@sayknow-cli/coding-agent 0.2.3 → 0.2.5

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","FORK_MAINTENANCE.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","bot-integration.md","brand-assets.md","bridge.md","codebase-overview.md","compaction.md","composer-codex-parity.md","computer-use/README.md","environment-variables.md","external-control-readiness.md","fs-scan-cache-architecture.md","geobench.md","grok-build-provider-design.md","handoff-generation-pipeline.md","hermes-mcp-bridge.md","hotspot-map-successor.md","keybindings.md","lsp-config.md","memory.md","models.md","native-ffi-optimization-policy.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","ooo-bridge-extension-contract.md","openclaw-hermes-rpc-integration.md","perf-profiling-corpus.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","readme/README.de.md","readme/README.es.md","readme/README.fr.md","readme/README.ja.md","readme/README.ko.md","readme/README.zh.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sayknow-remote.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","skc-dogfood-skill-template.md","telegram-remote.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/computer.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","FORK_MAINTENANCE.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","bot-integration.md","brand-assets.md","bridge.md","codebase-overview.md","compaction.md","composer-codex-parity.md","computer-use/README.md","environment-variables.md","external-control-readiness.md","fs-scan-cache-architecture.md","geobench.md","grok-build-provider-design.md","handoff-generation-pipeline.md","hermes-mcp-bridge.md","hotspot-map-successor.md","keybindings.md","lsp-config.md","memory.md","models.md","multi-vendor-profiles.md","native-ffi-optimization-policy.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","ooo-bridge-extension-contract.md","openclaw-hermes-rpc-integration.md","perf-profiling-corpus.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","readme/README.de.md","readme/README.es.md","readme/README.fr.md","readme/README.ja.md","readme/README.ko.md","readme/README.zh.md","render-mermaid.md","research-plan-ledger.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","skc-dogfood-skill-template.md","skc-session-clawhip-routing.md","standalone-mcp.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/computer.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: `~/.skc/stats.db` (`ss_tool_calls`, `ss_assistant_msgs`), through\n2026-05-10. 1.05M tool calls scanned.\n\n### 2.1 Rate\n\n| Model            | Leaks in tool args | Calls   | per million |\n|------------------|-------------------:|--------:|------------:|\n| gpt-5.4          | 37                 | 226,957 | 163         |\n| gpt-5.3-openai-code    | 17                 | 112,243 | 151         |\n| gpt-5.5          | 2                  |  80,750 |  25         |\n| gpt-5.2-openai-code    | 0                  |    —    |   —         |\n\nPlus 15 hits in assistant visible text / thinking blobs.\n\n### 2.2 Tool distribution\n\n| Tool                | Hits |\n|---------------------|-----:|\n| `edit`              | 38   |\n| `eval`              | 11   |\n| `report_tool_issue` | 3    |\n| `grep`/`read`/`search`/`yield` | 1 each |\n\nConcentrated in tools with free-form (non-JSON-schema) argument formats.\n\n### 2.3 Leak shape (deterministic)\n\n```\nLEAK         ::= JUNK_PREFIX MARKER CHANNEL_BODY (LEAK)?\nMARKER       ::= \"to=functions.\" TOOL_NAME\nCHANNEL_BODY ::= \" code \" (SPAM | reasoning_prose | fake_tool_output)*\nJUNK_PREFIX  ::= (GLITCH_TOKEN | CHANNEL_WORD | NON_LATIN_RUN | \"}\" | \"】【\")+\n```\n\n**Cascading is common.** Of 96 marker occurrences across 71 contaminated\nrecords, 39 contain ≥2 markers and 7 contain ≥3 — the model emits\nmultiple fake `to=functions.X code …` blocks back-to-back, often with\nfake `code_output\\nCell N:\\n…` framing between them. Once the\nplain-text scaffolding is in the residual stream, the prefix now *looks\nlike* a fresh tool envelope start, so the macro prior over continuations\nkeeps voting for more scaffolding. Self-amplifying.\n\n### 2.4 Glitch tokens\n\nSingle-token identifiers in `o200k_base` whose embeddings appear to be\nnear-init from underrepresentation in post-training. ASCII residue\nimmediately before the marker in the natural corpus:\n\n| Surface string    | Single-token | Token ID | Hits in corpus |\n|-------------------|:-:|---------:|---:|\n| `Japgolly`        | ✅ | 199,745 | 1 |\n| `Jsii`            | ✅ | 114,318 | (subtoken of `Jsii_commentary`) |\n| `Jsii_commentary` | — (3 toks) | — | 2 |\n| `changedFiles`    | — (2 toks) | — | 8 |\n| `RTLU`            | — (2 toks) | — | 3 |\n\n`Japgolly` is in the last 0.13% of the vocabulary — the same family of\nGitHub-corpus residue that produced `SolidGoldMagikarp` in the 2023\nGPT-2 vocabulary (Rumbelow & Watkins). `SolidGoldMagikarp` itself\ntokenizes to 5 tokens in `o200k_base` — that specific token was retired,\nbut the class wasn't.\n\nFor the multi-token entries, the corpus-level signature is the surface\nstring; the underlying glitch trigger is a sub-token (e.g. `Jsii` inside\n`Jsii_commentary`). The detector list (`G` signal) keys on the surface\nstrings.\n\nStable across unrelated sessions. Treated as a high-precision detector\nsignal.\n\n### 2.5 Channel-word leakage\n\n`analysis` (5), `assistant` (5), `commentary` (3), `user` (1) appear\ndirectly preceding `to=`. Always bare words; never `<|channel|>analysis`\nor any other bracketed form. Consistent with §1 — the brackets are\nmasked, the words are not.\n\n### 2.6 Non-Latin spam residue\n\n96 marker hits, by script: CJK 40, Cyrillic 12, Telugu/Kannada/Malayalam\n18, Thai 8, Georgian 7, Armenian 7, Arabic 1. Recurring fragments are\nChinese gambling SEO (`大发时时彩`, `天天中彩票`), Georgian/Abkhaz junk,\nand Thai casino spam — well-known low-quality crawl residue.\n\nThis is the same script distribution observed in the controlled\nreproduction (§7.3), independent of the prompt's natural language.\n\n### 2.7 Failure-mode breakdown for the `edit` tool\n\nThe `edit` tool exists in two variants in the corpus:\n\n| Variant                  | Calls | Recovery |\n|--------------------------|------:|----------|\n| Patch-DSL (`§PATH`/anchor/`«»≔` ops) | 27 | **Recoverable** by op-truncation (§3.3) |\n| JSON-schema (`{path,edits:[…]}`)      | 11 | **Not recoverable** — contamination is escaped *inside* JSON strings, parser accepts it cleanly, content would be written verbatim into source files |\n\nFor Patch-DSL leaks specifically:\n\n- 20/27 cases: contamination on the last input line; nothing follows.\n- 7/27 cases: contamination mid-input; what follows is one of: a\n  duplicate replay of an earlier file/anchor, intended content for a\n  *different* tool call (the model started its next call inline), or\n  pure hallucination. Post-contamination content is never trustworthy.\n\n### 2.8 Mechanism (confirmed)\n\n**Prior collapse from null-embedding glitch tokens, into a\ncontrol-token-masked basin whose mass redistributes onto the\nplain-text shadow of the Harmony protocol.**\n\nStep by step:\n\n1. The model is mid-`{ARGS}` of a Harmony tool call. The runtime applies\n   a logit mask suppressing structural control tokens (`<|channel|>`,\n   `<|message|>`, `<|call|>`, `<|start|>`, `<|end|>`) inside the args\n   region. Without this mask, normal generation would constantly\n   hallucinate envelope-closes; with it, those token IDs have logit\n   `-∞` in args.\n2. A glitch token `g` is sampled. By construction `g` was in the BPE\n   merge corpus but barely in LM/RL training, so its **input embedding\n   `e_g` ≈ near-init noise of small norm**.\n3. At position t+1, the residual update `h_{t+1} ≈ LN(h_t + e_g + Attn +\n   MLP)` is dominated by the prefix-derived terms; the just-emitted-token\n   signal is effectively absent. Generation diversity normally comes\n   from `e_x` steering the residual into different sub-regions —\n   stripped here.\n4. The next-token distribution therefore collapses onto the **conditional\n   prior over continuations of the prefix, with local conditioning\n   removed**. In a tool-calling rollout context, that prior is sharply\n   peaked on Harmony scaffolding (control tokens + routing tokens) —\n   that's what RL trained.\n5. The mask zeros the control-token IDs. Mass redistributes onto the\n   **next-best continuation**: the un-bracketed surface-form spelling of\n   the same protocol (`analysis`, `commentary`, ` to=functions.X`,\n   ` code `). This spelling is unmasked because those characters are\n   ordinary tokens.\n6. Once a few tokens of plain-text scaffolding land in the residual\n   stream, the prefix now resembles a fresh envelope start. The macro\n   prior keeps voting for more scaffolding. Cascading (§2.3) follows.\n7. Multilingual spam after the marker is the same prior-collapse\n   continuation, drawn from the training neighborhood of the glitch\n   token (often ESL/auto-generated multilingual web junk — exactly the\n   crawl residue in §2.6).\n\n**Two corollaries the corpus data demanded but only the experiment\nexplained:**\n\n- **The brackets never appear** (§1, §2.5). The mask is what makes the\n  leak land in plain text instead of as a real envelope-close.\n- **Counterintuitive grammar dependency** (§7.4). The leak is *worse* in\n  formats closest to OpenAI's training distribution. Off-distribution\n  custom grammars dampen the macro-prior basin; the official\n  `*** Begin Patch` format is the strongest collapse target.\n\nThe 2023 SolidGoldMagikarp paper documented mechanism (1)+(2)+(4). The\nnew piece is (5): when constrained decoding masks the natural collapse\ntarget, the mass laundered through the un-masked plain-text shadow\nbecomes a structurally-invisible exfiltration channel.",
@@ -10,7 +10,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"auth-broker-gateway.md": "# Auth Broker and Auth Gateway\n\nThe auth broker and auth gateway are two cooperating HTTP services that move OAuth refresh tokens and provider access tokens off developer laptops and into a single broker host.\n\n- **`skc auth-broker serve`** holds the canonical SQLite credential vault, performs OAuth refreshes, and exposes a small REST API (`/v1/snapshot`, `/v1/credential/:id/refresh`, `/v1/credential/:id/disable`, `/v1/credential`, `/v1/usage`, `/v1/healthz`).\n- **`skc auth-gateway serve`** is a forward-proxy. It accepts OpenAI Chat Completions, Anthropic Messages, and OpenAI Responses requests, injects the broker-resolved access token, and forwards the bytes to the real provider. Clients (containerised skc, llm-git, the macOS usage widget, …) never see the access token.\n\nTransport security between operator, broker, and gateway is delegated to the operator (Tailscale / Wireguard / reverse proxy + TLS). Every endpoint except `/v1/healthz` (broker) and `/healthz` (gateway) requires a bearer token.\n\nSource: `packages/ai/src/auth-broker/`, `packages/ai/src/auth-gateway/`, `packages/coding-agent/src/cli/auth-broker-cli.ts`, `packages/coding-agent/src/cli/auth-gateway-cli.ts`, `packages/coding-agent/src/session/auth-broker-config.ts`.\n\n## Data flow\n\n```\n                ┌────────────────────────────────────────────────────────────┐\n                │ broker host                                                │\n                │                                                            │\n  developer ──▶ │  ┌──────────────────────────┐    ┌────────────────────┐    │\n  laptop /      │  │  skc auth-broker serve   │◀──▶│  SQLite agent.db    │    │\n  CI / roboskc   │  │  - holds refresh tokens  │    │  (canonical writer)│    │\n                │  │  - background refresher  │    └────────────────────┘    │\n                │  │  /v1/{snapshot,refresh,…}│                              │\n                │  └─────────┬────────────────┘                              │\n                │            │  bearer ($CONFIG_DIR/auth-broker.token)       │\n                │            ▼                                               │\n                │  ┌──────────────────────────┐                              │\n                │  │  skc auth-gateway serve  │  RemoteAuthCredentialStore   │\n                │  │  /v1/{chat,messages,…}   │  pulls /v1/snapshot at boot, │\n                │  │  /v1/usage, /v1/models   │  refreshes credentials by id │\n                │  └─────────┬────────────────┘  via the broker on expiry    │\n                └────────────┼───────────────────────────────────────────────┘\n                             │  bearer ($CONFIG_DIR/auth-gateway.token)\n                             ▼\n                  unauthenticated clients\n                  (llm-git, macOS widget, roboskc containers, IDE plugins, …)\n                                │\n                                ▼ same path is forwarded with Authorization\n                  api.anthropic.com / api.openai.com / …\n```\n\nThe broker is the only writer of OAuth refresh tokens. Clients (including the gateway itself) load a redacted snapshot in which every `refresh` field has been replaced with `REMOTE_REFRESH_SENTINEL`; when an access token expires the client calls `POST /v1/credential/:id/refresh` and the broker performs the refresh server-side. `RemoteAuthCredentialStore` rejects any local code path that tries to write through it, with an error pointing at `skc auth-broker login` / `skc auth-broker logout`.\n\n## auth-broker\n\n### CLI\n\n```\nskc auth-broker serve     [--bind=host:port]                    # boot the broker\nskc auth-broker token     [--regenerate] [--json]               # print or rotate the bearer token\nskc auth-broker login     <provider> [--via=user@host] [--dry-run]\nskc auth-broker logout    <provider>\nskc auth-broker import    <file|dir> [--provider=<id>] [--include-disabled] [--dry-run] [--json]\nskc auth-broker migrate   --from-local [--dry-run] [--json]\nskc auth-broker status    [--json]\n```\n\n- `serve` opens the local SQLite store at `getAgentDbPath()` and binds an HTTP listener (default `127.0.0.1:8765`). On startup a token is ensured at `<config-dir>/auth-broker.token` (mode `0600`, `0700` parent dir). The background refresher refreshes any OAuth credential whose `expires - Date.now() < refreshSkewMs` (default 5 min) every `refreshIntervalMs` (default 60 s).\n- `token` prints the cached bearer or generates a new one. `--regenerate` rotates it.\n- `login <provider>` runs the per-provider OAuth flow locally, or — with `--via=user@host` — `ssh -L <callback-port>:127.0.0.1:<callback-port> user@host skc auth-broker login <provider>` so the OAuth callback hits the local browser but the credential is written on the broker host. Built-in callback ports: `anthropic:54545`, `openai-code:1455`, `google-gemini-cli:8085`, `google-antigravity:51121`, `gitlab-duo:8080`.\n- `logout <provider>` deletes every credential row for `<provider>`.\n- `import <file|dir>` imports CLIProxyAPI-style JSON credentials into the local SQLite store. Maps `type` field → skc provider (`anthropic-model → anthropic`, `openai-code → openai-code`, `gemini → google-gemini-cli`, `antigravity → google-antigravity`, `gemini-cli → google-gemini-cli`).\n- `migrate --from-local` walks the local SQLite store + env-derived credentials and idempotently uploads them to the configured broker (`POST /v1/credential`).\n- `status` health-pings the configured remote broker.\n\n### Endpoints\n\n| Method | Path | Auth | Purpose |\n| ------ | ---- | ---- | ------- |\n| `GET`  | `/v1/healthz` | none | Liveness + version |\n| `GET`  | `/v1/snapshot` | bearer | Redacted snapshot (refresh tokens replaced by sentinel) |\n| `POST` | `/v1/credential` | bearer | Upsert one OAuth or API-key credential |\n| `POST` | `/v1/credential/:id/refresh` | bearer | Force-refresh one OAuth credential |\n| `POST` | `/v1/credential/:id/disable` | bearer | Disable one credential with a recorded cause |\n| `GET`  | `/v1/usage` | bearer | Aggregate `UsageReport[]` across credentials |\n\nRequests use `Authorization: Bearer <token>`. The server compares against an in-memory token allow-list; the gateway’s implementation uses a timing-safe comparison.\n\n### Background refresher\n\n`AuthBrokerRefresher` iterates active OAuth credentials at `refreshIntervalMs` cadence and refreshes any within `refreshSkewMs` of expiry. Refreshes are single-flighted per credential id so a slow refresh cannot be retriggered. The refresher distinguishes:\n\n- **definitive failures** (`invalid_grant`, `invalid_token`, `revoked`, unauthorized refresh-token, 401/403 not from a network blip) — credentials are passed to `AuthStorage.disableCredentialById(id, cause)` so the next snapshot pull surfaces a clean delete on the client;\n- **transient failures** (timeout / ECONNREFUSED / fetch failed) — left in place for the next sweep.\n\n## auth-gateway\n\n### CLI\n\n```\nskc auth-gateway serve   [--bind=host:port] [--no-auth]\nskc auth-gateway token   [--regenerate] [--json]\nskc auth-gateway status  [--json]\n```\n\n- `serve` requires `SKC_AUTH_BROKER_URL` (or `auth.broker.url` in `config.yml`) — the gateway is itself a broker client. It calls `AuthBrokerClient.fetchSnapshot()`, wraps it in `RemoteAuthCredentialStore`, and constructs an `AuthStorage` that resolves access tokens through the broker. Default bind is `127.0.0.1:4000`. The gateway token is stored at `<config-dir>/auth-gateway.token` (`0600`); `--no-auth` disables the bearer check entirely (loopback-only use).\n- `token` / `status` mirror the broker’s equivalents.\n\n### Endpoints\n\n| Method | Path | Auth | Purpose |\n| ------ | ---- | ---- | ------- |\n| `GET`  | `/healthz` | none | Liveness + version |\n| `GET`  | `/v1/usage` | bearer | Aggregate `UsageReport[]` (proxied through `AuthStorage`) |\n| `GET`  | `/v1/models` | bearer | Bundled-model catalog filtered to providers with credentials |\n| `POST` | `/v1/chat/completions` | bearer | OpenAI Chat Completions wire format |\n| `POST` | `/v1/messages` | bearer | Anthropic Messages wire format |\n| `POST` | `/v1/responses` | bearer | OpenAI Responses wire format |\n\nThe model id is read from the top-level `model` field. The gateway picks the first bundled `Model<Api>` matching that id and:\n\n- **Passthrough fast-path** — when the inbound wire format matches the model’s native API (`openai-chat → openai-completions`, `anthropic-messages → anthropic-messages`, `openai-responses → openai-responses`), the request body is forwarded byte-for-byte with the client `Authorization`/`x-api-key` stripped and replaced by `Authorization: Bearer <resolved-access-token>`. Provider-specific fields (`cache_control`, `service_tier`, tool-choice extensions, …) flow through unmodified. Hop-by-hop headers (RFC 7230) plus `Content-Encoding`/`Content-Length` are stripped from the upstream response.\n- **Translate path** — when the inbound format and the resolved model’s API differ (e.g. `/v1/chat/completions` targeting an Anthropic model, or `/v1/responses` targeting `openai-code-responses` which runs over a websocket transport), the request is parsed against the wire schema, rebuilt into an skc `Context`, dispatched through `streamSimple()`, and re-encoded back to the inbound format (SSE for streamed responses).\n\n`idleTimeout` on the underlying `Bun.serve` is set to `255 s` so long thinking-budget calls do not get killed by Bun’s default idle timeout.\n\n## Usage cache: server-side 5-min jitter + client-side 15 s single-flight\n\nTwo layers cache the aggregate provider-usage report. Both are intentional and stacked.\n\n### Server-side cache (broker `AuthStorage`)\n\n`AuthStorage` caches each credential’s `UsageReport` in the broker’s SQLite store at a **5-minute per-credential TTL with ±25 % jitter**. Anthropic and OpenAI rate-limit `/usage` aggressively per source IP, and a synchronized 5-credential fan-out trips 429s every cycle; the jitter decorrelates refresh times within a few cycles. On fetch failure the store keeps the **last-good** report for up to 24 h with a short jittered re-poll window — so a transient upstream blip never blanks out the widget.\n\nConstants: `USAGE_REPORT_TTL_MS = 5 * 60_000`, `USAGE_LAST_GOOD_RETENTION_MS = 24 * 60 * 60_000` (`packages/ai/src/auth-storage.ts`).\n\n### Client-side single-flight (`RemoteAuthCredentialStore`)\n\nWhen the gateway (or any other broker client) calls `fetchUsageReports()` / `getUsageReport(provider, credential)`, `RemoteAuthCredentialStore` coalesces concurrent calls into a single `GET /v1/usage` round-trip and caches the result for **15 s** in memory.\n\n- `USAGE_CACHE_TTL_MS = 15_000` (`packages/ai/src/auth-broker/remote-store.ts`).\n- A single `#usageInflight` promise is shared across all callers; a per-caller `AbortSignal` is **raced** against the shared promise, not threaded into it, so one caller’s abort never cascades into a peer’s in-flight request.\n- On fetch failure the rejected promise is logged and the awaited value is `null` — callers (`AuthStorage.fetchUsageReports`, `#getUsageReport`) treat a `null` report as \"no usage signal for this cycle\" and proceed without it. **This is the 15 s TTL fallback**: the client absorbs transient broker outages by suppressing the error, returning `null` to ranking, and re-attempting after the 15 s window.\n\nThe 15 s client window deliberately sits below the broker’s 5 min server cache, so almost every client poll is served from the broker’s already-cached value; the client cache exists to absorb the parallel fan-out generated by `AuthStorage.#rankOAuthSelections` into a single broker round-trip.\n\n## Operator opt-in\n\nThe broker is **off** unless `SKC_AUTH_BROKER_URL` (or `auth.broker.url` in `config.yml`) is set. When set, `discoverAuthStorage` in `packages/coding-agent/src/sdk.ts` swaps the local SQLite credential store for `RemoteAuthCredentialStore` and every API call resolves credentials through the broker.\n\n### Environment variables\n\n| Variable | Purpose | Required when |\n| -------- | ------- | ------------- |\n| `SKC_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`). Selecting this puts the client in broker mode — local SQLite is bypassed. | Any time the skc client should resolve credentials through a broker (and required by `skc auth-gateway serve`). |\n| `SKC_AUTH_BROKER_TOKEN` | Bearer token used for every broker endpoint except `/v1/healthz`. | When `SKC_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`. |\n\nResolution order in `resolveAuthBrokerConfig()`:\n\n1. `SKC_AUTH_BROKER_URL` env (else `auth.broker.url` from `config.yml`, with `$ENV_NAME` resolution);\n2. `SKC_AUTH_BROKER_TOKEN` env (else `auth.broker.token` from `config.yml`, else `<config-dir>/auth-broker.token`);\n3. URL set but no token resolvable → hard error pointing at the token file path.\n\nThe gateway has no dedicated env vars — it inherits `SKC_AUTH_BROKER_*` because it is itself a broker client.\n\n### `config.yml` keys\n\n| Key | Default | Purpose |\n| --- | ------- | ------- |\n| `auth.broker.url`   | unset | Same as `SKC_AUTH_BROKER_URL`; env wins. Hidden from the settings UI. |\n| `auth.broker.token` | unset | Same as `SKC_AUTH_BROKER_TOKEN`; env wins. Values may be the literal token or `$ENV_NAME` to indirect through env. |\n\n### Token files\n\n| Path | Owner | Mode |\n| ---- | ----- | ---- |\n| `<config-dir>/auth-broker.token`  | `skc auth-broker serve` (created at first start) | `0600` in a `0700` parent dir |\n| `<config-dir>/auth-gateway.token` | `skc auth-gateway serve` (skipped under `--no-auth`) | `0600` in a `0700` parent dir |\n\n`<config-dir>` resolves to `~/.skc/` (respecting `SKC_CONFIG_DIR`).\n\n## Interaction with the local API-key resolution order\n\nThe broker only owns OAuth credentials and provider-API-key credentials that were uploaded to it. The standard credential ladder in `models.md` (`Auth and API key resolution order`) is preserved, with one addition committed alongside the gateway:\n\n- `AuthStorage.setConfigApiKey / removeConfigApiKey / clearConfigApiKeys` let a `models.yml` `apiKey` beat a stored OAuth token **without** overriding an explicit `--api-key`. This is what allows a broker-resolved OAuth credential to be reliably shadowed by a per-environment `models.yml` config key when both are present.\n\n## See also\n\n- [`secrets.md`](./secrets.md) — secret obfuscation around tokens that *do* leak through (e.g. `SKC_AUTH_BROKER_TOKEN` in shell output).\n- [`models.md`](./models.md) — provider auth resolution order; the broker plugs in at layers 2–3 (stored credentials).\n- [`environment-variables.md`](./environment-variables.md) — full env reference including `SKC_AUTH_BROKER_URL` / `SKC_AUTH_BROKER_TOKEN`.\n",
 	"bash-tool-runtime.md": "# Bash tool runtime\n\nThis document describes the **`bash` tool** runtime path used by agent tool calls, from command normalization to execution, truncation/artifacts, and rendering.\n\nIt also calls out where behavior diverges in interactive TUI, print mode, RPC mode, and user-initiated bang (`!`) shell execution.\n\n## Scope and runtime surfaces\n\nThere are two different bash execution surfaces in coding-agent:\n\n1. **Tool-call surface** (`toolName: \"bash\"`): used when the model calls the bash tool.\n   - Entry point: `BashTool.execute()`.\n   - Parameters include `command`, optional `env`, `timeout`, `cwd`, `head`, `tail`, `pty`, and, when `async.enabled` is true, `async`.\n2. **User bang-command surface** (`!cmd` from interactive input or RPC `bash` command): session-level helper path.\n   - Entry point: `AgentSession.executeBash()`.\n\nBoth eventually use `executeBash()` in `src/exec/bash-executor.ts` for non-PTY execution, but only the tool-call path runs normalization/interception, optional managed background-job handling, and tool renderer logic.\n\n## End-to-end tool-call pipeline\n\n## 1) Input handling and parameter merge\n\n`BashTool.execute()` currently handles input before execution as follows:\n\n- validates optional `env` names against shell-variable syntax,\n- extracts a leading `cd <path> && ...` into `cwd` when `cwd` was not supplied,\n- rejects `async: true` when `async.enabled` is false,\n- uses only explicit `head`/`tail` tool args for post-run filtering.\n\n`normalizeBashCommand()` still exists in `src/tools/bash-normalize.ts`, but `BashTool.execute()` does not call it in the current source. Trailing shell pipes such as `| head -n 50` remain part of the shell command unless the caller uses the structured `head`/`tail` args.\n\n## 2) Optional interception (blocked-command path)\n\nIf `bashInterceptor.enabled` is true, `BashTool` loads rules from settings and runs `checkBashInterception()` against the normalized command.\n\nInterception behavior:\n\n- command is blocked **only** when:\n  - regex rule matches, and\n  - the suggested tool is present in `ctx.toolNames`.\n- invalid regex rules are silently skipped.\n- on block, `BashTool` throws `ToolError` with message:\n  - `Blocked: ...`\n  - original command included.\n\nDefault rule patterns (defined in code) target common misuses:\n\n- file readers (`cat`, `head`, `tail`, ...)\n- search tools (`grep`, `rg`, ...)\n- file finders (`find`, `fd`, ...)\n- in-place editors (`sed -i`, `perl -i`, `awk -i inplace`)\n- shell redirection writes (`echo ... > file`, heredoc redirection)\n\n### Caveat\n\n`InterceptionResult` includes `suggestedTool`, but `BashTool` currently surfaces only the message text (no structured suggested-tool field in `details`).\n\n## 3) CWD validation and timeout clamping\n\n`cwd` is resolved relative to session cwd (`resolveToCwd`), then validated via `stat`:\n\n- missing path -> `ToolError(\"Working directory does not exist: ...\")`\n- non-directory -> `ToolError(\"Working directory is not a directory: ...\")`\n\nTimeout is clamped to `[1, 3600]` seconds and converted to milliseconds.\n\n## 4) Artifact allocation\n\nBefore execution, the tool allocates an artifact path/id (best-effort) for truncated output storage.\n\n- artifact allocation failure is non-fatal (execution continues without artifact spill file),\n- artifact id/path are passed into execution path for full-output persistence on truncation.\n\n## 5) PTY vs non-PTY execution selection\n\n`BashTool` chooses PTY execution only when all are true:\n\n- tool input `pty === true`\n- `SKC_NO_PTY !== \"1\"`\n- tool context has UI (`ctx.hasUI === true` and `ctx.ui` set)\n\nOtherwise it uses non-interactive `executeBash()`.\n\nThat means print mode and non-UI RPC/tool contexts always use non-PTY.\n\n## Non-interactive execution engine (`executeBash`)\n\n## Shell session reuse model\n\n`executeBash()` caches native `Shell` instances in a process-global map keyed by:\n\n- shell path,\n- configured command prefix,\n- snapshot path,\n- serialized shell env,\n- optional agent session key.\n\nSession-level bang-command executions pass `sessionKey: this.sessionId`.\n\nTool-call executions pass `sessionKey: this.session.getSessionId?.()`, when available. In both surfaces, a session key isolates shell reuse per session; without one, reuse falls back to shell config/snapshot/env.\n\n## Shell config and snapshot behavior\n\nAt each call, executor loads settings shell config (`shell`, `env`, optional `prefix`).\n\nIf selected shell includes `bash`, it attempts `getOrCreateSnapshot()`:\n\n- snapshot captures aliases/functions/options from user rc,\n- snapshot creation is best-effort,\n- failure falls back to no snapshot.\n\nIf `prefix` is configured, command becomes:\n\n```text\n<prefix> <command>\n```\n\n## Streaming and cancellation\n\n`Shell.run()` streams chunks to `OutputSink` and optional `onChunk` callback.\n\nCancellation:\n\n- aborted signal triggers `shellSession.abort(...)`,\n- timeout from native result is mapped to `cancelled: true` + annotation text,\n- explicit cancellation similarly returns `cancelled: true` + annotation.\n\nNo exception is thrown inside executor for timeout/cancel; it returns structured `BashResult` and lets caller map error semantics.\n\n## Interactive PTY path (`runInteractiveBashPty`)\n\nWhen PTY is enabled, tool runs `runInteractiveBashPty()` which opens an overlay console component and drives a native `PtySession`.\n\nBehavior highlights:\n\n- xterm-headless virtual terminal renders viewport in overlay,\n- keyboard input is normalized (including Kitty sequences and application cursor mode handling),\n- `esc` while running kills the PTY session,\n- terminal resize propagates to PTY (`session.resize(cols, rows)`).\n\nEnvironment hardening defaults are injected for unattended runs:\n\n- pagers disabled (`PAGER=cat`, `GIT_PAGER=cat`, etc.),\n- editor prompts disabled (`GIT_EDITOR=true`, `EDITOR=true`, ...),\n- terminal/auth prompts reduced (`GIT_TERMINAL_PROMPT=0`, `SSH_ASKPASS=/usr/bin/false`, `CI=1`),\n- package-manager/tool automation flags for non-interactive behavior.\n\nPTY output is normalized (`CRLF`/`CR` to `LF`, `sanitizeText`) and written into `OutputSink`, including artifact spill support.\n\nOn PTY startup/runtime error, sink receives `PTY error: ...` line and command finalizes with undefined exit code.\n\n## Output handling: streaming, truncation, artifact spill\n\nBoth PTY and non-PTY paths use `OutputSink`.\n\n## OutputSink semantics\n\n- keeps an in-memory UTF-8-safe tail buffer (`DEFAULT_MAX_BYTES`, currently 50KB),\n- tracks total bytes/lines seen,\n- if artifact path exists and output overflows (or file already active), writes full stream to artifact file,\n- when memory threshold overflows, trims in-memory buffer to tail (UTF-8 boundary safe),\n- marks `truncated` when overflow/file spill occurs.\n\n`dump()` returns:\n\n- `output` (possibly annotated prefix),\n- `truncated`,\n- `totalLines/totalBytes`,\n- `outputLines/outputBytes`,\n- `artifactId` if artifact file was active.\n\n### Long-output caveat\n\nRuntime truncation is byte-threshold based in `OutputSink` (50KB default). It does not enforce a hard 2000-line cap in this code path.\n\n## Live tool updates and async jobs\n\nFor non-PTY foreground execution, `BashTool` uses a separate `TailBuffer` for partial updates and emits `onUpdate` snapshots while command is running.\n\nFor PTY execution, live rendering is handled by custom UI overlay, not by `onUpdate` text chunks.\n\nWhen `async.enabled` is true and the call passes `async: true`, `BashTool` starts a managed bash job, returns a running job result with a job id, and stores completion through the session managed-job path. Auto-backgrounding can also start this path after `bash.autoBackground.thresholdMs`.\n\n## Result shaping, metadata, and error mapping\n\nAfter execution:\n\n1. `cancelled` handling:\n   - if abort signal is aborted -> throw `ToolAbortError` (abort semantics),\n   - else -> throw `ToolError` (treated as tool failure).\n2. PTY `timedOut` -> throw `ToolError`.\n3. apply head/tail filters to final output text (`applyHeadTail`, head then tail).\n4. empty output becomes `(no output)`.\n5. attach truncation metadata via `toolResult(...).truncationFromSummary(result, { direction: \"tail\" })`.\n6. exit-code mapping:\n   - missing exit code -> `ToolError(\"... missing exit status\")`\n   - non-zero exit -> `ToolError(\"... Command exited with code N\")`\n   - zero exit -> success result.\n\nSuccess payload structure:\n\n- `content`: text output,\n- `details.meta.truncation` when truncated, including:\n  - `direction`, `truncatedBy`, total/output line+byte counts,\n  - `shownRange`,\n  - `artifactId` when available.\n\nBecause built-in tools are wrapped with `wrapToolWithMetaNotice()`, truncation notice text is appended to final text content automatically (for example: `Full: artifact://<id>`).\n\n## Rendering paths\n\n## Tool-call renderer (`bashToolRenderer`)\n\n`bashToolRenderer` is used for tool-call messages (`toolCall` / `toolResult`):\n\n- collapsed mode shows visual-line-truncated preview,\n- expanded mode shows all currently available output text,\n- warning line includes truncation reason and `artifact://<id>` when truncated,\n- timeout value (from args) is shown in footer metadata line.\n\n### Caveat: full artifact expansion\n\n`BashRenderContext` has `isFullOutput`, but current renderer context builder does not set it for bash tool results. Expanded view still uses the text already in result content (tail/truncated output) unless another caller provides full artifact content.\n\n## User bang-command component (`BashExecutionComponent`)\n\n`BashExecutionComponent` is for user `!` commands in interactive mode (not model tool calls):\n\n- streams chunks live,\n- collapsed preview keeps last 20 logical lines,\n- line clamp at 4000 chars per line,\n- shows truncation + artifact warnings when metadata is present,\n- marks cancelled/error/exit state separately.\n\nThis component is wired by `CommandController.handleBashCommand()` and fed from `AgentSession.executeBash()`.\n\n## Mode-specific behavior differences\n\n| Surface                        | Entry path                                            | PTY eligible                                                         | Live output UX                                                           | Error surfacing                                  |\n| ------------------------------ | ----------------------------------------------------- | -------------------------------------------------------------------- | ------------------------------------------------------------------------ | ------------------------------------------------ |\n| Interactive tool call          | `BashTool.execute`                                    | Yes, when `pty=true` and UI exists and `SKC_NO_PTY!=1`                | PTY overlay (interactive) or streamed tail updates                       | Tool errors become `toolResult.isError`          |\n| Print mode tool call           | `BashTool.execute`                                    | No (no UI context)                                                   | No TUI overlay; output appears in event stream/final assistant text flow | Same tool error mapping                          |\n| RPC tool call (agent tooling)  | `BashTool.execute`                                    | Usually no UI -> non-PTY                                             | Structured tool events/results                                           | Same tool error mapping                          |\n| Interactive bang command (`!`) | `AgentSession.executeBash` + `BashExecutionComponent` | No (uses executor directly)                                          | Dedicated bash execution component                                       | Controller catches exceptions and shows UI error |\n| RPC `bash` command             | `rpc-mode` -> `session.executeBash`                   | No                                                                   | Returns `BashResult` directly                                            | Consumer handles returned fields                 |\n\n## Operational caveats\n\n- Interceptor only blocks commands when suggested tool is currently available in context.\n- If artifact allocation fails, truncation still occurs but no `artifact://` back-reference is available.\n- Shell session cache has no explicit eviction in this module; lifetime is process-scoped.\n- PTY and non-PTY timeout surfaces differ:\n  - PTY exposes explicit `timedOut` result field,\n  - non-PTY maps timeout into `cancelled + annotation` summary.\n\n## Implementation files\n\n- [`src/tools/bash.ts`](../packages/coding-agent/src/tools/bash.ts) — tool entrypoint, input handling/interception, async and PTY/non-PTY selection, result/error mapping, bash tool renderer.\n- [`src/tools/bash-normalize.ts`](../packages/coding-agent/src/tools/bash-normalize.ts) — post-run head/tail filtering; also contains an unused command-normalization helper.\n- [`src/tools/bash-interceptor.ts`](../packages/coding-agent/src/tools/bash-interceptor.ts) — interceptor rule matching and blocked-command messages.\n- [`src/exec/bash-executor.ts`](../packages/coding-agent/src/exec/bash-executor.ts) — non-PTY executor, shell session reuse, cancellation wiring, output sink integration.\n- [`src/tools/bash-interactive.ts`](../packages/coding-agent/src/tools/bash-interactive.ts) — PTY runtime, overlay UI, input normalization, non-interactive env defaults.\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts) — `OutputSink`, `TailBuffer`, truncation/artifact spill, and summary metadata.\n- [`src/tools/output-meta.ts`](../packages/coding-agent/src/tools/output-meta.ts) — truncation metadata shape + notice injection wrapper.\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — session-level `executeBash`, message recording, abort lifecycle.\n- [`src/modes/components/bash-execution.ts`](../packages/coding-agent/src/modes/components/bash-execution.ts) — interactive `!` command execution component.\n- [`src/modes/controllers/command-controller.ts`](../packages/coding-agent/src/modes/controllers/command-controller.ts) — wiring for interactive `!` command UI stream/update completion.\n- [`src/modes/rpc/rpc-mode.ts`](../packages/coding-agent/src/modes/rpc/rpc-mode.ts) — RPC `bash` and `abort_bash` command surface.\n- [`src/internal-urls/artifact-protocol.ts`](../packages/coding-agent/src/internal-urls/artifact-protocol.ts) — `artifact://<id>` resolution.\n",
 	"blob-artifact-architecture.md": "# Blob and artifact storage architecture\n\nThis document describes how coding-agent stores large/binary payloads outside session JSONL, how truncated tool output is persisted, and how internal URLs (`artifact://`, `agent://`) resolve back to stored data.\n\n## Why two storage systems exist\n\nThe runtime uses two different persistence mechanisms for different data shapes:\n\n- **Content-addressed blobs** (`blob:sha256:<hash>`): global storage used to externalize large image base64 payloads and provider image data URLs from persisted session entries.\n- **Session-scoped artifacts** (files under `<sessionFile-without-.jsonl>/`): per-session text files used for full tool outputs and subagent outputs.\n\nThey are intentionally separate:\n\n- blob storage optimizes deduplication and stable references by content hash,\n- artifact storage optimizes append-only session tooling and human/tool retrieval by local IDs.\n\n## Storage boundaries and on-disk layout\n\n## Blob store boundary (global)\n\n`SessionManager` constructs `BlobStore(getBlobsDir())`, so blob files live in a shared global blob directory (not in a session folder).\n\nBlob file naming:\n\n- file path: `<blobsDir>/<sha256-hex>`\n- no extension\n- reference string stored in entries: `blob:sha256:<sha256-hex>`\n\nImplications:\n\n- same binary content across sessions resolves to the same hash/path,\n- writes are idempotent at the content level,\n- blobs can outlive any individual session file.\n\n## Artifact boundary (session-local)\n\n`ArtifactManager` derives artifact directory from session file path:\n\n- session file: `.../<timestamp>_<sessionId>.jsonl`\n- artifacts directory: `.../<timestamp>_<sessionId>/` (strip `.jsonl`)\n\nArtifact types share this directory:\n\n- truncated tool output files: `<numericId>.<toolType>.log` (for `artifact://`)\n- subagent output files: `<outputId>.md` (for `agent://`)\n\n## ID and name allocation schemes\n\n## Blob IDs: content hash\n\n`BlobStore.put()` computes SHA-256 over the bytes it is given and returns:\n\n- `hash`: hex digest,\n- `path`: `<blobsDir>/<hash>`,\n- `ref`: `blob:sha256:<hash>`.\n\nNo session-local counter is used.\n\n## Artifact IDs: session-local monotonic integer\n\n`ArtifactManager` scans existing `*.log` artifact files on first use to find max existing numeric ID and sets `nextId = max + 1`.\n\nAllocation behavior:\n\n- file format: `{id}.{toolType}.log`\n- IDs are sequential strings (`\"0\"`, `\"1\"`, ...)\n- resume does not overwrite existing artifacts because scan happens before allocation.\n\nIf artifact directory is missing, scanning yields empty list and allocation starts from `0`.\n\n## Agent output IDs (`agent://`)\n\n`AgentOutputManager` allocates IDs for subagent outputs as `<index>-<requestedId>` (optionally nested under parent prefix, e.g. `0-Parent.1-Child`). It scans existing `.md` files on initialization to continue from the next index on resume.\n\n## Persistence dataflow\n\n## 1) Session entry persistence rewrite path\n\nBefore session entries are written (`#rewriteFile` / incremental persist), `SessionManager` calls `prepareEntryForPersistence()` (via `truncateForPersistence`).\n\nKey behaviors:\n\n1. **Large string truncation**: oversized strings are cut and suffixed with `\"[Session persistence truncated large content]\"`; signature fields (`thinkingSignature`, `thoughtSignature`, `textSignature`) are cleared instead of truncated.\n2. **Transient field stripping**: `partialJson` and `jsonlEvents` are removed from persisted entries.\n3. **Image externalization to blobs**:\n   - image blocks in `content` arrays are externalized when `data` is not already a blob ref and base64 length is at least threshold (`BLOB_EXTERNALIZE_THRESHOLD = 1024`),\n   - provider-style `image_url` data URLs are externalized when they start with `data:image/` and contain `;base64,`,\n   - image block `data` is stored as decoded binary bytes,\n   - provider data URLs are stored as the original UTF-8 data URL string,\n   - persisted values are replaced with `blob:sha256:<hash>`.\n\nThis keeps session JSONL compact while preserving recoverability.\n\n## 2) Session load rehydration path\n\nWhen opening a session (`setSessionFile`), after migrations, `SessionManager` runs `resolveBlobRefsInEntries()`.\n\nFor message/custom-message image blocks with `blob:sha256:<hash>` and for persisted provider `image_url` fields with blob refs:\n\n- reads blob bytes from blob store,\n- converts image-block bytes back to base64,\n- converts provider `image_url` blobs back to the original string,\n- mutates in-memory entry fields for runtime consumers.\n\nIf blob is missing:\n\n- `resolveImageData()` logs warning,\n- returns original ref string unchanged,\n- load continues (no hard crash).\n\n## 3) Tool output spill/truncation path\n\n`OutputSink` powers streaming output in bash/python/ssh and related executors.\n\nBehavior:\n\n1. Every chunk is sanitized and appended to in-memory tail buffer.\n2. When in-memory bytes exceed spill threshold (`DEFAULT_MAX_BYTES`, 50KB), sink marks output truncated.\n3. If an artifact path is available, sink opens a file writer and writes:\n   - existing buffered content once,\n   - all subsequent chunks.\n4. In-memory buffer is always trimmed to tail window for display.\n5. `dump()` returns summary including `artifactId` only when file sink was successfully created.\n\nPractical effect:\n\n- UI/tool return shows truncated tail,\n- full output is preserved in artifact file and referenced as `artifact://<id>`.\n\nIf file sink creation fails (I/O error, missing path, etc.), sink silently falls back to in-memory truncation only; full output is not persisted.\n\n## URL access model\n\n## `blob:` references\n\n`blob:sha256:<hash>` is a persistence reference inside session entry payloads, not an internal URL scheme handled by the router. Resolution is done by `SessionManager` during session load.\n\n## `artifact://<id>`\n\nHandled by `ArtifactProtocolHandler`:\n\n- requires active session artifact directory,\n- ID must be numeric,\n- resolves by matching filename prefix `<id>.`,\n- returns raw text (`text/plain`) from the matched `.log` file,\n- when missing, error includes list of available artifact IDs.\n\nMissing directory behavior:\n\n- if artifacts directory does not exist, throws `No artifacts directory found`.\n\n## `agent://<id>`\n\nHandled by `AgentProtocolHandler` over `<artifactsDir>/<id>.md`:\n\n- plain form returns markdown text,\n- `/path` or `?q=` forms perform JSON extraction,\n- path and query extraction cannot be combined,\n- if extraction requested, file content must parse as JSON.\n\nMissing directory behavior:\n\n- throws `No artifacts directory found`.\n\nMissing output behavior:\n\n- throws `Not found: <id>` with available IDs from existing `.md` files.\n\nRead tool integration:\n\n- `read` supports offset/limit pagination for non-extraction internal URL reads,\n- rejects `offset/limit` when `agent://` extraction is used.\n\n## Resume, fork, and move semantics\n\n## Resume\n\n- `ArtifactManager` scans existing `{id}.*.log` files on first allocation and continues numbering.\n- `AgentOutputManager` scans existing `.md` output IDs and continues numbering.\n- `SessionManager` rehydrates blob refs to base64 on load.\n\n## Fork\n\n`SessionManager.fork()` creates a new session file with new session ID and `parentSession` link, then returns old/new file paths. Artifact copying is handled by `AgentSession.fork()`:\n\n- attempts recursive copy of old artifact directory to new artifact directory,\n- missing old directory is tolerated,\n- non-ENOENT copy errors are logged as warnings and fork still completes.\n\nID implications after fork:\n\n- if copy succeeded, artifact counters in new session continue after max copied ID,\n- if copy failed/skipped, new session artifact IDs start from `0`.\n\nBlob implications after fork:\n\n- blobs are global and content-addressed, so no blob directory copy is required.\n\n## Move to new cwd\n\n`SessionManager.moveTo()` renames both session file and artifact directory to the new default session directory, with rollback logic if a later step fails. This preserves artifact identity while relocating session scope.\n\n## Failure handling and fallback paths\n\n| Case                                                     | Behavior                                                              |\n| -------------------------------------------------------- | --------------------------------------------------------------------- |\n| Blob file missing during rehydration                     | Warn and keep `blob:sha256:` ref string in-memory                     |\n| Blob read ENOENT via `BlobStore.get`                     | Returns `null`                                                        |\n| Artifact directory missing (`ArtifactManager.listFiles`) | Returns empty list (allocation can start fresh)                       |\n| Artifact directory missing (`artifact://` / `agent://`)  | Throws explicit `No artifacts directory found`                        |\n| Artifact ID not found                                    | Throws with available IDs listing                                     |\n| OutputSink artifact writer init fails                    | Continues with tail-only truncation (no full-output artifact)         |\n| No session file (some task paths)                        | Task tool falls back to temp artifacts directory for subagent outputs |\n\n## Binary blob externalization vs text-output artifacts\n\n- **Blob externalization** is for image payloads inside persisted session entry content and provider image data URLs; it replaces inline payload strings in JSONL with stable content refs.\n- **Artifacts** are plain text files for execution output and subagent output; they are addressable by session-local IDs through internal URLs.\n\nThe two systems intersect only indirectly (both reduce session JSONL bloat) but have different identity, lifetime, and retrieval paths.\n\n## Implementation files\n\n- [`src/session/blob-store.ts`](../packages/coding-agent/src/session/blob-store.ts) — blob reference format, hashing, put/get, externalize/resolve helpers.\n- [`src/session/artifacts.ts`](../packages/coding-agent/src/session/artifacts.ts) — session artifact directory model and numeric artifact ID/path allocation.\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts) — `OutputSink` truncation/spill-to-file behavior and summary metadata.\n- [`src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts) — persistence transforms, blob rehydration on load, session fork/move interactions.\n- [`src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — artifact directory copy during interactive fork.\n- [`src/internal-urls/artifact-protocol.ts`](../packages/coding-agent/src/internal-urls/artifact-protocol.ts) — `artifact://` resolver.\n- [`src/internal-urls/agent-protocol.ts`](../packages/coding-agent/src/internal-urls/agent-protocol.ts) — `agent://` resolver + JSON extraction.\n- [`src/sdk.ts`](../packages/coding-agent/src/sdk.ts) — internal URL router wiring and artifacts-dir resolver.\n- [`src/task/output-manager.ts`](../packages/coding-agent/src/task/output-manager.ts) — session-scoped agent output ID allocation for `agent://`.\n- [`src/task/executor.ts`](../packages/coding-agent/src/task/executor.ts) — subagent output artifact writes (`<id>.md`) and temp artifact directory fallback.\n",
-	"bot-integration.md": "# External controller integration guide\n\nThis guide is for authors of bots and orchestrators that want to drive Sayknow-CLI (`skc`) without scraping terminal scrollback. Hermes, OpenClaw, GitHub bots, chatops bots, and custom schedulers are examples of external controllers; none of them need bespoke SKC behavior if they can speak the Coordinator MCP or RPC lifecycle below.\n\nSKC is an external runner. Your controller owns queueing, identity, policy, and credentials; SKC owns the coding-agent session, workflows, tools, artifacts, and evidence inside the selected repository or worktree.\n\n## Integration surfaces\n\nUse the smallest surface that fits your bot:\n\n| Surface | Best for | Command | Stability notes |\n| --- | --- | --- | --- |\n| Coordinator MCP | Any external controller that can call MCP tools to start/register tmux sessions, send turns, answer questions, and read artifacts. | `skc mcp-serve coordinator` | Preferred orchestration surface. `skc mcp-serve hermes` is a compatibility alias, not a separate contract. |\n| Setup adapter | Rendering a portable MCP config and operator instructions for a controller profile. | `skc setup hermes --root /path/to/repo` | Compatibility-oriented config renderer; does not call an LLM or validate provider credentials. |\n| RPC stdio | A controller that embeds a single `skc --mode rpc` subprocess and handles JSONL frames directly or through `python/skc-rpc`. | `skc --mode rpc` | Best for process-backed, single-session bot workers. |\n| Bridge HTTPS | Experimental remote control for an already-running session. | `skc --mode bridge` | Session-control endpoints are fail-closed by default; do not use as the default bot lifecycle surface yet. |\n| Visible tmux fallback | Human-supervised lanes where an existing visible `skc --tmux` pane should become coordinator-authoritative. | `skc --tmux`, then `skc_coordinator_register_session` | Use when an operator already opened a pane or wants direct terminal visibility. |\n\n## Recommended architecture\n\n```text\nexternal controller / bot\n  ├─ chooses repo/worktree and task policy\n  ├─ starts MCP server: skc mcp-serve coordinator\n  ├─ starts or registers one SKC tmux session\n  ├─ sends one bounded turn at a time\n  ├─ answers structured questions explicitly\n  ├─ marks turn completion/failure with report_status\n  └─ reads artifacts/reports from allowlisted roots\n```\n\nDo not infer completion from terminal output. Treat durable turn state as authoritative and tmux tail output as advisory debug context only.\n\n## Coordinator MCP setup\n\nRender a non-mutating config preview:\n\n```sh\nskc setup hermes --root /path/to/repo --profile my-bot --repo my-repo\n```\n\nInstall into a Hermes-compatible profile only when the target path is intentional:\n\n```sh\nskc setup hermes \\\n  --root /path/to/repo \\\n  --profile my-bot \\\n  --repo my-repo \\\n  --mutation sessions,questions,reports \\\n  --profile-dir /path/to/hermes/profile \\\n  --install\n```\n\nRun provider-independent contract smokes before trying a live model:\n\n```sh\nskc setup hermes --root /path/to/repo --smoke --json\nskc mcp-serve coordinator --check --json\n```\n\nThe generated config uses these environment variables:\n\n| Variable | Purpose |\n| --- | --- |\n| `SKC_COORDINATOR_MCP_WORKDIR_ROOTS` | Required allowlist for workdirs and artifact paths. |\n| `SKC_COORDINATOR_MCP_MUTATIONS` | Startup opt-in for mutation classes: `sessions`, `questions`, `reports`, or `all`. |\n| `SKC_COORDINATOR_MCP_SESSION_COMMAND` | Command used to start real SKC sessions, defaulting to `skc --worktree` in generated setup. |\n| `SKC_COORDINATOR_MCP_PROFILE` | Optional profile namespace so one bot cannot enumerate another profile's state. |\n| `SKC_COORDINATOR_MCP_REPO` | Optional repo namespace so one repo cannot enumerate another repo's state. |\n| `SKC_COORDINATOR_MCP_STATE_ROOT` | Optional coordination state root; defaults under `.skc/state/coordinator-mcp`. |\n| `SKC_COORDINATOR_MCP_ARTIFACT_BYTE_CAP` | Maximum bytes returned by artifact reads. |\n\nMutating calls require both startup opt-in and per-call `allow_mutation: true`. Missing either one fails closed.\n\n## Generic smoke strategy\n\nUse three different smoke levels so CI does not depend on one operator's model, API key, tmux layout, or desktop:\n\n| Smoke | Required for CI | What it proves | Example |\n| --- | --- | --- | --- |\n| Contract smoke | Yes | MCP server metadata, tool discovery, exported tool names, input schemas, read-only default, and mutation-gate failures. No provider credentials or tmux pane required. | `skc mcp-serve coordinator --check --json` and focused tests around `tools/list` plus mutation denial. |\n| Dry-run lifecycle smoke | Yes when changed behavior affects lifecycle state | A generic controller can start/register a mocked session, send a turn, observe active-turn protection, report terminal status, and read the completed turn without a real LLM. | `bun test packages/coding-agent/test/coordinator-mcp.test.ts` uses mocked coordinator services and temporary state roots. |\n| Optional live smoke | No | One operator's local provider/model/profile/tmux setup can run end-to-end in their chosen repo. Failure diagnoses that setup; it must not fail CI or PR validation. | Start `skc mcp-serve coordinator` with local env, dispatch a tiny task, then report/read evidence. |\n\nA public bot integration change should at least preserve the contract smoke and local-leak docs test. Live smokes are diagnostics, not mandatory gates.\n\n## MCP tool contract\n\nRead-only tools:\n\n- `skc_coordinator_list_sessions`\n- `skc_coordinator_read_status`\n- `skc_coordinator_read_tail`\n- `skc_coordinator_read_turn`\n- `skc_coordinator_await_turn`\n- `skc_coordinator_list_questions`\n- `skc_coordinator_list_artifacts`\n- `skc_coordinator_read_artifact`\n- `skc_coordinator_read_coordination_status`\n- `skc_coordinator_watch_events`\n\nMutating tools:\n\n- `skc_coordinator_start_session`\n- `skc_coordinator_register_session`\n- `skc_coordinator_send_prompt`\n- `skc_coordinator_submit_question_answer`\n- `skc_coordinator_report_status`\n\n### Start a managed SKC session\n\nCall `skc_coordinator_start_session` with a canonical workdir inside `SKC_COORDINATOR_MCP_WORKDIR_ROOTS`:\n\n```json\n{\n  \"cwd\": \"/path/to/repo\",\n  \"prompt\": \"Optional first bounded task prompt\",\n  \"allow_mutation\": true\n}\n```\n\nThe returned payload includes `session.session_id`, `session_state`, and, when a prompt is provided, `turn_id`, `status`, `delivery`, `queued`, and `delivered`.\n\n### Register a visible tmux fallback session\n\nIf an operator already started a visible session, register it instead of starting a hidden coordinator session:\n\n```sh\nskc --tmux\n```\n\n```json\n{\n  \"session_id\": \"visible-skc-1\",\n  \"cwd\": \"/path/to/repo\",\n  \"tmux_session\": \"visible-skc-1\",\n  \"tmux_target\": \"visible-skc-1:0.0\",\n  \"visible\": true,\n  \"source\": \"operator-visible-tmux\",\n  \"allow_mutation\": true\n}\n```\n\n`skc_coordinator_register_session` validates safe ids, workdir allowlists, tmux target syntax, and liveness before writing coordinator state.\n\n### Send work as turns\n\nSend one bounded task prompt and persist the returned `turn_id`:\n\n```json\n{\n  \"session_id\": \"skc-demo\",\n  \"prompt\": \"Use /skill:ralplan to build a plan for ...\",\n  \"allow_mutation\": true\n}\n```\n\nA session may have one active turn by default. A second prompt returns `active_turn_exists` unless the bot passes:\n\n- `queue: true` to enqueue a durable follow-up turn, or\n- `force: true` to supersede the previous active turn and audit the supersession.\n\n### Wait or watch for completion\n\nUse `skc_coordinator_read_turn` for polling or `skc_coordinator_await_turn` for bounded waiting:\n\n```json\n{\n  \"session_id\": \"skc-demo\",\n  \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"timeout_ms\": 30000,\n  \"poll_interval_ms\": 1000,\n  \"lines\": 80\n}\n```\n\nTerminal turn statuses are `completed`, `failed`, `cancelled`, and `superseded`. Non-terminal statuses include `queued`, `delivering`, `active`, `waiting_for_answer`, and `completing`.\n\nWhen the work is done, your bot must call `skc_coordinator_report_status` with the turn id. This writes the final response/error, evidence paths, and coordinator report that later reads consume:\n\n```json\n{\n  \"session_id\": \"skc-demo\",\n  \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"status\": \"completed\",\n  \"summary\": \"Implemented the requested fix and ran focused tests.\",\n  \"evidence_paths\": [\"/path/to/repo/test-output.txt\"],\n  \"allow_mutation\": true\n}\n```\n\nUse `status: \"failed\"` plus `blocker` for provider failures, unrecoverable tool failures, missing credentials, policy denial, or task blockers.\nUse `status: \"cancelled\"` when the coordinator policy intentionally stops tracking an active turn, for example after an operator abort or a bot-side shutdown decision. This records the turn as terminal in coordinator state; it does not kill the underlying tmux process. To supersede one active turn with replacement work, send the replacement prompt with `force: true` and preserve the superseded turn id in your audit trail.\n\n### Answer structured questions\n\nList pending questions:\n\n```json\n{\n  \"session_id\": \"skc-demo\",\n  \"status\": \"pending\"\n}\n```\n\nThen answer by id:\n\n```json\n{\n  \"session_id\": \"skc-demo\",\n  \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"question_id\": \"question-1\",\n  \"answer\": { \"decision\": \"approve\" },\n  \"allow_mutation\": true\n}\n```\n\nAlways answer the advertised shape. Do not synthesize approvals for destructive actions unless your bot policy explicitly permits that action.\n\n### Read artifacts and reports\n\nUse `skc_coordinator_list_artifacts` to inspect safe roots and `skc_coordinator_read_artifact` to read a bounded artifact:\n\n```json\n{ \"path\": \"/path/to/repo/.skc/ultragoal/ledger.jsonl\" }\n```\n\nArtifact paths are canonicalized, symlink escapes are rejected, and output is byte-capped. Use `skc_coordinator_read_coordination_status` for status reports written through `skc_coordinator_report_status`.\n\n## RPC stdio integration\n\nUse RPC when your bot owns a single worker subprocess rather than an MCP coordinator. The wire protocol is JSONL over stdio:\n\n```sh\nskc --mode rpc --provider anthropic --model claude-sonnet-4-5\n```\n\nRecommended Python client:\n\n```python\nfrom skc_rpc import RpcClient, WorkflowGate\n\nwith RpcClient(no_session=True, no_rules=True) as client:\n    client.install_headless_ui()\n\n    def on_gate(gate: WorkflowGate) -> None:\n        if gate.kind == \"approval\":\n            client.respond_gate(gate.gate_id, {\"decision\": \"approve\"})\n\n    client.on_workflow_gate(on_gate)\n    turn = client.prompt_and_wait(\"Inspect this repo and report the integration contract.\")\n    print(turn.require_assistant_text())\n```\n\nRPC hosts can also expose host-owned tools and URI schemes. Use these to give SKC controlled access to your bot's issue tracker, queue, database rows, or artifact store without leaking long-lived credentials into the SKC process.\n\nKey RPC lifecycle facts:\n\n- `{ \"type\": \"ready\" }` means the subprocess is ready for commands.\n- `prompt` is acknowledged immediately; completion is observed through `agent_end` or `RpcClient.prompt_and_wait()`.\n- `workflow_gate` frames are answered with `workflow_gate_response`.\n- `extension_ui_request` frames are answered with `extension_ui_response` or a headless policy.\n- Host tool calls and host URI requests are explicit callback frames that must be completed or rejected by the host.\n- `RpcClient` enforces single-flight prompt lifecycle collection; use one client per concurrent worker.\n- `abort` and `abort_and_prompt` are the RPC cancellation commands for subprocess workers; coordinator MCP cancellation is recorded through terminal turn status instead.\n\n## Error handling playbook\n\n| Situation | Bot behavior |\n| --- | --- |\n| `coordinator_mutation_class_disabled:*` | Re-render setup with the required mutation class, or keep the bot in read-only mode. |\n| `coordinator_mutation_call_not_allowed:*` | Add `allow_mutation: true` only after policy approval for that specific call. |\n| `unknown_session` | Re-list sessions; start a new managed session or register the visible tmux fallback. |\n| `active_turn_exists` | Poll the active turn, send with `queue: true`, or use `force: true` only when supersession is intentional. |\n| `timeout` from `await_turn` | Treat as non-terminal. Poll again or inspect `read_status`/`read_tail`; do not mark failure solely from a bounded wait timeout. |\n| Coordinator cancellation | Use `skc_coordinator_report_status` with `status: \"cancelled\"` for an intentionally stopped turn, or send replacement work with `force: true` when supersession is policy-approved. This is coordinator state, not a tmux process kill. |\n| Stale tmux/session state | Check `read_status.session_state` and advisory liveness. Register a new visible session or report the turn failed with a recoverable blocker. |\n| Provider/auth failure | Capture the model/provider error in `report_status` with `status: \"failed\"`; do not retry forever without a policy budget. |\n| Artifact denied | Keep the artifact inside allowlisted roots and avoid symlink escapes. |\n| Malformed or invalid question answer | Re-read the question/gate schema and submit a value matching the advertised shape. |\n| Bot shutdown | Persist `session_id` and active `turn_id`; on restart use `read_turn` and `read_status` before sending more work. |\n\n## Controller examples\n\nGeneric MCP controller config:\n\n```json\n{\n  \"mcp_servers\": {\n    \"skc_coordinator\": {\n      \"command\": \"skc\",\n      \"args\": [\"mcp-serve\", \"coordinator\"],\n      \"env\": {\n        \"SKC_COORDINATOR_MCP_WORKDIR_ROOTS\": \"/home/bot/src/project:/home/bot/src/worktrees\",\n        \"SKC_COORDINATOR_MCP_MUTATIONS\": \"sessions,questions,reports\",\n        \"SKC_COORDINATOR_MCP_PROFILE\": \"controller-prod\",\n        \"SKC_COORDINATOR_MCP_REPO\": \"project\",\n        \"SKC_COORDINATOR_MCP_SESSION_COMMAND\": \"skc --worktree\"\n      },\n      \"enabled\": true\n    }\n  }\n}\n```\n\nExample controller loop:\n\n```text\n1. Start `skc mcp-serve coordinator` with repo/worktree roots allowlisted.\n2. Call `skc_coordinator_start_session` for a SKC-managed worktree session.\n3. Send `/skill:deep-interview`, `/skill:ralplan`, or an approved `skc ultragoal ...` task as one turn.\n4. Await the turn; answer `skc_coordinator_list_questions` entries using bot policy.\n5. Report terminal status with evidence paths.\n6. Read artifacts/reports for the user-facing bot response.\n```\n\nHermes and OpenClaw can use the same MCP tool contract. Their names here are examples of controller products, not privileged integration modes.\n\n## Security and credential boundaries\n\n- Do not put provider API keys, GitHub tokens, or bot secrets in prompts.\n- Prefer host tools, host URI schemes, or bot-side sidecars for credentialed external writes.\n- Keep `SKC_COORDINATOR_MCP_WORKDIR_ROOTS` narrow; do not allow `/`, `/home`, or broad parent directories.\n- Use namespaces for multi-tenant bots.\n- Keep mutation classes minimal: read-only for dashboards, `sessions` for work dispatch, `questions` for answering questions, and `reports` for final state.\n- Treat `.skc/` as local runtime state and evidence. Do not expose it wholesale to untrusted users.\n\n## Related references\n\n- [`docs/hermes-mcp-bridge.md`](./hermes-mcp-bridge.md) — coordinator MCP details and setup adapter behavior.\n- [`docs/rpc.md`](./rpc.md) — JSONL RPC protocol, event frames, workflow gates, host tools, and host URI schemes.\n- [`docs/bridge.md`](./bridge.md) — experimental HTTPS bridge and fail-closed endpoint matrix.\n- [`python/skc-rpc/README.md`](../python/skc-rpc/README.md) — typed Python RPC client examples.\n- [`python/roboskc/README.md`](../python/roboskc/README.md) — example self-hosted GitHub bot using `skc --mode rpc`.\n",
