@sayknow-cli/coding-agent 0.3.5 → 0.3.7

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

@@ -1,12 +1,13 @@
 // 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","aside-integration.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","bot-integration.md","brand-assets.md","bridge.md","codebase-overview.md","codegraph-custom-tool.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","notifications-sdk.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-plugins.md","skc-session-clawhip-routing.md","standalone-mcp.md","telegram-onboarding.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/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","ui-design-visual-qa.md"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","FORK_MAINTENANCE.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","analyze-me-with-skc.md","aside-integration.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","bot-integration.md","brand-assets.md","bridge.md","codebase-overview.md","codegraph-custom-tool.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","git-daemon.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-package-split-plan.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","notifications-sdk.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","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","skc-plugins.md","skc-session-clawhip-routing.md","standalone-mcp.md","telegram-onboarding.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/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","ui-design-visual-qa.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.",
 	"FORK_MAINTENANCE.md": "# Fork maintenance — keeping Sayknow-CLI synced with upstream\n\nSayknow-CLI is a **rebranded fork** of upstream `gajae-code`. We track upstream\nreleases without re-doing the rename by hand each time: the fork is a\n**reproducible function of `{upstream tag, our fork layer}`**.\n\n```\nfork tree  =  gen-tree(clean upstream tag)\n           =  codemod  +  fork-identity  +  overlay  +  patches\n```\n\nVerified: `gen-tree(v0.5.4)` byte-reproduces the `sayknow-fork` branch (excluding\nregenerated lockfiles + `*.generated.ts`).\n\n## Branch / remote topology\n\n| ref | meaning |\n| --- | --- |\n| `upstream` (remote) | `github.com/Yeachan-Heo/gajae-code` — read-only source |\n| `origin` (remote) | `github.com/jaybeyond/Sayknow_CLI` — our fork |\n| `main` (local) / `origin/main` | our shippable fork (local branch `sayknow-fork` → `origin/main`) |\n| `origin/upstream-mirror` | pristine upstream mirror (tag `upstream/v0.5.4`) |\n| tag `sayknow-v0.1.0` | fork release; tag `upstream/v0.5.4` | the upstream base it was generated from |\n\nBacked up: `git push origin sayknow-fork:main` (done). Local branch `sayknow-fork`\ntracks `origin/main`.\n\n## The four layers\n\n1. **codemod** — `scripts/apply-rebrand.ts`: deterministic brand rename\n   (`gajae/gjc → sayknow/skc`, paths, `@sayknow-cli` scope) + identity\n   special-cases (`can1357`/`Yeachan-Heo → jaybeyond`, discord → placeholder).\n   Skips `bun.lock`/`Cargo.lock` (integrity hashes). Reproduces ~1885 files with\n   **zero residual tokens**.\n2. **fork-identity** — `scripts/apply-fork-identity.ts` + `rebrand/identity.json`:\n   stamps the fork **version** (`0.1.0`) onto workspace `package.json` + root\n   catalog + `Cargo.toml`, as minimal format-preserving edits. **Bump the version\n   here**, never with a global replace (that would corrupt CHANGELOG/lockfiles).\n3. **overlay** — `rebrand/overlay/**`: whole files we own outright (i18n module,\n   `blue-octopus`/`red-octopus` themes, octopus assets, brand docs). Copied over\n   the codemod output. **No line-level merge → zero conflict.**\n4. **patches** — `rebrand/patches/NN-*.patch`: the ~17 **in-place edits** to\n   upstream-owned files (welcome redesign, theme default, i18n wiring, tests).\n   Applied with `git apply --reject`. **This is the only conflict-prone layer.**\n\n`rebrand/manifest.json` declares which files are `patch` / `regenerate` /\n`toolingOnly`; everything else that differs becomes overlay automatically.\n\n## Sync to a new upstream release\n\n```sh\nbash scripts/sync-upstream.sh v0.5.5          # fetch tag, regenerate, run gates G1–G4\n```\n\nThis produces a generated, gate-verified tree in a temp worktree (it does **not**\nauto-commit). Then **adopt** it:\n\n```sh\n# review the generated tree printed by the sync command, then:\nrsync -a --delete --exclude .git <generated-wt>/ .\nbun install                  # refresh lockfiles\ngit add -A && git commit -m \"sync: upstream v0.5.5\"\ngit tag sayknow-v0.<n>.0     # bump rebrand/identity.json first if releasing\n```\n\n### When a patch conflicts (upstream changed a patched file)\n\n`git apply --reject` leaves `*.rej` files in the generated worktree. For each:\n\n1. Open the `.rej` and the target file, apply the change by hand.\n2. Re-extract so the patch matches the new upstream base:\n   ```sh\n   # after upstream is mirrored + codemod+finalizer applied to <base>:\n   bun scripts/extract-fork-layer.ts --base <base> --fork <fixed-tree> --apply\n   ```\n3. Commit the refreshed `rebrand/patches/`.\n\n**Lever:** the fewer in-place edits, the fewer future conflicts. Prefer expressing\nnew fork features as *new files* (overlay) or additive hooks rather than edits to\nupstream files. Today only ~17 files are patches; keep it small.\n\n## Gates (run by `sync`, or manually)\n\n| gate | check |\n| --- | --- |\n| **G1** | no residual `gajae/gjc/red-claw/...` tokens in the generated tree |\n| **G2** | codemod idempotence — a *second* `apply-rebrand` changes **0 files** (diff-based; the printed hit-count is unreliable, do not gate on it) |\n| **G3** | `bun --cwd=packages/coding-agent run check:types` |\n| **G4** | `bun test` brand/i18n/welcome suites |\n\n## Publishing to npm\n\n`scripts/publish-npm.ts` publishes the 9 workspace packages in dependency order\nusing **`bun publish`** (not `npm publish`): bun resolves `catalog:`/`workspace:`\ndeps to concrete versions at pack time, so the packages actually install. Plain\n`npm publish` leaves `catalog:` in the tarball and breaks `bun install -g sayknow-cli`.\n\nOne-time prerequisites (need your npm account — the script can't do these):\n\n1. Create the **`@sayknow-cli`** org/scope on npmjs.com (Settings → Add Organization\n   → free unlimited public). All 9 packages are `@sayknow-cli/*`.\n2. `bunx npm login`\n\nThen:\n\n```sh\nbun run build:native                       # build the platform .node first\nbun scripts/publish-npm.ts --dry-run       # preview tarballs (no login needed)\nbun scripts/publish-npm.ts                 # publish for real\n```\n\nAfter publishing, `bun install -g sayknow-cli` works.\n\n> **Native binary is platform-specific.** `@sayknow-cli/natives` bundles a prebuilt\n> `.node` for the machine you publish from (e.g. `darwin-arm64`). A publish from an\n> Apple-Silicon Mac works for Apple-Silicon Mac users; **Linux / Windows / Intel-Mac\n> users get a \"failed to load native addon\" error.** Full cross-platform support\n> needs each platform's `.node` built in CI (`scripts/ci-release-build-binaries.ts`)\n> and shipped together — a follow-up, not a single-machine publish.\n\n## Regenerating the fork from scratch (audit)\n\n```sh\ngit worktree add --detach /tmp/u v0.6.0\nbun scripts/gen-tree.ts /tmp/u --build\ndiff -rq /tmp/u . -x .git -x node_modules -x bun.lock -x Cargo.lock -x '*.generated.ts'\n# → empty means the fork is fully reproducible from upstream + the fork layer\n```\n",
 	"REBRANDING_PLAN_260525.md": "# SKC Rebranding Plan — 2026-05-26\n\n## Status\n\nApproved plan for the sayknow-cli/SKC rebrand and visible UI redesign. This document records the implementation contract to track in GitHub and preserve in-repo.\nGitHub tracking issue: https://github.com/jaybeyond/Sayknow_CLI/issues/3\n\n## Decision\n\nRedesign the visible SKC terminal, export, and documentation surfaces around a coherent red-octopus sayknow-cli identity while preserving clegacyatibility boundaries.\n\nThe default-visible product should read as **sayknow-cli / SKC**, not legacy upstream branding or a generic inherited terminal skin. Red-claw becomes the default dark visual direction for users without an explicit override. Session exports and README screenshots should show the same brand direction, while exported transcript content remains neutral and readable.\n\n## Principles\n\n1. **SKC-first visible identity** — Default-visible UI should present sayknow-cli/red-octopus as the current product identity.\n2. **Clegacyatibility preservation** — Keep `skc`, `skc-stats`, `skc-swarm`, `@sayknow-cli/*`, legacy runtime roots/env aliases, and explicit attribution/history.\n3. **Semantic color integrity** — Brand red/coral/shell colors must stay distinct from error, warning, and diff-removal semantics.\n4. **Readable fallbacks** — Truecolor, 256-color, Unicode, Nerd Font, ASCII, narrow terminal, and imperfect-font modes must remain usable.\n5. **Audit-friendly exports** — HTML exports and docs use SKC header/accent/metadata branding without making transcript content decorative or hard to review.\n6. **Visible workflow minimization** — Default repo-shipped visible skills/workflows remain limited to `deep-interview`, `ralplan`, `team`, and `ultragoal`.\n\n## Scope\n\n### In scope\n\n- Default dark theme and bundled red-octopus palette.\n- Visible TUI surfaces: welcome, status line, footer/keybinding hints, message frames, assistant/user/custom/system messages, tool execution cards, ask/approval cards, selectors/settings, todo/plan surfaces, transcript chrome, diff/tool output styling.\n- Status-line identity cutover away from default-visible legacy/Pi/powerline styling.\n- Session HTML export header/accent/metadata branding while preserving transcript readability.\n- README screenshots/alt text and docs pages that present current SKC UI/export identity.\n- Static scans and tests for current-product brand leaks, clegacyatibility names, theme defaults, fallback readability, and export branding.\n\n### Out of scope\n\n- Renaming `skc`, `skc-stats`, `skc-swarm`, or `@sayknow-cli/*` package surfaces.\n- Removing legacy runtime roots, env aliases, clegacyatibility internals, migration notes, generated/vendor content, or attribution/history solely because they mention legacy/Pi.\n- Copying OpenAI code provider, SST/opencode, Anthropic Code, or legacy upstream visuals verbatim.\n- Making exports decorative enough to reduce audit readability.\n- Replacing the TUI framework as part of the brand redesign.\n\n## Implementation Plan\n\n### Phase 1 — Inventory and allowlist\n\n- Search active visible UI/docs/export surfaces for old-brand and inherited UI identity markers: legacy upstream markers, `skc`, `pi`, `powerline`, and generic export labels.\n- Classify hits as current product identity, explicit user opt-in setting labels, clegacyatibility internals, attribution/history/migration notes, or generated/vendor content.\n- Build or update verification gates so current-product visible leaks fail, but clegacyatibility and attribution do not.\n\n### Phase 2 — Theme defaults and palette semantics\n\n- Make red-octopus the default dark visual direction for users without explicit theme overrides.\n- Separate brand tokens (`brandRed`, `claw`, `coral`, `shell`) from semantic tokens (`dangerRed`, `warningAmber`, `diffRemovalRed`).\n- Ensure accents, borders, markdown, status-line identity, and export header variables use brand tokens while errors, warnings, and removals use semantic tokens.\n- Add focused tests for default theme resolution and token separation.\n\n### Phase 3 — Status-line identity cutover\n\n- Remove Pi from bundled default-visible status presets or replace it with clegacyact SKC/claw identity.\n- Preserve legacy segment/symbol clegacyatibility only as explicit opt-in or internal alias behavior.\n- Change default separators away from powerline-like styling; keep powerline variants available only as explicit user choices.\n- Verify status-line overflow, narrow-width, and ASCII/minimal-symbol behavior.\n\n### Phase 4 — Coherent TUI clegacyonent pass\n\nUse existing theme tokens rather than a new UI framework abstraction.\n\n- Apply shell/ink backgrounds, coral/claw accents, clegacyact borders, and lower-noise hierarchy across visible clegacyonents.\n- Refresh welcome, status line, footer hints, message frames, tool cards, ask/approval cards, selectors/settings, todo/plan surfaces, and transcript chrome.\n- Keep high-frequency tool cards inspectable: tool name, path/args, status, diff preview, truncation/expand hints, and error states remain clearer than decoration.\n- Confirm Unicode/Nerd/ASCII fallbacks for new visible symbols.\n\n### Phase 5 — Export and docs alignment\n\n- Update HTML export title/header/metadata to present SKC session export branding.\n- Keep message bodies, code blocks, tool output, system prlegacyts, and transcript content neutral and high contrast.\n- Regenerate derived export templates if required by the repository workflow.\n- Update README screenshots/alt text and docs references so the demonstrated TUI/export direction matches the implemented default.\n\n### Phase 6 — Verification and review\n\n- Run focused theme/status/export/static-scan tests first.\n- Run package-local checks after focused tests pass.\n- Run cleanup/refactor review on changed files.\n- Rerun verification after cleanup.\n- Run final code review and resolve blockers before considering the implementation clegacylete.\n\n## Acceptance Criteria\n\n- [ ] Default dark theme resolves to red-octopus/SKC for users without explicit theme override.\n- [ ] Brand/accent tokens are distinct from error, warning, and diff-removal tokens.\n- [ ] Default-visible status-line identity no longer leads with legacy/Pi-style branding.\n- [ ] Default-visible status separators no longer use powerline-style styling unless explicitly opted in.\n- [ ] Visible TUI clegacyonents share one coherent SKC language across welcome, status line, footer hints, message frames, tool execution cards, ask/approval cards, selectors/settings, and todo/plan surfaces.\n- [ ] Static scans of active UI/docs/export surfaces do not present legacy/Pi as current product identity; clegacyatibility internals, attribution/history, generated/vendor content, and migration notes remain allowlisted.\n- [ ] Full session HTML export includes SKC header/accent/metadata branding while preserving neutral readable transcript content.\n- [ ] README screenshots and alt text show the same SKC/red-octopus brand direction as the TUI/export surfaces.\n- [ ] Redesign remains readable under fallback terminal modes, including ASCII/minimal-symbol operation.\n- [ ] Focused verification covers default theme, visible brand allowlist, export branding, and preserved clegacyatibility names.\n\n## Planned Evidence\n\nFocused tests/probes after implementation:\n\n```bash\nbun test packages/coding-agent/test/skc-ui-redesign.test.ts\nbun test packages/coding-agent/test/theme-auto-detection.test.ts packages/coding-agent/test/status-line-overflow.test.ts packages/coding-agent/test/status-line-path.test.ts\nbun scripts/verify-skc-ui-redesign.ts\nbun --cwd=packages/coding-agent run check\n```\n\nManual/render probes:\n\n1. Launch with no explicit theme config and capture welcome/status/footer/tool-card flow.\n2. Launch with explicit non-red theme config and confirm it is not overwritten.\n3. Render status line at normal and narrow widths for default, clegacyact, full, Nerd, ASCII, and preserved custom settings.\n4. Render representative tool executions: pending, success, error, diff added/removed, spilled/truncated output, and image fallback.\n5. Render selectors/settings and ask/approval cards under red-octopus and ASCII/minimal-symbol mode.\n6. Generate a full session HTML export and inspect header/title/metadata/accent variables plus transcript readability.\n7. Inspect README screenshots/alt text and clegacyare them against the generated full-session export direction.\n\n## Risks and Mitigations\n\n- **Brand red becomes error/removal red** — Add token-level tests and rendered probes for brand, error, warning, and diff states.\n- **User-selected themes/status settings are overwritten** — Change defaults and bundled presets only; test explicit non-red theme/custom status preservation.\n- **Visible legacy/Pi removal breaks legacy configs** — Keep clegacyatibility aliases internally or opt-in, while removing current-product default visibility.\n- **Visual pass becomes subjective churn** — Centralize design in existing theme tokens and focused snapshots/probes; avoid framework replacement.\n- **Exports become too decorative for audits** — Brand only header/accent/metadata; keep transcript/code/tool content neutral and high contrast.\n- **Terminal fallback regressions** — Verify ASCII/minimal-symbol and narrow-width render paths.\n\n## Approval State\n\nThis plan is approved for tracking. Implementation still requires normal code review and verification before clegacyletion.\n",
 	"ai-schema-normalize.md": "# AI tool-schema normalization\n\n`@sayknow-cli/ai` exposes one unified schema normalizer that providers consume\nbefore tools are sent on the wire. All walkers live in\n`packages/ai/src/utils/schema/normalize.ts`; the operational contract is\n`packages/ai/src/utils/schema/CONSTRAINTS.md`.\n\nThere is no separate `strict-mode.ts` module any more — OpenAI strict-mode\nsanitization, OpenAI Responses `oneOf` rewriting, Google/Vertex/Gemini-CLI\nsanitization, Cloud Code Assist Anthropic sanitization, and MCP sanitization all\nshare the same option-driven walk.\n\n## Entry points\n\nAll exports live under `@sayknow-cli/ai/utils/schema`:\n\n- `normalizeSchema(value, options)` — generic option-driven walker.\n- `normalizeSchemaForGoogle(value)` — Gemini / Vertex / Gemini CLI.\n- `normalizeSchemaForCCA(value)` — Cloud Code Assist Anthropic (Antigravity + GCA).\n- `normalizeSchemaForMCP(value)` — MCP inputSchemas before they enter the\n  custom-tool registry. `tool-bridge.ts` runs every MCP `inputSchema` through\n  this dispatcher.\n- `normalizeSchemaForOpenAIResponses(schema)` (alias\n  `sanitizeSchemaForOpenAIResponses`) — rewrites `oneOf` → `anyOf` for the\n  Responses family.\n- `sanitizeSchemaForStrictMode(schema)` and\n  `enforceStrictSchema(schema)` / `tryEnforceStrictSchema(schema)` — the\n  OpenAI strict-mode pipeline (sanitize → enforce). All three are exported\n  from `normalize.ts`.\n- `adaptSchemaForStrict(schema, strict)` from `./adapt` — thin composer that\n  wraps `tryEnforceStrictSchema` for provider call sites and consults\n  `SKC_NO_STRICT` (env `SKC_NO_STRICT`) for the global bypass.\n\nRemoved in the unified-flow refactor:\n\n- `strict-mode.ts` (merged into `normalize.ts`).\n- `sanitize-google.ts` and `normalize-cca.ts` (replaced by\n  `normalizeSchemaFor*` dispatchers).\n- `StringEnum` helper — use `z.enum([...])` directly; Zod's emitted JSON\n  Schema is already wire-compatible with Google and other providers.\n- `sanitizeSchemaFor{Google,CCA,MCP}` / `prepareSchemaForCCA` — renamed to\n  `normalizeSchemaFor{Google,CCA,MCP}`.\n\n## Dispatcher mapping\n\n| Provider transport(s)                                                | Dispatcher                                   |\n| -------------------------------------------------------------------- | -------------------------------------------- |\n| `openai-completions`, `openai-responses`, `openai-code-responses`   | `adaptSchemaForStrict` (sanitize + enforce)  |\n| `openai-responses` family (`oneOf` → `anyOf` only)                   | `normalizeSchemaForOpenAIResponses`          |\n| `google-generative-ai`, `google-vertex`, Gemini CLI                  | `normalizeSchemaForGoogle`                   |\n| Cloud Code Assist Anthropic (Antigravity + GCA, `anthropic-model-*` model ids)   | `normalizeSchemaForCCA`                      |\n| MCP `inputSchema` ingestion                                          | `normalizeSchemaForMCP`                      |\n| `anthropic-messages` (native, not CCA)                               | per-provider whitelist in `anthropic.ts`     |\n\nGemini CLI / Antigravity CCA MUST run the full `normalizeSchemaForCCA`\npipeline (not just the first keyword-stripping pass) to keep parity with the\nshared Google Anthropic path.\n\n## Walk semantics\n\n`normalizeSchema` first upgrades the input to JSON Schema 2020-12, then\nwalks the tree with the option set pinned by the dispatcher. Each node:\n\n1. Inlines `$ref` (see \"Edge cases\" below).\n2. Renames `snake_case` combinator/property keys to camelCase\n   (`any_of` → `anyOf`, etc.; collisions follow python-genai\n   `pop(from)`/`set(to)` semantics — snake_case wins).\n3. Applies the `handle_null_fields` collapse for nullable unions before\n   recursing into children.\n4. Strips keys the target provider does not support, optionally lifting\n   human-meaningful keys (`pattern`, `format`, min/max, `default`,\n   `examples`, ...) into the sibling `description` via the spill formatter\n   (`spill.ts`). Structural/meta keys (`$ref`, `$defs`,\n   `additionalProperties`) are not spilled.\n5. Normalizes type unions (`type: [\"T\", \"null\"]` → `type: \"T\"` + nullable\n   marker on Google, plain `type: \"T\"` on CCA).\n6. Collapses object-only / same-type combiners, optionally lossy-collapses\n   mixed-type combiners (CCA only), and runs the residual-combiner fixpoint.\n7. Validates against AJV 2020 when `validateAndFallback` is set (CCA path)\n   and emits the per-tool fallback `{ \"type\": \"object\", \"properties\": {} }`\n   on residual incompatibility — `type` array, `type: \"null\"`, `nullable`\n   key, or any remaining `anyOf`/`oneOf`/`allOf`.\n\n## OpenAI strict-mode pipeline\n\n`adaptSchemaForStrict(schema, strict)` runs `tryEnforceStrictSchema`,\nwhich composes:\n\n1. **Sanitize** (`sanitizeSchemaForStrictMode`): strips non-structural\n   keywords (`format`, `pattern`, min/max, `examples`, `default`,\n   `if`/`then`/`else`, `not`, `unevaluated*`, `patternProperties`,\n   `dependent*`, `content*`, `min/maxProperties`, `$dynamicRef`, etc.). The\n   `default` value is inlined into the sibling `description` as\n   ` (default: X)` before being dropped, unless `description` already\n   contains `(default:` or no `description` exists.\n2. **Enforce** (`enforceStrictSchema`): every object node gets\n   `additionalProperties: false`, every property goes into `required`, and\n   optional properties become nullable unions\n   (`anyOf: [<original>, { \"type\": \"null\" }]`). Tuple `prefixItems` are\n   strictified recursively.\n\nThe two passes share node-level caches and the same epoch-based cycle\nguard, so a single walk on the wire path normalizes refs, allOf, and\nnullable wrapping consistently. `tryEnforceStrictSchema` is fail-open:\nif anything throws, it returns `{ strict: false, schema: original }` so\ncallers MUST emit `strict: true` only when enforcement actually succeeded.\n\n### Edge cases the strict-mode normalizer handles\n\n- **Local `$ref` inlining.** OpenAI strict mode rejects\n  `{ \"$ref\": \"...\", \"description\": \"...\" }` with sibling keys. The\n  sanitizer pre-resolves local `#/...` refs against the root and merges\n  with **sibling keys winning** over the resolved def — same precedence\n  as `openai-python`'s `_ensure_strict_json_schema`. Recursive refs are\n  guarded by the per-walk epoch.\n- **Single-item `allOf`.** A `{ \"allOf\": [X], ...siblings }` collapses to\n  `{ ...X, ...siblings }` with the inlined entry's keys winning over the\n  original siblings (matches `openai-python`'s `_pydantic.py:79-83`). Multi-\n  item `allOf` is left intact for the downstream validator to reject if\n  needed.\n- **Type-array branches and nullable unions.** When a node has\n  `type: [\"T\", \"U\"]`, the sanitizer emits one variant schema per type,\n  pruning type-specific keywords (e.g. `properties`/`required` only stay on\n  the `object` variant, `items` only on the `array` variant). The shared\n  `description` is **hoisted onto the `anyOf` wrapper** instead of being\n  duplicated on every branch — so a strict nullable union becomes\n  `{ anyOf: [T, { type: \"null\" }], description: \"...\" }`, not\n  `anyOf: [{ ..., description }, { ..., description }]`.\n- **Enum/const without a `type`.** Both sanitize and enforce paths call\n  `inferStrictPrimitiveTypeFromEnumOrConst` to infer the primitive `type`\n  from `enum` / `const` values. Mixed-primitive enums (`[1, \"two\", null]`),\n  enums containing objects/arrays, and non-primitive `const` values\n  (`{a:1}`, `[1,2,3]`) cannot be described by a single `type` keyword and\n  trigger the strict-mode fail-open path — emitting a typeless schema\n  would just be rejected on the wire by OpenAI.\n\n## Performance: static fingerprint cache\n\n`resolveProviderModels` in `packages/ai/src/model-manager.ts` and\n`readModelCache`/`writeModelCache` in `model-cache.ts` cooperate via a\nschema-v3 `static_fingerprint` column on the `model_cache` SQLite table.\n\n- `fingerprintStatic(staticModels)` hashes the static catalog slice\n  (`Bun.hash(JSON.stringify(models))` in base36) and memoizes the result\n  in a per-process `WeakMap` keyed by the array reference. Multiple\n  cold-start arms calling `resolveProviderModels` with the same\n  `staticModels` array pay the JSON+hash cost once.\n- On cache read, if the network fetch is being skipped, the cached row is\n  fresh + authoritative, and the cached `static_fingerprint` matches the\n  current one, `resolveProviderModels` returns the cached models verbatim\n  — the cache already incorporates the same static state, so re-running\n  `mergeDynamicModels(static, cache)` would just rebuild the same objects.\n- `mergeModelSources` and `mergeDynamicModels` short-circuit on\n  empty-source inputs (the common shape after `(static, [])` or for\n  providers without a static catalog), avoiding Map churn entirely.\n\nCache rows written before schema v3 are dropped by the cache-version\ncheck; the column defaults to `''` for any row that survives a version\nupgrade so the fingerprint-equality check naturally fails closed and the\nfull merge re-runs.\n\n## Related\n\n- `docs/models.md` — registry, equivalence, compat flags\n  (`supportsStrictMode`, `toolStrictMode`, `disableStrictTools`).\n- `docs/provider-streaming-internals.md` — how the normalized schemas are\n  used downstream during the provider stream loop.\n- `packages/ai/src/utils/schema/CONSTRAINTS.md` — operational contract for\n  every normalization rule.\n",
+	"analyze-me-with-skc.md": "# Analyze Me with SKC\n\nUse this prompt for meetup icebreakers where each participant asks SKC to introduce them from their own local SKC usage history.\n\nThe prompt is designed to be repeatable: it tells SKC what local artifacts to inspect, what patterns to extract, how to avoid leaking secrets, and how to turn the analysis into a short spoken self-introduction.\n\n## Full prompt\n\n```text\n~/.skc 에 있는 내 가재코드 사용내역을 바탕으로, 가재코드 밋업 아이스브레이킹용 “가재코드가 보는 나” 자기소개 글을 작성해줘.\n\n목표:\n- 내 실제 가재코드 사용패턴을 분석해서, 내가 어떤 개발자/빌더/운영자인지 소개하는 글을 써줘.\n- 단순 통계 나열이 아니라, 사용 습관과 관심사에서 드러나는 성향을 해석해줘.\n- 밋업에서 2~4분 정도 읽을 수 있는 분량으로 작성해줘.\n- 너무 딱딱한 리포트 말고, 사람 소개글처럼 재미있고 선명하게 써줘.\n- 과장하거나 없는 사실을 만들지 말고, 실제 ~/.skc 기록에서 관찰된 패턴만 근거로 삼아줘.\n\n분석 지시:\n1. ~/.skc 디렉터리 구조를 먼저 확인해줘.\n2. 가능한 경우 아래의 안전한 메타데이터 중심 자료만 분석해줘:\n   - ~/.skc/agent/history.db 의 집계값\n   - ~/.skc/agent/sessions/**/*.jsonl 의 세션 메타데이터(세션 제목, timestamp, cwd, 메시지 수, tool-call 수, 파일 크기, subagent/task 이름)\n   - ~/.skc 내부의 추가 파일은 사용패턴 집계에 꼭 필요하고 민감정보가 없다고 판단되는 경우에만 읽어줘.\n   - 기본적으로 ~/.skc/logs/*, auth/config/credential 파일, env dump, raw tool-result body, raw prompt body, secret-like 값은 읽지 마.\n3. history.db에서는 최소한 다음을 봐줘:\n   - 전체 프롬프트 수\n   - 기간 범위\n   - 작업 디렉터리 / 레포지토리 분포\n   - 자주 등장하는 주제어\n   - 짧은 명령과 긴 프롬프트의 비율\n   - /skill:ultragoal, /skill:ralplan, /skill:deep-interview, /skill:team 사용 빈도\n   - continue, fix, review, merge, PR, CI, test, verify, implement, delegate 같은 실행/검증 관련 단어 빈도\n4. sessions jsonl에서는 가능하면 다음을 봐줘:\n   - 메인 세션 수\n   - 서브에이전트 / task 세션 수\n   - 짧은 세션과 긴 세션의 분포\n   - 세션 title 또는 worktree 이름에서 보이는 관심사\n   - 장기 실행, 병렬 위임, 검증, 리뷰, 릴리스 운영 흔적\n5. 레포지토리와 주제 다양성을 꼭 반영해줘:\n   - 어떤 레포지토리/워크트리에서 많이 일했는지\n   - SKC core, 개인 프로젝트, 연구/quant, infra, UI, automation, image/media 등 주제 범위가 보이면 묶어서 설명해줘.\n6. 민감정보는 절대 노출하지 마:\n   - API key, 토큰, credential, 개인 연락처, 로컬 secret, private URL, 인증정보는 출력하지 마.\n   - 프롬프트 예시는 필요할 때만 짧게 paraphrase해서 써줘.\n   - 파일 경로나 레포 이름은 자기소개에 필요한 수준으로만 언급해줘.\n   - 분석 중에도 민감정보를 모델 컨텍스트에 올리지 않도록 metadata-first / aggregate-only 방식으로 처리해줘.\n\n출력 형식:\n\n먼저 아주 짧게 “분석한 근거”를 3~6개 bullet로 요약해줘.\n예:\n- 분석 기간:\n- 프롬프트 수:\n- 주요 작업 공간:\n- 세션 패턴:\n- 자주 보인 workflow/skill:\n- 주요 관심사:\n\n그 다음 아래 제목으로 자기소개 글을 써줘:\n\n# 가재코드가 보는 나\n\n글 스타일:\n- 한국어로 작성.\n- 살짝 위트 있게.\n- “당신은 …” 또는 “나는 …” 중 더 자연스러운 쪽을 선택해도 됨.\n- 밋업에서 읽기 좋게 문단을 나눠줘.\n- 너무 아부하지 말고, 사용패턴에서 드러나는 장점과 특이한 습관을 솔직하게 말해줘.\n- 마지막에는 한 문장으로 요약해줘:\n  “한 문장으로 말하면, 나는 ___ 하는 사람이다.”\n\n추가로 마지막에 선택사항으로 아래 3개를 붙여줘:\n\n## 10초 버전\n한두 문장짜리 초단기 자기소개.\n\n## 한 줄 별명\n사용패턴 기반 별명 3개.\n\n## 밋업용 오프닝 멘트\n처음 인사할 때 바로 읽을 수 있는 20~30초짜리 멘트.\n\n주의:\n- 분석 없이 일반론으로 쓰지 마.\n- 실제 ~/.skc 기록을 읽고 나서 작성해.\n- 숫자를 말할 때는 실제로 확인한 숫자만 써.\n- 확인하지 못한 항목은 “확인 불가”라고 하지 말고, 그 항목을 빼고 자연스럽게 작성해.\n```\n\n## Short meetup prompt\n\nUse this when participants need a shorter copy/paste prompt.\n\n```text\n~/.skc 사용내역을 분석해서 밋업 아이스브레이킹용 “가재코드가 보는 나” 자기소개 글을 써줘.\n\n반드시 실제 ~/.skc 기록을 읽되, 안전한 메타데이터와 집계값 중심으로 근거 기반 작성해:\n- history.db의 프롬프트 수, 기간, cwd/레포 분포, 자주 쓰는 단어, skill 사용량\n- sessions jsonl의 세션 수, 세션 길이 다양성, subagent/task 사용 흔적\n- 레포지토리/주제 다양성\n- 짧은 명령 vs 긴 지시문 패턴\n- 실행/검증/리뷰/PR/CI/릴리스/위임 습관\n\n민감정보는 읽지도 출력하지도 마. API key, 토큰, private credential, 개인 secret, 긴 원문 프롬프트, raw tool-result body, ~/.skc/logs/*, auth/config/env dump는 기본적으로 건너뛰고, 필요한 경우에도 안전한 집계값과 짧은 paraphrase만 써.\n\n출력:\n1. 분석 근거 bullet 3~6개\n2. 제목: “가재코드가 보는 나”\n3. 밋업에서 2~4분 읽을 수 있는 한국어 자기소개 글\n4. 마지막에:\n   - 10초 버전\n   - 사용패턴 기반 별명 3개\n   - 20~30초 오프닝 멘트\n\n스타일:\n- 재미있고 선명하게\n- 과장 없이\n- 통계 나열보다 “이 사람이 어떤 식으로 일하는 사람인지” 해석 중심\n- 마지막 문장은 “한 문장으로 말하면, 나는 ___ 하는 사람이다.”\n```\n\n## Optional: SayknowTI prompt\n\nA meetup host can also turn the same analysis into a playful, MBTI-like “SayknowTI” result. This is only an icebreaker taxonomy, not a psychological assessment.\n\n```text\n~/.skc 사용내역을 안전한 메타데이터와 집계값 중심으로 분석해서, 밋업 아이스브레이킹용 “가재TI”를 만들어줘.\n\n목표:\n- MBTI처럼 4글자 코드와 타입명을 만들되, 실제 성격검사가 아니라 가재코드 사용패턴 기반의 재미있는 작업 스타일 분류로 작성해.\n- 실제 ~/.skc 기록에서 확인한 사용패턴만 근거로 삼아줘.\n- 민감정보는 읽지도 출력하지도 마. API key, 토큰, private credential, 개인 secret, 긴 원문 프롬프트, raw tool-result body, ~/.skc/logs/*, auth/config/env dump는 기본적으로 건너뛰고, 안전한 집계값과 짧은 paraphrase만 써.\n\n먼저 아래 4개 축을 기준으로 타입을 판정해줘. 각 축은 한쪽을 고르되, 애매하면 근거와 함께 중간 성향이라고 설명해.\n\n1. E / P — Execute vs Plan\n   - E: fix, implement, merge, ship, PR, CI, release처럼 실행/운영 명령이 강함.\n   - P: deep-interview, ralplan, spec, architecture, review처럼 계획/정의/합의 흐름이 강함.\n\n2. S / M — Sprint vs Marathon\n   - S: 짧은 명령, 빠른 follow-up, `continue`, 작은 세션이 많음.\n   - M: 장기 세션, durable goal, 긴 프롬프트, 며칠짜리 작업 흐름이 많음.\n\n3. C / D — Craft vs Delegate\n   - C: 직접 구현/수정/탐색 중심.\n   - D: subagent, executor, architect, critic, team, parallel delegation 사용이 강함.\n\n4. X / O — Explore vs Operate\n   - X: 새로운 모델/provider/tool/research/실험 주제가 많음.\n   - O: PR, CI, release, changelog, version, production 운영/마감 흐름이 많음.\n\n분석할 최소 근거:\n- history.db의 프롬프트 수, 기간, cwd/레포 분포, 자주 쓰는 단어, skill 사용량\n- sessions jsonl의 세션 수, 세션 길이 다양성, subagent/task 흔적\n- 레포지토리/주제 다양성\n- 짧은 명령 vs 긴 지시문 패턴\n- 실행/검증/리뷰/PR/CI/릴리스/위임 습관\n\n출력 형식:\n\n# 나의 가재TI: <4글자 코드> — <타입명>\n\n## 판정 근거\n- E/P: <선택> — <실제 집계 또는 관찰 근거>\n- S/M: <선택> — <실제 집계 또는 관찰 근거>\n- C/D: <선택> — <실제 집계 또는 관찰 근거>\n- X/O: <선택> — <실제 집계 또는 관찰 근거>\n\n## 타입 설명\n밋업에서 1분 정도 읽을 수 있게, 이 사람이 가재코드를 어떻게 쓰는 사람인지 재미있게 설명해줘.\n\n## 강점\n3개 bullet.\n\n## 주의할 점\n놀리는 느낌은 살짝 있어도 되지만, 비하하지 말고 작업 습관상 조심할 점 2~3개.\n\n## 어울리는 밋업 별명\n3개.\n\n주의:\n- 이건 성격검사가 아니라 사용패턴 기반 밋업 놀이야.\n- 숫자는 실제로 확인한 값만 써.\n- 확인하지 못한 축은 억지로 단정하지 말고 “근거 부족” 또는 “혼합형”이라고 써.\n```\n",
 	"aside-integration.md": "# Aside sidecar evaluation\n\nThis note records the safe first-step boundary for evaluating [Aside](https://aside.com/) with Sayknow-CLI (`skc`). It is intentionally docs-only: SKC does not ship an Aside adapter, does not auto-discover Aside, and does not enable browser-control behavior by default.\n\n## Current public surface\n\nOfficial Aside docs currently describe Aside as a browser agent that can run tasks across websites, accounts, browsing history, files, saved credentials, and browser state. The developer surface includes:\n\n- `aside \"...\"` for starting a browser task from the terminal.\n- `aside --session <session-id> \"...\"` for continuing a task.\n- `aside mcp` for exposing Aside to another agent or coding tool as an MCP server.\n- `aside repl` for direct browser automation REPL tasks.\n\nThose are useful evaluation hooks, but they are not a narrow SKC-native search API. The documented Aside product surface is broader than search/context retrieval, including browser actions, login-adjacent flows, files, payments, messages, and internal websites. SKC therefore treats Aside as an external, user-owned sidecar until a separate design approves a smaller protocol contract.\n\n## Supported SKC boundary\n\nUse Aside with SKC only when the user explicitly configures it. The safe default scope is:\n\n- search, source-heavy research, summarization, and context retrieval;\n- read-only inspection prompts where possible;\n- explicit user-provided endpoint, command, and credentials;\n- no raw browser/session/private payloads in logs, PRs, issues, or support bundles.\n\nOut of scope by default:\n\n- browser actions and form submissions;\n- login flows, credential autofill, MFA, account recovery, and password-manager operations;\n- payments, purchases, subscriptions, billing changes, posts, messages, or destructive actions;\n- internal-tool workflows, customer/admin dashboards, or privileged production data;\n- file writes or local computer control through Aside;\n- automatic import of Aside browser history, cookies, task transcripts, screenshots, or local profile data into SKC.\n\nIf a task needs any out-of-scope behavior, stop and require a separate explicit design and approval path. Do not smuggle that behavior through a generic “search” tool name.\n\n## Option A: local Aside MCP command\n\nWhen the Aside CLI is installed and the operator intentionally wants SKC to see the Aside MCP tools, register the MCP server explicitly:\n\n```sh\nskc mcp add aside aside mcp --project\n```\n\nUse `--project` for repo-local evaluation. Omit it only when the operator wants the server available to all local SKC sessions.\n\nAfter registration, inspect the redacted definition:\n\n```sh\nskc mcp list --json\n```\n\nDo not paste task transcripts, browser screenshots, cookies, saved credential state, or private Aside profile paths into issues or PRs. If you need to share evidence, summarize the tool list and a benign query result.\n\nRecommended prompt boundary for evaluation:\n\n```text\nUse the Aside sidecar only for read-only search/context retrieval. Do not click, submit, sign in, autofill credentials, use payment or billing flows, post messages, write files, or operate internal tools. Return a short answer with source titles/URLs only.\n```\n\n## Option B: future HTTP/SSE MCP endpoint\n\nIf Aside or a wrapper later exposes a narrow search/context MCP endpoint, keep endpoint and credentials user-owned:\n\n```sh\nexport ASIDE_MCP_URL=\"https://aside.example.invalid/mcp\"\nexport ASIDE_API_KEY=\"...\"\nskc mcp add aside-search --type http --url \"$ASIDE_MCP_URL\" --header Authorization=\"Bearer $ASIDE_API_KEY\" --project\n```\n\n`skc mcp list` and `skc mcp remove` redact header/auth values, but operators are still responsible for not echoing secrets in shell history, CI logs, screenshots, or copied terminal output. Prefer environment indirection over literals whenever possible.\n\nA future Aside search endpoint should be accepted only if it is narrower than browser automation. Minimum shape:\n\n- one or more read-only search/context tools;\n- no browser click/type/navigation tool in the same registered server unless explicitly approved;\n- no direct access to cookies, saved credentials, raw screenshots, raw task transcripts, or browser profile paths;\n- bounded response sizes with source titles/URLs and short snippets by default;\n- clear auth failure vs endpoint/network failure errors without dumping request headers or private response bodies.\n\n## Benign smoke checklist\n\nUse this checklist instead of a live login/payment/internal-site scenario:\n\n1. Register the MCP server with `skc mcp add ... --project`.\n2. Run `skc mcp list --json` and confirm secrets are redacted.\n3. Start a SKC session in a disposable repo/worktree.\n4. Ask one public, non-personal query, for example: `Find the Aside public help page that describes MCP support and summarize the documented command names.`\n5. Confirm the response includes only public page titles/URLs or short snippets.\n6. Confirm no API key, Authorization header, cookie, browser profile path, screenshot, raw task transcript, or private session payload appears in terminal output, logs, issue comments, or PR text.\n7. Remove the evaluation server if it is no longer needed:\n\n```sh\nskc mcp remove aside --project\n# or\nskc mcp remove aside-search --project\n```\n\n## Troubleshooting\n\n| Symptom | Check |\n| --- | --- |\n| `aside` command not found | Install the Aside CLI from Aside developer settings, then use the concrete CLI path as the MCP `command` if needed. |\n| MCP server does not appear | Re-run `skc mcp list --json`; confirm whether the registration was user-scoped or project-scoped. |\n| Auth failure | Rotate or re-enter the Aside-side token/API key. Do not paste it into SKC prompts or issue comments. |\n| Endpoint/network failure | Check the URL, proxy, and TLS path outside SKC with a benign health check; do not dump request headers. |\n| Retrieval misses context | Narrow the query to public sources first. Do not add browser history, cookies, screenshots, or account pages unless a separate approved design covers that data flow. |\n| Tool list includes browser actions | Treat the server as browser automation, not search-only. Keep it disabled for default SKC workflows unless an operator explicitly approves that broader sidecar for the session. |\n\n## Decision\n\nDocs-only is the smallest safe outcome for issue #1097. Existing SKC MCP registration can connect to a user-provided Aside MCP server, and Aside already documents `aside mcp`; no SKC adapter glue is required. The future-safe boundary is to keep Aside external and opt-in, document read/search/context-only use, and require a separate design before SKC claims support for browser actions, login, payment, internal-tool, or private browser-session workflows.\n",
 	"auth-broker-gateway.md": "# Auth Broker and Auth Gateway\n\nThe auth broker and auth gateway are two cooperating HTTP services that move OAuth refresh tokens and provider access tokens off developer laptops and into a single broker host.\n\n- **`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",
@@ -23,11 +24,12 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"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.\nIt also exposes high-level `skc_delegate_plan` / `skc_delegate_execute` / `skc_delegate_team` tools so a host can delegate a whole SKC workflow (ralplan/ultragoal/team) in one call and consume the durable turn result. The canonical sayknow-cli plugin bundles under `plugins/` and `skc setup claude|codex|hermes` package this surface with fail-closed defaults (workdir-scoped roots, mutations off until opt-in). Claude Code is installable through its generated local marketplace; Codex artifacts are preview-only until a versioned Codex local marketplace smoke proves install and runtime activation.\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",
