n6. Once a few tokens of plain-text scaffolding land in the residual\n   stream, the prefix now resembles a fresh envelope start. The macro\n   prior keeps voting for more scaffolding. Cascading (§2.3) follows.\n7. Multilingual spam after the marker is the same prior-collapse\n   continuation, drawn from the training neighborhood of the glitch\n   token (often ESL/auto-generated multilingual web junk — exactly the\n   crawl residue in §2.6).\n\n**Two corollaries the corpus data demanded but only the experiment\nexplained:**\n\n- **The brackets never appear** (§1, §2.5). The mask is what makes the\n  leak land in plain text instead of as a real envelope-close.\n- **Counterintuitive grammar dependency** (§7.4). The leak is *worse* in\n  formats closest to OpenAI's training distribution. Off-distribution\n  custom grammars dampen the macro-prior basin; the official\n  `*** Begin Patch` format is the strongest collapse target.\n\nThe 2023 SolidGoldMagikarp paper documented mechanism (1)+(2)+(4). The\nnew piece is (5): when constrained decoding masks the natural collapse\ntarget, the mass laundered through the un-masked plain-text shadow\nbecomes a structurally-invisible exfiltration channel.",
@@ -13,10 +13,12 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"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 plus the `control` scope on this (default-disabled) endpoint; `X-GJC-Bridge-Owner-Token` may be carried by SDK helpers and participates in idempotency/cache correlation, but — unlike UI/permission responses — gate resolution does not separately validate it as the current controller token. `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| `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` | `prompt` |\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 plus the `control` scope on the (by-default-disabled) `ui-responses` endpoint; the owner token is carried for idempotency/controller correlation, but — unlike UI/permission responses — gate resolution itself is gated by `control` scope rather than a separately enforced controller-owner-token check.\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` (or `gjc --tmux --worktree <path>` when the worktree path is part of the launch).\n3. Submit the workflow appropriate to the task: `/skill:deep-interview` for requirements discovery, `/skill:ralplan` for plan consensus, and `gjc ultragoal ...` for durable goal tracking through execution and verification.\n4. Use `gjc team ...` only when coordinated parallel tmux workers help with implementation or verification; single-lane work should stay in the leader session.\n5. Collect the handoff state: whether the session stopped cleanly, changed files, commands/checks run, failures, unresolved risks, and evidence summaries.\n\nBridge mode remains the public remote-control protocol for an already-running GJC session, but the session-control endpoints are fail-closed by default. Keep lifecycle, worktree selection, and evidence policy above the bridge frames, and avoid documenting private deployment, routing, or credential internals. Introducing another authenticated remote-control protocol for the same purpose should require ADR-level rationale.\n\nThe same external-runner workflow is summarized in the README section [Using GJC with other coding agents](../README.md#using-gjc-with-other-coding-agents).\n",
 	"codebase-overview.md": "# Codebase Overview\n\nThis document maps the main parts of the `gajae-code` repository. The root README stays intentionally small; this file is the architecture-oriented companion.\n\n## Product shape\n\nGajae-Code (`gjc`) is centered on `packages/coding-agent/`. The public workflow surface is intentionally fixed at four source-bundled skills and four public role subagents. Runtime state, specs, plans, goals, team state, and local overrides live under `.gjc/`.\n\nDefault workflow skills are embedded from:\n\n```text\npackages/coding-agent/src/defaults/gjc/skills/<name>/SKILL.md\n```\n\nPublic role subagent prompts are embedded from:\n\n```text\npackages/coding-agent/src/prompts/agents/<role>.md\n```\n\nThe runtime can still discover project/user overrides, but the bundled defaults are loaded from source so a missing project `.gjc` directory does not remove the default workflow surface.\n\n## Packages\n\n### `packages/coding-agent/`\n\nMain `gjc` CLI and product runtime.\n\n- `packages/coding-agent/package.json` exposes the `gjc` binary at `src/cli.ts` and the SDK/barrel entrypoint at `src/index.ts`.\n- `packages/coding-agent/src/cli.ts` is the executable bootstrap. It registers CLI commands such as `setup`, `deep-interview`, `ralplan`, `ultragoal`, `team`, and the default launch path.\n- `packages/coding-agent/src/main.ts` adapts CLI options into session creation and dispatches interactive, print, RPC, RPC-UI, and ACP modes.\n- `packages/coding-agent/src/sdk.ts` assembles settings, model registry, auth, workspace/context discovery, skills, rules, tools, system prompt, and the underlying `@gajae-code/agent-core` agent.\n- `packages/coding-agent/src/tools/index.ts` is the built-in tool registry for file/code/runtime tools such as read, bash, edit, AST tools, eval, find/search, LSP, browser, task/subagent, recipe, IRC, todo, web search, and write. Memory backends are private integrations, not public coding-harness tools.\n- `packages/coding-agent/src/defaults/gjc-defaults.ts` embeds and installs the default workflow skills.\n- `packages/coding-agent/src/task/agents.ts` embeds bundled task-agent prompts. The public contract is `executor`, `architect`, `planner`, and `critic`; other bundled prompts are internal/runtime utilities.\n\n### `packages/ai/`\n\nProvider/model boundary for LLM access.\n\n- `packages/ai/src/index.ts` exports model registry/resolution, provider implementations, auth broker/gateway/storage, streaming, usage, retry/overflow utilities, OAuth, discovery, and validation helpers.\n- `packages/ai/src/types.ts` defines provider, model, context, message, tool, usage, reasoning, and stream-event contracts.\n- `packages/ai/src/stream.ts` dispatches model-driven streams to the right provider/API implementation and normalizes streaming events.\n- `packages/ai/src/model-manager.ts` merges static, cached, dynamic, and remote model sources.\n- `packages/ai/README.md` documents tool calling, partial streaming tool calls, thinking/reasoning, provider configuration, context handoff, and OAuth flows.\n\n### `packages/agent/`\n\nStateful agent runtime built on `@gajae-code/ai`.\n\n- `packages/agent/src/index.ts` exports the `Agent`, loop APIs, append-only context, compaction, telemetry, proxy utilities, thinking helpers, and shared types.\n- `packages/agent/src/agent-loop.ts` owns the turn loop: transform context, call the model stream, execute tool calls, append tool results, and emit lifecycle events.\n- `packages/agent/src/agent.ts` wraps the loop with mutable state, subscriptions, prompt/continue/abort APIs, queues, provider session state, telemetry, and state mutation helpers.\n- `packages/agent/src/types.ts` defines `AgentMessage`, `AgentTool`, loop config, event, and runtime state contracts.\n\n### `packages/tui/`\n\nTerminal UI framework used by the CLI.\n\n- `packages/tui/src/index.ts` exports components, keybindings, autocomplete, terminal abstractions, image support, TUI core, and utilities.\n- `packages/tui/src/tui.ts` manages component rendering, focus, overlays, terminal dimensions, diff state, and synchronized output.\n- `packages/tui/src/terminal.ts` abstracts terminal lifecycle, dimensions, cursor controls, title/progress, Kitty protocol state, and appearance notifications.\n- `packages/tui/README.md` documents the component model and built-in components such as text, input, editor, markdown, loaders, select/settings lists, spacer, image, box, and container.\n\n### `packages/natives/` and Rust crates\n\nNative helper layer exposed through N-API.\n\n- `packages/natives/package.json` exports `native/index.js` and generated TypeScript definitions.\n- `packages/natives/native/loader-state.js` resolves platform/CPU-specific native binaries and validates package/native version alignment.\n- `crates/pi-natives/src/lib.rs` is the N-API root for appearance, AST search/editing, clipboard, filesystem scan/cache, grep/glob, syntax highlighting, HTML-to-Markdown, keyboard parsing, process/PTY/shell support, SIXEL, code summarization, token counting, text measurement/wrapping/truncation, workspace scanning, power assertions, and isolation helpers.\n- `crates/pi-shell/src/lib.rs` exposes brush-based shell execution primitives used by the native shell adapter.\n- `crates/pi-shell/src/shell.rs` implements persistent and one-shot shell execution, streaming, environment handling, cancellation, and output minimizer telemetry.\n- `crates/pi-shell/src/fixup.rs` performs conservative AST-based bash command fixups.\n- `crates/pi-natives/src/pty.rs` implements interactive PTY sessions.\n\n### `packages/utils/`\n\nShared TypeScript utilities.\n\n- `packages/utils/src/index.ts` exports abortable/async helpers, color/env/dir utilities, fetch retry, formatting, frontmatter, glob helpers, JSON helpers, logging, MIME detection, prompt rendering, process-tree helpers, sanitization, streams, temp files, tab spacing, type guards, and executable lookup.\n- `packages/utils/src/ptree.ts` and `packages/utils/src/procmgr.ts` wrap native process helpers for ergonomic TypeScript use.\n\n### `packages/stats/`\n\nLocal observability dashboard for session and model usage.\n\n- `packages/stats/src/index.ts` exposes the `gjc-stats` CLI entrypoint and exports aggregation/server APIs.\n- `packages/stats/src/aggregator.ts` parses session-derived request metrics and writes aggregated data through SQLite.\n- `packages/stats/src/server.ts` serves local dashboard API routes and static SPA assets.\n- `packages/stats/src/types.ts` and `packages/stats/src/shared-types.ts` define dashboard and aggregate metric shapes.\n\n### `packages/typescript-edit-benchmark/`\n\nPrivate benchmark package for TypeScript edit tasks.\n\n- `packages/typescript-edit-benchmark/package.json` exposes `typescript-edit-benchmark` and depends on the coding-agent, agent-core, ai, tui, utils, diff, prettier, and Babel tooling.\n- `packages/typescript-edit-benchmark/src/index.ts` is the benchmark CLI: it resolves fixtures, loads tasks, runs edit attempts, records progress, and writes reports/conversation dumps under `runs/`.\n\n## Python packages\n\n### `python/gjc-rpc/`\n\nTyped Python client for `gjc --mode rpc`.\n\n- `python/gjc-rpc/pyproject.toml` packages `gjc-rpc` for Python 3.11+.\n- `python/gjc-rpc/README.md` documents the process-backed stdio client, typed command methods, startup flags, event listeners, todo seeding, host-owned tools, and host-owned URI schemes.\n\n### `python/robogjc/`\n\nSelf-hosted GitHub triage/fix bot that drives `gjc --mode rpc`.\n\n- `python/robogjc/AGENTS.md` is the authoritative local contract for this subtree.\n- `python/robogjc/pyproject.toml` packages `robogjc` for Python 3.11+ with FastAPI, httpx, pydantic settings, Click, and `gjc-rpc`.\n- `python/robogjc/README.md` documents the webhook-to-worktree-to-gjc flow, GitHub sidecar trust boundary, persistent per-issue sessions, and audit trail.\n- Important modules include `src/server.py`, `src/queue.py`, `src/tasks.py`, `src/worker.py`, `src/host_tools.py`, `src/sandbox.py`, `src/github_client.py`, `src/github_events.py`, `src/db.py`, and `src/config.py`.\n\n## Runtime flow\n\nA normal CLI session starts in `packages/coding-agent/src/cli.ts`, routes through command handling, then reaches `packages/coding-agent/src/main.ts`. `main.ts` converts CLI/runtime settings into `CreateAgentSessionOptions` and calls `createAgentSession()` in `packages/coding-agent/src/sdk.ts`.\n\nThe SDK builds the session context, loads the default skills, creates built-in tools, resolves model/auth state through `@gajae-code/ai`, constructs the system prompt, and instantiates `@gajae-code/agent-core`. The agent loop streams model events, executes tools, records tool results, and hands state back to the selected mode: interactive TUI, print, RPC, RPC-UI, or ACP.\n\n## Verification and gates\n\nPackage-local checks are defined in each `package.json`. For workflow-definition or default-surface changes, the focused gates are:\n\n```sh\nbun scripts/check-visible-definitions.ts\nbun scripts/verify-g002-gates.ts\nbun scripts/rebrand-inventory.ts --strict\nbun test packages/coding-agent/test/default-gjc-definitions.test.ts\n```\n\nFor broader TypeScript verification, use the root script:\n\n```sh\nbun run check:ts\n```\n\nDo not use `tsc` or `npx tsc` directly in this repository.\n",
 	"compaction.md": "# Compaction and Branch Summaries\n\nCompaction and branch summaries are the two mechanisms that keep long sessions usable without losing prior work context.\n\n- **Compaction** rewrites old history into a summary on the current branch.\n- **Branch summary** captures abandoned branch context during `/tree` navigation.\n\nBoth are persisted as session entries and converted back into user-context messages when rebuilding LLM input.\n\n## Key implementation files\n\n- `packages/agent/src/compaction/compaction.ts` (context-full summarization and handoff generation)\n- `packages/agent/src/compaction/branch-summarization.ts`\n- `packages/agent/src/compaction/pruning.ts`\n- `packages/agent/src/compaction/utils.ts`\n- `packages/agent/src/compaction/openai.ts`\n- `packages/coding-agent/src/session/session-manager.ts`\n- `packages/coding-agent/src/session/agent-session.ts`\n- `packages/coding-agent/src/session/messages.ts`\n- `packages/coding-agent/src/extensibility/hooks/types.ts`\n- `packages/coding-agent/src/config/settings-schema.ts`\n\n## Session entry model\n\nCompaction and branch summaries are first-class session entries, not plain assistant/user messages.\n\n- `CompactionEntry`\n  - `type: \"compaction\"`\n  - `summary`, optional `shortSummary`\n  - `firstKeptEntryId` (compaction boundary)\n  - `tokensBefore`\n  - optional `details`, `preserveData`, `fromExtension`\n- `BranchSummaryEntry`\n  - `type: \"branch_summary\"`\n  - `fromId`, `summary`\n  - optional `details`, `fromExtension`\n\nWhen context is rebuilt (`buildSessionContext`):\n\n1. Latest compaction on the active path is converted to one `compactionSummary` message.\n2. Kept entries from `firstKeptEntryId` to the compaction point are re-included.\n3. Later entries on the path are appended.\n4. `branch_summary` entries are converted to `branchSummary` messages.\n5. `custom_message` entries are converted to `custom` messages.\n\nThose custom roles are then transformed into LLM-facing user messages in `convertToLlm()` using the static templates:\n\n- `packages/agent/src/compaction/prompts/compaction-summary-context.md`\n- `packages/agent/src/compaction/prompts/branch-summary-context.md`\n- `packages/agent/src/compaction/prompts/handoff-document.md`\n\n## Compaction pipeline\n\n### Triggers\n\nCompaction/context maintenance can run in four ways:\n\n1. **Manual context compaction**: `/compact [instructions]` calls `AgentSession.compact(...)`.\n2. **Automatic overflow recovery**: after a same-model assistant error that matches context overflow.\n3. **Automatic threshold maintenance**: after a successful turn when context exceeds the resolved threshold.\n4. **Idle maintenance**: `runIdleCompaction()` can invoke the same auto-maintenance path with reason `\"idle\"`.\n\n### Compaction shape (visual)\n\n```text\nBefore compaction:\n\n  entry:  0     1     2     3      4     5     6      7      8     9\n        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┐\n        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │\n        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┘\n                └────────┬───────┘ └──────────────┬──────────────┘\n               messagesToSummarize            kept messages\n                                   ↑\n                          firstKeptEntryId (entry 4)\n\nAfter compaction (new entry appended):\n\n  entry:  0     1     2     3      4     5     6      7      8     9      10\n        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┬─────┐\n        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │ cmp │\n        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┴─────┘\n               └──────────┬──────┘ └──────────────────────┬───────────────────┘\n                 not sent to LLM                    sent to LLM\n                                                         ↑\n                                              starts from firstKeptEntryId\n\nWhat the LLM sees:\n\n  ┌────────┬─────────┬─────┬─────┬──────┬──────┬─────┬──────┐\n  │ system │ summary │ usr │ ass │ tool │ tool │ ass │ tool │\n  └────────┴─────────┴─────┴─────┴──────┴──────┴─────┴──────┘\n       ↑         ↑      └─────────────────┬────────────────┘\n    prompt   from cmp          messages from firstKeptEntryId\n```\n\n### Overflow-retry vs threshold/idle maintenance\n\nThe automatic paths are intentionally different:\n\n- **Overflow recovery**\n  - Trigger: current-model assistant error is detected as context overflow and the error is not older than the latest compaction.\n  - The failing assistant error message is removed from active agent state before retry.\n  - Context promotion is tried first; if a configured larger model is available, the agent switches model and retries without compacting.\n  - If promotion is unavailable and compaction is enabled, context-full compaction runs with `reason: \"overflow\"` and `willRetry: true`; handoff strategy is not used for overflow.\n  - On success, agent auto-continues (`agent.continue()`) after compaction.\n\n- **Threshold maintenance**\n  - Trigger: successful, non-error assistant message whose adjusted context tokens exceed `resolveThresholdTokens(...)`.\n  - Tool-output pruning can reduce the measured token count before threshold comparison.\n  - Context promotion is tried before compaction.\n  - If promotion is unavailable, auto maintenance runs with `reason: \"threshold\"` and `willRetry: false`.\n  - With `compaction.strategy: \"handoff\"`, threshold maintenance starts a new handoff session instead of writing a compaction entry; if handoff returns no document without aborting, it falls back to context-full compaction.\n  - On success, if `compaction.autoContinue !== false`, schedules an agent-authored developer auto-continue prompt from `prompts/system/auto-continue.md`.\n\n- **Idle maintenance**\n  - Trigger: `runIdleCompaction()` when not streaming or already compacting.\n  - Uses `reason: \"idle\"` and does not auto-continue afterward.\n\n### Pre-compaction pruning\n\nBefore compaction checks, tool-result pruning may run (`pruneToolOutputs`).\n\nDefault prune policy:\n\n- Protect newest `40_000` tool-output tokens.\n- Require at least `20_000` total estimated savings.\n- Never prune tool results from `skill` or `read`.\n\nPruned tool results are replaced with:\n\n- `[Output truncated - N tokens]`\n\nIf pruning changes entries, session storage is rewritten and agent message state is refreshed before compaction decisions.\n\n### Boundary and cut-point logic\n\n`prepareCompaction()` only considers entries since the last compaction entry (if any).\n\n1. Find previous compaction index.\n2. Compute `boundaryStart = prevCompactionIndex + 1`.\n3. Adapt `keepRecentTokens` using measured usage ratio when available.\n4. Run `findCutPoint()` over the boundary window.\n\nValid cut points include:\n\n- message entries with roles: `user`, `assistant`, `bashExecution`, `hookMessage`, `branchSummary`, `compactionSummary`\n- `custom_message` entries\n- `branch_summary` entries\n\nHard rule: never cut at `toolResult`.\n\nIf there are non-message metadata entries immediately before the cut point (`model_change`, `thinking_level_change`, labels, etc.), they are pulled into the kept region by moving cut index backward until a message or compaction boundary is hit.\n\n### Split-turn handling\n\nIf cut point is not at a user-turn start, compaction treats it as a split turn.\n\nTurn start detection treats these as user-turn boundaries:\n\n- `message.role === \"user\"`\n- `message.role === \"bashExecution\"`\n- `custom_message` entry\n- `branch_summary` entry\n\nSplit-turn compaction generates two summaries:\n\n1. History summary (`messagesToSummarize`)\n2. Turn-prefix summary (`turnPrefixMessages`)\n\nFinal stored summary is merged as:\n\n```markdown\n<history summary>\n\n---\n\n**Turn Context (split turn):**\n\n<turn prefix summary>\n```\n\n### Summary generation\n\n`compact(...)` builds summaries from serialized conversation text:\n\n1. Convert messages via `convertToLlm()`.\n2. Serialize with `serializeConversation()`.\n3. Wrap in `<conversation>...</conversation>`.\n4. Optionally include `<previous-summary>...</previous-summary>`.\n5. Optionally inject hook context as `<additional-context>` list.\n6. Execute summarization prompt with `SUMMARIZATION_SYSTEM_PROMPT`.\n\nPrompt selection:\n\n- first compaction: `compaction-summary.md`\n- iterative compaction with prior summary: `compaction-update-summary.md`\n- split-turn second pass: `compaction-turn-prefix.md`\n- short UI summary: `compaction-short-summary.md`\n- handoff document: `handoff-document.md` (used by `generateHandoff(...)`, not serialized compaction)\n\nRemote summarization modes:\n\n- If `compaction.remoteEndpoint` is set and remote compaction is enabled, local summary generation POSTs:\n  - `{ systemPrompt, prompt }`\n- Expects JSON containing at least `{ summary }`.\n- For OpenAI/OpenAI code provider models, compaction first tries the provider-native `/responses/compact` endpoint when remote compaction is enabled. It preserves provider replacement history in `preserveData.openaiRemoteCompaction` and falls back to local summarization if that native request fails.\n\n### Handoff generation\n\n`packages/agent/src/compaction/compaction.ts` also exports `generateHandoff(...)`. Handoff generation uses the same `completeSimple(...)` oneshot style as summarization, but it preserves the live agent cache prefix by sending the active system prompt, tool array, and real LLM message history, then appending one agent-attributed `user` message containing the handoff prompt. It forces `toolChoice: \"none\"` and returns joined text blocks directly.\n\nHandoff does not write a `CompactionEntry`. `AgentSession.handoff()` owns the session transition: it starts a new session, injects the generated document as a visible `custom_message` with `customType: \"handoff\"`, and rebuilds agent messages from that new session.\n\n### File-operation context in summaries\n\nCompaction tracks cumulative file activity using assistant tool calls:\n\n- `read(path)` → read set\n- `write(path)` → modified set\n- `edit(path)` → modified set\n\nCumulative behavior:\n\n- Includes prior compaction details only when prior entry is pi-generated (`fromExtension !== true`).\n- In split turns, includes turn-prefix file ops too.\n- `readFiles` excludes files also modified.\n\nSummary text gets file tags appended via prompt template:\n\n```xml\n<read-files>\n...\n</read-files>\n<modified-files>\n...\n</modified-files>\n```\n\n### Persist and reload\n\nAfter summary generation (or hook-provided summary), agent session:\n\n1. Appends `CompactionEntry` with `appendCompaction(...)` for context-full maintenance; handoff strategy creates a new session and injects a handoff `custom_message` instead.\n2. Rebuilds display context from the active leaf via `buildDisplaySessionContext()`.\n3. Replaces live agent messages with rebuilt context.\n4. Emits `session_compact` hook event.\n\n## Branch summarization pipeline\n\nBranch summarization is tied to tree navigation, not token overflow.\n\n### Trigger\n\nDuring `navigateTree(...)`:\n\n1. Compute abandoned entries from old leaf to common ancestor using `collectEntriesForBranchSummary(...)`.\n2. If caller requested summary (`options.summarize`), generate summary before switching leaf.\n3. If summary exists, attach it at the navigation target using `branchWithSummary(...)`.\n\nOperationally this is commonly driven by `/tree` flow when `branchSummary.enabled` is enabled.\n\n### Branch switch shape (visual)\n\n```text\nTree before navigation:\n\n         ┌─ B ─ C ─ D (old leaf, being abandoned)\n    A ───┤\n         └─ E ─ F (target)\n\nCommon ancestor: A\nEntries to summarize: B, C, D\n\nAfter navigation with summary:\n\n         ┌─ B ─ C ─ D ─ [summary of B,C,D]\n    A ───┤\n         └─ E ─ F (new leaf)\n```\n\n### Preparation and token budget\n\n`generateBranchSummary(...)` computes budget as:\n\n- `tokenBudget = model.contextWindow - branchSummary.reserveTokens`\n\n`prepareBranchEntries(...)` then:\n\n1. First pass: collect cumulative file ops from all summarized entries, including prior pi-generated `branch_summary` details.\n2. Second pass: walk newest → oldest, adding messages until token budget is reached.\n3. Prefer preserving recent context.\n4. May still include large summary entries near budget edge for continuity.\n\nCompaction entries are included as messages (`compactionSummary`) during branch summarization input.\n\n### Summary generation and persistence\n\nBranch summarization:\n\n1. Converts and serializes selected messages.\n2. Wraps in `<conversation>`.\n3. Uses custom instructions if supplied, otherwise `branch-summary.md`.\n4. Calls summarization model with `SUMMARIZATION_SYSTEM_PROMPT`.\n5. Prepends `branch-summary-preamble.md`.\n6. Appends file-operation tags.\n\nResult is stored as `BranchSummaryEntry` with optional details (`readFiles`, `modifiedFiles`).\n\n## Extension and hook touchpoints\n\n### `session_before_compact`\n\nPre-compaction hook.\n\nCan:\n\n- cancel compaction (`{ cancel: true }`)\n- provide full custom compaction payload (`{ compaction: CompactionResult }`)\n\n### `session.compacting`\n\nPrompt/context customization hook for default compaction.\n\nCan return:\n\n- `prompt` (override base summary prompt)\n- `context` (extra context lines injected into `<additional-context>`)\n- `preserveData` (stored on compaction entry)\n\n### `session_compact`\n\nPost-compaction notification with saved `compactionEntry` and `fromExtension` flag.\n\n### `session_before_tree`\n\nRuns on tree navigation before default branch summary generation.\n\nCan:\n\n- cancel navigation\n- provide custom `{ summary: { summary, details } }` used when user requested summarization\n\n### `session_tree`\n\nPost-navigation event exposing new/old leaf and optional summary entry.\n\n## Runtime behavior and failure semantics\n\n- Manual compaction aborts current agent operation first.\n- `abortCompaction()` cancels both manual and auto-compaction controllers.\n- Auto compaction emits start/end session events for UI/state updates.\n- Auto compaction can try multiple model candidates and retry transient failures; long retry delays prefer the next candidate when one is available.\n- Overflow errors are excluded from generic retry path because they are handled by context promotion/compaction.\n- If auto-compaction fails:\n  - overflow path emits `Context overflow recovery failed: ...`\n  - threshold path emits `Auto-compaction failed: ...`\n- Branch summarization can be cancelled via abort signal (e.g., Escape), returning canceled/aborted navigation result.\n\n## Settings and defaults\n\nFrom `settings-schema.ts`:\n\n- `compaction.enabled` = `true`\n- `compaction.strategy` = `\"context-full\"` (`\"handoff\"` and `\"off\"` are also supported)\n- `compaction.reserveTokens` = `16384`\n- `compaction.keepRecentTokens` = `20000`\n- `compaction.autoContinue` = `true`\n- `compaction.remoteEnabled` = `true`\n- `compaction.remoteEndpoint` = `undefined`\n- `compaction.thresholdPercent` = `-1` and `compaction.thresholdTokens` = `-1`; when no positive override is set, the threshold is `contextWindow - max(15% of contextWindow, reserveTokens)`\n- `compaction.idleEnabled` = `true`\n- `branchSummary.enabled` = `false`\n- `branchSummary.reserveTokens` = `16384`\n\nThese values are consumed at runtime by `AgentSession` and compaction/branch summarization modules.\n",
-	"environment-variables.md": "# Environment Variables (Current Runtime Reference)\n\nThis reference is derived from current code paths in:\n\n- `packages/coding-agent/src/**`\n- `packages/ai/src/**` (provider/auth resolution used by coding-agent)\n- `packages/utils/src/**` and `packages/tui/src/**` where those vars directly affect coding-agent runtime\n\nIt documents only active behavior.\n\n## Resolution model and precedence\n\nMost runtime lookups use `$env` from `@gajae-code/utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Agent `.env` (`~/.gjc/agent/.env`, respecting `GJC_CONFIG_DIR` / `GJC_CODING_AGENT_DIR`) for keys not already set\n4. Config-root `.env` (`~/.gjc/.env`, respecting `GJC_CONFIG_DIR`) for keys not already set\n5. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule inside each `.env` file: `GJC_*` keys are mirrored to `GJC_*` keys in that parsed file.\n\n---\n\n## 1) Model/provider authentication\n\nThese are consumed via `getEnvApiKey()` (`packages/ai/src/stream.ts`) unless noted otherwise.\n\n### Core provider credentials\n\n| Variable                        | Used for                                         | Required when                                                  | Notes / precedence                                                                                  |\n| ------------------------------- | ------------------------------------------------ | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- |\n| `ANTHROPIC_OAUTH_TOKEN`         | Anthropic API auth                               | Using Anthropic with OAuth token auth                          | Takes precedence over `ANTHROPIC_API_KEY` for provider auth resolution                              |\n| `ANTHROPIC_API_KEY`             | Anthropic API auth                               | Using Anthropic without OAuth token                            | Fallback after `ANTHROPIC_OAUTH_TOKEN`                                                              |\n| `ANTHROPIC_FOUNDRY_API_KEY`     | Anthropic via Azure Foundry / enterprise gateway | `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` enabled                              | Takes precedence over `ANTHROPIC_OAUTH_TOKEN` and `ANTHROPIC_API_KEY` when Foundry mode is enabled  |\n| `OPENAI_API_KEY`                | OpenAI auth                                      | Using OpenAI-family providers without explicit apiKey argument | Used by OpenAI Completions/Responses providers                                                      |\n| `GEMINI_API_KEY`                | Google Gemini auth                               | Using `google` provider models                                 | Primary key for Gemini provider mapping                                                             |\n| `GOOGLE_API_KEY`                | Gemini image tool auth fallback                  | Using `gemini_image` tool without `GEMINI_API_KEY`             | Used by coding-agent image tool fallback path                                                       |\n| `GROQ_API_KEY`                  | Groq auth                                        | Using Groq models                                              |                                                                                                     |\n| `CEREBRAS_API_KEY`              | Cerebras auth                                    | Using Cerebras models                                          |                                                                                                     |\n| `FIREWORKS_API_KEY`             | Fireworks auth                                   | Using Fireworks models                                         |                                                                                                     |\n| `TOGETHER_API_KEY`              | Together auth                                    | Using `together` provider                                      |                                                                                                     |\n| `HUGGINGFACE_HUB_TOKEN`         | Hugging Face auth                                | Using `huggingface` provider                                   | Primary Hugging Face token env var                                                                  |\n| `HF_TOKEN`                      | Hugging Face auth                                | Using `huggingface` provider                                   | Fallback when `HUGGINGFACE_HUB_TOKEN` is unset                                                      |\n| `SYNTHETIC_API_KEY`             | Synthetic auth                                   | Using Synthetic models                                         |                                                                                                     |\n| `NVIDIA_API_KEY`                | NVIDIA auth                                      | Using `nvidia` provider                                        |                                                                                                     |\n| `NANO_GPT_API_KEY`              | NanoGPT auth                                     | Using `nanogpt` provider                                       |                                                                                                     |\n| `VENICE_API_KEY`                | Venice auth                                      | Using `venice` provider                                        |                                                                                                     |\n| `LITELLM_API_KEY`               | LiteLLM auth                                     | Using `litellm` provider                                       | OpenAI-compatible LiteLLM proxy key                                                                 |\n| `LM_STUDIO_API_KEY`             | LM Studio auth (optional)                        | Using `lm-studio` provider with authenticated hosts            | Local LM Studio usually runs without auth; any non-empty token works when a key is required         |\n| `OLLAMA_API_KEY`                | Ollama auth (optional)                           | Using `ollama` provider with authenticated hosts               | Local Ollama usually runs without auth; any non-empty token works when a key is required            |\n| `LLAMA_CPP_API_KEY`             | llama.cpp auth (optional)                        | Using `llama.cpp` provider with authenticated hosts            | Local llama.cpp usually runs without auth; any non-empty token works when a key is configured       |\n| `XIAOMI_API_KEY`                | Xiaomi