+	"bot-integration.md": "# External controller integration guide\n\nThis guide is for authors of bots and orchestrators that want to drive Sayknow-CLI (`skc`) without scraping terminal scrollback. Hermes, OpenClaw, GitHub bots, chatops bots, and custom schedulers are examples of external controllers; none of them need bespoke SKC behavior if they can speak the Coordinator MCP or RPC lifecycle below.\n\nSKC is an external runner. Your controller owns queueing, identity, policy, and credentials; SKC owns the coding-agent session, workflows, tools, artifacts, and evidence inside the selected repository or worktree.\n\n## Integration surfaces\n\nUse the smallest surface that fits your bot:\n\n| Surface | Best for | Command | Stability notes |\n| --- | --- | --- | --- |\n| Coordinator MCP | Any external controller that can call MCP tools to start/register tmux sessions, send turns, answer questions, and read artifacts. | `skc mcp-serve coordinator` | Preferred orchestration surface. `skc mcp-serve hermes` is a compatibility alias, not a separate contract. |\n| Setup adapter | Rendering a portable MCP config and operator instructions for a controller profile. | `skc setup hermes --root /path/to/repo` | Compatibility-oriented config renderer; does not call an LLM or validate provider credentials. |\n| RPC stdio | A controller that embeds a single `skc --mode rpc` subprocess and handles JSONL frames directly or through `python/skc-rpc`. | `skc --mode rpc` | Best for process-backed, single-session bot workers. |\n| Bridge HTTPS | Experimental remote control for an already-running session. | `skc --mode bridge` | Session-control endpoints are fail-closed by default; do not use as the default bot lifecycle surface yet. |\n| Visible tmux fallback | Human-supervised lanes where an existing visible `skc --tmux` pane should become coordinator-authoritative. | `skc --tmux`, then `skc_coordinator_register_session` | Use when an operator already opened a pane or wants direct terminal visibility. |\n\n## Recommended architecture\n\n```text\nexternal controller / bot\n  ├─ chooses repo/worktree and task policy\n  ├─ starts MCP server: skc mcp-serve coordinator\n  ├─ starts or registers one SKC tmux session\n  ├─ sends one bounded turn at a time\n  ├─ answers structured questions explicitly\n  ├─ marks turn completion/failure with report_status\n  └─ reads artifacts/reports from allowlisted roots\n```\n\nDo not infer completion from terminal output. Treat durable turn state as authoritative and tmux tail output as advisory debug context only.\n\n## Coordinator MCP setup\n\nRender a non-mutating config preview:\n\n```sh\nskc setup hermes --root /path/to/repo --profile my-bot --repo my-repo\n```\n\nInstall into a Hermes-compatible profile only when the target path is intentional:\n\n```sh\nskc setup hermes \\\n  --root /path/to/repo \\\n  --profile my-bot \\\n  --repo my-repo \\\n  --mutation sessions,questions,reports \\\n  --profile-dir /path/to/hermes/profile \\\n  --install\n```\n\nRun provider-independent contract smokes before trying a live model:\n\n```sh\nskc setup hermes --root /path/to/repo --smoke --json\nskc mcp-serve coordinator --check --json\n```\n\nThe generated config uses these environment variables:\n\n| Variable | Purpose |\n| --- | --- |\n| `SKC_COORDINATOR_MCP_WORKDIR_ROOTS` | Required allowlist for workdirs and artifact paths. |\n| `SKC_COORDINATOR_MCP_MUTATIONS` | Startup opt-in for mutation classes: `sessions`, `questions`, `reports`, or `all`. |\n| `SKC_COORDINATOR_MCP_SESSION_COMMAND` | Command used to start real SKC sessions, defaulting to `skc --worktree` in generated setup. |\n| `SKC_COORDINATOR_MCP_PROFILE` | Optional profile namespace so one bot cannot enumerate another profile's state. |\n| `SKC_COORDINATOR_MCP_REPO` | Optional repo namespace so one repo cannot enumerate another repo's state. |\n| `SKC_COORDINATOR_MCP_STATE_ROOT` | Optional coordination state root; defaults under `.skc/state/coordinator-mcp`. |\n| `SKC_COORDINATOR_MCP_ARTIFACT_BYTE_CAP` | Maximum bytes returned by artifact reads. |\n\nMutating calls require both startup opt-in and per-call `allow_mutation: true`. Missing either one fails closed.\n\n## Generic smoke strategy\n\nUse three different smoke levels so CI does not depend on one operator's model, API key, tmux layout, or desktop:\n\n| Smoke | Required for CI | What it proves | Example |\n| --- | --- | --- | --- |\n| Contract smoke | Yes | MCP server metadata, tool discovery, exported tool names, input schemas, read-only default, and mutation-gate failures. No provider credentials or tmux pane required. | `skc mcp-serve coordinator --check --json` and focused tests around `tools/list` plus mutation denial. |\n| Dry-run lifecycle smoke | Yes when changed behavior affects lifecycle state | A generic controller can start/register a mocked session, send a turn, observe active-turn protection, report terminal status, and read the completed turn without a real LLM. | `bun test packages/coding-agent/test/coordinator-mcp.test.ts` uses mocked coordinator services and temporary state roots. |\n| Optional live smoke | No | One operator's local provider/model/profile/tmux setup can run end-to-end in their chosen repo. Failure diagnoses that setup; it must not fail CI or PR validation. | Start `skc mcp-serve coordinator` with local env, dispatch a tiny task, then report/read evidence. |\n\nA public bot integration change should at least preserve the contract smoke and local-leak docs test. Live smokes are diagnostics, not mandatory gates.\n\n## MCP tool contract\n\nRead-only tools:\n\n- `skc_coordinator_list_sessions`\n- `skc_coordinator_read_status`\n- `skc_coordinator_read_tail`\n- `skc_coordinator_read_turn`\n- `skc_coordinator_await_turn`\n- `skc_coordinator_list_questions`\n- `skc_coordinator_list_artifacts`\n- `skc_coordinator_read_artifact`\n- `skc_coordinator_read_coordination_status`\n- `skc_coordinator_watch_events`\n\nMutating tools:\n\n- `skc_coordinator_start_session`\n- `skc_coordinator_register_session`\n- `skc_coordinator_send_prompt`\n- `skc_coordinator_submit_question_answer`\n- `skc_coordinator_report_status`\n\n### Start a managed SKC session\n\nCall `skc_coordinator_start_session` with a canonical workdir inside `SKC_COORDINATOR_MCP_WORKDIR_ROOTS`:\n\n```json\n{\n  \"cwd\": \"/path/to/repo\",\n  \"prompt\": \"Optional first bounded task prompt\",\n  \"allow_mutation\": true\n}\n```\n\nThe returned payload includes `session.session_id`, `session_state`, and, when a prompt is provided, `turn_id`, `status`, `delivery`, `queued`, and `delivered`.\n\n### Register a visible tmux fallback session\n\nIf an operator already started a visible session, register it instead of starting a hidden coordinator session:\n\n```sh\nskc --tmux\n```\n\n```json\n{\n  \"session_id\": \"visible-skc-1\",\n  \"cwd\": \"/path/to/repo\",\n  \"tmux_session\": \"visible-skc-1\",\n  \"tmux_target\": \"visible-skc-1:0.0\",\n  \"visible\": true,\n  \"source\": \"operator-visible-tmux\",\n  \"allow_mutation\": true\n}\n```\n\n`skc_coordinator_register_session` validates safe ids, workdir allowlists, tmux target syntax, and liveness before writing coordinator state.\n\n### Send work as turns\n\nSend one bounded task prompt and persist the returned `turn_id`:\n\n```json\n{\n  \"session_id\": \"skc-demo\",\n  \"prompt\": \"Use /skill:ralplan to build a plan for ...\",\n  \"allow_mutation\": true\n}\n```\n\nA session may have one active turn by default. A second prompt returns `active_turn_exists` unless the bot passes:\n\n- `queue: true` to enqueue a durable follow-up turn, or\n- `force: true` to supersede the previous active turn and audit the supersession.\n\n### Wait or watch for completion\n\nUse `skc_coordinator_read_turn` for polling or `skc_coordinator_await_turn` for bounded waiting:\n\n```json\n{\n  \"session_id\": \"skc-demo\",\n  \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"timeout_ms\": 30000,\n  \"poll_interval_ms\": 1000,\n  \"lines\": 80\n}\n```\n\nTerminal turn statuses are `completed`, `failed`, `cancelled`, and `superseded`. Non-terminal statuses include `queued`, `delivering`, `active`, `waiting_for_answer`, and `completing`.\n\nWhen the work is done, your bot must call `skc_coordinator_report_status` with the turn id. This writes the final response/error, evidence paths, and coordinator report that later reads consume:\n\n```json\n{\n  \"session_id\": \"skc-demo\",\n  \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"status\": \"completed\",\n  \"summary\": \"Implemented the requested fix and ran focused tests.\",\n  \"evidence_paths\": [\"/path/to/repo/test-output.txt\"],\n  \"allow_mutation\": true\n}\n```\n\nUse `status: \"failed\"` plus `blocker` for provider failures, unrecoverable tool failures, missing credentials, policy denial, or task blockers.\nUse `status: \"cancelled\"` when the coordinator policy intentionally stops tracking an active turn, for example after an operator abort or a bot-side shutdown decision. This records the turn as terminal in coordinator state; it does not kill the underlying tmux process. To supersede one active turn with replacement work, send the replacement prompt with `force: true` and preserve the superseded turn id in your audit trail.\n\n### Forward finish/stop lifecycle notifications\n\nDiscord, Hermes, Clawhip, and similar external notifiers should be opt-in and should forward only the public lifecycle surface. Use one of these supported paths:\n\n- Coordinator controllers: watch or poll turn state with `skc_coordinator_watch_events`, `skc_coordinator_await_turn`, or `skc_coordinator_read_turn`, then notify from the terminal turn status your controller records with `skc_coordinator_report_status`.\n- In-process extensions or hooks: subscribe to the public lifecycle events `turn_end` and `agent_end` from the shared hook/extension event contract.\n\nRecommended notification mapping:\n\n| Notification intent | Public surface | Safe meaning |\n| --- | --- | --- |\n| Turn finished | `turn_end` or terminal coordinator turn status `completed` | One LLM turn produced its final assistant message. |\n| Agent stopped / finished | `agent_end` | The agent loop ended for the submitted prompt. |\n| Waiting for user | Coordinator turn status `waiting_for_answer` | The agent is blocked on a structured question. |\n| Failed or blocked | Coordinator status `failed` with a public `blocker` summary | The controller recorded a terminal failure. |\n| Cancelled / superseded | Coordinator status `cancelled` or `superseded` | The controller intentionally stopped tracking or replaced the turn. |\n\nDo not forward raw prompts, transcripts, tool outputs, hidden instructions, private configs, host paths, channel ids, webhook URLs, or tokens. If your notifier needs a human-readable sentence, create a caller-supplied sanitized summary and keep provider/tool details out of the payload.\n\nExample public-safe extension event payloads:\n\n```json\n{ \"type\": \"turn_end\", \"turnIndex\": 2, \"summary\": \"Turn finished; review the local SKC session for details.\" }\n```\n\n```json\n{ \"type\": \"agent_end\", \"summary\": \"Agent loop ended; no raw transcript is included.\" }\n```\n\nExample opt-in forwarding policy:\n\n```json\n{\n  \"enabled\": true,\n  \"events\": [\"turn_end\", \"agent_end\"],\n  \"destination\": \"external-notifier-profile\",\n  \"redaction\": \"metadata-only\"\n}\n```\n\nSKC does not currently expose a structured stop-reason field on `agent_end`; integrators that need `waiting_for_answer`, `failed`, `cancelled`, or `superseded` should prefer the Coordinator MCP turn status because it is explicit, terminal-state oriented, and safe to relay after controller-side redaction.\n\n### Answer structured questions\n\nList pending questions:\n\n```json\n{\n  \"session_id\": \"skc-demo\",\n  \"status\": \"pending\"\n}\n```\n\nThen answer by id:\n\n```json\n{\n  \"session_id\": \"skc-demo\",\n  \"turn_id\": \"turn-00000000-0000-0000-0000-000000000000\",\n  \"question_id\": \"question-1\",\n  \"answer\": { \"decision\": \"approve\" },\n  \"allow_mutation\": true\n}\n```\n\nAlways answer the advertised shape. Do not synthesize approvals for destructive actions unless your bot policy explicitly permits that action.\n\n### Read artifacts and reports\n\nUse `skc_coordinator_list_artifacts` to inspect safe roots and `skc_coordinator_read_artifact` to read a bounded artifact:\n\n```json\n{ \"path\": \"/path/to/repo/.skc/ultragoal/ledger.jsonl\" }\n```\n\nArtifact paths are canonicalized, symlink escapes are rejected, and output is byte-capped. Use `skc_coordinator_read_coordination_status` for status reports written through `skc_coordinator_report_status`.\n\n## RPC stdio integration\n\nUse RPC when your bot owns a single worker subprocess rather than an MCP coordinator. The wire protocol is JSONL over stdio:\n\n```sh\nskc --mode rpc --provider anthropic --model claude-sonnet-4-5\n```\n\nRecommended Python client:\n\n```python\nfrom skc_rpc import RpcClient, WorkflowGate\n\nwith RpcClient(no_session=True, no_rules=True) as client:\n    client.install_headless_ui()\n\n    def on_gate(gate: WorkflowGate) -> None:\n        if gate.kind == \"approval\":\n            client.respond_gate(gate.gate_id, {\"decision\": \"approve\"})\n\n    client.on_workflow_gate(on_gate)\n    turn = client.prompt_and_wait(\"Inspect this repo and report the integration contract.\")\n    print(turn.require_assistant_text())\n```\n\nRPC hosts can also expose host-owned tools and URI schemes. Use these to give SKC controlled access to your bot's issue tracker, queue, database rows, or artifact store without leaking long-lived credentials into the SKC process.\n\nKey RPC lifecycle facts:\n\n- `{ \"type\": \"ready\" }` means the subprocess is ready for commands.\n- `prompt` is acknowledged immediately; completion is observed through `agent_end` or `RpcClient.prompt_and_wait()`.\n- `workflow_gate` frames are answered with `workflow_gate_response`.\n- `extension_ui_request` frames are answered with `extension_ui_response` or a headless policy.\n- Host tool calls and host URI requests are explicit callback frames that must be completed or rejected by the host.\n- `RpcClient` enforces single-flight prompt lifecycle collection; use one client per concurrent worker.\n- `abort` and `abort_and_prompt` are the RPC cancellation commands for subprocess workers; coordinator MCP cancellation is recorded through terminal turn status instead.\n\n## Error handling playbook\n\n| Situation | Bot behavior |\n| --- | --- |\n| `coordinator_mutation_class_disabled:*` | Re-render setup with the required mutation class, or keep the bot in read-only mode. |\n| `coordinator_mutation_call_not_allowed:*` | Add `allow_mutation: true` only after policy approval for that specific call. |\n| `unknown_session` | Re-list sessions; start a new managed session or register the visible tmux fallback. |\n| `active_turn_exists` | Poll the active turn, send with `queue: true`, or use `force: true` only when supersession is intentional. |\n| `timeout` from `await_turn` | Treat as non-terminal. Poll again or inspect `read_status`/`read_tail`; do not mark failure solely from a bounded wait timeout. |\n| Coordinator cancellation | Use `skc_coordinator_report_status` with `status: \"cancelled\"` for an intentionally stopped turn, or send replacement work with `force: true` when supersession is policy-approved. This is coordinator state, not a tmux process kill. |\n| Stale tmux/session state | Check `read_status.session_state` and advisory liveness. Register a new visible session or report the turn failed with a recoverable blocker. |\n| Provider/auth failure | Capture the model/provider error in `report_status` with `status: \"failed\"`; do not retry forever without a policy budget. |\n| Artifact denied | Keep the artifact inside allowlisted roots and avoid symlink escapes. |\n| Malformed or invalid question answer | Re-read the question/gate schema and submit a value matching the advertised shape. |\n| Bot shutdown | Persist `session_id` and active `turn_id`; on restart use `read_turn` and `read_status` before sending more work. |\n\n## Controller examples\n\nGeneric MCP controller config:\n\n```json\n{\n  \"mcp_servers\": {\n    \"skc_coordinator\": {\n      \"command\": \"skc\",\n      \"args\": [\"mcp-serve\", \"coordinator\"],\n      \"env\": {\n        \"SKC_COORDINATOR_MCP_WORKDIR_ROOTS\": \"/home/bot/src/project:/home/bot/src/worktrees\",\n        \"SKC_COORDINATOR_MCP_MUTATIONS\": \"sessions,questions,reports\",\n        \"SKC_COORDINATOR_MCP_PROFILE\": \"controller-prod\",\n        \"SKC_COORDINATOR_MCP_REPO\": \"project\",\n        \"SKC_COORDINATOR_MCP_SESSION_COMMAND\": \"skc --worktree\"\n      },\n      \"enabled\": true\n    }\n  }\n}\n```\n\nExample controller loop:\n\n```text\n1. Start `skc mcp-serve coordinator` with repo/worktree roots allowlisted.\n2. Call `skc_coordinator_start_session` for a SKC-managed worktree session.\n3. Send `/skill:deep-interview`, `/skill:ralplan`, or an approved `skc ultragoal ...` task as one turn.\n4. Await the turn; answer `skc_coordinator_list_questions` entries using bot policy.\n5. Report terminal status with evidence paths.\n6. Read artifacts/reports for the user-facing bot response.\n```\n\nHermes and OpenClaw can use the same MCP tool contract. Their names here are examples of controller products, not privileged integration modes.\n\n## Security and credential boundaries\n\n- Do not put provider API keys, GitHub tokens, or bot secrets in prompts.\n- Prefer host tools, host URI schemes, or bot-side sidecars for credentialed external writes.\n- Keep `SKC_COORDINATOR_MCP_WORKDIR_ROOTS` narrow; do not allow `/`, `/home`, or broad parent directories.\n- Use namespaces for multi-tenant bots.\n- Keep mutation classes minimal: read-only for dashboards, `sessions` for work dispatch, `questions` for answering questions, and `reports` for final state.\n- Treat `.skc/` as local runtime state and evidence. Do not expose it wholesale to untrusted users.\n\n## Related references\n\n- [`docs/hermes-mcp-bridge.md`](./hermes-mcp-bridge.md) — coordinator MCP details and setup adapter behavior.\n- [`docs/rpc.md`](./rpc.md) — JSONL RPC protocol, event frames, workflow gates, host tools, and host URI schemes.\n- [`docs/bridge.md`](./bridge.md) — experimental HTTPS bridge and fail-closed endpoint matrix.\n- [`python/skc-rpc/README.md`](../python/skc-rpc/README.md) — typed Python RPC client examples.\n- [`python/roboskc/README.md`](../python/roboskc/README.md) — example self-hosted GitHub bot using `skc --mode rpc`.\n",
 	"brand-assets.md": "# Brand assets\n\nSayknow-CLI's mascot is an **octopus** 🐙. The source artwork is\n[`assets/brand/mascot.png`](../assets/brand/mascot.png) (512×512, transparent);\nall product images are derived from it.\n\n| Asset | Purpose |\n| --- | --- |\n| [`assets/brand/mascot.png`](../assets/brand/mascot.png) | Source mascot (transparent, 512×512). Edit/replace this to rebrand. |\n| [`assets/hero.png`](../assets/hero.png) | Wide README/docs hero — mascot + `sayknow` wordmark on a deep-navy field. |\n| [`assets/character.png`](../assets/character.png) | Standalone mascot (square). |\n| [`python/roboskc/assets/icon.png`](../python/roboskc/assets/icon.png) | App/service icon (square, transparent). |\n| [`python/roboskc/assets/icon.jpg`](../python/roboskc/assets/icon.jpg) | Same, flattened on a navy background for JPEG. |\n| [`assets/tool-image-fixture.webp`](../assets/tool-image-fixture.webp) | Minimal WebP fixture for terminal image rendering tests. Not a product brand asset. |\n\n## Regenerating\n\nDerived images are composited from `assets/brand/mascot.png` with ImageMagick:\n\n```sh\nSRC=assets/brand/mascot.png\nmagick \"$SRC\" -resize 800x800 assets/character.png\ncp \"$SRC\" python/roboskc/assets/icon.png\nmagick \"$SRC\" -background '#06182b' -flatten -resize 512x512 python/roboskc/assets/icon.jpg\nmagick -size 1200x630 gradient:'#0c2a47'-'#020812' \\\n  \\( \"$SRC\" -resize 300x300 \\) -gravity North -geometry +0+72 -composite \\\n  -gravity North -font \"/System/Library/Fonts/Supplemental/Arial Bold.ttf\" \\\n  -fill '#eef7ff' -pointsize 104 -annotate +0+392 'sayknow' \\\n  -fill '#ff8a4c' -pointsize 27 -annotate +0+520 'Coding should feel like thinking.' \\\n  assets/hero.png\n```\n\n> Note: the mascot is warm/orange while the bundled TUI theme is `blue-octopus`\n> (blue). They coexist intentionally; if you want the terminal palette to match\n> the mascot, switch the default theme to `red-octopus` or add a warm theme.\n",
 	"bridge.md": "# Bridge Protocol Reference (Experimental, Fail-Closed)\n\nBridge mode runs the coding agent as an experimental network control surface over\nHTTPS. The session-control surface is intentionally **fail-closed by default**\nwhile the bridge security model is hardened.\n\nDefault availability:\n\n- `GET /healthz` is available without auth and returns `{ \"status\": \"ok\" }`.\n- `GET /v1/help` is available without auth and reports the fail-closed endpoint\n  matrix.\n- `POST /v1/handshake` remains authenticated, but the default response advertises\n  no enabled session endpoints, no accepted capabilities, no accepted scopes, and\n  no frame types.\n- `GET /v1/sessions/{session_id}/events` fails closed with\n  `403 endpoint_disabled` after bearer auth succeeds.\n- `POST /v1/sessions/{session_id}/commands` fails closed with\n  `403 endpoint_disabled` after bearer auth succeeds and before body parsing,\n  command validation, scope checks, or dispatch.\n- `POST /v1/sessions/{session_id}/control:claim` and\n  `POST /v1/sessions/{session_id}/control:disconnect` fail closed with\n  `403 endpoint_disabled` after bearer auth succeeds.\n- `POST /v1/sessions/{session_id}/ui-responses/{correlation_id}` fails closed\n  with `403 endpoint_disabled` after bearer auth succeeds and before body parsing\n  or controller checks.\n- `POST /v1/sessions/{session_id}/host-tool-results/{correlation_id}` and\n  `POST /v1/sessions/{session_id}/host-uri-results/{correlation_id}` fail closed\n  with `403 endpoint_disabled` after bearer auth succeeds and before body parsing\n  or host callback handling.\n\nThe implementation still contains the v1 protocol scaffolding and internal tests\nfor the previously enabled surface, but external clients must treat events,\ncommands, controller ownership, UI responses, host tool results, and host URI\nresults as unavailable unless a future release explicitly re-enables them.\n\nPrimary implementation:\n\n- `src/modes/bridge/bridge-mode.ts`\n- `src/modes/bridge/auth.ts`\n- `src/modes/bridge/event-stream.ts`\n- `src/modes/bridge/bridge-client-bridge.ts`\n- `src/modes/bridge/bridge-ui-context.ts`\n- `src/modes/shared/agent-wire/*` (protocol, scopes, handshake, command dispatch/validation, host bridges)\n- `packages/bridge-client/src/*`\n\n## Startup\n\n```bash\nskc --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| `SKC_BRIDGE_TOKEN` | Yes | — | Bearer token for authenticated endpoints. **Secret — never commit.** |\n| `SKC_BRIDGE_TLS_CERT` | Yes | — | Path to the TLS certificate (PEM). |\n| `SKC_BRIDGE_TLS_KEY` | Yes | — | Path to the TLS private key (PEM). **Secret — never commit.** |\n| `SKC_BRIDGE_HOST` | No | `127.0.0.1` | Bind hostname. |\n| `SKC_BRIDGE_PORT` | No | `4077` | Bind port (1–65535). |\n| `SKC_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 `SKC_BRIDGE_TLS_CERT` and `SKC_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-SKC-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| `get_pending_workflow_gates` | `message:read` |\n| `set_model` | `model` |\n| `cycle_model` | `model` |\n| `get_available_models` | `model` |\n| `set_thinking_level` | `model` |\n| `cycle_thinking_level` | `model` |\n| `set_steering_mode` | `control` |\n| `set_follow_up_mode` | `control` |\n| `set_interrupt_mode` | `control` |\n| `compact` | `control` |\n| `set_auto_compaction` | `control` |\n| `set_auto_retry` | `control` |\n| `abort_retry` | `control` |\n| `bash` | `bash` |\n| `abort_bash` | `bash` |\n| `get_session_stats` | `message:read` |\n| `export_html` | `export` |\n| `switch_session` | `session` |\n| `branch` | `session` |\n| `get_branch_messages` | `session` |\n| `get_last_assistant_text` | `message:read` |\n| `set_session_name` | `session` |\n| `handoff` | `admin` |\n| `get_messages` | `message:read` |\n| `get_login_providers` | `admin` |\n| `login` | `admin` |\n| `negotiate_unattended` | `control` |\n| `workflow_gate_response` | `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`@sayknow-cli/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 `@sayknow-cli/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 `skc` 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 `skc --tmux` from that directory. SKC 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 SKC leader with `skc --tmux` from that directory. If you want SKC to create the sibling worktree, use `skc --tmux --worktree <branch-like-name>`; the argument is a worktree/branch name, not a filesystem path.\n3. Submit the workflow appropriate to the task: `/skill:deep-interview` for requirements discovery, `/skill:ralplan` for plan consensus, and `skc ultragoal ...` for durable goal tracking through execution and verification.\n4. Use `skc 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 SKC 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 SKC with other coding agents](../README.md#using-skc-with-other-coding-agents).\n",
 	"codebase-overview.md": "# Codebase Overview\n\nThis document maps the main parts of the `sayknow-cli` repository. The root README stays intentionally small; this file is the architecture-oriented companion.\n\n## Product shape\n\nSayknow-CLI (`skc`) 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 `.skc/`.\n\nDefault workflow skills are embedded from:\n\n```text\npackages/coding-agent/src/defaults/skc/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 `.skc` directory does not remove the default workflow surface.\n\n## Packages\n\n### `packages/coding-agent/`\n\nMain `skc` CLI and product runtime.\n\n- `packages/coding-agent/package.json` exposes the `skc` binary at `src/cli.ts` and the SDK/barrel entrypoint at `src/index.ts`.\n- `packages/coding-agent/src/cli.ts` is the executable bootstrap. It registers CLI commands such as `setup`, `deep-interview`, `ralplan`, `ultragoal`, `team`, and the default launch path.\n- `packages/coding-agent/src/main.ts` adapts CLI options into session creation and dispatches interactive, print, RPC, RPC-UI, ACP, and Bridge modes.\n- `packages/coding-agent/src/sdk.ts` assembles settings, model registry, auth, workspace/context discovery, skills, rules, tools, system prompt, and the underlying `@sayknow-cli/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/skc-defaults.ts` embeds and installs the default workflow skills.\n- `packages/coding-agent/src/task/agents.ts` embeds bundled task-agent prompts. The public contract is `executor`, `architect`, `planner`, and `critic`; other bundled prompts are internal/runtime utilities.\n- `packages/coding-agent/src/coordinator/contract.ts` defines the transport-neutral third-party coordinator contract used by `skc mcp-serve coordinator`, `skc coordinator`, and `skc setup hermes`.\n- `packages/coding-agent/src/coordinator-mcp/server.ts` implements the outward MCP adapter for bot/coordinator integrations, including session start/register, turn state, question answering, status reports, and artifact reads.\n- `docs/external-control-readiness.md` classifies the public external-control surfaces: Coordinator MCP for multi-session control planes, RPC stdio for subprocess workers, ACP for editor/ACP clients, and Bridge HTTPS as experimental/fail-closed protocol scaffolding.\n\n### `packages/ai/`\n\nProvider/model boundary for LLM access.\n\n- `packages/ai/src/index.ts` exports model registry/resolution, provider implementations, auth broker/gateway/storage, streaming, usage, retry/overflow utilities, OAuth, discovery, and validation helpers.\n- `packages/ai/src/types.ts` defines provider, model, context, message, tool, usage, reasoning, and stream-event contracts.\n- `packages/ai/src/stream.ts` dispatches model-driven streams to the right provider/API implementation and normalizes streaming events.\n- `packages/ai/src/model-manager.ts` merges static, cached, dynamic, and remote model sources.\n- `packages/ai/README.md` documents tool calling, partial streaming tool calls, thinking/reasoning, provider configuration, context handoff, and OAuth flows.\n\n### `packages/agent/`\n\nStateful agent runtime built on `@sayknow-cli/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 `skc-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/skc-rpc/`\n\nTyped Python client for `skc --mode rpc`.\n\n- `python/skc-rpc/pyproject.toml` packages `skc-rpc` for Python 3.11+.\n- `python/skc-rpc/README.md` documents the process-backed stdio client, typed command methods, startup flags, event listeners, todo seeding, host-owned tools, and host-owned URI schemes.\n- `docs/bot-integration.md` is the practical entry guide for generic external controller and bot authors; it ties together coordinator MCP, RPC stdio, bridge limitations, visible tmux fallback, provider-independent smokes, errors, and artifact/report consumption.\n\n### `python/roboskc/`\n\nSelf-hosted GitHub triage/fix bot that drives `skc --mode rpc`.\n\n- `python/roboskc/AGENTS.md` is the authoritative local contract for this subtree.\n- `python/roboskc/pyproject.toml` packages `roboskc` for Python 3.11+ with FastAPI, httpx, pydantic settings, Click, and `skc-rpc`.\n- `python/roboskc/README.md` documents the webhook-to-worktree-to-skc 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 `@sayknow-cli/ai`, constructs the system prompt, and instantiates `@sayknow-cli/agent-core`. The agent loop streams model events, executes tools, records tool results, and hands state back to the selected mode: interactive TUI, print, RPC, RPC-UI, ACP, or Bridge.\n\n## Verification and gates\n\nPackage-local checks are defined in each `package.json`. For workflow-definition or default-surface changes, the focused gates are:\n\n```sh\nbun scripts/check-visible-definitions.ts\nbun scripts/verify-g002-gates.ts\nbun scripts/rebrand-inventory.ts --strict\nbun test packages/coding-agent/test/default-skc-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",
@@ -18,17 +18,18 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"composer-codex-parity.md": "# Composer 2.5 Fast parity repro\n\nThis document records the one-command repros for the Composer 2.5 Fast stability work. Scope is SKC-local only: no OpenClaw reference, no Cursor live e2e, no upstream xAI/server change, and no Codex refactor. Codex is the baseline/report model only.\n\n## Focused discipline regression\n\n```sh\nbun test packages/ai/test/composer-discipline.test.ts\n```\n\nExpected contract:\n\n- `grok-build/grok-composer-2.5-fast` and other composer ids receive `COMPOSER_EDIT_DISCIPLINE_PROMPT` ahead of host/default system prompts on the `openai-completions`, `openai-responses`, and Cursor RPC prompt paths.\n- Non-composer models keep their system prompt payload unchanged.\n- The prompt explicitly covers adversarial shell file discovery, shell file reads, out-of-band shell writes, fabricated/stale anchors, malformed tool arguments, and contaminated bash command strings.\n\n## V3 mock P1 gate\n\n```sh\nbun packages/agent/bench/composer-stability-v3.ts --mock --seed 42 -n 5 --model grok-build/grok-composer-2.5-fast --baseline-model openai-codex/gpt-5.5:low\n```\n\nEquivalent package script:\n\n```sh\nbun run bench:composer-stability-v3\n```\n\nP1 passes when `candidateFailureCount <= baselineFailureCount` over the same deterministic scenario matrix. Mock mode is a smoke gate, not live parity proof.\n\n## V3 trace-backed gate\n\n```sh\nbun packages/agent/bench/composer-stability-v3.ts --trace --trace-file packages/agent/test/fixtures/composer-stability-v3/traces/parity.json\n```\n\nEquivalent package script:\n\n```sh\nbun run bench:composer-stability-v3:trace\n```\n\nTrace files can be JSON, JSON arrays, JSON `{ \"records\": [...] }`, or JSONL. Each record declares `scenarioId`, `modelRole` (`candidate` or `baseline`), `model`, `trial`, optional `expected`, and `events`. The classifier maps recorded tool behavior to failure classes:\n\n- `shell-read`\n- `shell-file-discovery`\n- `shell-write`\n- `contaminated-command`\n- `bad-anchor-unrecovered`\n- `malformed-tool-args-unrecovered`\n- `sanitize-replay-regression`\n- `wrong-file-edit`\n- `missing-tool-turn`\n- `timeout`\n\nTrace P1 is applicable only when both candidate and baseline records exist, and it can pass only with at least three comparable candidate/baseline scenario ids so a one-scenario smoke cannot fake parity. It reports `candidateFailureCount`, `baselineFailureCount`, `parityDelta`, per-scenario counts, and the trace artifact paths that were scored.\n\n## Optional live smoke\n\n```sh\nbun packages/agent/bench/composer-stability-v3.ts --live -n 3 --model grok-build/grok-composer-2.5-fast --baseline-model openai-codex/gpt-5.5:low\n```\n\nLive smoke is informational. Without `GROK_CLI_OAUTH_TOKEN` and Codex/OpenAI credentials, or without trace artifacts from a real capture, `--live` exits successfully with an explicit skip record and `p1.applicable=false`; it does not fake a P1 pass. Pass `--live --trace-dir <captured-traces>` to score real captured runs through the same trace classifier. Cursor live e2e is intentionally out of scope.\n\n## Broader local verification\n\n```sh\nbun test packages/agent/test/composer-stability-v3.test.ts packages/coding-agent/test/grok-cli-sanitize.test.ts packages/coding-agent/test/grok-build-stream.test.ts\nbun test packages/agent packages/ai\nbun scripts/verify-g002-gates.ts\n```\n\nUse `mise x bun@1.3.14 -- <command>` when `bun` is not on `PATH`.\n",
 	"computer-use/README.md": "# Native computer-use tool\n\nStatus: **in progress (draft)** — coordinate contract + native `screenshot`\ncapture landed and verified; input primitives, kill-switch, and napi/TS surface\nto follow.\n\nA new, model-agnostic `computer` tool that lets any model drive the user's real\nmacOS desktop via the OpenAI computer-use action set. Built fresh (the\nopen-source `openai/codex` repo has no GUI computer-use source to copy; only the\npublic action *schema* is mirrored).\n\nThis feature was scoped through SKC's deep-interview (requirements) and ralplan\n(Planner/Architect/Critic consensus) workflows. The full deep-interview spec and\nthe consensus plan + ADR are the authoritative source of truth; this document is\nthe committed summary and roadmap.\n\n## Locked decisions (ADR summary)\n\n- **Target:** the user's real macOS desktop, OS-native control. v1 is macOS-only\n  (Linux/Windows deferred behind the same tool schema).\n- **Driver:** any model via a generic structured tool-call interface — no\n  provider-specific computer-use API.\n- **Action set:** the exact OpenAI computer-use primitives — `screenshot`,\n  `click`, `double_click`, `move`, `drag`, `scroll`, `type`, `keypress`, `wait`.\n- **Implementation:** built fresh in the Rust `pi-natives` crate (napi),\n  exposed through `packages/natives` to a new\n  `packages/coding-agent/src/tools/computer.ts`, kept deliberately lower-level\n  than the existing `browser` tool (coordinate/input primitives only, no web\n  semantics).\n- **Coordinate contract:** a single normalized virtual display. The returned\n  screenshot's pixel dimensions *are* the action coordinate space; Rust owns the\n  transform to macOS logical points (Retina/HiDPI-safe) and display selection.\n- **Permissions:** macOS TCC (Accessibility + Screen Recording) auto-preflighted;\n  on a missing grant, open the relevant Settings pane and return a clear\n  \"grant then retry/relaunch\" error.\n- **Gating:** off by default; opt-in config flag (per session) plus a persistent\n  always-on option.\n- **Safety:** no per-action approval (autonomous), **but** a daemon-enforced\n  global kill-switch outside model control (global hotkey OR TUI stop key) that\n  aborts queued actions, releases held keys/buttons, suspends further input, and\n  snapshots the last screen. Reset is user-only, never via the model-facing tool.\n- **Architecture:** every primitive delegates to one central Rust\n  `execute_action` state machine (preflight, validation, cancellation, audit,\n  screenshot policy, release-all) so per-primitive methods cannot drift past the\n  safety contract. The in-process supervisor sits behind a `SupervisorClient`\n  boundary so an out-of-process daemon can replace it later without changing the\n  napi surface.\n\n## Capture + coordinate contract (shipped)\n\n`crates/pi-natives/src/computer/coords.rs` implements the pure, framework-free\ncore: `NormalizedDisplay` maps a screenshot-space pixel `(x, y)` to a macOS\nlogical point via per-axis scale and the display's logical origin, rejecting\nout-of-bounds and non-finite inputs. It is unit-tested (scale 1.0/2.0,\nfractional and anisotropic scale, non-zero origins, edges, out-of-bounds,\ninvalid scale) and requires no display or granted permissions.\n\n`crates/pi-natives/src/computer/capture.rs` (macOS) implements the read-only\n`screenshot` primitive: it captures the primary display via CoreGraphics into a\nPNG and derives the `NormalizedDisplay` scale from captured physical pixels vs\nlogical bounds, surfacing a missing Screen Recording grant as\n`CaptureError::CaptureFailed` (never a silent black frame). Verified live: a\nreal, non-uniform primary-display capture decodes as a PNG with matching\ndimensions (`cargo test -p pi-natives --ignored captures_non_uniform_primary_display`).\n\n## Delivery roadmap\n\nDelivery ships a `screenshot`+`click`+`type` vertical slice first; the remaining\nsix primitives fast-follow; v1 acceptance = all nine primitives drive a real\nmacOS app end-to-end plus a kill-switch drill (per-primitive napi unit tests +\nmanual macOS E2E).\n\n| Slice | Scope | Status |\n|-------|-------|--------|\n| Coordinate contract + planning docs | `coords` module + unit tests + this doc | **done (this PR)** |\n| Native screen capture (`screenshot`) | `capture` module, primary display, PNG + scale | **done (this PR, verified live)** |\n| TCC preflight (`permissions`) | Accessibility + Screen Recording checks, Settings openers, fail-closed guards | **done (this PR, verified live)** |\n| napi screenshot binding (`computerScreenshot`) | napi → `packages/natives` → TS, verified live | **done (this PR)** |\n| Native input orchestration (`input`) | `InputController` click/double_click/move/drag/scroll/type/keypress + release_all over an `EventSink` | **done (this PR)** — logic unit-tested; **live cursor-move injection verified** (Accessibility granted) |\n| Central `execute_action` state machine | preflight + supervisor + cancellation + audit + release-all | planned |\n| Kill-switch supervisor + global-hotkey event-tap | `supervisor` (fail-closed `input_allowed`, user-only reset) + `hotkey` CGEventTap on a CFRunLoop thread | **done (this PR)** — supervisor unit-tested; **synthetic-hotkey latch verified live** |\n| Supervisor-gated `execute_action` + napi/TS `computer` tool | wire input through `input_allowed` + cancellation; `ComputerController` napi; `computer.ts` schema/gating/prompt/renderer | next |\n| Manual macOS E2E acceptance | TextEdit all-nine + kill-switch drill | planned (requires macOS hardware + granted TCC + human operator) |\n\nThe remaining input backend, kill-switch, napi/TS surface, and manual\nend-to-end acceptance still require injecting events into a live desktop and a\nhuman-operated drill, so they are tracked as follow-up work rather than landed\nin this draft.\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 `$env` from `@sayknow-cli/utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Agent `.env` (`~/.skc/agent/.env`, respecting `SKC_CONFIG_DIR` / `SKC_CODING_AGENT_DIR`) for keys not already set\n4. Config-root `.env` (`~/.skc/.env`, respecting `SKC_CONFIG_DIR`) for keys not already set\n5. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule inside each `.env` file: `SKC_*` keys are mirrored to `SKC_*` 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| `SKC_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 `skc 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| `SKC_AUTH_BROKER_TOKEN` | Bearer token sent on every broker endpoint except `/v1/healthz`                                   | `SKC_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 `~/.skc/` (respecting `SKC_CONFIG_DIR`).         |\n\nThe gateway has no dedicated env vars — it inherits `SKC_AUTH_BROKER_*`. Its own inbound bearer token lives at `<config-dir>/auth-gateway.token` and is managed via `skc auth-gateway token`.\n\n### Multi-account credential ranking\n\nWhen more than one OAuth credential is stored for the same provider (e.g. several Anthropic accounts), `AuthStorage` ranks them at session start to pick which one serves the session. This env var selects the ranking strategy; it is fully opt-in and does not change the default.\n\n| Variable                      | Used for                                          | Required when  | Notes / precedence                                                                                                                                                                                                                                                                                            |\n| ----------------------------- | ------------------------------------------------- | -------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `SKC_CREDENTIAL_RANKING_MODE` | Multi-account OAuth credential selection strategy | Never (opt-in) | `balanced` (default) prefers the least-drained account (spreads load, keeps burst headroom). `earliest-reset` prefers the soonest-to-reset non-blocked account (earliest-expiry-first) so perishable tumbling-window quota (e.g. Claude 5h/7d) is drained before reset. Unset/unknown → `balanced`. Only affects session-start ranking; blocked/exhausted accounts still sort last. |\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, SKC explicitly sends `User-Agent: Sayknow-CLI/<package version>` plus OpenRouter attribution headers. For the built-in OpenAI Responses transport and generic OpenAI-compatible Chat Completions transport, SKC passes model/provider headers through the OpenAI JavaScript SDK and does not set a SKC 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### SKC workflow bridge commands\n\n`skc ralplan`, `skc deep-interview`, and `skc state` are private runtime bridge commands. They require `SKC_RUNTIME_BINARY` (or legacy `SKC_LEGACY_RUNTIME_BINARY`) to point at the private runtime executable; public bundled workflow use remains through `/skill:ralplan` and `/skill:deep-interview` inside a SKC session.\n\n| Variable | Behavior |\n| --- | --- |\n| `SKC_RUNTIME_BINARY` | Private runtime bridge binary for `skc ralplan`, `skc deep-interview`, and `skc state` |\n| `SKC_LEGACY_RUNTIME_BINARY` | Legacy fallback bridge binary name |\n\n### Interactive `--tmux` startup and scroll/mouse profile\n\n`skc --tmux` launches the interactive TUI inside a fresh SKC-managed tmux session. When SKC creates that session it applies a profile that is **scoped to the SKC session only** (it never runs `set -g` / global tmux options), including:\n\n- `mouse on` — enables mouse-wheel scrolling into tmux copy-mode (history/scrollback).\n- `set-clipboard on` and a readable copy-mode `mode-style`.\n- SKC ownership/identity tags (`@skc-profile`, branch/project markers).\n\nThis profile is applied on macOS, Linux, and WSL (Linux) alike; only native Windows (`win32`) skips the tmux launch. It is applied **only to sessions SKC itself creates**. If you start tmux yourself and then run `skc` inside it, SKC leaves your tmux configuration untouched — add `set -g mouse on` to your own `~/.tmux.conf`, or relaunch with `skc --tmux` to get the managed profile.\n\n| Variable | Behavior |\n| --- | --- |\n| `SKC_LAUNCH_POLICY` | Launch policy for `--tmux` startup: `tmux` (default) or `direct` (skip the tmux session) |\n| `SKC_TMUX_SESSION` | Explicit tmux session name override for `--tmux` startup |\n| `SKC_TMUX_COMMAND` | tmux binary/command override for every SKC tmux flow (`SKC_TEAM_TMUX_COMMAND` is honored as a team-path alias) |\n| `SKC_TMUX_PROFILE` | Set `0`/`false`/`off` to apply only the required ownership tags and skip the scroll/mouse/clipboard profile |\n| `SKC_MOUSE` | Set `0`/`false`/`off` to skip `mouse on`, leaving wheel scrolling to the host terminal instead of tmux copy-mode |\n\n#### WSL / Windows Terminal scrolling\n\nOn WSL with Windows Terminal, scrolling behaves differently depending on whether tmux owns the mouse:\n\n- **With the SKC profile (default):** the mouse wheel enters tmux copy-mode and scrolls the pane's scrollback. Keyboard fallback: `Ctrl-b [` to enter copy-mode, then `PgUp`/arrows; `q` to exit.\n- **Without tmux mouse capture (`SKC_MOUSE=off`, or running outside `skc --tmux`):** Windows Terminal handles the wheel and scrolls its own native scrollback.\n\nIf the wheel does not scroll inside `skc --tmux` on WSL, confirm the session is SKC-managed (`skc session list`) so the `mouse on` profile is actually applied; sessions you launched yourself do not receive it. Set `SKC_MOUSE=off` if you prefer Windows Terminal's native scrollback over tmux copy-mode.\n\n### Team tmux backend, dry-run, and state paths\n\n`skc team ...` starts tmux worker panes from the current tmux-backed leader session. Start that leader with `skc --tmux` first; `skc team` intentionally does not create or attach the leader session itself.\n\n`skc 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>/.skc/state/team/<team>/`; treat it as ephemeral smoke-test/review state. Do not commit generated `.skc/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| `SKC_TEAM_STATE_ROOT` | Overrides the team state root (default `<cwd>/.skc/state/team`) |\n| `SKC_TEAM_TMUX_COMMAND` | tmux binary/command override for team launch |\n| `SKC_TEAM_WORKER_COMMAND` | Worker SKC command override |\n| `SKC_TEAM_WORKER_CLI` | Team worker CLI selector; accepted values are `auto` or `skc` |\n| `SKC_TEAM_WORKER_CLI_MAP` | Comma-separated worker CLI selector map; entries must be `auto` or `skc` |\n\n### Hermes MCP bridge\n\n`skc mcp-serve coordinator` exposes a SKC-native outward MCP bridge for Hermes-style coordinators. `skc 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\nCoordinator MCP currently exposes durable polling/await tools, not push subscriptions. Consume `skc_coordinator_read_coordination_status`, `skc_coordinator_read_turn`, or bounded `skc_coordinator_await_turn` for state changes.\n\n| Variable | Behavior |\n| --- | --- |\n| `SKC_COORDINATOR_MCP_WORKDIR_ROOTS` | Required allowlist for workdir and artifact paths. `skc 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| `SKC_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| `SKC_COORDINATOR_MCP_ARTIFACT_BYTE_CAP` | Max bytes returned by artifact reads (default `65536`, capped at `1048576`). |\n| `SKC_COORDINATOR_MCP_STATE_ROOT` | Bridge coordination state root (default `<cwd>/.skc/state/coordinator-mcp`). |\n| `SKC_COORDINATOR_MCP_PROFILE` | Optional profile namespace for session/question/report state. Missing scope never widens to global session enumeration. |\n| `SKC_COORDINATOR_MCP_REPO` | Optional repo namespace for session/question/report state. Missing scope never widens to global session enumeration. |\n| `SKC_COORDINATOR_MCP_SESSION_COMMAND` | SKC-compatible command used by mutating session startup to launch a detached tmux session. `skc setup hermes` renders this to `skc --worktree` by default so Hermes-installed configs start real SKC work in a SKC-managed worktree while preserving SKC 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| `SKC_COORDINATOR_MCP_SETUP_MANAGED_BY` | Marker written by `skc setup hermes` for safe managed config updates. |\n| `SKC_COORDINATOR_MCP_SETUP_SCHEMA_VERSION` | Managed setup schema version written by `skc setup hermes`. |\n| `SKC_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| `SKC_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| `SKC_OPENAI_CODE_DEBUG`                     | `1`/`true` enables OpenAI code provider debug logging      |\n| `SKC_OPENAI_CODE_WEBSOCKET`                 | `1`/`true` enables websocket transport preference    |\n| `SKC_OPENAI_CODE_WEBSOCKET_V2`              | `1`/`true` enables websocket v2 path                 |\n| `SKC_OPENAI_CODE_WEBSOCKET_IDLE_TIMEOUT_MS` | Positive integer override (default 300000)           |\n| `SKC_OPENAI_CODE_WEBSOCKET_RETRY_BUDGET`    | Non-negative integer override (default 5)            |\n| `SKC_OPENAI_CODE_WEBSOCKET_RETRY_DELAY_MS`  | Positive integer base backoff override (default 500) |\n| `SKC_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| `SKC_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution); any other value forces `short`. The Anthropic provider already defaults to `long` (1h) when unset, so this is mainly an opt-out (`short`) or a way to extend long retention to other providers. |\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| `SKC_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 `~/.skc/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| `SKC_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| `SKC_PY`                   | Eval backend override: `0`/`bash`=JavaScript only, `1`/`py`=Python only, `mix`/`both`=both; invalid values ignored |\n| `SKC_PYTHON_SKIP_CHECK`    | If `1`, skips Python interpreter availability checks (subprocess runner still starts on demand)                     |\n| `SKC_PYTHON_INTEGRATION`   | If `1`, opts gated integration tests in (e.g. `python-runner.integration.test.ts`) into running against real Python |\n| `SKC_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_`, `SKC_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable                     | Default / behavior                                                                                 |\n| ---------------------------- | -------------------------------------------------------------------------------------------------- |\n| `SKC_SMOL_MODEL`              | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence)                           |\n| `SKC_SLOW_MODEL`              | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence)                           |\n| `SKC_PLAN_MODEL`              | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence)                           |\n| `SKC_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| `SKC_BLOCKED_AGENT`           | Blocks a specific subagent type in task tool                                                       |\n| `SKC_SUBPROCESS_CMD`          | Overrides subagent spawn command (`skc` / `skc.cmd` resolution bypass)                             |\n| `SKC_TASK_MAX_OUTPUT_BYTES`   | Max captured output bytes per subagent (default `500000`)                                          |\n| `SKC_TASK_MAX_OUTPUT_LINES`   | Max captured output lines per subagent (default `5000`)                                            |\n| `SKC_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. `SKC_TIMING=x` exits the process with code 0 right after printing in interactive mode (use to measure cold startup only). `SKC_TIMING=full` lists every module-load entry instead of just the top N. |\n| `SKC_PACKAGE_DIR`             | Overrides package asset base dir resolution (docs/examples/changelog path lookup)                  |\n| `SKC_DISABLE_LSPMUX`          | If `1`, disables lspmux detection/integration and forces direct LSP server spawning                |\n| `SKC_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| `SKC_EDIT_VARIANT`            | Forces edit tool variant when valid (`patch`, `replace`, `hashline`, `atom`, `vim`, `apply_patch`) |\n| `SKC_FORCE_IMAGE_PROTOCOL`    | Forces supported image protocol (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) where used            |\n| `SKC_ALLOW_SIXEL_PASSTHROUGH` | Allows SIXEL passthrough when `SKC_FORCE_IMAGE_PROTOCOL=sixel`                                      |\n| `SKC_NO_PTY`                  | If `1`, disables interactive PTY path for bash tool                                                |\n\n`SKC_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 `@sayknow-cli/utils/dirs` and affect where coding-agent stores data.\n\n| Variable              | Default / behavior                                                            |\n| --------------------- | ----------------------------------------------------------------------------- |\n| `SKC_CONFIG_DIR`       | Config root dirname under home (default `.skc`)                               |\n| `SKC_CODING_AGENT_DIR` | Full override for agent directory (default `~/<SKC_CONFIG_DIR or .skc>/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| `SKC_BASH_NO_CI`            | Suppresses automatic `CI=true` injection into spawned shell env                |\n| `ANTHROPIC_MODEL_BASH_NO_CI`        | Legacy alias fallback for `SKC_BASH_NO_CI`                                      |\n| `SKC_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 `SKC_BASH_NO_LOGIN`                                   |\n| `SKC_SHELL_PREFIX`          | Optional command prefix wrapper                                                |\n| `ANTHROPIC_MODEL_CODE_SHELL_PREFIX` | Legacy alias fallback for `SKC_SHELL_PREFIX`                                    |\n| `VISUAL`                   | Preferred external editor command                                              |\n| `EDITOR`                   | Fallback external editor command                                               |\n\nCurrent implementation: `SKC_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| `SKC_NOTIFICATIONS`        | `off` / `0` / `false` suppress desktop notifications                                  |\n| `SKC_TUI_WRITE_LOG`        | If set, logs TUI writes to file                                                       |\n| `SKC_HARDWARE_CURSOR`      | If `1`, enables hardware cursor mode                                                  |\n| `SKC_CLEAR_ON_SHRINK`      | If `1`, clears empty rows when content shrinks                                        |\n| `SKC_DEBUG_REDRAW`         | If `1`, enables redraw debug logging                                                  |\n| `SKC_TUI_DEBUG`            | If `1`, enables deep TUI debug dump path                                              |\n| `SKC_FORCE_IMAGE_PROTOCOL` | Forces terminal image protocol detection (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) |\n| `SKC_TUI_KEYBOARD_PROTOCOL` | Enhanced keyboard input (Kitty keyboard protocol + xterm modifyOtherKeys). Enabled by default; set `0` / `false` to leave the keyboard in its default mode. Use this when a terminal (e.g. Android Termius) breaks IME/Hangul composition while these enhanced modes are active. |\n\n---\n\n## 10) Commit generation controls\n\n| Variable                  | Behavior                                                            |\n| ------------------------- | ------------------------------------------------------------------- |\n| `SKC_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `SKC_COMMIT_NO_FALLBACK`   | If `true`, disables fallback when agent returns no proposal         |\n| `SKC_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| `SKC_BRIDGE_TOKEN` | Yes | — | Bearer token required on authenticated endpoints. **Secret — never commit.** |\n| `SKC_BRIDGE_TLS_CERT` | Yes | — | Path to the TLS certificate (PEM). Startup fails closed if cert/key are missing (TLS is mandatory, including loopback). |\n| `SKC_BRIDGE_TLS_KEY` | Yes | — | Path to the TLS private key (PEM). **Secret — never commit; `chmod 600`.** |\n| `SKC_BRIDGE_HOST` | No | `127.0.0.1` | Bind hostname. |\n| `SKC_BRIDGE_PORT` | No | `4077` | Bind port (1–65535). |\n| `SKC_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 (`SKC_BRIDGE_TOKEN` and the `SKC_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",
-	"external-control-readiness.md": "# External control surface readiness\n\nThis document classifies every public SKC surface that an external controller, bot, editor, or harness can use to drive `skc`. It is intentionally narrower than the generic bot guide: it states what is ready today, what is only editor/client-oriented, and what remains experimental.\n\n## Readiness matrix\n\n| Surface | Current readiness | Primary command | Use when | Do not use when | Provider-independent smoke path |\n| --- | --- | --- | --- | --- | --- |\n| Coordinator MCP | Preferred multi-session bot/control-plane surface. | `skc mcp-serve coordinator` | A controller needs to start/register SKC sessions, send bounded turns, answer questions, read artifacts, and write durable status reports across one or more repo/worktree lanes. | The controller only needs one embedded subprocess and can own stdio directly. | `skc mcp-serve coordinator --check --json`; `packages/coding-agent/test/coordinator-mcp.test.ts`; `packages/coding-agent/test/setup-cli.test.ts`. |\n| RPC stdio | Stable subprocess worker surface. | `skc --mode rpc` | A host embeds one SKC worker process, sends JSONL commands over stdin, consumes stdout frames, and optionally uses `python/skc-rpc`. | The host needs remote HTTPS, multi-session orchestration, or MCP tool discovery. | `packages/coding-agent/test/rpc-unattended-stdio.test.ts`; `packages/coding-agent/test/rpc-client.start.test.ts`; `packages/coding-agent/test/rpc-host-tools.test.ts`; `packages/coding-agent/test/rpc-host-uris.test.ts`. |\n| ACP mode | Editor/ACP client surface with tested protocol initialization, session lifecycle, client-owned MCP, file/terminal client bridges, permission routing, and stdout hygiene. | `skc --mode acp` or `skc acp` | An editor or ACP-compatible client wants to drive SKC through the Agent Client Protocol over stdio. | A bot needs a generic multi-session control plane; use Coordinator MCP instead. | `packages/coding-agent/test/acp-initialize-conformance.test.ts`; `packages/coding-agent/test/acp-stdout-hygiene.test.ts`; `packages/coding-agent/test/acp-lazy-startup.test.ts`; `packages/coding-agent/test/acp-mcp-isolation.test.ts`; `packages/coding-agent/test/read-acp-fs.test.ts`; `packages/coding-agent/test/write-acp-fs.test.ts`; `packages/coding-agent/test/bash-acp-terminal.test.ts`. |\n| Bridge HTTPS | Experimental, fail-closed remote session-control surface. | `skc --mode bridge` | A future remote client needs HTTPS protocol scaffolding, authenticated health/help/handshake behavior, or SDK compatibility tests. | Production bot lifecycle, default external-controller integration, or claims that remote session events/commands are enabled by default. | `packages/coding-agent/test/bridge/bridge-auth.test.ts`; `packages/coding-agent/test/bridge/bridge-mode-handler.test.ts`; `packages/coding-agent/test/bridge/bridge-conformance.test.ts`; `packages/bridge-client/test/bridge-client.test.ts`. |\n\n## Surface details\n\n### Coordinator MCP\n\nCoordinator MCP is the default answer for external bot and orchestration integrations. It exposes a transport-level MCP tool contract for session discovery, managed session start, visible tmux registration, prompt delivery, bounded turn waiting, structured question answering, artifact reads, and explicit completion/failure/cancellation reports.\n\nReadiness claim:\n\n- Ready as the preferred generic external-controller control plane.\n- Provider-independent contract checks exist for server metadata, tool discovery, read-only defaults, mutation gates, setup rendering, and dry-run lifecycle behavior.\n- It is not a provider/model contract. Live model execution remains the operator's environment-specific smoke.\n\nPrimary references:\n\n- `docs/bot-integration.md`\n- `docs/hermes-mcp-bridge.md`\n- `packages/coding-agent/src/coordinator/contract.ts`\n- `packages/coding-agent/src/coordinator-mcp/server.ts`\n\n### RPC stdio\n\nRPC mode is the stable embedded-worker surface. It is newline-delimited JSON over stdio and emits a `{ \"type\": \"ready\" }` frame before accepting commands. Hosts can drive prompts, state queries, host tools, host URI schemes, workflow gates, extension UI responses, cancellation, and unattended negotiation through the RPC command catalog.\n\nReadiness claim:\n\n- Ready for single-process host integration and subprocess workers.\n- The public Python client in `python/skc-rpc` is the recommended typed client for Python hosts.\n- Multi-session orchestration and MCP tool discovery are out of scope for RPC; use Coordinator MCP for those.\n\nPrimary references:\n\n- `docs/rpc.md`\n- `python/skc-rpc/README.md`\n- `packages/coding-agent/src/modes/rpc/rpc-mode.ts`\n- `packages/coding-agent/src/modes/rpc/rpc-types.ts`\n\n### ACP mode\n\nACP mode runs SKC as an Agent Client Protocol server over stdio. It is useful for editor-style clients that own the ACP transport and want session creation, session load/fork/resume/close metadata, prompt handling, client-provided MCP servers, permission prompts, editor file reads/writes, terminal-backed bash, and elicitation support.\n\nReadiness claim:\n\n- ACP is implemented and covered for current editor/client contracts: initialize conformance, agent capability advertisement, lazy startup, stdout JSON-RPC hygiene, client-owned MCP isolation, event mapping, file bridge routing, terminal routing, and permission routing.\n- ACP is not the preferred bot control-plane surface. It is not positioned as a multi-session external bot coordinator, and it does not replace Coordinator MCP reports/artifacts/turn state.\n- A real prompt still depends on the selected provider/model credentials, so required PR smokes should stay on provider-independent initialize, lifecycle, bridge, and mapper tests.\n\nCurrent entrypoints:\n\n```sh\nskc --mode acp\n# equivalent ACP subcommand for ACP clients that prefer command-style launch\nskc acp\n```\n\nPrimary references:\n\n- `packages/coding-agent/src/commands/acp.ts`\n- `packages/coding-agent/src/modes/acp/acp-mode.ts`\n- `packages/coding-agent/src/modes/acp/acp-agent.ts`\n- `packages/coding-agent/src/modes/acp/acp-client-bridge.ts`\n- `packages/coding-agent/src/modes/acp/acp-event-mapper.ts`\n\n### Bridge HTTPS\n\nBridge mode is an experimental network protocol surface over HTTPS. Its current public posture is deliberately fail-closed: unauthenticated health/help are available, authenticated handshake is available, and default session-control endpoints advertise no accepted capabilities/scopes and reject with `endpoint_disabled`.\n\nReadiness claim:\n\n- Ready as experimental protocol scaffolding with fail-closed behavior and SDK/client conformance tests.\n- Not ready as the default external-bot product surface.\n- Do not document events, commands, controller ownership, UI responses, host tool results, or host URI results as enabled by default. Those names remain in the protocol catalog for internal compatibility and future re-enable work.\n\nPrimary references:\n\n- `docs/bridge.md`\n- `packages/coding-agent/src/modes/bridge/bridge-mode.ts`\n- `packages/coding-agent/src/modes/bridge/auth.ts`\n- `packages/bridge-client/src/index.ts`\n\n## PR smoke checklist\n\nFor external-control PRs, use this provider-independent checklist before any optional live provider smoke:\n\n1. **Docs-to-code alignment:** the readiness matrix still matches CLI mode parsing, MCP command registration, ACP command registration, bridge endpoint defaults, and RPC/ACP/Bridge tests.\n2. **Coordinator MCP:** `skc mcp-serve coordinator --check --json` still reports the coordinator server and tool list, and focused MCP tests pass without provider credentials.\n3. **RPC stdio:** at least one stdio or client contract test proves JSONL startup/command routing without a real provider key.\n4. **ACP mode:** initialize/stdout or conformance tests prove the ACP JSON-RPC entrypoint and capability advertisement without a real provider key.\n5. **Bridge HTTPS:** bridge auth/handler tests prove TLS requirement, authenticated handshake, help/health behavior, and default `endpoint_disabled` session-control posture.\n6. **Local leak audit:** deliverable docs/tests must not contain private profile names, user-home paths, callback artifact paths, local proxy names, terminal app names, or private launch wrappers.\n\nOptional live smokes are useful diagnostics for one operator's model/profile/network setup, but they must not be required for PR readiness unless the PR explicitly changes live provider behavior.\n",