+	"git-daemon.md": "# Git daemon\n\nThe git daemon is the autonomous per-repo service that watches a repository and resolves referenced work items by opening reviewed pull requests.\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\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- `skc_delegate_plan`\n- `skc_delegate_execute`\n- `skc_delegate_team`\n\nThe `skc_delegate_*` tools are high-level, session-level delegation: each starts (or reuses) a session and sends one workflow-tagged turn that runs `/skill:ralplan`, `/skill:ultragoal`, or `/skill:team` to completion, returning a durable `turn_id`, status, and artifact references. They use the same `sessions` mutation class and fail-closed workdir gating as `skc_coordinator_start_session`, and emit a `delegation.started` event. Pass `cwd` and `task`; set `allow_mutation: true` only with startup mutation opt-in plus per-call consent. Prefer these over manual `start_session` + `send_prompt` when delegating a whole workflow.\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` | _(none)_ | Optional remap for a follow-up message; `Ctrl+Enter` is reserved for editor newline |\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\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` | `Ctrl+Enter` and `Ctrl+Shift+Enter` are also accepted by the editor when the terminal encodes them distinctly |\n\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` | _(none)_ | `Ctrl+Enter` remains newline unless the user explicitly remaps this action; while idle the chord still falls through to newline |\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",
+	"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.commandPalette.open\": \"Ctrl+P\",\n  \"app.model.cycleForward\": \"Alt+N\",\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+N`, `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.commandPalette.open` | `Ctrl+P` | Open the command palette |\n| `app.model.cycleForward` | `Alt+N` | Cycle role models forward |\n| `app.model.cycleBackward` | `Alt+Shift+N` | 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` | _(none)_ | Optional remap for a follow-up message; `Ctrl+Enter` is reserved for editor newline |\n| `app.message.queue` | `Alt+Enter` (`Alt+Q` on win32) | Explicitly queue a message for the next turn |\n| `app.message.dequeue` | `Alt+Up` | Dequeue a queued message back into the editor |\n\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\nOn native Windows terminals, SKC defaults `app.message.queue` to `Alt+Q` because Windows Terminal and PowerShell commonly reserve `Alt+Enter` for fullscreen before SKC can receive it. Users who prefer another chord can remap `app.message.queue` in `~/.skc/agent/keybindings.json`.\n\nIn the main SKC composer, plain `PageUp` / `PageDown` page the visible transcript viewport instead of browsing prompt history; use `Up` / `Down` or `Ctrl+R` for prompt history. Autocomplete and selector surfaces still use `PageUp` / `PageDown` for list paging while they have focus.\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` | `Ctrl+Enter` and `Ctrl+Shift+Enter` are also accepted by the editor when the terminal encodes them distinctly |\n\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.commandPalette.open` | `ctrl+p` | Open command palette from the editor |\n| `app.model.cycleForward` | `alt+n` | |\n| `app.model.cycleBackward` | `alt+shift+n` | |\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` | _(none)_ | `Ctrl+Enter` remains newline unless the user explicitly remaps this action; while idle the chord still falls through to newline |\n| `app.message.queue` | `alt+enter` (`alt+q` on win32) | platform-aware; avoids the Windows Terminal fullscreen shortcut |\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+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\nWhen multiple built-in primary servers support the same file, a default server can list lower-precedence servers in `supersedes`. For example, `csharp-ls` supersedes `omnisharp` only when both C# servers are installed and detected; if `csharp-ls` is unavailable, `omnisharp` remains the fallback.\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| `csharp-ls` | C# | `csharp-ls` |\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> 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",
@@ -38,12 +40,13 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"natives-binding-contract.md": "# Natives Binding Contract (JavaScript/TypeScript Side)\n\nThis document defines the JS/TS contract between `@sayknow-cli/natives` callers and the loaded N-API addon.\n\n> When a port is proposed to **optimize** a leftover algorithmic hot path (rather than add a new OS/process/native primitive), it must additionally clear the evidence and cost gates in [`native-ffi-optimization-policy.md`](./native-ffi-optimization-policy.md).\n\nCurrent package shape is direct-to-native: there is no `packages/natives/src/<module>` TypeScript wrapper layer. The public API is the generated `packages/natives/native/index.d.ts` declaration file, the CommonJS loader in `packages/natives/native/index.js`, and the Rust `#[napi]` exports in `crates/pi-natives/src`.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n- Rust modules under `crates/pi-natives/src/*.rs`\n\n## Contract model\n\nThe contract has three parts:\n\n1. **Generated runtime loader** (`native/index.js`)\n   - computes candidates and `require(...)`s the `.node` addon;\n   - exports the loaded addon object directly;\n   - appends enum objects generated by `scripts/gen-enums.ts`.\n2. **Generated TypeScript declarations** (`native/index.d.ts`)\n   - generated by napi-rs during `scripts/build-native.ts`;\n   - declares exported functions, classes, object interfaces, and native enums;\n   - is the package `types` entry.\n3. **Rust N-API exports** (`crates/pi-natives/src`)\n   - `#[napi]` functions/classes/objects/enums are the source of generated declarations and runtime symbols;\n   - snake_case Rust names become camelCase JavaScript names by napi-rs convention.\n\nThere is no current `NativeBindings` declaration-merging lifecycle and no `validateNative(...)` required-export list in the loader.\n\n## Public export surface organization\n\n`packages/natives/package.json` exposes the package root only:\n\n```json\n{\n  \"main\": \"./native/index.js\",\n  \"types\": \"./native/index.d.ts\",\n  \"exports\": {\n    \".\": {\n      \"types\": \"./native/index.d.ts\",\n      \"import\": \"./native/index.js\"\n    }\n  }\n}\n```\n\nConsumers in `packages/coding-agent` and `packages/tui` import directly from `@sayknow-cli/natives`.\n\n## JS API ↔ native export mapping (representative)\n\n| Category          | Public JS API                                                                                              | Rust source                                                 | Return style                  |\n| ----------------- | ---------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- | ----------------------------- |\n| Grep              | `grep(options, onMatch?)`                                                                                  | `grep.rs`                                                   | `Promise<GrepResult>`         |\n| Grep              | `search(content, options)`                                                                                 | `grep.rs`                                                   | `SearchResult`                |\n| Grep              | `hasMatch(content, pattern, ignoreCase?, multiline?)`                                                      | `grep.rs`                                                   | `boolean`                     |\n| Fuzzy path search | `fuzzyFind(options)`                                                                                       | `fd.rs`                                                     | `Promise<FuzzyFindResult>`    |\n| Glob              | `glob(options, onMatch?)`                                                                                  | `glob.rs`                                                   | `Promise<GlobResult>`         |\n| Glob cache        | `invalidateFsScanCache(path?)`                                                                             | `fs_cache.rs`                                               | `void`                        |\n| AST search/edit   | `astGrep(options)`, `astEdit(options)`                                                                     | `ast.rs`                                                    | `Promise<...>`                |\n| Shell             | `executeShell(options, onChunk?)`                                                                          | `shell.rs`                                                  | `Promise<ShellExecuteResult>` |\n| Shell             | `new Shell(options?)`, `shell.run(...)`, `shell.abort()`                                                   | `shell.rs`                                                  | class / promises              |\n| PTY               | `new PtySession()`, `start/write/resize/kill`                                                              | `pty.rs`                                                    | class / promises              |\n| Process           | `killTree(pid, signal)`, `listDescendants(pid)`                                                            | `ps.rs`                                                     | sync                          |\n| Keys              | `parseKey`, `matchesKey`, Kitty/legacy helpers                                                             | `keys.rs`                                                   | sync                          |\n| Text              | `wrapTextWithAnsi`, `truncateToWidth`, `sliceWithWidth`, `extractSegments`, `visibleWidth`                 | `text.rs`                                                   | sync                          |\n| Highlight         | `highlightCode`, `supportsLanguage`, `getSupportedLanguages`                                               | `highlight.rs`                                              | sync                          |\n| HTML              | `htmlToMarkdown(html, options?)`                                                                           | `html.rs`                                                   | `Promise<string>`             |\n| Image             | `PhotonImage`, `encodeSixel`                                                                               | `image.rs`                                                  | class / sync / promises       |\n| Clipboard         | `copyToClipboard`, `readImageFromClipboard`                                                                | `clipboard.rs`                                              | sync / promise                |\n| Tokens            | `countTokens(input, encoding?)`                                                                            | `tokens.rs`                                                 | sync                          |\n| System            | `detectMacOSAppearance`, `MacAppearanceObserver`, `MacOSPowerAssertion`, `getWorkProfile`, ProjFS helpers  | `appearance.rs`, `power.rs`, `prof.rs`, `projfs_overlay.rs` | mixed                         |\n\n## Sync vs async contract differences\n\nThe contract preserves Rust/N-API call style:\n\n- **Promise-returning exports** for worker-thread or async runtime work (`grep`, `glob`, `fuzzyFind`, `astGrep`, `astEdit`, `htmlToMarkdown`, shell/PTY runs, image parse/resize/encode, clipboard image read).\n- **Synchronous exports** for deterministic in-memory transforms/parsers or direct system calls (`search`, `hasMatch`, highlighting, text utilities, token counting, process queries, `copyToClipboard`, `encodeSixel`).\n- **Constructor exports** for stateful runtime objects (`Shell`, `PtySession`, `PhotonImage`, macOS observer/power handles).\n\nChanging sync ↔ async for an existing export is a breaking public API change because consumers call these exports directly.\n\n## Object and enum typing patterns\n\n### Object patterns\n\n`#[napi(object)]` Rust structs become TS interfaces, for example:\n\n- `GrepResult`, `SearchResult`, `GlobResult`, `FuzzyFindResult`\n- `ShellRunResult`, `ShellExecuteResult`, `PtyRunResult`, `MinimizerResult`\n- `AstFindResult`, `AstReplaceResult`\n- `System`/media payloads such as `ClipboardImage`, `WorkProfile`, `ParsedKittyResult`\n\nRuntime shape correctness is owned by napi-rs and the Rust implementation.\n\n### Enum patterns\n\nNative enums are represented in generated declarations and also appended to `module.exports` by `scripts/gen-enums.ts`, because the loader is hand-maintained CommonJS around the generated addon. Current enum objects include:\n\n- `AstMatchStrictness`\n- `Ellipsis`\n- `Encoding`\n- `FileType`\n- `GrepOutputMode`\n- `ImageFormat`\n- `KeyEventType`\n- `MacOSAppearance`\n- `SamplingFilter`\n\n## Error behavior and caveats\n\n- Addon load failure or unsupported platform throws during package import from `native/index.js`.\n- The loader does not verify the full export set after `require(...)`; stale or mismatched binaries surface as native load errors or missing members at use sites.\n- N-API conversion validates basic argument conversion, but TS optional fields do not guarantee semantic validity for untyped callers.\n- Numeric enum declarations do not prevent out-of-range numeric values from untyped callers unless the Rust function rejects them during conversion.\n- Callback exports use napi-rs `ThreadsafeFunction` shape: `(error: Error | null, value) => void`. Native code generally emits successful values; hard failures reject/throw through the owning call.\n\n## Maintainer checklist for binding changes\n\nWhen adding/changing an export, update all of:\n\n1. Rust `#[napi]` implementation in the owning `crates/pi-natives/src/<module>.rs`.\n2. `crates/pi-natives/src/lib.rs` if a new module is added.\n3. Any consumer imports/callsites in `packages/coding-agent` or `packages/tui`.\n4. Build output by running the natives build so `native/index.d.ts` and `native/index.js` stay in sync.\n5. `scripts/gen-enums.ts` if enum runtime export patching needs to change.\n\nDo not add a parallel TS wrapper convention unless the package design intentionally moves back to wrappers; current consumers depend on the direct generated API.\n",
 	"natives-build-release-debugging.md": "# Natives Build, Release, and Debugging Runbook\n\nThis runbook describes how `@sayknow-cli/natives` produces `.node` addons, generated declarations, and compiled-binary embedded payloads, and how to debug loader/build failures.\n\nIt follows the architecture terms from `docs/natives-architecture.md`:\n\n- **build-time artifact production** (`scripts/build-native.ts`)\n- **embedded addon manifest generation** (`scripts/embed-native.ts`)\n- **runtime addon loading** (`native/index.js`, `native/loader-state.js`)\n\n## Implementation files\n\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `packages/natives/native/index.js`\n- `packages/natives/native/loader-state.js`\n- `crates/pi-natives/Cargo.toml`\n\n## Build pipeline overview\n\n### 1) Build entrypoints\n\n`packages/natives/package.json` scripts:\n\n- `bun scripts/build-native.ts` (`build`) → N-API build, addon install, generated declarations install, enum export patch.\n- `bun scripts/embed-native.ts` (`embed:native`) → generate `native/embedded-addon.js` from built files.\n\nRoot scripts include `build:native` as `bun --cwd=packages/natives run build`.\n\n### 2) N-API/Rust artifact build\n\n`build-native.ts` invokes the `@napi-rs/cli` binary directly from `node_modules/.bin` with:\n\n- `napi build`\n- `--manifest-path crates/pi-natives/Cargo.toml`\n- `--package-json-path packages/natives/package.json`\n- `--platform`\n- `--no-js`\n- `--dts index.d.ts`\n- `--profile local` for non-CI local native builds, otherwise `--profile ci`\n- optional `--target <CROSS_TARGET>`\n\n`crates/pi-natives/Cargo.toml` declares `crate-type = [\"cdylib\"]`; napi-rs emits `.node` artifacts plus generated `index.d.ts` in an isolated temporary output directory under `packages/natives/native/.build/`.\n\n### 3) Artifact install\n\nAfter napi-rs succeeds, `build-native.ts`:\n\n1. resolves the built addon in the isolated output directory;\n2. normalizes its name to `pi_natives.<platform>-<arch>(-variant).node` when needed;\n3. installs the addon into `packages/natives/native/` with temp-file + rename semantics;\n4. copies generated `index.js` and `index.d.ts` into `packages/natives/native/` when present;\n5. runs `generateEnumExports()` to append enum runtime objects to `native/index.js`.\n\nWindows locked-DLL replacement failures are reported with an explicit close-running-processes hint.\n\n## Target/variant model and naming conventions\n\n## Platform tag\n\nBoth build and runtime use platform tag:\n\n`<platform>-<arch>` (example: `darwin-arm64`, `linux-x64`).\n\n## Variant model (x64 only)\n\nx64 supports CPU variants:\n\n- `modern` (AVX2-capable path)\n- `baseline` (fallback)\n\nNon-x64 uses a single default artifact with no variant suffix.\n\n### Output filenames\n\n- x64: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- non-x64: `pi_natives.<platform>-<arch>.node`\n\nRuntime x64 candidate order also includes the unsuffixed default filename after the selected variant candidates.\n\n## Environment flags and build options\n\n## Runtime flags\n\n- `SKC_NATIVE_VARIANT`: x64 runtime override; valid values are `modern` and `baseline`.\n- `SKC_COMPILED`: legacy compiled-mode signal. A populated embedded-addon manifest is also a compiled-mode signal and is the authoritative signal for Bun standalone builds that do not preserve `process.env.SKC_COMPILED`.\n\n## Build-time flags/options\n\n- `CROSS_TARGET`: passed to napi-rs as `--target <CROSS_TARGET>`.\n- `TARGET_PLATFORM`: override output platform tag naming.\n- `TARGET_ARCH`: override output arch naming.\n- `TARGET_VARIANT` (x64 only): force `modern` or `baseline` for output filename and RUSTFLAGS policy.\n- `CARGO_TARGET_DIR`: respected if set; otherwise the default `target/` dir is used so `Swatinem/rust-cache` can cache cleanly.\n- `RUSTFLAGS`:\n  - if unset and not cross-compiling, script sets:\n    - modern: `-C target-cpu=x86-64-v3`\n    - baseline: `-C target-cpu=x86-64-v2`\n    - non-x64 / no variant: `-C target-cpu=native`\n  - if already set, script does not override.\n\n## Build state/lifecycle transitions\n\n### Build lifecycle (`build-native.ts`)\n\n1. **Init**: parse env, resolve target tuple, cross/local mode, profile label.\n2. **Variant resolve**:\n   - non-x64 → no variant;\n   - x64 + `TARGET_VARIANT` → explicit variant;\n   - x64 cross-build without `TARGET_VARIANT` → hard error;\n   - x64 local build without override → detect host AVX2.\n3. **CPU policy**: set `RUSTFLAGS` for the resolved variant unless the caller already provided one.\n4. **Compile**: run napi-rs against `crates/pi-natives` into an isolated output directory.\n5. **Locate artifact**: accept the canonical filename or a single napi-rs-generated `pi_natives.<platform>-<arch>*.node` candidate.\n6. **Install**: copy/rename addon into `packages/natives/native`.\n7. **Install generated bindings**: copy `index.js`/`index.d.ts` if needed.\n8. **Patch enums**: append generated enum runtime exports.\n9. **Cleanup**: remove the temporary build output directory.\n\nFailure exits have explicit error text for invalid variants, failed napi build, missing/multiple output artifacts, generated binding install failure, and install/rename failure.\n\n### Embed lifecycle (`embed-native.ts`)\n\n1. **Init**: compute platform tag from `TARGET_PLATFORM`/`TARGET_ARCH` or host values.\n2. **Candidate set**:\n   - x64 looks for `modern` and `baseline` files;\n   - non-x64 looks for one default file.\n3. **Validate availability**: at least one expected file must exist in `packages/natives/native`.\n4. **Generate manifest** (`native/embedded-addon.js`) with Bun `file` imports and package version.\n5. **Runtime extraction ready** for compiled mode.\n\n`--reset` writes the null manifest stub (`embeddedAddon = null`) without validating addon availability.\n\n## Dev workflow vs shipped/compiled behavior\n\n## Local development workflow\n\nTypical local loop:\n\n1. Build addon: `bun --cwd=packages/natives run build`.\n2. Loader resolves package-local `native/` candidates, then executable-dir fallback candidates.\n3. Generated declarations in `native/index.d.ts` describe the public TS API.\n\n## Shipped/compiled binary workflow\n\nIn compiled mode (`SKC_COMPILED`, Bun embedded URL markers, or populated embedded manifest):\n\n1. Loader computes versioned cache dir: `<getNativesDir()>/<packageVersion>`.\n2. If embedded manifest matches current platform+version, loader may extract the selected embedded file into that versioned dir.\n3. Runtime candidate order includes:\n   - versioned cache dir,\n   - legacy compiled-binary dir (`%LOCALAPPDATA%/skc` on Windows, `~/.local/bin` elsewhere),\n   - package/executable directories.\n4. First successfully loaded addon is returned.\n\nThis is why packaging + runtime loader expectations must align: filenames, platform tags, CPU variants, and embedded manifest version must match what `native/index.js` probes.\n\n## JS API ↔ Rust export mapping (build sanity subset)\n\nGenerated declarations currently include exports from these Rust modules:\n\n| Area                   | Representative JS exports                                                                         | Rust source                                                                             |\n| ---------------------- | ------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |\n| Search                 | `grep`, `search`, `hasMatch`, `fuzzyFind`, `glob`, `invalidateFsScanCache`                        | `grep.rs`, `fd.rs`, `glob.rs`, `fs_cache.rs`                                            |\n| AST                    | `astGrep`, `astEdit`                                                                              | `ast.rs`                                                                                |\n| Text/highlight/tokens  | `visibleWidth`, `truncateToWidth`, `highlightCode`, `countTokens`                                 | `text.rs`, `highlight.rs`, `tokens.rs`                                                  |\n| Shell/PTY/process/keys | `executeShell`, `Shell`, `PtySession`, `killTree`, `parseKey`                                     | `shell.rs`, `pty.rs`, `ps.rs`, `keys.rs`                                                |\n| Media/system           | `PhotonImage`, `encodeSixel`, clipboard, macOS appearance/power, `getWorkProfile`, ProjFS helpers | `image.rs`, `clipboard.rs`, `appearance.rs`, `power.rs`, `prof.rs`, `projfs_overlay.rs` |\n\n## Failure behavior and diagnostics\n\n## Build-time failures\n\n- Invalid variant configuration:\n  - `TARGET_VARIANT` set on non-x64 → immediate error.\n  - unsupported `TARGET_VARIANT` value → immediate error.\n  - x64 cross-build without explicit `TARGET_VARIANT` → immediate error.\n- napi-rs build failure: script surfaces non-zero exit and stderr.\n- Artifact not found or ambiguous: script prints expected/candidate filenames and output directory contents.\n- Install failure: explicit message; Windows includes locked-file hint.\n- Generated binding install failure: explicit source/destination message.\n\n## Runtime loader failures (`native/index.js`)\n\n- Unsupported platform tag: throws with supported platform list after probing fails.\n- No candidate could load: throws with full candidate error list and mode-specific remediation hints.\n- Embedded extraction problems: extraction mkdir/write errors are recorded and included in final diagnostics if load fails.\n\n## Troubleshooting matrix\n\n| Symptom                                                                | Likely cause                                                                                | Verify                                                            | Fix                                                                                           |\n| ---------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- | ----------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `Cannot find module` or dynamic library load error for every candidate | Missing release artifact, wrong platform tag, or stale compiled cache                       | Inspect loader error list and `packages/natives/native` filenames | Build correct target/variant; delete stale cache for the package version                      |\n| Export is missing at runtime but present in TypeScript                 | Stale `.node` loaded, generated declarations newer than binary, or Rust export not compiled | Require the actual candidate and inspect `Object.keys(mod)`       | Rebuild native package and remove stale candidate/cache paths                                 |\n| x64 machine loads baseline when modern expected                        | `SKC_NATIVE_VARIANT=baseline`, no AVX2 detected, or modern file unavailable                  | Check env and filenames in `native/`                              | Build modern variant (`TARGET_VARIANT=modern ... build`) and ship it                          |\n| Cross-build produces wrong-labeled binary                              | Mismatch between `CROSS_TARGET` and `TARGET_PLATFORM`/`TARGET_ARCH`, or missing x64 variant | Confirm env tuple and output filename                             | Re-run with consistent env values and explicit x64 `TARGET_VARIANT`                           |\n| Compiled binary fails after upgrade                                    | Stale extracted cache or embedded manifest version mismatch                                 | Inspect `<getNativesDir()>/<version>` and loader error list       | Delete versioned cache for the package version; regenerate embedded manifest during packaging |\n| `embed:native` fails with `No native addons found`                     | Required platform artifact was not built before embedding                                   | Check expected list in error text                                 | Build at least one expected artifact for the target, then rerun `embed:native`                |\n\n## Operational commands\n\n```bash\n# Release artifact for current host\nbun --cwd=packages/natives run build\n\n# Build explicit x64 variants\nTARGET_VARIANT=modern bun --cwd=packages/natives run build\nTARGET_VARIANT=baseline bun --cwd=packages/natives run build\n\n# Generate embedded addon manifest from built native files\nbun --cwd=packages/natives run embed:native\n\n# Reset embedded manifest to null stub\nbun --cwd=packages/natives run embed:native -- --reset\n```\n\n## Orchestrator-side content-addressed build cache (roboskc)\n\nWhen `pi-natives` is built inside the roboskc orchestrator (`python/roboskc/`), workspaces share built artifacts through a content-addressed cache instead of rebuilding from scratch in every per-issue worktree. The cache is **orchestrator-side only** — `bun --cwd=packages/natives run build` itself is unchanged; the cache lives outside the build pipeline and is populated/captured around `ensure_workspace` and post-task success in `python/roboskc/src/natives_cache.py`.\n\n### What is cached\n\nThe complete set of files in `packages/natives/native/` that are pure functions of the cache-key inputs:\n\n- `pi_natives.<platform>-<arch>[-variant].node` (glob `pi_natives.*.node`)\n- `index.d.ts`\n- `index.js`\n- `embedded-addon.js`\n- `manifest.json` (cache metadata: key, target triple, capture timestamp, source workspace, commit)\n\nAn entry is only considered a hit when the `.node` glob matches AND every companion plus the manifest is present. Partial entries are evicted on GC.\n\n### Cache key\n\nThe key is `sha256` over `(path \\t git-tree-hash \\n)` pairs for the following inputs, in this order (order is significant), followed by the target triple:\n\n1. `crates` (whole subtree — pi-natives transitively depends on other workspace crates)\n2. `Cargo.lock`\n3. `Cargo.toml`\n4. `rust-toolchain.toml`\n5. `packages/natives` (whole subtree — build script, `scripts/*`, package.json with napi config)\n\nTree hashes come from one `git cat-file --batch-check` invocation against `HEAD`; paths missing from `HEAD` fold in as a fixed null hash so the key stays deterministic across repos that don't ship every input. The target-triple suffix matches the napi addon basename convention (`<platform>-<arch>` for non-x64, `<platform>-<arch>-<variant>` for x64). When `TARGET_VARIANT` is unset on an x64 host the variant component is `host` rather than autodetected — the key is stable on a given machine but a `modern`/`baseline` build with an explicit `TARGET_VARIANT` gets a different key.\n\nAnything outside this input set (Rust toolchain auto-installed delta, host glibc, env vars other than `TARGET_VARIANT`) is **not** in the key. If you need to invalidate after such a change, delete the cache directory by hand or bump one of the input files.\n\n### Layout and ownership\n\n- Root: `/data/cache/pi-natives` (provisioned by `entrypoint.sh` alongside the cargo caches, owned `root:skc`, mode `02770` setgid so cached files inherit `gid=skc` and stay readable by every slot user).\n- Per-repo subdirectory: `<root>/<repo-slug>/` where the slug is `owner__repo` (mirrors `SandboxManager.pool_path`).\n- Per-entry directory: `<root>/<repo-slug>/<sha256-key>/` containing the cached files plus `manifest.json`.\n- Per-repo lockfile: `<root>/<repo-slug>/.lock` (advisory `fcntl.flock`, exclusive on capture and GC).\n- Staging dirs (`.<key>.tmp.<pid>`) during capture; renamed atomically into the final entry path. Stale staging dirs from crashed captures are swept on GC.\n\n### Populate and capture semantics\n\n- **Populate** (workspace ← cache) runs inside `ensure_workspace`. On a key hit the `.node` is **hardlinked** into the workspace (zero-copy, shared inode); the companion `index.d.ts` / `index.js` / `embedded-addon.js` are **copied** (independent inodes) because the napi build's `installGeneratedBindings` and `gen-enums.ts` rewrite those files via `open(..., 'w')` — an in-place truncate that would otherwise propagate through a hardlink and corrupt the cache. Cross-device hardlink failures (`EXDEV`) fall back to copy.\n- **Capture** (cache ← workspace) runs from the post-task success path when the build produced a complete artifact set. Capture uses **copy**, not hardlink: hardlinking a slot-owned workspace file would preserve slot UID ownership on the cached inode and defeat the shared-group model. Copying creates a fresh root-owned, `gid=skc` inode via the setgid cache root. Capture is idempotent under the per-repo flock: a concurrent capture for the same key returns the existing entry.\n\n### Garbage collection\n\nA periodic GC loop runs in `WorkerPool` with two caps per repo. When either cap is exceeded, oldest entries (by `manifest.json.captured_at`) are dropped first:\n\n- entry count cap (`max_entries_per_repo`, default 8)\n- byte cap (`max_bytes`, default 4 GiB)\n\nWorkspaces that hardlinked a `.node` before GC retain access via the kernel inode refcount — `rmtree` of the cache entry does not delete the file from the workspace.\n\n### Configuration (settings on `roboskc.config.Settings`)\n\n| Env var                                      | Default                  | Effect                                                        |\n| -------------------------------------------- | ------------------------ | ------------------------------------------------------------- |\n| `ROBSKC_NATIVES_CACHE_ENABLED`               | `true`                   | Master switch. When false the populate/capture hooks no-op and every workspace builds from scratch. |\n| `ROBSKC_NATIVES_CACHE_ROOT`                  | `/data/cache/pi-natives` | Cache root directory. Must be `root:skc 02770` for cross-slot reads.                                  |\n| `ROBSKC_NATIVES_CACHE_MAX_ENTRIES_PER_REPO`  | `8`                      | LRU entry-count cap, per repo slug.                                                                  |\n| `ROBSKC_NATIVES_CACHE_MAX_BYTES`             | `4294967296` (4 GiB)     | LRU byte cap, per repo slug.                                                                          |\n| `ROBSKC_NATIVES_CACHE_GC_INTERVAL_SECONDS`   | `3600`                   | Period of the background GC loop in `WorkerPool`.                                                    |\n\n### Manual invalidation\n\n- One key: `rm -rf /data/cache/pi-natives/<repo-slug>/<sha256>`.\n- One repo: `rm -rf /data/cache/pi-natives/<repo-slug>`.\n- Everything: `rm -rf /data/cache/pi-natives/*` (preserve the root so its setgid mode survives).\n- Stuck lock: `rm /data/cache/pi-natives/<repo-slug>/.lock` (only when no orchestrator process is touching the repo).\n\nTrigger an automatic miss by editing any path in the key set: a single touched byte under `crates/`, `Cargo.lock`, `Cargo.toml`, `rust-toolchain.toml`, or `packages/natives/` shifts the tree hash and forces a fresh build at the next populate.\n",
 	"natives-media-system-utils.md": "# Natives media + system utilities\n\nThis document covers the media/system/conversion exports in `@sayknow-cli/natives`: image processing, HTML conversion, clipboard access, token counting, macOS appearance/power helpers, ProjFS helpers, and work profiling.\n\n## Implementation files\n\n- `crates/pi-natives/src/image.rs`\n- `crates/pi-natives/src/html.rs`\n- `crates/pi-natives/src/clipboard.rs`\n- `crates/pi-natives/src/tokens.rs`\n- `crates/pi-natives/src/appearance.rs`\n- `crates/pi-natives/src/power.rs`\n- `crates/pi-natives/src/projfs_overlay.rs`\n- `crates/pi-natives/src/prof.rs`\n- `crates/pi-natives/src/task.rs`\n- `packages/natives/native/index.d.ts`\n\n> Note: there is no `crates/pi-natives/src/work.rs`; work profiling is implemented in `prof.rs` and fed by instrumentation in `task.rs`.\n\n## JS API ↔ Rust export/module mapping\n\n| JS export                                           | Rust N-API export              | Rust module         |\n| --------------------------------------------------- | ------------------------------ | ------------------- |\n| `PhotonImage.parse(bytes)`                          | `PhotonImage::parse`           | `image.rs`          |\n| `PhotonImage#resize(width, height, filter)`         | `PhotonImage::resize`          | `image.rs`          |\n| `PhotonImage#encode(format, quality)`               | `PhotonImage::encode`          | `image.rs`          |\n| `encodeSixel(bytes, targetWidthPx, targetHeightPx)` | `encode_sixel`                 | `image.rs`          |\n| `htmlToMarkdown(html, options?)`                    | `html_to_markdown`             | `html.rs`           |\n| `copyToClipboard(text)`                             | `copy_to_clipboard`            | `clipboard.rs`      |\n| `readImageFromClipboard()`                          | `read_image_from_clipboard`    | `clipboard.rs`      |\n| `countTokens(input, encoding?)`                     | `count_tokens`                 | `tokens.rs`         |\n| `detectMacOSAppearance()`                           | `detect_mac_os_appearance`     | `appearance.rs`     |\n| `MacAppearanceObserver.start(callback)`             | `MacAppearanceObserver::start` | `appearance.rs`     |\n| `MacOSPowerAssertion.start(options?)`               | `MacOSPowerAssertion::start`   | `power.rs`          |\n| `projfsOverlayProbe/start/stop`                     | ProjFS exports                 | `projfs_overlay.rs` |\n| `getWorkProfile(lastSeconds)`                       | `get_work_profile`             | `prof.rs`           |\n\n## Data format boundaries and conversions\n\n### Image (`image`)\n\n- **JS input boundary**: `Uint8Array` encoded image bytes for `PhotonImage.parse` and `encodeSixel`.\n- **Rust decode boundary**: bytes are copied/read, format is guessed with `ImageReader::with_guessed_format()`, then decoded to `DynamicImage`.\n- **In-memory state**: `PhotonImage` stores `Arc<DynamicImage>`.\n- **Output boundary**:\n  - `PhotonImage#encode(format, quality)` returns a promise for encoded bytes (`Vec<u8>` in Rust; generated TS currently declares `Promise<Array<number>>`).\n  - `encodeSixel(...)` returns a SIXEL escape string synchronously.\n\nFormat IDs:\n\n- `0`: PNG\n- `1`: JPEG\n- `2`: WebP\n- `3`: GIF\n\nEncoding behavior:\n\n- JPEG uses the provided `quality` with `JpegEncoder::new_with_quality`.\n- WebP uses the `webp` crate encoder with `quality` as `f32` in the same 0..=100 range.\n- PNG/GIF ignore `quality`.\n- Invalid dimensions for SIXEL (`0` width or height) fail with `Target SIXEL dimensions must be greater than zero`.\n\n### HTML conversion (`html`)\n\n- **JS input boundary**: HTML `string` + optional `{ cleanContent?: boolean; skipImages?: boolean }`.\n- **Rust conversion boundary**: conversion is scheduled through `task::blocking(\"html_to_markdown\", (), ...)`.\n- **Output boundary**: Markdown `string` promise.\n\nConversion behavior:\n\n- `cleanContent` defaults to `false`.\n- When `cleanContent=true`, preprocessing uses `PreprocessingPreset::Aggressive` and hard-removal flags for navigation/forms.\n- `skipImages` defaults to `false`.\n\n### Clipboard (`clipboard`)\n\n- `copyToClipboard(text)` is a synchronous native call using `arboard::Clipboard::set_text`.\n- `readImageFromClipboard()` runs in `task::blocking(\"clipboard.read_image\", (), ...)`.\n- Image read returns `null`/`undefined` when `arboard` reports `ContentNotAvailable`.\n- Successful image read re-encodes clipboard RGBA data as PNG and returns `{ data: Uint8Array, mimeType: \"image/png\" }`.\n- Clipboard access or image encoding failures reject/throw as native errors.\n\nThere is no current `packages/natives` TS wrapper that emits OSC52, handles Termux, or suppresses native clipboard failures. Any best-effort clipboard policy must live in consumers.\n\n### Tokens (`tokens`)\n\n- `countTokens(input, encoding?)` accepts a single string or an array of strings.\n- Arrays return one aggregate token count; encoding work is parallelized in Rust.\n- Default encoding is `O200kBase`; `Cl100kBase` remains exported as a compatibility alias that routes to `o200k_base` (the cl100k BPE table is not embedded in default builds).\n- The implementation uses ordinary encoding, not special-token handling.\n\n### macOS appearance and power helpers\n\n- `detectMacOSAppearance()` returns `\"dark\"`, `\"light\"`, or `null` on non-macOS.\n- `MacAppearanceObserver.start(callback)` returns a handle with `stop()`; on macOS it uses distributed notifications plus a 2-second polling fallback, and on non-macOS it is a no-op observer.\n- `MacOSPowerAssertion.start(options?)` returns a handle with `stop()`; on macOS it acquires an IOKit assertion, and on other platforms it is a no-op handle.\n\n### Windows ProjFS helpers\n\n- `projfsOverlayProbe()` reports whether ProjFS APIs are available.\n- `projfsOverlayStart(lowerRoot, projectionRoot)` starts an overlay.\n- `projfsOverlayStop(projectionRoot)` stops an overlay session.\n\nThese helpers are platform-specific; availability must be checked before relying on overlay behavior.\n\n### Work profiling (`work`)\n\n- **Collection boundary**: profiling samples are produced by `profile_region(tag)` guards in `task::blocking` and `task::future`.\n- **Storage format**: fixed-size circular buffer (`MAX_SAMPLES = 10_000`) storing stack path, duration, and timestamp.\n- **Output boundary**: `getWorkProfile(lastSeconds)` returns:\n  - `folded`: folded-stack text (flamegraph input)\n  - `summary`: markdown table summary\n  - `svg`: optional flamegraph SVG\n  - `totalMs`, `sampleCount`\n\n## Lifecycle and state transitions\n\n### Image lifecycle\n\n1. `PhotonImage.parse(bytes)` schedules a blocking decode task (`image.decode`).\n2. On success, a native `PhotonImage` handle exists in JS.\n3. `resize(...)` creates a new native handle (`image.resize`); old and new handles can coexist.\n4. `encode(...)` schedules `image.encode` and materializes bytes without mutating image dimensions.\n5. `encodeSixel(...)` decodes, optionally resizes to exact target dimensions with Lanczos3, and returns SIXEL text synchronously.\n\nFailure transitions:\n\n- Format detection/decode failure rejects parse promise or throws from SIXEL encoding.\n- Encode failure rejects encode promise.\n- Invalid SIXEL dimensions throw.\n\n### HTML lifecycle\n\n1. `htmlToMarkdown(html, options)` schedules a blocking conversion task.\n2. Conversion runs with defaulted options (`cleanContent=false`, `skipImages=false`) unless specified.\n3. Returns markdown string or rejects.\n\n### Clipboard lifecycle\n\n- Text copy constructs an `arboard::Clipboard` and calls `set_text` synchronously.\n- Image read constructs an `arboard::Clipboard`, calls `get_image`, encodes PNG on success, maps `ContentNotAvailable` to `None`, and rejects other errors.\n\n### Work profiling lifecycle\n\n1. No explicit start: profiling is active when task helpers execute.\n2. Every instrumented task scope records one sample on guard drop.\n3. Samples overwrite oldest entries after buffer capacity is reached.\n4. `getWorkProfile(lastSeconds)` reads a time window and derives folded/summary/svg artifacts.\n\nFailure transitions:\n\n- SVG generation failure is soft (`svg` omitted/undefined), while folded and summary still return.\n- Empty sample windows return empty folded data and no SVG, not an error.\n\n## Unsupported operations and error propagation\n\n### Image\n\n- Unsupported decode input or corrupted bytes: strict failure.\n- Invalid SIXEL target dimensions: strict failure.\n- No JS fallback path in the natives package.\n\n### HTML\n\n- Conversion errors are strict failures.\n- Option omission is defaulting, not failure.\n\n### Clipboard\n\n- Text copy is strict at the native API surface.\n- Image read distinguishes \"no image\" (`null`/`undefined`) from operational failure (rejection).\n\n### Work profiling\n\n- Retrieval is strict for the function call itself.\n- Flamegraph SVG generation is nullable/optional.\n- Buffer truncation is expected ring-buffer behavior.\n\n## Platform caveats\n\n- Clipboard access depends on OS/session support exposed through `arboard`.\n- macOS appearance and power helpers intentionally return no-op/null behavior on unsupported platforms.\n- ProjFS helpers are Windows-specific and should be gated by `projfsOverlayProbe()`.\n",
