@gajae-code/coding-agent 0.2.0 → 0.2.2

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","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","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.",
@@ -12,13 +12,14 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"brand-assets.md": "# Brand assets\n\nGajae-Code uses the current GJC character and hero images in `assets/` for README and documentation surfaces.\n\n| Asset | Purpose |\n| --- | --- |\n| [`assets/hero.png`](../assets/hero.png) | Wide README/docs hero image for Gajae-Code. |\n| [`assets/character.png`](../assets/character.png) | Standalone Gajae-Code character mascot. |\n| [`assets/tool-image-fixture.webp`](../assets/tool-image-fixture.webp) | Minimal WebP fixture for terminal image rendering tests. Not a product brand asset. |\n\nThe old legacy demo artwork has been removed from the active asset set; new public surfaces should reference the Gajae-Code assets above.\n",
 	"codebase-overview.md": "# Codebase Overview\n\nThis document maps the main parts of the `gajae-code` repository. The root README stays intentionally small; this file is the architecture-oriented companion.\n\n## Product shape\n\nGajae-Code (`gjc`) is centered on `packages/coding-agent/`. The public workflow surface is intentionally fixed at four source-bundled skills and four public role subagents. Runtime state, specs, plans, goals, team state, and local overrides live under `.gjc/`.\n\nDefault workflow skills are embedded from:\n\n```text\npackages/coding-agent/src/defaults/gjc/skills/<name>/SKILL.md\n```\n\nPublic role subagent prompts are embedded from:\n\n```text\npackages/coding-agent/src/prompts/agents/<role>.md\n```\n\nThe runtime can still discover project/user overrides, but the bundled defaults are loaded from source so a missing project `.gjc` directory does not remove the default workflow surface.\n\n## Packages\n\n### `packages/coding-agent/`\n\nMain `gjc` CLI and product runtime.\n\n- `packages/coding-agent/package.json` exposes the `gjc` binary at `src/cli.ts` and the SDK/barrel entrypoint at `src/index.ts`.\n- `packages/coding-agent/src/cli.ts` is the executable bootstrap. It registers CLI commands such as `setup`, `deep-interview`, `ralplan`, `ultragoal`, `team`, and the default launch path.\n- `packages/coding-agent/src/main.ts` adapts CLI options into session creation and dispatches interactive, print, RPC, RPC-UI, and ACP modes.\n- `packages/coding-agent/src/sdk.ts` assembles settings, model registry, auth, workspace/context discovery, skills, rules, tools, system prompt, and the underlying `@gajae-code/agent-core` agent.\n- `packages/coding-agent/src/tools/index.ts` is the built-in tool registry for file/code/runtime tools such as read, bash, edit, AST tools, eval, find/search, LSP, browser, task/subagent, recipe, IRC, todo, web search, write, and memory tools.\n- `packages/coding-agent/src/defaults/gjc-defaults.ts` embeds and installs the default workflow skills.\n- `packages/coding-agent/src/task/agents.ts` embeds bundled task-agent prompts. The public contract is `executor`, `architect`, `planner`, and `critic`; other bundled prompts are internal/runtime utilities.\n\n### `packages/ai/`\n\nProvider/model boundary for LLM access.\n\n- `packages/ai/src/index.ts` exports model registry/resolution, provider implementations, auth broker/gateway/storage, streaming, usage, retry/overflow utilities, OAuth, discovery, and validation helpers.\n- `packages/ai/src/types.ts` defines provider, model, context, message, tool, usage, reasoning, and stream-event contracts.\n- `packages/ai/src/stream.ts` dispatches model-driven streams to the right provider/API implementation and normalizes streaming events.\n- `packages/ai/src/model-manager.ts` merges static, cached, dynamic, and remote model sources.\n- `packages/ai/README.md` documents tool calling, partial streaming tool calls, thinking/reasoning, provider configuration, context handoff, and OAuth flows.\n\n### `packages/agent/`\n\nStateful agent runtime built on `@gajae-code/ai`.\n\n- `packages/agent/src/index.ts` exports the `Agent`, loop APIs, append-only context, compaction, telemetry, proxy utilities, thinking helpers, and shared types.\n- `packages/agent/src/agent-loop.ts` owns the turn loop: transform context, call the model stream, execute tool calls, append tool results, and emit lifecycle events.\n- `packages/agent/src/agent.ts` wraps the loop with mutable state, subscriptions, prompt/continue/abort APIs, queues, provider session state, telemetry, and state mutation helpers.\n- `packages/agent/src/types.ts` defines `AgentMessage`, `AgentTool`, loop config, event, and runtime state contracts.\n\n### `packages/tui/`\n\nTerminal UI framework used by the CLI.\n\n- `packages/tui/src/index.ts` exports components, keybindings, autocomplete, terminal abstractions, image support, TUI core, and utilities.\n- `packages/tui/src/tui.ts` manages component rendering, focus, overlays, terminal dimensions, diff state, and synchronized output.\n- `packages/tui/src/terminal.ts` abstracts terminal lifecycle, dimensions, cursor controls, title/progress, Kitty protocol state, and appearance notifications.\n- `packages/tui/README.md` documents the component model and built-in components such as text, input, editor, markdown, loaders, select/settings lists, spacer, image, box, and container.\n\n### `packages/natives/` and Rust crates\n\nNative helper layer exposed through N-API.\n\n- `packages/natives/package.json` exports `native/index.js` and generated TypeScript definitions.\n- `packages/natives/native/loader-state.js` resolves platform/CPU-specific native binaries and validates package/native version alignment.\n- `crates/pi-natives/src/lib.rs` is the N-API root for appearance, AST search/editing, clipboard, filesystem scan/cache, grep/glob, syntax highlighting, HTML-to-Markdown, keyboard parsing, process/PTY/shell support, SIXEL, code summarization, token counting, text measurement/wrapping/truncation, workspace scanning, power assertions, and isolation helpers.\n- `crates/pi-shell/src/lib.rs` exposes brush-based shell execution primitives used by the native shell adapter.\n- `crates/pi-shell/src/shell.rs` implements persistent and one-shot shell execution, streaming, environment handling, cancellation, and output minimizer telemetry.\n- `crates/pi-shell/src/fixup.rs` performs conservative AST-based bash command fixups.\n- `crates/pi-natives/src/pty.rs` implements interactive PTY sessions.\n\n### `packages/utils/`\n\nShared TypeScript utilities.\n\n- `packages/utils/src/index.ts` exports abortable/async helpers, color/env/dir utilities, fetch retry, formatting, frontmatter, glob helpers, JSON helpers, logging, MIME detection, prompt rendering, process-tree helpers, sanitization, streams, temp files, tab spacing, type guards, and executable lookup.\n- `packages/utils/src/ptree.ts` and `packages/utils/src/procmgr.ts` wrap native process helpers for ergonomic TypeScript use.\n\n### `packages/stats/`\n\nLocal observability dashboard for session and model usage.\n\n- `packages/stats/src/index.ts` exposes the `gjc-stats` CLI entrypoint and exports aggregation/server APIs.\n- `packages/stats/src/aggregator.ts` parses session-derived request metrics and writes aggregated data through SQLite.\n- `packages/stats/src/server.ts` serves local dashboard API routes and static SPA assets.\n- `packages/stats/src/types.ts` and `packages/stats/src/shared-types.ts` define dashboard and aggregate metric shapes.\n\n### `packages/swarm-extension/`\n\nOptional YAML/DAG multi-agent extension outside the fixed default workflow surface.\n\n- `packages/swarm-extension/README.md` documents standalone `gjc-swarm` execution and in-TUI `/swarm` commands.\n- Swarm workflows define agents, tasks, dependency edges, waves, and shared workspace state under `.swarm_<name>/`.\n\n### `packages/typescript-edit-benchmark/`\n\nPrivate benchmark package for TypeScript edit tasks.\n\n- `packages/typescript-edit-benchmark/package.json` exposes `typescript-edit-benchmark` and depends on the coding-agent, agent-core, ai, tui, utils, diff, prettier, and Babel tooling.\n- `packages/typescript-edit-benchmark/src/index.ts` is the benchmark CLI: it resolves fixtures, loads tasks, runs edit attempts, records progress, and writes reports/conversation dumps under `runs/`.\n\n## Python packages\n\n### `python/gjc-rpc/`\n\nTyped Python client for `gjc --mode rpc`.\n\n- `python/gjc-rpc/pyproject.toml` packages `gjc-rpc` for Python 3.11+.\n- `python/gjc-rpc/README.md` documents the process-backed stdio client, typed command methods, startup flags, event listeners, todo seeding, host-owned tools, and host-owned URI schemes.\n\n### `python/robogjc/`\n\nSelf-hosted GitHub triage/fix bot that drives `gjc --mode rpc`.\n\n- `python/robogjc/AGENTS.md` is the authoritative local contract for this subtree.\n- `python/robogjc/pyproject.toml` packages `robogjc` for Python 3.11+ with FastAPI, httpx, pydantic settings, Click, and `gjc-rpc`.\n- `python/robogjc/README.md` documents the webhook-to-worktree-to-gjc flow, GitHub sidecar trust boundary, persistent per-issue sessions, and audit trail.\n- Important modules include `src/server.py`, `src/queue.py`, `src/tasks.py`, `src/worker.py`, `src/host_tools.py`, `src/sandbox.py`, `src/github_client.py`, `src/github_events.py`, `src/db.py`, and `src/config.py`.\n\n## Runtime flow\n\nA normal CLI session starts in `packages/coding-agent/src/cli.ts`, routes through command handling, then reaches `packages/coding-agent/src/main.ts`. `main.ts` converts CLI/runtime settings into `CreateAgentSessionOptions` and calls `createAgentSession()` in `packages/coding-agent/src/sdk.ts`.\n\nThe SDK builds the session context, loads the default skills, creates built-in tools, resolves model/auth state through `@gajae-code/ai`, constructs the system prompt, and instantiates `@gajae-code/agent-core`. The agent loop streams model events, executes tools, records tool results, and hands state back to the selected mode: interactive TUI, print, RPC, RPC-UI, or ACP.\n\n## Verification and gates\n\nPackage-local checks are defined in each `package.json`. For workflow-definition or default-surface changes, the focused gates are:\n\n```sh\nbun scripts/check-visible-definitions.ts\nbun scripts/verify-g002-gates.ts\nbun scripts/rebrand-inventory.ts --strict\nbun test packages/coding-agent/test/default-gjc-definitions.test.ts\n```\n\nFor broader TypeScript verification, use the root script:\n\n```sh\nbun run check:ts\n```\n\nDo not use `tsc` or `npx tsc` directly in this repository.\n",
 	"compaction.md": "# Compaction and Branch Summaries\n\nCompaction and branch summaries are the two mechanisms that keep long sessions usable without losing prior work context.\n\n- **Compaction** rewrites old history into a summary on the current branch.\n- **Branch summary** captures abandoned branch context during `/tree` navigation.\n\nBoth are persisted as session entries and converted back into user-context messages when rebuilding LLM input.\n\n## Key implementation files\n\n- `packages/agent/src/compaction/compaction.ts` (context-full summarization and handoff generation)\n- `packages/agent/src/compaction/branch-summarization.ts`\n- `packages/agent/src/compaction/pruning.ts`\n- `packages/agent/src/compaction/utils.ts`\n- `packages/agent/src/compaction/openai.ts`\n- `packages/coding-agent/src/session/session-manager.ts`\n- `packages/coding-agent/src/session/agent-session.ts`\n- `packages/coding-agent/src/session/messages.ts`\n- `packages/coding-agent/src/extensibility/hooks/types.ts`\n- `packages/coding-agent/src/config/settings-schema.ts`\n\n## Session entry model\n\nCompaction and branch summaries are first-class session entries, not plain assistant/user messages.\n\n- `CompactionEntry`\n  - `type: \"compaction\"`\n  - `summary`, optional `shortSummary`\n  - `firstKeptEntryId` (compaction boundary)\n  - `tokensBefore`\n  - optional `details`, `preserveData`, `fromExtension`\n- `BranchSummaryEntry`\n  - `type: \"branch_summary\"`\n  - `fromId`, `summary`\n  - optional `details`, `fromExtension`\n\nWhen context is rebuilt (`buildSessionContext`):\n\n1. Latest compaction on the active path is converted to one `compactionSummary` message.\n2. Kept entries from `firstKeptEntryId` to the compaction point are re-included.\n3. Later entries on the path are appended.\n4. `branch_summary` entries are converted to `branchSummary` messages.\n5. `custom_message` entries are converted to `custom` messages.\n\nThose custom roles are then transformed into LLM-facing user messages in `convertToLlm()` using the static templates:\n\n- `packages/agent/src/compaction/prompts/compaction-summary-context.md`\n- `packages/agent/src/compaction/prompts/branch-summary-context.md`\n- `packages/agent/src/compaction/prompts/handoff-document.md`\n\n## Compaction pipeline\n\n### Triggers\n\nCompaction/context maintenance can run in four ways:\n\n1. **Manual context compaction**: `/compact [instructions]` calls `AgentSession.compact(...)`.\n2. **Automatic overflow recovery**: after a same-model assistant error that matches context overflow.\n3. **Automatic threshold maintenance**: after a successful turn when context exceeds the resolved threshold.\n4. **Idle maintenance**: `runIdleCompaction()` can invoke the same auto-maintenance path with reason `\"idle\"`.