@gajae-code/coding-agent 0.2.2 → 0.2.4

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

@@ -1,6 +1,6 @@
 // Auto-generated by scripts/generate-docs-index.ts - DO NOT EDIT
 
-export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","brand-assets.md","codebase-overview.md","compaction.md","environment-variables.md","fs-scan-cache-architecture.md","gjc-dogfood-skill-template.md","handoff-generation-pipeline.md","keybindings.md","lsp-config.md","memory.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/recipe.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","brand-assets.md","codebase-overview.md","compaction.md","environment-variables.md","fs-scan-cache-architecture.md","gjc-dogfood-skill-template.md","handoff-generation-pipeline.md","keybindings.md","lsp-config.md","memory.md","models.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","onboarding-packet.md","onboarding-receipt.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","render-mermaid.md","resolve-tool-runtime.md","rpc.md","rulebook-matching-pipeline.md","sdk.md","secrets.md","session-operations-export-share-fork-resume.md","session-switching-and-recent-listing.md","session-tree-plan.md","session.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.md","tools/checkpoint.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/read.md","tools/recall.md","tools/recipe.md","tools/reflect.md","tools/render_mermaid.md","tools/resolve.md","tools/retain.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md"];
 
 export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"ERRATA-GPT5-HARMONY.md": "# ERRATA — GPT-5 Harmony-Header Leakage\n\n## 1. The problem\n\nOpenAI frames tool calls in the Harmony chat protocol:\n\n```\n<|start|>assistant<|channel|>commentary to=functions.<NAME><|message|>{ARGS}<|call|>\n```\n\n`<|channel|>commentary to=functions.NAME` is the **routing header** —\ncontrol tokens consumed by the runtime to dispatch the call. These\ntokens never appear as content under normal operation; the runtime\nstrips them.\n\nThe defect: gpt-5 models occasionally emit, **as ordinary content\ninside `{ARGS}`**, the **plain-text shadow** of these routing tokens —\nthe same characters without the `<|…|>` brackets — and continue\nproducing more pseudo-routing structure (channel name, body marker,\nmultilingual spam, fake tool-result framing). The contamination lives\ninside the visible tool argument and is dispatched to the tool as if it\nwere intended content.\n\n**Critical detail.** The actual `<|start|>` / `<|channel|>` /\n`<|message|>` / `<|call|>` special tokens almost never appear in tool\nargs. What leaks is the bracket-less spelling — `analysis to=functions.X\ncode …` — because OpenAI applies a logit mask suppressing the\ncontrol-token IDs inside the args region. The mass that would have gone\nto those special tokens redistributes onto the un-bracketed plain-text\nrepresentation the model also learned. This makes the leak structurally\ninvisible to the routing parser and lands it in the tool input verbatim.\n\nManifestation in tool args (real corpus example):\n\n```\n~      add_function(iso, ctx, ns, \"installSystemChangeObserver\",\n        os_install_system_change_observer);】【\"】【analysis to=functions.edit\n        code above เงินไทยฟรีuser to=functions.edit code …\n```\n\nThe leading code is real and intended. Everything after the first\nnon-Latin token through the next clean structural boundary is corruption.\n\n---\n\n## 2. Observed statistics & failure modes\n\nSource: `~/.gjc/stats.db` (`ss_tool_calls`, `ss_assistant_msgs`), through\n2026-05-10. 1.05M tool calls scanned.\n\n### 2.1 Rate\n\n| Model            | Leaks in tool args | Calls   | per million |\n|------------------|-------------------:|--------:|------------:|\n| gpt-5.4          | 37                 | 226,957 | 163         |\n| gpt-5.3-openai-code    | 17                 | 112,243 | 151         |\n| gpt-5.5          | 2                  |  80,750 |  25         |\n| gpt-5.2-openai-code    | 0                  |    —    |   —         |\n\nPlus 15 hits in assistant visible text / thinking blobs.\n\n### 2.2 Tool distribution\n\n| Tool                | Hits |\n|---------------------|-----:|\n| `edit`              | 38   |\n| `eval`              | 11   |\n| `report_tool_issue` | 3    |\n| `grep`/`read`/`search`/`yield` | 1 each |\n\nConcentrated in tools with free-form (non-JSON-schema) argument formats.\n\n### 2.3 Leak shape (deterministic)\n\n```\nLEAK         ::= JUNK_PREFIX MARKER CHANNEL_BODY (LEAK)?\nMARKER       ::= \"to=functions.\" TOOL_NAME\nCHANNEL_BODY ::= \" code \" (SPAM | reasoning_prose | fake_tool_output)*\nJUNK_PREFIX  ::= (GLITCH_TOKEN | CHANNEL_WORD | NON_LATIN_RUN | \"}\" | \"】【\")+\n```\n\n**Cascading is common.** Of 96 marker occurrences across 71 contaminated\nrecords, 39 contain ≥2 markers and 7 contain ≥3 — the model emits\nmultiple fake `to=functions.X code …` blocks back-to-back, often with\nfake `code_output\\nCell N:\\n…` framing between them. Once the\nplain-text scaffolding is in the residual stream, the prefix now *looks\nlike* a fresh tool envelope start, so the macro prior over continuations\nkeeps voting for more scaffolding. Self-amplifying.\n\n### 2.4 Glitch tokens\n\nSingle-token identifiers in `o200k_base` whose embeddings appear to be\nnear-init from underrepresentation in post-training. ASCII residue\nimmediately before the marker in the natural corpus:\n\n| Surface string    | Single-token | Token ID | Hits in corpus |\n|-------------------|:-:|---------:|---:|\n| `Japgolly`        | ✅ | 199,745 | 1 |\n| `Jsii`            | ✅ | 114,318 | (subtoken of `Jsii_commentary`) |\n| `Jsii_commentary` | — (3 toks) | — | 2 |\n| `changedFiles`    | — (2 toks) | — | 8 |\n| `RTLU`            | — (2 toks) | — | 3 |\n\n`Japgolly` is in the last 0.13% of the vocabulary — the same family of\nGitHub-corpus residue that produced `SolidGoldMagikarp` in the 2023\nGPT-2 vocabulary (Rumbelow & Watkins). `SolidGoldMagikarp` itself\ntokenizes to 5 tokens in `o200k_base` — that specific token was retired,\nbut the class wasn't.\n\nFor the multi-token entries, the corpus-level signature is the surface\nstring; the underlying glitch trigger is a sub-token (e.g. `Jsii` inside\n`Jsii_commentary`). The detector list (`G` signal) keys on the surface\nstrings.\n\nStable across unrelated sessions. Treated as a high-precision detector\nsignal.\n\n### 2.5 Channel-word leakage\n\n`analysis` (5), `assistant` (5), `commentary` (3), `user` (1) appear\ndirectly preceding `to=`. Always bare words; never `<|channel|>analysis`\nor any other bracketed form. Consistent with §1 — the brackets are\nmasked, the words are not.\n\n### 2.6 Non-Latin spam residue\n\n96 marker hits, by script: CJK 40, Cyrillic 12, Telugu/Kannada/Malayalam\n18, Thai 8, Georgian 7, Armenian 7, Arabic 1. Recurring fragments are\nChinese gambling SEO (`大发时时彩`, `天天中彩票`), Georgian/Abkhaz junk,\nand Thai casino spam — well-known low-quality crawl residue.\n\nThis is the same script distribution observed in the controlled\nreproduction (§7.3), independent of the prompt's natural language.\n\n### 2.7 Failure-mode breakdown for the `edit` tool\n\nThe `edit` tool exists in two variants in the corpus:\n\n| Variant                  | Calls | Recovery |\n|--------------------------|------:|----------|\n| Patch-DSL (`§PATH`/anchor/`«»≔` ops) | 27 | **Recoverable** by op-truncation (§3.3) |\n| JSON-schema (`{path,edits:[…]}`)      | 11 | **Not recoverable** — contamination is escaped *inside* JSON strings, parser accepts it cleanly, content would be written verbatim into source files |\n\nFor Patch-DSL leaks specifically:\n\n- 20/27 cases: contamination on the last input line; nothing follows.\n- 7/27 cases: contamination mid-input; what follows is one of: a\n  duplicate replay of an earlier file/anchor, intended content for a\n  *different* tool call (the model started its next call inline), or\n  pure hallucination. Post-contamination content is never trustworthy.\n\n### 2.8 Mechanism (confirmed)\n\n**Prior collapse from null-embedding glitch tokens, into a\ncontrol-token-masked basin whose mass redistributes onto the\nplain-text shadow of the Harmony protocol.**\n\nStep by step:\n\n1. The model is mid-`{ARGS}` of a Harmony tool call. The runtime applies\n   a logit mask suppressing structural control tokens (`<|channel|>`,\n   `<|message|>`, `<|call|>`, `<|start|>`, `<|end|>`) inside the args\n   region. Without this mask, normal generation would constantly\n   hallucinate envelope-closes; with it, those token IDs have logit\n   `-∞` in args.\n2. A glitch token `g` is sampled. By construction `g` was in the BPE\n   merge corpus but barely in LM/RL training, so its **input embedding\n   `e_g` ≈ near-init noise of small norm**.\n3. At position t+1, the residual update `h_{t+1} ≈ LN(h_t + e_g + Attn +\n   MLP)` is dominated by the prefix-derived terms; the just-emitted-token\n   signal is effectively absent. Generation diversity normally comes\n   from `e_x` steering the residual into different sub-regions —\n   stripped here.\n4. The next-token distribution therefore collapses onto the **conditional\n   prior over continuations of the prefix, with local conditioning\n   removed**. In a tool-calling rollout context, that prior is sharply\n   peaked on Harmony scaffolding (control tokens + routing tokens) —\n   that's what RL trained.\n5. The mask zeros the control-token IDs. Mass redistributes onto the\n   **next-best continuation**: the un-bracketed surface-form spelling of\n   the same protocol (`analysis`, `commentary`, ` to=functions.X`,\n   ` code `). This spelling is unmasked because those characters are\n   ordinary tokens.\n6. Once a few tokens of plain-text scaffolding land in the residual\n   stream, the prefix now resembles a fresh envelope start. The macro\n   prior keeps voting for more scaffolding. Cascading (§2.3) follows.\n7. Multilingual spam after the marker is the same prior-collapse\n   continuation, drawn from the training neighborhood of the glitch\n   token (often ESL/auto-generated multilingual web junk — exactly the\n   crawl residue in §2.6).\n\n**Two corollaries the corpus data demanded but only the experiment\nexplained:**\n\n- **The brackets never appear** (§1, §2.5). The mask is what makes the\n  leak land in plain text instead of as a real envelope-close.\n- **Counterintuitive grammar dependency** (§7.4). The leak is *worse* in\n  formats closest to OpenAI's training distribution. Off-distribution\n  custom grammars dampen the macro-prior basin; the official\n  `*** Begin Patch` format is the strongest collapse target.\n\nThe 2023 SolidGoldMagikarp paper documented mechanism (1)+(2)+(4). The\nnew piece is (5): when constrained decoding masks the natural collapse\ntarget, the mass laundered through the un-masked plain-text shadow\nbecomes a structurally-invisible exfiltration channel.",
@@ -19,7 +19,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"keybindings.md": "# Keybindings\n\nRun `/hotkeys` inside an `gjc` session to see the active chords for your current build. The list reflects any remaps loaded from disk and any bindings added by extensions.\n\n## Customize keybindings\n\nUser remaps live in `~/.gjc/agent/keybindings.json`. The file is a JSON object whose keys are keybinding action IDs and whose values are either one chord string or an array of chord strings. It is not read from `~/.gjc/agent/config.yml`, and there is no nested `keybindings` object.\n\n```json\n{\n  \"app.model.cycleForward\": \"Ctrl+P\",\n  \"app.model.selectTemporary\": \"Alt+P\",\n  \"app.plan.toggle\": \"Alt+Shift+P\"\n}\n```\n\nChord names are case-insensitive and use the same notation shown in the UI, such as `Ctrl+P`, `Alt+Shift+P`, `Shift+Enter`, and `Ctrl+Backspace`.\n\nSet an action to an empty array to disable it:\n\n```json\n{\n  \"app.stt.toggle\": []\n}\n```\n\n## Common action IDs\n\n| Action ID | Default | Meaning |\n| --- | --- | --- |\n| `app.model.cycleForward` | `Ctrl+P` | Cycle role models forward |\n| `app.model.cycleBackward` | `Shift+Ctrl+P` | Cycle role models backward |\n| `app.model.selectTemporary` | `Alt+P` | Pick a model temporarily for this session |\n| `app.model.select` | `Ctrl+L` | Open the model selector and set roles |\n| `app.plan.toggle` | `Alt+Shift+P` | Toggle plan mode |\n| `app.history.search` | `Ctrl+R` | Search prompt history |\n| `app.tools.expand` | `Ctrl+O` | Toggle tool-output expansion |\n| `app.thinking.toggle` | `Ctrl+T` | Toggle thinking-block visibility |\n| `app.thinking.cycle` | `Shift+Tab` | Cycle thinking level |\n| `app.editor.external` | `Ctrl+G` | Edit the draft in `$VISUAL` / `$EDITOR` |\n| `app.message.followUp` | `Ctrl+Enter` | Queue a follow-up message |\n| `app.message.dequeue` | `Alt+Up` | Dequeue a queued message back into the editor |\n| `app.clipboard.copyLine` | `Alt+Shift+L` | Copy the current line |\n| `app.clipboard.copyPrompt` | `Alt+Shift+C` | Copy the whole prompt |\n| `app.stt.toggle` | `Alt+H` | Toggle speech-to-text recording |\n\nOlder unqualified action names are migrated when `keybindings.json` is loaded, but new docs and new configs should use the namespaced action IDs above.\n",
 	"lsp-config.md": "# LSP configuration in GJC\n\nThis guide explains how to configure language servers for the GJC coding agent.\n\nSource of truth in code:\n\n- Server config type: `packages/coding-agent/src/lsp/types.ts` (`ServerConfig`)\n- Config loader: `packages/coding-agent/src/lsp/config.ts`\n- Built-in server definitions: `packages/coding-agent/src/lsp/defaults.json`\n\n## Auto-detection\n\nWhen no LSP config file is present, GJC auto-detects servers by intersecting two conditions:\n\n1. The project directory contains at least one of the server's `rootMarkers`.\n2. The server binary is available — checked in project-local bin directories first (e.g., `node_modules/.bin/`, `.venv/bin/`), then `$PATH`.\n\nNo configuration is required for common setups. The built-in server list covers most popular languages; see [`defaults.json`](../packages/coding-agent/src/lsp/defaults.json) for the full set.\n\n## Config file locations\n\nGJC merges LSP config from multiple files, lowest to highest priority:\n\n| Priority | Location |\n|----------|----------|\n| 5 (lowest) | `~/lsp.json`, `~/.lsp.json`, `~/lsp.yaml`, `~/.lsp.yaml` |\n| 3 | `~/.gjc/agent/lsp.json`, `~/.gjc/agent/lsp.yaml`, `~/.gemini/lsp.*` |\n| 2 | `<project>/.gjc/lsp.json`, `<project>/.gjc/lsp.yaml`, `<project>/.gemini/lsp.*` |\n| 1 (highest) | `<project>/lsp.json`, `<project>/.lsp.json`, `<project>/lsp.yaml` |\n\nEach location accepts both `.json` and `.yaml` / `.yml` variants, as well as hidden-file versions (`.lsp.json`, `.lsp.yaml`). Files are merged in order: higher-priority files override lower-priority fields for the same server. Servers not mentioned in any override file remain at their built-in defaults.\n\n**Recommended locations:**\n\n- User-wide preferences → `~/.gjc/agent/lsp.json`\n- Project-specific overrides → `<project>/.gjc/lsp.json`\n\n> **Note:** The presence of any LSP config file disables auto-detection. When at least one file is found, GJC skips the binary-scan phase and loads all servers that have matching `rootMarkers`, an available binary, and are not explicitly `disabled`.\n\n## File shape\n\nBoth JSON and YAML are accepted. The top-level object can use either a `servers` wrapper key or a flat map directly:\n\n```json\n{\n  \"servers\": {\n    \"server-name\": { ... }\n  },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nor (flat, without the `servers` wrapper):\n\n```json\n{\n  \"server-name\": { ... },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nTop-level keys:\n\n- `servers` — map of server name to `ServerConfig` (optional wrapper; flat form is equivalent)\n- `idleTimeoutMs` — shut down idle language servers after this many milliseconds; disabled by default\n\n## ServerConfig fields\n\n| Field | Type | Required | Description |\n|-------|------|----------|-------------|\n| `command` | `string` | yes | Binary name (resolved via PATH/local bins) or absolute path |\n| `args` | `string[]` | no | Arguments passed to the binary |\n| `fileTypes` | `string[]` | yes | File extensions this server handles, e.g. `[\".ts\", \".tsx\"]` |\n| `rootMarkers` | `string[]` | yes | Files/dirs that indicate a project root; glob patterns (e.g. `*.cabal`) are supported |\n| `initOptions` | `object` | no | Sent as `initializationOptions` during LSP handshake |\n| `settings` | `object` | no | Workspace settings pushed via `workspace/didChangeConfiguration` |\n| `disabled` | `boolean` | no | Set to `true` to disable this server entirely |\n| `warmupTimeoutMs` | `number` | no | Startup timeout in ms for this server (overrides the global default) |\n| `isLinter` | `boolean` | no | Mark server as linter/formatter only; excluded from type-intelligence operations (hover, go-to-definition, etc.) |\n| `capabilities` | `object` | no | Opt-in server-specific features; see [Capabilities](#capabilities) |\n\n`resolvedCommand` is populated automatically at runtime — do not set it manually.\n\n### Capabilities\n\nThe `capabilities` object enables optional server-specific features that GJC supports on a per-server basis:\n\n```json\n{\n  \"capabilities\": {\n    \"flycheck\": true,\n    \"ssr\": true,\n    \"expandMacro\": true,\n    \"runnables\": true,\n    \"relatedTests\": true\n  }\n}\n```\n\nAll fields are boolean and optional. They are currently used by `rust-analyzer`.\n\n## Common recipes\n\n### Override a built-in server's settings\n\nPartial overrides are merged onto the built-in defaults. You only need to specify the fields you want to change.\n\n```json\n{\n  \"servers\": {\n    \"typescript-language-server\": {\n      \"args\": [\"--stdio\", \"--log-level\", \"4\"]\n    }\n  }\n}\n```\n\n```yaml\nservers:\n  gopls:\n    settings:\n      gopls:\n        gofumpt: false\n        staticcheck: false\n```\n\n### Disable a built-in server\n\n```json\n{\n  \"servers\": {\n    \"eslint\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\n### Register a custom server\n\nNew servers require `command`, `fileTypes`, and `rootMarkers`. All other fields are optional.\n\n```json\n{\n  \"servers\": {\n    \"my-lsp\": {\n      \"command\": \"my-lsp-server\",\n      \"args\": [\"--stdio\"],\n      \"fileTypes\": [\".xyz\"],\n      \"rootMarkers\": [\".xyz-project\", \".git\"]\n    }\n  }\n}\n```\n\n### Set a global idle timeout\n\nShut down language servers that have been inactive for more than five minutes:\n\n```json\n{\n  \"idleTimeoutMs\": 300000\n}\n```\n\n### Disable a server for one project, keep it globally\n\nPlace the override in `<project>/.gjc/lsp.json`:\n\n```json\n{\n  \"servers\": {\n    \"pylsp\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\nThe user-level config in `~/.gjc/agent/lsp.json` is unaffected; pylsp is only suppressed in this project.\n\n## Built-in server list\n\nThe following servers ship in `defaults.json` and are eligible for auto-detection:\n\n| Server key | Language(s) | Binary |\n|---|---|---|\n| `rust-analyzer` | Rust | `rust-analyzer` |\n| `clangd` | C, C++, ObjC | `clangd` |\n| `zls` | Zig | `zls` |\n| `gopls` | Go | `gopls` |\n| `typescript-language-server` | TypeScript, JavaScript | `typescript-language-server` |\n| `denols` | TypeScript, JavaScript (Deno) | `deno` |\n| `biome` | TS/JS/JSON (linter) | `biome` |\n| `eslint` | TS/JS/Vue/Svelte (linter) | `vscode-eslint-language-server` |\n| `vscode-html-language-server` | HTML | `vscode-html-language-server` |\n| `vscode-css-language-server` | CSS, SCSS, Less | `vscode-css-language-server` |\n| `vscode-json-language-server` | JSON | `vscode-json-language-server` |\n| `tailwindcss` | HTML, CSS, TS/JS | `tailwindcss-language-server` |\n| `svelte` | Svelte | `svelteserver` |\n| `vue-language-server` | Vue | `vue-language-server` |\n| `astro` | Astro | `astro-ls` |\n| `pyright` | Python | `pyright-langserver` |\n| `basedpyright` | Python | `basedpyright-langserver` |\n| `pylsp` | Python | `pylsp` |\n| `ruff` | Python (linter) | `ruff` |\n| `jdtls` | Java | `jdtls` |\n| `kotlin-lsp` | Kotlin | `kotlin-lsp` |\n| `metals` | Scala | `metals` |\n| `hls` | Haskell | `haskell-language-server-wrapper` |\n| `ocamllsp` | OCaml | `ocamllsp` |\n| `elixirls` | Elixir | `elixir-ls` |\n| `erlangls` | Erlang | `erlang_ls` |\n| `gleam` | Gleam | `gleam` |\n| `solargraph` | Ruby | `solargraph` |\n| `ruby-lsp` | Ruby | `ruby-lsp` |\n| `rubocop` | Ruby (linter) | `rubocop` |\n| `bashls` | Bash, Zsh | `bash-language-server` |\n| `lua-language-server` | Lua | `lua-language-server` |\n| `intelephense` | PHP | `intelephense` |\n| `phpactor` | PHP | `phpactor` |\n| `omnisharp` | C# | `omnisharp` |\n| `yamlls` | YAML | `yaml-language-server` |\n| `terraformls` | Terraform | `terraform-ls` |\n| `dockerls` | Dockerfile | `docker-langserver` |\n| `helm-ls` | Helm | `helm_ls` |\n| `nixd` | Nix | `nixd` |\n| `nil` | Nix | `nil` |\n| `ols` | Odin | `ols` |\n| `dartls` | Dart | `dart` |\n| `marksman` | Markdown | `marksman` |\n| `texlab` | LaTeX | `texlab` |\n| `graphql` | GraphQL | `graphql-lsp` |\n| `prismals` | Prisma | `prisma-language-server` |\n| `vimls` | Vim script | `vim-language-server` |\n| `emmet-language-server` | HTML, CSS, JSX | `emmet-language-server` |\n| `sourcekit-lsp` | Swift | `sourcekit-lsp` |\n| `swiftlint` | Swift (linter) | `swiftlint` |\n| `tlaplus` | TLA+ | `tlapm_lsp` |\n",
 	"memory.md": "# Autonomous Memory\n\nWhen enabled, the agent automatically extracts durable knowledge from past sessions and injects a compact summary into each new session. Over time it builds a project-scoped memory store — technical decisions, recurring workflows, pitfalls — that carries forward without manual effort.\n\nDisabled by default. Enable via `/settings` or `config.yml`:\n\n```yaml\nmemories:\n  enabled: true\n```\n\n## Usage\n\n### What gets injected\n\nAt session start, if a memory summary exists for the current project, it is injected into the system prompt as a **Memory Guidance** block. The agent is instructed to:\n\n- Treat memory as heuristic context — useful for process and prior decisions, not authoritative on current repo state.\n- Cite the memory artifact path when memory changes the plan, and pair it with current-repo evidence before acting.\n- Prefer repo state and user instruction when they conflict with memory; treat conflicting memory as stale.\n\n### Reading memory artifacts\n\nThe agent can read memory files directly using `memory://` URLs with the `read` tool:\n\n| URL                                    | Content                             |\n| -------------------------------------- | ----------------------------------- |\n| `memory://root`                        | Compact summary injected at startup |\n| `memory://root/MEMORY.md`              | Full long-term memory document      |\n| `memory://root/skills/<name>/SKILL.md` | A generated skill playbook          |\n\n### `/memory` slash command\n\n| Subcommand            | Effect                                         |\n| --------------------- | ---------------------------------------------- |\n| `view`                | Show the current memory injection payload      |\n| `clear` / `reset`     | Delete all memory data and generated artifacts |\n| `enqueue` / `rebuild` | Force consolidation to run at next startup     |\n\n## How it works\n\nMemories are built by a background pipeline that runs at startup or when manually triggered via slash command.\n\n**Phase 1 — per-session extraction:** For each past session that has changed since it was last processed, a model reads the session history and extracts durable signal: technical decisions, constraints, resolved failures, recurring workflows. Sessions that are too recent, too old, or currently active are skipped. Each extraction produces a raw memory block and a short synopsis for that session.\n\n**Phase 2 — consolidation:** After extraction, a second model pass reads all per-session extractions and produces three outputs written to disk:\n\n- `MEMORY.md` — a curated long-term memory document\n- `memory_summary.md` — the compact text injected at session start\n- `skills/` — reusable procedural playbooks, each in its own subdirectory\n\nPhase 2 uses a lease to prevent double-running when multiple processes start simultaneously. Stale skill directories from prior runs are pruned automatically.\n\nAll output is scanned for secrets before being written to disk.\n\n### Extraction behavior\n\nMemory extraction and consolidation behavior is driven by static prompt files in `packages/coding-agent/src/prompts/memories/`.\n\n| File                  | Purpose                                     | Variables                                   |\n| --------------------- | ------------------------------------------- | ------------------------------------------- |\n| `stage_one_system.md` | System prompt for per-session extraction    | —                                           |\n| `stage_one_input.md`  | User-turn template wrapping session content | `{{thread_id}}`, `{{response_items_json}}`  |\n| `consolidation.md`    | Prompt for cross-session consolidation      | `{{raw_memories}}`, `{{rollout_summaries}}` |\n| `read_path.md`        | Memory guidance injected into live sessions | `{{memory_summary}}`                        |\n\n### Model selection\n\nMemory piggybacks on the model role system.\n\n| Phase                   | Role                                                                | Purpose                          |\n| ----------------------- | ------------------------------------------------------------------- | -------------------------------- |\n| Phase 1 (extraction)    | `default`                                                           | Per-session knowledge extraction |\n| Phase 2 (consolidation) | `smol` (falls back to `default`, then current/first registry model) | Cross-session synthesis          |\n\nIf the requested memory role is not configured, memory model resolution falls back to the `default` role, then the active session model, then the first model in the registry.\n\n## Configuration\n\n| Setting                               | Default | Description                                               |\n| ------------------------------------- | ------- | --------------------------------------------------------- |\n| `memories.enabled`                    | `false` | Master switch                                             |\n| `memories.maxRolloutAgeDays`          | `30`    | Sessions older than this are not processed                |\n| `memories.minRolloutIdleHours`        | `12`    | Sessions active more recently than this are skipped       |\n| `memories.maxRolloutsPerStartup`      | `64`    | Cap on sessions processed in a single startup             |\n| `memories.summaryInjectionTokenLimit` | `5000`  | Max tokens of the summary injected into the system prompt |\n\nAdditional tuning knobs (concurrency, lease durations, token budgets) are available in config for advanced use.\n\n## Key files\n\n- `packages/coding-agent/src/memories/index.ts` — pipeline orchestration, injection, slash command handling\n- `packages/coding-agent/src/memories/storage.ts` — SQLite-backed job queue and thread registry\n- `packages/coding-agent/src/prompts/memories/` — memory prompt templates\n- `packages/coding-agent/src/internal-urls/memory-protocol.ts` — `memory://` URL handler\n",