+	"natives-package-split-plan.md": "# Native package split plan\n\nIssue #1280 reports Bun 1.3.14 extraction failures when installing the published `@sayknow-cli/natives` tarball because the package ships every platform's prebuilt `.node` file in one mandatory dependency. PR #1281 added the safe `skc update` partial-success verifier; this follow-up implements the package-topology split that prevents the oversized native tarball in the first place.\n\nThe stable loader package remains `@sayknow-cli/natives`; platform binaries now publish as optional packages so package managers install only the host package.\n\n## Target package topology\n\n- Keep `@sayknow-cli/natives` as the stable JS/types loader package.\n- Move prebuilt binaries into optional packages named by host triple, for example:\n  - `@sayknow-cli/natives-darwin-arm64`\n  - `@sayknow-cli/natives-darwin-x64`\n  - `@sayknow-cli/natives-linux-arm64`\n  - `@sayknow-cli/natives-linux-x64`\n  - `@sayknow-cli/natives-win32-x64`\n- Add those packages as `optionalDependencies` of `@sayknow-cli/natives` with the lockstep release version.\n- Publish each platform package with exactly its relevant `pi_natives.<platform>-<arch>*.node` file(s), `README.md`, and `package.json` using `os` / `cpu` fields so non-host package-manager failures remain optional.\n- Update `native/loader-state.js` to search the host optional package before falling back to the legacy bundled `native/` directory and compiled-binary embedded addons.\n\n## Release-script work\n\n1. The release npm job still downloads every `pi_natives.*.node` artifact into `packages/natives/native`.\n2. `scripts/ci-release-publish.ts` stages matching artifacts into the platform package directories and publishes the optional native packages before `@sayknow-cli/natives` / `@sayknow-cli/coding-agent`.\n3. The monorepo release version bump keeps all new package manifests in lockstep.\n4. Release/loader tests pin publish ordering, stable-package file inclusion, optional-package resolution, and fallback to the legacy bundled path.\n\n## Compatibility notes\n\n- The legacy `@sayknow-cli/natives/native/*.node` fallback should remain for one release cycle so local dev, older release artifacts, and compiled standalone binaries keep working.\n- The `skc --smoke-test` verification path should remain the final update guard even after the split, because optional dependency installation semantics vary by package manager.\n",
 	"natives-rust-task-cancellation.md": "# Native Rust task execution and cancellation (`pi-natives`)\n\nThis document describes how `crates/pi-natives` schedules native work and how cancellation flows from JS options (`timeoutMs`, `AbortSignal`) into Rust execution.\n\n## Implementation files\n\n- `crates/pi-natives/src/task.rs`\n- `crates/pi-natives/src/grep.rs`\n- `crates/pi-natives/src/glob.rs`\n- `crates/pi-natives/src/fd.rs`\n- `crates/pi-natives/src/ast.rs`\n- `crates/pi-natives/src/shell.rs`\n- `crates/pi-natives/src/pty.rs`\n- `crates/pi-natives/src/html.rs`\n- `crates/pi-natives/src/image.rs`\n- `crates/pi-natives/src/clipboard.rs`\n- `crates/pi-natives/src/text.rs`\n- `crates/pi-natives/src/ps.rs`\n\n## Core primitives (`task.rs`)\n\n`task.rs` defines:\n\n1. `task::blocking(tag, cancel_token, work)`\n   - Wraps `napi::AsyncTask` / `Task`.\n   - `compute()` runs on libuv worker threads.\n   - Returns a JS `Promise<T>` for exported functions.\n   - Records a profiling sample through `profile_region(tag)`.\n\n2. `task::future(env, tag, work)`\n   - Wraps `env.spawn_future(...)`.\n   - Runs async work on Tokio's runtime.\n   - Returns `PromiseRaw<'env, T>`.\n   - Records a profiling sample through `profile_region(tag)`.\n\n3. `CancelToken` / `AbortToken` / `AbortReason`\n   - `CancelToken::new(timeout_ms, signal)` combines an optional deadline and optional JS `AbortSignal` converted from `Unknown`.\n   - `CancelToken::heartbeat()` is cooperative cancellation for blocking loops.\n   - `CancelToken::wait()` asynchronously waits for signal, timeout, or Ctrl-C.\n   - `CancelToken::emplace_abort_token()` creates an abortable flag when a later `Shell.abort()`/internal bridge needs one.\n   - `AbortToken::abort(reason)` lets external code request abort.\n\n## `blocking` vs `future`: execution model and selection\n\n### Use `task::blocking`\n\nUse when work is CPU-heavy or fundamentally synchronous/blocking:\n\n- regex/file scanning (`grep`, `glob`, `fuzzyFind`)\n- ast-grep search/edit worker work\n- PTY loop internals through `tokio::task::spawn_blocking`\n- image decode/resize/encode\n- HTML conversion\n- clipboard image read\n\nBehavior:\n\n- Work closure receives a cloned `CancelToken`.\n- Cancellation is only observed where code checks `ct.heartbeat()?`.\n- Closure `Err(...)` rejects the JS promise.\n\n### Use `task::future`\n\nUse when work must `await` async operations:\n\n- shell session orchestration (`Shell.run`, `executeShell`)\n- PTY outer promise (`PtySession.start`) before it enters `spawn_blocking`\n- task racing (`tokio::select!`) between completion and cancellation\n\nBehavior:\n\n- Future code can race normal completion against `ct.wait()`.\n- On cancel path, async implementations typically cancel subordinate machinery and may force-abort after a grace timeout.\n\n## JS API ↔ Rust export mapping (task/cancel relevant)\n\n| JS-facing API                           | Rust export                          | Scheduler                                                      | Cancellation hookup                                                                      |\n| --------------------------------------- | ------------------------------------ | -------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |\n| `grep(options, onMatch?)`               | `grep`                               | `task::blocking(\"grep\", ct, ...)`                              | `CancelToken::new(options.timeoutMs, options.signal)` + heartbeat checks                 |\n| `glob(options, onMatch?)`               | `glob`                               | `task::blocking(\"glob\", ct, ...)`                              | `CancelToken::new(...)` + heartbeat checks                                               |\n| `fuzzyFind(options)`                    | `fuzzy_find`                         | `task::blocking(\"fuzzy_find\", ct, ...)`                        | `CancelToken::new(...)` + heartbeat checks                                               |\n| `astGrep(options)` / `astEdit(options)` | ast exports                          | blocking worker path                                           | timeout/signal fields are accepted by options and checked cooperatively in worker loops  |\n| `Shell#run(options, onChunk?)`          | `Shell::run`                         | `task::future(env, \"shell.run\", ...)`                          | `ct.wait()` raced against run task; bridges to Tokio cancellation token and `AbortToken` |\n| `executeShell(options, onChunk?)`       | `execute_shell`                      | `task::future(env, \"shell.execute\", ...)`                      | same cancel race and 2s graceful window                                                  |\n| `PtySession#start(options, onChunk?)`   | `PtySession::start`                  | `task::future(env, \"pty.start\", ...)` + inner `spawn_blocking` | `CancelToken` checked in sync PTY loop via `heartbeat()`                                 |\n| `htmlToMarkdown(html, options?)`        | `html_to_markdown`                   | `task::blocking(\"html_to_markdown\", (), ...)`                  | none (`()` token)                                                                        |\n| `PhotonImage.parse/encode/resize`       | `PhotonImage::{parse,encode,resize}` | `task::blocking(...)`                                          | none (`()` token)                                                                        |\n| `readImageFromClipboard()`              | `read_image_from_clipboard`          | `task::blocking(\"clipboard.read_image\", (), ...)`              | none (`()` token)                                                                        |\n\n`text.rs`, `tokens.rs`, `keys.rs`, most `ps.rs` functions, and synchronous utility exports do not use `task::blocking`/`task::future` and therefore do not participate in this cancellation path.\n\n## Cancellation lifecycle and state transitions\n\n### `CancelToken` lifecycle\n\n```text\nCreated\n  ├─ no signal + no timeout  -> passive token\n  ├─ signal registered        -> AbortSignal callback can set AbortReason::Signal\n  └─ deadline set             -> timeout check becomes active\n\nRunning\n  ├─ heartbeat()/wait() sees signal   -> AbortReason::Signal\n  ├─ heartbeat()/wait() sees deadline -> AbortReason::Timeout\n  ├─ wait() sees Ctrl-C               -> AbortReason::User\n  └─ no abort                         -> continue\n\nAborted\n  └─ flag stores first observed cause for waiters; heartbeat formats it as \"Aborted: <reason>\"\n```\n\n### Before-start vs mid-execution cancellation\n\n- **Before start / before first cancellation check**:\n  - `task::future` users that race on `ct.wait()` can resolve cancellation once they enter `select!`.\n  - `task::blocking` users only observe cancellation when closure code reaches `heartbeat()`.\n\n- **Mid-execution**:\n  - `blocking`: next `heartbeat()` returns `Err(\"Aborted: ...\")`.\n  - `future`: `ct.wait()` branch wins `select!`, then code cancels subordinate async machinery.\n  - shell: cancellation triggers a Tokio cancellation token, waits up to 2 seconds, then aborts the task if needed.\n  - PTY: heartbeat failure or `kill()` terminates PTY child/process tree and drains output briefly.\n\n## Heartbeat expectations for long-running loops\n\n`heartbeat()` must run at predictable cadence in loops with unbounded or large work sets.\n\nObserved patterns:\n\n- `glob` filtering checks entries during scan/filter work.\n- `fd` scoring checks scanned candidates.\n- `grep` checks before/during expensive search and passes tokens into shared scan/cache helpers.\n- `run_pty_sync` checks every loop tick with a maximum 16ms wait cadence.\n\nPractical rule: no loop over external-size input should exceed a short bounded interval without a heartbeat.\n\n## Failure behavior and error propagation to JS\n\n### Blocking tasks\n\nError path:\n\n1. Closure returns `Err(napi::Error)` (including `heartbeat()` abort).\n2. `Task::compute()` returns `Err`.\n3. `AsyncTask` rejects JS promise.\n\nTypical error strings:\n\n- `Aborted: Timeout`\n- `Aborted: Signal`\n- domain errors (`Failed to decode image: ...`, `Conversion error: ...`, etc.)\n\n### Future tasks\n\nError path:\n\n1. Async body returns `Err(napi::Error)` or join failure is mapped (`... task failed: {err}`).\n2. `task::future`-spawned promise rejects.\n3. Shell and PTY command APIs model cancellation as structured results instead of rejection when the cancellation path wins: `exitCode` omitted, `cancelled` or `timedOut` set.\n\n### Cancellation reporting split\n\n- **Abort as error**: blocking exports using `heartbeat()?`.\n- **Abort as typed result**: shell/PTY command APIs that model cancellation in result structs.\n\nChoose one model per API and document it explicitly.\n\n## Common pitfalls\n\n1. **Missing heartbeat in blocking loops**\n   - Symptom: timeout/signal appears ignored until loop ends.\n   - Fix: add `ct.heartbeat()?` at loop top and before expensive per-item steps.\n\n2. **Long uncancelable sections**\n   - Symptom: cancellation latency spikes during single large call (decode, sort, compression, parser invocation, etc.).\n   - Fix: split work into chunks with heartbeat boundaries; if impossible, document latency.\n\n3. **Blocking async executor**\n   - Symptom: async API stalls when sync-heavy code runs directly in future.\n   - Fix: move CPU/sync blocks to `task::blocking` or `tokio::task::spawn_blocking`.\n\n4. **Inconsistent cancel semantics**\n   - Symptom: one API rejects on cancel, another resolves with flags, confusing callers.\n   - Fix: standardize per domain and keep docs aligned.\n\n5. **Forgetting cancellation bridge in nested async tasks**\n   - Symptom: outer token is cancelled but inner readers/subprocess tasks keep running.\n   - Fix: bridge cancellation to inner token/signal and enforce grace timeout + forced abort fallback.\n\n## Checklist for new cancellable exports\n\n1. Classify work correctly:\n   - CPU-bound or sync blocking -> `task::blocking`.\n   - async I/O / `await` orchestration -> `task::future`.\n\n2. Expose cancel inputs when needed:\n   - include `timeoutMs` and `signal` in `#[napi(object)]` options,\n   - create `let ct = task::CancelToken::new(timeout_ms, signal);`.\n\n3. Wire cancellation through all layers:\n   - blocking loops: `ct.heartbeat()?` at stable intervals,\n   - async orchestration: race with `ct.wait()` and cancel sub-tasks/tokens.\n\n4. Decide cancellation contract:\n   - reject promise with abort error, or\n   - resolve typed `{ cancelled, timedOut, ... }`,\n   - keep this contract consistent for the API family.\n\n5. Propagate failures with context:\n   - map errors via `Error::from_reason(format!(\"...: {err}\"))`,\n   - include stage-specific prefixes (`spawn`, `decode`, `wait`, etc.).\n\n6. Handle before-start and mid-flight cancellation:\n   - cancellation check/await must happen before expensive body and during long execution.\n\n7. Validate no executor misuse:\n   - no long sync work directly inside async futures without `spawn_blocking`/blocking task wrapper.\n",
 	"natives-shell-pty-process.md": "# Natives Shell, PTY, Process, and Key Internals\n\nThis document covers the execution/process/terminal primitives in `@sayknow-cli/natives`: `shell`, `pty`, `ps`, and `keys`, using the architecture terms from `docs/natives-architecture.md`.\n\n## Implementation files\n\n- `crates/pi-natives/src/shell.rs`\n- `crates/pi-natives/src/shell/windows.rs` (Windows-only PATH enrichment)\n- `crates/pi-natives/src/pty.rs`\n- `crates/pi-natives/src/ps.rs`\n- `crates/pi-natives/src/keys.rs`\n- `crates/pi-natives/src/task.rs`\n- `packages/natives/native/index.d.ts`\n\n## Layer ownership\n\n- **Package entrypoint** (`packages/natives/native/index.js`): loads the `.node` addon and exports generated N-API bindings.\n- **Rust N-API module layer** (`crates/pi-natives/src/*`): shell/PTY process execution, process-tree traversal/termination, and key-sequence parsing.\n- **Consumers** (`packages/coding-agent`, `packages/tui`): higher-level session policy, output artifact/minimizer handling, render policy, and UI key handling.\n\n## Shell subsystem (`shell`)\n\n### API model\n\nTwo execution modes are exposed:\n\n1. **One-shot** via `executeShell(options, onChunk?)`.\n2. **Persistent session** via `new Shell(options?)` then `shell.run(...)` repeatedly.\n\nBoth stream output through a threadsafe callback and return `{ exitCode?, cancelled, timedOut, minimized? }`.\n\n`ShellOptions` supports `sessionEnv`, `snapshotPath`, and optional output `minimizer`. `ShellExecuteOptions` supports command-scoped `env`, session-level `sessionEnv`, `snapshotPath`, timeout/signal, and optional minimizer. `ShellRunOptions` supports command, cwd, command-scoped env, timeout, and signal.\n\n### Session creation and environment model\n\nRust creates `brush_core::Shell` with:\n\n- non-interactive, non-login mode,\n- `no_profile` and `no_rc`,\n- `do_not_inherit_env: true`,\n- bash-mode builtins, with `exec` and `suspend` disabled,\n- explicit environment reconstruction from host env,\n- skip-list for shell-sensitive vars (`PS1`, `PWD`, `SHLVL`, bash function exports, etc.).\n\nSession env behavior:\n\n- `ShellOptions.sessionEnv` / one-shot `sessionEnv` is applied at session creation.\n- `ShellRunOptions.env` / one-shot `env` is command-scoped (`EnvironmentScope::Command`) and popped after the command.\n- `PATH` is merged specially on Windows with case-insensitive dedupe.\n- Windows-only path enrichment (`shell/windows.rs`) appends discovered Git-for-Windows paths when present and not already included.\n- `snapshotPath`, when present, is sourced during session creation with stdout/stderr/stdin wired to null files.\n\n### Runtime lifecycle and state transitions\n\nPersistent shell (`Shell.run`) uses this state machine:\n\n- **Idle/Uninitialized**: `session: None`.\n- **Running**: first `run()` lazily creates a session, stores an abort token, executes command.\n- **Completed + keepalive**: if execution control flow is normal, abort state is cleared and session is reused.\n- **Completed + teardown**: if control flow is loop/script/shell-exit related, session is dropped.\n- **Cancelled/Timed out**: run task is cancelled, grace wait is 2 seconds, task may be force-aborted, session is dropped if lock can be acquired.\n- **Error**: session is dropped.\n\nOne-shot shell (`executeShell`) always creates and drops a fresh session per call.\n\n### Streaming/output and minimizer behavior\n\n- Stdout/stderr are routed into a shared pipe and read concurrently.\n- Reader decodes UTF-8 incrementally; invalid byte sequences emit `U+FFFD` replacement chunks.\n- The command runs in a new process group policy.\n- Optional minimizer configuration can capture and rewrite output. When minimization occurs, the result includes `minimized` with filter name, replacement text, original text, and byte counts.\n- Consumers are responsible for persisting or displaying minimizer artifacts; the native result only carries the data.\n\n### Cancellation, timeout, and abort\n\n- `CancelToken` is constructed from `timeoutMs` and optional `AbortSignal`.\n- On cancellation/timeout, shell cancellation token is triggered, then task gets a 2-second graceful window before forced abort.\n- Structured result flags are used:\n  - timeout -> `exitCode` omitted, `timedOut: true`.\n  - abort signal / `Shell.abort()` -> `exitCode` omitted, `cancelled: true`.\n\n`Shell.abort()` behavior:\n\n- aborts the current running command for that `Shell` instance through the stored `AbortToken`,\n- resolves successfully even when nothing is running.\n\n### Failure behavior\n\nCommon surfaced errors include:\n\n- session init failures (`Failed to initialize shell`),\n- cwd errors (`Failed to set cwd`),\n- env set/pop failures,\n- snapshot source failures (`Failed to source snapshot`),\n- pipe creation/clone failures,\n- execution failure (`Shell execution failed: ...`),\n- task wrapper failures (`Shell execution task failed: ...`).\n\n## PTY subsystem (`pty`)\n\n### API model\n\n`new PtySession()` exposes:\n\n- `start(options, onChunk?) -> Promise<{ exitCode?, cancelled, timedOut }>`\n- `write(data)`\n- `resize(cols, rows)`\n- `kill()`\n\n`PtyStartOptions` supports `command`, optional `cwd`, optional `env`, `timeoutMs`, `signal`, `cols`, and `rows`.\n\n### Runtime lifecycle and state transitions\n\n`PtySession` state machine:\n\n- **Idle**: `core: None`.\n- **Reserved**: `start()` installs control channel synchronously (`core: Some`) before async work begins, so `write/resize/kill` become immediately valid.\n- **Running**: blocking PTY loop handles child state, reader events, cancellation heartbeat, and control messages.\n- **Terminal closed / drain**: child exit or cancellation starts a short reader drain window.\n- **Finalized**: `core` is always reset to `None` after start task completion (success or error).\n\nConcurrency guard:\n\n- starting while already running returns `PTY session already running`.\n\n### Spawn/attach/write/read/terminate patterns\n\n- PTY opened via `portable_pty::native_pty_system().openpty(...)`.\n- Command currently runs as `sh -lc <command>` with optional `cwd` and env overrides.\n- Default size is `120x40`; dimensions are clamped (`cols 20..400`, `rows 5..200`).\n- `write()` sends raw bytes to PTY stdin.\n- `resize()` sends a control message and clamps dimensions again.\n- `kill()` sends a control message that marks the run cancelled and terminates the child/process tree.\n\nOutput path:\n\n- dedicated reader thread reads master stream,\n- incremental UTF-8 decode emits `U+FFFD` for invalid bytes,\n- chunks forwarded through N-API threadsafe callback.\n\nTermination path:\n\n- Unix: terminate process group when known, terminate child tree, call child kill, then repeat with SIGKILL.\n- Non-Unix: terminate child tree, call child kill, then repeat with SIGKILL-equivalent process-tree helper.\n\n### Cancellation and timeout semantics\n\n- `timeoutMs` and `AbortSignal` feed a `CancelToken`.\n- Loop calls `ct.heartbeat()` periodically with a 16ms maximum wait cadence.\n- Timeout classification is based on the heartbeat error string containing `Timeout`.\n- Cancellation/kill starts a 300ms post-cancel drain window; normal child exit starts a 300ms post-exit drain window.\n\n### Failure behavior\n\nError surfaces include:\n\n- PTY allocation/open failure,\n- PTY spawn failure,\n- writer/reader acquisition failure,\n- child status/wait failures,\n- lock poisoning,\n- control-channel disconnection (`PTY session is no longer available`).\n\nControl call failures when not running:\n\n- `write/resize/kill` return `PTY session is not running`.\n\n## Process-tree subsystem (`ps`)\n\n### API model\n\n- `killTree(pid, signal) -> number`\n- `listDescendants(pid) -> number[]`\n\n### Platform-specific implementation\n\n- **Linux**: recursively reads `/proc/<pid>/task/<pid>/children`.\n- **macOS**: uses `libproc` `proc_listchildpids`.\n- **Windows**: snapshots process table with `CreateToolhelp32Snapshot`, builds parent->children map, terminates with `OpenProcess(PROCESS_TERMINATE)` + `TerminateProcess`.\n\n### Kill-tree behavior\n\n- Descendants are collected recursively.\n- Kill order is bottom-up (deepest descendants first).\n- Root pid is killed last.\n- Return value is count of successful terminations.\n\nSignal behavior:\n\n- POSIX: provided `signal` is passed to `kill`.\n- Windows: `signal` is ignored; termination is unconditional process terminate.\n\n### Failure behavior\n\nThis module is intentionally non-throwing at API surface for ordinary process misses:\n\n- missing/inaccessible process tree branches are skipped,\n- per-pid kill failures are counted as unsuccessful,\n- lookup miss typically yields `[]` from `listDescendants` and `0` from `killTree`.\n\n## Key parsing subsystem (`keys`)\n\n### API model\n\nExposed helpers:\n\n- `parseKey(data, kittyProtocolActive)`\n- `matchesKey(data, keyId, kittyProtocolActive)`\n- `parseKittySequence(data)`\n- `matchesKittySequence(data, expectedCodepoint, expectedModifier)`\n- `matchesLegacySequence(data, keyName)`\n\n### Parsing model\n\nThe parser combines:\n\n- direct single-byte mappings (`enter`, `tab`, `ctrl+<letter>`, printable ASCII),\n- O(1) legacy escape-sequence lookup (PHF map),\n- xterm `modifyOtherKeys` parsing,\n- Kitty protocol parsing (`CSI u`, `CSI ~`, `CSI 1;...<letter>`),\n- normalization to key IDs (`ctrl+c`, `shift+tab`, `pageUp`, `f5`, etc.).\n\nModifier handling:\n\n- only shift/alt/ctrl bits are compared for key matching,\n- lock bits are masked out before comparisons.\n\nLayout behavior:\n\n- base-layout fallback is intentionally constrained so remapped layouts do not create false matches for ASCII letters/symbols.\n\n### Failure behavior\n\n- Unrecognized or invalid sequences produce `null` from parse functions.\n- Match functions return `false` on parse failure or mismatch.\n- No thrown error surface for malformed key input.\n\n## JS API ↔ Rust export mapping\n\n### Shell + PTY + Process\n\n| JS API                            | Rust N-API export                      | Notes                                     |\n| --------------------------------- | -------------------------------------- | ----------------------------------------- |\n| `executeShell(options, onChunk?)` | `executeShell` (`execute_shell`)       | One-shot shell execution                  |\n| `new Shell(options?)`             | `Shell` class                          | Persistent shell session                  |\n| `shell.run(options, onChunk?)`    | `Shell::run`                           | Reuses session on keepalive control flow  |\n| `shell.abort()`                   | `Shell::abort`                         | Aborts active run for that shell instance |\n| `new PtySession()`                | `PtySession` class                     | Stateful PTY session                      |\n| `pty.start(options, onChunk?)`    | `PtySession::start`                    | Interactive PTY run                       |\n| `pty.write(data)`                 | `PtySession::write`                    | Raw stdin passthrough                     |\n| `pty.resize(cols, rows)`          | `PtySession::resize`                   | Clamped terminal dimensions               |\n| `pty.kill()`                      | `PtySession::kill`                     | Force-kills active PTY child              |\n| `killTree(pid, signal)`           | `killTree` (`kill_tree`)               | Children-first process tree termination   |\n| `listDescendants(pid)`            | `listDescendants` (`list_descendants`) | Recursive descendants listing             |\n\n### Keys\n\n| JS API                                         | Rust N-API export                                   | Notes                           |\n| ---------------------------------------------- | --------------------------------------------------- | ------------------------------- |\n| `matchesKittySequence(data, cp, mod)`          | `matchesKittySequence` (`matches_kitty_sequence`)   | Kitty codepoint+modifier match  |\n| `parseKey(data, kittyProtocolActive)`          | `parseKey` (`parse_key`)                            | Normalized key-id parser        |\n| `matchesLegacySequence(data, keyName)`         | `matchesLegacySequence` (`matches_legacy_sequence`) | Exact legacy sequence map check |\n| `parseKittySequence(data)`                     | `parseKittySequence` (`parse_kitty_sequence`)       | Structured Kitty parse result   |\n| `matchesKey(data, keyId, kittyProtocolActive)` | `matchesKey` (`matches_key`)                        | High-level key matcher          |\n\n## Abandoned session cleanup and finalization notes\n\n- **Shell persistent session**: if a run is cancelled/timed out/errors/non-keepalive control flow, Rust drops the internal session state. Successful normal runs keep the session for reuse.\n- **PTY session**: `core` is always cleared after `start()` finishes, including failure paths.\n- **No explicit JS finalizer-driven kill contract** is exposed by wrappers; cleanup is primarily tied to run completion/cancellation paths. Callers should use `timeoutMs`, `AbortSignal`, `shell.abort()`, or `pty.kill()` for deterministic teardown.\n",
 	"natives-text-search-pipeline.md": "# Natives Text/Search Pipeline\n\nThis document maps the `@sayknow-cli/natives` text/search/code surface from generated JS/TS exports to Rust N-API modules and back to JS result objects.\n\nTerminology follows `docs/natives-architecture.md`:\n\n- **Generated binding**: public API in `packages/natives/native/index.d.ts`.\n- **Rust module layer**: N-API exports in `crates/pi-natives/src/*`.\n- **Shared scan cache**: `fs_cache`-backed directory-entry cache used by discovery/search flows.\n\n## Implementation files\n\n- `packages/natives/native/index.d.ts`\n- `crates/pi-natives/src/grep.rs`\n- `crates/pi-natives/src/glob.rs`\n- `crates/pi-natives/src/glob_util.rs`\n- `crates/pi-natives/src/fs_cache.rs`\n- `crates/pi-natives/src/fd.rs`\n- `crates/pi-natives/src/ast.rs`\n- `crates/pi-natives/src/text.rs`\n- `crates/pi-natives/src/highlight.rs`\n- `crates/pi-natives/src/tokens.rs`\n\n## JS API ↔ Rust export mapping\n\n| JS API                                                                          | Rust export (`#[napi]`, snake_case -> camelCase) | Rust module    |\n| ------------------------------------------------------------------------------- | ------------------------------------------------ | -------------- |\n| `grep(options, onMatch?)`                                                       | `grep`                                           | `grep.rs`      |\n| `search(content, options)`                                                      | `search`                                         | `grep.rs`      |\n| `hasMatch(content, pattern, ignoreCase?, multiline?)`                           | `hasMatch`                                       | `grep.rs`      |\n| `fuzzyFind(options)`                                                            | `fuzzyFind`                                      | `fd.rs`        |\n| `glob(options, onMatch?)`                                                       | `glob`                                           | `glob.rs`      |\n| `invalidateFsScanCache(path?)`                                                  | `invalidateFsScanCache`                          | `fs_cache.rs`  |\n| `astGrep(options)`                                                              | `astGrep`                                        | `ast.rs`       |\n| `astEdit(options)`                                                              | `astEdit`                                        | `ast.rs`       |\n| `wrapTextWithAnsi(text, width, tabWidth)`                                       | `wrapTextWithAnsi`                               | `text.rs`      |\n| `truncateToWidth(text, maxWidth, ellipsis, pad, tabWidth)`                      | `truncateToWidth`                                | `text.rs`      |\n| `sliceWithWidth(line, startCol, length, strict, tabWidth)`                      | `sliceWithWidth`                                 | `text.rs`      |\n| `extractSegments(line, beforeEnd, afterStart, afterLen, strictAfter, tabWidth)` | `extractSegments`                                | `text.rs`      |\n| `visibleWidth(text, tabWidth)`                                                  | `visibleWidth`                                   | `text.rs`      |\n| `highlightCode(code, lang, colors)`                                             | `highlightCode`                                  | `highlight.rs` |\n| `supportsLanguage(lang)`                                                        | `supportsLanguage`                               | `highlight.rs` |\n| `getSupportedLanguages()`                                                       | `getSupportedLanguages`                          | `highlight.rs` |\n| `countTokens(input, encoding?)`                                                 | `countTokens`                                    | `tokens.rs`    |\n\n## Pipeline overview by subsystem\n\n## 1) Regex search (`grep`, `search`, `hasMatch`)\n\n### Input/options flow\n\n1. Callers invoke generated native exports directly; there is no package-local TS wrapper that renames `search` to `searchContent`.\n2. Rust option structs in `grep.rs` deserialize camelCase fields (`ignoreCase`, `maxCount`, `contextBefore`, `contextAfter`, `maxColumns`, `timeoutMs`).\n3. `grep` creates `CancelToken` from `timeoutMs` + `AbortSignal` and runs inside `task::blocking(\"grep\", ...)`.\n4. `search` and `hasMatch` operate on provided string/`Uint8Array` content and do not scan the filesystem.\n\n### Execution branches\n\n- **In-memory branch**\n  - `search` -> `search_sync` / search helpers over provided content bytes.\n  - `hasMatch` compiles/checks pattern against provided content and returns a boolean.\n  - No filesystem scan, no `fs_cache`.\n- **Single-file branch**\n  - `grep` resolves path, checks metadata is file, and searches that file.\n- **Directory branch**\n  - Optional cache lookup via `fs_cache::get_or_scan` when `cache: true`.\n  - Fresh scan via `fs_cache::force_rescan` when `cache: false`.\n  - Optional empty-result recheck when cached results are older than the empty-result recheck threshold.\n  - Entry filtering: file-only + optional glob filter (`glob_util`) + optional type filter mapping (`js`, `ts`, `rust`, etc.).\n\n### Search/collection semantics\n\n- Regex engine: `grep_regex::RegexMatcherBuilder` with `ignoreCase` and `multiline`.\n- Context resolution:\n  - `contextBefore/contextAfter` override legacy `context`.\n  - Non-content modes do not collect context.\n- Output modes:\n  - `content` -> one `GrepMatch` per hit.\n  - `count` and `filesWithMatches` map to count-style entries (`lineNumber=0`, `line=\"\"`, `matchCount` set).\n- Limits:\n  - Global `offset` and `maxCount` apply across files.\n  - Parallel path is used only when `maxCount` is unset and `offset == 0`; otherwise sequential path preserves deterministic global offset/limit semantics.\n\n### Result shaping back to JS\n\n- Rust `SearchResult`/`GrepResult` fields map to TS interfaces via N-API object conversion.\n- Counters are clamped before crossing N-API where needed.\n- `GrepResult.limitReached` is optional and emitted when true.\n- Streaming callback receives each shaped `GrepMatch` for content or count-style entries.\n\n### Failure behavior\n\n- `search` returns `SearchResult.error` for regex/search failures instead of throwing.\n- `grep` rejects on hard errors such as invalid path, invalid glob/regex, or cancellation timeout/abort.\n- `hasMatch` returns a boolean on success and throws on invalid pattern/UTF-8 conversion errors.\n- File open/search errors in multi-file scans are skipped per-file; scan continues.\n\n### Malformed regex handling\n\n`grep.rs` sanitizes braces before regex compile:\n\n- Invalid repetition-like braces are escaped (`{`/`}` -> `\\{`/`\\}`) when they cannot form `{N}`, `{N,}`, `{N,M}`.\n- This prevents common literal-template fragments (for example `${platform}`) from failing as malformed repetition.\n- Remaining invalid regex syntax still returns a regex error.\n\n## 2) File discovery (`glob`) and fuzzy path search (`fuzzyFind`)\n\n`glob` and `fuzzyFind` share `fs_cache` scans; matching logic differs.\n\n### `glob` flow\n\n1. Caller passes `GlobOptions` directly. `pattern` and `path` are required in the generated type.\n2. Rust resolves the search path and compiles pattern via `glob_util::compile_glob`.\n3. Entry source:\n   - `cache=true` -> `get_or_scan` + optional stale-empty `force_rescan`.\n   - `cache=false` -> `force_rescan(..., store=false)` (fresh only).\n4. Filtering:\n   - skip `.git` always;\n   - skip `node_modules` unless requested (`includeNodeModules`) or pattern mentions `node_modules`;\n   - apply glob match;\n   - apply file-type filter; symlink `file`/`dir` filters resolve target metadata.\n5. Optional sort by mtime descending (`sortByMtime`) before truncating to `maxResults`.\n\n### `fuzzyFind` flow\n\n1. Rust implementation lives in `fd.rs`; generated export is `fuzzyFind`.\n2. Shared scan source from `fs_cache` with the same cache/no-cache split and stale-empty recheck policy.\n3. Scoring:\n   - exact / starts-with / contains / subsequence-based fuzzy score;\n   - separator/punctuation-normalized scoring path;\n   - directory bonus and deterministic tie-break (`score desc`, then `path asc`).\n4. Symlink entries are excluded from fuzzy results.\n\n### Failure behavior\n\n- Invalid glob pattern returns an error from `glob_util::compile_glob`.\n- Search root must resolve to an existing directory for directory discovery flows.\n- Cancellation/timeouts propagate as abort errors via `CancelToken::heartbeat()` checks in loops.\n\n### Malformed glob handling\n\n`glob_util::build_glob_pattern` is tolerant:\n\n- normalizes `\\` to `/`,\n- auto-prefixes simple recursive patterns with `**/` when `recursive=true`,\n- auto-closes unbalanced `{...` alternation groups before compile.\n\n## 3) AST search/edit (`astGrep`, `astEdit`)\n\n`ast.rs` exposes syntax-aware code search and rewrite operations.\n\n- `astGrep(options)` returns matches with byte/line/column coordinates and optional metavariable bindings.\n- `astEdit(options)` returns replacement changes, per-file counts, searched/touched file counts, parse errors, and whether edits were applied.\n- `dryRun` defaults to true for edit options in the generated documentation.\n- Options include language override, path/glob/selector, strictness, limits, parse-error policy, `signal`, and `timeoutMs`.\n\nThese exports are direct native APIs used by tooling; they are not mediated by a TS wrapper in `packages/natives`.\n\n## 4) Shared scan/cache lifecycle (`fs_cache`)\n\n`fs_cache` stores scan results as normalized relative entries (`path`, `fileType`, optional `mtime`) keyed by:\n\n- canonical search root,\n- `include_hidden`,\n- `use_gitignore`.\n\n### Cache state transitions\n\n1. **Miss / disabled**\n   - TTL is `0` or key absent/expired -> fresh collection.\n2. **Hit**\n   - Entry age is within TTL -> return cached entries + `cache_age_ms`.\n3. **Stale-empty recheck**\n   - If query yields zero matches and cache age exceeds the empty-result threshold, force one rescan.\n4. **Invalidation**\n   - `invalidateFsScanCache(path?)`:\n     - no arg: clear all keys;\n     - path arg: remove keys for roots affected by that path.\n\n### Stale-result tradeoff\n\n- Cache favors low-latency repeated scans over immediate consistency.\n- TTL window can return stale positives/negatives.\n- Empty-result recheck reduces stale negatives for older cached scans at the cost of one extra scan.\n- Explicit invalidation is the intended correctness hook after file mutations.\n\n## 5) ANSI text utilities (`text`)\n\nThese are pure, in-memory utilities.\n\n### Boundaries and responsibilities\n\n- `text.rs` owns terminal-cell semantics:\n  - ANSI sequence parsing,\n  - grapheme-aware width and slicing,\n  - wrap/truncate/sanitize behavior,\n  - explicit tab-width parameter on width-sensitive APIs.\n- `grep.rs` line truncation (`maxColumns`) is separate:\n  - simple character-boundary truncation of matched lines with `...`,\n  - not ANSI-state-preserving and not terminal-cell width aware.\n\n### Key behaviors\n\n- `wrapTextWithAnsi`: wraps by visible width, carries active SGR codes across wrapped lines.\n- `truncateToWidth`: visible-cell truncation with ellipsis policy (`Unicode`, `Ascii`, `Omit`), optional right padding.\n- `sliceWithWidth`: column slicing with optional strict width enforcement.\n- `extractSegments`: extracts before/after segments around an overlay while restoring ANSI state for the `after` segment.\n- `sanitizeText` (ANSI/control/surrogate stripping with line-ending normalization) no longer lives in `text.rs`; it moved to `@sayknow-cli/utils` as a pure-JS implementation in `packages/utils/src/sanitize-text.ts`. The native binding was removed in the same change because the JS version was competitive on the benchmarked workloads, and keeping a Rust copy forced every caller (including `pi-utils`) to pull in `@sayknow-cli/natives`.\n- `visibleWidth`: counts visible terminal cells using caller-supplied tab width.\n\n### Failure behavior\n\nText functions generally return deterministic transformed output; errors are limited to N-API argument/string conversion boundaries.\n\n## 6) Syntax highlighting (`highlight`)\n\n`highlight.rs` is pure transformation; it does not use the filesystem scan cache.\n\n### Flow\n\n1. Caller passes `code`, optional `lang`, and ANSI color palette.\n2. Rust resolves syntax by token/name lookup, extension lookup, alias table fallback, then plain-text fallback.\n3. Each line is parsed with syntect `ParseState` and scope stack.\n4. Scopes map to semantic color categories and ANSI color codes are injected/reset.\n\n### Failure behavior\n\n- Per-line parse failure does not fail the call: that line is appended unhighlighted and processing continues.\n- Unknown/unsupported language falls back to plain text syntax.\n\n## 7) Token counting (`tokens`)\n\n`countTokens(input, encoding?)` is an in-memory utility.\n\n- `input` may be a single string or an array of strings.\n- Arrays return one aggregate count and are encoded in parallel in Rust.\n- Default encoding is `O200kBase`; `Cl100kBase` remains available as a compatibility alias routing to `o200k_base` in default builds.\n- The implementation uses ordinary tokenization, not special-token handling.\n\n## Pure utility vs filesystem-dependent flows\n\n| Flow                         | Filesystem access | Shared cache         | Notes                                         |\n| ---------------------------- | ----------------- | -------------------- | --------------------------------------------- |\n| `search` / `hasMatch`        | No                | No                   | regex on provided bytes/string only           |\n| `text` module functions      | No                | No                   | ANSI/width/sanitization only                  |\n| `highlight` module functions | No                | No                   | syntax + ANSI coloring only                   |\n| `countTokens`                | No                | No                   | tokenization only                             |\n| `astGrep` / `astEdit`        | Yes               | No                   | syntax-aware file search/edit                 |\n| `glob`                       | Yes               | Optional             | directory scans + glob filtering              |\n| `fuzzyFind`                  | Yes               | Optional             | directory scans + fuzzy scoring               |\n| `grep` (file/dir path)       | Yes               | Optional in dir mode | ripgrep over files, optional filters/callback |\n\n## End-to-end lifecycle summary\n\n1. Caller invokes generated native export with typed options.\n2. Rust validates/normalizes options and builds matcher/search config.\n3. For filesystem flows, entries are scanned (cache hit/miss/rescan where applicable) then filtered/scored/searched.\n4. Worker loops periodically call cancel heartbeat; timeout/abort can terminate execution.\n5. Rust shapes outputs into N-API objects (`lineNumber`, `matchCount`, `limitReached`, etc.).\n6. Generated bindings return typed JS objects and optional per-match callbacks for `grep`/`glob`.\n",