MiMo auth                                 | Using `xiaomi` provider                                        |                                                                                                     |\n| `MOONSHOT_API_KEY`              | Moonshot auth                                    | Using `moonshot` provider                                      |                                                                                                     |\n| `XAI_API_KEY`                   | xAI auth                                         | Using xAI models                                               |                                                                                                     |\n| `OPENROUTER_API_KEY`            | OpenRouter auth                                  | Using OpenRouter models                                        | Also used by image tool when preferred/auto provider is OpenRouter                                  |\n| `MISTRAL_API_KEY`               | Mistral auth                                     | Using Mistral models                                           |                                                                                                     |\n| `ZAI_API_KEY`                   | z.ai auth                                        | Using z.ai models                                              | Also used by z.ai web search provider                                                               |\n| `MINIMAX_API_KEY`               | MiniMax auth                                     | Using `minimax` provider                                       |                                                                                                     |\n| `AZURE_OPENAI_API_KEY`          | Azure OpenAI auth                               | Using `azure-openai` / `azure-openai-responses` models         | Pair with `AZURE_OPENAI_BASE_URL` or `AZURE_OPENAI_RESOURCE_NAME`                                   |\n| `MINIMAX_CODE_API_KEY`          | MiniMax Code auth                                | Using `minimax-code` provider                                  |                                                                                                     |\n| `MINIMAX_CODE_CN_API_KEY`       | MiniMax Code CN auth                             | Using `minimax-code-cn` provider                               |                                                                                                     |\n| `OPENCODE_API_KEY`              | OpenCode auth                                    | Using `opencode-go` / `opencode-zen` models                    |                                                                                                     |\n| `QIANFAN_API_KEY`               | Qianfan auth                                     | Using `qianfan` provider                                       |                                                                                                     |\n| `QWEN_OAUTH_TOKEN`              | Qwen Portal auth                                 | Using `qwen-portal` with OAuth token                           | Takes precedence over `QWEN_PORTAL_API_KEY`                                                         |\n| `QWEN_PORTAL_API_KEY`           | Qwen Portal auth                                 | Using `qwen-portal` with API key                               | Fallback after `QWEN_OAUTH_TOKEN`                                                                   |\n| `ZENMUX_API_KEY`                | ZenMux auth                                      | Using `zenmux` provider                                        | Used for ZenMux OpenAI and Anthropic-compatible routes                                              |\n| `VLLM_API_KEY`                  | vLLM auth/discovery opt-in                       | Using `vllm` provider (local OpenAI-compatible servers)        | Any non-empty value works for no-auth local servers                                                 |\n| `CURSOR_ACCESS_TOKEN`           | Cursor provider auth                             | Using Cursor provider                                          |                                                                                                     |\n| `AI_GATEWAY_API_KEY`            | Vercel AI Gateway auth                           | Using `vercel-ai-gateway` provider                             |                                                                                                     |\n| `CLOUDFLARE_AI_GATEWAY_API_KEY` | Cloudflare AI Gateway auth                       | Using `cloudflare-ai-gateway` provider                         | Base URL must be configured as `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic` |\n| `ALIBABA_CODING_PLAN_API_KEY`   | Alibaba Coding Plan auth                         | Using `alibaba-coding-plan` provider                           |                                                                                                     |\n| `DEEPSEEK_API_KEY`              | DeepSeek auth                                    | Using DeepSeek models                                          |                                                                                                     |\n| `KILO_API_KEY`                  | Kilo auth                                        | Using Kilo models                                              |                                                                                                     |\n| `OLLAMA_CLOUD_API_KEY`          | Ollama Cloud auth                                | Using `ollama-cloud` provider                                  |                                                                                                     |\n| `GITLAB_TOKEN`                  | GitLab Duo auth                                  | Using `gitlab-duo` provider                                    |                                                                                                     |\n\n### GitHub/Copilot token chains\n\n| Variable               | Used for                                         | Chain                                                |\n| ---------------------- | ------------------------------------------------ | ---------------------------------------------------- |\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth                     | `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` |\n| `GH_TOKEN`             | Copilot fallback; GitHub API auth in web scraper | In web scraper: `GITHUB_TOKEN` → `GH_TOKEN`          |\n| `GITHUB_TOKEN`         | Copilot fallback; GitHub API auth in web scraper | In web scraper: checked before `GH_TOKEN`            |\n\n### Auth broker / auth gateway (remote credential vault)\n\nWhen the broker is enabled, the local SQLite credential store is bypassed and all OAuth refresh / access tokens live on the broker host. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full protocol, CLI surface, and 5-min/15-s usage cache layering.\n\n| Variable                | Used for                                                                                          | Required when                                                                                                          | Notes / precedence                                                                                                                                                                                  |\n| ----------------------- | ------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `GJC_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`); selects broker mode      | Resolving credentials through a broker; also required by `gjc auth-gateway serve` (the gateway is itself a broker client) | Wins over `auth.broker.url` in `config.yml`. When set with no resolvable token, `resolveAuthBrokerConfig()` hard-errors instead of falling back to local SQLite.                                    |\n| `GJC_AUTH_BROKER_TOKEN` | Bearer token sent on every broker endpoint except `/v1/healthz`                                   | `GJC_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`     | Resolution: this env → `auth.broker.token` (`$ENV_NAME` indirection supported) → `<config-dir>/auth-broker.token` (mode `0600`). `<config-dir>` is `~/.gjc/` (respecting `GJC_CONFIG_DIR`).         |\n\nThe gateway has no dedicated env vars — it inherits `GJC_AUTH_BROKER_*`. Its own inbound bearer token lives at `<config-dir>/auth-gateway.token` and is managed via `gjc auth-gateway token`.\n\n---\n\n## 2) Provider-specific runtime configuration\n\n### Anthropic Foundry Gateway (Azure / enterprise proxy)\n\nWhen `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled, Anthropic requests switch to Foundry mode:\n\n- Base URL resolves from `FOUNDRY_BASE_URL` (fallback remains model/default base URL if unset).\n- API key resolution for provider `anthropic` becomes:\n  `ANTHROPIC_FOUNDRY_API_KEY` → `ANTHROPIC_OAUTH_TOKEN` → `ANTHROPIC_API_KEY`.\n- `ANTHROPIC_CUSTOM_HEADERS` is parsed as comma/newline-separated `key: value` pairs and merged into request headers.\n- TLS client/server material can be injected from env values:\n  `NODE_EXTRA_CA_CERTS`, `ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`.\n  Each accepts either:\n  - a filesystem path to PEM content, or\n  - inline PEM (including escaped `\\n` sequences).\n\n| Variable                    | Value type                                     | Behavior                                                                      |\n| --------------------------- | ---------------------------------------------- | ----------------------------------------------------------------------------- |\n| `ANTHROPIC_MODEL_CODE_USE_FOUNDRY`   | Boolean-like string (`1`, `true`, `yes`, `on`) | Enables Foundry mode for Anthropic provider                                   |\n| `FOUNDRY_BASE_URL`          | URL string                                     | Anthropic endpoint base URL in Foundry mode                                   |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Token string                                   | Used for `Authorization: Bearer <token>`                                      |\n| `ANTHROPIC_CUSTOM_HEADERS`  | Header list string                             | Extra headers; format `header-a: value, header-b: value` or newline-separated |\n| `NODE_EXTRA_CA_CERTS`       | PEM path or inline PEM                         | Extra CA chain for server certificate validation                              |\n| `ANTHROPIC_MODEL_CODE_CLIENT_CERT`   | PEM path or inline PEM                         | mTLS client certificate                                                       |\n| `ANTHROPIC_MODEL_CODE_CLIENT_KEY`    | PEM path or inline PEM                         | mTLS client private key (must be paired with cert)                            |\n\n### Amazon Bedrock\n\n| Variable                                                                        | Default / behavior                                                                            |\n| ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `AWS_REGION`                                                                    | Primary region source                                                                         |\n| `AWS_DEFAULT_REGION`                                                            | Fallback if `AWS_REGION` unset                                                                |\n| `AWS_PROFILE`                                                                   | Enables named profile auth path                                                               |\n| `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`                                   | Enables IAM key auth path                                                                     |\n| `AWS_BEARER_TOKEN_BEDROCK`                                                      | Enables bearer token auth path                                                                |\n| `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI` / `AWS_CONTAINER_CREDENTIALS_FULL_URI` | Enables ECS task credential path                                                              |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN`                                  | Enables web identity auth path                                                                |\n| `AWS_BEDROCK_SKIP_AUTH`                                                         | If `1`, injects dummy credentials (proxy/non-auth scenarios)                                  |\n| `AWS_BEDROCK_FORCE_HTTP1`                                                       | If `1`, forces Node HTTP/1 request handler                                                    |\n| `HTTPS_PROXY` / `HTTP_PROXY` / `ALL_PROXY`                                      | Routes Bedrock runtime and AWS SSO credential calls through the configured proxy using HTTP/1 |\n| `NO_PROXY`                                                                      | Excludes matching hosts from proxy routing when a proxy variable is configured                |\n\nRegion fallback in provider code: `options.region` → `AWS_REGION` → `AWS_DEFAULT_REGION` → `us-east-1`.\n\nCredential fallback order is static env (`AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY` plus optional `AWS_SESSION_TOKEN`), named profile / SSO / `credential_process`, then EC2 IMDSv2. `models.yml` Bedrock entries use `api: bedrock-converse-stream` and do not require `apiKey` or `apiKeyEnv` because the provider signs requests from this AWS chain.\n\n### Azure OpenAI Responses\n\n| Variable                           | Default / behavior                                                          |\n| ---------------------------------- | --------------------------------------------------------------------------- |\n| `AZURE_OPENAI_API_KEY`             | Required unless API key passed as option                                    |\n| `AZURE_OPENAI_API_VERSION`         | Default `v1`                                                                |\n| `AZURE_OPENAI_BASE_URL`            | Direct base URL override                                                    |\n| `AZURE_OPENAI_RESOURCE_NAME`       | Used to construct base URL: `https://<resource>.openai.azure.com/openai/v1` |\n| `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` | Optional mapping string: `modelId=deploymentName,model2=deployment2`        |\n\nBase URL resolution: option `azureBaseUrl` → env `AZURE_OPENAI_BASE_URL` → option/env resource name → `model.baseUrl`.\n\n### Model provider base URL overrides\n\nBuilt-in model provider base URLs resolve with this precedence:\n\n1. `models.yml` / model config provider `baseUrl`\n2. provider-specific base URL environment variable\n3. bundled provider default\n\nSupported aliases:\n\n| Provider | Variables |\n| --- | --- |\n| OpenAI | `OPENAI_BASE_URL` |\n| Anthropic | `ANTHROPIC_BASE_URL` |\n| Google Gemini | `GOOGLE_BASE_URL`, `GEMINI_BASE_URL` |\n| Google Antigravity | `GOOGLE_ANTIGRAVITY_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Gemini CLI | `GOOGLE_GEMINI_CLI_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Vertex | `GOOGLE_VERTEX_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Any provider id | derived `<PROVIDER_ID>_BASE_URL`, uppercased with non-alphanumerics converted to `_` (for example `my-proxy` → `MY_PROXY_BASE_URL`) |\n\nOpenAI-compatible proxy note: the built-in `openai` provider keeps its bundled API transport (`openai-responses`). Setting `OPENAI_BASE_URL` changes the host but still calls `<baseUrl>/responses`. If your proxy only supports Chat Completions, configure a custom `models.yml` provider with `api: openai-completions` instead of using the built-in OpenAI provider override:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKey: OPENAI_API_KEY\n    api: openai-completions\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        api: openai-completions\n```\n\nFor OpenRouter traffic, GJC explicitly sends `User-Agent: Gajae-Code/<package version>` plus OpenRouter attribution headers. For the built-in OpenAI Responses transport and generic OpenAI-compatible Chat Completions transport, GJC passes model/provider headers through the OpenAI JavaScript SDK and does not set a GJC user-agent unless the provider-specific code adds one.\n\n### OpenAI-compatible proxy provider config\n\nFor OpenAI-compatible proxies that only implement Chat Completions, prefer a custom `models.yml` provider over `OPENAI_BASE_URL`:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        reasoning: false\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n```\n\n`models.yml` is strict: unsupported provider/model keys fail validation before the provider request is dispatched.\n\n### GJC workflow bridge commands\n\n`gjc ralplan`, `gjc deep-interview`, and `gjc state` are private runtime bridge commands. They require `GJC_RUNTIME_BINARY` (or legacy `GJC_LEGACY_RUNTIME_BINARY`) to point at the private runtime executable; public bundled workflow use remains through `/skill:ralplan` and `/skill:deep-interview` inside a GJC session.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_RUNTIME_BINARY` | Private runtime bridge binary for `gjc ralplan`, `gjc deep-interview`, and `gjc state` |\n| `GJC_LEGACY_RUNTIME_BINARY` | Legacy fallback bridge binary name |\n\n### Team tmux backend, dry-run, and state paths\n\n`gjc team ...` starts tmux worker panes from the current tmux-backed leader session. Start that leader with `gjc --tmux` first; `gjc team` intentionally does not create or attach the leader session itself.\n\n`gjc team ... --dry-run --json` creates the same machine-readable state tree as a team launch without starting tmux panes. By default that state is written under `<cwd>/.gjc/state/team/<team>/`; treat it as ephemeral smoke-test/review state. Do not commit generated `.gjc/state/team` contents. Remove the generated team directory after a dry-run when the harness no longer needs it.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_TEAM_STATE_ROOT` | Overrides the team state root (default `<cwd>/.gjc/state/team`) |\n| `GJC_TEAM_TMUX_COMMAND` | tmux binary/command override for team launch |\n| `GJC_TEAM_WORKER_COMMAND` | Worker GJC command override |\n| `GJC_TEAM_WORKER_CLI` | Team worker CLI selector; accepted values are `auto` or `gjc` |\n| `GJC_TEAM_WORKER_CLI_MAP` | Comma-separated worker CLI selector map; entries must be `auto` or `gjc` |\n\n### Google Vertex AI\n\n| Variable                         | Required?                      | Notes                                                                                                                     |\n| -------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |\n| `GOOGLE_CLOUD_PROJECT`           | Yes (unless passed in options) | Fallback: `GCLOUD_PROJECT`                                                                                                |\n| `GCLOUD_PROJECT`                 | Fallback                       | Used as alternate project ID source                                                                                       |\n| `GOOGLE_CLOUD_PROJECT_ID`        | OAuth login helper only        | Used by Gemini CLI OAuth project discovery                                                                                |\n| `GOOGLE_CLOUD_LOCATION`          | Yes (unless passed in options) | No default in provider                                                                                                    |\n| `GOOGLE_CLOUD_API_KEY`           | Conditional                    | Direct Vertex API-key auth; otherwise ADC fallback can authenticate when project and location are set                     |\n| `GOOGLE_APPLICATION_CREDENTIALS` | Conditional                    | If set, file must exist; otherwise ADC fallback path is checked (`~/.config/gcloud/application_default_credentials.json`) |\n\n### Kimi\n\n| Variable               | Default / behavior                                       |\n| ---------------------- | -------------------------------------------------------- |\n| `KIMI_CODE_OAUTH_HOST` | Primary OAuth host override                              |\n| `KIMI_OAUTH_HOST`      | Fallback OAuth host override                             |\n| `KIMI_CODE_BASE_URL`   | Overrides Kimi usage endpoint base URL (`usage/kimi.ts`) |\n\nOAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth.kimi.com`.\n\n### Gemini CLI compatibility\n\n| Variable                   | Default / behavior                                              |\n| -------------------------- | --------------------------------------------------------------- |\n| `GJC_AI_GEMINI_CLI_VERSION` | Overrides Gemini CLI user-agent version tag (`0.35.3` if unset) |\n\n### OpenAI code provider responses (feature/debug controls)\n\n| Variable                             | Behavior                                             |\n| ------------------------------------ | ---------------------------------------------------- |\n| `GJC_OPENAI_CODE_DEBUG`                     | `1`/`true` enables OpenAI code provider debug logging      |\n| `GJC_OPENAI_CODE_WEBSOCKET`                 | `1`/`true` enables websocket transport preference    |\n| `GJC_OPENAI_CODE_WEBSOCKET_V2`              | `1`/`true` enables websocket v2 path                 |\n| `GJC_OPENAI_CODE_WEBSOCKET_IDLE_TIMEOUT_MS` | Positive integer override (default 300000)           |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_BUDGET`    | Non-negative integer override (default 5)            |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_DELAY_MS`  | Positive integer base backoff override (default 500) |\n| `GJC_OPENAI_STREAM_IDLE_TIMEOUT_MS`   | Positive integer OpenAI stream idle timeout override |\n\n### Cursor provider debug\n\n| Variable           | Behavior                                                                 |\n| ------------------ | ------------------------------------------------------------------------ |\n| `DEBUG_CURSOR`     | Enables provider debug logs; `2`/`verbose` for detailed payload snippets |\n| `DEBUG_CURSOR_LOG` | Optional file path for JSONL debug log output                            |\n\n### Prompt cache compatibility switch\n\n| Variable             | Behavior                                                                                                          |\n| -------------------- | ----------------------------------------------------------------------------------------------------------------- |\n| `GJC_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution) |\n\n---\n\n## 3) Web search subsystem\n\n### Search provider credentials\n\n| Variable                                            | Used by                                                       |\n| --------------------------------------------------- | ------------------------------------------------------------- |\n| `EXA_API_KEY`                                       | Exa search provider                         |\n| `BRAVE_API_KEY`                                     | Brave search provider                                         |\n| `PERPLEXITY_API_KEY`                                | Perplexity search provider API-key mode                       |\n| `PERPLEXITY_COOKIES`                                | Perplexity cookie-auth search mode                            |\n| `TAVILY_API_KEY`                                    | Tavily search provider                                        |\n| `ZAI_API_KEY`                                       | z.ai search provider (also checks stored OAuth in `agent.db`) |\n| `OPENAI_API_KEY` / OpenAI code OAuth in DB                | OpenAI code search provider availability/auth                       |\n| `GJC_OPENAI_CODE_WEB_SEARCH_MODEL`                         | OpenAI code search provider model override                          |\n| `MOONSHOT_SEARCH_API_KEY` / `KIMI_SEARCH_API_KEY`   | Kimi/Moonshot search provider env auth                        |\n| `MOONSHOT_SEARCH_BASE_URL` / `KIMI_SEARCH_BASE_URL` | Kimi/Moonshot search endpoint override                        |\n| `KAGI_API_KEY`                                      | Kagi search provider                                          |\n| `JINA_API_KEY`                                      | Jina search provider                                          |\n| `PARALLEL_API_KEY`                                  | Parallel search provider                                      |\n| `SEARXNG_ENDPOINT`, `SEARXNG_TOKEN`                 | SearXNG endpoint and optional bearer token                    |\n| `SEARXNG_BASIC_USERNAME`, `SEARXNG_BASIC_PASSWORD`  | SearXNG HTTP Basic Auth credentials                           |\n\nSearXNG also reads the equivalent `searxng.endpoint`, `searxng.token`, `searxng.basicUsername`, and `searxng.basicPassword` settings from `~/.gjc/agent/config.yml`; environment variables are fallbacks.\n\n### Anthropic web search auth chain\n\nAnthropic web search uses `findAnthropicAuth()` from `packages/ai/src/utils/anthropic-auth.ts` in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY` (+ optional `ANTHROPIC_SEARCH_BASE_URL`)\n2. `ANTHROPIC_FOUNDRY_API_KEY` when `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled\n3. Anthropic OAuth credentials from `agent.db` (must not expire within 5-minute buffer)\n4. Anthropic API-key credentials from `agent.db`\n5. Generic Anthropic env fallback: provider key (`ANTHROPIC_FOUNDRY_API_KEY` in Foundry mode, otherwise `ANTHROPIC_OAUTH_TOKEN`/`ANTHROPIC_API_KEY`) + optional `ANTHROPIC_BASE_URL` (`FOUNDRY_BASE_URL` when Foundry mode is enabled)\n\nRelated vars:\n\n| Variable                    | Default / behavior                                   |\n| --------------------------- | ---------------------------------------------------- |\n| `ANTHROPIC_SEARCH_API_KEY`  | Highest-priority explicit search key                 |\n| `ANTHROPIC_SEARCH_BASE_URL` | Defaults to `https://api.anthropic.com` when omitted |\n| `ANTHROPIC_SEARCH_MODEL`    | Defaults to `anthropic-model-haiku-4-5`                       |\n| `ANTHROPIC_BASE_URL`        | Generic fallback base URL for tier-4 auth path       |\n\n### Perplexity OAuth flow behavior flag\n\n| Variable            | Behavior                                                                        |\n| ------------------- | ------------------------------------------------------------------------------- |\n| `GJC_AUTH_NO_BORROW` | If set, disables macOS native-app token borrowing path in Perplexity login flow |\n\n---\n\n## 4) Python tooling and kernel runtime\n\n| Variable                  | Default / behavior                                                                                                  |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------- |\n| `GJC_PY`                   | Eval backend override: `0`/`bash`=JavaScript only, `1`/`py`=Python only, `mix`/`both`=both; invalid values ignored |\n| `GJC_PYTHON_SKIP_CHECK`    | If `1`, skips Python interpreter availability checks (subprocess runner still starts on demand)                     |\n| `GJC_PYTHON_INTEGRATION`   | If `1`, opts gated integration tests in (e.g. `python-runner.integration.test.ts`) into running against real Python |\n| `GJC_PYTHON_IPC_TRACE`     | If `1`, logs NDJSON frames exchanged with the Python runner subprocess                                              |\n| `VIRTUAL_ENV`             | Highest-priority venv path for Python runtime resolution                                                            |\n\nExtra conditional behavior:\n\n- If `BUN_ENV=test` or `NODE_ENV=test`, Python availability checks are treated as OK and warming is skipped.\n- Python env filtering denies common API keys and allows safe base vars + `LC_`, `XDG_`, `GJC_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable                     | Default / behavior                                                                                 |\n| ---------------------------- | -------------------------------------------------------------------------------------------------- |\n| `GJC_SMOL_MODEL`              | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence)                           |\n| `GJC_SLOW_MODEL`              | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence)                           |\n| `GJC_PLAN_MODEL`              | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence)                           |\n| `GJC_NO_TITLE`                | If set (any non-empty value), disables auto session title generation on first user message         |\n| `NULL_PROMPT`                | If `true`, system prompt builder returns empty string                                              |\n| `GJC_BLOCKED_AGENT`           | Blocks a specific subagent type in task tool                                                       |\n| `GJC_SUBPROCESS_CMD`          | Overrides subagent spawn command (`gjc` / `gjc.cmd` resolution bypass)                             |\n| `GJC_TASK_MAX_OUTPUT_BYTES`   | Max captured output bytes per subagent (default `500000`)                                          |\n| `GJC_TASK_MAX_OUTPUT_LINES`   | Max captured output lines per subagent (default `5000`)                                            |\n| `GJC_TIMING`                  | If set (any non-empty value), prints a hierarchical timing-span tree to **stderr** via `logger.printTimings()`. In interactive mode the tree prints once the agent is ready (before the TUI starts); in print mode it prints after the whole prompt batch completes. Print-mode prompts are wrapped in `print:prompt:initial` / `print:prompt:next` spans so each user message shows up as its own row. `GJC_TIMING=x` exits the process with code 0 right after printing in interactive mode (use to measure cold startup only). `GJC_TIMING=full` lists every module-load entry instead of just the top N. |\n| `GJC_PACKAGE_DIR`             | Overrides package asset base dir resolution (docs/examples/changelog path lookup)                  |\n| `GJC_DISABLE_LSPMUX`          | If `1`, disables lspmux detection/integration and forces direct LSP server spawning                |\n| `GJC_RPC_EMIT_TITLE`          | Boolean-like flag enabling title events in RPC mode                                                |\n| `SMITHERY_URL`               | Smithery web URL override (default `https://smithery.ai`)                                          |\n| `SMITHERY_API_URL`           | Smithery API base URL override (default `https://api.smithery.ai`)                                 |\n| `PUPPETEER_EXECUTABLE_PATH`  | Browser tool Chromium executable override                                                          |\n| `LM_STUDIO_BASE_URL`         | Default implicit LM Studio discovery base URL override (`http://127.0.0.1:1234/v1` if unset)       |\n| `OLLAMA_BASE_URL`            | Default implicit Ollama discovery base URL override (`http://127.0.0.1:11434` if unset)            |\n| `LLAMA_CPP_BASE_URL`         | Default implicit Llama.cpp discovery base URL override (`http://127.0.0.1:8080` if unset)          |\n| `GJC_EDIT_VARIANT`            | Forces edit tool variant when valid (`patch`, `replace`, `hashline`, `atom`, `vim`, `apply_patch`) |\n| `GJC_FORCE_IMAGE_PROTOCOL`    | Forces supported image protocol (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) where used            |\n| `GJC_ALLOW_SIXEL_PASSTHROUGH` | Allows SIXEL passthrough when `GJC_FORCE_IMAGE_PROTOCOL=sixel`                                      |\n| `GJC_NO_PTY`                  | If `1`, disables interactive PTY path for bash tool                                                |\n\n`GJC_NO_PTY` is also set internally when CLI `--no-pty` is used.\n\n---\n\n## 6) Storage and config root paths\n\nThese are consumed via `@gajae-code/utils/dirs` and affect where coding-agent stores data.\n\n| Variable              | Default / behavior                                                            |\n| --------------------- | ----------------------------------------------------------------------------- |\n| `GJC_CONFIG_DIR`       | Config root dirname under home (default `.gjc`)                               |\n| `GJC_CODING_AGENT_DIR` | Full override for agent directory (default `~/<GJC_CONFIG_DIR or .gjc>/agent`) |\n| `PWD`                 | Used when matching canonical current working directory in path helpers        |\n\n---\n\n## 7) Shell/tool execution environment\n\n(From `packages/utils/src/procmgr.ts` and coding-agent bash tool integration.)\n\n| Variable                   | Behavior                                                                       |\n| -------------------------- | ------------------------------------------------------------------------------ |\n| `GJC_BASH_NO_CI`            | Suppresses automatic `CI=true` injection into spawned shell env                |\n| `ANTHROPIC_MODEL_BASH_NO_CI`        | Legacy alias fallback for `GJC_BASH_NO_CI`                                      |\n| `GJC_BASH_NO_LOGIN`         | Disables login-shell mode; shell args become `['-c']` instead of `['-l','-c']` |\n| `ANTHROPIC_MODEL_BASH_NO_LOGIN`     | Legacy alias fallback for `GJC_BASH_NO_LOGIN`                                   |\n| `GJC_SHELL_PREFIX`          | Optional command prefix wrapper                                                |\n| `ANTHROPIC_MODEL_CODE_SHELL_PREFIX` | Legacy alias fallback for `GJC_SHELL_PREFIX`                                    |\n| `VISUAL`                   | Preferred external editor command                                              |\n| `EDITOR`                   | Fallback external editor command                                               |\n\nCurrent implementation: `GJC_BASH_NO_LOGIN`/`ANTHROPIC_MODEL_BASH_NO_LOGIN` are active; when either is set, `getShellArgs()` returns `['-c']`.\n\n---\n\n## 8) UI/theme/session detection (auto-detected env)\n\nThese are read as runtime signals; they are usually set by the terminal/OS rather than manually configured.\n\n| Variable                                                                                                           | Used for                                                  |\n| ------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------- |\n| `COLORTERM`, `TERM`, `WT_SESSION`                                                                                  | Color capability detection (theme color mode)             |\n| `COLORFGBG`                                                                                                        | Terminal background light/dark auto-detection             |\n| `TERM_PROGRAM`, `TERM_PROGRAM_VERSION`, `TERMINAL_EMULATOR`                                                        | Terminal identity in system prompt/context                |\n| `KDE_FULL_SESSION`, `XDG_CURRENT_DESKTOP`, `DESKTOP_SESSION`, `XDG_SESSION_DESKTOP`, `GDMSESSION`, `WINDOWMANAGER` | Desktop/window-manager detection in system prompt/context |\n| `KITTY_WINDOW_ID`, `TMUX_PANE`, `TERM_SESSION_ID`, `WT_SESSION`                                                    | Stable per-terminal session breadcrumb IDs                |\n| `SHELL`, `ComSpec`, `TERM_PROGRAM`, `TERM`                                                                         | System info diagnostics                                   |\n| `APPDATA`, `XDG_CONFIG_HOME`                                                                                       | lspmux config path resolution                             |\n| `HOME`                                                                                                             | Path shortening in command UI                         |\n\n---\n\n## 9) TUI runtime flags (shared package, affects coding-agent UX)\n\n| Variable                  | Behavior                                                                              |\n| ------------------------- | ------------------------------------------------------------------------------------- |\n| `GJC_NOTIFICATIONS`        | `off` / `0` / `false` suppress desktop notifications                                  |\n| `GJC_TUI_WRITE_LOG`        | If set, logs TUI writes to file                                                       |\n| `GJC_HARDWARE_CURSOR`      | If `1`, enables hardware cursor mode                                                  |\n| `GJC_CLEAR_ON_SHRINK`      | If `1`, clears empty rows when content shrinks                                        |\n| `GJC_DEBUG_REDRAW`         | If `1`, enables redraw debug logging                                                  |\n| `GJC_TUI_DEBUG`            | If `1`, enables deep TUI debug dump path                                              |\n| `GJC_FORCE_IMAGE_PROTOCOL` | Forces terminal image protocol detection (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) |\n\n---\n\n## 10) Commit generation controls\n\n| Variable                  | Behavior                                                            |\n| ------------------------- | ------------------------------------------------------------------- |\n| `GJC_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `GJC_COMMIT_NO_FALLBACK`   | If `true`, disables fallback when agent returns no proposal         |\n| `GJC_COMMIT_MAP_REDUCE`    | If `false`, disables map-reduce commit analysis path                |\n| `DEBUG`                   | If set, commit agent error stack traces are printed                 |\n\n---\n\n## 11) Bridge mode (`--mode bridge`)\n\nConsumed by `packages/coding-agent/src/modes/bridge/*`. The bridge is a\nnetwork-reachable control surface and is **secure-by-default**: it refuses to\nstart without TLS and a bearer token, and the 0.3.1 default endpoint matrix\nfail-closes session events, commands, controller ownership, UI responses, host\ntool results, and host URI results. See `docs/bridge.md` for protocol details.\n\n| Variable | Required | Default | Behavior |\n| --- | --- | --- | --- |\n| `GJC_BRIDGE_TOKEN` | Yes | — | Bearer token required on authenticated endpoints. **Secret — never commit.** |\n| `GJC_BRIDGE_TLS_CERT` | Yes | — | Path to the TLS certificate (PEM). Startup fails closed if cert/key are missing (TLS is mandatory, including loopback). |\n| `GJC_BRIDGE_TLS_KEY` | Yes | — | Path to the TLS private key (PEM). **Secret — never commit; `chmod 600`.** |\n| `GJC_BRIDGE_HOST` | No | `127.0.0.1` | Bind hostname. |\n| `GJC_BRIDGE_PORT` | No | `4077` | Bind port (1–65535). |\n| `GJC_BRIDGE_SCOPES` | No | `prompt` | Parsed for dormant command-surface compatibility. Valid scopes: `prompt`, `control`, `bash`, `export`, `session`, `model`, `message:read`, `host_tools`, `host_uri`, `admin`. The default endpoint matrix still advertises no accepted scopes and rejects commands before scope checks. |\n\nLocal development with a self-signed certificate must add the local CA to the\nclient trust store; there is no plaintext or certificate-verification-bypass mode.\n\n---\n\n## Security-sensitive variables\n\nTreat these as secrets; do not log or commit them:\n\n- Provider/API keys and OAuth/bearer credentials (all `*_API_KEY`, `*_TOKEN`, OAuth access/refresh tokens)\n- Cloud credentials (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS` path may expose service-account material)\n- Search/provider auth vars (`EXA_API_KEY`, `BRAVE_API_KEY`, `PERPLEXITY_API_KEY`, Anthropic search keys)\n- Foundry mTLS material (`ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`, `NODE_EXTRA_CA_CERTS` when it points to private CA bundles)\n- Bridge auth/TLS material (`GJC_BRIDGE_TOKEN` and the `GJC_BRIDGE_TLS_KEY` private key; never commit cert/key/token material)\n\nPython runtime also explicitly strips many common key vars before spawning kernel subprocesses (`packages/coding-agent/src/eval/py/runtime.ts`).\n",