-	"models.md": "# Model and Provider Configuration (`models.yml`)\n\nThis document describes how the coding-agent currently loads models, applies overrides, resolves credentials, and chooses models at runtime.\n\n## What controls model behavior\n\nPrimary implementation files:\n\n- `src/config/model-registry.ts` — loads built-in + custom models, provider overrides, runtime discovery, auth integration\n- `src/config/model-resolver.ts` — parses model patterns and selects initial/smol/slow models\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.gjc/agent/models.yml`\n\nLegacy behavior still present:\n\n- If `models.yml` is missing and `models.json` exists at the same location, it is migrated to `models.yml`.\n- Explicit `.json` / `.jsonc` config paths are still supported when passed programmatically to `ModelRegistry`.\n\n## `models.yml` shape\n\n```yaml\nproviders:\n  <provider-id>:\n    # provider-level config\nequivalence:\n  overrides:\n    <provider-id>/<model-id>: <canonical-model-id>\n  exclude:\n    - <provider-id>/<model-id>\n```\n\n`provider-id` is the canonical provider key used across selection and auth lookup.\n\n`equivalence` is optional and configures canonical model grouping on top of concrete provider models:\n\n- `overrides` maps an exact concrete selector (`provider/modelId`) to an official upstream canonical id\n- `exclude` opts a concrete selector out of canonical grouping\n\n## Provider-level fields\n\n```yaml\nproviders:\n  my-provider:\n    baseUrl: https://api.example.com/v1\n    apiKey: MY_PROVIDER_API_KEY\n    api: openai-completions\n    headers:\n      X-Team: platform\n    authHeader: true\n    auth: apiKey\n    disableStrictTools: false  # set true for Anthropic-compatible endpoints that reject the strict field\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\nmodelBindings:\n  modelRoles:\n    default: my-provider/some-model-id:high\n  agentModelOverrides:\n    executor: my-provider/some-model-id\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `bedrock-converse-stream`\n- `anthropic-messages`\n- `bedrock-converse-stream`\n- `google-generative-ai`\n- `google-vertex`\n- `google-gemini-cli`\n- `ollama-chat`\n- `cursor-agent`\n\n\n### First-class Azure OpenAI and Amazon Bedrock examples\n\nAzure OpenAI uses canonical OpenAI model IDs in GJC and resolves those IDs to Azure deployment names at request time. Set `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` to avoid assuming model id equals deployment name:\n\n```yaml\nproviders:\n  azure-openai:\n    baseUrl: https://my-resource.openai.azure.com/openai/v1\n    apiKeyEnv: AZURE_OPENAI_API_KEY\n    api: azure-openai-responses\n    models:\n      - id: gpt-4.1\n      - id: o3\n```\n\n```sh\nexport AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-4.1=gpt-41-prod,o3=o3-reasoning-prod'\n```\n\nAmazon Bedrock uses the native `bedrock-converse-stream` transport and AWS credential chain auth. Do not put AWS access keys in `models.yml`; configure `AWS_REGION` / `AWS_PROFILE` or standard static AWS credential environment variables instead:\n\n```yaml\nproviders:\n  amazon-bedrock:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com\n    api: bedrock-converse-stream\n    models:\n      - id: us.anthropic.claude-opus-4-6-v1\n      - id: anthropic.claude-3-5-sonnet-20241022-v2:0\n```\n\n### MiniMax and GLM custom provider examples\n\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://open.bigmodel.cn/api/paas/v4\n    apiKeyEnv: ZAI_API_KEY\n    api: openai-completions\n    compat:\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n    models:\n      - id: glm-4.6\n```\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `models.yml` is strict: unknown provider/model keys fail validation before provider dispatch, so stale keys such as `requestTransform` or `wireModelId` only work where this document lists them.\n- `discovery.type`: `ollama`, `llama.cpp`, or `lm-studio`\n\n## OpenAI-compatible proxy configuration\n\nOpenAI-compatible proxy providers should use schema-supported provider keys first:\n\n```yaml\nproviders:\n  proxy-provider:\n    baseUrl: https://api.proxy.example/v1\n    apiKeyEnv: PROXY_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: local-gpt\n        name: Local GPT\n        reasoning: true\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n```\n\nUse provider-level `headers` for proxy-required headers. Keep the provider `api` set to `openai-completions` when the proxy exposes Chat Completions-compatible `/v1/chat/completions` semantics. `auth: apiKey` sends the resolved token as bearer auth; use `auth: none` only for trusted local/no-auth endpoints.\n\n`requestTransform` and `wireModelId` remain supported for request-body shaping, but they are not needed for ordinary OpenAI-compatible proxies whose local model id is already the upstream wire id. Unknown config keys fail validation before a provider request is sent.\n\nWhen request shaping is needed:\n\n- `requestTransform.profile: openai-proxy` strips OpenAI SDK/Stainless telemetry headers at final fetch time and sets a generic GJC user agent.\n- `stripHeaders` replaces the preset strip list when provided.\n- `setHeaders` is applied after stripping; use `null` to remove a header.\n- `extraBody` is shallow-merged into the JSON request body after provider compatibility fields; core transport keys such as `model`, `messages`/`input`, `stream`, `tools`, and `tool_choice` are protected and ignored.\n- Model-level `requestTransform` overrides provider-level fields and shallow-merges `setHeaders`/`extraBody`.\n- `wireModelId` changes only the upstream request body model id; local selection still uses `provider/id`.\n\n### Layofflabs-style proxy example\n\n```yaml\nproviders:\n  layofflabs:\n    baseUrl: https://api.layofflabs.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-5.5\n        name: GPT 5.5 via Layofflabs\n        reasoning: true\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n\nmodelBindings:\n  modelRoles:\n    default: layofflabs/gpt-5.5:high\n  agentModelOverrides:\n    executor: layofflabs/gpt-5.5:high\n```\n\n## Validation rules (current)\n\n### Full custom provider (`models` is non-empty)\n\nRequired:\n\n- `baseUrl`\n- `apiKey` unless `auth: none`\n- `api` at provider level or each model\n\n### Override-only provider (`models` missing or empty)\n\nMust define at least one of:\n\n- `baseUrl`\n- `headers`\n- `compat`\n- `requestTransform`\n- `disableStrictTools`\n- `modelOverrides`\n- `discovery`\n\n### Discovery\n\n- `discovery` requires provider-level `api`.\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\n- unknown provider, model, override, and request-transform keys fail schema validation; remove stale keys instead of relying on them being ignored.\n\n## Merge and override order\n\nModelRegistry pipeline (on refresh):\n\n1. Load built-in providers/models from `@gajae-code/ai`.\n2. Load `models.yml` custom config.\n3. Apply provider overrides (`baseUrl`, `headers`, `requestTransform`, `disableStrictTools`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (schema v3) with a `static_fingerprint` column that hashes the\nstatic catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process via a WeakMap keyed by the static-models array\nreference, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `anthropic-model-opus-4-6`\n- `anthropic-model-haiku-4-5`\n- `gpt-5.3-openai-code`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: openai-code\n        name: Zenmux OpenAI code\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/openai-code: gpt-5.3-openai-code\n    p-openai-code/openai-code: gpt-5.3-openai-code\n  exclude:\n    - demo/openai-code-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `input`, `cost`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL` or `http://127.0.0.1:11434`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `GJC_AUTH_BROKER_URL` (or `auth.broker.url`) is set, the local SQLite credential store is replaced by `RemoteAuthCredentialStore`. Layers 2 and 3 above (stored API key / OAuth in `agent.db`) are served from a broker-supplied snapshot whose `refresh` tokens are redacted; expiry triggers `POST /v1/credential/:id/refresh` on the broker rather than a local refresh.\n\n`AuthStorage.setConfigApiKey` lets a `models.yml` `apiKey` win over a broker-resolved OAuth token without overriding a runtime `--api-key`. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full broker / gateway design and env surface (`GJC_AUTH_BROKER_URL`, `GJC_AUTH_BROKER_TOKEN`, `auth.broker.url`, `auth.broker.token`).\n\n## Model availability vs all models\n\n- `getAll()` returns the loaded model registry (built-in + merged custom + discovered).\n- `getAvailable()` filters to models that are keyless or have resolvable auth.\n\nSo a model can exist in registry but not be selectable until auth is available.\n\n## Runtime model resolution\n\n### CLI and pattern parsing\n\n`model-resolver.ts` supports:\n\n- exact `provider/modelId`\n- exact canonical model id\n- exact model id (provider inferred)\n- fuzzy/substring matching\n- glob scope patterns in `--models` (e.g. `openai/*`, `*sonnet*`)\n- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh`)\n\n`--provider` is legacy; `--model` is preferred.\n\nResolution precedence for exact selectors:\n\n1. exact `provider/modelId` bypasses coalescing\n2. exact canonical id resolves through the canonical index\n3. exact bare concrete id still works\n4. fuzzy and glob matching run after the exact paths\n\n### Initial model selection priority\n\n`findInitialModel(...)` uses this order:\n\n1. explicit CLI provider+model\n2. first scoped model (if not resuming)\n3. saved default provider/model\n4. known provider defaults (e.g. OpenAI/Anthropic/etc.) among available models\n5. first available model\n\n### Role aliases and settings\n\nSupported model roles:\n\n- `default`, `smol`, `slow`, `vision`, `plan`, `designer`, `commit`, `task`\n\nRole aliases like `pi/smol` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI code provider transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-openai-code` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - anthropic-model-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/anthropic-model-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `--list-models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `--list-models` prints a canonical section plus the concrete provider rows\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI code provider websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for Spark -> non-Spark on the same provider:\n\n```yaml\nproviders:\n  openai-code:\n    modelOverrides:\n      gpt-5.3-openai-code-spark:\n        contextPromotionTarget: openai-code/gpt-5.3-openai-code\n```\n\nThe built-in model generator also assigns this automatically for `*-spark` models when a same-provider base model exists.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/ai/src/providers/openai-completions-compat.ts`. It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/model-registry.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/ai/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok and zAI).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true  # if the proxy doesn't support strict tool schemas\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/anthropic-model-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.gjc/agent/models.yml`.\n\n## Failure mode\n\nIf `models.yml` fails schema or validation checks:\n\n- registry keeps operating with built-in models\n- error is exposed via `ModelRegistry.getError()` and surfaced in UI/notifications\n",
+	"models.md": "# Model and Provider Configuration (`models.yml`)\n\nThis document describes how the coding-agent currently loads models, applies overrides, resolves credentials, and chooses models at runtime.\n\n## What controls model behavior\n\nPrimary implementation files:\n\n- `src/config/model-registry.ts` — loads built-in + custom models, provider overrides, runtime discovery, auth integration\n- `src/config/model-resolver.ts` — parses model patterns and selects initial/smol/slow models\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.gjc/agent/models.yml`\n\nLegacy behavior still present:\n\n- If `models.yml` is missing and `models.json` exists at the same location, it is migrated to `models.yml`.\n- Explicit `.json` / `.jsonc` config paths are still supported when passed programmatically to `ModelRegistry`.\n\n## `models.yml` shape\n\n```yaml\nproviders:\n  <provider-id>:\n    # provider-level config\nequivalence:\n  overrides:\n    <provider-id>/<model-id>: <canonical-model-id>\n  exclude:\n    - <provider-id>/<model-id>\n```\n\n`provider-id` is the canonical provider key used across selection and auth lookup.\n\n`equivalence` is optional and configures canonical model grouping on top of concrete provider models:\n\n- `overrides` maps an exact concrete selector (`provider/modelId`) to an official upstream canonical id\n- `exclude` opts a concrete selector out of canonical grouping\n\n## Provider-level fields\n\n```yaml\nproviders:\n  my-provider:\n    baseUrl: https://api.example.com/v1\n    apiKey: MY_PROVIDER_API_KEY\n    api: openai-completions\n    headers:\n      X-Team: platform\n    authHeader: true\n    auth: apiKey\n    disableStrictTools: false  # set true for Anthropic-compatible endpoints that reject the strict field\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\nmodelBindings:\n  modelRoles:\n    default: my-provider/some-model-id:high\n  agentModelOverrides:\n    executor: my-provider/some-model-id\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `bedrock-converse-stream`\n- `anthropic-messages`\n- `bedrock-converse-stream`\n- `google-generative-ai`\n- `google-vertex`\n- `google-gemini-cli`\n- `ollama-chat`\n- `cursor-agent`\n\n\n### First-class Azure OpenAI and Amazon Bedrock examples\n\nAzure OpenAI uses canonical OpenAI model IDs in GJC and resolves those IDs to Azure deployment names at request time. Set `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` to avoid assuming model id equals deployment name:\n\n```yaml\nproviders:\n  azure-openai:\n    baseUrl: https://my-resource.openai.azure.com/openai/v1\n    apiKeyEnv: AZURE_OPENAI_API_KEY\n    api: azure-openai-responses\n    models:\n      - id: gpt-4.1\n      - id: o3\n```\n\n```sh\nexport AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-4.1=gpt-41-prod,o3=o3-reasoning-prod'\n```\n\nAmazon Bedrock uses the native `bedrock-converse-stream` transport and AWS credential chain auth. Do not put AWS access keys in `models.yml`; configure `AWS_REGION` / `AWS_PROFILE` or standard static AWS credential environment variables instead:\n\n```yaml\nproviders:\n  amazon-bedrock:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com\n    api: bedrock-converse-stream\n    models:\n      - id: us.anthropic.claude-opus-4-6-v1\n      - id: anthropic.claude-3-5-sonnet-20241022-v2:0\n```\n\n### MiniMax and GLM custom provider examples\n\nFor common MiniMax and GLM/zAI setup, prefer the provider presets so the OpenAI-compatible API, base URL, env var, model id, and compatibility flags are written together:\n\n```sh\ngjc setup provider --preset minimax\ngjc setup provider --preset minimax-cn\ngjc setup provider --preset glm\n```\n\nThe same presets are available inside the TUI:\n\n```text\n/provider add --preset minimax\n/provider add --preset glm\n/provider add zai\n```\n\nPresets only write `models.yml` entries that reference documented environment variable names (`MINIMAX_CODE_API_KEY`, `MINIMAX_CODE_CN_API_KEY`, or `ZAI_API_KEY`); they do not store or validate real credentials. The GLM preset aliases (`glm`, `zai`, `z-ai`) write an OpenAI-compatible custom provider named `glm-proxy` and do not replace the first-class `zai` provider.\n\nMiniMax's OpenAI-compatible endpoint rejects multiple system messages and emits thinking in `reasoning_content`, so pin the public-safe compatibility fields when hand-authoring a custom provider:\n\n```yaml\nproviders:\n  minimax-custom:\n    baseUrl: https://api.minimax.io/v1\n    apiKeyEnv: MINIMAX_API_KEY\n    api: openai-completions\n    compat:\n      supportsStore: false\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n      reasoningContentField: reasoning_content\n    models:\n      - id: MiniMax-M2.5\n```\n\nGLM via z.ai is available as the first-class `zai` provider. For a private GLM-compatible proxy, keep secrets in an env var and disable OpenAI-only request fields as needed:\n\n```yaml\nproviders:\n  glm-proxy:\n    baseUrl: https://api.z.ai/api/paas/v4\n    apiKeyEnv: ZAI_API_KEY\n    api: openai-completions\n    compat:\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n    models:\n      - id: glm-4.6\n```\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `models.yml` is strict: unknown provider/model keys fail validation before provider dispatch, so stale keys such as `requestTransform` or `wireModelId` only work where this document lists them.\n- `discovery.type`: `ollama`, `llama.cpp`, or `lm-studio`\n\n## OpenAI-compatible proxy configuration\n\nOpenAI-compatible proxy providers should use schema-supported provider keys first:\n\n```yaml\nproviders:\n  proxy-provider:\n    baseUrl: https://api.proxy.example/v1\n    apiKeyEnv: PROXY_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: local-gpt\n        name: Local GPT\n        reasoning: true\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n```\n\nUse provider-level `headers` for proxy-required headers. Keep the provider `api` set to `openai-completions` when the proxy exposes Chat Completions-compatible `/v1/chat/completions` semantics. `auth: apiKey` sends the resolved token as bearer auth; use `auth: none` only for trusted local/no-auth endpoints.\n\n`requestTransform` and `wireModelId` remain supported for request-body shaping, but they are not needed for ordinary OpenAI-compatible proxies whose local model id is already the upstream wire id. Unknown config keys fail validation before a provider request is sent.\n\nWhen request shaping is needed:\n\n- `requestTransform.profile: openai-proxy` strips OpenAI SDK/Stainless telemetry headers at final fetch time and sets a generic GJC user agent.\n- `stripHeaders` replaces the preset strip list when provided.\n- `setHeaders` is applied after stripping; use `null` to remove a header.\n- `extraBody` is shallow-merged into the JSON request body after provider compatibility fields; core transport keys such as `model`, `messages`/`input`, `stream`, `tools`, and `tool_choice` are protected and ignored.\n- Model-level `requestTransform` overrides provider-level fields and shallow-merges `setHeaders`/`extraBody`.\n- `wireModelId` changes only the upstream request body model id; local selection still uses `provider/id`.\n\n### Layofflabs-style proxy example\n\n```yaml\nproviders:\n  layofflabs:\n    baseUrl: https://api.layofflabs.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-5.5\n        name: GPT 5.5 via Layofflabs\n        reasoning: true\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n\nmodelBindings:\n  modelRoles:\n    default: layofflabs/gpt-5.5:high\n  agentModelOverrides:\n    executor: layofflabs/gpt-5.5:high\n```\n\n## Validation rules (current)\n\n### Full custom provider (`models` is non-empty)\n\nRequired:\n\n- `baseUrl`\n- `apiKey` unless `auth: none`\n- `api` at provider level or each model\n\n### Override-only provider (`models` missing or empty)\n\nMust define at least one of:\n\n- `baseUrl`\n- `headers`\n- `compat`\n- `requestTransform`\n- `disableStrictTools`\n- `modelOverrides`\n- `discovery`\n\n### Discovery\n\n- `discovery` requires provider-level `api`.\n\n### Model value checks\n\n- `id` required\n- `contextWindow` and `maxTokens` must be positive if provided\n- unknown provider, model, override, and request-transform keys fail schema validation; remove stale keys instead of relying on them being ignored.\n\n## Merge and override order\n\nModelRegistry pipeline (on refresh):\n\n1. Load built-in providers/models from `@gajae-code/ai`.\n2. Load `models.yml` custom config.\n3. Apply provider overrides (`baseUrl`, `headers`, `requestTransform`, `disableStrictTools`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (schema v3) with a `static_fingerprint` column that hashes the\nstatic catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process via a WeakMap keyed by the static-models array\nreference, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `anthropic-model-opus-4-6`\n- `anthropic-model-haiku-4-5`\n- `gpt-5.3-openai-code`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: openai-code\n        name: Zenmux OpenAI code\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/openai-code: gpt-5.3-openai-code\n    p-openai-code/openai-code: gpt-5.3-openai-code\n  exclude:\n    - demo/openai-code-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `input`, `cost`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL` or `http://127.0.0.1:11434`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `GJC_AUTH_BROKER_URL` (or `auth.broker.url`) is set, the local SQLite credential store is replaced by `RemoteAuthCredentialStore`. Layers 2 and 3 above (stored API key / OAuth in `agent.db`) are served from a broker-supplied snapshot whose `refresh` tokens are redacted; expiry triggers `POST /v1/credential/:id/refresh` on the broker rather than a local refresh.\n\n`AuthStorage.setConfigApiKey` lets a `models.yml` `apiKey` win over a broker-resolved OAuth token without overriding a runtime `--api-key`. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full broker / gateway design and env surface (`GJC_AUTH_BROKER_URL`, `GJC_AUTH_BROKER_TOKEN`, `auth.broker.url`, `auth.broker.token`).\n\n## Model availability vs all models\n\n- `getAll()` returns the loaded model registry (built-in + merged custom + discovered).\n- `getAvailable()` filters to models that are keyless or have resolvable auth.\n\nSo a model can exist in registry but not be selectable until auth is available.\n\n## Runtime model resolution\n\n### CLI and pattern parsing\n\n`model-resolver.ts` supports:\n\n- exact `provider/modelId`\n- exact canonical model id\n- exact model id (provider inferred)\n- fuzzy/substring matching\n- glob scope patterns in `--models` (e.g. `openai/*`, `*sonnet*`)\n- optional `:thinkingLevel` suffix (`off|minimal|low|medium|high|xhigh`)\n\n`--provider` is legacy; `--model` is preferred.\n\nResolution precedence for exact selectors:\n\n1. exact `provider/modelId` bypasses coalescing\n2. exact canonical id resolves through the canonical index\n3. exact bare concrete id still works\n4. fuzzy and glob matching run after the exact paths\n\n### Initial model selection priority\n\n`findInitialModel(...)` uses this order:\n\n1. explicit CLI provider+model\n2. first scoped model (if not resuming)\n3. saved default provider/model\n4. known provider defaults (e.g. OpenAI/Anthropic/etc.) among available models\n5. first available model\n\n### Role aliases and settings\n\nSupported model roles:\n\n- `default`, `smol`, `slow`, `vision`, `plan`, `designer`, `commit`, `task`\n\nRole aliases like `pi/smol` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI code provider transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-openai-code` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - anthropic-model-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/anthropic-model-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `--list-models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `--list-models` prints a canonical section plus the concrete provider rows\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI code provider websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for Spark -> non-Spark on the same provider:\n\n```yaml\nproviders:\n  openai-code:\n    modelOverrides:\n      gpt-5.3-openai-code-spark:\n        contextPromotionTarget: openai-code/gpt-5.3-openai-code\n```\n\nThe built-in model generator also assigns this automatically for `*-spark` models when a same-provider base model exists.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/ai/src/providers/openai-completions-compat.ts`. It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/model-registry.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/ai/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok and zAI).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true  # if the proxy doesn't support strict tool schemas\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/anthropic-model-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.gjc/agent/models.yml`.\n\n## Failure mode\n\nIf `models.yml` fails schema or validation checks:\n\n- registry keeps operating with built-in models\n- error is exposed via `ModelRegistry.getError()` and surfaced in UI/notifications\n",