+	"external-control-readiness.md": "# External control surface readiness\n\nThis document classifies every public SKC surface that an external controller, bot, editor, or harness can use to drive `skc`. It is intentionally narrower than the generic bot guide: it states what is ready today, what is only editor/client-oriented, and what remains experimental.\n\n## Readiness matrix\n\n| Surface | Current readiness | Primary command | Use when | Do not use when | Provider-independent smoke path |\n| --- | --- | --- | --- | --- | --- |\n| Coordinator MCP | Preferred multi-session bot/control-plane surface. | `skc mcp-serve coordinator` | A controller needs to start/register SKC sessions, send bounded turns, answer questions, read artifacts, and write durable status reports across one or more repo/worktree lanes. | The controller only needs one embedded subprocess and can own stdio directly. | `skc mcp-serve coordinator --check --json`; `packages/coding-agent/test/coordinator-mcp.test.ts`; `packages/coding-agent/test/setup-cli.test.ts`. |\n| RPC stdio | Stable subprocess worker surface. | `skc --mode rpc` | A host embeds one SKC worker process, sends JSONL commands over stdin, consumes stdout frames, and optionally uses `python/skc-rpc`. | The host needs remote HTTPS, multi-session orchestration, or MCP tool discovery. | `packages/coding-agent/test/rpc-unattended-stdio.test.ts`; `packages/coding-agent/test/rpc-client.start.test.ts`; `packages/coding-agent/test/rpc-host-tools.test.ts`; `packages/coding-agent/test/rpc-host-uris.test.ts`. |\n| ACP mode | Editor/ACP client surface with tested protocol initialization, session lifecycle, client-owned MCP, file/terminal client bridges, permission routing, and stdout hygiene. | `skc --mode acp` or `skc acp` | An editor or ACP-compatible client wants to drive SKC through the Agent Client Protocol over stdio. | A bot needs a generic multi-session control plane; use Coordinator MCP instead. | `packages/coding-agent/test/acp-initialize-conformance.test.ts`; `packages/coding-agent/test/acp-stdout-hygiene.test.ts`; `packages/coding-agent/test/acp-lazy-startup.test.ts`; `packages/coding-agent/test/acp-mcp-isolation.test.ts`; `packages/coding-agent/test/read-acp-fs.test.ts`; `packages/coding-agent/test/write-acp-fs.test.ts`; `packages/coding-agent/test/bash-acp-terminal.test.ts`. |\n| Bridge HTTPS | Experimental, fail-closed remote session-control surface. | `skc --mode bridge` | A future remote client needs HTTPS protocol scaffolding, authenticated health/help/handshake behavior, or SDK compatibility tests. | Production bot lifecycle, default external-controller integration, or claims that remote session events/commands are enabled by default. | `packages/coding-agent/test/bridge/bridge-auth.test.ts`; `packages/coding-agent/test/bridge/bridge-mode-handler.test.ts`; `packages/coding-agent/test/bridge/bridge-conformance.test.ts`; `packages/bridge-client/test/bridge-client.test.ts`. |\n\n## Surface details\n\n### Standalone TUI and MCP inheritance\n\nNormal standalone SKC (`skc`, `skc --tmux`, and print-mode prompts) does not inherit Claude Code, Codex, Cursor, Gemini, Windsurf, or other tools' MCP servers as a public startup contract. It also does not expose a supported standalone-TUI setting that automatically imports arbitrary MCP servers for the model. See [Standalone SKC MCP support](./standalone-mcp.md) for the user-facing boundary and workarounds.\n\n### Coordinator MCP\n\nCoordinator MCP is the default answer for external bot and orchestration integrations. It exposes a transport-level MCP tool contract for session discovery, managed session start, visible tmux registration, prompt delivery, bounded turn waiting, structured question answering, artifact reads, and explicit completion/failure/cancellation reports.\n\nReadiness claim:\n\n- Ready as the preferred generic external-controller control plane.\n- Provider-independent contract checks exist for server metadata, tool discovery, read-only defaults, mutation gates, setup rendering, and dry-run lifecycle behavior.\n- It is not a provider/model contract. Live model execution remains the operator's environment-specific smoke.\n\nPrimary references:\n\n- `docs/bot-integration.md`\n- `docs/hermes-mcp-bridge.md`\n- `packages/coding-agent/src/coordinator/contract.ts`\n- `packages/coding-agent/src/coordinator-mcp/server.ts`\n\n### RPC stdio\n\nRPC mode is the stable embedded-worker surface. It is newline-delimited JSON over stdio and emits a `{ \"type\": \"ready\" }` frame before accepting commands. Hosts can drive prompts, state queries, host tools, host URI schemes, workflow gates, extension UI responses, cancellation, and unattended negotiation through the RPC command catalog.\n\nReadiness claim:\n\n- Ready for single-process host integration and subprocess workers.\n- The public Python client in `python/skc-rpc` is the recommended typed client for Python hosts.\n- Multi-session orchestration and MCP tool discovery are out of scope for RPC; use Coordinator MCP for those.\n\nPrimary references:\n\n- `docs/rpc.md`\n- `python/skc-rpc/README.md`\n- `packages/coding-agent/src/modes/rpc/rpc-mode.ts`\n- `packages/coding-agent/src/modes/rpc/rpc-types.ts`\n\n### ACP mode\n\nACP mode runs SKC as an Agent Client Protocol server over stdio. It is useful for editor-style clients that own the ACP transport and want session creation, session load/fork/resume/close metadata, prompt handling, client-provided MCP servers, permission prompts, editor file reads/writes, terminal-backed bash, and elicitation support.\n\nReadiness claim:\n\n- ACP is implemented and covered for current editor/client contracts: initialize conformance, agent capability advertisement, lazy startup, stdout JSON-RPC hygiene, client-owned MCP isolation, event mapping, file bridge routing, terminal routing, and permission routing.\n- ACP is not the preferred bot control-plane surface. It is not positioned as a multi-session external bot coordinator, and it does not replace Coordinator MCP reports/artifacts/turn state.\n- A real prompt still depends on the selected provider/model credentials, so required PR smokes should stay on provider-independent initialize, lifecycle, bridge, and mapper tests.\n\nCurrent entrypoints:\n\n```sh\nskc --mode acp\n# equivalent ACP subcommand for ACP clients that prefer command-style launch\nskc acp\n```\n\nPrimary references:\n\n- `packages/coding-agent/src/commands/acp.ts`\n- `packages/coding-agent/src/modes/acp/acp-mode.ts`\n- `packages/coding-agent/src/modes/acp/acp-agent.ts`\n- `packages/coding-agent/src/modes/acp/acp-client-bridge.ts`\n- `packages/coding-agent/src/modes/acp/acp-event-mapper.ts`\n\n### Bridge HTTPS\n\nBridge mode is an experimental network protocol surface over HTTPS. Its current public posture is deliberately fail-closed: unauthenticated health/help are available, authenticated handshake is available, and default session-control endpoints advertise no accepted capabilities/scopes and reject with `endpoint_disabled`.\n\nReadiness claim:\n\n- Ready as experimental protocol scaffolding with fail-closed behavior and SDK/client conformance tests.\n- Not ready as the default external-bot product surface.\n- Do not document events, commands, controller ownership, UI responses, host tool results, or host URI results as enabled by default. Those names remain in the protocol catalog for internal compatibility and future re-enable work.\n\nPrimary references:\n\n- `docs/bridge.md`\n- `packages/coding-agent/src/modes/bridge/bridge-mode.ts`\n- `packages/coding-agent/src/modes/bridge/auth.ts`\n- `packages/bridge-client/src/index.ts`\n\n## PR smoke checklist\n\nFor external-control PRs, use this provider-independent checklist before any optional live provider smoke:\n\n1. **Docs-to-code alignment:** the readiness matrix still matches CLI mode parsing, MCP command registration, ACP command registration, bridge endpoint defaults, and RPC/ACP/Bridge tests.\n2. **Coordinator MCP:** `skc mcp-serve coordinator --check --json` still reports the coordinator server and tool list, and focused MCP tests pass without provider credentials.\n3. **RPC stdio:** at least one stdio or client contract test proves JSONL startup/command routing without a real provider key.\n4. **ACP mode:** initialize/stdout or conformance tests prove the ACP JSON-RPC entrypoint and capability advertisement without a real provider key.\n5. **Bridge HTTPS:** bridge auth/handler tests prove TLS requirement, authenticated handshake, help/health behavior, and default `endpoint_disabled` session-control posture.\n6. **Local leak audit:** deliverable docs/tests must not contain private profile names, user-home paths, callback artifact paths, local proxy names, terminal app names, or private launch wrappers.\n\nOptional live smokes are useful diagnostics for one operator's model/profile/network setup, but they must not be required for PR readiness unless the PR explicitly changes live provider behavior.\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",
 	"geobench.md": "# GEO benchmark for Sayknow-CLI\n\nThis repository includes a [`geobench`](https://github.com/NomaDamas/geobench) product spec for measuring LLM answer visibility: hit rate, MRR, share of voice, citation rate/share, and confidence intervals.\n\n```bash\n/path/to/geobench/dist/geobench estimate --product geobench/sayknow-cli.yaml --providers openai --tier cheap\n/path/to/geobench/dist/geobench profile geobench/sayknow-cli.yaml\n/path/to/geobench/dist/geobench bench --product geobench/sayknow-cli.yaml --providers openai --tier cheap --mode benchmark\n```\n\nPublish aggregate metrics only; do not publish raw provider answers, secrets, or private run logs.\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 SKC 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 SKC 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\nSKC 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\nskc -> /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 SKC 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 SKC 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 SKC 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": "# Coordinator MCP bridge\n\nSKC exposes a native outward MCP bridge for external coordinators:\n\n```bash\nskc mcp-serve coordinator\n```\n\n`skc mcp-serve hermes` is accepted as a compatibility alias for the same coordinator bridge.\n\nThe bridge is intentionally separate from SKC'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 or Hermes-only product direction. Hermes is one compatibility preset, not a privileged integration mode:\n\n- `packages/coding-agent/src/coordinator/contract.ts` owns transport-neutral server metadata and tool names.\n- `skc mcp-serve coordinator` is the outward MCP adapter for external agents.\n- `skc coordinator` is the read-only CLI/debug adapter for humans and scripts that need to inspect the same contract without starting MCP transport.\n- `skc setup hermes` is the compatibility 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## Coordinator setup adapter\n\nUse `skc setup hermes` to render or install a portable MCP setup package for any controller that accepts Hermes-compatible MCP config:\n\n```bash\nskc setup hermes --root /path/to/repo --profile my-bot --repo sayknow-cli\n```\n\nThe default mode is render-only and writes no files. To install into a Hermes profile:\n\n```bash\nskc setup hermes \\\n  --root /path/to/repo \\\n  --profile my-bot \\\n  --repo sayknow-cli \\\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 `SKC_COORDINATOR_MCP_SESSION_COMMAND` as `skc --worktree`, so spawned sessions launch inside a SKC-managed sibling worktree while SKC 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\nskc setup hermes \\\n  --root /path/to/repo \\\n  --worktree-name hermes-sayknow-cli\n```\n\n```bash\nskc setup hermes \\\n  --root /path/to/repo \\\n  --session-command \"skc --worktree hermes-custom --model <provider/model>\"\n```\n\nProvider/model examples are examples only; SKC 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\nskc 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 SKC_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 SKC_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/SKC actuation uses the configured SKC-compatible session command. `skc setup hermes` writes this as `skc --worktree` by default so SKC owns worktree creation and resume identity:\n\n```bash\nexport SKC_COORDINATOR_MCP_SESSION_COMMAND=\"skc --worktree\"\n```\n\nWith that command configured, `skc_coordinator_start_session` launches a detached tmux session, `skc_coordinator_send_prompt` creates a durable turn and sends input to that pane, `skc_coordinator_read_coordination_status` returns a canonical polling snapshot for sessions, session states, turns, questions, reports, and bounded event summaries, and `skc_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 runtime session state or `skc_coordinator_report_status`.\n\nFor resume safety, prefer the generated SKC-native worktree command over creating a git worktree in Hermes itself. SKC'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 `SKC_COORDINATOR_MCP_ARTIFACT_BYTE_CAP`.\n\n`skc setup hermes` renders `SKC_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 SKC_COORDINATOR_MCP_PROFILE=\"team-a\"\nexport SKC_COORDINATOR_MCP_REPO=\"sayknow-cli\"\n```\n\nMissing namespace never widens into global session enumeration.\n\n## Tool surface\n\nRead tools:\n\n- `skc_coordinator_list_sessions`\n- `skc_coordinator_read_status`\n- `skc_coordinator_read_tail`\n- `skc_coordinator_list_questions`\n- `skc_coordinator_list_artifacts`\n- `skc_coordinator_read_artifact`\n- `skc_coordinator_read_coordination_status`\n- `skc_coordinator_read_turn`\n- `skc_coordinator_await_turn`\n- `skc_coordinator_watch_events`\n\n\nMutating tools:\n\n- `skc_coordinator_start_session`\n- `skc_coordinator_register_session`\n- `skc_coordinator_send_prompt`\n- `skc_coordinator_submit_question_answer`\n- `skc_coordinator_report_status`\n\n\n`skc_coordinator_register_session` registers an existing visible tmux-backed SKC pane as the coordinator-authoritative session. Use it when an operator has already launched a visible terminal/tmux lane and the external coordinator must send prompts to that same pane instead of creating a hidden `skc-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\nExternal coordinators should treat turns, not terminal scrollback, as the unit of work:\n\n1. Call `skc_coordinator_start_session` with `allow_mutation: true`.\n2. Call `skc_coordinator_send_prompt` with `allow_mutation: true`.\n3. Store the returned `turn_id`.\n4. Poll `skc_coordinator_read_turn`, or call bounded `skc_coordinator_await_turn`, until the turn is terminal.\n5. If `skc_coordinator_list_questions` shows a question for that turn, answer with `skc_coordinator_submit_question_answer`.\n6. Use `skc_coordinator_report_status` with `session_id` and `turn_id` to write explicit completion/failure evidence.\n   Use `status: \"cancelled\"` for coordinator-policy cancellation, and `status: \"failed\"` plus `blocker` for provider/tool/task failures.\n\n`skc_coordinator_send_prompt` preserves the legacy `queued` and `delivered` fields and adds turn fields:\n\n```json\n{\n  \"ok\": true,\n  \"session_id\": \"skc-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 `skc_coordinator_report_status`. Force supersedes the previous active turn and audits that state in the turn journal.\nCoordinator cancellation is recorded through `skc_coordinator_report_status` with terminal `status: \"cancelled\"`; this updates durable turn state but does not kill the underlying tmux process. If the correct policy is replacement work rather than cancellation, send the replacement prompt with `force: true` so the previous active turn is superseded and audited.\n\n`skc_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\": \"skc-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\nThe coordinator MCP bridge is currently a durable polling/await surface. It does not expose a push subscription stream; external coordinators should poll `skc_coordinator_read_coordination_status`, `skc_coordinator_read_turn`, or bounded `skc_coordinator_await_turn` instead of waiting for server-sent push events.\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\n## Coordinator event journal\n\nThe bridge persists a restart-safe event journal under the configured coordinator state namespace, for example:\n\n```text\n$SKC_COORDINATOR_MCP_STATE_ROOT/<profile>/<repo>/events/event-journal.jsonl\n```\n\nEach event is a bounded JSONL record with `schema_version`, monotonic namespace-local `seq`, stable `id`, `timestamp`, canonical `kind`, optional `session_id`/`turn_id`/`question_id`/`report_id`, short `summary`, optional `payload_ref`, and bounded scalar `metadata`. Full prompts, reports, final responses, and artifacts stay in their existing turn/report/artifact read paths; event records only point at them.\n\n`skc_coordinator_watch_events` is a bounded long-poll MCP tool, not an unbounded stream. Inputs are `after_seq` (default `0`), optional `session_id`, optional `event_types`, `timeout_ms` capped at 30000, and `limit` capped at 100. If matching events already exist after `after_seq`, it returns immediately. Otherwise it waits for the event journal to change or for timeout. The response includes `events`, `latest_seq`, `timed_out`, and `transport: { \"mcp\": \"long_poll\", \"push_subscriptions\": false }`, so coordinators can persist `latest_seq` and resume safely after restart.\n\n`skc_coordinator_read_coordination_status` keeps its existing report fields and now also includes `latest_event_seq` plus recent event summaries for snapshot-style consumers.\n\n## Generic controller config snippet\n\n```json\n{\n  \"mcp_servers\": {\n    \"skc_coordinator\": {\n      \"command\": \"skc\",\n      \"args\": [\"mcp-serve\", \"coordinator\"],\n      \"env\": {\n        \"SKC_COORDINATOR_MCP_WORKDIR_ROOTS\": \"/path/to/repo\",\n        \"SKC_COORDINATOR_MCP_PROFILE\": \"team-a\",\n        \"SKC_COORDINATOR_MCP_REPO\": \"project\",\n        \"SKC_COORDINATOR_MCP_SESSION_COMMAND\": \"skc --worktree\"\n      },\n      \"enabled\": true\n    }\n  }\n}\n```\n\n## Smoke check\n\n```bash\nskc mcp-serve coordinator --check --json\n```\n\nExpected result includes `ok: true`, server name `skc-coordinator-mcp`, and the SKC-named tool list.\n",
+	"hermes-mcp-bridge.md": "# Coordinator MCP bridge\n\nSKC exposes a native outward MCP bridge for external coordinators:\n\n```bash\nskc mcp-serve coordinator\n```\n\n`skc mcp-serve hermes` is accepted as a compatibility alias for the same coordinator bridge.\n\nThe bridge is intentionally separate from SKC'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 or Hermes-only product direction. Hermes is one compatibility preset, not a privileged integration mode:\n\n- `packages/coding-agent/src/coordinator/contract.ts` owns transport-neutral server metadata and tool names.\n- `skc mcp-serve coordinator` is the outward MCP adapter for external agents.\n- `skc coordinator` is the read-only CLI/debug adapter for humans and scripts that need to inspect the same contract without starting MCP transport.\n- `skc setup hermes` is the compatibility 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## Coordinator setup adapter\n\nUse `skc setup hermes` to render or install a portable MCP setup package for any controller that accepts Hermes-compatible MCP config:\n\n```bash\nskc setup hermes --root /path/to/repo --profile my-bot --repo sayknow-cli\n```\n\nThe default mode is render-only and writes no files. To install into a Hermes profile:\n\n```bash\nskc setup hermes \\\n  --root /path/to/repo \\\n  --profile my-bot \\\n  --repo sayknow-cli \\\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 `SKC_COORDINATOR_MCP_SESSION_COMMAND` as `skc --worktree`, so spawned sessions launch inside a SKC-managed sibling worktree while SKC 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\nskc setup hermes \\\n  --root /path/to/repo \\\n  --worktree-name hermes-sayknow-cli\n```\n\n```bash\nskc setup hermes \\\n  --root /path/to/repo \\\n  --session-command \"skc --worktree hermes-custom --model <provider/model>\"\n```\n\nProvider/model examples are examples only; SKC 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\nskc 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 SKC_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 SKC_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/SKC actuation uses the configured SKC-compatible session command. `skc setup hermes` writes this as `skc --worktree` by default so SKC owns worktree creation and resume identity:\n\n```bash\nexport SKC_COORDINATOR_MCP_SESSION_COMMAND=\"skc --worktree\"\n```\n\nWith that command configured, `skc_coordinator_start_session` launches a detached tmux session, `skc_coordinator_send_prompt` creates a durable turn and sends input to that pane, `skc_coordinator_read_coordination_status` returns a canonical polling snapshot for sessions, session states, turns, questions, reports, and bounded event summaries, and `skc_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 runtime session state or `skc_coordinator_report_status`.\n\nFor resume safety, prefer the generated SKC-native worktree command over creating a git worktree in Hermes itself. SKC'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\nWhen an operator needs the session to stay visible in a routed tmux pane (for example a Clawhip/Hermes/OpenClaw channel that watches stale sessions and accepts follow-up prompts), use the documented visible-session fallback instead of inventing a private terminal protocol: [`docs/skc-session-clawhip-routing.md`](./skc-session-clawhip-routing.md). It keeps the same worktree isolation discipline while making the router, not SKC internals, own channel ids, mentions, and notification policy.\n\nArtifact reads are canonicalized, symlink escapes are rejected, and returned content is byte-capped by `SKC_COORDINATOR_MCP_ARTIFACT_BYTE_CAP`.\n\n`skc setup hermes` renders `SKC_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 SKC_COORDINATOR_MCP_PROFILE=\"team-a\"\nexport SKC_COORDINATOR_MCP_REPO=\"sayknow-cli\"\n```\n\nMissing namespace never widens into global session enumeration.\n\n## Tool surface\n\nRead tools:\n\n- `skc_coordinator_list_sessions`\n- `skc_coordinator_read_status`\n- `skc_coordinator_read_tail`\n- `skc_coordinator_list_questions`\n- `skc_coordinator_list_artifacts`\n- `skc_coordinator_read_artifact`\n- `skc_coordinator_read_coordination_status`\n- `skc_coordinator_read_turn`\n- `skc_coordinator_await_turn`\n- `skc_coordinator_watch_events`\n\n\nMutating tools:\n\n- `skc_coordinator_start_session`\n- `skc_coordinator_register_session`\n- `skc_coordinator_send_prompt`\n- `skc_coordinator_submit_question_answer`\n- `skc_coordinator_report_status`\n\n\n`skc_coordinator_register_session` registers an existing visible tmux-backed SKC pane as the coordinator-authoritative session. Use it when an operator has already launched a visible terminal/tmux lane and the external coordinator must send prompts to that same pane instead of creating a hidden `skc-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\nExternal coordinators should treat turns, not terminal scrollback, as the unit of work:\n\n1. Call `skc_coordinator_start_session` with `allow_mutation: true`.\n2. Call `skc_coordinator_send_prompt` with `allow_mutation: true`.\n3. Store the returned `turn_id`.\n4. Poll `skc_coordinator_read_turn`, or call bounded `skc_coordinator_await_turn`, until the turn is terminal.\n5. If `skc_coordinator_list_questions` shows a question for that turn, answer with `skc_coordinator_submit_question_answer`.\n6. Use `skc_coordinator_report_status` with `session_id` and `turn_id` to write explicit completion/failure evidence.\n   Use `status: \"cancelled\"` for coordinator-policy cancellation, and `status: \"failed\"` plus `blocker` for provider/tool/task failures.\n\n`skc_coordinator_send_prompt` preserves the legacy `queued` and `delivered` fields and adds turn fields:\n\n```json\n{\n  \"ok\": true,\n  \"session_id\": \"skc-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 `skc_coordinator_report_status`. Force supersedes the previous active turn and audits that state in the turn journal.\nCoordinator cancellation is recorded through `skc_coordinator_report_status` with terminal `status: \"cancelled\"`; this updates durable turn state but does not kill the underlying tmux process. If the correct policy is replacement work rather than cancellation, send the replacement prompt with `force: true` so the previous active turn is superseded and audited.\n\n`skc_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\": \"skc-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\nThe coordinator MCP bridge is currently a durable polling/await surface. It does not expose a push subscription stream; external coordinators should poll `skc_coordinator_read_coordination_status`, `skc_coordinator_read_turn`, or bounded `skc_coordinator_await_turn` instead of waiting for server-sent push events.\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\n## Coordinator event journal\n\nThe bridge persists a restart-safe event journal under the configured coordinator state namespace, for example:\n\n```text\n$SKC_COORDINATOR_MCP_STATE_ROOT/<profile>/<repo>/events/event-journal.jsonl\n```\n\nEach event is a bounded JSONL record with `schema_version`, monotonic namespace-local `seq`, stable `id`, `timestamp`, canonical `kind`, optional `session_id`/`turn_id`/`question_id`/`report_id`, short `summary`, optional `payload_ref`, and bounded scalar `metadata`. Full prompts, reports, final responses, and artifacts stay in their existing turn/report/artifact read paths; event records only point at them.\n\n`skc_coordinator_watch_events` is a bounded long-poll MCP tool, not an unbounded stream. Inputs are `after_seq` (default `0`), optional `session_id`, optional `event_types`, `timeout_ms` capped at 30000, and `limit` capped at 100. If matching events already exist after `after_seq`, it returns immediately. Otherwise it waits for the event journal to change or for timeout. The response includes `events`, `latest_seq`, `timed_out`, and `transport: { \"mcp\": \"long_poll\", \"push_subscriptions\": false }`, so coordinators can persist `latest_seq` and resume safely after restart.\n\n`skc_coordinator_read_coordination_status` keeps its existing report fields and now also includes `latest_event_seq` plus recent event summaries for snapshot-style consumers.\n\n## Generic controller config snippet\n\n```json\n{\n  \"mcp_servers\": {\n    \"skc_coordinator\": {\n      \"command\": \"skc\",\n      \"args\": [\"mcp-serve\", \"coordinator\"],\n      \"env\": {\n        \"SKC_COORDINATOR_MCP_WORKDIR_ROOTS\": \"/path/to/repo\",\n        \"SKC_COORDINATOR_MCP_PROFILE\": \"team-a\",\n        \"SKC_COORDINATOR_MCP_REPO\": \"project\",\n        \"SKC_COORDINATOR_MCP_SESSION_COMMAND\": \"skc --worktree\"\n      },\n      \"enabled\": true\n    }\n  }\n}\n```\n\n## Smoke check\n\n```bash\nskc mcp-serve coordinator --check --json\n```\n\nExpected result includes `ok: true`, server name `skc-coordinator-mcp`, and the SKC-named tool list.\n",
 	"hotspot-map-successor.md": "# cpu-hotspot-map.json — successor pointer\n\n[`cpu-hotspot-map.json`](./cpu-hotspot-map.json) is **closed out**. All 11 CPU hotspots (H01–H11) and 5 memory hotspots (M01–M05) are resolved or rationally deferred across Optimization Suites v1 (#356), v2 (#530), and v3 (#548/#557/#558). Do **not** treat it as an open implementation backlog.\n\nThat map was a **static structural ranking** (algorithmic complexity × trigger frequency). Its `method` field records that real CPU self-time was \"to be measured by the agreed profiling corpus during optimization.\"\n\nFuture perf prioritization comes from the **profiling corpus**, not from this static map:\n\n- Evidence classes (`wallClockPhase`, `processCpuUsage`, `profilerSelfTime`, `rssMemory`, `byteParity`) and the corpus schema: see `docs/perf-profiling-corpus.md` (added with the corpus foundation).\n- Native algorithmic ports proposed for leftover hotspots are gated by [`native-ffi-optimization-policy.md`](./native-ffi-optimization-policy.md).\n\nA hotspot may be labeled `CPU-self-time confirmed` only when a `profilerSelfTime` artifact exists; v1–v3 shipped wins are otherwise classified as `covered-current`, `not-visible`, `needs-trace-coverage`, or `fallback-toggle-confirmed`.\n",
-	"keybindings.md": "# Keybindings\n\nRun `/hotkeys` inside an `skc` 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 `~/.skc/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 `~/.skc/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` | Send a follow-up message |\n| `app.message.queue` | `Alt+Enter` | Explicitly queue a message for the next turn |\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",
+	"keybindings.md": "# Keybindings\n\nRun `/hotkeys` inside an `skc` 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 `~/.skc/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 `~/.skc/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` | Send a follow-up message |\n| `app.message.queue` | `Alt+Enter` | Explicitly queue a message for the next turn |\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\n## Auditing default-key collisions\n\nSome default chords are intentionally reused across different UI contexts, where the focused component disambiguates them at dispatch time. For example `Enter` maps to both input submit and selection confirm, and `Ctrl+C` maps to both input copy and selection cancel. These are not conflicts — only one context is active at a time.\n\nTo audit the registry for keys whose default binding is claimed by more than one action, use `detectDefaultKeyCollisions(definitions)` from `@sayknow-cli/tui/keybindings`. It returns one entry per colliding key with the list of claiming action IDs, which is useful when adding new defaults or reviewing the surface. User-remap conflicts (multiple actions bound to the same chord in `keybindings.json`) continue to be reported separately by `KeybindingsManager.getConflicts()`.\n\nTwo audit clarifications for the current surface:\n\n- `app.clipboard.copyLine` is registry-backed and dispatched through the input controller's custom key handlers, not hardcoded.\n- `tui.input.copy` is declared in the registry but is not currently dispatched by `Editor.handleInput`.\n\nThe editor's configurable action defaults (including the platform-aware `app.clipboard.pasteImage` default) are derived directly from the central `KEYBINDINGS` registry, so there is a single source of truth for those defaults.\n\n## Current surface audit\n\nAuthoritative inventory of the keybinding registry, one row per action. Generated from `TUI_KEYBINDINGS` (`packages/tui/src/keybindings.ts`) and `KEYBINDINGS` (`packages/coding-agent/src/config/keybindings.ts`). Every action ID below is remappable via `~/.skc/agent/keybindings.json` unless noted. A drift test (`packages/coding-agent/test/keybindings-audit.test.ts`) asserts every registry action ID appears in this table.\n\n### Editor context (`tui.editor.*`)\n\n| Action ID | Default | Notes |\n| --- | --- | --- |\n| `tui.editor.cursorUp` | `up` | |\n| `tui.editor.cursorDown` | `down` | |\n| `tui.editor.cursorLeft` | `left`, `ctrl+b` | `ctrl+b` also `app.tool.backgroundFold` (other context) |\n| `tui.editor.cursorRight` | `right`, `ctrl+f` | |\n| `tui.editor.cursorWordLeft` | `alt+left`, `ctrl+left`, `alt+b` | `ctrl+left` also `app.tree.foldOrUp` |\n| `tui.editor.cursorWordRight` | `alt+right`, `ctrl+right`, `alt+f` | `ctrl+right` also `app.tree.unfoldOrDown` |\n| `tui.editor.cursorLineStart` | `home`, `ctrl+a` | |\n| `tui.editor.cursorLineEnd` | `end`, `ctrl+e` | |\n| `tui.editor.jumpForward` | `ctrl+]` | |\n| `tui.editor.jumpBackward` | `ctrl+alt+]` | |\n| `tui.editor.pageUp` | `pageUp` | |\n| `tui.editor.pageDown` | `pageDown` | |\n| `tui.editor.deleteCharBackward` | `backspace` | |\n| `tui.editor.deleteCharForward` | `delete`, `ctrl+d` | `ctrl+d` also `app.exit` / `app.session.delete` |\n| `tui.editor.deleteWordBackward` | `ctrl+w`, `alt+backspace`, `ctrl+backspace` | |\n| `tui.editor.deleteWordForward` | `alt+delete`, `alt+d` | |\n| `tui.editor.deleteToLineStart` | `ctrl+u` | |\n| `tui.editor.deleteToLineEnd` | `ctrl+k` | |\n| `tui.editor.yank` | `ctrl+y` | |\n| `tui.editor.yankPop` | `alt+y` | |\n| `tui.editor.undo` | `ctrl+-`, `ctrl+_` | |\n\n### Input context (`tui.input.*`)\n\n| Action ID | Default | Notes |\n| --- | --- | --- |\n| `tui.input.newLine` | `shift+enter` | |\n| `tui.input.submit` | `enter` | also `tui.select.confirm` (other context) |\n| `tui.input.tab` | `tab` | |\n| `tui.input.copy` | `ctrl+c` | declared but not dispatched by `Editor.handleInput` |\n\n### Selection context (`tui.select.*`)\n\n| Action ID | Default | Notes |\n| --- | --- | --- |\n| `tui.select.up` | `up` | |\n| `tui.select.down` | `down` | |\n| `tui.select.pageUp` | `pageUp` | |\n| `tui.select.pageDown` | `pageDown` | |\n| `tui.select.confirm` | `enter` | |\n| `tui.select.cancel` | `escape`, `ctrl+c` | `escape` also `app.interrupt` |\n\n### Application context (`app.*`)\n\n| Action ID | Default | Notes |\n| --- | --- | --- |\n| `app.interrupt` | `escape` | |\n| `app.clear` | `ctrl+c` | |\n| `app.exit` | `ctrl+d` | |\n| `app.suspend` | `ctrl+z` | |\n| `app.thinking.cycle` | `shift+tab` | |\n| `app.thinking.toggle` | `ctrl+t` | |\n| `app.model.cycleForward` | `ctrl+p` | also `app.session.togglePath` (session list) |\n| `app.model.cycleBackward` | `shift+ctrl+p` | |\n| `app.model.select` | `ctrl+l` | |\n| `app.model.selectTemporary` | `alt+p` | |\n| `app.tools.expand` | `ctrl+o` | |\n| `app.tool.backgroundFold` | `ctrl+b` | |\n| `app.editor.external` | `ctrl+g` | |\n| `app.message.followUp` | `ctrl+enter` | |\n| `app.message.queue` | `alt+enter` | |\n| `app.message.dequeue` | `alt+up` | |\n| `app.clipboard.pasteImage` | `ctrl+v` (`alt+v` on win32) | platform-aware; single source of truth in `KEYBINDINGS` |\n| `app.clipboard.copyLine` | `alt+shift+l` | registry-backed via input-controller custom handler |\n| `app.clipboard.copyPrompt` | `alt+shift+c` | |\n| `app.session.new` | _(none)_ | command-driven; empty default |\n| `app.session.tree` | _(none)_ | command-driven; empty default |\n| `app.session.fork` | _(none)_ | command-driven; empty default |\n| `app.session.resume` | _(none)_ | command-driven; empty default |\n| `app.session.observe` | `ctrl+s` | also `app.session.toggleSort` (session list) |\n| `app.jobs.open` | `alt+j` | |\n| `app.session.togglePath` | `ctrl+p` | session-list context |\n| `app.session.toggleSort` | `ctrl+s` | session-list context |\n| `app.session.rename` | `ctrl+r` | also `app.history.search` |\n| `app.session.delete` | `ctrl+d` | session-list context |\n| `app.session.deleteNoninvasive` | `ctrl+backspace` | |\n| `app.tree.foldOrUp` | `ctrl+left`, `alt+left` | |\n| `app.tree.unfoldOrDown` | `ctrl+right`, `alt+right` | |\n| `app.plan.toggle` | `alt+shift+p` | |\n| `app.history.search` | `ctrl+r` | |\n| `app.stt.toggle` | `alt+h` | |\n\n### Global engine context (`tui.global.*`)\n\n| Action ID | Default | Notes |\n| --- | --- | --- |\n| `tui.global.debug` | `shift+ctrl+d` | Toggle debug overlay; resolved through the registry in `tui.ts` |\n\nCross-context default reuse (`ctrl+p`, `ctrl+s`, `ctrl+r`, `ctrl+d`, `ctrl+b`, `ctrl+left`/`ctrl+right`, `enter`, `escape`, `ctrl+c`) is intentional: each pair is active in a different focused context and is disambiguated at dispatch time. Use `detectDefaultKeyCollisions()` (above) to re-derive this list from the registry.\n\n### Not yet registry-managed\n\nA few contexts still match chords directly instead of resolving through the registry, and are tracked for a later phase:\n\n- Tree selector (`tree-selector.ts`): up/down/left/right/enter, `ctrl+c`, filter cycling (`ctrl+o` / `ctrl+shift+o`), filter modes (`alt+d/t/u/l/a`), label edit (`shift+l`).\n- Parts of the model selector.\n",
 	"lsp-config.md": "# LSP configuration in SKC\n\nThis guide explains how to configure language servers for the SKC 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, SKC 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\nSKC 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 | `~/.skc/agent/lsp.json`, `~/.skc/agent/lsp.yaml`, `~/.gemini/lsp.*` |\n| 2 | `<project>/.skc/lsp.json`, `<project>/.skc/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 → `~/.skc/agent/lsp.json`\n- Project-specific overrides → `<project>/.skc/lsp.json`\n\n> **Note:** The presence of any LSP config file disables auto-detection. When at least one file is found, SKC 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 SKC 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>/.skc/lsp.json`:\n\n```json\n{\n  \"servers\": {\n    \"pylsp\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\nThe user-level config in `~/.skc/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",
-	"models.md": "# Model and Provider Configuration (`models.yml`)\n\nThis document describes how the coding-agent currently loads models, applies overrides, resolves credentials, and chooses models at runtime.\n\n## What controls model behavior\n\nPrimary implementation files:\n\n- `src/config/model-registry.ts` — loads built-in + custom models, provider overrides, runtime discovery, auth integration\n- `src/config/model-resolver.ts` — parses model patterns and selects models for the default and agent roles\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.skc/agent/models.yml`\n\nLegacy behavior still present:\n\n- If `models.yml` is missing and `models.json` exists at the same location, it is migrated to `models.yml`.\n- Explicit `.json` / `.jsonc` config paths are still supported when passed programmatically to `ModelRegistry`.\n\n## `models.yml` shape\n\n```yaml\nproviders:\n  <provider-id>:\n    # provider-level config\nequivalence:\n  overrides:\n    <provider-id>/<model-id>: <canonical-model-id>\n  exclude:\n    - <provider-id>/<model-id>\n```\n\n`provider-id` is the canonical provider key used across selection and auth lookup.\n\n`equivalence` is optional and configures canonical model grouping on top of concrete provider models:\n\n- `overrides` maps an exact concrete selector (`provider/modelId`) to an official upstream canonical id\n- `exclude` opts a concrete selector out of canonical grouping\n\n## Provider-level fields\n\n```yaml\nproviders:\n  my-provider:\n    baseUrl: https://api.example.com/v1\n    apiKey: MY_PROVIDER_API_KEY\n    api: openai-completions\n    headers:\n      X-Team: platform\n    authHeader: true\n    auth: apiKey\n    disableStrictTools: false  # set true for Anthropic-compatible endpoints that reject the strict field\n    cacheRetention: short  # none | short | long; model entries and modelOverrides can override this\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n        cacheRetention: long\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        cacheRetention: none\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\nmodelBindings:\n  modelRoles:\n    default: my-provider/some-model-id:high\n  agentModelOverrides:\n    executor: my-provider/some-model-id\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `bedrock-converse-stream`\n- `anthropic-messages`\n- `bedrock-converse-stream`\n- `google-generative-ai`\n- `google-vertex`\n- `google-gemini-cli`\n- `ollama-chat`\n- `cursor-agent`\n\n\n### First-class Azure OpenAI and Amazon Bedrock examples\n\nAzure OpenAI uses canonical OpenAI model IDs in SKC and resolves those IDs to Azure deployment names at request time. Set `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` to avoid assuming model id equals deployment name:\n\n```yaml\nproviders:\n  azure-openai:\n    baseUrl: https://my-resource.openai.azure.com/openai/v1\n    apiKeyEnv: AZURE_OPENAI_API_KEY\n    api: azure-openai-responses\n    models:\n      - id: gpt-4.1\n      - id: o3\n```\n\n```sh\nexport AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-4.1=gpt-41-prod,o3=o3-reasoning-prod'\n```\n\nAmazon Bedrock uses the native `bedrock-converse-stream` transport and AWS credential chain auth. Do not put AWS access keys in `models.yml`; configure `AWS_REGION` / `AWS_PROFILE` or standard static AWS credential environment variables instead:\n\n```yaml\nproviders:\n  amazon-bedrock:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com\n    api: bedrock-converse-stream\n    models:\n      - id: us.anthropic.claude-opus-4-6-v1\n      - id: anthropic.claude-3-5-sonnet-20241022-v2:0\n```\n\n### MiniMax and GLM custom provider examples\n\nFor common MiniMax and GLM/zAI setup, prefer the provider presets so the OpenAI-compatible API, base URL, env var, model id, and compatibility flags are written together:\n\n```sh\nskc setup provider --preset minimax\nskc setup provider --preset minimax-cn\nskc setup provider --preset glm\n```\n\nThe same presets are available inside the TUI:\n\n```text\n/provider add --preset minimax\n/provider add --preset glm\n/provider add zai\n```\n\nPresets only write `models.yml` entries that reference documented environment variable names (`MINIMAX_CODE_API_KEY`, `MINIMAX_CODE_CN_API_KEY`, or `ZAI_API_KEY`); they do not store or validate real credentials. The GLM preset aliases (`glm`, `zai`, `z-ai`) write an OpenAI-compatible custom provider named `glm-proxy` and do not replace the first-class `zai` provider.\n\n## Model profiles (`--mpreset`)\n\nModel profiles are optional top-level `profiles:` entries in `~/.skc/agent/models.yml`. A profile can require provider credentials before activation and can map one or more model roles; omitted roles inherit from the active defaults.\n\n```yaml\nprofiles:\n  team-standard:\n    required_providers: [openai, anthropic]\n    model_mapping:\n      default: openai/gpt-5.2\n      executor: anthropic/claude-sonnet-4-6:medium\n      architect: openai/o3:high\n      planner: openai/o3:high\n      critic: openai/o3:high\n```\n\n`model_mapping` keys are role names (`default`, `executor`, `architect`, `planner`, `critic`). Each role maps to exactly one model selector in the form `provider/modelId[:effort]`; comma-separated fallback chains are not supported in a single role value.\n`required_providers` is the aggregate set of providers required across the profile's mapped roles, not a per-role fallback chain.\n\nBuilt-in profiles are grouped by provider mix and tier:\n\n- `codex-{eco,medium,pro}` — all roles on `openai-codex/gpt-5.5`, differing only by per-role reasoning effort\n- `opencodego` — single OpenCode Go preset (Kimi default, DeepSeek executor/architect, Qwen planner, MiMo critic)\n- `claude-opus` — Anthropic OAuth preset centered on `claude-opus-4-8`\n- Single-provider tiers: `glm-{eco,medium,pro}`, `kimi-coding-plan-{eco,medium,pro}`, `mimo-{eco,medium,pro}`, `grok-{eco,medium,pro}`, `cursor-{eco,medium,pro}`, `minimax-{eco,medium,pro}`\n- Combos: `opus-codex` (Claude main agent with Codex support roles), `codex-opencodego` (Codex orchestrator/architect with OpenCode Go workers)\n\nThe `eco` tier favors cheaper/faster defaults, `medium` matches normal production defaults, and `pro` raises reasoning for architect, critic, and planner roles. Effort suffixes are clamped to each model's supported thinking range at preview and activation time (for example `codex-eco`'s executor `:minimal` resolves to effective `low` on `gpt-5.5`). Single-provider tiers pin each provider's current flagship (`zai/glm-5.2`, `kimi-code/kimi-k2.7-code`, `xiaomi/mimo-v2.5-pro`, `xai/grok-4.3`, `cursor/composer-1.5`, `minimax-code/minimax-m3`). User-defined profiles override built-ins by exact profile name.\n\n\nUse `skc --mpreset <name>` to activate a profile for the current session only. Activation hard-blocks when any provider listed in `required_providers` lacks credentials. Add `--default` to persist the selected profile as `modelProfile.default` in `config.yml`, so it applies at startup:\n\n```sh\nskc --mpreset codex-medium\nskc --mpreset opencodego --default\n```\n\nThe `/model` command opens to a preset landing view: presets are grouped by provider with live auth marks (✓/✗), highlighting a group expands its tiers, and selecting a tier shows the full role→model preview before applying for the session or as default. Typing jumps straight to model search, and `Browse all models` opens the classic tabbed model selector. In `/login`, `Add custom provider` is the first option for configuring credentials needed by custom or profile-required providers; after a successful provider login, the matching preset is recommended automatically.\n\nMiniMax's OpenAI-compatible endpoint rejects multiple system messages and emits thinking in `reasoning_content`, so pin the public-safe compatibility fields when hand-authoring a custom provider:\n\n```yaml\nproviders:\n  minimax-custom:\n    baseUrl: https://api.minimax.io/v1\n    apiKeyEnv: MINIMAX_API_KEY\n    api: openai-completions\n    compat:\n      supportsStore: false\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n      reasoningContentField: reasoning_content\n    models:\n      - id: MiniMax-M2.5\n```\n\nGLM via z.ai is available as the first-class `zai` provider. For a private GLM-compatible proxy, keep secrets in an env var and disable OpenAI-only request fields as needed:\n\n```yaml\nproviders:\n  glm-proxy:\n    baseUrl: https://api.z.ai/api/paas/v4\n    apiKeyEnv: ZAI_API_KEY\n    api: openai-completions\n    compat:\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n    models:\n      - id: glm-4.6\n```\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `models.yml` is strict: unknown provider/model keys fail validation before provider dispatch, so stale keys such as `requestTransform` or `wireModelId` only work where this document lists them.\n- `discovery.type`: `ollama`, `llama.cpp`, or `lm-studio`\n- `cacheRetention`: `none`, `short`, or `long`; request-time options win over model/modelOverride values, then provider values, then `SKC_CACHE_RETENTION`, then the runtime default. The runtime default is `short` for most providers, but the Anthropic provider defaults to `long` (`ttl: \"1h\"`) because the ~5m default is too fragile for long-running subagent workflows. The 1h marker is only emitted on the canonical Anthropic API (`api.anthropic.com`) for models advertising `supportsLongCacheRetention`; proxies, gateways, and incapable models fall back to the default ephemeral (~5m) breakpoint. For OpenAI Responses, this controls `prompt_cache_retention` only; it does not disable `prompt_cache_key` when a stable session id exists.\n\n## OpenAI-compatible proxy configuration\n\nOpenAI-compatible proxy providers should use schema-supported provider keys first:\n\n```yaml\nproviders:\n  proxy-provider:\n    baseUrl: https://api.proxy.example/v1\n    apiKeyEnv: PROXY_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: local-gpt\n        name: Local GPT\n        reasoning: true\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n```\n\nUse provider-level `headers` for proxy-required headers. Keep the provider `api` set to `openai-completions` when the proxy exposes Chat Completions-compatible `/v1/chat/completions` semantics. `auth: apiKey` sends the resolved token as bearer auth; use `auth: none` only for trusted local/no-auth endpoints.\n\n`requestTransform` and `wireModelId` remain supported for request-body shaping, but they are not needed for ordinary OpenAI-compatible proxies whose local model id is already the upstream wire id. Unknown config keys fail validation before a provider request is sent.\n\nWhen request shaping is needed:\n\n- `requestTransform.profile: openai-proxy` strips OpenAI SDK/Stainless telemetry and beta headers at final fetch time and sets a generic SKC user agent.\n- `stripHeaders` replaces the preset strip list when provided.\n- `setHeaders` is applied after stripping; use `null` to remove a header.\n- `extraBody` is shallow-merged into the JSON request body after provider compatibility fields; core transport keys such as `model`, `messages`/`input`, `stream`, `tools`, and `tool_choice` are protected and ignored.\n- Model-level `requestTransform` overrides provider-level fields and shallow-merges `setHeaders`/`extraBody`.\n- `wireModelId` changes only the upstream request body model id; local selection still uses `provider/id`.\n\n### Layofflabs-style proxy example\n\n```yaml\nproviders:\n  layofflabs:\n    baseUrl: https://api.layofflabs.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-5.5\n        name: GPT 5.5 via Layofflabs\n        reasoning: true\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n\nmodelBindings:\n  modelRoles:\n    default: layofflabs/gpt-5.5:high\n  agentModelOverrides:\n    executor: layofflabs/gpt-5.5:high\n```\n\n## Validation rules (current)\n\n### Full custom provider (`models` is non-empty)\n\nRequired:\n\n- `baseUrl`\n- `apiKey` unless `auth: none`\n- `api` at provider level or each model\n\n### Override-only provider (`models` missing or empty)\n\nMust define at least one of:\n\n- `baseUrl`\n- `headers`\n- `compat`\n- `requestTransform`\n- `disableStrictTools`\n- `modelOverrides`\n- `discovery`\n\n### Discovery\n\n- `discovery` requires provider-level `api`.\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\n- unknown provider, model, override, and request-transform keys fail schema validation; remove stale keys instead of relying on them being ignored.\n\n## Merge and override order\n\nModelRegistry pipeline (on refresh):\n\n1. Load built-in providers/models from `@sayknow-cli/ai`.\n2. Load `models.yml` custom config.\n3. Apply provider overrides (`baseUrl`, `headers`, `requestTransform`, `disableStrictTools`, `cacheRetention`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (schema v3) with a `static_fingerprint` column that hashes the\nstatic catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process via a WeakMap keyed by the static-models array\nreference, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `anthropic-model-opus-4-6`\n- `anthropic-model-haiku-4-5`\n- `gpt-5.3-openai-code`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: openai-code\n        name: Zenmux OpenAI code\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/openai-code: gpt-5.3-openai-code\n    p-openai-code/openai-code: gpt-5.3-openai-code\n  exclude:\n    - demo/openai-code-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `input`, `cost`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL` or `http://127.0.0.1:11434`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `SKC_AUTH_BROKER_URL` (or `auth.broker.url`) is set, the local SQLite credential store is replaced by `RemoteAuthCredentialStore`. Layers 2 and 3 above (stored API key / OAuth in `agent.db`) are served from a broker-supplied snapshot whose `refresh` tokens are redacted; expiry triggers `POST /v1/credential/:id/refresh` on the broker rather than a local refresh.\n\n`AuthStorage.setConfigApiKey` lets a `models.yml` `apiKey` win over a broker-resolved OAuth token without overriding a runtime `--api-key`. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full broker / gateway design and env surface (`SKC_AUTH_BROKER_URL`, `SKC_AUTH_BROKER_TOKEN`, `auth.broker.url`, `auth.broker.token`).\n\n## Model availability vs all models\n\n- `getAll()` returns the loaded model registry (built-in + merged custom + discovered).\n- `getAvailable()` filters to models that are keyless or have resolvable auth.\n\nSo a model can exist in registry but not be selectable until auth is available.\n\n## Runtime model resolution\n\n### CLI and pattern parsing\n\n`model-resolver.ts` supports:\n\n- exact `provider/modelId`\n- exact canonical model id\n- exact model id (provider inferred)\n- fuzzy/substring matching\n- glob scope patterns in `--models` (e.g. `openai/*`, `*sonnet*`)\n- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh`)\n\n`--provider` is legacy; `--model` is preferred.\n\nResolution precedence for exact selectors:\n\n1. exact `provider/modelId` bypasses coalescing\n2. exact canonical id resolves through the canonical index\n3. exact bare concrete id still works\n4. fuzzy and glob matching run after the exact paths\n\n### Initial model selection priority\n\n`findInitialModel(...)` uses this order:\n\n1. explicit CLI provider+model\n2. first scoped model (if not resuming)\n3. saved default provider/model\n4. known provider defaults (e.g. OpenAI/Anthropic/etc.) among available models\n5. first available model\n\n### Role aliases and settings\n\nSupported model roles:\n\n- `default` plus the agent assignment targets `executor`, `architect`, `planner`, `critic`\n\nRole aliases like `pi/default` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI code provider transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-openai-code` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - anthropic-model-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/anthropic-model-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `--list-models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `--list-models` prints a canonical section plus the concrete provider rows\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error. It is **off by default** (`contextPromotion.enabled` is `false`); opt in to enable it.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI code provider websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for Spark -> non-Spark on the same provider:\n\n```yaml\nproviders:\n  openai-code:\n    modelOverrides:\n      gpt-5.3-openai-code-spark:\n        contextPromotionTarget: openai-code/gpt-5.3-openai-code\n```\n\nThe built-in model generator also assigns this automatically for `*-spark` models when a same-provider base model exists.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/ai/src/providers/openai-completions-compat.ts`. It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/model-registry.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/ai/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok and zAI).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true  # if the proxy doesn't support strict tool schemas\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/anthropic-model-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.skc/agent/models.yml`.\n\n## Failure mode\n\nIf `models.yml` fails schema or validation checks:\n\n- registry keeps operating with built-in models\n- error is exposed via `ModelRegistry.getError()` and surfaced in UI/notifications\n",
+	"models.md": "# Model and Provider Configuration (`models.yml`)\n\nThis document describes how the coding-agent currently loads models, applies overrides, resolves credentials, and chooses models at runtime.\n\n## What controls model behavior\n\nPrimary implementation files:\n\n- `src/config/model-registry.ts` — loads built-in + custom models, provider overrides, runtime discovery, auth integration\n- `src/config/model-resolver.ts` — parses model patterns and selects models for the default and agent roles\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.skc/agent/models.yml`\n\nLegacy behavior still present:\n\n- If `models.yml` is missing and `models.json` exists at the same location, it is migrated to `models.yml`.\n- Explicit `.json` / `.jsonc` config paths are still supported when passed programmatically to `ModelRegistry`.\n\n## `models.yml` shape\n\n```yaml\nproviders:\n  <provider-id>:\n    # provider-level config\nequivalence:\n  overrides:\n    <provider-id>/<model-id>: <canonical-model-id>\n  exclude:\n    - <provider-id>/<model-id>\n```\n\n`provider-id` is the canonical provider key used across selection and auth lookup.\n\n`equivalence` is optional and configures canonical model grouping on top of concrete provider models:\n\n- `overrides` maps an exact concrete selector (`provider/modelId`) to an official upstream canonical id\n- `exclude` opts a concrete selector out of canonical grouping\n\n## Provider-level fields\n\n```yaml\nproviders:\n  my-provider:\n    baseUrl: https://api.example.com/v1\n    apiKey: MY_PROVIDER_API_KEY\n    api: openai-completions\n    headers:\n      X-Team: platform\n    authHeader: true\n    auth: apiKey\n    disableStrictTools: false  # set true for Anthropic-compatible endpoints that reject the strict field\n    cacheRetention: short  # none | short | long; model entries and modelOverrides can override this\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n        cacheRetention: long\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        cacheRetention: none\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\nmodelBindings:\n  modelRoles:\n    default: my-provider/some-model-id:high\n  agentModelOverrides:\n    executor: my-provider/some-model-id\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `bedrock-converse-stream`\n- `anthropic-messages`\n- `bedrock-converse-stream`\n- `google-generative-ai`\n- `google-vertex`\n- `google-gemini-cli`\n- `ollama-chat`\n- `cursor-agent`\n\n\n### First-class Azure OpenAI and Amazon Bedrock examples\n\nAzure OpenAI uses canonical OpenAI model IDs in SKC and resolves those IDs to Azure deployment names at request time. Set `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` to avoid assuming model id equals deployment name:\n\n```yaml\nproviders:\n  azure-openai:\n    baseUrl: https://my-resource.openai.azure.com/openai/v1\n    apiKeyEnv: AZURE_OPENAI_API_KEY\n    api: azure-openai-responses\n    models:\n      - id: gpt-4.1\n      - id: o3\n```\n\n```sh\nexport AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-4.1=gpt-41-prod,o3=o3-reasoning-prod'\n```\n\nAmazon Bedrock uses the native `bedrock-converse-stream` transport and AWS credential chain auth. Do not put AWS access keys in `models.yml`; configure `AWS_REGION` / `AWS_PROFILE` or standard static AWS credential environment variables instead:\n\n```yaml\nproviders:\n  amazon-bedrock:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com\n    api: bedrock-converse-stream\n    models:\n      - id: us.anthropic.claude-opus-4-6-v1\n      - id: anthropic.claude-3-5-sonnet-20241022-v2:0\n```\n\n### MiniMax and GLM custom provider examples\n\nFor common MiniMax and GLM/zAI setup, prefer the provider presets so the OpenAI-compatible API, base URL, env var, model id, and compatibility flags are written together:\n\n```sh\nskc setup provider --preset minimax\nskc setup provider --preset minimax-cn\nskc setup provider --preset glm\n```\n\nThe same presets are available inside the TUI:\n\n```text\n/provider add --preset minimax\n/provider add --preset glm\n/provider add zai\n```\n\nPresets only write `models.yml` entries that reference documented environment variable names (`MINIMAX_CODE_API_KEY`, `MINIMAX_CODE_CN_API_KEY`, or `ZAI_API_KEY`); they do not store or validate real credentials. The GLM preset aliases (`glm`, `zai`, `z-ai`) write an OpenAI-compatible custom provider named `glm-proxy` and do not replace the first-class `zai` provider.\n\n## Model profiles (`--mpreset`)\n\nModel profiles are optional top-level `profiles:` entries in `~/.skc/agent/models.yml`. A profile can require provider credentials before activation and can map one or more model roles; omitted roles inherit from the active defaults.\n\n> See also: [Cross-vendor role-based profiles](./multi-vendor-profiles.md) — a curated multi-vendor `profiles:` recipe and verified selector notes that build on the mechanism described here.\n\n```yaml\nprofiles:\n  team-standard:\n    required_providers: [openai, anthropic]\n    model_mapping:\n      default: openai/gpt-5.2\n      executor: anthropic/claude-sonnet-4-6:medium\n      architect: openai/o3:high\n      planner: openai/o3:high\n      critic: openai/o3:high\n```\n\n`model_mapping` keys are role names (`default`, `executor`, `architect`, `planner`, `critic`). Each role maps to exactly one model selector in the form `provider/modelId[:effort]`; comma-separated fallback chains are not supported in a single role value.\n`required_providers` is the aggregate set of providers required across the profile's mapped roles, not a per-role fallback chain.\n\nBuilt-in profiles are grouped by provider mix and tier:\n\n- `codex-{eco,medium,pro}` — all roles on `openai-codex/gpt-5.5`, differing only by per-role reasoning effort\n- `opencodego` — single OpenCode Go preset (Kimi default, DeepSeek executor/architect, Qwen planner, MiMo critic)\n- `claude-opus` — Anthropic OAuth preset centered on `claude-opus-4-8`\n- Single-provider tiers: `glm-{eco,medium,pro}`, `kimi-coding-plan-{eco,medium,pro}`, `mimo-{eco,medium,pro}`, `grok-{eco,medium,pro}`, `cursor-{eco,medium,pro}`, `minimax-{eco,medium,pro}`\n- Combos: `opus-codex` (Claude main agent with Codex support roles), `codex-opencodego` (Codex orchestrator/architect with OpenCode Go workers)\n\nThe `eco` tier favors cheaper/faster defaults, `medium` matches normal production defaults, and `pro` raises reasoning for architect, critic, and planner roles. Effort suffixes are clamped to each model's supported thinking range at preview and activation time (for example `codex-eco`'s executor `:minimal` resolves to effective `low` on `gpt-5.5`). Single-provider tiers pin each provider's current flagship (`zai/glm-5.2`, `kimi-code/kimi-k2.7-code`, `xiaomi/mimo-v2.5-pro`, `xai/grok-4.3`, `cursor/composer-1.5`, `minimax-code/minimax-m3`). User-defined profiles override built-ins by exact profile name.\n\n\nUse `skc --mpreset <name>` to activate a profile for the current session only. Activation hard-blocks when any provider listed in `required_providers` lacks credentials. Add `--default` to persist the selected profile as `modelProfile.default` in `config.yml`, so it applies at startup:\n\n```sh\nskc --mpreset codex-medium\nskc --mpreset opencodego --default\n```\n\nThe `/model` command opens to a preset landing view: presets are grouped by provider with live auth marks (✓/✗), highlighting a group expands its tiers, and selecting a tier shows the full role→model preview before applying for the session or as default. Typing jumps straight to model search, and `Browse all models` opens the classic tabbed model selector. In `/login`, `Add custom provider` is the first option for configuring credentials needed by custom or profile-required providers; after a successful provider login, the matching preset is recommended automatically.\n\nMiniMax's OpenAI-compatible endpoint rejects multiple system messages and emits thinking in `reasoning_content`, so pin the public-safe compatibility fields when hand-authoring a custom provider:\n\n```yaml\nproviders:\n  minimax-custom:\n    baseUrl: https://api.minimax.io/v1\n    apiKeyEnv: MINIMAX_API_KEY\n    api: openai-completions\n    compat:\n      supportsStore: false\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n      reasoningContentField: reasoning_content\n    models:\n      - id: MiniMax-M2.5\n```\n\nGLM via z.ai is available as the first-class `zai` provider. For a private GLM-compatible proxy, keep secrets in an env var and disable OpenAI-only request fields as needed:\n\n```yaml\nproviders:\n  glm-proxy:\n    baseUrl: https://api.z.ai/api/paas/v4\n    apiKeyEnv: ZAI_API_KEY\n    api: openai-completions\n    compat:\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n    models:\n      - id: glm-4.6\n```\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `models.yml` is strict: unknown provider/model keys fail validation before provider dispatch, so stale keys such as `requestTransform` or `wireModelId` only work where this document lists them.\n- `discovery.type`: `ollama`, `llama.cpp`, or `lm-studio`\n- `cacheRetention`: `none`, `short`, or `long`; request-time options win over model/modelOverride values, then provider values, then `SKC_CACHE_RETENTION`, then the runtime default. The runtime default is `short` for most providers, but the Anthropic provider defaults to `long` (`ttl: \"1h\"`) because the ~5m default is too fragile for long-running subagent workflows. The 1h marker is only emitted on the canonical Anthropic API (`api.anthropic.com`) for models advertising `supportsLongCacheRetention`; proxies, gateways, and incapable models fall back to the default ephemeral (~5m) breakpoint. For OpenAI Responses, this controls `prompt_cache_retention` only; it does not disable `prompt_cache_key` when a stable session id exists.\n\n## OpenAI-compatible proxy configuration\n\nOpenAI-compatible proxy providers should use schema-supported provider keys first:\n\n```yaml\nproviders:\n  proxy-provider:\n    baseUrl: https://api.proxy.example/v1\n    apiKeyEnv: PROXY_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: local-gpt\n        name: Local GPT\n        reasoning: true\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n```\n\nUse provider-level `headers` for proxy-required headers. Keep the provider `api` set to `openai-completions` when the proxy exposes Chat Completions-compatible `/v1/chat/completions` semantics. `auth: apiKey` sends the resolved token as bearer auth; use `auth: none` only for trusted local/no-auth endpoints.\n\n`requestTransform` and `wireModelId` remain supported for request-body shaping, but they are not needed for ordinary OpenAI-compatible proxies whose local model id is already the upstream wire id. Unknown config keys fail validation before a provider request is sent.\n\nWhen request shaping is needed:\n\n- `requestTransform.profile: openai-proxy` strips OpenAI SDK/Stainless telemetry and beta headers at final fetch time and sets a generic SKC user agent.\n- `stripHeaders` replaces the preset strip list when provided.\n- `setHeaders` is applied after stripping; use `null` to remove a header.\n- `extraBody` is shallow-merged into the JSON request body after provider compatibility fields; core transport keys such as `model`, `messages`/`input`, `stream`, `tools`, and `tool_choice` are protected and ignored.\n- Model-level `requestTransform` overrides provider-level fields and shallow-merges `setHeaders`/`extraBody`.\n- `wireModelId` changes only the upstream request body model id; local selection still uses `provider/id`.\n\n### Layofflabs-style proxy example\n\n```yaml\nproviders:\n  layofflabs:\n    baseUrl: https://api.layofflabs.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-5.5\n        name: GPT 5.5 via Layofflabs\n        reasoning: true\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n\nmodelBindings:\n  modelRoles:\n    default: layofflabs/gpt-5.5:high\n  agentModelOverrides:\n    executor: layofflabs/gpt-5.5:high\n```\n\n## Validation rules (current)\n\n### Full custom provider (`models` is non-empty)\n\nRequired:\n\n- `baseUrl`\n- `apiKey` unless `auth: none`\n- `api` at provider level or each model\n\n### Override-only provider (`models` missing or empty)\n\nMust define at least one of:\n\n- `baseUrl`\n- `headers`\n- `compat`\n- `requestTransform`\n- `disableStrictTools`\n- `modelOverrides`\n- `discovery`\n\n### Discovery\n\n- `discovery` requires provider-level `api`.\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\n- unknown provider, model, override, and request-transform keys fail schema validation; remove stale keys instead of relying on them being ignored.\n\n## Merge and override order\n\nModelRegistry pipeline (on refresh):\n\n1. Load built-in providers/models from `@sayknow-cli/ai`.\n2. Load `models.yml` custom config.\n3. Apply provider overrides (`baseUrl`, `headers`, `requestTransform`, `disableStrictTools`, `cacheRetention`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (schema v3) with a `static_fingerprint` column that hashes the\nstatic catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process via a WeakMap keyed by the static-models array\nreference, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `anthropic-model-opus-4-6`\n- `anthropic-model-haiku-4-5`\n- `gpt-5.3-openai-code`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: openai-code\n        name: Zenmux OpenAI code\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/openai-code: gpt-5.3-openai-code\n    p-openai-code/openai-code: gpt-5.3-openai-code\n  exclude:\n    - demo/openai-code-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `input`, `cost`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL` or `http://127.0.0.1:11434`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `SKC_AUTH_BROKER_URL` (or `auth.broker.url`) is set, the local SQLite credential store is replaced by `RemoteAuthCredentialStore`. Layers 2 and 3 above (stored API key / OAuth in `agent.db`) are served from a broker-supplied snapshot whose `refresh` tokens are redacted; expiry triggers `POST /v1/credential/:id/refresh` on the broker rather than a local refresh.\n\n`AuthStorage.setConfigApiKey` lets a `models.yml` `apiKey` win over a broker-resolved OAuth token without overriding a runtime `--api-key`. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full broker / gateway design and env surface (`SKC_AUTH_BROKER_URL`, `SKC_AUTH_BROKER_TOKEN`, `auth.broker.url`, `auth.broker.token`).\n\n## Model availability vs all models\n\n- `getAll()` returns the loaded model registry (built-in + merged custom + discovered).\n- `getAvailable()` filters to models that are keyless or have resolvable auth.\n\nSo a model can exist in registry but not be selectable until auth is available.\n\n## Runtime model resolution\n\n### CLI and pattern parsing\n\n`model-resolver.ts` supports:\n\n- exact `provider/modelId`\n- exact canonical model id\n- exact model id (provider inferred)\n- fuzzy/substring matching\n- glob scope patterns in `--models` (e.g. `openai/*`, `*sonnet*`)\n- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh`)\n\n`--provider` is legacy; `--model` is preferred.\n\nResolution precedence for exact selectors:\n\n1. exact `provider/modelId` bypasses coalescing\n2. exact canonical id resolves through the canonical index\n3. exact bare concrete id still works\n4. fuzzy and glob matching run after the exact paths\n\n### Initial model selection priority\n\n`findInitialModel(...)` uses this order:\n\n1. explicit CLI provider+model\n2. first scoped model (if not resuming)\n3. saved default provider/model\n4. known provider defaults (e.g. OpenAI/Anthropic/etc.) among available models\n5. first available model\n\n### Role aliases and settings\n\nSupported model roles:\n\n- `default` plus the agent assignment targets `executor`, `architect`, `planner`, `critic`\n\nRole aliases like `pi/default` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI code provider transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-openai-code` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - anthropic-model-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/anthropic-model-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `--list-models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `--list-models` prints a canonical section plus the concrete provider rows\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error. It is **off by default** (`contextPromotion.enabled` is `false`); opt in to enable it.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI code provider websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for Spark -> non-Spark on the same provider:\n\n```yaml\nproviders:\n  openai-code:\n    modelOverrides:\n      gpt-5.3-openai-code-spark:\n        contextPromotionTarget: openai-code/gpt-5.3-openai-code\n```\n\nThe built-in model generator also assigns this automatically for `*-spark` models when a same-provider base model exists.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/ai/src/providers/openai-completions-compat.ts`. It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/model-registry.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/ai/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `sendSessionHeaders` — forward the agent session id as `session_id` and `x-session-id` request headers so OpenAI-compatible relays/proxies can do session-affinity routing and reuse a server-side prompt cache. Default: `false`. Caller-set `headers`/`requestTransform` values are never overwritten.\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok and zAI).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true  # if the proxy doesn't support strict tool schemas\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/anthropic-model-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.skc/agent/models.yml`.\n\n## Failure mode\n\nIf `models.yml` fails schema or validation checks:\n\n- registry keeps operating with built-in models\n- error is exposed via `ModelRegistry.getError()` and surfaced in UI/notifications\n",