+	"environment-variables.md": "# Environment Variables (Current Runtime Reference)\n\nThis reference is derived from current code paths in:\n\n- `packages/coding-agent/src/**`\n- `packages/ai/src/**` (provider/auth resolution used by coding-agent)\n- `packages/utils/src/**` and `packages/tui/src/**` where those vars directly affect coding-agent runtime\n\nIt documents only active behavior.\n\n## Resolution model and precedence\n\nMost runtime lookups use `$env` from `@gajae-code/utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Agent `.env` (`~/.gjc/agent/.env`, respecting `GJC_CONFIG_DIR` / `GJC_CODING_AGENT_DIR`) for keys not already set\n4. Config-root `.env` (`~/.gjc/.env`, respecting `GJC_CONFIG_DIR`) for keys not already set\n5. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule inside each `.env` file: `GJC_*` keys are mirrored to `GJC_*` keys in that parsed file.\n\n---\n\n## 1) Model/provider authentication\n\nThese are consumed via `getEnvApiKey()` (`packages/ai/src/stream.ts`) unless noted otherwise.\n\n### Core provider credentials\n\n| Variable                        | Used for                                         | Required when                                                  | Notes / precedence                                                                                  |\n| ------------------------------- | ------------------------------------------------ | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- |\n| `ANTHROPIC_OAUTH_TOKEN`         | Anthropic API auth                               | Using Anthropic with OAuth token auth                          | Takes precedence over `ANTHROPIC_API_KEY` for provider auth resolution                              |\n| `ANTHROPIC_API_KEY`             | Anthropic API auth                               | Using Anthropic without OAuth token                            | Fallback after `ANTHROPIC_OAUTH_TOKEN`                                                              |\n| `ANTHROPIC_FOUNDRY_API_KEY`     | Anthropic via Azure Foundry / enterprise gateway | `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` enabled                              | Takes precedence over `ANTHROPIC_OAUTH_TOKEN` and `ANTHROPIC_API_KEY` when Foundry mode is enabled  |\n| `OPENAI_API_KEY`                | OpenAI auth                                      | Using OpenAI-family providers without explicit apiKey argument | Used by OpenAI Completions/Responses providers                                                      |\n| `GEMINI_API_KEY`                | Google Gemini auth                               | Using `google` provider models                                 | Primary key for Gemini provider mapping                                                             |\n| `GOOGLE_API_KEY`                | Gemini image tool auth fallback                  | Using `gemini_image` tool without `GEMINI_API_KEY`             | Used by coding-agent image tool fallback path                                                       |\n| `GROQ_API_KEY`                  | Groq auth                                        | Using Groq models                                              |                                                                                                     |\n| `CEREBRAS_API_KEY`              | Cerebras auth                                    | Using Cerebras models                                          |                                                                                                     |\n| `FIREWORKS_API_KEY`             | Fireworks auth                                   | Using Fireworks models                                         |                                                                                                     |\n| `TOGETHER_API_KEY`              | Together auth                                    | Using `together` provider                                      |                                                                                                     |\n| `HUGGINGFACE_HUB_TOKEN`         | Hugging Face auth                                | Using `huggingface` provider                                   | Primary Hugging Face token env var                                                                  |\n| `HF_TOKEN`                      | Hugging Face auth                                | Using `huggingface` provider                                   | Fallback when `HUGGINGFACE_HUB_TOKEN` is unset                                                      |\n| `SYNTHETIC_API_KEY`             | Synthetic auth                                   | Using Synthetic models                                         |                                                                                                     |\n| `NVIDIA_API_KEY`                | NVIDIA auth                                      | Using `nvidia` provider                                        |                                                                                                     |\n| `NANO_GPT_API_KEY`              | NanoGPT auth                                     | Using `nanogpt` provider                                       |                                                                                                     |\n| `VENICE_API_KEY`                | Venice auth                                      | Using `venice` provider                                        |                                                                                                     |\n| `LITELLM_API_KEY`               | LiteLLM auth                                     | Using `litellm` provider                                       | OpenAI-compatible LiteLLM proxy key                                                                 |\n| `LM_STUDIO_API_KEY`             | LM Studio auth (optional)                        | Using `lm-studio` provider with authenticated hosts            | Local LM Studio usually runs without auth; any non-empty token works when a key is required         |\n| `OLLAMA_API_KEY`                | Ollama auth (optional)                           | Using `ollama` provider with authenticated hosts               | Local Ollama usually runs without auth; any non-empty token works when a key is required            |\n| `LLAMA_CPP_API_KEY`             | llama.cpp auth (optional)                        | Using `llama.cpp` provider with authenticated hosts            | Local llama.cpp usually runs without auth; any non-empty token works when a key is configured       |\n| `XIAOMI_API_KEY`                | Xiaomi MiMo auth                                 | Using `xiaomi` provider                                        |                                                                                                     |\n| `MOONSHOT_API_KEY`              | Moonshot auth                                    | Using `moonshot` provider                                      |                                                                                                     |\n| `XAI_API_KEY`                   | xAI auth                                         | Using xAI models                                               |                                                                                                     |\n| `OPENROUTER_API_KEY`            | OpenRouter auth                                  | Using OpenRouter models                                        | Also used by image tool when preferred/auto provider is OpenRouter                                  |\n| `MISTRAL_API_KEY`               | Mistral auth                                     | Using Mistral models                                           |                                                                                                     |\n| `ZAI_API_KEY`                   | z.ai auth                                        | Using z.ai models                                              | Also used by z.ai web search provider                                                               |\n| `MINIMAX_API_KEY`               | MiniMax auth                                     | Using `minimax` provider                                       |                                                                                                     |\n| `AZURE_OPENAI_API_KEY`          | Azure OpenAI auth                               | Using `azure-openai` / `azure-openai-responses` models         | Pair with `AZURE_OPENAI_BASE_URL` or `AZURE_OPENAI_RESOURCE_NAME`                                   |\n| `MINIMAX_CODE_API_KEY`          | MiniMax Code auth                                | Using `minimax-code` provider                                  |                                                                                                     |\n| `MINIMAX_CODE_CN_API_KEY`       | MiniMax Code CN auth                             | Using `minimax-code-cn` provider                               |                                                                                                     |\n| `OPENCODE_API_KEY`              | OpenCode auth                                    | Using `opencode-go` / `opencode-zen` models                    |                                                                                                     |\n| `QIANFAN_API_KEY`               | Qianfan auth                                     | Using `qianfan` provider                                       |                                                                                                     |\n| `QWEN_OAUTH_TOKEN`              | Qwen Portal auth                                 | Using `qwen-portal` with OAuth token                           | Takes precedence over `QWEN_PORTAL_API_KEY`                                                         |\n| `QWEN_PORTAL_API_KEY`           | Qwen Portal auth                                 | Using `qwen-portal` with API key                               | Fallback after `QWEN_OAUTH_TOKEN`                                                                   |\n| `ZENMUX_API_KEY`                | ZenMux auth                                      | Using `zenmux` provider                                        | Used for ZenMux OpenAI and Anthropic-compatible routes                                              |\n| `VLLM_API_KEY`                  | vLLM auth/discovery opt-in                       | Using `vllm` provider (local OpenAI-compatible servers)        | Any non-empty value works for no-auth local servers                                                 |\n| `CURSOR_ACCESS_TOKEN`           | Cursor provider auth                             | Using Cursor provider                                          |                                                                                                     |\n| `AI_GATEWAY_API_KEY`            | Vercel AI Gateway auth                           | Using `vercel-ai-gateway` provider                             |                                                                                                     |\n| `CLOUDFLARE_AI_GATEWAY_API_KEY` | Cloudflare AI Gateway auth                       | Using `cloudflare-ai-gateway` provider                         | Base URL must be configured as `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic` |\n| `ALIBABA_CODING_PLAN_API_KEY`   | Alibaba Coding Plan auth                         | Using `alibaba-coding-plan` provider                           |                                                                                                     |\n| `DEEPSEEK_API_KEY`              | DeepSeek auth                                    | Using DeepSeek models                                          |                                                                                                     |\n| `KILO_API_KEY`                  | Kilo auth                                        | Using Kilo models                                              |                                                                                                     |\n| `OLLAMA_CLOUD_API_KEY`          | Ollama Cloud auth                                | Using `ollama-cloud` provider                                  |                                                                                                     |\n| `GITLAB_TOKEN`                  | GitLab Duo auth                                  | Using `gitlab-duo` provider                                    |                                                                                                     |\n\n### GitHub/Copilot token chains\n\n| Variable               | Used for                                         | Chain                                                |\n| ---------------------- | ------------------------------------------------ | ---------------------------------------------------- |\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth                     | `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` |\n| `GH_TOKEN`             | Copilot fallback; GitHub API auth in web scraper | In web scraper: `GITHUB_TOKEN` → `GH_TOKEN`          |\n| `GITHUB_TOKEN`         | Copilot fallback; GitHub API auth in web scraper | In web scraper: checked before `GH_TOKEN`            |\n\n### Auth broker / auth gateway (remote credential vault)\n\nWhen the broker is enabled, the local SQLite credential store is bypassed and all OAuth refresh / access tokens live on the broker host. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full protocol, CLI surface, and 5-min/15-s usage cache layering.\n\n| Variable                | Used for                                                                                          | Required when                                                                                                          | Notes / precedence                                                                                                                                                                                  |\n| ----------------------- | ------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `GJC_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`); selects broker mode      | Resolving credentials through a broker; also required by `gjc auth-gateway serve` (the gateway is itself a broker client) | Wins over `auth.broker.url` in `config.yml`. When set with no resolvable token, `resolveAuthBrokerConfig()` hard-errors instead of falling back to local SQLite.                                    |\n| `GJC_AUTH_BROKER_TOKEN` | Bearer token sent on every broker endpoint except `/v1/healthz`                                   | `GJC_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`     | Resolution: this env → `auth.broker.token` (`$ENV_NAME` indirection supported) → `<config-dir>/auth-broker.token` (mode `0600`). `<config-dir>` is `~/.gjc/` (respecting `GJC_CONFIG_DIR`).         |\n\nThe gateway has no dedicated env vars — it inherits `GJC_AUTH_BROKER_*`. Its own inbound bearer token lives at `<config-dir>/auth-gateway.token` and is managed via `gjc auth-gateway token`.\n\n---\n\n## 2) Provider-specific runtime configuration\n\n### Anthropic Foundry Gateway (Azure / enterprise proxy)\n\nWhen `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled, Anthropic requests switch to Foundry mode:\n\n- Base URL resolves from `FOUNDRY_BASE_URL` (fallback remains model/default base URL if unset).\n- API key resolution for provider `anthropic` becomes:\n  `ANTHROPIC_FOUNDRY_API_KEY` → `ANTHROPIC_OAUTH_TOKEN` → `ANTHROPIC_API_KEY`.\n- `ANTHROPIC_CUSTOM_HEADERS` is parsed as comma/newline-separated `key: value` pairs and merged into request headers.\n- TLS client/server material can be injected from env values:\n  `NODE_EXTRA_CA_CERTS`, `ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`.\n  Each accepts either:\n  - a filesystem path to PEM content, or\n  - inline PEM (including escaped `\\n` sequences).\n\n| Variable                    | Value type                                     | Behavior                                                                      |\n| --------------------------- | ---------------------------------------------- | ----------------------------------------------------------------------------- |\n| `ANTHROPIC_MODEL_CODE_USE_FOUNDRY`   | Boolean-like string (`1`, `true`, `yes`, `on`) | Enables Foundry mode for Anthropic provider                                   |\n| `FOUNDRY_BASE_URL`          | URL string                                     | Anthropic endpoint base URL in Foundry mode                                   |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Token string                                   | Used for `Authorization: Bearer <token>`                                      |\n| `ANTHROPIC_CUSTOM_HEADERS`  | Header list string                             | Extra headers; format `header-a: value, header-b: value` or newline-separated |\n| `NODE_EXTRA_CA_CERTS`       | PEM path or inline PEM                         | Extra CA chain for server certificate validation                              |\n| `ANTHROPIC_MODEL_CODE_CLIENT_CERT`   | PEM path or inline PEM                         | mTLS client certificate                                                       |\n| `ANTHROPIC_MODEL_CODE_CLIENT_KEY`    | PEM path or inline PEM                         | mTLS client private key (must be paired with cert)                            |\n\n### Amazon Bedrock\n\n| Variable                                                                        | Default / behavior                                                                            |\n| ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `AWS_REGION`                                                                    | Primary region source                                                                         |\n| `AWS_DEFAULT_REGION`                                                            | Fallback if `AWS_REGION` unset                                                                |\n| `AWS_PROFILE`                                                                   | Enables named profile auth path                                                               |\n| `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`                                   | Enables IAM key auth path                                                                     |\n| `AWS_BEARER_TOKEN_BEDROCK`                                                      | Enables bearer token auth path                                                                |\n| `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI` / `AWS_CONTAINER_CREDENTIALS_FULL_URI` | Enables ECS task credential path                                                              |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN`                                  | Enables web identity auth path                                                                |\n| `AWS_BEDROCK_SKIP_AUTH`                                                         | If `1`, injects dummy credentials (proxy/non-auth scenarios)                                  |\n| `AWS_BEDROCK_FORCE_HTTP1`                                                       | If `1`, forces Node HTTP/1 request handler                                                    |\n| `HTTPS_PROXY` / `HTTP_PROXY` / `ALL_PROXY`                                      | Routes Bedrock runtime and AWS SSO credential calls through the configured proxy using HTTP/1 |\n| `NO_PROXY`                                                                      | Excludes matching hosts from proxy routing when a proxy variable is configured                |\n\nRegion fallback in provider code: `options.region` → `AWS_REGION` → `AWS_DEFAULT_REGION` → `us-east-1`.\n\nCredential fallback order is static env (`AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY` plus optional `AWS_SESSION_TOKEN`), named profile / SSO / `credential_process`, then EC2 IMDSv2. `models.yml` Bedrock entries use `api: bedrock-converse-stream` and do not require `apiKey` or `apiKeyEnv` because the provider signs requests from this AWS chain.\n\n### Azure OpenAI Responses\n\n| Variable                           | Default / behavior                                                          |\n| ---------------------------------- | --------------------------------------------------------------------------- |\n| `AZURE_OPENAI_API_KEY`             | Required unless API key passed as option                                    |\n| `AZURE_OPENAI_API_VERSION`         | Default `v1`                                                                |\n| `AZURE_OPENAI_BASE_URL`            | Direct base URL override                                                    |\n| `AZURE_OPENAI_RESOURCE_NAME`       | Used to construct base URL: `https://<resource>.openai.azure.com/openai/v1` |\n| `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` | Optional mapping string: `modelId=deploymentName,model2=deployment2`        |\n\nBase URL resolution: option `azureBaseUrl` → env `AZURE_OPENAI_BASE_URL` → option/env resource name → `model.baseUrl`.\n\n### Model provider base URL overrides\n\nBuilt-in model provider base URLs resolve with this precedence:\n\n1. `models.yml` / model config provider `baseUrl`\n2. provider-specific base URL environment variable\n3. bundled provider default\n\nSupported aliases:\n\n| Provider | Variables |\n| --- | --- |\n| OpenAI | `OPENAI_BASE_URL` |\n| Anthropic | `ANTHROPIC_BASE_URL` |\n| Google Gemini | `GOOGLE_BASE_URL`, `GEMINI_BASE_URL` |\n| Google Antigravity | `GOOGLE_ANTIGRAVITY_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Gemini CLI | `GOOGLE_GEMINI_CLI_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Vertex | `GOOGLE_VERTEX_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Any provider id | derived `<PROVIDER_ID>_BASE_URL`, uppercased with non-alphanumerics converted to `_` (for example `my-proxy` → `MY_PROXY_BASE_URL`) |\n\nOpenAI-compatible proxy note: the built-in `openai` provider keeps its bundled API transport (`openai-responses`). Setting `OPENAI_BASE_URL` changes the host but still calls `<baseUrl>/responses`. If your proxy only supports Chat Completions, configure a custom `models.yml` provider with `api: openai-completions` instead of using the built-in OpenAI provider override:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKey: OPENAI_API_KEY\n    api: openai-completions\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        api: openai-completions\n```\n\nFor OpenRouter traffic, GJC explicitly sends `User-Agent: Gajae-Code/<package version>` plus OpenRouter attribution headers. For the built-in OpenAI Responses transport and generic OpenAI-compatible Chat Completions transport, GJC passes model/provider headers through the OpenAI JavaScript SDK and does not set a GJC user-agent unless the provider-specific code adds one.\n\n### OpenAI-compatible proxy provider config\n\nFor OpenAI-compatible proxies that only implement Chat Completions, prefer a custom `models.yml` provider over `OPENAI_BASE_URL`:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        reasoning: false\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n```\n\n`models.yml` is strict: unsupported provider/model keys fail validation before the provider request is dispatched.\n\n### GJC workflow bridge commands\n\n`gjc ralplan`, `gjc deep-interview`, and `gjc state` are private runtime bridge commands. They require `GJC_RUNTIME_BINARY` (or legacy `GJC_LEGACY_RUNTIME_BINARY`) to point at the private runtime executable; public bundled workflow use remains through `/skill:ralplan` and `/skill:deep-interview` inside a GJC session.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_RUNTIME_BINARY` | Private runtime bridge binary for `gjc ralplan`, `gjc deep-interview`, and `gjc state` |\n| `GJC_LEGACY_RUNTIME_BINARY` | Legacy fallback bridge binary name |\n\n### Team tmux backend, dry-run, and state paths\n\n`gjc team ...` starts tmux worker panes from the current tmux-backed leader session. Start that leader with `gjc --tmux` first; `gjc team` intentionally does not create or attach the leader session itself.\n\n`gjc team ... --dry-run --json` creates the same machine-readable state tree as a team launch without starting tmux panes. By default that state is written under `<cwd>/.gjc/state/team/<team>/`; treat it as ephemeral smoke-test/review state. Do not commit generated `.gjc/state/team` contents. Remove the generated team directory after a dry-run when the harness no longer needs it.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_TEAM_STATE_ROOT` | Overrides the team state root (default `<cwd>/.gjc/state/team`) |\n| `GJC_TEAM_TMUX_COMMAND` | tmux binary/command override for team launch |\n| `GJC_TEAM_WORKER_COMMAND` | Worker GJC command override |\n| `GJC_TEAM_WORKER_CLI` | Team worker CLI selector; accepted values are `auto` or `gjc` |\n| `GJC_TEAM_WORKER_CLI_MAP` | Comma-separated worker CLI selector map; entries must be `auto` or `gjc` |\n\n### Hermes MCP bridge\n\n`gjc mcp-serve coordinator` exposes a GJC-native outward MCP bridge for Hermes-style coordinators. `gjc mcp-serve hermes` is a compatibility alias for the same bridge. The bridge is read-only by default and fails closed until roots and mutation classes are explicitly configured.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_COORDINATOR_MCP_WORKDIR_ROOTS` | Required allowlist for workdir and artifact paths. `gjc setup hermes` renders absolute normalized paths joined with the platform path delimiter (`:` on POSIX, `;` on Windows). The bridge parser also accepts commas, semicolons, and newlines for legacy manual configs. |\n| `GJC_COORDINATOR_MCP_MUTATIONS` | Enables mutating tool classes as a comma-separated list (`sessions`, `questions`, `reports`) or `all`. `sessions` covers session startup, prompt delivery, durable turn journal updates, queue, and force operations. Per-call `allow_mutation: true` is still required. |\n| `GJC_COORDINATOR_MCP_ARTIFACT_BYTE_CAP` | Max bytes returned by artifact reads (default `65536`, capped at `1048576`). |\n| `GJC_COORDINATOR_MCP_STATE_ROOT` | Bridge coordination state root (default `<cwd>/.gjc/state/coordinator-mcp`). |\n| `GJC_COORDINATOR_MCP_PROFILE` | Optional profile namespace for session/question/report state. Missing scope never widens to global session enumeration. |\n| `GJC_COORDINATOR_MCP_REPO` | Optional repo namespace for session/question/report state. Missing scope never widens to global session enumeration. |\n| `GJC_COORDINATOR_MCP_SESSION_COMMAND` | GJC-compatible command used by mutating session startup to launch a detached tmux session. `gjc setup hermes` renders this to `gjc --worktree` by default so Hermes-installed configs start real GJC work in a GJC-managed worktree while preserving GJC project/session resume identity. Explicit values are preserved as user intent. When manually omitted, mutating session startup fails closed unless a service adapter is injected. |\n| `GJC_COORDINATOR_MCP_SETUP_MANAGED_BY` | Marker written by `gjc setup hermes` for safe managed config updates. |\n| `GJC_COORDINATOR_MCP_SETUP_SCHEMA_VERSION` | Managed setup schema version written by `gjc setup hermes`. |\n| `GJC_COORDINATOR_MCP_SETUP_SIGNATURE` | Deterministic managed setup signature used to detect safe updates versus unmanaged conflicts. |\n\n### Google Vertex AI\n\n| Variable                         | Required?                      | Notes                                                                                                                     |\n| -------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |\n| `GOOGLE_CLOUD_PROJECT`           | Yes (unless passed in options) | Fallback: `GCLOUD_PROJECT`                                                                                                |\n| `GCLOUD_PROJECT`                 | Fallback                       | Used as alternate project ID source                                                                                       |\n| `GOOGLE_CLOUD_PROJECT_ID`        | OAuth login helper only        | Used by Gemini CLI OAuth project discovery                                                                                |\n| `GOOGLE_CLOUD_LOCATION`          | Yes (unless passed in options) | No default in provider                                                                                                    |\n| `GOOGLE_CLOUD_API_KEY`           | Conditional                    | Direct Vertex API-key auth; otherwise ADC fallback can authenticate when project and location are set                     |\n| `GOOGLE_APPLICATION_CREDENTIALS` | Conditional                    | If set, file must exist; otherwise ADC fallback path is checked (`~/.config/gcloud/application_default_credentials.json`) |\n\n### Kimi\n\n| Variable               | Default / behavior                                       |\n| ---------------------- | -------------------------------------------------------- |\n| `KIMI_CODE_OAUTH_HOST` | Primary OAuth host override                              |\n| `KIMI_OAUTH_HOST`      | Fallback OAuth host override                             |\n| `KIMI_CODE_BASE_URL`   | Overrides Kimi usage endpoint base URL (`usage/kimi.ts`) |\n\nOAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth.kimi.com`.