 	"natives-addon-loader-runtime.md": "# Natives Addon Loader Runtime\n\nThis document covers the runtime loader shipped by `@gajae-code/natives`: how `native/index.js` decides which `.node` file to require, how compiled-binary embedded payloads are extracted, and what startup failures report.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/package.json`\n\n## Scope and responsibility\n\nThe loader is intentionally narrow:\n\n- Build a platform/CPU-aware candidate list for addon filenames and directories.\n- Treat an embedded-addon manifest as the authoritative compiled-binary signal when present.\n- Optionally materialize an embedded addon into a versioned per-user cache directory.\n- Attempt candidates in deterministic order and return the first addon that `require(...)` loads.\n\nThe current loader does **not** run a separate `validateNative(...)` export-presence gate. API shape is provided by the generated N-API binding file (`native/index.d.ts`) and the loaded addon itself. A stale binary therefore normally fails as a missing property or native load error rather than as a custom \"missing exports\" validation error.\n\n## Runtime inputs and derived state\n\nAt module initialization, `native/index.js` computes:\n\n- **Platform tag**: `${process.platform}-${process.arch}` (for example `darwin-arm64`).\n- **Package version**: from `packages/natives/package.json`.\n- **Core directories**:\n  - `nativeDir`: package-local `packages/natives/native`.\n  - `execDir`: directory containing `process.execPath`.\n  - `versionedDir`: `<getNativesDir()>/<packageVersion>`.\n  - `userDataDir` fallback:\n    - Windows: `%LOCALAPPDATA%/gjc` or `%USERPROFILE%/AppData/Local/gjc`.\n    - Non-Windows: `~/.local/bin`.\n- **Natives cache root** (`getNativesDir()`):\n  - if `$XDG_DATA_HOME/gjc` exists, `$XDG_DATA_HOME/gjc/natives`;\n  - otherwise `~/.gjc/natives`.\n- **Compiled-binary mode** (`detectCompiledBinary`): true if any of:\n  - embedded-addon manifest is non-null,\n  - `GJC_COMPILED` env var is set,\n  - `import.meta.url` contains Bun embedded markers (`$bunfs`, `~BUN`, `%7EBUN`).\n- **Variant override**: `GJC_NATIVE_VARIANT` (`modern`/`baseline` only; invalid values ignored).\n- **Selected variant**: explicit override, otherwise runtime AVX2 detection on x64 (`modern` if AVX2, else `baseline`).\n\n## Platform support and tag resolution\n\n`SUPPORTED_PLATFORMS` is fixed to:\n\n- `linux-x64`\n- `linux-arm64`\n- `darwin-x64`\n- `darwin-arm64`\n- `win32-x64`\n\nUnsupported platforms are not rejected before probing. The loader first tries the computed candidate paths. If all fail and `platformTag` is unsupported, it throws an unsupported-platform error listing supported tags.\n\n## Variant selection (`modern` / `baseline` / default)\n\n### x64 behavior\n\n1. `GJC_NATIVE_VARIANT=modern|baseline` wins when valid.\n2. Otherwise AVX2 support is detected:\n   - Linux: scan `/proc/cpuinfo` for `avx2`.\n   - macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`.\n   - Windows: PowerShell `[System.Runtime.Intrinsics.X86.Avx2]::IsSupported`.\n3. AVX2 selects `modern`; unavailable or undetectable AVX2 selects `baseline`.\n\n### Non-x64 behavior\n\nNo variant suffix is used; the filename is `pi_natives.<platform>-<arch>.node`.\n\n### Filename construction\n\n`loader-state.js#getAddonFilenames` returns:\n\n- Non-x64 or no variant: `pi_natives.<tag>.node`\n- x64 + `modern`:\n  1. `pi_natives.<tag>-modern.node`\n  2. `pi_natives.<tag>-baseline.node`\n  3. `pi_natives.<tag>.node`\n- x64 + `baseline`:\n  1. `pi_natives.<tag>-baseline.node`\n  2. `pi_natives.<tag>.node`\n\nThe default unsuffixed fallback remains part of the x64 candidate list.\n\n## Candidate path construction and fallback ordering\n\n`resolveLoaderCandidates(...)` expands every filename across directories, then de-duplicates while preserving first occurrence order.\n\n### Non-compiled runtime\n\nFor each filename, candidates are:\n\n1. `<nativeDir>/<filename>`\n2. `<execDir>/<filename>`\n\n### Compiled runtime\n\nFor each filename, candidates are:\n\n1. `<versionedDir>/<filename>`\n2. `<userDataDir>/<filename>`\n3. `<nativeDir>/<filename>`\n4. `<execDir>/<filename>`\n\nAt load time, an extracted embedded candidate, when produced, is prepended ahead of these de-duplicated candidates.\n\n## Embedded addon extraction lifecycle\n\n`embedded-addon.js` is generated by `scripts/embed-native.ts`. The reset stub exports `embeddedAddon = null`. A populated manifest has:\n\n- `platformTag`\n- `version`\n- `files[]` entries with `variant`, `filename`, and `filePath`\n\nExtraction (`maybeExtractEmbeddedAddon`) runs only when:\n\n1. compiled-binary mode is true,\n2. `embeddedAddon` is non-null,\n3. manifest `platformTag` equals the runtime platform tag,\n4. manifest `version` equals the package version,\n5. a variant-appropriate embedded file exists.\n\nVariant file selection:\n\n- Non-x64: prefer `default`, then first available file.\n- x64 + `modern`: prefer `modern`, fallback to `baseline`.\n- x64 + `baseline`: require `baseline`.\n\nMaterialization:\n\n1. Ensure `<versionedDir>` exists.\n2. Reuse `<versionedDir>/<selected filename>` if it already exists.\n3. Otherwise read `selectedEmbeddedFile.filePath` and write the target path.\n4. Return the target path as the first candidate.\n\nDirectory creation or write failures are appended to the loader error list; probing continues through normal candidates.\n\n## Lifecycle and state transitions\n\n```text\nInit\n  -> Load package metadata and embedded-addon manifest\n  -> Compute platform/version/variant/filenames/candidate paths\n  -> (compiled + embedded manifest matches?)\n       yes -> try extract to versionedDir (record errors, continue)\n       no  -> skip extraction\n  -> For each runtime candidate in order:\n       require(candidate)\n       -> success: return addon exports (READY)\n       -> failure: record error, continue\n  -> none loaded:\n       if unsupported platform tag -> throw Unsupported platform\n       else -> throw Failed to load (tried-path diagnostics + hints)\n```\n\n## Failure behavior and diagnostics\n\n### Unsupported platform\n\nIf all candidates fail and `platformTag` is not supported, the loader throws:\n\n- `Unsupported platform: <tag>`\n- supported platform list\n- issue-reporting guidance\n\n### No loadable candidate\n\nIf the platform is supported but no candidate can be loaded, the final error includes:\n\n- `Failed to load pi_natives native addon for <platformTag>` or `<platformTag> (<variant>)`\n- every attempted path with the corresponding `require(...)` error\n- mode-specific remediation hints\n\n### Compiled-binary startup failures\n\nCompiled mode diagnostics include:\n\n- expected versioned cache target paths (`<versionedDir>/<filename>`),\n- remediation to delete the versioned cache and rerun,\n- direct release download `curl` commands for each expected filename.\n\n### Non-compiled startup failures\n\nNormal package/runtime diagnostics include:\n\n- reinstall hint (`bun install @gajae-code/natives`),\n- local rebuild command (`bun --cwd=packages/natives run build`),\n- optional x64 variant build hint (`TARGET_VARIANT=baseline|modern bun --cwd=packages/natives run build`).\n",
 	"natives-architecture.md": "# Natives Architecture\n\n`@gajae-code/natives` is now a two-layer package around a loader:\n\n1. **CommonJS loader/package entrypoint** resolves and loads the correct `.node` addon and patches generated enum objects onto the export object.\n2. **Rust N-API module layer** implements the exported functions/classes and emits the generated TypeScript declarations.\n\nThis document is the foundation for deeper module-level docs.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n\n## Package entrypoint and public surface\n\n`packages/natives/package.json` points directly at generated native bindings:\n\n- `main`: `./native/index.js`\n- `types`: `./native/index.d.ts`\n- `exports[\".\"].types`: `./native/index.d.ts`\n- `exports[\".\"].import`: `./native/index.js`\n\nThere is no current `packages/natives/src` TypeScript wrapper layer. Consumers import functions/classes/enums directly from `@gajae-code/natives`; the type contract is the generated `native/index.d.ts` plus enum exports appended by `scripts/gen-enums.ts`.\n\nCurrent capability groups in the generated API include:\n\n- **Search/text/code primitives**: `grep`, `search`, `hasMatch`, `fuzzyFind`, `glob`, `astGrep`, `astEdit`, text width/slicing/wrapping/sanitization, syntax highlighting, token counting.\n- **Execution/process/terminal primitives**: `executeShell`, `Shell`, `PtySession`, process-tree helpers, key parsing.\n- **System/media/conversion primitives**: clipboard, image resize/encode/SIXEL, HTML-to-Markdown, macOS appearance/power helpers, work profiling, Windows ProjFS overlay helpers.\n\n## Loader layer\n\n`packages/natives/native/index.js` owns runtime addon selection and optional embedded extraction.\n\n### Candidate resolution model\n\n- Platform tag is `${process.platform}-${process.arch}`.\n- Supported tags are currently:\n  - `linux-x64`\n  - `linux-arm64`\n  - `darwin-x64`\n  - `darwin-arm64`\n  - `win32-x64`\n- x64 can use CPU variants:\n  - `modern` (AVX2-capable)\n  - `baseline` (fallback)\n- Non-x64 uses the default filename without a variant suffix.\n\nFilename strategy:\n\n- Default: `pi_natives.<platform>-<arch>.node`\n- x64 variant: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- x64 runtime fallback includes the unsuffixed default filename after variant candidates.\n\n### Platform-specific variant detection\n\nFor x64, variant selection uses:\n\n- Linux: `/proc/cpuinfo`\n- macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`\n- Windows: PowerShell check for `System.Runtime.Intrinsics.X86.Avx2`\n\n`GJC_NATIVE_VARIANT` can force `modern` or `baseline`; invalid values are ignored.\n\n### Binary distribution and extraction model\n\n`packages/natives/package.json` publishes `native/`, which contains the loader, generated declarations, generated enum patch, embedded-addon manifest stub, and prebuilt `.node` artifacts.\n\nFor compiled binaries, loader behavior is:\n\n1. Check versioned user cache path: `<getNativesDir()>/<packageVersion>/...`.\n2. Check legacy compiled-binary location:\n   - Windows: `%LOCALAPPDATA%/gjc` (fallback `%USERPROFILE%/AppData/Local/gjc`)\n   - non-Windows: `~/.local/bin`\n3. Fall back to packaged `native/` and executable directory candidates.\n\n`getNativesDir()` uses `$XDG_DATA_HOME/gjc/natives` when `$XDG_DATA_HOME/gjc` exists; otherwise it uses `~/.gjc/natives`.\n\nIf a populated embedded addon manifest is present, it is also treated as a compiled-binary signal. The loader can extract the matching embedded `.node` into the versioned cache directory before candidate probing.\n\n### Failure modes\n\nLoader failures are explicit:\n\n- **Unsupported platform tag**: after failed probing, throws with supported platform list.\n- **No loadable candidate**: throws with all attempted paths and remediation hints.\n- **Embedded extraction errors**: directory/write failures are recorded and included in final load diagnostics if no candidate loads.\n\nThe current loader does not perform a separate post-`require` export validation pass.\n\n## Rust N-API module layer\n\n`crates/pi-natives/src/lib.rs` declares exported module ownership:\n\n- `appearance`\n- `ast`\n- `clipboard`\n- `fd`\n- `fs_cache`\n- `glob`\n- `glob_util`\n- `grep`\n- `highlight`\n- `html`\n- `image`\n- `keys`\n- `language`\n- `power`\n- `prof`\n- `projfs_overlay`\n- `ps`\n- `pty`\n- `shell`\n- `task`\n- `text`\n- `tokens`\n- `utils` (crate-private helpers)\n\nN-API exports are generated from Rust `#[napi]` functions/classes/objects/enums. Snake_case Rust names are exposed as camelCase JavaScript names unless explicitly configured by napi-rs.\n\n## Ownership boundaries\n\n- **Loader/package ownership (`packages/natives/native`, `packages/natives/scripts`)**\n  - runtime binary selection\n  - CPU variant selection and override handling\n  - compiled-binary embedded extraction\n  - generated TypeScript declarations and enum export patching\n- **Rust ownership (`crates/pi-natives/src`)**\n  - algorithmic and system-level implementation\n  - platform-native behavior and performance-sensitive logic\n  - N-API symbol implementation consumed directly by package callers\n- **Consumer ownership (`packages/coding-agent`, `packages/tui`)**\n  - user-facing policy and fallbacks that are not built into the native API\n  - higher-level rendering, artifact, shell-session, and command behavior\n\n## Runtime flow (high level)\n\n1. Consumer imports from `@gajae-code/natives`.\n2. `native/index.js` computes platform/arch/variant and candidate paths.\n3. Optional embedded binary extraction occurs for compiled distributions.\n4. The first `require(candidate)` that succeeds becomes the exported addon object.\n5. Generated enum objects are appended to `module.exports`.\n6. Caller invokes generated N-API functions/classes directly.\n\n## Glossary\n\n- **Native addon**: A `.node` binary loaded via Node-API (N-API).\n- **Platform tag**: Runtime tuple `platform-arch` (for example `darwin-arm64`).\n- **Variant**: x64 CPU-specific build flavor (`modern` AVX2, `baseline` fallback).\n- **Generated binding declaration**: `native/index.d.ts` emitted by napi-rs during `build-native.ts`.\n- **Compiled binary mode**: Runtime mode where the CLI is bundled and native addons are resolved from embedded/cache paths before package-local paths.\n- **Embedded addon**: Build artifact metadata and file references generated into `native/embedded-addon.js` so compiled binaries can extract matching `.node` payloads.\n",
 	"natives-binding-contract.md": "# Natives Binding Contract (JavaScript/TypeScript Side)\n\nThis document defines the JS/TS contract between `@gajae-code/natives` callers and the loaded N-API addon.\n\nCurrent package shape is direct-to-native: there is no `packages/natives/src/<module>` TypeScript wrapper layer. The public API is the generated `packages/natives/native/index.d.ts` declaration file, the CommonJS loader in `packages/natives/native/index.js`, and the Rust `#[napi]` exports in `crates/pi-natives/src`.\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n- Rust modules under `crates/pi-natives/src/*.rs`\n\n## Contract model\n\nThe contract has three parts:\n\n1. **Generated runtime loader** (`native/index.js`)\n   - computes candidates and `require(...)`s the `.node` addon;\n   - exports the loaded addon object directly;\n   - appends enum objects generated by `scripts/gen-enums.ts`.\n2. **Generated TypeScript declarations** (`native/index.d.ts`)\n   - generated by napi-rs during `scripts/build-native.ts`;\n   - declares exported functions, classes, object interfaces, and native enums;\n   - is the package `types` entry.\n3. **Rust N-API exports** (`crates/pi-natives/src`)\n   - `#[napi]` functions/classes/objects/enums are the source of generated declarations and runtime symbols;\n   - snake_case Rust names become camelCase JavaScript names by napi-rs convention.\n\nThere is no current `NativeBindings` declaration-merging lifecycle and no `validateNative(...)` required-export list in the loader.\n\n## Public export surface organization\n\n`packages/natives/package.json` exposes the package root only:\n\n```json\n{\n  \"main\": \"./native/index.js\",\n  \"types\": \"./native/index.d.ts\",\n  \"exports\": {\n    \".\": {\n      \"types\": \"./native/index.d.ts\",\n      \"import\": \"./native/index.js\"\n    }\n  }\n}\n```\n\nConsumers in `packages/coding-agent` and `packages/tui` import directly from `@gajae-code/natives`.\n\n## JS API ↔ native export mapping (representative)\n\n| Category          | Public JS API                                                                                              | Rust source                                                 | Return style                  |\n| ----------------- | ---------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------- | ----------------------------- |\n| Grep              | `grep(options, onMatch?)`                                                                                  | `grep.rs`                                                   | `Promise<GrepResult>`         |\n| Grep              | `search(content, options)`                                                                                 | `grep.rs`                                                   | `SearchResult`                |\n| Grep              | `hasMatch(content, pattern, ignoreCase?, multiline?)`                                                      | `grep.rs`                                                   | `boolean`                     |\n| Fuzzy path search | `fuzzyFind(options)`                                                                                       | `fd.rs`                                                     | `Promise<FuzzyFindResult>`    |\n| Glob              | `glob(options, onMatch?)`                                                                                  | `glob.rs`                                                   | `Promise<GlobResult>`         |\n| Glob cache        | `invalidateFsScanCache(path?)`                                                                             | `fs_cache.rs`                                               | `void`                        |\n| AST search/edit   | `astGrep(options)`, `astEdit(options)`                                                                     | `ast.rs`                                                    | `Promise<...>`                |\n| Shell             | `executeShell(options, onChunk?)`                                                                          | `shell.rs`                                                  | `Promise<ShellExecuteResult>` |\n| Shell             | `new Shell(options?)`, `shell.run(...)`, `shell.abort()`                                                   | `shell.rs`                                                  | class / promises              |\n| PTY               | `new PtySession()`, `start/write/resize/kill`                                                              | `pty.rs`                                                    | class / promises              |\n| Process           | `killTree(pid, signal)`, `listDescendants(pid)`                                                            | `ps.rs`                                                     | sync                          |\n| Keys              | `parseKey`, `matchesKey`, Kitty/legacy helpers                                                             | `keys.rs`                                                   | sync                          |\n| Text              | `wrapTextWithAnsi`, `truncateToWidth`, `sliceWithWidth`, `extractSegments`, `visibleWidth`                 | `text.rs`                                                   | sync                          |\n| Highlight         | `highlightCode`, `supportsLanguage`, `getSupportedLanguages`                                               | `highlight.rs`                                              | sync                          |\n| HTML              | `htmlToMarkdown(html, options?)`                                                                           | `html.rs`                                                   | `Promise<string>`             |\n| Image             | `PhotonImage`, `encodeSixel`                                                                               | `image.rs`                                                  | class / sync / promises       |\n| Clipboard         | `copyToClipboard`, `readImageFromClipboard`                                                                | `clipboard.rs`                                              | sync / promise                |\n| Tokens            | `countTokens(input, encoding?)`                                                                            | `tokens.rs`                                                 | sync                          |\n| System            | `detectMacOSAppearance`, `MacAppearanceObserver`, `MacOSPowerAssertion`, `getWorkProfile`, ProjFS helpers  | `appearance.rs`, `power.rs`, `prof.rs`, `projfs_overlay.rs` | mixed                         |\n\n## Sync vs async contract differences\n\nThe contract preserves Rust/N-API call style:\n\n- **Promise-returning exports** for worker-thread or async runtime work (`grep`, `glob`, `fuzzyFind`, `astGrep`, `astEdit`, `htmlToMarkdown`, shell/PTY runs, image parse/resize/encode, clipboard image read).\n- **Synchronous exports** for deterministic in-memory transforms/parsers or direct system calls (`search`, `hasMatch`, highlighting, text utilities, token counting, process queries, `copyToClipboard`, `encodeSixel`).\n- **Constructor exports** for stateful runtime objects (`Shell`, `PtySession`, `PhotonImage`, macOS observer/power handles).\n\nChanging sync ↔ async for an existing export is a breaking public API change because consumers call these exports directly.\n\n## Object and enum typing patterns\n\n### Object patterns\n\n`#[napi(object)]` Rust structs become TS interfaces, for example:\n\n- `GrepResult`, `SearchResult`, `GlobResult`, `FuzzyFindResult`\n- `ShellRunResult`, `ShellExecuteResult`, `PtyRunResult`, `MinimizerResult`\n- `AstFindResult`, `AstReplaceResult`\n- `System`/media payloads such as `ClipboardImage`, `WorkProfile`, `ParsedKittyResult`\n\nRuntime shape correctness is owned by napi-rs and the Rust implementation.\n\n### Enum patterns\n\nNative enums are represented in generated declarations and also appended to `module.exports` by `scripts/gen-enums.ts`, because the loader is hand-maintained CommonJS around the generated addon. Current enum objects include:\n\n- `AstMatchStrictness`\n- `Ellipsis`\n- `Encoding`\n- `FileType`\n- `GrepOutputMode`\n- `ImageFormat`\n- `KeyEventType`\n- `MacOSAppearance`\n- `SamplingFilter`\n\n## Error behavior and caveats\n\n- Addon load failure or unsupported platform throws during package import from `native/index.js`.\n- The loader does not verify the full export set after `require(...)`; stale or mismatched binaries surface as native load errors or missing members at use sites.\n- N-API conversion validates basic argument conversion, but TS optional fields do not guarantee semantic validity for untyped callers.\n- Numeric enum declarations do not prevent out-of-range numeric values from untyped callers unless the Rust function rejects them during conversion.\n- Callback exports use napi-rs `ThreadsafeFunction` shape: `(error: Error | null, value) => void`. Native code generally emits successful values; hard failures reject/throw through the owning call.\n\n## Maintainer checklist for binding changes\n\nWhen adding/changing an export, update all of:\n\n1. Rust `#[napi]` implementation in the owning `crates/pi-natives/src/<module>.rs`.\n2. `crates/pi-natives/src/lib.rs` if a new module is added.\n3. Any consumer imports/callsites in `packages/coding-agent` or `packages/tui`.\n4. Build output by running the natives build so `native/index.d.ts` and `native/index.js` stay in sync.\n5. `scripts/gen-enums.ts` if enum runtime export patching needs to change.\n\nDo not add a parallel TS wrapper convention unless the package design intentionally moves back to wrappers; current consumers depend on the direct generated API.\n",
@@ -28,8 +28,10 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"natives-rust-task-cancellation.md": "# Native Rust task execution and cancellation (`pi-natives`)\n\nThis document describes how `crates/pi-natives` schedules native work and how cancellation flows from JS options (`timeoutMs`, `AbortSignal`) into Rust execution.\n\n## Implementation files\n\n- `crates/pi-natives/src/task.rs`\n- `crates/pi-natives/src/grep.rs`\n- `crates/pi-natives/src/glob.rs`\n- `crates/pi-natives/src/fd.rs`\n- `crates/pi-natives/src/ast.rs`\n- `crates/pi-natives/src/shell.rs`\n- `crates/pi-natives/src/pty.rs`\n- `crates/pi-natives/src/html.rs`\n- `crates/pi-natives/src/image.rs`\n- `crates/pi-natives/src/clipboard.rs`\n- `crates/pi-natives/src/text.rs`\n- `crates/pi-natives/src/ps.rs`\n\n## Core primitives (`task.rs`)\n\n`task.rs` defines:\n\n1. `task::blocking(tag, cancel_token, work)`\n   - Wraps `napi::AsyncTask` / `Task`.\n   - `compute()` runs on libuv worker threads.\n   - Returns a JS `Promise<T>` for exported functions.\n   - Records a profiling sample through `profile_region(tag)`.\n\n2. `task::future(env, tag, work)`\n   - Wraps `env.spawn_future(...)`.\n   - Runs async work on Tokio's runtime.\n   - Returns `PromiseRaw<'env, T>`.\n   - Records a profiling sample through `profile_region(tag)`.\n\n3. `CancelToken` / `AbortToken` / `AbortReason`\n   - `CancelToken::new(timeout_ms, signal)` combines an optional deadline and optional JS `AbortSignal` converted from `Unknown`.\n   - `CancelToken::heartbeat()` is cooperative cancellation for blocking loops.\n   - `CancelToken::wait()` asynchronously waits for signal, timeout, or Ctrl-C.\n   - `CancelToken::emplace_abort_token()` creates an abortable flag when a later `Shell.abort()`/internal bridge needs one.\n   - `AbortToken::abort(reason)` lets external code request abort.\n\n## `blocking` vs `future`: execution model and selection\n\n### Use `task::blocking`\n\nUse when work is CPU-heavy or fundamentally synchronous/blocking:\n\n- regex/file scanning (`grep`, `glob`, `fuzzyFind`)\n- ast-grep search/edit worker work\n- PTY loop internals through `tokio::task::spawn_blocking`\n- image decode/resize/encode\n- HTML conversion\n- clipboard image read\n\nBehavior:\n\n- Work closure receives a cloned `CancelToken`.\n- Cancellation is only observed where code checks `ct.heartbeat()?`.\n- Closure `Err(...)` rejects the JS promise.\n\n### Use `task::future`\n\nUse when work must `await` async operations:\n\n- shell session orchestration (`Shell.run`, `executeShell`)\n- PTY outer promise (`PtySession.start`) before it enters `spawn_blocking`\n- task racing (`tokio::select!`) between completion and cancellation\n\nBehavior:\n\n- Future code can race normal completion against `ct.wait()`.\n- On cancel path, async implementations typically cancel subordinate machinery and may force-abort after a grace timeout.\n\n## JS API ↔ Rust export mapping (task/cancel relevant)\n\n| JS-facing API                           | Rust export                          | Scheduler                                                      | Cancellation hookup                                                                      |\n| --------------------------------------- | ------------------------------------ | -------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |\n| `grep(options, onMatch?)`               | `grep`                               | `task::blocking(\"grep\", ct, ...)`                              | `CancelToken::new(options.timeoutMs, options.signal)` + heartbeat checks                 |\n| `glob(options, onMatch?)`               | `glob`                               | `task::blocking(\"glob\", ct, ...)`                              | `CancelToken::new(...)` + heartbeat checks                                               |\n| `fuzzyFind(options)`                    | `fuzzy_find`                         | `task::blocking(\"fuzzy_find\", ct, ...)`                        | `CancelToken::new(...)` + heartbeat checks                                               |\n| `astGrep(options)` / `astEdit(options)` | ast exports                          | blocking worker path                                           | timeout/signal fields are accepted by options and checked cooperatively in worker loops  |\n| `Shell#run(options, onChunk?)`          | `Shell::run`                         | `task::future(env, \"shell.run\", ...)`                          | `ct.wait()` raced against run task; bridges to Tokio cancellation token and `AbortToken` |\n| `executeShell(options, onChunk?)`       | `execute_shell`                      | `task::future(env, \"shell.execute\", ...)`                      | same cancel race and 2s graceful window                                                  |\n| `PtySession#start(options, onChunk?)`   | `PtySession::start`                  | `task::future(env, \"pty.start\", ...)` + inner `spawn_blocking` | `CancelToken` checked in sync PTY loop via `heartbeat()`                                 |\n| `htmlToMarkdown(html, options?)`        | `html_to_markdown`                   | `task::blocking(\"html_to_markdown\", (), ...)`                  | none (`()` token)                                                                        |\n| `PhotonImage.parse/encode/resize`       | `PhotonImage::{parse,encode,resize}` | `task::blocking(...)`                                          | none (`()` token)                                                                        |\n| `readImageFromClipboard()`              | `read_image_from_clipboard`          | `task::blocking(\"clipboard.read_image\", (), ...)`              | none (`()` token)                                                                        |\n\n`text.rs`, `tokens.rs`, `keys.rs`, most `ps.rs` functions, and synchronous utility exports do not use `task::blocking`/`task::future` and therefore do not participate in this cancellation path.\n\n## Cancellation lifecycle and state transitions\n\n### `CancelToken` lifecycle\n\n```text\nCreated\n  ├─ no signal + no timeout  -> passive token\n  ├─ signal registered        -> AbortSignal callback can set AbortReason::Signal\n  └─ deadline set             -> timeout check becomes active\n\nRunning\n  ├─ heartbeat()/wait() sees signal   -> AbortReason::Signal\n  ├─ heartbeat()/wait() sees deadline -> AbortReason::Timeout\n  ├─ wait() sees Ctrl-C               -> AbortReason::User\n  └─ no abort                         -> continue\n\nAborted\n  └─ flag stores first observed cause for waiters; heartbeat formats it as \"Aborted: <reason>\"\n```\n\n### Before-start vs mid-execution cancellation\n\n- **Before start / before first cancellation check**:\n  - `task::future` users that race on `ct.wait()` can resolve cancellation once they enter `select!`.\n  - `task::blocking` users only observe cancellation when closure code reaches `heartbeat()`.\n\n- **Mid-execution**:\n  - `blocking`: next `heartbeat()` returns `Err(\"Aborted: ...\")`.\n  - `future`: `ct.wait()` branch wins `select!`, then code cancels subordinate async machinery.\n  - shell: cancellation triggers a Tokio cancellation token, waits up to 2 seconds, then aborts the task if needed.\n  - PTY: heartbeat failure or `kill()` terminates PTY child/process tree and drains output briefly.\n\n## Heartbeat expectations for long-running loops\n\n`heartbeat()` must run at predictable cadence in loops with unbounded or large work sets.\n\nObserved patterns:\n\n- `glob` filtering checks entries during scan/filter work.\n- `fd` scoring checks scanned candidates.\n- `grep` checks before/during expensive search and passes tokens into shared scan/cache helpers.\n- `run_pty_sync` checks every loop tick with a maximum 16ms wait cadence.\n\nPractical rule: no loop over external-size input should exceed a short bounded interval without a heartbeat.\n\n## Failure behavior and error propagation to JS\n\n### Blocking tasks\n\nError path:\n\n1. Closure returns `Err(napi::Error)` (including `heartbeat()` abort).\n2. `Task::compute()` returns `Err`.\n3. `AsyncTask` rejects JS promise.\n\nTypical error strings:\n\n- `Aborted: Timeout`\n- `Aborted: Signal`\n- domain errors (`Failed to decode image: ...`, `Conversion error: ...`, etc.)\n\n### Future tasks\n\nError path:\n\n1. Async body returns `Err(napi::Error)` or join failure is mapped (`... task failed: {err}`).\n2. `task::future`-spawned promise rejects.\n3. Shell and PTY command APIs model cancellation as structured results instead of rejection when the cancellation path wins: `exitCode` omitted, `cancelled` or `timedOut` set.\n\n### Cancellation reporting split\n\n- **Abort as error**: blocking exports using `heartbeat()?`.\n- **Abort as typed result**: shell/PTY command APIs that model cancellation in result structs.\n\nChoose one model per API and document it explicitly.\n\n## Common pitfalls\n\n1. **Missing heartbeat in blocking loops**\n   - Symptom: timeout/signal appears ignored until loop ends.\n   - Fix: add `ct.heartbeat()?` at loop top and before expensive per-item steps.\n\n2. **Long uncancelable sections**\n   - Symptom: cancellation latency spikes during single large call (decode, sort, compression, parser invocation, etc.).\n   - Fix: split work into chunks with heartbeat boundaries; if impossible, document latency.\n\n3. **Blocking async executor**\n   - Symptom: async API stalls when sync-heavy code runs directly in future.\n   - Fix: move CPU/sync blocks to `task::blocking` or `tokio::task::spawn_blocking`.\n\n4. **Inconsistent cancel semantics**\n   - Symptom: one API rejects on cancel, another resolves with flags, confusing callers.\n   - Fix: standardize per domain and keep docs aligned.\n\n5. **Forgetting cancellation bridge in nested async tasks**\n   - Symptom: outer token is cancelled but inner readers/subprocess tasks keep running.\n   - Fix: bridge cancellation to inner token/signal and enforce grace timeout + forced abort fallback.\n\n## Checklist for new cancellable exports\n\n1. Classify work correctly:\n   - CPU-bound or sync blocking -> `task::blocking`.\n   - async I/O / `await` orchestration -> `task::future`.\n\n2. Expose cancel inputs when needed:\n   - include `timeoutMs` and `signal` in `#[napi(object)]` options,\n   - create `let ct = task::CancelToken::new(timeout_ms, signal);`.\n\n3. Wire cancellation through all layers:\n   - blocking loops: `ct.heartbeat()?` at stable intervals,\n   - async orchestration: race with `ct.wait()` and cancel sub-tasks/tokens.\n\n4. Decide cancellation contract:\n   - reject promise with abort error, or\n   - resolve typed `{ cancelled, timedOut, ... }`,\n   - keep this contract consistent for the API family.\n\n5. Propagate failures with context:\n   - map errors via `Error::from_reason(format!(\"...: {err}\"))`,\n   - include stage-specific prefixes (`spawn`, `decode`, `wait`, etc.).\n\n6. Handle before-start and mid-flight cancellation:\n   - cancellation check/await must happen before expensive body and during long execution.\n\n7. Validate no executor misuse:\n   - no long sync work directly inside async futures without `spawn_blocking`/blocking task wrapper.\n",