 	"non-compaction-retry-policy.md": "# Non-compaction auto-retry policy\n\nThis document describes the standard API-error retry path in `AgentSession`.\n\nIt explicitly excludes context-overflow recovery via auto-compaction. Overflow is handled by compaction logic and is documented separately in [`compaction.md`](../docs/compaction.md).\n\n## Implementation files\n\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`../src/config/settings-schema.ts`](../packages/coding-agent/src/config/settings-schema.ts)\n- [`../src/modes/controllers/event-controller.ts`](../packages/coding-agent/src/modes/controllers/event-controller.ts)\n- [`../src/modes/rpc/rpc-mode.ts`](../packages/coding-agent/src/modes/rpc/rpc-mode.ts)\n- [`../src/modes/rpc/rpc-client.ts`](../packages/coding-agent/src/modes/rpc/rpc-client.ts)\n- [`../src/modes/rpc/rpc-types.ts`](../packages/coding-agent/src/modes/rpc/rpc-types.ts)\n\n## Scope boundary vs compaction\n\nRetry and compaction are checked from the same `agent_end` path, but they are intentionally separated:\n\n1. `agent_end` inspects the last assistant message.\n2. `#isRetryableError(...)` runs first.\n3. If retry is initiated, compaction checks are skipped for that turn.\n4. Context-overflow errors are hard-excluded from retry classification (`isContextOverflow(...)` short-circuits retry).\n5. Overflow therefore falls through to `#checkCompaction(...)` instead of standard retry.\n\nSo: overload/rate/server/network-style failures use this retry policy; context-window overflow uses compaction recovery.\n\n## Retry classification\n\n`#isRetryableError(...)` requires all of the following:\n\n- assistant `stopReason === \"error\"`\n- `errorMessage` exists\n- message is **not** context overflow\n- `errorMessage` matches transient transport/envelope patterns or `isUsageLimitError(...)`\n\nCurrent retryable inputs are regex/string-classified:\n\n- transient transport/envelope failures, including Anthropic stream-envelope failures before `message_start`\n- overloaded/provider-returned-error wording\n- rate limit / usage limit / too many requests\n- HTTP-like server classes: 429, 500, 502, 503, 504\n- service unavailable / server/internal error\n- provider-suggested retry wording, including OpenAI `retry your request` failures\n- network/connection/socket failures, refused/closed connections, upstream connect/reset-before-headers, socket hang up, timeout/timed out, fetch failed, terminated, retry delay wording, and unexpected socket close messages\n\nThis is string-pattern classification, not typed provider error codes.\n\n## Retry lifecycle and state transitions\n\nSession state used by retry:\n\n- `#retryAttempt: number` (`0` means idle)\n- `#retryPromise: Promise<void> | undefined` (tracks in-progress retry lifecycle)\n- `#retryResolve: (() => void) | undefined` (resolves `#retryPromise`)\n- `#retryAbortController: AbortController | undefined` (cancels backoff sleep)\n\nFlow (`#handleRetryableError`):\n\n1. Read `retry` settings group.\n2. If `retry.enabled === false`, stop immediately (`false`, no retry started).\n3. Increment `#retryAttempt`.\n4. Create `#retryPromise` once (first attempt in a chain).\n5. If attempt exceeded `retry.maxRetries`, emit final failure event and stop.\n6. Compute base delay: `retry.baseDelayMs * 2^(attempt-1)`.\n7. For usage-limit errors, parse retry hints and call auth storage (`markUsageLimitReached(...)`); if credential switching succeeds, force delay to `0`, otherwise use a larger retry-after/backoff hint when present.\n8. If no credential switch occurred, suppress the current model selector for cooldown, try configured retry model fallback chains, and force delay to `0` on model switch.\n9. Emit `auto_retry_start`.\n10. Remove the trailing assistant error message from agent runtime state (kept in persisted session history).\n11. Sleep with abort support.\n12. Schedule `agent.continue()` through the post-prompt task scheduler (`delayMs: 1`) for the same prompt generation.\n\n### What resets retry counters\n\n`#retryAttempt` resets to `0` in these cases:\n\n- first successful non-error, non-aborted assistant message after retries started (emits `auto_retry_end { success: true }`)\n- retry cancellation during backoff sleep\n- max retries exceeded path\n\n`#retryPromise` resolves/clears when retry chain ends (success, cancellation, or max-exceeded), via `#resolveRetry()`.\n\n## Backoff and max-attempt semantics\n\nSettings:\n\n- `retry.enabled` (default `true`)\n- `retry.maxRetries` (default `3`)\n- `retry.baseDelayMs` (default `2000`)\n- `retry.maxDelayMs` (default `300000`)\n- `retry.requestMaxRetries` (default `5`) — provider request retries before a stream is established; counts retries, not the initial request\n- `retry.streamMaxRetries` (default `5`) — provider stream replay retries for replay-safe transient stream failures; counts retries, not the initial stream attempt\n\nAttempt numbering:\n\n- attempt counter is incremented before max-check\n- start events use current attempt (1-based)\n- max-exceeded end event reports `attempt: this.#retryAttempt - 1` (last attempted retry count)\n\nBackoff sequence with default settings:\n\n- attempt 1: 2000 ms\n- attempt 2: 4000 ms\n- attempt 3: 8000 ms\n\nDelay override inputs can come from parsed retry headers (`retry-after-ms`, `retry-after`, `x-ratelimit-reset-ms`, `x-ratelimit-reset`) or usage-limit backoff. Credential/model fallback switches set delay to `0`; otherwise parsed hints can extend the exponential local delay.\n\n## Abort mechanics\n\n### Explicit retry abort\n\n`abortRetry()`:\n\n- aborts `#retryAbortController` (if present)\n- resolves retry promise (`#resolveRetry()`) so awaiters are unblocked\n\nIf abort hits while sleeping, catch path emits:\n\n- `auto_retry_end { success: false, finalError: \"Retry cancelled\" }`\n- resets attempt/controller\n\n### Global operation abort interaction\n\n`abort()` calls `abortRetry()` before aborting the active agent stream. This guarantees retry backoff is cancelled when user issues a general abort.\n\n### TUI interaction\n\nOn `auto_retry_start`, EventController:\n\n- swaps `Esc` handler to `session.abortRetry()`\n- renders loader text: `Retrying (attempt/maxAttempts) in Ns… (esc to cancel)`\n\nOn `auto_retry_end`, it restores prior `Esc` handler and clears loader state.\n\n## Streaming and prompt completion behavior\n\n`prompt()` ultimately waits on `#waitForRetry()` after `agent.prompt(...)` returns.\n\nEffect:\n\n- a prompt call does not fully resolve until any started retry chain finishes (success/failure/cancel)\n- retry lifecycle is part of one logical prompt execution boundary\n\nThis prevents callers from treating a retrying turn as complete too early.\n\n## Controls: settings and RPC\n\n### Configuration knobs\n\nDefined in settings schema under retry group:\n\n- `retry.enabled`\n- `retry.maxRetries`\n- `retry.baseDelayMs`\n- `retry.fallbackChains`\n- `retry.fallbackRevertPolicy` (`\"cooldown-expiry\"` by default; `\"never\"` disables automatic restoration)\n\nProgrammatic toggles in session:\n\n- `setAutoRetryEnabled(enabled)` writes `retry.enabled`\n- `autoRetryEnabled` reads `retry.enabled`\n- `isRetrying` reports whether retry lifecycle promise is active\n\n### RPC controls\n\nRPC command surface:\n\n- `set_auto_retry` → `session.setAutoRetryEnabled(command.enabled)`\n- `abort_retry` → `session.abortRetry()`\n\nClient helpers:\n\n- `RpcClient.setAutoRetry(enabled)`\n- `RpcClient.abortRetry()`\n\nBoth commands return success responses; retry progress/failure details come from streamed session events, not command response payloads.\n\n## Event emission and failure surfacing\n\nSession-level retry events:\n\n- `auto_retry_start { attempt, maxAttempts, delayMs, errorMessage }`\n- `auto_retry_end { success, attempt, finalError? }`\n- `retry_fallback_applied { from, to, role }`\n- `retry_fallback_succeeded { model, role }`\n\nPropagation:\n\n- emitted through `AgentSession.subscribe(...)`\n- forwarded to extension runner as extension events\n- in RPC mode, forwarded directly as JSON event objects (`session.subscribe(event => output(event))`)\n- in TUI, consumed by `EventController` for loader/error UI\n\nFinal failure surfacing:\n\n- On max-exceeded or cancellation, `auto_retry_end.success === false`\n- TUI shows: `Retry failed after N attempts: <finalError>`\n- Extensions/hooks receive `auto_retry_end` with same fields\n- RPC consumers receive same event object on stdout stream\n\n## Permanent stop conditions\n\nRetry stops and will not auto-continue when any of these occur:\n\n- `retry.enabled` is false\n- error is not retry-classified\n- error is context overflow (delegated to compaction path)\n- max retries exceeded\n- user cancels retry (`abort_retry` or `Esc` during retry loader)\n- global abort (`abort`) cancels retry first\n\nA new retry chain can still start later on a future retryable error after counters reset.\n\n## Operational caveats\n\n- Classification is regex text matching; provider-specific structured errors are not used here.\n- Retry strips the failing assistant error from **runtime context** before re-continue, but session history still keeps that error entry.\n- `RpcSessionState` currently exposes `autoCompactionEnabled` but not an `autoRetryEnabled` field; RPC callers must track their own toggle state or query settings through other APIs.\n- Model fallback changes append temporary `model_change` entries and may later restore the primary model when its cooldown expires, depending on `retry.fallbackRevertPolicy`.\n\n## Provider request/stream retry budgets\n\nThe provider budgets are deliberately separate from session auto-retry:\n\n```yaml\nretry:\n  requestMaxRetries: 4\n  streamMaxRetries: 100\n```\n\n`requestMaxRetries` maps to provider SDK/fetch retry counts for request setup failures such as retryable 5xx/408/429/network errors. `streamMaxRetries` maps to provider-specific stream replay loops that are safe to repeat without duplicating visible assistant output. Providers that cannot safely replay a stream continue to surface the terminal error so the session-level auto-retry layer can decide whether to retry the turn.\n\nFail-fast cases stay fail-fast: invalid credentials (after any credential-refresh path is exhausted), unsupported model/provider configuration, malformed requests, context overflow, explicit user aborts, and permanent quota failures are not treated as transient provider budget candidates.\n",
 	"notebook-tool-runtime.md": "# Notebook tool runtime internals\n\nThis document describes the current `notebook` tool implementation and its relationship to the kernel-backed Python runtime.\n\nThe critical distinction: **`notebook` is a JSON notebook editor, not a notebook executor**. It edits `.ipynb` cell sources directly; it does not start or talk to a Python kernel.\n\n## Implementation files\n\n- [`src/tools/notebook.ts`](../packages/coding-agent/src/tools/notebook.ts)\n- [`src/eval/py/executor.ts`](../packages/coding-agent/src/eval/py/executor.ts)\n- [`src/eval/py/kernel.ts`](../packages/coding-agent/src/eval/py/kernel.ts)\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts)\n- [`src/tools/eval.ts`](../packages/coding-agent/src/tools/eval.ts)\n\n## 1) Runtime boundary: editing vs executing\n\n## `notebook` tool (`src/tools/notebook.ts`)\n\n- Supports `action: edit | insert | delete` on a `.ipynb` file.\n- Resolves path relative to session CWD (`resolveToCwd`).\n- Loads notebook JSON, validates `cells` array, validates `cell_index` bounds.\n- Applies source edits in-memory and writes full notebook JSON back with `JSON.stringify(notebook, null, 1)`.\n- Returns textual summary + structured `details` (`action`, `cellIndex`, `cellType`, `totalCells`, `cellSource`).\n\nNo kernel lifecycle exists in this tool:\n\n- no gateway acquisition\n- no kernel session ID\n- no `execute_request`\n- no stream chunks from kernel channels\n- no rich display capture (`image/png`, JSON display, status MIME)\n\n## Notebook-like execution path (`src/tools/eval.ts` + `src/eval/py/*`)\n\nWhen the agent needs to run cell-style Python code (sequential cells, persistent state, rich displays), that goes through the **`eval` tool** with `language: \"python\"`, not `notebook`.\n\nThat path is where kernel modes, restart/cancel behavior, chunk streaming, and output artifact truncation live.\n\n## 2) Notebook cell handling semantics (`notebook` tool)\n\n## Source normalization\n\n`content` is split into `source: string[]` with newline preservation:\n\n- each non-final line keeps trailing `\\n`\n- final line has no forced trailing newline\n\nThis mirrors notebook JSON conventions and avoids accidental line concatenation on later edits.\n\n## Action behavior\n\n- `edit`\n  - replaces `cells[cell_index].source`\n  - preserves existing `cell_type`\n- `insert`\n  - inserts at `[0..cellCount]`\n  - `cell_type` defaults to `code`\n  - code cells initialize `execution_count: null` and `outputs: []`\n  - markdown cells initialize only `metadata` + `source`\n- `delete`\n  - removes `cells[cell_index]`\n  - returns removed `source` in details for renderer preview\n\n## Error surfaces\n\nHard failures are thrown for:\n\n- missing notebook file\n- invalid JSON\n- missing/non-array `cells`\n- out-of-range index (insert and non-insert have different valid ranges)\n- missing `content` for `edit`/`insert`\n\nThese become `Error:` tool responses upstream; renderer uses notebook path + formatted error text.\n\n## 3) Kernel session semantics (where they actually exist)\n\nKernel semantics are implemented in `executePython` / `PythonKernel` and apply to the Python backend of the `eval` tool.\n\n## Modes\n\n`PythonKernelMode`:\n\n- `session` (default)\n  - kernels cached in `kernelSessions` map\n  - max 4 sessions; oldest evicted on overflow\n  - idle/dead cleanup every 30s, timeout after 5 minutes\n  - per-session queue serializes execution (`session.queue`)\n- `per-call`\n  - creates kernel for request\n  - executes\n  - always shuts down kernel in `finally`\n\n## Reset behavior\n\n`eval` passes `reset` only for the first cell in a multi-cell Python call; later cells always run with `reset: false`.\n\n## Kernel death / restart / retry\n\nIn session mode (`withKernelSession`):\n\n- dead kernel detected by heartbeat (`kernel.isAlive()` check every 5s) or execute failure.\n- pre-run dead state triggers `restartKernelSession`.\n- execute-time crash path retries once: restart kernel, rerun handler.\n- `restartCount > 1` in same session throws `Python kernel restarted too many times in this session`.\n\nStartup retry behavior:\n\n- shared gateway kernel creation retries once on `SharedGatewayCreateError` with HTTP 5xx.\n\nResource exhaustion recovery:\n\n- detects `EMFILE`/`ENFILE`/\"Too many open files\" style failures\n- clears tracked sessions\n- calls `shutdownSharedGateway()`\n- retries kernel session creation once\n\n## 4) Environment/session variable injection\n\nKernel startup receives the optional session file path from executor:\n\n- `SKC_SESSION_FILE` (session state file path)\n\n`PythonKernel.#initializeKernelEnvironment(...)` then runs init script inside kernel to:\n\n- `os.chdir(cwd)`\n- inject env entries into `os.environ`\n- prepend cwd to `sys.path` if missing\n\nImplication:\n\n- prelude helpers that read session context rely on this env var in Python process state.\n\n## 5) Streaming/chunk and display handling (kernel-backed path)\n\nThe kernel client processes Jupyter protocol messages per execution:\n\n- `stream` -> text chunk to `onChunk`\n- `execute_result` / `display_data` ->\n  - display text chosen by MIME precedence: `text/markdown` > `text/plain` > converted `text/html`\n  - structured outputs captured separately:\n    - `application/json` -> `{ type: \"json\" }`\n    - `image/png` -> `{ type: \"image\" }`\n    - `application/x-skc-status` -> `{ type: \"status\" }` (no text emission)\n- `error` -> traceback text pushed to chunk stream + structured error metadata\n- `input_request` -> emits stdin warning text, sends empty `input_reply`, marks stdin requested\n- completion waits for both `execute_reply` and kernel `status=idle`\n\nCancellation/timeout:\n\n- abort signal triggers `interrupt()` (REST `/interrupt` + control-channel `interrupt_request`)\n- result marks `cancelled=true`\n- timeout path annotates output with `Command timed out after <n> seconds`\n\n## 6) Truncation and artifact behavior\n\n`OutputSink` in `src/session/streaming-output.ts` is used by kernel execution paths (`executeWithKernel`):\n\n- sanitizes every chunk (`sanitizeText`)\n- tracks total/output lines and bytes\n- optional artifact spill file (`artifactPath`, `artifactId`)\n- when in-memory buffer exceeds threshold (`DEFAULT_MAX_BYTES` unless overridden):\n  - marks truncated\n  - keeps tail bytes in memory (UTF-8 safe boundary)\n  - can spill full stream to artifact sink\n\n`dump()` returns:\n\n- visible output text (possibly tail-truncated)\n- truncation flag + counts\n- artifact ID (for `artifact://<id>` references)\n\n`eval` converts this metadata into result truncation notices and TUI warnings.\n\n`notebook` tool does **not** use `OutputSink`; it has no stream/artifact truncation pipeline because it does not execute code.\n\n## 7) Renderer assumptions and formatting\n\n## Notebook renderer (`notebookToolRenderer`)\n\n- call view: status line with action + notebook path + cell/type metadata\n- result view:\n  - success summary derived from `details`\n  - `cellSource` rendered via `renderCodeCell`\n  - markdown cells set language hint `markdown`; other cells have no explicit language override\n  - collapsed code preview limit is `PREVIEW_LIMITS.COLLAPSED_LINES * 2`\n  - supports expanded mode via shared render options\n  - uses render cache keyed by width + expanded state\n\nError rendering assumption:\n\n- if first text content starts with `Error:`, renderer formats as notebook error block.\n\n## Python renderer (for actual execution output)\n\nKernel-backed execution rendering expects:\n\n- per-cell status transitions (`pending/running/complete/error`)\n- optional structured status event section\n- optional JSON output trees\n- truncation warnings + optional `artifact://<id>` pointer\n\nThis renderer behavior is unrelated to `notebook` JSON editing results except that both reuse shared TUI primitives.\n\n## 8) Divergence from eval Python backend behavior\n\nIf \"plain Python execution\" means the `eval` tool with `language: \"python\"`:\n\n- `eval` executes code in a kernel, persists state by mode, streams chunks, captures rich displays, handles interrupts/timeouts, and supports output truncation/artifacts.\n- `notebook` performs deterministic notebook JSON mutations only; no execution, no kernel state, no chunk stream, no display outputs, no artifact pipeline.\n\nIf a workflow needs both:\n\n1. edit notebook source with `notebook`\n2. execute code cells via `eval` with `language: \"python\"` (manually passing code), not through `notebook`\n\nCurrent implementation does not provide a single tool that both mutates `.ipynb` and executes notebook cells through kernel context.\n",
-	"notifications-sdk.md": "# Notifications SDK\n\n<p align=\"center\">\n  <img src=\"../assets/telegram-mobile-hero.png\" alt=\"Sayknow-CLI 0.7.0 mobile answers for coding agents hero illustration\" width=\"100%\" />\n</p>\n\nA small, transport-agnostic way to get **action-needed** signals out of a SKC\nsession and deliver **replies** back — without scraping the terminal and without\nthe depth of the RPC / Coordinator / Bridge surfaces.\n\nThe stable contract is deliberately generic: every running session exposes one\nloopback WebSocket endpoint, and integrations are user-written clients that\nconnect to that endpoint. Telegram, Discord, Slack, mobile apps, and local tools\nall use the same JSON protocol. No upstream Rust, N-API, or wire-protocol change\nis required for a new integration.\n\n> Status: the Rust core (`crates/skc-notifications`) provides the wire protocol,\n> action lifecycle, loopback WebSocket server, and endpoint discovery file. The\n> bundled Telegram daemon is a reference client layered on top of this SDK; it is\n> not the upstream topology.\n\n## Architecture\n\n```\nSKC session (upstream)                          your client (anywhere)\n┌───────────────────────────────┐               ┌──────────────────────────┐\n│ ask-tool fires / agent idle    │  action_needed │ Telegram / Discord / ... │\n│   → notifications core         │ ─────────────▶ │  render + collect reply  │\n│ ws://127.0.0.1:<port> (+token) │ ◀───────────── │                          │\n│   reply → resolve ask gate     │     reply       │                          │\n└───────────────────────────────┘               └──────────────────────────┘\n```\n\n- **One endpoint per session.** Each session runs its own loopback WebSocket\n  server. Upstream does not maintain a shared daemon, singleton, or\n  chat-to-session registry; multiplexing many sessions into one integration is a\n  client-side concern.\n- **Integrations are clients.** A client discovers endpoint files, connects to\n  one or more WebSockets, renders `action_needed`, and sends `reply` messages.\n- **Zero upstream change.** New transports do not require changes to\n  `crates/skc-notifications` or the JSON protocol.\n- **Off unless configured.** No endpoint exists unless notifications are enabled\n  and a token is present.\n- **tmux-agnostic.** The endpoint behaves identically with or without tmux.\n\n## Endpoint discovery\n\nA running session writes a discovery file at:\n\n```\n<repo>/.skc/state/notifications/<sessionId>.json\n```\n\n(`.skc/state/` is git-ignored.) Shape:\n\n```json\n{\n  \"version\": 1,\n  \"sessionId\": \"019edd41-...\",\n  \"pid\": 12345,\n  \"host\": \"127.0.0.1\",\n  \"port\": 53124,\n  \"url\": \"ws://127.0.0.1:53124\",\n  \"token\": \"<per-session token>\",\n  \"startedAt\": 1718760000000,\n  \"updatedAt\": 1718760000000,\n  \"stale\": false\n}\n```\n\n- The file is created `0700`/`0600` (unix) and written atomically.\n- The **token is in the file** because clients need it; never log it raw.\n  Stale files (dead PID, past TTL, or explicitly marked) are cleaned up on the\n  next start.\n\nConnect with the token as a query parameter:\n\n```\nws://127.0.0.1:<port>/?token=<token>\n```\n\nA wrong/missing token is rejected at the handshake with HTTP `401`.\n\n## Protocol\n\nJSON text frames. Field names are `camelCase`; the `type` discriminator is\n`snake_case`.\n\n### Server → client\n\n`action_needed` — something needs attention:\n\n```json\n{ \"type\": \"action_needed\", \"id\": \"wg_run_stage_1\", \"kind\": \"ask\",\n  \"sessionId\": \"sess-1\", \"question\": \"Proceed?\", \"options\": [\"Yes\", \"No\"] }\n```\n\n```json\n{ \"type\": \"action_needed\", \"id\": \"idle-sess-1-7\", \"kind\": \"idle\",\n  \"sessionId\": \"sess-1\", \"summary\": \"finished refactor; awaiting next step\" }\n```\n\n- `kind: \"ask\"` is answerable in both interactive/TUI and unattended/RPC modes.\n  The `id` is the real workflow-gate id.\n- `kind: \"idle\"` is notify-only and ephemeral (not replayed to clients that\n  connect later).\n\n`action_resolved` — a pending action is now terminal and **non-repliable**:\n\n```json\n{ \"type\": \"action_resolved\", \"id\": \"wg_run_stage_1\", \"resolvedBy\": \"local\" }\n```\n\n`resolvedBy` is `local` (answered in the CLI/TUI), `client` (a remote reply won),\nor `timeout`.\n\n`reply_rejected` — sent only to the client whose reply failed:\n\n```json\n{ \"type\": \"reply_rejected\", \"id\": \"wg_run_stage_1\", \"reason\": \"already_answered\" }\n```\n\nReasons: `already_answered`, `unknown_action`, `invalid_answer`,\n`resolver_unavailable`, `idempotency_conflict`, `unauthorized`.\n\nThe frames above are the minimal contract every client implements. Threaded\nclients (like the managed Telegram daemon) may also receive optional\nserver → client frames they can render or ignore: `identity_header` (one-time\nper-session repo/branch/machine header), `context_update` (last message, task,\ngoal, token usage, model, diff), `turn_stream` (live/finalized turn output),\n`image_attachment` (agent-produced images), `activity` (busy/idle, drives the\ntyping indicator), `inbound_ack` (delivery state of an injected user message),\n`session_closed` (endpoint teardown; threaded clients may delete/archive the\nremote conversation), `config_update` (current verbosity/redact), `hello`\n(server capability/version), and `pong`. A minimal client only needs\n`action_needed`, `action_resolved`, and `reply_rejected`.\n\n### Client → server\n\n`reply` — answer a pending `ask`:\n\n```json\n{ \"type\": \"reply\", \"id\": \"wg_run_stage_1\", \"answer\": 0, \"token\": \"<token>\" }\n```\n\n`answer` accepts:\n\n- a number — zero-based option index (`0` = first option);\n- a string — an option label, or free text;\n- an object — `{ \"selected\": [0, \"Maybe\"], \"custom\": \"...\" }` for multi-select.\n\nOptional `idempotencyKey` makes retries safe: the same key + same body re-acks;\nthe same key + different body is rejected with `idempotency_conflict`.\n\nThreaded clients may also send optional client → server frames: `user_message`\n(inject/steer a turn with free text), `config_command` (toggle verbosity/redact\nin-thread), `hello` (capability/version), and `ping`. A minimal client only\nneeds `reply`.\n\n## Answer semantics\n\nA remote reply answers a pending ask in **both** modes — RPC is not required:\n\n- **Interactive / TUI mode:** the ask tool races the local selector against the\n  remote reply (first valid answer wins). If you tap a button in the client, the\n  ask resolves with that option; if you answer locally, the client receives\n  `action_resolved` (`resolvedBy: \"local\"`) and the action becomes non-repliable.\n- **Unattended / RPC mode:** the reply resolves the real workflow-gate, driving\n  the session the same way a local answer would.\n\nIn both modes the first valid reply wins; later replies get `already_answered`.\nIdle pings are notify-only.\n\n## Minimal client example\n\n```js\nimport { readFileSync } from \"node:fs\";\nimport WebSocket from \"ws\";\n\nconst { url, token } = JSON.parse(\n  readFileSync(`.skc/state/notifications/${sessionId}.json`, \"utf8\"),\n);\n\nconst ws = new WebSocket(`${url}/?token=${encodeURIComponent(token)}`);\n\nws.on(\"message\", (data) => {\n  const msg = JSON.parse(data.toString());\n  if (msg.type === \"action_needed\" && msg.kind === \"ask\") {\n    // present msg.question / msg.options to the human, then:\n    ws.send(JSON.stringify({ type: \"reply\", id: msg.id, answer: 0, token }));\n  } else if (msg.type === \"action_resolved\") {\n    // mark this action as no longer answerable in your UI\n  } else if (msg.type === \"reply_rejected\") {\n    // e.g. reason === \"already_answered\" → the ask was answered elsewhere\n  }\n});\n```\n\nSwap `ws` for a Telegram bot's long-poll loop, a Discord gateway client, or a\nSlack socket-mode app — the contract above is all you implement.\n\n## Managed notification adapters\n\nFor the exact user setup flow (`skc notify setup`, BotFather token, private-chat pairing, status, and troubleshooting), see [Telegram notification onboarding](./telegram-onboarding.md).\n\n## Managed Telegram daemon (bundled reference client)\n\nSKC also ships a managed Telegram reference client for the common phone-notify\nworkflow. It remains a client of the generic SDK: it scans session discovery\nfiles, opens each session WebSocket, and routes Telegram replies back to the\nmatching endpoint.\n\nThe daemon/session engine is shared. Session discovery, WebSocket protocol,\nredaction decisions, rate-limit pooling, reply routing, singleton ownership, and\nlifecycle control are not reimplemented by each chat surface. Telegram, Discord,\nand Slack adapters are thin presentation layers: they render internal notification\nevents into transport payloads and map transport interactions back to `{sessionId,\nactionId,answer}` replies.\n\n### Setup and auto-connect\n\nRun the setup command once:\n\n```sh\nskc notify setup\n```\n\nThe wizard validates the bot token with Telegram, verifies private-chat Threaded\nMode capability via `getMe.has_topics_enabled`, waits for a private DM to the bot,\nand writes canonical global Settings under `config.yml` in the SKC agent\ndirectory. It enables:\n\n- `notifications.enabled`\n- `notifications.telegram.botToken`\n- `notifications.telegram.chatId`\n- `notifications.redact` (optional; default false)\n- `notifications.discord.botToken` / `notifications.discord.channelId` (optional Discord adapter)\n- `notifications.slack.botToken` / `notifications.slack.channelId` (optional Slack adapter)\n\nAfter setup, sessions auto-connect when notifications are enabled. Each session\nstill publishes its own loopback endpoint; the daemon is only the Telegram-side\nmultiplexer.\n\nFor Telegram forum topics, the daemon deletes the per-session topic when the local\nnotification endpoint shuts down, so it disappears from the topic list. A resumed\nsession creates a fresh topic before sending again. The bot must be allowed to\ndelete messages in that chat; without that permission, deletion is best-effort and\ndelivery continues.\n\n### Singleton poller and trust model\n\nTelegram `getUpdates` allows only one active long-poll owner per bot token. The\nmanaged daemon enforces **one bot token = one getUpdates poller** with a local\nlock/state file under the agent directory. New sessions attach to the existing\nfresh daemon owner instead of starting another poller, preventing Telegram 409\nconflicts.\n\nThe trust model is intentionally strict:\n\n- setup pairs exactly one private Telegram chat;\n- runtime accepts updates only from that paired chat id;\n- groups, supergroups, channels, and unpaired users never receive session names,\n  action ids, pending status, or configuration hints;\n- daemon state stores a token fingerprint, not the raw bot token.\n\n### Routing in private-chat topics\n\nThe paired private chat prefers per-session Telegram topics (Threaded Mode). The\ndaemon tags messages by session, stores compact callback aliases for inline\nbuttons, and routes replies back to the exact session/action. A forum-enabled\nsupergroup is no longer required: when the bot owner enables Threaded Mode in\n@BotFather, the daemon creates one topic per session in the paired private chat.\nSKC cannot enable Threaded Mode through the Bot API; setup only verifies the\ncapability and guides the manual BotFather toggle.\n\nIf BotFather's per-bot **Bot Settings** menu does not show **Threads Settings**\nor **Threaded Mode**, the supported fallback is the normal private-chat pairing.\nSetup can be saved as `threaded=unverified`/`threaded=unknown`, and the daemon\nstill tries topics when Telegram allows them. When `createForumTopic` is refused,\nthe daemon does not drop the send: it routes the notification to the normal\n(flat) paired private chat and posts a one-time `turn on threaded mode from\nbotfather miniapp to receive skc notification!` nudge. Pairing is private-only,\nso flat delivery stays within the user's own private DM.\n\nSupported reply paths:\n\n- tap an inline button on an ask notification;\n- reply inside the session's thread/topic (replies are thread-native; the\n  topic identifies the session, so no session tag is needed).\n\nIn threaded mode the user can also adjust per-session behaviour with in-thread\nconfig commands: `/verbose`, `/lean`, `/verbosity <lean|verbose>`, and\n`/redact <on|off>`. The legacy `/answer <session-tag> <answer>` command is\nremoved — replies are routed by the topic they arrive in.\n\nFlat fallback keeps outbound notifications and inline-button answers working,\nbut free-text replies and `/verbose`/`/lean`/`/verbosity`/`/redact` commands are\nthread-native and require topic routing. Do not pair a group, supergroup, or\nchannel to work around a missing BotFather menu; the bundled setup flow is\nprivate-chat only, and non-private chat ids remain fail-closed to avoid session\ndata leaks.\n\nUnknown, expired, or restart-unvalidated callback aliases fail closed: the daemon\nsends guidance and does not guess a target session or action.\n\n### Discord and Slack setup\n\nDiscord and Slack use the same internal notification events and reply protocol as\nTelegram. Store only runtime credentials in local SKC settings or environment;\nnever paste bot tokens, webhook URLs, transcripts, prompts, host paths, or raw logs\ninto docs, tests, issues, or PR comments.\n\nConfiguration keys:\n\n```yaml\nnotifications:\n  enabled: true\n  discord:\n    botToken: \"<local Discord bot token>\"\n    channelId: \"<Discord channel id>\"\n  slack:\n    botToken: \"<local Slack bot token>\"\n    channelId: \"<Slack channel id>\"\n  redact: true\n```\n\nThe bundled adapters intentionally render public-safe message bodies and return\nroute metadata only for pending internal actions. They do not own polling,\nsession scans, daemon locks, rate limits, or SDK lifecycle. Production transport\nsenders should consume the adapter payloads and keep all credential-bearing HTTP\nor gateway details outside logged payloads.\n### Redaction\n\n`notifications.redact` strips sensitive content before remote delivery, but\n**asks are exempt**: an ask is an interactive prompt the human must read and\nanswer remotely, so its `question` and `options` are always sent unredacted\n(otherwise it would be unanswerable). When redaction is enabled, `idle`\nsummaries are removed and streamed content frames (`turn_stream`,\n`context_update`, `image_attachment`) are suppressed at their emit sites. When\nredaction is disabled, all content is delivered unchanged.\n\n### Local `/notify`\n\nInside a SKC session, `/notify` controls the current session only:\n\n- `/notify status` reports enabled/disabled state, daemon observation when known,\n  and redaction state without printing secrets;\n- `/notify off` disables the current session's notification endpoint and removes\n  its discovery record without mutating global Settings;\n- `/notify on` re-enables the current session when global setup is complete and\n  `SKC_NOTIFICATIONS=0` is not forcing opt-out.\n\n### Manual Telegram CLI is for debugging\n\n`packages/coding-agent/src/notifications/telegram-cli.ts` remains as a manual\nreference/debug client and template for other integrations. It is not the primary\nTelegram UX.\n\n```sh\nbun run packages/coding-agent/src/notifications/telegram-cli.ts --bot-token \"$BOT_TOKEN\"\n```\n\nBy default it refuses to start when a fresh managed daemon already owns the same\nbot token for the same paired chat, because a second poller will cause Telegram\n409 conflicts. Use `--force` only for deliberate debugging when you have stopped\nor intentionally want to override the daemon guard.\n## Two client surfaces: per-session vs daemon-owned lifecycle control\n\nThe SDK now exposes **two distinct surfaces**. Do not confuse them:\n\n1. **Per-session notification clients (the normal, documented contract above).**\n   A client discovers `<repo>/.skc/state/notifications/<sessionId>.json`, connects\n   to that session's loopback WebSocket, and handles `action_needed`,\n   `action_resolved`, `reply_rejected`, and the optional threaded frames. This is\n   all an ordinary integration (Telegram, Discord, Slack, mobile, local tools)\n   needs. It requires **zero** upstream changes.\n\n2. **The daemon-owned session *lifecycle* control endpoint (privileged).**\n   A separate, **session-independent**, loopback-only, authenticated control\n   endpoint that accepts `session_create` / `session_close` / `session_resume`\n   frames. It exists because creating a session cannot use a per-session socket\n   (none exists before the session does). It is **not** part of the normal\n   integration contract: ordinary clients never implement it. Only the bundled,\n   trusted daemon (e.g. the managed Telegram daemon) speaks it.\n\n### Lifecycle control endpoint\n\n- **Discovery:** `<agentDir>/notifications/control.json` (daemon-owned, mode\n  `0600`), distinct from per-session endpoint files. It carries only non-secret\n  endpoint metadata (url/host/port/pid/owner). The control token is held **in\n  memory** by the daemon (the sole client) and is **never** written to disk.\n- **Auth:** loopback-only bind (a non-loopback bind is refused). The WebSocket\n  upgrade requires `?token=<control-token>` (HTTP `401` otherwise), and every\n  lifecycle frame's `token` is re-checked (`unauthorized` on mismatch). The Rust\n  ingress authenticates and forwards; it never spawns or applies policy.\n- **Frames:** `session_create` (target `existing_path` | `worktree` |\n  `plain_dir`), `session_close` (hard-kill, history preserved, recoverable),\n  `session_resume` (reattach if alive, else cold-restart from history); responses\n  `session_create_response` / `session_close_response` / `session_resume_response`\n  / `session_lifecycle_error`. The protocol also defines a replayable\n  `session_ready` per-session frame for readiness-gated creates; the current MVP\n  daemon replies once the tmux launch is requested (see the phone guide) rather\n  than waiting on it. Inline prompt text (`-- <prompt>`) is rejected in the MVP.\n\n### Trust model and hardening (daemon side)\n\nThe control endpoint trusts the configured paired chat for any path (an accepted\nrisk). It is hardened around that boundary:\n\n- **Strict paired-chat gating** — non-paired chats are rejected *before* any path\n  parsing, filesystem, or process action.\n- **Durable idempotency** — a locked, atomic, fsynced ledger keyed by\n  `chatId:updateId` + request hash (`telegram-lifecycle-idempotency.json`).\n  Duplicate updates never repeat side effects, including across daemon restart; a\n  duplicate while in-progress reports pending (never a second spawn); a same id\n  with a different body is `duplicate_conflict`; an effect failure is recorded\n  `terminal_uncertain` (never auto-respawned).\n- **Per-chat create rate limit.**\n- **Audit log** — append-only `telegram-lifecycle-audit.jsonl` (`0600`) recording\n  every accept/reject/duplicate/rate-limit/spawn/success/failure. Raw control\n  tokens and raw prompts are never logged (prompt hash + byte length only).\n- **Inline prompts rejected (MVP)** — `session_create` with `-- <prompt>` text is\n  rejected with usage; no prompt is ever placed in argv, audit, or responses. (A\n  redacted prompt-ref flow is reserved for a future revision.)\n- **SKC-managed-only close** — force-close re-reads the exact `@skc-profile`\n  immediately before kill and requires the `@skc-session-id` (and optional\n  `@skc-session-state-file`) tag to match; it never touches non-SKC tmux.\n- **Recent-activity picker** — sessions are ranked by history-file mtime and\n  enriched with terminal breadcrumbs so the operator picks a recent repo/session\n  instead of typing raw paths. Ambiguous resumes fail closed with candidates.\n### Phone test guide (create / close / resume from Telegram)\n\nEnd-to-end manual check once `skc notify setup` has paired your private chat:\n\n1. **Pair + start.** Run `skc notify setup` (BotFather token, DM the bot to pair).\n   Start any SKC session with notifications enabled so the daemon owner is\n   running (`skc launch` in a repo, or `SKC_NOTIFICATIONS=1`). The owner starts\n   the loopback control endpoint and accepts `/session_*` while running; with zero\n   active sessions it still idle-exits after the inactivity timeout.\n2. **Create.** From your paired chat send `/session_create path <repo-dir>` (or\n   `/session_create worktree <repo> <branch>`, or `/session_create dir <newdir>`).\n   `<repo-dir>`, `<repo>`, and `<newdir>` may use `~`/`~/...` for your own home\n   directory; named-user forms such as `~alice/repo` are rejected. The bot replies\n   once the tmux launch is requested; the session shows up in `/session_recent`\n   once it is ready. (Inline prompts via `-- <text>` are rejected for now with\n   usage text.)\n3. **List.** `/session_recent` shows recent sessions (most-recent first) to copy\n   an id from.\n4. **Close.** `/session_close <sessionId>` hard-kills the SKC-managed session\n   (history is preserved); the bot confirms.\n5. **Resume.** `/session_resume <sessionId|prefix>` reattaches if it is still\n   alive, otherwise cold-restarts it from saved history. An ambiguous prefix\n   replies with the matching candidates instead of guessing.\n\nCommands are accepted **only** from the paired chat; **create** is rate-limited,\nand all lifecycle commands are idempotent per Telegram update id and audited (no\ntokens or prompts are logged).\nFor an automated proof of the wire path without a real bot, see\n`packages/coding-agent/scripts/g011-daemon-path-smoke.ts` (real native control\nendpoint + loopback WebSocket).\n",