\n\n### Gemini CLI compatibility\n\n| Variable                   | Default / behavior                                              |\n| -------------------------- | --------------------------------------------------------------- |\n| `GJC_AI_GEMINI_CLI_VERSION` | Overrides Gemini CLI user-agent version tag (`0.35.3` if unset) |\n\n### OpenAI code provider responses (feature/debug controls)\n\n| Variable                             | Behavior                                             |\n| ------------------------------------ | ---------------------------------------------------- |\n| `GJC_OPENAI_CODE_DEBUG`                     | `1`/`true` enables OpenAI code provider debug logging      |\n| `GJC_OPENAI_CODE_WEBSOCKET`                 | `1`/`true` enables websocket transport preference    |\n| `GJC_OPENAI_CODE_WEBSOCKET_V2`              | `1`/`true` enables websocket v2 path                 |\n| `GJC_OPENAI_CODE_WEBSOCKET_IDLE_TIMEOUT_MS` | Positive integer override (default 300000)           |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_BUDGET`    | Non-negative integer override (default 5)            |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_DELAY_MS`  | Positive integer base backoff override (default 500) |\n| `GJC_OPENAI_STREAM_IDLE_TIMEOUT_MS`   | Positive integer OpenAI stream idle timeout override |\n\n### Cursor provider debug\n\n| Variable           | Behavior                                                                 |\n| ------------------ | ------------------------------------------------------------------------ |\n| `DEBUG_CURSOR`     | Enables provider debug logs; `2`/`verbose` for detailed payload snippets |\n| `DEBUG_CURSOR_LOG` | Optional file path for JSONL debug log output                            |\n\n### Prompt cache compatibility switch\n\n| Variable             | Behavior                                                                                                          |\n| -------------------- | ----------------------------------------------------------------------------------------------------------------- |\n| `GJC_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution) |\n\n---\n\n## 3) Web search subsystem\n\n### Search provider credentials\n\n| Variable                                            | Used by                                                       |\n| --------------------------------------------------- | ------------------------------------------------------------- |\n| `EXA_API_KEY`                                       | Exa search provider                         |\n| `BRAVE_API_KEY`                                     | Brave search provider                                         |\n| `PERPLEXITY_API_KEY`                                | Perplexity search provider API-key mode                       |\n| `PERPLEXITY_COOKIES`                                | Perplexity cookie-auth search mode                            |\n| `TAVILY_API_KEY`                                    | Tavily search provider                                        |\n| `ZAI_API_KEY`                                       | z.ai search provider (also checks stored OAuth in `agent.db`) |\n| `OPENAI_API_KEY` / OpenAI code OAuth in DB                | OpenAI code search provider availability/auth                       |\n| `GJC_OPENAI_CODE_WEB_SEARCH_MODEL`                         | OpenAI code search provider model override                          |\n| `MOONSHOT_SEARCH_API_KEY` / `KIMI_SEARCH_API_KEY`   | Kimi/Moonshot search provider env auth                        |\n| `MOONSHOT_SEARCH_BASE_URL` / `KIMI_SEARCH_BASE_URL` | Kimi/Moonshot search endpoint override                        |\n| `KAGI_API_KEY`                                      | Kagi search provider                                          |\n| `JINA_API_KEY`                                      | Jina search provider                                          |\n| `PARALLEL_API_KEY`                                  | Parallel search provider                                      |\n| `SEARXNG_ENDPOINT`, `SEARXNG_TOKEN`                 | SearXNG endpoint and optional bearer token                    |\n| `SEARXNG_BASIC_USERNAME`, `SEARXNG_BASIC_PASSWORD`  | SearXNG HTTP Basic Auth credentials                           |\n\nSearXNG also reads the equivalent `searxng.endpoint`, `searxng.token`, `searxng.basicUsername`, and `searxng.basicPassword` settings from `~/.gjc/agent/config.yml`; environment variables are fallbacks.\n\n### Anthropic web search auth chain\n\nAnthropic web search uses `findAnthropicAuth()` from `packages/ai/src/utils/anthropic-auth.ts` in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY` (+ optional `ANTHROPIC_SEARCH_BASE_URL`)\n2. `ANTHROPIC_FOUNDRY_API_KEY` when `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled\n3. Anthropic OAuth credentials from `agent.db` (must not expire within 5-minute buffer)\n4. Anthropic API-key credentials from `agent.db`\n5. Generic Anthropic env fallback: provider key (`ANTHROPIC_FOUNDRY_API_KEY` in Foundry mode, otherwise `ANTHROPIC_OAUTH_TOKEN`/`ANTHROPIC_API_KEY`) + optional `ANTHROPIC_BASE_URL` (`FOUNDRY_BASE_URL` when Foundry mode is enabled)\n\nRelated vars:\n\n| Variable                    | Default / behavior                                   |\n| --------------------------- | ---------------------------------------------------- |\n| `ANTHROPIC_SEARCH_API_KEY`  | Highest-priority explicit search key                 |\n| `ANTHROPIC_SEARCH_BASE_URL` | Defaults to `https://api.anthropic.com` when omitted |\n| `ANTHROPIC_SEARCH_MODEL`    | Defaults to `anthropic-model-haiku-4-5`                       |\n| `ANTHROPIC_BASE_URL`        | Generic fallback base URL for tier-4 auth path       |\n\n### Perplexity OAuth flow behavior flag\n\n| Variable            | Behavior                                                                        |\n| ------------------- | ------------------------------------------------------------------------------- |\n| `GJC_AUTH_NO_BORROW` | If set, disables macOS native-app token borrowing path in Perplexity login flow |\n\n---\n\n## 4) Python tooling and kernel runtime\n\n| Variable                  | Default / behavior                                                                                                  |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------- |\n| `GJC_PY`                   | Eval backend override: `0`/`bash`=JavaScript only, `1`/`py`=Python only, `mix`/`both`=both; invalid values ignored |\n| `GJC_PYTHON_SKIP_CHECK`    | If `1`, skips Python interpreter availability checks (subprocess runner still starts on demand)                     |\n| `GJC_PYTHON_INTEGRATION`   | If `1`, opts gated integration tests in (e.g. `python-runner.integration.test.ts`) into running against real Python |\n| `GJC_PYTHON_IPC_TRACE`     | If `1`, logs NDJSON frames exchanged with the Python runner subprocess                                              |\n| `VIRTUAL_ENV`             | Highest-priority venv path for Python runtime resolution                                                            |\n\nExtra conditional behavior:\n\n- If `BUN_ENV=test` or `NODE_ENV=test`, Python availability checks are treated as OK and warming is skipped.\n- Python env filtering denies common API keys and allows safe base vars + `LC_`, `XDG_`, `GJC_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable                     | Default / behavior                                                                                 |\n| ---------------------------- | -------------------------------------------------------------------------------------------------- |\n| `GJC_SMOL_MODEL`              | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence)                           |\n| `GJC_SLOW_MODEL`              | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence)                           |\n| `GJC_PLAN_MODEL`              | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence)                           |\n| `GJC_NO_TITLE`                | If set (any non-empty value), disables auto session title generation on first user message         |\n| `NULL_PROMPT`                | If `true`, system prompt builder returns empty string                                              |\n| `GJC_BLOCKED_AGENT`           | Blocks a specific subagent type in task tool                                                       |\n| `GJC_SUBPROCESS_CMD`          | Overrides subagent spawn command (`gjc` / `gjc.cmd` resolution bypass)                             |\n| `GJC_TASK_MAX_OUTPUT_BYTES`   | Max captured output bytes per subagent (default `500000`)                                          |\n| `GJC_TASK_MAX_OUTPUT_LINES`   | Max captured output lines per subagent (default `5000`)                                            |\n| `GJC_TIMING`                  | If set (any non-empty value), prints a hierarchical timing-span tree to **stderr** via `logger.printTimings()`. In interactive mode the tree prints once the agent is ready (before the TUI starts); in print mode it prints after the whole prompt batch completes. Print-mode prompts are wrapped in `print:prompt:initial` / `print:prompt:next` spans so each user message shows up as its own row. `GJC_TIMING=x` exits the process with code 0 right after printing in interactive mode (use to measure cold startup only). `GJC_TIMING=full` lists every module-load entry instead of just the top N. |\n| `GJC_PACKAGE_DIR`             | Overrides package asset base dir resolution (docs/examples/changelog path lookup)                  |\n| `GJC_DISABLE_LSPMUX`          | If `1`, disables lspmux detection/integration and forces direct LSP server spawning                |\n| `GJC_RPC_EMIT_TITLE`          | Boolean-like flag enabling title events in RPC mode                                                |\n| `SMITHERY_URL`               | Smithery web URL override (default `https://smithery.ai`)                                          |\n| `SMITHERY_API_URL`           | Smithery API base URL override (default `https://api.smithery.ai`)                                 |\n| `PUPPETEER_EXECUTABLE_PATH`  | Browser tool Chromium executable override                                                          |\n| `LM_STUDIO_BASE_URL`         | Default implicit LM Studio discovery base URL override (`http://127.0.0.1:1234/v1` if unset)       |\n| `OLLAMA_BASE_URL`            | Default implicit Ollama discovery base URL override (`http://127.0.0.1:11434` if unset)            |\n| `LLAMA_CPP_BASE_URL`         | Default implicit Llama.cpp discovery base URL override (`http://127.0.0.1:8080` if unset)          |\n| `GJC_EDIT_VARIANT`            | Forces edit tool variant when valid (`patch`, `replace`, `hashline`, `atom`, `vim`, `apply_patch`) |\n| `GJC_FORCE_IMAGE_PROTOCOL`    | Forces supported image protocol (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) where used            |\n| `GJC_ALLOW_SIXEL_PASSTHROUGH` | Allows SIXEL passthrough when `GJC_FORCE_IMAGE_PROTOCOL=sixel`                                      |\n| `GJC_NO_PTY`                  | If `1`, disables interactive PTY path for bash tool                                                |\n\n`GJC_NO_PTY` is also set internally when CLI `--no-pty` is used.\n\n---\n\n## 6) Storage and config root paths\n\nThese are consumed via `@gajae-code/utils/dirs` and affect where coding-agent stores data.\n\n| Variable              | Default / behavior                                                            |\n| --------------------- | ----------------------------------------------------------------------------- |\n| `GJC_CONFIG_DIR`       | Config root dirname under home (default `.gjc`)                               |\n| `GJC_CODING_AGENT_DIR` | Full override for agent directory (default `~/<GJC_CONFIG_DIR or .gjc>/agent`) |\n| `PWD`                 | Used when matching canonical current working directory in path helpers        |\n\n---\n\n## 7) Shell/tool execution environment\n\n(From `packages/utils/src/procmgr.ts` and coding-agent bash tool integration.)\n\n| Variable                   | Behavior                                                                       |\n| -------------------------- | ------------------------------------------------------------------------------ |\n| `GJC_BASH_NO_CI`            | Suppresses automatic `CI=true` injection into spawned shell env                |\n| `ANTHROPIC_MODEL_BASH_NO_CI`        | Legacy alias fallback for `GJC_BASH_NO_CI`                                      |\n| `GJC_BASH_NO_LOGIN`         | Disables login-shell mode; shell args become `['-c']` instead of `['-l','-c']` |\n| `ANTHROPIC_MODEL_BASH_NO_LOGIN`     | Legacy alias fallback for `GJC_BASH_NO_LOGIN`                                   |\n| `GJC_SHELL_PREFIX`          | Optional command prefix wrapper                                                |\n| `ANTHROPIC_MODEL_CODE_SHELL_PREFIX` | Legacy alias fallback for `GJC_SHELL_PREFIX`                                    |\n| `VISUAL`                   | Preferred external editor command                                              |\n| `EDITOR`                   | Fallback external editor command                                               |\n\nCurrent implementation: `GJC_BASH_NO_LOGIN`/`ANTHROPIC_MODEL_BASH_NO_LOGIN` are active; when either is set, `getShellArgs()` returns `['-c']`.\n\n---\n\n## 8) UI/theme/session detection (auto-detected env)\n\nThese are read as runtime signals; they are usually set by the terminal/OS rather than manually configured.\n\n| Variable                                                                                                           | Used for                                                  |\n| ------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------- |\n| `COLORTERM`, `TERM`, `WT_SESSION`                                                                                  | Color capability detection (theme color mode)             |\n| `COLORFGBG`                                                                                                        | Terminal background light/dark auto-detection             |\n| `TERM_PROGRAM`, `TERM_PROGRAM_VERSION`, `TERMINAL_EMULATOR`                                                        | Terminal identity in system prompt/context                |\n| `KDE_FULL_SESSION`, `XDG_CURRENT_DESKTOP`, `DESKTOP_SESSION`, `XDG_SESSION_DESKTOP`, `GDMSESSION`, `WINDOWMANAGER` | Desktop/window-manager detection in system prompt/context |\n| `KITTY_WINDOW_ID`, `TMUX_PANE`, `TERM_SESSION_ID`, `WT_SESSION`                                                    | Stable per-terminal session breadcrumb IDs                |\n| `SHELL`, `ComSpec`, `TERM_PROGRAM`, `TERM`                                                                         | System info diagnostics                                   |\n| `APPDATA`, `XDG_CONFIG_HOME`                                                                                       | lspmux config path resolution                             |\n| `HOME`                                                                                                             | Path shortening in command UI                         |\n\n---\n\n## 9) TUI runtime flags (shared package, affects coding-agent UX)\n\n| Variable                  | Behavior                                                                              |\n| ------------------------- | ------------------------------------------------------------------------------------- |\n| `GJC_NOTIFICATIONS`        | `off` / `0` / `false` suppress desktop notifications                                  |\n| `GJC_TUI_WRITE_LOG`        | If set, logs TUI writes to file                                                       |\n| `GJC_HARDWARE_CURSOR`      | If `1`, enables hardware cursor mode                                                  |\n| `GJC_CLEAR_ON_SHRINK`      | If `1`, clears empty rows when content shrinks                                        |\n| `GJC_DEBUG_REDRAW`         | If `1`, enables redraw debug logging                                                  |\n| `GJC_TUI_DEBUG`            | If `1`, enables deep TUI debug dump path                                              |\n| `GJC_FORCE_IMAGE_PROTOCOL` | Forces terminal image protocol detection (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) |\n\n---\n\n## 10) Commit generation controls\n\n| Variable                  | Behavior                                                            |\n| ------------------------- | ------------------------------------------------------------------- |\n| `GJC_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `GJC_COMMIT_NO_FALLBACK`   | If `true`, disables fallback when agent returns no proposal         |\n| `GJC_COMMIT_MAP_REDUCE`    | If `false`, disables map-reduce commit analysis path                |\n| `DEBUG`                   | If set, commit agent error stack traces are printed                 |\n\n---\n\n## 11) Bridge mode (`--mode bridge`)\n\nConsumed by `packages/coding-agent/src/modes/bridge/*`. The bridge is a\nnetwork-reachable control surface and is **secure-by-default**: it refuses to\nstart without TLS and a bearer token, and the 0.3.1 default endpoint matrix\nfail-closes session events, commands, controller ownership, UI responses, host\ntool results, and host URI results. See `docs/bridge.md` for protocol details.\n\n| Variable | Required | Default | Behavior |\n| --- | --- | --- | --- |\n| `GJC_BRIDGE_TOKEN` | Yes | — | Bearer token required on authenticated endpoints. **Secret — never commit.** |\n| `GJC_BRIDGE_TLS_CERT` | Yes | — | Path to the TLS certificate (PEM). Startup fails closed if cert/key are missing (TLS is mandatory, including loopback). |\n| `GJC_BRIDGE_TLS_KEY` | Yes | — | Path to the TLS private key (PEM). **Secret — never commit; `chmod 600`.** |\n| `GJC_BRIDGE_HOST` | No | `127.0.0.1` | Bind hostname. |\n| `GJC_BRIDGE_PORT` | No | `4077` | Bind port (1–65535). |\n| `GJC_BRIDGE_SCOPES` | No | `prompt` | Parsed for dormant command-surface compatibility. Valid scopes: `prompt`, `control`, `bash`, `export`, `session`, `model`, `message:read`, `host_tools`, `host_uri`, `admin`. The default endpoint matrix still advertises no accepted scopes and rejects commands before scope checks. |\n\nLocal development with a self-signed certificate must add the local CA to the\nclient trust store; there is no plaintext or certificate-verification-bypass mode.\n\n---\n\n## Security-sensitive variables\n\nTreat these as secrets; do not log or commit them:\n\n- Provider/API keys and OAuth/bearer credentials (all `*_API_KEY`, `*_TOKEN`, OAuth access/refresh tokens)\n- Cloud credentials (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS` path may expose service-account material)\n- Search/provider auth vars (`EXA_API_KEY`, `BRAVE_API_KEY`, `PERPLEXITY_API_KEY`, Anthropic search keys)\n- Foundry mTLS material (`ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`, `NODE_EXTRA_CA_CERTS` when it points to private CA bundles)\n- Bridge auth/TLS material (`GJC_BRIDGE_TOKEN` and the `GJC_BRIDGE_TLS_KEY` private key; never commit cert/key/token material)\n\nPython runtime also explicitly strips many common key vars before spawning kernel subprocesses (`packages/coding-agent/src/eval/py/runtime.ts`).\n",
 	"fs-scan-cache-architecture.md": "# Filesystem Scan Cache Architecture Contract\n\nThis document defines the current contract for the shared filesystem scan cache implemented in Rust (`crates/pi-natives/src/fs_cache.rs`) and consumed by native discovery/search APIs exposed to `packages/coding-agent`.\n\n## What this cache is\n\nThe cache stores full directory-scan entry lists (`GlobMatch[]`) keyed by scan scope and traversal policy, then lets higher-level operations (glob filtering, fuzzy scoring, grep file selection) run against those cached entries.\n\nPrimary goals:\n\n- avoid repeated filesystem walks for repeated discovery/search calls\n- keep consistency across `glob`, `fuzzyFind`, and `grep` when they share the same scan policy\n- allow explicit staleness recovery for empty results and explicit invalidation after file mutations\n\n## Ownership and public surface\n\n- Cache implementation and policy: `crates/pi-natives/src/fs_cache.rs`\n- Native consumers:\n  - `crates/pi-natives/src/glob.rs`\n  - `crates/pi-natives/src/fd.rs` (`fuzzyFind`)\n  - `crates/pi-natives/src/grep.rs`\n- JS binding/export:\n  - `packages/natives/src/glob/index.ts` (`invalidateFsScanCache`)\n  - `packages/natives/src/glob/types.ts`\n  - `packages/natives/src/grep/types.ts`\n- Coding-agent mutation invalidation helpers:\n  - `packages/coding-agent/src/tools/fs-cache-invalidation.ts`\n\n## Cache key partitioning (hard contract)\n\nEach entry is keyed by:\n\n- canonicalized `root` directory path\n- `include_hidden` boolean\n- `use_gitignore` boolean\n- `skip_node_modules` boolean\n\nImplications:\n\n- Hidden and non-hidden scans do **not** share entries.\n- Gitignore-respecting and ignore-disabled scans do **not** share entries.\n- Scans that prune `node_modules` do **not** share entries with scans that include it.\n- Consumers must pass stable semantics for hidden/gitignore/node_modules behavior; changing any flag creates a different cache partition.\n\n## Scan collection behavior\n\nCache population uses a deterministic walker (`ignore::WalkBuilder`) configured by `include_hidden`, `use_gitignore`, and `skip_node_modules`:\n\n- `follow_links(false)`\n- sorted by file path\n- `.git` is always skipped\n- `node_modules` is pruned at traversal time when `skip_node_modules=true`\n- entry file type + `mtime` are captured via `symlink_metadata`\n\nSearch roots are resolved by `resolve_search_path`:\n\n- relative paths are resolved against current cwd\n- target must be an existing directory\n- root is canonicalized when possible\n\n## Freshness and eviction policy\n\nGlobal policy (environment-overridable):\n\n- `FS_SCAN_CACHE_TTL_MS` (default `1000`)\n- `FS_SCAN_EMPTY_RECHECK_MS` (default `200`)\n- `FS_SCAN_CACHE_MAX_ENTRIES` (default `16`)\n\nBehavior:\n\n- `get_or_scan(...)`\n  - if TTL is `0`: bypass cache entirely, always fresh scan (`cache_age_ms = 0`)\n  - on cache hit within TTL: return cached entries + non-zero `cache_age_ms`\n  - on expired hit: evict key, rescan, store fresh entry\n- max entry enforcement is oldest-first eviction by `created_at`\n\n## Empty-result fast recheck (separate from normal hits)\n\nNormal cache hit:\n\n- a cache hit inside TTL returns cached entries and does nothing else.\n\nEmpty-result fast recheck:\n\n- this is a **caller-side** policy using `ScanResult.cache_age_ms`\n- if filtered/query result is empty and cached scan age is at least `empty_recheck_ms()`, caller performs one `force_rescan(...)` and retries\n- intended to reduce stale-negative results when files were recently added but cache is still within TTL\n\nCurrent consumers:\n\n- `glob`: rechecks when filtered matches are empty and scan age exceeds threshold\n- `fuzzyFind` (`fd.rs`): rechecks only when query is non-empty and scored matches are empty\n- `grep`: rechecks when selected candidate file list is empty\n\n## Consumer defaults and cache usage\n\nCache is opt-in on all exposed APIs (`cache?: boolean`, default `false`).\n\nCurrent defaults in native APIs:\n\n- `glob`: `hidden=false`, `gitignore=true`, `cache=false`, and `node_modules` included only when the pattern mentions `node_modules`\n- `fuzzyFind`: `hidden=false`, `gitignore=true`, `cache=false`, and `node_modules` is skipped\n- `grep`: `hidden=true`, `gitignore=true`, `cache=false`, and `node_modules` included only when the glob mentions `node_modules`\n\nCoding-agent callers today:\n\n- High-volume mention candidate discovery enables cache:\n  - `packages/coding-agent/src/utils/file-mentions.ts`\n  - profile: `hidden=true`, `gitignore=true`, `includeNodeModules=true`, `cache=true`\n- Tool-level `grep` integration currently disables scan cache (`cache: false`):\n  - `packages/coding-agent/src/tools/grep.ts`\n\n## Invalidation contract\n\nNative invalidation entrypoint:\n\n- `invalidateFsScanCache(path?: string)`\n  - with `path`: remove cache entries whose root is a prefix of target path\n  - without path: clear all scan cache entries\n\nPath handling details:\n\n- relative invalidation paths are resolved against cwd\n- invalidation attempts canonicalization\n- if target does not exist (e.g., delete), fallback canonicalizes parent and reattaches filename when possible\n- this preserves invalidation behavior for create/delete/rename where one side may not exist\n\n## Coding-agent mutation flow responsibilities\n\nCoding-agent code must invalidate after successful filesystem mutations.\n\nCentral helpers:\n\n- `invalidateFsScanAfterWrite(path)`\n- `invalidateFsScanAfterDelete(path)`\n- `invalidateFsScanAfterRename(oldPath, newPath)` (invalidates both sides when paths differ)\n\nCurrent mutation tool callsites:\n\n- `packages/coding-agent/src/tools/write.ts`\n- `packages/coding-agent/src/patch/index.ts` (hashline/patch/replace flows)\n\nRule: if a flow mutates filesystem content or location and bypasses these helpers, cache staleness bugs are expected.\n\n## Adding a new cache consumer safely\n\nWhen introducing cache use in a new scanner/search path:\n\n1. **Use stable scan policy inputs**\n   - decide hidden/gitignore/node_modules semantics first\n   - pass them consistently to `get_or_scan`/`force_rescan` so cache partitions are intentional\n\n2. **Treat cache data as pre-filtered only by traversal policy**\n   - apply tool-specific filtering (glob patterns, type filters, scoring) after retrieval\n   - never assume cached entries already reflect your higher-level filters\n\n3. **Implement empty-result fast recheck only for stale-negative risk**\n   - use `scan.cache_age_ms >= empty_recheck_ms()`\n   - retry once with `force_rescan(..., store=true, ...)`\n   - keep this path separate from normal cache-hit logic\n\n4. **Respect no-cache mode explicitly**\n   - when caller disables cache, call `force_rescan(..., store=false, ...)`\n   - do not populate shared cache in a no-cache request path\n\n5. **Wire mutation invalidation for any new write path**\n   - after successful write/edit/delete/rename, call the coding-agent invalidation helper\n   - for rename/move, invalidate both old and new paths\n\n6. **Do not add per-call TTL knobs**\n   - current contract is global policy only (env-configured), no per-request TTL override\n\n## Known boundaries\n\n- Cache scope is process-local in-memory (`DashMap`), not persisted across process restarts.\n- Cache stores scan entries, not final tool results.\n- `glob`/`fuzzyFind`/`grep` share scan entries only when key dimensions (`root`, `hidden`, `gitignore`, `skip_node_modules`) match.\n- `.git` is always excluded at scan collection time regardless of caller options.\n",
 	"gjc-dogfood-skill-template.md": "# GJC dogfood local skill template\n\nIssue #93 requested a gaebal-gajae/operator dogfood skill. The live issue has no comment approving a fifth bundled default workflow skill, so this stays a local template instead of changing the default workflow surface. Operators can copy it into a user or project override when they want GJC-first session guidance:\n\n```sh\nmkdir -p ~/.gjc/skills/gjc-dogfood\ncp docs/gjc-dogfood-skill-template.md ~/.gjc/skills/gjc-dogfood/SKILL.md\n```\n\nFor a single project, copy it to `<project>/.gjc/skills/gjc-dogfood/SKILL.md` instead. Do not commit that project `.gjc` copy unless the project explicitly wants a local override.\n\n---\nname: gjc-dogfood\ndescription: Use when running or reviewing work through GJC sessions, dogfooding Gajae-Code, or migrating an operator workflow from OMX to GJC.\n---\n\n# GJC Dogfood Operator Workflow\n\nUse GJC first for coding, review, planning, and follow-up sessions. Treat OMX as a fallback only when GJC is unavailable, broken, or missing a required capability.\n\n## Locate and launch GJC\n\n- Installed CLI: run `command -v gjc` and then launch with `gjc --tmux`.\n- Repository checkout: from the gajae-code repo, prefer `bun packages/coding-agent/src/cli.ts --tmux` when testing source changes before install.\n- Worktree isolation: for branch-specific work, launch from or point at the branch worktree with `gjc --tmux --worktree <path>`.\n- Name sessions explicitly with the project and issue, for example `gajae-code-93-dogfood-skill`, so tmux panes, logs, and exports remain traceable.\n\n## Start the session\n\n- Put git operations inside the GJC session: fetch, branch/worktree setup, focused commits, pushes, and PR creation should be visible in-session.\n- Submit the initial prompt with the issue URL, target branch, acceptance criteria, verification limits, and any existing plan/spec link.\n- Verify the prompt was accepted: the TUI should show the user prompt, an active assistant turn, or a tool/action request. If the session silently idles, resend once with a shorter prompt and capture the failure.\n- Verify working state before leaving the session unattended: confirm the target cwd/worktree, branch, and issue scope are visible in the transcript or command output.\n\n## During work\n\n- Keep session names and branch names issue-scoped.\n- Prefer GJC workflow skills only when they fit: `deep-interview` for unclear requirements, `ralplan` for planning, `ultragoal` for durable ledgers, and `team` for coordinated tmux execution.\n- Keep evidence in the session: issue reads, focused tests/checks, screenshots only when visual behavior matters, and PR URLs.\n- When GJC is weaker than OMX, finish the urgent work with the smallest safe fallback and file a gajae-code follow-up issue with the missing capability, exact command/session context, expected behavior, and evidence.\n\n## Fallback policy\n\nUse OMX or another operator path only when:\n\n- `gjc` cannot be located or launched after checking installed and repo-local commands;\n- authentication, model routing, tmux, or prompt submission is broken;\n- GJC lacks a required capability that OMX already has;\n- an urgent production/review deadline would be missed by debugging GJC first.\n\nRecord the fallback reason and create or link the gajae-code issue that would make GJC sufficient next time.\n\n## Evidence checklist\n\nReport:\n\n- project, issue, branch/worktree, and session name;\n- whether GJC was installed or repo-local;\n- prompt acceptance and working-state evidence;\n- git operations performed in-session;\n- focused verification commands and results;\n- PR/issue URLs;\n- follow-up gajae-code issues for any GJC gap or fallback.\n",