\n\n### Compaction shape (visual)\n\n```text\nBefore compaction:\n\n  entry:  0     1     2     3      4     5     6      7      8     9\n        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┐\n        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │\n        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┘\n                └────────┬───────┘ └──────────────┬──────────────┘\n               messagesToSummarize            kept messages\n                                   ↑\n                          firstKeptEntryId (entry 4)\n\nAfter compaction (new entry appended):\n\n  entry:  0     1     2     3      4     5     6      7      8     9      10\n        ┌─────┬─────┬─────┬──────┬─────┬─────┬──────┬──────┬─────┬──────┬─────┐\n        │ hdr │ usr │ ass │ tool │ usr │ ass │ tool │ tool │ ass │ tool │ cmp │\n        └─────┴─────┴─────┴──────┴─────┴─────┴──────┴──────┴─────┴──────┴─────┘\n               └──────────┬──────┘ └──────────────────────┬───────────────────┘\n                 not sent to LLM                    sent to LLM\n                                                         ↑\n                                              starts from firstKeptEntryId\n\nWhat the LLM sees:\n\n  ┌────────┬─────────┬─────┬─────┬──────┬──────┬─────┬──────┐\n  │ system │ summary │ usr │ ass │ tool │ tool │ ass │ tool │\n  └────────┴─────────┴─────┴─────┴──────┴──────┴─────┴──────┘\n       ↑         ↑      └─────────────────┬────────────────┘\n    prompt   from cmp          messages from firstKeptEntryId\n```\n\n### Overflow-retry vs threshold/idle maintenance\n\nThe automatic paths are intentionally different:\n\n- **Overflow recovery**\n  - Trigger: current-model assistant error is detected as context overflow and the error is not older than the latest compaction.\n  - The failing assistant error message is removed from active agent state before retry.\n  - Context promotion is tried first; if a configured larger model is available, the agent switches model and retries without compacting.\n  - If promotion is unavailable and compaction is enabled, context-full compaction runs with `reason: \"overflow\"` and `willRetry: true`; handoff strategy is not used for overflow.\n  - On success, agent auto-continues (`agent.continue()`) after compaction.\n\n- **Threshold maintenance**\n  - Trigger: successful, non-error assistant message whose adjusted context tokens exceed `resolveThresholdTokens(...)`.\n  - Tool-output pruning can reduce the measured token count before threshold comparison.\n  - Context promotion is tried before compaction.\n  - If promotion is unavailable, auto maintenance runs with `reason: \"threshold\"` and `willRetry: false`.\n  - With `compaction.strategy: \"handoff\"`, threshold maintenance starts a new handoff session instead of writing a compaction entry; if handoff returns no document without aborting, it falls back to context-full compaction.\n  - On success, if `compaction.autoContinue !== false`, schedules an agent-authored developer auto-continue prompt from `prompts/system/auto-continue.md`.\n\n- **Idle maintenance**\n  - Trigger: `runIdleCompaction()` when not streaming or already compacting.\n  - Uses `reason: \"idle\"` and does not auto-continue afterward.\n\n### Pre-compaction pruning\n\nBefore compaction checks, tool-result pruning may run (`pruneToolOutputs`).\n\nDefault prune policy:\n\n- Protect newest `40_000` tool-output tokens.\n- Require at least `20_000` total estimated savings.\n- Never prune tool results from `skill` or `read`.\n\nPruned tool results are replaced with:\n\n- `[Output truncated - N tokens]`\n\nIf pruning changes entries, session storage is rewritten and agent message state is refreshed before compaction decisions.\n\n### Boundary and cut-point logic\n\n`prepareCompaction()` only considers entries since the last compaction entry (if any).\n\n1. Find previous compaction index.\n2. Compute `boundaryStart = prevCompactionIndex + 1`.\n3. Adapt `keepRecentTokens` using measured usage ratio when available.\n4. Run `findCutPoint()` over the boundary window.\n\nValid cut points include:\n\n- message entries with roles: `user`, `assistant`, `bashExecution`, `hookMessage`, `branchSummary`, `compactionSummary`\n- `custom_message` entries\n- `branch_summary` entries\n\nHard rule: never cut at `toolResult`.\n\nIf there are non-message metadata entries immediately before the cut point (`model_change`, `thinking_level_change`, labels, etc.), they are pulled into the kept region by moving cut index backward until a message or compaction boundary is hit.\n\n### Split-turn handling\n\nIf cut point is not at a user-turn start, compaction treats it as a split turn.\n\nTurn start detection treats these as user-turn boundaries:\n\n- `message.role === \"user\"`\n- `message.role === \"bashExecution\"`\n- `custom_message` entry\n- `branch_summary` entry\n\nSplit-turn compaction generates two summaries:\n\n1. History summary (`messagesToSummarize`)\n2. Turn-prefix summary (`turnPrefixMessages`)\n\nFinal stored summary is merged as:\n\n```markdown\n<history summary>\n\n---\n\n**Turn Context (split turn):**\n\n<turn prefix summary>\n```\n\n### Summary generation\n\n`compact(...)` builds summaries from serialized conversation text:\n\n1. Convert messages via `convertToLlm()`.\n2. Serialize with `serializeConversation()`.\n3. Wrap in `<conversation>...</conversation>`.\n4. Optionally include `<previous-summary>...</previous-summary>`.\n5. Optionally inject hook context as `<additional-context>` list.\n6. Execute summarization prompt with `SUMMARIZATION_SYSTEM_PROMPT`.\n\nPrompt selection:\n\n- first compaction: `compaction-summary.md`\n- iterative compaction with prior summary: `compaction-update-summary.md`\n- split-turn second pass: `compaction-turn-prefix.md`\n- short UI summary: `compaction-short-summary.md`\n- handoff document: `handoff-document.md` (used by `generateHandoff(...)`, not serialized compaction)\n\nRemote summarization modes:\n\n- If `compaction.remoteEndpoint` is set and remote compaction is enabled, local summary generation POSTs:\n  - `{ systemPrompt, prompt }`\n- Expects JSON containing at least `{ summary }`.\n- For OpenAI/OpenAI code provider models, compaction first tries the provider-native `/responses/compact` endpoint when remote compaction is enabled. It preserves provider replacement history in `preserveData.openaiRemoteCompaction` and falls back to local summarization if that native request fails.\n\n### Handoff generation\n\n`packages/agent/src/compaction/compaction.ts` also exports `generateHandoff(...)`. Handoff generation uses the same `completeSimple(...)` oneshot style as summarization, but it preserves the live agent cache prefix by sending the active system prompt, tool array, and real LLM message history, then appending one agent-attributed `user` message containing the handoff prompt. It forces `toolChoice: \"none\"` and returns joined text blocks directly.\n\nHandoff does not write a `CompactionEntry`. `AgentSession.handoff()` owns the session transition: it starts a new session, injects the generated document as a visible `custom_message` with `customType: \"handoff\"`, and rebuilds agent messages from that new session.\n\n### File-operation context in summaries\n\nCompaction tracks cumulative file activity using assistant tool calls:\n\n- `read(path)` → read set\n- `write(path)` → modified set\n- `edit(path)` → modified set\n\nCumulative behavior:\n\n- Includes prior compaction details only when prior entry is pi-generated (`fromExtension !== true`).\n- In split turns, includes turn-prefix file ops too.\n- `readFiles` excludes files also modified.\n\nSummary text gets file tags appended via prompt template:\n\n```xml\n<read-files>\n...\n</read-files>\n<modified-files>\n...\n</modified-files>\n```\n\n### Persist and reload\n\nAfter summary generation (or hook-provided summary), agent session:\n\n1. Appends `CompactionEntry` with `appendCompaction(...)` for context-full maintenance; handoff strategy creates a new session and injects a handoff `custom_message` instead.\n2. Rebuilds display context from the active leaf via `buildDisplaySessionContext()`.\n3. Replaces live agent messages with rebuilt context.\n4. Emits `session_compact` hook event.\n\n## Branch summarization pipeline\n\nBranch summarization is tied to tree navigation, not token overflow.\n\n### Trigger\n\nDuring `navigateTree(...)`:\n\n1. Compute abandoned entries from old leaf to common ancestor using `collectEntriesForBranchSummary(...)`.\n2. If caller requested summary (`options.summarize`), generate summary before switching leaf.\n3. If summary exists, attach it at the navigation target using `branchWithSummary(...)`.\n\nOperationally this is commonly driven by `/tree` flow when `branchSummary.enabled` is enabled.\n\n### Branch switch shape (visual)\n\n```text\nTree before navigation:\n\n         ┌─ B ─ C ─ D (old leaf, being abandoned)\n    A ───┤\n         └─ E ─ F (target)\n\nCommon ancestor: A\nEntries to summarize: B, C, D\n\nAfter navigation with summary:\n\n         ┌─ B ─ C ─ D ─ [summary of B,C,D]\n    A ───┤\n         └─ E ─ F (new leaf)\n```\n\n### Preparation and token budget\n\n`generateBranchSummary(...)` computes budget as:\n\n- `tokenBudget = model.contextWindow - branchSummary.reserveTokens`\n\n`prepareBranchEntries(...)` then:\n\n1. First pass: collect cumulative file ops from all summarized entries, including prior pi-generated `branch_summary` details.\n2. Second pass: walk newest → oldest, adding messages until token budget is reached.\n3. Prefer preserving recent context.\n4. May still include large summary entries near budget edge for continuity.\n\nCompaction entries are included as messages (`compactionSummary`) during branch summarization input.\n\n### Summary generation and persistence\n\nBranch summarization:\n\n1. Converts and serializes selected messages.\n2. Wraps in `<conversation>`.\n3. Uses custom instructions if supplied, otherwise `branch-summary.md`.\n4. Calls summarization model with `SUMMARIZATION_SYSTEM_PROMPT`.\n5. Prepends `branch-summary-preamble.md`.\n6. Appends file-operation tags.\n\nResult is stored as `BranchSummaryEntry` with optional details (`readFiles`, `modifiedFiles`).\n\n## Extension and hook touchpoints\n\n### `session_before_compact`\n\nPre-compaction hook.\n\nCan:\n\n- cancel compaction (`{ cancel: true }`)\n- provide full custom compaction payload (`{ compaction: CompactionResult }`)\n\n### `session.compacting`\n\nPrompt/context customization hook for default compaction.\n\nCan return:\n\n- `prompt` (override base summary prompt)\n- `context` (extra context lines injected into `<additional-context>`)\n- `preserveData` (stored on compaction entry)\n\n### `session_compact`\n\nPost-compaction notification with saved `compactionEntry` and `fromExtension` flag.\n\n### `session_before_tree`\n\nRuns on tree navigation before default branch summary generation.\n\nCan:\n\n- cancel navigation\n- provide custom `{ summary: { summary, details } }` used when user requested summarization\n\n### `session_tree`\n\nPost-navigation event exposing new/old leaf and optional summary entry.\n\n## Runtime behavior and failure semantics\n\n- Manual compaction aborts current agent operation first.\n- `abortCompaction()` cancels both manual and auto-compaction controllers.\n- Auto compaction emits start/end session events for UI/state updates.\n- Auto compaction can try multiple model candidates and retry transient failures; long retry delays prefer the next candidate when one is available.\n- Overflow errors are excluded from generic retry path because they are handled by context promotion/compaction.\n- If auto-compaction fails:\n  - overflow path emits `Context overflow recovery failed: ...`\n  - threshold path emits `Auto-compaction failed: ...`\n- Branch summarization can be cancelled via abort signal (e.g., Escape), returning canceled/aborted navigation result.\n\n## Settings and defaults\n\nFrom `settings-schema.ts`:\n\n- `compaction.enabled` = `true`\n- `compaction.strategy` = `\"context-full\"` (`\"handoff\"` and `\"off\"` are also supported)\n- `compaction.reserveTokens` = `16384`\n- `compaction.keepRecentTokens` = `20000`\n- `compaction.autoContinue` = `true`\n- `compaction.remoteEnabled` = `true`\n- `compaction.remoteEndpoint` = `undefined`\n- `compaction.thresholdPercent` = `-1` and `compaction.thresholdTokens` = `-1`; when no positive override is set, the threshold is `contextWindow - max(15% of contextWindow, reserveTokens)`\n- `compaction.idleEnabled` = `true`\n- `branchSummary.enabled` = `false`\n- `branchSummary.reserveTokens` = `16384`\n\nThese values are consumed at runtime by `AgentSession` and compaction/branch summarization modules.\n",