+	"multi-vendor-profiles.md": "# Choosing models in SKC: role-based profiles\n\nA practical guide to picking models for SKC's roles, for every subscription situation — one vendor, two vendors, or the full multi-vendor set. It adds curated cross-vendor `profiles:` for `~/.skc/agent/models.yml` and verified selector notes on top of the mechanism in [Model profiles](./models.md#model-profiles---mpreset). Everything here is **user config**; it complements the built-in `--mpreset` presets and overrides a built-in only when it shares its exact name.\n\n> Selectors, prices, and \"axis leaders\" are catalog- and time-sensitive (observed 2026-06 on the current bundled catalog). Re-verify any selector with `skc -p --no-session --no-tools --model <selector> \"Reply OK\"`.\n\n## The five roles\n\n`default` runs the main loop and most turns; `executor` / `architect` / `planner` / `critic` are the four bundled task agents, delegated only when the work calls for it.\n\n| Role | What it optimizes for |\n| --- | --- |\n| `default` | tool-calling reliability + honesty (it routes — its quality bounds the whole system) |\n| `executor` | real coding (SWE-bench Verified) |\n| `planner` | reasoning + sequencing (GPQA / ARC-AGI-2) |\n| `architect` | large-context + multimodal review |\n| `critic` | independent adversarial review (different family from what it reviews) |\n\n## Pick by what you subscribe to\n\n| You have | Use |\n| --- | --- |\n| **One vendor** | the built-in preset for that vendor — `claude-opus` (Anthropic), `codex-{eco,medium,pro}` (OpenAI/Codex), `opencodego` (OpenCode Go), or a single-vendor flagship tier (`zai/glm-5.2`, `kimi-code/...`, `xiaomi/...`, `xai/grok-4.3`, `minimax-code/...`). These already map all five roles inside one vendor. |\n| **Claude + Codex** | the built-in `opus-codex` (Claude main loop + Codex support roles). |\n| **Three or more / all five** | the cross-vendor profiles below — each role on its axis leader, `critic` kept cross-family. |\n\nThe single guiding rule across all of these: **keep `default` on the strongest router you have** (Anthropic Opus when available). A weak `default` caps quality regardless of the delegated models.\n\n## Cross-vendor profiles (3+ vendors)\n\nNo single vendor leads every axis, so these put each role on its axis leader and keep `critic` on a different family from the `executor` it reviews.\n\n```yaml\nprofiles:\n\n  daily:                 # everyday balance\n    required_providers: [anthropic, openai-codex, google-antigravity, xai]\n    model_mapping:\n      default:   anthropic/claude-opus-4-8:medium\n      executor:  openai-codex/gpt-5.4:high\n      planner:   google-antigravity/gemini-3.1-pro-low:high\n      architect: google-antigravity/gemini-3.1-pro-low:high\n      critic:    xai/grok-4.3:medium\n\n  ultimate:              # cost-no-object, best per role\n    required_providers: [anthropic, openai-codex, google-antigravity, xai]\n    model_mapping:\n      default:   anthropic/claude-opus-4-8:high\n      executor:  anthropic/claude-opus-4-8:max\n      planner:   openai-codex/gpt-5.5:xhigh\n      architect: google-antigravity/gemini-3.1-pro-low:high\n      critic:    xai/grok-4.3:high\n\n  eco:                   # cheapest delegated work; main loop stays on Opus\n    required_providers: [anthropic, opencode-go, google-antigravity, xai]\n    model_mapping:\n      default:   anthropic/claude-opus-4-8:low\n      executor:  opencode-go/deepseek-v4-flash\n      planner:   xai/grok-4-1-fast:high\n      architect: google-antigravity/gemini-3.1-pro-low\n      critic:    google-antigravity/gemini-3.5-flash\n\n  monorepo:              # huge codebases (openai-codex excluded: 272k context cap)\n    required_providers: [anthropic, google-antigravity, opencode-go]\n    model_mapping:\n      default:   anthropic/claude-opus-4-8:medium\n      executor:  anthropic/claude-opus-4-8:high\n      planner:   google-antigravity/gemini-3.1-pro-low:high\n      architect: anthropic/claude-opus-4-8:high\n      critic:    opencode-go/glm-5.2\n```\n\n## Model cheatsheet (by need)\n\nCurrent axis leaders and the cheaper second option, with metered price ($/1M in/out; Gemini via Antigravity runs on the Google AI subscription):\n\n| Need | First pick | Cheaper option |\n| --- | --- | --- |\n| Router / tool-calling (`default`) | `anthropic/claude-opus-4-8` (5/25) | `anthropic/claude-sonnet-4-6` (3/15) |\n| Coding (`executor`) | `anthropic/claude-opus-4-8` — SWE-bench Verified ~88.6 (5/25) | `openai-codex/gpt-5.4` (2.5/15) · `opencode-go/deepseek-v4-flash` (0.14/0.28) |\n| Reasoning (`planner`) | `openai-codex/gpt-5.5` (ARC-AGI-2) / `google-antigravity/gemini-3.1-pro-low:high` (GPQA) | `xai/grok-4-1-fast` (0.2/0.5) |\n| Large context (`architect`) | `anthropic/claude-opus-4-8` (effective long-context) | `xai/grok-4-fast` (2M nominal, 0.2/0.5) |\n| Multimodal review (`architect`) | `google-antigravity/gemini-3.1-pro-low:high` | `google-antigravity/gemini-3.5-flash` |\n| Independent critic | `xai/grok-4.3` (1.25/2.5) | `opencode-go/glm-5.2` · `google-antigravity/gemini-3.5-flash` |\n\nOn standard tasks, all current frontier models in the catalog are accurate; **pick by cost, latency, and role fit, not by raw accuracy on easy prompts.** As an indicative SKC-routed latency reference (`skc -p`, identical coding + reasoning prompts, all correct): `grok-4.3` and `glm-5.2` ≈ 2–3s, `deepseek-v4-pro` ≈ 3–4s, `claude-opus-4-8` / `gpt-5.5` ≈ 4–7s, `gemini-3.1-pro-low:high` ≈ 7s.\n\n## Verified selector notes (current catalog)\n\nObserved via live `skc -p` calls; useful when wiring the profiles above:\n\n- **Antigravity Gemini, high reasoning** → use `google-antigravity/gemini-3.1-pro-low:high`. The id `gemini-3.1-pro-high` returns HTTP 400 (no matching backend model); `thinkingLevel` is a per-request parameter, so raising it on `gemini-3.1-pro-low` invokes the model's native high-reasoning mode rather than a degraded one.\n- **openai-codex on a ChatGPT account** serves base GPT only (`gpt-5.5`, `gpt-5.4`). Standalone `-codex` variants (`gpt-5.3-codex`, `gpt-5.2-codex`, `gpt-5.1-codex-max` / `-mini`) return `not supported when using Codex with a ChatGPT account`.\n- **Single-message input limit is separate from the context window.** `claude-opus-4-8` runs with a 1M window via multi-turn accumulation, but a single `@file` message above ~400k tokens returns 400 on `anthropic` / `google-antigravity`; `xai` / `opencode-go` accept larger single messages. Chunk very large inputs across turns instead of pasting one block.\n- **Some selectors come from a provider's live catalog, not the bundled snapshot.** `opencode-go/glm-5.2` and `google-antigravity/gemini-3.5-flash` resolved in `skc -p` tests but are **not** in `packages/ai/src/models.json`; they appear only after the provider's online model discovery has populated the registry. `required_providers` verifies credentials at activation — it does **not** guarantee fresh, non-stale discovery — so activation can still fail with `selector did not resolve` until discovery runs (re-login or retry to refresh). If you hit that, substitute a bundled id: `opencode-go/deepseek-v4-pro` for the critic, or `zai/glm-5.2` (add `zai` to `required_providers`) for GLM 5.2.\n\n## Activation\n\n```bash\nskc --mpreset daily               # this session only\nskc --mpreset ultimate --default  # persist as the startup default (config.yml)\n```\n\nActivation hard-blocks when any provider in `required_providers` lacks credentials, so log in first: `/login anthropic`, `/login openai-codex`, `/login google-antigravity`, `/login xai` (and `opencode-go` via `OPENCODE_API_KEY`).\n",
 	"native-ffi-optimization-policy.md": "# ADR: Native FFI Optimization Policy\n\n- Status: Accepted\n- Scope: `crates/pi-natives` algorithmic ports proposed for performance reasons\n- Related: [`porting-to-natives.md`](./porting-to-natives.md), [`natives-architecture.md`](./natives-architecture.md), [`natives-binding-contract.md`](./natives-binding-contract.md), [`cpu-hotspot-map.json`](./cpu-hotspot-map.json), [`hotspot-map-successor.md`](./hotspot-map-successor.md)\n\n## Decision\n\nA new native (Rust N-API / FFI) port proposed **to optimize a leftover hot path** does not land unless **all** of the following gates pass:\n\n1. **Corpus evidence** — a profiling-corpus trace shows the path has user-visible latency or RSS impact on a representative workload (not just a static complexity argument).\n2. **Self-time attribution** — a `profilerSelfTime` artifact identifies the proposed hotspot, **or** fallback-toggle evidence proves an end-to-end benefit without byte changes. Wall-clock proxy timing alone is never sufficient.\n3. **Measured FFI overhead** — the N-API call/marshalling overhead is measured against the JS/TS baseline, not assumed away.\n4. **Representative win** — a representative p50/p95 win exists on realistic inputs, not only microbenchmark seed results.\n5. **Byte parity** — a byte-identical corpus covers rendered, persisted, and provider-visible bytes for the changed path.\n6. **Operational cost** — fallback, packaging, and rollback costs are documented.\n\nThis policy governs **speculative algorithmic ports**. It does **not** re-litigate already-native platform/system surfaces (see [Scope boundary](#scope-boundary)).\n\n## Context\n\nThe CPU/memory hotspot program (Optimization Suites v1–v3, tracked in [`cpu-hotspot-map.json`](./cpu-hotspot-map.json)) is closed out. Its prioritization was a **static structural ranking** (algorithmic complexity × trigger frequency), and the map's own `method` field records that real CPU self-time was \"to be measured by the agreed profiling corpus during optimization.\" That corpus is being built separately; until its evidence exists, new native ports for leftover hotspots would repeat the same evidence gap.\n\nThe suites already produced concrete decisions that this policy codifies so they are not re-discovered:\n\n- **v2 (#530)** measured and **rejected the five remaining Rust port candidates** per the FFI cost gates after shipping only `diffLines` (H03) natively. Native overhead did not beat the JS/TS baseline for those candidates on realistic inputs.\n- **v3 (#558) rejected a native word-diff (H04)** \"without a fresh FFI gate\" — the TS fast paths were retained instead; a native port would need to re-clear gates 1–6 above.\n- **Hunt-Szymanski LCS (H05)** was implemented as a native/algorithmic replacement, then **reverted** because it produced byte-different rendered diffs (reproduced by red-team). Byte parity is the gate, not raw speed.\n- **The custom JSON length counter (H08)** was implemented, made exact, then **deleted** — an exact JS reimplementation was not faster than native `JSON.stringify`. \"More native\" is not automatically \"faster.\"\n\nThese four precedents share a root cause: a plausible algorithmic/native win that failed a real gate (cost, byte parity, or end-to-end benefit). The policy makes those gates a precondition rather than a post-hoc discovery.\n\n## Evidence taxonomy\n\nNative-port claims must classify their evidence using the same separated classes as the profiling corpus. These classes must never be conflated:\n\n- **`wallClockPhase`** — elapsed timing around a phase or operation. Useful for perceived-latency and regression detection; **insufficient** to confirm CPU self-time or to justify a port on its own.\n- **`processCpuUsage`** — `process.cpuUsage()` user/system deltas, optionally normalized by elapsed time. Indicates process-level CPU pressure; **cannot** attribute self-time to a specific hotspot.\n- **`profilerSelfTime`** — profiler (or equivalent sampled/trace) attribution of self-time to a function, module, or native symbol. **Required** before a hotspot may be called \"CPU-self-time confirmed.\"\n\nA native-optimization proposal that cites only `wallClockPhase` or `processCpuUsage` is **not** CPU-self-time confirmed and does not clear gate 2.\n\n## Approval checklist\n\nBefore opening a native-optimization PR, confirm and attach evidence for each:\n\n- [ ] Corpus trace shows user-visible latency or RSS impact for the path (gate 1).\n- [ ] `profilerSelfTime` artifact identifies the hotspot, **or** fallback-toggle before/after evidence proves end-to-end benefit without byte changes (gate 2).\n- [ ] FFI/marshalling overhead measured vs the JS/TS baseline in the same benchmark run (gate 3).\n- [ ] Representative p50/p95 win on realistic inputs, not only seeded microbench results (gate 4).\n- [ ] Byte-identical corpus covers rendered, persisted, and provider-visible bytes (gate 5).\n- [ ] Fallback, packaging (platform variants / embedded addon), and rollback costs documented (gate 6).\n\nIf any box is unchecked, keep the work in TypeScript or hold it as a tracked candidate; do not switch callsites. This mirrors the existing **Rule of thumb** in [`porting-to-natives.md`](./porting-to-natives.md): if native is not faster *and* behavior-compatible, do not switch callsites.\n\n## Scope boundary\n\nThis policy targets **speculative algorithmic ports**, not the established native surface. The following are **already native** by design and are explicitly out of scope (see `alreadyNativeExcluded` in [`cpu-hotspot-map.json`](./cpu-hotspot-map.json)):\n\n`grep`, `fd`/`glob`, text width/wrap/truncate/slice, syntax highlighting, HTML→Markdown, token counting, AST, summary, process/PTY/shell, SIXEL, clipboard, `Bun.hash.xxHash32/64`, and `JSON.parse`/`JSON.stringify`.\n\nThese are native because they are I/O, OS/process integration, or platform primitives — the criteria in [`porting-to-natives.md`](./porting-to-natives.md#when-to-port). Distinguishing them from algorithmic ports matters: a leftover algorithmic hotspot must clear gates 1–6, whereas adding a new OS/process/native-primitive binding follows the standard porting guide.\n\n## Consequences\n\n- New native algorithmic ports require profiling-corpus evidence and a measured cost gate before review; this slows speculative optimization but prevents byte-parity regressions and dead native code.\n- The default answer for a leftover hotspot is \"keep it in TypeScript\" until the corpus proves it matters.\n- Already-native platform/system primitives and new OS/process bindings are unaffected; they follow [`porting-to-natives.md`](./porting-to-natives.md) as before.\n- Reviewers can reject a native-optimization PR purely on a missing gate, citing this ADR, without re-deriving the rationale.\n\n## Follow-ups\n\n- Held native candidates (H04 word-diff, H05 LCS, and other v2-rejected candidates) stay held unless a future PR clears gates 1–6 with fresh corpus evidence.\n- When the profiling corpus lands, link its threshold/evidence ledger here so native-port proposals can cite concrete corpus artifacts.\n",
 	"natives-addon-loader-runtime.md": "# Natives Addon Loader Runtime\n\nThis document covers the runtime loader shipped by `@sayknow-cli/natives`: how `native/index.js` decides which `.node` file to require, how compiled-binary embedded payloads are extracted, and what startup failures report.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/package.json`\n\n## Scope and responsibility\n\nThe loader is intentionally narrow:\n\n- Build a platform/CPU-aware candidate list for addon filenames and directories.\n- Treat an embedded-addon manifest as the authoritative compiled-binary signal when present.\n- Optionally materialize an embedded addon into a versioned per-user cache directory.\n- Attempt candidates in deterministic order and return the first addon that `require(...)` loads.\n\nThe current loader does **not** run a separate `validateNative(...)` export-presence gate. API shape is provided by the generated N-API binding file (`native/index.d.ts`) and the loaded addon itself. A stale binary therefore normally fails as a missing property or native load error rather than as a custom \"missing exports\" validation error.\n\n## Runtime inputs and derived state\n\nAt module initialization, `native/index.js` computes:\n\n- **Platform tag**: `${process.platform}-${process.arch}` (for example `darwin-arm64`).\n- **Package version**: from `packages/natives/package.json`.\n- **Core directories**:\n  - `nativeDir`: package-local `packages/natives/native`.\n  - `execDir`: directory containing `process.execPath`.\n  - `versionedDir`: `<getNativesDir()>/<packageVersion>`.\n  - `userDataDir` fallback:\n    - Windows: `%LOCALAPPDATA%/skc` or `%USERPROFILE%/AppData/Local/skc`.\n    - Non-Windows: `~/.local/bin`.\n- **Natives cache root** (`getNativesDir()`):\n  - if `$XDG_DATA_HOME/skc` exists, `$XDG_DATA_HOME/skc/natives`;\n  - otherwise `~/.skc/natives`.\n- **Compiled-binary mode** (`detectCompiledBinary`): true if any of:\n  - embedded-addon manifest is non-null,\n  - `SKC_COMPILED` env var is set,\n  - `import.meta.url` contains Bun embedded markers (`$bunfs`, `~BUN`, `%7EBUN`).\n- **Variant override**: `SKC_NATIVE_VARIANT` (`modern`/`baseline` only; invalid values ignored).\n- **Selected variant**: explicit override, otherwise runtime AVX2 detection on x64 (`modern` if AVX2, else `baseline`).\n\n## Platform support and tag resolution\n\n`SUPPORTED_PLATFORMS` is fixed to:\n\n- `linux-x64`\n- `linux-arm64`\n- `darwin-arm64`\n- `win32-x64`\n\nUnsupported platforms are not rejected before probing. The loader first tries the computed candidate paths. If all fail and `platformTag` is unsupported, it throws an unsupported-platform error listing supported tags.\n\n## Variant selection (`modern` / `baseline` / default)\n\n### x64 behavior\n\n1. `SKC_NATIVE_VARIANT=modern|baseline` wins when valid.\n2. Otherwise AVX2 support is detected:\n   - Linux: scan `/proc/cpuinfo` for `avx2`.\n   - macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`.\n   - Windows: PowerShell `[System.Runtime.Intrinsics.X86.Avx2]::IsSupported`.\n3. AVX2 selects `modern`; unavailable or undetectable AVX2 selects `baseline`.\n\n### Non-x64 behavior\n\nNo variant suffix is used; the filename is `pi_natives.<platform>-<arch>.node`.\n\n### Filename construction\n\n`loader-state.js#getAddonFilenames` returns:\n\n- Non-x64 or no variant: `pi_natives.<tag>.node`\n- x64 + `modern`:\n  1. `pi_natives.<tag>-modern.node`\n  2. `pi_natives.<tag>-baseline.node`\n  3. `pi_natives.<tag>.node`\n- x64 + `baseline`:\n  1. `pi_natives.<tag>-baseline.node`\n  2. `pi_natives.<tag>.node`\n\nThe default unsuffixed fallback remains part of the x64 candidate list.\n\n## Candidate path construction and fallback ordering\n\n`resolveLoaderCandidates(...)` expands every filename across directories, then de-duplicates while preserving first occurrence order.\n\n### Non-compiled runtime\n\nFor each filename, candidates are:\n\n1. `<nativeDir>/<filename>`\n2. `<execDir>/<filename>`\n\n### Compiled runtime\n\nFor each filename, candidates are:\n\n1. `<versionedDir>/<filename>`\n2. `<userDataDir>/<filename>`\n3. `<nativeDir>/<filename>`\n4. `<execDir>/<filename>`\n\nAt load time, an extracted embedded candidate, when produced, is prepended ahead of these de-duplicated candidates.\n\n## Embedded addon extraction lifecycle\n\n`embedded-addon.js` is generated by `scripts/embed-native.ts`. The reset stub exports `embeddedAddon = null`. A populated manifest has:\n\n- `platformTag`\n- `version`\n- `files[]` entries with `variant`, `filename`, and `filePath`\n\nExtraction (`maybeExtractEmbeddedAddon`) runs only when:\n\n1. compiled-binary mode is true,\n2. `embeddedAddon` is non-null,\n3. manifest `platformTag` equals the runtime platform tag,\n4. manifest `version` equals the package version,\n5. a variant-appropriate embedded file exists.\n\nVariant file selection:\n\n- Non-x64: prefer `default`, then first available file.\n- x64 + `modern`: prefer `modern`, fallback to `baseline`.\n- x64 + `baseline`: require `baseline`.\n\nMaterialization:\n\n1. Ensure `<versionedDir>` exists.\n2. Reuse `<versionedDir>/<selected filename>` if it already exists.\n3. Otherwise read `selectedEmbeddedFile.filePath` and write the target path.\n4. Return the target path as the first candidate.\n\nDirectory creation or write failures are appended to the loader error list; probing continues through normal candidates.\n\n## Lifecycle and state transitions\n\n```text\nInit\n  -> Load package metadata and embedded-addon manifest\n  -> Compute platform/version/variant/filenames/candidate paths\n  -> (compiled + embedded manifest matches?)\n       yes -> try extract to versionedDir (record errors, continue)\n       no  -> skip extraction\n  -> For each runtime candidate in order:\n       require(candidate)\n       -> success: return addon exports (READY)\n       -> failure: record error, continue\n  -> none loaded:\n       if unsupported platform tag -> throw Unsupported platform\n       else -> throw Failed to load (tried-path diagnostics + hints)\n```\n\n## Failure behavior and diagnostics\n\n### Unsupported platform\n\nIf all candidates fail and `platformTag` is not supported, the loader throws:\n\n- `Unsupported platform: <tag>`\n- supported platform list\n- issue-reporting guidance\n\n### No loadable candidate\n\nIf the platform is supported but no candidate can be loaded, the final error includes:\n\n- `Failed to load pi_natives native addon for <platformTag>` or `<platformTag> (<variant>)`\n- every attempted path with the corresponding `require(...)` error\n- mode-specific remediation hints\n\n### Compiled-binary startup failures\n\nCompiled mode diagnostics include:\n\n- expected versioned cache target paths (`<versionedDir>/<filename>`),\n- remediation to delete the versioned cache and rerun,\n- direct release download `curl` commands for each expected filename.\n\n### Non-compiled startup failures\n\nNormal package/runtime diagnostics include:\n\n- reinstall hint (`bun install @sayknow-cli/natives`),\n- local rebuild command (`bun --cwd=packages/natives run build`),\n- optional x64 variant build hint (`TARGET_VARIANT=baseline|modern bun --cwd=packages/natives run build`).\n",
 	"natives-architecture.md": "# Natives Architecture\n\n`@sayknow-cli/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. Performance-motivated native ports of leftover algorithmic hot paths are additionally gated by [`native-ffi-optimization-policy.md`](./native-ffi-optimization-policy.md).\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 `@sayknow-cli/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}-${process.arch}`.\n- Supported tags are currently:\n  - `linux-x64`\n  - `linux-arm64`\n  - `darwin-arm64`\n  - `win32-x64`\n- x64 can use CPU variants:\n  - `modern` (AVX2-capable)\n  - `baseline` (fallback)\n- Non-x64 uses the default filename without a variant suffix.\n\nFilename strategy:\n\n- Default: `pi_natives.<platform>-<arch>.node`\n- x64 variant: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- x64 runtime fallback includes the unsuffixed default filename after variant candidates.\n\n### Platform-specific variant detection\n\nFor x64, variant selection uses:\n\n- Linux: `/proc/cpuinfo`\n- macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`\n- Windows: PowerShell check for `System.Runtime.Intrinsics.X86.Avx2`\n\n`SKC_NATIVE_VARIANT` can force `modern` or `baseline`; invalid values are ignored.\n\n### Binary distribution and extraction model\n\n`packages/natives/package.json` publishes `native/`, which contains the loader, generated declarations, generated enum patch, embedded-addon manifest stub, and prebuilt `.node` artifacts.\n\nFor compiled binaries, loader behavior is:\n\n1. Check versioned user cache path: `<getNativesDir()>/<packageVersion>/...`.\n2. Check legacy compiled-binary location:\n   - Windows: `%LOCALAPPDATA%/skc` (fallback `%USERPROFILE%/AppData/Local/skc`)\n   - non-Windows: `~/.local/bin`\n3. Fall back to packaged `native/` and executable directory candidates.\n\n`getNativesDir()` uses `$XDG_DATA_HOME/skc/natives` when `$XDG_DATA_HOME/skc` exists; otherwise it uses `~/.skc/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 `@sayknow-cli/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",
@@ -56,10 +57,10 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"readme/README.ko.md": "<p align=\"center\">\n  <img src=\"../../assets/hero.png\" alt=\"Sayknow-CLI autonomous coding-agent hero illustration\" width=\"100%\" />\n</p>\n\n<h1 align=\"center\">Sayknow-CLI</h1>\n\n<p align=\"center\">\n  <strong>코딩은 사고처럼 느껴져야 합니다.</strong><br />\n  인터뷰, 검토된 계획, tmux 네이티브 실행, 견고한 검증을 위한 집중형 코딩 에이전트 러너.\n</p>\n\n<p align=\"center\">\n  <a href=\"https://github.com/jaybeyond/Sayknow_CLI/releases\"><img alt=\"Release\" src=\"https://img.shields.io/github/v/tag/jaybeyond/Sayknow_CLI?sort=semver&label=release&style=flat-square&color=2f9bff\"></a>\n  <a href=\"LICENSE\"><img alt=\"License: MIT\" src=\"https://img.shields.io/github/license/jaybeyond/Sayknow_CLI?style=flat-square&color=green\"></a>\n  <a href=\"https://github.com/jaybeyond/Sayknow_CLI/stargazers\"><img alt=\"Stars\" src=\"https://img.shields.io/github/stars/jaybeyond/Sayknow_CLI?style=flat-square&color=f5c518\"></a>\n  <a href=\"https://github.com/jaybeyond/Sayknow_CLI/issues\"><img alt=\"Issues\" src=\"https://img.shields.io/github/issues/jaybeyond/Sayknow_CLI?style=flat-square\"></a>\n  <a href=\"https://bun.sh\"><img alt=\"Built with Bun\" src=\"https://img.shields.io/badge/built%20with-Bun-fbf0df?style=flat-square&logo=bun&logoColor=black\"></a>\n  <a href=\"#languages\"><img alt=\"i18n\" src=\"https://img.shields.io/badge/i18n-7%20languages-2f9bff?style=flat-square\"></a>\n</p>\n\n<p align=\"center\">\n  <a href=\"../../README.md\">English</a> ·\n  <b>한국어</b> ·\n  <a href=\"README.zh.md\">中文</a> ·\n  <a href=\"README.ja.md\">日本語</a> ·\n  <a href=\"README.es.md\">Español</a> ·\n  <a href=\"README.fr.md\">Français</a> ·\n  <a href=\"README.de.md\">Deutsch</a>\n</p>\n\n<p align=\"center\">\n  <img src=\"../../assets/character.png\" alt=\"Sayknow-CLI character mascot\" width=\"320\" />\n</p>\n\n> Sayknow-CLI는 실험적인 베타 단계 프로젝트입니다. 거친 부분이 있을 수 있으니 중요한 작업에 의존하기 전에 출력 결과를 검증하세요.\n\n## Languages\n\n인터페이스는 **7개 언어** — English, 한국어 (Korean),\n中文 (简体 / Simplified Chinese), 日本語 (Japanese), Español (Spanish),\nFrançais (French), Deutsch (German) — 로 현지화되어 있습니다. 첫 실행 시\n시스템 로케일을 자동으로 감지하며, 언제든지 **Settings → Appearance → Language** 에서\n전환하거나 예를 들어 `LANG=ja_JP.UTF-8 skc` 로 실행할 수 있습니다. 번역되지 않은 문자열은\nEnglish로 대체되며, 브랜드/기술 이름(Claude, OpenAI, MCP, …)은 모든 로케일에서 그대로 유지됩니다.\n\n## What is Sayknow-CLI?\n\nSayknow-CLI(`skc`)는 외부 코딩 에이전트 하니스입니다. 선택한 저장소나 워크트리에서 실행되며, 에이전트에게 작고 명시적인 워크플로 표면을 제공합니다:\n\n```text\ndeep-interview -> ralplan -> ultragoal\n                         └─ optional team execution when parallel tmux workers help\n```\n\n이것은 의도적으로 Codex CLI, Claude Code, OpenCode, Claw Code의 숨겨진 플러그인이 아닙니다. 구조화된 계획, 지속적인 증거, tmux 기반 워커, 또는 격리된 워크트리를 원할 때 이러한 도구들 옆에서 `skc`를 시작하세요.\n\n## Install\n\n```sh\nnpm install -g sayknow-cli       # 또는: bun install -g sayknow-cli\nskc --version\n```\n\n프리빌드 네이티브(macOS·Linux·Windows)가 포함돼 있어 Rust 툴체인이나 빌드가 필요 없습니다. 업데이트는 `npm install -g sayknow-cli@latest` 또는 터미널에서 `skc update`.\n\n> 이전에 소스(git clone)로 설치했다면 한 번만 `rm -f ~/.local/bin/skc && npm install -g sayknow-cli`로 전환하세요. 소스/개발 설치는 [영문 README](../../README.md#install-from-source-development) 참고.\n\n## Quick start\n\n```sh\n# Run directly in the current checkout\nskc\n\n# Use a tmux-backed leader session\nskc --tmux\n\n# Use an isolated worktree for risky or reviewable work\n# --worktree takes an optional branch-like name, not a filesystem path.\nskc --tmux --worktree my-task-branch\n\n# If you already created a worktree directory, launch from that directory instead.\ncd ../my-task-worktree && skc --tmux\n```\n\nSKC 세션 내부에서는, 공개 워크플로 표면을 사용하세요:\n\n```text\n/skill:deep-interview clarify ambiguous requirements\n/skill:ralplan build and critique the implementation plan\nskc ultragoal create-goals --brief-file <approved-plan>\nskc ultragoal complete-goals\n```\n\n조율된 tmux 워커가 실질적으로 도움이 될 때만 `skc team ...`을 추가하세요.\n\n## Core capabilities\n\n- **추측하기 전에 인터뷰**: `deep-interview`는 모호한 요청을 구체적인 요구사항으로 바꿉니다.\n- **변경하기 전에 계획**: `ralplan`은 코드 변경 전에 접근 방식을 검토합니다.\n- **증거와 함께 실행**: `ultragoal`은 목표, 수정, 점검, 완료 증거를 추적합니다.\n- **유용할 때 병렬화**: `team`은 더 큰 작업을 위해 tmux 기반 워커를 조율합니다.\n- **외부에서 검토 가능하게 유지**: 다른 에이전트 런타임을 패치하지 않고 선택한 저장소나 워크트리에서 실행합니다.\n\n## Workflow surface\n\nSayknow-CLI는 네 가지 기본 워크플로 스킬을 제공합니다:\n\n| Skill            | What it does                                                          |\n| ---------------- | --------------------------------------------------------------------- |\n| `deep-interview` | 계획이나 코드 변경 전에 모호한 요구사항을 명확히 합니다.     |\n| `ralplan`        | 변경 전에 구현 계획을 구축하고 비평합니다.          |\n| `ultragoal`      | 실행, 수정, 검증, 증거를 거쳐 목표를 추적합니다. |\n| `team`           | 병렬 실행이 가치가 있을 때 tmux 기반 워커를 조율합니다.  |\n\n그리고 네 가지 번들 역할 에이전트:\n\n| Agent       | What it does                                       |\n| ----------- | -------------------------------------------------- |\n| `executor`  | 범위가 정해진 구현, 수정, 리팩터.      |\n| `architect` | 읽기 전용 아키텍처 및 코드 리뷰 평가. |\n| `planner`   | 읽기 전용 순서 결정 및 수용 기준.      |\n| `critic`    | 읽기 전용 계획 비평 및 실행 가능성 검토.  |\n\n광범위한 기본 스킬 동물원은 없습니다: SKC는 이 작은 방법을 더 좋게 만들어 개선됩니다.\n\n## Works beside your existing agent or bot\n\n| Tool or bot | Recommended SKC command | Boundary |\n| ----------- | ----------------------- | -------- |\n| Codex CLI | `skc --tmux --worktree <name>` or `skc` | `--worktree`는 SKC가 관리하는 형제 워크트리의 이름을 지정합니다. 기존 경로의 경우 먼저 그곳으로 `cd` 하세요. |\n| Claude Code | `skc --tmux` or `skc --tmux --worktree <name>` | SKC는 Claude Code 확장이 되지 않습니다. |\n| OpenCode | `skc` or `skc --tmux` | 현재로서는 외부 러너 워크플로만 지원합니다. |\n| Claw Code | `skc --tmux --worktree <name>` | SKC는 Claw Code에 설치되거나 그것을 대체하지 않습니다. |\n| External controller / bot | 호환 가능한 구성을 위한 `skc mcp-serve coordinator` 및 `skc setup hermes`, 또는 서브프로세스 워커를 위한 `skc --mode rpc` | MCP/RPC 지원 봇이라면 무엇이든 스크롤백 스크래핑이 아니라 일반 coordinator/RPC 계약을 통해 SKC를 구동합니다. |\n\n일반 서드파티 봇 설정 및 공급자 독립적 스모크에 대해서는 [`docs/bot-integration.md`](docs/bot-integration.md)를 참조하세요. MCP, RPC, ACP, Bridge/HTTPS 표면 전반의 준비도 분류에 대해서는 [`docs/external-control-readiness.md`](docs/external-control-readiness.md)를 참조하세요. 더 낮은 수준의 프로토콜 세부 사항에 대해서는 [`docs/hermes-mcp-bridge.md`](docs/hermes-mcp-bridge.md), [`docs/rpc.md`](docs/rpc.md), [`docs/bridge.md`](docs/bridge.md)를 참조하세요. 원격 운영자 표면 로드맵에 대해서는 [`docs/sayknow-remote.md`](docs/sayknow-remote.md)(웹 스티어링 휠) 및 [`docs/telegram-remote.md`](docs/telegram-remote.md)(Telegram 라이프사이클 버튼)를 참조하세요.\n\n## Configuration\n\n공급자 재시도 예산은 `~/.skc/config.yml`에 있습니다:\n\n```yaml\nretry:\n  requestMaxRetries: 4\n  streamMaxRetries: 100\n  maxRetries: 3\n  maxDelayMs: 300000\n```\n\n`requestMaxRetries`는 스트림이 설정되기 전에 적용됩니다. `streamMaxRetries`는 재생 안전한 일시적 스트림 실패에만 적용됩니다. 잘못된 인증, 지원되지 않는 모델/공급자, 잘못된 형식의 요청, 컨텍스트 오버플로, 사용자 중단, 영구적인 할당량 실패는 즉시 실패(fail-fast)로 유지됩니다.\n\n## TUI identity\n\n기본 TUI 정체성은 SKC **blue-octopus** 테마 — 파란 두족류 마스코트 — 로, 다크 및 라이트 터미널 모두에 적용됩니다. 더 어둡고 고대비 팔레트를 선호하는 사람들을 위해 따뜻한 **red-octopus** 변형도 번들로 제공됩니다. 세 가지 추가 마이그레이션 테마 — `claude-code`, `codex`, `opencode` — 는 쉬운 눈 마이그레이션을 위해 해당 도구들의 모습을 그대로 따르며 Settings 또는 `/theme`에서 선택할 수 있습니다. 명시적인 사용자 테마 설정이 여전히 우선합니다.\n\n### Bundled theme grid\n\nSettings (`Appearance -> Dark theme` / `Light theme`) 또는 `/theme`에서 선택하세요.\n\n| Theme | Visual feel | Best fit |\n| --- | --- | --- |\n| `blue-octopus` | 기본 SKC 정체성 — 촉수 블루 액센트가 있는 파란 문어 팔레트. | 다크 및 라이트 터미널의 기본값. |\n| `red-octopus` | 강한 상태 대비를 가진 따뜻한 빨간 문어 변형. | 고대비 다크 대안. |\n| `claude-code` | 테라코타와 핑크 하이라이트가 있는 Claude Code 영감 다크 팔레트. | SKC를 떠나지 않고 Claude Code 근육 기억을 유지. |\n| `codex` | 더 날카로운 코딩 세션 대비를 가진 선명한 다크 블루그레이 팔레트. | Codex 같은 다크 작업 공간. |\n| `opencode` | 더 강렬한 터미널 액센트를 가진 OpenCode 영감 다크 팔레트. | 번들 선택기에서의 OpenCode 근육 기억. |\n\n## Development\n\n의존성을 설치하고, 네이티브 바인딩을 빌드하고, 로컬 기본값을 설정하세요:\n\n```sh\nbun install\nbun run build:native\nbun run install:defaults\n```\n\n`@sayknow-cli/natives`용 `.node` 바이너리는 gitignore되어 있으며 모든 CLI 호출(`install:defaults`, `dev:link`, 테스트) 전에 필요합니다.\n\n### Canonical: build and link the dev `skc`\n\n전역 `skc` 명령이 **이 체크아웃의 TypeScript 소스**(모든 편집에 즉시 반영되며, 스킬/네이티브가 작동함)를 실행하도록 하려면, `PATH`에 링크하세요:\n\n```sh\nbun install\nbun run dev:link\n```\n\n`dev:link`는 `skc` → `packages/coding-agent/src/cli.ts`를 `~/.local/bin`에 심볼릭 링크하고(`SKC_DEV_LINK_DIR`로 재정의 가능), 그 관리되는 대상을 교체하며, 다른 `skc`가 여전히 `PATH`에서 더 앞쪽에 있어 그것을 가린다면 경고하고 실패하며, `--smoke-test`를 실행하여 `@sayknow-cli/natives`가 로드되는지 확인합니다. 전체 부트스트랩(install + link + `setup defaults`)을 위해서는 `bun run install:dev`를 사용하세요.\n\n당신의 `skc`가 표류했는지(잘못된 소스, 또는 스킬을 로드할 수 없는 컴파일된 바이너리) 언제든지 확인하세요:\n\n```sh\nbun run dev:doctor\n```\n\n> 일상적인 개발에는 컴파일된 바이너리를 **사용하지 마세요**. `bun --cwd=packages/coding-agent run build`는 독립 실행형 `dist/skc`를 생성하지만, `bun build --compile` 바이너리는 `@sayknow-cli/natives`를 동적으로 로드할 수 없으므로 스킬이 `Cannot find module '@sayknow-cli/natives' from '/$bunfs/root/skc'`로 실패합니다. `dev:link`를 통해 소스에서 실행하면 이를 피할 수 있습니다. 릴리스를 검증할 때만 바이너리를 빌드하세요.\n\n링크 없이 소스에서 직접 CLI를 실행하세요:\n\n```sh\nbun packages/coding-agent/src/cli.ts --help\n```\n\n기본 워크플로 정의는 커밋된 `.skc` 사본이 아니라 소스에 있습니다:\n\n```text\npackages/coding-agent/src/defaults/skc/skills/<name>/SKILL.md\npackages/coding-agent/src/prompts/agents/<role>.md\n```\n\n워크플로 정의 또는 리브랜드 표면 변경의 경우, 프로젝트 게이트를 실행하세요:\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-skc-definitions.test.ts\n```\n\n패키지별 맵에 대해서는 [`docs/codebase-overview.md`](docs/codebase-overview.md)를 참조하세요.\n\n## Contributors\n\n기여, 버그 보고, 릴리스 검증은 GitHub Issues와 Pull Request를 통해 환영합니다.\n\n## Inspirations and lineage\n\nSayknow-CLI의 기본 TUI 정체성은 두족류 쌍입니다: 기본값인 blue-octopus와 따뜻한 red-octopus 대안. 또한 해당 도구들에서 옮겨오는 사용자들이 익숙한 모습을 얻도록 팔레트가 그 도구들에서 영감을 받은 `claude-code`, `codex`, `opencode` 마이그레이션 테마를 번들로 제공합니다. 공개 SKC 표면을 의도적으로 집중된 상태로 유지하면서, 작은 에이전트 하니스 계열에서 얻은 교훈을 바탕으로 만들어졌습니다. 역사적 출처 표기는 [`NOTICE.md`](NOTICE.md)에 보관되어 있습니다.\n\n## License\n\nMIT. [`LICENSE`](LICENSE)를 참조하세요.\n",
 	"readme/README.zh.md": "<p align=\"center\">\n  <img src=\"../../assets/hero.png\" alt=\"Sayknow-CLI autonomous coding-agent hero illustration\" width=\"100%\" />\n</p>\n\n<h1 align=\"center\">Sayknow-CLI</h1>\n\n<p align=\"center\">\n  <strong>编码应当如思考般自然。</strong><br />\n  一个专注的编码智能体运行器，面向访谈式需求澄清、经评审的计划、tmux 原生执行与持久化验证。\n</p>\n\n<p align=\"center\">\n  <a href=\"https://github.com/jaybeyond/Sayknow_CLI/releases\"><img alt=\"Release\" src=\"https://img.shields.io/github/v/tag/jaybeyond/Sayknow_CLI?sort=semver&label=release&style=flat-square&color=2f9bff\"></a>\n  <a href=\"LICENSE\"><img alt=\"License: MIT\" src=\"https://img.shields.io/github/license/jaybeyond/Sayknow_CLI?style=flat-square&color=green\"></a>\n  <a href=\"https://github.com/jaybeyond/Sayknow_CLI/stargazers\"><img alt=\"Stars\" src=\"https://img.shields.io/github/stars/jaybeyond/Sayknow_CLI?style=flat-square&color=f5c518\"></a>\n  <a href=\"https://github.com/jaybeyond/Sayknow_CLI/issues\"><img alt=\"Issues\" src=\"https://img.shields.io/github/issues/jaybeyond/Sayknow_CLI?style=flat-square\"></a>\n  <a href=\"https://bun.sh\"><img alt=\"Built with Bun\" src=\"https://img.shields.io/badge/built%20with-Bun-fbf0df?style=flat-square&logo=bun&logoColor=black\"></a>\n  <a href=\"#languages\"><img alt=\"i18n\" src=\"https://img.shields.io/badge/i18n-7%20languages-2f9bff?style=flat-square\"></a>\n</p>\n\n<p align=\"center\">\n  <a href=\"../../README.md\">English</a> ·\n  <a href=\"README.ko.md\">한국어</a> ·\n  <b>中文</b> ·\n  <a href=\"README.ja.md\">日本語</a> ·\n  <a href=\"README.es.md\">Español</a> ·\n  <a href=\"README.fr.md\">Français</a> ·\n  <a href=\"README.de.md\">Deutsch</a>\n</p>\n\n<p align=\"center\">\n  <img src=\"../../assets/character.png\" alt=\"Sayknow-CLI character mascot\" width=\"320\" />\n</p>\n\n> Sayknow-CLI 是一个实验性的、处于 beta 阶段的项目。请预期会有粗糙之处，并在依赖其结果完成重要工作之前先行验证输出。\n\n## Languages\n\n界面已本地化为 **7 种语言**——English、한국어（韩语）、\n中文（简体）、日本語（日语）、Español（西班牙语）、\nFrançais（法语）以及 Deutsch（德语）。首次运行时它会自动检测你的系统区域设置；\n你可以随时在 **Settings → Appearance → Language** 中切换，或者使用例如\n`LANG=ja_JP.UTF-8 skc` 的方式启动。未翻译的字符串会回退到英文，而\n品牌/技术名称（Claude、OpenAI、MCP……）在所有语言环境中均保持原样。\n\n## What is Sayknow-CLI?\n\nSayknow-CLI（`skc`）是一个外部编码智能体框架（harness）。它从你选择的仓库或工作树（worktree）中运行，然后为智能体提供一个精简、明确的工作流界面：\n\n```text\ndeep-interview -> ralplan -> ultragoal\n                         └─ optional team execution when parallel tmux workers help\n```\n\n它有意不做成 Codex CLI、Claude Code、OpenCode 或 Claw Code 的隐藏插件。当你需要结构化的规划、持久化的证据、tmux 支持的工作进程或一个隔离的工作树时，就在这些工具旁边启动 `skc`。\n\n## Install\n\n```sh\nnpm install -g sayknow-cli       # 或：bun install -g sayknow-cli\nskc --version\n```\n\n已内置 macOS·Linux·Windows 的预编译原生模块，无需 Rust 工具链或构建步骤。更新：`npm install -g sayknow-cli@latest` 或在终端运行 `skc update`。\n\n> 如果你之前是从源码（git clone）安装的，只需一次性切换：`rm -f ~/.local/bin/skc && npm install -g sayknow-cli`。源码/开发安装请参见[英文 README](../../README.md#install-from-source-development)。\n\n## Quick start\n\n```sh\n# Run directly in the current checkout\nskc\n\n# Use a tmux-backed leader session\nskc --tmux\n\n# Use an isolated worktree for risky or reviewable work\n# --worktree takes an optional branch-like name, not a filesystem path.\nskc --tmux --worktree my-task-branch\n\n# If you already created a worktree directory, launch from that directory instead.\ncd ../my-task-worktree && skc --tmux\n```\n\n在 SKC 会话内部，使用公共工作流界面：\n\n```text\n/skill:deep-interview clarify ambiguous requirements\n/skill:ralplan build and critique the implementation plan\nskc ultragoal create-goals --brief-file <approved-plan>\nskc ultragoal complete-goals\n```\n\n仅当协同的 tmux 工作进程能带来实质性帮助时，才加上 `skc team ...`。\n\n## Core capabilities\n\n- **先访谈，不靠猜**：`deep-interview` 把模糊的请求转化为具体的需求。\n- **先规划，再变更**：`ralplan` 在代码改动之前评审方案。\n- **带证据地执行**：`ultragoal` 跟踪目标、修订、检查以及完成证据。\n- **在有用时并行化**：`team` 为较大的任务协调 tmux 支持的工作进程。\n- **保持外部化且可评审**：从所选的仓库或工作树中运行，无需给另一个智能体运行时打补丁。\n\n## Workflow surface\n\nSayknow-CLI 内置四项默认工作流技能：\n\n| Skill            | What it does                                                          |\n| ---------------- | --------------------------------------------------------------------- |\n| `deep-interview` | 在规划或代码改动之前澄清模糊的需求。     |\n| `ralplan`        | 在变更之前构建并评审实现计划。          |\n| `ultragoal`      | 在执行、修订、验证与证据收集的全过程中跟踪目标。 |\n| `team`           | 当并行执行值得时，协调 tmux 支持的工作进程。  |\n\n以及四个捆绑的角色智能体：\n\n| Agent       | What it does                                       |\n| ----------- | -------------------------------------------------- |\n| `executor`  | 有边界的实现、修复与重构。      |\n| `architect` | 只读的架构与代码评审评估。 |\n| `planner`   | 只读的排序与验收标准。 |\n| `critic`    | 只读的计划评审与可执行性审查。  |\n\n没有庞杂的默认技能堆砌：SKC 通过把这一精简方法做得更好来持续改进。\n\n## Works beside your existing agent or bot\n\n| Tool or bot | Recommended SKC command | Boundary |\n| ----------- | ----------------------- | -------- |\n| Codex CLI | `skc --tmux --worktree <name>` or `skc` | `--worktree` 指定一个由 SKC 管理的同级工作树；对于已存在的路径，请先 `cd` 到那里。 |\n| Claude Code | `skc --tmux` or `skc --tmux --worktree <name>` | SKC 不会成为 Claude Code 的扩展。 |\n| OpenCode | `skc` or `skc --tmux` | 目前仅支持外部运行器（external-runner）工作流。 |\n| Claw Code | `skc --tmux --worktree <name>` | SKC 不会安装到 Claw Code 中，也不会替代它。 |\n| External controller / bot | `skc mcp-serve coordinator` plus `skc setup hermes` for compatible config, or `skc --mode rpc` for a subprocess worker | 任何具备 MCP/RPC 能力的 bot 都通过通用的 coordinator/RPC 契约来驱动 SKC，而非抓取滚动回显（scrollback scraping）。 |\n\n关于通用第三方 bot 的设置以及与提供商无关的冒烟测试，请参阅 [`docs/bot-integration.md`](docs/bot-integration.md)。关于在 MCP、RPC、ACP 与 Bridge/HTTPS 各界面上的就绪度分级，请参阅 [`docs/external-control-readiness.md`](docs/external-control-readiness.md)。关于更底层的协议细节，请参阅 [`docs/hermes-mcp-bridge.md`](docs/hermes-mcp-bridge.md)、[`docs/rpc.md`](docs/rpc.md) 以及 [`docs/bridge.md`](docs/bridge.md)。关于远程操作员界面的路线图，请参阅 [`docs/sayknow-remote.md`](docs/sayknow-remote.md)（网页方向盘）以及 [`docs/telegram-remote.md`](docs/telegram-remote.md)（Telegram 生命周期按钮）。\n\n## Configuration\n\n提供商重试预算位于 `~/.skc/config.yml`：\n\n```yaml\nretry:\n  requestMaxRetries: 4\n  streamMaxRetries: 100\n  maxRetries: 3\n  maxDelayMs: 300000\n```\n\n`requestMaxRetries` 在流（stream）建立之前生效。`streamMaxRetries` 仅适用于可安全重放的瞬时流失败。无效的认证、不受支持的模型/提供商、格式错误的请求、上下文溢出、用户中止以及永久性配额失败仍然保持快速失败（fail-fast）。\n\n## TUI identity\n\n默认的 TUI 标识是 SKC 的 **blue-octopus**（蓝章鱼）主题——蓝色头足类吉祥物——同时适用于深色和浅色终端。还捆绑了一个暖色调的 **red-octopus**（红章鱼）变体，供偏好更深、高对比度配色的用户使用。另有三个迁移主题——`claude-code`、`codex` 和 `opencode`——分别复刻了这些工具的外观，以便于视觉迁移，可从 Settings 或 `/theme` 中选择。显式的用户主题设置仍然优先生效。\n\n### Bundled theme grid\n\n从 Settings（`Appearance -> Dark theme` / `Light theme`）或 `/theme` 中选择。\n\n| Theme | Visual feel | Best fit |\n| --- | --- | --- |\n| `blue-octopus` | 默认 SKC 标识——蓝章鱼配色，带触手蓝点缀。 | 深色和浅色终端的默认主题。 |\n| `red-octopus` | 暖色调红章鱼变体，状态对比强烈。 | 高对比度的深色替代方案。 |\n| `claude-code` | 受 Claude Code 启发的深色配色，带赤陶色和粉色高光。 | 在不离开 SKC 的情况下保留 Claude Code 的肌肉记忆。 |\n| `codex` | 清爽的深蓝灰配色，编码会话对比更锐利。 | 类似 Codex 的深色工作区。 |\n| `opencode` | 受 OpenCode 启发的深色配色，终端点缀更鲜明。 | 在捆绑选择器中保留 OpenCode 的肌肉记忆。 |\n\n## Development\n\n安装依赖、构建原生绑定，并设置本地默认值：\n\n```sh\nbun install\nbun run build:native\nbun run install:defaults\n```\n\n`@sayknow-cli/natives` 的 `.node` 二进制文件已被 gitignore，且在任何 CLI 调用（`install:defaults`、`dev:link`、测试）之前都是必需的。\n\n### Canonical: build and link the dev `skc`\n\n要让全局 `skc` 命令运行**此检出的 TypeScript 源码**（对每一次编辑都即时生效，且技能/原生绑定均可用），请把它链接到你的 `PATH`：\n\n```sh\nbun install\nbun run dev:link\n```\n\n`dev:link` 会把 `skc` → `packages/coding-agent/src/cli.ts` 软链接到 `~/.local/bin`（可用 `SKC_DEV_LINK_DIR` 覆盖），替换该受管目标，如果另一个 `skc` 仍在 `PATH` 上更靠前地遮蔽它则会发出警告并失败，并运行 `--smoke-test` 以确认 `@sayknow-cli/natives` 能够加载。使用 `bun run install:dev` 进行完整的引导（install + link + `setup defaults`）。\n\n随时检查你的 `skc` 是否已经漂移（源码错误，或一个无法加载技能的已编译二进制文件）：\n\n```sh\nbun run dev:doctor\n```\n\n> 在日常开发中**不要**使用已编译的二进制文件。`bun --cwd=packages/coding-agent run build` 会产出一个独立的 `dist/skc`，但 `bun build --compile` 生成的二进制无法动态加载 `@sayknow-cli/natives`，因此技能会以 `Cannot find module '@sayknow-cli/natives' from '/$bunfs/root/skc'` 失败。通过 `dev:link` 从源码运行可避免此问题。仅在验证发布版本时才构建该二进制文件。\n\n不进行链接，直接从源码运行 CLI：\n\n```sh\nbun packages/coding-agent/src/cli.ts --help\n```\n\n默认工作流定义存放在源码中，而非已提交的 `.skc` 副本：\n\n```text\npackages/coding-agent/src/defaults/skc/skills/<name>/SKILL.md\npackages/coding-agent/src/prompts/agents/<role>.md\n```\n\n对于工作流定义或品牌重塑界面（rebrand-surface）的改动，请运行项目门禁（gates）：\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-skc-definitions.test.ts\n```\n\n关于逐包（package-by-package）的对照图，请参阅 [`docs/codebase-overview.md`](docs/codebase-overview.md)。\n\n## Contributors\n\n欢迎通过 GitHub Issues 和 Pull Requests 进行贡献、提交错误报告以及参与发布验证。\n\n## Inspirations and lineage\n\nSayknow-CLI 默认的 TUI 标识是这对头足类：blue-octopus 作为默认，搭配一个暖色调的 red-octopus 备选。它还捆绑了 `claude-code`、`codex` 和 `opencode` 迁移主题，其配色受这些工具启发，以便从它们迁移过来的用户能获得熟悉的外观。它在一个小型智能体框架家族的经验之上构建，同时有意保持公共 SKC 界面的专注。历史归属保留在 [`NOTICE.md`](NOTICE.md) 中。\n\n## License\n\nMIT。参见 [`LICENSE`](LICENSE)。\n",
 	"render-mermaid.md": "# RenderMermaid\n\n`RenderMermaid` is an optional built-in tool that renders Mermaid source to terminal-friendly text.\n\n## Enable it\n\nDisabled by default. Turn it on in `/settings` under **Tools → Render Mermaid**, or in `~/.skc/agent/config.yml`:\n\n```yaml\nrenderMermaid:\n  enabled: true\n```\n\n## What it does\n\n- Tool name: `render_mermaid`\n- Input: Mermaid source in the required `mermaid` field\n- Output: rendered ASCII/Unicode text, not SVG or PNG\n- Storage: when artifact storage is available, the full render is also saved as an `artifact://...`\n\nThere are no model-specific or environment-variable prerequisites. Once enabled, any model that can call built-in tools can use it.\n\n## Parameters\n\n```json\n{\n  \"mermaid\": \"graph TD\\n  A[Start] --> B[Stop]\",\n  \"config\": {\n    \"useAscii\": false,\n    \"paddingX\": 2,\n    \"paddingY\": 2,\n    \"boxBorderPadding\": 0\n  }\n}\n```\n\nAvailable `config` fields:\n\n- `useAscii` — `true` for plain ASCII, `false` for Unicode box-drawing characters (default and usually more readable)\n- `paddingX` — horizontal spacing between nodes\n- `paddingY` — vertical spacing between nodes\n- `boxBorderPadding` — inner padding inside node boxes\n\n## Current limitations\n\n`RenderMermaid` uses the `beautiful-mermaid` ASCII renderer. It works best for flowcharts and small diagrams.\n\nComplex sequence diagrams, especially with `alt` / `else` blocks, can become very wide in a terminal. That is current renderer behavior, not a provider or model configuration problem.\n\nIf a sequence diagram is hard to read:\n\n1. Keep Unicode output (`useAscii: false`)\n2. Reduce spacing with a tighter config such as `paddingX: 2`, `paddingY: 2`, `boxBorderPadding: 0`\n3. Prefer smaller sub-diagrams over one large sequence diagram\n4. Open the saved artifact if the inline preview is truncated in the TUI\n\n## Example\n\nInput:\n\n```mermaid\ngraph TD\n  A[Start] --> B{Decision}\n  B -->|Yes| C[Action]\n  B -->|No| D[End]\n```\n\nTypical result:\n\n```text\n┌─────┐\n│Start│\n└─────┘\n   │\n   ▼\n┌────────┐\n│Decision│\n└────────┘\n```\n",
+	"research-plan-ledger.md": "# Research plan items and evidence ledger\n\nResearch/deep-research workflows need a planning contract that is stronger than an execution-order checklist. A plan item should name the claim under investigation, the uncertainty around it, what evidence is required, what counterexamples would falsify it, and how a verifier should handle source conflicts.\n\nThis document defines the public product-facing spike for issue #932. It intentionally avoids private operator, session, channel, and routing internals.\n\n## Research plan item schema\n\n```ts\ntype ResearchPlanConfidence = \"low\" | \"medium\" | \"high\";\n\ntype ResearchPlanItem = {\n  claim: string;\n  confidence: ResearchPlanConfidence;\n  unknowns: string[];\n  evidenceNeeded: string[];\n  counterexampleQueries: string[];\n  sourceConflictPolicy: string;\n  dropCondition: string;\n  verifierChecks: string[];\n};\n```\n\nField intent:\n\n- `claim`: The smallest claim that can survive or fail verification.\n- `confidence`: Planner's initial confidence before evidence collection.\n- `unknowns`: Known gaps the final answer must resolve or explicitly carry forward.\n- `evidenceNeeded`: Evidence workers must collect before the claim can be accepted.\n- `counterexampleQueries`: Directed search prompts for evidence that would weaken or falsify the claim.\n- `sourceConflictPolicy`: How the verifier treats conflicting sources, stale sources, or mismatched methodology.\n- `dropCondition`: The explicit condition that removes this claim from the final answer.\n- `verifierChecks`: Checklist the verifier applies before accepting the claim.\n\n## Evidence ledger schema\n\n```ts\ntype ResearchEvidenceVerdict = \"support\" | \"contradict\" | \"uncertain\";\n\ntype ResearchEvidenceEntry = {\n  claim: string;\n  source: string;\n  confidence: ResearchPlanConfidence;\n  verdict: ResearchEvidenceVerdict;\n  notes?: string;\n};\n\ntype ResearchLedgerVerdict = {\n  claim: string;\n  finalVerdict: \"accepted\" | \"rejected\" | \"uncertain\";\n  survivingSources: ResearchEvidenceEntry[];\n  rejectReason?: string;\n  unresolvedUnknowns: string[];\n};\n```\n\nThe ledger is claim-centric. Workers add evidence entries against plan-item claims; the verifier reduces those entries into a final verdict. Accepted claims can be cited in the final answer. Rejected claims are named with `rejectReason`. Uncertain claims are either excluded or marked explicitly as unresolved.\n\n## Ralplan/research workflow shape\n\n1. Planner emits `ResearchPlanItem[]` alongside the normal plan narrative when the task is research-heavy.\n2. Workers gather independent evidence for each item, including counterexample-oriented searches.\n3. Verifier checks contradictions, source quality, stale information, and unresolved uncertainty using the item's `verifierChecks`, `sourceConflictPolicy`, and `dropCondition`.\n4. The final answer cites accepted claims, lists rejected claims with reasons, and marks any surviving uncertainty.\n\n## Example\n\n```ts\nconst item: ResearchPlanItem = {\n  claim: \"Model X reduces latency by 30% on production-like workloads\",\n  confidence: \"medium\",\n  unknowns: [\"production workload mix\"],\n  evidenceNeeded: [\"benchmark with production-like fixture\", \"baseline comparison\"],\n  counterexampleQueries: [\"regression on long-context workload\", \"cold-start latency increase\"],\n  sourceConflictPolicy: \"Reject the claim when any credible counterexample contradicts the benchmark.\",\n  dropCondition: \"Drop if a counterexample contradicts the claim or key unknowns remain unresolved.\",\n  verifierChecks: [\"check source freshness\", \"compare benchmark harness\", \"inspect counterexample evidence\"],\n};\n```\n\nIf the ledger contains a supporting benchmark and a credible long-context counterexample, the verifier rejects the broad claim instead of letting a plausible summary survive by vibes.\n\n## Current spike\n\nThe first implementation spike lives in `packages/coding-agent/src/research-plan/ledger.ts` and provides:\n\n- TypeScript interfaces for research plan items, evidence entries, and final verdicts.\n- Validators for product-facing plan/evidence objects.\n- A deterministic verifier helper that rejects plausible claims when counterexample/source-conflict/drop-condition evidence applies.\n- Regression tests in `packages/coding-agent/test/research-plan-ledger.test.ts`.\n\nFuture runtime integration can make `/skill:ralplan` emit these structures as a fenced JSON block or structured sidecar in the persisted ralplan artifact. The spike keeps the schema independent from private session state so it can be exposed in docs and tests safely.\n",
 	"resolve-tool-runtime.md": "# Resolve tool runtime internals\n\nThis document explains how preview/apply workflows are modeled in coding-agent and how built-in or custom tools can participate via the tool-choice queue and `pushPendingAction`.\n\n## Scope and key files\n\n- [`src/tools/resolve.ts`](../packages/coding-agent/src/tools/resolve.ts)\n- [`src/tools/ast-edit.ts`](../packages/coding-agent/src/tools/ast-edit.ts)\n- [`src/extensibility/custom-tools/types.ts`](../packages/coding-agent/src/extensibility/custom-tools/types.ts)\n- [`src/extensibility/custom-tools/loader.ts`](../packages/coding-agent/src/extensibility/custom-tools/loader.ts)\n- [`src/sdk.ts`](../packages/coding-agent/src/sdk.ts)\n\n## What `resolve` does\n\n`resolve` is a hidden tool that finalizes a pending preview action.\n\n- `action: \"apply\"` executes the queued action's `apply(reason)` callback and returns that result with resolve metadata.\n- `action: \"discard\"` invokes `reject(reason)` if provided; otherwise returns `Discarded: <label>. Reason: <reason>`.\n\nIf no pending action exists, `resolve` fails with:\n\n- `No pending action to resolve. Nothing to apply or discard.`\n\n## Pending actions use the tool-choice queue\n\nPreview producers call `queueResolveHandler(...)`, which pushes a one-shot forced `resolve` directive onto the session tool-choice queue and adds a `resolve-reminder` steering message.\n\nRuntime behavior:\n\n- the queued handler owns the pending `apply`/`reject` callbacks,\n- `resolve` looks up the current queue invoker with `session.peekQueueInvoker()`,\n- if the model rejects the forced tool choice, the queue directive is requeued,\n- `resolve` does not maintain a separate pending-action stack.\n\nMultiple pending previews therefore follow the active tool-choice queue ordering, not an independent pending-action store.\n\n## Built-in producer example (`ast_edit`)\n\n`ast_edit` previews structural replacements first. When the preview has replacements and is not applied yet, it queues a resolve handler that contains:\n\n- label (human-readable summary)\n- `sourceToolName` (`ast_edit`)\n- `apply(reason: string)` callback that reruns AST edit with `dryRun: false`\n\n`resolve(action=\"apply\", reason=\"...\")` passes `reason` into this callback.\n\n## Custom tools: `pushPendingAction`\n\nCustom tools can register resolve-compatible pending actions through `CustomToolAPI.pushPendingAction(...)`. The custom tool loader forwards these actions to `queueResolveHandler(...)` when that hook is available.\n\n`CustomToolPendingAction`:\n\n- `label: string` (required)\n- `apply(reason: string): Promise<AgentToolResult<unknown>>` (required) — invoked on apply; `reason` is the string passed to `resolve`\n- `reject?(reason: string): Promise<AgentToolResult<unknown> | undefined>` (optional) — invoked on discard; return value replaces the default \"Discarded\" message if provided\n- `details?: unknown` exists on the public custom-tool type but is not currently forwarded by the loader into resolve metadata\n- `sourceToolName?: string` (optional, defaults to `\"custom_tool\"`)\n\n### Minimal usage example\n\n```ts\nimport type { CustomToolFactory } from \"@sayknow-cli/coding-agent\";\n\nconst factory: CustomToolFactory = (pi) => ({\n  name: \"batch_rename_preview\",\n  label: \"Batch Rename Preview\",\n  description: \"Previews renames and defers commit to resolve\",\n  parameters: pi.zod.object({\n    files: pi.zod.array(pi.zod.string()),\n  }),\n\n  async execute(_toolCallId, params) {\n    const previewSummary = `Prepared rename plan for ${params.files.length} files`;\n\n    pi.pushPendingAction({\n      label: `Batch rename: ${params.files.length} files`,\n      sourceToolName: \"batch_rename_preview\",\n      apply: async (reason) => {\n        // apply writes here\n        return {\n          content: [\n            { type: \"text\", text: `Applied batch rename. Reason: ${reason}` },\n          ],\n        };\n      },\n      reject: async (reason) => {\n        // optional: cleanup or notify on discard\n        return {\n          content: [\n            { type: \"text\", text: `Discarded batch rename. Reason: ${reason}` },\n          ],\n        };\n      },\n    });\n\n    return {\n      content: [\n        {\n          type: \"text\",\n          text: `${previewSummary}. Call resolve to apply or discard.`,\n        },\n      ],\n    };\n  },\n});\n\nexport default factory;\n```\n\n## Runtime availability and failures\n\n`pushPendingAction` is wired by the custom tool loader through the active session's resolve queue hook.\n\nIf the runtime did not provide the resolve queue hook, `pushPendingAction` throws:\n\n- `Pending action store unavailable for custom tools in this runtime.`\n\n## Tool-choice behavior\n\nWhen `queueResolveHandler(...)` registers a preview, the agent runtime forces a one-shot `resolve` tool choice so pending previews are explicitly finalized before normal tool flow continues.\n\n## Developer guidance\n\n- Use pending actions only for destructive or high-impact operations that should support explicit apply/discard.\n- Keep `label` concise and specific; it is shown in resolve renderer output.\n- Ensure `apply(reason)` is deterministic and idempotent enough for one-shot execution; `reason` is informational and should not change behavior.\n- Implement `reject(reason)` when the discard needs cleanup (temp state, locks, notifications); omit it for stateless previews where the default message suffices.\n- If your tool can stage multiple previews, remember they are mediated by the tool-choice queue rather than a separate pending-action stack.\n",
 	"rpc.md": "# RPC Protocol Reference\n\nRPC mode runs the coding agent as a newline-delimited JSON protocol over stdio.\n\n- **stdin**: commands (`RpcCommand`), `workflow_gate_response`, extension UI responses, and host-tool updates/results\n- **stdout**: a ready frame, command responses (`RpcResponse`), session/agent events, `workflow_gate`, extension UI requests, host-tool requests/cancellations\n\nPrimary implementation:\n\n- `src/modes/rpc/rpc-mode.ts`\n- `src/modes/rpc/rpc-types.ts`\n- `src/session/agent-session.ts`\n- `packages/agent/src/agent.ts`\n- `packages/agent/src/agent-loop.ts`\n\n## Startup\n\n```bash\nskc --mode rpc [regular CLI options]\n```\n\nBehavior notes:\n\n- `@file` CLI arguments are rejected in RPC mode.\n- RPC mode disables automatic session title generation by default to avoid an extra model call.\n- RPC mode resets workflow-altering `todo.*`, `task.*`, `async.*`, and `bash.autoBackground.*` settings to their built-in defaults instead of inheriting user overrides.\n- The process reads stdin as JSONL (`readJsonl(Bun.stdin.stream())`).\n- At startup it writes `{ \"type\": \"ready\" }` before processing commands.\n- When stdin closes, pending host-tool calls are rejected and the process exits with code `0`.\n- Responses/events are written as one JSON object per line.\n\n## Transport and Framing\n\nEach frame is a single JSON object followed by `\\n`.\n\nAgent session events are wrapped in canonical `event` frames. Ready, response, workflow gate, extension UI/error, host tool, and host URI frames remain flat.\n\n### Outbound frame categories (stdout)\n\n1. Ready frame (`{ type: \"ready\" }`)\n2. `RpcResponse` (`{ type: \"response\", ... }`)\n3. Canonical event frames wrapping `AgentSessionEvent` objects (`{ type: \"event\", ... }`)\n4. `RpcWorkflowGateEvent` (`{ type: \"workflow_gate\", ... }`)\n5. `RpcExtensionUIRequest` (`{ type: \"extension_ui_request\", ... }`)\n6. Host tool requests/cancellations (`host_tool_call`, `host_tool_cancel`)\n7. Host URI requests/cancellations (`host_uri_request`, `host_uri_cancel`)\n8. Extension errors (`{ type: \"extension_error\", extensionPath, event, error }`)\n\n### Inbound frame categories (stdin)\n\n1. `RpcCommand`\n2. `RpcWorkflowGateResponse` (`{ type: \"workflow_gate_response\", gate_id, answer }`)\n3. `RpcExtensionUIResponse` (`{ type: \"extension_ui_response\", ... }`)\n4. Host tool updates/results (`host_tool_update`, `host_tool_result`)\n5. Host URI results (`host_uri_result`)\n\n## Request/Response Correlation\n\nAll commands accept optional `id?: string`.\n\n- If provided, normal command responses echo the same `id`.\n- `RpcClient` relies on this for pending-request resolution.\n\nImportant edge behavior from runtime:\n\n- Unknown command responses are emitted with `id: undefined` (even if the request had an `id`).\n- Parse/handler exceptions in the input loop emit `command: \"parse\"` with `id: undefined`.\n- `prompt` and `abort_and_prompt` return immediate success, then may emit a later error response with the **same** id if async prompt scheduling fails.\n\n## Command Schema (canonical)\n\n`RpcCommand` is defined in `src/modes/rpc/rpc-types.ts`:\n\n### Prompting\n\n- `{ id?, type: \"prompt\", message: string, images?: ImageContent[], streamingBehavior?: \"steer\" | \"followUp\" }`\n- `{ id?, type: \"steer\", message: string, images?: ImageContent[] }`\n- `{ id?, type: \"follow_up\", message: string, images?: ImageContent[] }`\n- `{ id?, type: \"abort\" }`\n- `{ id?, type: \"abort_and_prompt\", message: string, images?: ImageContent[] }`\n- `{ id?, type: \"new_session\", parentSession?: string }`\n\n### State\n\n- `{ id?, type: \"get_state\", include?: (\"tools\" | \"dumpTools\" | \"systemPrompt\")[] }` (`dumpTools` is accepted as an alias for the older response field name.)\n- `{ id?, type: \"set_todos\", phases: TodoPhase[] }`\n- `{ id?, type: \"set_host_tools\", tools: RpcHostToolDefinition[] }`\n- `{ id?, type: \"set_host_uri_schemes\", schemes: RpcHostUriSchemeDefinition[] }`\n- `{ id?, type: \"workflow_gate_response\", gate_id: string, answer: unknown }`\n\n### Model\n\n- `{ id?, type: \"set_model\", provider: string, modelId: string }`\n- `{ id?, type: \"cycle_model\" }`\n- `{ id?, type: \"get_available_models\" }`\n\n### Thinking\n\n- `{ id?, type: \"set_thinking_level\", level: ThinkingLevel }`\n- `{ id?, type: \"cycle_thinking_level\" }`\n\n### Queue modes\n\n- `{ id?, type: \"set_steering_mode\", mode: \"all\" | \"one-at-a-time\" }`\n- `{ id?, type: \"set_follow_up_mode\", mode: \"all\" | \"one-at-a-time\" }`\n- `{ id?, type: \"set_interrupt_mode\", mode: \"immediate\" | \"wait\" }`\n\n### Compaction\n\n- `{ id?, type: \"compact\", customInstructions?: string }`\n- `{ id?, type: \"set_auto_compaction\", enabled: boolean }`\n\n### Retry\n\n- `{ id?, type: \"set_auto_retry\", enabled: boolean }`\n- `{ id?, type: \"abort_retry\" }`\n\n### Bash\n\n- `{ id?, type: \"bash\", command: string }`\n- `{ id?, type: \"abort_bash\" }`\n\n### Session\n\n- `{ id?, type: \"get_session_stats\" }`\n- `{ id?, type: \"export_html\", outputPath?: string }`\n- `{ id?, type: \"switch_session\", sessionPath: string }`\n- `{ id?, type: \"branch\", entryId: string }`\n- `{ id?, type: \"get_branch_messages\" }`\n- `{ id?, type: \"get_last_assistant_text\" }`\n- `{ id?, type: \"set_session_name\", name: string }`\n\n### Messages\n\n- `{ id?, type: \"get_messages\" }`\n\n## Response Schema\n\nAll command results use `RpcResponse`:\n\n- Success: `{ id?, type: \"response\", command: <command>, success: true, data?: ... }`\n- Failure: `{ id?, type: \"response\", command: string, success: false, error: string | object }`; typed control-plane failures use object-valued errors such as `{ \"code\": \"scope_denied\", ... }`.\n\nData payloads are command-specific and defined in `rpc-types.ts`.\n\n\nBy default, `get_state` omits large static fields. Request `include: [\"tools\"]` to include `dumpTools`, `include: [\"systemPrompt\"]` to include `systemPrompt`, or both when a host needs a one-shot full session dump.\n### `get_state` payload\n\n```json\n{\n  \"model\": { \"provider\": \"...\", \"id\": \"...\" },\n  \"thinkingLevel\": \"off|minimal|low|medium|high|xhigh\",\n  \"isStreaming\": false,\n  \"isCompacting\": false,\n  \"steeringMode\": \"all|one-at-a-time\",\n  \"followUpMode\": \"all|one-at-a-time\",\n  \"interruptMode\": \"immediate|wait\",\n  \"sessionFile\": \"...\",\n  \"sessionId\": \"...\",\n  \"sessionName\": \"...\",\n  \"autoCompactionEnabled\": true,\n  \"messageCount\": 0,\n  \"queuedMessageCount\": 0,\n  \"todoPhases\": [\n    {\n      \"id\": \"phase-1\",\n      \"name\": \"Todos\",\n      \"tasks\": [\n        {\n          \"id\": \"task-1\",\n          \"content\": \"Map the tool surface\",\n          \"status\": \"in_progress\"\n        }\n      ]\n    }\n  ],\n  \"contextUsage\": {\n    \"tokens\": 0,\n    \"contextWindow\": 200000,\n    \"percent\": 0\n  }\n  // Optional with include: [\"systemPrompt\"]:\n  // \"systemPrompt\": [\"...\"],\n  // Optional with include: [\"tools\"] (or [\"dumpTools\"]):\n  // \"dumpTools\": [\n  //   { \"name\": \"read\", \"description\": \"Read files and URLs\", \"parameters\": {} }\n  // ]\n}\n```\n\n### `set_todos` payload\n\nReplaces the in-memory todo state for the current session and returns the normalized phase list:\n\n```json\n{\n  \"id\": \"req_2\",\n  \"type\": \"set_todos\",\n  \"phases\": [\n    {\n      \"id\": \"phase-1\",\n      \"name\": \"Evaluation\",\n      \"tasks\": [\n        {\n          \"id\": \"task-1\",\n          \"content\": \"Map the read tool surface\",\n          \"status\": \"in_progress\"\n        },\n        {\n          \"id\": \"task-2\",\n          \"content\": \"Exercise edit operations\",\n          \"status\": \"pending\"\n        }\n      ]\n    }\n  ]\n}\n```\n\nThis is useful for hosts that want to pre-seed a plan before the first prompt.\n\n### `set_host_tools` payload\n\nReplaces the current set of host-owned tools that the RPC server may call back\ninto over stdio:\n\n```json\n{\n  \"id\": \"req_3\",\n  \"type\": \"set_host_tools\",\n  \"tools\": [\n    {\n      \"name\": \"echo_host\",\n      \"label\": \"Echo Host\",\n      \"description\": \"Echo a value from the embedding host\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"message\": { \"type\": \"string\" }\n        },\n        \"required\": [\"message\"],\n        \"additionalProperties\": false\n      }\n    }\n  ]\n}\n```\n\nThe response payload is:\n\n```json\n{\n  \"toolNames\": [\"echo_host\"]\n}\n```\n\nThese tools are added to the active session tool registry before the next model\ncall. Re-sending `set_host_tools` replaces the previous host-owned set.\n\n### `set_host_uri_schemes` payload\n\nReplaces the current set of host-owned URL schemes the RPC server should\ndispatch reads/writes through:\n\n```json\n{\n  \"id\": \"req_4\",\n  \"type\": \"set_host_uri_schemes\",\n  \"schemes\": [\n    {\n      \"scheme\": \"db\",\n      \"description\": \"Virtual db row files\",\n      \"writable\": true,\n      \"immutable\": false\n    }\n  ]\n}\n```\n\nThe response payload is:\n\n```json\n{\n  \"schemes\": [\"db\"]\n}\n```\n\nSchemes are case-insensitive on the wire and normalized to lowercase before\nthe response is sent. Re-sending `set_host_uri_schemes` replaces the entire\nprevious set — schemes missing from the new list are unregistered.\n\n## Event Stream Schema\n\nRPC mode forwards `AgentSessionEvent` objects from `AgentSession.subscribe(...)` as canonical `event` frames:\n\n```json\n{\n  \"type\": \"event\",\n  \"protocol_version\": 2,\n  \"session_id\": \"...\",\n  \"seq\": 1,\n  \"frame_id\": \"...\",\n  \"payload\": {\n    \"event_type\": \"agent_start\",\n    \"event\": { \"type\": \"agent_start\" }\n  }\n}\n```\n\n`seq` is monotonic per session starting at `1`. `payload.event_type` duplicates the inner event `type` for routing, and `payload.event` contains the original `AgentSessionEvent` fields.\n\nCommon inner event types:\n\n- `agent_start`, `agent_end`\n- `turn_start`, `turn_end`\n- `message_start`, `message_update`, `message_end`\n- `tool_execution_start`, `tool_execution_update`, `tool_execution_end`\n- `auto_compaction_start`, `auto_compaction_end`\n- `auto_retry_start`, `auto_retry_end`\n- `ttsr_triggered`\n- `todo_reminder`\n- `todo_auto_clear`\n\nNon-event stdout categories remain flat: `ready`, `response`, `workflow_gate`, `extension_ui_request`, `extension_error`, `host_tool_call`, `host_tool_cancel`, `host_uri_request`, and `host_uri_cancel`.\n\n`message_update` includes streaming deltas in the inner event's `assistantMessageEvent` (text/thinking/toolcall deltas).