+	"grok-build-provider-design.md": "# Grok Build provider design\n\n## Status\n\nProposal for maintainer design review. This document intentionally does not add a bundled provider implementation. It records the product/API decisions that must be accepted before any Grok Build implementation PR should land.\n\nThis is not an authorization claim for xAI endpoints, not a final naming decision, not approval for a bundled-loading exception, and not trademark/display-name approval. Those items require explicit owner sign-off before implementation.\n\n## Required owner sign-off gates\n\nImplementation should remain blocked until the owner signs off on these gates:\n\n1. **Authorized use / ToS** — confirm that GJC may use `cli-chat-proxy.grok.com` and the xAI CLI OAuth public client from a third-party tool. A public OAuth client id is not proof that this use is authorized.\n2. **Bundled-loading trust boundary** — confirm whether a source-controlled bundled provider may load even when ordinary user extension discovery is disabled.\n3. **Public selector naming** — choose the stable provider selector prefix: `grok-cli`, `grok-build`, or another owner-selected id.\n4. **Trademark/display-name** — confirm whether GJC may present the provider/profile using `Grok Build` or should use a more neutral owner-approved label.\n\nIf gate 1 is not accepted, the Grok Build provider implementation should not ship against `cli-chat-proxy.grok.com`. The fallback direction would be a documented user-supplied xAI/API-key provider or a different officially authorized integration path.\n\n## Problem\n\nGJC can load third-party extensions, but the first-run interactive path needs a maintainer-owned decision before a bundled Grok Build provider can be accepted. The desired product flow is:\n\n```text\ngjc -> /login -> OAuth -> Grok Build -> browser xAI login -> /model -> <provider-id>/grok-composer-2.5-fast\n```\n\nThe previously proposed implementation touched bundled extension loading, OAuth registration, model profiles, vendor code, usage reporting, and tests in one PR. That is too much surface for review without first agreeing on the provider contract and the owner sign-off gates above.\n\n## Goals\n\n- Keep Grok Build, if accepted, as a bundled provider extension rather than a workflow skill.\n- Preserve the existing four bundled workflow skills and four role agents.\n- Define the `/login` OAuth contract for an owner-approved display name, with `Grok Build` only as a candidate label.\n- Define the `/model` contract for `grok-composer-2.5-fast` without committing to the final selector prefix before owner sign-off.\n- Define the guardrails for any bundled provider that loads while ordinary extension discovery is disabled.\n- Keep credentials in the existing auth storage path; no tokens or user env values are checked into the repo.\n- Keep implementation PRs small enough for independent review, rejection, or rollback.\n\n## Non-goals\n\n- No new workflow command or `/skill` surface.\n- No automatic installation from npm or remote code at runtime.\n- No direct `packages/ai/src/models.json` edits.\n- No broad model-profile reshuffle.\n- No provider-specific secrets in source.\n- No claim that xAI has authorized this endpoint/client usage without owner review.\n\n## Candidate provider contract\n\nThese are candidate values for owner review, not final commitments:\n\n| Field | Candidate value | Decision status | Notes |\n| --- | --- | --- | --- |\n| Public provider id | `grok-cli` or `grok-build` | **Owner decision required** | See naming section below. |\n| Display name | `Grok Build` or owner-selected label | **Owner decision required** | Name shown in `/login` and UI surfaces; see trademark/display-name section below. |\n| Default model id | `grok-composer-2.5-fast` | Proposed | Full selector depends on final provider id. |\n| Secondary model id | `grok-build` | Proposed | Candidate for executor/architect roles if a profile is accepted. |\n| Base URL | `https://cli-chat-proxy.grok.com/v1` | **Authorized-use sign-off required** | Undocumented/private-looking endpoint; do not ship without owner approval. |\n| OAuth issuer | `https://auth.x.ai` | **Authorized-use sign-off required** | OIDC discovery must validate xAI-owned HTTPS endpoints. |\n| OAuth callback | loopback `127.0.0.1` | Proposed | Uses PKCE + state validation. |\n| API adapter | `grok-cli-responses` | Proposed internal name | Provider-specific stream adapter; not a new generic API shape. |\n| Env bypass | `GROK_CLI_OAUTH_TOKEN` | Optional follow-up | Local bypass only; no refresh or discovery guarantees. |\n\n## Authorized-use and ToS caveat\n\n`cli-chat-proxy.grok.com` and the xAI CLI OAuth public client appear to be designed for xAI/Grok CLI traffic. Reusing them from GJC may be technically possible but still unauthorized or contrary to xAI terms.\n\nBefore implementation, the owner should explicitly decide one of:\n\n- **Accept** — proceed with this integration after reviewing the legal/product risk.\n- **Defer** — keep this design document only; no code ships until authorization is clarified.\n- **Reject** — do not integrate against `cli-chat-proxy.grok.com`; use only an official public API path.\n\nImplementation PRs must not describe the public client id as a secret, but they also must not present it as authorization. Tests should avoid real tokens and should not require an xAI account.\n\n## Trademark/display-name caveat\n\n`Grok` and `xAI` are third-party marks. `Grok Build` may also imply an official xAI/Grok product relationship even when the integration is third-party. Before implementation, the owner should explicitly choose one of:\n\n- **Use `Grok Build`** — acceptable as the user-facing provider/profile label after trademark/product-risk review.\n- **Use a neutral label** — for example `xAI Grok`, `Grok OAuth`, or another owner-selected name that avoids implying official endorsement.\n- **Avoid built-in branding** — keep any Grok-specific naming only in user-provided configuration until authorization/branding is clarified.\n\nImplementation PRs should avoid lock-in language such as \"official\" unless there is explicit authorization. UI labels, profile names, docs, tests, and screenshots must all use the owner-approved label consistently.\n\n## OAuth behavior\n\nIf authorized-use is accepted, the OAuth implementation should use the existing custom OAuth provider path:\n\n1. The chosen provider id registers an OAuth provider using the owner-approved display name.\n2. `/login` calls the existing auth storage login path for that provider.\n3. The provider opens an xAI authorization URL using OIDC discovery, PKCE, `state`, and a loopback callback.\n4. The callback exchanges the authorization code for access and refresh tokens.\n5. Credentials are stored by the existing auth storage code path.\n6. Refresh uses the stored refresh token and validates the token endpoint origin.\n\nSecurity constraints:\n\n- OIDC `authorization_endpoint` and `token_endpoint` must be HTTPS and under owner-approved xAI hosts.\n- The callback server binds to loopback by default.\n- The callback must reject state mismatches.\n- Access and refresh tokens must not be logged, rendered, committed, or included in tests.\n- Error messages may include status and provider error text, but not credential values.\n- Env overrides for base URL, scope, callback host, or client id must be treated as local developer/debug escape hatches, not default product behavior.\n\n## Bundled-loading trust boundary\n\nA bundled provider is different from ordinary user extension discovery, but loading it while `disableExtensionDiscovery: true` still expands the bootstrap trust boundary. Owner sign-off is required before implementation.\n\nMinimum guardrails if accepted:\n\n- Load only source-controlled, maintainer-reviewed bundled provider paths.\n- Use a static allowlist or exported enumerator; never scan arbitrary user directories for this path.\n- Do not install, fetch, or resolve remote package code at runtime.\n- Keep ordinary user extension discovery disabled when `disableExtensionDiscovery: true`; the exception is only for bundled provider defaults.\n- Add tests proving bundled providers load before model selection and caller-supplied `additionalExtensionPaths` still coexist.\n- Keep this bootstrap change separate from the Grok vendor implementation so it can be reviewed independently.\n\nAlternatives the owner may choose:\n\n- Do not load bundled providers when extension discovery is disabled; require explicit setup/defaults install.\n- Gate bundled provider loading behind a setting or compile-time default.\n- Allow bundled loading only in packaged builds, not arbitrary source checkouts.\n\n## Provider selector naming\n\nThe selector prefix is a stable user-facing contract and must be chosen before implementation.\n\n| Option | Example selector | Pros | Cons |\n| --- | --- | --- | --- |\n| `grok-cli` | `grok-cli/grok-composer-2.5-fast` | Matches the upstream CLI/proxy lineage and existing prototype. | User-facing name is less aligned with `Grok Build`; may expose implementation detail. |\n| `grok-build` | `grok-build/grok-composer-2.5-fast` | Matches UI label and requested product wording. | Diverges from existing prototype and env names; migration needed if prototypes used `grok-cli`. |\n| Owner-selected third id | `<id>/grok-composer-2.5-fast` | Lets maintainers align with broader provider taxonomy. | Requires updating all docs/tests before implementation. |\n\nUntil this is decided, implementation docs and PRs should use `<provider-id>` when describing the public selector. Internal adapter names may still use `grok-cli-responses` if maintainers accept that as an implementation detail.\n\n## Model/profile behavior\n\nModel registration should be provider-owned. If accepted, the provider should register at least:\n\n- `grok-composer-2.5-fast`\n- `grok-build`\n\nA built-in profile is optional and should be reviewed separately. If accepted, a candidate profile is:\n\n```text\ngrok-pro.default   -> <provider-id>/grok-composer-2.5-fast\ngrok-pro.planner   -> <provider-id>/grok-composer-2.5-fast\ngrok-pro.critic    -> <provider-id>/grok-composer-2.5-fast\ngrok-pro.executor  -> <provider-id>/grok-build\ngrok-pro.architect -> <provider-id>/grok-build\n```\n\nIf maintainers prefer not to add a built-in profile, the provider can still satisfy the core `/login` and `/model` flow through direct model selection.\n\n## Usage reporting behavior\n\nUsage reporting should be an optional follow-up after login/model support lands:\n\n- Provider id: the owner-selected `<provider-id>`.\n- Fetches usage with the effective OAuth access token.\n- Returns `null` when no token is available.\n- Does not require the usage provider for chat/model selection to work.\n- Should be skipped entirely if the authorized-use gate is not accepted.\n\n## Staged PR plan\n\n### PR 1: this design document\n\nPurpose: agree on caveats, owner sign-off gates, provider id, OAuth contract, bundled-loading trust boundary, model selector, security boundaries, and implementation split.\n\n### PR 2: bundled provider bootstrap contract\n\nSmall core change only, after owner sign-off on the bundled-loading gate:\n\n- Add a maintainer-owned way to enumerate bundled provider extension paths.\n- Load those paths during session/bootstrap only under the accepted guardrails.\n- Add tests proving bundled providers and caller-supplied extension paths coexist.\n\nNo Grok vendor implementation in this PR.\n\n### PR 3: Grok Build provider extension\n\nProvider implementation only, after owner sign-off on authorized use, public selector naming, and trademark/display-name:\n\n- Add bundled Grok Build provider source.\n- Register the chosen provider id, OAuth provider, and models.\n- Include sanitize and provider-specific stream handling.\n- Test `/login` provider registration and `grok-composer-2.5-fast` model availability.\n\n### PR 4: profile and model defaults\n\nOptional product-surface PR:\n\n- Add `grok-pro` only if maintainers accept a built-in profile.\n- Add model profile catalog tests.\n\n### PR 5: usage reporting\n\nOptional observability PR:\n\n- Add usage provider for the owner-selected provider id.\n- Add focused usage tests.\n\n## Acceptance criteria for the implementation series\n\n- Owner sign-off is recorded for authorized use, bundled loading, selector naming, and trademark/display-name before implementation lands.\n- Fresh checkout test proves `createAgentSession` registers the bundled provider under the accepted bootstrap rules.\n- `/login` includes the owner-approved display name for the owner-selected provider id.\n- `/model` includes `<provider-id>/grok-composer-2.5-fast`.\n- A real OAuth URL redirects to the owner-approved xAI account login page.\n- Third-party extension paths still load alongside bundled providers when configured.\n- Token values never appear in tests, logs, checked-in docs, or git history.\n\n## Open maintainer decisions\n\n- Is using `cli-chat-proxy.grok.com` plus the xAI CLI OAuth client from GJC authorized and acceptable for this project?\n- Should bundled provider defaults load while `disableExtensionDiscovery: true`, and under which guardrails?\n- Should the final public provider id be `grok-cli`, `grok-build`, or another id?\n- May GJC use `Grok Build` as the display/profile name, or should the integration use a neutral owner-selected label?\n- Should `grok-pro` be a built-in profile or documented as a user profile?\n- Should usage reporting be included in the initial provider PR or kept as a separate follow-up?",
 	"handoff-generation-pipeline.md": "# `/handoff` generation pipeline\n\nThis document describes how the coding-agent implements `/handoff`: trigger path, oneshot generation, session switch, context reinjection, persistence, and UI behavior.\n\n## Scope\n\nCovers:\n\n- Interactive `/handoff` command dispatch\n- `AgentSession.handoff()` lifecycle and state transitions\n- `generateHandoff(...)` request shape\n- How old/new sessions persist handoff data differently\n- UI behavior for success, cancel, and failure\n\nDoes not cover:\n\n- Generic tree navigation/branch internals\n- Non-handoff session commands (`/new`, `/fork`, `/resume`)\n\n## Implementation files\n\n- [`../src/modes/controllers/input-controller.ts`](../packages/coding-agent/src/modes/controllers/input-controller.ts)\n- [`../src/modes/controllers/command-controller.ts`](../packages/coding-agent/src/modes/controllers/command-controller.ts)\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`packages/agent/src/compaction/compaction.ts`](../packages/agent/src/compaction/compaction.ts)\n- [`../src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts)\n- [`../src/extensibility/slash-commands.ts`](../packages/coding-agent/src/extensibility/slash-commands.ts)\n\n## Trigger path\n\n1. `/handoff` is declared in builtin slash command metadata (`slash-commands.ts`) with optional inline hint: `[focus instructions]`.\n2. In interactive input handling (`InputController`), submit text matching `/handoff` or `/handoff ...` is intercepted before normal prompt submission.\n3. The editor is cleared and `handleHandoffCommand(customInstructions?)` is called.\n4. `CommandController.handleHandoffCommand` performs a preflight guard using current entries:\n   - Counts `type === \"message\"` entries.\n   - If `< 2`, it warns: `Nothing to hand off (no messages yet)` and returns.\n\nThe same minimum-content guard exists again inside `AgentSession.handoff()` and throws if violated. This duplicates safety at both UI and session layers.\n\n## End-to-end lifecycle\n\n### 1) Start handoff generation\n\n`AgentSession.handoff(customInstructions?)`:\n\n- Reads current branch entries (`sessionManager.getBranch()`).\n- Validates minimum message count (`>= 2`).\n- Creates `#handoffAbortController` and links any caller-provided abort signal to it.\n- Resolves the current model API key through `ModelRegistry`.\n- Calls `generateHandoff(...)` with:\n  - live agent messages (`agent.state.messages`),\n  - the current model and API key,\n  - the base system prompt (`#baseSystemPrompt`),\n  - the live tool array (`agent.state.tools`),\n  - optional focus instructions,\n  - coding-agent message conversion (`convertToLlm`),\n  - provider metadata and `initiatorOverride: \"agent\"`.\n\n`generateHandoff(...)` lives in `packages/agent/src/compaction/compaction.ts` next to summarization. It renders `packages/agent/src/compaction/prompts/handoff-document.md` via `renderHandoffPrompt(...)` with optional `additionalFocus`.\n\n### 2) Generate and capture output\n\n`generateHandoff(...)` converts the existing `AgentMessage[]` history to real LLM `Message[]` history, then appends one trailing agent-attributed `user` message containing the rendered handoff prompt.\n\nThe request uses `completeSimple(...)` directly:\n\n```ts\nawait completeSimple(\n  model,\n  {\n    systemPrompt,\n    messages: requestMessages,\n    tools,\n  },\n  {\n    apiKey,\n    signal,\n    reasoning: Effort.High,\n    toolChoice: \"none\",\n    initiatorOverride,\n    metadata,\n  },\n);\n```\n\nImportant generation properties:\n\n- The request preserves the live provider cache prefix by reusing the same system prompt, tool definitions, and real message history shape as the active agent.\n- The handoff instruction is a trailing `user` message, not a developer message, so the cached prefix remains aligned with the prior turn.\n- `toolChoice: \"none\"` prevents intentional tool dispatch.\n- The returned assistant content is filtered to text blocks and joined with `\\n`; stray tool-call blocks are ignored if a provider does not honor `toolChoice: \"none\"`.\n- `stopReason === \"error\"` throws a generation error.\n\nNo agent-loop events are used for capture. The handoff path no longer waits for `agent_end` and no longer scans the latest assistant message.\n\n### 3) Cancellation checks\n\nCancellation throws `Error(\"Handoff cancelled\")`; a completed generation with no text returns `undefined`.\n\n- caller signal aborts `#handoffAbortController`\n- `completeSimple(...)` receives the abort signal\n- aborted handoff signal or provider `AbortError` is normalized to `Error(\"Handoff cancelled\")`\n- empty generated text returns `undefined`\n\n`AgentSession.handoff()` always clears `#handoffAbortController` in `finally`.\n\n### 4) New session creation\n\nIf text was generated and not aborted:\n\n1. Flush current session writer (`sessionManager.flush()`).\n2. Cancel session-owned async jobs.\n3. Start a brand-new session with `parentSession` pointing at the previous session file when one exists.\n4. Reset in-memory agent state (`agent.reset()`).\n5. Rebind `agent.sessionId` to the new session id.\n6. Rekey/reset hindsight state for the new session.\n7. Clear queued context arrays (`#steeringMessages`, `#followUpMessages`, `#pendingNextTurnMessages`) and any scheduled hidden next-turn generation.\n8. Reset todo reminder counter.\n\n### 5) Handoff-context injection\n\nThe generated handoff document is wrapped by coding-agent session glue and appended to the new session as a `custom_message` entry:\n\n```text\n<handoff-context>\n...handoff text...\n</handoff-context>\n\nThe above is a handoff document from a previous session. Use this context to continue the work seamlessly.\n```\n\nInsertion call:\n\n```ts\nthis.sessionManager.appendCustomMessageEntry(\"handoff\", handoffContent, true, undefined, \"agent\");\n```\n\nSemantics:\n\n- `customType`: `\"handoff\"`\n- `display`: `true` (visible in TUI rebuild)\n- attribution: `\"agent\"`\n- Entry type: `custom_message` (participates in LLM context)\n\n### 6) Rebuild active agent context\n\nAfter injection:\n\n1. `buildDisplaySessionContext()` resolves message list for current leaf.\n2. `agent.replaceMessages(sessionContext.messages)` makes the injected handoff message active context.\n3. Todo phases are synchronized from the new branch.\n4. Method returns `{ document: handoffText, savedPath? }`.\n\nAt this point, the active LLM context in the new session contains the injected handoff message, not the old transcript.\n\n## Persistence model: old session vs new session\n\n### Old session\n\nHandoff generation is a oneshot request, not a visible agent turn. The generated handoff text is not appended to the old session as an assistant message.\n\nResult: the original session keeps its prior transcript unchanged except for data already persisted before handoff began.\n\n### New session\n\nAfter session reset, handoff is persisted as `custom_message` with `customType: \"handoff\"`.\n\n`buildSessionContext()` converts this entry into a runtime custom/user-context message via `createCustomMessage(...)`, so it is included in future prompts from the new session.\n\nAuto-triggered handoffs can additionally write a timestamped `handoff-*.md` artifact under the session artifacts directory when `compaction.handoffSaveToDisk` is enabled. Manual `/handoff` does not write that artifact.\n\n## Controller/UI behavior\n\n`CommandController.handleHandoffCommand` behavior:\n\n- Shows a status loader: `Generating handoff… (esc to cancel)`.\n- Calls `await session.handoff(customInstructions)`.\n- If result is `undefined`: `showError(\"Handoff cancelled\")`.\n- On success:\n  - `rebuildChatFromMessages()` (loads new session context, including injected handoff)\n  - invalidates status line and editor top border\n  - reloads todos\n  - appends success chat line: `New session started with handoff context`\n- On exception:\n  - if message is `\"Handoff cancelled\"` or error name is `AbortError`: `showError(\"Handoff cancelled\")`\n  - otherwise: `showError(\"Handoff failed: <message>\")`\n- Stops the loader, restores the previous Escape handler, and requests render at end.\n\nManual `/handoff` no longer streams the generated document into chat. A cancellable loader remains visible while the oneshot request runs, and the chat is rebuilt after generation completes.\n\n## Cancellation semantics\n\n### Session-level cancellation primitive\n\n`AgentSession` exposes:\n\n- `abortHandoff()` → aborts `#handoffAbortController`\n- `isGeneratingHandoff` → true while controller exists\n\nWhen this abort path is used, the abort signal is passed to `completeSimple(...)`; `handoff()` normalizes the cancellation to `Error(\"Handoff cancelled\")`, and command controller maps it to cancellation UI.\n\n### Interactive `/handoff` path\n\nThe command controller installs a temporary Escape handler for `/handoff` while the loader is visible. Pressing Escape calls `session.abortHandoff()`, which aborts the `completeSimple(...)` request through `#handoffAbortController`.\n\n## Aborted vs failed handoff\n\nCurrent UI classification:\n\n- **Aborted/cancelled**\n  - `abortHandoff()` path triggers `\"Handoff cancelled\"`, or\n  - thrown `AbortError`\n  - UI shows `Handoff cancelled`\n- **Failed**\n  - any other thrown error from `handoff()` / `generateHandoff()` / provider request path\n  - UI shows `Handoff failed: ...`\n\nAdditional nuance: if generation completes but no text is returned, `handoff()` returns `undefined` and controller currently reports **cancelled**, not **failed**.\n\n## Short-session and minimum-content guardrails\n\nTwo guards prevent low-signal handoffs:\n\n- UI layer (`handleHandoffCommand`): warns and returns early for `< 2` message entries\n- Session layer (`handoff()`): throws the same condition as an error\n\nThis avoids creating a new session with empty/near-empty handoff context.\n\n## State transition summary\n\nHigh-level state flow:\n\n1. Interactive slash command intercepted.\n2. Preflight message-count guard.\n3. `#handoffAbortController` created (`isGeneratingHandoff = true`).\n4. `generateHandoff(...)` issues one `completeSimple(...)` request with live system prompt, tools, message history, and trailing handoff prompt.\n5. Assistant response text blocks are joined; tool-call blocks are discarded.\n6. If missing text → return `undefined`; if aborted → cancellation error path.\n7. If present:\n   - flush old session\n   - cancel async jobs\n   - create new empty session with previous session as parent\n   - reset runtime queues/counters\n   - append `custom_message(handoff)`\n   - optionally save an auto-triggered handoff document under the session artifacts directory when `compaction.handoffSaveToDisk` is enabled\n8. Controller rebuilds chat UI and announces success.\n9. `#handoffAbortController` cleared (`isGeneratingHandoff = false`).\n\n## Known assumptions and limitations\n\n- No structural validation checks that generated markdown follows the requested section format.\n- Missing generated text is reported as cancellation in controller UX.\n- Manual handoff has no streaming visibility; a cancellable loader is shown until the UI updates after generation completes.\n- Auto-triggered handoffs can write a timestamped `handoff-*.md` artifact when `compaction.handoffSaveToDisk` is enabled; write failure is logged and does not fail the handoff.\n",
+	"hermes-mcp-bridge.md": "# Hermes MCP bridge\n\nGJC exposes a native outward MCP bridge for Hermes-style coordinators:\n\n```bash\ngjc mcp-serve coordinator\n```\n\n`gjc mcp-serve hermes` is accepted as a compatibility alias for the same coordinator bridge.\n\nThe bridge is intentionally separate from GJC's client-side MCP runtime. It lets an external coordinator list sessions, start worktree/tmux-oriented sessions, queue bounded follow-up prompts, read status/tail/artifacts, handle structured questions, and write coordination reports without scraping terminal scrollback.\n\n## Core contract and adapters\n\nThe coordinator bridge is intentionally a core contract with multiple adapters, not an MCP-only product direction. Hermes is one coordinator preset, not a product layer:\n\n- `packages/coding-agent/src/coordinator/contract.ts` owns transport-neutral server metadata and tool names.\n- `gjc mcp-serve coordinator` is the outward MCP adapter for Hermes-style agents.\n- `gjc coordinator` is the read-only CLI/debug adapter for humans and scripts that need to inspect the same contract without starting MCP transport.\n- `gjc setup hermes` is the setup adapter that renders coordinator config and operator guidance.\n\nFuture session, turn, question, artifact, and report behavior should move toward shared coordinator core services that both MCP and CLI adapters call instead of duplicating transport-specific logic.\n\n## Standard Hermes setup\n\nUse `gjc setup hermes` to render or install a portable Hermes MCP setup package:\n\n```bash\ngjc setup hermes --root /path/to/repo --profile my-bot --repo gajae-code\n```\n\nThe default mode is render-only and writes no files. To install into a Hermes profile:\n\n```bash\ngjc setup hermes \\\n  --root /path/to/repo \\\n  --profile my-bot \\\n  --repo gajae-code \\\n  --mutation sessions,questions,reports \\\n  --profile-dir /path/to/hermes/profile \\\n  --install\n```\n\nThe generated setup is model-agnostic and worktree-isolated. By default it renders `GJC_COORDINATOR_MCP_SESSION_COMMAND` as `gjc --worktree`, so spawned sessions launch inside a GJC-managed sibling worktree while GJC still records the original repo as the project identity for tmux/session resume. Users who need a stable named branch can set `--worktree-name`; users who need a specific local wrapper, dev checkout, or provider/model can opt in explicitly:\n\n```bash\ngjc setup hermes \\\n  --root /path/to/repo \\\n  --worktree-name hermes-gajae-code\n```\n\n```bash\ngjc setup hermes \\\n  --root /path/to/repo \\\n  --session-command \"gjc --worktree hermes-custom --model <provider/model>\"\n```\n\nProvider/model examples are examples only; GJC does not hard-code GPT, Anthropic, or any other provider as the Hermes bridge default.\n\nRun a non-mutating setup smoke check with:\n\n```bash\ngjc setup hermes --root /path/to/repo --smoke\n```\n\nSmoke verifies the MCP server/tool contract. It does not call a downstream LLM and does not validate provider credentials.\n\n\n## Safety model\n\nThe bridge is read-only and fail-closed by default.\n\nRequired root allowlist:\n\n```bash\nexport GJC_COORDINATOR_MCP_WORKDIR_ROOTS=\"/path/to/repo:/path/to/worktrees\"\n```\n\nMutating tools require both startup opt-in and per-call consent:\n\n```bash\nexport GJC_COORDINATOR_MCP_MUTATIONS=\"sessions,questions,reports\"\n```\n\nEvery mutating MCP call must also include `allow_mutation: true`. Missing startup opt-in or missing per-call consent returns an error instead of falling back to shell or terminal relay.\n\nReal tmux/GJC actuation uses the configured GJC-compatible session command. `gjc setup hermes` writes this as `gjc --worktree` by default so GJC owns worktree creation and resume identity:\n\n```bash\nexport GJC_COORDINATOR_MCP_SESSION_COMMAND=\"gjc --worktree\"\n```\n\nWith that command configured, `gjc_coordinator_start_session` launches a detached tmux session, `gjc_coordinator_send_prompt` creates a durable turn and sends input to that pane, and `gjc_coordinator_read_tail` reads bounded advisory pane output. Tmux tail parsing is not the completion source of truth; turn completion comes from explicit durable turn state such as `gjc_coordinator_report_status`.\n\nFor resume safety, prefer the generated GJC-native worktree command over creating a git worktree in Hermes itself. GJC's launch path records the original repo as the project identity while running in the worktree, so session listing/resume can still group the session under the source project. If Hermes creates and later deletes an unmanaged worktree, a saved session may still exist but its cwd can be gone.\n\nArtifact reads are canonicalized, symlink escapes are rejected, and returned content is byte-capped by `GJC_COORDINATOR_MCP_ARTIFACT_BYTE_CAP`.\n\n`gjc setup hermes` renders `GJC_COORDINATOR_MCP_WORKDIR_ROOTS` with the host platform path delimiter (`:` on POSIX, `;` on Windows). Manual configs should prefer the same encoding.\n\n## Optional namespace\n\nUse namespace variables to prevent cross-profile or cross-repo enumeration:\n\n```bash\nexport GJC_COORDINATOR_MCP_PROFILE=\"meeseeks2\"\nexport GJC_COORDINATOR_MCP_REPO=\"gajae-code\"\n```\n\nMissing namespace never widens into global session enumeration.\n\n## Tool surface\n\nRead tools:\n\n- `gjc_coordinator_list_sessions`\n- `gjc_coordinator_read_status`\n- `gjc_coordinator_read_tail`\n- `gjc_coordinator_list_questions`\n- `gjc_coordinator_list_artifacts`\n- `gjc_coordinator_read_artifact`\n- `gjc_coordinator_read_coordination_status`\n- `gjc_coordinator_read_turn`\n- `gjc_coordinator_await_turn`\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\n\n`gjc_coordinator_register_session` registers an existing visible tmux-backed GJC pane as the coordinator-authoritative session. Use it when an operator has already launched a visible Warp/tmux lane and Hermes must send prompts to that same pane instead of creating a hidden `gjc-coordinator-*` session. The tool validates the workdir allowlist, safe session/target tokens, and tmux target liveness before writing session state.\n## Turn orchestration flow\n\nHermes coordinators should treat turns, not terminal scrollback, as the unit of work:\n\n1. Call `gjc_coordinator_start_session` with `allow_mutation: true`.\n2. Call `gjc_coordinator_send_prompt` with `allow_mutation: true`.\n3. Store the returned `turn_id`.\n4. Poll `gjc_coordinator_read_turn`, or call bounded `gjc_coordinator_await_turn`, until the turn is terminal.\n5. If `gjc_coordinator_list_questions` shows a question for that turn, answer with `gjc_coordinator_submit_question_answer`.\n6. Use `gjc_coordinator_report_status` with `session_id` and `turn_id` to write explicit completion/failure evidence.\n\n`gjc_coordinator_send_prompt` preserves the legacy `queued` and `delivered` fields and adds turn fields:\n\n```json\n{\n  \"ok\": true,\n  \"session_id\": \"gjc-coordinator-demo\",\n  \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"active_turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"status\": \"active\",\n  \"queued\": false,\n  \"delivered\": true\n}\n```\n\nA session may have only one active turn by default. A second prompt is rejected with `active_turn_exists` unless the caller explicitly passes `queue: true` or `force: true`. Queued turns are durable and the next queued turn is promoted when the active turn reaches a terminal `gjc_coordinator_report_status`. Force supersedes the previous active turn and audits that state in the turn journal.\n\n`gjc_coordinator_read_turn` returns the authoritative durable turn plus advisory pane status:\n\n```json\n{\n  \"ok\": true,\n  \"turn\": {\n    \"schema_version\": 1,\n    \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n    \"session_id\": \"gjc-coordinator-demo\",\n    \"status\": \"completed\",\n    \"final_response\": {\n      \"text\": \"Done\",\n      \"format\": \"markdown\",\n      \"source\": \"report_status\",\n      \"artifact_path\": null,\n      \"truncated\": false\n    },\n    \"evidence\": [{ \"path\": \"artifact.txt\" }],\n    \"error\": null\n  },\n  \"advisory_status\": {\n    \"live\": true,\n    \"state\": \"idle_or_unknown\"\n  }\n}\n```\n\nExternal `session_id`, `turn_id`, and `question_id` values are validated before path use, and loaded records must match the requested session/turn owner.\n## Hermes config snippet\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/doyun/src/gajae-code\",\n        \"GJC_COORDINATOR_MCP_PROFILE\": \"meeseeks2\",\n        \"GJC_COORDINATOR_MCP_REPO\": \"gajae-code\",\n        \"GJC_COORDINATOR_MCP_SESSION_COMMAND\": \"/home/doyun/.local/bin/gjc-dev-meeseeks2\"\n      },\n      \"enabled\": true\n    }\n  }\n}\n```\n\n## Smoke check\n\n```bash\ngjc mcp-serve coordinator --check --json\n```\n\nExpected result includes `ok: true`, server name `gjc-coordinator-mcp`, and the GJC-named tool list.\n",
 	"keybindings.md": "# Keybindings\n\nRun `/hotkeys` inside an `gjc` session to see the active chords for your current build. The list reflects any remaps loaded from disk and any bindings added by extensions.\n\n## Customize keybindings\n\nUser remaps live in `~/.gjc/agent/keybindings.json`. The file is a JSON object whose keys are keybinding action IDs and whose values are either one chord string or an array of chord strings. It is not read from `~/.gjc/agent/config.yml`, and there is no nested `keybindings` object.\n\n```json\n{\n  \"app.model.cycleForward\": \"Ctrl+P\",\n  \"app.model.selectTemporary\": \"Alt+P\",\n  \"app.plan.toggle\": \"Alt+Shift+P\"\n}\n```\n\nChord names are case-insensitive and use the same notation shown in the UI, such as `Ctrl+P`, `Alt+Shift+P`, `Shift+Enter`, and `Ctrl+Backspace`.\n\nSet an action to an empty array to disable it:\n\n```json\n{\n  \"app.stt.toggle\": []\n}\n```\n\n## Common action IDs\n\n| Action ID | Default | Meaning |\n| --- | --- | --- |\n| `app.model.cycleForward` | `Ctrl+P` | Cycle role models forward |\n| `app.model.cycleBackward` | `Shift+Ctrl+P` | Cycle role models backward |\n| `app.model.selectTemporary` | `Alt+P` | Pick a model temporarily for this session |\n| `app.model.select` | `Ctrl+L` | Open the model selector and set roles |\n| `app.plan.toggle` | `Alt+Shift+P` | Toggle plan mode |\n| `app.history.search` | `Ctrl+R` | Search prompt history |\n| `app.tools.expand` | `Ctrl+O` | Toggle tool-output expansion |\n| `app.thinking.toggle` | `Ctrl+T` | Toggle thinking-block visibility |\n| `app.thinking.cycle` | `Shift+Tab` | Cycle thinking level |\n| `app.editor.external` | `Ctrl+G` | Edit the draft in `$VISUAL` / `$EDITOR` |\n| `app.message.followUp` | `Ctrl+Enter` | Queue a follow-up message |\n| `app.message.dequeue` | `Alt+Up` | Dequeue a queued message back into the editor |\n| `app.clipboard.copyLine` | `Alt+Shift+L` | Copy the current line |\n| `app.clipboard.copyPrompt` | `Alt+Shift+C` | Copy the whole prompt |\n| `app.stt.toggle` | `Alt+H` | Toggle speech-to-text recording |\n\nOlder unqualified action names are migrated when `keybindings.json` is loaded, but new docs and new configs should use the namespaced action IDs above.\n",