-	"environment-variables.md": "# Environment Variables (Current Runtime Reference)\n\nThis reference is derived from current code paths in:\n\n- `packages/coding-agent/src/**`\n- `packages/ai/src/**` (provider/auth resolution used by coding-agent)\n- `packages/utils/src/**` and `packages/tui/src/**` where those vars directly affect coding-agent runtime\n\nIt documents only active behavior.\n\n## Resolution model and precedence\n\nMost runtime lookups use `$env` from `@gajae-code/utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Agent `.env` (`~/.gjc/agent/.env`, respecting `GJC_CONFIG_DIR` / `GJC_CODING_AGENT_DIR`) for keys not already set\n4. Config-root `.env` (`~/.gjc/.env`, respecting `GJC_CONFIG_DIR`) for keys not already set\n5. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule inside each `.env` file: `GJC_*` keys are mirrored to `GJC_*` keys in that parsed file.\n\n---\n\n## 1) Model/provider authentication\n\nThese are consumed via `getEnvApiKey()` (`packages/ai/src/stream.ts`) unless noted otherwise.\n\n### Core provider credentials\n\n| Variable                        | Used for                                         | Required when                                                  | Notes / precedence                                                                                  |\n| ------------------------------- | ------------------------------------------------ | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- |\n| `ANTHROPIC_OAUTH_TOKEN`         | Anthropic API auth                               | Using Anthropic with OAuth token auth                          | Takes precedence over `ANTHROPIC_API_KEY` for provider auth resolution                              |\n| `ANTHROPIC_API_KEY`             | Anthropic API auth                               | Using Anthropic without OAuth token                            | Fallback after `ANTHROPIC_OAUTH_TOKEN`                                                              |\n| `ANTHROPIC_FOUNDRY_API_KEY`     | Anthropic via Azure Foundry / enterprise gateway | `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` enabled                              | Takes precedence over `ANTHROPIC_OAUTH_TOKEN` and `ANTHROPIC_API_KEY` when Foundry mode is enabled  |\n| `OPENAI_API_KEY`                | OpenAI auth                                      | Using OpenAI-family providers without explicit apiKey argument | Used by OpenAI Completions/Responses providers                                                      |\n| `GEMINI_API_KEY`                | Google Gemini auth                               | Using `google` provider models                                 | Primary key for Gemini provider mapping                                                             |\n| `GOOGLE_API_KEY`                | Gemini image tool auth fallback                  | Using `gemini_image` tool without `GEMINI_API_KEY`             | Used by coding-agent image tool fallback path                                                       |\n| `GROQ_API_KEY`                  | Groq auth                                        | Using Groq models                                              |                                                                                                     |\n| `CEREBRAS_API_KEY`              | Cerebras auth                                    | Using Cerebras models                                          |                                                                                                     |\n| `FIREWORKS_API_KEY`             | Fireworks auth                                   | Using Fireworks models                                         |                                                                                                     |\n| `TOGETHER_API_KEY`              | Together auth                                    | Using `together` provider                                      |                                                                                                     |\n| `HUGGINGFACE_HUB_TOKEN`         | Hugging Face auth                                | Using `huggingface` provider                                   | Primary Hugging Face token env var                                                                  |\n| `HF_TOKEN`                      | Hugging Face auth                                | Using `huggingface` provider                                   | Fallback when `HUGGINGFACE_HUB_TOKEN` is unset                                                      |\n| `SYNTHETIC_API_KEY`             | Synthetic auth                                   | Using Synthetic models                                         |                                                                                                     |\n| `NVIDIA_API_KEY`                | NVIDIA auth                                      | Using `nvidia` provider                                        |                                                                                                     |\n| `NANO_GPT_API_KEY`              | NanoGPT auth                                     | Using `nanogpt` provider                                       |                                                                                                     |\n| `VENICE_API_KEY`                | Venice auth                                      | Using `venice` provider                                        |                                                                                                     |\n| `LITELLM_API_KEY`               | LiteLLM auth                                     | Using `litellm` provider                                       | OpenAI-compatible LiteLLM proxy key                                                                 |\n| `LM_STUDIO_API_KEY`             | LM Studio auth (optional)                        | Using `lm-studio` provider with authenticated hosts            | Local LM Studio usually runs without auth; any non-empty token works when a key is required         |\n| `OLLAMA_API_KEY`                | Ollama auth (optional)                           | Using `ollama` provider with authenticated hosts               | Local Ollama usually runs without auth; any non-empty token works when a key is required            |\n| `LLAMA_CPP_API_KEY`             | llama.cpp auth (optional)                        | Using `llama.cpp` provider with authenticated hosts            | Local llama.cpp usually runs without auth; any non-empty token works when a key is configured       |\n| `XIAOMI_API_KEY`                | Xiaomi MiMo auth                                 | Using `xiaomi` provider                                        |                                                                                                     |\n| `MOONSHOT_API_KEY`              | Moonshot auth                                    | Using `moonshot` provider                                      |                                                                                                     |\n| `XAI_API_KEY`                   | xAI auth                                         | Using xAI models                                               |                                                                                                     |\n| `OPENROUTER_API_KEY`            | OpenRouter auth                                  | Using OpenRouter models                                        | Also used by image tool when preferred/auto provider is OpenRouter                                  |\n| `MISTRAL_API_KEY`               | Mistral auth                                     | Using Mistral models                                           |                                                                                                     |\n| `ZAI_API_KEY`                   | z.ai auth                                        | Using z.ai models                                              | Also used by z.ai web search provider                                                               |\n| `MINIMAX_API_KEY`               | MiniMax auth                                     | Using `minimax` provider                                       |                                                                                                     |\n| `MINIMAX_CODE_API_KEY`          | MiniMax Code auth                                | Using `minimax-code` provider                                  |                                                                                                     |\n| `MINIMAX_CODE_CN_API_KEY`       | MiniMax Code CN auth                             | Using `minimax-code-cn` provider                               |                                                                                                     |\n| `OPENCODE_API_KEY`              | OpenCode auth                                    | Using `opencode-go` / `opencode-zen` models                    |                                                                                                     |\n| `QIANFAN_API_KEY`               | Qianfan auth                                     | Using `qianfan` provider                                       |                                                                                                     |\n| `QWEN_OAUTH_TOKEN`              | Qwen Portal auth                                 | Using `qwen-portal` with OAuth token                           | Takes precedence over `QWEN_PORTAL_API_KEY`                                                         |\n| `QWEN_PORTAL_API_KEY`           | Qwen Portal auth                                 | Using `qwen-portal` with API key                               | Fallback after `QWEN_OAUTH_TOKEN`                                                                   |\n| `ZENMUX_API_KEY`                | ZenMux auth                                      | Using `zenmux` provider                                        | Used for ZenMux OpenAI and Anthropic-compatible routes                                              |\n| `VLLM_API_KEY`                  | vLLM auth/discovery opt-in                       | Using `vllm` provider (local OpenAI-compatible servers)        | Any non-empty value works for no-auth local servers                                                 |\n| `CURSOR_ACCESS_TOKEN`           | Cursor provider auth                             | Using Cursor provider                                          |                                                                                                     |\n| `AI_GATEWAY_API_KEY`            | Vercel AI Gateway auth                           | Using `vercel-ai-gateway` provider                             |                                                                                                     |\n| `CLOUDFLARE_AI_GATEWAY_API_KEY` | Cloudflare AI Gateway auth                       | Using `cloudflare-ai-gateway` provider                         | Base URL must be configured as `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic` |\n| `ALIBABA_CODING_PLAN_API_KEY`   | Alibaba Coding Plan auth                         | Using `alibaba-coding-plan` provider                           |                                                                                                     |\n| `DEEPSEEK_API_KEY`              | DeepSeek auth                                    | Using DeepSeek models                                          |                                                                                                     |\n| `KILO_API_KEY`                  | Kilo auth                                        | Using Kilo models                                              |                                                                                                     |\n| `OLLAMA_CLOUD_API_KEY`          | Ollama Cloud auth                                | Using `ollama-cloud` provider                                  |                                                                                                     |\n| `GITLAB_TOKEN`                  | GitLab Duo auth                                  | Using `gitlab-duo` provider                                    |                                                                                                     |\n\n### GitHub/Copilot token chains\n\n| Variable               | Used for                                         | Chain                                                |\n| ---------------------- | ------------------------------------------------ | ---------------------------------------------------- |\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth                     | `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` |\n| `GH_TOKEN`             | Copilot fallback; GitHub API auth in web scraper | In web scraper: `GITHUB_TOKEN` → `GH_TOKEN`          |\n| `GITHUB_TOKEN`         | Copilot fallback; GitHub API auth in web scraper | In web scraper: checked before `GH_TOKEN`            |\n\n### Auth broker / auth gateway (remote credential vault)\n\nWhen the broker is enabled, the local SQLite credential store is bypassed and all OAuth refresh / access tokens live on the broker host. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full protocol, CLI surface, and 5-min/15-s usage cache layering.\n\n| Variable                | Used for                                                                                          | Required when                                                                                                          | Notes / precedence                                                                                                                                                                                  |\n| ----------------------- | ------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `GJC_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`); selects broker mode      | Resolving credentials through a broker; also required by `gjc auth-gateway serve` (the gateway is itself a broker client) | Wins over `auth.broker.url` in `config.yml`. When set with no resolvable token, `resolveAuthBrokerConfig()` hard-errors instead of falling back to local SQLite.                                    |\n| `GJC_AUTH_BROKER_TOKEN` | Bearer token sent on every broker endpoint except `/v1/healthz`                                   | `GJC_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`     | Resolution: this env → `auth.broker.token` (`$ENV_NAME` indirection supported) → `<config-dir>/auth-broker.token` (mode `0600`). `<config-dir>` is `~/.gjc/` (respecting `GJC_CONFIG_DIR`).         |\n\nThe gateway has no dedicated env vars — it inherits `GJC_AUTH_BROKER_*`. Its own inbound bearer token lives at `<config-dir>/auth-gateway.token` and is managed via `gjc auth-gateway token`.\n\n---\n\n## 2) Provider-specific runtime configuration\n\n### Anthropic Foundry Gateway (Azure / enterprise proxy)\n\nWhen `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled, Anthropic requests switch to Foundry mode:\n\n- Base URL resolves from `FOUNDRY_BASE_URL` (fallback remains model/default base URL if unset).