+	"notifications-sdk.md": "# Notifications SDK\n\n<p align=\"center\">\n  <img src=\"../assets/telegram-mobile-hero.png\" alt=\"Sayknow-CLI 0.7.0 mobile answers for coding agents hero illustration\" width=\"100%\" />\n</p>\n\nA small, transport-agnostic way to get **action-needed** signals out of a SKC\nsession and deliver **replies** back — without scraping the terminal and without\nthe depth of the RPC / Coordinator / Bridge surfaces.\n\nThe stable contract is deliberately generic: every running session exposes one\nloopback WebSocket endpoint, and integrations are user-written clients that\nconnect to that endpoint. Telegram, Discord, Slack, mobile apps, and local tools\nall use the same JSON protocol. No upstream Rust, N-API, or wire-protocol change\nis required for a new integration.\n\n> Status: the Rust core (`crates/skc-notifications`) provides the wire protocol,\n> action lifecycle, loopback WebSocket server, and endpoint discovery file. The\n> bundled Telegram daemon is a reference client layered on top of this SDK; it is\n> not the upstream topology.\n\n## Architecture\n\n```\nSKC session (upstream)                          your client (anywhere)\n┌───────────────────────────────┐               ┌──────────────────────────┐\n│ ask-tool fires / agent idle    │  action_needed │ Telegram / Discord / ... │\n│   → notifications core         │ ─────────────▶ │  render + collect reply  │\n│ ws://127.0.0.1:<port> (+token) │ ◀───────────── │                          │\n│   reply → resolve ask gate     │     reply       │                          │\n└───────────────────────────────┘               └──────────────────────────┘\n```\n\n- **One endpoint per session.** Each session runs its own loopback WebSocket\n  server. Upstream does not maintain a shared daemon, singleton, or\n  chat-to-session registry; multiplexing many sessions into one integration is a\n  client-side concern.\n- **Integrations are clients.** A client discovers endpoint files, connects to\n  one or more WebSockets, renders `action_needed`, and sends `reply` messages.\n- **Zero upstream change.** New transports do not require changes to\n  `crates/skc-notifications` or the JSON protocol.\n- **Off unless configured.** No endpoint exists unless notifications are enabled\n  and a token is present.\n- **tmux-agnostic.** The endpoint behaves identically with or without tmux.\n\n## Endpoint discovery\n\nA running session writes a discovery file at:\n\n```\n<repo>/.skc/state/notifications/<sessionId>.json\n```\n\n(`.skc/state/` is git-ignored.) Shape:\n\n```json\n{\n  \"version\": 1,\n  \"sessionId\": \"019edd41-...\",\n  \"pid\": 12345,\n  \"host\": \"127.0.0.1\",\n  \"port\": 53124,\n  \"url\": \"ws://127.0.0.1:53124\",\n  \"token\": \"<per-session token>\",\n  \"startedAt\": 1718760000000,\n  \"updatedAt\": 1718760000000,\n  \"stale\": false\n}\n```\n\n- The file is created `0700`/`0600` (unix) and written atomically.\n- The **token is in the file** because clients need it; never log it raw.\n  Stale files (dead PID, past TTL, or explicitly marked) are cleaned up on the\n  next start.\n\nConnect with the token as a query parameter:\n\n```\nws://127.0.0.1:<port>/?token=<token>\n```\n\nA wrong/missing token is rejected at the handshake with HTTP `401`.\n\n## Protocol\n\nJSON text frames. Field names are `camelCase`; the `type` discriminator is\n`snake_case`.\n\n### Server → client\n\n`action_needed` — something needs attention:\n\n```json\n{ \"type\": \"action_needed\", \"id\": \"wg_run_stage_1\", \"kind\": \"ask\",\n  \"sessionId\": \"sess-1\", \"question\": \"Proceed?\", \"options\": [\"Yes\", \"No\"] }\n```\n\n```json\n{ \"type\": \"action_needed\", \"id\": \"idle-sess-1-7\", \"kind\": \"idle\",\n  \"sessionId\": \"sess-1\", \"summary\": \"finished refactor; awaiting next step\" }\n```\n\n- `kind: \"ask\"` is answerable in both interactive/TUI and unattended/RPC modes.\n  The `id` is the real workflow-gate id.\n- `kind: \"idle\"` is notify-only and ephemeral (not replayed to clients that\n  connect later).\n\n`action_resolved` — a pending action is now terminal and **non-repliable**:\n\n```json\n{ \"type\": \"action_resolved\", \"id\": \"wg_run_stage_1\", \"resolvedBy\": \"local\" }\n```\n\n`resolvedBy` is `local` (answered in the CLI/TUI), `client` (a remote reply won),\nor `timeout`.\n\n`reply_rejected` — sent only to the client whose reply failed:\n\n```json\n{ \"type\": \"reply_rejected\", \"id\": \"wg_run_stage_1\", \"reason\": \"already_answered\" }\n```\n\nReasons: `already_answered`, `unknown_action`, `invalid_answer`,\n`resolver_unavailable`, `idempotency_conflict`, `unauthorized`.\n\nThe frames above are the minimal contract every client implements. Threaded\nclients (like the managed Telegram daemon) may also receive optional\nserver → client frames they can render or ignore: `identity_header` (one-time\nper-session repo/branch/machine header), `context_update` (last message, task,\ngoal, token usage, model, diff), `turn_stream` (live/finalized turn output),\n`image_attachment` (agent-produced images), `activity` (busy/idle, drives the\ntyping indicator), `inbound_ack` (delivery state of an injected user message),\n`session_closed` (endpoint teardown; threaded clients may delete/archive the\nremote conversation), `config_update` (current verbosity/redact), `hello`\n(server capability/version), and `pong`. A minimal client only needs\n`action_needed`, `action_resolved`, and `reply_rejected`.\n\n### Client → server\n\n`reply` — answer a pending `ask`:\n\n```json\n{ \"type\": \"reply\", \"id\": \"wg_run_stage_1\", \"answer\": 0, \"token\": \"<token>\" }\n```\n\n`answer` accepts:\n\n- a number — zero-based option index (`0` = first option);\n- a string — an option label, or free text;\n- an object — `{ \"selected\": [0, \"Maybe\"], \"custom\": \"...\" }` for multi-select.\n\nOptional `idempotencyKey` makes retries safe: the same key + same body re-acks;\nthe same key + different body is rejected with `idempotency_conflict`.\n\nThreaded clients may also send optional client → server frames: `user_message`\n(inject/steer a turn with free text), `config_command` (toggle verbosity/redact\nin-thread), `hello` (capability/version), and `ping`. A minimal client only\nneeds `reply`.\n\n## Answer semantics\n\nA remote reply answers a pending ask in **both** modes — RPC is not required:\n\n- **Interactive / TUI mode:** the ask tool races the local selector against the\n  remote reply (first valid answer wins). If you tap a button in the client, the\n  ask resolves with that option; if you answer locally, the client receives\n  `action_resolved` (`resolvedBy: \"local\"`) and the action becomes non-repliable.\n- **Unattended / RPC mode:** the reply resolves the real workflow-gate, driving\n  the session the same way a local answer would.\n\nIn both modes the first valid reply wins; later replies get `already_answered`.\nIdle pings are notify-only.\n\n## Minimal client example\n\n```js\nimport { readFileSync } from \"node:fs\";\nimport WebSocket from \"ws\";\n\nconst { url, token } = JSON.parse(\n  readFileSync(`.skc/state/notifications/${sessionId}.json`, \"utf8\"),\n);\n\nconst ws = new WebSocket(`${url}/?token=${encodeURIComponent(token)}`);\n\nws.on(\"message\", (data) => {\n  const msg = JSON.parse(data.toString());\n  if (msg.type === \"action_needed\" && msg.kind === \"ask\") {\n    // present msg.question / msg.options to the human, then:\n    ws.send(JSON.stringify({ type: \"reply\", id: msg.id, answer: 0, token }));\n  } else if (msg.type === \"action_resolved\") {\n    // mark this action as no longer answerable in your UI\n  } else if (msg.type === \"reply_rejected\") {\n    // e.g. reason === \"already_answered\" → the ask was answered elsewhere\n  }\n});\n```\n\nSwap `ws` for a Telegram bot's long-poll loop, a Discord gateway client, or a\nSlack socket-mode app — the contract above is all you implement.\n\n## Managed notification adapters\n\nFor the exact user setup flow (`skc notify setup`, BotFather token, private-chat pairing, status, and troubleshooting), see [Telegram notification onboarding](./telegram-onboarding.md).\n\n## Managed Telegram daemon (bundled reference client)\n\nSKC also ships a managed Telegram reference client for the common phone-notify\nworkflow. It remains a client of the generic SDK: it scans session discovery\nfiles, opens each session WebSocket, and routes Telegram replies back to the\nmatching endpoint.\n\nThe daemon/session engine is shared. Session discovery, WebSocket protocol,\nredaction decisions, rate-limit pooling, reply routing, singleton ownership, and\nlifecycle control are not reimplemented by each chat surface. Telegram, Discord,\nand Slack adapters are thin presentation layers: they render internal notification\nevents into transport payloads and map transport interactions back to `{sessionId,\nactionId,answer}` replies.\n\n### Setup and auto-connect\n\nRun the setup command once:\n\n```sh\nskc notify setup\n```\n\nThe wizard validates the bot token with Telegram, verifies private-chat Threaded\nMode capability via `getMe.has_topics_enabled`, waits for a private DM to the bot,\nand writes canonical global Settings under `config.yml` in the SKC agent\ndirectory. It enables:\n\n- `notifications.enabled`\n- `notifications.telegram.botToken`\n- `notifications.telegram.chatId`\n- `notifications.redact` (optional; default false)\n- `notifications.discord.botToken` / `notifications.discord.channelId` (optional Discord adapter)\n- `notifications.slack.botToken` / `notifications.slack.channelId` (optional Slack adapter)\n\nAfter setup, sessions auto-connect when notifications are enabled. Each session\nstill publishes its own loopback endpoint; the daemon is only the Telegram-side\nmultiplexer.\n\nFor Telegram forum topics, the daemon deletes the per-session topic when the local\nnotification endpoint shuts down, so it disappears from the topic list. A resumed\nsession creates a fresh topic before sending again. The bot must be allowed to\ndelete messages in that chat; without that permission, deletion is best-effort and\ndelivery continues.\n\n### Singleton poller and trust model\n\nTelegram `getUpdates` allows only one active long-poll owner per bot token. The\nmanaged daemon enforces **one bot token = one getUpdates poller** with a local\nlock/state file under the agent directory. New sessions attach to the existing\nfresh daemon owner instead of starting another poller, preventing Telegram 409\nconflicts.\n\nThe trust model is intentionally strict:\n\n- setup pairs exactly one private Telegram chat;\n- runtime accepts updates only from that paired chat id;\n- groups, supergroups, channels, and unpaired users never receive session names,\n  action ids, pending status, or configuration hints;\n- daemon state stores a token fingerprint, not the raw bot token.\n\n### Routing in private-chat topics\n\nThe paired private chat prefers per-session Telegram topics (Threaded Mode). The\ndaemon tags messages by session, stores compact callback aliases for inline\nbuttons, and routes replies back to the exact session/action. A forum-enabled\nsupergroup is no longer required: when the bot owner enables Threaded Mode in\n@BotFather, the daemon creates one topic per session in the paired private chat.\nSKC cannot enable Threaded Mode through the Bot API; setup only verifies the\ncapability and guides the manual BotFather toggle.\n\nIf BotFather's per-bot **Bot Settings** menu does not show **Threads Settings**\nor **Threaded Mode**, the supported fallback is the normal private-chat pairing.\nSetup can be saved as `threaded=unverified`/`threaded=unknown`, and the daemon\nstill tries topics when Telegram allows them. When `createForumTopic` is refused,\nthe daemon does not drop the send: it routes the notification to the normal\n(flat) paired private chat and posts a one-time `turn on threaded mode from\nbotfather miniapp to receive skc notification!` nudge. Pairing is private-only,\nso flat delivery stays within the user's own private DM.\n\nSupported reply paths:\n\n- tap an inline button on an ask notification;\n- reply inside the session's thread/topic (replies are thread-native; the\n  topic identifies the session, so no session tag is needed).\n\nIn threaded mode the user can also adjust per-session behaviour with in-thread\nconfig commands: `/verbose`, `/lean`, `/verbosity <lean|verbose>`, and\n`/redact <on|off>`. The legacy `/answer <session-tag> <answer>` command is\nremoved — replies are routed by the topic they arrive in.\n\nFlat fallback keeps outbound notifications and inline-button answers working,\nbut free-text replies and `/verbose`/`/lean`/`/verbosity`/`/redact` commands are\nthread-native and require topic routing. Do not pair a group, supergroup, or\nchannel to work around a missing BotFather menu; the bundled setup flow is\nprivate-chat only, and non-private chat ids remain fail-closed to avoid session\ndata leaks.\n\nUnknown, expired, or restart-unvalidated callback aliases fail closed: the daemon\nsends guidance and does not guess a target session or action.\n\n### Discord and Slack setup\n\nDiscord and Slack use the same internal notification events and reply protocol as\nTelegram. Store only runtime credentials in local SKC settings or environment;\nnever paste bot tokens, webhook URLs, transcripts, prompts, host paths, or raw logs\ninto docs, tests, issues, or PR comments.\n\nConfiguration keys:\n\n```yaml\nnotifications:\n  enabled: true\n  discord:\n    botToken: \"<local Discord bot token>\"\n    channelId: \"<Discord channel id>\"\n  slack:\n    botToken: \"<local Slack bot token>\"\n    channelId: \"<Slack channel id>\"\n  redact: true\n```\n\nThe bundled adapters intentionally render public-safe message bodies and return\nroute metadata only for pending internal actions. They do not own polling,\nsession scans, daemon locks, rate limits, or SDK lifecycle. Production transport\nsenders should consume the adapter payloads and keep all credential-bearing HTTP\nor gateway details outside logged payloads.\n### Redaction\n\n`notifications.redact` strips sensitive content before remote delivery, but\n**asks are exempt**: an ask is an interactive prompt the human must read and\nanswer remotely, so its `question` and `options` are always sent unredacted\n(otherwise it would be unanswerable). When redaction is enabled, `idle`\nsummaries are removed and streamed content frames (`turn_stream`,\n`context_update`, `image_attachment`) are suppressed at their emit sites. When\nredaction is disabled, all content is delivered unchanged.\n\n### Local `/notify`\n\nInside a SKC session, `/notify` controls the current session only:\n\n- `/notify status` reports enabled/disabled state, daemon observation when known,\n  and redaction state without printing secrets;\n- `/notify off` disables the current session's notification endpoint and removes\n  its discovery record without mutating global Settings;\n- `/notify on` re-enables the current session when global setup is complete and\n  `SKC_NOTIFICATIONS=0` is not forcing opt-out.\n\n### Manual Telegram CLI is for debugging\n\n`packages/coding-agent/src/notifications/telegram-cli.ts` remains as a manual\nreference/debug client and template for other integrations. It is not the primary\nTelegram UX.\n\n```sh\nbun run packages/coding-agent/src/notifications/telegram-cli.ts --bot-token \"$BOT_TOKEN\"\n```\n\nBy default it refuses to start when a fresh managed daemon already owns the same\nbot token for the same paired chat, because a second poller will cause Telegram\n409 conflicts. Use `--force` only for deliberate debugging when you have stopped\nor intentionally want to override the daemon guard.\n## Two client surfaces: per-session vs daemon-owned lifecycle control\n\nThe SDK now exposes **two distinct surfaces**. Do not confuse them:\n\n1. **Per-session notification clients (the normal, documented contract above).**\n   A client discovers `<repo>/.skc/state/notifications/<sessionId>.json`, connects\n   to that session's loopback WebSocket, and handles `action_needed`,\n   `action_resolved`, `reply_rejected`, and the optional threaded frames. This is\n   all an ordinary integration (Telegram, Discord, Slack, mobile, local tools)\n   needs. It requires **zero** upstream changes.\n\n2. **The daemon-owned session *lifecycle* control endpoint (privileged).**\n   A separate, **session-independent**, loopback-only, authenticated control\n   endpoint that accepts `session_create` / `session_close` / `session_resume`\n   frames. It exists because creating a session cannot use a per-session socket\n   (none exists before the session does). It is **not** part of the normal\n   integration contract: ordinary clients never implement it. Only the bundled,\n   trusted daemon (e.g. the managed Telegram daemon) speaks it.\n\n### Lifecycle control endpoint\n\n- **Discovery:** `<agentDir>/notifications/control.json` (daemon-owned, mode\n  `0600`), distinct from per-session endpoint files. It carries only non-secret\n  endpoint metadata (url/host/port/pid/owner). The control token is held **in\n  memory** by the daemon (the sole client) and is **never** written to disk.\n- **Auth:** loopback-only bind (a non-loopback bind is refused). The WebSocket\n  upgrade requires `?token=<control-token>` (HTTP `401` otherwise), and every\n  lifecycle frame's `token` is re-checked (`unauthorized` on mismatch). The Rust\n  ingress authenticates and forwards; it never spawns or applies policy.\n- **Frames:** `session_create` (target `existing_path` | `worktree` |\n  `plain_dir`), `session_close` (hard-kill, history preserved, recoverable),\n  `session_resume` (reattach if alive, else cold-restart from history); responses\n  `session_create_response` / `session_close_response` / `session_resume_response`\n  / `session_lifecycle_error`. The protocol also defines a replayable\n  `session_ready` per-session frame for readiness-gated creates; the current MVP\n  daemon replies once the tmux launch is requested (see the phone guide) rather\n  than waiting on it. Inline prompt text (`-- <prompt>`) is rejected in the MVP.\n\n### Trust model and hardening (daemon side)\n\nThe control endpoint trusts the configured paired chat for any path (an accepted\nrisk). It is hardened around that boundary:\n\n- **Strict paired-chat gating** — non-paired chats are rejected *before* any path\n  parsing, filesystem, or process action.\n- **Durable idempotency** — a locked, atomic, fsynced ledger keyed by\n  `chatId:updateId` + request hash (`telegram-lifecycle-idempotency.json`).\n  Duplicate updates never repeat side effects, including across daemon restart; a\n  duplicate while in-progress reports pending (never a second spawn); a same id\n  with a different body is `duplicate_conflict`; an effect failure is recorded\n  `terminal_uncertain` (never auto-respawned).\n- **Per-chat create rate limit.**\n- **Audit log** — append-only `telegram-lifecycle-audit.jsonl` (`0600`) recording\n  every accept/reject/duplicate/rate-limit/spawn/success/failure. Raw control\n  tokens and raw prompts are never logged (prompt hash + byte length only).\n- **Inline prompts rejected (MVP)** — `session_create` with `-- <prompt>` text is\n  rejected with usage; no prompt is ever placed in argv, audit, or responses. (A\n  redacted prompt-ref flow is reserved for a future revision.)\n- **SKC-managed-only close** — force-close re-reads the exact `@skc-profile`\n  immediately before kill and requires the `@skc-session-id` (and optional\n  `@skc-session-state-file`) tag to match; it never touches non-SKC tmux.\n- **Recent-activity picker** — sessions are ranked by history-file mtime and\n  enriched with terminal breadcrumbs so the operator picks a recent repo/session\n  instead of typing raw paths. Ambiguous resumes fail closed with candidates.\n### Phone test guide (create / close / resume from Telegram)\n\nEnd-to-end manual check once `skc notify setup` has paired your private chat:\n\n1. **Pair + start.** Run `skc notify setup` (BotFather token, DM the bot to pair).\n   Start any SKC session with notifications enabled so the daemon owner is\n   running (`skc launch` in a repo, or `SKC_NOTIFICATIONS=1`). The owner starts\n   the loopback control endpoint and accepts `/session_*` while running; with zero\n   active sessions it still idle-exits after the inactivity timeout.\n2. **Create.** From your paired chat, pick `/session_create` from the Telegram\n   command menu or send `/session_create path <repo-dir>` (or\n   `/session_create worktree <repo> <branch>`, or `/session_create dir <newdir>`).\n   `<repo-dir>`, `<repo>`, and `<newdir>` may use `~`/`~/...` for your own home\n   directory; named-user forms such as `~alice/repo` are rejected. The bot replies\n   once the tmux launch is requested; the session shows up in `/session_recent`\n   once it is ready. (Inline prompts via `-- <text>` are rejected for now with\n   usage text.)\n3. **List.** `/session_recent` shows recent sessions (most-recent first) to copy\n   an id from.\n4. **Close.** `/session_close <sessionId>` hard-kills the SKC-managed session\n   (history is preserved); the bot confirms.\n5. **Resume.** `/session_resume <sessionId|prefix>` reattaches if it is still\n   alive, otherwise cold-restarts it from saved history. An ambiguous prefix\n   replies with the matching candidates instead of guessing.\n\nCommands are accepted **only** from the paired chat; **create** is rate-limited,\nand all lifecycle commands are idempotent per Telegram update id and audited (no\ntokens or prompts are logged).\nFor an automated proof of the wire path without a real bot, see\n`packages/coding-agent/scripts/g011-daemon-path-smoke.ts` (real native control\nendpoint + loopback WebSocket).\n",
 	"onboarding-packet.md": "# Sayknow-CLI Onboarding Packet\n\nThis packet is a docs-only, public-safe context seed for the `sayknow-cli` repository as inspected on 2026-06-01. It is intentionally a no-new-skill artifact: not a new workflow skill, command, agent, configuration surface, issue template, or runtime behavior.\n\n## Purpose in one paragraph\n\nSayknow-CLI is the `skc` coding-agent CLI and supporting monorepo. The product centers on a small public workflow loop: clarify with `deep-interview`, plan with `ralplan`, execute and verify through `ultragoal`, and use `team` only when parallel tmux workers are useful. The main product package is `packages/coding-agent/`; supporting packages provide LLM/provider access, agent runtime, TUI rendering, native helpers, stats, utilities, benchmarks, and Python RPC/bot integrations.\n\n## Fixed public surface\n\nKeep this invariant front-and-center when onboarding to the repo:\n\n- Default workflow skills: `deep-interview`, `ralplan`, `team`, `ultragoal`.\n- Public role agents: `executor`, `architect`, `planner`, `critic`.\n- Bundled default workflow skill sources live under `packages/coding-agent/src/defaults/skc/skills/`.\n- Bundled role-agent prompt sources live under `packages/coding-agent/src/prompts/agents/`.\n- Runtime state, specs, plans, goals, team state, and local overrides belong under `.skc/` for the product and `.omx/` only for this agent-run orchestration.\n\nDo not add a fifth default skill, fifth public role agent, new command, new config surface, or feature-intake behavior unless that product decision has already been made and the default-surface gates are updated.\n\n## Primary entrypoints\n\n| Area             | Repo-relative path                                   | Why it matters                                                                                    |\n| ---------------- | ---------------------------------------------------- | ------------------------------------------------------------------------------------------------- |\n| CLI bootstrap    | `packages/coding-agent/src/cli.ts`                   | Registers top-level CLI commands and routes default launch behavior.                              |\n| Session launch   | `packages/coding-agent/src/main.ts`                  | Converts CLI/runtime settings into agent-session creation and mode dispatch.                      |\n| Agent assembly   | `packages/coding-agent/src/sdk.ts`                   | Loads settings, default skills, rules, tools, auth/model state, system prompt, and agent runtime. |\n| Built-in tools   | `packages/coding-agent/src/tools/index.ts`           | Registers file, shell, edit, search, browser, task/subagent, and related public coding-harness tools. Memory backends are private integrations, not public tools. |\n| Default skills   | `packages/coding-agent/src/defaults/skc-defaults.ts` | Embeds and installs the four default workflow skills plus deep-interview fragments.               |\n| Role agents      | `packages/coding-agent/src/task/agents.ts`           | Embeds bundled task-agent prompts; tests enforce public role-agent expectations.                  |\n| Product overview | `README.md`                                          | Explains installation, product story, fixed workflow surface, and development entry commands.     |\n| Architecture map | `docs/codebase-overview.md`                          | Public package map and runtime-flow reference.                                                    |\n\n## Package map\n\n- `packages/coding-agent/` — main `skc` CLI, workflows, session runtime, tool registry, discovery, settings, prompts, and tests.\n- `packages/ai/` — provider/model boundary, streaming, auth, model registry, retries, and provider integrations.\n- `packages/agent/` — stateful agent loop and append-only context runtime.\n- `packages/tui/` — terminal UI framework and rendering primitives.\n- `packages/natives/` plus `crates/*` — native helpers, Rust/N-API bindings, shell/PTY, text search, AST, filesystem, and media utilities.\n- `packages/utils/` — shared TypeScript utilities, logging, formatting, process helpers, JSON/frontmatter, and sanitization.\n- `packages/stats/` — local observability dashboard and session/model usage aggregation.\n- `packages/typescript-edit-benchmark/` — TypeScript edit benchmark tooling.\n- `python/skc-rpc/` — Python client for `skc --mode rpc`.\n- `python/roboskc/` — GitHub triage/fix bot that drives `skc --mode rpc`; this subtree has its own `AGENTS.md`.\n\n## Build, test, and validation commands\n\nPrefer targeted checks first, then broader checks when code changes justify them. For this docs-only packet, lightweight validation is enough.\n\n| Command                                                               | Scope                               | When to use                                                                 |\n| --------------------------------------------------------------------- | ----------------------------------- | --------------------------------------------------------------------------- |\n| `bun install`                                                         | Workspace dependencies              | Initial local setup.                                                        |\n| `bun run install:defaults`                                            | Local default install               | Installs source-bundled default workflow definitions for local development. |\n| `bun packages/coding-agent/src/cli.ts --help`                         | CLI smoke/discovery                 | Fast source checkout CLI sanity check.                                      |\n| `bun run check:ts`                                                    | Type/lint/default UI checks         | Broad TypeScript validation; heavier than docs-only changes.                |\n| `bun run test`                                                        | Full TS + Rust tests                | Broad regression check; use for runtime/product changes.                    |\n| `bun run ci:test:smoke`                                               | CLI version/help/stats worker smoke | Useful before release/install changes.                                      |\n| `bun scripts/check-visible-definitions.ts`                            | Default surface gate                | Required after workflow-definition changes.                                 |\n| `bun scripts/verify-g002-gates.ts`                                    | Rebrand/default-surface gate        | Required after workflow-definition or public-surface changes.               |\n| `bun scripts/rebrand-inventory.ts --strict`                           | Rebrand inventory gate              | Required after workflow-definition or public-surface changes.               |\n| `bun test packages/coding-agent/test/default-skc-definitions.test.ts` | Four-skills/four-agents contract    | Required after default workflow/agent surface changes.                      |\n\nRepository rule: do not run `tsc` or `npx tsc`; use the Bun scripts above.\n\n## Danger zones\n\n- **Default surface expansion:** `packages/coding-agent/src/defaults/skc/skills/`, `packages/coding-agent/src/defaults/skc-defaults.ts`, `packages/coding-agent/src/prompts/agents/`, and model-assignment tests are contract-heavy. Changes here can accidentally alter the fixed four-skills/four-agents shape.\n- **CLI commands:** `packages/coding-agent/src/cli.ts` and `packages/coding-agent/src/commands/` define visible behavior. Adding commands or aliases is a product-surface change.\n- **Runtime/session assembly:** `packages/coding-agent/src/main.ts`, `packages/coding-agent/src/sdk.ts`, discovery, settings, tools, and system-prompt paths can affect every session.\n- **TUI/logging:** Avoid `console.log`, `console.warn`, or `console.error` inside `packages/coding-agent/`; use the centralized logger to avoid corrupting TUI rendering.\n- **Secrets/auth/config:** Keep `docs/secrets.md`, auth broker/gateway code, settings, and environment-variable docs public-safe. Do not expose tokens or private infrastructure.\n- **Native/Rust build:** `packages/natives/` and `crates/*` can require platform-specific toolchains and CI artifact behavior.\n- **Python bot subtree:** `python/roboskc/` has its own local instructions and trust boundaries.\n- **Generated model data:** Do not edit `packages/ai/src/models.json` directly; update generators/descriptors/resolvers and regenerate with `bun --cwd=packages/ai run generate-models`.\n\n## Unknowns worth preserving\n\n- Which onboarding packet shape will be most useful for future `skc` context ingestion is still an experiment, not a product contract.\n- Public issue #158 / `sayknow-deep-onboarding` context is summarized only from the user-provided prompt in this run; this packet does not add issue intake or feature workflow behavior.\n- Full CI may depend on runner/system dependencies and native artifacts; docs-only changes usually do not need the full matrix locally.\n- Some packages contain internal or hidden utility prompts/agents beyond the four public role agents. Public-facing docs should keep the four-role contract clear.\n\n## First safe tasks for a new contributor or agent\n\n1. Read `README.md`, `docs/codebase-overview.md`, and this packet.\n2. Run `bun packages/coding-agent/src/cli.ts --help` for a fast CLI surface check after dependencies are installed.\n3. For docs-only edits, run formatting/check commands that do not mutate runtime behavior.\n4. For default-surface edits, run the four required gates listed in the command table before claiming completion.\n5. For package code edits, start with the nearest package test, then escalate to `bun run check:ts` or `bun run test` as risk increases.\n6. Before changing `packages/coding-agent/src/defaults/skc/skills/`, `packages/coding-agent/src/prompts/agents/`, `packages/coding-agent/src/commands/`, or config/settings paths, write down whether the change alters public surface area.\n\n## Context seed checklist\n\nA future agent can use this packet as context if it preserves these constraints:\n\n- Keep changes public-safe and repo-relative.\n- Prefer docs and tests over new runtime abstractions for onboarding experiments.\n- Treat the fixed four-skills/four-agents shape as a product constraint.\n- Verify claims with repo files before summarizing them.\n- Report validation evidence and caveats instead of implying hidden automation.\n",
 	"onboarding-receipt.md": "# Onboarding Packet Receipt\n\n- Date: 2026-06-01\n- Scope: docs-only no-new-skill onboarding packet experiment for this repository.\n- Output files:\n  - `docs/onboarding-packet.md`\n  - `docs/onboarding-receipt.md`\n- Public-safe boundary: no secrets, tokens, hidden prompts, private infrastructure, internal ops, or private paths beyond repo-relative paths.\n- Product boundary: no new skill, command, agent slot, issue, config, or runtime behavior.\n\n## Evidence inspected\n\n- `README.md`\n- `docs/codebase-overview.md`\n- `package.json`\n- `packages/coding-agent/package.json`\n- `packages/coding-agent/src/cli.ts`\n- `packages/coding-agent/src/main.ts`\n- `packages/coding-agent/src/sdk.ts`\n- `packages/coding-agent/src/defaults/skc-defaults.ts`\n- `packages/coding-agent/src/task/agents.ts`\n- `packages/coding-agent/test/default-skc-definitions.test.ts`\n- `.github/workflows/ci.yml`\n- `.github/workflows/dev-ci.yml`\n\n## Result\n\nThe packet records repo purpose, package layout, main entrypoints, build/test commands, danger zones, unknowns, and first safe tasks without changing the product surface. It is suitable as a public context seed for future onboarding experiments, not as a feature intake mechanism.\n\n## Caveats\n\n- The attempted `omx question --input '<json>' --json` interview round failed before user input because the runtime reported no attached tmux client; no human answer was inferred from that failed call.\n- Public issue context is limited to the user-provided prompt summary for this run.\n- Full CI was not required for the docs-only artifact unless later code/runtime files change.\n",
 	"ooo-bridge-extension-contract.md": "# Ouroboros `ooo` bridge extension contract\n\nSKC exposes the `ooo` bridge through the existing extension input-event surface. It is not a default workflow skill, hook, slash command, or built-in agent.\n\n## Interception surface\n\nExtensions register an `input` handler:\n\n```ts\nimport { createOuroborosOooBridge } from \"@sayknow-cli/coding-agent/extensibility/extensions\";\n\nexport default function activate(skc) {\n  skc.on(\"input\", createOuroborosOooBridge());\n}\n```\n\nThe handler matches only the bare exact prefix:\n\n- `ooo`\n- `ooo ...`\n\nIt does not match embedded or longer-token text such as `please ooo status`, `oooo`, or `/ooo`.\n\nThe extension runner already treats `InputEventResult.handled === true` as terminal: the input is not sent through normal model flow. An empty result (`{}`) means continue/pass-through, preserving existing chained input handlers and normal prompt handling.\n\n## Dispatch and result semantics\n\n`createOuroborosOooBridge()` is a small specialization of `createExactPrefixCommandBridge()`:\n\n- command: `ouroboros`\n- arguments: `dispatch`, then the full submitted input text\n- recursion guard variable: `_OUROBOROS_SKC_BRIDGE_DEPTH`\n- continue/pass-through exit code: `78`\n\nExit-code mapping:\n\n| Dispatch result | SKC input result |\n| --- | --- |\n| `0` | `{ handled: true }`; do not send input to the model. |\n| `78` | `{}`; continue/pass-through so SKC processes the input normally. |\n| any other non-zero | Surface an extension error notification using stderr, then stdout, then a generic exit-code message, and return `{ handled: true }`; the failed `ooo` command is terminal and is not sent to the model. |\n\n## Recursion guard\n\nBefore dispatch, the helper sets `_OUROBOROS_SKC_BRIDGE_DEPTH` to the next numeric depth and restores the previous value after dispatch finishes. A current numeric depth of `0` or `1` is dispatchable, which preserves concurrent independent interactive inputs while marking child dispatcher processes with depth `1`. A current numeric depth greater than `1`, or any non-empty non-numeric value, returns `{}` without dispatching.\n\nThis means the bridge allows exactly one inherited bridge-marked dispatcher level and blocks recursive re-entry from deeper bridge-marked children. The guard also passes through `event.source === \"extension\"` to avoid extension-originated messages re-entering the bridge.\n\n## Installation and discovery\n\nThe canonical install location is the agent extensions directory discovered by the native SKC provider:\n\n- user-level: `${SKC_CODING_AGENT_DIR:-$HOME/.skc/agent}/extensions`\n- project-level: `<cwd>/${SKC_CONFIG_DIR:-.skc}/extensions`\n\nFor native discovery, install one of:\n\n- `extensions/<name>.ts` or `extensions/<name>.js`\n- `extensions/<name>/index.ts` or `extensions/<name>/index.js`\n- `extensions/<name>/package.json` declaring extension entries\n\nThe loader scans one level under each `extensions` directory. Complex packages should use a package manifest instead of relying on recursive discovery.\n\n`SKC_CONFIG_DIR` selects the project config directory name. `SKC_CODING_AGENT_DIR` selects the user agent directory name under `$HOME`. The native provider resolves those locations before loading extension modules, skills, rules, hooks, and related capabilities.\n\nHooks are not the input bridge surface: `packages/coding-agent/src/capability/hook.ts` defines pre/post tool hooks only.\n",