 	"lsp-config.md": "# LSP configuration in GJC\n\nThis guide explains how to configure language servers for the GJC coding agent.\n\nSource of truth in code:\n\n- Server config type: `packages/coding-agent/src/lsp/types.ts` (`ServerConfig`)\n- Config loader: `packages/coding-agent/src/lsp/config.ts`\n- Built-in server definitions: `packages/coding-agent/src/lsp/defaults.json`\n\n## Auto-detection\n\nWhen no LSP config file is present, GJC auto-detects servers by intersecting two conditions:\n\n1. The project directory contains at least one of the server's `rootMarkers`.\n2. The server binary is available — checked in project-local bin directories first (e.g., `node_modules/.bin/`, `.venv/bin/`), then `$PATH`.\n\nNo configuration is required for common setups. The built-in server list covers most popular languages; see [`defaults.json`](../packages/coding-agent/src/lsp/defaults.json) for the full set.\n\n## Config file locations\n\nGJC merges LSP config from multiple files, lowest to highest priority:\n\n| Priority | Location |\n|----------|----------|\n| 5 (lowest) | `~/lsp.json`, `~/.lsp.json`, `~/lsp.yaml`, `~/.lsp.yaml` |\n| 3 | `~/.gjc/agent/lsp.json`, `~/.gjc/agent/lsp.yaml`, `~/.gemini/lsp.*` |\n| 2 | `<project>/.gjc/lsp.json`, `<project>/.gjc/lsp.yaml`, `<project>/.gemini/lsp.*` |\n| 1 (highest) | `<project>/lsp.json`, `<project>/.lsp.json`, `<project>/lsp.yaml` |\n\nEach location accepts both `.json` and `.yaml` / `.yml` variants, as well as hidden-file versions (`.lsp.json`, `.lsp.yaml`). Files are merged in order: higher-priority files override lower-priority fields for the same server. Servers not mentioned in any override file remain at their built-in defaults.\n\n**Recommended locations:**\n\n- User-wide preferences → `~/.gjc/agent/lsp.json`\n- Project-specific overrides → `<project>/.gjc/lsp.json`\n\n> **Note:** The presence of any LSP config file disables auto-detection. When at least one file is found, GJC skips the binary-scan phase and loads all servers that have matching `rootMarkers`, an available binary, and are not explicitly `disabled`.\n\n## File shape\n\nBoth JSON and YAML are accepted. The top-level object can use either a `servers` wrapper key or a flat map directly:\n\n```json\n{\n  \"servers\": {\n    \"server-name\": { ... }\n  },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nor (flat, without the `servers` wrapper):\n\n```json\n{\n  \"server-name\": { ... },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nTop-level keys:\n\n- `servers` — map of server name to `ServerConfig` (optional wrapper; flat form is equivalent)\n- `idleTimeoutMs` — shut down idle language servers after this many milliseconds; disabled by default\n\n## ServerConfig fields\n\n| Field | Type | Required | Description |\n|-------|------|----------|-------------|\n| `command` | `string` | yes | Binary name (resolved via PATH/local bins) or absolute path |\n| `args` | `string[]` | no | Arguments passed to the binary |\n| `fileTypes` | `string[]` | yes | File extensions this server handles, e.g. `[\".ts\", \".tsx\"]` |\n| `rootMarkers` | `string[]` | yes | Files/dirs that indicate a project root; glob patterns (e.g. `*.cabal`) are supported |\n| `initOptions` | `object` | no | Sent as `initializationOptions` during LSP handshake |\n| `settings` | `object` | no | Workspace settings pushed via `workspace/didChangeConfiguration` |\n| `disabled` | `boolean` | no | Set to `true` to disable this server entirely |\n| `warmupTimeoutMs` | `number` | no | Startup timeout in ms for this server (overrides the global default) |\n| `isLinter` | `boolean` | no | Mark server as linter/formatter only; excluded from type-intelligence operations (hover, go-to-definition, etc.) |\n| `capabilities` | `object` | no | Opt-in server-specific features; see [Capabilities](#capabilities) |\n\n`resolvedCommand` is populated automatically at runtime — do not set it manually.\n\n### Capabilities\n\nThe `capabilities` object enables optional server-specific features that GJC supports on a per-server basis:\n\n```json\n{\n  \"capabilities\": {\n    \"flycheck\": true,\n    \"ssr\": true,\n    \"expandMacro\": true,\n    \"runnables\": true,\n    \"relatedTests\": true\n  }\n}\n```\n\nAll fields are boolean and optional. They are currently used by `rust-analyzer`.\n\n## Common recipes\n\n### Override a built-in server's settings\n\nPartial overrides are merged onto the built-in defaults. You only need to specify the fields you want to change.\n\n```json\n{\n  \"servers\": {\n    \"typescript-language-server\": {\n      \"args\": [\"--stdio\", \"--log-level\", \"4\"]\n    }\n  }\n}\n```\n\n```yaml\nservers:\n  gopls:\n    settings:\n      gopls:\n        gofumpt: false\n        staticcheck: false\n```\n\n### Disable a built-in server\n\n```json\n{\n  \"servers\": {\n    \"eslint\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\n### Register a custom server\n\nNew servers require `command`, `fileTypes`, and `rootMarkers`. All other fields are optional.\n\n```json\n{\n  \"servers\": {\n    \"my-lsp\": {\n      \"command\": \"my-lsp-server\",\n      \"args\": [\"--stdio\"],\n      \"fileTypes\": [\".xyz\"],\n      \"rootMarkers\": [\".xyz-project\", \".git\"]\n    }\n  }\n}\n```\n\n### Set a global idle timeout\n\nShut down language servers that have been inactive for more than five minutes:\n\n```json\n{\n  \"idleTimeoutMs\": 300000\n}\n```\n\n### Disable a server for one project, keep it globally\n\nPlace the override in `<project>/.gjc/lsp.json`:\n\n```json\n{\n  \"servers\": {\n    \"pylsp\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\nThe user-level config in `~/.gjc/agent/lsp.json` is unaffected; pylsp is only suppressed in this project.\n\n## Built-in server list\n\nThe following servers ship in `defaults.json` and are eligible for auto-detection:\n\n| Server key | Language(s) | Binary |\n|---|---|---|\n| `rust-analyzer` | Rust | `rust-analyzer` |\n| `clangd` | C, C++, ObjC | `clangd` |\n| `zls` | Zig | `zls` |\n| `gopls` | Go | `gopls` |\n| `typescript-language-server` | TypeScript, JavaScript | `typescript-language-server` |\n| `denols` | TypeScript, JavaScript (Deno) | `deno` |\n| `biome` | TS/JS/JSON (linter) | `biome` |\n| `eslint` | TS/JS/Vue/Svelte (linter) | `vscode-eslint-language-server` |\n| `vscode-html-language-server` | HTML | `vscode-html-language-server` |\n| `vscode-css-language-server` | CSS, SCSS, Less | `vscode-css-language-server` |\n| `vscode-json-language-server` | JSON | `vscode-json-language-server` |\n| `tailwindcss` | HTML, CSS, TS/JS | `tailwindcss-language-server` |\n| `svelte` | Svelte | `svelteserver` |\n| `vue-language-server` | Vue | `vue-language-server` |\n| `astro` | Astro | `astro-ls` |\n| `pyright` | Python | `pyright-langserver` |\n| `basedpyright` | Python | `basedpyright-langserver` |\n| `pylsp` | Python | `pylsp` |\n| `ruff` | Python (linter) | `ruff` |\n| `jdtls` | Java | `jdtls` |\n| `kotlin-lsp` | Kotlin | `kotlin-lsp` |\n| `metals` | Scala | `metals` |\n| `hls` | Haskell | `haskell-language-server-wrapper` |\n| `ocamllsp` | OCaml | `ocamllsp` |\n| `elixirls` | Elixir | `elixir-ls` |\n| `erlangls` | Erlang | `erlang_ls` |\n| `gleam` | Gleam | `gleam` |\n| `solargraph` | Ruby | `solargraph` |\n| `ruby-lsp` | Ruby | `ruby-lsp` |\n| `rubocop` | Ruby (linter) | `rubocop` |\n| `bashls` | Bash, Zsh | `bash-language-server` |\n| `lua-language-server` | Lua | `lua-language-server` |\n| `intelephense` | PHP | `intelephense` |\n| `phpactor` | PHP | `phpactor` |\n| `omnisharp` | C# | `omnisharp` |\n| `yamlls` | YAML | `yaml-language-server` |\n| `terraformls` | Terraform | `terraform-ls` |\n| `dockerls` | Dockerfile | `docker-langserver` |\n| `helm-ls` | Helm | `helm_ls` |\n| `nixd` | Nix | `nixd` |\n| `nil` | Nix | `nil` |\n| `ols` | Odin | `ols` |\n| `dartls` | Dart | `dart` |\n| `marksman` | Markdown | `marksman` |\n| `texlab` | LaTeX | `texlab` |\n| `graphql` | GraphQL | `graphql-lsp` |\n| `prismals` | Prisma | `prisma-language-server` |\n| `vimls` | Vim script | `vim-language-server` |\n| `emmet-language-server` | HTML, CSS, JSX | `emmet-language-server` |\n| `sourcekit-lsp` | Swift | `sourcekit-lsp` |\n| `swiftlint` | Swift (linter) | `swiftlint` |\n| `tlaplus` | TLA+ | `tlapm_lsp` |\n",
 	"memory.md": "# Autonomous Memory\n\nWhen enabled, the agent automatically extracts durable knowledge from past sessions and injects a compact summary into each new session. Over time it builds a project-scoped memory store — technical decisions, recurring workflows, pitfalls — that carries forward without manual effort.\n\nDisabled by default. Enable via `/settings` or `config.yml`:\n\n```yaml\nmemories:\n  enabled: true\n```\n\n## Usage\n\n### What gets injected\n\nAt session start, if a memory summary exists for the current project, it is injected into the system prompt as a **Memory Guidance** block. The agent is instructed to:\n\n- Treat memory as heuristic context — useful for process and prior decisions, not authoritative on current repo state.\n- Pair memory-influenced decisions with current-repo evidence before acting.\n- Prefer repo state and user instruction when they conflict with memory; treat conflicting memory as stale.\n\n### Memory artifacts\n\nGenerated local-memory artifacts are private runtime state, not a public tool or URI surface. They may be summarized into the system prompt when local memory is enabled, but users and model-facing tool docs should not rely on direct `memory://` reads. The legacy internal `memory://` resolver remains only for compatibility with existing persisted guidance and is not part of the public coding harness contract; remove it after legacy local-memory prompts no longer reference it.\n### `/memory` slash command\n\n| Subcommand            | Effect                                         |\n| --------------------- | ---------------------------------------------- |\n| `view`                | Show the current memory injection payload      |\n| `clear` / `reset`     | Delete all memory data and generated artifacts |\n| `enqueue` / `rebuild` | Force consolidation to run at next startup     |\n\n## How it works\n\nMemories are built by a background pipeline that runs at startup or when manually triggered via slash command.\n\n**Phase 1 — per-session extraction:** For each past session that has changed since it was last processed, a model reads the session history and extracts durable signal: technical decisions, constraints, resolved failures, recurring workflows. Sessions that are too recent, too old, or currently active are skipped. Each extraction produces a raw memory block and a short synopsis for that session.\n\n**Phase 2 — consolidation:** After extraction, a second model pass reads all per-session extractions and produces three outputs written to disk:\n\n- `MEMORY.md` — a curated long-term memory document\n- `memory_summary.md` — the compact text injected at session start\n- `skills/` — reusable procedural playbooks, each in its own subdirectory\n\nPhase 2 uses a lease to prevent double-running when multiple processes start simultaneously. Stale skill directories from prior runs are pruned automatically.\n\nAll output is scanned for secrets before being written to disk.\n\n### Extraction behavior\n\nMemory extraction and consolidation behavior is driven by static prompt files in `packages/coding-agent/src/prompts/memories/`.\n\n| File                  | Purpose                                     | Variables                                   |\n| --------------------- | ------------------------------------------- | ------------------------------------------- |\n| `stage_one_system.md` | System prompt for per-session extraction    | —                                           |\n| `stage_one_input.md`  | User-turn template wrapping session content | `{{thread_id}}`, `{{response_items_json}}`  |\n| `consolidation.md`    | Prompt for cross-session consolidation      | `{{raw_memories}}`, `{{rollout_summaries}}` |\n| `read_path.md`        | Memory guidance injected into live sessions | `{{memory_summary}}`                        |\n\n### Model selection\n\nMemory piggybacks on the model role system.\n\n| Phase                   | Role                                                                | Purpose                          |\n| ----------------------- | ------------------------------------------------------------------- | -------------------------------- |\n| Phase 1 (extraction)    | `default`                                                           | Per-session knowledge extraction |\n| Phase 2 (consolidation) | `smol` (falls back to `default`, then current/first registry model) | Cross-session synthesis          |\n\nIf the requested memory role is not configured, memory model resolution falls back to the `default` role, then the active session model, then the first model in the registry.\n\n## Configuration\n\n| Setting                               | Default | Description                                               |\n| ------------------------------------- | ------- | --------------------------------------------------------- |\n| `memories.enabled`                    | `false` | Master switch                                             |\n| `memories.maxRolloutAgeDays`          | `30`    | Sessions older than this are not processed                |\n| `memories.minRolloutIdleHours`        | `12`    | Sessions active more recently than this are skipped       |\n| `memories.maxRolloutsPerStartup`      | `64`    | Cap on sessions processed in a single startup             |\n| `memories.summaryInjectionTokenLimit` | `5000`  | Max tokens of the summary injected into the system prompt |\n\nAdditional tuning knobs (concurrency, lease durations, token budgets) are available in config for advanced use.\n\n## Key files\n\n- `packages/coding-agent/src/memories/index.ts` — pipeline orchestration, injection, slash command handling\n- `packages/coding-agent/src/memories/storage.ts` — SQLite-backed job queue and thread registry\n- `packages/coding-agent/src/prompts/memories/` — memory prompt templates\n- `packages/coding-agent/src/internal-urls/memory-protocol.ts` — legacy non-public `memory://` compatibility handler\n",
@@ -25,10 +27,10 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"natives-architecture.md": "# Natives Architecture\n\n`@gajae-code/natives` is now a two-layer package around a loader:\n\n1. **CommonJS loader/package entrypoint** resolves and loads the correct `.node` addon and patches generated enum objects onto the export object.\n2. **Rust N-API module layer** implements the exported functions/classes and emits the generated TypeScript declarations.\n\nThis document is the foundation for deeper module-level docs.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n\n## Package entrypoint and public surface\n\n`packages/natives/package.json` points directly at generated native bindings:\n\n- `main`: `./native/index.js`\n- `types`: `./native/index.d.ts`\n- `exports[\".\"].types`: `./native/index.d.ts`\n- `exports[\".\"].import`: `./native/index.js`\n\nThere is no current `packages/natives/src` TypeScript wrapper layer. Consumers import functions/classes/enums directly from `@gajae-code/natives`; the type contract is the generated `native/index.d.ts` plus enum exports appended by `scripts/gen-enums.ts`.\n\nCurrent capability groups in the generated API include:\n\n- **Search/text/code primitives**: `grep`, `search`, `hasMatch`, `fuzzyFind`, `glob`, `astGrep`, `astEdit`, text width/slicing/wrapping/sanitization, syntax highlighting, token counting.\n- **Execution/process/terminal primitives**: `executeShell`, `Shell`, `PtySession`, process-tree helpers, key parsing.\n- **System/media/conversion primitives**: clipboard, image resize/encode/SIXEL, HTML-to-Markdown, macOS appearance/power helpers, work profiling, Windows ProjFS overlay helpers.\n\n## Loader layer\n\n`packages/natives/native/index.js` owns runtime addon selection and optional embedded extraction.\n\n### Candidate resolution model\n\n- Platform tag is `${process.platform}-${process.arch}`.\n- Supported tags are currently:\n  - `linux-x64`\n  - `linux-arm64`\n  - `darwin-x64`\n  - `darwin-arm64`\n  - `win32-x64`\n- x64 can use CPU variants:\n  - `modern` (AVX2-capable)\n  - `baseline` (fallback)\n- Non-x64 uses the default filename without a variant suffix.\n\nFilename strategy:\n\n- Default: `pi_natives.<platform>-<arch>.node`\n- x64 variant: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- x64 runtime fallback includes the unsuffixed default filename after variant candidates.\n\n### Platform-specific variant detection\n\nFor x64, variant selection uses:\n\n- Linux: `/proc/cpuinfo`\n- macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`\n- Windows: PowerShell check for `System.Runtime.Intrinsics.X86.Avx2`\n\n`GJC_NATIVE_VARIANT` can force `modern` or `baseline`; invalid values are ignored.\n\n### Binary distribution and extraction model\n\n`packages/natives/package.json` publishes `native/`, which contains the loader, generated declarations, generated enum patch, embedded-addon manifest stub, and prebuilt `.node` artifacts.\n\nFor compiled binaries, loader behavior is:\n\n1. Check versioned user cache path: `<getNativesDir()>/<packageVersion>/...`.\n2. Check legacy compiled-binary location:\n   - Windows: `%LOCALAPPDATA%/gjc` (fallback `%USERPROFILE%/AppData/Local/gjc`)\n   - non-Windows: `~/.local/bin`\n3. Fall back to packaged `native/` and executable directory candidates.\n\n`getNativesDir()` uses `$XDG_DATA_HOME/gjc/natives` when `$XDG_DATA_HOME/gjc` exists; otherwise it uses `~/.gjc/natives`.\n\nIf a populated embedded addon manifest is present, it is also treated as a compiled-binary signal. The loader can extract the matching embedded `.node` into the versioned cache directory before candidate probing.\n\n### Failure modes\n\nLoader failures are explicit:\n\n- **Unsupported platform tag**: after failed probing, throws with supported platform list.\n- **No loadable candidate**: throws with all attempted paths and remediation hints.\n- **Embedded extraction errors**: directory/write failures are recorded and included in final load diagnostics if no candidate loads.\n\nThe current loader does not perform a separate post-`require` export validation pass.\n\n## Rust N-API module layer\n\n`crates/pi-natives/src/lib.rs` declares exported module ownership:\n\n- `appearance`\n- `ast`\n- `clipboard`\n- `fd`\n- `fs_cache`\n- `glob`\n- `glob_util`\n- `grep`\n- `highlight`\n- `html`\n- `image`\n- `keys`\n- `language`\n- `power`\n- `prof`\n- `projfs_overlay`\n- `ps`\n- `pty`\n- `shell`\n- `task`\n- `text`\n- `tokens`\n- `utils` (crate-private helpers)\n\nN-API exports are generated from Rust `#[napi]` functions/classes/objects/enums. Snake_case Rust names are exposed as camelCase JavaScript names unless explicitly configured by napi-rs.\n\n## Ownership boundaries\n\n- **Loader/package ownership (`packages/natives/native`, `packages/natives/scripts`)**\n  - runtime binary selection\n  - CPU variant selection and override handling\n  - compiled-binary embedded extraction\n  - generated TypeScript declarations and enum export patching\n- **Rust ownership (`crates/pi-natives/src`)**\n  - algorithmic and system-level implementation\n  - platform-native behavior and performance-sensitive logic\n  - N-API symbol implementation consumed directly by package callers\n- **Consumer ownership (`packages/coding-agent`, `packages/tui`)**\n  - user-facing policy and fallbacks that are not built into the native API\n  - higher-level rendering, artifact, shell-session, and command behavior\n\n## Runtime flow (high level)\n\n1. Consumer imports from `@gajae-code/natives`.\n2. `native/index.js` computes platform/arch/variant and candidate paths.\n3. Optional embedded binary extraction occurs for compiled distributions.\n4. The first `require(candidate)` that succeeds becomes the exported addon object.\n5. Generated enum objects are appended to `module.exports`.\n6. Caller invokes generated N-API functions/classes directly.\n\n## Glossary\n\n- **Native addon**: A `.node` binary loaded via Node-API (N-API).\n- **Platform tag**: Runtime tuple `platform-arch` (for example `darwin-arm64`).\n- **Variant**: x64 CPU-specific build flavor (`modern` AVX2, `baseline` fallback).\n- **Generated binding declaration**: `native/index.d.ts` emitted by napi-rs during `build-native.ts`.\n- **Compiled binary mode**: Runtime mode where the CLI is bundled and native addons are resolved from embedded/cache paths before package-local paths.\n- **Embedded addon**: Build artifact metadata and file references generated into `native/embedded-addon.js` so compiled binaries can extract matching `.node` payloads.\n",
 	"natives-binding-contract.md": "# Natives Binding Contract (JavaScript/TypeScript Side)\n\nThis document defines the JS/TS contract between `@gajae-code/natives` callers and the loaded N-API addon.\n\nCurrent package shape is direct-to-native: there is no `packages/natives/src/<module>` TypeScript wrapper layer. The public API is the generated `packages/natives/native/index.d.ts` declaration file, the CommonJS loader in `packages/natives/native/index.js`, and the Rust `#[napi]` exports in `crates/pi-natives/src`.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n- Rust modules under `crates/pi-natives/src/*.rs`\n\n## Contract model\n\nThe contract has three parts:\n\n1. **Generated runtime loader** (`native/index.js`)\n   - computes candidates and `require(...)`s the `.node` addon;\n   - exports the loaded addon object directly;\n   - appends enum objects generated by `scripts/gen-enums.ts`.\n2. **Generated TypeScript declarations** (`native/index.d.ts`)\n   - generated by napi-rs during `scripts/build-native.ts`;\n   - declares exported functions, classes, object interfaces, and native enums;\n   - is the package `types` entry.\n3. **Rust N-API exports** (`crates/pi-natives/src`)\n   - `#[napi]` functions/classes/objects/enums are the source of generated declarations and runtime symbols;\n   - snake_case Rust names become camelCase JavaScript names by napi-rs convention.\n\nThere is no current `NativeBindings` declaration-merging lifecycle and no `validateNative(...)` required-export list in the loader.\n\n## Public export surface organization\n\n`packages/natives/package.json` exposes the package root only:\n\n```json\n{\n  \"main\": \"./native/index.js\",\n  \"types\": \"./native/index.d.ts\",\n  \"exports\": {\n    \".\": {\n      \"types\": \"./native/index.d.ts\",\n      \"import\": \"./native/index.js\"\n    }\n  }\n}\n```\n\nConsumers in `packages/coding-agent` and `packages/tui` import directly from `@gajae-code/natives`.\n\n## JS API ↔ native export mapping (representative)\n\n| Category          | Public JS API                                                                                              | Rust source                                                 | Return style                  |\n| ----------------- | ---------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- | ----------------------------- |\n| Grep              | `grep(options, onMatch?)`                                                                                  | `grep.rs`                                                   | `Promise<GrepResult>`         |\n| Grep              | `search(content, options)`                                                                                 | `grep.rs`                                                   | `SearchResult`                |\n| Grep              | `hasMatch(content, pattern, ignoreCase?, multiline?)`                                                      | `grep.rs`                                                   | `boolean`                     |\n| Fuzzy path search | `fuzzyFind(options)`                                                                                       | `fd.rs`                                                     | `Promise<FuzzyFindResult>`    |\n| Glob              | `glob(options, onMatch?)`                                                                                  | `glob.rs`                                                   | `Promise<GlobResult>`         |\n| Glob cache        | `invalidateFsScanCache(path?)`                                                                             | `fs_cache.rs`                                               | `void`                        |\n| AST search/edit   | `astGrep(options)`, `astEdit(options)`                                                                     | `ast.rs`                                                    | `Promise<...>`                |\n| Shell             | `executeShell(options, onChunk?)`                                                                          | `shell.rs`                                                  | `Promise<ShellExecuteResult>` |\n| Shell             | `new Shell(options?)`, `shell.run(...)`, `shell.abort()`                                                   | `shell.rs`                                                  | class / promises              |\n| PTY               | `new PtySession()`, `start/write/resize/kill`                                                              | `pty.rs`                                                    | class / promises              |\n| Process           | `killTree(pid, signal)`, `listDescendants(pid)`                                                            | `ps.rs`                                                     | sync                          |\n| Keys              | `parseKey`, `matchesKey`, Kitty/legacy helpers                                                             | `keys.rs`                                                   | sync                          |\n| Text              | `wrapTextWithAnsi`, `truncateToWidth`, `sliceWithWidth`, `extractSegments`, `visibleWidth`                 | `text.rs`                                                   | sync                          |\n| Highlight         | `highlightCode`, `supportsLanguage`, `getSupportedLanguages`                                               | `highlight.rs`                                              | sync                          |\n| HTML              | `htmlToMarkdown(html, options?)`                                                                           | `html.rs`                                                   | `Promise<string>`             |\n| Image             | `PhotonImage`, `encodeSixel`                                                                               | `image.rs`                                                  | class / sync / promises       |\n| Clipboard         | `copyToClipboard`, `readImageFromClipboard`                                                                | `clipboard.rs`                                              | sync / promise                |\n| Tokens            | `countTokens(input, encoding?)`                                                                            | `tokens.rs`                                                 | sync                          |\n| System            | `detectMacOSAppearance`, `MacAppearanceObserver`, `MacOSPowerAssertion`, `getWorkProfile`, ProjFS helpers  | `appearance.rs`, `power.rs`, `prof.rs`, `projfs_overlay.rs` | mixed                         |\n\n## Sync vs async contract differences\n\nThe contract preserves Rust/N-API call style:\n\n- **Promise-returning exports** for worker-thread or async runtime work (`grep`, `glob`, `fuzzyFind`, `astGrep`, `astEdit`, `htmlToMarkdown`, shell/PTY runs, image parse/resize/encode, clipboard image read).\n- **Synchronous exports** for deterministic in-memory transforms/parsers or direct system calls (`search`, `hasMatch`, highlighting, text utilities, token counting, process queries, `copyToClipboard`, `encodeSixel`).\n- **Constructor exports** for stateful runtime objects (`Shell`, `PtySession`, `PhotonImage`, macOS observer/power handles).\n\nChanging sync ↔ async for an existing export is a breaking public API change because consumers call these exports directly.\n\n## Object and enum typing patterns\n\n### Object patterns\n\n`#[napi(object)]` Rust structs become TS interfaces, for example:\n\n- `GrepResult`, `SearchResult`, `GlobResult`, `FuzzyFindResult`\n- `ShellRunResult`, `ShellExecuteResult`, `PtyRunResult`, `MinimizerResult`\n- `AstFindResult`, `AstReplaceResult`\n- `System`/media payloads such as `ClipboardImage`, `WorkProfile`, `ParsedKittyResult`\n\nRuntime shape correctness is owned by napi-rs and the Rust implementation.\n\n### Enum patterns\n\nNative enums are represented in generated declarations and also appended to `module.exports` by `scripts/gen-enums.ts`, because the loader is hand-maintained CommonJS around the generated addon. Current enum objects include:\n\n- `AstMatchStrictness`\n- `Ellipsis`\n- `Encoding`\n- `FileType`\n- `GrepOutputMode`\n- `ImageFormat`\n- `KeyEventType`\n- `MacOSAppearance`\n- `SamplingFilter`\n\n## Error behavior and caveats\n\n- Addon load failure or unsupported platform throws during package import from `native/index.js`.\n- The loader does not verify the full export set after `require(...)`; stale or mismatched binaries surface as native load errors or missing members at use sites.\n- N-API conversion validates basic argument conversion, but TS optional fields do not guarantee semantic validity for untyped callers.\n- Numeric enum declarations do not prevent out-of-range numeric values from untyped callers unless the Rust function rejects them during conversion.\n- Callback exports use napi-rs `ThreadsafeFunction` shape: `(error: Error | null, value) => void`. Native code generally emits successful values; hard failures reject/throw through the owning call.\n\n## Maintainer checklist for binding changes\n\nWhen adding/changing an export, update all of:\n\n1. Rust `#[napi]` implementation in the owning `crates/pi-natives/src/<module>.rs`.\n2. `crates/pi-natives/src/lib.rs` if a new module is added.\n3. Any consumer imports/callsites in `packages/coding-agent` or `packages/tui`.\n4. Build output by running the natives build so `native/index.d.ts` and `native/index.js` stay in sync.\n5. `scripts/gen-enums.ts` if enum runtime export patching needs to change.\n\nDo not add a parallel TS wrapper convention unless the package design intentionally moves back to wrappers; current consumers depend on the direct generated API.\n",
 	"natives-build-release-debugging.md": "# Natives Build, Release, and Debugging Runbook\n\nThis runbook describes how `@gajae-code/natives` produces `.node` addons, generated declarations, and compiled-binary embedded payloads, and how to debug loader/build failures.\n\nIt follows the architecture terms from `docs/natives-architecture.md`:\n\n- **build-time artifact production** (`scripts/build-native.ts`)\n- **embedded addon manifest generation** (`scripts/embed-native.ts`)\n- **runtime addon loading** (`native/index.js`, `native/loader-state.js`)\n\n## Implementation files\n\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `packages/natives/native/index.js`\n- `packages/natives/native/loader-state.js`\n- `crates/pi-natives/Cargo.toml`\n\n## Build pipeline overview\n\n### 1) Build entrypoints\n\n`packages/natives/package.json` scripts:\n\n- `bun scripts/build-native.ts` (`build`) → N-API build, addon install, generated declarations install, enum export patch.\n- `bun scripts/embed-native.ts` (`embed:native`) → generate `native/embedded-addon.js` from built files.\n\nRoot scripts include `build:native` as `bun --cwd=packages/natives run build`.\n\n### 2) N-API/Rust artifact build\n\n`build-native.ts` invokes the `@napi-rs/cli` binary directly from `node_modules/.bin` with:\n\n- `napi build`\n- `--manifest-path crates/pi-natives/Cargo.toml`\n- `--package-json-path packages/natives/package.json`\n- `--platform`\n- `--no-js`\n- `--dts index.d.ts`\n- `--profile local` for non-CI local native builds, otherwise `--profile ci`\n- optional `--target <CROSS_TARGET>`\n\n`crates/pi-natives/Cargo.toml` declares `crate-type = [\"cdylib\"]`; napi-rs emits `.node` artifacts plus generated `index.d.ts` in an isolated temporary output directory under `packages/natives/native/.build/`.\n\n### 3) Artifact install\n\nAfter napi-rs succeeds, `build-native.ts`:\n\n1. resolves the built addon in the isolated output directory;\n2. normalizes its name to `pi_natives.<platform>-<arch>(-variant).node` when needed;\n3. installs the addon into `packages/natives/native/` with temp-file + rename semantics;\n4. copies generated `index.js` and `index.d.ts` into `packages/natives/native/` when present;\n5. runs `generateEnumExports()` to append enum runtime objects to `native/index.js`.\n\nWindows locked-DLL replacement failures are reported with an explicit close-running-processes hint.\n\n## Target/variant model and naming conventions\n\n## Platform tag\n\nBoth build and runtime use platform tag:\n\n`<platform>-<arch>` (example: `darwin-arm64`, `linux-x64`).\n\n## Variant model (x64 only)\n\nx64 supports CPU variants:\n\n- `modern` (AVX2-capable path)\n- `baseline` (fallback)\n\nNon-x64 uses a single default artifact with no variant suffix.\n\n### Output filenames\n\n- x64: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- non-x64: `pi_natives.<platform>-<arch>.node`\n\nRuntime x64 candidate order also includes the unsuffixed default filename after the selected variant candidates.\n\n## Environment flags and build options\n\n## Runtime flags\n\n- `GJC_NATIVE_VARIANT`: x64 runtime override; valid values are `modern` and `baseline`.\n- `GJC_COMPILED`: legacy compiled-mode signal. A populated embedded-addon manifest is also a compiled-mode signal and is the authoritative signal for Bun standalone builds that do not preserve `process.env.GJC_COMPILED`.\n\n## Build-time flags/options\n\n- `CROSS_TARGET`: passed to napi-rs as `--target <CROSS_TARGET>`.\n- `TARGET_PLATFORM`: override output platform tag naming.\n- `TARGET_ARCH`: override output arch naming.\n- `TARGET_VARIANT` (x64 only): force `modern` or `baseline` for output filename and RUSTFLAGS policy.\n- `CARGO_TARGET_DIR`: respected if set; otherwise the default `target/` dir is used so `Swatinem/rust-cache` can cache cleanly.\n- `RUSTFLAGS`:\n  - if unset and not cross-compiling, script sets:\n    - modern: `-C target-cpu=x86-64-v3`\n    - baseline: `-C target-cpu=x86-64-v2`\n    - non-x64 / no variant: `-C target-cpu=native`\n  - if already set, script does not override.\n\n## Build state/lifecycle transitions\n\n### Build lifecycle (`build-native.ts`)\n\n1. **Init**: parse env, resolve target tuple, cross/local mode, profile label.\n2. **Variant resolve**:\n   - non-x64 → no variant;\n   - x64 + `TARGET_VARIANT` → explicit variant;\n   - x64 cross-build without `TARGET_VARIANT` → hard error;\n   - x64 local build without override → detect host AVX2.\n3. **CPU policy**: set `RUSTFLAGS` for the resolved variant unless the caller already provided one.\n4. **Compile**: run napi-rs against `crates/pi-natives` into an isolated output directory.\n5. **Locate artifact**: accept the canonical filename or a single napi-rs-generated `pi_natives.<platform>-<arch>*.node` candidate.\n6. **Install**: copy/rename addon into `packages/natives/native`.\n7. **Install generated bindings**: copy `index.js`/`index.d.ts` if needed.\n8. **Patch enums**: append generated enum runtime exports.\n9. **Cleanup**: remove the temporary build output directory.\n\nFailure exits have explicit error text for invalid variants, failed napi build, missing/multiple output artifacts, generated binding install failure, and install/rename failure.\n\n### Embed lifecycle (`embed-native.ts`)\n\n1. **Init**: compute platform tag from `TARGET_PLATFORM`/`TARGET_ARCH` or host values.\n2. **Candidate set**:\n   - x64 looks for `modern` and `baseline` files;\n   - non-x64 looks for one default file.\n3. **Validate availability**: at least one expected file must exist in `packages/natives/native`.\n4. **Generate manifest** (`native/embedded-addon.js`) with Bun `file` imports and package version.\n5. **Runtime extraction ready** for compiled mode.\n\n`--reset` writes the null manifest stub (`embeddedAddon = null`) without validating addon availability.\n\n## Dev workflow vs shipped/compiled behavior\n\n## Local development workflow\n\nTypical local loop:\n\n1. Build addon: `bun --cwd=packages/natives run build`.\n2. Loader resolves package-local `native/` candidates, then executable-dir fallback candidates.\n3. Generated declarations in `native/index.d.ts` describe the public TS API.\n\n## Shipped/compiled binary workflow\n\nIn compiled mode (`GJC_COMPILED`, Bun embedded URL markers, or populated embedded manifest):\n\n1. Loader computes versioned cache dir: `<getNativesDir()>/<packageVersion>`.\n2. If embedded manifest matches current platform+version, loader may extract the selected embedded file into that versioned dir.\n3. Runtime candidate order includes:\n   - versioned cache dir,\n   - legacy compiled-binary dir (`%LOCALAPPDATA%/gjc` on Windows, `~/.local/bin` elsewhere),\n   - package/executable directories.\n4. First successfully loaded addon is returned.\n\nThis is why packaging + runtime loader expectations must align: filenames, platform tags, CPU variants, and embedded manifest version must match what `native/index.js` probes.