\n- API key resolution for provider `anthropic` becomes:\n  `ANTHROPIC_FOUNDRY_API_KEY` → `ANTHROPIC_OAUTH_TOKEN` → `ANTHROPIC_API_KEY`.\n- `ANTHROPIC_CUSTOM_HEADERS` is parsed as comma/newline-separated `key: value` pairs and merged into request headers.\n- TLS client/server material can be injected from env values:\n  `NODE_EXTRA_CA_CERTS`, `ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`.\n  Each accepts either:\n  - a filesystem path to PEM content, or\n  - inline PEM (including escaped `\\n` sequences).\n\n| Variable                    | Value type                                     | Behavior                                                                      |\n| --------------------------- | ---------------------------------------------- | ----------------------------------------------------------------------------- |\n| `ANTHROPIC_MODEL_CODE_USE_FOUNDRY`   | Boolean-like string (`1`, `true`, `yes`, `on`) | Enables Foundry mode for Anthropic provider                                   |\n| `FOUNDRY_BASE_URL`          | URL string                                     | Anthropic endpoint base URL in Foundry mode                                   |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Token string                                   | Used for `Authorization: Bearer <token>`                                      |\n| `ANTHROPIC_CUSTOM_HEADERS`  | Header list string                             | Extra headers; format `header-a: value, header-b: value` or newline-separated |\n| `NODE_EXTRA_CA_CERTS`       | PEM path or inline PEM                         | Extra CA chain for server certificate validation                              |\n| `ANTHROPIC_MODEL_CODE_CLIENT_CERT`   | PEM path or inline PEM                         | mTLS client certificate                                                       |\n| `ANTHROPIC_MODEL_CODE_CLIENT_KEY`    | PEM path or inline PEM                         | mTLS client private key (must be paired with cert)                            |\n\n### Amazon Bedrock\n\n| Variable                                                                        | Default / behavior                                                                            |\n| ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `AWS_REGION`                                                                    | Primary region source                                                                         |\n| `AWS_DEFAULT_REGION`                                                            | Fallback if `AWS_REGION` unset                                                                |\n| `AWS_PROFILE`                                                                   | Enables named profile auth path                                                               |\n| `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`                                   | Enables IAM key auth path                                                                     |\n| `AWS_BEARER_TOKEN_BEDROCK`                                                      | Enables bearer token auth path                                                                |\n| `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI` / `AWS_CONTAINER_CREDENTIALS_FULL_URI` | Enables ECS task credential path                                                              |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN`                                  | Enables web identity auth path                                                                |\n| `AWS_BEDROCK_SKIP_AUTH`                                                         | If `1`, injects dummy credentials (proxy/non-auth scenarios)                                  |\n| `AWS_BEDROCK_FORCE_HTTP1`                                                       | If `1`, forces Node HTTP/1 request handler                                                    |\n| `HTTPS_PROXY` / `HTTP_PROXY` / `ALL_PROXY`                                      | Routes Bedrock runtime and AWS SSO credential calls through the configured proxy using HTTP/1 |\n| `NO_PROXY`                                                                      | Excludes matching hosts from proxy routing when a proxy variable is configured                |\n\nRegion fallback in provider code: `options.region` → `AWS_REGION` → `AWS_DEFAULT_REGION` → `us-east-1`.\n\n### Azure OpenAI Responses\n\n| Variable                           | Default / behavior                                                          |\n| ---------------------------------- | --------------------------------------------------------------------------- |\n| `AZURE_OPENAI_API_KEY`             | Required unless API key passed as option                                    |\n| `AZURE_OPENAI_API_VERSION`         | Default `v1`                                                                |\n| `AZURE_OPENAI_BASE_URL`            | Direct base URL override                                                    |\n| `AZURE_OPENAI_RESOURCE_NAME`       | Used to construct base URL: `https://<resource>.openai.azure.com/openai/v1` |\n| `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` | Optional mapping string: `modelId=deploymentName,model2=deployment2`        |\n\nBase URL resolution: option `azureBaseUrl` → env `AZURE_OPENAI_BASE_URL` → option/env resource name → `model.baseUrl`.\n\n### Model provider base URL overrides\n\nBuilt-in model provider base URLs resolve with this precedence:\n\n1. `models.yml` / model config provider `baseUrl`\n2. provider-specific base URL environment variable\n3. bundled provider default\n\nSupported aliases:\n\n| Provider | Variables |\n| --- | --- |\n| OpenAI | `OPENAI_BASE_URL` |\n| Anthropic | `ANTHROPIC_BASE_URL` |\n| Google Gemini | `GOOGLE_BASE_URL`, `GEMINI_BASE_URL` |\n| Google Antigravity | `GOOGLE_ANTIGRAVITY_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Gemini CLI | `GOOGLE_GEMINI_CLI_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Vertex | `GOOGLE_VERTEX_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Any provider id | derived `<PROVIDER_ID>_BASE_URL`, uppercased with non-alphanumerics converted to `_` (for example `my-proxy` → `MY_PROXY_BASE_URL`) |\n\nOpenAI-compatible proxy note: the built-in `openai` provider keeps its bundled API transport (`openai-responses`). Setting `OPENAI_BASE_URL` changes the host but still calls `<baseUrl>/responses`. If your proxy only supports Chat Completions, configure a custom `models.yml` provider with `api: openai-completions` instead of using the built-in OpenAI provider override:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKey: OPENAI_API_KEY\n    api: openai-completions\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        api: openai-completions\n```\n\nFor OpenRouter traffic, GJC explicitly sends `User-Agent: Gajae-Code/<package version>` plus OpenRouter attribution headers. For the built-in OpenAI Responses transport and generic OpenAI-compatible Chat Completions transport, GJC passes model/provider headers through the OpenAI JavaScript SDK and does not set a GJC user-agent unless the provider-specific code adds one.\n\n### Google Vertex AI\n\n| Variable                         | Required?                      | Notes                                                                                                                     |\n| -------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |\n| `GOOGLE_CLOUD_PROJECT`           | Yes (unless passed in options) | Fallback: `GCLOUD_PROJECT`                                                                                                |\n| `GCLOUD_PROJECT`                 | Fallback                       | Used as alternate project ID source                                                                                       |\n| `GOOGLE_CLOUD_PROJECT_ID`        | OAuth login helper only        | Used by Gemini CLI OAuth project discovery                                                                                |\n| `GOOGLE_CLOUD_LOCATION`          | Yes (unless passed in options) | No default in provider                                                                                                    |\n| `GOOGLE_CLOUD_API_KEY`           | Conditional                    | Direct Vertex API-key auth; otherwise ADC fallback can authenticate when project and location are set                     |\n| `GOOGLE_APPLICATION_CREDENTIALS` | Conditional                    | If set, file must exist; otherwise ADC fallback path is checked (`~/.config/gcloud/application_default_credentials.json`) |\n\n### Kimi\n\n| Variable               | Default / behavior                                       |\n| ---------------------- | -------------------------------------------------------- |\n| `KIMI_CODE_OAUTH_HOST` | Primary OAuth host override                              |\n| `KIMI_OAUTH_HOST`      | Fallback OAuth host override                             |\n| `KIMI_CODE_BASE_URL`   | Overrides Kimi usage endpoint base URL (`usage/kimi.ts`) |\n\nOAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth.kimi.com`.\n\n### Gemini CLI compatibility\n\n| Variable                   | Default / behavior                                              |\n| -------------------------- | --------------------------------------------------------------- |\n| `GJC_AI_GEMINI_CLI_VERSION` | Overrides Gemini CLI user-agent version tag (`0.35.3` if unset) |\n\n### OpenAI code provider responses (feature/debug controls)\n\n| Variable                             | Behavior                                             |\n| ------------------------------------ | ---------------------------------------------------- |\n| `GJC_OPENAI_CODE_DEBUG`                     | `1`/`true` enables OpenAI code provider debug logging      |\n| `GJC_OPENAI_CODE_WEBSOCKET`                 | `1`/`true` enables websocket transport preference    |\n| `GJC_OPENAI_CODE_WEBSOCKET_V2`              | `1`/`true` enables websocket v2 path                 |\n| `GJC_OPENAI_CODE_WEBSOCKET_IDLE_TIMEOUT_MS` | Positive integer override (default 300000)           |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_BUDGET`    | Non-negative integer override (default 5)            |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_DELAY_MS`  | Positive integer base backoff override (default 500) |\n| `GJC_OPENAI_STREAM_IDLE_TIMEOUT_MS`   | Positive integer OpenAI stream idle timeout override |\n\n### Cursor provider debug\n\n| Variable           | Behavior                                                                 |\n| ------------------ | ------------------------------------------------------------------------ |\n| `DEBUG_CURSOR`     | Enables provider debug logs; `2`/`verbose` for detailed payload snippets |\n| `DEBUG_CURSOR_LOG` | Optional file path for JSONL debug log output                            |\n\n### Prompt cache compatibility switch\n\n| Variable             | Behavior                                                                                                          |\n| -------------------- | ----------------------------------------------------------------------------------------------------------------- |\n| `GJC_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution) |\n\n---\n\n## 3) Web search subsystem\n\n### Search provider credentials\n\n| Variable                                            | Used by                                                       |\n| --------------------------------------------------- | ------------------------------------------------------------- |\n| `EXA_API_KEY`                                       | Exa search provider                         |\n| `BRAVE_API_KEY`                                     | Brave search provider                                         |\n| `PERPLEXITY_API_KEY`                                | Perplexity search provider API-key mode                       |\n| `PERPLEXITY_COOKIES`                                | Perplexity cookie-auth search mode                            |\n| `TAVILY_API_KEY`                                    | Tavily search provider                                        |\n| `ZAI_API_KEY`                                       | z.ai search provider (also checks stored OAuth in `agent.db`) |\n| `OPENAI_API_KEY` / OpenAI code OAuth in DB                | OpenAI code search provider availability/auth                       |\n| `GJC_OPENAI_CODE_WEB_SEARCH_MODEL`                         | OpenAI code search provider model override                          |\n| `MOONSHOT_SEARCH_API_KEY` / `KIMI_SEARCH_API_KEY`   | Kimi/Moonshot search provider env auth                        |\n| `MOONSHOT_SEARCH_BASE_URL` / `KIMI_SEARCH_BASE_URL` | Kimi/Moonshot search endpoint override                        |\n| `KAGI_API_KEY`                                      | Kagi search provider                                          |\n| `JINA_API_KEY`                                      | Jina search provider                                          |\n| `PARALLEL_API_KEY`                                  | Parallel search provider                                      |\n| `SEARXNG_ENDPOINT`, `SEARXNG_TOKEN`                 | SearXNG endpoint and optional bearer token                    |\n| `SEARXNG_BASIC_USERNAME`, `SEARXNG_BASIC_PASSWORD`  | SearXNG HTTP Basic Auth credentials                           |\n\nSearXNG also reads the equivalent `searxng.endpoint`, `searxng.token`, `searxng.basicUsername`, and `searxng.basicPassword` settings from `~/.gjc/agent/config.yml`; environment variables are fallbacks.