\n\nExtension runner errors are emitted separately as flat frames:\n\n```json\n{\n  \"type\": \"extension_error\",\n  \"extensionPath\": \"...\",\n  \"event\": \"...\",\n  \"error\": \"...\"\n}\n```\n\n## Prompt/Queue Concurrency and Ordering\n\nThis is the most important operational behavior.\n\n### Immediate ack vs completion\n\n`prompt` and `abort_and_prompt` are **acknowledged immediately**:\n\n```json\n{ \"id\": \"req_1\", \"type\": \"response\", \"command\": \"prompt\", \"success\": true }\n```\n\nThat means:\n\n- command acceptance != run completion\n- final completion is observed via `agent_end`\n\n### While streaming\n\n`AgentSession.prompt()` requires `streamingBehavior` during active streaming:\n\n- `\"steer\"` => queued steering message (interrupt path)\n- `\"followUp\"` => queued follow-up message (post-turn path)\n\nIf omitted during streaming, prompt fails.\n\n### Queue defaults\n\nFrom `packages/agent/src/agent.ts` defaults:\n\n- `steeringMode`: `\"one-at-a-time\"`\n- `followUpMode`: `\"one-at-a-time\"`\n- `interruptMode`: `\"immediate\"`\n\n### Mode semantics\n\n- `set_steering_mode` / `set_follow_up_mode`\n  - `\"one-at-a-time\"`: dequeue one queued message per turn\n  - `\"all\"`: dequeue entire queue at once\n- `set_interrupt_mode`\n  - `\"immediate\"`: tool execution checks steering between tool calls; pending steering can abort remaining tool calls in the turn\n  - `\"wait\"`: defer steering until turn completion\n\n## Workflow Gate Sub-Protocol\n\nInteractive workflow stages emit a machine-addressable gate frame before the legacy extension UI request:\n\n```json\n{\n  \"type\": \"workflow_gate\",\n  \"gate_id\": \"wg_4845_ralplan_000001\",\n  \"stage\": \"ralplan\",\n  \"kind\": \"approval\",\n  \"schema\": { \"type\": \"string\", \"enum\": [\"approve\", \"request-changes\", \"reject\"] },\n  \"schema_hash\": \"<sha256 of canonical schema>\",\n  \"options\": [{ \"value\": \"approve\", \"label\": \"Approve execution\" }],\n  \"context\": { \"title\": \"Approve plan?\", \"summary\": \"…\" },\n  \"created_at\": \"2026-06-05T05:00:00.000Z\",\n  \"required\": true\n}\n```\n\nFields:\n\n- `gate_id`: run-scoped, monotonic, stable id of the form `wg_<run>_<stage>_NNNNNN`.\n- `stage`: one of `\"deep-interview\"`, `\"ralplan\"`, or `\"ultragoal\"` (`team` is reserved and rejected for v1).\n- `kind`: one of `\"question\"`, `\"approval\"`, or `\"execution\"`.\n- `schema`: documented JSON Schema 2020-12 subset for the expected answer; `schema_hash` is the canonical hash of `schema` and equals the server-side validation hash.\n- `options`: optional `RpcWorkflowGateOption[]` (`{ value, label, description? }`), emitted for select-style gates.\n- `context`: `RpcWorkflowGateContext` (`title`, `prompt`, `summary`, `stage_state`, `artifact_refs`, `language`).\n- `created_at`: ISO timestamp the gate was opened; `required` is always `true`.\n\nHosts answer with:\n\n```json\n{ \"id\": \"resp_1\", \"type\": \"workflow_gate_response\", \"gate_id\": \"wg_4845_ralplan_000001\", \"answer\": \"approve\" }\n```\n\nA valid answer resolves the pending gate and returns:\n\n```json\n{ \"id\": \"resp_1\", \"type\": \"response\", \"command\": \"workflow_gate_response\", \"success\": true }\n```\n\nA schema mismatch is **not** a command failure: the response succeeds and the\nresolution data carries `status: \"rejected\"` plus a typed validation `error`\nwith code `invalid_workflow_gate_answer`:\n\n```json\n{\n  \"id\": \"resp_1\",\n  \"type\": \"response\",\n  \"command\": \"workflow_gate_response\",\n  \"success\": true,\n  \"data\": {\n    \"gate_id\": \"wg_1\",\n    \"status\": \"rejected\",\n    \"answer_hash\": \"…\",\n    \"resolved_at\": \"…\",\n    \"error\": {\n      \"code\": \"invalid_workflow_gate_answer\",\n      \"gate_id\": \"wg_1\",\n      \"schema_hash\": \"…\",\n      \"errors\": [{ \"path\": \"/answer\", \"keyword\": \"type\", \"message\": \"must be boolean\" }]\n    }\n  }\n}\n```\n\nAnswering a gate that does not exist is a recoverable command failure carrying\nthe broker error code `unknown_gate` (other broker codes are `already_resolved`,\n`idempotency_conflict`, and `invalid_workflow_stage`).\n## Extension UI Sub-Protocol\n\nExtensions in RPC mode use request/response UI frames.\n\n### Outbound request\n\n`RpcExtensionUIRequest` (`type: \"extension_ui_request\"`) methods:\n\n- `select`, `confirm`, `input`, `editor`, `cancel`\n- `notify`, `setStatus`, `setWidget`, `setTitle`, `set_editor_text`\n\nRuntime note:\n\n- Automatic session title generation is disabled in RPC mode, and `setTitle` UI\n  requests are also suppressed by default because most hosts do not have a\n  meaningful terminal-title surface. Set `SKC_RPC_EMIT_TITLE=1` to opt back in to\n  the UI event only.\n\nExample:\n\n```json\n{\n  \"type\": \"extension_ui_request\",\n  \"id\": \"123\",\n  \"method\": \"confirm\",\n  \"title\": \"Confirm\",\n  \"message\": \"Continue?\",\n  \"timeout\": 30000\n}\n```\n\n### Inbound response\n\n`RpcExtensionUIResponse` (`type: \"extension_ui_response\"`):\n\n- `{ type: \"extension_ui_response\", id: string, value: string }`\n- `{ type: \"extension_ui_response\", id: string, confirmed: boolean }`\n- `{ type: \"extension_ui_response\", id: string, cancelled: true, timedOut?: boolean }`\n\nIf a dialog has a timeout, RPC mode resolves to a default value when timeout/abort fires.\n\n## Host Tool Sub-Protocol\n\nRPC hosts can expose custom tools to the agent by sending `set_host_tools`, then\nserving execution requests over the same transport.\n\n### Outbound request\n\nWhen the agent wants the host to execute one of those tools, RPC mode emits:\n\n```json\n{\n  \"type\": \"host_tool_call\",\n  \"id\": \"host_1\",\n  \"toolCallId\": \"toolu_123\",\n  \"toolName\": \"echo_host\",\n  \"arguments\": { \"message\": \"hello\" }\n}\n```\n\nIf the tool execution is later aborted, RPC mode emits:\n\n```json\n{\n  \"type\": \"host_tool_cancel\",\n  \"id\": \"host_cancel_1\",\n  \"targetId\": \"host_1\"\n}\n```\n\n### Inbound updates and completion\n\nHosts can optionally stream progress:\n\n```json\n{\n  \"type\": \"host_tool_update\",\n  \"id\": \"host_1\",\n  \"partialResult\": {\n    \"content\": [{ \"type\": \"text\", \"text\": \"working\" }]\n  }\n}\n```\n\nCompletion uses:\n\n```json\n{\n  \"type\": \"host_tool_result\",\n  \"id\": \"host_1\",\n  \"result\": {\n    \"content\": [{ \"type\": \"text\", \"text\": \"done\" }]\n  }\n}\n```\n\nSet top-level `isError: true` on `host_tool_result` to reject the pending host tool call and surface the returned text content as a tool error.\n\n## Host URI Sub-Protocol\n\nRPC hosts can also own custom URL schemes (virtual files). After\n`set_host_uri_schemes`, every read of `<scheme>://…` and write of\n`<scheme>://…` (when registered as `writable`) is bounced back to the host\nover the same transport.\n\n### Outbound request\n\nWhen a session tool resolves a host-owned URL, RPC mode emits:\n\n```json\n{\n  \"type\": \"host_uri_request\",\n  \"id\": \"uri_1\",\n  \"operation\": \"read\",\n  \"url\": \"db://users/42\"\n}\n```\n\nWrites look the same with `\"operation\": \"write\"` and an additional\n`\"content\": \"...\"` field carrying the full replacement bytes.\n\nIf the request is later aborted (caller cancels, session ends), RPC mode\nemits:\n\n```json\n{\n  \"type\": \"host_uri_cancel\",\n  \"id\": \"uri_cancel_1\",\n  \"targetId\": \"uri_1\"\n}\n```\n\n### Inbound result\n\nFor successful reads:\n\n```json\n{\n  \"type\": \"host_uri_result\",\n  \"id\": \"uri_1\",\n  \"content\": \"id=42\\nname=Alice\\n\",\n  \"contentType\": \"text/plain\",\n  \"notes\": [\"fresh from cache\"],\n  \"immutable\": false\n}\n```\n\nFor successful writes, omit content:\n\n```json\n{ \"type\": \"host_uri_result\", \"id\": \"uri_1\" }\n```\n\nTo reject the request, set `isError: true` and either populate `error` with\na message or fall back to `content` for textual error surfacing:\n\n```json\n{\n  \"type\": \"host_uri_result\",\n  \"id\": \"uri_1\",\n  \"isError\": true,\n  \"error\": \"row 42 not found\"\n}\n```\n\n### Constraints\n\n- The agent's `edit` tool does not target host URIs. Hosts that want to\n  mutate virtual files expose `write` and let the model use the `write` tool\n  with replacement content.\n- Schemes are global to the process; `set_host_uri_schemes` replaces the\n  previous set, unregistering anything not in the new list.\n- Schemes are normalized to lowercase before registration.\n\n## Error Model and Recoverability\n\n### Command-level failures\n\nFailures are `success: false` with string `error`.\n\n```json\n{\n  \"id\": \"req_2\",\n  \"type\": \"response\",\n  \"command\": \"set_model\",\n  \"success\": false,\n  \"error\": \"Model not found: provider/model\"\n}\n```\n\n### Recoverability expectations\n\n- Most command failures are recoverable; process remains alive.\n- Malformed JSONL / parse-loop exceptions emit a `parse` error response and continue reading subsequent lines.\n- Empty `set_session_name` is rejected (`Session name cannot be empty`).\n- Extension UI responses with unknown `id` are ignored.\n- Process termination conditions are stdin close or explicit extension-triggered shutdown after the current command.\n\n## Compact Command Flows\n\n### 1) Prompt and stream\n\nstdin:\n\n```json\n{ \"id\": \"req_1\", \"type\": \"prompt\", \"message\": \"Summarize this repo\" }\n```\n\nstdout sequence (typical):\n\n```json\n{ \"id\": \"req_1\", \"type\": \"response\", \"command\": \"prompt\", \"success\": true }\n{ \"type\": \"agent_start\" }\n{ \"type\": \"message_update\", \"assistantMessageEvent\": { \"type\": \"text_delta\", \"delta\": \"...\" }, \"message\": { \"role\": \"assistant\", \"content\": [] } }\n{ \"type\": \"agent_end\", \"messages\": [] }\n```\n\n### 2) Prompt during streaming with explicit queue policy\n\nstdin:\n\n```json\n{\n  \"id\": \"req_2\",\n  \"type\": \"prompt\",\n  \"message\": \"Also include risks\",\n  \"streamingBehavior\": \"followUp\"\n}\n```\n\n### 3) Inspect and tune queue behavior\n\nstdin:\n\n```json\n{ \"id\": \"q1\", \"type\": \"get_state\" }\n{ \"id\": \"q2\", \"type\": \"set_steering_mode\", \"mode\": \"all\" }\n{ \"id\": \"q3\", \"type\": \"set_interrupt_mode\", \"mode\": \"wait\" }\n```\n\n### 4) Extension UI round trip\n\nstdout:\n\n```json\n{\n  \"type\": \"extension_ui_request\",\n  \"id\": \"ui_7\",\n  \"method\": \"input\",\n  \"title\": \"Branch name\",\n  \"placeholder\": \"feature/...\"\n}\n```\n\nstdin:\n\n```json\n{ \"type\": \"extension_ui_response\", \"id\": \"ui_7\", \"value\": \"feature/rpc-host\" }\n```\n\n## OpenClaw / Hermes host integrations\n\nFor OpenClaw- or Hermes-style hosts, keep MCP servers and skills on the host side and expose the selected capabilities through RPC host tools. Do not import SKC runtime MCP internals directly; those package paths are intentionally quarantined. See [OpenClaw / Hermes RPC integration notes](./openclaw-hermes-rpc-integration.md).\n\n## Notes on `RpcClient` helper\n\n`src/modes/rpc/rpc-client.ts` is a convenience wrapper, not the protocol definition.\n\nCurrent helper characteristics:\n\n- Spawns `bun <cliPath> --mode rpc`\n- Correlates responses by generated `req_<n>` ids\n- Dispatches recognized `AgentEvent` types to event listeners\n- Dispatches top-level `workflow_gate` frames to `onWorkflowGate()` listeners\n- Supports host-owned custom tools via `setCustomTools()` and automatic handling of `host_tool_call` / `host_tool_cancel`\n- Exposes `respondGate()` for `workflow_gate_response` and waits for the accepted/rejected resolution envelope\n- Does **not** expose helper methods for every protocol command (for example, `set_interrupt_mode` and `set_session_name` are in protocol types but not wrapped as dedicated methods)\n\nUse raw protocol frames if you need complete surface coverage.\n\n## Workflow gates (agent-driven lifecycle)\n\nThe workflow-gate contract makes every human-gated lifecycle moment\n(deep-interview questions, ralplan approval, ultragoal execution sign-off)\nmachine-addressable so an external agent can answer it over RPC without\nscreen-scraping.\n\n### Outbound event: `workflow_gate`\n\n```json\n{\n  \"type\": \"workflow_gate\",\n  \"gate_id\": \"wg_4845_ralplan_000001\",\n  \"stage\": \"ralplan\",\n  \"kind\": \"approval\",\n  \"schema\": { \"type\": \"string\", \"enum\": [\"approve\", \"request-changes\", \"reject\"] },\n  \"schema_hash\": \"<sha256 of canonical schema>\",\n  \"options\": [{ \"value\": \"approve\", \"label\": \"Approve execution\" }],\n  \"context\": { \"title\": \"Approve plan?\", \"summary\": \"…\" },\n  \"created_at\": \"2026-06-05T05:00:00.000Z\",\n  \"required\": true\n}\n```\n\n- `gate_id` is **run-scoped and monotonic**: `wg_<run>_<stage>_<NNNNNN>`.\n- `stage` is one of `deep-interview` | `ralplan` | `ultragoal`. `team` is\n  reserved and rejected for v1 (single-agent only).\n- `kind` is `question` | `approval` | `execution`.\n- `schema` is a **documented subset of JSON Schema 2020-12**. Supported keywords:\n  `type`, `enum`, `const`, `properties`, `required`, `additionalProperties`,\n  `items`, `minLength`, `maxLength`, `minimum`, `maximum`, `title`,\n  `description`, `oneOf`, `anyOf`. Any other keyword is rejected at gate\n  construction (`invalid_workflow_gate_schema`) so the server never advertises a\n  schema it will not validate. `schema_hash` equals the server-side validation\n  hash for that gate.\n\n### Inbound command: `workflow_gate_response`\n\n```json\n{ \"type\": \"workflow_gate_response\", \"gate_id\": \"wg_4845_ralplan_000001\", \"answer\": \"approve\", \"idempotency_key\": \"k1\" }\n```\n\nThe answer is validated against the advertised schema **before acceptance**:\n\n- Valid → resolution persisted before the workflow advances; response:\n  `{ \"type\": \"response\", \"command\": \"workflow_gate_response\", \"success\": true, \"data\": { \"gate_id\": \"…\", \"status\": \"accepted\", \"answer_hash\": \"…\", \"resolved_at\": \"…\" } }`.\n- Invalid → the gate stays **pending** and the resolution carries a typed\n  `invalid_workflow_gate_answer` error listing each `{ path, keyword, message, expected? }`.\n- Idempotency: replaying the same `idempotency_key` + identical body returns the\n  cached resolution; the same key with a different body is an\n  `idempotency_conflict`; answering an already-accepted gate is `already_resolved`.\n- Client helpers wait for this accepted/rejected resolution envelope; they must not treat the write of `workflow_gate_response` itself as completion.\n\n### Entering unattended mode: `negotiate_unattended`\n\nUnattended (zero-human) operation is **fail-closed**. The external agent must\ndeclare its budget, scopes, and action allowlist up front:\n\n```json\n{\n  \"type\": \"negotiate_unattended\",\n  \"declaration\": {\n    \"actor\": \"openclaw/hermes\",\n    \"budget\": { \"max_tokens\": 2000000, \"max_tool_calls\": 5000, \"max_wall_time_ms\": 3600000, \"max_cost_usd\": 20 },\n    \"scopes\": [\"prompt\", \"control\", \"bash\"],\n    \"action_allowlist\": [\"bash.readonly\", \"file.write\"]\n  }\n}\n```\n\nA missing or partial declaration refuses unattended mode. Budget, scope, and\naudit enforcement are layered on this contract by the unattended control plane\n(see issues #318/#319/#320). Attended mode is unaffected: clients that never send\n`negotiate_unattended` keep the existing extension-UI / permission behavior.\n\n\n> **Status (live, #315/#318/#321):** the `workflow_gate` /\n> `workflow_gate_response` / `negotiate_unattended` frames, the answer-schema\n> validator, and the durable gate broker are defined, tested, and wired into\n> live session dispatch. When an unattended control plane is attached to the\n> session, `dispatchRpcCommand` routes `negotiate_unattended` and\n> `workflow_gate_response` through it (see\n> `packages/coding-agent/src/modes/shared/agent-wire/command-dispatch.ts`); a\n> session without that control plane returns a typed \"not available\" error for\n> these frames rather than silently dropping them.\n\n\n### Answering gates from a client (#322)\n\nBoth clients expose typed `workflow_gate` receive + respond helpers so an agent\ncan answer a gate from its own memory via a callback.\n\nFor bridge sessions, gate responses are **not** posted through `/commands`. The\nclient must first own the UI/control plane, then post the answer body to\n`POST /v1/sessions/{session_id}/ui-responses/{gate_id}` with\n`X-SKC-Bridge-Owner-Token: <ownerToken>`. `Idempotency-Key` may be supplied as a\nheader and the same value is also accepted in the JSON body as `idempotency_key`.\n\n`@sayknow-cli/bridge-client` (TypeScript):\n\n```ts\nimport { BridgeClient } from \"@sayknow-cli/bridge-client\";\n\nconst client = new BridgeClient({ baseUrl, token });\n// Headless policy: every received gate is routed to the resolver and answered.\nfor await (const { gate, answer } of client.consumeWorkflowGates(sessionId, ownerToken, gate => {\n  if (gate.kind === \"approval\") return { decision: \"approve\" };\n  if (gate.kind === \"question\") return { selected: [gate.options?.[0]?.value], other: false };\n  return { decision: \"approve\" };\n})) {\n  console.log(`answered ${gate.gate_id} (${gate.kind}) with`, answer);\n}\n// Or answer a single gate directly:\nawait client.respondGate(sessionId, gateId, ownerToken, { decision: \"approve\" });\n```\n\n`python/skc-rpc` (Python):\n\n```python\nfrom skc_rpc import RpcClient, WorkflowGate\n\nclient = RpcClient(executable=\"skc\")\n\ndef resolver(gate: WorkflowGate) -> object:\n    if gate.kind == \"approval\":\n        return {\"decision\": \"approve\"}\n    if gate.kind == \"question\":\n        return {\"selected\": [gate.options[0].value] if gate.options else [], \"other\": False}\n    return {\"decision\": \"approve\"}\n\n# Headless policy: route every received gate to the resolver and respond.\nclient.run_workflow_gate_policy(resolver)\nclient.start()\n# Or answer a single gate directly: client.respond_gate(gate_id, {\"decision\": \"approve\"})\n```\n",
 	"rulebook-matching-pipeline.md": "# Rulebook Matching Pipeline\n\nThis document describes how coding-agent discovers rules from supported config formats, normalizes them into a single `Rule` shape, resolves precedence conflicts, and splits the result into:\n\n- **Rulebook rules** (available to the model via system prompt + `rule://` URLs)\n- **TTSR rules** (time-travel stream interruption rules)\n\nIt reflects the current implementation, including partial semantics and metadata that is parsed but not enforced.\n\n## Implementation files\n\n- [`../src/capability/rule.ts`](../packages/coding-agent/src/capability/rule.ts)\n- [`../src/capability/index.ts`](../packages/coding-agent/src/capability/index.ts)\n- [`../src/discovery/index.ts`](../packages/coding-agent/src/discovery/index.ts)\n- [`../src/discovery/helpers.ts`](../packages/coding-agent/src/discovery/helpers.ts)\n- [`../src/discovery/builtin.ts`](../packages/coding-agent/src/discovery/builtin.ts)\n- [`../src/discovery/cursor.ts`](../packages/coding-agent/src/discovery/cursor.ts)\n- [`../src/discovery/windsurf.ts`](../packages/coding-agent/src/discovery/windsurf.ts)\n- [`../src/discovery/cline.ts`](../packages/coding-agent/src/discovery/cline.ts)\n- [`../src/sdk.ts`](../packages/coding-agent/src/sdk.ts)\n- [`../src/system-prompt.ts`](../packages/coding-agent/src/system-prompt.ts)\n- [`../src/internal-urls/rule-protocol.ts`](../packages/coding-agent/src/internal-urls/rule-protocol.ts)\n- [`../src/utils/frontmatter.ts`](../packages/coding-agent/src/utils/frontmatter.ts)\n\n## 1. Canonical rule shape\n\nAll providers normalize source files into `Rule`:\n\n```ts\ninterface Rule {\n  name: string;\n  path: string;\n  content: string;\n  globs?: string[];\n  alwaysApply?: boolean;\n  description?: string;\n  condition?: string[];\n  scope?: string[];\n  interruptMode?: \"never\" | \"prose-only\" | \"tool-only\" | \"always\";\n  _source: SourceMeta;\n}\n```\n\nCapability identity is `rule.name` (`ruleCapability.key = rule => rule.name`).\n\nConsequence: precedence and deduplication are **name-based only**. Two different files with the same `name` are considered the same logical rule.\n\n## 2. Discovery sources and normalization\n\n`src/discovery/index.ts` auto-registers providers. For `rules`, current providers are:\n\n- `native` (priority `100`)\n- `cursor` (priority `50`)\n- `windsurf` (priority `50`)\n- `cline` (priority `40`)\n\n### Native provider (`builtin.ts`)\n\nLoads `.skc` rules from:\n\n- project: `<cwd>/.skc/rules/*.{md,mdc}`\n- user: `~/.skc/agent/rules/*.{md,mdc}`\n\nNormalization:\n\n- `name` = filename without `.md`/`.mdc`\n- frontmatter parsed via `parseFrontmatter`\n- `content` = body (frontmatter stripped)\n- `globs`, `alwaysApply`, `description`, `condition`/legacy `ttsr_trigger`, `scope`, and `interruptMode` are parsed by `buildRuleFromMarkdown`\n\nImportant caveat: `condition` values that look like file globs are converted into `tool:edit(...)` / `tool:write(...)` scope shorthands with catch-all condition `.*`.\n\n### Cursor provider (`cursor.ts`)\n\nLoads from:\n\n- user: `~/.cursor/rules/*.{mdc,md}`\n- project: `<cwd>/.cursor/rules/*.{mdc,md}`\n\nNormalization (`transformMDCRule`):\n\n- `description`: kept only if string\n- `alwaysApply`: only `true` is preserved (`false` becomes `undefined`)\n- `globs`: accepts array (string elements only) or single string\n- `condition`/legacy `ttsr_trigger`, `scope`, and `interruptMode` are parsed by shared rule helpers\n- `name` from filename without extension\n\n### Windsurf provider (`windsurf.ts`)\n\nLoads from:\n\n- user: `~/.codeium/windsurf/memories/global_rules.md` (fixed rule name `global_rules`)\n- project: `<cwd>/.windsurf/rules/*.md`\n\nNormalization:\n\n- `globs`: array-of-string or single string\n- `alwaysApply`, `description`, `condition`/legacy `ttsr_trigger`, `scope`, and `interruptMode` parsed by shared rule helpers\n- `name` is fixed to `global_rules` for the user global file and derived from filename for project rules\n\n### Cline provider (`cline.ts`)\n\nSearches upward from `cwd` for nearest `.clinerules`:\n\n- if directory: loads `*.md` inside it\n- if file: loads single file as rule named `clinerules`\n\nNormalization:\n\n- `globs`: array-of-string or single string\n- `alwaysApply`, `description`, `condition`/legacy `ttsr_trigger`, `scope`, and `interruptMode` parsed by shared rule helpers\n- `name` is fixed to `clinerules` for a `.clinerules` file and derived from filename for `.clinerules/*.md`\n\n## 3. Frontmatter parsing behavior and ambiguity\n\nAll providers use `parseFrontmatter` (`utils/frontmatter.ts`) with these semantics:\n\n1. Frontmatter is parsed only when content starts with `---` and has a closing `\\n---`.\n2. Body is trimmed after frontmatter extraction.\n3. If YAML parse fails:\n   - warning is logged,\n   - parser falls back to simple `key: value` line parsing (`^(\\w+):\\s*(.*)$`).\n\nAmbiguity consequences:\n\n- Fallback parser does not support arrays, nested objects, quoting rules, or hyphenated keys.\n- Fallback values become strings (for example `alwaysApply: true` becomes string `\"true\"`), so providers requiring boolean/string types may drop metadata.\n- `ttsr_trigger` works in fallback (underscore key); keys like `thinking-level` would not.\n- Files without valid frontmatter still load as rules with empty metadata and full content body.\n\n## 4. Provider precedence and deduplication\n\n`loadCapability(\"rules\")` (`capability/index.ts`) merges provider outputs and then deduplicates by `rule.name`.\n\n### Precedence model\n\n- Providers are ordered by priority descending.\n- Equal priority keeps registration order (`cursor` before `windsurf` from `discovery/index.ts`).\n- Dedup is first-wins: first encountered rule name is kept; later same-name items are marked `_shadowed` in `all` and excluded from `items`.\n\nEffective rule provider order is currently:\n\n1. `native` (100)\n2. `cursor` (50)\n3. `windsurf` (50)\n4. `cline` (40)\n\n### Intra-provider ordering caveat\n\nWithin a provider, item order comes from `loadFilesFromDir` glob result ordering plus explicit push order. This is deterministic enough for normal use but not explicitly sorted in code.\n\nNotable source-order differences:\n\n- `native` appends project then user config dirs.\n- `cursor` appends user then project results.\n- `windsurf` appends user `global_rules` first, then project rules.\n- `cline` loads only nearest `.clinerules` source.\n\n## 5. Split into Rulebook, Always-Apply, and TTSR buckets\n\nAfter rule discovery in `createAgentSession` (`sdk.ts`):\n\n1. All discovered rules are scanned.\n2. Rules with `condition` entries are registered into `TtsrManager`; legacy `ttsr_trigger` / `ttsrTrigger` are accepted during rule parsing as condition fallbacks.\n3. A separate `rulebookRules` list is built with this predicate:\n\n```ts\n!isTtsrRule && rule.alwaysApply !== true && !!rule.description;\n```\n\n4. An `alwaysApplyRules` list is built:\n\n```ts\n!isTtsrRule && rule.alwaysApply === true;\n```\n\n### Bucket behavior\n\n- **TTSR bucket**: any rule with a non-empty parsed `condition` that `TtsrManager.addRule(...)` accepts. Takes priority over other buckets.\n- **Always-apply bucket**: `alwaysApply === true`, not TTSR. Full content injected into system prompt. Resolvable via `rule://`.\n- **Rulebook bucket**: must have description, must not be TTSR, must not be `alwaysApply`. Listed in system prompt by name+description; content read on demand via `rule://`.\n- A rule with both `condition` and `alwaysApply` goes to TTSR only (TTSR takes priority).\n- A rule with both `alwaysApply` and `description` goes to always-apply only (not rulebook).\n\n## 6. How metadata affects runtime surfaces\n\n### `description`\n\n- Required for inclusion in rulebook.\n- Rendered in system prompt `<rules>` block.\n- Missing description means rule is not available via `rule://` and not listed in system prompt rules.\n\n### `globs`\n\n- Carried through on `Rule`.\n- Rendered as `<glob>...</glob>` entries in the system prompt rules block.\n- Exposed in rules UI state (`extensions` mode list).\n- **Not enforced for automatic matching in this pipeline.** There is no runtime glob matcher selecting rules by current file/tool target.\n\n### `alwaysApply`\n\n- Parsed and preserved by providers.\n- Used in UI display (`\"always\"` trigger label in extensions state manager).\n- Used as an exclusion condition from `rulebookRules`.\n- **Full rule content is auto-injected into the system prompt** (before the rulebook rules section).\n- Rule is also addressable via `rule://<name>` for re-reading.\n\n### `condition`, `scope`, and `interruptMode`\n\n- `condition` is the current TTSR trigger field; legacy `ttsr_trigger` / `ttsrTrigger` are accepted as fallback inputs during parsing.\n- `scope` narrows TTSR matching scope. A condition token that looks like a file glob becomes `tool:edit(<glob>)` and `tool:write(<glob>)` scope entries plus catch-all condition `.*`.\n- `interruptMode` can override the global TTSR interrupt mode for the rule.\n\n## 7. System prompt inclusion path\n\n`buildSystemPromptInternal` receives both `rules` (rulebook) and `alwaysApplyRules`.\n\nAlways-apply rules are rendered first, injecting their raw content directly into the prompt.\n\nRulebook rules are rendered in a `# Rules` section with:\n\n- `Read rule://<name> when working in matching domain`\n- Each rule's `name`, `description`, and optional `<glob>` list\n\nThis is advisory/contextual: prompt text asks the model to read applicable rules, but code does not enforce glob applicability.\n\n## 8. `rule://` internal URL behavior\n\n`RuleProtocolHandler` is registered with:\n\n```ts\nnew RuleProtocolHandler({\n  getRules: () => [...rulebookRules, ...alwaysApplyRules],\n});\n```\n\nImplications:\n\n- `rule://<name>` resolves against both **rulebookRules** and **alwaysApplyRules**.\n- TTSR-only rules and rules with no description and no `alwaysApply` are not addressable via `rule://`.\n- Resolution is exact name match.\n- Unknown names return error listing available rule names.\n- Returned content is raw `rule.content` (frontmatter stripped), content type `text/markdown`.\n\n## 9. Known partial / non-enforced semantics\n\n1. Provider descriptions mention legacy files (`.cursorrules`, `.windsurfrules`), but current loader code paths do not actually read those files.\n2. `globs` metadata is surfaced to prompt/UI but not enforced by rule selection logic.\n3. Rule selection for `rule://` includes rulebook and always-apply rules, but not TTSR-only rules.\n4. Discovery warnings (`loadCapability(\"rules\").warnings`) are produced but `createAgentSession` does not currently surface/log them in this path.\n",
-	"sayknow-remote.md": "# Sayknow Remote — v0 Design (thin phone steering wheel)\n\nStatus: **design / pending approval** · Tracks issue #565 · Scope: **v0 only**\n\nSayknow Remote is a thin remote *steering wheel* for an already-running PC-side\n`skc` session. It is intentionally **not** a universal phone shell, a remote\nfilesystem editor, or a remote-desktop replacement. The PC stays the authority\nboundary for file edits, shell execution, approval gates, and sensitive output.\n\nThis document fixes the two things the issue calls out as blockers/gates before\nany code lands: the **authority boundary contract** and the **transmitted-data\ncontract**. It then maps v0 onto existing surfaces and splits the work into\nPR-sized steps.\n\n## TL;DR architecture decision\n\nv0 is a thin **read + one-line-submit** surface layered on subsystems that\nalready exist. It introduces **no new remote-control protocol** — that would\nrequire ADR-level rationale per [`docs/bridge.md`](bridge.md).\n\n| Concern | Reused existing surface |\n| --- | --- |\n| Network transport, TLS, bearer auth, fail-closed posture | Bridge mode (`skc --mode bridge`), [`docs/bridge.md`](bridge.md) |\n| Client SDK / framing | `@sayknow-cli/bridge-client` (`BridgeClient`, `events()`) |\n| Session state storage, liveness, bounded status, submit gating | Harness control plane (`skc harness`), `packages/coding-agent/src/harness-control-plane/` |\n| Bounded observation (never a raw transcript dump) | `Observation` / `SessionStateView` in `harness-control-plane/types.ts` |\n| Web client precedent (local server + SPA) | `packages/stats` (`server.ts` + `src/client/`) |\n\nThe only genuinely new piece is a thin **Sayknow Remote gateway**: one PC-side\nprocess that enumerates harness control-plane sessions and proxies a strict,\nbounded subset of read/submit operations to each session's owner. The phone\ntalks to exactly one gateway endpoint.\n\n## Why a gateway (and not one bridge per session)\n\nBridge mode serves **exactly one live `AgentSession` per process** and is\nfail-closed by default (see the endpoint matrix in\n`packages/coding-agent/src/modes/bridge/bridge-mode.ts`). The v0 requirement\n\"list active PC-side sessions\" needs cross-session enumeration, which a single\nbridge process does not provide.\n\nThe harness control plane already centralizes exactly this: per-session\n`state.json`, lease + heartbeat liveness, a single-writer severity event log,\nand a **bounded** observation vocabulary. So the gateway is a thin read/submit\nproxy over the control plane, wearing the bridge security model (TLS + bearer +\nfail-closed). This keeps bridge single-session semantics untouched and avoids a\nproliferation of per-session ports and pairing surfaces.\n\n```\n phone (mobile web)\n        │  HTTPS + bearer (scoped: remote:view + remote:submit)\n        ▼\n Sayknow Remote gateway  ── enumerates ─▶ harness control-plane session-state dir\n   (one PC process)     ── observe ───▶ owner process (RuntimeOwner, lease holder)\n                        ── submit ────▶ owner submit path (readyForSubmit gating)\n        │\n        └─ never: file edits · shell · gate answers · raw transcript · secrets\n```\n\n## Authority boundary contract\n\nThe PC-side runtime is the sole authority. The gateway and the phone are\n**observers + one-line submitters**, nothing more.\n\nThe gateway MUST NOT, in v0:\n\n- edit files, run shell, or invoke any mutating tool;\n- answer workflow-gate / permission / approval prompts (those stay on the PC);\n- expose bridge/RPC command scopes (`message:read`, `session`, `model`, `bash`,\n  `host_tools`, `host_uri`, `export`, `admin`, or `control`) to the phone;\n- stream raw pane output, transcripts, tool arguments/results, diffs, file\n  contents, environment, or secrets;\n- bypass the owner's `readyForSubmit` gating or submit while a session is busy.\n\nThe phone MAY, in v0:\n\n- list active sessions (bounded metadata);\n- open one session and read its **bounded** status/observation;\n- submit a single one-line instruction through the owner's normal submit path;\n- see idle / working / blocked status and a human-readable reason when blocked.\n\nA one-line submit travels the same path as a local `skc harness submit`, so it\ninherits the owner's submission gating (`Observation.readyForSubmit` /\n`submitUnavailableReason`). The phone cannot force a submit the local runtime\nwould itself refuse.\n\n## Transmitted-data contract (allowlist)\n\nThe contract is an **allowlist**: only the fields below leave the PC. Anything\nnot listed is withheld by default. This is enforced in code as a typed\nprojection from the control plane's already-bounded `Observation` /\n`SessionStateView` — never a passthrough of internal state.\n\n### Session list entry → phone (`RemoteSessionSummary`)\n\n| Field | Source | Notes |\n| --- | --- | --- |\n| `sessionId` | `SessionState.sessionId` | opaque id |\n| `name` | derived from handle metadata (`issueOrPr`, repo, branch, or session id fallback) | sanitized, length-capped |\n| `harness` | `SessionState.harness` | `sayknow-cli` in v1 |\n| `status` | derived (see state mapping) | `idle` \\| `working` \\| `blocked` \\| `offline` |\n| `lastActivityAt` | `Observation.lastActivityAt` | ISO timestamp |\n| `branch` | `Observation.branch` | branch name only |\n\n### Open-session view → phone (`RemoteSessionView`)\n\n| Field | Source | Notes |\n| --- | --- | --- |\n| `sessionId`, `name`, `harness`, `status` | as above | |\n| `lifecycle` | `SessionStateView.lifecycle` | bounded enum |\n| `ownerLive` | `SessionStateView.ownerLive` | liveness |\n| `blockers` | `SessionStateView.blockers` | reason strings, sanitized |\n| `observedSignals` | `Observation.observedSignals` | bounded vocab only (`tool-call`, `test-running`, `streaming`, `idle`, …) |\n| `gitDelta` | `Observation.gitDelta` | enum: `clean`/`dirty`/`zero-delta`/`unknown` |\n| `risk` | `Observation.risk` | enum |\n| `readyForSubmit` | `Observation.readyForSubmit` | submit affordance |\n| `submitUnavailableReason` | `Observation.submitUnavailableReason` | when not ready |\n| `lastActivityAt`, `branch` | as above | |\n\n### Phone → PC (`RemoteSubmitRequest`)\n\n| Field | Notes |\n| --- | --- |\n| `sessionId` | target session |\n| `text` | single one-line instruction; length-capped, control-chars stripped |\n| `idempotencyKey` | optional; dedupes retries (mirrors bridge idempotency) |\n\n### Never transmitted by default\n\nRaw pane/terminal output, full transcript / message bodies, tool call arguments\nor results, file contents, diffs, system prompt, environment variables, tokens\nor secrets, and absolute paths beyond the session `cwd`/`branch` metadata. When\ncontent is intentionally held back, the phone shows a neutral *\"withheld on PC\"*\nmarker rather than a redacted blob.\n\n## Session-state model (idle / working / blocked)\n\n`status` is derived from harness lifecycle + liveness + bounded signals:\n\n- **offline** — `ownerLive == false`, lease dead, or gateway cannot reach the\n  owner. (Distinct from blocked; the PC is gone, not waiting.)\n- **blocked** — `lifecycle == \"blocked\"`, OR a workflow-gate / permission prompt\n  is pending on the PC, OR `readyForSubmit == false` with a\n  `submitUnavailableReason`. Phone shows the reason; it does **not** resolve it.\n- **working** — owner live and `lifecycle` in\n  `{started, submitted, observing, recovering, validating, finalizing}` with\n  recent activity signals (`streaming` / `tool-call` / `test-running`).\n- **idle** — owner live, stable lifecycle, last signal `idle`/`completed`, and\n  `readyForSubmit == true`.\n\n## Failure states (must be understandable)\n\n| Condition | Detection | Phone UX |\n| --- | --- | --- |\n| Disconnected PC | `ownerLive`/lease dead or gateway unreachable | `offline`; submit disabled; \"PC is offline\" |\n| Expired pairing | bearer/pairing token expired or revoked | \"Pairing expired — re-pair on PC\" |\n| Session busy | `readyForSubmit == false` (+ reason) | submit disabled with reason; optionally queue |\n| Submit rejected | typed object error (e.g. `{ code: \"scope_denied\" }`, see [`docs/rpc.md`](rpc.md)) | inline rejection reason |\n| Sensitive output withheld | bounded observation by design | neutral \"withheld on PC\" marker |\n\n## Pairing and auth (minimum that is not security soup)\n\nv0 = **local pairing only**. Reuse the bridge security model for transport and authentication posture, but expose a gateway-specific authorization surface:\n\n- **TLS mandatory for every bind, including loopback** (no plaintext fallback;\n  matches `docs/bridge.md`).\n- **Bearer token mandatory** for every endpoint except health/help.\n- Pairing flow: the PC prints/serves a short-lived **pairing code**; the phone\n  submits host + code and receives a **scoped bearer** capped to\n  gateway-only scopes: `remote:view` + `remote:submit` only. These scopes are\n  not aliases for bridge/RPC `message:read` or `prompt`. Phone bearers MUST NOT\n  authorize bridge command-catalog calls such as `get_messages`,\n  `get_last_assistant_text`, `get_state` with `include: [\"systemPrompt\",\n  \"tools\"]`, `new_session`, `switch_session`, `branch`, `set_model`,\n  `bash`, `host_*`, `control`, or `admin`.\n- Tokens expire; re-pairing is the recovery path. The gateway is fail-closed:\n  unknown/expired tokens, non-gateway scopes, bridge command-catalog methods,\n  and out-of-scope commands are rejected before dispatch.\n\nHosted relay is **deferred to v1** and gated behind a separate ADR (it changes\nthe trust model and is where \"security soup\" risk concentrates).\n\n## Open questions from the issue — v0 decisions\n\n| Question | v0 decision | Deferred |\n| --- | --- | --- |\n| Hosted relay vs local pairing vs both | Local pairing only | Hosted relay → v1 (ADR) |\n| Minimum pairing/auth | Pairing code → gateway-scoped bearer, TLS mandatory | Identity/relay accounts → v1 |\n| Which session states are public | Bounded: `idle`/`working`/`blocked`/`offline` + bounded observation vocab | Richer telemetry → v1 |\n| Web vs native first | Mobile web first (reuse stats SPA build pattern) | Native app / PWA polish → v1 |\n| Notifications / pause / resume | Out of scope for v0 | Staged in v1 |\n\n## Implementation plan (PR-sized steps)\n\nEach step is independently shippable; later steps stay fail-closed until wired.\n\n1. **PR 1 — this doc.** `docs/sayknow-remote.md` + README cross-link. Resolves the\n   authority + transmitted-data gates. No code.\n2. **PR 2 — typed contract + schema.** `RemoteSessionSummary`,\n   `RemoteSessionView`, `RemoteSubmitRequest`, `RemoteSubmitResult`,\n   `RemoteErrorCode`, plus a projection `Observation`/`SessionStateView →\n   RemoteSessionView` and a JSON schema. Tests assert the allowlist (no\n   forbidden field can leak). Types only; no runtime wiring.\n3. **PR 3 — gateway read path.** Enumerate harness sessions (list) and serve the\n   per-session bounded view, behind an explicit opt-in flag, fail-closed\n   otherwise, reusing bridge TLS + bearer. Tests for liveness derivation and the\n   redaction projection.\n4. **PR 4 — gateway submit path.** One-line submit through the owner's submit\n   gating; typed rejections for busy/denied; idempotency. Tests for\n   busy/rejected paths.\n5. **PR 5 — pairing/auth.** Pairing code → gateway-scoped bearer\n   (`remote:view` + `remote:submit`) with expiry. Tests prove phone bearers\n   cannot call bridge/RPC `message:read`, `prompt`, session/model, shell, host,\n   control, or admin surfaces.\n6. **PR 6 — mobile web client.** Minimal SPA (list → open → status → submit)\n   using `@sayknow-cli/bridge-client` and the `packages/stats` build pattern.\n7. **PR 7 — failure-state UX + hardening.** Failure-state surfaces, redaction\n   hardening, CHANGELOG, docs finalize.\n\n## Non-goals (v0)\n\n- No arbitrary phone-side shell.\n- No raw secret/log dumping to mobile by default.\n- No direct filesystem editor from the phone.\n- No bypass around PC-side approval/confirmation gates.\n- No remote-desktop replacement.\n- No second authenticated remote-control protocol (reuse bridge; relay needs an\n  ADR).\n\n## Key source references\n\n- Bridge transport / security: `packages/coding-agent/src/modes/bridge/`, [`docs/bridge.md`](bridge.md)\n- RPC command/response contract: `packages/coding-agent/src/modes/rpc/`, [`docs/rpc.md`](rpc.md)\n- Client SDK: `packages/bridge-client/src/`\n- Control plane (sessions, leases, bounded observation, submit): `packages/coding-agent/src/harness-control-plane/`, `packages/coding-agent/src/commands/harness.ts`\n- Web client precedent: `packages/stats/src/server.ts`, `packages/stats/src/client/`\n\n—\n*[repo owner's gaebal-sayknow (clawdbot) 🦞]*\n",
 	"sdk.md": "# SDK\n\nThe SDK is the in-process integration surface for `@sayknow-cli/coding-agent`.\nUse it when you want direct access to agent state, event streaming, tool wiring, and session control from your own Bun/Node process.\n\nIf you need cross-language/process isolation, use RPC mode instead.\n\n## Installation\n\n```bash\nbun add @sayknow-cli/coding-agent\n```\n\n## Entry points\n\n`@sayknow-cli/coding-agent` exports the SDK APIs from the package root (and also via `@sayknow-cli/coding-agent/sdk`).\n\nCore exports for embedders:\n\n- `createAgentSession`\n- `SessionManager`\n- `Settings`\n- `AuthStorage`\n- `ModelRegistry`\n- `discoverAuthStorage`\n- Discovery helpers for retained context/prompt surfaces (`discoverContextFiles`, `discoverPromptTemplates`)\n- Tool factory surface (`createTools`, `BUILTIN_TOOLS`, tool classes)\n\n## Quick start (auto-discovery defaults)\n\n```ts\nimport { createAgentSession } from \"@sayknow-cli/coding-agent\";\n\nconst { session, modelFallbackMessage } = await createAgentSession();\n\nif (modelFallbackMessage) {\n  process.stderr.write(`${modelFallbackMessage}\\n`);\n}\n\nconst unsubscribe = session.subscribe((event) => {\n  if (\n    event.type === \"message_update\" &&\n    event.assistantMessageEvent.type === \"text_delta\"\n  ) {\n    process.stdout.write(event.assistantMessageEvent.delta);\n  }\n});\n\nawait session.prompt(\"Summarize this repository in 3 bullets.\");\nunsubscribe();\nawait session.dispose();\n```\n\n## What `createAgentSession()` discovers by default\n\n`createAgentSession()` follows “provide to override, omit to discover”.\n\nIf omitted, it resolves:\n\n- `cwd`: `getProjectDir()`\n- `agentDir`: `~/.skc/agent` (via `getAgentDir()`)\n- `authStorage`: `discoverAuthStorage(agentDir)`\n- `modelRegistry`: `new ModelRegistry(authStorage)` + background `refreshInBackground()` when the registry is not provided\n- `settings`: `await Settings.init({ cwd, agentDir })`\n- `sessionManager`: `SessionManager.create(cwd)` (file-backed)\n- context files and prompt templates\n- built-in tools via `createTools(...)`\n- LSP integration (enabled by default)\n- `eventBus`: new `EventBus()` unless supplied\n\n### Required vs optional inputs\n\nTypically you must provide only what you want to control:\n\n- **Must provide**: nothing for a minimal session\n- **Usually provide explicitly** in embedders:\n  - `sessionManager` (if you need in-memory or custom location)\n  - `authStorage` + `modelRegistry` (if you own credential/model lifecycle)\n  - `model` or `modelPattern` (if deterministic model selection matters)\n  - `settings` (if you need isolated/test config)\n\n## Session manager behavior (persistent vs in-memory)\n\n`AgentSession` always uses a `SessionManager`; behavior depends on which factory you use.\n\n### File-backed (default)\n\n```ts\nimport { createAgentSession, SessionManager } from \"@sayknow-cli/coding-agent\";\n\nconst { session } = await createAgentSession({\n  sessionManager: SessionManager.create(process.cwd()),\n});\n\nconsole.log(session.sessionFile); // absolute .jsonl path\n```\n\n- Persists conversation/messages/state deltas to session files.\n- Supports resume/open/list/fork workflows.\n- `session.sessionFile` is defined.\n\n### In-memory\n\n```ts\nimport { createAgentSession, SessionManager } from \"@sayknow-cli/coding-agent\";\n\nconst { session } = await createAgentSession({\n  sessionManager: SessionManager.inMemory(),\n});\n\nconsole.log(session.sessionFile); // undefined\n```\n\n- No filesystem persistence.\n- Useful for tests, ephemeral workers, request-scoped agents.\n- Session methods still work, but persistence-specific behaviors (file resume/fork paths) are naturally limited.\n\n### Resume/open/list helpers\n\n```ts\nimport { SessionManager } from \"@sayknow-cli/coding-agent\";\n\nconst recent = await SessionManager.continueRecent(process.cwd());\nconst listed = await SessionManager.list(process.cwd());\nconst opened = listed[0] ? await SessionManager.open(listed[0].path) : null;\n```\n\n## Model and auth wiring\n\n`createAgentSession()` uses `ModelRegistry` + `AuthStorage` for model selection and API key resolution.\n\n### Explicit wiring\n\n```ts\nimport {\n  createAgentSession,\n  discoverAuthStorage,\n  ModelRegistry,\n  SessionManager,\n} from \"@sayknow-cli/coding-agent\";\n\nconst authStorage = await discoverAuthStorage();\nconst modelRegistry = new ModelRegistry(authStorage);\nawait modelRegistry.refresh();\n\nconst available = modelRegistry.getAvailable();\nif (available.length === 0)\n  throw new Error(\"No authenticated models available\");\n\nconst { session } = await createAgentSession({\n  authStorage,\n  modelRegistry,\n  model: available[0],\n  thinkingLevel: \"medium\",\n  sessionManager: SessionManager.inMemory(),\n});\n```\n\n### Selection order when `model` is omitted\n\nWhen no explicit `model`/`modelPattern` is provided:\n\n1. restore model from existing session (if restorable + key available)\n2. settings default model role (`default`)\n3. first available model with valid auth\n\nIf restore fails, `modelFallbackMessage` explains fallback.\n\n### Auth priority\n\n`AuthStorage.getApiKey(...)` resolves in this order:\n\n1. runtime override (`setRuntimeApiKey`)\n2. stored credentials in `agent.db`\n3. provider environment variables\n4. custom-provider resolver fallback (if configured)\n\n## Event subscription model\n\nSubscribe with `session.subscribe(listener)`; it returns an unsubscribe function.\n\n```ts\nconst unsubscribe = session.subscribe((event) => {\n  switch (event.type) {\n    case \"agent_start\":\n    case \"turn_start\":\n    case \"tool_execution_start\":\n      break;\n    case \"message_update\":\n      if (event.assistantMessageEvent.type === \"text_delta\") {\n        process.stdout.write(event.assistantMessageEvent.delta);\n      }\n      break;\n  }\n});\n```\n\n`AgentSessionEvent` includes core `AgentEvent` plus session-level events:\n\n- `auto_compaction_start` / `auto_compaction_end`\n- `auto_retry_start` / `auto_retry_end`\n- `retry_fallback_applied` / `retry_fallback_succeeded`\n- `ttsr_triggered`\n- `todo_reminder` / `todo_auto_clear`\n- `irc_message`\n\n## Prompt lifecycle\n\n`session.prompt(text, options?)` is the primary entry point.\n\nBehavior:\n\n1. optional command/template expansion (`/` commands, custom commands, file slash commands, prompt templates)\n2. if currently streaming:\n   - requires `streamingBehavior: \"steer\" | \"followUp\"`\n   - queues instead of throwing work away\n3. if idle:\n   - validates model + API key\n   - appends user message\n   - starts agent turn\n\nRelated APIs:\n\n- `sendUserMessage(content, { deliverAs? })`\n- `steer(text, images?)`\n- `followUp(text, images?)`\n- `sendCustomMessage({ customType, content, ... }, { deliverAs?, triggerTurn? })`\n- `abort()`\n\n## Tools integration\n\n### Built-ins and filtering\n\n- Built-ins come from `createTools(...)` and `BUILTIN_TOOLS`.\n- `toolNames` acts as an allowlist for built-ins.\n- Hidden tools (for example `yield`) are opt-in unless required by options.\n\n```ts\nconst { session } = await createAgentSession({\n  toolNames: [\"read\", \"grep\", \"find\", \"write\"],\n  requireYieldTool: true,\n});\n```\n\n### Runtime tool set changes\n\n`AgentSession` supports runtime activation updates:\n\n- `getActiveToolNames()`\n- `getAllToolNames()`\n- `setActiveToolsByName(names)`\n\nSystem prompt is rebuilt to reflect active tool changes.\n\n## Discovery helpers\n\nUse these when you want partial control without recreating internal discovery logic:\n\n- `discoverAuthStorage(agentDir?)`\n- `discoverContextFiles(cwd?, _agentDir?)`\n- `discoverPromptTemplates(cwd?, agentDir?)`\n- `buildSystemPrompt(options?)`\n\n## Subagent-oriented options\n\nFor SDK consumers building orchestrators (similar to task executor flow):\n\n- `outputSchema`: passes structured output expectation into tool context\n- `requireYieldTool`: forces `yield` tool inclusion\n- `taskDepth`: recursion-depth context for nested task sessions\n- `parentTaskPrefix`: artifact naming prefix for nested task outputs\n\nThese are optional for normal single-agent embedding.\n\n## `createAgentSession()` return value\n\n```ts\ntype CreateAgentSessionResult = {\n  session: AgentSession;\n  setToolUIContext: (uiContext: ExtensionUIContext, hasUI: boolean) => void;\n  modelFallbackMessage?: string;\n  lspServers?: Array<{\n    name: string;\n    status: \"ready\" | \"error\";\n    fileTypes: string[];\n    error?: string;\n  }>;\n  eventBus: EventBus;\n};\n```\n\nUse `setToolUIContext(...)` only if your embedder provides UI capabilities that tools should call into.\n\n## Startup performance\n\n`createAgentSession()` runs two background optimizations to overlap I/O with the rest of session setup:\n\n- **Model-host preconnect.** As soon as the model is resolved, the SDK fires a best-effort `fetch.preconnect(model.baseUrl)` so DNS + TCP + TLS + HTTP/2 to the provider's host happens in parallel with tool registry build, and system-prompt assembly. The first real `fetch(...)` then reuses the warm connection, saving 100–300 ms on transcontinental hops (e.g. residential IP → `api.anthropic.com`). Implementation lives in `preconnectModelHost()` in `packages/coding-agent/src/sdk.ts`. If `fetch.preconnect` is unavailable (non-Bun runtime) or the call throws, the optimization is silently skipped — never a hard dependency. Applies to every mode (interactive, print, RPC, ACP).\n- **Conditional LSP warmup.** Startup LSP servers (those returned by `discoverStartupLspServers(cwd)`) are only warmed when **all** of these hold:\n  - `enableLsp !== false` on the session options, **and**\n  - `options.hasUI === true` (interactive TUI), **and**\n  - the `lsp.diagnosticsOnWrite` setting is enabled.\n\n  Print / script / RPC / ACP invocations (`hasUI=false`) skip the warmup entirely: they don't render the warmup status indicator and typically finish before the language servers would stabilize, so warming them just spends CPU parsing big `initialize` responses concurrently with the LLM stream consumer and jitters perceived latency. Tools that actually need an LSP server still spin one up on demand through `getOrCreateClient()` — only the *startup* warmup is skipped. The returned `lspServers` field in `CreateAgentSessionResult` is therefore `undefined` (not an empty array) whenever the warmup branch was bypassed.\n\n## Minimal controlled embed example\n\n```ts\nimport {\n  createAgentSession,\n  discoverAuthStorage,\n  ModelRegistry,\n  SessionManager,\n  Settings,\n} from \"@sayknow-cli/coding-agent\";\n\nconst authStorage = await discoverAuthStorage();\nconst modelRegistry = new ModelRegistry(authStorage);\nawait modelRegistry.refresh();\n\nconst settings = Settings.isolated({\n  \"compaction.enabled\": true,\n  \"retry.enabled\": true,\n});\n\nconst { session } = await createAgentSession({\n  authStorage,\n  modelRegistry,\n  settings,\n  sessionManager: SessionManager.inMemory(),\n  toolNames: [\"read\", \"grep\", \"find\", \"edit\", \"write\"],\n  enableLsp: true,\n});\n\nsession.subscribe((event) => {\n  if (\n    event.type === \"message_update\" &&\n    event.assistantMessageEvent.type === \"text_delta\"\n  ) {\n    process.stdout.write(event.assistantMessageEvent.delta);\n  }\n});\n\nawait session.prompt(\"Find all TODO comments in this repo and propose fixes.\");\nawait session.dispose();\n```\n",
 	"secrets.md": "# Secret Obfuscation\n\nPrevents sensitive values (API keys, tokens, passwords) from being sent to LLM providers. When enabled, secrets are replaced with deterministic placeholders before leaving the process, and restored in tool call arguments returned by the model.\n\n## Enabling\n\nDisabled by default. Toggle via `/settings` UI or directly in `config.yml`:\n\n```yaml\nsecrets:\n  enabled: true\n```\n\n## How it works\n\n1. On session startup, secrets are collected from two sources:\n   - **Environment variables** whose names match common secret patterns (`KEY`, `SECRET`, `TOKEN`, `PASSWORD`, `PASS`, `AUTH`, `CREDENTIAL`, `PRIVATE`, `OAUTH`) with values >= 8 characters\n   - **`secrets.yml` files** (see below)\n\n2. Outbound text messages to the LLM have secret values replaced with deterministic placeholders like `#AB12#`.\n\n3. Session context/tool arguments returned from the model are deep-walked and obfuscation placeholders are restored to original values before display or execution.\n\nTwo modes control what happens to each secret:\n\n| Mode                  | Behavior                                                | Reversible                                      |\n| --------------------- | ------------------------------------------------------- | ----------------------------------------------- |\n| `obfuscate` (default) | Replaced with deterministic placeholder `#[A-Z0-9]{4}#` | Yes (deobfuscated in tool args/session context) |\n| `replace`             | Replaced with deterministic same-length string          | No (one-way)                                    |\n\n## secrets.yml\n\nDefine custom secret entries in YAML. Two locations are checked:\n\n| Level   | Path                       | Purpose                     |\n| ------- | -------------------------- | --------------------------- |\n| Global  | `~/.skc/agent/secrets.yml` | Secrets across all projects |\n| Project | `<cwd>/.skc/secrets.yml`   | Project-specific secrets    |\n\nProject entries override global entries with matching `content`.\n\n### Schema\n\nEach entry in the array has these fields:\n\n| Field         | Type                         | Required | Description                                       |\n| ------------- | ---------------------------- | -------- | ------------------------------------------------- |\n| `type`        | `\"plain\"` or `\"regex\"`       | Yes      | Match strategy                                    |\n| `content`     | string                       | Yes      | The secret value (plain) or regex pattern (regex) |\n| `mode`        | `\"obfuscate\"` or `\"replace\"` | No       | Default: `\"obfuscate\"`                            |\n| `replacement` | string                       | No       | Custom replacement (replace mode only)            |\n| `flags`       | string                       | No       | Regex flags (regex type only)                     |\n\n### Examples\n\n#### Plain secrets\n\n```yaml\n# Obfuscate a specific API key (default mode)\n- type: plain\n  content: sk-proj-abc123def456\n\n# Replace a database password with a fixed string\n- type: plain\n  content: hunter2\n  mode: replace\n  replacement: \"********\"\n```\n\n#### Regex secrets\n\n```yaml\n# Obfuscate any AWS-style key\n- type: regex\n  content: \"AKIA[0-9A-Z]{16}\"\n\n# Case-insensitive match with explicit flags\n- type: regex\n  content: \"api[_-]?key\\\\s*=\\\\s*\\\\w+\"\n  flags: \"i\"\n\n# Regex literal syntax (pattern and flags in one string)\n- type: regex\n  content: \"/bearer\\\\s+[a-zA-Z0-9._~+\\\\/=-]+/i\"\n```\n\nRegex entries always scan globally (the `g` flag is enforced automatically). The regex literal syntax `/pattern/flags` is supported as an alternative to separate `content` + `flags` fields. Escaped slashes within the pattern (`\\\\/`) are handled correctly.\n\n#### Replace mode with regex\n\n```yaml\n# One-way replace connection strings (not reversible)\n- type: regex\n  content: \"postgres://[^\\\\s]+\"\n  mode: replace\n  replacement: \"postgres://***\"\n```\n\n## Interaction with env var detection\n\nEnvironment variables are collected first, then file-defined entries are appended. File entries can cover secrets that don't live in env vars (config files, hardcoded values, etc.). If the same plain value appears in both env and file entries, the env entry's obfuscate-mode mapping is used first.\n\n## Key files\n\n- `packages/coding-agent/src/secrets/index.ts` -- loading, merging, env var collection\n- `packages/coding-agent/src/secrets/obfuscator.ts` -- `SecretObfuscator` class, placeholder generation, message obfuscation\n- `packages/coding-agent/src/secrets/regex.ts` -- regex literal parsing and compilation\n- `packages/coding-agent/src/config/settings-schema.ts` -- `secrets.enabled` setting definition\n\n## See also\n\n- [`auth-broker-gateway.md`](./auth-broker-gateway.md) -- remote credential vault and forward-proxy that keep provider OAuth refresh tokens and access tokens off developer hosts entirely (complementary to in-process obfuscation).\n",
 	"session-operations-export-share-fork-resume.md": "# Session Operations: export, dump, share, fork, resume/continue\n\nThis document describes operator-visible behavior for session export/share/fork/resume operations as currently implemented.\n\n## Implementation files\n\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- [`../src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts)\n- [`../src/export/html/index.ts`](../packages/coding-agent/src/export/html/index.ts)\n- [`../src/export/custom-share.ts`](../packages/coding-agent/src/export/custom-share.ts)\n- [`../src/main.ts`](../packages/coding-agent/src/main.ts)\n\n## Operation matrix\n\n| Operation                               | Entry path                | Session mutation                      | Session file creation/switch                                                       | Output artifact                                                                  |\n| --------------------------------------- | ------------------------- | ------------------------------------- | ---------------------------------------------------------------------------------- | -------------------------------------------------------------------------------- | ---- |\n| `/dump`                                 | Interactive slash command | No                                    | No                                                                                 | Clipboard text                                                                   |\n| `/export [path]`                        | Interactive slash command | No                                    | No                                                                                 | HTML file                                                                        |\n| `--export <session.jsonl> [outputPath]` | CLI startup fast-path     | No runtime session mutation           | No active session; reads target file                                               | HTML file                                                                        |\n| `/share`                                | Interactive slash command | No                                    | No                                                                                 | Temp HTML + share URL/gist                                                       |\n| `/fork`                                 | Interactive slash command | Yes (active session identity changes) | Creates new session file and switches current session to it (persistent mode only) | Copies artifact directory to new session namespace when present                  |\n| `--fork <id                             | path>`                    | CLI startup                           | Yes after session creation                                                         | Creates a new session fork from the selected source into current cwd/session dir | None |\n| `/resume`                               | Interactive slash command | Yes (active in-memory state replaced) | Switches to selected existing session file                                         | None                                                                             |\n| `--resume`                              | CLI startup (picker)      | Yes after session creation            | Opens selected existing session file                                               | None                                                                             |\n| `--resume <id                           | path>`                    | CLI startup                           | Yes after session creation                                                         | Opens existing session; cross-project case can fork into current project         | None |\n| `--continue`                            | CLI startup               | Yes after session creation            | Opens terminal breadcrumb or most-recent session; creates new one if none exists   | None                                                                             |\n\n## Export and dump\n\n### `/export [outputPath]` (interactive)\n\nFlow:\n\n1. `InputController` routes `/export...` to `CommandController.handleExportCommand`.\n2. The command splits on whitespace and uses only the first argument after `/export` as `outputPath`.\n3. `AgentSession.exportToHtml()` calls `exportSessionToHtml(sessionManager, state, { outputPath, themeName })`.\n4. On success, UI shows path and opens the file in browser.\n\nBehavior details:\n\n- `--copy`, `clipboard`, and `copy` arguments are explicitly rejected with a warning to use `/dump`.\n- Export embeds session header/entries/leaf plus current `systemPrompt` and tool descriptions from agent state.\n- No session entries are appended during export.\n\nCaveat:\n\n- Argument parsing is whitespace-based (`text.split(/\\s+/)`), so quoted paths with spaces are not preserved as a single path by this command path.\n\n### `--export <inputSessionFile> [outputPath]` (CLI)\n\nFlow in `main.ts`:\n\n1. Handled early (before interactive/session startup).\n2. Calls `exportFromFile(inputPath, outputPath?)`.\n3. `SessionManager.open(inputPath)` loads entries, then HTML is generated and written.\n4. Process prints `Exported to: ...` and exits.\n\nBehavior details:\n\n- Missing input file surfaces as `File not found: <path>`.\n- This path does not create an `AgentSession` and does not mutate any running session.\n\n### `/dump` (interactive clipboard export)\n\nFlow:\n\n1. `CommandController.handleDumpCommand()` calls `session.formatSessionAsText()`.\n2. If empty string, reports `No messages to dump yet.`\n3. Otherwise copies to clipboard via native `copyToClipboard`.\n\nDump content includes:\n\n- System prompt\n- Active model/thinking level\n- Tool definitions + parameters\n- User/assistant messages\n- Thinking blocks and tool calls\n- Tool results and execution blocks (except `excludeFromContext` bash/python entries)\n- Custom/hook/file mention/branch summary/compaction summary entries\n\nNo session persistence changes are made by dumping.\n\n## Share\n\n`/share` is interactive-only and always starts by exporting current session to a temp HTML file.\n\n### Phase 1: temp export\n\n- Temp file path: `${os.tmpdir()}/${Snowflake.next()}.html`\n- Uses `session.exportToHtml(tmpFile)`\n- If export fails (notably in-memory sessions), share ends with error.\n\n### Phase 2: custom share handler (if present)\n\n`loadCustomShare()` checks `~/.skc/agent` for first existing candidate:\n\n- `share.ts`\n- `share.js`\n- `share.mjs`\n\nRequirements:\n\n- Module must default-export a function `(htmlPath) => Promise<CustomShareResult | string | undefined>`.\n\nIf present and valid:\n\n- UI enters `Sharing...` loader state.\n- Handler result interpretation:\n  - string => treated as URL, shown and opened\n  - object => `url` and/or `message` shown; `url` opened\n  - `undefined`/falsy => generic `Session shared`\n- Temp file is removed after completion.\n\nCritical fallback behavior:\n\n- If custom handler exists but loading fails, command errors and returns.\n- If custom handler executes and throws, command errors and returns.\n- In both failure cases, it **does not** fall back to GitHub gist.\n- Gist fallback happens only when no custom share script exists.\n\n### Phase 3: default gist fallback\n\nOnly when no custom share handler is found:\n\n1. Validates `gh auth status`.\n2. Shows `Creating gist...` loader.\n3. Runs `gh gist create --public=false <tmpFile>`.\n4. Parses gist URL, derives gist id, builds preview URL `https://gistpreview.github.io/?<id>`.\n5. Shows both preview and gist URLs; opens preview.\n\nCancellation/abort semantics in share:\n\n- Loader has `onAbort` hook that restores editor UI and reports `Share cancelled`.\n- The underlying `gh gist create` command is not passed an abort signal in this code path; cancellation is UI-level and checked after command returns.\n\n## Fork\n\nInteractive `/fork` creates a new session from the current one and switches the active session identity.\n\n### Preconditions and immediate guards\n\n- If agent is streaming, `/fork` is rejected with warning.\n- UI status/loading indicators are cleared before operation.\n\n### Session-level flow\n\n`AgentSession.fork()`:\n\n1. Emits `session_before_switch` with `reason: \"fork\"` (cancellable).\n2. Flushes pending writes.\n3. Calls `SessionManager.fork()`.\n4. Copies artifacts directory from old session namespace to new namespace (best-effort; non-ENOENT copy failures are logged, not fatal).\n5. Updates `agent.sessionId`.\n6. Emits `session_switch` with `reason: \"fork\"`.\n\n`SessionManager.fork()` behavior:\n\n- Requires persistent mode and existing session file.\n- Creates new session id and new JSONL file path.\n- Rewrites header with:\n  - new `id`\n  - new timestamp\n  - `cwd` unchanged\n  - `parentSession` set to previous session id\n- Keeps all non-header entries unchanged in the new file.\n\n### Non-persistent behavior\n\n- In-memory session manager returns `undefined` from `fork()`.\n- `AgentSession.fork()` returns `false`.\n- UI reports `Fork failed (session not persisted or cancelled)`.\n\n### CLI `--fork <id|path>`\n\nStartup `--fork` is resolved before normal session creation:\n\n1. `--fork` is rejected with `--no-session`.\n2. Path-like values (`/`, `\\`, or `.jsonl`) call `SessionManager.forkFrom(path, cwd, sessionDir)`.\n3. Other values resolve like resumable session ids via current scope and then global search when allowed.\n4. The forked file is created in the current cwd/session-dir scope and becomes the active session manager for startup.\n\n## Resume and continue\n\n## Interactive `/resume`\n\nFlow:\n\n1. Opens session selector populated via `SessionManager.list(currentCwd, currentSessionDir)`.\n2. On selection, `SelectorController.handleResumeSession(sessionPath)` calls `session.switchSession(sessionPath)`.\n3. UI clears/rebuilds chat and todos, then reports `Resumed session`.\n\nNotes:\n\n- This picker only lists sessions in the current session directory scope.\n- It does not use global cross-project search.\n\n## CLI `--resume`\n\n### `--resume` (no value)\n\n- `main.ts` lists sessions for current cwd/sessionDir and opens picker.\n- Selected path is opened with `SessionManager.open(selectedPath)` before session creation.\n\n### `--resume <value>`\n\n`createSessionManager()` resolution order:\n\n1. If value looks like path (`/`, `\\`, or `.jsonl`), open directly.\n2. Else treat as id prefix:\n   - search current scope (`SessionManager.list(cwd, sessionDir)`)\n   - if not found and no explicit `sessionDir`, search global (`SessionManager.listAll()`)\n\nCross-project id match behavior:\n\n- If matched session cwd differs from current cwd, CLI asks:\n  - `Session found in different project ... Fork into current directory? [y/N]`\n- On yes: `SessionManager.forkFrom(match.path, cwd, sessionDir)` creates a new local forked file.\n- On no/non-TTY default: command errors.\n\n## CLI `--continue`\n\n`SessionManager.continueRecent(cwd, sessionDir)`:\n\n1. Resolves session dir for current cwd.\n2. Reads terminal-scoped breadcrumb first.\n3. Falls back to most recently modified session file.\n4. Opens found session; if none exists, creates new session.\n\nThis is startup-only behavior; there is no interactive `/continue` slash command.\n\n## How session switching actually mutates runtime state\n\n`AgentSession.switchSession(sessionPath)` does the runtime transition used by resume-like operations:\n\n1. Emit `session_before_switch` with `reason: \"resume\"` and `targetSessionFile` (cancellable).\n2. Disconnect agent event subscription and abort in-flight work.\n3. Clear queued steering/follow-up/next-turn messages.\n4. Flush current session manager writes.\n5. `sessionManager.setSessionFile(sessionPath)` and update `agent.sessionId`.\n6. Build session context from loaded entries.\n7. Emit `session_switch` with `reason: \"resume\"`.\n8. Replace agent messages from context.\n9. Restore model (if available in current registry).\n10. Restore or initialize thinking level.\n11. Reconnect agent event subscription.\n\nNo new session file is created by `switchSession()` itself.\n\n## Event emissions and cancellation points\n\n### Switch/fork lifecycle hooks\n\nFor `newSession`, `fork`, and `switchSession`:\n\n- Before event: `session_before_switch`\n  - reasons: `new`, `fork`, `resume`\n  - cancellable by returning `{ cancel: true }`\n- After event: `session_switch`\n  - same reason set\n  - includes `previousSessionFile`\n\n`ExtensionRunner.emit()` returns early on the first cancelling before-event result.\n\n### Custom tool `onSession` behavior\n\nSDK bridges extension session events to custom tool `onSession` callbacks:\n\n- `session_switch` -> `onSession({ reason: \"switch\", previousSessionFile })`\n- `session_branch` -> `reason: \"branch\"`\n- `session_start` -> `reason: \"start\"`\n- `session_tree` -> `reason: \"tree\"`\n- `session_shutdown` -> `reason: \"shutdown\"`\n\nThese callbacks are observational; they do not cancel switch/fork.\n\n### Other cancellation surfaces relevant to this doc\n\n- `/fork` is blocked while streaming (user must wait/abort current response first).\n- `/resume` selector can be cancelled by user closing selector.\n- Cross-project `--resume <id>` can be cancelled by declining fork prompt.\n- `/share` has UI abort path (`Share cancelled`) for gist flow; it does not wire process-kill semantics for `gh gist create` in this code path.\n\n## Non-persistent (in-memory) session behavior\n\nWhen session manager is created with `SessionManager.inMemory()` (`--no-session`):\n\n- Session file path is absent.\n- `/export` and `/share` fail with `Cannot export in-memory session to HTML` (propagated to command error UI).\n- `/fork` fails because `SessionManager.fork()` requires persistence.\n- `/dump` still works because it serializes in-memory agent state.\n- CLI resume/continue semantics are bypassed if `--no-session` is set, because manager creation returns in-memory immediately.\n\n## Known implementation caveats (as of current code)\n\n- `SelectorController.handleResumeSession()` does not check the boolean result from `session.switchSession(...)`; a hook-cancelled switch can still proceed through UI \"Resumed session\" repaint/status path.\n- `/share` custom-share failures do not degrade to default gist fallback; they terminate the command with error.\n- `/export` argument tokenization is simplistic and does not preserve quoted paths with spaces.\n",