 	"natives-shell-pty-process.md": "# Natives Shell, PTY, Process, and Key Internals\n\nThis document covers the execution/process/terminal primitives in `@gajae-code/natives`: `shell`, `pty`, `ps`, and `keys`, using the architecture terms from `docs/natives-architecture.md`.\n\n## Implementation files\n\n- `crates/pi-natives/src/shell.rs`\n- `crates/pi-natives/src/shell/windows.rs` (Windows-only PATH enrichment)\n- `crates/pi-natives/src/pty.rs`\n- `crates/pi-natives/src/ps.rs`\n- `crates/pi-natives/src/keys.rs`\n- `crates/pi-natives/src/task.rs`\n- `packages/natives/native/index.d.ts`\n\n## Layer ownership\n\n- **Package entrypoint** (`packages/natives/native/index.js`): loads the `.node` addon and exports generated N-API bindings.\n- **Rust N-API module layer** (`crates/pi-natives/src/*`): shell/PTY process execution, process-tree traversal/termination, and key-sequence parsing.\n- **Consumers** (`packages/coding-agent`, `packages/tui`): higher-level session policy, output artifact/minimizer handling, render policy, and UI key handling.\n\n## Shell subsystem (`shell`)\n\n### API model\n\nTwo execution modes are exposed:\n\n1. **One-shot** via `executeShell(options, onChunk?)`.\n2. **Persistent session** via `new Shell(options?)` then `shell.run(...)` repeatedly.\n\nBoth stream output through a threadsafe callback and return `{ exitCode?, cancelled, timedOut, minimized? }`.\n\n`ShellOptions` supports `sessionEnv`, `snapshotPath`, and optional output `minimizer`. `ShellExecuteOptions` supports command-scoped `env`, session-level `sessionEnv`, `snapshotPath`, timeout/signal, and optional minimizer. `ShellRunOptions` supports command, cwd, command-scoped env, timeout, and signal.\n\n### Session creation and environment model\n\nRust creates `brush_core::Shell` with:\n\n- non-interactive, non-login mode,\n- `no_profile` and `no_rc`,\n- `do_not_inherit_env: true`,\n- bash-mode builtins, with `exec` and `suspend` disabled,\n- explicit environment reconstruction from host env,\n- skip-list for shell-sensitive vars (`PS1`, `PWD`, `SHLVL`, bash function exports, etc.).\n\nSession env behavior:\n\n- `ShellOptions.sessionEnv` / one-shot `sessionEnv` is applied at session creation.\n- `ShellRunOptions.env` / one-shot `env` is command-scoped (`EnvironmentScope::Command`) and popped after the command.\n- `PATH` is merged specially on Windows with case-insensitive dedupe.\n- Windows-only path enrichment (`shell/windows.rs`) appends discovered Git-for-Windows paths when present and not already included.\n- `snapshotPath`, when present, is sourced during session creation with stdout/stderr/stdin wired to null files.\n\n### Runtime lifecycle and state transitions\n\nPersistent shell (`Shell.run`) uses this state machine:\n\n- **Idle/Uninitialized**: `session: None`.\n- **Running**: first `run()` lazily creates a session, stores an abort token, executes command.\n- **Completed + keepalive**: if execution control flow is normal, abort state is cleared and session is reused.\n- **Completed + teardown**: if control flow is loop/script/shell-exit related, session is dropped.\n- **Cancelled/Timed out**: run task is cancelled, grace wait is 2 seconds, task may be force-aborted, session is dropped if lock can be acquired.\n- **Error**: session is dropped.\n\nOne-shot shell (`executeShell`) always creates and drops a fresh session per call.\n\n### Streaming/output and minimizer behavior\n\n- Stdout/stderr are routed into a shared pipe and read concurrently.\n- Reader decodes UTF-8 incrementally; invalid byte sequences emit `U+FFFD` replacement chunks.\n- The command runs in a new process group policy.\n- Optional minimizer configuration can capture and rewrite output. When minimization occurs, the result includes `minimized` with filter name, replacement text, original text, and byte counts.\n- Consumers are responsible for persisting or displaying minimizer artifacts; the native result only carries the data.\n\n### Cancellation, timeout, and abort\n\n- `CancelToken` is constructed from `timeoutMs` and optional `AbortSignal`.\n- On cancellation/timeout, shell cancellation token is triggered, then task gets a 2-second graceful window before forced abort.\n- Structured result flags are used:\n  - timeout -> `exitCode` omitted, `timedOut: true`.\n  - abort signal / `Shell.abort()` -> `exitCode` omitted, `cancelled: true`.\n\n`Shell.abort()` behavior:\n\n- aborts the current running command for that `Shell` instance through the stored `AbortToken`,\n- resolves successfully even when nothing is running.\n\n### Failure behavior\n\nCommon surfaced errors include:\n\n- session init failures (`Failed to initialize shell`),\n- cwd errors (`Failed to set cwd`),\n- env set/pop failures,\n- snapshot source failures (`Failed to source snapshot`),\n- pipe creation/clone failures,\n- execution failure (`Shell execution failed: ...`),\n- task wrapper failures (`Shell execution task failed: ...`).\n\n## PTY subsystem (`pty`)\n\n### API model\n\n`new PtySession()` exposes:\n\n- `start(options, onChunk?) -> Promise<{ exitCode?, cancelled, timedOut }>`\n- `write(data)`\n- `resize(cols, rows)`\n- `kill()`\n\n`PtyStartOptions` supports `command`, optional `cwd`, optional `env`, `timeoutMs`, `signal`, `cols`, and `rows`.\n\n### Runtime lifecycle and state transitions\n\n`PtySession` state machine:\n\n- **Idle**: `core: None`.\n- **Reserved**: `start()` installs control channel synchronously (`core: Some`) before async work begins, so `write/resize/kill` become immediately valid.\n- **Running**: blocking PTY loop handles child state, reader events, cancellation heartbeat, and control messages.\n- **Terminal closed / drain**: child exit or cancellation starts a short reader drain window.\n- **Finalized**: `core` is always reset to `None` after start task completion (success or error).\n\nConcurrency guard:\n\n- starting while already running returns `PTY session already running`.\n\n### Spawn/attach/write/read/terminate patterns\n\n- PTY opened via `portable_pty::native_pty_system().openpty(...)`.\n- Command currently runs as `sh -lc <command>` with optional `cwd` and env overrides.\n- Default size is `120x40`; dimensions are clamped (`cols 20..400`, `rows 5..200`).\n- `write()` sends raw bytes to PTY stdin.\n- `resize()` sends a control message and clamps dimensions again.\n- `kill()` sends a control message that marks the run cancelled and terminates the child/process tree.\n\nOutput path:\n\n- dedicated reader thread reads master stream,\n- incremental UTF-8 decode emits `U+FFFD` for invalid bytes,\n- chunks forwarded through N-API threadsafe callback.\n\nTermination path:\n\n- Unix: terminate process group when known, terminate child tree, call child kill, then repeat with SIGKILL.\n- Non-Unix: terminate child tree, call child kill, then repeat with SIGKILL-equivalent process-tree helper.\n\n### Cancellation and timeout semantics\n\n- `timeoutMs` and `AbortSignal` feed a `CancelToken`.\n- Loop calls `ct.heartbeat()` periodically with a 16ms maximum wait cadence.\n- Timeout classification is based on the heartbeat error string containing `Timeout`.\n- Cancellation/kill starts a 300ms post-cancel drain window; normal child exit starts a 300ms post-exit drain window.\n\n### Failure behavior\n\nError surfaces include:\n\n- PTY allocation/open failure,\n- PTY spawn failure,\n- writer/reader acquisition failure,\n- child status/wait failures,\n- lock poisoning,\n- control-channel disconnection (`PTY session is no longer available`).\n\nControl call failures when not running:\n\n- `write/resize/kill` return `PTY session is not running`.\n\n## Process-tree subsystem (`ps`)\n\n### API model\n\n- `killTree(pid, signal) -> number`\n- `listDescendants(pid) -> number[]`\n\n### Platform-specific implementation\n\n- **Linux**: recursively reads `/proc/<pid>/task/<pid>/children`.\n- **macOS**: uses `libproc` `proc_listchildpids`.\n- **Windows**: snapshots process table with `CreateToolhelp32Snapshot`, builds parent->children map, terminates with `OpenProcess(PROCESS_TERMINATE)` + `TerminateProcess`.\n\n### Kill-tree behavior\n\n- Descendants are collected recursively.\n- Kill order is bottom-up (deepest descendants first).\n- Root pid is killed last.\n- Return value is count of successful terminations.\n\nSignal behavior:\n\n- POSIX: provided `signal` is passed to `kill`.\n- Windows: `signal` is ignored; termination is unconditional process terminate.\n\n### Failure behavior\n\nThis module is intentionally non-throwing at API surface for ordinary process misses:\n\n- missing/inaccessible process tree branches are skipped,\n- per-pid kill failures are counted as unsuccessful,\n- lookup miss typically yields `[]` from `listDescendants` and `0` from `killTree`.\n\n## Key parsing subsystem (`keys`)\n\n### API model\n\nExposed helpers:\n\n- `parseKey(data, kittyProtocolActive)`\n- `matchesKey(data, keyId, kittyProtocolActive)`\n- `parseKittySequence(data)`\n- `matchesKittySequence(data, expectedCodepoint, expectedModifier)`\n- `matchesLegacySequence(data, keyName)`\n\n### Parsing model\n\nThe parser combines:\n\n- direct single-byte mappings (`enter`, `tab`, `ctrl+<letter>`, printable ASCII),\n- O(1) legacy escape-sequence lookup (PHF map),\n- xterm `modifyOtherKeys` parsing,\n- Kitty protocol parsing (`CSI u`, `CSI ~`, `CSI 1;...<letter>`),\n- normalization to key IDs (`ctrl+c`, `shift+tab`, `pageUp`, `f5`, etc.).\n\nModifier handling:\n\n- only shift/alt/ctrl bits are compared for key matching,\n- lock bits are masked out before comparisons.\n\nLayout behavior:\n\n- base-layout fallback is intentionally constrained so remapped layouts do not create false matches for ASCII letters/symbols.\n\n### Failure behavior\n\n- Unrecognized or invalid sequences produce `null` from parse functions.\n- Match functions return `false` on parse failure or mismatch.\n- No thrown error surface for malformed key input.\n\n## JS API ↔ Rust export mapping\n\n### Shell + PTY + Process\n\n| JS API                            | Rust N-API export                      | Notes                                     |\n| --------------------------------- | -------------------------------------- | ----------------------------------------- |\n| `executeShell(options, onChunk?)` | `executeShell` (`execute_shell`)       | One-shot shell execution                  |\n| `new Shell(options?)`             | `Shell` class                          | Persistent shell session                  |\n| `shell.run(options, onChunk?)`    | `Shell::run`                           | Reuses session on keepalive control flow  |\n| `shell.abort()`                   | `Shell::abort`                         | Aborts active run for that shell instance |\n| `new PtySession()`                | `PtySession` class                     | Stateful PTY session                      |\n| `pty.start(options, onChunk?)`    | `PtySession::start`                    | Interactive PTY run                       |\n| `pty.write(data)`                 | `PtySession::write`                    | Raw stdin passthrough                     |\n| `pty.resize(cols, rows)`          | `PtySession::resize`                   | Clamped terminal dimensions               |\n| `pty.kill()`                      | `PtySession::kill`                     | Force-kills active PTY child              |\n| `killTree(pid, signal)`           | `killTree` (`kill_tree`)               | Children-first process tree termination   |\n| `listDescendants(pid)`            | `listDescendants` (`list_descendants`) | Recursive descendants listing             |\n\n### Keys\n\n| JS API                                         | Rust N-API export                                   | Notes                           |\n| ---------------------------------------------- | --------------------------------------------------- | ------------------------------- |\n| `matchesKittySequence(data, cp, mod)`          | `matchesKittySequence` (`matches_kitty_sequence`)   | Kitty codepoint+modifier match  |\n| `parseKey(data, kittyProtocolActive)`          | `parseKey` (`parse_key`)                            | Normalized key-id parser        |\n| `matchesLegacySequence(data, keyName)`         | `matchesLegacySequence` (`matches_legacy_sequence`) | Exact legacy sequence map check |\n| `parseKittySequence(data)`                     | `parseKittySequence` (`parse_kitty_sequence`)       | Structured Kitty parse result   |\n| `matchesKey(data, keyId, kittyProtocolActive)` | `matchesKey` (`matches_key`)                        | High-level key matcher          |\n\n## Abandoned session cleanup and finalization notes\n\n- **Shell persistent session**: if a run is cancelled/timed out/errors/non-keepalive control flow, Rust drops the internal session state. Successful normal runs keep the session for reuse.\n- **PTY session**: `core` is always cleared after `start()` finishes, including failure paths.\n- **No explicit JS finalizer-driven kill contract** is exposed by wrappers; cleanup is primarily tied to run completion/cancellation paths. Callers should use `timeoutMs`, `AbortSignal`, `shell.abort()`, or `pty.kill()` for deterministic teardown.\n",
 	"natives-text-search-pipeline.md": "# Natives Text/Search Pipeline\n\nThis document maps the `@gajae-code/natives` text/search/code surface from generated JS/TS exports to Rust N-API modules and back to JS result objects.\n\nTerminology follows `docs/natives-architecture.md`:\n\n- **Generated binding**: public API in `packages/natives/native/index.d.ts`.\n- **Rust module layer**: N-API exports in `crates/pi-natives/src/*`.\n- **Shared scan cache**: `fs_cache`-backed directory-entry cache used by discovery/search flows.\n\n## Implementation files\n\n- `packages/natives/native/index.d.ts`\n- `crates/pi-natives/src/grep.rs`\n- `crates/pi-natives/src/glob.rs`\n- `crates/pi-natives/src/glob_util.rs`\n- `crates/pi-natives/src/fs_cache.rs`\n- `crates/pi-natives/src/fd.rs`\n- `crates/pi-natives/src/ast.rs`\n- `crates/pi-natives/src/text.rs`\n- `crates/pi-natives/src/highlight.rs`\n- `crates/pi-natives/src/tokens.rs`\n\n## JS API ↔ Rust export mapping\n\n| JS API                                                                          | Rust export (`#[napi]`, snake_case -> camelCase) | Rust module    |\n| ------------------------------------------------------------------------------- | ------------------------------------------------ | -------------- |\n| `grep(options, onMatch?)`                                                       | `grep`                                           | `grep.rs`      |\n| `search(content, options)`                                                      | `search`                                         | `grep.rs`      |\n| `hasMatch(content, pattern, ignoreCase?, multiline?)`                           | `hasMatch`                                       | `grep.rs`      |\n| `fuzzyFind(options)`                                                            | `fuzzyFind`                                      | `fd.rs`        |\n| `glob(options, onMatch?)`                                                       | `glob`                                           | `glob.rs`      |\n| `invalidateFsScanCache(path?)`                                                  | `invalidateFsScanCache`                          | `fs_cache.rs`  |\n| `astGrep(options)`                                                              | `astGrep`                                        | `ast.rs`       |\n| `astEdit(options)`                                                              | `astEdit`                                        | `ast.rs`       |\n| `wrapTextWithAnsi(text, width, tabWidth)`                                       | `wrapTextWithAnsi`                               | `text.rs`      |\n| `truncateToWidth(text, maxWidth, ellipsis, pad, tabWidth)`                      | `truncateToWidth`                                | `text.rs`      |\n| `sliceWithWidth(line, startCol, length, strict, tabWidth)`                      | `sliceWithWidth`                                 | `text.rs`      |\n| `extractSegments(line, beforeEnd, afterStart, afterLen, strictAfter, tabWidth)` | `extractSegments`                                | `text.rs`      |\n| `visibleWidth(text, tabWidth)`                                                  | `visibleWidth`                                   | `text.rs`      |\n| `highlightCode(code, lang, colors)`                                             | `highlightCode`                                  | `highlight.rs` |\n| `supportsLanguage(lang)`                                                        | `supportsLanguage`                               | `highlight.rs` |\n| `getSupportedLanguages()`                                                       | `getSupportedLanguages`                          | `highlight.rs` |\n| `countTokens(input, encoding?)`                                                 | `countTokens`                                    | `tokens.rs`    |\n\n## Pipeline overview by subsystem\n\n## 1) Regex search (`grep`, `search`, `hasMatch`)\n\n### Input/options flow\n\n1. Callers invoke generated native exports directly; there is no package-local TS wrapper that renames `search` to `searchContent`.\n2. Rust option structs in `grep.rs` deserialize camelCase fields (`ignoreCase`, `maxCount`, `contextBefore`, `contextAfter`, `maxColumns`, `timeoutMs`).\n3. `grep` creates `CancelToken` from `timeoutMs` + `AbortSignal` and runs inside `task::blocking(\"grep\", ...)`.\n4. `search` and `hasMatch` operate on provided string/`Uint8Array` content and do not scan the filesystem.\n\n### Execution branches\n\n- **In-memory branch**\n  - `search` -> `search_sync` / search helpers over provided content bytes.\n  - `hasMatch` compiles/checks pattern against provided content and returns a boolean.\n  - No filesystem scan, no `fs_cache`.\n- **Single-file branch**\n  - `grep` resolves path, checks metadata is file, and searches that file.\n- **Directory branch**\n  - Optional cache lookup via `fs_cache::get_or_scan` when `cache: true`.\n  - Fresh scan via `fs_cache::force_rescan` when `cache: false`.\n  - Optional empty-result recheck when cached results are older than the empty-result recheck threshold.\n  - Entry filtering: file-only + optional glob filter (`glob_util`) + optional type filter mapping (`js`, `ts`, `rust`, etc.).\n\n### Search/collection semantics\n\n- Regex engine: `grep_regex::RegexMatcherBuilder` with `ignoreCase` and `multiline`.\n- Context resolution:\n  - `contextBefore/contextAfter` override legacy `context`.\n  - Non-content modes do not collect context.\n- Output modes:\n  - `content` -> one `GrepMatch` per hit.\n  - `count` and `filesWithMatches` map to count-style entries (`lineNumber=0`, `line=\"\"`, `matchCount` set).\n- Limits:\n  - Global `offset` and `maxCount` apply across files.\n  - Parallel path is used only when `maxCount` is unset and `offset == 0`; otherwise sequential path preserves deterministic global offset/limit semantics.\n\n### Result shaping back to JS\n\n- Rust `SearchResult`/`GrepResult` fields map to TS interfaces via N-API object conversion.\n- Counters are clamped before crossing N-API where needed.\n- `GrepResult.limitReached` is optional and emitted when true.\n- Streaming callback receives each shaped `GrepMatch` for content or count-style entries.\n\n### Failure behavior\n\n- `search` returns `SearchResult.error` for regex/search failures instead of throwing.\n- `grep` rejects on hard errors such as invalid path, invalid glob/regex, or cancellation timeout/abort.\n- `hasMatch` returns a boolean on success and throws on invalid pattern/UTF-8 conversion errors.\n- File open/search errors in multi-file scans are skipped per-file; scan continues.\n\n### Malformed regex handling\n\n`grep.rs` sanitizes braces before regex compile:\n\n- Invalid repetition-like braces are escaped (`{`/`}` -> `\\{`/`\\}`) when they cannot form `{N}`, `{N,}`, `{N,M}`.\n- This prevents common literal-template fragments (for example `${platform}`) from failing as malformed repetition.\n- Remaining invalid regex syntax still returns a regex error.\n\n## 2) File discovery (`glob`) and fuzzy path search (`fuzzyFind`)\n\n`glob` and `fuzzyFind` share `fs_cache` scans; matching logic differs.\n\n### `glob` flow\n\n1. Caller passes `GlobOptions` directly. `pattern` and `path` are required in the generated type.\n2. Rust resolves the search path and compiles pattern via `glob_util::compile_glob`.\n3. Entry source:\n   - `cache=true` -> `get_or_scan` + optional stale-empty `force_rescan`.\n   - `cache=false` -> `force_rescan(..., store=false)` (fresh only).\n4. Filtering:\n   - skip `.git` always;\n   - skip `node_modules` unless requested (`includeNodeModules`) or pattern mentions `node_modules`;\n   - apply glob match;\n   - apply file-type filter; symlink `file`/`dir` filters resolve target metadata.\n5. Optional sort by mtime descending (`sortByMtime`) before truncating to `maxResults`.\n\n### `fuzzyFind` flow\n\n1. Rust implementation lives in `fd.rs`; generated export is `fuzzyFind`.\n2. Shared scan source from `fs_cache` with the same cache/no-cache split and stale-empty recheck policy.\n3. Scoring:\n   - exact / starts-with / contains / subsequence-based fuzzy score;\n   - separator/punctuation-normalized scoring path;\n   - directory bonus and deterministic tie-break (`score desc`, then `path asc`).\n4. Symlink entries are excluded from fuzzy results.\n\n### Failure behavior\n\n- Invalid glob pattern returns an error from `glob_util::compile_glob`.\n- Search root must resolve to an existing directory for directory discovery flows.\n- Cancellation/timeouts propagate as abort errors via `CancelToken::heartbeat()` checks in loops.\n\n### Malformed glob handling\n\n`glob_util::build_glob_pattern` is tolerant:\n\n- normalizes `\\` to `/`,\n- auto-prefixes simple recursive patterns with `**/` when `recursive=true`,\n- auto-closes unbalanced `{...` alternation groups before compile.\n\n## 3) AST search/edit (`astGrep`, `astEdit`)\n\n`ast.rs` exposes syntax-aware code search and rewrite operations.\n\n- `astGrep(options)` returns matches with byte/line/column coordinates and optional metavariable bindings.\n- `astEdit(options)` returns replacement changes, per-file counts, searched/touched file counts, parse errors, and whether edits were applied.\n- `dryRun` defaults to true for edit options in the generated documentation.\n- Options include language override, path/glob/selector, strictness, limits, parse-error policy, `signal`, and `timeoutMs`.\n\nThese exports are direct native APIs used by tooling; they are not mediated by a TS wrapper in `packages/natives`.\n\n## 4) Shared scan/cache lifecycle (`fs_cache`)\n\n`fs_cache` stores scan results as normalized relative entries (`path`, `fileType`, optional `mtime`) keyed by:\n\n- canonical search root,\n- `include_hidden`,\n- `use_gitignore`.\n\n### Cache state transitions\n\n1. **Miss / disabled**\n   - TTL is `0` or key absent/expired -> fresh collection.\n2. **Hit**\n   - Entry age is within TTL -> return cached entries + `cache_age_ms`.\n3. **Stale-empty recheck**\n   - If query yields zero matches and cache age exceeds the empty-result threshold, force one rescan.\n4. **Invalidation**\n   - `invalidateFsScanCache(path?)`:\n     - no arg: clear all keys;\n     - path arg: remove keys for roots affected by that path.\n\n### Stale-result tradeoff\n\n- Cache favors low-latency repeated scans over immediate consistency.\n- TTL window can return stale positives/negatives.\n- Empty-result recheck reduces stale negatives for older cached scans at the cost of one extra scan.\n- Explicit invalidation is the intended correctness hook after file mutations.\n\n## 5) ANSI text utilities (`text`)\n\nThese are pure, in-memory utilities.\n\n### Boundaries and responsibilities\n\n- `text.rs` owns terminal-cell semantics:\n  - ANSI sequence parsing,\n  - grapheme-aware width and slicing,\n  - wrap/truncate/sanitize behavior,\n  - explicit tab-width parameter on width-sensitive APIs.