\n\n### Anthropic web search auth chain\n\nAnthropic web search uses `findAnthropicAuth()` from `packages/ai/src/utils/anthropic-auth.ts` in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY` (+ optional `ANTHROPIC_SEARCH_BASE_URL`)\n2. `ANTHROPIC_FOUNDRY_API_KEY` when `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled\n3. Anthropic OAuth credentials from `agent.db` (must not expire within 5-minute buffer)\n4. Anthropic API-key credentials from `agent.db`\n5. Generic Anthropic env fallback: provider key (`ANTHROPIC_FOUNDRY_API_KEY` in Foundry mode, otherwise `ANTHROPIC_OAUTH_TOKEN`/`ANTHROPIC_API_KEY`) + optional `ANTHROPIC_BASE_URL` (`FOUNDRY_BASE_URL` when Foundry mode is enabled)\n\nRelated vars:\n\n| Variable                    | Default / behavior                                   |\n| --------------------------- | ---------------------------------------------------- |\n| `ANTHROPIC_SEARCH_API_KEY`  | Highest-priority explicit search key                 |\n| `ANTHROPIC_SEARCH_BASE_URL` | Defaults to `https://api.anthropic.com` when omitted |\n| `ANTHROPIC_SEARCH_MODEL`    | Defaults to `anthropic-model-haiku-4-5`                       |\n| `ANTHROPIC_BASE_URL`        | Generic fallback base URL for tier-4 auth path       |\n\n### Perplexity OAuth flow behavior flag\n\n| Variable            | Behavior                                                                        |\n| ------------------- | ------------------------------------------------------------------------------- |\n| `GJC_AUTH_NO_BORROW` | If set, disables macOS native-app token borrowing path in Perplexity login flow |\n\n---\n\n## 4) Python tooling and kernel runtime\n\n| Variable                  | Default / behavior                                                                                                  |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------- |\n| `GJC_PY`                   | Eval backend override: `0`/`bash`=JavaScript only, `1`/`py`=Python only, `mix`/`both`=both; invalid values ignored |\n| `GJC_PYTHON_SKIP_CHECK`    | If `1`, skips Python interpreter availability checks (subprocess runner still starts on demand)                     |\n| `GJC_PYTHON_INTEGRATION`   | If `1`, opts gated integration tests in (e.g. `python-runner.integration.test.ts`) into running against real Python |\n| `GJC_PYTHON_IPC_TRACE`     | If `1`, logs NDJSON frames exchanged with the Python runner subprocess                                              |\n| `VIRTUAL_ENV`             | Highest-priority venv path for Python runtime resolution                                                            |\n\nExtra conditional behavior:\n\n- If `BUN_ENV=test` or `NODE_ENV=test`, Python availability checks are treated as OK and warming is skipped.\n- Python env filtering denies common API keys and allows safe base vars + `LC_`, `XDG_`, `GJC_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable                     | Default / behavior                                                                                 |\n| ---------------------------- | -------------------------------------------------------------------------------------------------- |\n| `GJC_SMOL_MODEL`              | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence)                           |\n| `GJC_SLOW_MODEL`              | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence)                           |\n| `GJC_PLAN_MODEL`              | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence)                           |\n| `GJC_NO_TITLE`                | If set (any non-empty value), disables auto session title generation on first user message         |\n| `NULL_PROMPT`                | If `true`, system prompt builder returns empty string                                              |\n| `GJC_BLOCKED_AGENT`           | Blocks a specific subagent type in task tool                                                       |\n| `GJC_SUBPROCESS_CMD`          | Overrides subagent spawn command (`gjc` / `gjc.cmd` resolution bypass)                             |\n| `GJC_TASK_MAX_OUTPUT_BYTES`   | Max captured output bytes per subagent (default `500000`)                                          |\n| `GJC_TASK_MAX_OUTPUT_LINES`   | Max captured output lines per subagent (default `5000`)                                            |\n| `GJC_TIMING`                  | If set (any non-empty value), prints a hierarchical timing-span tree to **stderr** via `logger.printTimings()`. In interactive mode the tree prints once the agent is ready (before the TUI starts); in print mode it prints after the whole prompt batch completes. Print-mode prompts are wrapped in `print:prompt:initial` / `print:prompt:next` spans so each user message shows up as its own row. `GJC_TIMING=x` exits the process with code 0 right after printing in interactive mode (use to measure cold startup only). `GJC_TIMING=full` lists every module-load entry instead of just the top N. |\n| `GJC_PACKAGE_DIR`             | Overrides package asset base dir resolution (docs/examples/changelog path lookup)                  |\n| `GJC_DISABLE_LSPMUX`          | If `1`, disables lspmux detection/integration and forces direct LSP server spawning                |\n| `GJC_RPC_EMIT_TITLE`          | Boolean-like flag enabling title events in RPC mode                                                |\n| `SMITHERY_URL`               | Smithery web URL override (default `https://smithery.ai`)                                          |\n| `SMITHERY_API_URL`           | Smithery API base URL override (default `https://api.smithery.ai`)                                 |\n| `PUPPETEER_EXECUTABLE_PATH`  | Browser tool Chromium executable override                                                          |\n| `LM_STUDIO_BASE_URL`         | Default implicit LM Studio discovery base URL override (`http://127.0.0.1:1234/v1` if unset)       |\n| `OLLAMA_BASE_URL`            | Default implicit Ollama discovery base URL override (`http://127.0.0.1:11434` if unset)            |\n| `LLAMA_CPP_BASE_URL`         | Default implicit Llama.cpp discovery base URL override (`http://127.0.0.1:8080` if unset)          |\n| `GJC_EDIT_VARIANT`            | Forces edit tool variant when valid (`patch`, `replace`, `hashline`, `atom`, `vim`, `apply_patch`) |\n| `GJC_FORCE_IMAGE_PROTOCOL`    | Forces supported image protocol (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) where used            |\n| `GJC_ALLOW_SIXEL_PASSTHROUGH` | Allows SIXEL passthrough when `GJC_FORCE_IMAGE_PROTOCOL=sixel`                                      |\n| `GJC_NO_PTY`                  | If `1`, disables interactive PTY path for bash tool                                                |\n\n`GJC_NO_PTY` is also set internally when CLI `--no-pty` is used.\n\n---\n\n## 6) Storage and config root paths\n\nThese are consumed via `@gajae-code/utils/dirs` and affect where coding-agent stores data.\n\n| Variable              | Default / behavior                                                            |\n| --------------------- | ----------------------------------------------------------------------------- |\n| `GJC_CONFIG_DIR`       | Config root dirname under home (default `.gjc`)                               |\n| `GJC_CODING_AGENT_DIR` | Full override for agent directory (default `~/<GJC_CONFIG_DIR or .gjc>/agent`) |\n| `PWD`                 | Used when matching canonical current working directory in path helpers        |\n\n---\n\n## 7) Shell/tool execution environment\n\n(From `packages/utils/src/procmgr.ts` and coding-agent bash tool integration.)\n\n| Variable                   | Behavior                                                                       |\n| -------------------------- | ------------------------------------------------------------------------------ |\n| `GJC_BASH_NO_CI`            | Suppresses automatic `CI=true` injection into spawned shell env                |\n| `ANTHROPIC_MODEL_BASH_NO_CI`        | Legacy alias fallback for `GJC_BASH_NO_CI`                                      |\n| `GJC_BASH_NO_LOGIN`         | Disables login-shell mode; shell args become `['-c']` instead of `['-l','-c']` |\n| `ANTHROPIC_MODEL_BASH_NO_LOGIN`     | Legacy alias fallback for `GJC_BASH_NO_LOGIN`                                   |\n| `GJC_SHELL_PREFIX`          | Optional command prefix wrapper                                                |\n| `ANTHROPIC_MODEL_CODE_SHELL_PREFIX` | Legacy alias fallback for `GJC_SHELL_PREFIX`                                    |\n| `VISUAL`                   | Preferred external editor command                                              |\n| `EDITOR`                   | Fallback external editor command                                               |\n\nCurrent implementation: `GJC_BASH_NO_LOGIN`/`ANTHROPIC_MODEL_BASH_NO_LOGIN` are active; when either is set, `getShellArgs()` returns `['-c']`.\n\n---\n\n## 8) UI/theme/session detection (auto-detected env)\n\nThese are read as runtime signals; they are usually set by the terminal/OS rather than manually configured.\n\n| Variable                                                                                                           | Used for                                                  |\n| ------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------- |\n| `COLORTERM`, `TERM`, `WT_SESSION`                                                                                  | Color capability detection (theme color mode)             |\n| `COLORFGBG`                                                                                                        | Terminal background light/dark auto-detection             |\n| `TERM_PROGRAM`, `TERM_PROGRAM_VERSION`, `TERMINAL_EMULATOR`                                                        | Terminal identity in system prompt/context                |\n| `KDE_FULL_SESSION`, `XDG_CURRENT_DESKTOP`, `DESKTOP_SESSION`, `XDG_SESSION_DESKTOP`, `GDMSESSION`, `WINDOWMANAGER` | Desktop/window-manager detection in system prompt/context |\n| `KITTY_WINDOW_ID`, `TMUX_PANE`, `TERM_SESSION_ID`, `WT_SESSION`                                                    | Stable per-terminal session breadcrumb IDs                |\n| `SHELL`, `ComSpec`, `TERM_PROGRAM`, `TERM`                                                                         | System info diagnostics                                   |\n| `APPDATA`, `XDG_CONFIG_HOME`                                                                                       | lspmux config path resolution                             |\n| `HOME`                                                                                                             | Path shortening in command UI                         |\n\n---\n\n## 9) TUI runtime flags (shared package, affects coding-agent UX)\n\n| Variable                  | Behavior                                                                              |\n| ------------------------- | ------------------------------------------------------------------------------------- |\n| `GJC_NOTIFICATIONS`        | `off` / `0` / `false` suppress desktop notifications                                  |\n| `GJC_TUI_WRITE_LOG`        | If set, logs TUI writes to file                                                       |\n| `GJC_HARDWARE_CURSOR`      | If `1`, enables hardware cursor mode                                                  |\n| `GJC_CLEAR_ON_SHRINK`      | If `1`, clears empty rows when content shrinks                                        |\n| `GJC_DEBUG_REDRAW`         | If `1`, enables redraw debug logging                                                  |\n| `GJC_TUI_DEBUG`            | If `1`, enables deep TUI debug dump path                                              |\n| `GJC_FORCE_IMAGE_PROTOCOL` | Forces terminal image protocol detection (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) |\n\n---\n\n## 10) Commit generation controls\n\n| Variable                  | Behavior                                                            |\n| ------------------------- | ------------------------------------------------------------------- |\n| `GJC_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `GJC_COMMIT_NO_FALLBACK`   | If `true`, disables fallback when agent returns no proposal         |\n| `GJC_COMMIT_MAP_REDUCE`    | If `false`, disables map-reduce commit analysis path                |\n| `DEBUG`                   | If set, commit agent error stack traces are printed                 |\n\n---\n\n## Security-sensitive variables\n\nTreat these as secrets; do not log or commit them:\n\n- Provider/API keys and OAuth/bearer credentials (all `*_API_KEY`, `*_TOKEN`, OAuth access/refresh tokens)\n- Cloud credentials (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS` path may expose service-account material)\n- Search/provider auth vars (`EXA_API_KEY`, `BRAVE_API_KEY`, `PERPLEXITY_API_KEY`, Anthropic search keys)\n- Foundry mTLS material (`ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`, `NODE_EXTRA_CA_CERTS` when it points to private CA bundles)\n\nPython runtime also explicitly strips many common key vars before spawning kernel subprocesses (`packages/coding-agent/src/eval/py/runtime.ts`).\n",