@@ -67,7 +68,8 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"session-tree-plan.md": "# Session tree architecture (current)\n\nReference: [session.md](../docs/session.md)\n\nThis document describes how session tree navigation works today: in-memory tree model, leaf movement rules, branching behavior, and extension/event integration.\n\n## What this subsystem is\n\nThe session is stored as an append-only entry log, but runtime behavior is tree-based:\n\n- Every non-header entry has `id` and `parentId`.\n- The active position is `leafId` in `SessionManager`.\n- Appending an entry always creates a child of the current leaf.\n- Branching does **not** rewrite history; it only changes where the leaf points before the next append.\n\nKey files:\n\n- `src/session/session-manager.ts` — tree data model, traversal, leaf movement, branch/session extraction\n- `src/session/agent-session.ts` — `/tree` navigation flow, summarization, hook/event emission\n- `src/modes/components/tree-selector.ts` — interactive tree UI behavior and filtering\n- `src/modes/controllers/selector-controller.ts` — selector orchestration for `/tree` and `/branch`\n- `src/modes/controllers/input-controller.ts` — command routing (`/tree`, `/branch`, double-escape behavior)\n- `src/session/messages.ts` — conversion of `branch_summary`, `compaction`, and `custom_message` entries into LLM context messages\n\n## Tree data model in `SessionManager`\n\nRuntime indices:\n\n- `#byId: Map<string, SessionEntry>` — fast lookup for any entry\n- `#leafId: string | null` — current position in the tree\n- `#labelsById: Map<string, string>` — resolved labels by target entry id\n\nTree APIs:\n\n- `getBranch(fromId?)` walks parent links to root and returns root→node path\n- `getTree()` returns `SessionTreeNode[]` (`entry`, `children`, `label`)\n  - parent links become children arrays\n  - entries with missing parents are treated as roots\n  - children are sorted oldest→newest by timestamp\n- `getChildren(parentId)` returns direct children\n- `getLabel(id)` resolves current label from `labelsById`\n\n`getTree()` is a runtime projection; persistence remains append-only JSONL entries.\n\n## Leaf movement semantics\n\nThere are three leaf movement primitives:\n\n1. `branch(entryId)`\n   - Validates entry exists\n   - Sets `leafId = entryId`\n   - No new entry is written\n\n2. `resetLeaf()`\n   - Sets `leafId = null`\n   - Next append creates a new root entry (`parentId = null`)\n\n3. `branchWithSummary(branchFromId, summary, details?, fromExtension?)`\n   - Accepts `branchFromId: string | null`\n   - Sets `leafId = branchFromId`\n   - Appends a `branch_summary` entry as child of that leaf\n   - When `branchFromId` is `null`, `fromId` is persisted as `\"root\"`\n\n## `/tree` navigation behavior (same session file)\n\n`AgentSession.navigateTree()` is navigation, not file forking.\n\nFlow:\n\n1. Validate target and compute abandoned path (`collectEntriesForBranchSummary`)\n2. Emit `session_before_tree` with `TreePreparation`\n3. Optionally summarize abandoned entries (hook-provided summary or built-in summarizer)\n4. Compute new leaf target:\n   - selecting a **user** message: leaf moves to its parent, and message text is returned for editor prefill\n   - selecting a **custom_message**: same rule as user message (leaf = parent, text prefills editor)\n   - selecting any other entry: leaf = selected entry id\n5. Apply leaf move:\n   - with summary: `branchWithSummary(newLeafId, ...)`\n   - without summary and `newLeafId === null`: `resetLeaf()`\n   - otherwise: `branch(newLeafId)`\n6. Rebuild agent context from new leaf and emit `session_tree`\n\nImportant: summary entries are attached at the **new navigation position**, not on the abandoned branch tail.\n\n## `/branch` behavior (new session file)\n\n`/branch` and `/tree` are intentionally different:\n\n- `/tree` navigates within the current session file.\n- `/branch` creates a new session branch file (or in-memory replacement for non-persistent mode).\n\nUser-facing `/branch` flow (`SelectorController.showUserMessageSelector` → `AgentSession.branch`):\n\n- Branch source must be a **user message**.\n- Selected user text is extracted for editor prefill.\n- If selected user message is root (`parentId === null`): start a new session via `newSession({ parentSession: previousSessionFile })`.\n- Otherwise: `createBranchedSession(selectedEntry.parentId)` to fork history up to the selected prompt boundary.\n\n`SessionManager.createBranchedSession(leafId)` specifics:\n\n- Builds root→leaf path via `getBranch(leafId)`; throws if missing.\n- Excludes existing `label` entries from copied path.\n- Rebuilds fresh label entries from resolved `labelsById` for entries that remain in path.\n- Persistent mode: writes new JSONL file and switches manager to it; returns new file path.\n- In-memory mode: replaces in-memory entries; returns `undefined`.\n\n## Context reconstruction and summary/custom integration\n\n`buildSessionContext()` (in `session-manager.ts`) resolves the active root→leaf path and builds effective LLM context state:\n\n- Tracks latest thinking/model/service-tier/mode/TTSR/MCP-selection state on path.\n- Handles latest compaction on path:\n  - emits compaction summary first\n  - replays kept messages from `firstKeptEntryId` to compaction point\n  - then replays post-compaction messages\n- Includes `branch_summary` and `custom_message` entries as `AgentMessage` objects.\n\n`session/messages.ts` then maps these message types for model input:\n\n- `branchSummary` and `compactionSummary` become user-role templated context messages\n- `custom`/`hookMessage` become user-role content messages\n\nSo tree movement changes context by changing the active leaf path, not by mutating old entries.\n\n## Labels and tree UI behavior\n\nLabel persistence:\n\n- `appendLabelChange(targetId, label?)` writes `label` entries on the current leaf chain.\n- `labelsById` is updated immediately (set or delete).\n- `getTree()` resolves current label onto each returned node.\n\nTree selector behavior (`tree-selector.ts`):\n\n- Flattens tree for navigation, keeps active-path highlighting, and prioritizes displaying the active branch first.\n- Supports filter modes: `default`, `no-tools`, `user-only`, `labeled-only`, `all`.\n- Supports free-text search over rendered semantic content.\n- `Shift+L` opens inline label editing and writes via `appendLabelChange`.\n\nCommand routing:\n\n- `/tree` always opens tree selector.\n- `/branch` opens user-message selector unless `doubleEscapeAction=tree`, in which case it also uses tree selector UX.\n\n## Extension and hook touchpoints for tree operations\n\nCommand-time extension API (`ExtensionCommandContext`):\n\n- `branch(entryId)` — create branched session file\n- `navigateTree(targetId, { summarize? })` — move within current tree/file\n\nEvents around tree navigation:\n\n- `session_before_tree`\n  - receives `TreePreparation`:\n    - `targetId`\n    - `oldLeafId`\n    - `commonAncestorId`\n    - `entriesToSummarize`\n    - `userWantsSummary`\n  - may cancel navigation\n  - may provide summary payload used instead of built-in summarizer\n  - receives abort `signal` (Escape cancellation path)\n- `session_tree`\n  - emits `newLeafId`, `oldLeafId`\n  - includes `summaryEntry` when a summary was created\n  - `fromExtension` indicates summary origin\n\nAdjacent but related lifecycle hooks:\n\n- `session_before_branch` / `session_branch` for `/branch` flow\n- `session_before_compact`, `session.compacting`, `session_compact` for compaction entries that later affect tree-context reconstruction\n\n## Real constraints and edge conditions\n\n- `branch()` cannot target `null`; use `resetLeaf()` for root-before-first-entry state.\n- `branchWithSummary()` supports `null` target and records `fromId: \"root\"`.\n- Selecting current leaf in tree selector is a no-op.\n- Summarization requires an active model; if absent, summarize navigation fails fast.\n- If summarization is aborted, navigation is cancelled and leaf is unchanged.\n- In-memory sessions never return a branch file path from `createBranchedSession`.\n- Tree context reconstruction includes service-tier and MCP tool-selection state, but those entries do not become LLM messages.\n\n## Plan approval session naming\n\nWhen a user approves a plan from plan mode (`InteractiveMode.#approvePlan`), the approval handler seeds the session name from the plan's title so the resulting (fresh or compacted) session does not stay unnamed.\n\nTrigger:\n\n- Plan approval reaches `#approvePlan(...)` with `options.title` populated from the plan-approval details.\n- This runs for every approval choice (`Approve and execute`, `Approve and compact context`, plain `Approve`); the synthetic `plan-approved` prompt is what otherwise bypasses the input-controller's title-generation path.\n\nNaming source:\n\n- The normalized plan title is humanized via `humanizePlanTitle(title)` (`packages/coding-agent/src/plan-mode/approved-plan.ts`):\n  - replaces runs of `-`/`_` with a single space\n  - trims whitespace\n  - capitalizes the first character\n  - returns `\"\"` for whitespace-only / separator-only input\n- The humanized name is applied with `sessionManager.setSessionName(name, \"auto\")`. Because `setSessionName` is a no-op when `titleSource === \"user\"`, the seeded name never overrides a name the user already chose (e.g. on the `preserveContext` path where the session continues with prior naming).\n- On successful apply, the terminal title (`setSessionTerminalTitle`) and the editor border color are refreshed to reflect the new name.\n\nExamples (from `humanizePlanTitle`):\n\n- `migrate-mcp-loader` → `Migrate mcp loader`\n- `fix_session_naming` → `Fix session naming`\n- `foo--bar__baz` → `Foo bar baz`\n- `RefactorRouter` → `RefactorRouter` (no separators to expand)\n- `\"\"` / `\"---\"` → `\"\"` (no name applied)\n\n## Legacy compatibility still present\n\nSession migrations still run on load:\n\n- v1→v2 adds `id`/`parentId` and converts compaction index anchor to id anchor\n- v2→v3 migrates legacy `hookMessage` role to `custom`\n\nCurrent runtime behavior is version-3 tree semantics after migration.\n",
 	"session.md": "# Session Storage and Entry Model\n\nThis document is the source of truth for how coding-agent sessions are represented, persisted, migrated, and reconstructed at runtime.\n\n## Scope\n\nCovers:\n\n- Session JSONL format and versioning\n- Entry taxonomy and tree semantics (`id`/`parentId` + leaf pointer)\n- Migration/compatibility behavior when loading old or malformed files\n- Context reconstruction (`buildSessionContext`)\n- Persistence guarantees, failure behavior, truncation/blob externalization\n- Storage abstractions (`FileSessionStorage`, `MemorySessionStorage`) and related utilities\n\nDoes not cover `/tree` UI rendering behavior beyond semantics that affect session data.\n\n## Implementation Files\n\n- [`src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts)\n- [`src/session/messages.ts`](../packages/coding-agent/src/session/messages.ts)\n- [`src/session/session-storage.ts`](../packages/coding-agent/src/session/session-storage.ts)\n- [`src/session/history-storage.ts`](../packages/coding-agent/src/session/history-storage.ts)\n- [`src/session/blob-store.ts`](../packages/coding-agent/src/session/blob-store.ts)\n\n## On-Disk Layout\n\nDefault session file location:\n\n```text\n~/.skc/agent/sessions/--<cwd-encoded>--/<timestamp>_<sessionId>.jsonl\n```\n\n`<cwd-encoded>` is derived from the working directory by stripping leading slash and replacing `/`, `\\\\`, and `:` with `-`.\n\nBlob store location:\n\n```text\n~/.skc/agent/blobs/<sha256>\n```\n\nTerminal breadcrumb files are written under:\n\n```text\n~/.skc/agent/terminal-sessions/<terminal-id>\n```\n\nBreadcrumb content is two lines: original cwd, then session file path. `continueRecent()` prefers this terminal-scoped pointer before scanning most-recent mtime.\n\n## File Format\n\nSession files are JSONL: one JSON object per line.\n\n- Line 1 is always the session header (`type: \"session\"`).\n- Remaining lines are `SessionEntry` values.\n- Entries are append-only at runtime; branch navigation moves a pointer (`leafId`) rather than mutating existing entries.\n\n### Header (`SessionHeader`)\n\n```json\n{\n  \"type\": \"session\",\n  \"version\": 3,\n  \"id\": \"1f9d2a6b9c0d1234\",\n  \"timestamp\": \"2026-02-16T10:20:30.000Z\",\n  \"cwd\": \"/work/pi\",\n  \"title\": \"optional session title\",\n  \"titleSource\": \"auto\",\n  \"parentSession\": \"optional lineage marker\"\n}\n```\n\nNotes:\n\n- `version` is optional in v1 files; absence means v1.\n- `parentSession` is an opaque lineage string. Current code writes either a session id or a session path depending on flow (`fork`, `forkFrom`, `createBranchedSession`, or explicit `newSession({ parentSession })`). Treat as metadata, not a typed foreign key.\n\n### Entry Base (`SessionEntryBase`)\n\nAll non-header entries include:\n\n```json\n{\n  \"type\": \"...\",\n  \"id\": \"8-char-id\",\n  \"parentId\": \"previous-or-branch-parent\",\n  \"timestamp\": \"2026-02-16T10:20:30.000Z\"\n}\n```\n\n`parentId` can be `null` for a root entry (first append, or after `resetLeaf()`).\n\n## Entry Taxonomy\n\n`SessionEntry` is the union of:\n\n- `message`\n- `thinking_level_change`\n- `service_tier_change`\n- `compaction`\n- `branch_summary`\n- `custom`\n- `custom_message`\n- `label`\n- `ttsr_injection`\n- `session_init`\n- `mode_change`\n- `mcp_tool_selection`\n\n### `message`\n\nStores an `AgentMessage` directly.\n\n```json\n{\n  \"type\": \"message\",\n  \"id\": \"a1b2c3d4\",\n  \"parentId\": null,\n  \"timestamp\": \"2026-02-16T10:21:00.000Z\",\n  \"message\": {\n    \"role\": \"assistant\",\n    \"provider\": \"anthropic\",\n    \"model\": \"anthropic-model-sonnet-4-5\",\n    \"content\": [{ \"type\": \"text\", \"text\": \"Done.\" }],\n    \"usage\": {\n      \"input\": 100,\n      \"output\": 20,\n      \"cacheRead\": 0,\n      \"cacheWrite\": 0,\n      \"cost\": {\n        \"input\": 0,\n        \"output\": 0,\n        \"cacheRead\": 0,\n        \"cacheWrite\": 0,\n        \"total\": 0\n      }\n    },\n    \"timestamp\": 1760000000000\n  }\n}\n```\n\n### `model_change`\n\n```json\n{\n  \"type\": \"model_change\",\n  \"id\": \"b1c2d3e4\",\n  \"parentId\": \"a1b2c3d4\",\n  \"timestamp\": \"2026-02-16T10:21:30.000Z\",\n  \"model\": \"openai/gpt-4o\",\n  \"role\": \"default\"\n}\n```\n\n`role` is optional; missing is treated as `default` in context reconstruction.\n\n### `service_tier_change`\n\n```json\n{\n  \"type\": \"service_tier_change\",\n  \"id\": \"c1d2e3f4\",\n  \"parentId\": \"b1c2d3e4\",\n  \"timestamp\": \"2026-02-16T10:21:45.000Z\",\n  \"serviceTier\": \"flex\"\n}\n```\n\n`serviceTier` can also be `null`.\n\n### `thinking_level_change`\n\n```json\n{\n  \"type\": \"thinking_level_change\",\n  \"id\": \"c1d2e3f4\",\n  \"parentId\": \"b1c2d3e4\",\n  \"timestamp\": \"2026-02-16T10:22:00.000Z\",\n  \"thinkingLevel\": \"high\"\n}\n```\n\n### `compaction`\n\n```json\n{\n  \"type\": \"compaction\",\n  \"id\": \"d1e2f3a4\",\n  \"parentId\": \"c1d2e3f4\",\n  \"timestamp\": \"2026-02-16T10:23:00.000Z\",\n  \"summary\": \"Conversation summary\",\n  \"shortSummary\": \"Short recap\",\n  \"firstKeptEntryId\": \"a1b2c3d4\",\n  \"tokensBefore\": 42000,\n  \"details\": { \"readFiles\": [\"src/a.ts\"] },\n  \"preserveData\": { \"hookState\": true },\n  \"fromExtension\": false\n}\n```\n\n### `branch_summary`\n\n```json\n{\n  \"type\": \"branch_summary\",\n  \"id\": \"e1f2a3b4\",\n  \"parentId\": \"a1b2c3d4\",\n  \"timestamp\": \"2026-02-16T10:24:00.000Z\",\n  \"fromId\": \"a1b2c3d4\",\n  \"summary\": \"Summary of abandoned path\",\n  \"details\": { \"note\": \"optional\" },\n  \"fromExtension\": true\n}\n```\n\nIf branching from root (`branchFromId === null`), `fromId` is the literal string `\"root\"`.\n\n### `custom`\n\nExtension state persistence; ignored by `buildSessionContext`.\n\n```json\n{\n  \"type\": \"custom\",\n  \"id\": \"f1a2b3c4\",\n  \"parentId\": \"e1f2a3b4\",\n  \"timestamp\": \"2026-02-16T10:25:00.000Z\",\n  \"customType\": \"my-extension\",\n  \"data\": { \"state\": 1 }\n}\n```\n\n### `custom_message`\n\nExtension-provided message that does participate in LLM context. `content` can be a string or text/image content blocks, and `attribution` records whether the user or agent initiated it.\n\n```json\n{\n  \"type\": \"custom_message\",\n  \"id\": \"a2b3c4d5\",\n  \"parentId\": \"f1a2b3c4\",\n  \"timestamp\": \"2026-02-16T10:26:00.000Z\",\n  \"customType\": \"my-extension\",\n  \"content\": \"Injected context\",\n  \"display\": true,\n  \"details\": { \"debug\": false },\n  \"attribution\": \"agent\"\n}\n```\n\n### `label`\n\n```json\n{\n  \"type\": \"label\",\n  \"id\": \"b2c3d4e5\",\n  \"parentId\": \"a2b3c4d5\",\n  \"timestamp\": \"2026-02-16T10:27:00.000Z\",\n  \"targetId\": \"a1b2c3d4\",\n  \"label\": \"checkpoint\"\n}\n```\n\n`label: undefined` clears a label for `targetId`.\n\n### `ttsr_injection`\n\n```json\n{\n  \"type\": \"ttsr_injection\",\n  \"id\": \"c2d3e4f5\",\n  \"parentId\": \"b2c3d4e5\",\n  \"timestamp\": \"2026-02-16T10:28:00.000Z\",\n  \"injectedRules\": [\"ruleA\", \"ruleB\"]\n}\n```\n\n### `mcp_tool_selection`\n\n```json\n{\n  \"type\": \"mcp_tool_selection\",\n  \"id\": \"d2e3f4a5\",\n  \"parentId\": \"c2d3e4f5\",\n  \"timestamp\": \"2026-02-16T10:28:30.000Z\",\n  \"selectedToolNames\": [\"server.tool\"]\n}\n```\n\n### `session_init`\n\n```json\n{\n  \"type\": \"session_init\",\n  \"id\": \"d2e3f4a5\",\n  \"parentId\": \"c2d3e4f5\",\n  \"timestamp\": \"2026-02-16T10:29:00.000Z\",\n  \"systemPrompt\": \"...\",\n  \"task\": \"...\",\n  \"tools\": [\"read\", \"edit\"],\n  \"outputSchema\": { \"type\": \"object\" }\n}\n```\n\n### `mode_change`\n\n```json\n{\n  \"type\": \"mode_change\",\n  \"id\": \"e2f3a4b5\",\n  \"parentId\": \"d2e3f4a5\",\n  \"timestamp\": \"2026-02-16T10:30:00.000Z\",\n  \"mode\": \"plan\",\n  \"data\": { \"planFile\": \"/tmp/plan.md\" }\n}\n```\n\n## Versioning and Migration\n\nCurrent session version: `3`.\n\n### v1 -> v2\n\nApplied when header `version` is missing or `< 2`:\n\n- Adds `id` and `parentId` to each non-header entry.\n- Reconstructs a linear parent chain using file order.\n- Migrates compaction field `firstKeptEntryIndex` -> `firstKeptEntryId` when present.\n- Sets header `version = 2`.\n\n### v2 -> v3\n\nApplied when header `version < 3`:\n\n- For `message` entries: rewrites legacy `message.role === \"hookMessage\"` to `\"custom\"`.\n- Sets header `version = 3`.\n\n### Migration Trigger and Persistence\n\n- Migrations run during session load (`setSessionFile`).\n- If any migration ran, the entire file is rewritten to disk immediately.\n- Migration mutates in-memory entries first, then persists rewritten JSONL.\n\n## Load and Compatibility Behavior\n\n`loadEntriesFromFile(path)` behavior:\n\n- Missing file (`ENOENT`) -> returns `[]`.\n- Non-parseable lines are handled by lenient JSONL parser (`parseJsonlLenient`).\n- If first parsed entry is not a valid session header (`type !== \"session\"` or missing string `id`) -> returns `[]`.\n\n`SessionManager.setSessionFile()` behavior:\n\n- `[]` from loader is treated as empty/nonexistent session and replaced with a new initialized session file at that path.\n- Valid files are loaded, migrated if needed, blob refs resolved, then indexed.\n\n## Tree and Leaf Semantics\n\nThe underlying model is append-only tree + mutable leaf pointer:\n\n- Every append method creates exactly one new entry whose `parentId` is current `leafId`.\n- The new entry becomes the new `leafId`.\n- `branch(entryId)` moves only `leafId`; existing entries remain unchanged.\n- `resetLeaf()` sets `leafId = null`; next append creates a new root entry (`parentId: null`).\n- `branchWithSummary()` sets leaf to branch target and appends a `branch_summary` entry.\n\n`getEntries()` returns all non-header entries in insertion order. Existing entries are not deleted in normal operation; rewrites preserve logical history while updating representation (migrations, move, targeted rewrite helpers).\n\n## Context Reconstruction (`buildSessionContext`)\n\n`buildSessionContext(entries, leafId, byId?)` resolves what is sent to the model.\n\nAlgorithm:\n\n1. Determine leaf:\n   - `leafId === null` -> return empty context.\n   - explicit `leafId` -> use that entry if found.\n   - otherwise fallback to last entry.\n2. Walk `parentId` chain from leaf to root and reverse to root->leaf path.\n3. Derive runtime state across path:\n   - `thinkingLevel` from latest `thinking_level_change` (default `\"off\"`)\n   - `serviceTier` from latest `service_tier_change`\n   - model map from `model_change` entries (`role ?? \"default\"`)\n   - fallback `models.default` from assistant message provider/model if no explicit model change\n   - deduplicated `injectedTtsrRules` from all `ttsr_injection` entries\n   - selected MCP discovery tools from latest `mcp_tool_selection`\n   - mode/modeData from latest `mode_change` (default mode `\"none\"`)\n4. Build message list:\n   - `message` entries pass through\n   - `custom_message` entries become `custom` AgentMessages via `createCustomMessage`\n   - `branch_summary` entries become `branchSummary` AgentMessages via `createBranchSummaryMessage`\n   - if a `compaction` exists on path:\n     - emit compaction summary first (`createCompactionSummaryMessage`)\n     - emit path entries starting at `firstKeptEntryId` up to the compaction boundary\n     - emit entries after the compaction boundary\n\n`custom`, `session_init`, `service_tier_change`, `mcp_tool_selection`, and `ttsr_injection` entries do not inject model context directly.\n\n## Persistence Guarantees and Failure Model\n\n### Persist vs in-memory\n\n- `SessionManager.create/open/continueRecent/forkFrom` -> persistent mode (`persist = true`).\n- `SessionManager.inMemory` -> non-persistent mode (`persist = false`) with `MemorySessionStorage`.\n\n### Write pipeline\n\nWrites are serialized through an internal promise chain (`#persistChain`) and `NdjsonFileWriter`.\n\n- `append*` updates in-memory state immediately.\n- Persistence is deferred until at least one assistant message exists.\n  - Before first assistant: entries are retained in memory; no file append occurs.\n  - When first assistant exists: full in-memory session is flushed to file.\n  - Afterwards: new entries append incrementally.\n\nRationale in code: avoid persisting sessions that never produced an assistant response.\n\n### Durability operations\n\n- `flush()` flushes writer and calls `fsync()`.\n- Atomic full rewrites (`#rewriteFile`) write to temp file, flush+fsync, close, then rename over target.\n- Used for migrations, `setSessionName`, `rewriteEntries`, move operations, and tool-call arg rewrites.\n\n### Error behavior\n\n- Persistence errors are latched (`#persistError`) and rethrown on subsequent operations.\n- First error is logged once with session file context.\n- Writer close is best-effort but propagates the first meaningful error.\n\n## Data Size Controls and Blob Externalization\n\nBefore persisting entries:\n\n- Large strings are truncated to `MAX_PERSIST_CHARS` (500,000 chars) with notice:\n  - `\"[Session persistence truncated large content]\"`\n- Transient fields `partialJson` and `jsonlEvents` are removed.\n- If object has both `content` and `lineCount`, line count is recomputed after truncation.\n- Image blocks in `content` arrays with base64 length >= 1024 are externalized to blob refs:\n  - stored as `blob:sha256:<hash>`\n  - raw bytes written to blob store (`BlobStore.put`)\n\nOn load, blob refs are resolved back to base64 for message/custom_message image blocks.\n\n## Storage Abstractions\n\n`SessionStorage` interface provides all filesystem operations used by `SessionManager`:\n\n- sync: `ensureDirSync`, `existsSync`, `writeTextSync`, `statSync`, `listFilesSync`\n- async: `exists`, `readText`, `readTextPrefix`, `writeText`, `rename`, `unlink`, `openWriter`\n\nImplementations:\n\n- `FileSessionStorage`: real filesystem (Bun + node fs)\n- `MemorySessionStorage`: map-backed in-memory implementation for tests/non-persistent sessions\n\n`SessionStorageWriter` exposes `writeLine`, `flush`, `fsync`, `close`, `getError`.\n\n## Session Discovery Utilities\n\nDefined in `session-manager.ts`:\n\n- `getRecentSessions(sessionDir, limit)` -> lightweight metadata for UI/session picker\n- `findMostRecentSession(sessionDir)` -> newest by mtime\n- `list(cwd, sessionDir?)` -> sessions in one project scope\n- `listAll()` -> sessions across all project scopes under `~/.skc/agent/sessions`\n\nMetadata extraction reads only a prefix (`readTextPrefix(..., 4096)`) where possible.\n\n## Related but Distinct: Prompt History Storage\n\n`HistoryStorage` (`history-storage.ts`) is a separate SQLite subsystem for prompt recall/search, not session replay.\n\n- DB: `~/.skc/agent/history.db`\n- Table: `history(id, prompt, created_at, cwd)`\n- FTS5 index: `history_fts` with trigger-maintained sync\n- Deduplicates consecutive identical prompts using in-memory last-prompt cache\n- Async insertion (`setImmediate`) so prompt capture does not block turn execution\n\nUse session files for conversation graph/state replay; use `HistoryStorage` for prompt history UX.\n",
 	"skc-dogfood-skill-template.md": "# SKC dogfood local skill template\n\nIssue #93 requested a gaebal-sayknow/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 SKC-first session guidance:\n\n```sh\nmkdir -p ~/.skc/skills/skc-dogfood\ncp docs/skc-dogfood-skill-template.md ~/.skc/skills/skc-dogfood/SKILL.md\n```\n\nFor a single project, copy it to `<project>/.skc/skills/skc-dogfood/SKILL.md` instead. Do not commit that project `.skc` copy unless the project explicitly wants a local override.\n\n---\nname: skc-dogfood\ndescription: Use when running or reviewing work through SKC sessions, dogfooding Sayknow-CLI, or migrating an operator workflow from OMX to SKC.\n---\n\n# SKC Dogfood Operator Workflow\n\nUse SKC first for coding, review, planning, and follow-up sessions. Treat OMX as a fallback only when SKC is unavailable, broken, or missing a required capability.\n\n## Locate and launch SKC\n\n- Installed CLI: run `command -v skc` and then launch with `skc --tmux`.\n- Repository checkout: from the sayknow-cli repo, prefer `bun packages/coding-agent/src/cli.ts --tmux` when testing source changes before install.\n- Worktree isolation: for branch-specific work, either let SKC create a managed sibling worktree with `skc --tmux --worktree <branch-like-name>` or `cd <existing-worktree-path>` and run `skc --tmux` there. Do not pass filesystem paths to `--worktree`.\n- Name sessions explicitly with the project and issue, for example `sayknow-cli-93-dogfood-skill`, so tmux panes, logs, and exports remain traceable.\n\n## Start the session\n\n- Put git operations inside the SKC 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 SKC 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 SKC is weaker than OMX, finish the urgent work with the smallest safe fallback and file a sayknow-cli 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- `skc` cannot be located or launched after checking installed and repo-local commands;\n- authentication, model routing, tmux, or prompt submission is broken;\n- SKC lacks a required capability that OMX already has;\n- an urgent production/review deadline would be missed by debugging SKC first.\n\nRecord the fallback reason and create or link the sayknow-cli issue that would make SKC sufficient next time.\n\n## Evidence checklist\n\nReport:\n\n- project, issue, branch/worktree, and session name;\n- whether SKC 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 sayknow-cli issues for any SKC gap or fallback.\n",
-	"telegram-remote.md": "# Telegram Remote — v0 Roadmap (tiny operator button, not a cockpit)\n\nStatus: **spec + reference implementation** · Tracks issue #681 · Target: **0.6.0** · Reference implementation: [`packages/telegram-remote`](../packages/telegram-remote/README.md) (incl. rich messaging; push deferred)\n\nTelegram Remote is a tiny, safe operator surface for Sayknow-CLI (`skc`) session\n**lifecycle and observation** from a phone. It is deliberately **not** a remote\nRPC cockpit, a remote shell, a config editor, or a transcript viewer. The real\nsession owner stays SKC/tmux/harness-side; Telegram is only the control button.\n\nThis document fixes the v0 contract the issue calls out before any code lands:\nthe **first backend** (Coordinator MCP), the **preset-only session model**, the\n**minimal command contract**, the **authorization posture**, and the\n**transmitted-data allowlist**. It then splits the work into PR-sized steps.\n\n## TL;DR architecture decision\n\nv0 is a thin **command + bounded-read** surface layered on the **Coordinator\nMCP**, which already exists and already enforces the safety properties this\nroadmap needs. It introduces **no new remote-control protocol** — a second\nauthenticated control protocol would require ADR-level rationale per\n[`docs/bridge.md`](bridge.md).\n\n| Concern | Reused existing surface |\n| --- | --- |\n| Cross-session enumeration + bounded status | Coordinator MCP read tools ([`docs/bot-integration.md`](bot-integration.md), [`docs/hermes-mcp-bridge.md`](hermes-mcp-bridge.md)) |\n| Preset-bounded session creation (workdir allowlist + session command) | `SKC_COORDINATOR_MCP_WORKDIR_ROOTS`, `SKC_COORDINATOR_MCP_SESSION_COMMAND` |\n| Mutation gating (fail-closed: startup opt-in **and** per-call `allow_mutation`) | `SKC_COORDINATOR_MCP_MUTATIONS` |\n| Namespacing so one bot cannot enumerate another's state | `SKC_COORDINATOR_MCP_PROFILE`, `SKC_COORDINATOR_MCP_REPO` |\n| Bounded artifact reads (byte-capped, symlink-safe) | `SKC_COORDINATOR_MCP_ARTIFACT_BYTE_CAP` |\n\nThe only genuinely new piece is a thin **Telegram gateway**: one PC-side or\nsystemd-managed process that authenticates an allowlisted Telegram user/chat,\nmaps a four-command vocabulary onto Coordinator MCP tool calls, and projects the\nalready-bounded coordinator state into short, redacted chat messages.\n\n```\n Telegram user (allowlisted chat id)\n        │  bot commands: /start-session /sessions /observe /stop\n        ▼\n Telegram gateway  ── default-deny auth (allowlist) ──▶ reject everyone else\n   (one process)   ── preset resolve ────────────────▶ fixed workdir + command + task template\n        │          ── Coordinator MCP calls ─────────▶ skc mcp-serve coordinator\n        │\n        └─ never: arbitrary shell · raw RPC · gate answers · raw tail/transcript · secrets\n```\n\n## Why Coordinator MCP first (and not bridge or harness directly)\n\nThe issue asks which backend is the first supported target. v0 picks\n**Coordinator MCP** because it is the only existing surface that already gives\nthe gateway everything it needs without new code:\n\n- **Cross-session enumeration.** `skc_coordinator_list_sessions` answers\n  `/sessions` directly. Bridge mode serves exactly one live session per process,\n  so it cannot list.\n- **Preset-bounded creation.** `skc_coordinator_start_session` is constrained to\n  `SKC_COORDINATOR_MCP_WORKDIR_ROOTS` and launches `SKC_COORDINATOR_MCP_SESSION_COMMAND`.\n  That is exactly the \"fixed workdir root + fixed session command\" preset model\n  below — no arbitrary command string crosses Telegram.\n- **Fail-closed mutations.** Mutating calls require both a startup mutation\n  opt-in and per-call `allow_mutation: true`. Missing either fails closed, so a\n  read-only gateway is the safe default.\n- **Bounded observation.** Coordinator read tools return durable, bounded status\n  rather than raw scrollback, which matches the \"no raw dumps in Telegram\" rule.\n\nThe web \"steering wheel\" remote ([`docs/sayknow-remote.md`](sayknow-remote.md), issue\n#565) chose the harness control plane + bridge because it needs live\n`Observation`/`readyForSubmit` submit gating for a one-line submit surface.\nTelegram Remote v0 has **no submit surface** — only lifecycle and observation —\nso it does not need the harness/bridge path. The two roadmaps stay independent;\na future Telegram backend adapter could front the harness control plane behind\nthe same four commands without changing this contract.\n\n## Authority boundary contract\n\nThe Coordinator MCP and the SKC/tmux/harness runtime behind it are the sole\nauthority. The Telegram gateway and the chat user are **operators of a tiny\nbutton set**, nothing more.\n\nThe gateway MUST NOT, in v0:\n\n- run arbitrary shell, send arbitrary prompts/turns, or proxy raw RPC/MCP calls\n  from chat text;\n- accept a workdir, session command, branch, or repo chosen from chat (only\n  preset ids are accepted);\n- answer workflow-gate / permission / approval / structured questions (those\n  stay owner-side; the gateway never enables the `questions` mutation class);\n- stream raw tmux tail, transcripts, tool arguments/results, diffs, file\n  contents, environment, system prompt, or secrets to chat;\n- expand the preset task template into anything beyond a single length-capped,\n  control-char-stripped task string.\n\nThe chat user MAY, in v0:\n\n- start one session from an **approved preset** (`/start-session`);\n- list live/recent sessions with concise bounded status (`/sessions`);\n- read one session's bounded public-safe status slice (`/observe`);\n- request a graceful stop/retire for one session (`/stop`), with confirmation.\n\n## Preset-only session model\n\nSession creation is **preset-only**. A preset is a named, server-side bundle —\nnever assembled from chat input:\n\n| Preset field | Source / binding | Notes |\n| --- | --- | --- |\n| `workdir` | one entry from `SKC_COORDINATOR_MCP_WORKDIR_ROOTS` | fixed; chat cannot pass a path |\n| `sessionCommand` | `SKC_COORDINATOR_MCP_SESSION_COMMAND` | fixed; e.g. `skc --worktree`; chat cannot pass a command |\n| `taskTemplate` | optional fixed template string | optional; the only injection point is one `{{task}}` slot |\n| `taskMaxLen` | gateway config | hard length cap on the chat-supplied task string |\n| `id` | gateway config | the only preset reference a chat user may name |\n\n`/start-session <presetId> [task]` resolves `presetId` to a configured preset and,\nif the preset has a `taskTemplate`, substitutes a **single length-capped,\ncontrol-char-stripped** task string into the `{{task}}` slot. With no template,\nthe task argument is ignored or rejected per preset policy. The resolved\n`{ cwd, prompt }` is passed to `skc_coordinator_start_session` with\n`allow_mutation: true`. No part of `workdir` or `sessionCommand` is ever derived\nfrom chat input. This is the \"smallest preset format that is useful without\nbecoming arbitrary remote execution\" the issue asks for.\n\n## Command contract (v0)\n\nFour commands plus help. Everything else is rejected as unknown.\n\n| Command | Intent | Coordinator MCP mapping | Mutation |\n| --- | --- | --- | --- |\n| `/start-session <presetId> [task]` | Create a bounded session from an approved preset | `skc_coordinator_start_session` (preset `cwd` + templated `prompt`) | `sessions` |\n| `/sessions` | List live/recent sessions with concise status | `skc_coordinator_list_sessions` (+ `skc_coordinator_read_status` for derived status) | none (read) |\n| `/observe <sessionId>` | Show one session's bounded public-safe status slice | `skc_coordinator_read_status` / `skc_coordinator_read_coordination_status` | none (read) |\n| `/stop <sessionId>` | Request graceful stop/retire for a session | `skc_coordinator_report_status` with `status: \"cancelled\"` (records terminal turn state) | `reports` |\n| `/help` | Show the command set | none | none |\n\nNotes:\n\n- `/observe` deliberately uses **bounded status**, not `skc_coordinator_read_tail`.\n  Raw tail is advisory debug context that can contain scrollback and is never\n  surfaced to chat in v0.\n- `/stop` over Coordinator MCP records a **terminal turn status** (`cancelled`);\n  per the coordinator contract this is coordination state, **not** a tmux process\n  kill. v0 treats `/stop` as \"request graceful stop/retire\"; the actual process\n  teardown remains an owner-side concern. A true remote teardown is deferred and\n  gated behind an explicit decision (see open questions).\n- The gateway runs the Coordinator MCP with the **smallest** mutation set it\n  needs: `sessions` for `/start-session`, plus `reports` only if `/stop` is\n  enabled. It NEVER enables `questions`, and it exposes no read tool beyond list\n  and bounded status.\n\n## Authorization and safety posture\n\n- **Default deny.** Only an explicit allowlist of Telegram user ids (and/or chat\n  ids) may issue any command. Unlisted senders get a boring, identical refusal —\n  no capability hints, no enumeration, no preset names.\n- **No raw dumps.** Chat output is short and redacted by construction: session\n  ids, derived status, branch, timestamps. Never transcripts, tool IO, diffs,\n  file contents, env, system prompt, or secrets.\n- **Allowlisted presets only.** Session creation cannot name a workdir, command,\n  repo, or branch from chat — only a configured preset id.\n- **Confirmation for destructive actions.** `/stop` requires an explicit\n  confirmation step (e.g. a confirm callback or a second `/stop <id> confirm`)\n  before any cancellation is recorded.\n- **Stable session identity.** `/observe` and `/stop` operate on the coordinator\n  `session_id`; the gateway resolves and echoes a stable id so the operator\n  cannot accidentally stop the wrong owner.\n- **Telegram is the button, SKC owns the session.** The gateway never bypasses\n  coordinator mutation gating, never answers PC-side gates, and degrades to\n  read-only or fully closed when mutations are not opted in.\n\n## Transmitted-data contract (allowlist)\n\nOnly the fields below leave the PC into chat. Anything not listed is withheld by\ndefault; this is a typed projection from the coordinator's already-bounded\nstatus, never a passthrough of internal state.\n\n### Session list entry → chat\n\n| Field | Source | Notes |\n| --- | --- | --- |\n| `sessionId` | coordinator session id | opaque, stable id |\n| `name` | derived (repo/branch/preset or id fallback) | sanitized, length-capped |\n| `status` | derived from coordinator session/turn state | bounded enum: `idle` \\| `working` \\| `blocked` \\| `offline` |\n| `branch` | coordinator status | branch name only |\n| `lastActivityAt` | coordinator status | timestamp |\n\n### Open-session view → chat\n\n| Field | Source | Notes |\n| --- | --- | --- |\n| `sessionId`, `name`, `status`, `branch` | as above | |\n| `lifecycle` | coordinator session/turn lifecycle | bounded enum |\n| `activeTurn` | coordinator turn status | `queued`/`active`/`waiting_for_answer`/terminal, no body |\n| `blockerSummary` | coordinator status | short sanitized reason when blocked |\n\n### Never transmitted\n\nRaw tmux tail / scrollback, full transcript or message bodies, tool call\narguments or results, file contents, diffs, system prompt, environment\nvariables, tokens or secrets, and absolute paths beyond `branch`/preset\nmetadata. When content is intentionally withheld, chat shows a neutral\n*\"withheld on PC\"* marker rather than a redacted blob.\n\n## Failure states (must be boring and understandable)\n\n| Condition | Detection | Chat UX |\n| --- | --- | --- |\n| Unauthorized sender | not in allowlist | identical boring refusal; no hints |\n| Unknown preset | preset id not configured | \"unknown preset\"; no preset enumeration |\n| Mutations disabled | `coordinator_mutation_class_disabled:*` | \"session control is disabled\"; stays read-only |\n| Mutation not allowed for call | `coordinator_mutation_call_not_allowed:*` | refusal; no auto-escalation |\n| Unknown session | `unknown_session` | \"no such session\"; re-list with `/sessions` |\n| Active turn exists | `active_turn_exists` | report current turn; do not force |\n| Coordinator unreachable / session offline | liveness/`offline` | \"session offline\"; control disabled |\n| Task too long | exceeds `taskMaxLen` | rejected before any MCP call |\n\n## Open questions from the issue — v0 decisions\n\n| Question | v0 decision | Deferred |\n| --- | --- | --- |\n| Where does it live (in-repo app / example / companion package)? | Companion **gateway** spec here; first reference implementation as an example integration / small service, not a core `skc` mode | In-repo first-class mode → later, behind a decision |\n| First session backend (tmux SKC / harness / both)? | **Coordinator MCP** (covers managed + registered visible-tmux sessions) | Harness control-plane adapter behind the same four commands → later |\n| Smallest useful preset format? | Fixed `workdir` + fixed `sessionCommand` + optional fixed `taskTemplate` with one length-capped `{{task}}` slot | Multi-step / parameterized presets → later |\n| Does `/stop` kill the process? | No — v0 records coordinator terminal status (`cancelled`); teardown stays owner-side | True remote teardown → decision-gated |\n| Hosted relay vs local bot token? | Standard Telegram bot token + allowlist; PC/systemd-hosted gateway | Hosted multi-tenant relay → ADR-gated |\n\n## Implementation plan (PR-sized steps)\n\nEach step is independently shippable; later steps stay fail-closed until wired.\n\n1. **PR 1 — this doc.** `docs/telegram-remote.md` + README cross-link. Resolves\n   the backend, preset, command, authorization, and transmitted-data decisions.\n   No code.\n2. **PR 2 — preset + command contract types.** Preset shape (`id`, `workdir`,\n   `sessionCommand`, `taskTemplate?`, `taskMaxLen`), command parse model, and a\n   typed projection `coordinator status → chat summary/view`. Tests assert the\n   allowlist (no forbidden field can leak; task length cap enforced). Types only;\n   no Telegram wiring.\n3. **PR 3 — gateway read path.** `/sessions` + `/observe` over coordinator read\n   tools, behind an explicit opt-in, default-deny allowlist, redaction\n   projection. Tests for status derivation and redaction.\n4. **PR 4 — gateway create path.** `/start-session <presetId> [task]` →\n   `skc_coordinator_start_session` with preset-bound `cwd`/`prompt` and the\n   length-capped task slot. Tests for preset resolution and rejection of\n   arbitrary workdir/command/task injection.\n5. **PR 5 — gateway stop path.** `/stop <sessionId>` with confirmation →\n   coordinator `cancelled`. Tests for confirmation gating and unknown/active\n   session handling.\n6. **PR 6 — auth + hardening.** Allowlist enforcement, boring refusals, mutation\n   opt-in matrix, CHANGELOG, docs finalize. Tests prove unauthorized senders and\n   non-preset inputs are rejected before any MCP call.\n\n## Non-goals (v0)\n\n- No arbitrary Telegram-side shell or raw RPC/MCP passthrough.\n- No raw transcript/tail/secret/log dumping to chat by default.\n- No filesystem editor or config editor from chat.\n- No answering of PC-side approval/confirmation/structured-question gates.\n- No second authenticated remote-control protocol (reuse Coordinator MCP; relay\n  needs an ADR).\n- No remote-desktop replacement.\n\n## Key source references\n\n- Coordinator MCP contract + setup: [`docs/bot-integration.md`](bot-integration.md), [`docs/hermes-mcp-bridge.md`](hermes-mcp-bridge.md), `packages/coding-agent/src/commands/harness.ts`\n- External-control readiness classification: [`docs/external-control-readiness.md`](external-control-readiness.md)\n- Web \"steering wheel\" remote (sibling roadmap, harness/bridge-backed): [`docs/sayknow-remote.md`](sayknow-remote.md)\n- Bridge transport / fail-closed posture (why no second protocol): [`docs/bridge.md`](bridge.md)\n- RPC command/response contract and error shapes: [`docs/rpc.md`](rpc.md)\n- v0 reference implementation (this contract, as a small companion service): [`packages/telegram-remote`](../packages/telegram-remote/README.md)\n\n## Rich messaging and push notifications (implemented)\n\nThe reference implementation adds optional rich messaging (default on) as a presentation +\nalternate-entry layer, without widening the action surface or transmitted-data allowlist:\n\n- HTML formatting and inline keyboards (**Observe** / **Stop** / **Refresh** / **Confirm stop** /\n  **Cancel**), a `setMyCommands` Bot menu (`sessions`/`observe`/`stop`/`help`/`start`; the hyphenated\n  `/start-session` cannot be registered and is documented in `/help`), and `/start` onboarding.\n- Callback queries are a new authenticated input channel that reuses the **same** default-deny\n  authorization, the **same** `CoordinatorClient` → Coordinator MCP calls, and the **same**\n  redaction. `callback_data` is an opaque `gtr:v1:<token>` (≤64 bytes, never the session id) backed\n  by TTL-bound, chat/user-bound, single-use server-side token metadata holding the exact raw id.\n  Every callback is answered; unauthorized/expired/malformed/missing-chat/replayed/cancel callbacks\n  are answer-only (no chat message, no backend call).\n\n**Push notifications reuse the `skc_coordinator_watch_events` event surface.** Follow/Mute state is gateway-owned and bounded; delivery preserves the transmitted-data allowlist and does not introduce a Telegram-side session journal or shadow notification protocol.\n\n## RPC mode (second backend)\n\nThe package also supports a second backend, `SKC_TELEGRAM_REMOTE_BACKEND=rpc`,\nfor a single persistent session. In this mode the gateway dials an existing\nowner-only UNIX socket exposed by `skc launch --output rpc`; it never spawns,\nkills, or tears down the session. Telegram acts as an attach/detach remote\nkeyboard with `/attach`, `/detach`, `/status`, `/abort`, and `/help`/`/start`.\nCoordinator browsing commands (`/sessions`, `/observe`, `/presets`,\n`/start-session`, `/stop`) are not part of RPC mode and are rejected as unknown.\n\nRPC delivery is event-driven: agent questions and gates render as inline buttons,\nand turn completion sends only the final assistant text, HTML-escaped and\nTelegram-chunked. Session exit or liveness timeout produces exactly one\nstale-attachment alert. The socket's OS ownership is the real boundary: same-UID\nclients are fully trusted in v1, while protection targets different-UID users and\nunsafe filesystem placement. Controller ownership is last-connected-wins; a later\nUDS client becomes current, the gateway alerts once, reconnects, and resyncs.\nSee [`packages/telegram-remote/README.md`](../packages/telegram-remote/README.md)\nand [`packages/telegram-remote/.env.example`](../packages/telegram-remote/.env.example)\nfor RPC knobs.\n\n## Managed service examples\n\n`packages/telegram-remote/examples/systemd/` contains Linux systemd **user-unit** examples, which are the canonical always-on deployment path:\n\n- `skc-telegram-remote-coordinator.service` runs the default Coordinator MCP backend as one bot service.\n- `skc-rpc-session.service` runs the persistent `skc launch --output rpc --listen <socket>` session.\n- `skc-telegram-remote-rpc.service` runs the RPC Telegram bot, orders after and wants the session unit, and performs a finite socket wait because `After=` is not readiness.\n- `telegram-remote.env.example` is a service-oriented env template; copied real env files must be owner-only (`0600`).\n\n`packages/telegram-remote/examples/launchd/` contains macOS LaunchAgent parity examples. They use `com.example...` labels so operators replace the namespace, and shell wrappers source a protected env file then `exec` the real command. launchd parity cannot express systemd `Wants=`/`After=`/`BindsTo=` semantics; the RPC bot wrapper performs a finite socket wait.\n\nService examples are not a new daemon and do not change the runtime contract. Coordinator mode remains one service. RPC mode remains two services because the Telegram gateway dials an existing owner-only socket and never owns the session. The examples document the same-UID socket boundary, `last-connected-wins`, concrete socket paths, `loginctl enable-linger` for boot-start Linux user services, absolute executable paths or a service-local `PATH`, no token in units/plists/argv/logs, and install/uninstall verification.\n\n—\n*[repo owner's gaebal-sayknow (clawdbot) 🦞]*\n",
+	"skc-session-clawhip-routing.md": "# Clawhip-routed SKC sessions\n\nThis guide documents the visible tmux session pattern used by operator bots such as Clawhip, Hermes, and OpenClaw when repository work must stay observable in a routed channel.\n\nUse this pattern when a human or chatops router needs to watch the session, receive stale-session alerts, and send follow-up prompts into the same visible SKC pane.\n\nFor pure machine control, prefer the Coordinator MCP tools in [`docs/hermes-mcp-bridge.md`](./hermes-mcp-bridge.md). For a single embedded worker process, prefer [`docs/rpc.md`](./rpc.md). This visible-session pattern is the operator-facing fallback/interop lane.\n\n## Contract\n\n1. Create or verify a dedicated git worktree for the issue or PR.\n2. Register a named tmux session with the host router before launching SKC.\n3. Start interactive `skc` inside the worktree.\n4. Wait until the SKC TUI is ready.\n5. Inject the real task prompt separately.\n6. Verify acceptance from actual work evidence, not from a visible pasted prompt.\n\nDo not launch visible routed work in the canonical repo checkout. Use a worktree so branch changes, generated files, tests, and cleanup stay scoped to the task.\n\n## Session naming\n\nUse stable names that include the project and artifact id:\n\n```text\nsayknow-cli-issue-905-ctrl-shift-enter-newline\nsayknow-cli-pr-911-ctrl-shift-enter-review\nclawhip-issue-269-lightweight-zero-receipt\n```\n\nAvoid ambiguous names such as `fix-tui`, `review`, or `issue-905` when multiple repositories route into the same chat surface.\n\n## Portable script shape\n\nThe exact router command is host-owned. A Clawhip-style wrapper usually has three small scripts:\n\n```sh\n# create.sh\n# create/register a routed tmux session and start interactive skc in the worktree\ncreate-skc-session <session-name> <worktree-path> [channel-id] [mention]\n\n# prompt.sh\n# inject the real task after the TUI is ready\nprompt-skc-session <session-name> @/path/to/task.md\n\n# tail.sh\n# inspect bounded pane output before/after prompt delivery\ntail-skc-session <session-name> [lines]\n```\n\nA concrete Clawhip deployment can implement those helpers with `clawhip tmux new`, `tmux send-keys`, and `tmux capture-pane`. Keep that implementation in the host/operator repository when it depends on private channel ids, mention targets, socket names, or routing policy.\n\n## Example flow\n\n```sh\n# 1. Prepare a dedicated worktree.\ngit -C /repo/sayknow-cli fetch origin dev\ngit -C /repo/sayknow-cli worktree add \\\n  /repo/worktrees/sayknow-cli-issue-905-ctrl-shift-enter-newline \\\n  -b issue-905-ctrl-shift-enter-newline origin/dev\n\n# 2. Start the routed visible session.\ncreate-skc-session \\\n  sayknow-cli-issue-905-ctrl-shift-enter-newline \\\n  /repo/worktrees/sayknow-cli-issue-905-ctrl-shift-enter-newline \\\n  \"$CHANNEL_ID\" \\\n  \"$MENTION\"\n\n# 3. Confirm TUI readiness.\ntail-skc-session sayknow-cli-issue-905-ctrl-shift-enter-newline 80\n\n# 4. Inject the task prompt.\nprompt-skc-session \\\n  sayknow-cli-issue-905-ctrl-shift-enter-newline \\\n  @/tmp/issue-905-task.md\n\n# 5. Confirm real work started.\ntail-skc-session sayknow-cli-issue-905-ctrl-shift-enter-newline 160\n```\n\n## Prompt shape\n\nImplementation prompt:\n\n```text\n/skill:ralplan\n\nskc ultragoal fix issue #905 missed Ctrl+Shift+Enter newline case.\n\nRepo: jaybeyond/Sayknow_CLI\nWorktree: /repo/worktrees/sayknow-cli-issue-905-ctrl-shift-enter-newline\nBranch: issue-905-ctrl-shift-enter-newline\nBase: dev\n\nScope:\n- inspect parser/key matching and packages/tui/src/components/editor.ts\n- add explicit ctrl+shift+enter newline handling\n- add focused tests for the reported terminal sequences\n- run targeted verification\n- commit, push, and open a PR to dev\n\nNon-goals:\n- no unrelated tmux/session/process changes\n- no synchronous filesystem, process, tmux, network, or durable writes in keystroke paths\n```\n\nReview prompt:\n\n```text\n/skill:ralplan\n\nReview PR #911 as a red-team-only merge gate.\nInspect origin/dev...HEAD, changed files, CI, and contract risks.\nLook for blockers, regressions, test gaps, and hidden user-facing drift.\nPost MERGE_READY or REQUEST_CHANGES with evidence. Do not merge.\n```\n\n## Acceptance checks\n\nAfter prompt delivery, require one of these before reporting that the session is working:\n\n- a tool call or file read in the pane,\n- an explicit plan or todo update,\n- a diff or test command,\n- a GitHub comment/review/PR URL,\n- a terminal verdict such as `MERGE_READY` or `REQUEST_CHANGES`.\n\nA prompt being visible in tmux scrollback is not acceptance by itself.\n\n## Anti-patterns\n\n- Starting `skc -p` for long-running visible repo work.\n- Launching from the canonical repo checkout instead of a task worktree.\n- Running a long SKC/tmux session under a short shell timeout that can SIGKILL the owner process.\n- Treating tmux process existence as proof that the prompt was accepted.\n- Hard-coding private channel ids, bot mentions, or router tokens into public SKC docs.\n- Using this visible-session pattern when Coordinator MCP turn state is available and sufficient.\n",
+	"standalone-mcp.md": "# Standalone SKC MCP support\n\nThis page answers the common user question: “Does normal `skc` inherit my Claude Code/Codex MCP servers, or can I configure MCP servers directly for the standalone TUI?”\n\n## Short answer\n\nNormal standalone SKC (`skc`, `skc --tmux`, and print-mode prompts) does **not** inherit MCP servers from Claude Code, Codex, Cursor, Gemini, Windsurf, or other tools as a public startup contract.\n\nThere is also no supported user-facing `~/.skc/agent/config.yml` setting that makes the normal standalone TUI automatically load arbitrary MCP servers for the model. Historical/internal MCP discovery code and `.mcp.json` shapes exist in the repository, but they are not the supported public integration boundary for ordinary standalone sessions.\n\nIf you rely on a specific MCP server, run it through one of the supported integration surfaces below instead of assuming another tool's MCP config will be imported into standalone SKC.\n\n## What is supported today\n\n| Need | Use | Notes |\n| --- | --- | --- |\n| External bot or multi-session controller wants to drive SKC | [Coordinator MCP](./hermes-mcp-bridge.md) via `skc mcp-serve coordinator` | SKC exposes an **outward** MCP server with SKC coordinator tools. This is not a way to import arbitrary MCP tools into the standalone TUI. |\n| Editor/ACP client owns MCP servers and wants SKC as the agent backend | [ACP mode](./external-control-readiness.md#acp-mode) via `skc --mode acp` or `skc acp` | The ACP client supplies and owns MCP servers. SKC keeps those client-owned MCP tools isolated from standalone on-disk discovery. |\n| Host application already manages MCP servers and policies | [RPC host tools](./rpc.md#host-tool-sub-protocol) via `skc --mode rpc` | Convert the selected MCP capabilities into host-owned RPC tools. The host executes the MCP call and returns `host_tool_result`. |\n| OpenClaw/Hermes-style host wants to map its own MCP/skills into SKC | [OpenClaw / Hermes RPC integration notes](./openclaw-hermes-rpc-integration.md) | Treat MCP as a host implementation detail and expose only policy-approved capabilities as RPC host tools. |\n\n## What standalone SKC does not do\n\nStandalone SKC does **not** currently promise any of these behaviors:\n\n- reading Claude Code's global MCP server list and automatically enabling it;\n- reading Codex MCP server config as an inherited runtime contract;\n- merging multiple tools' MCP configs into the normal TUI at startup;\n- making `.mcp.json`, `mcp.json`, `.codex/config.toml`, or other discovered files a stable public standalone-TUI config API;\n- exposing Coordinator MCP tools as ordinary in-session model tools.\n\nThis boundary is intentional: MCP servers often carry credentials, local filesystem reach, browser/session state, approval semantics, and tool names that belong to the host that configured them. Blind inheritance would mix policies between products and make it unclear which process owns credentials, approvals, sandboxing, and lifecycle.\n\n## Recommended workaround for a specific MCP server\n\nIf you need a context engine, internal search server, browser MCP, database MCP, or another custom MCP inside SKC:\n\n1. Keep the MCP server configured in the host that owns its credentials and policy.\n2. Start SKC through RPC (`skc --mode rpc`) from that host.\n3. Register a narrow host-owned tool with `set_host_tools` / `RpcClient#setCustomTools()`.\n4. Have the host tool call the real MCP server and return the result to SKC as `host_tool_result`.\n\nThat shape keeps the MCP server's auth, approvals, filesystem access, and process lifetime with the host while still letting the SKC model request the capability when needed.\n\nFor multi-session orchestration, prefer Coordinator MCP instead. Coordinator MCP lets an external controller start/register sessions, send turns, answer questions, read artifacts, and write durable status reports; it does not import arbitrary MCP servers into a standalone TUI session.\n\n## Related docs\n\n- [Coordinator MCP bridge](./hermes-mcp-bridge.md)\n- [External control surface readiness](./external-control-readiness.md)\n- [RPC Protocol Reference](./rpc.md)\n- [OpenClaw / Hermes RPC integration notes](./openclaw-hermes-rpc-integration.md)\n- [Clawhip-routed SKC sessions](./skc-session-clawhip-routing.md)\n",