\n\n## JS API ↔ Rust export mapping (build sanity subset)\n\nGenerated declarations currently include exports from these Rust modules:\n\n| Area                   | Representative JS exports                                                                         | Rust source                                                                             |\n| ---------------------- | ------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |\n| Search                 | `grep`, `search`, `hasMatch`, `fuzzyFind`, `glob`, `invalidateFsScanCache`                        | `grep.rs`, `fd.rs`, `glob.rs`, `fs_cache.rs`                                            |\n| AST                    | `astGrep`, `astEdit`                                                                              | `ast.rs`                                                                                |\n| Text/highlight/tokens  | `visibleWidth`, `truncateToWidth`, `highlightCode`, `countTokens`                                 | `text.rs`, `highlight.rs`, `tokens.rs`                                                  |\n| Shell/PTY/process/keys | `executeShell`, `Shell`, `PtySession`, `killTree`, `parseKey`                                     | `shell.rs`, `pty.rs`, `ps.rs`, `keys.rs`                                                |\n| Media/system           | `PhotonImage`, `encodeSixel`, clipboard, macOS appearance/power, `getWorkProfile`, ProjFS helpers | `image.rs`, `clipboard.rs`, `appearance.rs`, `power.rs`, `prof.rs`, `projfs_overlay.rs` |\n\n## Failure behavior and diagnostics\n\n## Build-time failures\n\n- Invalid variant configuration:\n  - `TARGET_VARIANT` set on non-x64 → immediate error.\n  - unsupported `TARGET_VARIANT` value → immediate error.\n  - x64 cross-build without explicit `TARGET_VARIANT` → immediate error.\n- napi-rs build failure: script surfaces non-zero exit and stderr.\n- Artifact not found or ambiguous: script prints expected/candidate filenames and output directory contents.\n- Install failure: explicit message; Windows includes locked-file hint.\n- Generated binding install failure: explicit source/destination message.\n\n## Runtime loader failures (`native/index.js`)\n\n- Unsupported platform tag: throws with supported platform list after probing fails.\n- No candidate could load: throws with full candidate error list and mode-specific remediation hints.\n- Embedded extraction problems: extraction mkdir/write errors are recorded and included in final diagnostics if load fails.\n\n## Troubleshooting matrix\n\n| Symptom                                                                | Likely cause                                                                                | Verify                                                            | Fix                                                                                           |\n| ---------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `Cannot find module` or dynamic library load error for every candidate | Missing release artifact, wrong platform tag, or stale compiled cache                       | Inspect loader error list and `packages/natives/native` filenames | Build correct target/variant; delete stale cache for the package version                      |\n| Export is missing at runtime but present in TypeScript                 | Stale `.node` loaded, generated declarations newer than binary, or Rust export not compiled | Require the actual candidate and inspect `Object.keys(mod)`       | Rebuild native package and remove stale candidate/cache paths                                 |\n| x64 machine loads baseline when modern expected                        | `GJC_NATIVE_VARIANT=baseline`, no AVX2 detected, or modern file unavailable                  | Check env and filenames in `native/`                              | Build modern variant (`TARGET_VARIANT=modern ... build`) and ship it                          |\n| Cross-build produces wrong-labeled binary                              | Mismatch between `CROSS_TARGET` and `TARGET_PLATFORM`/`TARGET_ARCH`, or missing x64 variant | Confirm env tuple and output filename                             | Re-run with consistent env values and explicit x64 `TARGET_VARIANT`                           |\n| Compiled binary fails after upgrade                                    | Stale extracted cache or embedded manifest version mismatch                                 | Inspect `<getNativesDir()>/<version>` and loader error list       | Delete versioned cache for the package version; regenerate embedded manifest during packaging |\n| `embed:native` fails with `No native addons found`                     | Required platform artifact was not built before embedding                                   | Check expected list in error text                                 | Build at least one expected artifact for the target, then rerun `embed:native`                |\n\n## Operational commands\n\n```bash\n# Release artifact for current host\nbun --cwd=packages/natives run build\n\n# Build explicit x64 variants\nTARGET_VARIANT=modern bun --cwd=packages/natives run build\nTARGET_VARIANT=baseline bun --cwd=packages/natives run build\n\n# Generate embedded addon manifest from built native files\nbun --cwd=packages/natives run embed:native\n\n# Reset embedded manifest to null stub\nbun --cwd=packages/natives run embed:native -- --reset\n```\n\n## Orchestrator-side content-addressed build cache (robogjc)\n\nWhen `pi-natives` is built inside the robogjc orchestrator (`python/robogjc/`), workspaces share built artifacts through a content-addressed cache instead of rebuilding from scratch in every per-issue worktree. The cache is **orchestrator-side only** — `bun --cwd=packages/natives run build` itself is unchanged; the cache lives outside the build pipeline and is populated/captured around `ensure_workspace` and post-task success in `python/robogjc/src/natives_cache.py`.\n\n### What is cached\n\nThe complete set of files in `packages/natives/native/` that are pure functions of the cache-key inputs:\n\n- `pi_natives.<platform>-<arch>[-variant].node` (glob `pi_natives.*.node`)\n- `index.d.ts`\n- `index.js`\n- `embedded-addon.js`\n- `manifest.json` (cache metadata: key, target triple, capture timestamp, source workspace, commit)\n\nAn entry is only considered a hit when the `.node` glob matches AND every companion plus the manifest is present. Partial entries are evicted on GC.\n\n### Cache key\n\nThe key is `sha256` over `(path \\t git-tree-hash \\n)` pairs for the following inputs, in this order (order is significant), followed by the target triple:\n\n1. `crates` (whole subtree — pi-natives transitively depends on other workspace crates)\n2. `Cargo.lock`\n3. `Cargo.toml`\n4. `rust-toolchain.toml`\n5. `packages/natives` (whole subtree — build script, `scripts/*`, package.json with napi config)\n\nTree hashes come from one `git cat-file --batch-check` invocation against `HEAD`; paths missing from `HEAD` fold in as a fixed null hash so the key stays deterministic across repos that don't ship every input. The target-triple suffix matches the napi addon basename convention (`<platform>-<arch>` for non-x64, `<platform>-<arch>-<variant>` for x64). When `TARGET_VARIANT` is unset on an x64 host the variant component is `host` rather than autodetected — the key is stable on a given machine but a `modern`/`baseline` build with an explicit `TARGET_VARIANT` gets a different key.\n\nAnything outside this input set (Rust toolchain auto-installed delta, host glibc, env vars other than `TARGET_VARIANT`) is **not** in the key. If you need to invalidate after such a change, delete the cache directory by hand or bump one of the input files.\n\n### Layout and ownership\n\n- Root: `/data/cache/pi-natives` (provisioned by `entrypoint.sh` alongside the cargo caches, owned `root:gjc`, mode `02770` setgid so cached files inherit `gid=gjc` and stay readable by every slot user).\n- Per-repo subdirectory: `<root>/<repo-slug>/` where the slug is `owner__repo` (mirrors `SandboxManager.pool_path`).\n- Per-entry directory: `<root>/<repo-slug>/<sha256-key>/` containing the cached files plus `manifest.json`.\n- Per-repo lockfile: `<root>/<repo-slug>/.lock` (advisory `fcntl.flock`, exclusive on capture and GC).\n- Staging dirs (`.<key>.tmp.<pid>`) during capture; renamed atomically into the final entry path. Stale staging dirs from crashed captures are swept on GC.\n\n### Populate and capture semantics\n\n- **Populate** (workspace ← cache) runs inside `ensure_workspace`. On a key hit the `.node` is **hardlinked** into the workspace (zero-copy, shared inode); the companion `index.d.ts` / `index.js` / `embedded-addon.js` are **copied** (independent inodes) because the napi build's `installGeneratedBindings` and `gen-enums.ts` rewrite those files via `open(..., 'w')` — an in-place truncate that would otherwise propagate through a hardlink and corrupt the cache. Cross-device hardlink failures (`EXDEV`) fall back to copy.\n- **Capture** (cache ← workspace) runs from the post-task success path when the build produced a complete artifact set. Capture uses **copy**, not hardlink: hardlinking a slot-owned workspace file would preserve slot UID ownership on the cached inode and defeat the shared-group model. Copying creates a fresh root-owned, `gid=gjc` inode via the setgid cache root. Capture is idempotent under the per-repo flock: a concurrent capture for the same key returns the existing entry.\n\n### Garbage collection\n\nA periodic GC loop runs in `WorkerPool` with two caps per repo. When either cap is exceeded, oldest entries (by `manifest.json.captured_at`) are dropped first:\n\n- entry count cap (`max_entries_per_repo`, default 8)\n- byte cap (`max_bytes`, default 4 GiB)\n\nWorkspaces that hardlinked a `.node` before GC retain access via the kernel inode refcount — `rmtree` of the cache entry does not delete the file from the workspace.\n\n### Configuration (settings on `robogjc.config.Settings`)\n\n| Env var                                      | Default                  | Effect                                                        |\n| -------------------------------------------- | ------------------------ | ------------------------------------------------------------- |\n| `ROBGJC_NATIVES_CACHE_ENABLED`               | `true`                   | Master switch. When false the populate/capture hooks no-op and every workspace builds from scratch. |\n| `ROBGJC_NATIVES_CACHE_ROOT`                  | `/data/cache/pi-natives` | Cache root directory. Must be `root:gjc 02770` for cross-slot reads.                                  |\n| `ROBGJC_NATIVES_CACHE_MAX_ENTRIES_PER_REPO`  | `8`                      | LRU entry-count cap, per repo slug.                                                                  |\n| `ROBGJC_NATIVES_CACHE_MAX_BYTES`             | `4294967296` (4 GiB)     | LRU byte cap, per repo slug.                                                                          |\n| `ROBGJC_NATIVES_CACHE_GC_INTERVAL_SECONDS`   | `3600`                   | Period of the background GC loop in `WorkerPool`.                                                    |\n\n### Manual invalidation\n\n- One key: `rm -rf /data/cache/pi-natives/<repo-slug>/<sha256>`.\n- One repo: `rm -rf /data/cache/pi-natives/<repo-slug>`.\n- Everything: `rm -rf /data/cache/pi-natives/*` (preserve the root so its setgid mode survives).\n- Stuck lock: `rm /data/cache/pi-natives/<repo-slug>/.lock` (only when no orchestrator process is touching the repo).\n\nTrigger an automatic miss by editing any path in the key set: a single touched byte under `crates/`, `Cargo.lock`, `Cargo.toml`, `rust-toolchain.toml`, or `packages/natives/` shifts the tree hash and forces a fresh build at the next populate.\n",
-	"natives-media-system-utils.md": "# Natives media + system utilities\n\nThis document covers the media/system/conversion exports in `@gajae-code/natives`: image processing, HTML conversion, clipboard access, token counting, macOS appearance/power helpers, ProjFS helpers, and work profiling.\n\n## Implementation files\n\n- `crates/pi-natives/src/image.rs`\n- `crates/pi-natives/src/html.rs`\n- `crates/pi-natives/src/clipboard.rs`\n- `crates/pi-natives/src/tokens.rs`\n- `crates/pi-natives/src/appearance.rs`\n- `crates/pi-natives/src/power.rs`\n- `crates/pi-natives/src/projfs_overlay.rs`\n- `crates/pi-natives/src/prof.rs`\n- `crates/pi-natives/src/task.rs`\n- `packages/natives/native/index.d.ts`\n\n> Note: there is no `crates/pi-natives/src/work.rs`; work profiling is implemented in `prof.rs` and fed by instrumentation in `task.rs`.\n\n## JS API ↔ Rust export/module mapping\n\n| JS export                                           | Rust N-API export              | Rust module         |\n| --------------------------------------------------- | ------------------------------ | ------------------- |\n| `PhotonImage.parse(bytes)`                          | `PhotonImage::parse`           | `image.rs`          |\n| `PhotonImage#resize(width, height, filter)`         | `PhotonImage::resize`          | `image.rs`          |\n| `PhotonImage#encode(format, quality)`               | `PhotonImage::encode`          | `image.rs`          |\n| `encodeSixel(bytes, targetWidthPx, targetHeightPx)` | `encode_sixel`                 | `image.rs`          |\n| `htmlToMarkdown(html, options?)`                    | `html_to_markdown`             | `html.rs`           |\n| `copyToClipboard(text)`                             | `copy_to_clipboard`            | `clipboard.rs`      |\n| `readImageFromClipboard()`                          | `read_image_from_clipboard`    | `clipboard.rs`      |\n| `countTokens(input, encoding?)`                     | `count_tokens`                 | `tokens.rs`         |\n| `detectMacOSAppearance()`                           | `detect_mac_os_appearance`     | `appearance.rs`     |\n| `MacAppearanceObserver.start(callback)`             | `MacAppearanceObserver::start` | `appearance.rs`     |\n| `MacOSPowerAssertion.start(options?)`               | `MacOSPowerAssertion::start`   | `power.rs`          |\n| `projfsOverlayProbe/start/stop`                     | ProjFS exports                 | `projfs_overlay.rs` |\n| `getWorkProfile(lastSeconds)`                       | `get_work_profile`             | `prof.rs`           |\n\n## Data format boundaries and conversions\n\n### Image (`image`)\n\n- **JS input boundary**: `Uint8Array` encoded image bytes for `PhotonImage.parse` and `encodeSixel`.\n- **Rust decode boundary**: bytes are copied/read, format is guessed with `ImageReader::with_guessed_format()`, then decoded to `DynamicImage`.\n- **In-memory state**: `PhotonImage` stores `Arc<DynamicImage>`.\n- **Output boundary**:\n  - `PhotonImage#encode(format, quality)` returns a promise for encoded bytes (`Vec<u8>` in Rust; generated TS currently declares `Promise<Array<number>>`).\n  - `encodeSixel(...)` returns a SIXEL escape string synchronously.\n\nFormat IDs:\n\n- `0`: PNG\n- `1`: JPEG\n- `2`: WebP\n- `3`: GIF\n\nEncoding behavior:\n\n- JPEG uses the provided `quality` with `JpegEncoder::new_with_quality`.\n- WebP uses the `webp` crate encoder with `quality` as `f32` in the same 0..=100 range.\n- PNG/GIF ignore `quality`.\n- Invalid dimensions for SIXEL (`0` width or height) fail with `Target SIXEL dimensions must be greater than zero`.\n\n### HTML conversion (`html`)\n\n- **JS input boundary**: HTML `string` + optional `{ cleanContent?: boolean; skipImages?: boolean }`.\n- **Rust conversion boundary**: conversion is scheduled through `task::blocking(\"html_to_markdown\", (), ...)`.\n- **Output boundary**: Markdown `string` promise.\n\nConversion behavior:\n\n- `cleanContent` defaults to `false`.\n- When `cleanContent=true`, preprocessing uses `PreprocessingPreset::Aggressive` and hard-removal flags for navigation/forms.\n- `skipImages` defaults to `false`.\n\n### Clipboard (`clipboard`)\n\n- `copyToClipboard(text)` is a synchronous native call using `arboard::Clipboard::set_text`.\n- `readImageFromClipboard()` runs in `task::blocking(\"clipboard.read_image\", (), ...)`.\n- Image read returns `null`/`undefined` when `arboard` reports `ContentNotAvailable`.\n- Successful image read re-encodes clipboard RGBA data as PNG and returns `{ data: Uint8Array, mimeType: \"image/png\" }`.\n- Clipboard access or image encoding failures reject/throw as native errors.\n\nThere is no current `packages/natives` TS wrapper that emits OSC52, handles Termux, or suppresses native clipboard failures. Any best-effort clipboard policy must live in consumers.\n\n### Tokens (`tokens`)\n\n- `countTokens(input, encoding?)` accepts a single string or an array of strings.\n- Arrays return one aggregate token count; encoding work is parallelized in Rust.\n- Default encoding is `O200kBase`; `Cl100kBase` is also exported.\n- The implementation uses ordinary encoding, not special-token handling.\n\n### macOS appearance and power helpers\n\n- `detectMacOSAppearance()` returns `\"dark\"`, `\"light\"`, or `null` on non-macOS.\n- `MacAppearanceObserver.start(callback)` returns a handle with `stop()`; on macOS it uses distributed notifications plus a 2-second polling fallback, and on non-macOS it is a no-op observer.\n- `MacOSPowerAssertion.start(options?)` returns a handle with `stop()`; on macOS it acquires an IOKit assertion, and on other platforms it is a no-op handle.\n\n### Windows ProjFS helpers\n\n- `projfsOverlayProbe()` reports whether ProjFS APIs are available.\n- `projfsOverlayStart(lowerRoot, projectionRoot)` starts an overlay.\n- `projfsOverlayStop(projectionRoot)` stops an overlay session.\n\nThese helpers are platform-specific; availability must be checked before relying on overlay behavior.\n\n### Work profiling (`work`)\n\n- **Collection boundary**: profiling samples are produced by `profile_region(tag)` guards in `task::blocking` and `task::future`.\n- **Storage format**: fixed-size circular buffer (`MAX_SAMPLES = 10_000`) storing stack path, duration, and timestamp.\n- **Output boundary**: `getWorkProfile(lastSeconds)` returns:\n  - `folded`: folded-stack text (flamegraph input)\n  - `summary`: markdown table summary\n  - `svg`: optional flamegraph SVG\n  - `totalMs`, `sampleCount`\n\n## Lifecycle and state transitions\n\n### Image lifecycle\n\n1. `PhotonImage.parse(bytes)` schedules a blocking decode task (`image.decode`).\n2. On success, a native `PhotonImage` handle exists in JS.\n3. `resize(...)` creates a new native handle (`image.resize`); old and new handles can coexist.\n4. `encode(...)` schedules `image.encode` and materializes bytes without mutating image dimensions.\n5. `encodeSixel(...)` decodes, optionally resizes to exact target dimensions with Lanczos3, and returns SIXEL text synchronously.\n\nFailure transitions:\n\n- Format detection/decode failure rejects parse promise or throws from SIXEL encoding.\n- Encode failure rejects encode promise.\n- Invalid SIXEL dimensions throw.\n\n### HTML lifecycle\n\n1. `htmlToMarkdown(html, options)` schedules a blocking conversion task.\n2. Conversion runs with defaulted options (`cleanContent=false`, `skipImages=false`) unless specified.\n3. Returns markdown string or rejects.\n\n### Clipboard lifecycle\n\n- Text copy constructs an `arboard::Clipboard` and calls `set_text` synchronously.\n- Image read constructs an `arboard::Clipboard`, calls `get_image`, encodes PNG on success, maps `ContentNotAvailable` to `None`, and rejects other errors.\n\n### Work profiling lifecycle\n\n1. No explicit start: profiling is active when task helpers execute.\n2. Every instrumented task scope records one sample on guard drop.\n3. Samples overwrite oldest entries after buffer capacity is reached.\n4. `getWorkProfile(lastSeconds)` reads a time window and derives folded/summary/svg artifacts.\n\nFailure transitions:\n\n- SVG generation failure is soft (`svg` omitted/undefined), while folded and summary still return.\n- Empty sample windows return empty folded data and no SVG, not an error.\n\n## Unsupported operations and error propagation\n\n### Image\n\n- Unsupported decode input or corrupted bytes: strict failure.\n- Invalid SIXEL target dimensions: strict failure.\n- No JS fallback path in the natives package.\n\n### HTML\n\n- Conversion errors are strict failures.\n- Option omission is defaulting, not failure.\n\n### Clipboard\n\n- Text copy is strict at the native API surface.\n- Image read distinguishes \"no image\" (`null`/`undefined`) from operational failure (rejection).\n\n### Work profiling\n\n- Retrieval is strict for the function call itself.\n- Flamegraph SVG generation is nullable/optional.\n- Buffer truncation is expected ring-buffer behavior.\n\n## Platform caveats\n\n- Clipboard access depends on OS/session support exposed through `arboard`.\n- macOS appearance and power helpers intentionally return no-op/null behavior on unsupported platforms.\n- ProjFS helpers are Windows-specific and should be gated by `projfsOverlayProbe()`.\n",
+	"natives-media-system-utils.md": "# Natives media + system utilities\n\nThis document covers the media/system/conversion exports in `@gajae-code/natives`: image processing, HTML conversion, clipboard access, token counting, macOS appearance/power helpers, ProjFS helpers, and work profiling.\n\n## Implementation files\n\n- `crates/pi-natives/src/image.rs`\n- `crates/pi-natives/src/html.rs`\n- `crates/pi-natives/src/clipboard.rs`\n- `crates/pi-natives/src/tokens.rs`\n- `crates/pi-natives/src/appearance.rs`\n- `crates/pi-natives/src/power.rs`\n- `crates/pi-natives/src/projfs_overlay.rs`\n- `crates/pi-natives/src/prof.rs`\n- `crates/pi-natives/src/task.rs`\n- `packages/natives/native/index.d.ts`\n\n> Note: there is no `crates/pi-natives/src/work.rs`; work profiling is implemented in `prof.rs` and fed by instrumentation in `task.rs`.\n\n## JS API ↔ Rust export/module mapping\n\n| JS export                                           | Rust N-API export              | Rust module         |\n| --------------------------------------------------- | ------------------------------ | ------------------- |\n| `PhotonImage.parse(bytes)`                          | `PhotonImage::parse`           | `image.rs`          |\n| `PhotonImage#resize(width, height, filter)`         | `PhotonImage::resize`          | `image.rs`          |\n| `PhotonImage#encode(format, quality)`               | `PhotonImage::encode`          | `image.rs`          |\n| `encodeSixel(bytes, targetWidthPx, targetHeightPx)` | `encode_sixel`                 | `image.rs`          |\n| `htmlToMarkdown(html, options?)`                    | `html_to_markdown`             | `html.rs`           |\n| `copyToClipboard(text)`                             | `copy_to_clipboard`            | `clipboard.rs`      |\n| `readImageFromClipboard()`                          | `read_image_from_clipboard`    | `clipboard.rs`      |\n| `countTokens(input, encoding?)`                     | `count_tokens`                 | `tokens.rs`         |\n| `detectMacOSAppearance()`                           | `detect_mac_os_appearance`     | `appearance.rs`     |\n| `MacAppearanceObserver.start(callback)`             | `MacAppearanceObserver::start` | `appearance.rs`     |\n| `MacOSPowerAssertion.start(options?)`               | `MacOSPowerAssertion::start`   | `power.rs`          |\n| `projfsOverlayProbe/start/stop`                     | ProjFS exports                 | `projfs_overlay.rs` |\n| `getWorkProfile(lastSeconds)`                       | `get_work_profile`             | `prof.rs`           |\n\n## Data format boundaries and conversions\n\n### Image (`image`)\n\n- **JS input boundary**: `Uint8Array` encoded image bytes for `PhotonImage.parse` and `encodeSixel`.\n- **Rust decode boundary**: bytes are copied/read, format is guessed with `ImageReader::with_guessed_format()`, then decoded to `DynamicImage`.\n- **In-memory state**: `PhotonImage` stores `Arc<DynamicImage>`.\n- **Output boundary**:\n  - `PhotonImage#encode(format, quality)` returns a promise for encoded bytes (`Vec<u8>` in Rust; generated TS currently declares `Promise<Array<number>>`).\n  - `encodeSixel(...)` returns a SIXEL escape string synchronously.\n\nFormat IDs:\n\n- `0`: PNG\n- `1`: JPEG\n- `2`: WebP\n- `3`: GIF\n\nEncoding behavior:\n\n- JPEG uses the provided `quality` with `JpegEncoder::new_with_quality`.\n- WebP uses the `webp` crate encoder with `quality` as `f32` in the same 0..=100 range.\n- PNG/GIF ignore `quality`.\n- Invalid dimensions for SIXEL (`0` width or height) fail with `Target SIXEL dimensions must be greater than zero`.\n\n### HTML conversion (`html`)\n\n- **JS input boundary**: HTML `string` + optional `{ cleanContent?: boolean; skipImages?: boolean }`.\n- **Rust conversion boundary**: conversion is scheduled through `task::blocking(\"html_to_markdown\", (), ...)`.\n- **Output boundary**: Markdown `string` promise.\n\nConversion behavior:\n\n- `cleanContent` defaults to `false`.\n- When `cleanContent=true`, preprocessing uses `PreprocessingPreset::Aggressive` and hard-removal flags for navigation/forms.\n- `skipImages` defaults to `false`.\n\n### Clipboard (`clipboard`)\n\n- `copyToClipboard(text)` is a synchronous native call using `arboard::Clipboard::set_text`.\n- `readImageFromClipboard()` runs in `task::blocking(\"clipboard.read_image\", (), ...)`.\n- Image read returns `null`/`undefined` when `arboard` reports `ContentNotAvailable`.\n- Successful image read re-encodes clipboard RGBA data as PNG and returns `{ data: Uint8Array, mimeType: \"image/png\" }`.\n- Clipboard access or image encoding failures reject/throw as native errors.\n\nThere is no current `packages/natives` TS wrapper that emits OSC52, handles Termux, or suppresses native clipboard failures. Any best-effort clipboard policy must live in consumers.\n\n### Tokens (`tokens`)\n\n- `countTokens(input, encoding?)` accepts a single string or an array of strings.\n- Arrays return one aggregate token count; encoding work is parallelized in Rust.\n- Default encoding is `O200kBase`; `Cl100kBase` remains exported as a compatibility alias that routes to `o200k_base` (the cl100k BPE table is not embedded in default builds).\n- The implementation uses ordinary encoding, not special-token handling.\n\n### macOS appearance and power helpers\n\n- `detectMacOSAppearance()` returns `\"dark\"`, `\"light\"`, or `null` on non-macOS.\n- `MacAppearanceObserver.start(callback)` returns a handle with `stop()`; on macOS it uses distributed notifications plus a 2-second polling fallback, and on non-macOS it is a no-op observer.\n- `MacOSPowerAssertion.start(options?)` returns a handle with `stop()`; on macOS it acquires an IOKit assertion, and on other platforms it is a no-op handle.\n\n### Windows ProjFS helpers\n\n- `projfsOverlayProbe()` reports whether ProjFS APIs are available.\n- `projfsOverlayStart(lowerRoot, projectionRoot)` starts an overlay.\n- `projfsOverlayStop(projectionRoot)` stops an overlay session.\n\nThese helpers are platform-specific; availability must be checked before relying on overlay behavior.\n\n### Work profiling (`work`)\n\n- **Collection boundary**: profiling samples are produced by `profile_region(tag)` guards in `task::blocking` and `task::future`.\n- **Storage format**: fixed-size circular buffer (`MAX_SAMPLES = 10_000`) storing stack path, duration, and timestamp.\n- **Output boundary**: `getWorkProfile(lastSeconds)` returns:\n  - `folded`: folded-stack text (flamegraph input)\n  - `summary`: markdown table summary\n  - `svg`: optional flamegraph SVG\n  - `totalMs`, `sampleCount`\n\n## Lifecycle and state transitions\n\n### Image lifecycle\n\n1. `PhotonImage.parse(bytes)` schedules a blocking decode task (`image.decode`).\n2. On success, a native `PhotonImage` handle exists in JS.\n3. `resize(...)` creates a new native handle (`image.resize`); old and new handles can coexist.\n4. `encode(...)` schedules `image.encode` and materializes bytes without mutating image dimensions.\n5. `encodeSixel(...)` decodes, optionally resizes to exact target dimensions with Lanczos3, and returns SIXEL text synchronously.\n\nFailure transitions:\n\n- Format detection/decode failure rejects parse promise or throws from SIXEL encoding.\n- Encode failure rejects encode promise.\n- Invalid SIXEL dimensions throw.\n\n### HTML lifecycle\n\n1. `htmlToMarkdown(html, options)` schedules a blocking conversion task.\n2. Conversion runs with defaulted options (`cleanContent=false`, `skipImages=false`) unless specified.\n3. Returns markdown string or rejects.\n\n### Clipboard lifecycle\n\n- Text copy constructs an `arboard::Clipboard` and calls `set_text` synchronously.\n- Image read constructs an `arboard::Clipboard`, calls `get_image`, encodes PNG on success, maps `ContentNotAvailable` to `None`, and rejects other errors.\n\n### Work profiling lifecycle\n\n1. No explicit start: profiling is active when task helpers execute.\n2. Every instrumented task scope records one sample on guard drop.\n3. Samples overwrite oldest entries after buffer capacity is reached.\n4. `getWorkProfile(lastSeconds)` reads a time window and derives folded/summary/svg artifacts.\n\nFailure transitions:\n\n- SVG generation failure is soft (`svg` omitted/undefined), while folded and summary still return.\n- Empty sample windows return empty folded data and no SVG, not an error.\n\n## Unsupported operations and error propagation\n\n### Image\n\n- Unsupported decode input or corrupted bytes: strict failure.\n- Invalid SIXEL target dimensions: strict failure.\n- No JS fallback path in the natives package.\n\n### HTML\n\n- Conversion errors are strict failures.\n- Option omission is defaulting, not failure.\n\n### Clipboard\n\n- Text copy is strict at the native API surface.\n- Image read distinguishes \"no image\" (`null`/`undefined`) from operational failure (rejection).\n\n### Work profiling\n\n- Retrieval is strict for the function call itself.\n- Flamegraph SVG generation is nullable/optional.\n- Buffer truncation is expected ring-buffer behavior.\n\n## Platform caveats\n\n- Clipboard access depends on OS/session support exposed through `arboard`.\n- macOS appearance and power helpers intentionally return no-op/null behavior on unsupported platforms.\n- ProjFS helpers are Windows-specific and should be gated by `projfsOverlayProbe()`.\n",