+	"environment-variables.md": "# Environment Variables (Current Runtime Reference)\n\nThis reference is derived from current code paths in:\n\n- `packages/coding-agent/src/**`\n- `packages/ai/src/**` (provider/auth resolution used by coding-agent)\n- `packages/utils/src/**` and `packages/tui/src/**` where those vars directly affect coding-agent runtime\n\nIt documents only active behavior.\n\n## Resolution model and precedence\n\nMost runtime lookups use `$env` from `@gajae-code/utils` (`packages/utils/src/env.ts`).\n\n`$env` loading order:\n\n1. Existing process environment (`Bun.env`)\n2. Project `.env` (`$PWD/.env`) for keys not already set\n3. Agent `.env` (`~/.gjc/agent/.env`, respecting `GJC_CONFIG_DIR` / `GJC_CODING_AGENT_DIR`) for keys not already set\n4. Config-root `.env` (`~/.gjc/.env`, respecting `GJC_CONFIG_DIR`) for keys not already set\n5. Home `.env` (`~/.env`) for keys not already set\n\nAdditional rule inside each `.env` file: `GJC_*` keys are mirrored to `GJC_*` keys in that parsed file.\n\n---\n\n## 1) Model/provider authentication\n\nThese are consumed via `getEnvApiKey()` (`packages/ai/src/stream.ts`) unless noted otherwise.\n\n### Core provider credentials\n\n| Variable                        | Used for                                         | Required when                                                  | Notes / precedence                                                                                  |\n| ------------------------------- | ------------------------------------------------ | -------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- |\n| `ANTHROPIC_OAUTH_TOKEN`         | Anthropic API auth                               | Using Anthropic with OAuth token auth                          | Takes precedence over `ANTHROPIC_API_KEY` for provider auth resolution                              |\n| `ANTHROPIC_API_KEY`             | Anthropic API auth                               | Using Anthropic without OAuth token                            | Fallback after `ANTHROPIC_OAUTH_TOKEN`                                                              |\n| `ANTHROPIC_FOUNDRY_API_KEY`     | Anthropic via Azure Foundry / enterprise gateway | `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` enabled                              | Takes precedence over `ANTHROPIC_OAUTH_TOKEN` and `ANTHROPIC_API_KEY` when Foundry mode is enabled  |\n| `OPENAI_API_KEY`                | OpenAI auth                                      | Using OpenAI-family providers without explicit apiKey argument | Used by OpenAI Completions/Responses providers                                                      |\n| `GEMINI_API_KEY`                | Google Gemini auth                               | Using `google` provider models                                 | Primary key for Gemini provider mapping                                                             |\n| `GOOGLE_API_KEY`                | Gemini image tool auth fallback                  | Using `gemini_image` tool without `GEMINI_API_KEY`             | Used by coding-agent image tool fallback path                                                       |\n| `GROQ_API_KEY`                  | Groq auth                                        | Using Groq models                                              |                                                                                                     |\n| `CEREBRAS_API_KEY`              | Cerebras auth                                    | Using Cerebras models                                          |                                                                                                     |\n| `FIREWORKS_API_KEY`             | Fireworks auth                                   | Using Fireworks models                                         |                                                                                                     |\n| `TOGETHER_API_KEY`              | Together auth                                    | Using `together` provider                                      |                                                                                                     |\n| `HUGGINGFACE_HUB_TOKEN`         | Hugging Face auth                                | Using `huggingface` provider                                   | Primary Hugging Face token env var                                                                  |\n| `HF_TOKEN`                      | Hugging Face auth                                | Using `huggingface` provider                                   | Fallback when `HUGGINGFACE_HUB_TOKEN` is unset                                                      |\n| `SYNTHETIC_API_KEY`             | Synthetic auth                                   | Using Synthetic models                                         |                                                                                                     |\n| `NVIDIA_API_KEY`                | NVIDIA auth                                      | Using `nvidia` provider                                        |                                                                                                     |\n| `NANO_GPT_API_KEY`              | NanoGPT auth                                     | Using `nanogpt` provider                                       |                                                                                                     |\n| `VENICE_API_KEY`                | Venice auth                                      | Using `venice` provider                                        |                                                                                                     |\n| `LITELLM_API_KEY`               | LiteLLM auth                                     | Using `litellm` provider                                       | OpenAI-compatible LiteLLM proxy key                                                                 |\n| `LM_STUDIO_API_KEY`             | LM Studio auth (optional)                        | Using `lm-studio` provider with authenticated hosts            | Local LM Studio usually runs without auth; any non-empty token works when a key is required         |\n| `OLLAMA_API_KEY`                | Ollama auth (optional)                           | Using `ollama` provider with authenticated hosts               | Local Ollama usually runs without auth; any non-empty token works when a key is required            |\n| `LLAMA_CPP_API_KEY`             | llama.cpp auth (optional)                        | Using `llama.cpp` provider with authenticated hosts            | Local llama.cpp usually runs without auth; any non-empty token works when a key is configured       |\n| `XIAOMI_API_KEY`                | Xiaomi MiMo auth                                 | Using `xiaomi` provider                                        |                                                                                                     |\n| `MOONSHOT_API_KEY`              | Moonshot auth                                    | Using `moonshot` provider                                      |                                                                                                     |\n| `XAI_API_KEY`                   | xAI auth                                         | Using xAI models                                               |                                                                                                     |\n| `OPENROUTER_API_KEY`            | OpenRouter auth                                  | Using OpenRouter models                                        | Also used by image tool when preferred/auto provider is OpenRouter                                  |\n| `MISTRAL_API_KEY`               | Mistral auth                                     | Using Mistral models                                           |                                                                                                     |\n| `ZAI_API_KEY`                   | z.ai auth                                        | Using z.ai models                                              | Also used by z.ai web search provider                                                               |\n| `MINIMAX_API_KEY`               | MiniMax auth                                     | Using `minimax` provider                                       |                                                                                                     |\n| `AZURE_OPENAI_API_KEY`          | Azure OpenAI auth                               | Using `azure-openai` / `azure-openai-responses` models         | Pair with `AZURE_OPENAI_BASE_URL` or `AZURE_OPENAI_RESOURCE_NAME`                                   |\n| `MINIMAX_CODE_API_KEY`          | MiniMax Code auth                                | Using `minimax-code` provider                                  |                                                                                                     |\n| `MINIMAX_CODE_CN_API_KEY`       | MiniMax Code CN auth                             | Using `minimax-code-cn` provider                               |                                                                                                     |\n| `OPENCODE_API_KEY`              | OpenCode auth                                    | Using `opencode-go` / `opencode-zen` models                    |                                                                                                     |\n| `QIANFAN_API_KEY`               | Qianfan auth                                     | Using `qianfan` provider                                       |                                                                                                     |\n| `QWEN_OAUTH_TOKEN`              | Qwen Portal auth                                 | Using `qwen-portal` with OAuth token                           | Takes precedence over `QWEN_PORTAL_API_KEY`                                                         |\n| `QWEN_PORTAL_API_KEY`           | Qwen Portal auth                                 | Using `qwen-portal` with API key                               | Fallback after `QWEN_OAUTH_TOKEN`                                                                   |\n| `ZENMUX_API_KEY`                | ZenMux auth                                      | Using `zenmux` provider                                        | Used for ZenMux OpenAI and Anthropic-compatible routes                                              |\n| `VLLM_API_KEY`                  | vLLM auth/discovery opt-in                       | Using `vllm` provider (local OpenAI-compatible servers)        | Any non-empty value works for no-auth local servers                                                 |\n| `CURSOR_ACCESS_TOKEN`           | Cursor provider auth                             | Using Cursor provider                                          |                                                                                                     |\n| `AI_GATEWAY_API_KEY`            | Vercel AI Gateway auth                           | Using `vercel-ai-gateway` provider                             |                                                                                                     |\n| `CLOUDFLARE_AI_GATEWAY_API_KEY` | Cloudflare AI Gateway auth                       | Using `cloudflare-ai-gateway` provider                         | Base URL must be configured as `https://gateway.ai.cloudflare.com/v1/<account>/<gateway>/anthropic` |\n| `ALIBABA_CODING_PLAN_API_KEY`   | Alibaba Coding Plan auth                         | Using `alibaba-coding-plan` provider                           |                                                                                                     |\n| `DEEPSEEK_API_KEY`              | DeepSeek auth                                    | Using DeepSeek models                                          |                                                                                                     |\n| `KILO_API_KEY`                  | Kilo auth                                        | Using Kilo models                                              |                                                                                                     |\n| `OLLAMA_CLOUD_API_KEY`          | Ollama Cloud auth                                | Using `ollama-cloud` provider                                  |                                                                                                     |\n| `GITLAB_TOKEN`                  | GitLab Duo auth                                  | Using `gitlab-duo` provider                                    |                                                                                                     |\n\n### GitHub/Copilot token chains\n\n| Variable               | Used for                                         | Chain                                                |\n| ---------------------- | ------------------------------------------------ | ---------------------------------------------------- |\n| `COPILOT_GITHUB_TOKEN` | GitHub Copilot provider auth                     | `COPILOT_GITHUB_TOKEN` → `GH_TOKEN` → `GITHUB_TOKEN` |\n| `GH_TOKEN`             | Copilot fallback; GitHub API auth in web scraper | In web scraper: `GITHUB_TOKEN` → `GH_TOKEN`          |\n| `GITHUB_TOKEN`         | Copilot fallback; GitHub API auth in web scraper | In web scraper: checked before `GH_TOKEN`            |\n\n### Auth broker / auth gateway (remote credential vault)\n\nWhen the broker is enabled, the local SQLite credential store is bypassed and all OAuth refresh / access tokens live on the broker host. See [`auth-broker-gateway.md`](./auth-broker-gateway.md) for the full protocol, CLI surface, and 5-min/15-s usage cache layering.