@@ -64,6 +67,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"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",
@@ -72,9 +76,10 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"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",
 	"skc-plugins.md": "# SKC Plugin Bundles\n\nSKC supports two distinct plugin families. Do not confuse them:\n\n1. **Legacy marketplace / npm plugins** (`packages/coding-agent/src/extensibility/plugins`) — installed through the existing `skc plugin install <marketplace-ref|npm-spec>` marketplace/npm flows. Unchanged by this system.\n2. **SKC plugin bundles** — directories whose root contains a **`sayknow-plugin.json`** manifest (`kind: \"sayknow-cli-plugin\"`). These *extend* existing SKC capabilities and are the subject of this document.\n\nA SKC plugin bundle may only **extend** existing skills/agents — it can never register a new top-level skill, slash-command, command, or agent. SKC exposes exactly four default workflow skills (`deep-interview`, `ralplan`, `team`, `ultragoal`) and four role agents (`executor`, `architect`, `planner`, `critic`); bundles add sub-skills/appendices/tools/hooks/MCPs to those existing parents only.\n\n## Manifest (`sayknow-plugin.json`)\n\n```json\n{\n  \"kind\": \"sayknow-cli-plugin\",\n  \"name\": \"example-domain-bundle\",\n  \"version\": \"1.0.0\",\n  \"subskills\": [\"subskills/ralplan-design/SKILL.md\"],\n  \"tools\": [\n    { \"name\": \"domain_note\", \"path\": \"tools/domain-note.ts\", \"description\": \"...\" }\n  ],\n  \"hooks\": [\n    { \"name\": \"audit-read\", \"event\": \"tool_call\", \"target\": \"read\", \"phase\": \"before\", \"path\": \"hooks/audit-read.ts\" }\n  ],\n  \"mcps\": [\n    { \"name\": \"domain_docs\", \"transport\": \"stdio\", \"command\": \"bun\", \"args\": [\"mcp/domain-docs.ts\"], \"cwd\": \".\" }\n  ],\n  \"system_appendix\": [{ \"name\": \"domain-policy\", \"path\": \"prompts/system-appendix.md\" }],\n  \"agent-appendix\": [{ \"agent\": \"executor\", \"name\": \"domain-executor\", \"path\": \"prompts/executor-appendix.md\" }]\n}\n```\n\n### Surfaces (the only allowed extension points)\n\n| Surface | Purpose | Additive rule |\n|---------|---------|---------------|\n| `subskills` | Inline sub-skills bound to an existing skill/agent (`binds_to`/`phase`/`activation_arg`) | Two-tier (see below) |\n| `tools` | Always-on custom tools (object entries) or legacy subskill-scoped string paths | Additive; manifest-declared name is authoritative, never overwrites an existing tool |\n| `hooks` | Constrained event hooks bound to a declared `event`/`target`/`phase` | Additive; run alongside built-ins, never replace |\n| `mcps` | MCP servers (`stdio`/`http`/`sse`) | Additive; server-name collisions are hard errors |\n| `system_appendix` | Lower-authority text appended to the default agent system prompt | Append-only, never overrides base |\n| `agent-appendix` | Lower-authority text appended to an existing role agent's prompt | Append-only per named agent |\n\n### Forbidden / unsupported keys\n\n- **Forbidden** (`forbidden_surface`): `skills`, `slash-commands`, `commands`, `agents` — bundles may not register new top-level definitions.\n- **Unsupported** (`unsupported_surface`): `mcp`, `mcpServers` (use the canonical `mcps`), and any unknown top-level key.\n\n## Installation\n\n```sh\nskc plugin install <path|git-url|tarball> --user      # install into the user root\nskc plugin install <path|git-url|tarball> --project   # install into the project root\n```\n\nExactly one of `--user` / `--project` is required for SKC plugin bundles (there is no default root). A source containing `sayknow-plugin.json` is classified as a SKC bundle and routed to the bundle installer **before** the marketplace/npm path; non-bundle sources fall through to the legacy flow.\n\nInstall is **compile-validate-then-copy**:\n\n1. The bundle is compiled and validated **without importing any plugin code** (manifest, frontmatter, and declared files are read as bytes only).\n2. Collision and MCP security policy are enforced (the durable registry is the collision authority — never capability \"first-wins\").\n3. Only the validated, hashed files are copied into a temp sibling, then atomically renamed into place; the registry entry is written last under a per-scope lock. Nothing is mutated on failure.\n\nIdempotency: re-installing identical content is a no-op; different content requires `--force`.\n\n## Security model\n\n- **Install validation never executes plugin code.** Tool/hook names are manifest-declared; at runtime the loaded factory must return/register exactly the declared name/event or the surface is quarantined (`runtime_mismatch`).\n- **MCP policy** (install + runtime connect): HTTPS-only for `http`/`sse`; private/loopback/link-local/unique-local/multicast and the `169.254.169.254` metadata endpoint are denied across IPv4, IPv6, IPv4-mapped/compatible, zone-id and trailing-dot forms; URL credentials and CRLF headers are rejected; DNS is re-resolved before connect (rebinding defence). `stdio` servers are confined to the plugin root (allowed launchers `node`/`bun` or a root-confined executable; required bundled script argument; no eval/loader flags; no env expansion).\n- **Hooks** run through a *constrained* API: only a handler for the declared event may be registered. `registerCommand`, `sendMessage`, `appendEntry`, renderer registration, and shell `exec` are denied (`security_policy`). The broad first-party hook API is never exposed to bundle hooks.\n- **Appendices** render as lower-authority, delimited `<skc-plugin-system-appendix>` / `<skc-plugin-agent-appendix>` blocks appended after the base/project prompt; size-capped (8 KiB/appendix, 32 KiB total) fail-closed; content is escaped and control-char sanitized. They can never override base/developer instructions.\n- **Hash drift**: installed files are re-verified against the registry at session start; any drift quarantines the plugin (`runtime_mismatch`).\n\n## Sub-skills: Tier-1 vs Tier-2\n\n- **Tier-1 advertisement** (metadata-only): when a parent skill/agent prompt is built, installed sub-skills bound to it are advertised as a bounded list (`plugin` / `name` / `description` / `activation_arg` / `phase`; max 12 items, 200-char descriptions, 4 KiB block, with an overflow note). No body content; rendered only in the target parent prompt, never the global public-workflow surface.\n- **Tier-2 activation** (full body): on explicit activation (e.g. `deep-interview --autoresearch`) or an agent's contextual choice, the full sub-skill body is injected as a `<skc-subskill>` block at the matching phase.\n\n## Registry, enablement, and quarantine\n\nEach scope keeps a durable `registry.json` recording per-plugin: name/version, source (`path`/`git`/`tarball` + ref/sha), manifest hash, copied files (relative path + sha256 — the uninstall ownership boundary), per-surface extension IDs, `enabled` flag, `disabledSurfaceIds`, and any `quarantine` entries.\n\nExtension IDs are stable: `tool:<name>`, `hook:<event>:<phase>:<target>:<name>`, `mcp:<name>`, `system-appendix:<plugin>:<name>`, `agent-appendix:<agent>:<plugin>:<name>`, `subskill:<parent>:<phase>:<activation_arg>`. Disabled is user-controlled (not an error); quarantine is fail-closed and visible.\n\n## Status / scope notes\n\n- Always-on **tools**, **system appendices**, **agent appendices**, and **Tier-1 advertisement** activate at session start (additive; no-op when no bundle is installed).\n- **MCP runtime connection** and the **live hook runner** integration are gated behind the same validated registry + policy; consult the ledger/run notes for their wiring status.\n- Full enable/disable/uninstall/upgrade UX is a planned follow-up; the registry already records everything required for it (per-surface IDs + copied-file ownership).\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\nscripts/skc-session/create.sh <session-name> <worktree-path> [channel-id] [mention]\n\n# prompt.sh\n# inject the real task after the TUI is ready\nscripts/skc-session/prompt.sh <session-name> @/path/to/task.md\n\n# tail.sh\n# inspect bounded pane output before/after prompt delivery\nscripts/skc-session/tail.sh <session-name> [lines]\n```\n\nThis repository includes a portable implementation in `scripts/skc-session/`. It keeps private routing values outside the script body: channel ids and mentions are runtime arguments, the router binary is optional, and credentials are never embedded. Host deployments can still override router behavior with environment variables instead of editing the scripts.\n\n\n## Included helper scripts\n\nThe `scripts/skc-session/` directory contains the public version of the operator helpers:\n\n- `create.sh` validates a dedicated git worktree, starts interactive `skc` in tmux, preserves the pane after exit, prints and writes the session-specific durable state path, writes `metadata.json`, mirrors pane output to `pane.log`, records lifecycle events in `events.log`, writes normal-exit `final.json`, and optionally registers a Clawhip-style `tmux watch`.\n- `prompt.sh` sends a text or `@file` prompt only after the pane looks like a ready SKC TUI; if the tmux session vanished, it refuses injection and prints the durable metadata/log/final/events recovery paths plus the last pane-log excerpt.\n- `tail.sh` captures bounded pane output for readiness and acceptance checks, with durable metadata, pane-log, event-log, and final-status fallback when tmux vanished.\n- `harness-tmux-owner-start.sh` starts the SKC harness control plane with the RuntimeOwner resident inside tmux for dogfood/debug cases that need visible owner liveness.\n\nConfiguration is runtime-only:\n\n```sh\nexport SKC_BIN=/path/to/skc                         # optional; defaults to command -v skc\nexport SKC_SESSION_FLAGS=\"--model provider/model\"   # optional interactive skc flags\nexport SKC_SESSION_ROUTER=clawhip                   # optional router binary\nexport SKC_SESSION_SKIP_ROUTER=1                    # skip router registration\nexport SKC_SESSION_STATE_DIR=/tmp/skc-session-state # optional durable metadata/log root\nexport SKC_SESSION_LOG_SEARCH_ROOT=$HOME/Workspace  # optional tail/prompt fallback search root\nexport SKC_SESSION_STALE_MINUTES=60                 # router stale window\nexport SKC_SESSION_KEYWORDS=\"/skill:ralplan,Question\"\n```\n\nNo token, channel id, mention, workspace root, or private host path is hard-coded. Pass channel/mention values at invocation time when your router needs them.\n\n## Example flow\n\n```sh\n# 1. Prepare a dedicated worktree.\ngit -C /repo/sayknow-cli fetch origin dev\ngit -C /repo/sayknow-cli worktree add \\\n  /repo/worktrees/sayknow-cli-issue-905-ctrl-shift-enter-newline \\\n  -b issue-905-ctrl-shift-enter-newline origin/dev\n\n# 2. Start the routed visible session.\n./scripts/skc-session/create.sh \\\n  sayknow-cli-issue-905-ctrl-shift-enter-newline \\\n  /repo/worktrees/sayknow-cli-issue-905-ctrl-shift-enter-newline \\\n  \"$CHANNEL_ID\" \\\n  \"$MENTION\"\n\n# 3. Confirm TUI readiness.\n./scripts/skc-session/tail.sh sayknow-cli-issue-905-ctrl-shift-enter-newline 80\n\n# 4. Inject the task prompt.\n./scripts/skc-session/prompt.sh \\\n  sayknow-cli-issue-905-ctrl-shift-enter-newline \\\n  @/tmp/issue-905-task.md\n\n# 5. Confirm real work started.\n./scripts/skc-session/tail.sh 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. If tmux disappears before terminal verdict, inspect the state path printed by `create.sh`: `metadata.json` identifies the worktree/session, `pane.log` contains the mirrored transcript, `events.log` records launch/exit milestones, and `final.json` is present when `skc` exited normally. Use `tail.sh <session-name> [lines]` to surface these artifacts without a live tmux server.\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- Restarting a vanished session without first checking its durable metadata, pane log, event log, and final status.\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",
+	"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\nscripts/skc-session/create.sh <session-name> <worktree-path> [channel-id] [mention]\n\n# prompt.sh\n# inject the real task after the TUI is ready\nscripts/skc-session/prompt.sh <session-name> @/path/to/task.md\n\n# tail.sh\n# inspect bounded pane output before/after prompt delivery\nscripts/skc-session/tail.sh <session-name> [lines]\n```\n\nThis repository includes a portable implementation in `scripts/skc-session/`. It keeps private routing values outside the script body: channel ids and mentions are runtime arguments, the router binary is optional, and credentials are never embedded. Host deployments can still override router behavior with environment variables instead of editing the scripts.\n\n\n## Included helper scripts\n\nThe `scripts/skc-session/` directory contains the public version of the operator helpers:\n\n- `create.sh` validates a dedicated git worktree, starts interactive `skc` in tmux, preserves the pane after exit, prints and writes the session-specific durable state path, writes `metadata.json`, mirrors pane output to `pane.log`, records lifecycle events in `events.log`, bridges the inner `skc` process to a public-safe `runtime-state.json`, writes normal-exit `final.json`, and optionally registers a Clawhip-style `tmux watch`.\n- `prompt.sh` sends a text or `@file` prompt only after the pane looks like a ready SKC TUI; if the tmux session vanished, it refuses injection and prints the durable metadata/log/final/events recovery paths plus the last pane-log excerpt.\n- `tail.sh` captures bounded pane output for readiness and acceptance checks, with durable metadata, pane-log, event-log, and final-status fallback when tmux vanished.\n- `harness-tmux-owner-start.sh` starts the SKC harness control plane with the RuntimeOwner resident inside tmux for dogfood/debug cases that need visible owner liveness.\n\nConfiguration is runtime-only:\n\n```sh\nexport SKC_BIN=/path/to/skc                         # optional; defaults to command -v skc\nexport SKC_SESSION_FLAGS=\"--model provider/model\"   # optional interactive skc flags\nexport SKC_SESSION_ROUTER=clawhip                   # optional router binary\nexport SKC_SESSION_SKIP_ROUTER=1                    # skip router registration\nexport SKC_SESSION_STATE_DIR=/tmp/skc-session-state # optional durable metadata/log root\nexport SKC_SESSION_LOG_SEARCH_ROOT=$HOME/Workspace  # optional tail/prompt fallback search root\nexport SKC_SESSION_STALE_MINUTES=60                 # router stale window\nexport SKC_SESSION_KEYWORDS=\"/skill:ralplan,Question\"\n```\n\nNo token, channel id, mention, workspace root, or private host path is hard-coded. Pass channel/mention values at invocation time when your router needs them.\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.\n./scripts/skc-session/create.sh \\\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.\n./scripts/skc-session/tail.sh sayknow-cli-issue-905-ctrl-shift-enter-newline 80\n\n# 4. Inject the task prompt.\n./scripts/skc-session/prompt.sh \\\n  sayknow-cli-issue-905-ctrl-shift-enter-newline \\\n  @/tmp/issue-905-task.md\n\n# 5. Confirm real work started.\n./scripts/skc-session/tail.sh 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. If tmux disappears before terminal verdict, inspect the state path printed by `create.sh`: `metadata.json` identifies the worktree/session and links `runtime-state.json`; `runtime-state.json` contains public-safe SKC lifecycle state (`completed` / `errored`, timestamps, cwd/workdir, branch, session file, exit code/signal/error when available) without pane logs, prompts, transcripts, tokens, config, environment dumps, or raw tool output; `pane.log` contains the private mirrored transcript; `events.log` records launch/exit milestones; `final.json` is present when the wrapper observed `skc` exit; and `vanished.json` is present when the external monitor observed the tmux session disappear. Use `tail.sh <session-name> [lines]` to surface these artifacts without a live tmux server.\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- Restarting a vanished session without first checking its durable metadata, pane log, event log, and final status.\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\nStandalone SKC also has a narrow direct-registration command for explicit user-provided server definitions:\n\n```bash\nskc mcp add context7 npx -y @upstash/context7-mcp\nskc mcp add docs --type http --url https://example.test/mcp --header Authorization=\"Bearer $TOKEN\"\nskc mcp list\nskc mcp remove context7\n```\n\n`skc mcp add` writes only the definition supplied on that invocation to SKC's own MCP config (`~/.skc/agent/mcp.json` by default, or `./.skc/mcp.json` with `--project`). It does not read Claude Code, Codex, OpenCode, Cursor, Gemini, Windsurf, or other live configs. `skc mcp list` and `skc mcp remove` print redacted definitions so env/header/auth/OAuth credential values are not exposed in public output.\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| Codex / Claude Code want a one-step install to delegate planning/execution to SKC | [Canonical sayknow-cli plugin](./hermes-mcp-bridge.md) under `plugins/` via `skc setup claude` / `skc setup codex` | Installs the Coordinator MCP server plus `skc_delegate_plan/execute/team` commands. Fail-closed: workdir-scoped roots, mutations off until opt-in. Install with `codex plugin marketplace add ./plugins` (verified on Codex CLI 0.139.0) or `/plugin marketplace add ./plugins` for Claude Code. |\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",
-	"telegram-onboarding.md": "# Telegram notification onboarding\n\nThis guide documents the current bundled Telegram notification setup path from\nSayknow-CLI source. It is for the managed reference client used by\n`skc notify setup`, not a separate remote-control product.\n\n## What you are setting up\n\nSayknow-CLI notifications are a loopback WebSocket SDK plus a managed Telegram\nreference daemon:\n\n- each SKC session publishes a local notification endpoint under\n  `.skc/state/notifications/<sessionId>.json`;\n- the managed Telegram daemon scans those endpoints, connects to them, and sends\n  action-needed events to the configured Telegram chat;\n- replies and inline button taps route back to the exact session/action through\n  the same notification protocol. When the configured chat supports Telegram\n  forum topics, each session is routed through its own topic.\n\nThe setup command stores global notification settings in your SKC agent config\nand later sessions auto-connect when notifications are enabled.\n\n## 1. Create a Telegram bot with BotFather\n\nUse Telegram's official BotFather flow to create a bot and copy its HTTP API\ntoken:\n\n- Official BotFather documentation: <https://core.telegram.org/bots/features#botfather>\n- General Telegram Bot API documentation: <https://core.telegram.org/bots/api>\n\nIn Telegram, open `@BotFather`, run `/newbot`, choose a display name and a unique\nusername ending in `bot`, then copy the token BotFather returns. Treat the token\nlike a password: do not paste it into logs, screenshots, issues, or shell history\nthat other people can read.\n\n## 2. Run the interactive setup wizard\n\nFrom any terminal where `skc` is installed:\n\n```sh\nskc notify setup\n```\n\nCurrent implementation path: `packages/coding-agent/src/cli/notify-cli.ts`.\n\nThe wizard does this:\n\n1. prompts for `Telegram BotFather token:`;\n2. validates the token with Telegram `getMe`;\n3. verifies private-chat Threaded Mode capability via `getMe.has_topics_enabled`\n   and, when it is off in an interactive run, prints @BotFather guidance and\n   lets you retry or continue unverified;\n4. asks you to message the bot from a private Telegram chat;\n5. polls Telegram `getUpdates` until it sees a private chat message;\n6. writes the paired chat id and enables notifications.\n\nThe setup pairing flow is private-chat only. If setup sees a `group`,\n`supergroup`, or `channel`, it rejects that chat and keeps waiting for a private\nDM. This is intentional for safe local discovery: group chats must not receive\nsession names, action ids, or pending status by accident.\n\nTelegram private-chat topics: the managed daemon's per-session delivery uses\nTelegram forum topics (`createForumTopic` + `message_thread_id`). Telegram now\nsupports forum topics in **private chats** when the bot owner enables **Threaded\nMode** for the bot in @BotFather. SKC cannot enable Threaded Mode through the Bot\nAPI; setup only detects the capability (`getMe.has_topics_enabled`) and guides the\nmanual BotFather toggle. A forum-enabled supergroup is no longer required.\n\nNote: enabling topics in private chats may require an additional Telegram Stars\npurchase fee, per Telegram's Terms of Service for Bot Developers.\n\nIf BotFather's **Bot Settings** menu does not show **Threads Settings** or\n**Threaded Mode**, do not treat that as a setup blocker. Telegram exposes this\ncapability unevenly across clients/accounts/bot states, and SKC cannot force the\nmenu to appear through the Bot API. The safe fallback is to continue setup with a\nprivate DM pairing: choose `skip` in the interactive prompt (or use\n`--token <botToken> --chat-id <chatId>` for non-interactive setup). SKC will save\n`threaded=unverified`/`threaded=unknown`, try topics at runtime when possible,\nand otherwise deliver notifications flat to the paired private chat with the\none-time nudge shown below.\n\nSetup verification is capability verification, not a delivery guarantee: even when\nsetup reports `threaded=verified`, the first runtime `createForumTopic` for the\npaired chat can still fail if Telegram refuses it. When per-session topics are\nunavailable, the daemon does **not** drop notifications — it routes them to the\nnormal (flat) paired chat and posts a one-time nudge: `turn on threaded mode from\nbotfather miniapp to receive skc notification!`. Because pairing is private-only,\nflat delivery lands in your own private DM with the bot.\n\nThe final setup line reports a `threaded=` status:\n\n- `threaded=verified`: the bot has Threaded Mode capability (`has_topics_enabled`\n  was true during setup);\n- `threaded=unverified`: Threaded Mode was off and you skipped, or setup ran\n  non-interactively; setup is saved, topics are attempted when available, and\n  runtime delivery falls back to the paired flat private chat when Telegram\n  refuses topic creation;\n- `threaded=unknown`: the Telegram response did not include `has_topics_enabled`,\n  so capability could not be verified.\n\nAfter setup succeeds, it prints a masked token and the paired chat id:\n\n```text\nNotifications enabled. botToken=1234…(len N) chatId=123456789 threaded=verified\n```\n\nThe raw token is never printed by SKC status/setup output after it is stored.\n\n## 3. Non-interactive setup\n\nFor scripts or CI-style local provisioning, pass the bot token and known private\nchat id explicitly. Non-interactive runs cannot prompt for the BotFather toggle,\nso if Threaded Mode is off (or the capability is unknown) setup is still saved\nwith a warning and a `threaded=unverified`/`threaded=unknown` status:\n\n```sh\nskc notify setup --token <botToken> --chat-id <chatId>\n```\n\nOptional redaction can be enabled during setup:\n\n```sh\nskc notify setup --token <botToken> --chat-id <chatId> --redact\n```\n\n`--redact` sets `notifications.redact = true`. Under redaction, idle summaries\nand streamed content are suppressed before remote delivery, but ask questions and\noptions remain readable because they must be answerable remotely.\n\n## 4. Check status without leaking secrets\n\n```sh\nskc notify status\n```\n\nThe status command reads the typed notification settings and prints:\n\n- `enabled`\n- masked `botToken`\n- paired `chatId`\n- `redact`\n\nIt uses the same masking helper as setup (`first 4 chars + … + length`), so it is\nsafe to paste into a support thread if the chat id itself is not sensitive in\nyour environment.\n\n## 5. What setup writes\n\n`skc notify setup` writes these settings through the SKC Settings layer:\n\n- `notifications.enabled = true`\n- `notifications.telegram.botToken = <token>`\n- `notifications.telegram.chatId = <paired chat id>`\n- `notifications.redact = true` only when `--redact` was passed\n\nAt runtime, notifications are considered globally configured only when all of\nthese are present:\n\n- `notifications.enabled`\n- `notifications.telegram.botToken`\n- `notifications.telegram.chatId`\n\nEnvironment/session precedence from `packages/coding-agent/src/notifications/config.ts`:\n\n1. `SKC_NOTIFICATIONS=0` is a hard opt-out.\n2. Local `/notify off` disables only the current session.\n3. `SKC_NOTIFICATIONS=1` or `SKC_NOTIFICATIONS_TOKEN` enables the legacy explicit path.\n4. A complete global setup enables notifications automatically.\n5. Otherwise notifications stay off.\n\n## 6. Start or reuse sessions\n\nAfter setup, start SKC normally:\n\n```sh\nskc --tmux\n```\n\nor use any other supported SKC launch mode. When the notification extension is\nregistered, the session writes its endpoint discovery file and ensures the\nTelegram daemon is running.\n\nThe daemon is a singleton per bot token/chat pair. Telegram allows only one\nactive `getUpdates` long-poll owner for a bot token, so SKC keeps a local daemon\nlock/state file and makes later sessions attach to the fresh owner instead of\nstarting a second poller. This avoids Telegram `409 Conflict` failures.\n\n## 7. Use the Telegram chat\n\nThe managed daemon prefers Telegram forum-topic delivery for per-session routing\nin the paired private chat. When Threaded Mode is available for the bot (verified\nduring setup via `getMe.has_topics_enabled`), the daemon calls\n`createForumTopic`/`editForumTopic` and sends messages with `message_thread_id`\nagainst the paired `notifications.telegram.chatId`. If BotFather does not show\n**Threads Settings**/**Threaded Mode**, or if Telegram refuses topic creation even\nafter setup reported `threaded=verified`, the daemon routes notifications to the\nnormal (flat) paired private chat and posts a one-time nudge to enable Threaded\nMode rather than dropping them.\n\nFlat private-chat fallback preserves outbound notifications and inline-button\nanswers, but it cannot provide a separate Telegram topic per SKC session. Free-\ntext replies and in-topic config commands depend on topic routing, so use\nThreaded Mode when you need multi-session reply separation from Telegram. Do not\npair a group, supergroup, or channel as a substitute: setup intentionally accepts\nonly a private DM, and hand-edited non-private chat ids remain fail-closed to\navoid leaking session data. If you specifically want group topics, create a\nforum-enabled Telegram group and use a separate/custom notification integration;\nthe bundled `skc notify setup` onboarding path is private-chat only.\n\nThe managed daemon can render:\n\n- session identity headers;\n- context updates;\n- live/finalized assistant output;\n- image attachments;\n- ask prompts with inline buttons;\n- activity/typing indicators;\n- inbound delivery acknowledgements.\n\nReply paths:\n\n- tap an inline button on an ask notification;\n- reply in the session topic with free text when forum-topic routing is\n  available;\n- send in-topic config commands:\n  - `/verbose`\n  - `/lean`\n  - `/verbosity <lean|verbose>`\n  - `/redact <on|off>`\n\nThe removed legacy `/answer <session-tag> <answer>` flow is not the primary UX;\nTelegram topic routing identifies the target session when the configured chat\nsupports it.\n\n## 8. Local `/notify` inside a session\n\nInside a running SKC session:\n\n- `/notify status` reports current session notification status without secrets;\n- `/notify off` disables the current session endpoint and removes its discovery\n  record without changing global setup;\n- `/notify on` re-enables the current session when global setup is complete and\n  `SKC_NOTIFICATIONS=0` is not forcing opt-out.\n\n## 9. Debug-only manual bridge\n\nThe manual Telegram CLI remains a reference/debug tool:\n\n```sh\nbun run packages/coding-agent/src/notifications/telegram-cli.ts --bot-token \"$BOT_TOKEN\"\n```\n\nIf a fresh managed daemon already owns the same bot token and paired chat, the\nmanual CLI refuses to start by default because a second poller would cause\nTelegram `409 Conflict`. Use `--force` only for deliberate debugging after you\nunderstand which daemon owns polling.\n\n## Troubleshooting\n\n### `Telegram getMe failed`\n\nThe BotFather token is invalid or was revoked. Re-copy the token from BotFather\nor regenerate it in the official BotFather UI.\n\n### Setup times out waiting for a private chat\n\nSend any message directly to the bot from your Telegram user account. Do not add\nit to a group for pairing; groups/supergroups/channels are intentionally rejected\nby the current setup flow.\n\n### Setup succeeds but no Telegram session messages arrive\n\nCheck the `threaded=` status from the last `skc notify setup` run. If it is\n`threaded=unverified` or `threaded=unknown`, first try the current Telegram\nclient's @BotFather flow for this bot. If BotFather's **Bot Settings** menu lacks\n**Threads Settings**/**Threaded Mode**, continue with the saved private-chat\npairing; this is supported. SKC cannot enable Threaded Mode through the Bot API,\nand no paid/Stars option is required just to receive flat private-chat\nnotifications. When `createForumTopic` is refused for the paired chat, the daemon\nfalls back to flat delivery in the paired private chat and posts a one-time\n`turn on threaded mode from botfather miniapp to receive skc notification!` nudge.\n\n### Telegram 409 conflict\n\nOnly one `getUpdates` poller can own a bot token. Stop any old manual bridge or\nexternal bot process using the same token, then let SKC's managed daemon own it.\n\n### A session does not send notifications\n\nCheck, in order:\n\n1. `skc notify status`\n2. `SKC_NOTIFICATIONS` is not set to `0`\n3. the session has not run `/notify off`\n4. the repo has `.skc/state/notifications/<sessionId>.json`\n5. the managed daemon state is fresh under the SKC agent notifications directory\n\nDo not paste endpoint discovery files into public issues; they contain the\nper-session WebSocket token needed by clients.\n",
+	"telegram-onboarding.md": "# Telegram notification onboarding\n\nThis guide documents the current bundled Telegram notification setup path from\nSayknow-CLI source. It is for the managed reference client used by\n`skc notify setup`, not a separate remote-control product.\n\n## What you are setting up\n\nSayknow-CLI notifications are a loopback WebSocket SDK plus a managed Telegram\nreference daemon:\n\n- each SKC session publishes a local notification endpoint under\n  `.skc/state/notifications/<sessionId>.json`;\n- the managed Telegram daemon scans those endpoints, connects to them, and sends\n  action-needed events to the configured Telegram chat;\n- replies and inline button taps route back to the exact session/action through\n  the same notification protocol. When the configured chat supports Telegram\n  forum topics, each session is routed through its own topic.\n\nThe setup command stores global notification settings in your SKC agent config\nand later sessions auto-connect when notifications are enabled.\n\n## 1. Create a Telegram bot with BotFather\n\nUse Telegram's official BotFather flow to create a bot and copy its HTTP API\ntoken:\n\n- Official BotFather documentation: <https://core.telegram.org/bots/features#botfather>\n- General Telegram Bot API documentation: <https://core.telegram.org/bots/api>\n\nIn Telegram, open `@BotFather`, run `/newbot`, choose a display name and a unique\nusername ending in `bot`, then copy the token BotFather returns. Treat the token\nlike a password: do not paste it into logs, screenshots, issues, or shell history\nthat other people can read.\n\n## 2. Run the interactive setup wizard\n\nFrom any terminal where `skc` is installed:\n\n```sh\nskc notify setup\n```\n\nCurrent implementation path: `packages/coding-agent/src/cli/notify-cli.ts`.\n\nThe wizard does this:\n\n1. prompts for `Telegram BotFather token:`;\n2. validates the token with Telegram `getMe`;\n3. verifies private-chat Threaded Mode capability via `getMe.has_topics_enabled`\n   and, when it is off in an interactive run, prints @BotFather guidance and\n   lets you retry or continue unverified;\n4. asks you to message the bot from a private Telegram chat;\n5. polls Telegram `getUpdates` until it sees a private chat message;\n6. writes the paired chat id and enables notifications.\n\nThe setup pairing flow is private-chat only. If setup sees a `group`,\n`supergroup`, or `channel`, it rejects that chat and keeps waiting for a private\nDM. This is intentional for safe local discovery: group chats must not receive\nsession names, action ids, or pending status by accident.\n\nTelegram private-chat topics: the managed daemon's per-session delivery uses\nTelegram forum topics (`createForumTopic` + `message_thread_id`). Telegram now\nsupports forum topics in **private chats** when the bot owner enables **Threaded\nMode** for the bot in @BotFather. SKC cannot enable Threaded Mode through the Bot\nAPI; setup only detects the capability (`getMe.has_topics_enabled`) and guides the\nmanual BotFather toggle. A forum-enabled supergroup is no longer required.\n\nNote: enabling topics in private chats may require an additional Telegram Stars\npurchase fee, per Telegram's Terms of Service for Bot Developers.\n\nIf BotFather's **Bot Settings** menu does not show **Threads Settings** or\n**Threaded Mode**, do not treat that as a setup blocker. Telegram exposes this\ncapability unevenly across clients/accounts/bot states, and SKC cannot force the\nmenu to appear through the Bot API. The safe fallback is to continue setup with a\nprivate DM pairing: choose `skip` in the interactive prompt (or use\n`--token <botToken> --chat-id <chatId>` for non-interactive setup). SKC will save\n`threaded=unverified`/`threaded=unknown`, try topics at runtime when possible,\nand otherwise deliver notifications flat to the paired private chat with the\none-time nudge shown below.\n\nSetup verification is capability verification, not a delivery guarantee: even when\nsetup reports `threaded=verified`, the first runtime `createForumTopic` for the\npaired chat can still fail if Telegram refuses it. When per-session topics are\nunavailable, the daemon does **not** drop notifications — it routes them to the\nnormal (flat) paired chat and posts a one-time nudge: `turn on threaded mode from\nbotfather miniapp to receive skc notification!`. Because pairing is private-only,\nflat delivery lands in your own private DM with the bot.\n\nThe final setup line reports a `threaded=` status:\n\n- `threaded=verified`: the bot has Threaded Mode capability (`has_topics_enabled`\n  was true during setup);\n- `threaded=unverified`: Threaded Mode was off and you skipped, or setup ran\n  non-interactively; setup is saved, topics are attempted when available, and\n  runtime delivery falls back to the paired flat private chat when Telegram\n  refuses topic creation;\n- `threaded=unknown`: the Telegram response did not include `has_topics_enabled`,\n  so capability could not be verified.\n\nAfter setup succeeds, it prints a masked token and the paired chat id:\n\n```text\nNotifications enabled. botToken=1234…(len N) chatId=123456789 threaded=verified\n```\n\nThe raw token is never printed by SKC status/setup output after it is stored.\n\n## 3. Non-interactive setup\n\nFor scripts or CI-style local provisioning, pass the bot token and known private\nchat id explicitly. Non-interactive runs cannot prompt for the BotFather toggle,\nso if Threaded Mode is off (or the capability is unknown) setup is still saved\nwith a warning and a `threaded=unverified`/`threaded=unknown` status:\n\n```sh\nskc notify setup --token <botToken> --chat-id <chatId>\n```\n\nOptional redaction can be enabled during setup:\n\n```sh\nskc notify setup --token <botToken> --chat-id <chatId> --redact\n```\n\n`--redact` sets `notifications.redact = true`. Under redaction, idle summaries\nand streamed content are suppressed before remote delivery, but ask questions and\noptions remain readable because they must be answerable remotely.\n\n## 4. Check status without leaking secrets\n\n```sh\nskc notify status\n```\n\nThe status command reads the typed notification settings and prints:\n\n- `enabled`\n- masked `botToken`\n- paired `chatId`\n- `redact`\n\nIt uses the same masking helper as setup (`first 4 chars + … + length`), so it is\nsafe to paste into a support thread if the chat id itself is not sensitive in\nyour environment.\n\n## 5. What setup writes\n\n`skc notify setup` writes these settings through the SKC Settings layer:\n\n- `notifications.enabled = true`\n- `notifications.telegram.botToken = <token>`\n- `notifications.telegram.chatId = <paired chat id>`\n- `notifications.redact = true` only when `--redact` was passed\n\nAt runtime, notifications are considered globally configured only when all of\nthese are present:\n\n- `notifications.enabled`\n- `notifications.telegram.botToken`\n- `notifications.telegram.chatId`\n\nEnvironment/session precedence from `packages/coding-agent/src/notifications/config.ts`:\n\n1. `SKC_NOTIFICATIONS=0` is a hard opt-out.\n2. Local `/notify off` disables only the current session.\n3. `SKC_NOTIFICATIONS=1` or `SKC_NOTIFICATIONS_TOKEN` enables the legacy explicit path.\n4. A complete global setup enables notifications automatically.\n5. Otherwise notifications stay off.\n\n## 6. Start or reuse sessions\n\nAfter setup, start SKC normally:\n\n```sh\nskc --tmux\n```\n\nor use any other supported SKC launch mode. When the notification extension is\nregistered, the session writes its endpoint discovery file and ensures the\nTelegram daemon is running.\n\nThe daemon is a singleton per bot token/chat pair. Telegram allows only one\nactive `getUpdates` long-poll owner for a bot token, so SKC keeps a local daemon\nlock/state file and makes later sessions attach to the fresh owner instead of\nstarting a second poller. This avoids Telegram `409 Conflict` failures.\n\n## 7. Use the Telegram chat\n\nThe managed daemon prefers Telegram forum-topic delivery for per-session routing\nin the paired private chat. When Threaded Mode is available for the bot (verified\nduring setup via `getMe.has_topics_enabled`), the daemon calls\n`createForumTopic`/`editForumTopic` and sends messages with `message_thread_id`\nagainst the paired `notifications.telegram.chatId`. If BotFather does not show\n**Threads Settings**/**Threaded Mode**, or if Telegram refuses topic creation even\nafter setup reported `threaded=verified`, the daemon routes notifications to the\nnormal (flat) paired private chat and posts a one-time nudge to enable Threaded\nMode rather than dropping them.\n\nFlat private-chat fallback preserves outbound notifications and inline-button\nanswers, but it cannot provide a separate Telegram topic per SKC session. Free-\ntext replies and in-topic config commands depend on topic routing, so use\nThreaded Mode when you need multi-session reply separation from Telegram. Do not\npair a group, supergroup, or channel as a substitute: setup intentionally accepts\nonly a private DM, and hand-edited non-private chat ids remain fail-closed to\navoid leaking session data. If you specifically want group topics, create a\nforum-enabled Telegram group and use a separate/custom notification integration;\nthe bundled `skc notify setup` onboarding path is private-chat only.\n\nThe managed daemon can render:\n\n- session identity headers;\n- context updates;\n- live/finalized assistant output;\n- image attachments;\n- ask prompts with inline buttons;\n- activity/typing indicators;\n- inbound delivery acknowledgements.\n\nReply paths:\n\n- tap an inline button on an ask notification;\n- reply in the session topic with free text when forum-topic routing is\n  available;\n- send in-topic config commands:\n  - `/verbose`\n  - `/lean`\n  - `/verbosity <lean|verbose>`\n  - `/redact <on|off>`\n- send paired-chat lifecycle commands from the Telegram command menu or by typing:\n  - `/session_create path <dir>`\n  - `/session_create worktree <repo> <branch>`\n  - `/session_create dir <newdir>`\n  - `/session_recent [create|resume]`\n  - `/session_close <sessionId>`\n  - `/session_resume <sessionId|prefix>`\n\nThe removed legacy `/answer <session-tag> <answer>` flow is not the primary UX;\nTelegram topic routing identifies the target session when the configured chat\nsupports it.\n\n## 8. Local `/notify` inside a session\n\nInside a running SKC session:\n\n- `/notify status` reports current session notification status without secrets;\n- `/notify off` disables the current session endpoint and removes its discovery\n  record without changing global setup;\n- `/notify on` re-enables the current session when global setup is complete and\n  `SKC_NOTIFICATIONS=0` is not forcing opt-out.\n\n## 9. Debug-only manual bridge\n\nThe manual Telegram CLI remains a reference/debug tool:\n\n```sh\nbun run packages/coding-agent/src/notifications/telegram-cli.ts --bot-token \"$BOT_TOKEN\"\n```\n\nIf a fresh managed daemon already owns the same bot token and paired chat, the\nmanual CLI refuses to start by default because a second poller would cause\nTelegram `409 Conflict`. Use `--force` only for deliberate debugging after you\nunderstand which daemon owns polling.\n\n## Troubleshooting\n\n### `Telegram getMe failed`\n\nThe BotFather token is invalid or was revoked. Re-copy the token from BotFather\nor regenerate it in the official BotFather UI.\n\n### Setup times out waiting for a private chat\n\nSend any message directly to the bot from your Telegram user account. Do not add\nit to a group for pairing; groups/supergroups/channels are intentionally rejected\nby the current setup flow.\n\n### Setup succeeds but no Telegram session messages arrive\n\nCheck the `threaded=` status from the last `skc notify setup` run. If it is\n`threaded=unverified` or `threaded=unknown`, first try the current Telegram\nclient's @BotFather flow for this bot. If BotFather's **Bot Settings** menu lacks\n**Threads Settings**/**Threaded Mode**, continue with the saved private-chat\npairing; this is supported. SKC cannot enable Threaded Mode through the Bot API,\nand no paid/Stars option is required just to receive flat private-chat\nnotifications. When `createForumTopic` is refused for the paired chat, the daemon\nfalls back to flat delivery in the paired private chat and posts a one-time\n`turn on threaded mode from botfather miniapp to receive skc notification!` nudge.\n\n### Telegram 409 conflict\n\nOnly one `getUpdates` poller can own a bot token. Stop any old manual bridge or\nexternal bot process using the same token, then let SKC's managed daemon own it.\n\n### A session does not send notifications\n\nCheck, in order:\n\n1. `skc notify status`\n2. `SKC_NOTIFICATIONS` is not set to `0`\n3. the session has not run `/notify off`\n4. the repo has `.skc/state/notifications/<sessionId>.json`\n5. the managed daemon state is fresh under the SKC agent notifications directory\n\nDo not paste endpoint discovery files into public issues; they contain the\nper-session WebSocket token needed by clients.\n",