 	"theme.md": "# Theming Reference\n\nThis document describes how theming works in the coding-agent today: schema, loading, runtime behavior, and failure modes.\n\n## What the theme system controls\n\nThe theme system drives:\n\n- foreground/background color tokens used across the TUI\n- markdown styling adapters (`getMarkdownTheme()`)\n- selector/editor/settings list adapters (`getSelectListTheme()`, `getEditorTheme()`, `getSettingsListTheme()`)\n- symbol preset + symbol overrides (`unicode`, `nerd`, `ascii`)\n- syntax highlighting colors used by native highlighter (`@sayknow-cli/natives`)\n- status line segment colors\n\nPrimary implementation: `src/modes/theme/theme.ts`.\n\n## Theme JSON shape\n\nTheme files are JSON objects validated against the runtime schema in `theme.ts` (`ThemeJsonSchema`) and mirrored by `src/modes/theme/theme-schema.json`.\n\nTop-level fields:\n\n- `name` (required)\n- `colors` (required; all color tokens required)\n- `vars` (optional; reusable color variables)\n- `export` (optional; HTML export colors)\n- `symbols` (optional)\n  - `preset` (optional: `unicode | nerd | ascii`)\n  - `overrides` (optional: key/value overrides for `SymbolKey`)\n\nColor values accept:\n\n- hex string (`\"#RRGGBB\"`)\n- 256-color index (`0..255`)\n- variable reference string (resolved through `vars`)\n- empty string (`\"\"`) meaning terminal default (`\\x1b[39m` fg, `\\x1b[49m` bg)\n\n## Required color tokens (current)\n\nAll tokens below are required in `colors`.\n\n### Core text and borders (11)\n\n`accent`, `border`, `borderAccent`, `borderMuted`, `success`, `error`, `warning`, `muted`, `dim`, `text`, `thinkingText`\n\n### Background blocks (7)\n\n`selectedBg`, `userMessageBg`, `customMessageBg`, `toolPendingBg`, `toolSuccessBg`, `toolErrorBg`, `statusLineBg`\n\n### Message/tool text (5)\n\n`userMessageText`, `customMessageText`, `customMessageLabel`, `toolTitle`, `toolOutput`\n\n### Markdown (10)\n\n`mdHeading`, `mdLink`, `mdLinkUrl`, `mdCode`, `mdCodeBlock`, `mdCodeBlockBorder`, `mdQuote`, `mdQuoteBorder`, `mdHr`, `mdListBullet`\n\n### Tool diff + syntax highlighting (12)\n\n`toolDiffAdded`, `toolDiffRemoved`, `toolDiffContext`,\n`syntaxComment`, `syntaxKeyword`, `syntaxFunction`, `syntaxVariable`, `syntaxString`, `syntaxNumber`, `syntaxType`, `syntaxOperator`, `syntaxPunctuation`\n\n### Mode/thinking borders (8)\n\n`thinkingOff`, `thinkingMinimal`, `thinkingLow`, `thinkingMedium`, `thinkingHigh`, `thinkingXhigh`, `bashMode`, `pythonMode`\n\n### Status line segment colors (14)\n\n`statusLineSep`, `statusLineModel`, `statusLinePath`, `statusLineGitClean`, `statusLineGitDirty`, `statusLineContext`, `statusLineSpend`, `statusLineStaged`, `statusLineDirty`, `statusLineUntracked`, `statusLineOutput`, `statusLineCost`, `statusLineSubagents`\n\n## Optional tokens\n\n### `export` section (optional)\n\nUsed for HTML export theming helpers:\n\n- `export.pageBg`\n- `export.cardBg`\n- `export.infoBg`\n\nIf omitted, export code derives defaults from resolved theme colors.\n\n### `symbols` section (optional)\n\n- `symbols.preset` sets a theme-level default symbol set.\n- `symbols.overrides` can override individual `SymbolKey` values.\n\nRuntime precedence:\n\n1. settings `symbolPreset` override (if set)\n2. theme JSON `symbols.preset`\n3. fallback `\"unicode\"`\n\nInvalid override keys are ignored and logged (`logger.debug`).\n\n## Built-in vs custom theme sources\n\nTheme lookup order (`loadThemeJson`):\n\n1. built-in embedded themes (`red-octopus.json`, `blue-octopus.json`, `claude-code.json`, `codex.json`, and `opencode.json` compiled into `defaultThemes`)\n2. custom theme file: `<customThemesDir>/<name>.json`\n\nCustom themes directory comes from `getCustomThemesDir()`:\n\n- default: `~/.skc/agent/themes`\n- overridden by `SKC_CODING_AGENT_DIR` (`$SKC_CODING_AGENT_DIR/themes`)\n\n`getAvailableThemes()` returns merged built-in + custom names, sorted, with built-ins taking precedence on name collision.\n\n## Loading, validation, and resolution\n\nFor custom theme files:\n\n1. read JSON\n2. parse JSON\n3. validate against `ThemeJsonSchema`\n4. resolve `vars` references recursively\n5. convert resolved values to ANSI by terminal capability mode\n\nValidation behavior:\n\n- missing required color tokens: explicit grouped error message\n- bad token types/values: validation errors with JSON path\n- unknown theme file: `Theme not found: <name>`\n\nVar reference behavior:\n\n- supports nested references\n- throws on missing variable reference\n- throws on circular references\n\n## Terminal color mode behavior\n\nColor mode detection (`detectColorMode`):\n\n- `COLORTERM=truecolor|24bit` => truecolor\n- `WT_SESSION` => truecolor\n- `TERM` in `dumb`, `linux`, or empty => 256color\n- otherwise => truecolor\n\nConversion behavior:\n\n- hex -> `Bun.color(..., \"ansi-16m\" | \"ansi-256\")`\n- numeric -> `38;5` / `48;5` ANSI\n- `\"\"` -> default fg/bg reset\n\n## Runtime switching behavior\n\n### Initial theme (`initTheme`)\n\n`main.ts` initializes theme with settings:\n\n- `symbolPreset`\n- `colorBlindMode`\n- `theme.dark`\n- `theme.light`\n\nAuto theme slot selection uses terminal appearance in this order:\n\n1. terminal-reported OSC 11 background luminance, unless the macOS/Zellij fallback path is active\n2. `COLORFGBG` background index (`< 8` => dark, `>= 8` => light)\n3. macOS appearance fallback only for the known-broken macOS/Zellij OSC 11 path\n4. dark slot fallback\n\nBuilt-in theme note: `blue-octopus` is the default SKC theme for both the dark and light slots, and `red-octopus` is a bundled warm, high-contrast alternate. Both are cephalopod brand themes with separate semantic error/warning/diff-removal tokens and octopus-oriented symbol overrides. Three additional bundled migration themes — `claude-code`, `codex`, and `opencode` — mirror the look of those tools for easy eye-migration. All three are dark-classified and recommended for `theme.dark`, but are selectable in either slot; they keep SKC's default symbol identity (no crab-symbol overrides).\n\nCurrent defaults from settings schema:\n\n- `theme.dark = \"blue-octopus\"`\n- `theme.light = \"blue-octopus\"`\n- `symbolPreset = \"unicode\"`\n- `colorBlindMode = false`\n\n### Explicit switching (`setTheme`)\n\n- loads selected theme\n- updates global `theme` singleton\n- optionally starts watcher\n- triggers `onThemeChange` callback\n\nOn failure:\n\n- falls back to built-in `dark`\n- returns `{ success: false, error }`\n\n### Preview switching (`previewTheme`)\n\n- applies temporary preview theme to global `theme`\n- does **not** change persisted settings by itself\n- returns success/error without fallback replacement\n\nThe settings theme picker is confirm-only; arrow-key browsing does not call `previewTheme`, so the rendered theme and displayed/persisted theme name stay aligned until Enter confirms a new selection.\n\n## Watchers and live reload\n\nWhen watcher is enabled (`setTheme(..., true)` / interactive init):\n\n- watches `<customThemesDir>/<currentTheme>.json` only when that file exists\n- built-ins are effectively not watched; built-in theme lookup also takes precedence over same-name custom files\n- matching file changes schedule a debounced reload; reload errors or temporary file absence keep the last successfully loaded theme\n- the watcher does not perform a delete/rename fallback; it waits for a future successful reload or explicit theme switch\n\nAuto mode also reevaluates dark/light slot mapping from terminal appearance changes, `SIGWINCH`, and the macOS fallback observer when active.\n\n## Color-blind mode behavior\n\n`colorBlindMode` changes only one token at runtime:\n\n- `toolDiffAdded` is HSV-adjusted (green shifted toward blue)\n- adjustment is applied only when resolved value is a hex string\n\nOther tokens are unchanged.\n\n## Where theme settings are persisted\n\nTheme-related settings are persisted by `Settings` to global config YAML:\n\n- path: `<agentDir>/config.yml`\n- default agent dir: `~/.skc/agent`\n- effective default file: `~/.skc/agent/config.yml`\n\nPersisted keys:\n\n- `theme.dark`\n- `theme.light`\n- `symbolPreset`\n- `colorBlindMode`\n\nLegacy migration exists: old flat `theme: \"name\"` is migrated to nested `theme.dark` or `theme.light` based on luminance detection; legacy built-in names `dark`/`light` map to `red-octopus`/`blue-octopus` unless matching custom theme files exist.\n\n## Creating a custom theme (practical)\n\n1. Create file in custom themes dir, e.g. `~/.skc/agent/themes/my-theme.json`.\n2. Include `name`, optional `vars`, and **all required** `colors` tokens.\n3. Optionally include `symbols` and `export`.\n4. Select the theme in Settings (`Display -> Dark theme` or `Display -> Light theme`) depending on which auto slot you want. All bundled themes are selectable: the crustacean defaults `red-octopus` and `blue-octopus`, plus the migration themes `claude-code`, `codex`, and `opencode` (dark-classified, recommended for the dark slot but selectable in either).\n\nMinimal skeleton:\n\n```json\n{\n  \"name\": \"my-theme\",\n  \"vars\": {\n    \"accent\": \"#7aa2f7\",\n    \"muted\": 244\n  },\n  \"colors\": {\n    \"accent\": \"accent\",\n    \"border\": \"#4c566a\",\n    \"borderAccent\": \"accent\",\n    \"borderMuted\": \"muted\",\n    \"success\": \"#9ece6a\",\n    \"error\": \"#f7768e\",\n    \"warning\": \"#e0af68\",\n    \"muted\": \"muted\",\n    \"dim\": 240,\n    \"text\": \"\",\n    \"thinkingText\": \"muted\",\n\n    \"selectedBg\": \"#2a2f45\",\n    \"userMessageBg\": \"#1f2335\",\n    \"userMessageText\": \"\",\n    \"customMessageBg\": \"#24283b\",\n    \"customMessageText\": \"\",\n    \"customMessageLabel\": \"accent\",\n    \"toolPendingBg\": \"#1f2335\",\n    \"toolSuccessBg\": \"#1f2d2a\",\n    \"toolErrorBg\": \"#2d1f2a\",\n    \"toolTitle\": \"\",\n    \"toolOutput\": \"muted\",\n\n    \"mdHeading\": \"accent\",\n    \"mdLink\": \"accent\",\n    \"mdLinkUrl\": \"muted\",\n    \"mdCode\": \"#c0caf5\",\n    \"mdCodeBlock\": \"#c0caf5\",\n    \"mdCodeBlockBorder\": \"muted\",\n    \"mdQuote\": \"muted\",\n    \"mdQuoteBorder\": \"muted\",\n    \"mdHr\": \"muted\",\n    \"mdListBullet\": \"accent\",\n\n    \"toolDiffAdded\": \"#9ece6a\",\n    \"toolDiffRemoved\": \"#f7768e\",\n    \"toolDiffContext\": \"muted\",\n\n    \"syntaxComment\": \"#565f89\",\n    \"syntaxKeyword\": \"#bb9af7\",\n    \"syntaxFunction\": \"#7aa2f7\",\n    \"syntaxVariable\": \"#c0caf5\",\n    \"syntaxString\": \"#9ece6a\",\n    \"syntaxNumber\": \"#ff9e64\",\n    \"syntaxType\": \"#2ac3de\",\n    \"syntaxOperator\": \"#89ddff\",\n    \"syntaxPunctuation\": \"#9aa5ce\",\n\n    \"thinkingOff\": 240,\n    \"thinkingMinimal\": 244,\n    \"thinkingLow\": \"#7aa2f7\",\n    \"thinkingMedium\": \"#2ac3de\",\n    \"thinkingHigh\": \"#bb9af7\",\n    \"thinkingXhigh\": \"#f7768e\",\n\n    \"bashMode\": \"#2ac3de\",\n    \"pythonMode\": \"#bb9af7\",\n\n    \"statusLineBg\": \"#16161e\",\n    \"statusLineSep\": 240,\n    \"statusLineModel\": \"#bb9af7\",\n    \"statusLinePath\": \"#7aa2f7\",\n    \"statusLineGitClean\": \"#9ece6a\",\n    \"statusLineGitDirty\": \"#e0af68\",\n    \"statusLineContext\": \"#2ac3de\",\n    \"statusLineSpend\": \"#7dcfff\",\n    \"statusLineStaged\": \"#9ece6a\",\n    \"statusLineDirty\": \"#e0af68\",\n    \"statusLineUntracked\": \"#f7768e\",\n    \"statusLineOutput\": \"#c0caf5\",\n    \"statusLineCost\": \"#ff9e64\",\n    \"statusLineSubagents\": \"#bb9af7\"\n  }\n}\n```\n\n## Testing custom themes\n\nUse this workflow:\n\n1. Start interactive mode (watcher enabled from startup).\n2. Open settings and confirm the custom theme in the dark/light theme picker; arrow-key browsing is intentionally non-mutating.\n3. For custom theme files, edit the JSON while running and confirm auto-reload on save.\n4. Exercise critical surfaces:\n   - markdown rendering\n   - tool blocks (pending/success/error)\n   - diff rendering (added/removed/context)\n   - status line readability\n   - thinking level border changes\n   - bash/python mode border colors\n5. Validate both symbol presets if your theme depends on glyph width/appearance.\n\n## Real constraints and caveats\n\n- All `colors` tokens are required for custom themes.\n- `export` and `symbols` are optional.\n- `$schema` in theme JSON is informational; runtime validation is enforced by a Zod schema in code.\n- `setTheme` failure falls back to `dark`; `previewTheme` failure does not replace current theme.\n- File watcher reload errors or temporary missing files keep the current loaded theme until a successful reload or explicit theme switch.\n",
 	"tools/ask.md": "# ask\n\n> Prompts the interactive user for one or more choices or free-form answers.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ask.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ask.md`\n- Key collaborators:\n  - `packages/coding-agent/src/config/settings-schema.ts` — `ask.timeout` / `ask.notify` defaults\n  - `packages/coding-agent/src/modes/theme/theme.ts` — checkbox and tree glyphs for TUI rendering\n  - `packages/coding-agent/src/tui.ts` — status-line rendering\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `questions` | `Question[]` | Yes | One or more questions. Empty arrays are rejected by schema and also guarded at runtime. |\n\n### `Question`\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `id` | `string` | Yes | Stable identifier used in multi-question results. |\n| `question` | `string` | Yes | Prompt text shown to the user. |\n| `options` | `{ label: string }[]` | Yes | Explicit options. The UI always appends `Other (type your own)`; callers must not include it. |\n| `multi` | `boolean` | No | Enables multi-select mode. Default: `false`. |\n| `recommended` | `number` | No | Zero-based recommended option index. In single-select mode the label gets ` (Recommended)` appended in the UI. |\n\n## Outputs\n- Single-shot result.\n- `content[0].text` is plain text:\n  - single question: `User selected: ...` and/or `User provided custom input: ...`\n  - multiple questions: `User answers:` followed by one line per `id`\n- `details`:\n  - single question: `{ question, options, multi, selectedOptions, customInput? }`\n  - multiple questions: `{ results: QuestionResult[] }`, where each item includes `id`, `question`, `options`, `multi`, `selectedOptions`, and optional `customInput`\n- Cancellation and headless cases throw instead of returning a structured success result.\n\n## Flow\n1. `AskTool.createIf()` only registers the tool when `session.hasUI` is true; headless sessions never get it.\n2. `execute()` requires `context.ui`; if missing it aborts the context and throws `ToolAbortError(\"Ask tool requires interactive mode\")`.\n3. It reads `ask.timeout` from settings, converts seconds to milliseconds, and disables timeout entirely while plan mode is enabled (`packages/coding-agent/src/tools/ask.ts`).\n4. If `ask.notify` is not `off`, it sends a terminal notification: `Waiting for input`.\n5. For each question, `askSingleQuestion()` drives either:\n   - single-select list + optional editor for `Other`\n   - multi-select checkbox loop + `Done selecting` sentinel + optional editor for `Other`\n6. In multi-question mode, left/right arrow handlers enable back/forward navigation between questions and preserve prior selections.\n7. If a timeout fires before any selection/custom input, the tool auto-selects the recommended option, or the first option when no valid `recommended` index exists.\n8. If the user cancels without timeout, `execute()` aborts the tool context and throws `ToolAbortError(\"Ask tool was cancelled by the user\")`.\n9. On success it formats human-readable text plus structured `details`; the TUI renderer uses `details` for rich display.\n\n## Modes / Variants\n- Single question: returns flattened `details` fields for one question.\n- Multiple questions: returns `details.results[]` and allows back/forward navigation across questions.\n- Single-select: one option or custom input.\n- Multi-select: toggled checkbox list, `Done selecting` sentinel only when forward navigation is not active.\n\n## Side Effects\n- User-visible prompts / interactive UI\n  - Opens a selection dialog via `context.ui.select(...)`.\n  - Opens a text editor dialog via `context.ui.editor(...)` for `Other`.\n  - Sends a terminal notification unless `ask.notify=off`.\n- Session state\n  - Reads plan-mode state to disable timeouts.\n  - Calls `context.abort()` on headless use or user cancellation.\n- Background work / cancellation\n  - Wraps UI waits in `untilAborted(...)` so abort signals interrupt pending dialogs.\n\n## Limits & Caps\n- `questions` must contain at least 1 item (`askSchema` in `packages/coding-agent/src/tools/ask.ts`).\n- `ask.timeout` default is `30` seconds; `0` disables timeout (`packages/coding-agent/src/config/settings-schema.ts`).\n- Prompt guidance says provide 2-5 options, but code does not enforce that (`packages/coding-agent/src/prompts/tools/ask.md`).\n- Timeout only applies to the option picker; once the user chooses `Other`, the editor has no timeout (`packages/coding-agent/src/prompts/tools/ask.md`).\n\n## Errors\n- Missing interactive UI: throws `ToolAbortError(\"Ask tool requires interactive mode\")`.\n- User cancels picker/editor without timeout: throws `ToolAbortError(\"Ask tool was cancelled by the user\")`.\n- Abort signal during input: converted to `ToolAbortError(\"Ask input was cancelled\")`.\n- Empty `questions` at runtime returns a text error payload instead of throwing: `Error: questions must not be empty`.\n\n## Notes\n- `recommended` is only a UI hint; invalid indexes are ignored.\n- In single-select mode the returned `selectedOptions` value strips the appended ` (Recommended)` suffix.\n- Multi-select results preserve selection order by `Set` insertion order, not original option order after arbitrary toggles.\n- Option labels and prompt text are returned verbatim in `details`; the tool does not interpret them beyond UI affordances like `Other` and ` (Recommended)`.\n",
 	"tools/ast-edit.md": "# ast_edit\n\n> Preview and apply structural rewrites over source files via native ast-grep.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ast-edit.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ast-edit.md`\n- Key collaborators:\n  - `crates/pi-natives/src/ast.rs` — native rewrite planning and file mutation\n  - `crates/pi-natives/src/language/mod.rs` — language aliases and extension inference\n  - `packages/coding-agent/src/tools/path-utils.ts` — path/glob parsing and multi-path resolution\n  - `packages/coding-agent/src/tools/resolve.ts` — preview/apply queueing\n  - `packages/coding-agent/src/tools/render-utils.ts` — parse-error dedupe and display caps\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — hashline vs line-number diff references\n  - `packages/coding-agent/src/hashline/hash.ts` — stable hashline diff anchors\n  - `packages/natives/native/index.d.ts` — JS-visible native binding contract\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `ops` | `{ pat: string; out: string }[]` | Yes | One or more rewrite rules. `pat` must be non-empty. Duplicate `pat` values fail before native execution. Empty `out` deletes the matched node. |\n| `paths` | `string[]` | Yes | One or more files, directories, globs, or internal URLs with backing files. Empty entries are rejected. Globs are forbidden for internal URLs. |\n\nShared AST pattern grammar and language catalog: see [`ast_grep`](./ast-grep.md#inputs).\n\n- `ast_edit` uses the same `$NAME`, `$_`, `$$$NAME`, and `$$$` metavariable semantics.\n- The tool prompt adds rewrite-specific constraints:\n  - metavariable names must be uppercase and must stand for whole AST nodes,\n  - captures from `pat` are substituted into `out`,\n  - each rewrite is a 1:1 structural substitution; one capture cannot expand into multiple sibling nodes unless the grammar itself permits that expansion at that position.\n\n## Outputs\n- Single-shot preview result from `ast_edit` itself.\n- Model-facing `content` is one text block showing proposed edits, grouped by file for directory/multi-file runs.\n  - Each change renders as two lines: `-REF|before` and `+REF|after` in hashline mode, or `-LINE:COLUMN before` / `+LINE:COLUMN after` when hashlines are off.\n  - Only the first line of each `before`/`after` snippet is shown, truncated to 120 characters in the wrapper.\n  - `Limit reached; narrow paths.` and formatted parse issues are appended when applicable.\n- If no rewrites match, text is `No replacements made` plus formatted parse issues when present.\n- `details` includes aggregate preview metadata:\n  - `totalReplacements`, `filesTouched`, `filesSearched`, `applied`, `limitReached`\n  - optional `parseErrors`, `scopePath`, `files`, `fileReplacements`, `displayContent`, `meta`\n- The tool always previews first (`applied: false` in the direct result). Actual file writes happen only later through `resolve(action: \"apply\", ...)`.\n- When preview produced replacements, `ast_edit` also queues a pending `resolve` action. Successful apply returns a separate `resolve` result, not another `ast_edit` result.\n\n## Flow\n1. `AstEditTool.execute()` validates each op in `packages/coding-agent/src/tools/ast-edit.ts`:\n   - empty `pat` fails,\n   - at least one op is required,\n   - duplicate `pat` values fail,\n   - ops are converted to a `Record<pattern, replacement>`.\n2. The wrapper reads `SKC_MAX_AST_FILES` via `$envpos(..., 1000)` and uses that as the native `maxFiles` cap for both preview and apply.\n3. Path normalization, internal URL handling, missing-path partitioning, and multi-path resolution follow the same `path-utils.ts` flow as `ast_grep`.\n4. The wrapper stats the resolved base path to decide whether to render grouped directory output.\n5. `runAstEditOnce(...)` always runs native `astEdit(...)` with `dryRun: true` and `failOnParseError: false` on the first pass.\n6. Native `ast_edit` in `crates/pi-natives/src/ast.rs`:\n   - normalizes the rewrite map and sorts rules by pattern string,\n   - resolves strictness (`smart` by default),\n   - collects candidate files from a file or gitignore-aware directory scan,\n   - infers a single language for the whole call unless `lang` was supplied,\n   - compiles every rewrite pattern for that language,\n   - parses each file, skips files with syntax-error trees, collects `replace_by(...)` edits for every match, enforces replacement and file caps, and returns textual before/after slices plus source ranges.\n7. The TS wrapper deduplicates parse errors, groups changes by file, and renders preview diff lines.\n8. If preview found replacements and `applied` is false, `queueResolveHandler(...)` registers a forced `resolve` action and injects a `resolve-reminder` steering message.\n9. On `resolve(action: \"apply\")`, the queued callback reruns the same rewrite set with `dryRun: false`, recomputes counts, and rejects the apply as an error if the live result no longer matches the preview (`stalePreview`).\n10. On a non-stale apply, the callback returns `Applied N replacements in M files.`; on discard, `resolve` returns a discard message without mutating files.\n\n## Modes / Variants\n- Single file: preview or apply against one file.\n- Directory + optional glob: native scan walks the directory, then filters by compiled glob.\n- Multiple explicit paths/globs: wrapper unions them into one synthetic scope or runs per-target native calls when paths only meet at root.\n- Internal URL inputs: only supported when the router resolves them to a backing file path.\n- Preview mode: always the direct `ast_edit` tool result.\n- Apply mode: only reachable through the queued `resolve` callback after a preview.\n- Hashline output mode vs plain line/column mode: controlled by `resolveFileDisplayMode()`.\n\n## Side Effects\n- Filesystem\n  - Preview reads files and scans directories.\n  - Apply rewrites files in place with `std::fs::write(...)`, but only when the computed output differs from the original source.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Queues a one-shot forced `resolve` tool choice through `queueResolveHandler(...)`.\n  - Adds a `resolve-reminder` steering message.\n- User-visible prompts / interactive UI\n  - Direct `ast_edit` results are previews.\n  - Follow-up apply/discard is exposed through the hidden `resolve` tool.\n- Background work / cancellation\n  - Native preview/apply work runs on a blocking worker via `task::blocking(...)`.\n  - Cancellation and optional native timeout are cooperative through `CancelToken::heartbeat()`.\n\n## Limits & Caps\n- File cap exposed by the wrapper: `SKC_MAX_AST_FILES`, default `1000`, in `packages/coding-agent/src/tools/ast-edit.ts`.\n- Native `maxFiles` and `maxReplacements` are both clamped to at least `1` when provided in `crates/pi-natives/src/ast.rs`.\n- The wrapper never sets `maxReplacements`; native behavior therefore defaults to effectively unbounded replacements for a run.\n- Parse issues are rendered with at most `PARSE_ERRORS_LIMIT = 20` lines in `packages/coding-agent/src/tools/render-utils.ts`; `details.parseErrors` is deduplicated but not capped.\n- Directory scans use `include_hidden: true`, `use_gitignore: true`, and skip `node_modules` unless the glob text explicitly mentions `node_modules` in `crates/pi-natives/src/ast.rs`.\n- No separate glob-expansion count cap exists. Candidate count is whatever the resolved path/glob expands to after gitignore filtering, then native `maxFiles` stops mutations after the configured number of touched files.\n- Preview text truncates each rendered `before` and `after` first line to 120 characters in `packages/coding-agent/src/tools/ast-edit.ts`.\n\n## Errors\n- TS wrapper throws `ToolError` for empty patterns, duplicate rewrite patterns, empty path entries, unsupported internal-URL globs, internal URLs without `sourcePath`, and missing paths.\n- Native code returns hard errors for:\n  - inability to infer one language across all candidates when `lang` is absent,\n  - unsupported explicit `lang`,\n  - bad glob compilation or unreadable search roots,\n  - overlapping computed edits (`Overlapping replacements detected; refine pattern to avoid ambiguous edits`),\n  - out-of-bounds edit ranges or non-UTF-8 replacement text,\n  - write failures during apply,\n  - cancellation or timeout.\n- With `failOnParseError: false` (the wrapper always uses this), pattern compile failures and file parse failures become `parseErrors` instead of aborting the whole run.\n- If every rewrite pattern fails to compile, native `ast_edit` returns a successful zero-replacement result with `parseErrors` populated.\n- Files containing tree-sitter error nodes are skipped for rewriting; they do not get partial edits.\n- Apply can fail after a successful preview if the preview becomes stale. The resolve callback compares replacement totals and per-file counts and returns an error result rather than applying a mismatched preview silently.\n\n## Notes\n- `ast_edit` does not expose the native `lang`, `strictness`, `selector`, `maxReplacements`, `failOnParseError`, or `timeoutMs` fields to the model. The runtime fixes the call shape to a preview-first, smart-strictness, best-effort parse mode.\n- Because the wrapper does not expose `lang`, mixed-language rewrites only succeed when every candidate infers to the same canonical language. This is stricter than `ast_grep`.\n- Idempotency is not enforced syntactically. A rewrite like `foo($A) -> foo($A)` previews zero changes because output equals input; a rewrite that keeps matching its own output may still produce replacements on repeated calls.\n- Rewrites are accumulated per file, then applied from the end of the file backward after an overlap check. Independent matches can coexist; overlapping matches abort the run.\n- Native rewrite rule order is by pattern-string sort, not by the original `ops` array order, because `normalize_rewrite_map(...)` sorts the `(pattern, rewrite)` pairs.\n- Preview/apply parity is validated only by totals and per-file counts, not by a byte-for-byte diff of every replacement payload.",
@@ -96,7 +98,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"tools/search.md": "# search\n\n> Search file contents with a regex across files, directories, globs, and internal URLs.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/search.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/search.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/match-line-format.ts` — model-facing anchor formatting.\n  - `packages/coding-agent/src/tools/path-utils.ts` — path normalization, glob splitting, internal URL resolution.\n  - `packages/coding-agent/src/tools/file-recorder.ts` — file ordering for grouped output.\n  - `packages/coding-agent/src/tools/grouped-file-output.ts` — grouped per-file text layout.\n  - `packages/coding-agent/src/session/streaming-output.ts` — line truncation and final byte truncation.\n  - `packages/coding-agent/src/config/settings-schema.ts` — default context lines.\n  - `packages/natives/native/index.d.ts` — native `grep()` types exposed to TS.\n  - `crates/pi-natives/src/grep.rs` — native regex/file search implementation.\n  - `docs/natives-text-search-pipeline.md` — native search pipeline overview.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `pattern` | `string` | Yes | Regex pattern. `search.ts` trims it and rejects empty input. The native matcher enables multiline only when the pattern text contains a literal newline or the two-character sequence `\\\\n`. The model prompt explicitly documents literal-brace escaping such as ``interface\\\\{\\\\}``, although the native layer also auto-escapes braces that cannot be valid repetition quantifiers. |\n| `paths` | `string[]` | Yes | One or more file paths, directory paths, glob-like paths, or internal URLs. Empty strings are rejected after trimming/quote stripping. Internal URLs must resolve to a backing file and cannot contain glob characters. |\n| `i` | `boolean` | No | Case-insensitive search. Defaults to `false`. Passed to native `ignoreCase`. |\n| `gitignore` | `boolean` | No | Respect `.gitignore` during directory scans. Defaults to `true`. Passed to native `gitignore`. |\n| `skip` | `number` | No | Global match offset. Defaults to `0`. `search.ts` floors finite numbers and rejects negative or non-finite values. |\n\n## Outputs\nThe tool returns a single text block in `content[0].text` plus structured `details`.\n\n- Match lines are formatted by `formatMatchLine()` as `*<anchor>|<line>` for matches and ` <anchor>|<line>` for context.\n  - Hashline mode: `*5th|content`, ` 9x}|content`.\n  - Plain mode: `*5|content`, ` 9|content`.\n- Directory results are grouped by file, with `# <path>` headings and blank lines between groups.\n- `details` may include:\n  - `scopePath` — formatted search scope.\n  - `matchCount`, `fileCount`, `files`, `fileMatches` — counts for the returned page, not necessarily total corpus counts.\n  - `matchLimitReached` — visible-page limit hit (`100`).\n  - `resultLimitReached` — native preselection limit hit (`500`).\n  - `linesTruncated` — one or more matched lines were shortened to `1024` chars plus `…`.\n  - `truncated` and `meta.truncation` — final text output was head-truncated by `truncateHead()`.\n  - `displayContent` — TUI-only rendering text with `│` gutters instead of model anchors.\n  - `missingPaths` — multi-path entries skipped because their base path did not exist.\n- No-match result text is `No matches found`, optionally followed by `Skipped missing paths: ...`.\n\n## Flow\n1. `SearchTool.execute()` validates and normalizes input in `packages/coding-agent/src/tools/search.ts`:\n   - trims `pattern`, rejects empty patterns;\n   - normalizes `skip` to a non-negative integer;\n   - reads `search.contextBefore` and `search.contextAfter` from session settings (`1` and `3` by default);\n   - enables multiline only when `pattern` contains `\\n` or an actual newline.\n2. Each `paths` entry is normalized with `normalizePathLikeInput()`.\n3. Internal URLs are resolved through `session.internalRouter`:\n   - glob metacharacters (`*`, `?`, `[`, `{`) are rejected for internal URLs;\n   - URLs without `resource.sourcePath` fail;\n   - immutable sources are tracked so output can suppress editable hashline anchors per file.\n4. For multi-path calls, `partitionExistingPaths()` skips only ENOENT entries. If every entry is missing, the tool errors.\n5. Path resolution branches:\n   - one entry: `parseSearchPath()` splits `basePath` and optional glob;\n   - multiple entries: `resolveExplicitSearchPaths()` computes a common base directory, brace-union glob, exact-file list, or degenerate-root target list.\n6. `search.ts` stats the resolved base path to decide file vs directory behavior.\n7. It calls native `grep()` from `@sayknow-cli/natives` with:\n   - `pattern`, `ignoreCase`, `multiline`, `gitignore`;\n   - `hidden: true`;\n   - `cache: false`;\n   - `contextBefore` / `contextAfter` from settings;\n   - `maxColumns: 1024`;\n   - `mode: content`.\n8. Native execution happens in `crates/pi-natives/src/grep.rs`:\n   - `build_matcher()` sanitizes non-quantifier braces before regex compile;\n   - if compile fails with unopened/unclosed-group errors, it retries after escaping previously unescaped parentheses;\n   - directory scans use the grep pipeline described in `docs/natives-text-search-pipeline.md`.\n9. Search dispatch differs by resolved path set:\n   - exact explicit files or degenerate-root multi-targets: JS loops over targets and merges `grep()` results itself;\n   - single file/directory base: one `grep()` call handles offset/limit natively.\n10. JS output shaping then:\n   - round-robins directory matches down to `100` visible matches so one file does not monopolize the page;\n   - keeps the first `100` file matches for single-file searches;\n   - formats lines through `formatMatchLine()` for the model and `formatCodeFrameLine()` for TUI;\n   - records non-truncated matched/context lines into the session file-read cache with `recordSparse()`.\n11. Final text is passed through `truncateHead(rawOutput, { maxLines: Number.MAX_SAFE_INTEGER })`, so the effective cap is the default byte cap from `streaming-output.ts`, not the default line cap.\n12. `toolResult()` attaches text plus limit/truncation metadata.\n\n## Modes / Variants\n1. **Single file path**\n   - `grep()` searches one file.\n   - Output is a flat list of match/context lines.\n   - Visible limit is the first `100` matches after native offset handling.\n2. **Single directory path or single glob-like path**\n   - `parseSearchPath()` may split the input into `path` + `glob`.\n   - One native `grep()` scans the directory tree with `gitignore` and `hidden:true`.\n   - Native `offset` handles `skip` globally across files.\n   - JS round-robins the returned matches to `100` visible rows.\n3. **Multiple explicit paths/globs**\n   - `resolveExplicitSearchPaths()` collapses them into a common base and either a brace-union glob, an explicit file list, or per-target searches when the only common base is the filesystem root.\n   - Missing entries are skipped non-fatally unless all are missing.\n4. **Internal URL paths**\n   - Supported only when the internal resource resolves to a real backing file.\n   - No internal-URL globbing.\n   - Immutable sources switch to the immutable display mode when formatting anchors.\n\n## Side Effects\n- Filesystem\n  - Stats resolved search roots and input paths.\n  - Reads matched files through native `grep()`.\n  - Records sparse matched/context lines into the session file-read cache via `getFileReadCache(...).recordSparse(...)`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Reads session settings for context defaults.\n  - Uses `session.internalRouter` to resolve internal URLs.\n  - Populates tool `details.meta` with truncation/limit metadata.\n- Background work / cancellation\n  - Wrapped in `untilAborted(signal, ...)` at the JS level.\n  - `search.ts` does not pass `signal` or `timeoutMs` into native `grep()`, so native grep cancellation/timeouts are not used by this tool.\n\n## Limits & Caps\n- Visible page limit: `100` matches (`DEFAULT_MATCH_LIMIT` in `packages/coding-agent/src/tools/search.ts`).\n- Native preselection limit: `500` matches (`internalLimit = Math.min(DEFAULT_MATCH_LIMIT * 5, 2000)` in `packages/coding-agent/src/tools/search.ts`).\n- Line truncation: `1024` characters per emitted line (`DEFAULT_MAX_COLUMN` in `packages/coding-agent/src/session/streaming-output.ts`). Native grep marks truncated lines; JS reports `linesTruncated`.\n- Final text truncation: `truncateHead()` default byte cap `50 * 1024` bytes (`DEFAULT_MAX_BYTES` in `packages/coding-agent/src/session/streaming-output.ts`). `search.ts` overrides `maxLines` to `Number.MAX_SAFE_INTEGER`, so normal search output is byte-capped, not line-capped.\n- Context defaults: `search.contextBefore = 1`, `search.contextAfter = 3` in `packages/coding-agent/src/config/settings-schema.ts`.\n- Pagination: `skip` is a global match offset. In single-base searches it is pushed into native `offset`; in exact-file/multi-target aggregation it is applied in JS with `matches.slice(skip)`.\n- Native directory-scan cache: available in `grep.rs`, but this tool always sets `cache: false`.\n\n## Errors\n- `Pattern must not be empty` when trimmed `pattern` is empty.\n- `Skip must be a non-negative number` for negative or non-finite `skip`.\n- `` `paths` must contain non-empty paths or globs `` when any normalized path is empty.\n- `Glob patterns are not supported for internal URLs: ...` for internal URL + glob metacharacters.\n- `Cannot search internal URL without a backing file: ...` when the router resolves a virtual resource without `sourcePath`.\n- `Path not found: ...` when the resolved base path is missing, or when every multi-path entry is missing.\n- Regex compile failures bubble from native `grep()` as tool errors. `search.ts` has a special catch for messages beginning with `regex parse error`, then otherwise rethrows.\n- Multi-file native scans skip per-file open/search failures inside `grep.rs`; the scan continues with surviving files.\n\n## Notes\n- The model-facing prompt documents standard regex syntax plus two search-specific rules: escape literal braces, and use `\\n` or a literal newline for cross-line matching.\n- Native `build_matcher()` already auto-escapes braces that cannot be valid quantifiers, so patterns like `${platform}` become searchable instead of failing. Valid quantifiers like `a{2,4}` remain unchanged.\n- Native compile retry also escapes unescaped literal parentheses only after an unopened/unclosed-group parse error. It is a fallback, not a general parser mode.\n- Internal URLs are resolved before path existence checks. After resolution, the native layer sees ordinary filesystem paths.\n- `hidden:true` is hard-coded in `search.ts`; there is no model-facing flag to exclude dotfiles.\n- `gitignore:false` only affects native directory traversal. It does not disable the tool's own path normalization or explicit-file handling.\n- When `paths` resolves to multiple exact files, `search.ts` does not apply the native `500` match cap and reports `totalMatches` internally as the post-skip length for that branch.\n- The anchor suffix in hashline mode comes from `computeLineHash()` in `packages/coding-agent/src/hashline/hash.ts`; `search` itself only formats it.\n",
 	"tools/search_tool_bm25.md": "# search_tool_bm25\n\n> Search the hidden tool-discovery index and activate the top matches for the current session.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/search-tool-bm25.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/search-tool-bm25.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tool-discovery/tool-index.ts` — discoverable-tool metadata and BM25 index/search.\n  - `packages/coding-agent/src/session/agent-session.ts` — session discovery mode, corpus assembly, activation, cache invalidation.\n  - `packages/coding-agent/src/sdk.ts` — initial hiding of discoverable built-ins and prompt-time discoverable summary.\n  - `packages/coding-agent/src/tools/index.ts` — tool-session discovery hooks, essential/discoverable load modes, registry wiring.\n  - `packages/coding-agent/src/config/settings-schema.ts` — `tools.discoveryMode` and legacy `mcp.discoveryMode` settings.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `query` | `string` | Yes | Natural-language or keyword query. Trimmed before search; empty-after-trim is rejected. |\n| `limit` | `integer` | No | Max matches to return and activate. Minimum `1`. Defaults to `8` (`DEFAULT_LIMIT`). |\n\n## Outputs\n- Single-shot `AgentToolResult`.\n- Model-visible `content` is one text part containing JSON with:\n\n```json\n{\"query\":\"...\",\"activated_tools\":[\"...\"],\"match_count\":2,\"total_tools\":17}\n```\n\n- Runtime-only `details` carries the ranked matches used by the TUI renderer:\n  - `query`, `limit`, `total_tools`\n  - `activated_tools`: tool names activated by this call\n  - `active_selected_tools`: cumulative discovered-tool selections still active\n  - `tools`: array of match objects with\n    - `name`\n    - `label`\n    - `description` (`tool.summary`; this is the only snippet-like field)\n    - optional `server_name`\n    - optional `mcp_tool_name`\n    - `schema_keys`\n    - `score` rounded to 6 decimals\n- The renderer shows a status line plus up to 5 collapsed tree items by default (`COLLAPSED_MATCH_LIMIT`), each with label, optional server name, score to 3 decimals, and truncated description. The ranked match list is not serialized into `content`.\n\n## Flow\n1. `SearchToolBm25Tool.createIf()` in `packages/coding-agent/src/tools/search-tool-bm25.ts` exposes the tool only when `tools.discoveryMode !== \"off\"` and the session implements discovery hooks.\n2. `description` is rendered from `packages/coding-agent/src/prompts/tools/search-tool-bm25.md` via `renderSearchToolBm25Description()`, using the current discoverable-tool list plus per-server summary/count.\n3. `execute()` re-checks capability and settings:\n   - missing discovery hooks -> `ToolError(\"Tool discovery is unavailable in this session.\")`\n   - discovery disabled -> `ToolError(\"Tool discovery is disabled. Enable tools.discoveryMode or mcp.discoveryMode to use search_tool_bm25.\")`\n4. `query` is trimmed and validated; `limit` is defaulted/validated.\n5. `getDiscoverableToolSearchIndexForExecution()` fetches the cached generic search index from the session when available, otherwise rebuilds an index from the current discoverable-tool list.\n6. `getSelectedToolNames()` reads the current discovered selections so already-selected tools can be excluded from fresh results.\n7. `searchDiscoverableTools()` in `packages/coding-agent/src/tool-discovery/tool-index.ts` tokenizes the query, scores every document with BM25, sorts by descending score then `tool.name`, and returns up to `searchIndex.documents.length` results; `execute()` then filters already-selected names and slices to `limit`.\n8. If any matches remain, `activateTools()` activates all matched tool names through `session.activateDiscoveredTools()`.\n9. `details` is assembled from the activated names, current selected names, corpus size, and formatted matches; `content` is reduced to the compact JSON summary from `buildSearchToolBm25Content()`.\n10. `searchToolBm25Renderer` renders either:\n   - the structured `details` view, or\n   - a fallback text-only warning block if `details` is absent.\n\n## Modes / Variants\n- Discovery-mode gating:\n  - `tools.discoveryMode = \"all\"`: searches hidden discoverable built-ins.\n- Search-index source:\n  - generic cached discoverable index from the session\n  - rebuilt ad hoc from the current discoverable-tool list if neither cache path works\n- Activation backend:\n  - generic `activateDiscoveredTools()`\n  - legacy `activateDiscoveredMCPTools()` fallback\n\n## Side Effects\n- Session state\n  - Adds matched tools to the active session tool set through `activateDiscoveredTools()`.\n  - Updates discovered-tool selection state so repeated searches accumulate selections instead of replacing them.\n  - Invalidates the cached discoverable search index when newly activated built-ins change the hidden corpus (`packages/coding-agent/src/session/agent-session.ts`).\n  - Tool availability changes before the next model call in the same turn; the prompt text says this explicitly.\n- User-visible prompts / interactive UI\n  - The tool description includes discoverable server summaries and total discoverable-tool count.\n  - The TUI renderer shows ranked matches, but the model-visible text summary does not.\n\n## Limits & Caps\n- Default result cap: `8` (`DEFAULT_LIMIT` in `packages/coding-agent/src/tools/search-tool-bm25.ts`).\n- `limit` must be a positive integer; no tool-level upper bound beyond corpus size.\n- Renderer collapsed list cap: `5` (`COLLAPSED_MATCH_LIMIT`).\n- Renderer truncation widths:\n  - label: `72` chars (`MATCH_LABEL_LEN`)\n  - description: `96` chars (`MATCH_DESCRIPTION_LEN`)\n- BM25 parameters in `packages/coding-agent/src/tool-discovery/tool-index.ts`:\n  - `BM25_K1 = 1.2`\n  - `BM25_B = 0.75`\n- Weighted corpus fields (`FIELD_WEIGHTS`):\n  - `name`: `6`\n  - `label`: `4`\n  - `mcpToolName`: `4`\n  - `serverName`: `2`\n  - `summary`: `2`\n  - each `schemaKey`: `1`\n- Summary fallback length for discoverable metadata: first `200` chars of `description` when no explicit summary exists (`getDiscoverableTool()` in `packages/coding-agent/src/tool-discovery/tool-index.ts`).\n\n## Errors\n- `execute()` throws `ToolError` for unavailable discovery hooks, disabled discovery mode, empty trimmed query, and non-positive/non-integer `limit`.\n- `searchDiscoverableTools()` throws `Error(\"Query must contain at least one letter or number.\")` if tokenization produces no alphanumeric tokens; `execute()` catches `Error` and rethrows `ToolError(error.message)`.\n- Empty corpus is not an error; search returns `[]`, activation is skipped, and the renderer message becomes either `No discoverable tools are currently loaded.` or `No matching tools found.`\n- `getDiscoverableToolsForDescription()` and `getDiscoverableToolSearchIndexForExecution()` swallow discovery-hook/cache errors and fall back to an empty corpus or rebuilt index.\n\n## Notes\n- The tool wire name stays `search_tool_bm25` for persisted-session back-compat, even though the source file is `search-tool-bm25.ts`.\n- Corpus composition is session-dependent and excludes already-active tools:\n  - Built-in entries appear only in `\"all\"` mode and only for registry tools whose `loadMode === \"discoverable\"` and are not currently active.\n  - Hidden/internal built-ins are intentionally excluded from the built-in corpus: `resolve`, `yield`, `report_finding`, `report_tool_issue` are called out in the `#collectDiscoverableBuiltinTools()` comment.\n- `AgentSession.getDiscoverableTools()` currently assembles built-in discoverable tools.\n- On startup, `packages/coding-agent/src/sdk.ts` hides non-essential discoverable built-ins in `tools.discoveryMode = \"all\"`; defaults are `read`, `bash`, and `edit` unless `tools.essentialOverride` changes them.\n- Query tokenization is simple and deterministic: camelCase is split, non-alphanumerics become spaces, tokens are lowercased, and only non-empty alphanumeric tokens survive.\n- Scores are rounded differently by surface: `details.tools[].score` keeps 6 decimals; the TUI line renders 3.\n",
 	"tools/ssh.md": "# ssh\n\n> Execute one remote command on a discovered SSH host.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ssh.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ssh.md`\n- Key collaborators:\n  - `packages/coding-agent/src/ssh/ssh-executor.ts` — runs `ssh`, captures output\n  - `packages/coding-agent/src/ssh/connection-manager.ts` — master-connection reuse, host probing\n  - `packages/coding-agent/src/ssh/sshfs-mount.ts` — optional `sshfs` mount side effect\n  - `packages/coding-agent/src/discovery/ssh.ts` — discovers host configs\n  - `packages/coding-agent/src/capability/ssh.ts` — canonical host shape\n  - `packages/coding-agent/src/session/streaming-output.ts` — tail streaming, truncation, artifacts\n  - `packages/coding-agent/src/tools/tool-timeouts.ts` — timeout clamp rules\n  - `packages/utils/src/dirs.ts` — user/project ssh config paths\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `host` | `string` | Yes | Host name key from discovered SSH config entries, not an arbitrary hostname/IP. |\n| `command` | `string` | Yes | Remote command string passed to `ssh` as the remote command. |\n| `cwd` | `string` | No | Remote working directory. The tool prepends a shell-specific `cd`/`Set-Location` wrapper. |\n| `timeout` | `number` | No | Timeout in seconds. Default `60`; clamped to `1..3600`. |\n\n## Outputs\nThe tool returns a standard text tool result built in `packages/coding-agent/src/tools/ssh.ts`:\n\n- `content`: one text block containing combined remote stdout+stderr, or `\"(no output)\"` when empty.\n- `details.meta.truncation`: present when output exceeded the in-memory tail window; derived from the executor summary.\n\nStreaming behavior:\n\n- While the command runs, `onUpdate` receives tail-only text snapshots built from `TailBuffer` in `packages/coding-agent/src/session/streaming-output.ts`.\n- Final output is single-shot after process exit.\n\nSide-channel artifacts:\n\n- When session artifact allocation is available and output exceeds the spill threshold, full output is written to a session artifact file and the returned summary carries its `artifactId` internally.\n- The ssh tool itself does not print the `artifact://...` URI into the result text.\n\nFailure behavior:\n\n- Unknown host, missing host config, timeout, cancellation, SSH startup failure, key validation failure, or non-zero remote exit all surface as thrown `ToolError`s.\n- Non-zero remote exit includes captured output plus `Command exited with code N`.\n\n## Flow\n1. `loadSshTool()` in `packages/coding-agent/src/tools/ssh.ts` calls `loadCapability(sshCapability.id, { cwd: session.cwd })` to discover hosts.\n2. `packages/coding-agent/src/discovery/ssh.ts` loads host entries from, in this order: project managed ssh config, user managed ssh config, `ssh.json` in the repo root, `.ssh.json` in the repo root.\n3. `getSSHConfigPath(\"project\")` and `getSSHConfigPath(\"user\")` in `packages/utils/src/dirs.ts` resolve those managed files to `.skc/ssh.json` in the project and `~/.skc/agent/ssh.json` in the user config dir. This tool does not read `~/.ssh/config`.\n4. Capability loading deduplicates by host name with first item winning; provider order is priority-sorted and the SSH JSON provider registers at priority `5`.\n5. `loadHosts()` in `packages/coding-agent/src/tools/ssh.ts` builds `hostsByName` and drops later duplicates again with `if (!hostsByName.has(host.name))`.\n6. Tool description text is built from `packages/coding-agent/src/prompts/tools/ssh.md` plus an `Available hosts:` list. Each host entry calls `getHostInfoForHost()` to show detected shell/OS when cached; otherwise it renders `detecting...`.\n7. On execute, `SshTool.execute()` rejects any `host` not in the discovered host-name set.\n8. `ensureHostInfo()` in `packages/coding-agent/src/ssh/connection-manager.ts` ensures an SSH master connection exists, loads cached host info from disk if present, and probes remote OS/shell when cache is missing or stale.\n9. `buildRemoteCommand()` in `packages/coding-agent/src/tools/ssh.ts` prepends a cwd change when `cwd` is provided:\n   - Unix-like or Windows compat shells: `cd -- '<cwd>' && <command>`\n   - Windows PowerShell: `Set-Location -Path '<cwd>'; <command>`\n   - Windows cmd: `cd /d \"<cwd>\" && <command>`\n10. `clampTimeout(\"ssh\", rawTimeout)` applies the `1..3600` second clamp from `packages/coding-agent/src/tools/tool-timeouts.ts`.\n11. `executeSSH()` in `packages/coding-agent/src/ssh/ssh-executor.ts` calls `ensureConnection(host)` again, opportunistically mounts the remote host root with `sshfs` if available, optionally wraps the command in `bash -c` or `sh -c` for Windows compat mode, then spawns `ssh` with `ptree.spawn`.\n12. Output from both stdout and stderr is piped into one `OutputSink`; chunks are sanitized and forwarded to streaming updates through `streamTailUpdates()`.\n13. On normal exit, the sink returns combined output plus truncation counters. On timeout or abort, `executeSSH()` returns `cancelled: true` and prefixes the output with a notice line such as `[SSH: ...]` or `[Command aborted: ...]`.\n14. `SshTool.execute()` converts `cancelled: true` into `ToolError`, converts non-zero exit codes into `ToolError`, otherwise returns the text result with truncation metadata.\n\n## Modes / Variants\n- **Tool unavailable**: `loadSshTool()` returns `null` when discovery finds no hosts, so the tool is not registered for that session.\n- **Unix-like target**: remote command is passed through directly, with optional `cd -- ... &&` prefix.\n- **Windows native shell**: cwd wrapper uses PowerShell `Set-Location` or cmd `cd /d`; command otherwise runs in the remote default Windows shell.\n- **Windows compat shell**: if host probing finds `bash` or `sh` on Windows, `executeSSH()` wraps the remote command as `bash -c '...'` or `sh -c '...'`. Host config can force compat on/off with `compat`.\n- **Cached vs probed host info**: shell/OS detection comes from in-memory cache, persisted JSON under the remote-host dir, or a fresh probe over SSH.\n- **Truncated vs untruncated output**: small output stays in memory; large output keeps only the last 50 KiB in memory and may spill full output to an artifact file.\n\n## Side Effects\n- Filesystem\n  - Reads managed SSH config JSON plus legacy `ssh.json` / `.ssh.json`.\n  - Validates private-key path existence and permissions before connecting.\n  - Persists probed host info as JSON under the remote-host cache dir via `persistHostInfo()`.\n  - May create the SSH control socket dir and, when `sshfs` exists, remote mount dirs.\n  - May write full command output to a session artifact file.\n- Network\n  - Opens SSH connections to the selected host.\n  - May issue extra probe commands to detect OS/shell and compat shells.\n- Subprocesses / native bindings\n  - Requires `ssh` on `PATH`; spawns it for connection checks, master startup, probing, and command execution.\n  - May call `sshfs`, `mountpoint`, `fusermount`/`fusermount3`, or `umount`.\n  - Sanitizes streamed text with `@sayknow-cli/natives` text sanitization.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Uses session artifact allocation when available.\n  - Registers postmortem cleanup hooks for SSH master connections and sshfs mounts.\n  - Tool concurrency is `exclusive`, so the agent scheduler should not run multiple ssh tool calls concurrently.\n- Background work / cancellation\n  - Process spawn receives the tool `AbortSignal`.\n  - Cancellation/timeout ends the running ssh process and returns a cancelled result that the tool turns into an error.\n\n## Limits & Caps\n- Timeout defaults/clamps: `default=60`, `min=1`, `max=3600` in `packages/coding-agent/src/tools/tool-timeouts.ts`.\n- Output tail window: `DEFAULT_MAX_BYTES = 50 * 1024` in `packages/coding-agent/src/session/streaming-output.ts`.\n- Output sink spill threshold defaults to the same `50 KiB`; once exceeded, only the tail remains in memory.\n- SSH master reuse persistence: `ControlPersist=3600` in `packages/coding-agent/src/ssh/connection-manager.ts` and `packages/coding-agent/src/ssh/sshfs-mount.ts`.\n- SSH host info schema version: `HOST_INFO_VERSION = 2` in `packages/coding-agent/src/ssh/connection-manager.ts`; stale cache entries are reprobed.\n- Streaming tail buffer compacts after more than `10` pending chunks (`MAX_PENDING`) before trimming.\n\n## Errors\n- `Unknown SSH host: ... Available hosts: ...` when the model passes a host name not present in discovery.\n- `SSH host not loaded: ...` if the discovered-name set and `hostsByName` map diverge.\n- `ssh binary not found on PATH` when `ssh` is unavailable.\n- `SSH key not found: ...`, `SSH key is not a file: ...`, or `SSH key permissions must be 600 or stricter: ...` from key validation.\n- `Failed to start SSH master for <target>: <stderr>` when control-master startup fails.\n- Non-zero remote command exit becomes `ToolError` with captured output and `Command exited with code N`.\n- Timeout becomes a cancelled result with output notice `[SSH: <timeout message>]`, then `ToolError`.\n- Abort becomes a cancelled result with output notice `[Command aborted: <message>]`, then `ToolError`.\n- `sshfs` mount failures are logged and ignored in `executeSSH()`; they do not fail the tool call.\n- Discovery parse problems do not fail tool loading; they become capability warnings. If all sources are empty/invalid, the tool simply does not load.\n\n## Notes\n- Host discovery is JSON-based only. The tool does not parse OpenSSH config files.\n- Discovery expands environment variables recursively in the parsed JSON and expands `~` in `key`/`keyPath`.\n- Host names are capability keys; the model must pass the config key, not the raw hostname.\n- Commands run without a PTY. `executeSSH()` uses `ptree.spawn(..., { stdin: \"pipe\", stderr: \"full\" })` and does not request an interactive terminal.\n- The tool exposes `cwd` but no `env`, `pty`, upload, download, or explicit file-transfer fields.\n- Lower layers support an `artifactId` for full output and a `remotePath` mount target, but `SshTool.execute()` does not expose those knobs.\n- Both stdout and stderr are merged into one output stream; ordering is whatever arrives through the two streams.\n- `StrictHostKeyChecking=accept-new` and `BatchMode=yes` are always set for connection checks, master startup, and command runs.\n- Connection reuse is keyed by discovered host name, not by raw target tuple alone.\n- `closeAllConnections()` and sshfs unmount cleanup run through postmortem hooks, not per-call teardown.\n",
-	"tools/task.md": "# task\n\n> Launch subagents for parallel, optionally isolated work.\n\n## Source\n- Entry: `packages/coding-agent/src/task/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/task.md`\n- Key collaborators:\n  - `packages/coding-agent/src/task/types.ts` — dynamic schema, progress/result types, output caps.\n  - `packages/coding-agent/src/task/discovery.ts` — resolve bundled SKC agents.\n  - `packages/coding-agent/src/task/agents.ts` — bundled agent definitions and frontmatter parsing.\n  - `packages/coding-agent/src/task/executor.ts` — create child sessions, run subagents, collect output.\n  - `packages/coding-agent/src/task/parallel.ts` — concurrency-limited scheduling and async semaphore.\n  - `packages/coding-agent/src/task/isolation-backend.ts` — isolation backend resolution and platform fallback.\n  - `packages/coding-agent/src/task/worktree.ts` — worktree / FUSE / ProjFS setup, patch capture, branch merge.\n  - `packages/coding-agent/src/task/output-manager.ts` — session-scoped `agent://` id allocation.\n  - `packages/coding-agent/src/task/simple-mode.ts` — `default` / `schema-free` / `independent` field gating.\n  - `packages/coding-agent/src/internal-urls/agent-protocol.ts` — resolve `agent://<id>` to saved subagent output.\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and recursion-depth gating.\n  - `packages/coding-agent/src/sdk.ts` — child-session router/tool wiring and per-subagent `AgentOutputManager`.\n  - `docs/task-agent-discovery.md` — deeper discovery and precedence notes.\n  - `docs/handoff-generation-pipeline.md` — session artifact/handoff persistence patterns used by the wider session layer.\n\n## Inputs\n\n### Default mode (`task.simple = \"default\"`)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `agent` | `string` | Yes | Exact agent name for every task item. Resolved at execution time through `discoverAgents(...)`. |\n| `tasks` | `Array<{ id: string; description: string; assignment: string }>` | Yes | Batch of small, self-contained task items. `id` max length 48 in schema; duplicate ids are rejected case-insensitively at runtime. |\n| `context` | `string` | No | Shared background prepended to every subagent system prompt. Trimmed before use. |\n| `schema` | `string` | No | JSON-encoded JTD schema. Overrides agent/session output schema when this mode allows task-level schemas. |\n| `isolated` | `boolean` | No | Only present when the tool is created with isolation enabled. Requests isolated execution for the whole batch. |\n\n`tasks[].description` is UI-only. `tasks[].assignment` is the actual per-task instruction.\n\n### Schema-free mode (`task.simple = \"schema-free\"`)\n\nSame as default, except `schema` is rejected by `validateTaskModeParams(...)` in `packages/coding-agent/src/task/index.ts`.\n\n### Independent mode (`task.simple = \"independent\"`)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `agent` | `string` | Yes | Exact agent name. |\n| `tasks` | `Array<{ id: string; description: string; assignment: string }>` | Yes | Same item shape, but each `assignment` must carry all required background because shared `context` is disabled. |\n| `isolated` | `boolean` | No | Same conditional field as above. |\n\nIn this mode both `context` and `schema` are rejected.\n\n## Outputs\nThe tool returns one text block plus `details: TaskToolDetails`.\n\n`details` fields:\n- `projectAgentsDir: string | null` — nearest discovered project `agents/` dir.\n- `results: SingleResult[]` — one entry per task in input order for synchronous execution; empty for async-launch responses.\n- `totalDurationMs: number`\n- `usage?: Usage` — sum of per-subagent assistant-message usage.\n- `outputPaths?: string[]` — written `.md` artifact paths for completed subagent outputs.\n- `progress?: AgentProgress[]` — live or final per-task progress snapshots.\n- `async?: { state: \"running\" | \"completed\" | \"failed\"; jobId: string; type: \"task\" }` — present for background execution updates/results.\n\n`SingleResult` includes:\n- identity: `index`, `id`, `agent`, `agentSource`, `description`, optional `assignment`\n- status: `exitCode`, optional `error`, optional `aborted`, optional `abortReason`\n- output: `output`, `stderr`, `truncated`, `durationMs`, `tokens`\n- artifact metadata: `outputPath?`, `patchPath?`, `branchName?`, `nestedPatches?`, `outputMeta?`\n- extracted tool data: `extractedToolData?` from registered subprocess tool handlers such as `yield` and `report_finding`\n\nArtifacts and side channels:\n- Every subagent with an artifacts dir writes `<id>.md`; `agent://<id>` resolves to that file.\n- If the output file is JSON, `agent://<id>/<path>` and `agent://<id>?q=<query>` perform JSON extraction in `packages/coding-agent/src/internal-urls/agent-protocol.ts`.\n- When the parent session persists artifacts, each subagent also gets `<id>.jsonl` session history.\n- Isolated patch mode writes `<id>.patch` per successful task before merge.\n- Async mode returns immediately after job registration, then emits `onUpdate(...)` progress snapshots and later hands completion to the session async-job pipeline.\n\n## Flow\n1. `TaskTool.create(...)` in `packages/coding-agent/src/task/index.ts` calls `discoverAgents(session.cwd)` once to build the dynamic prompt description from current agents and `task.simple` capabilities.\n2. `execute(...)` validates mode-gated fields with `validateTaskModeParams(...)`.\n3. It decides async vs sync:\n   - sync when `async.enabled` is false\n   - sync when the selected cached agent has `blocking === true`\n   - sync when `tasks.length === 0`\n   - otherwise async job scheduling\n4. Async path:\n   - allocate unique output ids with `AgentOutputManager.allocateBatch(...)`\n   - create one async job per task through `session.asyncJobManager.register(...)`\n   - limit concurrent job bodies with `Semaphore(task.maxConcurrency)` from `packages/coding-agent/src/task/parallel.ts`\n   - each job body calls `#executeSync(...)` with a one-task batch and the preallocated id\n   - `onUpdate(...)` emits aggregate `progress` snapshots and `details.async`\n5. Sync path (`#executeSync(...)`) rediscovers agents from disk via `discoverAgents(...)`, so runtime resolution can differ from the earlier prompt description.\n6. It resolves the requested agent with `getAgent(...)`, rejects unknown or disabled agents, and enforces parent spawn policy plus `SKC_BLOCKED_AGENT` self-recursion prevention.\n7. It derives the effective output schema in priority order: task call `schema` (if allowed) → agent frontmatter `output` → inherited parent session schema.\n8. It validates task ids: missing ids and case-insensitive duplicates are immediate errors.\n9. If `isolated` was requested, it requires a git repo (`getRepoRoot(...)` / `captureBaseline(...)`) and resolves the actual backend through `resolveIsolationBackendForTaskExecution(...)`.\n10. It chooses an artifacts dir from the parent session when available, otherwise a temp dir, and writes `context.md` there when `session.getCompactContext?.()` returns content.\n11. It allocates unique ids again if the caller did not preallocate them, then builds `tasksWithUniqueIds`.\n12. For each task, it seeds an `AgentProgress` entry and runs `runTask(...)` through `mapWithConcurrencyLimit(...)` using `task.maxConcurrency`.\n13. Non-isolated `runTask(...)` calls `runSubprocess(...)` directly with parent cwd.\n14. Isolated `runTask(...)`:\n   - creates an isolation workspace (`ensureWorktree(...)`, `ensureFuseOverlay(...)`, or `ensureProjfsOverlay(...)`)\n   - applies the captured baseline for worktrees\n   - runs `runSubprocess(...)` inside that workspace\n   - on success, either commits to a per-task branch (`mergeMode === \"branch\"`) or captures a patch with `captureDeltaPatch(...)`\n   - always cleans up the isolation workspace/backend\n15. `runSubprocess(...)` in `packages/coding-agent/src/task/executor.ts` creates a child agent session with:\n   - isolated settings snapshot via `Settings.isolated(...)`, forcing `async.enabled = false` and `bash.autoBackground.enabled = false`\n   - child `agentId` / `parentTaskPrefix` equal to the allocated task id\n   - child internal URL router and `AgentOutputManager` from `packages/coding-agent/src/sdk.ts`\n   - the shared `context`, optional `context.md` reference, optional isolation worktree path, output schema, and IRC peer roster in the system prompt template\n16. Child tool availability is derived from the agent definition plus runtime guards:\n   - explicit `agent.tools` if provided\n   - auto-add `task` when the agent has `spawns` and recursion depth allows it\n   - remove `task` at or past `task.maxRecursionDepth`\n   - expand `exec` to `eval` and `bash`\n   - strip parent-owned `todo_write` after session creation\n17. `runSubprocess(...)` subscribes to child agent events, coalesces progress updates every 150 ms, forwards lifecycle/progress events on the parent event bus, and extracts tool data through `subprocessToolRegistry`.\n18. The child must finish through the hidden `yield` tool. If it does not, `runSubprocess(...)` sends up to 3 reminder prompts; the last reminder forces `toolChoice = yield` when supported.\n19. Finalization uses `finalizeSubprocessOutput(...)` to reconcile raw assistant text, `yield` payloads, structured schemas, `report_finding` data, and abort states. Output is truncated with `MAX_OUTPUT_BYTES` / `MAX_OUTPUT_LINES` before returning to the parent, but the full raw output is still written to `<id>.md`.\n20. After all sync tasks finish, `#executeSync(...)` aggregates usage, collects artifact paths, and if isolation was used merges results back:\n   - branch mode: cherry-pick per-task branches with `mergeTaskBranches(...)`, then delete merged branches with `cleanupTaskBranches(...)`\n   - patch mode: combine non-empty patch artifacts, dry-check with `git.patch.canApplyText(...)`, then apply or leave manual artifacts\n   - nested repo patches are applied separately with `applyNestedPatches(...)`\n21. The final text summary is rendered from `packages/coding-agent/src/prompts/tools/task-summary.md` and includes `agent://<id>` handles for outputs that exist.\n\n## Modes / Variants\n- Execution mode\n  - Sync inline execution — default path.\n  - Async background execution — one async job per task item when `async.enabled` is on and the chosen agent is not marked `blocking`.\n- Simple mode\n  - `default` — accepts shared `context` and per-call `schema`.\n  - `schema-free` — accepts `context`, rejects `schema`.\n  - `independent` — rejects `context` and `schema`; each assignment stands alone.\n- Isolation backend\n  - `none` — no isolation.\n  - `worktree` — detached git worktree plus baseline replay.\n  - `fuse-overlay` — Unix FUSE overlay mount.\n  - `fuse-projfs` — Windows ProjFS overlay.\n- Isolation merge strategy\n  - Patch mode — capture/apply root patches, keep patch artifacts when application fails.\n  - Branch mode — commit each task onto `skc/task/<id>` branch, cherry-pick into parent, preserve failed branches for manual resolution.\n- Agent source\n  - Bundled SKC agents — retained four-agent surface.\n  - Bundled agents — appended last from `packages/coding-agent/src/task/agents.ts`.\n- Bundled agent types\n  - `explore` — read-only scout with structured handoff output.\n  - `plan` — architecture/planning agent; may spawn `explore`.\n  - `designer` — UI/UX specialist.\n  - `reviewer` — review agent with `report_finding` extraction.\n  - `task` — general-purpose worker with full capabilities.\n  - `quick_task` — low-reasoning mechanical worker using the same task prompt body.\n  - `librarian` — source-grounded external API/library researcher.\n\n## Side Effects\n- Filesystem\n  - Writes `context.md`, `<id>.jsonl`, and `<id>.md` under the session artifacts dir or a temp task dir.\n  - In isolated patch mode writes `<id>.patch` artifacts.\n  - Creates/removes worktrees or overlay mount directories.\n  - In branch mode creates temporary worktrees and task branches.\n- Network\n  - Child sessions may use whichever networked tools/models their active tool set permits.\n- Subprocesses / native bindings\n  - `fuse-overlayfs` and `fusermount`/`fusermount3` for FUSE isolation.\n  - ProjFS native bindings via `@sayknow-cli/natives` on Windows.\n  - Git operations for baseline capture, patch apply, worktrees, branches, stash, cherry-pick, commits.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Creates child `AgentSession` instances with isolated settings snapshots.\n  - Registers async jobs in `session.asyncJobManager` for background task mode.\n  - Emits `task:subagent:event`, `task:subagent:progress`, and `task:subagent:lifecycle` on the parent event bus.\n  - Allocates session-scoped output ids through `AgentOutputManager` so `agent://` remains unique across invocations and resumes.\n  - Shares the parent `local://` root with subagents by passing `localProtocolOptions` through `createAgentSession(...)`.\n- User-visible prompts / interactive UI\n  - Async mode streams aggregate progress updates.\n  - Missing-`yield` recovery sends up to three internal reminder prompts to the child session.\n  - Final summaries include `<system-notification>` blocks for isolation fallbacks or merge failures.\n- Background work / cancellation\n  - Parent abort stops scheduling new work, aborts active child sessions, and marks unscheduled tasks as skipped.\n  - Async jobs keep their own cancellation via `AsyncJobManager`.\n  - Await timeouts are observation windows only: they do not stop, fail, or make a subagent stale. Inspect/list and continue work; cancel only when the subagent has actually failed, gone off-track, or become unrecoverably wrong.\n\n## Limits & Caps\n- Per-subagent output truncation: `MAX_OUTPUT_BYTES = 500_000` and `MAX_OUTPUT_LINES = 5000` in `packages/coding-agent/src/task/types.ts`. Full raw output is still written to `<id>.md` before truncation is returned to the caller.\n- Progress coalescing in child execution: `PROGRESS_COALESCE_MS = 150` in `packages/coding-agent/src/task/executor.ts`.\n- Recent output tail for progress: `RECENT_OUTPUT_TAIL_BYTES = 8 * 1024` and `recentOutput` keeps the last 8 non-empty lines in `packages/coding-agent/src/task/executor.ts`.\n- Missing-`yield` reminder retries: `MAX_YIELD_RETRIES = 3` in `packages/coding-agent/src/task/executor.ts`.\n- Task id schema cap: `tasks[].id` `maxLength: 48` in `packages/coding-agent/src/task/types.ts`.\n- Prompt text says ids should be `≤32` chars, but the runtime schema allows 48; this mismatch is real.\n- Async/full sync parallelism both use `task.maxConcurrency` from settings:\n  - sync path: `mapWithConcurrencyLimit(...)`\n  - async path: `Semaphore(...)` around job bodies\n- Recursion depth gate: `task.maxRecursionDepth` from settings; `packages/coding-agent/src/tools/index.ts` hides the `task` tool at or beyond the limit, and `runSubprocess(...)` also strips child `task` access at max depth.\n- Final inline summary preview per task uses `fullOutputThreshold = 5000` chars in `packages/coding-agent/src/task/index.ts`; longer outputs are summarized while `agent://<id>` points to the full artifact.\n\n## Errors\n- Most validation failures are returned as normal tool text with empty `results`, not thrown:\n  - invalid simple-mode fields\n  - unknown/disabled agent\n  - missing tasks\n  - missing/duplicate task ids\n  - spawn-policy denial\n  - requesting `isolated` while isolation mode is `none`\n- Isolated execution without a git repo returns `Isolated task execution requires a git repository. ...`.\n- Backend resolution can return a hard error (`ProjFS isolation initialization failed...`) or a non-fatal warning with fallback to `worktree`.\n- `mapWithConcurrencyLimit(...)` fails fast on non-abort worker exceptions; already completed results are preserved only in the thrown path’s local state, not surfaced unless the caller catches and converts them.\n- Child-session failures surface as `SingleResult.exitCode = 1` with `stderr`/`error` populated.\n- If the child omits `yield`, `finalizeSubprocessOutput(...)` injects warnings such as `SYSTEM WARNING: Subagent exited without calling yield tool after 3 reminders.`\n- Async scheduling failures are accumulated per task; if no jobs start, the tool returns `Failed to start background task jobs: ...`.\n- `agent://<id>` resolution errors are model-visible when another tool reads them: no session, no artifacts dir, missing id, conflicting extraction syntax, or invalid JSON for extraction.\n\n## Notes\n- Bundled agent definitions are embedded in `packages/coding-agent/src/task/agents.ts`.\n- `TaskTool.create(...)` caches discovered agents only for description rendering and the async blocking-agent decision. `#executeSync(...)` rediscovers agents each call.\n- Custom agent frontmatter can override bundled agents by name. Bundled definitions are embedded at build time in `packages/coding-agent/src/task/agents.ts`.\n- Child sessions do not inherit conversation history automatically. The only built-in carry-over is shared `context`, optional `context.md`, workspace tree/context files, and shared `local://` root.\n- `Settings.isolated(...)` gives each child a session-isolated settings snapshot; tool enablement is recomputed inside the child session rather than sharing mutable parent tool state.\n- Plan mode mutates an `effectiveAgent` with a read-only tool subset and plan-mode prompt text, but `runSubprocess(...)` is still invoked with `agent` rather than `effectiveAgent`. Model/thinking/schema overrides use the effective agent; prompt/tool/spawn restrictions do not fully flow through this call path.\n- Branch-mode merge temporarily stashes the parent repo before cherry-picking task branches. A stash-pop conflict is treated as merge failure and leaves recovery state behind.\n- Patch-mode only applies combined root patches if every successful task produced a patch and `git.patch.canApplyText(...)` succeeds.\n- Nested git repos are handled separately from the root repo. They are copied into isolated worktrees, diffed independently, and merged later with `applyNestedPatches(...)` because parent git cannot track their file-level changes.\n- `agent://` ids are numeric-prefixed (`0-Task`, `1-Task`, nested like `0-Parent.0-Child`) by `AgentOutputManager`; this is what prevents artifact collisions across repeated or nested task invocations.\n",