\n- `grep.rs` line truncation (`maxColumns`) is separate:\n  - simple character-boundary truncation of matched lines with `...`,\n  - not ANSI-state-preserving and not terminal-cell width aware.\n\n### Key behaviors\n\n- `wrapTextWithAnsi`: wraps by visible width, carries active SGR codes across wrapped lines.\n- `truncateToWidth`: visible-cell truncation with ellipsis policy (`Unicode`, `Ascii`, `Omit`), optional right padding.\n- `sliceWithWidth`: column slicing with optional strict width enforcement.\n- `extractSegments`: extracts before/after segments around an overlay while restoring ANSI state for the `after` segment.\n- `sanitizeText` (ANSI/control/surrogate stripping with line-ending normalization) no longer lives in `text.rs`; it moved to `@gajae-code/utils` as a pure-JS implementation in `packages/utils/src/sanitize-text.ts`. The native binding was removed in the same change because the JS version was competitive on the benchmarked workloads, and keeping a Rust copy forced every caller (including `pi-utils`) to pull in `@gajae-code/natives`.\n- `visibleWidth`: counts visible terminal cells using caller-supplied tab width.\n\n### Failure behavior\n\nText functions generally return deterministic transformed output; errors are limited to N-API argument/string conversion boundaries.\n\n## 6) Syntax highlighting (`highlight`)\n\n`highlight.rs` is pure transformation; it does not use the filesystem scan cache.\n\n### Flow\n\n1. Caller passes `code`, optional `lang`, and ANSI color palette.\n2. Rust resolves syntax by token/name lookup, extension lookup, alias table fallback, then plain-text fallback.\n3. Each line is parsed with syntect `ParseState` and scope stack.\n4. Scopes map to semantic color categories and ANSI color codes are injected/reset.\n\n### Failure behavior\n\n- Per-line parse failure does not fail the call: that line is appended unhighlighted and processing continues.\n- Unknown/unsupported language falls back to plain text syntax.\n\n## 7) Token counting (`tokens`)\n\n`countTokens(input, encoding?)` is an in-memory utility.\n\n- `input` may be a single string or an array of strings.\n- Arrays return one aggregate count and are encoded in parallel in Rust.\n- Default encoding is `O200kBase`; `Cl100kBase` is also available.\n- The implementation uses ordinary tokenization, not special-token handling.\n\n## Pure utility vs filesystem-dependent flows\n\n| Flow                         | Filesystem access | Shared cache         | Notes                                         |\n| ---------------------------- | ----------------- | -------------------- | --------------------------------------------- |\n| `search` / `hasMatch`        | No                | No                   | regex on provided bytes/string only           |\n| `text` module functions      | No                | No                   | ANSI/width/sanitization only                  |\n| `highlight` module functions | No                | No                   | syntax + ANSI coloring only                   |\n| `countTokens`                | No                | No                   | tokenization only                             |\n| `astGrep` / `astEdit`        | Yes               | No                   | syntax-aware file search/edit                 |\n| `glob`                       | Yes               | Optional             | directory scans + glob filtering              |\n| `fuzzyFind`                  | Yes               | Optional             | directory scans + fuzzy scoring               |\n| `grep` (file/dir path)       | Yes               | Optional in dir mode | ripgrep over files, optional filters/callback |\n\n## End-to-end lifecycle summary\n\n1. Caller invokes generated native export with typed options.\n2. Rust validates/normalizes options and builds matcher/search config.\n3. For filesystem flows, entries are scanned (cache hit/miss/rescan where applicable) then filtered/scored/searched.\n4. Worker loops periodically call cancel heartbeat; timeout/abort can terminate execution.\n5. Rust shapes outputs into N-API objects (`lineNumber`, `matchCount`, `limitReached`, etc.).\n6. Generated bindings return typed JS objects and optional per-match callbacks for `grep`/`glob`.\n",
-	"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\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",
+	"non-compaction-retry-policy.md": "# Non-compaction auto-retry policy\n\nThis document describes the standard API-error retry path in `AgentSession`.\n\nIt explicitly excludes context-overflow recovery via auto-compaction. Overflow is handled by compaction logic and is documented separately in [`compaction.md`](../docs/compaction.md).\n\n## Implementation files\n\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`../src/config/settings-schema.ts`](../packages/coding-agent/src/config/settings-schema.ts)\n- [`../src/modes/controllers/event-controller.ts`](../packages/coding-agent/src/modes/controllers/event-controller.ts)\n- [`../src/modes/rpc/rpc-mode.ts`](../packages/coding-agent/src/modes/rpc/rpc-mode.ts)\n- [`../src/modes/rpc/rpc-client.ts`](../packages/coding-agent/src/modes/rpc/rpc-client.ts)\n- [`../src/modes/rpc/rpc-types.ts`](../packages/coding-agent/src/modes/rpc/rpc-types.ts)\n\n## Scope boundary vs compaction\n\nRetry and compaction are checked from the same `agent_end` path, but they are intentionally separated:\n\n1. `agent_end` inspects the last assistant message.\n2. `#isRetryableError(...)` runs first.\n3. If retry is initiated, compaction checks are skipped for that turn.\n4. Context-overflow errors are hard-excluded from retry classification (`isContextOverflow(...)` short-circuits retry).\n5. Overflow therefore falls through to `#checkCompaction(...)` instead of standard retry.\n\nSo: overload/rate/server/network-style failures use this retry policy; context-window overflow uses compaction recovery.\n\n## Retry classification\n\n`#isRetryableError(...)` requires all of the following:\n\n- assistant `stopReason === \"error\"`\n- `errorMessage` exists\n- message is **not** context overflow\n- `errorMessage` matches transient transport/envelope patterns or `isUsageLimitError(...)`\n\nCurrent retryable inputs are regex/string-classified:\n\n- transient transport/envelope failures, including Anthropic stream-envelope failures before `message_start`\n- overloaded/provider-returned-error wording\n- rate limit / usage limit / too many requests\n- HTTP-like server classes: 429, 500, 502, 503, 504\n- service unavailable / server/internal error\n- provider-suggested retry wording, including OpenAI `retry your request` failures\n- network/connection/socket failures, refused/closed connections, upstream connect/reset-before-headers, socket hang up, timeout/timed out, fetch failed, terminated, retry delay wording, and unexpected socket close messages\n\nThis is string-pattern classification, not typed provider error codes.\n\n## Retry lifecycle and state transitions\n\nSession state used by retry:\n\n- `#retryAttempt: number` (`0` means idle)\n- `#retryPromise: Promise<void> | undefined` (tracks in-progress retry lifecycle)\n- `#retryResolve: (() => void) | undefined` (resolves `#retryPromise`)\n- `#retryAbortController: AbortController | undefined` (cancels backoff sleep)\n\nFlow (`#handleRetryableError`):\n\n1. Read `retry` settings group.\n2. If `retry.enabled === false`, stop immediately (`false`, no retry started).\n3. Increment `#retryAttempt`.\n4. Create `#retryPromise` once (first attempt in a chain).\n5. If attempt exceeded `retry.maxRetries`, emit final failure event and stop.\n6. Compute base delay: `retry.baseDelayMs * 2^(attempt-1)`.\n7. For usage-limit errors, parse retry hints and call auth storage (`markUsageLimitReached(...)`); if credential switching succeeds, force delay to `0`, otherwise use a larger retry-after/backoff hint when present.\n8. If no credential switch occurred, suppress the current model selector for cooldown, try configured retry model fallback chains, and force delay to `0` on model switch.\n9. Emit `auto_retry_start`.\n10. Remove the trailing assistant error message from agent runtime state (kept in persisted session history).\n11. Sleep with abort support.\n12. Schedule `agent.continue()` through the post-prompt task scheduler (`delayMs: 1`) for the same prompt generation.\n\n### What resets retry counters\n\n`#retryAttempt` resets to `0` in these cases:\n\n- first successful non-error, non-aborted assistant message after retries started (emits `auto_retry_end { success: true }`)\n- retry cancellation during backoff sleep\n- max retries exceeded path\n\n`#retryPromise` resolves/clears when retry chain ends (success, cancellation, or max-exceeded), via `#resolveRetry()`.\n\n## Backoff and max-attempt semantics\n\nSettings:\n\n- `retry.enabled` (default `true`)\n- `retry.maxRetries` (default `3`)\n- `retry.baseDelayMs` (default `2000`)\n- `retry.maxDelayMs` (default `300000`)\n- `retry.requestMaxRetries` (default `5`) — provider request retries before a stream is established; counts retries, not the initial request\n- `retry.streamMaxRetries` (default `5`) — provider stream replay retries for replay-safe transient stream failures; counts retries, not the initial stream attempt\n\nAttempt numbering:\n\n- attempt counter is incremented before max-check\n- start events use current attempt (1-based)\n- max-exceeded end event reports `attempt: this.#retryAttempt - 1` (last attempted retry count)\n\nBackoff sequence with default settings:\n\n- attempt 1: 2000 ms\n- attempt 2: 4000 ms\n- attempt 3: 8000 ms\n\nDelay override inputs can come from parsed retry headers (`retry-after-ms`, `retry-after`, `x-ratelimit-reset-ms`, `x-ratelimit-reset`) or usage-limit backoff. Credential/model fallback switches set delay to `0`; otherwise parsed hints can extend the exponential local delay.\n\n## Abort mechanics\n\n### Explicit retry abort\n\n`abortRetry()`:\n\n- aborts `#retryAbortController` (if present)\n- resolves retry promise (`#resolveRetry()`) so awaiters are unblocked\n\nIf abort hits while sleeping, catch path emits:\n\n- `auto_retry_end { success: false, finalError: \"Retry cancelled\" }`\n- resets attempt/controller\n\n### Global operation abort interaction\n\n`abort()` calls `abortRetry()` before aborting the active agent stream. This guarantees retry backoff is cancelled when user issues a general abort.\n\n### TUI interaction\n\nOn `auto_retry_start`, EventController:\n\n- swaps `Esc` handler to `session.abortRetry()`\n- renders loader text: `Retrying (attempt/maxAttempts) in Ns… (esc to cancel)`\n\nOn `auto_retry_end`, it restores prior `Esc` handler and clears loader state.\n\n## Streaming and prompt completion behavior\n\n`prompt()` ultimately waits on `#waitForRetry()` after `agent.prompt(...)` returns.\n\nEffect:\n\n- a prompt call does not fully resolve until any started retry chain finishes (success/failure/cancel)\n- retry lifecycle is part of one logical prompt execution boundary\n\nThis prevents callers from treating a retrying turn as complete too early.\n\n## Controls: settings and RPC\n\n### Configuration knobs\n\nDefined in settings schema under retry group:\n\n- `retry.enabled`\n- `retry.maxRetries`\n- `retry.baseDelayMs`\n- `retry.fallbackChains`\n- `retry.fallbackRevertPolicy` (`\"cooldown-expiry\"` by default; `\"never\"` disables automatic restoration)\n\nProgrammatic toggles in session:\n\n- `setAutoRetryEnabled(enabled)` writes `retry.enabled`\n- `autoRetryEnabled` reads `retry.enabled`\n- `isRetrying` reports whether retry lifecycle promise is active\n\n### RPC controls\n\nRPC command surface:\n\n- `set_auto_retry` → `session.setAutoRetryEnabled(command.enabled)`\n- `abort_retry` → `session.abortRetry()`\n\nClient helpers:\n\n- `RpcClient.setAutoRetry(enabled)`\n- `RpcClient.abortRetry()`\n\nBoth commands return success responses; retry progress/failure details come from streamed session events, not command response payloads.\n\n## Event emission and failure surfacing\n\nSession-level retry events:\n\n- `auto_retry_start { attempt, maxAttempts, delayMs, errorMessage }`\n- `auto_retry_end { success, attempt, finalError? }`\n- `retry_fallback_applied { from, to, role }`\n- `retry_fallback_succeeded { model, role }`\n\nPropagation:\n\n- emitted through `AgentSession.subscribe(...)`\n- forwarded to extension runner as extension events\n- in RPC mode, forwarded directly as JSON event objects (`session.subscribe(event => output(event))`)\n- in TUI, consumed by `EventController` for loader/error UI\n\nFinal failure surfacing:\n\n- On max-exceeded or cancellation, `auto_retry_end.success === false`\n- TUI shows: `Retry failed after N attempts: <finalError>`\n- Extensions/hooks receive `auto_retry_end` with same fields\n- RPC consumers receive same event object on stdout stream\n\n## Permanent stop conditions\n\nRetry stops and will not auto-continue when any of these occur:\n\n- `retry.enabled` is false\n- error is not retry-classified\n- error is context overflow (delegated to compaction path)\n- max retries exceeded\n- user cancels retry (`abort_retry` or `Esc` during retry loader)\n- global abort (`abort`) cancels retry first\n\nA new retry chain can still start later on a future retryable error after counters reset.\n\n## Operational caveats\n\n- Classification is regex text matching; provider-specific structured errors are not used here.\n- Retry strips the failing assistant error from **runtime context** before re-continue, but session history still keeps that error entry.\n- `RpcSessionState` currently exposes `autoCompactionEnabled` but not an `autoRetryEnabled` field; RPC callers must track their own toggle state or query settings through other APIs.\n- Model fallback changes append temporary `model_change` entries and may later restore the primary model when its cooldown expires, depending on `retry.fallbackRevertPolicy`.\n\n## Provider request/stream retry budgets\n\nThe provider budgets are deliberately separate from session auto-retry:\n\n```yaml\nretry:\n  requestMaxRetries: 4\n  streamMaxRetries: 100\n```\n\n`requestMaxRetries` maps to provider SDK/fetch retry counts for request setup failures such as retryable 5xx/408/429/network errors. `streamMaxRetries` maps to provider-specific stream replay loops that are safe to repeat without duplicating visible assistant output. Providers that cannot safely replay a stream continue to surface the terminal error so the session-level auto-retry layer can decide whether to retry the turn.\n\nFail-fast cases stay fail-fast: invalid credentials (after any credential-refresh path is exhausted), unsupported model/provider configuration, malformed requests, context overflow, explicit user aborts, and permanent quota failures are not treated as transient provider budget candidates.\n",
 	"notebook-tool-runtime.md": "# Notebook tool runtime internals\n\nThis document describes the current `notebook` tool implementation and its relationship to the kernel-backed Python runtime.\n\nThe critical distinction: **`notebook` is a JSON notebook editor, not a notebook executor**. It edits `.ipynb` cell sources directly; it does not start or talk to a Python kernel.\n\n## Implementation files\n\n- [`src/tools/notebook.ts`](../packages/coding-agent/src/tools/notebook.ts)\n- [`src/eval/py/executor.ts`](../packages/coding-agent/src/eval/py/executor.ts)\n- [`src/eval/py/kernel.ts`](../packages/coding-agent/src/eval/py/kernel.ts)\n- [`src/session/streaming-output.ts`](../packages/coding-agent/src/session/streaming-output.ts)\n- [`src/tools/eval.ts`](../packages/coding-agent/src/tools/eval.ts)\n\n## 1) Runtime boundary: editing vs executing\n\n## `notebook` tool (`src/tools/notebook.ts`)\n\n- Supports `action: edit | insert | delete` on a `.ipynb` file.\n- Resolves path relative to session CWD (`resolveToCwd`).\n- Loads notebook JSON, validates `cells` array, validates `cell_index` bounds.\n- Applies source edits in-memory and writes full notebook JSON back with `JSON.stringify(notebook, null, 1)`.\n- Returns textual summary + structured `details` (`action`, `cellIndex`, `cellType`, `totalCells`, `cellSource`).\n\nNo kernel lifecycle exists in this tool:\n\n- no gateway acquisition\n- no kernel session ID\n- no `execute_request`\n- no stream chunks from kernel channels\n- no rich display capture (`image/png`, JSON display, status MIME)\n\n## Notebook-like execution path (`src/tools/eval.ts` + `src/eval/py/*`)\n\nWhen the agent needs to run cell-style Python code (sequential cells, persistent state, rich displays), that goes through the **`eval` tool** with `language: \"python\"`, not `notebook`.\n\nThat path is where kernel modes, restart/cancel behavior, chunk streaming, and output artifact truncation live.\n\n## 2) Notebook cell handling semantics (`notebook` tool)\n\n## Source normalization\n\n`content` is split into `source: string[]` with newline preservation:\n\n- each non-final line keeps trailing `\\n`\n- final line has no forced trailing newline\n\nThis mirrors notebook JSON conventions and avoids accidental line concatenation on later edits.\n\n## Action behavior\n\n- `edit`\n  - replaces `cells[cell_index].source`\n  - preserves existing `cell_type`\n- `insert`\n  - inserts at `[0..cellCount]`\n  - `cell_type` defaults to `code`\n  - code cells initialize `execution_count: null` and `outputs: []`\n  - markdown cells initialize only `metadata` + `source`\n- `delete`\n  - removes `cells[cell_index]`\n  - returns removed `source` in details for renderer preview\n\n## Error surfaces\n\nHard failures are thrown for:\n\n- missing notebook file\n- invalid JSON\n- missing/non-array `cells`\n- out-of-range index (insert and non-insert have different valid ranges)\n- missing `content` for `edit`/`insert`\n\nThese become `Error:` tool responses upstream; renderer uses notebook path + formatted error text.\n\n## 3) Kernel session semantics (where they actually exist)\n\nKernel semantics are implemented in `executePython` / `PythonKernel` and apply to the Python backend of the `eval` tool.\n\n## Modes\n\n`PythonKernelMode`:\n\n- `session` (default)\n  - kernels cached in `kernelSessions` map\n  - max 4 sessions; oldest evicted on overflow\n  - idle/dead cleanup every 30s, timeout after 5 minutes\n  - per-session queue serializes execution (`session.queue`)\n- `per-call`\n  - creates kernel for request\n  - executes\n  - always shuts down kernel in `finally`\n\n## Reset behavior\n\n`eval` passes `reset` only for the first cell in a multi-cell Python call; later cells always run with `reset: false`.\n\n## Kernel death / restart / retry\n\nIn session mode (`withKernelSession`):\n\n- dead kernel detected by heartbeat (`kernel.isAlive()` check every 5s) or execute failure.\n- pre-run dead state triggers `restartKernelSession`.\n- execute-time crash path retries once: restart kernel, rerun handler.\n- `restartCount > 1` in same session throws `Python kernel restarted too many times in this session`.\n\nStartup retry behavior:\n\n- shared gateway kernel creation retries once on `SharedGatewayCreateError` with HTTP 5xx.\n\nResource exhaustion recovery:\n\n- detects `EMFILE`/`ENFILE`/\"Too many open files\" style failures\n- clears tracked sessions\n- calls `shutdownSharedGateway()`\n- retries kernel session creation once\n\n## 4) Environment/session variable injection\n\nKernel startup receives the optional session file path from executor:\n\n- `GJC_SESSION_FILE` (session state file path)\n\n`PythonKernel.#initializeKernelEnvironment(...)` then runs init script inside kernel to:\n\n- `os.chdir(cwd)`\n- inject env entries into `os.environ`\n- prepend cwd to `sys.path` if missing\n\nImplication:\n\n- prelude helpers that read session context rely on this env var in Python process state.\n\n## 5) Streaming/chunk and display handling (kernel-backed path)\n\nThe kernel client processes Jupyter protocol messages per execution:\n\n- `stream` -> text chunk to `onChunk`\n- `execute_result` / `display_data` ->\n  - display text chosen by MIME precedence: `text/markdown` > `text/plain` > converted `text/html`\n  - structured outputs captured separately:\n    - `application/json` -> `{ type: \"json\" }`\n    - `image/png` -> `{ type: \"image\" }`\n    - `application/x-gjc-status` -> `{ type: \"status\" }` (no text emission)\n- `error` -> traceback text pushed to chunk stream + structured error metadata\n- `input_request` -> emits stdin warning text, sends empty `input_reply`, marks stdin requested\n- completion waits for both `execute_reply` and kernel `status=idle`\n\nCancellation/timeout:\n\n- abort signal triggers `interrupt()` (REST `/interrupt` + control-channel `interrupt_request`)\n- result marks `cancelled=true`\n- timeout path annotates output with `Command timed out after <n> seconds`\n\n## 6) Truncation and artifact behavior\n\n`OutputSink` in `src/session/streaming-output.ts` is used by kernel execution paths (`executeWithKernel`):\n\n- sanitizes every chunk (`sanitizeText`)\n- tracks total/output lines and bytes\n- optional artifact spill file (`artifactPath`, `artifactId`)\n- when in-memory buffer exceeds threshold (`DEFAULT_MAX_BYTES` unless overridden):\n  - marks truncated\n  - keeps tail bytes in memory (UTF-8 safe boundary)\n  - can spill full stream to artifact sink\n\n`dump()` returns:\n\n- visible output text (possibly tail-truncated)\n- truncation flag + counts\n- artifact ID (for `artifact://<id>` references)\n\n`eval` converts this metadata into result truncation notices and TUI warnings.\n\n`notebook` tool does **not** use `OutputSink`; it has no stream/artifact truncation pipeline because it does not execute code.\n\n## 7) Renderer assumptions and formatting\n\n## Notebook renderer (`notebookToolRenderer`)\n\n- call view: status line with action + notebook path + cell/type metadata\n- result view:\n  - success summary derived from `details`\n  - `cellSource` rendered via `renderCodeCell`\n  - markdown cells set language hint `markdown`; other cells have no explicit language override\n  - collapsed code preview limit is `PREVIEW_LIMITS.COLLAPSED_LINES * 2`\n  - supports expanded mode via shared render options\n  - uses render cache keyed by width + expanded state\n\nError rendering assumption:\n\n- if first text content starts with `Error:`, renderer formats as notebook error block.\n\n## Python renderer (for actual execution output)\n\nKernel-backed execution rendering expects:\n\n- per-cell status transitions (`pending/running/complete/error`)\n- optional structured status event section\n- optional JSON output trees\n- truncation warnings + optional `artifact://<id>` pointer\n\nThis renderer behavior is unrelated to `notebook` JSON editing results except that both reuse shared TUI primitives.\n\n## 8) Divergence from eval Python backend behavior\n\nIf \"plain Python execution\" means the `eval` tool with `language: \"python\"`:\n\n- `eval` executes code in a kernel, persists state by mode, streams chunks, captures rich displays, handles interrupts/timeouts, and supports output truncation/artifacts.\n- `notebook` performs deterministic notebook JSON mutations only; no execution, no kernel state, no chunk stream, no display outputs, no artifact pipeline.\n\nIf a workflow needs both:\n\n1. edit notebook source with `notebook`\n2. execute code cells via `eval` with `language: \"python\"` (manually passing code), not through `notebook`\n\nCurrent implementation does not provide a single tool that both mutates `.ipynb` and executes notebook cells through kernel context.\n",