\n\n| Variable                | Used for                                                                                          | Required when                                                                                                          | Notes / precedence                                                                                                                                                                                  |\n| ----------------------- | ------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `GJC_AUTH_BROKER_URL`   | Base URL of the remote auth-broker (e.g. `https://broker.tailnet:8765`); selects broker mode      | Resolving credentials through a broker; also required by `gjc auth-gateway serve` (the gateway is itself a broker client) | Wins over `auth.broker.url` in `config.yml`. When set with no resolvable token, `resolveAuthBrokerConfig()` hard-errors instead of falling back to local SQLite.                                    |\n| `GJC_AUTH_BROKER_TOKEN` | Bearer token sent on every broker endpoint except `/v1/healthz`                                   | `GJC_AUTH_BROKER_URL` is set and no token is available from `auth.broker.token` or `<config-dir>/auth-broker.token`     | Resolution: this env → `auth.broker.token` (`$ENV_NAME` indirection supported) → `<config-dir>/auth-broker.token` (mode `0600`). `<config-dir>` is `~/.gjc/` (respecting `GJC_CONFIG_DIR`).         |\n\nThe gateway has no dedicated env vars — it inherits `GJC_AUTH_BROKER_*`. Its own inbound bearer token lives at `<config-dir>/auth-gateway.token` and is managed via `gjc auth-gateway token`.\n\n---\n\n## 2) Provider-specific runtime configuration\n\n### Anthropic Foundry Gateway (Azure / enterprise proxy)\n\nWhen `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled, Anthropic requests switch to Foundry mode:\n\n- Base URL resolves from `FOUNDRY_BASE_URL` (fallback remains model/default base URL if unset).\n- API key resolution for provider `anthropic` becomes:\n  `ANTHROPIC_FOUNDRY_API_KEY` → `ANTHROPIC_OAUTH_TOKEN` → `ANTHROPIC_API_KEY`.\n- `ANTHROPIC_CUSTOM_HEADERS` is parsed as comma/newline-separated `key: value` pairs and merged into request headers.\n- TLS client/server material can be injected from env values:\n  `NODE_EXTRA_CA_CERTS`, `ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`.\n  Each accepts either:\n  - a filesystem path to PEM content, or\n  - inline PEM (including escaped `\\n` sequences).\n\n| Variable                    | Value type                                     | Behavior                                                                      |\n| --------------------------- | ---------------------------------------------- | ----------------------------------------------------------------------------- |\n| `ANTHROPIC_MODEL_CODE_USE_FOUNDRY`   | Boolean-like string (`1`, `true`, `yes`, `on`) | Enables Foundry mode for Anthropic provider                                   |\n| `FOUNDRY_BASE_URL`          | URL string                                     | Anthropic endpoint base URL in Foundry mode                                   |\n| `ANTHROPIC_FOUNDRY_API_KEY` | Token string                                   | Used for `Authorization: Bearer <token>`                                      |\n| `ANTHROPIC_CUSTOM_HEADERS`  | Header list string                             | Extra headers; format `header-a: value, header-b: value` or newline-separated |\n| `NODE_EXTRA_CA_CERTS`       | PEM path or inline PEM                         | Extra CA chain for server certificate validation                              |\n| `ANTHROPIC_MODEL_CODE_CLIENT_CERT`   | PEM path or inline PEM                         | mTLS client certificate                                                       |\n| `ANTHROPIC_MODEL_CODE_CLIENT_KEY`    | PEM path or inline PEM                         | mTLS client private key (must be paired with cert)                            |\n\n### Amazon Bedrock\n\n| Variable                                                                        | Default / behavior                                                                            |\n| ------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- |\n| `AWS_REGION`                                                                    | Primary region source                                                                         |\n| `AWS_DEFAULT_REGION`                                                            | Fallback if `AWS_REGION` unset                                                                |\n| `AWS_PROFILE`                                                                   | Enables named profile auth path                                                               |\n| `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY`                                   | Enables IAM key auth path                                                                     |\n| `AWS_BEARER_TOKEN_BEDROCK`                                                      | Enables bearer token auth path                                                                |\n| `AWS_CONTAINER_CREDENTIALS_RELATIVE_URI` / `AWS_CONTAINER_CREDENTIALS_FULL_URI` | Enables ECS task credential path                                                              |\n| `AWS_WEB_IDENTITY_TOKEN_FILE` + `AWS_ROLE_ARN`                                  | Enables web identity auth path                                                                |\n| `AWS_BEDROCK_SKIP_AUTH`                                                         | If `1`, injects dummy credentials (proxy/non-auth scenarios)                                  |\n| `AWS_BEDROCK_FORCE_HTTP1`                                                       | If `1`, forces Node HTTP/1 request handler                                                    |\n| `HTTPS_PROXY` / `HTTP_PROXY` / `ALL_PROXY`                                      | Routes Bedrock runtime and AWS SSO credential calls through the configured proxy using HTTP/1 |\n| `NO_PROXY`                                                                      | Excludes matching hosts from proxy routing when a proxy variable is configured                |\n\nRegion fallback in provider code: `options.region` → `AWS_REGION` → `AWS_DEFAULT_REGION` → `us-east-1`.\n\nCredential fallback order is static env (`AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY` plus optional `AWS_SESSION_TOKEN`), named profile / SSO / `credential_process`, then EC2 IMDSv2. `models.yml` Bedrock entries use `api: bedrock-converse-stream` and do not require `apiKey` or `apiKeyEnv` because the provider signs requests from this AWS chain.\n\n### Azure OpenAI Responses\n\n| Variable                           | Default / behavior                                                          |\n| ---------------------------------- | --------------------------------------------------------------------------- |\n| `AZURE_OPENAI_API_KEY`             | Required unless API key passed as option                                    |\n| `AZURE_OPENAI_API_VERSION`         | Default `v1`                                                                |\n| `AZURE_OPENAI_BASE_URL`            | Direct base URL override                                                    |\n| `AZURE_OPENAI_RESOURCE_NAME`       | Used to construct base URL: `https://<resource>.openai.azure.com/openai/v1` |\n| `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` | Optional mapping string: `modelId=deploymentName,model2=deployment2`        |\n\nBase URL resolution: option `azureBaseUrl` → env `AZURE_OPENAI_BASE_URL` → option/env resource name → `model.baseUrl`.\n\n### Model provider base URL overrides\n\nBuilt-in model provider base URLs resolve with this precedence:\n\n1. `models.yml` / model config provider `baseUrl`\n2. provider-specific base URL environment variable\n3. bundled provider default\n\nSupported aliases:\n\n| Provider | Variables |\n| --- | --- |\n| OpenAI | `OPENAI_BASE_URL` |\n| Anthropic | `ANTHROPIC_BASE_URL` |\n| Google Gemini | `GOOGLE_BASE_URL`, `GEMINI_BASE_URL` |\n| Google Antigravity | `GOOGLE_ANTIGRAVITY_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Gemini CLI | `GOOGLE_GEMINI_CLI_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Google Vertex | `GOOGLE_VERTEX_BASE_URL`, then `GOOGLE_BASE_URL`, then `GEMINI_BASE_URL` |\n| Any provider id | derived `<PROVIDER_ID>_BASE_URL`, uppercased with non-alphanumerics converted to `_` (for example `my-proxy` → `MY_PROXY_BASE_URL`) |\n\nOpenAI-compatible proxy note: the built-in `openai` provider keeps its bundled API transport (`openai-responses`). Setting `OPENAI_BASE_URL` changes the host but still calls `<baseUrl>/responses`. If your proxy only supports Chat Completions, configure a custom `models.yml` provider with `api: openai-completions` instead of using the built-in OpenAI provider override:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKey: OPENAI_API_KEY\n    api: openai-completions\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        api: openai-completions\n```\n\nFor OpenRouter traffic, GJC explicitly sends `User-Agent: Gajae-Code/<package version>` plus OpenRouter attribution headers. For the built-in OpenAI Responses transport and generic OpenAI-compatible Chat Completions transport, GJC passes model/provider headers through the OpenAI JavaScript SDK and does not set a GJC user-agent unless the provider-specific code adds one.\n\n### OpenAI-compatible proxy provider config\n\nFor OpenAI-compatible proxies that only implement Chat Completions, prefer a custom `models.yml` provider over `OPENAI_BASE_URL`:\n\n```yaml\nproviders:\n  openai-compatible:\n    baseUrl: https://proxy.example.com/v1\n    apiKeyEnv: OPENAI_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: gpt-4o\n        name: GPT-4o via proxy\n        reasoning: false\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n```\n\n`models.yml` is strict: unsupported provider/model keys fail validation before the provider request is dispatched.\n\n### GJC workflow bridge commands\n\n`gjc ralplan`, `gjc deep-interview`, and `gjc state` are private runtime bridge commands. They require `GJC_RUNTIME_BINARY` (or legacy `GJC_LEGACY_RUNTIME_BINARY`) to point at the private runtime executable; public bundled workflow use remains through `/skill:ralplan` and `/skill:deep-interview` inside a GJC session.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_RUNTIME_BINARY` | Private runtime bridge binary for `gjc ralplan`, `gjc deep-interview`, and `gjc state` |\n| `GJC_LEGACY_RUNTIME_BINARY` | Legacy fallback bridge binary name |\n\n### Team dry-run and state paths\n\n`gjc team ... --dry-run --json` creates the same machine-readable state tree as a team launch without starting tmux panes. By default that state is written under `<cwd>/.gjc/state/team/<team>/`; treat it as ephemeral smoke-test/review state. Do not commit generated `.gjc/state/team` contents. Remove the generated team directory after a dry-run when the harness no longer needs it.\n\n| Variable | Behavior |\n| --- | --- |\n| `GJC_TEAM_STATE_ROOT` | Overrides the team state root (default `<cwd>/.gjc/state/team`) |\n| `GJC_TEAM_TMUX_COMMAND` | tmux binary/command override for team launch |\n| `GJC_TEAM_WORKER_COMMAND` | Worker GJC command override |\n| `GJC_TEAM_WORKER_CLI` | Team worker CLI selector; accepted values are `auto` or `gjc` |\n| `GJC_TEAM_WORKER_CLI_MAP` | Comma-separated worker CLI selector map; entries must be `auto` or `gjc` |\n\n### Google Vertex AI\n\n| Variable                         | Required?                      | Notes                                                                                                                     |\n| -------------------------------- | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------- |\n| `GOOGLE_CLOUD_PROJECT`           | Yes (unless passed in options) | Fallback: `GCLOUD_PROJECT`                                                                                                |\n| `GCLOUD_PROJECT`                 | Fallback                       | Used as alternate project ID source                                                                                       |\n| `GOOGLE_CLOUD_PROJECT_ID`        | OAuth login helper only        | Used by Gemini CLI OAuth project discovery                                                                                |\n| `GOOGLE_CLOUD_LOCATION`          | Yes (unless passed in options) | No default in provider                                                                                                    |\n| `GOOGLE_CLOUD_API_KEY`           | Conditional                    | Direct Vertex API-key auth; otherwise ADC fallback can authenticate when project and location are set                     |\n| `GOOGLE_APPLICATION_CREDENTIALS` | Conditional                    | If set, file must exist; otherwise ADC fallback path is checked (`~/.config/gcloud/application_default_credentials.json`) |\n\n### Kimi\n\n| Variable               | Default / behavior                                       |\n| ---------------------- | -------------------------------------------------------- |\n| `KIMI_CODE_OAUTH_HOST` | Primary OAuth host override                              |\n| `KIMI_OAUTH_HOST`      | Fallback OAuth host override                             |\n| `KIMI_CODE_BASE_URL`   | Overrides Kimi usage endpoint base URL (`usage/kimi.ts`) |\n\nOAuth host chain: `KIMI_CODE_OAUTH_HOST` → `KIMI_OAUTH_HOST` → `https://auth.kimi.com`.