+	"tools/task.md": "# task\n\n> Launch subagents for parallel, optionally isolated work.\n\n## Source\n- Entry: `packages/coding-agent/src/task/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/task.md`\n- Key collaborators:\n  - `packages/coding-agent/src/task/types.ts` — dynamic schema, progress/result types, output caps.\n  - `packages/coding-agent/src/task/discovery.ts` — resolve bundled SKC agents.\n  - `packages/coding-agent/src/task/agents.ts` — bundled agent definitions and frontmatter parsing.\n  - `packages/coding-agent/src/task/executor.ts` — create child sessions, run subagents, collect output.\n  - `packages/coding-agent/src/task/parallel.ts` — concurrency-limited scheduling and async semaphore.\n  - `packages/coding-agent/src/task/isolation-backend.ts` — isolation backend resolution and platform fallback.\n  - `packages/coding-agent/src/task/worktree.ts` — worktree / FUSE / ProjFS setup, patch capture, branch merge.\n  - `packages/coding-agent/src/task/output-manager.ts` — session-scoped `agent://` id allocation.\n  - `packages/coding-agent/src/task/simple-mode.ts` — `default` / `schema-free` / `independent` field gating.\n  - `packages/coding-agent/src/internal-urls/agent-protocol.ts` — resolve `agent://<id>` to saved subagent output.\n  - `packages/coding-agent/src/tools/index.ts` — tool registration and recursion-depth gating.\n  - `packages/coding-agent/src/sdk.ts` — child-session router/tool wiring and per-subagent `AgentOutputManager`.\n  - `docs/task-agent-discovery.md` — deeper discovery and precedence notes.\n  - `docs/handoff-generation-pipeline.md` — session artifact/handoff persistence patterns used by the wider session layer.\n\n## Inputs\n\n### Default mode (`task.simple = \"default\"`)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `agent` | `string` | Yes | Exact agent name for every task item. Resolved at execution time through `discoverAgents(...)`. |\n| `tasks` | `Array<{ id: string; description: string; assignment: string }>` | Yes | Batch of small, self-contained task items. `id` max length 48 in schema; duplicate ids are rejected case-insensitively at runtime. |\n| `context` | `string` | No | Shared background prepended to every subagent system prompt. Trimmed before use. |\n| `schema` | `string` | No | JSON-encoded JTD schema. Overrides agent/session output schema when this mode allows task-level schemas. |\n| `isolated` | `boolean` | No | Only present when the tool is created with isolation enabled. Requests isolated execution for the whole batch. |\n\n`tasks[].description` is UI-only. `tasks[].assignment` is the actual per-task instruction.\n\n### Schema-free mode (`task.simple = \"schema-free\"`)\n\nSame as default, except `schema` is rejected by `validateTaskModeParams(...)` in `packages/coding-agent/src/task/index.ts`.\n\n### Independent mode (`task.simple = \"independent\"`)\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `agent` | `string` | Yes | Exact agent name. |\n| `tasks` | `Array<{ id: string; description: string; assignment: string }>` | Yes | Same item shape, but each `assignment` must carry all required background because shared `context` is disabled. |\n| `isolated` | `boolean` | No | Same conditional field as above. |\n\nIn this mode both `context` and `schema` are rejected.\n\n## Outputs\nThe tool returns one text block plus `details: TaskToolDetails`.\n\n`details` fields:\n- `projectAgentsDir: string | null` — nearest discovered project `agents/` dir.\n- `results: SingleResult[]` — one entry per task in input order for synchronous execution; empty for async-launch responses.\n- `totalDurationMs: number`\n- `usage?: Usage` — sum of per-subagent assistant-message usage.\n- `outputPaths?: string[]` — written `.md` artifact paths for completed subagent outputs.\n- `progress?: AgentProgress[]` — live or final per-task progress snapshots.\n- `async?: { state: \"running\" | \"completed\" | \"failed\"; jobId: string; type: \"task\" }` — present for background execution updates/results.\n\n`SingleResult` includes:\n- identity: `index`, `id`, `agent`, `agentSource`, `description`, optional `assignment`\n- status: `exitCode`, optional `error`, optional `aborted`, optional `abortReason`\n- output: `output`, `stderr`, `truncated`, `durationMs`, `tokens`\n- artifact metadata: `outputPath?`, `patchPath?`, `branchName?`, `nestedPatches?`, `outputMeta?`\n- extracted tool data: `extractedToolData?` from registered subprocess tool handlers such as `yield` and `report_finding`\n\nArtifacts and side channels:\n- Every subagent with an artifacts dir writes `<id>.md`; `agent://<id>` resolves to that file.\n- If the output file is JSON, `agent://<id>/<path>` and `agent://<id>?q=<query>` perform JSON extraction in `packages/coding-agent/src/internal-urls/agent-protocol.ts`.\n- When the parent session persists artifacts, each subagent also gets `<id>.jsonl` session history.\n- Isolated patch mode writes `<id>.patch` per successful task before merge.\n- Async mode returns immediately after job registration, then emits `onUpdate(...)` progress snapshots and later hands completion to the session async-job pipeline.\n\n## Flow\n1. `TaskTool.create(...)` in `packages/coding-agent/src/task/index.ts` calls `discoverAgents(session.cwd)` once to build the dynamic prompt description from current agents and `task.simple` capabilities.\n2. `execute(...)` validates mode-gated fields with `validateTaskModeParams(...)`.\n3. It decides async vs sync:\n   - sync when `async.enabled` is false\n   - sync when the selected cached agent has `blocking === true`\n   - sync when `tasks.length === 0`\n   - otherwise async job scheduling\n4. Async path:\n   - allocate unique output ids with `AgentOutputManager.allocateBatch(...)`\n   - create one async job per task through `session.asyncJobManager.register(...)`\n   - limit concurrent job bodies with `Semaphore(task.maxConcurrency)` from `packages/coding-agent/src/task/parallel.ts`\n   - each job body calls `#executeSync(...)` with a one-task batch and the preallocated id\n   - `onUpdate(...)` emits aggregate `progress` snapshots and `details.async`\n5. Sync path (`#executeSync(...)`) rediscovers agents from disk via `discoverAgents(...)`, so runtime resolution can differ from the earlier prompt description.\n6. It resolves the requested agent with `getAgent(...)`, rejects unknown or disabled agents, and enforces parent spawn policy plus `SKC_BLOCKED_AGENT` self-recursion prevention.\n7. It derives the effective output schema in priority order: task call `schema` (if allowed) → agent frontmatter `output` → inherited parent session schema.\n8. It validates task ids: missing ids and case-insensitive duplicates are immediate errors.\n9. If `isolated` was requested, it requires a git repo (`getRepoRoot(...)` / `captureBaseline(...)`) and resolves the actual backend through `resolveIsolationBackendForTaskExecution(...)`.\n10. It chooses an artifacts dir from the parent session when available, otherwise a temp dir, and writes `context.md` there when `session.getCompactContext?.()` returns content.\n11. It allocates unique ids again if the caller did not preallocate them, then builds `tasksWithUniqueIds`.\n12. For each task, it seeds an `AgentProgress` entry and runs `runTask(...)` through `mapWithConcurrencyLimit(...)` using `task.maxConcurrency`.\n13. Non-isolated `runTask(...)` calls `runSubprocess(...)` directly with parent cwd.\n14. Isolated `runTask(...)`:\n   - creates an isolation workspace (`ensureWorktree(...)`, `ensureFuseOverlay(...)`, or `ensureProjfsOverlay(...)`)\n   - applies the captured baseline for worktrees\n   - runs `runSubprocess(...)` inside that workspace\n   - on success, either commits to a per-task branch (`mergeMode === \"branch\"`) or captures a patch with `captureDeltaPatch(...)`\n   - always cleans up the isolation workspace/backend\n15. `runSubprocess(...)` in `packages/coding-agent/src/task/executor.ts` creates a child agent session with:\n   - isolated settings snapshot via `Settings.isolated(...)`, forcing `async.enabled = false` and `bash.autoBackground.enabled = false`\n   - child `agentId` / `parentTaskPrefix` equal to the allocated task id\n   - child internal URL router and `AgentOutputManager` from `packages/coding-agent/src/sdk.ts`\n   - the shared `context`, optional `context.md` reference, optional isolation worktree path, output schema, and IRC peer roster in the system prompt template\n16. Child tool availability is derived from the agent definition plus runtime guards:\n   - explicit `agent.tools` if provided\n   - auto-add `task` when the agent has `spawns` and recursion depth allows it\n   - remove `task` at or past `task.maxRecursionDepth`\n   - expand `exec` to `eval` and `bash`\n   - strip parent-owned `todo_write` after session creation\n17. `runSubprocess(...)` subscribes to child agent events, coalesces progress updates every 150 ms, forwards lifecycle/progress events on the parent event bus, and extracts tool data through `subprocessToolRegistry`.\n18. The child must finish through the hidden `yield` tool. If it does not, `runSubprocess(...)` sends up to 3 reminder prompts; the last reminder forces `toolChoice = yield` when supported.\n19. Finalization uses `finalizeSubprocessOutput(...)` to reconcile raw assistant text, `yield` payloads, structured schemas, `report_finding` data, and abort states. Output is truncated with `MAX_OUTPUT_BYTES` / `MAX_OUTPUT_LINES` before returning to the parent, but the full raw output is still written to `<id>.md`.\n20. After all sync tasks finish, `#executeSync(...)` aggregates usage, collects artifact paths, and if isolation was used merges results back:\n   - branch mode: cherry-pick per-task branches with `mergeTaskBranches(...)`, then delete merged branches with `cleanupTaskBranches(...)`\n   - patch mode: combine non-empty patch artifacts, dry-check with `git.patch.canApplyText(...)`, then apply or leave manual artifacts\n   - nested repo patches are applied separately with `applyNestedPatches(...)`\n21. The final text summary is rendered from `packages/coding-agent/src/prompts/tools/task-summary.md` and includes `agent://<id>` handles for outputs that exist.\n\n## Modes / Variants\n- Execution mode\n  - Sync inline execution — default path.\n  - Async background execution — one async job per task item when `async.enabled` is on and the chosen agent is not marked `blocking`.\n- Simple mode\n  - `default` — accepts shared `context` and per-call `schema`.\n  - `schema-free` — accepts `context`, rejects `schema`.\n  - `independent` — rejects `context` and `schema`; each assignment stands alone.\n- Isolation backend\n  - `none` — no isolation.\n  - `worktree` — detached git worktree plus baseline replay.\n  - `fuse-overlay` — Unix FUSE overlay mount.\n  - `fuse-projfs` — Windows ProjFS overlay.\n- Isolation merge strategy\n  - Patch mode — capture/apply root patches, keep patch artifacts when application fails.\n  - Branch mode — commit each task onto `skc/task/<id>` branch, cherry-pick into parent, preserve failed branches for manual resolution.\n- Agent source\n  - Project/user agents discovered from configured agent directories.\n  - Bundled SKC role agents — the retained canonical four-agent surface from `packages/coding-agent/src/task/agents.ts`.\n- Bundled agent types\n  - `executor` — bounded implementation, fixes, and refactors.\n  - `architect` — read-only architecture and code-review assessment.\n  - `planner` — read-only sequencing and acceptance criteria.\n  - `critic` — read-only plan critique and actionability review.\n\n## Side Effects\n- Filesystem\n  - Writes `context.md`, `<id>.jsonl`, and `<id>.md` under the session artifacts dir or a temp task dir.\n  - In isolated patch mode writes `<id>.patch` artifacts.\n  - Creates/removes worktrees or overlay mount directories.\n  - In branch mode creates temporary worktrees and task branches.\n- Network\n  - Child sessions may use whichever networked tools/models their active tool set permits.\n- Subprocesses / native bindings\n  - `fuse-overlayfs` and `fusermount`/`fusermount3` for FUSE isolation.\n  - ProjFS native bindings via `@sayknow-cli/natives` on Windows.\n  - Git operations for baseline capture, patch apply, worktrees, branches, stash, cherry-pick, commits.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Creates child `AgentSession` instances with isolated settings snapshots.\n  - Registers async jobs in `session.asyncJobManager` for background task mode.\n  - Emits `task:subagent:event`, `task:subagent:progress`, and `task:subagent:lifecycle` on the parent event bus.\n  - Allocates session-scoped output ids through `AgentOutputManager` so `agent://` remains unique across invocations and resumes.\n  - Shares the parent `local://` root with subagents by passing `localProtocolOptions` through `createAgentSession(...)`.\n- User-visible prompts / interactive UI\n  - Async mode streams aggregate progress updates.\n  - Missing-`yield` recovery sends up to three internal reminder prompts to the child session.\n  - Final summaries include `<system-notification>` blocks for isolation fallbacks or merge failures.\n- Background work / cancellation\n  - Parent abort stops scheduling new work, aborts active child sessions, and marks unscheduled tasks as skipped.\n  - Async jobs keep their own cancellation via `AsyncJobManager`.\n  - Await timeouts are observation windows only: they do not stop, fail, or make a subagent stale. Inspect/list and continue work; cancel only when the subagent has actually failed, gone off-track, or become unrecoverably wrong.\n\n## Limits & Caps\n- Per-subagent output truncation: `MAX_OUTPUT_BYTES = 500_000` and `MAX_OUTPUT_LINES = 5000` in `packages/coding-agent/src/task/types.ts`. Full raw output is still written to `<id>.md` before truncation is returned to the caller.\n- Progress coalescing in child execution: `PROGRESS_COALESCE_MS = 150` in `packages/coding-agent/src/task/executor.ts`.\n- Recent output tail for progress: `RECENT_OUTPUT_TAIL_BYTES = 8 * 1024` and `recentOutput` keeps the last 8 non-empty lines in `packages/coding-agent/src/task/executor.ts`.\n- Missing-`yield` reminder retries: `MAX_YIELD_RETRIES = 3` in `packages/coding-agent/src/task/executor.ts`.\n- Task id schema cap: `tasks[].id` `maxLength: 48` in `packages/coding-agent/src/task/types.ts`.\n- Prompt text says ids should be `≤32` chars, but the runtime schema allows 48; this mismatch is real.\n- Async/full sync parallelism both use `task.maxConcurrency` from settings:\n  - sync path: `mapWithConcurrencyLimit(...)`\n  - async path: `Semaphore(...)` around job bodies\n- Recursion depth gate: `task.maxRecursionDepth` from settings; `packages/coding-agent/src/tools/index.ts` hides the `task` tool at or beyond the limit, and `runSubprocess(...)` also strips child `task` access at max depth.\n- Final inline summary preview per task uses `fullOutputThreshold = 5000` chars in `packages/coding-agent/src/task/index.ts`; longer outputs are summarized while `agent://<id>` points to the full artifact.\n\n## Errors\n- Most validation failures are returned as normal tool text with empty `results`, not thrown:\n  - invalid simple-mode fields\n  - unknown/disabled agent\n  - missing tasks\n  - missing/duplicate task ids\n  - spawn-policy denial\n  - requesting `isolated` while isolation mode is `none`\n- Isolated execution without a git repo returns `Isolated task execution requires a git repository. ...`.\n- Backend resolution can return a hard error (`ProjFS isolation initialization failed...`) or a non-fatal warning with fallback to `worktree`.\n- `mapWithConcurrencyLimit(...)` fails fast on non-abort worker exceptions; already completed results are preserved only in the thrown path’s local state, not surfaced unless the caller catches and converts them.\n- Child-session failures surface as `SingleResult.exitCode = 1` with `stderr`/`error` populated.\n- If the child omits `yield`, `finalizeSubprocessOutput(...)` injects warnings such as `SYSTEM WARNING: Subagent exited without calling yield tool after 3 reminders.`\n- Async scheduling failures are accumulated per task; if no jobs start, the tool returns `Failed to start background task jobs: ...`.\n- `agent://<id>` resolution errors are model-visible when another tool reads them: no session, no artifacts dir, missing id, conflicting extraction syntax, or invalid JSON for extraction.\n\n## Notes\n- Bundled agent definitions are embedded in `packages/coding-agent/src/task/agents.ts`.\n- `TaskTool.create(...)` caches discovered agents only for description rendering and the async blocking-agent decision. `#executeSync(...)` rediscovers agents each call.\n- Custom agent frontmatter can override bundled agents by name. Bundled definitions are embedded at build time in `packages/coding-agent/src/task/agents.ts`.\n- Child sessions do not inherit conversation history automatically. The only built-in carry-over is shared `context`, optional `context.md`, workspace tree/context files, and shared `local://` root.\n- `Settings.isolated(...)` gives each child a session-isolated settings snapshot; tool enablement is recomputed inside the child session rather than sharing mutable parent tool state.\n- Plan mode mutates an `effectiveAgent` with a read-only tool subset and plan-mode prompt text, but `runSubprocess(...)` is still invoked with `agent` rather than `effectiveAgent`. Model/thinking/schema overrides use the effective agent; prompt/tool/spawn restrictions do not fully flow through this call path.\n- Branch-mode merge temporarily stashes the parent repo before cherry-picking task branches. A stash-pop conflict is treated as merge failure and leaves recovery state behind.\n- Patch-mode only applies combined root patches if every successful task produced a patch and `git.patch.canApplyText(...)` succeeds.\n- Nested git repos are handled separately from the root repo. They are copied into isolated worktrees, diffed independently, and merged later with `applyNestedPatches(...)` because parent git cannot track their file-level changes.\n- `agent://` ids are numeric-prefixed (`0-Task`, `1-Task`, nested like `0-Parent.0-Child`) by `AgentOutputManager`; this is what prevents artifact collisions across repeated or nested task invocations.\n",
 	"tools/todo_write.md": "# todo_write\n\n> Applies ordered mutations to the session todo list and returns a text summary plus the full phase/task state.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/todo-write.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/todo-write.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/index.ts` — registers tool, exposes session hooks, gates availability.\n  - `packages/coding-agent/src/modes/controllers/event-controller.ts` — updates the visible todo UI on tool completion.\n  - `packages/coding-agent/src/session/agent-session.ts` — stores cached phases, auto-clears done/dropped tasks, emits failure reminders.\n  - `packages/coding-agent/src/modes/controllers/todo-command-controller.ts` — `/todo` command path, custom-entry persistence, transcript reminder injection.\n  - `packages/coding-agent/src/tools/render-utils.ts` — collapsed-preview cap for renderer trees.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `ops` | `TodoOpEntry[]` | Yes | Ordered operations to apply. `minItems: 1`.\n\n### `TodoOpEntry`\n\n| Op | Required fields | Optional fields | Effect |\n| --- | --- | --- | --- |\n| `init` | `list` | None of the other fields are used | Replaces the entire list with `list`; every new task starts `pending` before normalization. |\n| `start` | `task` | None | Marks one task `in_progress`; any other `in_progress` task is demoted to `pending`. |\n| `done` | `task` or `phase` or neither | None | Marks the target task, phase, or all tasks `completed`. |\n| `drop` | `task` or `phase` or neither | None | Marks the target task, phase, or all tasks `abandoned`. |\n| `rm` | `task` or `phase` or neither | None | Removes the target task, clears the phase's task list, or clears all task lists. |\n| `append` | `phase`, `items` | None | Appends new `pending` tasks to a phase; creates the phase if missing. |\n| `note` | `task`, `text` | None | Appends one trimmed note string to the task's `notes` array. |\n\n### Fields used inside ops\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `op` | `\"init\" | \"start\" | \"done\" | \"rm\" | \"drop\" | \"append\" | \"note\"` | Yes | Operation discriminator. |\n| `list` | `{ phase: string; items: string[] }[]` | For `init` | Full replacement payload. Each `items` array has `minItems: 1`. |\n| `task` | `string` | For `start`; for task-targeted `done`/`drop`/`rm`/`note` | Exact task content match. |\n| `phase` | `string` | For `append`; for phase-targeted `done`/`drop`/`rm` | Exact phase name match, except `append` lazily creates a missing phase. |\n| `items` | `string[]` | For `append` | Tasks to append. `minItems: 1`. |\n| `text` | `string` | For `note` | Note text; trailing whitespace is stripped before storing. Empty-after-trim is rejected. |\n\n## Outputs\nThe tool returns a single-shot `AgentToolResult`:\n\n- `content`: one text part containing the summary from `formatSummary(...)`.\n  - Empty final state with no errors: `Todo list cleared.`\n  - Non-empty final state: remaining-item list, current phase progress, then a per-phase tree.\n  - If the active `in_progress` task has notes, the summary includes the note bodies inline.\n  - If any op produced validation/runtime errors, the summary starts with `Errors: ...` but still returns the mutated state.\n- `details`:\n  - `phases: TodoPhase[]`\n  - `storage: \"session\" | \"memory\"`\n\n`TodoPhase` / `TodoItem` state model:\n\n- `TodoPhase`: `{ name: string, tasks: TodoItem[] }`\n- `TodoItem`: `{ content: string, status: \"pending\" | \"in_progress\" | \"completed\" | \"abandoned\", notes?: string[] }`\n\nThe TUI renderer (`todoWriteToolRenderer`) merges call and result into one transcript block, renders phases as a tree, shows note counts as superscripts, and renders the note bodies only for the current `in_progress` task. Collapsed transcript previews cap tree items at `PREVIEW_LIMITS.COLLAPSED_ITEMS` (`8`).\n\n## Flow\n1. `TodoWriteTool.execute(...)` clones the current cached phases from `session.getTodoPhases?.() ?? []` (`packages/coding-agent/src/tools/todo-write.ts`).\n2. `applyParams(...)` walks `params.ops` in order and applies each entry with `applyEntry(...)`.\n3. Each op mutates the working phase array:\n   - `initPhases(...)` rebuilds the list from scratch.\n   - `start` resolves a task by exact `content`, demotes every other `in_progress` task to `pending`, then marks the target `in_progress`.\n   - `done` / `drop` use `getTaskTargets(...)` to target one task, one phase, or every task.\n   - `rm` removes one task, clears one phase's `tasks`, or clears all phases' task arrays.\n   - `appendItems(...)` resolves or creates the target phase and pushes new `pending` tasks unless the same task content already exists anywhere.\n   - `note` trims trailing whitespace, rejects empty text, and appends the note to `task.notes`.\n4. Missing task/phase references are recorded in an `errors` array by `resolveTaskOrError(...)` / `resolvePhaseOrError(...)`; execution continues through the rest of the batch.\n5. After the full batch, `normalizeInProgressTask(...)` enforces the single-active-task invariant:\n   - if multiple tasks are `in_progress`, only the first stays active and the rest become `pending`;\n   - if none are `in_progress`, the first `pending` task in phase/task order is auto-promoted to `in_progress`.\n6. `execute(...)` stores the normalized phases with `session.setTodoPhases?.(...)` and reports `storage` as `\"session\"` when `session.getSessionFile()` exists, else `\"memory\"`.\n7. The agent runtime also watches `todo_write` tool results in `packages/coding-agent/src/session/agent-session.ts`; successful results refresh cached todos, failed results inject a hidden next-turn reminder telling the model that todo progress is not visible until it retries.\n8. The event controller updates the visible todo UI from `result.details.phases` on success, or shows a warning on error (`packages/coding-agent/src/modes/controllers/event-controller.ts`).\n\n## Modes / Variants\n### State transitions\n\n| Current status | `start` | `done` | `drop` | `rm` | `append` | `note` |\n| --- | --- | --- | --- | --- | --- | --- |\n| `pending` | `in_progress` on target | `completed` | `abandoned` | Removed | New tasks enter as `pending` | No status change |\n| `in_progress` | Target stays `in_progress`; non-target active tasks become `pending` | `completed` | `abandoned` | Removed | No status change | No status change |\n| `completed` | Can be set back to `in_progress` if targeted | Stays `completed` | Becomes `abandoned` if targeted | Removed | No status change | No status change |\n| `abandoned` | Can be set back to `in_progress` if targeted | Becomes `completed` if targeted | Stays `abandoned` | Removed | No status change | No status change |\n\nNormalization then re-applies the single-active-task rule after the full op batch.\n\n### Op targeting rules\n- `done`, `drop`, `rm`:\n  - `task` set: affect one exact-content task.\n  - else `phase` set: affect every task in that exact-name phase.\n  - else: affect every task in every phase.\n- `append` is the only op that creates a missing phase.\n- `note` only targets a single task.\n- `init` discards previous phases entirely.\n\n### Markdown round-trip helpers\nThe same file also exposes non-tool helpers used by `/todo`:\n- `phasesToMarkdown(...)` serializes phases as headings plus checklist items (`[ ]`, `[/]`, `[x]`, `[-]`) with blockquote note bodies.\n- `markdownToPhases(...)` parses that format, defaults orphan tasks into a `Todos` phase, accepts `>` as an `in_progress` marker and `~` as `abandoned`, and runs the same normalization step.\n\n## Side Effects\n- Filesystem\n  - None in the tool itself.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Mutates the session todo cache through `setTodoPhases`.\n  - `storage` reports whether the session has a backing session file, but the tool does not append a custom session entry itself.\n  - Successful tool-result messages carry `details.phases`; `getLatestTodoPhasesFromEntries(...)` can reconstruct state later from those transcript entries.\n  - Failed `todo_write` results cause `agent-session` to enqueue a hidden next-turn reminder (`customType: \"todo-write-error-reminder\"`).\n- User-visible prompts / interactive UI\n  - Transcript block is rendered by `todoWriteToolRenderer` and merged with the call line.\n  - `event-controller` updates the visible todo panel from successful results.\n  - On error, `event-controller` shows `Todo update failed...`; the visible panel may stay stale until a later successful call.\n- Background work / cancellation\n  - `AgentSession.setTodoPhases(...)` schedules auto-clear timers for `completed` / `abandoned` tasks via `tasks.todoClearDelay`.\n\n## Limits & Caps\n- `ops` array: `minItems: 1` (`todoWriteSchema`).\n- `init.list[*].items`: `minItems: 1`.\n- `append.items`: `minItems: 1`.\n- Renderer collapsed preview: `PREVIEW_LIMITS.COLLAPSED_ITEMS = 8` (`packages/coding-agent/src/tools/render-utils.ts`).\n- Auto-clear delay: `tasks.todoClearDelay` default `60` seconds; `< 0` disables auto-clear, `0` clears on the next microtask (`packages/coding-agent/src/session/agent-session.ts`).\n- Tool execution mode: `concurrency = \"exclusive\"`, `strict = true`, `loadMode = \"discoverable\"`.\n\n## Errors\n- The tool does not throw for ordinary bad op payloads; it accumulates human-readable strings in `errors` and still returns success with the mutated state.\n- Error strings come from the helpers in `packages/coding-agent/src/tools/todo-write.ts`, including:\n  - `Missing list for init operation`\n  - `Missing task content`\n  - `Task \"...\" not found` with an extra empty-list hint when applicable\n  - `Missing phase name`\n  - `Phase \"...\" not found`\n  - `Missing phase name for append operation`\n  - `Missing items for append operation`\n  - `Task \"...\" already exists`\n  - `Missing text for note operation`\n- Because ops are processed in order, earlier errors do not roll back later ops.\n- Runtime-level tool failure is handled outside the tool body: `agent-session` injects a hidden reminder and the event controller warns the user that visible progress may be stale.\n- Idempotency is op-specific:\n  - `init` is a full replacement; replaying the same payload yields the same state.\n  - `start`, `done`, and `drop` are effectively idempotent on an existing target state, but `start` also demotes any other active task.\n  - `rm` is not idempotent for targeted removals: the second call errors because the task or phase is gone.\n  - `append` is not idempotent: duplicate task content is rejected with `Task \"...\" already exists`.\n  - `note` is append-only and never idempotent; replaying it adds another note entry.\n\n## Notes\n- Task lookup is exact string equality inside the tool. The model-facing prompt says task content and phase names are identifiers and should stay unique; `append` enforces task uniqueness globally, but `init` does not validate duplicate task or phase names.\n- `findTaskByContent(...)` returns the first matching task across phases. Duplicate task contents make later targeted ops ambiguous.\n- `normalizeInProgressTask(...)` runs after the whole batch, not after each op. A single call can intentionally build an intermediate invalid state and rely on final normalization.\n- `storage: \"session\"` means the session has a session-file backing; it does not mean this tool wrote a durable custom entry.\n- Reload persistence differs by path:\n  - plain `todo_write` calls survive in transcript tool-result details;\n  - `/todo` command edits additionally append `customType: \"user_todo_edit\"` entries and inject a visible-to-model `<system-reminder>` developer message describing the manual edit.\n- On session resume, `AgentSession.#syncTodoPhasesFromBranch()` strips `completed` and `abandoned` tasks before restoring the cached list. The `/todo` command works around that by reading the latest transcript/custom-entry state so historical done/dropped tasks still appear to the user.\n- Tool availability is gated by `todo.enabled`, and the registry excludes it when `includeYield` is enabled (`packages/coding-agent/src/tools/index.ts`).\n- Subagents do not inherit `todo_write`; `packages/coding-agent/src/task/executor.ts` filters it out as a parent-owned tool.\n",
 	"tools/web_search.md": "# web_search\n\n> Run one web query through the first available search provider and return LLM-formatted answer, source URLs, and optional citations.\n\n## Source\n- Entry: `packages/coding-agent/src/web/search/index.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/web-search.md`\n- Key collaborators:\n  - `packages/coding-agent/src/web/search/provider.ts` — lazy provider registry; availability chain.\n  - `packages/coding-agent/src/web/search/types.ts` — unified `SearchResponse` / `SearchProviderError` types.\n  - `packages/coding-agent/src/web/search/render.ts` — TUI renderer details type.\n  - `packages/coding-agent/src/web/search/providers/base.ts` — provider interface and shared params contract.\n  - `packages/coding-agent/src/web/search/providers/utils.ts` — credential lookup; source normalization.\n  - `packages/coding-agent/src/web/search/providers/anthropic.ts` — Anthropic model web-search provider.\n  - `packages/coding-agent/src/web/search/providers/brave.ts` — Brave Search API adapter.\n  - `packages/coding-agent/src/web/search/providers/duckduckgo.ts` — keyless DuckDuckGo html/lite scrape adapter (permissionless default/fallback).\n  - `packages/coding-agent/src/web/search/providers/openai-code.ts` — OpenAI code provider SSE adapter.\n  - `packages/coding-agent/src/web/search/providers/exa.ts` — Exa API adapter.\n  - `packages/coding-agent/src/web/search/providers/gemini.ts` — Gemini grounding SSE adapter.\n  - `packages/coding-agent/src/web/search/providers/jina.ts` — Jina Reader search adapter.\n  - `packages/coding-agent/src/web/search/providers/kagi.ts` — Kagi provider wrapper.\n  - `packages/coding-agent/src/web/search/providers/kimi.ts` — Kimi search adapter.\n  - `packages/coding-agent/src/web/search/providers/parallel.ts` — Parallel provider wrapper.\n  - `packages/coding-agent/src/web/search/providers/perplexity.ts` — Perplexity API / OAuth adapter.\n  - `packages/coding-agent/src/web/search/providers/searxng.ts` — self-hosted SearXNG adapter.\n  - `packages/coding-agent/src/web/search/providers/synthetic.ts` — Synthetic search adapter.\n  - `packages/coding-agent/src/web/search/providers/tavily.ts` — Tavily search adapter.\n  - `packages/coding-agent/src/web/search/providers/zai.ts` — Z.AI remote search adapter.\n  - `packages/coding-agent/src/web/parallel.ts` — Parallel search/extract HTTP client.\n  - `packages/coding-agent/src/web/kagi.ts` — Kagi HTTP client.\n  - `packages/coding-agent/src/tools/index.ts` — built-in tool registration and enable flag.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `query` | `string` | Yes | Search query. `executeSearch()` rewrites any `2020`-`2029` substring to the current year before dispatch. |\n| `recency` | `\"day\" \\| \"week\" \\| \"month\" \\| \"year\"` | No | Time filter. Only providers that implement it use it. Prompt text says Brave and Perplexity; code also maps it for Tavily and SearXNG. |\n| `limit` | `number` | No | Max results to return. Usually becomes the provider request's result-count parameter when `num_search_results` is absent. |\n| `max_tokens` | `number` | No | Passed through as `maxOutputTokens` / `max_tokens` only by Anthropic, Gemini, and Perplexity API-key mode. Ignored by the other providers. |\n| `temperature` | `number` | No | Passed through only by Anthropic, Gemini, and Perplexity API-key mode. Ignored by the other providers. |\n| `num_search_results` | `number` | No | Requested upstream search breadth. For most providers this is the same count used for returned sources. Perplexity is the only adapter that keeps it distinct from `limit`. |\n\n## Outputs\nThe tool returns a single text content block plus structured `details`.\n\n- `content`: `[{ type: \"text\", text: string }]`\n- `details`: `SearchRenderDetails` from `packages/coding-agent/src/web/search/render.ts`\n  - `response: SearchResponse`\n  - `error?: string`\n\n`text` is produced by `formatForLLM()` in `packages/coding-agent/src/web/search/index.ts`:\n\n- If `response.answer` exists, it is emitted first.\n- If sources exist, a `## Sources` section follows with a source count, then one entry per source:\n  - `[n] <title> (<formatted age or published date>)`\n  - `    <url>`\n  - optional snippet line truncated to 240 chars.\n- If citations exist, a `## Citations` section follows with URL/title plus optional cited text truncated to 240 chars.\n- If related questions exist, a `## Related` bullet list follows.\n- If search queries exist, a `Search queries: <n>` section follows, capped to the first 3 queries and 120 chars each.\n\nFailure output is not thrown at the tool boundary when at least one provider was attempted. Instead the tool returns:\n\n- `content[0].text = \"Error: ...\"`\n- `details.response.provider = <last attempted provider> | \"none\"`\n- `details.error = ...`\n\nStreaming: none. `WebSearchTool.execute()` does not forward its `_signal` argument into `executeSearch()`, so provider cancellation is only available to internal callers that place `signal` inside `SearchQueryParams`.\n\n## Flow\n1. `WebSearchTool.execute()` in `packages/coding-agent/src/web/search/index.ts` delegates directly to `executeSearch()`.\n2. `executeSearch()` resolves the provider list via a single `resolveProviderChain(authStorage, params.provider ?? \"auto\", activeModelProvider)` call. The active model's provider is threaded in from `WebSearchTool` (`this.#session.model?.provider`, falling back to parsing `getActiveModelString()`) and from the CustomTool path (`ctx.model?.provider`).\n3. `resolveProviderChain()` is active-model-gated, not credential-scanning:\n   - an explicitly preferred/selected provider that is `isAvailable()` becomes the primary;\n   - otherwise the active model's own native search (`MODEL_PROVIDER_TO_SEARCH`) becomes the primary, but only when that provider's own credentials exist (`isAvailable()`);\n   - keyed standalone providers are never auto-selected — explicit selection only.\n4. DuckDuckGo (keyless, `isAvailable()` always true) is always appended as the terminal fallback, so a missing primary — or a primary runtime failure — still returns results with zero configuration. There is no longer a \"No web search provider configured\" path.\n5. For each provider in order, `executeSearch()` calls `provider.search()` with:\n   - `query` after year-rewrite,\n   - `limit`, `recency`, `temperature`, `maxOutputTokens`, `numSearchResults`,\n   - `systemPrompt` from `packages/coding-agent/src/prompts/tools/web-search.md`.\n6. On the first successful `SearchResponse`, `formatForLLM()` renders answer/sources/citations/related/search-queries into one text block and returns it with `details.response`.\n7. If a provider throws, `executeSearch()` records the error and tries the next provider. There is no provider-level parallel fan-out; fallback is sequential.\n8. After all candidates fail, `formatProviderError()` normalizes the last error:\n   - Anthropic `404` becomes `Anthropic web search returned 404 (model or endpoint not found).`\n   - `401`/`403` become `<Provider> authorization failed ...` except Z.AI, which preserves its raw message.\n   - other `SearchProviderError`s surface `error.message`.\n9. If more than one provider was attempted, the final message is `All web search providers failed (<labels>). Last error: <message>`; otherwise it is just the normalized last error.\n\n## Modes / Variants\n- **Provider selection**\n  - **Forced provider**: internal callers may pass `provider`; an unavailable forced provider falls back to the chain (which always ends in DuckDuckGo) instead of hard-failing (`packages/coding-agent/src/web/search/index.ts`). This field is not in the model-facing schema.\n  - **Preferred provider**: `setPreferredSearchProvider()` sets a module-global default consumed by `resolveProviderChain()`. `packages/coding-agent/src/sdk.ts` and `packages/coding-agent/src/modes/controllers/selector-controller.ts` wire this from settings.\n  - **Active-model-gated auto**: in `auto` mode, resolution maps the active model's provider to its own native search via `MODEL_PROVIDER_TO_SEARCH` (`openai|openai-codex→codex`, `anthropic→anthropic`, `google|google-gemini-cli|google-antigravity|gemini→gemini`, `moonshot|kimi-code|kimi→kimi`, `zai`, `perplexity`, `synthetic`), used only if that provider's creds exist; everything else falls to DuckDuckGo. `SEARCH_PROVIDER_ORDER` no longer drives auto credential scanning — it is retained for explicit selection, labels, and CLI option lists.\n- **Provider adapters**\n  - **Tavily** — `packages/coding-agent/src/web/search/providers/tavily.ts`\n    - Availability: API key from env or `agent.db` via `findCredential()`.\n    - Querying: POST `https://api.tavily.com/search`.\n    - `recency` maps to Tavily `time_range`; code explicitly keeps `topic` at default general scope instead of narrowing to news.\n    - `limit` / `num_search_results`: adapter uses `params.numSearchResults ?? params.limit`, clamped to `5..20` with default `5`.\n    - Output: `answer`, `sources`, `requestId`, `authMode: \"api_key\"`.\n  - **Perplexity** — `packages/coding-agent/src/web/search/providers/perplexity.ts`\n    - Availability: auth precedence is `PERPLEXITY_COOKIES` -> OAuth token in `agent.db` -> `PERPLEXITY_API_KEY` / `PPLX_API_KEY`.\n    - OAuth/cookie mode: POSTs to `https://www.perplexity.ai/rest/sse/perplexity_ask`, consumes SSE, merges partial events, extracts answer and source URLs, sets `authMode: \"oauth\"`.\n    - API-key mode: POSTs to `https://api.perplexity.ai/chat/completions` with `model: \"sonar-pro\"`, `search_mode: \"web\"`, `num_search_results`, optional `search_recency_filter`, `max_tokens`, `temperature`.\n    - `num_search_results` controls upstream API breadth only in API-key mode. `limit` is preserved separately as `num_results` and slices returned `sources` after parsing in both auth modes.\n    - Output may include `answer`, `sources`, `citations`, `usage`, `model`, `requestId`, `authMode`.\n  - **Brave** — `packages/coding-agent/src/web/search/providers/brave.ts`\n    - Availability: `BRAVE_API_KEY` only.\n    - Querying: GET `https://api.search.brave.com/res/v1/web/search` with `count`, `extra_snippets=true`, and `freshness=pd|pw|pm|py` for `recency`.\n    - `limit` / `num_search_results`: `params.numSearchResults ?? params.limit`, clamped to `1..20`, default `10`.\n    - Output: `sources`, `requestId`.\n  - **Jina** — `packages/coding-agent/src/web/search/providers/jina.ts`\n    - Availability: `JINA_API_KEY` only.\n    - Querying: GET-like fetch to `https://s.jina.ai/<encoded query>` with bearer auth.\n    - Ignores `recency`, `max_tokens`, and `temperature`.\n    - `limit` / `num_search_results`: adapter slices sources to `params.numSearchResults ?? params.limit` when provided; otherwise returns all payload items.\n    - Output: `sources` only.\n  - **Kimi** — `packages/coding-agent/src/web/search/providers/kimi.ts`\n    - Availability: `MOONSHOT_SEARCH_API_KEY`, `KIMI_SEARCH_API_KEY`, `MOONSHOT_API_KEY`, or `agent.db` credentials for `moonshot` / `kimi-code`.\n    - Querying: POST to `MOONSHOT_SEARCH_BASE_URL` / `KIMI_SEARCH_BASE_URL` / default `https://api.kimi.com/coding/v1/search` with `text_query`, `limit`, `enable_page_crawling`, `timeout_seconds: 30`.\n    - `limit` / `num_search_results`: `params.numSearchResults ?? params.limit`, clamped to `1..20`, default `10`.\n    - Output: `sources`, `requestId`.\n  - **Anthropic** — `packages/coding-agent/src/web/search/providers/anthropic.ts`\n    - Availability: `findAnthropicAuth()` from `@sayknow-cli/ai`.\n    - Querying: Anthropic model Messages API with web-search tool enabled.\n    - `max_tokens` and `temperature` pass through.\n    - `limit` and `num_search_results` are collapsed together before dispatch: `num_results = params.numSearchResults ?? params.limit`.\n    - Output may include `answer`, `sources`, `citations`, `searchQueries`, `usage.searchRequests`, `model`, `requestId`.\n  - **Gemini** — `packages/coding-agent/src/web/search/providers/gemini.ts`\n    - Availability: OAuth credentials in `agent.db` for `google-gemini-cli` or `google-antigravity`.\n    - Querying: SSE `streamGenerateContent` call with Google Search grounding enabled. Antigravity auth tries two fallback endpoints and retries `401/403/400 invalid auth` once after token refresh; `429/5xx` retry with exponential backoff and server-provided retry delay, capped by a `5 * 60 * 1000` ms rate-limit budget.\n    - `max_tokens` and `temperature` pass through as `generationConfig.maxOutputTokens` / `generationConfig.temperature`.\n    - `limit` and `num_search_results` are collapsed together before dispatch.\n    - Output may include `answer`, `sources`, `citations`, `searchQueries`, `usage`, `model`.\n  - **OpenAI code** — `packages/coding-agent/src/web/search/providers/openai-code.ts`\n    - Availability: non-expired OAuth credential for `openai-code` in `agent.db`.\n    - Querying: SSE POST to `https://chatgpt.com/backend-api/openai-code/responses` with `tool_choice: { type: \"web_search\" }` and `search_context_size: \"high\"` by default.\n    - Ignores `recency`, `max_tokens`, and `temperature` in this tool path.\n    - `limit` and `num_search_results` are collapsed together before dispatch.\n    - Output may include `answer`, `sources`, `usage`, `model`, `requestId`. If the streamed response has no `url_citation` annotations, the adapter falls back to scraping markdown links and bare URLs from the answer text.\n  - **Z.AI** — `packages/coding-agent/src/web/search/providers/zai.ts`\n    - Availability: env or `agent.db` credential for `zai`.\n    - Querying: JSON-RPC `tools/call` against the Z.AI `web_search_prime` search endpoint.\n    - Fallback chain inside the provider: tries `{query,count}`, then `{search_query,count}`, then `{search_query, search_engine:\"search-prime\", count}` when earlier attempts fail with argument-shape errors.\n    - `limit` and `num_search_results` are collapsed together before dispatch.\n    - Output may include parsed free-text `answer`, `sources`, `requestId`.\n  - **Exa** — `packages/coding-agent/src/web/search/providers/exa.ts`\n    - Availability: requires `EXA_API_KEY` and settings must not disable `exa.enabled` or `exa.enableSearch`.\n    - Querying: POST `https://api.exa.ai/search` with `EXA_API_KEY`. No no-key fallback is used.\n    - `limit` and `num_search_results` are collapsed together before dispatch.\n    - Output: synthesized `answer` from up to 3 result summaries, `sources`, `requestId`.\n  - **Parallel** — `packages/coding-agent/src/web/search/providers/parallel.ts`, `packages/coding-agent/src/web/parallel.ts`\n    - Availability: env or `agent.db` credential for `parallel`.\n    - Querying: POST `https://api.parallel.ai/v1beta/search` with `objective=query`, `search_queries=[query]`, `mode:\"fast\"`, `max_chars_per_result: 10000`, beta header `search-extract-2025-10-10`.\n    - There is no provider fan-out here despite the name; the current adapter always sends a one-element `search_queries` array.\n    - `limit` and `num_search_results` are collapsed together before dispatch, clamped to `1..40`, default `10`.\n    - Output: `sources`, `requestId`.\n  - **Kagi** — `packages/coding-agent/src/web/search/providers/kagi.ts`, `packages/coding-agent/src/web/kagi.ts`\n    - Availability: env or `agent.db` credential for `kagi`.\n    - Querying: GET `https://kagi.com/api/v0/search?q=<query>&limit=<n>` with `Authorization: Bot <key>`.\n    - `limit` and `num_search_results` are collapsed together before dispatch, clamped to `1..40`, default `10`.\n    - Output: `sources`, `relatedQuestions`, `requestId`.\n  - **Synthetic** — `packages/coding-agent/src/web/search/providers/synthetic.ts`\n    - Availability: env or `agent.db` credential for `synthetic`.\n    - Querying: POST `https://api.synthetic.new/v2/search` with `{ query }`.\n    - Ignores `recency`, `max_tokens`, and `temperature`.\n    - `limit` and `num_search_results` are collapsed together before dispatch.\n    - Output: `sources` only.\n  - **SearXNG** — `packages/coding-agent/src/web/search/providers/searxng.ts`\n    - Availability: endpoint from `searxng.endpoint` setting or `SEARXNG_ENDPOINT` env.\n    - Querying: GET `<endpoint>/search?format=json&q=...`; optional settings add `categories` and `language`.\n    - Auth precedence: Basic auth (`searxng.basicUsername` / `searxng.basicPassword` or env equivalents) over bearer token (`searxng.token` / `SEARXNG_TOKEN`). Basic credentials are validated for RFC 7617 restrictions.\n    - `recency` maps to `time_range`; `week` is downgraded to `month` because SearXNG does not support week.\n    - `limit` and `num_search_results` are collapsed together before dispatch, clamped to `1..20`, default `10`.\n    - Output: `sources`, `relatedQuestions` from `suggestions`.\n\n## Side Effects\n- Network\n  - Calls one or more external search providers over HTTPS until one succeeds or all fail.\n  - Provider-specific transports include JSON POST, JSON GET, SSE streaming (Perplexity OAuth/API, Gemini, OpenAI code), and JSON-RPC over HTTP (Z.AI).\n- Subprocesses / native bindings\n  - None.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Uses a module-global provider-instance cache in `packages/coding-agent/src/web/search/provider.ts`.\n  - Uses a module-global preferred-provider setting in the same file.\n  - `packages/coding-agent/src/tools/index.ts` gates tool availability behind `session.settings.get(\"web_search.enabled\")`.\n- Background work / cancellation\n  - Many provider adapters accept `AbortSignal`, but `WebSearchTool.execute()` does not pass its `_signal` into `executeSearch()`. Internal callers can still use cancellation by calling `runSearchQuery()` / `executeSearch()` with `signal` embedded in params.\n\n## Limits & Caps\n- Provider registry size: 15 providers (`SEARCH_PROVIDER_ORDER` in `packages/coding-agent/src/web/search/provider.ts`), including the keyless `duckduckgo` default/fallback. `SEARCH_PROVIDER_ORDER` no longer drives auto selection — see \"Active-model-gated auto\" above.\n- `formatForLLM()` truncates source snippets and citation text to 240 chars (`packages/coding-agent/src/web/search/index.ts`).\n- `formatForLLM()` emits at most 3 search queries, each truncated to 120 chars (`packages/coding-agent/src/web/search/index.ts`).\n- Brave result count: default `10`, max `20` (`DEFAULT_NUM_RESULTS`, `MAX_NUM_RESULTS` in `packages/coding-agent/src/web/search/providers/brave.ts`).\n- Tavily result count: default `5`, max `20` (`packages/coding-agent/src/web/search/providers/tavily.ts`).\n- Kimi result count: default `10`, max `20`; request timeout field fixed to `30` seconds (`packages/coding-agent/src/web/search/providers/kimi.ts`).\n- Parallel result count: default `10`, max `40`; per-result excerpt cap `10_000` chars (`packages/coding-agent/src/web/search/providers/parallel.ts`, `packages/coding-agent/src/web/parallel.ts`).\n- Kagi result count: default `10`, max `40` (`packages/coding-agent/src/web/search/providers/kagi.ts`).\n- SearXNG result count: default `10`, max `20` (`packages/coding-agent/src/web/search/providers/searxng.ts`).\n- Perplexity API-key mode defaults: `max_tokens = 8192`, `temperature = 0.2`, `num_search_results = 10` (`packages/coding-agent/src/web/search/providers/perplexity.ts`).\n- Anthropic defaults: model `anthropic-model-haiku-4-5`, `DEFAULT_MAX_TOKENS = 4096` when the provider omits `max_tokens` (`packages/coding-agent/src/web/search/providers/anthropic.ts`).\n- Gemini retries: up to `3` retries per endpoint, base delay `1000` ms, rate-limit delay budget `5 * 60 * 1000` ms (`packages/coding-agent/src/web/search/providers/gemini.ts`).\n\n## Errors\n- There is no \"no provider configured\" case: DuckDuckGo (keyless) is always appended as the terminal fallback, so the chain is never empty.\n- Tool-level all-failed case also returns a normal tool result with `Error: ...`; failures are summarized from the last attempted provider.\n- Provider adapters usually throw `SearchProviderError(provider, message, status)` for HTTP or protocol failures.\n- Availability probes intentionally swallow lookup errors and report `false` in many providers via `isApiKeyAvailable()`.\n- Per-provider notable failures:\n  - Anthropic: missing credentials throw a plain `Error`; a `404` is remapped to a special final message by `formatProviderError()`.\n  - Perplexity: missing auth throws a plain `Error`; OAuth stream `error_code` events become `SearchProviderError(\"perplexity\", ...)`.\n  - Gemini: auth refresh, endpoint fallback, and retry logic are internal; final exhausted failures surface as `SearchProviderError(\"gemini\", ...)`.\n  - OpenAI code and Gemini both fail if the HTTP response has no body after a `200`.\n  - Z.AI treats malformed SSE/JSON-RPC payloads as provider errors and retries only argument-shape failures across request variants.\n  - SearXNG `findAuth()` can throw configuration errors before any HTTP call if Basic auth fields are incomplete or invalid.\n\n## Notes\n- The model-facing schema does not expose `provider`, but internal callers can force one through `SearchQueryParams`.\n- `resolveProviderChain()` lazily imports provider modules and caches singleton instances. Just asking for labels via `getSearchProviderLabel()` does not trigger those imports.\n- Most providers treat `limit` and `num_search_results` as the same number because adapters pass `params.numSearchResults ?? params.limit`. Perplexity is the only implementation that preserves both concepts.\n- The prompt says `recency` is for Brave and Perplexity, but code also implements it for Tavily and SearXNG.\n- The year rewrite in `executeSearch()` is blunt: any `2020`-`2029` substring is replaced with the current year.\n- `packages/coding-agent/src/config/settings-schema.ts` exposes provider preferences for `auto`, `exa`, `brave`, `jina`, `kimi`, `perplexity`, `anthropic`, `zai`, `tavily`, `kagi`, `synthetic`, `parallel`, and `searxng`. Gemini and OpenAI code are in the registry and auto chain but not in that settings enum.\n- Exa availability fails closed unless `EXA_API_KEY` is present and Exa settings remain enabled.\n",
 	"tools/write.md": "# write\n\n> Create or overwrite a file, archive entry, or SQLite row.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/write.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/write.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/archive-reader.ts` — parse `archive.ext:entry` selectors.\n  - `packages/coding-agent/src/tools/sqlite-reader.ts` — detect SQLite paths and perform row insert/update/delete.\n  - `packages/coding-agent/src/lsp/index.ts` — format-on-write and diagnostics writethrough.\n  - `packages/coding-agent/src/tools/auto-generated-guard.ts` — block overwriting generated files.\n  - `packages/coding-agent/src/tools/fs-cache-invalidation.ts` — invalidate shared FS scan caches after writes.\n  - `packages/coding-agent/src/tools/plan-mode-guard.ts` — resolve paths and enforce plan-mode write policy.\n\n## Inputs\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `path` | `string` | Yes | Target path. Plain file path writes a filesystem file. `archive.ext:inner/path` writes an archive entry for `.tar`, `.tar.gz`, `.tgz`, or `.zip`. `db.sqlite:table` inserts a row. `db.sqlite:table:key` updates or deletes a row. |\n| `content` | `string` | Yes | Full replacement file content, archive entry content, or SQLite row payload. SQLite non-delete writes must parse as a JSON5 object. Empty or whitespace-only content deletes a SQLite row when `path` includes a row key. |\n\nWorked examples:\n\n```text\npath: \"src/generated/config.json\"\ncontent: \"{\\n  \\\"enabled\\\": true\\n}\\n\"\n```\n\n```text\npath: \"fixtures/archive.zip:templates/email.txt\"\ncontent: \"hello\\n\"\n```\n\n```text\npath: \"data/app.sqlite:users:42\"\ncontent: \"{name: 'Ada', active: true}\"\n```\n\n## Outputs\nSingle-shot result.\n\n- Success always returns a text block.\n  - Plain file write: `Successfully wrote <bytes> bytes to <relative-path>`.\n  - Archive write: `Successfully wrote <bytes> bytes to <relative-archive-path>:<entry-path>`.\n  - SQLite write: one of `Inserted row into <table>`, `Updated row '<key>' in <table>`, `No row updated ...`, `Deleted row ...`, `No row deleted ...`.\n- If hashline prefixes were copied from `read` output and stripped first, the first text block gets an extra note.\n- Plain file writes may also return `details.diagnostics` plus `details.meta.diagnostics` when LSP diagnostics-on-write is enabled.\n- SQLite writes use `toolResult(...).sourcePath(...)`, so `details.meta.sourcePath` points at the database file.\n- Archive writes return empty `details`.\n\n## Flow\n1. `WriteTool.execute()` in `packages/coding-agent/src/tools/write.ts` strips `LINE+ID|` hashline prefixes from `content` when the session is in hashline display mode.\n2. It calls `#resolveArchiveWritePath()` first. That uses `parseArchivePathCandidates()` from `packages/coding-agent/src/tools/archive-reader.ts`, checks candidate archive files on disk, and falls back to the longest matching archive suffix even when the archive file does not exist yet.\n3. Archive writes call `enforcePlanModeWrite(..., { op: exists ? \"update\" : \"create\" })`, then `#writeArchiveEntry()`.\n   - The parent directory of the archive file is created with `fs.mkdir(..., { recursive: true })`.\n   - `.zip` archives are read with `fflate.unzipSync()`, the target entry is replaced in an in-memory map, and the archive is rewritten with `fflate.zipSync()` + `Bun.write()`.\n   - `.tar`, `.tar.gz`, and `.tgz` archives are read with `Bun.Archive`, existing entries are copied into an object map, the target entry is replaced, and `Bun.Archive.write()` rewrites the archive.\n   - `invalidateFsScanAfterWrite()` runs on the archive file path.\n4. If the path is not treated as an archive, `execute()` calls `#resolveSqliteWritePath()`. That uses `parseSqlitePathCandidates()` and `isSqliteFile()` from `packages/coding-agent/src/tools/sqlite-reader.ts`. Existing non-SQLite files suppress the SQLite path interpretation.\n5. SQLite writes call `enforcePlanModeWrite(..., { op: \"update\" })`, then `#writeSqliteRow()`.\n   - The database must already exist; missing DBs throw `SQLite database '<path>' not found`.\n   - The tool opens `new Database(..., { create: false, strict: true })` and sets `PRAGMA busy_timeout = 3000`.\n   - Whitespace-only `content` with a row key deletes a row.\n   - Non-empty `content` is parsed with `Bun.JSON5.parse()`, must be a JSON object, and is routed to insert/update helpers from `packages/coding-agent/src/tools/sqlite-reader.ts`.\n   - `invalidateFsScanAfterWrite()` runs on the DB path and the connection is closed in `finally`.\n6. Otherwise the tool treats `path` as a plain filesystem file.\n   - `enforcePlanModeWrite(..., { op: \"create\" })` runs before path resolution.\n   - Existing files are checked by `assertEditableFile()` to block overwriting detected generated files.\n   - The session’s writethrough callback writes content. With LSP enabled and `lsp.formatOnWrite` / `lsp.diagnosticsOnWrite` settings on, `createLspWritethrough()` may format content, sync it through LSP servers, save it, and collect diagnostics. Otherwise `writethroughNoop()` writes directly with `Bun.write()` or `file.write()`.\n   - `invalidateFsScanAfterWrite()` runs on the file path.\n7. The tool returns a text result and optional diagnostics metadata.\n\n## Modes / Variants\n### Plain file path\n- Target is any path that does not resolve as an archive selector and does not resolve as an existing-or-new SQLite selector.\n- Existing files are overwritten.\n- `write.ts` does not call `fs.mkdir()` on this path; parent-directory creation is only implemented in the archive branch.\n\nExample:\n\n```text\npath: \"tmp/output.txt\"\ncontent: \"hello\\n\"\n```\n\n### Archive entry write\n- Selector syntax: `archive.ext:inner/path`.\n- Supported archive suffixes come from `parseArchivePathCandidates()`: `.tar`, `.tar.gz`, `.tgz`, `.zip`.\n- The inner path is normalized to `/`, strips empty and `.` segments, rejects `..`, and rejects directory targets ending in `/`.\n- Rewrites the whole archive file after replacing one entry.\n- Creates the parent directory for the archive file if needed.\n\nExample:\n\n```text\npath: \"build/assets.tar.gz:css/app.css\"\ncontent: \"body { color: black; }\\n\"\n```\n\n### SQLite table insert\n- Selector syntax: `db.sqlite:table`.\n- `content` must parse as a JSON5 object.\n- Empty object is allowed and becomes `INSERT INTO <table> DEFAULT VALUES`.\n- Query parameters are rejected for SQLite writes.\n\nExample:\n\n```text\npath: \"data/app.db:users\"\ncontent: \"{name: 'Ada', active: true}\"\n```\n\n### SQLite row update / delete\n- Selector syntax: `db.sqlite:table:key`.\n- Non-empty `content` updates the row.\n- Empty or whitespace-only `content` deletes the row.\n- Row lookup uses the single-column primary key if present; otherwise it falls back to `rowid`. Composite primary keys and `WITHOUT ROWID` tables are rejected for key-based writes.\n\nExample update:\n\n```text\npath: \"data/app.sqlite:users:42\"\ncontent: \"{email: 'ada@example.com'}\"\n```\n\nExample delete:\n\n```text\npath: \"data/app.sqlite:users:42\"\ncontent: \"\"\n```\n\n## Side Effects\n- Filesystem\n  - Creates or overwrites plain files.\n  - Rewrites entire archive files when writing an archive entry.\n  - Creates parent directories for archive files only.\n  - Mutates existing SQLite databases; never creates a new SQLite DB.\n- Subprocesses / native bindings\n  - Uses Bun SQLite bindings via `bun:sqlite`.\n  - Uses Bun archive APIs and lazily imports `fflate` for ZIP reads/writes.\n  - May talk to configured LSP servers through `packages/coding-agent/src/lsp/index.ts`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Invalidates shared filesystem scan cache entries through `invalidateFsScanAfterWrite()`.\n  - Enforces plan-mode write restrictions before mutating the target.\n- Background work / cancellation\n  - Marks the tool `nonAbortable = true` and `concurrency = \"exclusive\"` in `WriteTool`.\n  - LSP writethrough can schedule deferred diagnostics fetches after a timeout, but plain `write.ts` only consumes the immediate return value.\n\n## Limits & Caps\n- `WriteTool` itself exposes no byte cap beyond storing `content` in memory and, for archives, rebuilding the archive in memory.\n- Generated-file detection reads at most `CHECK_BYTE_COUNT = 1024` bytes and `HEADER_LINE_LIMIT = 40` header lines from an existing file in `packages/coding-agent/src/tools/auto-generated-guard.ts`.\n- SQLite writes set `PRAGMA busy_timeout = 3000`.\n- LSP writethrough uses a `5_000` ms operation timeout in `runLspWritethrough()` and may schedule a deferred diagnostics fetch with `AbortSignal.timeout(25_000)` in `scheduleDeferredDiagnosticsFetch()`.\n\n## Errors\n- Invalid archive subpaths throw `ToolError` with messages such as:\n  - `Archive write path must target a file inside the archive`\n  - `Archive write path must target a file, not a directory`\n  - `Archive path cannot contain '..'`\n- SQLite path parsing throws on unsupported forms:\n  - `SQLite write paths do not support query parameters`\n  - `SQLite write path must target a table`\n  - `SQLite row writes require a non-empty row key`\n- Missing SQLite DBs surface as `SQLite database '<path>' not found`.\n- SQLite content errors are model-visible `ToolError`s, including invalid JSON5, non-object payloads, unknown columns, non-scalar values, empty update objects, composite primary keys, and `WITHOUT ROWID` tables.\n- Existing plain files may be rejected by `assertEditableFile()` when they look generated.\n- Archive read/write failures and unexpected SQLite exceptions are wrapped in `ToolError(error.message)`.\n- If no LSP server matches or LSP formatting/diagnostics times out, file writes still fall back to writing content; diagnostics may be omitted.\n\n## Notes\n- Archive path detection runs before SQLite detection. A path that matches an archive selector is never treated as SQLite.\n- SQLite detection declines when an existing file with a `.sqlite` / `.db` suffix is present but does not have SQLite magic bytes; then the path falls back to a plain file write.\n- ZIP entry content is encoded with `new TextEncoder().encode(content)` in `#writeArchiveEntry()`. Non-ZIP archive writes pass the string directly to `Bun.Archive.write()`.\n- The prompt forbids two common anti-patterns: using `write` for routine edits that should use `edit`, and creating `*.md` / `README` files unless explicitly requested. It also forbids emojis unless requested.\n- Plain file writes report byte count using `cleanContent.length`, which is UTF-16 code units in JS, not an on-disk byte measurement.\n- `stripWriteContent()` only removes hashline prefixes when the session’s file display mode has `hashLines` enabled; otherwise content is written unchanged.\n",