+	"telegram-remote.md": "# Telegram Remote — control skc sessions from your phone\n\nTelegram Remote is a **tiny, safe operator remote** for Sayknow-CLI (`skc`)\nsessions. It lets you list, observe, start, and stop sessions from a Telegram\nchat — a control button, not a remote shell or cockpit. The real session owner\nstays on your machine (skc/tmux); Telegram only issues bounded, allowlisted\ncommands over the Coordinator MCP.\n\nThe gateway implementation lives in\n[`packages/telegram-remote`](../packages/telegram-remote/README.md); this guide\ncovers how to turn it on and use it.\n\n## What you get\n\nTwo backends, selected by `telegram.backend`:\n\n- **`coordinator`** (default) — multi-session lifecycle + observation. Bot\n  commands: `/sessions`, `/observe <id>`, `/start-session <preset> [task]`,\n  `/stop <id>`, `/help`.\n- **`rpc`** — attach/detach keyboard for one persistent `skc launch --output rpc`\n  session. Bot commands: `/attach`, `/detach`, `/status`, `/abort`, `/help`.\n\nAnything outside this vocabulary is rejected as unknown.\n\n## Quick start (skc settings)\n\n1. **Create a bot.** Message [@BotFather](https://t.me/BotFather) → `/newbot`,\n   copy the token (`123456:AA...`).\n2. **Find your Telegram id.** Message [@userinfobot](https://t.me/userinfobot)\n   (or read it from your bot's `getUpdates`). You need your numeric user id\n   and/or chat id.\n3. **Configure skc.** Open `skc`, go to **Settings → Integrations**, and set:\n   - **Telegram Remote** (`telegram.enabled`) → on\n   - **Bot Token** (`telegram.botToken`) → the @BotFather token\n   - **Allowed User IDs** (`telegram.allowedUserIds`) → your id\n     (comma-separated; or **Allowed Chat IDs**). At least one allowlist is\n     required — unlisted senders are refused with no hints.\n   - **Session Presets** (`telegram.presets`) → JSON array of approved presets\n     (see below) if you want `/start-session`.\n\n   Settings persist to your skc config; you can also edit them directly in\n   `config.yml` under the `telegram.*` keys.\n\n4. **Start the gateway.**\n\n   ```sh\n   skc telegram start     # start with current settings\n   skc telegram status    # show whether it is configured / running\n   skc telegram env        # print the SKC_TELEGRAM_REMOTE_* env it would use\n   ```\n\n   When `telegram.enabled` is on, skc also **auto-starts** the gateway in the\n   background (PID-tracked, detached) the next time you launch an interactive\n   session, so `skc telegram start` is only needed for a manual/one-off start.\n\n5. **Use it from Telegram.** Send `/help` to your bot, then `/sessions`,\n   `/observe <id>`, `/start-session <preset>`, `/stop <id>` (coordinator mode).\n\n### Presets (`/start-session`)\n\nSession creation is **preset-only** — no workdir/command/branch ever comes from\nchat. A preset binds a fixed workdir + session command + an optional task\ntemplate with a single length-capped `{{task}}` slot:\n\n```json\n[\n  {\n    \"id\": \"proj\",\n    \"workdir\": \"/home/you/src/project\",\n    \"sessionCommand\": \"skc --worktree\",\n    \"taskTemplate\": \"Use /skill:ralplan to plan: {{task}}\",\n    \"taskMaxLen\": 2000\n  }\n]\n```\n\n`/start-session proj fix the flaky auth test` starts the `proj` preset with the\ntask substituted into the template.\n\n## RPC mode (one persistent session)\n\nSet **Backend** (`telegram.backend`) → `rpc` to attach to a single existing\nowner-only socket exposed by `skc launch --output rpc --listen <socket>`. The\ngateway never spawns, kills, or tears down that session — it is only a Telegram\nattach/detach remote keyboard. RPC mode requires **RPC Socket**\n(`telegram.rpcSocket`) and **State Directory** (`telegram.stateDir`) for\nreconnect/resync. Agent questions and gates render as inline buttons;\nturn-complete delivery sends the final assistant text (HTML-escaped, chunked to\nTelegram's 4096-byte limit).\n\n## Safety properties\n\n- **Default deny.** Only allowlisted Telegram user/chat ids may issue any\n  command; unlisted senders get an identical boring refusal.\n- **Preset-only creation.** No raw workdir/command/branch/shell/RPC from chat.\n- **Forced-minimal mutations.** The coordinator runs with the smallest mutation\n  set — `sessions` (read + start), plus `reports` only when `/stop` is enabled\n  (**Enable /stop**, `telegram.enableStop`). `questions` is never enabled.\n- **Redaction by construction.** Only a typed projection (session id, derived\n  name, bounded status/turn enums, branch, timestamps, short sanitized blocker)\n  ever leaves the machine. Raw tmux tail, transcripts, tool IO, diffs, file\n  contents, env, prompts, and tokens are never transmitted.\n- **`/stop` confirmation.** `/stop <id>` arms; a second `/stop <id> confirm` (or\n  the inline **Confirm stop** button) records a graceful coordinator\n  `cancelled`. It does not kill a tmux process.\n\n## Rich messaging & push (optional)\n\n- **Rich Messages** (`telegram.enableRich`, default on) — HTML formatting +\n  inline **Observe/Stop/Refresh** buttons. Set off for plain text.\n- **Register Bot Menu** (`telegram.registerCommands`, default on) — registers\n  the Bot command menu at startup.\n- **Push Notifications** (`telegram.enablePush`) — Follow/Mute subscriptions via\n  the coordinator event-watch surface (needs a state dir). Push never widens the\n  transmitted-data allowlist.\n\n## Settings ↔ environment\n\nThe `skc telegram` command and autostart translate `telegram.*` settings into\n`SKC_TELEGRAM_REMOTE_*` environment variables consumed by the gateway (see\n`skc telegram env`). You can also run the gateway standalone with those env vars\ndirectly — see [`packages/telegram-remote/README.md`](../packages/telegram-remote/README.md)\nfor the full variable list, `.env.example`, and turnkey **systemd**/**launchd**\nservice examples for always-on deployment.\n\n## Non-goals\n\nTelegram Remote is not a remote RPC cockpit, remote shell, config editor, or\ntranscript viewer. It is a bounded lifecycle + observation button. For richer\ncontrol, use skc directly on the host.\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.",
@@ -100,7 +105,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"tools/resolve.md": "# resolve\n\n> Finalizes a queued preview action by applying or discarding it.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/resolve.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/resolve.md`\n- Key collaborators:\n  - `docs/resolve-tool-runtime.md` — preview/apply runtime reference\n  - `packages/coding-agent/src/extensibility/custom-tools/loader.ts` — forwards custom pending actions into the queue\n  - `packages/coding-agent/src/tools/ast-edit.ts` — built-in preview producer example\n  - `packages/coding-agent/src/session/agent-session.ts` — tool-choice queue and invoker access\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `action` | `\"apply\" | \"discard\"` | Yes | Whether to commit or reject the queued preview. |\n| `reason` | `string` | Yes | Required explanation passed through to the queued callback. |\n\n## Outputs\n- Single-shot result.\n- `execute()` returns whatever the queued invoker returns, with `details` wrapped/augmented to include:\n  - `action`\n  - `reason`\n  - `sourceToolName?`\n  - `label?`\n  - `sourceResultDetails?` — original `result.details` from the apply/reject callback when present\n- If `discard` has no custom reject callback, the default success payload is `Discarded: <label>. Reason: <reason>`.\n- The TUI renderer is inline and merges call+result into one block.\n\n## Flow\n1. Preview-producing code calls `queueResolveHandler(...)` with a label, source tool name, and `apply(reason)` callback, plus optional `reject(reason)`.\n2. `queueResolveHandler(...)` asks the session for a forced `resolve` tool choice and pushes it into the tool-choice queue with `pushOnce(...)`.\n3. The queued entry is marked `now: true`; if the model rejects that forced tool choice, `onRejected` returns `requeue`, so the reminder comes back.\n4. `queueResolveHandler(...)` also injects a `resolve-reminder` steering message: `This is a preview. Call the resolve tool to apply or discard these changes.`\n5. When `resolve.execute()` runs, it wraps the call in `untilAborted(...)` and fetches the current queue invoker with `session.peekQueueInvoker()`.\n6. If no invoker exists, it throws `ToolError(\"No pending action to resolve. Nothing to apply or discard.\")`.\n7. Otherwise it invokes the queued callback with `{ action, reason }`.\n8. For `apply`, it always executes the producer's `apply(reason)` callback.\n9. For `discard`, it executes `reject(reason)` when provided; if that callback is absent or returns `undefined`, `resolve` fabricates the default discard message.\n10. Before returning, it merges resolve metadata into `result.details` so renderer/UI code can show the action, label, and originating tool.\n\n## Modes / Variants\n- `apply`: runs the queued `apply(reason)` callback and returns its content.\n- `discard` with reject callback: runs `reject(reason)` and returns that callback's content.\n- `discard` without reject callback: returns the built-in `Discarded: ...` text payload.\n\n## Side Effects\n- Session state\n  - Consumes the current pending preview through the session tool-choice queue; there is no separate pending-action stack.\n  - Adds a `resolve-reminder` steering message when a preview is queued.\n- User-visible prompts / interactive UI\n  - No direct prompt. The visible effect depends on the preview-producing tool and the resolve renderer.\n- Background work / cancellation\n  - `untilAborted(...)` lets abort signals interrupt resolution before invoking the callback completes.\n\n## Limits & Caps\n- Hidden tool: not discoverable in the normal tool index (`packages/coding-agent/src/tools/resolve.ts`, `packages/coding-agent/src/session/agent-session.ts`).\n- Exactly one active queue invoker is consulted per call via `session.peekQueueInvoker()`.\n- There is no independent queue depth cap in this tool; ordering follows the shared tool-choice queue (`docs/resolve-tool-runtime.md`).\n\n## Errors\n- No pending preview: throws `ToolError(\"No pending action to resolve. Nothing to apply or discard.\")`.\n- Any exception from the queued `apply` / `reject` callback propagates through `resolve`.\n- Aborts during `untilAborted(...)` surface as the underlying abort error from the utility.\n\n## Notes\n- `reason` is informational; `resolve` passes it through but does not interpret it.\n- `queueResolveHandler(...)` is the canonical built-in integration point; custom tools use `pushPendingAction(...)`, which the loader forwards into the same mechanism.\n- The tool only works because another tool already staged a preview and forced a one-shot `resolve` choice.\n- `sourceResultDetails` is added only when the apply/reject callback returned a non-null `details` field; custom pending-action `details` are not forwarded automatically by the loader.\n",
 	"tools/rewind.md": "# rewind\n\n> End an active checkpoint by pruning exploratory context and retaining a concise report.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/checkpoint.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/rewind.md`\n- Key collaborators:\n  - `packages/coding-agent/src/session/agent-session.ts` — validates pending rewind state, applies the actual rewind, and injects the retained report.\n  - `packages/coding-agent/src/session/session-manager.ts` — branches the persisted session tree and appends persisted summary/report entries.\n  - `packages/coding-agent/src/session/messages.ts` — converts persisted `branch_summary` entries into LLM-visible branch-summary messages on rebuilt context.\n  - `packages/coding-agent/src/tools/index.ts` — registers the tool and shares the `checkpoint.enabled` gate.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `report` | `string` | Yes | Investigation findings. `execute()` trims it and rejects the empty result. |\n\n## Outputs\nThe tool returns a single text result plus structured details:\n\n- text body:\n  - `Rewind requested.`\n  - `Report captured for context replacement.`\n- `details`:\n  - `report: string` — trimmed report text\n  - `rewound: true`\n\nThe returned tool result is not the final rewind. `AgentSession` waits until `turn_end`, then applies the rewind side effects asynchronously.\n\n## Flow\n1. `RewindTool.createIf()` in `packages/coding-agent/src/tools/checkpoint.ts` hides the tool from subagents.\n2. `RewindTool.execute()` rejects subagent calls with `ToolError(\"Checkpoint not available in subagents.\")`.\n3. It rejects calls with no active checkpoint using `ToolError(\"No active checkpoint.\")`.\n4. It trims `params.report`; if empty, it throws `ToolError(\"Report cannot be empty.\")`.\n5. It returns a `toolResult()` with `details.report` and `details.rewound = true`.\n6. On `tool_execution_end`, `AgentSession` extracts the report from `details.report` or the first text content block and stores it in `#pendingRewindReport`.\n7. On `turn_end`, if `#pendingRewindReport` is set, `AgentSession.#applyRewind()` runs.\n8. `#applyRewind()` computes `safeCount = clamp(checkpointMessageCount, 0, agent.state.messages.length)` and calls `agent.replaceMessages(agent.state.messages.slice(0, safeCount))`.\n9. It then calls `sessionManager.branchWithSummary(checkpointEntryId, report, { startedAt })`. That moves the persisted session leaf back to the checkpoint entry and appends a new `branch_summary` entry whose `summary` is the rewind report.\n10. If `checkpointEntryId` no longer resolves, it logs a warning and falls back to `branchWithSummary(null, report, { startedAt })`, branching from root instead.\n11. `#applyRewind()` appends a hidden in-memory custom message `{ customType: \"rewind-report\", content: report, display: false }` and persists the same payload through `sessionManager.appendCustomMessageEntry(\"rewind-report\", ...)` with `details = { startedAt, rewoundAt }`.\n12. Finally it clears `#checkpointState` and `#pendingRewindReport`.\n\n## Modes / Variants\n- Normal rewind: checkpoint entry exists; session history branches from that exact entry.\n- Fallback rewind: checkpoint entry ID is missing from the current session tree; rewind branches from root and logs a warning.\n- Immediate turn-end apply: rewind side effects happen only after the surrounding assistant turn finishes, not inside `RewindTool.execute()`.\n\n## Side Effects\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - Replaces in-memory conversation history with the prefix ending at the checkpoint tool result.\n  - Adds a hidden custom message `rewind-report` carrying the retained report.\n  - Clears the active checkpoint state and pending rewind report.\n  - Repositions the persisted session leaf to the checkpoint branch point and appends new session entries.\n- Filesystem\n  - Persists the new `branch_summary` and `custom_message` entries into the session `.jsonl` file through normal `SessionManager` append persistence.\n  - Session files are named `<ISO-timestamp-with-:-and-.-replaced>_<uuidv7>.jsonl` in the session directory; default directory selection is documented in `SessionManager.create()` as `~/.skc/agent/sessions/<encoded-cwd>/` when no override is passed.\n- User-visible prompts / interactive UI\n  - The tool result itself is visible.\n  - The persisted `branch_summary` becomes an LLM-visible `branchSummary` message when context is rebuilt from `SessionManager.buildSessionContext()`; `messages.ts` renders it as a user-role text message using `packages/agent/src/compaction/prompts/branch-summary-context.md`.\n  - The persisted `rewind-report` custom message also participates in rebuilt LLM context because `custom_message` entries are converted through `createCustomMessage()`.\n- Background work / cancellation\n  - Rewind application is deferred to `turn_end`. There is no separate job object or cancel handle.\n\n## Limits & Caps\n- Availability is gated by `checkpoint.enabled`, default `false`, in `packages/coding-agent/src/config/settings-schema.ts`.\n- Top-level sessions only.\n- Requires exactly one active checkpoint; there is no path to name or choose among multiple checkpoints.\n- Report text must be non-empty after `trim()`.\n- Rewind restores only the message prefix recorded by `checkpointMessageCount`; there is no file restore, artifact restore, blob restore, or process restore path.\n- Persisted report/summary content is still subject to the global session persistence cap `MAX_PERSIST_CHARS = 500_000` in `packages/coding-agent/src/session/session-manager.ts`.\n\n## Errors\n- `ToolError(\"Checkpoint not available in subagents.\")` — thrown for subagent sessions.\n- `ToolError(\"No active checkpoint.\")` — thrown when no checkpoint state is present.\n- `ToolError(\"Report cannot be empty.\")` — thrown when the trimmed report is empty.\n- Missing checkpoint entry IDs during apply do not fail the tool call; `#applyRewind()` catches the error, logs `Rewind branch checkpoint missing, falling back to root`, and branches from root.\n- If the agent turn is aborted while a checkpoint is active, `AgentSession` clears checkpoint state rather than applying a delayed rewind.\n\n## Notes\n- Checkpoint selection is implicit. `rewind` always targets the single `#checkpointState` captured by the last successful `checkpoint`; there is no checkpoint list, label, or ID parameter.\n- Restored state is transcript/session-tree state only:\n  - in-memory `agent.state.messages` prefix up to `checkpointMessageCount`\n  - persisted session leaf reset to `checkpointEntryId` or root fallback\n  - retained rewind report as `branch_summary` and hidden `rewind-report` custom message\n- Not restored:\n  - filesystem contents\n  - git state\n  - artifacts under `packages/coding-agent/src/session/artifacts.ts`\n  - blob-store payloads under `packages/coding-agent/src/session/blob-store.ts`\n  - prompt history rows in `packages/coding-agent/src/session/history-storage.ts`\n  - auth or other agent storage in `packages/coding-agent/src/session/agent-storage.ts`\n- There is no concurrent-edit reconciliation. If code or session-adjacent state changes during the checkpoint window, rewind does not merge or revert them; it only drops conversation context and rewires the session branch.\n- Rewind is not destructive to persisted session history. `branchWithSummary()` appends a new `branch_summary` entry and moves the leaf; it does not delete the abandoned path from the `.jsonl` session log. The active context is cut over to the new branch, but the old entries remain in session storage.\n",
 	"tools/search.md": "# search\n\n> Search file contents with a regex across files, directories, globs, and internal URLs.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/search.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/search.md`\n- Key collaborators:\n  - `packages/coding-agent/src/tools/match-line-format.ts` — model-facing anchor formatting.\n  - `packages/coding-agent/src/tools/path-utils.ts` — path normalization, glob splitting, internal URL resolution.\n  - `packages/coding-agent/src/tools/file-recorder.ts` — file ordering for grouped output.\n  - `packages/coding-agent/src/tools/grouped-file-output.ts` — grouped per-file text layout.\n  - `packages/coding-agent/src/session/streaming-output.ts` — line truncation and final byte truncation.\n  - `packages/coding-agent/src/config/settings-schema.ts` — default context lines.\n  - `packages/natives/native/index.d.ts` — native `grep()` types exposed to TS.\n  - `crates/pi-natives/src/grep.rs` — native regex/file search implementation.\n  - `docs/natives-text-search-pipeline.md` — native search pipeline overview.\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `pattern` | `string` | Yes | Regex pattern. `search.ts` trims it and rejects empty input. The native matcher enables multiline only when the pattern text contains a literal newline or the two-character sequence `\\\\n`. The model prompt explicitly documents literal-brace escaping such as ``interface\\\\{\\\\}``, although the native layer also auto-escapes braces that cannot be valid repetition quantifiers. |\n| `paths` | `string[]` | Yes | One or more file paths, directory paths, glob-like paths, or internal URLs. Empty strings are rejected after trimming/quote stripping. Internal URLs must resolve to a backing file and cannot contain glob characters. |\n| `i` | `boolean` | No | Case-insensitive search. Defaults to `false`. Passed to native `ignoreCase`. |\n| `gitignore` | `boolean` | No | Respect `.gitignore` during directory scans. Defaults to `true`. Passed to native `gitignore`. |\n| `skip` | `number` | No | Global match offset. Defaults to `0`. `search.ts` floors finite numbers and rejects negative or non-finite values. |\n\n## Outputs\nThe tool returns a single text block in `content[0].text` plus structured `details`.\n\n- Match lines are formatted by `formatMatchLine()` as `*<anchor>|<line>` for matches and ` <anchor>|<line>` for context.\n  - Hashline mode: `*5th|content`, ` 9x}|content`.\n  - Plain mode: `*5|content`, ` 9|content`.\n- Directory results are grouped by file, with `# <path>` headings and blank lines between groups.\n- `details` may include:\n  - `scopePath` — formatted search scope.\n  - `matchCount`, `fileCount`, `files`, `fileMatches` — counts for the returned page, not necessarily total corpus counts.\n  - `matchLimitReached` — visible-page limit hit (`100`).\n  - `resultLimitReached` — native preselection limit hit (`500`).\n  - `linesTruncated` — one or more matched lines were shortened to `1024` chars plus `…`.\n  - `truncated` and `meta.truncation` — final text output was head-truncated by `truncateHead()`.\n  - `displayContent` — TUI-only rendering text with `│` gutters instead of model anchors.\n  - `missingPaths` — multi-path entries skipped because their base path did not exist.\n- No-match result text is `No matches found`, optionally followed by `Skipped missing paths: ...`.\n\n## Flow\n1. `SearchTool.execute()` validates and normalizes input in `packages/coding-agent/src/tools/search.ts`:\n   - trims `pattern`, rejects empty patterns;\n   - normalizes `skip` to a non-negative integer;\n   - reads `search.contextBefore` and `search.contextAfter` from session settings (`1` and `3` by default);\n   - enables multiline only when `pattern` contains `\\n` or an actual newline.\n2. Each `paths` entry is normalized with `normalizePathLikeInput()`.\n3. Internal URLs are resolved through `session.internalRouter`:\n   - glob metacharacters (`*`, `?`, `[`, `{`) are rejected for internal URLs;\n   - URLs without `resource.sourcePath` fail;\n   - immutable sources are tracked so output can suppress editable hashline anchors per file.\n4. For multi-path calls, `partitionExistingPaths()` skips only ENOENT entries. If every entry is missing, the tool errors.\n5. Path resolution branches:\n   - one entry: `parseSearchPath()` splits `basePath` and optional glob;\n   - multiple entries: `resolveExplicitSearchPaths()` computes a common base directory, brace-union glob, exact-file list, or degenerate-root target list.\n6. `search.ts` stats the resolved base path to decide file vs directory behavior.\n7. It calls native `grep()` from `@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/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`, `edit`, `write`, `search`, and `find` 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  - 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",
@@ -108,6 +113,6 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"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",
 	"tree.md": "# `/tree` Command Reference\n\n`/tree` opens the interactive **Session Tree** navigator. It lets you jump to any entry in the current session file and continue from that point.\n\nThis is an in-file leaf move, not a new session export.\n\n## What `/tree` does\n\n- Builds a tree from current session entries (`SessionManager.getTree()`)\n- Opens `TreeSelectorComponent` with keyboard navigation, filters, and search\n- On selection, calls `AgentSession.navigateTree(targetId, { summarize, customInstructions })`\n- Rebuilds visible chat from the new leaf path\n- Optionally prefills editor text when selecting a user/custom message\n\nPrimary implementation:\n\n- `src/modes/controllers/input-controller.ts` (`/tree`, keybinding wiring, double-escape behavior)\n- `src/modes/controllers/selector-controller.ts` (tree UI launch + summary prompt flow)\n- `src/modes/components/tree-selector.ts` (navigation, filters, search, labels, rendering)\n- `src/session/agent-session.ts` (`navigateTree` leaf switching + optional summary)\n- `src/session/session-manager.ts` (`getTree`, `branch`, `branchWithSummary`, `resetLeaf`, label persistence)\n\n## How to open it\n\nAny of the following opens the same selector:\n\n- `/tree`\n- configured keybinding action `tree`\n- double-escape on empty editor when `doubleEscapeAction = \"tree\"` (default)\n- `/branch` when `doubleEscapeAction = \"tree\"` (routes to tree selector instead of user-only branch picker)\n\n## Tree UI model\n\nThe tree is rendered from session entry parent pointers (`id` / `parentId`).\n\n- Children are sorted by timestamp ascending (older first, newer lower)\n- Active branch (path from root to current leaf) is marked with a bullet\n- Labels (if present) render as `[label]` before node text\n- If multiple roots exist (orphaned/broken parent chains), they are shown under a virtual branching root\n\n```text\nExample tree view (active path marked with •):\n\n├─ user: \"Start task\"\n│  └─ assistant: \"Plan\"\n│     ├─ • user: \"Try approach A\"\n│     │  └─ • assistant: \"A result\"\n│     │     └─ • [milestone] user: \"Continue A\"\n│     └─ user: \"Try approach B\"\n│        └─ assistant: \"B result\"\n```\n\nThe selector recenters around current selection and shows up to:\n\n- `max(5, floor(terminalHeight / 2))` rows\n\n## Keybindings inside tree selector\n\n- `Up` / `Down`: move selection (wraps)\n- `Left` / `Right`: page up / page down\n- `Enter`: select node\n- `Esc`: clear search if active; otherwise close selector\n- `Ctrl+C`: close selector\n- `Type`: append to search query\n- `Backspace`: delete search character\n- `Shift+L`: edit/clear label on selected entry\n- `Ctrl+O`: cycle filter forward\n- `Shift+Ctrl+O`: cycle filter backward\n- `Alt+D/T/U/L/A`: jump directly to specific filter mode\n\n## Filters and search semantics\n\nFilter modes (`TreeList`):\n\n1. `default`\n2. `no-tools`\n3. `user-only`\n4. `labeled-only`\n5. `all`\n\n### `default`\n\nShows most conversational nodes, but hides bookkeeping entry types:\n\n- `label`\n- `custom`\n- `model_change`\n- `thinking_level_change`\n\n### `no-tools`\n\nSame as `default`, plus hides `toolResult` messages.\n\n### `user-only`\n\nOnly `message` entries where role is `user`.\n\n### `labeled-only`\n\nOnly entries that currently resolve to a label.\n\n### `all`\n\nEverything in the session tree, including bookkeeping/custom entries.\n\n### Tool-only assistant node behavior\n\nAssistant messages that contain **only tool calls** (no text) are hidden by default in all filtered views unless:\n\n- message is error/aborted (`stopReason` not `stop`/`toolUse`), or\n- it is the current leaf (always kept visible)\n\n### Search behavior\n\n- Query is tokenized by spaces\n- Matching is case-insensitive\n- All tokens must match (AND semantics)\n- Searchable text includes label, role, and type-specific content (message text, branch summary text, custom type, tool command snippets, etc.)\n\n## Selection outcomes (important)\n\n`navigateTree` computes new leaf behavior from selected entry type:\n\n### Selecting `user` message\n\n- New leaf becomes selected entry’s `parentId`\n- If parent is `null` (root user message), leaf resets to root (`resetLeaf()`)\n- Selected message text is copied to editor for editing/resubmit\n\n### Selecting `custom_message`\n\n- Same leaf rule as user messages (`parentId`)\n- Text content is extracted and copied to editor\n\n### Selecting non-user node (assistant/tool/summary/compaction/custom bookkeeping/etc.)\n\n- New leaf becomes selected node id\n- Editor is not prefilled\n\n### Selecting current leaf\n\n- No-op; selector closes with “Already at this point”\n\n```text\nSelection decision (simplified):\n\nselected node\n   │\n   ├─ is current leaf? ── yes ──> close selector (no-op)\n   │\n   ├─ is user/custom_message? ── yes ──> leaf := parentId (or resetLeaf for root)\n   │                                     + prefill editor text\n   │\n   └─ otherwise ──> leaf := selected node id\n                    + no editor prefill\n```\n\n## Summary-on-switch flow\n\nSummary prompt is controlled by `branchSummary.enabled` (default: `false`).\n\nWhen enabled, after picking a node the UI asks:\n\n- `No summary`\n- `Summarize`\n- `Summarize with custom prompt`\n\nFlow details:\n\n- Escape in summary prompt reopens tree selector\n- Custom prompt cancellation returns to summary choice loop\n- During summarization, UI shows loader and binds `Esc` to `abortBranchSummary()`\n- If summarization aborts, tree selector reopens and no move is applied\n\n`navigateTree` internals:\n\n- Collects abandoned-branch entries from old leaf to common ancestor\n- Emits `session_before_tree` (extensions can cancel or inject summary)\n- Uses default summarizer only if requested and needed\n- Applies move with:\n  - `branchWithSummary(...)` when summary exists\n  - `branch(newLeafId)` for non-root move without summary\n  - `resetLeaf()` for root move without summary\n- Replaces agent conversation with rebuilt session context\n- Emits `session_tree`\n\nNote: if user requests summary but there is nothing to summarize, navigation proceeds without creating a summary entry.\n\n## Labels\n\nLabel edits in tree UI call `appendLabelChange(targetId, label)`.\n\n- non-empty label sets/updates resolved label\n- empty label clears it\n- labels are stored as append-only `label` entries\n- tree nodes display resolved label state, not raw label-entry history\n\n## `/tree` vs adjacent operations\n\n| Operation | Scope                                            | Result                                                                                                                                                   |\n| --------- | ------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `/tree`   | Current session file                             | Moves leaf to selected point (same file)                                                                                                                 |\n| `/branch` | Usually current session file -> new session file | By default branches from selected **user** message into a new session file; if `doubleEscapeAction = \"tree\"`, `/branch` opens tree navigation UI instead |\n| `/fork`   | Whole current session                            | Duplicates session into a new persisted session file                                                                                                     |\n| `/resume` | Session list                                     | Switches to another session file                                                                                                                         |\n\nKey distinction: `/tree` is a navigation/repositioning tool inside one session file. `/branch`, `/fork`, and `/resume` all change session-file context.\n\n## Operator workflows\n\n### Re-run from an earlier user prompt without losing current branch\n\n1. `/tree`\n2. search/select earlier user message\n3. choose `No summary` (or summarize if needed)\n4. edit prefilled text in editor\n5. submit\n\nEffect: new branch grows from selected point within same session file.\n\n### Leave current branch with context breadcrumb\n\n1. enable `branchSummary.enabled`\n2. `/tree` and select target node\n3. choose `Summarize` (or custom prompt)\n\nEffect: a `branch_summary` entry is appended at the target position before continuing.\n\n### Investigate hidden bookkeeping entries\n\n1. `/tree`\n2. press `Alt+A` (all)\n3. search for `model`, `thinking`, `custom`, or labels\n\nEffect: inspect full internal timeline, not just conversational nodes.\n\n### Bookmark pivot points for later jumps\n\n1. `/tree`\n2. move to entry\n3. `Shift+L` and set label\n4. later use `Alt+L` (`labeled-only`) to jump quickly\n\nEffect: fast navigation among durable branch landmarks.\n",