+	"onboarding-packet.md": "# Gajae-Code Onboarding Packet\n\nThis packet is a docs-only, public-safe context seed for the `gajae-code` repository as inspected on 2026-06-01. It is intentionally a no-new-skill artifact: not a new workflow skill, command, agent, configuration surface, issue template, or runtime behavior.\n\n## Purpose in one paragraph\n\nGajae-Code is the `gjc` coding-agent CLI and supporting monorepo. The product centers on a small public workflow loop: clarify with `deep-interview`, plan with `ralplan`, execute and verify through `ultragoal`, and use `team` only when parallel tmux workers are useful. The main product package is `packages/coding-agent/`; supporting packages provide LLM/provider access, agent runtime, TUI rendering, native helpers, stats, utilities, benchmarks, and Python RPC/bot integrations.\n\n## Fixed public surface\n\nKeep this invariant front-and-center when onboarding to the repo:\n\n- Default workflow skills: `deep-interview`, `ralplan`, `team`, `ultragoal`.\n- Public role agents: `executor`, `architect`, `planner`, `critic`.\n- Bundled default workflow skill sources live under `packages/coding-agent/src/defaults/gjc/skills/`.\n- Bundled role-agent prompt sources live under `packages/coding-agent/src/prompts/agents/`.\n- Runtime state, specs, plans, goals, team state, and local overrides belong under `.gjc/` for the product and `.omx/` only for this agent-run orchestration.\n\nDo not add a fifth default skill, fifth public role agent, new command, new config surface, or feature-intake behavior unless that product decision has already been made and the default-surface gates are updated.\n\n## Primary entrypoints\n\n| Area             | Repo-relative path                                   | Why it matters                                                                                    |\n| ---------------- | ---------------------------------------------------- | ------------------------------------------------------------------------------------------------- |\n| CLI bootstrap    | `packages/coding-agent/src/cli.ts`                   | Registers top-level CLI commands and routes default launch behavior.                              |\n| Session launch   | `packages/coding-agent/src/main.ts`                  | Converts CLI/runtime settings into agent-session creation and mode dispatch.                      |\n| Agent assembly   | `packages/coding-agent/src/sdk.ts`                   | Loads settings, default skills, rules, tools, auth/model state, system prompt, and agent runtime. |\n| Built-in tools   | `packages/coding-agent/src/tools/index.ts`           | Registers file, shell, edit, search, browser, task/subagent, memory, and related tools.           |\n| Default skills   | `packages/coding-agent/src/defaults/gjc-defaults.ts` | Embeds and installs the four default workflow skills plus deep-interview fragments.               |\n| Role agents      | `packages/coding-agent/src/task/agents.ts`           | Embeds bundled task-agent prompts; tests enforce public role-agent expectations.                  |\n| Product overview | `README.md`                                          | Explains installation, product story, fixed workflow surface, and development entry commands.     |\n| Architecture map | `docs/codebase-overview.md`                          | Public package map and runtime-flow reference.                                                    |\n\n## Package map\n\n- `packages/coding-agent/` — main `gjc` CLI, workflows, session runtime, tool registry, discovery, settings, prompts, and tests.\n- `packages/ai/` — provider/model boundary, streaming, auth, model registry, retries, and provider integrations.\n- `packages/agent/` — stateful agent loop and append-only context runtime.\n- `packages/tui/` — terminal UI framework and rendering primitives.\n- `packages/natives/` plus `crates/*` — native helpers, Rust/N-API bindings, shell/PTY, text search, AST, filesystem, and media utilities.\n- `packages/utils/` — shared TypeScript utilities, logging, formatting, process helpers, JSON/frontmatter, and sanitization.\n- `packages/stats/` — local observability dashboard and session/model usage aggregation.\n- `packages/swarm-extension/` — optional YAML/DAG multi-agent extension outside the fixed default workflow surface.\n- `packages/typescript-edit-benchmark/` — TypeScript edit benchmark tooling.\n- `python/gjc-rpc/` — Python client for `gjc --mode rpc`.\n- `python/robogjc/` — GitHub triage/fix bot that drives `gjc --mode rpc`; this subtree has its own `AGENTS.md`.\n\n## Build, test, and validation commands\n\nPrefer targeted checks first, then broader checks when code changes justify them. For this docs-only packet, lightweight validation is enough.\n\n| Command                                                               | Scope                               | When to use                                                                 |\n| --------------------------------------------------------------------- | ----------------------------------- | --------------------------------------------------------------------------- |\n| `bun install`                                                         | Workspace dependencies              | Initial local setup.                                                        |\n| `bun run install:defaults`                                            | Local default install               | Installs source-bundled default workflow definitions for local development. |\n| `bun packages/coding-agent/src/cli.ts --help`                         | CLI smoke/discovery                 | Fast source checkout CLI sanity check.                                      |\n| `bun run check:ts`                                                    | Type/lint/default UI checks         | Broad TypeScript validation; heavier than docs-only changes.                |\n| `bun run test`                                                        | Full TS + Rust tests                | Broad regression check; use for runtime/product changes.                    |\n| `bun run ci:test:smoke`                                               | CLI version/help/stats worker smoke | Useful before release/install changes.                                      |\n| `bun scripts/check-visible-definitions.ts`                            | Default surface gate                | Required after workflow-definition changes.                                 |\n| `bun scripts/verify-g002-gates.ts`                                    | Rebrand/default-surface gate        | Required after workflow-definition or public-surface changes.               |\n| `bun scripts/rebrand-inventory.ts --strict`                           | Rebrand inventory gate              | Required after workflow-definition or public-surface changes.               |\n| `bun test packages/coding-agent/test/default-gjc-definitions.test.ts` | Four-skills/four-agents contract    | Required after default workflow/agent surface changes.                      |\n\nRepository rule: do not run `tsc` or `npx tsc`; use the Bun scripts above.\n\n## Danger zones\n\n- **Default surface expansion:** `packages/coding-agent/src/defaults/gjc/skills/`, `packages/coding-agent/src/defaults/gjc-defaults.ts`, `packages/coding-agent/src/prompts/agents/`, and model-assignment tests are contract-heavy. Changes here can accidentally alter the fixed four-skills/four-agents shape.\n- **CLI commands:** `packages/coding-agent/src/cli.ts` and `packages/coding-agent/src/commands/` define visible behavior. Adding commands or aliases is a product-surface change.\n- **Runtime/session assembly:** `packages/coding-agent/src/main.ts`, `packages/coding-agent/src/sdk.ts`, discovery, settings, tools, and system-prompt paths can affect every session.\n- **TUI/logging:** Avoid `console.log`, `console.warn`, or `console.error` inside `packages/coding-agent/`; use the centralized logger to avoid corrupting TUI rendering.\n- **Secrets/auth/config:** Keep `docs/secrets.md`, auth broker/gateway code, settings, and environment-variable docs public-safe. Do not expose tokens or private infrastructure.\n- **Native/Rust build:** `packages/natives/` and `crates/*` can require platform-specific toolchains and CI artifact behavior.\n- **Python bot subtree:** `python/robogjc/` has its own local instructions and trust boundaries.\n- **Generated model data:** Do not edit `packages/ai/src/models.json` directly; update generators/descriptors/resolvers and regenerate with `bun --cwd=packages/ai run generate-models`.\n\n## Unknowns worth preserving\n\n- Which onboarding packet shape will be most useful for future `gjc` context ingestion is still an experiment, not a product contract.\n- Public issue #158 / `gajae-deep-onboarding` context is summarized only from the user-provided prompt in this run; this packet does not add issue intake or feature workflow behavior.\n- Full CI may depend on runner/system dependencies and native artifacts; docs-only changes usually do not need the full matrix locally.\n- Some packages contain internal or hidden utility prompts/agents beyond the four public role agents. Public-facing docs should keep the four-role contract clear.\n\n## First safe tasks for a new contributor or agent\n\n1. Read `README.md`, `docs/codebase-overview.md`, and this packet.\n2. Run `bun packages/coding-agent/src/cli.ts --help` for a fast CLI surface check after dependencies are installed.\n3. For docs-only edits, run formatting/check commands that do not mutate runtime behavior.\n4. For default-surface edits, run the four required gates listed in the command table before claiming completion.\n5. For package code edits, start with the nearest package test, then escalate to `bun run check:ts` or `bun run test` as risk increases.\n6. Before changing `packages/coding-agent/src/defaults/gjc/skills/`, `packages/coding-agent/src/prompts/agents/`, `packages/coding-agent/src/commands/`, or config/settings paths, write down whether the change alters public surface area.\n\n## Context seed checklist\n\nA future agent can use this packet as context if it preserves these constraints:\n\n- Keep changes public-safe and repo-relative.\n- Prefer docs and tests over new runtime abstractions for onboarding experiments.\n- Treat the fixed four-skills/four-agents shape as a product constraint.\n- Verify claims with repo files before summarizing them.\n- Report validation evidence and caveats instead of implying hidden automation.\n",
+	"onboarding-receipt.md": "# Onboarding Packet Receipt\n\n- Date: 2026-06-01\n- Scope: docs-only no-new-skill onboarding packet experiment for this repository.\n- Output files:\n  - `docs/onboarding-packet.md`\n  - `docs/onboarding-receipt.md`\n- Public-safe boundary: no secrets, tokens, hidden prompts, private infrastructure, internal ops, or private paths beyond repo-relative paths.\n- Product boundary: no new skill, command, agent slot, issue, config, or runtime behavior.\n\n## Evidence inspected\n\n- `README.md`\n- `docs/codebase-overview.md`\n- `package.json`\n- `packages/coding-agent/package.json`\n- `packages/coding-agent/src/cli.ts`\n- `packages/coding-agent/src/main.ts`\n- `packages/coding-agent/src/sdk.ts`\n- `packages/coding-agent/src/defaults/gjc-defaults.ts`\n- `packages/coding-agent/src/task/agents.ts`\n- `packages/coding-agent/test/default-gjc-definitions.test.ts`\n- `.github/workflows/ci.yml`\n- `.github/workflows/dev-ci.yml`\n\n## Result\n\nThe packet records repo purpose, package layout, main entrypoints, build/test commands, danger zones, unknowns, and first safe tasks without changing the product surface. It is suitable as a public context seed for future onboarding experiments, not as a feature intake mechanism.\n\n## Caveats\n\n- The attempted `omx question --input '<json>' --json` interview round failed before user input because the runtime reported no attached tmux client; no human answer was inferred from that failed call.\n- Public issue context is limited to the user-provided prompt summary for this run.\n- Full CI was not required for the docs-only artifact unless later code/runtime files change.\n",
 	"porting-from-pi-mono.md": "# Porting From pi-mono: A Practical Merge Guide\n\nThis guide is a repeatable checklist for porting changes from pi-mono into this repo.\nUse it for any merge: single file, feature branch, or full release sync.\n\n## Last Sync Point (historical upstream marker)\n\n**Commit:** `b21b42d032919de2f2e6920a76fa9a37c3920c0a`\n**Date:** 2026-03-22\n\nUpdate this section after each sync; do not reuse the previous range. This commit is an upstream pi-mono marker and may not exist in this repo's local object database.\n\nWhen starting a new sync, generate patches from this commit forward in a pi-mono checkout or remote that contains the commit:\n\n```bash\ngit format-patch b21b42d032919de2f2e6920a76fa9a37c3920c0a..HEAD --stdout > changes.patch\n```\n\n## 0) Define the scope\n\n- Identify the upstream reference (commit, tag, or PR).\n- List the packages or folders you plan to touch.\n- Decide which features are in-scope and which are intentionally skipped.\n\n## 1) Bring code over safely\n\n- Prefer a clean, focused diff rather than a wholesale copy.\n- Avoid copying built artifacts or generated files.\n- If upstream added new files, add them explicitly and review contents.\n\n## 2) Match import extension conventions\n\nMost runtime TypeScript sources omit `.js` in internal imports, but several current entrypoints and tool modules keep `.js` for ESM/runtime compatibility. Follow the surrounding file and package export style; do not blanket-strip or blanket-add extensions.\n\n- In `packages/coding-agent` runtime sources, prefer extensionless internal imports when the surrounding module does, but preserve existing `.js` imports in files that already require them.\n- In `packages/tui/test` and `packages/natives/bench`, keep `.js` where surrounding files already use it.\n- Keep real file extensions when required by tooling or import assertions (e.g., `.json`, `.css`, `.md` text embeds).\n- Example: `import { x } from \"./foo.js\";` → `import { x } from \"./foo\";` only when that package/file convention is extensionless.\n\n## 3) Replace import scopes\n\nUpstream uses different package scopes. Replace them consistently.\n\n- Replace old scopes with the local scope used here.\n- Examples (adjust to match the actual packages you are porting):\n  - `@mariozechner/gajae-code` → `@gajae-code/coding-agent`\n  - `@mariozechner/pi-agent-core` → `@gajae-code/agent-core`\n  - `@mariozechner/pi-tui` → `@gajae-code/tui`\n  - `@mariozechner/pi-ai` → `@gajae-code/ai`\n\n## 4) Use Bun APIs where they improve on Node\n\nWe run on Bun, but the current source intentionally mixes Bun APIs with small Node standard-library APIs. Replace Node APIs only when Bun provides a clearer, safer, or simpler implementation; do not mechanically rewrite every Node import.\n\n**Prefer replacing when porting new code:**\n\n- Process spawning: prefer Bun Shell `$` for simple commands; use `Bun.spawn`/`Bun.spawnSync` for streaming or process control. Keep existing `child_process` only where its exact semantics are needed.\n- HTTP clients: `node-fetch`, `axios` → native `fetch`\n- SQLite: `better-sqlite3` → `bun:sqlite`\n- Env loading: `dotenv` → Bun loads `.env` automatically\n- Runtime text/assets: prefer Bun imports such as `with { type: \"text\" }` or `Bun.file()` over copy steps or bundled fallback file reads.\n\n**DO NOT replace (these work fine in Bun):**\n\n- `os.homedir()` — do NOT replace with `Bun.env.HOME` or literal `\"~\"`\n- `os.tmpdir()` — do NOT replace with `Bun.env.TMPDIR || \"/tmp\"` or hardcoded paths\n- `fs.mkdtempSync()` — do NOT replace with manual path construction\n- `path.join()`, `path.resolve()`, etc. — these are fine\n\n**Import style:** Use the `node:` prefix for Node standard-library imports. Namespace imports are common, but named imports are acceptable where the surrounding code already uses them.\n\n**Additional Bun conventions:**\n\n- Prefer Bun Shell `$` for short, non-streaming commands; use `Bun.spawn` only when you need streaming I/O or process control.\n- Use `Bun.file()`/`Bun.write()` for simple files and `node:fs/promises` for directory-oriented operations. Existing synchronous `node:fs` calls are acceptable when the calling flow is intentionally synchronous.\n- Avoid `Bun.file().exists()` checks; use `isEnoent` handling in try/catch.\n- Prefer `Bun.sleep(ms)` over `setTimeout` wrappers.\n\n**Wrong:**\n\n```typescript\n// BROKEN: env vars may be undefined, \"~\" is not expanded\nconst home = Bun.env.HOME || \"~\";\nconst tmp = Bun.env.TMPDIR || \"/tmp\";\n```\n\n**Correct:**\n\n```typescript\nimport * as os from \"node:os\";\nimport * as fs from \"node:fs\";\nimport * as path from \"node:path\";\n\nconst configDir = path.join(os.homedir(), \".config\", \"myapp\");\nconst tempDir = fs.mkdtempSync(path.join(os.tmpdir(), \"myapp-\"));\n```\n\n## 5) Prefer Bun embeds (no copying)\n\nDo not add new runtime asset copy steps. Keep assets in repo and prefer Bun embeds/imports; preserve existing explicit generation workflows such as `packages/coding-agent/src/export/html/template.generated.ts`.\n\n- If upstream copies assets into a dist folder, replace with Bun-friendly embeds.\n- Prompts are static `.md` files; use Bun text imports (`with { type: \"text\" }`) and Handlebars instead of inline prompt strings.\n- Use `import.meta.dir` + `Bun.file` to load adjacent non-text resources.\n- Keep assets in-repo and let the bundler include them.\n- Eliminate copy scripts unless the user explicitly requests them or the package already has an intentional generation step.\n- If upstream reads a bundled fallback file at runtime, replace filesystem reads with a Bun text embed import unless the current package already uses a generated asset pipeline.\n  - Example (provider instructions fallback):\n    - `const FALLBACK_PROMPT_PATH = join(import.meta.dir, \"openai-code-instructions.md\");` -> removed\n    - `import FALLBACK_INSTRUCTIONS from \"./openai-code-instructions.md\" with { type: \"text\" };`\n    - Use `return FALLBACK_INSTRUCTIONS;` instead of `readFileSync(FALLBACK_PROMPT_PATH, \"utf8\")`\n\n## 6) Port `package.json` carefully\n\nTreat `package.json` as a contract. Merge intentionally.\n\n- Keep existing `name`, `version`, `type`, `exports`, and `bin` unless the port requires changes.\n- Replace npm/node scripts with Bun equivalents (e.g., `bun check`, `bun test`).\n- Ensure dependencies use the correct scope.\n- Do not downgrade dependencies to fix type errors; upgrade instead.\n- Validate workspace package links and `peerDependencies`.\n\n## 7) Align code style and tooling\n\n- Keep existing formatting conventions.\n- Do not introduce `any` unless required.\n- Avoid dynamic imports unless they are required for optional dependencies, startup cost, or runtime-only modules; prefer top-level imports otherwise.\n- Never build prompts in code; prompts are static `.md` files rendered with Handlebars.\n- In `packages/coding-agent`, use `logger` from `@gajae-code/utils` for internal/runtime logging; CLI command files may use `console.*` for intentional user-facing output.\n- Use `Promise.withResolvers()` instead of `new Promise((resolve, reject) => ...)`.\n- Prefer ES `#` private fields for new encapsulated state. Constructor parameter properties already exist in current code and are acceptable; do not churn unrelated access modifiers while porting.\n- Prefer existing helpers and utilities over new ad-hoc code.\n  Preserve Bun-first infrastructure changes already made in this repo:\n  - Runtime is Bun (no Node entry points for the main CLI).\n  - Package manager is Bun (no npm lockfiles).\n  - Heavy Node APIs should not be introduced casually; current source still uses selected Node APIs (`node:crypto`, `node:readline`, synchronous `node:fs`, and `child_process`) where they fit provider, CLI, or process-control semantics.\n  - Lightweight Node APIs (`os.homedir`, `os.tmpdir`, `fs.mkdtempSync`, `path.*`) are kept.\n  - CLI shebangs use `bun` (not `node`, not `tsx`).\n  - TypeScript packages generally use source files directly; `@gajae-code/natives` exports generated native bindings from `packages/natives/native`.\n  - CI workflows run Bun for install/check/test.\n\n## 8) Remove old compatibility layers\n\nUnless requested, remove upstream compatibility shims.\n\n- Delete old APIs that were replaced.\n- Update all call sites to the new API directly.\n- Do not keep `*_v2` or parallel versions.\n\n## 9) Update docs and references\n\n- Replace pi-mono repo links where appropriate.\n- Update examples to use Bun and correct package scopes.\n- Ensure README instructions still match the current repo behavior.\n\n## 10) Validate the port\n\nRun the standard checks after changes:\n\n- `bun check`\n\nIf the repo already has failing checks unrelated to your changes, call that out.\nTests use Bun's runner (not Vitest), but only run `bun test` when explicitly requested.\n\n## 11) Protect improved features (regression trap list)\n\nIf you already improved behavior locally, treat those as **non‑negotiable**. Before porting, write down\nthe improvements and add explicit checks so they don’t get lost in the merge.\n\n- **Freeze the expected behavior**: add a short “before/after” note for each improvement (inputs, outputs,\n  defaults, edge cases). This prevents silent rollback.\n- **Map old → new APIs**: if upstream renamed concepts (hooks → extensions, custom tools → tools, etc.),\n  ensure every old entry point still wires through. One missed flag or export equals lost functionality.\n- **Verify exports**: check `package.json` `exports`, public types, and barrel files. Upstream ports often\n  forget to re-export local additions.\n- **Cover non‑happy paths**: if you fixed error handling, timeouts, or fallback logic, add a test or at\n  least a manual checklist that exercises those paths.\n- **Check defaults and config merge order**: improvements often live in defaults. Confirm new defaults\n  didn’t revert (e.g., new config precedence, disabled features, tool lists).\n- **Audit env/shell behavior**: if you fixed execution or sandboxing, verify the new path still uses your\n  sanitized env and does not reintroduce alias/function overrides.\n- **Re-run targeted samples**: keep a minimal set of \"known good\" examples and run them after the port\n  (CLI flags, extension registration, tool execution).\n\n## 12) Detect and handle reworked code\n\nBefore porting a file, check if upstream significantly refactored it:\n\n```bash\n# Compare the file you're about to port against what you have locally\ngit diff HEAD upstream/main -- path/to/file.ts\n```\n\nIf the diff shows the file was **reworked** (not just patched):\n\n- New abstractions, renamed concepts, merged modules, changed data flow\n\nThen you must **read the new implementation thoroughly** before porting. Blind merging of reworked code loses functionality because:\n\nNote: interactive mode was recently split into controllers/utils/types. When backporting related changes, port updates into the individual files we created and ensure `interactive-mode.ts` wiring stays in sync.\n\n1. **Defaults change silently** - A new variable `defaultFoo = [a, b]` may replace an old `getAllFoo()` that returned `[a, b, c, d, e]`.\n\n2. **API options get dropped** - When systems merge (e.g., `hooks` + `customTools` → `extensions`), old options may not wire through to the new implementation.\n\n3. **Code paths go stale** - A renamed concept (e.g., `hookMessage` → `custom`) needs updates in every switch statement, type guard, and handler—not just the definition.\n\n4. **Context/capabilities shrink** - Old APIs may have exposed `{ logger, typebox, pi }` that new APIs forgot to include.\n\n### Semantic porting process\n\nWhen upstream reworked a module:\n\n1. **Read the old implementation** - Understand what it did, what options it accepted, what it exposed.\n\n2. **Read the new implementation** - Understand the new abstractions and how they map to old behavior.\n\n3. **Verify feature parity** - For each capability in the old code, confirm the new code preserves it or explicitly removes it.\n\n4. **Grep for stragglers** - Search for old names/concepts that may have been missed in switch statements, handlers, UI components.\n\n5. **Test the boundaries** - CLI flags, SDK options, event handlers, default values—these are where regressions hide.\n\n### Quick checks\n\n```bash\n# Find all uses of an old concept that may need updating\nrg \"oldConceptName\" --type ts\n\n# Compare default values between versions\ngit show upstream/main:path/to/file.ts | rg \"default|DEFAULT\"\n\n# Check if all enum/union values have handlers\nrg \"case \\\"\" path/to/file.ts\n```\n\n## 13) Quick audit checklist\n\nUse this as a final pass before you finish:\n\n- [ ] Import extensions follow the local package convention (no blanket `.js` stripping)\n- [ ] No newly introduced Node-only APIs unless they match an existing justified pattern\n- [ ] All package scopes updated\n- [ ] `package.json` scripts use Bun\n- [ ] Prompts are `.md` text imports (no inline prompt strings)\n- [ ] No internal/runtime `console.*` in coding-agent; CLI user-facing output is intentional\n- [ ] Assets load via Bun embed/import patterns, or through an existing intentional generation pipeline\n- [ ] Tests or checks run (or explicitly noted as blocked)\n- [ ] No functionality regressions (see sections 11-12)\n\n## 14) Commit message format\n\nWhen committing a backport, follow the repo format `<type>(scope): <past-tense description>` and keep the commit\nrange in the title.\n\n```\nfix(coding-agent): backported pi-mono changes (<from>..<to>)\n\npackages/<package>:\n- <type>: <description>\n- <type>: <description> (#<issue> by @<contributor>)\n\npackages/<other-package>:\n- <type>: <description>\n```\n\n**Example:**\n\n```\nfix(coding-agent): backported pi-mono changes (9f3eef65f..52532c7c0)\n\npackages/ai:\n- fix: handle \"sensitive\" stop reason from Anthropic API\n- fix: normalize tool call IDs with special characters for Responses API\n- fix: add overflow detection for Bedrock, MiniMax, Kimi providers\n- fix: 429 status is rate limiting, not context overflow\n\npackages/tui:\n- fix: refactored autocomplete state tracking\n- fix: file autocomplete should not trigger on empty text\n- fix: configurable autocomplete max visible items\n- fix: improved table column width calculation with word-aware wrapping\n\npackages/coding-agent:\n- fix: preserve external config.yml edits on save (#1046 by @nicobailonMD)\n- fix: resolve macOS NFD and curly quote variants in file paths\n```\n\n**Rules:**\n\n- Group changes by package\n- Use conventional commit types (`fix`, `feat`, `refactor`, `perf`, `docs`)\n- Include upstream issue/PR numbers and contributor attribution for external contributions\n- The commit range in the title helps track sync points\n\n## 15) Intentional Divergences\n\nOur fork has architectural decisions that differ from upstream. **Do not port these upstream patterns:**\n\n### UI Architecture\n\n| Upstream                                    | Our Fork                                                  | Reason                                                                |\n| ------------------------------------------- | --------------------------------------------------------- | --------------------------------------------------------------------- |\n| `FooterDataProvider` class                  | `StatusLineComponent`                                     | Simpler, integrated status line                                       |\n| `ctx.ui.setHeader()` / `ctx.ui.setFooter()` | No-op stubs in current extension contexts                 | Not currently wired to replace the TUI status/header UI               |\n| `ctx.ui.setEditorComponent()`               | No-op stubs in current extension contexts                 | Custom editor replacement is not currently wired                      |\n| `InteractiveModeOptions` options object     | Positional constructor args (options type still exported) | Keep constructor signature; update the type when upstream adds fields |\n\n### Component Naming\n\n| Upstream                     | Our Fork                |\n| ---------------------------- | ----------------------- |\n| `extension-input.ts`         | `hook-input.ts`         |\n| `extension-selector.ts`      | `hook-selector.ts`      |\n| `ExtensionInputComponent`    | `HookInputComponent`    |\n| `ExtensionSelectorComponent` | `HookSelectorComponent` |\n\n### API Naming\n\n| Upstream                                 | Our Fork                                 | Notes                                     |\n| ---------------------------------------- | ---------------------------------------- | ----------------------------------------- |\n| `sessionManager.appendSessionInfo(name)` | `sessionManager.setSessionName(name)`    | We use `sessionName` throughout           |\n| `sessionManager.getSessionName()`        | `sessionManager.getSessionName()`        | Same (we unified to match upstream's RPC) |\n| `agent.sessionName` / `setSessionName()` | `agent.sessionName` / `setSessionName()` | Same                                      |\n\n### File Consolidation\n\n| Upstream                                           | Our Fork                                                  | Reason                                        |\n| -------------------------------------------------- | --------------------------------------------------------- | --------------------------------------------- |\n| `clipboard.ts` + `clipboard-image.ts` (tool files) | `src/utils/clipboard.ts` backed by `@gajae-code/natives` | Native implementation with a small TS wrapper |\n\n### Test Framework\n\n| Upstream                  | Our Fork                      |\n| ------------------------- | ----------------------------- |\n| `vitest` with `vi.mock()` | `bun:test` with `vi` from bun |\n| `node:test` assertions    | `expect()` matchers           |\n\n### Tool Architecture\n\n| Upstream                            | Our Fork                                                                                                      | Notes                                                     |\n| ----------------------------------- | ------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------- |\n| `createTool(cwd: string, options?)` | `createTools(session: ToolSession)` via `BUILTIN_TOOLS` registry                                              | Tool factories accept `ToolSession` and can return `null` |\n| Per-tool `*Operations` interfaces   | Only current per-tool override interfaces remain (for example `FindOperations`)                               | Used for SSH/remote overrides where present               |\n| Node.js `fs/promises` everywhere    | Bun file APIs for simple file writes/reads, `node:fs/promises` for dirs, selected sync `node:fs` where needed | Prefer Bun APIs when they simplify                        |\n\n### Auth Storage\n\n| Upstream                        | Our Fork                                    | Notes                                        |\n| ------------------------------- | ------------------------------------------- | -------------------------------------------- |\n| `proper-lockfile` + `auth.json` | `agent.db` (bun:sqlite)                     | Credentials stored exclusively in `agent.db` |\n| Single credential per provider  | Multi-credential with round-robin selection | Session affinity and backoff logic preserved |\n\n### Extensions\n\n| Upstream                      | Our Fork                                          |\n| ----------------------------- | ------------------------------------------------- |\n| `jiti` for TypeScript loading | Native Bun `import()`                             |\n| `pkg.pi` manifest field       | `pkg.gjc` preferred; fallback to `pkg.pi` remains |\n\n### Skip These Upstream Features\n\nWhen porting, **skip** these files/features entirely:\n\n- `footer-data-provider.ts` — we use StatusLineComponent\n- `clipboard-image.ts` — image clipboard support is exposed through `src/utils/clipboard.ts` backed by `@gajae-code/natives`\n- GitHub workflow files — we have our own CI\n- `models.generated.ts` — auto-generated, regenerate locally (as models.json instead)\n\n### Features We Added (Preserve These)\n\nThese exist in our fork but not upstream. **Never overwrite:**\n\n- `StatusLineComponent` in interactive mode\n- Multi-credential auth with session affinity\n- Capability-based discovery system (`defineCapability`, `registerProvider`, `loadCapability`, `skillCapability`, etc.)\n- MCP/Exa/SSH integrations\n- LSP writethrough for format-on-save\n- Bash interception (`checkBashInterception`)\n- Fuzzy path suggestions in read tool\n",