 	"natives-rust-task-cancellation.md": "# Native Rust task execution and cancellation (`pi-natives`)\n\nThis document describes how `crates/pi-natives` schedules native work and how cancellation flows from JS options (`timeoutMs`, `AbortSignal`) into Rust execution.\n\n## Implementation files\n\n- `crates/pi-natives/src/task.rs`\n- `crates/pi-natives/src/grep.rs`\n- `crates/pi-natives/src/glob.rs`\n- `crates/pi-natives/src/fd.rs`\n- `crates/pi-natives/src/ast.rs`\n- `crates/pi-natives/src/shell.rs`\n- `crates/pi-natives/src/pty.rs`\n- `crates/pi-natives/src/html.rs`\n- `crates/pi-natives/src/image.rs`\n- `crates/pi-natives/src/clipboard.rs`\n- `crates/pi-natives/src/text.rs`\n- `crates/pi-natives/src/ps.rs`\n\n## Core primitives (`task.rs`)\n\n`task.rs` defines:\n\n1. `task::blocking(tag, cancel_token, work)`\n   - Wraps `napi::AsyncTask` / `Task`.\n   - `compute()` runs on libuv worker threads.\n   - Returns a JS `Promise<T>` for exported functions.\n   - Records a profiling sample through `profile_region(tag)`.\n\n2. `task::future(env, tag, work)`\n   - Wraps `env.spawn_future(...)`.\n   - Runs async work on Tokio's runtime.\n   - Returns `PromiseRaw<'env, T>`.\n   - Records a profiling sample through `profile_region(tag)`.\n\n3. `CancelToken` / `AbortToken` / `AbortReason`\n   - `CancelToken::new(timeout_ms, signal)` combines an optional deadline and optional JS `AbortSignal` converted from `Unknown`.\n   - `CancelToken::heartbeat()` is cooperative cancellation for blocking loops.\n   - `CancelToken::wait()` asynchronously waits for signal, timeout, or Ctrl-C.\n   - `CancelToken::emplace_abort_token()` creates an abortable flag when a later `Shell.abort()`/internal bridge needs one.\n   - `AbortToken::abort(reason)` lets external code request abort.\n\n## `blocking` vs `future`: execution model and selection\n\n### Use `task::blocking`\n\nUse when work is CPU-heavy or fundamentally synchronous/blocking:\n\n- regex/file scanning (`grep`, `glob`, `fuzzyFind`)\n- ast-grep search/edit worker work\n- PTY loop internals through `tokio::task::spawn_blocking`\n- image decode/resize/encode\n- HTML conversion\n- clipboard image read\n\nBehavior:\n\n- Work closure receives a cloned `CancelToken`.\n- Cancellation is only observed where code checks `ct.heartbeat()?`.\n- Closure `Err(...)` rejects the JS promise.\n\n### Use `task::future`\n\nUse when work must `await` async operations:\n\n- shell session orchestration (`Shell.run`, `executeShell`)\n- PTY outer promise (`PtySession.start`) before it enters `spawn_blocking`\n- task racing (`tokio::select!`) between completion and cancellation\n\nBehavior:\n\n- Future code can race normal completion against `ct.wait()`.\n- On cancel path, async implementations typically cancel subordinate machinery and may force-abort after a grace timeout.\n\n## JS API ↔ Rust export mapping (task/cancel relevant)\n\n| JS-facing API                           | Rust export                          | Scheduler                                                      | Cancellation hookup                                                                      |\n| --------------------------------------- | ------------------------------------ | -------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |\n| `grep(options, onMatch?)`               | `grep`                               | `task::blocking(\"grep\", ct, ...)`                              | `CancelToken::new(options.timeoutMs, options.signal)` + heartbeat checks                 |\n| `glob(options, onMatch?)`               | `glob`                               | `task::blocking(\"glob\", ct, ...)`                              | `CancelToken::new(...)` + heartbeat checks                                               |\n| `fuzzyFind(options)`                    | `fuzzy_find`                         | `task::blocking(\"fuzzy_find\", ct, ...)`                        | `CancelToken::new(...)` + heartbeat checks                                               |\n| `astGrep(options)` / `astEdit(options)` | ast exports                          | blocking worker path                                           | timeout/signal fields are accepted by options and checked cooperatively in worker loops  |\n| `Shell#run(options, onChunk?)`          | `Shell::run`                         | `task::future(env, \"shell.run\", ...)`                          | `ct.wait()` raced against run task; bridges to Tokio cancellation token and `AbortToken` |\n| `executeShell(options, onChunk?)`       | `execute_shell`                      | `task::future(env, \"shell.execute\", ...)`                      | same cancel race and 2s graceful window                                                  |\n| `PtySession#start(options, onChunk?)`   | `PtySession::start`                  | `task::future(env, \"pty.start\", ...)` + inner `spawn_blocking` | `CancelToken` checked in sync PTY loop via `heartbeat()`                                 |\n| `htmlToMarkdown(html, options?)`        | `html_to_markdown`                   | `task::blocking(\"html_to_markdown\", (), ...)`                  | none (`()` token)                                                                        |\n| `PhotonImage.parse/encode/resize`       | `PhotonImage::{parse,encode,resize}` | `task::blocking(...)`                                          | none (`()` token)                                                                        |\n| `readImageFromClipboard()`              | `read_image_from_clipboard`          | `task::blocking(\"clipboard.read_image\", (), ...)`              | none (`()` token)                                                                        |\n\n`text.rs`, `tokens.rs`, `keys.rs`, most `ps.rs` functions, and synchronous utility exports do not use `task::blocking`/`task::future` and therefore do not participate in this cancellation path.\n\n## Cancellation lifecycle and state transitions\n\n### `CancelToken` lifecycle\n\n```text\nCreated\n  ├─ no signal + no timeout  -> passive token\n  ├─ signal registered        -> AbortSignal callback can set AbortReason::Signal\n  └─ deadline set             -> timeout check becomes active\n\nRunning\n  ├─ heartbeat()/wait() sees signal   -> AbortReason::Signal\n  ├─ heartbeat()/wait() sees deadline -> AbortReason::Timeout\n  ├─ wait() sees Ctrl-C               -> AbortReason::User\n  └─ no abort                         -> continue\n\nAborted\n  └─ flag stores first observed cause for waiters; heartbeat formats it as \"Aborted: <reason>\"\n```\n\n### Before-start vs mid-execution cancellation\n\n- **Before start / before first cancellation check**:\n  - `task::future` users that race on `ct.wait()` can resolve cancellation once they enter `select!`.\n  - `task::blocking` users only observe cancellation when closure code reaches `heartbeat()`.\n\n- **Mid-execution**:\n  - `blocking`: next `heartbeat()` returns `Err(\"Aborted: ...\")`.\n  - `future`: `ct.wait()` branch wins `select!`, then code cancels subordinate async machinery.\n  - shell: cancellation triggers a Tokio cancellation token, waits up to 2 seconds, then aborts the task if needed.\n  - PTY: heartbeat failure or `kill()` terminates PTY child/process tree and drains output briefly.\n\n## Heartbeat expectations for long-running loops\n\n`heartbeat()` must run at predictable cadence in loops with unbounded or large work sets.\n\nObserved patterns:\n\n- `glob` filtering checks entries during scan/filter work.\n- `fd` scoring checks scanned candidates.\n- `grep` checks before/during expensive search and passes tokens into shared scan/cache helpers.\n- `run_pty_sync` checks every loop tick with a maximum 16ms wait cadence.\n\nPractical rule: no loop over external-size input should exceed a short bounded interval without a heartbeat.\n\n## Failure behavior and error propagation to JS\n\n### Blocking tasks\n\nError path:\n\n1. Closure returns `Err(napi::Error)` (including `heartbeat()` abort).\n2. `Task::compute()` returns `Err`.\n3. `AsyncTask` rejects JS promise.\n\nTypical error strings:\n\n- `Aborted: Timeout`\n- `Aborted: Signal`\n- domain errors (`Failed to decode image: ...`, `Conversion error: ...`, etc.)\n\n### Future tasks\n\nError path:\n\n1. Async body returns `Err(napi::Error)` or join failure is mapped (`... task failed: {err}`).\n2. `task::future`-spawned promise rejects.\n3. Shell and PTY command APIs model cancellation as structured results instead of rejection when the cancellation path wins: `exitCode` omitted, `cancelled` or `timedOut` set.\n\n### Cancellation reporting split\n\n- **Abort as error**: blocking exports using `heartbeat()?`.\n- **Abort as typed result**: shell/PTY command APIs that model cancellation in result structs.\n\nChoose one model per API and document it explicitly.\n\n## Common pitfalls\n\n1. **Missing heartbeat in blocking loops**\n   - Symptom: timeout/signal appears ignored until loop ends.\n   - Fix: add `ct.heartbeat()?` at loop top and before expensive per-item steps.\n\n2. **Long uncancelable sections**\n   - Symptom: cancellation latency spikes during single large call (decode, sort, compression, parser invocation, etc.).\n   - Fix: split work into chunks with heartbeat boundaries; if impossible, document latency.\n\n3. **Blocking async executor**\n   - Symptom: async API stalls when sync-heavy code runs directly in future.\n   - Fix: move CPU/sync blocks to `task::blocking` or `tokio::task::spawn_blocking`.\n\n4. **Inconsistent cancel semantics**\n   - Symptom: one API rejects on cancel, another resolves with flags, confusing callers.\n   - Fix: standardize per domain and keep docs aligned.\n\n5. **Forgetting cancellation bridge in nested async tasks**\n   - Symptom: outer token is cancelled but inner readers/subprocess tasks keep running.\n   - Fix: bridge cancellation to inner token/signal and enforce grace timeout + forced abort fallback.\n\n## Checklist for new cancellable exports\n\n1. Classify work correctly:\n   - CPU-bound or sync blocking -> `task::blocking`.\n   - async I/O / `await` orchestration -> `task::future`.\n\n2. Expose cancel inputs when needed:\n   - include `timeoutMs` and `signal` in `#[napi(object)]` options,\n   - create `let ct = task::CancelToken::new(timeout_ms, signal);`.\n\n3. Wire cancellation through all layers:\n   - blocking loops: `ct.heartbeat()?` at stable intervals,\n   - async orchestration: race with `ct.wait()` and cancel sub-tasks/tokens.\n\n4. Decide cancellation contract:\n   - reject promise with abort error, or\n   - resolve typed `{ cancelled, timedOut, ... }`,\n   - keep this contract consistent for the API family.\n\n5. Propagate failures with context:\n   - map errors via `Error::from_reason(format!(\"...: {err}\"))`,\n   - include stage-specific prefixes (`spawn`, `decode`, `wait`, etc.).\n\n6. Handle before-start and mid-flight cancellation:\n   - cancellation check/await must happen before expensive body and during long execution.\n\n7. Validate no executor misuse:\n   - no long sync work directly inside async futures without `spawn_blocking`/blocking task wrapper.\n",
 	"natives-shell-pty-process.md": "# Natives Shell, PTY, Process, and Key Internals\n\nThis document covers the execution/process/terminal primitives in `@gajae-code/natives`: `shell`, `pty`, `ps`, and `keys`, using the architecture terms from `docs/natives-architecture.md`.\n\n## Implementation files\n\n- `crates/pi-natives/src/shell.rs`\n- `crates/pi-natives/src/shell/windows.rs` (Windows-only PATH enrichment)\n- `crates/pi-natives/src/pty.rs`\n- `crates/pi-natives/src/ps.rs`\n- `crates/pi-natives/src/keys.rs`\n- `crates/pi-natives/src/task.rs`\n- `packages/natives/native/index.d.ts`\n\n## Layer ownership\n\n- **Package entrypoint** (`packages/natives/native/index.js`): loads the `.node` addon and exports generated N-API bindings.\n- **Rust N-API module layer** (`crates/pi-natives/src/*`): shell/PTY process execution, process-tree traversal/termination, and key-sequence parsing.\n- **Consumers** (`packages/coding-agent`, `packages/tui`): higher-level session policy, output artifact/minimizer handling, render policy, and UI key handling.\n\n## Shell subsystem (`shell`)\n\n### API model\n\nTwo execution modes are exposed:\n\n1. **One-shot** via `executeShell(options, onChunk?)`.\n2. **Persistent session** via `new Shell(options?)` then `shell.run(...)` repeatedly.\n\nBoth stream output through a threadsafe callback and return `{ exitCode?, cancelled, timedOut, minimized? }`.\n\n`ShellOptions` supports `sessionEnv`, `snapshotPath`, and optional output `minimizer`. `ShellExecuteOptions` supports command-scoped `env`, session-level `sessionEnv`, `snapshotPath`, timeout/signal, and optional minimizer. `ShellRunOptions` supports command, cwd, command-scoped env, timeout, and signal.\n\n### Session creation and environment model\n\nRust creates `brush_core::Shell` with:\n\n- non-interactive, non-login mode,\n- `no_profile` and `no_rc`,\n- `do_not_inherit_env: true`,\n- bash-mode builtins, with `exec` and `suspend` disabled,\n- explicit environment reconstruction from host env,\n- skip-list for shell-sensitive vars (`PS1`, `PWD`, `SHLVL`, bash function exports, etc.).\n\nSession env behavior:\n\n- `ShellOptions.sessionEnv` / one-shot `sessionEnv` is applied at session creation.\n- `ShellRunOptions.env` / one-shot `env` is command-scoped (`EnvironmentScope::Command`) and popped after the command.\n- `PATH` is merged specially on Windows with case-insensitive dedupe.\n- Windows-only path enrichment (`shell/windows.rs`) appends discovered Git-for-Windows paths when present and not already included.\n- `snapshotPath`, when present, is sourced during session creation with stdout/stderr/stdin wired to null files.\n\n### Runtime lifecycle and state transitions\n\nPersistent shell (`Shell.run`) uses this state machine:\n\n- **Idle/Uninitialized**: `session: None`.\n- **Running**: first `run()` lazily creates a session, stores an abort token, executes command.\n- **Completed + keepalive**: if execution control flow is normal, abort state is cleared and session is reused.\n- **Completed + teardown**: if control flow is loop/script/shell-exit related, session is dropped.\n- **Cancelled/Timed out**: run task is cancelled, grace wait is 2 seconds, task may be force-aborted, session is dropped if lock can be acquired.\n- **Error**: session is dropped.\n\nOne-shot shell (`executeShell`) always creates and drops a fresh session per call.\n\n### Streaming/output and minimizer behavior\n\n- Stdout/stderr are routed into a shared pipe and read concurrently.\n- Reader decodes UTF-8 incrementally; invalid byte sequences emit `U+FFFD` replacement chunks.\n- The command runs in a new process group policy.\n- Optional minimizer configuration can capture and rewrite output. When minimization occurs, the result includes `minimized` with filter name, replacement text, original text, and byte counts.\n- Consumers are responsible for persisting or displaying minimizer artifacts; the native result only carries the data.\n\n### Cancellation, timeout, and abort\n\n- `CancelToken` is constructed from `timeoutMs` and optional `AbortSignal`.\n- On cancellation/timeout, shell cancellation token is triggered, then task gets a 2-second graceful window before forced abort.\n- Structured result flags are used:\n  - timeout -> `exitCode` omitted, `timedOut: true`.\n  - abort signal / `Shell.abort()` -> `exitCode` omitted, `cancelled: true`.\n\n`Shell.abort()` behavior:\n\n- aborts the current running command for that `Shell` instance through the stored `AbortToken`,\n- resolves successfully even when nothing is running.\n\n### Failure behavior\n\nCommon surfaced errors include:\n\n- session init failures (`Failed to initialize shell`),\n- cwd errors (`Failed to set cwd`),\n- env set/pop failures,\n- snapshot source failures (`Failed to source snapshot`),\n- pipe creation/clone failures,\n- execution failure (`Shell execution failed: ...`),\n- task wrapper failures (`Shell execution task failed: ...`).\n\n## PTY subsystem (`pty`)\n\n### API model\n\n`new PtySession()` exposes:\n\n- `start(options, onChunk?) -> Promise<{ exitCode?, cancelled, timedOut }>`\n- `write(data)`\n- `resize(cols, rows)`\n- `kill()`\n\n`PtyStartOptions` supports `command`, optional `cwd`, optional `env`, `timeoutMs`, `signal`, `cols`, and `rows`.\n\n### Runtime lifecycle and state transitions\n\n`PtySession` state machine:\n\n- **Idle**: `core: None`.\n- **Reserved**: `start()` installs control channel synchronously (`core: Some`) before async work begins, so `write/resize/kill` become immediately valid.\n- **Running**: blocking PTY loop handles child state, reader events, cancellation heartbeat, and control messages.\n- **Terminal closed / drain**: child exit or cancellation starts a short reader drain window.\n- **Finalized**: `core` is always reset to `None` after start task completion (success or error).\n\nConcurrency guard:\n\n- starting while already running returns `PTY session already running`.\n\n### Spawn/attach/write/read/terminate patterns\n\n- PTY opened via `portable_pty::native_pty_system().openpty(...)`.\n- Command currently runs as `sh -lc <command>` with optional `cwd` and env overrides.\n- Default size is `120x40`; dimensions are clamped (`cols 20..400`, `rows 5..200`).\n- `write()` sends raw bytes to PTY stdin.\n- `resize()` sends a control message and clamps dimensions again.\n- `kill()` sends a control message that marks the run cancelled and terminates the child/process tree.\n\nOutput path:\n\n- dedicated reader thread reads master stream,\n- incremental UTF-8 decode emits `U+FFFD` for invalid bytes,\n- chunks forwarded through N-API threadsafe callback.\n\nTermination path:\n\n- Unix: terminate process group when known, terminate child tree, call child kill, then repeat with SIGKILL.\n- Non-Unix: terminate child tree, call child kill, then repeat with SIGKILL-equivalent process-tree helper.\n\n### Cancellation and timeout semantics\n\n- `timeoutMs` and `AbortSignal` feed a `CancelToken`.\n- Loop calls `ct.heartbeat()` periodically with a 16ms maximum wait cadence.\n- Timeout classification is based on the heartbeat error string containing `Timeout`.\n- Cancellation/kill starts a 300ms post-cancel drain window; normal child exit starts a 300ms post-exit drain window.\n\n### Failure behavior\n\nError surfaces include:\n\n- PTY allocation/open failure,\n- PTY spawn failure,\n- writer/reader acquisition failure,\n- child status/wait failures,\n- lock poisoning,\n- control-channel disconnection (`PTY session is no longer available`).\n\nControl call failures when not running:\n\n- `write/resize/kill` return `PTY session is not running`.\n\n## Process-tree subsystem (`ps`)\n\n### API model\n\n- `killTree(pid, signal) -> number`\n- `listDescendants(pid) -> number[]`\n\n### Platform-specific implementation\n\n- **Linux**: recursively reads `/proc/<pid>/task/<pid>/children`.\n- **macOS**: uses `libproc` `proc_listchildpids`.\n- **Windows**: snapshots process table with `CreateToolhelp32Snapshot`, builds parent->children map, terminates with `OpenProcess(PROCESS_TERMINATE)` + `TerminateProcess`.\n\n### Kill-tree behavior\n\n- Descendants are collected recursively.\n- Kill order is bottom-up (deepest descendants first).\n- Root pid is killed last.\n- Return value is count of successful terminations.\n\nSignal behavior:\n\n- POSIX: provided `signal` is passed to `kill`.\n- Windows: `signal` is ignored; termination is unconditional process terminate.\n\n### Failure behavior\n\nThis module is intentionally non-throwing at API surface for ordinary process misses:\n\n- missing/inaccessible process tree branches are skipped,\n- per-pid kill failures are counted as unsuccessful,\n- lookup miss typically yields `[]` from `listDescendants` and `0` from `killTree`.\n\n## Key parsing subsystem (`keys`)\n\n### API model\n\nExposed helpers:\n\n- `parseKey(data, kittyProtocolActive)`\n- `matchesKey(data, keyId, kittyProtocolActive)`\n- `parseKittySequence(data)`\n- `matchesKittySequence(data, expectedCodepoint, expectedModifier)`\n- `matchesLegacySequence(data, keyName)`\n\n### Parsing model\n\nThe parser combines:\n\n- direct single-byte mappings (`enter`, `tab`, `ctrl+<letter>`, printable ASCII),\n- O(1) legacy escape-sequence lookup (PHF map),\n- xterm `modifyOtherKeys` parsing,\n- Kitty protocol parsing (`CSI u`, `CSI ~`, `CSI 1;...<letter>`),\n- normalization to key IDs (`ctrl+c`, `shift+tab`, `pageUp`, `f5`, etc.).\n\nModifier handling:\n\n- only shift/alt/ctrl bits are compared for key matching,\n- lock bits are masked out before comparisons.\n\nLayout behavior:\n\n- base-layout fallback is intentionally constrained so remapped layouts do not create false matches for ASCII letters/symbols.\n\n### Failure behavior\n\n- Unrecognized or invalid sequences produce `null` from parse functions.\n- Match functions return `false` on parse failure or mismatch.\n- No thrown error surface for malformed key input.\n\n## JS API ↔ Rust export mapping\n\n### Shell + PTY + Process\n\n| JS API                            | Rust N-API export                      | Notes                                     |\n| --------------------------------- | -------------------------------------- | ----------------------------------------- |\n| `executeShell(options, onChunk?)` | `executeShell` (`execute_shell`)       | One-shot shell execution                  |\n| `new Shell(options?)`             | `Shell` class                          | Persistent shell session                  |\n| `shell.run(options, onChunk?)`    | `Shell::run`                           | Reuses session on keepalive control flow  |\n| `shell.abort()`                   | `Shell::abort`                         | Aborts active run for that shell instance |\n| `new PtySession()`                | `PtySession` class                     | Stateful PTY session                      |\n| `pty.start(options, onChunk?)`    | `PtySession::start`                    | Interactive PTY run                       |\n| `pty.write(data)`                 | `PtySession::write`                    | Raw stdin passthrough                     |\n| `pty.resize(cols, rows)`          | `PtySession::resize`                   | Clamped terminal dimensions               |\n| `pty.kill()`                      | `PtySession::kill`                     | Force-kills active PTY child              |\n| `killTree(pid, signal)`           | `killTree` (`kill_tree`)               | Children-first process tree termination   |\n| `listDescendants(pid)`            | `listDescendants` (`list_descendants`) | Recursive descendants listing             |\n\n### Keys\n\n| JS API                                         | Rust N-API export                                   | Notes                           |\n| ---------------------------------------------- | --------------------------------------------------- | ------------------------------- |\n| `matchesKittySequence(data, cp, mod)`          | `matchesKittySequence` (`matches_kitty_sequence`)   | Kitty codepoint+modifier match  |\n| `parseKey(data, kittyProtocolActive)`          | `parseKey` (`parse_key`)                            | Normalized key-id parser        |\n| `matchesLegacySequence(data, keyName)`         | `matchesLegacySequence` (`matches_legacy_sequence`) | Exact legacy sequence map check |\n| `parseKittySequence(data)`                     | `parseKittySequence` (`parse_kitty_sequence`)       | Structured Kitty parse result   |\n| `matchesKey(data, keyId, kittyProtocolActive)` | `matchesKey` (`matches_key`)                        | High-level key matcher          |\n\n## Abandoned session cleanup and finalization notes\n\n- **Shell persistent session**: if a run is cancelled/timed out/errors/non-keepalive control flow, Rust drops the internal session state. Successful normal runs keep the session for reuse.\n- **PTY session**: `core` is always cleared after `start()` finishes, including failure paths.\n- **No explicit JS finalizer-driven kill contract** is exposed by wrappers; cleanup is primarily tied to run completion/cancellation paths. Callers should use `timeoutMs`, `AbortSignal`, `shell.abort()`, or `pty.kill()` for deterministic teardown.\n",
-	"natives-text-search-pipeline.md": "# Natives Text/Search Pipeline\n\nThis document maps the `@gajae-code/natives` text/search/code surface from generated JS/TS exports to Rust N-API modules and back to JS result objects.\n\nTerminology follows `docs/natives-architecture.md`:\n\n- **Generated binding**: public API in `packages/natives/native/index.d.ts`.\n- **Rust module layer**: N-API exports in `crates/pi-natives/src/*`.\n- **Shared scan cache**: `fs_cache`-backed directory-entry cache used by discovery/search flows.\n\n## Implementation files\n\n- `packages/natives/native/index.d.ts`\n- `crates/pi-natives/src/grep.rs`\n- `crates/pi-natives/src/glob.rs`\n- `crates/pi-natives/src/glob_util.rs`\n- `crates/pi-natives/src/fs_cache.rs`\n- `crates/pi-natives/src/fd.rs`\n- `crates/pi-natives/src/ast.rs`\n- `crates/pi-natives/src/text.rs`\n- `crates/pi-natives/src/highlight.rs`\n- `crates/pi-natives/src/tokens.rs`\n\n## JS API ↔ Rust export mapping\n\n| JS API                                                                          | Rust export (`#[napi]`, snake_case -> camelCase) | Rust module    |\n| ------------------------------------------------------------------------------- | ------------------------------------------------ | -------------- |\n| `grep(options, onMatch?)`                                                       | `grep`                                           | `grep.rs`      |\n| `search(content, options)`                                                      | `search`                                         | `grep.rs`      |\n| `hasMatch(content, pattern, ignoreCase?, multiline?)`                           | `hasMatch`                                       | `grep.rs`      |\n| `fuzzyFind(options)`                                                            | `fuzzyFind`                                      | `fd.rs`        |\n| `glob(options, onMatch?)`                                                       | `glob`                                           | `glob.rs`      |\n| `invalidateFsScanCache(path?)`                                                  | `invalidateFsScanCache`                          | `fs_cache.rs`  |\n| `astGrep(options)`                                                              | `astGrep`                                        | `ast.rs`       |\n| `astEdit(options)`                                                              | `astEdit`                                        | `ast.rs`       |\n| `wrapTextWithAnsi(text, width, tabWidth)`                                       | `wrapTextWithAnsi`                               | `text.rs`      |\n| `truncateToWidth(text, maxWidth, ellipsis, pad, tabWidth)`                      | `truncateToWidth`                                | `text.rs`      |\n| `sliceWithWidth(line, startCol, length, strict, tabWidth)`                      | `sliceWithWidth`                                 | `text.rs`      |\n| `extractSegments(line, beforeEnd, afterStart, afterLen, strictAfter, tabWidth)` | `extractSegments`                                | `text.rs`      |\n| `visibleWidth(text, tabWidth)`                                                  | `visibleWidth`                                   | `text.rs`      |\n| `highlightCode(code, lang, colors)`                                             | `highlightCode`                                  | `highlight.rs` |\n| `supportsLanguage(lang)`                                                        | `supportsLanguage`                               | `highlight.rs` |\n| `getSupportedLanguages()`                                                       | `getSupportedLanguages`                          | `highlight.rs` |\n| `countTokens(input, encoding?)`                                                 | `countTokens`                                    | `tokens.rs`    |\n\n## Pipeline overview by subsystem\n\n## 1) Regex search (`grep`, `search`, `hasMatch`)\n\n### Input/options flow\n\n1. Callers invoke generated native exports directly; there is no package-local TS wrapper that renames `search` to `searchContent`.\n2. Rust option structs in `grep.rs` deserialize camelCase fields (`ignoreCase`, `maxCount`, `contextBefore`, `contextAfter`, `maxColumns`, `timeoutMs`).\n3. `grep` creates `CancelToken` from `timeoutMs` + `AbortSignal` and runs inside `task::blocking(\"grep\", ...)`.\n4. `search` and `hasMatch` operate on provided string/`Uint8Array` content and do not scan the filesystem.\n\n### Execution branches\n\n- **In-memory branch**\n  - `search` -> `search_sync` / search helpers over provided content bytes.\n  - `hasMatch` compiles/checks pattern against provided content and returns a boolean.\n  - No filesystem scan, no `fs_cache`.\n- **Single-file branch**\n  - `grep` resolves path, checks metadata is file, and searches that file.\n- **Directory branch**\n  - Optional cache lookup via `fs_cache::get_or_scan` when `cache: true`.\n  - Fresh scan via `fs_cache::force_rescan` when `cache: false`.\n  - Optional empty-result recheck when cached results are older than the empty-result recheck threshold.\n  - Entry filtering: file-only + optional glob filter (`glob_util`) + optional type filter mapping (`js`, `ts`, `rust`, etc.).\n\n### Search/collection semantics\n\n- Regex engine: `grep_regex::RegexMatcherBuilder` with `ignoreCase` and `multiline`.\n- Context resolution:\n  - `contextBefore/contextAfter` override legacy `context`.\n  - Non-content modes do not collect context.\n- Output modes:\n  - `content` -> one `GrepMatch` per hit.\n  - `count` and `filesWithMatches` map to count-style entries (`lineNumber=0`, `line=\"\"`, `matchCount` set).\n- Limits:\n  - Global `offset` and `maxCount` apply across files.\n  - Parallel path is used only when `maxCount` is unset and `offset == 0`; otherwise sequential path preserves deterministic global offset/limit semantics.\n\n### Result shaping back to JS\n\n- Rust `SearchResult`/`GrepResult` fields map to TS interfaces via N-API object conversion.\n- Counters are clamped before crossing N-API where needed.\n- `GrepResult.limitReached` is optional and emitted when true.\n- Streaming callback receives each shaped `GrepMatch` for content or count-style entries.\n\n### Failure behavior\n\n- `search` returns `SearchResult.error` for regex/search failures instead of throwing.\n- `grep` rejects on hard errors such as invalid path, invalid glob/regex, or cancellation timeout/abort.\n- `hasMatch` returns a boolean on success and throws on invalid pattern/UTF-8 conversion errors.\n- File open/search errors in multi-file scans are skipped per-file; scan continues.\n\n### Malformed regex handling\n\n`grep.rs` sanitizes braces before regex compile:\n\n- Invalid repetition-like braces are escaped (`{`/`}` -> `\\{`/`\\}`) when they cannot form `{N}`, `{N,}`, `{N,M}`.\n- This prevents common literal-template fragments (for example `${platform}`) from failing as malformed repetition.\n- Remaining invalid regex syntax still returns a regex error.\n\n## 2) File discovery (`glob`) and fuzzy path search (`fuzzyFind`)\n\n`glob` and `fuzzyFind` share `fs_cache` scans; matching logic differs.\n\n### `glob` flow\n\n1. Caller passes `GlobOptions` directly. `pattern` and `path` are required in the generated type.\n2. Rust resolves the search path and compiles pattern via `glob_util::compile_glob`.\n3. Entry source:\n   - `cache=true` -> `get_or_scan` + optional stale-empty `force_rescan`.\n   - `cache=false` -> `force_rescan(..., store=false)` (fresh only).\n4. Filtering:\n   - skip `.git` always;\n   - skip `node_modules` unless requested (`includeNodeModules`) or pattern mentions `node_modules`;\n   - apply glob match;\n   - apply file-type filter; symlink `file`/`dir` filters resolve target metadata.\n5. Optional sort by mtime descending (`sortByMtime`) before truncating to `maxResults`.\n\n### `fuzzyFind` flow\n\n1. Rust implementation lives in `fd.rs`; generated export is `fuzzyFind`.\n2. Shared scan source from `fs_cache` with the same cache/no-cache split and stale-empty recheck policy.\n3. Scoring:\n   - exact / starts-with / contains / subsequence-based fuzzy score;\n   - separator/punctuation-normalized scoring path;\n   - directory bonus and deterministic tie-break (`score desc`, then `path asc`).\n4. Symlink entries are excluded from fuzzy results.\n\n### Failure behavior\n\n- Invalid glob pattern returns an error from `glob_util::compile_glob`.\n- Search root must resolve to an existing directory for directory discovery flows.\n- Cancellation/timeouts propagate as abort errors via `CancelToken::heartbeat()` checks in loops.\n\n### Malformed glob handling\n\n`glob_util::build_glob_pattern` is tolerant:\n\n- normalizes `\\` to `/`,\n- auto-prefixes simple recursive patterns with `**/` when `recursive=true`,\n- auto-closes unbalanced `{...` alternation groups before compile.\n\n## 3) AST search/edit (`astGrep`, `astEdit`)\n\n`ast.rs` exposes syntax-aware code search and rewrite operations.\n\n- `astGrep(options)` returns matches with byte/line/column coordinates and optional metavariable bindings.\n- `astEdit(options)` returns replacement changes, per-file counts, searched/touched file counts, parse errors, and whether edits were applied.\n- `dryRun` defaults to true for edit options in the generated documentation.\n- Options include language override, path/glob/selector, strictness, limits, parse-error policy, `signal`, and `timeoutMs`.\n\nThese exports are direct native APIs used by tooling; they are not mediated by a TS wrapper in `packages/natives`.\n\n## 4) Shared scan/cache lifecycle (`fs_cache`)\n\n`fs_cache` stores scan results as normalized relative entries (`path`, `fileType`, optional `mtime`) keyed by:\n\n- canonical search root,\n- `include_hidden`,\n- `use_gitignore`.\n\n### Cache state transitions\n\n1. **Miss / disabled**\n   - TTL is `0` or key absent/expired -> fresh collection.\n2. **Hit**\n   - Entry age is within TTL -> return cached entries + `cache_age_ms`.\n3. **Stale-empty recheck**\n   - If query yields zero matches and cache age exceeds the empty-result threshold, force one rescan.\n4. **Invalidation**\n   - `invalidateFsScanCache(path?)`:\n     - no arg: clear all keys;\n     - path arg: remove keys for roots affected by that path.\n\n### Stale-result tradeoff\n\n- Cache favors low-latency repeated scans over immediate consistency.\n- TTL window can return stale positives/negatives.\n- Empty-result recheck reduces stale negatives for older cached scans at the cost of one extra scan.\n- Explicit invalidation is the intended correctness hook after file mutations.\n\n## 5) ANSI text utilities (`text`)\n\nThese are pure, in-memory utilities.\n\n### Boundaries and responsibilities\n\n- `text.rs` owns terminal-cell semantics:\n  - ANSI sequence parsing,\n  - grapheme-aware width and slicing,\n  - wrap/truncate/sanitize behavior,\n  - explicit tab-width parameter on width-sensitive APIs.\n- `grep.rs` line truncation (`maxColumns`) is separate:\n  - simple character-boundary truncation of matched lines with `...`,\n  - not ANSI-state-preserving and not terminal-cell width aware.\n\n### Key behaviors\n\n- `wrapTextWithAnsi`: wraps by visible width, carries active SGR codes across wrapped lines.\n- `truncateToWidth`: visible-cell truncation with ellipsis policy (`Unicode`, `Ascii`, `Omit`), optional right padding.\n- `sliceWithWidth`: column slicing with optional strict width enforcement.\n- `extractSegments`: extracts before/after segments around an overlay while restoring ANSI state for the `after` segment.\n- `sanitizeText` (ANSI/control/surrogate stripping with line-ending normalization) no longer lives in `text.rs`; it moved to `@gajae-code/utils` as a pure-JS implementation in `packages/utils/src/sanitize-text.ts`. The native binding was removed in the same change because the JS version was competitive on the benchmarked workloads, and keeping a Rust copy forced every caller (including `pi-utils`) to pull in `@gajae-code/natives`.\n- `visibleWidth`: counts visible terminal cells using caller-supplied tab width.\n\n### Failure behavior\n\nText functions generally return deterministic transformed output; errors are limited to N-API argument/string conversion boundaries.\n\n## 6) Syntax highlighting (`highlight`)\n\n`highlight.rs` is pure transformation; it does not use the filesystem scan cache.\n\n### Flow\n\n1. Caller passes `code`, optional `lang`, and ANSI color palette.\n2. Rust resolves syntax by token/name lookup, extension lookup, alias table fallback, then plain-text fallback.\n3. Each line is parsed with syntect `ParseState` and scope stack.\n4. Scopes map to semantic color categories and ANSI color codes are injected/reset.\n\n### Failure behavior\n\n- Per-line parse failure does not fail the call: that line is appended unhighlighted and processing continues.\n- Unknown/unsupported language falls back to plain text syntax.\n\n## 7) Token counting (`tokens`)\n\n`countTokens(input, encoding?)` is an in-memory utility.\n\n- `input` may be a single string or an array of strings.\n- Arrays return one aggregate count and are encoded in parallel in Rust.\n- Default encoding is `O200kBase`; `Cl100kBase` is also available.\n- The implementation uses ordinary tokenization, not special-token handling.\n\n## Pure utility vs filesystem-dependent flows\n\n| Flow                         | Filesystem access | Shared cache         | Notes                                         |\n| ---------------------------- | ----------------- | -------------------- | --------------------------------------------- |\n| `search` / `hasMatch`        | No                | No                   | regex on provided bytes/string only           |\n| `text` module functions      | No                | No                   | ANSI/width/sanitization only                  |\n| `highlight` module functions | No                | No                   | syntax + ANSI coloring only                   |\n| `countTokens`                | No                | No                   | tokenization only                             |\n| `astGrep` / `astEdit`        | Yes               | No                   | syntax-aware file search/edit                 |\n| `glob`                       | Yes               | Optional             | directory scans + glob filtering              |\n| `fuzzyFind`                  | Yes               | Optional             | directory scans + fuzzy scoring               |\n| `grep` (file/dir path)       | Yes               | Optional in dir mode | ripgrep over files, optional filters/callback |\n\n## End-to-end lifecycle summary\n\n1. Caller invokes generated native export with typed options.\n2. Rust validates/normalizes options and builds matcher/search config.\n3. For filesystem flows, entries are scanned (cache hit/miss/rescan where applicable) then filtered/scored/searched.\n4. Worker loops periodically call cancel heartbeat; timeout/abort can terminate execution.\n5. Rust shapes outputs into N-API objects (`lineNumber`, `matchCount`, `limitReached`, etc.).\n6. Generated bindings return typed JS objects and optional per-match callbacks for `grep`/`glob`.\n",
+	"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",
 	"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",