 	"ttsr-injection-lifecycle.md": "# TTSR Injection Lifecycle\n\nThis document covers the current Time Traveling Stream Rules (TTSR) runtime path from rule discovery to stream interruption, retry injection, extension notifications, and session-state handling.\n\n## Implementation files\n\n- [`../src/sdk.ts`](../packages/coding-agent/src/sdk.ts)\n- [`../src/export/ttsr.ts`](../packages/coding-agent/src/export/ttsr.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/prompts/system/ttsr-interrupt.md`](../packages/coding-agent/src/prompts/system/ttsr-interrupt.md)\n- [`../src/capability/index.ts`](../packages/coding-agent/src/capability/index.ts)\n- [`../src/extensibility/extensions/types.ts`](../packages/coding-agent/src/extensibility/extensions/types.ts)\n- [`../src/extensibility/hooks/types.ts`](../packages/coding-agent/src/extensibility/hooks/types.ts)\n- [`../src/extensibility/custom-tools/types.ts`](../packages/coding-agent/src/extensibility/custom-tools/types.ts)\n- [`../src/modes/controllers/event-controller.ts`](../packages/coding-agent/src/modes/controllers/event-controller.ts)\n\n## 1. Discovery feed and rule registration\n\nAt session creation, `createAgentSession()` loads discovered rules and constructs a `TtsrManager`:\n\n```ts\nconst ttsrSettings = settings.getGroup(\"ttsr\");\nconst ttsrManager = new TtsrManager(ttsrSettings);\nconst rulesResult = await loadCapability<Rule>(ruleCapability.id, { cwd });\nfor (const rule of rulesResult.items) {\n  if (rule.condition?.length && ttsrManager.addRule(rule)) continue;\n  // non-TTSR rules continue through normal rule handling\n}\n```\n\n### Pre-registration dedupe behavior\n\n`loadCapability(\"rules\")` deduplicates by `rule.name` with first-wins semantics (higher provider priority first). Shadowed duplicates are removed before TTSR registration.\n\n### `TtsrManager.addRule()` behavior\n\nRegistration is skipped when:\n\n- `rule.condition` is absent or all condition regexes fail to compile\n- a rule with the same `rule.name` was already registered in this manager\n- the rule scope excludes all monitored streams\n\nInvalid regex conditions and unreachable scopes are logged as warnings and ignored; session startup continues.\n\n### Setting caveat\n\n`TtsrSettings.enabled` is loaded into the manager but is not currently checked in runtime gating. If TTSR rules exist, matching still runs.\n\n## 2. Streaming monitor lifecycle\n\nTTSR detection runs inside `AgentSession.#handleAgentEvent`.\n\n### Turn start\n\nOn `turn_start`, the stream buffer is reset:\n\n- `ttsrManager.resetBuffer()`\n\n### During stream (`message_update`)\n\nWhen assistant updates arrive and rules exist:\n\n- monitor `text_delta`, `thinking_delta`, and `toolcall_delta`\n- append delta into a source/tool scoped manager buffer\n- call `checkDelta(delta, matchContext)`\n\n`checkDelta()` iterates registered rules and returns all matching rules that pass scope, global-path, condition, and repeat policy checks.\n\n## 3. Trigger decision and immediate abort path\n\nWhen one or more rules match and at least one matched rule allows interruption:\n\n1. Matched rules are deduplicated into `#pendingTtsrInjections`.\n2. `#ttsrAbortPending = true` and a TTSR resume gate is created.\n3. `agent.abort()` is called immediately.\n4. `ttsr_triggered` event is emitted asynchronously (fire-and-forget).\n5. retry work is scheduled via the post-prompt task scheduler with a 50ms delay.\n\nAbort is not blocked on extension callbacks.\n\n## 4. Retry scheduling, context mode, and reminder injection\n\nAfter the 50ms timeout:\n\n1. `#ttsrAbortPending = false`\n2. read `ttsrManager.getSettings().contextMode`\n3. if `contextMode === \"discard\"`, drop the targeted partial assistant output with `agent.replaceMessages(...slice(0, targetAssistantIndex))`\n4. build injection content from pending rules using `ttsr-interrupt.md` template\n5. append and persist a hidden `custom_message`/runtime custom message with `customType: \"ttsr-injection\"` and `details.rules`\n6. mark those rule names injected, persist a `ttsr_injection` entry, and call `agent.continue()` to retry generation\n\nTemplate payload is:\n\n```xml\n<system-interrupt reason=\"rule_violation\" rule=\"{{name}}\" path=\"{{path}}\">\n...\n{{content}}\n</system-interrupt>\n```\n\nPending injections are cleared after content generation.\n\n### `contextMode` behavior on partial output\n\n- `discard`: partial/aborted assistant message is removed before retry.\n- `keep`: partial assistant output remains in conversation state; reminder is appended after it.\n\n### Non-interrupting matches\n\nNon-interrupting matches split by `matchContext.source`:\n\n- **`source === \"tool\"` (tool-source match).** The rule is bucketed into `#perToolTtsrInjections`, keyed by the matched tool call's `id`. There is **no** deferred follow-up turn and the stream is not aborted. When the tool actually produces a result, the `afterToolCall` hook prepends a rendered `ttsr-tool-reminder.md` block to `ctx.result.content` (a single `text` block inserted ahead of the tool's own content), and persists a `ttsr_injection` entry with the consumed rule names. The template payload is:\n\n  ```xml\n  <system-reminder reason=\"rule_violation\" rule=\"{{name}}\" path=\"{{path}}\">\n  ...\n  {{content}}\n  </system-reminder>\n  ```\n\n- **`source === \"text\"` / `\"thinking\"` (prose-source match).** Behavior is unchanged: the rule is queued in `#pendingTtsrInjections` and, after a successful non-error, non-aborted assistant message, `AgentSession` injects the hidden `ttsr-injection` custom message as a follow-up and schedules continuation.\n\nWithin a single matching batch, each rule is attached to exactly one sibling tool call — if multiple sibling tool calls would satisfy the same rule, deduplication picks one and the others are left untouched. Multiple distinct rules can still fold onto the same tool call.\n\n#### Implications for tool authors and transcript readers\n\n- The tool's own `toolResult` content is preserved verbatim; the reminder is **prepended** as an additional leading text block. Renderers that assume `content[0]` is the tool's primary output must scan past any block whose text begins with `<system-reminder reason=\"rule_violation\"` (or filter on the wrapper tag) to find the real payload.\n- The reminder is in-band on the tool result, not a separate `custom_message`/`ttsr-injection` entry. Transcript readers looking for non-interrupting TTSR activity on tool-source rules MUST inspect tool results (and the persisted `ttsr_injection` entry list), not just synthetic injection entries.\n- A single tool result may carry reminders for several rules concatenated with a blank line between rendered templates.\n- If the assistant message ends with `stopReason === \"aborted\"` or `\"error\"` before the matched tools run, the pending per-tool buckets are cleared — those rules are **not** persisted as injected and remain eligible to re-trigger on a future turn (subject to repeat policy).\n\n## 5. Repeat policy and gap logic\n\n`TtsrManager` tracks `#messageCount` and per-rule `lastInjectedAt`.\n\n### `repeatMode: \"once\"`\n\nA rule can trigger only once after it has an injection record.\n\n### `repeatMode: \"after-gap\"`\n\nA rule can re-trigger only when:\n\n- `messageCount - lastInjectedAt >= repeatGap`\n\n`messageCount` increments on `turn_end`, so gap is measured in completed turns, not stream chunks.\n\n## 6. Event emission and extension/hook surfaces\n\n### Session event\n\n`AgentSessionEvent` includes:\n\n```ts\n{ type: \"ttsr_triggered\"; rules: Rule[] }\n```\n\n### Extension runner\n\n`#emitSessionEvent()` routes the event to:\n\n- extension listeners (`ExtensionRunner.emit({ type: \"ttsr_triggered\", rules })`)\n- local session subscribers\n\n### Hook and custom-tool typing\n\n- extension API exposes `on(\"ttsr_triggered\", ...)`\n- hook API exposes `on(\"ttsr_triggered\", ...)`\n- custom tools receive `onSession({ reason: \"ttsr_triggered\", rules })`\n\n### Interactive-mode rendering difference\n\nInteractive mode uses `session.isTtsrAbortPending` to suppress showing the aborted assistant stop reason as a visible failure during TTSR interruption, and renders a `TtsrNotificationComponent` when the event arrives.\n\n## 7. Persistence and resume state (current implementation)\n\n`SessionManager` persists injected-rule state:\n\n- entry type: `ttsr_injection`\n- append API: `appendTtsrInjection(ruleNames)`\n- query API: `getInjectedTtsrRules()`\n- context reconstruction includes `SessionContext.injectedTtsrRules`\n\n`TtsrManager` supports restoration via `restoreInjected(ruleNames)`.\n\n### Current wiring status\n\nIn the current runtime path:\n\n- interrupted injections append a hidden `custom_message` with `customType: \"ttsr-injection\"` and append a `ttsr_injection` entry via `appendTtsrInjection(...)`\n- deferred non-interrupting prose-source injections are marked/persisted when their queued custom message reaches `message_end`\n- non-interrupting tool-source injections are marked at match time and persisted via `appendTtsrInjection(...)` from the `afterToolCall` hook when the matched tool's result is produced\n- `createAgentSession()` restores `existingSession.injectedTtsrRules` into `ttsrManager`\n\nNet effect: injected-rule suppression is persisted/restored across session reload/resume for the current branch path.\n\n## 8. Race boundaries and ordering guarantees\n\n### Abort vs retry callback\n\n- abort is synchronous from TTSR handler perspective (`agent.abort()` called immediately)\n- retry is deferred by timer (`50ms`)\n- extension notification is asynchronous and intentionally not awaited before abort/retry scheduling\n\n### Multiple matches in same stream window\n\n`checkDelta()` returns all currently matching eligible rules for that scoped buffer. Pending injections are deduplicated by rule name before injection.\n\n### Between abort and continue\n\nDuring the timer window, state can change (user interruption, mode actions, additional events). The retry call is best-effort: `agent.continue().catch(() => {})` swallows follow-up errors.\n\n## 9. Edge cases summary\n\n- Invalid `condition` regex: skipped with warning; other conditions/rules continue.\n- Duplicate rule names at capability layer: lower-priority duplicates are shadowed before registration.\n- Duplicate names at manager layer: second registration is ignored.\n- `contextMode: \"keep\"`: partial violating output can remain in context before reminder retry.\n- `interruptMode: \"never\"`: prose-source matches queue a deferred hidden injection after a successful assistant message; tool-source matches fold an in-band `<system-reminder>` into the matched tool call's `toolResult` content via the `afterToolCall` hook (no mid-stream abort, no separate follow-up turn).\n- Tool-source non-interrupting buckets are cleared when the parent assistant message ends with `stopReason === \"aborted\"` or `\"error\"`, so rules whose target tool never produced a result remain eligible to re-trigger.\n- Repeat-after-gap depends on turn count increments at `turn_end`; mid-turn chunks do not advance gap counters.\n",
-	"tui-runtime-internals.md": "# TUI runtime internals\n\nThis document maps the non-theme runtime path from terminal input to rendered output in interactive mode. It focuses on behavior in `packages/tui` and its integration from `packages/coding-agent` controllers.\n\n## Runtime layers and ownership\n\n- **`packages/tui` engine**: terminal lifecycle, stdin normalization, focus routing, render scheduling, differential painting, overlay composition, hardware cursor placement.\n- **`packages/coding-agent` interactive mode**: builds component tree, binds editor callbacks and keymaps, reacts to agent/session events, and translates domain state (streaming, tool execution, retries, plan mode) into UI components.\n\nBoundary rule: the TUI engine is message-agnostic. It only knows `Component.render(width)`, `handleInput(data)`, focus, and overlays. Agent semantics stay in interactive controllers.\n\n## Implementation files\n\n- [`../src/modes/interactive-mode.ts`](../packages/coding-agent/src/modes/interactive-mode.ts)\n- [`../src/modes/controllers/event-controller.ts`](../packages/coding-agent/src/modes/controllers/event-controller.ts)\n- [`../src/modes/controllers/input-controller.ts`](../packages/coding-agent/src/modes/controllers/input-controller.ts)\n- [`../src/modes/components/custom-editor.ts`](../packages/coding-agent/src/modes/components/custom-editor.ts)\n- [`../../tui/src/tui.ts`](../packages/tui/src/tui.ts)\n- [`../../tui/src/terminal.ts`](../packages/tui/src/terminal.ts)\n- [`../../tui/src/editor-component.ts`](../packages/tui/src/editor-component.ts)\n- [`../../tui/src/stdin-buffer.ts`](../packages/tui/src/stdin-buffer.ts)\n- [`../../tui/src/components/loader.ts`](../packages/tui/src/components/loader.ts)\n\n## Boot and component tree assembly\n\n`InteractiveMode` constructs `TUI(new ProcessTerminal(), settings.get(\"showHardwareCursor\"))`, applies `settings.get(\"clearOnShrink\")`, and creates persistent containers:\n\n- `chatContainer`\n- `pendingMessagesContainer`\n- `statusContainer`\n- `todoContainer`\n- `btwContainer`\n- `statusLine`\n- `hookWidgetContainerAbove`\n- `editorContainer` (holds `CustomEditor`)\n- `hookWidgetContainerBelow`\n\n`init()` wires the tree in that order, focuses the editor, registers input handlers via `InputController`, subscribes terminal appearance changes into theme auto-detection, starts TUI, and requests a forced render.\nA forced render (`requestRender(true)`) resets previous-line caches and cursor bookkeeping before repainting.\n\n## Terminal lifecycle and stdin normalization\n\n`ProcessTerminal.start()`:\n\n1. Enables raw mode and bracketed paste.\n2. Attaches resize handler.\n3. Creates a `StdinBuffer` to split partial escape chunks into complete sequences.\n4. Queries Kitty keyboard protocol support (`CSI ? u`), then enables protocol flags if supported; otherwise enables modifyOtherKeys fallback after a short timeout.\n5. Queries OSC 11 background color and enables Mode 2031 appearance notifications for dark/light theme detection.\n6. On Windows, attempts VT input enablement via `kernel32` mode flags.\n   `StdinBuffer` behavior:\n\n- Buffers fragmented escape sequences (CSI/OSC/DCS/APC/SS3).\n- Emits `data` only when a sequence is complete or timeout-flushed.\n- Detects bracketed paste and emits a `paste` event with raw pasted text.\n\nThis prevents partial escape chunks from being misinterpreted as normal keypresses.\n\n## Input routing and focus model\n\nInput path:\n\n`stdin -> ProcessTerminal -> StdinBuffer -> TUI.#handleInput -> focusedComponent.handleInput`\n\nRouting details:\n\n1. TUI runs registered input listeners first (`addInputListener`), allowing consume/transform behavior.\n2. TUI handles global debug shortcut (`shift+ctrl+d`) before component dispatch.\n3. If focused component belongs to an overlay that is now hidden/invisible, TUI reassigns focus to next visible overlay or saved pre-overlay focus.\n4. Key release events are filtered unless focused component sets `wantsKeyRelease = true`.\n5. After dispatch, TUI schedules render.\n\n`setFocus()` also toggles `Focusable.focused`, which controls whether components emit `CURSOR_MARKER` for hardware cursor placement.\n\n## Key handling split: editor vs controller\n\n`CustomEditor` intercepts high-priority combos first (escape, ctrl-c/d/z, ctrl-v, ctrl-p variants, ctrl-t, alt-up, extension custom keys) and delegates the rest to base `Editor` behavior (text editing, history, autocomplete, cursor movement).\n\n`InputController.setupKeyHandlers()` then binds editor callbacks to mode actions:\n\n- cancellation / mode exits on `Escape`\n- shutdown on double `Ctrl+C` or empty-editor `Ctrl+D`\n- suspend/resume on `Ctrl+Z`\n- slash-command and selector hotkeys\n- follow-up/dequeue toggles and expansion toggles\n\nThis keeps key parsing/editor mechanics in `packages/tui` and mode semantics in coding-agent controllers.\n\n## Render loop and diffing strategy\n\n`TUI.requestRender()` is debounced to one render per tick using `process.nextTick`. Multiple state changes in the same turn coalesce.\n\n`#doRender()` pipeline:\n\n1. Render root component tree to `newLines`.\n2. Composite visible overlays (if any).\n3. Extract and strip `CURSOR_MARKER` from visible viewport lines.\n4. Append segment reset suffixes for non-image lines.\n5. Choose full repaint vs differential patch:\n   - first frame\n   - width change\n   - shrink with `clearOnShrink` enabled and no overlays\n   - edits above previous viewport\n6. For differential updates, patch only changed line range and clear stale trailing lines when needed.\n7. Reposition hardware cursor for IME support.\n\nRender writes use synchronized output mode (`CSI ? 2026 h/l`) to reduce flicker/tearing.\n\n## Render safety constraints\n\nCritical safety checks in `TUI`:\n\n- Non-image rendered lines are expected to fit terminal width; the differential path truncates overwide lines as a last-resort guard and can write debug diagnostics when redraw debugging is enabled.\n- Overlay compositing includes defensive truncation and post-composite width guarding.\n- Width changes force full redraw because wrapping semantics change.\n- Cursor position is clamped before movement.\n\nThese constraints are runtime guards plus component conventions; renderers should still return width-safe lines rather than rely on truncation.\n\n## Virtual viewport (opt-in, `PI_TUI_VIRTUAL_VIEWPORT`)\n\nBy default `#doRender` normalizes/truncates and diffs the full rendered transcript every frame (`O(total lines)`), which becomes a per-frame cost on very long sessions / weak hardware.\n\nSetting `PI_TUI_VIRTUAL_VIEWPORT=1` enables an opt-in fast path: when the terminal width is unchanged and the off-screen raw prefix is unchanged from the previous frame (compared by raw value equality per line, which short-circuits to a fast reference check when components return stable string instances for unchanged lines), the previous frame's normalized prefix is reused and only the visible window (terminal rows + a small overscan) is re-normalized, with the differential diff starting at the window boundary. Output is byte-identical to the default path (reused entries are deterministic normalizations of identical raw lines), so it is a pure performance toggle.\n\nThe flag defaults to **off** because it changes a core render path; enable it to reduce per-frame normalize/diff cost on huge transcripts. Any width change, off-screen edit, forced render (`requestRender(true)`), or first frame transparently falls back to the full path. `PI_TUI_METRICS` exposes `lineCounts` gauges (`rendered`, `normalized`, `measured`, `diffed`, and `offscreenScan`) to observe the bound.\n\n## Resize handling\n\nResize events are event-driven from `ProcessTerminal` to `TUI.requestRender()`.\n\nEffects:\n\n- Width changes trigger full redraw.\n- Height changes trigger full redraw except in Termux and terminal multiplexers, where the renderer avoids scrollback-hostile full replays.\n- Viewport/top tracking (`#previousViewportTop`, `#maxLinesRendered`) avoids invalid relative cursor math when content or terminal size changes.\n- Overlay visibility can depend on terminal dimensions (`OverlayOptions.visible`); focus is corrected when overlays become non-visible after resize.\n\n## Streaming and incremental UI updates\n\n`EventController` subscribes to `AgentSessionEvent` and updates UI incrementally:\n\n- `agent_start`: starts loader in `statusContainer`.\n- `message_start` assistant: creates `streamingComponent` and mounts it.\n- `message_update`: updates streaming assistant content; creates/updates tool execution components as tool calls appear.\n- `tool_execution_update/end`: updates tool result components and completion state.\n- `message_end`: finalizes assistant stream, handles aborted/error annotations, marks pending tool args complete on normal stop.\n- `agent_end`: stops loaders, clears transient stream state, flushes deferred model switch, issues completion notification if backgrounded.\n\nRead-tool grouping is intentionally stateful (`#lastReadGroup`) to coalesce consecutive read tool calls into one visual block until a non-read break occurs.\n\n## Status and loader orchestration\n\nStatus lane ownership:\n\n- `statusContainer` holds transient loaders (`loadingAnimation`, `autoCompactionLoader`, `retryLoader`).\n- `statusLine` renders persistent status/hooks/plan indicators and drives editor top border updates.\n\nLoader behavior:\n\n- `Loader` updates every 80ms via interval and requests render each frame.\n- Escape handlers are temporarily overridden during auto-compaction and auto-retry to cancel those operations.\n- On end/cancel paths, controllers restore prior escape handlers and stop/clear loader components.\n\n## Mode transitions and backgrounding\n\n### Bash/Python input modes\n\nInput text prefixes toggle editor border mode flags:\n\n- `!` -> bash mode\n- `$` (non-template literal prefix) -> python mode\n\nEscape exits inactive mode by clearing editor text and restoring border color; when execution is active, escape aborts the running task instead.\n\n### Plan mode\n\n`InteractiveMode` tracks plan mode flags, status-line state, active tools, and model switching. Enter/exit updates session mode entries and status/UI state, including deferred model switch if streaming is active.\n\n### Suspend/resume (`Ctrl+Z`)\n\n`InputController.handleCtrlZ()`:\n\n1. Registers one-shot `SIGCONT` handler to restart TUI and force render.\n2. Stops TUI before suspend.\n3. Sends `SIGTSTP` to process group.\n\n### Background mode (`/background` or `/bg`)\n\n`handleBackgroundCommand()`:\n\n- Rejects when idle.\n- Switches tool UI context to non-interactive (`hasUI=false`) so interactive UI tools fail fast.\n- Stops loaders/status line and unsubscribes foreground event handler.\n- Subscribes background event handler (primarily waits for `agent_end`).\n- Stops TUI and sends `SIGTSTP` (POSIX job control path).\n\nOn `agent_end` in background with no queued work, controller sends completion notification and shuts down.\n\n## Cancellation paths\n\nPrimary cancellation inputs:\n\n- `Escape` during active stream loader: restores queued messages to editor and aborts agent.\n- `Escape` during bash/python execution: aborts running command.\n- `Escape` during auto-compaction/retry: invokes dedicated abort methods through temporary escape handlers.\n- `Ctrl+C` single press: clear editor; double press within 500ms: shutdown.\n\nCancellation is state-conditional; same key can mean abort, mode-exit, selector trigger, or no-op depending on runtime state.\n\n## Event-driven vs throttled behavior\n\nEvent-driven updates:\n\n- Agent session events (`EventController`)\n- Key input callbacks (`InputController`)\n- terminal resize callback\n- terminal appearance callbacks, SIGWINCH theme reevaluation, and git branch watchers in `InteractiveMode`\n\nThrottled/debounced paths:\n\n- TUI rendering is tick-debounced (`requestRender` coalescing).\n- Loader animation is fixed-interval (80ms), each frame requesting render.\n- Editor autocomplete updates (inside `Editor`) use debounce timers, reducing recompute churn during typing.\n\nThe runtime therefore mixes event-driven state transitions with bounded render cadence to keep interactivity responsive without repaint storms.\n",
+	"tui-runtime-internals.md": "# TUI runtime internals\n\nThis document maps the non-theme runtime path from terminal input to rendered output in interactive mode. It focuses on behavior in `packages/tui` and its integration from `packages/coding-agent` controllers.\n\n## Runtime layers and ownership\n\n- **`packages/tui` engine**: terminal lifecycle, stdin normalization, focus routing, render scheduling, differential painting, overlay composition, hardware cursor placement.\n- **`packages/coding-agent` interactive mode**: builds component tree, binds editor callbacks and keymaps, reacts to agent/session events, and translates domain state (streaming, tool execution, retries, plan mode) into UI components.\n\nBoundary rule: the TUI engine is message-agnostic. It only knows `Component.render(width)`, `handleInput(data)`, focus, and overlays. Agent semantics stay in interactive controllers.\n\n## Implementation files\n\n- [`../src/modes/interactive-mode.ts`](../packages/coding-agent/src/modes/interactive-mode.ts)\n- [`../src/modes/controllers/event-controller.ts`](../packages/coding-agent/src/modes/controllers/event-controller.ts)\n- [`../src/modes/controllers/input-controller.ts`](../packages/coding-agent/src/modes/controllers/input-controller.ts)\n- [`../src/modes/components/custom-editor.ts`](../packages/coding-agent/src/modes/components/custom-editor.ts)\n- [`../../tui/src/tui.ts`](../packages/tui/src/tui.ts)\n- [`../../tui/src/terminal.ts`](../packages/tui/src/terminal.ts)\n- [`../../tui/src/editor-component.ts`](../packages/tui/src/editor-component.ts)\n- [`../../tui/src/stdin-buffer.ts`](../packages/tui/src/stdin-buffer.ts)\n- [`../../tui/src/components/loader.ts`](../packages/tui/src/components/loader.ts)\n\n## Boot and component tree assembly\n\n`InteractiveMode` constructs `TUI(new ProcessTerminal(), settings.get(\"showHardwareCursor\"))`, applies `settings.get(\"clearOnShrink\")`, and creates persistent containers:\n\n- `chatContainer`\n- `pendingMessagesContainer`\n- `statusContainer`\n- `todoContainer`\n- `btwContainer`\n- `statusLine`\n- `hookWidgetContainerAbove`\n- `editorContainer` (holds `CustomEditor`)\n- `hookWidgetContainerBelow`\n\n`init()` wires the tree in that order, focuses the editor, registers input handlers via `InputController`, subscribes terminal appearance changes into theme auto-detection, starts TUI, and requests a forced render.\nA forced render (`requestRender(true)`) resets previous-line caches and cursor bookkeeping before repainting.\n\n## Terminal lifecycle and stdin normalization\n\n`ProcessTerminal.start()`:\n\n1. Enables raw mode and bracketed paste.\n2. Attaches resize handler.\n3. Creates a `StdinBuffer` to split partial escape chunks into complete sequences.\n4. Queries Kitty keyboard protocol support (`CSI ? u`), then enables protocol flags if supported; otherwise enables modifyOtherKeys fallback after a short timeout.\n5. Queries OSC 11 background color and enables Mode 2031 appearance notifications for dark/light theme detection.\n6. On Windows, attempts VT input enablement via `kernel32` mode flags.\n   `StdinBuffer` behavior:\n\n- Buffers fragmented escape sequences (CSI/OSC/DCS/APC/SS3).\n- Emits `data` only when a sequence is complete or timeout-flushed.\n- Detects bracketed paste and emits a `paste` event with raw pasted text.\n\nThis prevents partial escape chunks from being misinterpreted as normal keypresses.\n\n## Input routing and focus model\n\nInput path:\n\n`stdin -> ProcessTerminal -> StdinBuffer -> TUI.#handleInput -> focusedComponent.handleInput`\n\nRouting details:\n\n1. TUI runs registered input listeners first (`addInputListener`), allowing consume/transform behavior.\n2. TUI handles global debug shortcut (`shift+ctrl+d`) before component dispatch.\n3. If focused component belongs to an overlay that is now hidden/invisible, TUI reassigns focus to next visible overlay or saved pre-overlay focus.\n4. Key release events are filtered unless focused component sets `wantsKeyRelease = true`.\n5. After dispatch, TUI schedules render.\n\n`setFocus()` also toggles `Focusable.focused`, which controls whether components emit `CURSOR_MARKER` for hardware cursor placement.\n\n## Key handling split: editor vs controller\n\n`CustomEditor` intercepts high-priority combos first (escape, ctrl-c/d/z, ctrl-v, ctrl-p variants, ctrl-t, alt-up, extension custom keys) and delegates the rest to base `Editor` behavior (text editing, history, autocomplete, cursor movement).\n\n`InputController.setupKeyHandlers()` then binds editor callbacks to mode actions:\n\n- cancellation / mode exits on `Escape`\n- shutdown on double `Ctrl+C` or empty-editor `Ctrl+D`\n- suspend/resume on `Ctrl+Z`\n- slash-command and selector hotkeys\n- follow-up/dequeue toggles and expansion toggles\n\nThis keeps key parsing/editor mechanics in `packages/tui` and mode semantics in coding-agent controllers.\n\n## Render loop and diffing strategy\n\n`TUI.requestRender()` is debounced to one render per tick using `process.nextTick`. Multiple state changes in the same turn coalesce.\n\n`#doRender()` pipeline:\n\n1. Render root component tree to `newLines`.\n2. Composite visible overlays (if any).\n3. Extract and strip `CURSOR_MARKER` from visible viewport lines.\n4. Append segment reset suffixes for non-image lines.\n5. Choose full repaint vs differential patch:\n   - first frame\n   - width change\n   - shrink with `clearOnShrink` enabled and no overlays\n   - edits above previous viewport\n6. For differential updates, patch only changed line range and clear stale trailing lines when needed.\n7. Reposition hardware cursor for IME support.\n\nRender writes use synchronized output mode (`CSI ? 2026 h/l`) to reduce flicker/tearing.\n\n## Render safety constraints\n\nCritical safety checks in `TUI`:\n\n- Non-image rendered lines are expected to fit terminal width; the differential path truncates overwide lines as a last-resort guard and can write debug diagnostics when redraw debugging is enabled.\n- Overlay compositing includes defensive truncation and post-composite width guarding.\n- Width changes force full redraw because wrapping semantics change.\n- Cursor position is clamped before movement.\n\nThese constraints are runtime guards plus component conventions; renderers should still return width-safe lines rather than rely on truncation.\n\n## Virtual viewport (opt-in, `PI_TUI_VIRTUAL_VIEWPORT`)\n\nBy default `#doRender` normalizes/truncates and diffs the full rendered transcript every frame (`O(total lines)`), which becomes a per-frame cost on very long sessions / weak hardware.\n\nSetting `PI_TUI_VIRTUAL_VIEWPORT=1` enables an opt-in fast path: when the terminal width is unchanged and the off-screen raw prefix is unchanged from the previous frame (compared by raw value equality per line, which short-circuits to a fast reference check when components return stable string instances for unchanged lines), the previous frame's normalized prefix is reused and only the visible window (terminal rows + a small overscan) is re-normalized, with the differential diff starting at the window boundary. Output is byte-identical to the default path (reused entries are deterministic normalizations of identical raw lines), so it is a pure performance toggle.\n\nThe flag defaults to **off** because it changes a core render path; enable it to reduce per-frame normalize/diff cost on huge transcripts. Any width change, off-screen edit, forced render (`requestRender(true)`), or first frame transparently falls back to the full path. `PI_TUI_METRICS` exposes `lineCounts` gauges (`rendered`, `normalized`, `measured`, `diffed`, and `offscreenScan`) to observe the bound.\n\n## Resize handling\n\nResize events are event-driven from `ProcessTerminal` to `TUI.requestRender()`.\n\nEffects:\n\n- Width changes trigger full redraw.\n- Height changes trigger full redraw except in Termux and terminal multiplexers, where the renderer avoids scrollback-hostile full replays.\n- Viewport/top tracking (`#previousViewportTop`, `#maxLinesRendered`) avoids invalid relative cursor math when content or terminal size changes.\n- Overlay visibility can depend on terminal dimensions (`OverlayOptions.visible`); focus is corrected when overlays become non-visible after resize.\n\n## Streaming and incremental UI updates\n\n`EventController` subscribes to `AgentSessionEvent` and updates UI incrementally:\n\n- `agent_start`: starts loader in `statusContainer`.\n- `message_start` assistant: creates `streamingComponent` and mounts it.\n- `message_update`: updates streaming assistant content; creates/updates tool execution components as tool calls appear.\n- `tool_execution_update/end`: updates tool result components and completion state.\n- `message_end`: finalizes assistant stream, handles aborted/error annotations, marks pending tool args complete on normal stop.\n- `agent_end`: stops loaders, clears transient stream state, flushes deferred model switch, issues terminal completion notification if backgrounded, and runs the user-level completion command hook when configured.\n\nRead-tool grouping is intentionally stateful (`#lastReadGroup`) to coalesce consecutive read tool calls into one visual block until a non-read break occurs.\n\n## Status and loader orchestration\n\nStatus lane ownership:\n\n- `statusContainer` holds transient loaders (`loadingAnimation`, `autoCompactionLoader`, `retryLoader`).\n- `statusLine` renders persistent status/hooks/plan indicators and drives editor top border updates.\n\nLoader behavior:\n\n- `Loader` updates every 80ms via interval and requests render each frame.\n- Escape handlers are temporarily overridden during auto-compaction and auto-retry to cancel those operations.\n- On end/cancel paths, controllers restore prior escape handlers and stop/clear loader components.\n\n## Mode transitions and backgrounding\n\n### Bash/Python input modes\n\nInput text prefixes toggle editor border mode flags:\n\n- `!` -> bash mode\n- `$` (non-template literal prefix) -> python mode\n\nEscape exits inactive mode by clearing editor text and restoring border color; when execution is active, escape aborts the running task instead.\n\n### Plan mode\n\n`InteractiveMode` tracks plan mode flags, status-line state, active tools, and model switching. Enter/exit updates session mode entries and status/UI state, including deferred model switch if streaming is active.\n\n### Suspend/resume (`Ctrl+Z`)\n\n`InputController.handleCtrlZ()`:\n\n1. Registers one-shot `SIGCONT` handler to restart TUI and force render.\n2. Stops TUI before suspend.\n3. Sends `SIGTSTP` to process group.\n\n### Background mode (`/background` or `/bg`)\n\n`handleBackgroundCommand()`:\n\n- Rejects when idle.\n- Switches tool UI context to non-interactive (`hasUI=false`) so interactive UI tools fail fast.\n- Stops loaders/status line and unsubscribes foreground event handler.\n- Subscribes background event handler (primarily waits for `agent_end`).\n- Stops TUI and sends `SIGTSTP` (POSIX job control path).\n\nOn `agent_end` in background with no queued work, controller sends the terminal completion notification and shuts down. The configured `completion.notifyCommand` hook is not limited to background mode; it runs on completed agent turns so local tools such as cmux can receive foreground and background completion events.\n\n## Cancellation paths\n\nPrimary cancellation inputs:\n\n- `Escape` during active stream loader: restores queued messages to editor and aborts agent.\n- `Escape` during bash/python execution: aborts running command.\n- `Escape` during auto-compaction/retry: invokes dedicated abort methods through temporary escape handlers.\n- `Ctrl+C` single press: clear editor; double press within 500ms: shutdown.\n\nCancellation is state-conditional; same key can mean abort, mode-exit, selector trigger, or no-op depending on runtime state.\n\n## Event-driven vs throttled behavior\n\nEvent-driven updates:\n\n- Agent session events (`EventController`)\n- Key input callbacks (`InputController`)\n- terminal resize callback\n- terminal appearance callbacks, SIGWINCH theme reevaluation, and git branch watchers in `InteractiveMode`\n\nThrottled/debounced paths:\n\n- TUI rendering is tick-debounced (`requestRender` coalescing).\n- Loader animation is fixed-interval (80ms), each frame requesting render.\n- Editor autocomplete updates (inside `Editor`) use debounce timers, reducing recompute churn during typing.\n\nThe runtime therefore mixes event-driven state transitions with bounded render cadence to keep interactivity responsive without repaint storms.\n",
 	"ui-design-visual-qa.md": "# UI design and visual QA workflow\n\nThis is the repo-owned contract for future Sayknow-CLI UI, web, dashboard, terminal, and TUI visual work. It adapts the useful OMO design-reference and visual-QA workflow without vendoring any third-party design corpus.\n\nIt is not a fifth bundled workflow skill. Sayknow-CLI's public workflow surface remains `deep-interview`, `ralplan`, `ultragoal`, and `team`; use this document as planning/review guidance inside those workflows or direct implementation.\n\n## Required branch before implementation\n\nBefore writing broad UI code, choose and record exactly one workflow branch in the plan, issue update, PR body, or local `DESIGN.md`:\n\n1. **Existing design system** — the repository or product area already has a `DESIGN.md`, component system, theme, or comparable visual grammar. Read it first and update it when the change extends the system.\n2. **Greenfield selected references** — no usable system exists, so pick a small shortlist of design references before implementation. Record the exact references loaded and translate them into first-party project guidance; do not copy raw vendor files into the repo.\n3. **Extract existing system first** — the surface exists but its rules are implicit. The first deliverable is a minimal `DESIGN.md` that extracts the current tokens, layout grammar, component anatomy, and state rules before new product screens are built.\n\nA UI task that skips this branch selection is not ready for implementation.\n\n## `DESIGN.md` source material\n\nNew UI work must create or update the nearest product `DESIGN.md` before broad product-screen implementation. The document must be first-party source material for the implementation, not a screenshot dump or mood board. Include:\n\n- **Tokens** — colors, typography, spacing, radii, borders, iconography, density, terminal color roles, and accessibility contrast constraints.\n- **Layout grammar** — grids, page regions, navigation, hierarchy, rhythm, empty space, alignment, and composition rules.\n- **Component anatomy** — named parts, slots, content rules, affordances, constraints, and when not to use the component.\n- **States** — default, hover, active, focus, disabled, loading, empty, error, selected, expanded/collapsed, and permission/connection failure states where relevant.\n- **Motion and depth** — animation timing/easing, transitions, shadows/elevation, overlays, focus movement, and reduced-motion behavior.\n- **Responsive behavior** — mobile, tablet, desktop, narrow terminal, wide terminal, font scaling, wrapping, overflow, and high-density layouts.\n\nFor greenfield selected references, `DESIGN.md` must name the selected references and explain what was translated from each into the first-party system. It must not embed raw third-party corpus text as the system of record.\n\n## Component showcase before product screens\n\nBuild or update a component showcase/state harness before implementing broad product screens. The harness may be Storybook, a local route, a CLI/TUI fixture, a docs page with runnable examples, or a purpose-built screenshot fixture, but it must expose the component states needed by the product surface.\n\nThe harness must cover:\n\n- all states listed in `DESIGN.md` that the component supports;\n- representative realistic content, including long strings, empty content, error copy, and localization-sensitive text;\n- mobile/tablet/desktop or narrow/medium/wide terminal layouts as applicable;\n- keyboard focus and accessibility-visible states for interactive components.\n\nProduct screens can follow only after the harness proves the component vocabulary is stable enough to reuse.\n\n## Visual QA contract\n\nVisual QA is completion evidence, not decoration. A UI story is not done until it has fresh full-surface evidence from the current branch.\n\nRequired evidence:\n\n- **Fresh capture** — evidence must be generated after the current implementation, not reused from an older branch, design reference, or unrelated run.\n- **Full-surface coverage** — capture every page, route, modal, drawer, tab, breakpoint, component state, and error/empty/loading state in scope. Sampling a few representative screenshots is not enough.\n- **No hidden tails** — scrollable surfaces require evidence for top, middle, bottom, sticky regions, overflow behavior, and any virtualized content boundaries.\n- **CJK semantic line breaks block completion** — Korean, Japanese, Chinese, and mixed CJK/Latin copy must not wrap in semantically broken or visually misleading ways. Bad CJK line breaks are blocking defects, not cosmetic polish.\n- **Independent review before done** — a reviewer or review lane that did not author the implementation must inspect the full evidence set against `DESIGN.md`, the component harness, and acceptance criteria before the work is marked complete.\n- **Evidence references** — PRs should link or attach the current evidence artifacts instead of describing them only in prose.\n\n## Terminal and TUI evidence\n\nTerminal/TUI visual work must preserve terminal semantics in future helper flows. Until Sayknow-CLI has a dedicated helper, terminal visual-QA evidence must document the exact helper requirements and avoid flattening away the data needed for review.\n\nA terminal/TUI evidence helper must produce, at minimum:\n\n- `terminal.txt` with readable plain text;\n- `terminal-ansi.txt` preserving ANSI SGR color/style sequences and terminal control semantics needed for replay/review;\n- `terminal.html` rendering the ANSI-styled output for browser review;\n- optional `terminal.png` generated from the styled rendering when image evidence is useful;\n- `metadata.json` containing command or replay source, terminal size, font/rendering assumptions, capture timestamp, tool version, wrapping/truncation policy, and whether the artifact is from a live PTY, replay, or fixture.\n\nReviewers must reject terminal/TUI evidence that only contains flattened text when the change depends on color, emphasis, cursor state, layout, wrapping, or other ANSI/terminal behavior.\n\n## Provenance boundary\n\nDo not vendor raw third-party design corpora, screenshots, brand guides, prompt packs, or critique/reference material into this repository without an explicit materializer and provenance design.\n\nAllowed in a first PR:\n\n- first-party `DESIGN.md` guidance written for Sayknow-CLI;\n- a small hand-written reference index that names public sources and records why they were consulted;\n- pinned links, citations, or manifests that do not copy raw third-party corpus content.\n\nRequires explicit design before inclusion:\n\n- raw third-party corpus files;\n- copied design-system text, screenshots, or asset packs;\n- submodules or generated materialized corpora;\n- generated screenshots committed as durable source assets.\n\nA future materializer design must define source ownership, license/provenance metadata, pinning strategy, reproducible generation, update review, generated-file boundaries, and what artifacts are safe to attach to GitHub without committing.\n\n## PR checklist\n\nFor UI work, include this checklist in the PR body or equivalent review artifact:\n\n- [ ] UI workflow branch selected: existing `DESIGN.md`, greenfield selected references, or extract existing system first.\n- [ ] `DESIGN.md` created/updated with tokens, layout grammar, component anatomy, states, motion/depth, and responsive behavior.\n- [ ] Component showcase/state harness exists before broad product screens.\n- [ ] Fresh full-surface visual evidence covers every in-scope page/state/breakpoint; no sampling.\n- [ ] CJK semantic line breaks were checked and any defects were fixed before completion.\n- [ ] Terminal/TUI evidence preserves ANSI semantics or documents the exact helper requirements above.\n- [ ] Independent review inspected the evidence before the work was marked done.\n- [ ] No raw third-party corpus was vendored without an explicit materializer/provenance design.\n",
 };