 	"porting-to-natives.md": "# Porting to pi-natives (N-API) — Field Notes\n\nThis is a practical guide for moving hot paths into `crates/pi-natives` and wiring them through the generated native package entrypoint. It exists to avoid the same failures happening twice.\n\n## When to port\n\nPort when any of these are true:\n\n- The hot path runs in render loops, tight UI updates, or large batches.\n- JS allocations dominate (string churn, regex backtracking, large arrays).\n- You already have a JS baseline and can benchmark both versions side by side.\n- The work is CPU-bound or blocking I/O that can run on the libuv thread pool.\n- The work is async I/O that can run on Tokio's runtime (for example shell execution).\n\nRust is reserved for native bindings, native OS/process/filesystem integration, and measured hot paths. New crates or Rust source trees must have an explicit native/performance rationale in `scripts/check-rust-scope.ts`; keep product policy, orchestration, and glue code in TypeScript unless the benchmark or native boundary justifies moving it.\n\nAvoid ports that depend on JS-only state or dynamic imports. N-API exports should be data-in/data-out. Long-running work should go through `task::blocking` (CPU-bound/blocking I/O) or `task::future` (async I/O) with cancellation where the caller needs `timeoutMs` or `AbortSignal`.\n\n## Current package shape\n\n`@gajae-code/natives` no longer has a `packages/natives/src/<module>` TypeScript wrapper layer. The package root points at generated native artifacts:\n\n- runtime entry: `packages/natives/native/index.js`\n- types entry: `packages/natives/native/index.d.ts`\n- loader helpers: `packages/natives/native/loader-state.js`\n- embedded manifest: `packages/natives/native/embedded-addon.js`\n\nConsumers import directly from `@gajae-code/natives`. The generated declarations are produced during `bun --cwd=packages/natives run build`.\n\n## Anatomy of a native export\n\n**Rust side:**\n\n- Implementation lives in `crates/pi-natives/src/<module>.rs`.\n- If you add a new module, register it in `crates/pi-natives/src/lib.rs`.\n- Export with `#[napi]`; snake_case exports are converted to camelCase automatically. Use explicit JS names only for true aliases/non-default names. Use `#[napi(object)]` for object-shaped structs.\n- For CPU-bound or blocking work, use `task::blocking(tag, cancel_token, work)`.\n- For async work that needs Tokio, use `task::future(env, tag, work)`.\n- Pass a `CancelToken` when the API exposes `timeoutMs` or `AbortSignal`, and call `heartbeat()` inside long loops.\n\n**Package/build side:**\n\n- `packages/natives/scripts/build-native.ts` runs napi-rs, installs the `.node` artifact, copies generated `index.js`/`index.d.ts`, and appends enum runtime exports.\n- `packages/natives/native/index.js` is the loader that chooses a candidate `.node` file and returns the loaded addon.\n- `packages/natives/package.json` exposes only the package root (`@gajae-code/natives`).\n\n**Consumer side:**\n\n- Update direct imports/callsites in `packages/coding-agent` or `packages/tui` when the new export replaces a JS implementation.\n- Keep higher-level policy in consumers unless it belongs in the native primitive itself.\n\n## Porting checklist\n\n1. **Add the Rust implementation**\n\n- Put the core logic in a plain Rust function.\n- If it is a new module, add it to `crates/pi-natives/src/lib.rs`.\n- Expose it with `#[napi]` so the default snake_case -> camelCase mapping stays consistent.\n- Keep signatures owned and simple: `String`, `Vec<String>`, `Uint8Array`, `Either<JsString, Uint8Array>`, or `#[napi(object)]` structs.\n- For CPU-bound or blocking work, use `task::blocking`; for async work, use `task::future`.\n- If exposing cancellation, include `timeout_ms: Option<u32>` and `signal: Option<Unknown<'env>>` in options, create `CancelToken::new(...)`, and heartbeat in long loops.\n\n2. **Build generated bindings**\n\n- Run `bun --cwd=packages/natives run build`.\n- Confirm the generated `packages/natives/native/index.d.ts` includes the new export with the intended JS name/signature.\n- Confirm `packages/natives/native/index.js` still has generated enum exports appended when enum changes are involved.\n\n3. **Update consumers**\n\n- Import the new export directly from `@gajae-code/natives`.\n- Replace only callsites where the native implementation is faster/equivalent and preserves behavior.\n- Remove obsolete JS implementation code in the same change when the native path becomes canonical.\n\n4. **Add benchmarks**\n\n- Put benchmarks next to the owning package (`packages/tui/bench`, `packages/natives/bench`, or `packages/coding-agent/bench`).\n- Include a JS baseline and native version in the same run.\n- Use `Bun.nanoseconds()` and a fixed iteration count.\n- Keep benchmark inputs realistic for the hot path.\n\n5. **Run focused verification**\n\n- Build the native package.\n- Run the benchmark.\n- Run the narrow tests or scenario covering the changed export/callsites.\n\n## Pain points and how to avoid them\n\n### 1) Stale platform/variant artifacts\n\nThe loader probes platform-tagged artifacts in deterministic order. For x64, selected variant candidates are tried before the unsuffixed default fallback:\n\n- `modern`: `pi_natives.<tag>-modern.node`, then `...-baseline.node`, then `pi_natives.<tag>.node`.\n- `baseline`: `pi_natives.<tag>-baseline.node`, then `pi_natives.<tag>.node`.\n\nNon-x64 uses `pi_natives.<tag>.node`.\n\nCompiled binaries also probe `<getNativesDir()>/<version>/...` and a legacy user-data directory before package/executable locations. If any earlier candidate is stale, a new export may appear missing.\n\n**Fix:** remove stale candidate/cache files and rebuild.\n\n```bash\nrm packages/natives/native/pi_natives.<platform>-<arch>.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-modern.node\nrm packages/natives/native/pi_natives.<platform>-<arch>-baseline.node\nbun --cwd=packages/natives run build\n```\n\nFor compiled binaries, delete the versioned addon cache shown in the loader error (normally under `~/.gjc/natives/<version>` unless `$XDG_DATA_HOME/gjc` is used).\n\n### 2) Generated types do not match loaded binary\n\nThis can happen when `native/index.d.ts` was regenerated but the `.node` file being loaded is stale or from a different platform/variant.\n\nVerify the loaded export set from the actual candidate path:\n\n```bash\nbun -e 'const tag = `${process.platform}-${process.arch}`; const mod = require(`./packages/natives/native/pi_natives.${tag}.node`); console.log(Object.keys(mod).sort())'\n```\n\nFix the build/candidate mismatch. Do not paper over it with optional consumer checks if the export is required.\n\n### 3) Rust signature mismatch\n\nKeep N-API signatures simple and owned. Avoid borrowed references like `&str` in public exports. If you need structured data, use `#[napi(object)]` structs. If you need callbacks, use napi-rs `ThreadsafeFunction` and keep callback error/value behavior explicit.\n\n### 4) Enum runtime exports\n\nnapi-rs declarations alone are not enough for JS callers that use enum objects at runtime. `scripts/gen-enums.ts` appends enum objects to `native/index.js`. If you add or change a native enum, verify both `native/index.d.ts` and the generated enum export block in `native/index.js`.\n\n### 5) Benchmarking mistakes\n\n- Do not compare different inputs or allocations.\n- Keep JS and native using identical input arrays.\n- Run both in the same benchmark file to avoid skew.\n- Include enough iterations to smooth startup noise, but keep inputs realistic.\n\n## Benchmark template\n\n```ts\nconst ITERATIONS = 2000;\n\nfunction bench(name: string, fn: () => void): number {\n  const start = Bun.nanoseconds();\n  for (let i = 0; i < ITERATIONS; i++) fn();\n  const elapsed = (Bun.nanoseconds() - start) / 1e6;\n  console.log(\n    `${name}: ${elapsed.toFixed(2)}ms total (${(elapsed / ITERATIONS).toFixed(6)}ms/op)`,\n  );\n  return elapsed;\n}\n\nbench(\"feature/js\", () => {\n  jsImpl(sample);\n});\n\nbench(\"feature/native\", () => {\n  nativeImpl(sample);\n});\n```\n\n## Verification checklist\n\n- Generated `native/index.d.ts` includes the new export and intended TS signature.\n- The loaded `.node` file's `Object.keys(require(candidate))` includes the new export.\n- Runtime enum objects are present when the change adds/changes enums.\n- Bench numbers are recorded in the PR/notes.\n- Call sites are updated only if native is faster/equal and behavior-compatible.\n- Obsolete JS code is removed when the native implementation becomes canonical.\n\n## Rule of thumb\n\n- If native is slower, do not switch callsites. Keep or remove the export based on whether it has a near-term owner.\n- If native is faster and behavior-compatible, switch callsites and keep a benchmark to catch regressions.\n",
 	"provider-streaming-internals.md": "# Provider streaming internals\n\nThis document explains how token/tool streaming is normalized in `@gajae-code/ai`, then propagated through `@gajae-code/agent-core` and `coding-agent` session events.\n\n## End-to-end flow\n\n1. `streamSimple()` (`packages/ai/src/stream.ts`) maps generic options and dispatches to a provider stream function.\n2. Provider stream functions translate provider-native stream events into the unified `AssistantMessageEvent` sequence. Current built-ins include Anthropic, OpenAI Responses/Completions/OpenAI code/Azure Responses, Google Gemini/Gemini CLI/Vertex, Bedrock Converse, Ollama, Cursorand GitLab Duo/Kimi wrappers.\n3. Each provider pushes events into `AssistantMessageEventStream` (`packages/ai/src/utils/event-stream.ts`), which throttles delta events and exposes:\n   - async iteration for incremental updates\n   - `result()` for final `AssistantMessage`\n4. `agentLoop` (`packages/agent/src/agent-loop.ts`) consumes those events, mutates in-flight assistant state, and emits `message_update` events carrying the raw `assistantMessageEvent`.\n5. `AgentSession` (`packages/coding-agent/src/session/agent-session.ts`) subscribes to agent events, persists messages, and applies session behaviors (retry, compaction, TTSR, streaming-edit abort checks).\n\n## Unified stream contract in `@gajae-code/ai`\n\nAll providers emit the same shape (`AssistantMessageEvent` in `packages/ai/src/types.ts`):\n\n- `start`\n- content block lifecycle triplets:\n  - text: `text_start` → `text_delta`\\* → `text_end`\n  - thinking: `thinking_start` → `thinking_delta`\\* → `thinking_end`\n  - tool call: `toolcall_start` → `toolcall_delta`\\* → `toolcall_end`\n- terminal event:\n  - `done` with `reason: \"stop\" | \"length\" | \"toolUse\"`\n  - or `error` with `reason: \"aborted\" | \"error\"`\n\n`AssistantMessageEventStream` guarantees:\n\n- final result is resolved by terminal event (`done` or `error`)\n- deltas are batched/throttled (~50ms)\n- buffered deltas are flushed before non-delta events and before completion\n\n## Delta throttling and harmonization behavior\n\n`AssistantMessageEventStream` treats `text_delta`, `thinking_delta`, and `toolcall_delta` as mergeable events:\n\n- buffered deltas are merged only when **type + contentIndex** match\n- merge keeps the latest `partial` snapshot\n- non-delta events force immediate flush\n\nThis smooths high-frequency provider streams for TUI/event consumers, but is not provider backpressure: providers still produce at full speed, while the local stream buffers.\n\n## Provider normalization details\n\n## Anthropic (`anthropic-messages`)\n\nSource: `packages/ai/src/providers/anthropic.ts`\n\nNormalization points:\n\n- `message_start` initializes usage (input/output/cache tokens)\n- `content_block_start` maps to text/thinking/toolcall starts\n- `content_block_delta` maps:\n  - `text_delta` → `text_delta`\n  - `thinking_delta` → `thinking_delta`\n  - `input_json_delta` → `toolcall_delta`\n  - `signature_delta` updates `thinkingSignature` only (no event)\n- `content_block_stop` emits corresponding `*_end`\n- `message_delta.stop_reason` maps via `mapStopReason()`\n\nTool-call argument streaming:\n\n- each tool block carries internal `partialJson`\n- every JSON delta appends to `partialJson`\n- `arguments` are reparsed on each delta via `parseStreamingJson()`\n- `toolcall_end` reparses once more, then strips `partialJson`\n\n## OpenAI Responses family (`openai-responses`, `openai-code-responses`, `azure-openai-responses`)\n\nSources: `packages/ai/src/providers/openai-responses.ts`, `openai-code-responses.ts`, and `azure-openai-responses.ts`\n\nNormalization points:\n\n- `response.output_item.added` starts reasoning/text/function-call blocks\n- reasoning summary events (`response.reasoning_summary_text.delta`) become `thinking_delta`\n- output/refusal deltas become `text_delta`\n- `response.function_call_arguments.delta` becomes `toolcall_delta`\n- `response.output_item.done` emits `thinking_end` / `text_end` / `toolcall_end`\n- `response.completed` maps status to stop reason and usage\n\nTool-call argument streaming:\n\n- same `partialJson` accumulation pattern as Anthropic\n- providers that send only `response.function_call_arguments.done` still populate final args\n- tool call IDs are normalized as `\"<call_id>|<item_id>\"`\n\n## Google Generative AI (`google-generative-ai`)\n\nSource: `packages/ai/src/providers/google.ts`\n\nNormalization points:\n\n- iterates `candidate.content.parts`\n- text parts are split into thinking vs text by `isThinkingPart(part)`\n- block transitions close previous block before starting a new one\n- `part.functionCall` is treated as a complete tool call (start/delta/end emitted immediately)\n- finish reason mapped by `mapStopReason()` from `google-shared.ts`\n\nTool-call argument streaming:\n\n- function call args arrive as structured object, not incremental JSON text\n- implementation emits one synthetic `toolcall_delta` containing `JSON.stringify(arguments)`\n- no partial JSON parser needed for Google in this path\n\n## Partial tool-call JSON accumulation and recovery\n\nShared behavior for Anthropic/OpenAI Responses uses `parseStreamingJson()` (`packages/ai/src/utils/json-parse.ts`):\n\n1. try `JSON.parse`\n2. fallback to `partial-json` parser for incomplete fragments\n3. if both fail, return `{}`\n\nImplications:\n\n- malformed or truncated argument deltas do not crash stream processing immediately\n- in-progress `arguments` may temporarily be `{}`\n- later valid deltas can recover structured arguments because parsing is retried on every append\n- final `toolcall_end` performs one more parse attempt before emission\n\n## Stop reasons vs transport/runtime errors\n\nProvider stop reasons are mapped to normalized `stopReason`:\n\n- Anthropic: `end_turn`→`stop`, `max_tokens`→`length`, `tool_use`→`toolUse`, safety/refusal cases→`error`\n- OpenAI Responses: `completed`→`stop`, `incomplete`→`length`, `failed/cancelled`→`error`\n- Google: `STOP`→`stop`, `MAX_TOKENS`→`length`, safety/prohibited/malformed-function-call classes→`error`\n\nError semantics are split in two stages:\n\n1. **Model completion semantics** (provider reported finish reason/status)\n2. **Transport/runtime failure** (network/client/parser/abort exceptions)\n\nIf provider stream throws or signals failure, each provider wrapper catches and emits terminal `error` event with:\n\n- `stopReason = \"aborted\"` when abort signal is set\n- otherwise `stopReason = \"error\"`\n- `errorMessage = formatErrorMessageWithRetryAfter(error)`\n\n## Malformed chunk / SSE parse failure behavior\n\nFor these provider paths, chunk/SSE framing is handled by vendor SDK streams (Anthropic SDK, OpenAI SDK, Google SDK). This code does not implement a custom SSE decoder here.\n\nObserved behavior in current implementation:\n\n- malformed chunk/SSE parsing at SDK level surfaces as an exception or stream `error` event\n- provider wrapper converts that into unified terminal `error` event\n- no provider-specific resume/retry inside the stream function itself\n- higher-level retries are handled in `AgentSession` auto-retry logic (message-level retry, not stream-chunk replay)\n\n## Cancellation boundaries\n\nCancellation is layered:\n\n- AI provider request: `options.signal` is passed into provider client stream call.\n- Provider wrapper: after stream loop, aborted signal forces error path (`\"Request was aborted\"`).\n- Agent loop: checks `signal.aborted` before handling each provider event and can synthesize an aborted assistant message from the latest partial.\n- Session/agent controls: `AgentSession.abort()` -> `agent.abort()` -> shared abort controller cancellation.\n\nTool execution cancellation is separate from model stream cancellation:\n\n- tool runners use `AbortSignal.any([agentSignal, steeringAbortSignal])`\n- steering interrupts can abort remaining tool execution while preserving already-produced tool results\n\n## Backpressure boundaries\n\nThere is no hard backpressure mechanism between provider SDK stream and downstream consumers:\n\n- `EventStream` uses in-memory queues with no max size\n- throttling reduces UI update rate but does not slow provider intake\n- if consumers lag significantly, queued events can grow until completion\n\nCurrent design favors responsiveness and simple ordering over bounded-buffer flow control.\n\n## How stream events surface as agent/session events\n\n`agentLoop.streamAssistantResponse()` bridges `AssistantMessageEvent` to `AgentEvent`:\n\n- on `start`: pushes placeholder assistant message and emits `message_start`\n- on block events (`text_*`, `thinking_*`, `toolcall_*`): updates last assistant message, emits `message_update` with raw `assistantMessageEvent`\n- on terminal (`done`/`error`): resolves final message from `response.result()`, emits `message_end`\n\n`AgentSession` then consumes those events for session-level behaviors:\n\n- TTSR watches `message_update.assistantMessageEvent` for `text_delta`, `thinking_delta`, and `toolcall_delta`\n- streaming edit guard inspects `toolcall_delta`/`toolcall_end` on `edit` calls and can abort early\n- persistence writes finalized messages at `message_end`\n- auto-retry examines assistant `stopReason === \"error\"` plus `errorMessage` heuristics\n\n## Unified vs provider-specific responsibilities\n\nUnified (common contract):\n\n- event shape (`AssistantMessageEvent`)\n- final result extraction (`done`/`error`)\n- delta throttling + merge rules\n- agent/session event propagation model\n\nProvider-specific (not fully abstracted):\n\n- upstream event taxonomies and mapping logic\n- stop-reason translation tables\n- tool-call ID conventions\n- reasoning/thinking block semantics and signatures\n- usage token semantics and availability timing\n- message conversion constraints per API\n\n## Implementation files\n\n- [`../../ai/src/stream.ts`](../packages/ai/src/stream.ts) — provider dispatch, option mapping, API key/session plumbing, custom API dispatch, and provider-specific credential handling.\n- [`../../ai/src/utils/event-stream.ts`](../packages/ai/src/utils/event-stream.ts) — generic stream queue + assistant delta throttling.\n- [`../../ai/src/utils/json-parse.ts`](../packages/ai/src/utils/json-parse.ts) — partial JSON parsing for streamed tool arguments.\n- [`../../ai/src/providers/anthropic.ts`](../packages/ai/src/providers/anthropic.ts) — Anthropic event translation and tool JSON delta accumulation.\n- [`../../ai/src/providers/openai-responses.ts`](../packages/ai/src/providers/openai-responses.ts), [`openai-code-responses.ts`](../packages/ai/src/providers/openai-code-responses.ts), [`azure-openai-responses.ts`](../packages/ai/src/providers/azure-openai-responses.ts) — Responses-family event translation and status mapping.\n- [`../../ai/src/providers/google.ts`](../packages/ai/src/providers/google.ts), [`google-gemini-cli.ts`](../packages/ai/src/providers/google-gemini-cli.ts), [`google-vertex.ts`](../packages/ai/src/providers/google-vertex.ts) — Gemini stream chunk-to-block translation variants.\n- [`../../ai/src/providers/google-shared.ts`](../packages/ai/src/providers/google-shared.ts) — Gemini finish-reason mapping and shared conversion rules.\n- [`../../ai/src/providers/amazon-bedrock.ts`](../packages/ai/src/providers/amazon-bedrock.ts), [`openai-completions.ts`](../packages/ai/src/providers/openai-completions.ts), [`ollama.ts`](../packages/ai/src/providers/ollama.ts), [`cursor.ts`](../packages/ai/src/providers/cursor.ts) — additional built-in stream adapters using the same event contract.\n- [`../../agent/src/agent-loop.ts`](../packages/agent/src/agent-loop.ts) — provider stream consumption and `message_update` bridging.\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts) — session-level handling of streaming updates, abort, retry, and persistence.\n",
@@ -44,7 +46,7 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"session-switching-and-recent-listing.md": "# Session switching and recent session listing\n\nThis document describes how coding-agent discovers recent sessions, resolves `--resume` targets, presents session pickers, and switches the active runtime session.\n\nIt focuses on current implementation behavior, including fallback paths and caveats.\n\n## Implementation files\n\n- [`../src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts)\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`../src/cli/session-picker.ts`](../packages/coding-agent/src/cli/session-picker.ts)\n- [`../src/modes/components/session-selector.ts`](../packages/coding-agent/src/modes/components/session-selector.ts)\n- [`../src/modes/controllers/selector-controller.ts`](../packages/coding-agent/src/modes/controllers/selector-controller.ts)\n- [`../src/main.ts`](../packages/coding-agent/src/main.ts)\n- [`../src/sdk.ts`](../packages/coding-agent/src/sdk.ts)\n- [`../src/modes/interactive-mode.ts`](../packages/coding-agent/src/modes/interactive-mode.ts)\n- [`../src/modes/utils/ui-helpers.ts`](../packages/coding-agent/src/modes/utils/ui-helpers.ts)\n\n## Recent-session discovery\n\n### Directory scope\n\n`SessionManager` stores sessions under a cwd-scoped directory by default:\n\n- `~/.gjc/agent/sessions/--<cwd-encoded>--/*.jsonl`\n\n`SessionManager.list(cwd, sessionDir?)` reads only that directory unless an explicit `sessionDir` is provided.\n\n### Two listing paths with different payloads\n\nThere are two different listing pipelines:\n\n1. `getRecentSessions(sessionDir, limit)` (welcome/summary view)\n   - Reads only a 4KB prefix (`readTextPrefix(..., 4096)`) from each file.\n   - Parses header + earliest user text preview.\n   - Returns lightweight `RecentSessionInfo` with lazy `name` and `timeAgo` getters.\n   - Sorts by file `mtime` descending.\n\n2. `SessionManager.list(...)` / `SessionManager.listAll()` (resume pickers and ID matching)\n   - Reads full session files.\n   - Builds `SessionInfo` objects (`id`, `cwd`, `title`, `messageCount`, `firstMessage`, `allMessagesText`, timestamps).\n   - Drops sessions with zero `message` entries.\n   - Sorts by `modified` descending.\n\n### Metadata fallback behavior\n\nFor recent summaries (`RecentSessionInfo`):\n\n- display name preference: `header.title` -> first user prompt -> `header.id` -> filename\n- name is truncated to 40 chars for compact displays\n- control characters/newlines are stripped/sanitized from title-derived names\n\nFor `SessionInfo` list entries:\n\n- `title` is `header.title` or latest compaction `shortSummary`\n- `firstMessage` is first user message text or `\"(no messages)\"`\n\n## `--continue` resolution and terminal breadcrumb preference\n\n`SessionManager.continueRecent(cwd, sessionDir?)` resolves the target in this order:\n\n1. Read terminal-scoped breadcrumb (`~/.gjc/agent/terminal-sessions/<terminal-id>`)\n2. Validate breadcrumb:\n   - current terminal can be identified\n   - breadcrumb cwd matches current cwd (resolved path compare)\n   - referenced file still exists\n3. If breadcrumb is invalid/missing, fall back to newest file by mtime in the session dir (`findMostRecentSession`)\n4. If none found, create a new session\n\nTerminal ID derivation prefers TTY path and falls back to env-based identifiers (`KITTY_WINDOW_ID`, `TMUX_PANE`, `TERM_SESSION_ID`, `WT_SESSION`).\n\nBreadcrumb writes are best-effort and non-fatal.\n\n## Startup-time resume target resolution (`main.ts`)\n\n### `--resume <value>`\n\n`createSessionManager(...)` handles string-valued `--resume` in two modes:\n\n1. Path-like value (contains `/`, `\\\\`, or ends with `.jsonl`)\n   - direct `SessionManager.open(sessionArg, parsed.sessionDir)`\n\n2. ID prefix value\n   - find match in `SessionManager.list(cwd, sessionDir)` by `id.startsWith(sessionArg)`\n   - if no local match and `sessionDir` is not forced, try `SessionManager.listAll()`\n   - first match is used (no ambiguity prompt)\n\nCross-project match behavior:\n\n- if matched session cwd differs from current cwd, CLI prompts whether to fork into current project\n- yes -> `SessionManager.forkFrom(...)`\n- no -> throws error (`Session \"...\" is in another project (...)`)\n\nNo match -> throws error (`Session \"...\" not found.`).\n\n### `--resume` (no value)\n\nHandled after initial session-manager construction:\n\n1. list local sessions with `SessionManager.list(cwd, parsed.sessionDir)`\n2. if empty: print `No sessions found` and exit early\n3. open TUI picker (`selectSession`)\n4. if canceled: print `No session selected` and exit early\n5. if selected: `SessionManager.open(selectedPath)`\n\n### `--continue`\n\nUses `SessionManager.continueRecent(...)` directly (breadcrumb-first behavior above).\n\n## Picker-based selection internals\n\n## CLI picker (`src/cli/session-picker.ts`)\n\n`selectSession(sessions)` creates a standalone TUI with `SessionSelectorComponent` and resolves exactly once:\n\n- selection -> resolves selected path\n- cancel (Esc) -> resolves `null`\n- hard exit (Ctrl+C path) -> stops TUI and `process.exit(0)`\n\n## Interactive in-session picker (`SelectorController.showSessionSelector`)\n\nFlow:\n\n1. fetch sessions from current session dir via `SessionManager.list(currentCwd, currentSessionDir)`\n2. mount `SessionSelectorComponent` in editor area using `showSelector(...)`\n3. callbacks:\n   - select -> close selector and call `handleResumeSession(sessionPath)`\n   - cancel -> restore editor and rerender\n   - exit -> `ctx.shutdown()`\n\n## Session selector component behavior\n\n`SessionList` supports:\n\n- arrow/page navigation\n- Enter to select\n- Esc to cancel\n- Ctrl+C to exit\n- fuzzy search across session id/title/cwd/first message/all messages/path\n\nEmpty-list render behavior:\n\n- renders a message instead of crashing\n- Enter on empty does nothing (no callback)\n- Esc/Ctrl+C still work\n\nCaveat: UI text says `Press Tab to view all`, but this component currently has no Tab handler and current wiring only lists current-scope sessions.\n\n## Runtime switch execution (`AgentSession.switchSession`)\n\n`switchSession(sessionPath)` is the core in-process switch path.\n\nLifecycle/state transition:\n\n1. capture `previousSessionFile`\n2. emit `session_before_switch` hook event (`reason: \"resume\"`, cancellable)\n3. if canceled -> return `false` with no switch\n4. disconnect from current agent event stream\n5. abort active generation/tool flow\n6. clear queued steering/follow-up/next-turn message buffers\n7. flush session writer (`sessionManager.flush()`) to persist pending writes\n8. `sessionManager.setSessionFile(sessionPath)`\n   - updates session file pointer\n   - writes terminal breadcrumb\n   - loads entries / migrates / blob-resolves / reindexes\n   - if missing/invalid file data: initializes a new session at that path and rewrites header\n9. update `agent.sessionId`\n10. rebuild display context via `buildDisplaySessionContext()`\n11. restore persisted/discovered MCP tool selections and rebuild active tools/system prompt when discovery is enabled\n12. emit `session_switch` hook event (`reason: \"resume\"`, `previousSessionFile`)\n13. replace agent messages with rebuilt context and sync todos\n14. close provider sessions when switching to a different session or when same-session reload changed replay messages\n15. restore default model from `sessionContext.models.default` if available and present in model registry\n16. restore thinking level and service tier:\n    - thinking uses persisted `thinking_level_change`, otherwise the configured default clamped to model capability\n    - service tier uses persisted `service_tier_change`, otherwise the configured `serviceTier` setting (`\"none\"` becomes unset)\n17. reconnect agent listeners and return `true`\n\n## UI state rebuild after interactive switch\n\n`SelectorController.handleResumeSession` performs UI reset around `switchSession`:\n\n- stop loading animation\n- clear status container\n- clear pending-message UI and pending tool map\n- reset streaming component/message references\n- call `session.switchSession(...)`\n- clear chat container and rerender from session context (`renderInitialMessages`)\n- reload todos from new session artifacts\n- show `Resumed session`\n\nSo visible conversation/todo state is rebuilt from the new session file.\n\n## Startup resume vs in-session switch\n\n### Startup resume (`--continue`, `--resume`, direct open)\n\n- Session file is chosen before `createAgentSession(...)`.\n- `sdk.ts` builds `existingSession = sessionManager.buildSessionContext()`.\n- Agent messages are restored once during session creation.\n- Model/thinking are selected during creation (including restore/fallback logic).\n- Interactive mode then runs `#restoreModeFromSession()` to re-enter persisted mode state (currently plan/plan_paused).\n\n### In-session switch (`/resume`-style selector path)\n\n- Uses `AgentSession.switchSession(...)` on an already-running `AgentSession`.\n- Messages/model/thinking are rebuilt immediately in place.\n- Hook `session_before_switch`/`session_switch` events are emitted.\n- UI chat/todos are refreshed.\n- No dedicated post-switch mode restore call is made in selector flow; mode re-entry behavior is not symmetric with startup `#restoreModeFromSession()`.\n\n## Failure and edge-case behavior\n\n### Cancellation paths\n\n- CLI picker cancel -> returns `null`, caller prints `No session selected`, process exits early.\n- Interactive picker cancel -> editor restored, no session change.\n- Hook cancellation (`session_before_switch`) -> `switchSession()` returns `false`.\n\n### Empty list paths\n\n- CLI `--resume` (no value): empty list prints `No sessions found` and exits.\n- Interactive selector: empty list renders message and remains cancellable.\n\n### Missing/invalid target session file\n\nWhen opening/switching to a specific path (`setSessionFile`):\n\n- ENOENT -> treated as empty -> new session initialized at that exact path and persisted.\n- malformed/invalid header (or effectively unreadable parsed entries) -> treated as empty -> new session initialized and persisted.\n\nThis is recovery behavior, not hard failure.\n\n### Hard failures\n\nSwitch/open can still throw on true I/O failures (permission errors, rewrite failures, etc.), which propagate to callers.\n\n### ID prefix matching caveats\n\n- ID matching uses `startsWith` and takes first match in sorted list.\n- No ambiguity UI if multiple sessions share prefix.\n- `SessionManager.list(...)` excludes sessions with zero messages, so those sessions are not resumable via ID match/list picker.\n",
 	"session-tree-plan.md": "# Session tree architecture (current)\n\nReference: [session.md](../docs/session.md)\n\nThis document describes how session tree navigation works today: in-memory tree model, leaf movement rules, branching behavior, and extension/event integration.\n\n## What this subsystem is\n\nThe session is stored as an append-only entry log, but runtime behavior is tree-based:\n\n- Every non-header entry has `id` and `parentId`.\n- The active position is `leafId` in `SessionManager`.\n- Appending an entry always creates a child of the current leaf.\n- Branching does **not** rewrite history; it only changes where the leaf points before the next append.\n\nKey files:\n\n- `src/session/session-manager.ts` — tree data model, traversal, leaf movement, branch/session extraction\n- `src/session/agent-session.ts` — `/tree` navigation flow, summarization, hook/event emission\n- `src/modes/components/tree-selector.ts` — interactive tree UI behavior and filtering\n- `src/modes/controllers/selector-controller.ts` — selector orchestration for `/tree` and `/branch`\n- `src/modes/controllers/input-controller.ts` — command routing (`/tree`, `/branch`, double-escape behavior)\n- `src/session/messages.ts` — conversion of `branch_summary`, `compaction`, and `custom_message` entries into LLM context messages\n\n## Tree data model in `SessionManager`\n\nRuntime indices:\n\n- `#byId: Map<string, SessionEntry>` — fast lookup for any entry\n- `#leafId: string | null` — current position in the tree\n- `#labelsById: Map<string, string>` — resolved labels by target entry id\n\nTree APIs:\n\n- `getBranch(fromId?)` walks parent links to root and returns root→node path\n- `getTree()` returns `SessionTreeNode[]` (`entry`, `children`, `label`)\n  - parent links become children arrays\n  - entries with missing parents are treated as roots\n  - children are sorted oldest→newest by timestamp\n- `getChildren(parentId)` returns direct children\n- `getLabel(id)` resolves current label from `labelsById`\n\n`getTree()` is a runtime projection; persistence remains append-only JSONL entries.\n\n## Leaf movement semantics\n\nThere are three leaf movement primitives:\n\n1. `branch(entryId)`\n   - Validates entry exists\n   - Sets `leafId = entryId`\n   - No new entry is written\n\n2. `resetLeaf()`\n   - Sets `leafId = null`\n   - Next append creates a new root entry (`parentId = null`)\n\n3. `branchWithSummary(branchFromId, summary, details?, fromExtension?)`\n   - Accepts `branchFromId: string | null`\n   - Sets `leafId = branchFromId`\n   - Appends a `branch_summary` entry as child of that leaf\n   - When `branchFromId` is `null`, `fromId` is persisted as `\"root\"`\n\n## `/tree` navigation behavior (same session file)\n\n`AgentSession.navigateTree()` is navigation, not file forking.\n\nFlow:\n\n1. Validate target and compute abandoned path (`collectEntriesForBranchSummary`)\n2. Emit `session_before_tree` with `TreePreparation`\n3. Optionally summarize abandoned entries (hook-provided summary or built-in summarizer)\n4. Compute new leaf target:\n   - selecting a **user** message: leaf moves to its parent, and message text is returned for editor prefill\n   - selecting a **custom_message**: same rule as user message (leaf = parent, text prefills editor)\n   - selecting any other entry: leaf = selected entry id\n5. Apply leaf move:\n   - with summary: `branchWithSummary(newLeafId, ...)`\n   - without summary and `newLeafId === null`: `resetLeaf()`\n   - otherwise: `branch(newLeafId)`\n6. Rebuild agent context from new leaf and emit `session_tree`\n\nImportant: summary entries are attached at the **new navigation position**, not on the abandoned branch tail.\n\n## `/branch` behavior (new session file)\n\n`/branch` and `/tree` are intentionally different:\n\n- `/tree` navigates within the current session file.\n- `/branch` creates a new session branch file (or in-memory replacement for non-persistent mode).\n\nUser-facing `/branch` flow (`SelectorController.showUserMessageSelector` → `AgentSession.branch`):\n\n- Branch source must be a **user message**.\n- Selected user text is extracted for editor prefill.\n- If selected user message is root (`parentId === null`): start a new session via `newSession({ parentSession: previousSessionFile })`.\n- Otherwise: `createBranchedSession(selectedEntry.parentId)` to fork history up to the selected prompt boundary.\n\n`SessionManager.createBranchedSession(leafId)` specifics:\n\n- Builds root→leaf path via `getBranch(leafId)`; throws if missing.\n- Excludes existing `label` entries from copied path.\n- Rebuilds fresh label entries from resolved `labelsById` for entries that remain in path.\n- Persistent mode: writes new JSONL file and switches manager to it; returns new file path.\n- In-memory mode: replaces in-memory entries; returns `undefined`.\n\n## Context reconstruction and summary/custom integration\n\n`buildSessionContext()` (in `session-manager.ts`) resolves the active root→leaf path and builds effective LLM context state:\n\n- Tracks latest thinking/model/service-tier/mode/TTSR/MCP-selection state on path.\n- Handles latest compaction on path:\n  - emits compaction summary first\n  - replays kept messages from `firstKeptEntryId` to compaction point\n  - then replays post-compaction messages\n- Includes `branch_summary` and `custom_message` entries as `AgentMessage` objects.\n\n`session/messages.ts` then maps these message types for model input:\n\n- `branchSummary` and `compactionSummary` become user-role templated context messages\n- `custom`/`hookMessage` become user-role content messages\n\nSo tree movement changes context by changing the active leaf path, not by mutating old entries.\n\n## Labels and tree UI behavior\n\nLabel persistence:\n\n- `appendLabelChange(targetId, label?)` writes `label` entries on the current leaf chain.\n- `labelsById` is updated immediately (set or delete).\n- `getTree()` resolves current label onto each returned node.\n\nTree selector behavior (`tree-selector.ts`):\n\n- Flattens tree for navigation, keeps active-path highlighting, and prioritizes displaying the active branch first.\n- Supports filter modes: `default`, `no-tools`, `user-only`, `labeled-only`, `all`.\n- Supports free-text search over rendered semantic content.\n- `Shift+L` opens inline label editing and writes via `appendLabelChange`.\n\nCommand routing:\n\n- `/tree` always opens tree selector.\n- `/branch` opens user-message selector unless `doubleEscapeAction=tree`, in which case it also uses tree selector UX.\n\n## Extension and hook touchpoints for tree operations\n\nCommand-time extension API (`ExtensionCommandContext`):\n\n- `branch(entryId)` — create branched session file\n- `navigateTree(targetId, { summarize? })` — move within current tree/file\n\nEvents around tree navigation:\n\n- `session_before_tree`\n  - receives `TreePreparation`:\n    - `targetId`\n    - `oldLeafId`\n    - `commonAncestorId`\n    - `entriesToSummarize`\n    - `userWantsSummary`\n  - may cancel navigation\n  - may provide summary payload used instead of built-in summarizer\n  - receives abort `signal` (Escape cancellation path)\n- `session_tree`\n  - emits `newLeafId`, `oldLeafId`\n  - includes `summaryEntry` when a summary was created\n  - `fromExtension` indicates summary origin\n\nAdjacent but related lifecycle hooks:\n\n- `session_before_branch` / `session_branch` for `/branch` flow\n- `session_before_compact`, `session.compacting`, `session_compact` for compaction entries that later affect tree-context reconstruction\n\n## Real constraints and edge conditions\n\n- `branch()` cannot target `null`; use `resetLeaf()` for root-before-first-entry state.\n- `branchWithSummary()` supports `null` target and records `fromId: \"root\"`.\n- Selecting current leaf in tree selector is a no-op.\n- Summarization requires an active model; if absent, summarize navigation fails fast.\n- If summarization is aborted, navigation is cancelled and leaf is unchanged.\n- In-memory sessions never return a branch file path from `createBranchedSession`.\n- Tree context reconstruction includes service-tier and MCP tool-selection state, but those entries do not become LLM messages.\n\n## Plan approval session naming\n\nWhen a user approves a plan from plan mode (`InteractiveMode.#approvePlan`), the approval handler seeds the session name from the plan's title so the resulting (fresh or compacted) session does not stay unnamed.\n\nTrigger:\n\n- Plan approval reaches `#approvePlan(...)` with `options.title` populated from the plan-approval details.\n- This runs for every approval choice (`Approve and execute`, `Approve and compact context`, plain `Approve`); the synthetic `plan-approved` prompt is what otherwise bypasses the input-controller's title-generation path.\n\nNaming source:\n\n- The normalized plan title is humanized via `humanizePlanTitle(title)` (`packages/coding-agent/src/plan-mode/approved-plan.ts`):\n  - replaces runs of `-`/`_` with a single space\n  - trims whitespace\n  - capitalizes the first character\n  - returns `\"\"` for whitespace-only / separator-only input\n- The humanized name is applied with `sessionManager.setSessionName(name, \"auto\")`. Because `setSessionName` is a no-op when `titleSource === \"user\"`, the seeded name never overrides a name the user already chose (e.g. on the `preserveContext` path where the session continues with prior naming).\n- On successful apply, the terminal title (`setSessionTerminalTitle`) and the editor border color are refreshed to reflect the new name.\n\nExamples (from `humanizePlanTitle`):\n\n- `migrate-mcp-loader` → `Migrate mcp loader`\n- `fix_session_naming` → `Fix session naming`\n- `foo--bar__baz` → `Foo bar baz`\n- `RefactorRouter` → `RefactorRouter` (no separators to expand)\n- `\"\"` / `\"---\"` → `\"\"` (no name applied)\n\n## Legacy compatibility still present\n\nSession migrations still run on load:\n\n- v1→v2 adds `id`/`parentId` and converts compaction index anchor to id anchor\n- v2→v3 migrates legacy `hookMessage` role to `custom`\n\nCurrent runtime behavior is version-3 tree semantics after migration.\n",
 	"session.md": "# Session Storage and Entry Model\n\nThis document is the source of truth for how coding-agent sessions are represented, persisted, migrated, and reconstructed at runtime.\n\n## Scope\n\nCovers:\n\n- Session JSONL format and versioning\n- Entry taxonomy and tree semantics (`id`/`parentId` + leaf pointer)\n- Migration/compatibility behavior when loading old or malformed files\n- Context reconstruction (`buildSessionContext`)\n- Persistence guarantees, failure behavior, truncation/blob externalization\n- Storage abstractions (`FileSessionStorage`, `MemorySessionStorage`) and related utilities\n\nDoes not cover `/tree` UI rendering behavior beyond semantics that affect session data.\n\n## Implementation Files\n\n- [`src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts)\n- [`src/session/messages.ts`](../packages/coding-agent/src/session/messages.ts)\n- [`src/session/session-storage.ts`](../packages/coding-agent/src/session/session-storage.ts)\n- [`src/session/history-storage.ts`](../packages/coding-agent/src/session/history-storage.ts)\n- [`src/session/blob-store.ts`](../packages/coding-agent/src/session/blob-store.ts)\n\n## On-Disk Layout\n\nDefault session file location:\n\n```text\n~/.gjc/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~/.gjc/agent/blobs/<sha256>\n```\n\nTerminal breadcrumb files are written under:\n\n```text\n~/.gjc/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 `~/.gjc/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: `~/.gjc/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",
-	"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 (`@gajae-code/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 (`dark.json`, `light.json`, and all `defaults/*.json` compiled into `defaultThemes`, including the red-claw crustacean theme)\n2. custom theme file: `<customThemesDir>/<name>.json`\n\nCustom themes directory comes from `getCustomThemesDir()`:\n\n- default: `~/.gjc/agent/themes`\n- overridden by `GJC_CODING_AGENT_DIR` (`$GJC_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: `red-claw` is the default dark GJC theme, with red/orange brand tokens, separate semantic error/warning/diff-removal tokens, and crab-oriented symbol overrides.\n\nCurrent defaults from settings schema:\n\n- `theme.dark = \"red-claw\"`\n- `theme.light = \"light\"`\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\nSettings UI uses this for live preview and restores prior theme on cancel.\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: `~/.gjc/agent`\n- effective default file: `~/.gjc/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.\n\n## Creating a custom theme (practical)\n\n1. Create file in custom themes dir, e.g. `~/.gjc/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. For the bundled crustacean look, choose `red-claw`.\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 preview theme values (live `previewTheme`).\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",
+	"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 (`@gajae-code/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 (`dark.json`, `light.json`, and all `defaults/*.json` compiled into `defaultThemes`, including the red-claw crustacean theme)\n2. custom theme file: `<customThemesDir>/<name>.json`\n\nCustom themes directory comes from `getCustomThemesDir()`:\n\n- default: `~/.gjc/agent/themes`\n- overridden by `GJC_CODING_AGENT_DIR` (`$GJC_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: `red-claw` is the default dark GJC theme, with red/orange brand tokens, separate semantic error/warning/diff-removal tokens, and crab-oriented symbol overrides.\n\nCurrent defaults from settings schema:\n\n- `theme.dark = \"red-claw\"`\n- `theme.light = \"light\"`\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: `~/.gjc/agent`\n- effective default file: `~/.gjc/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.\n\n## Creating a custom theme (practical)\n\n1. Create file in custom themes dir, e.g. `~/.gjc/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. For the bundled crustacean look, choose `red-claw`.\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 `GJC_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: `GJC_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.",
 	"tools/ast-grep.md": "# ast_grep\n\n> Structural code search over supported source files via native ast-grep.\n\n## Source\n- Entry: `packages/coding-agent/src/tools/ast-grep.ts`\n- Model-facing prompt: `packages/coding-agent/src/prompts/tools/ast-grep.md`\n- Key collaborators:\n  - `crates/pi-natives/src/ast.rs` — native scan, parse, match engine\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/render-utils.ts` — parse-error dedupe and display caps\n  - `packages/coding-agent/src/tools/match-line-format.ts` — anchor-prefixed match rendering\n  - `packages/coding-agent/src/utils/file-display-mode.ts` — hashline vs line-number output mode\n  - `packages/natives/native/index.d.ts` — JS-visible native binding contract\n\n## Inputs\n\n| Field | Type | Required | Description |\n| --- | --- | --- | --- |\n| `pat` | `string` | Yes | Single AST pattern. The wrapper trims it and rejects empty strings. |\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| `skip` | `number` | No | Match offset. Defaults to `0`, then `Math.floor(...)`; negatives and non-finite values fail. |\n\nPattern grammar and language support exposed to the model:\n- `$NAME` — capture one AST node.\n- `$_` — match one AST node without binding.\n- `$$$NAME` — capture zero or more AST nodes; ast-grep stops lazily at the next satisfiable node.\n- `$$$` — match zero or more AST nodes without binding.\n- Metavariable names must be uppercase and must stand for whole AST nodes, not partial tokens or string fragments.\n- Reusing the same metavariable requires identical code at each occurrence.\n- Patterns must parse as one valid AST node for the inferred target language.\n- Supported canonical languages come from `SupportLang::all_langs()` in `crates/pi-natives/src/language/mod.rs`: `astro`, `bash`, `c`, `cmake`, `cpp`, `csharp`, `dart`, `clojure`, `css`, `diff`, `dockerfile`, `elixir`, `erlang`, `go`, `graphql`, `haskell`, `hcl`, `html`, `ini`, `java`, `javascript`, `json`, `just`, `julia`, `kotlin`, `lua`, `make`, `markdown`, `nix`, `objc`, `ocaml`, `odin`, `perl`, `php`, `powershell`, `protobuf`, `python`, `r`, `regex`, `ruby`, `rust`, `scala`, `solidity`, `sql`, `starlark`, `svelte`, `swift`, `toml`, `tlaplus`, `tsx`, `typescript`, `verilog`, `vue`, `xml`, `yaml`, `zig`.\n\n## Outputs\n- Single-shot tool result.\n- Model-facing `content` is one text block:\n  - grouped by file for directory/multi-file searches,\n  - match lines rendered as `*LINE+HASH|text` in hashline mode or `*LINE|text` otherwise,\n  - continuation lines for multi-line matches rendered with a leading space,\n  - optional `meta: NAME=value` lines when ast-grep captured metavariables.\n- If no matches are found, text is `No matches found` or `No matches found. Parse issues mean the query may be mis-scoped; narrow paths before concluding absence.` plus formatted parse issues.\n- If the wrapper truncates visible results, the text ends with `Result limit reached; narrow paths or increase limit.`\n- `details` includes counts and metadata, not full match payloads:\n  - `matchCount`, `fileCount`, `filesSearched`, `limitReached`\n  - optional `parseErrors`, `scopePath`, `files`, `fileMatches`, `displayContent`, `meta`\n- Native ranges (`byteStart`, `byteEnd`, `startLine`, `startColumn`, `endLine`, `endColumn`) exist only inside the native result; the wrapper does not emit them directly to the model.\n\n## Flow\n1. `AstGrepTool.execute()` validates `pat`, normalizes `skip`, and normalizes each `paths` entry in `packages/coding-agent/src/tools/ast-grep.ts`.\n2. Internal URLs are resolved through `session.internalRouter`; entries without `sourcePath` fail, and internal-URL globs fail early.\n3. For multiple path inputs, `partitionExistingPaths()` drops missing bases only when at least one surviving base remains; if all bases are missing the call fails.\n4. `parseSearchPath()` splits a single path into `basePath` plus optional `glob`. `resolveExplicitSearchPaths()` collapses multiple inputs into a common base plus a brace-union glob, or separate `targets` when the only common base is a filesystem root.\n5. The wrapper stats the resolved base path to decide whether output should be grouped as a directory result.\n6. Execution dispatches to either:\n   - one native `astGrep(...)` call for a single resolved base, or\n   - `runMultiTargetAstGrep(...)`, which calls the native binding once per target, rebases paths back to the common root, sorts globally, then applies `skip` and the wrapper limit.\n7. Native `ast_grep` in `crates/pi-natives/src/ast.rs`:\n   - normalizes and deduplicates patterns,\n   - resolves a `MatchStrictness` (`smart` by default),\n   - collects candidate files from a file or gitignore-aware directory scan,\n   - infers language per candidate from extension unless `lang` was provided,\n   - compiles the pattern separately for each language present,\n   - reads each file, reports syntax-error trees as parse issues, runs `find_all`, and optionally captures metavariable bindings.\n8. Native results are sorted by path and source position, then paged by `offset`/`limit`.\n9. The TS wrapper normalizes parse-error strings, deduplicates them, groups matches by formatted path, renders anchor lines, appends limit/parse notices, and returns `toolResult(...).text(...).done()`.\n\n## Modes / Variants\n- Single file: native path is the file; output is a flat list of rendered match lines.\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 can resolve them to a backing file path.\n- Hashline output mode vs plain line-number mode: controlled by `resolveFileDisplayMode()`; hashline mode requires the edit tool and non-raw, mutable sources.\n\n## Side Effects\n- Filesystem\n  - Stats input paths in the TS wrapper.\n  - Native code reads matched files and scans directories through `fs_cache`.\n- Session state (transcript, memory, jobs, checkpoints, registries)\n  - None beyond normal tool transcript/result metadata.\n- Background work / cancellation\n  - Native 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- Wrapper-visible result cap: `DEFAULT_AST_LIMIT = 50` in `packages/coding-agent/src/tools/ast-grep.ts`.\n  - Single-target calls rely on the native default limit of 50 in `crates/pi-natives/src/ast.rs`.\n  - Multi-target calls fetch `skip + 50 + 1` matches per target, then re-page after global sort.\n- Native `limit` is clamped to at least `1`; omitted `offset` defaults to `0` in `crates/pi-natives/src/ast.rs`.\n- Parse issues are rendered with at most `PARSE_ERRORS_LIMIT = 20` lines in `packages/coding-agent/src/tools/render-utils.ts`; `details.parseErrors` itself is only deduplicated, 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 hard file-count cap is applied by the wrapper or native `ast_grep`; candidate count is whatever the resolved path/glob expands to after gitignore filtering.\n- Multi-path union deduplicates identical path inputs before resolution in `resolveExplicitSearchPaths()`.\n\n## Errors\n- TS wrapper throws `ToolError` for empty patterns, invalid `skip`, empty path entries, unsupported internal-URL globs, internal URLs without `sourcePath`, and missing paths.\n- Native code returns hard errors for:\n  - unsupported explicit `lang`,\n  - inability to infer language for a candidate when `lang` is not supplied,\n  - invalid AST pattern compilation for every relevant language,\n  - unreadable search roots or bad glob compilation,\n  - cancellation (`Aborted: Signal`) or timeout (`Aborted: Timeout`).\n- File-level parse failures and many per-language pattern compile failures are non-fatal: they are accumulated in `parseErrors` and surfaced alongside successful matches.\n- `no matches` is not an error, even when parse issues were recorded.\n\n## Notes\n- `pat` is always wrapped into a one-element `patterns` array by the TS tool; the model cannot send multiple patterns through `ast_grep` even though the native binding supports it.\n- `ast_grep` can search mixed-language trees because native compilation happens per discovered language, but the prompt still tells the model to keep calls single-language when possible to reduce parse noise.\n- Pattern compilation is per language present in the candidate set. One pattern can succeed for some languages and generate per-file parse errors for others in the same run.\n- A file with tree-sitter error nodes still gets searched; the syntax warning is additive, not a skip condition.\n- For glob semantics, `*.ts` matches only direct children while `**/*.ts` recurses; this is covered by native tests in `crates/pi-natives/src/ast.rs`.\n- Output anchors are intended for follow-up tools, but the exact anchor format depends on session edit mode (`hashline` vs line-number mode).",