\n\n### Gemini CLI compatibility\n\n| Variable                   | Default / behavior                                              |\n| -------------------------- | --------------------------------------------------------------- |\n| `GJC_AI_GEMINI_CLI_VERSION` | Overrides Gemini CLI user-agent version tag (`0.35.3` if unset) |\n\n### OpenAI code provider responses (feature/debug controls)\n\n| Variable                             | Behavior                                             |\n| ------------------------------------ | ---------------------------------------------------- |\n| `GJC_OPENAI_CODE_DEBUG`                     | `1`/`true` enables OpenAI code provider debug logging      |\n| `GJC_OPENAI_CODE_WEBSOCKET`                 | `1`/`true` enables websocket transport preference    |\n| `GJC_OPENAI_CODE_WEBSOCKET_V2`              | `1`/`true` enables websocket v2 path                 |\n| `GJC_OPENAI_CODE_WEBSOCKET_IDLE_TIMEOUT_MS` | Positive integer override (default 300000)           |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_BUDGET`    | Non-negative integer override (default 5)            |\n| `GJC_OPENAI_CODE_WEBSOCKET_RETRY_DELAY_MS`  | Positive integer base backoff override (default 500) |\n| `GJC_OPENAI_STREAM_IDLE_TIMEOUT_MS`   | Positive integer OpenAI stream idle timeout override |\n\n### Cursor provider debug\n\n| Variable           | Behavior                                                                 |\n| ------------------ | ------------------------------------------------------------------------ |\n| `DEBUG_CURSOR`     | Enables provider debug logs; `2`/`verbose` for detailed payload snippets |\n| `DEBUG_CURSOR_LOG` | Optional file path for JSONL debug log output                            |\n\n### Prompt cache compatibility switch\n\n| Variable             | Behavior                                                                                                          |\n| -------------------- | ----------------------------------------------------------------------------------------------------------------- |\n| `GJC_CACHE_RETENTION` | If `long`, enables long retention where supported (`anthropic`, `openai-responses`, Bedrock retention resolution) |\n\n---\n\n## 3) Web search subsystem\n\n### Search provider credentials\n\n| Variable                                            | Used by                                                       |\n| --------------------------------------------------- | ------------------------------------------------------------- |\n| `EXA_API_KEY`                                       | Exa search provider                         |\n| `BRAVE_API_KEY`                                     | Brave search provider                                         |\n| `PERPLEXITY_API_KEY`                                | Perplexity search provider API-key mode                       |\n| `PERPLEXITY_COOKIES`                                | Perplexity cookie-auth search mode                            |\n| `TAVILY_API_KEY`                                    | Tavily search provider                                        |\n| `ZAI_API_KEY`                                       | z.ai search provider (also checks stored OAuth in `agent.db`) |\n| `OPENAI_API_KEY` / OpenAI code OAuth in DB                | OpenAI code search provider availability/auth                       |\n| `GJC_OPENAI_CODE_WEB_SEARCH_MODEL`                         | OpenAI code search provider model override                          |\n| `MOONSHOT_SEARCH_API_KEY` / `KIMI_SEARCH_API_KEY`   | Kimi/Moonshot search provider env auth                        |\n| `MOONSHOT_SEARCH_BASE_URL` / `KIMI_SEARCH_BASE_URL` | Kimi/Moonshot search endpoint override                        |\n| `KAGI_API_KEY`                                      | Kagi search provider                                          |\n| `JINA_API_KEY`                                      | Jina search provider                                          |\n| `PARALLEL_API_KEY`                                  | Parallel search provider                                      |\n| `SEARXNG_ENDPOINT`, `SEARXNG_TOKEN`                 | SearXNG endpoint and optional bearer token                    |\n| `SEARXNG_BASIC_USERNAME`, `SEARXNG_BASIC_PASSWORD`  | SearXNG HTTP Basic Auth credentials                           |\n\nSearXNG also reads the equivalent `searxng.endpoint`, `searxng.token`, `searxng.basicUsername`, and `searxng.basicPassword` settings from `~/.gjc/agent/config.yml`; environment variables are fallbacks.\n\n### Anthropic web search auth chain\n\nAnthropic web search uses `findAnthropicAuth()` from `packages/ai/src/utils/anthropic-auth.ts` in this order:\n\n1. `ANTHROPIC_SEARCH_API_KEY` (+ optional `ANTHROPIC_SEARCH_BASE_URL`)\n2. `ANTHROPIC_FOUNDRY_API_KEY` when `ANTHROPIC_MODEL_CODE_USE_FOUNDRY` is enabled\n3. Anthropic OAuth credentials from `agent.db` (must not expire within 5-minute buffer)\n4. Anthropic API-key credentials from `agent.db`\n5. Generic Anthropic env fallback: provider key (`ANTHROPIC_FOUNDRY_API_KEY` in Foundry mode, otherwise `ANTHROPIC_OAUTH_TOKEN`/`ANTHROPIC_API_KEY`) + optional `ANTHROPIC_BASE_URL` (`FOUNDRY_BASE_URL` when Foundry mode is enabled)\n\nRelated vars:\n\n| Variable                    | Default / behavior                                   |\n| --------------------------- | ---------------------------------------------------- |\n| `ANTHROPIC_SEARCH_API_KEY`  | Highest-priority explicit search key                 |\n| `ANTHROPIC_SEARCH_BASE_URL` | Defaults to `https://api.anthropic.com` when omitted |\n| `ANTHROPIC_SEARCH_MODEL`    | Defaults to `anthropic-model-haiku-4-5`                       |\n| `ANTHROPIC_BASE_URL`        | Generic fallback base URL for tier-4 auth path       |\n\n### Perplexity OAuth flow behavior flag\n\n| Variable            | Behavior                                                                        |\n| ------------------- | ------------------------------------------------------------------------------- |\n| `GJC_AUTH_NO_BORROW` | If set, disables macOS native-app token borrowing path in Perplexity login flow |\n\n---\n\n## 4) Python tooling and kernel runtime\n\n| Variable                  | Default / behavior                                                                                                  |\n| ------------------------- | ------------------------------------------------------------------------------------------------------------------- |\n| `GJC_PY`                   | Eval backend override: `0`/`bash`=JavaScript only, `1`/`py`=Python only, `mix`/`both`=both; invalid values ignored |\n| `GJC_PYTHON_SKIP_CHECK`    | If `1`, skips Python interpreter availability checks (subprocess runner still starts on demand)                     |\n| `GJC_PYTHON_INTEGRATION`   | If `1`, opts gated integration tests in (e.g. `python-runner.integration.test.ts`) into running against real Python |\n| `GJC_PYTHON_IPC_TRACE`     | If `1`, logs NDJSON frames exchanged with the Python runner subprocess                                              |\n| `VIRTUAL_ENV`             | Highest-priority venv path for Python runtime resolution                                                            |\n\nExtra conditional behavior:\n\n- If `BUN_ENV=test` or `NODE_ENV=test`, Python availability checks are treated as OK and warming is skipped.\n- Python env filtering denies common API keys and allows safe base vars + `LC_`, `XDG_`, `GJC_` prefixes.\n\n---\n\n## 5) Agent/runtime behavior toggles\n\n| Variable                     | Default / behavior                                                                                 |\n| ---------------------------- | -------------------------------------------------------------------------------------------------- |\n| `GJC_SMOL_MODEL`              | Ephemeral model-role override for `smol` (CLI `--smol` takes precedence)                           |\n| `GJC_SLOW_MODEL`              | Ephemeral model-role override for `slow` (CLI `--slow` takes precedence)                           |\n| `GJC_PLAN_MODEL`              | Ephemeral model-role override for `plan` (CLI `--plan` takes precedence)                           |\n| `GJC_NO_TITLE`                | If set (any non-empty value), disables auto session title generation on first user message         |\n| `NULL_PROMPT`                | If `true`, system prompt builder returns empty string                                              |\n| `GJC_BLOCKED_AGENT`           | Blocks a specific subagent type in task tool                                                       |\n| `GJC_SUBPROCESS_CMD`          | Overrides subagent spawn command (`gjc` / `gjc.cmd` resolution bypass)                             |\n| `GJC_TASK_MAX_OUTPUT_BYTES`   | Max captured output bytes per subagent (default `500000`)                                          |\n| `GJC_TASK_MAX_OUTPUT_LINES`   | Max captured output lines per subagent (default `5000`)                                            |\n| `GJC_TIMING`                  | If set (any non-empty value), prints a hierarchical timing-span tree to **stderr** via `logger.printTimings()`. In interactive mode the tree prints once the agent is ready (before the TUI starts); in print mode it prints after the whole prompt batch completes. Print-mode prompts are wrapped in `print:prompt:initial` / `print:prompt:next` spans so each user message shows up as its own row. `GJC_TIMING=x` exits the process with code 0 right after printing in interactive mode (use to measure cold startup only). `GJC_TIMING=full` lists every module-load entry instead of just the top N. |\n| `GJC_PACKAGE_DIR`             | Overrides package asset base dir resolution (docs/examples/changelog path lookup)                  |\n| `GJC_DISABLE_LSPMUX`          | If `1`, disables lspmux detection/integration and forces direct LSP server spawning                |\n| `GJC_RPC_EMIT_TITLE`          | Boolean-like flag enabling title events in RPC mode                                                |\n| `SMITHERY_URL`               | Smithery web URL override (default `https://smithery.ai`)                                          |\n| `SMITHERY_API_URL`           | Smithery API base URL override (default `https://api.smithery.ai`)                                 |\n| `PUPPETEER_EXECUTABLE_PATH`  | Browser tool Chromium executable override                                                          |\n| `LM_STUDIO_BASE_URL`         | Default implicit LM Studio discovery base URL override (`http://127.0.0.1:1234/v1` if unset)       |\n| `OLLAMA_BASE_URL`            | Default implicit Ollama discovery base URL override (`http://127.0.0.1:11434` if unset)            |\n| `LLAMA_CPP_BASE_URL`         | Default implicit Llama.cpp discovery base URL override (`http://127.0.0.1:8080` if unset)          |\n| `GJC_EDIT_VARIANT`            | Forces edit tool variant when valid (`patch`, `replace`, `hashline`, `atom`, `vim`, `apply_patch`) |\n| `GJC_FORCE_IMAGE_PROTOCOL`    | Forces supported image protocol (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) where used            |\n| `GJC_ALLOW_SIXEL_PASSTHROUGH` | Allows SIXEL passthrough when `GJC_FORCE_IMAGE_PROTOCOL=sixel`                                      |\n| `GJC_NO_PTY`                  | If `1`, disables interactive PTY path for bash tool                                                |\n\n`GJC_NO_PTY` is also set internally when CLI `--no-pty` is used.\n\n---\n\n## 6) Storage and config root paths\n\nThese are consumed via `@gajae-code/utils/dirs` and affect where coding-agent stores data.\n\n| Variable              | Default / behavior                                                            |\n| --------------------- | ----------------------------------------------------------------------------- |\n| `GJC_CONFIG_DIR`       | Config root dirname under home (default `.gjc`)                               |\n| `GJC_CODING_AGENT_DIR` | Full override for agent directory (default `~/<GJC_CONFIG_DIR or .gjc>/agent`) |\n| `PWD`                 | Used when matching canonical current working directory in path helpers        |\n\n---\n\n## 7) Shell/tool execution environment\n\n(From `packages/utils/src/procmgr.ts` and coding-agent bash tool integration.)\n\n| Variable                   | Behavior                                                                       |\n| -------------------------- | ------------------------------------------------------------------------------ |\n| `GJC_BASH_NO_CI`            | Suppresses automatic `CI=true` injection into spawned shell env                |\n| `ANTHROPIC_MODEL_BASH_NO_CI`        | Legacy alias fallback for `GJC_BASH_NO_CI`                                      |\n| `GJC_BASH_NO_LOGIN`         | Disables login-shell mode; shell args become `['-c']` instead of `['-l','-c']` |\n| `ANTHROPIC_MODEL_BASH_NO_LOGIN`     | Legacy alias fallback for `GJC_BASH_NO_LOGIN`                                   |\n| `GJC_SHELL_PREFIX`          | Optional command prefix wrapper                                                |\n| `ANTHROPIC_MODEL_CODE_SHELL_PREFIX` | Legacy alias fallback for `GJC_SHELL_PREFIX`                                    |\n| `VISUAL`                   | Preferred external editor command                                              |\n| `EDITOR`                   | Fallback external editor command                                               |\n\nCurrent implementation: `GJC_BASH_NO_LOGIN`/`ANTHROPIC_MODEL_BASH_NO_LOGIN` are active; when either is set, `getShellArgs()` returns `['-c']`.\n\n---\n\n## 8) UI/theme/session detection (auto-detected env)\n\nThese are read as runtime signals; they are usually set by the terminal/OS rather than manually configured.\n\n| Variable                                                                                                           | Used for                                                  |\n| ------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------- |\n| `COLORTERM`, `TERM`, `WT_SESSION`                                                                                  | Color capability detection (theme color mode)             |\n| `COLORFGBG`                                                                                                        | Terminal background light/dark auto-detection             |\n| `TERM_PROGRAM`, `TERM_PROGRAM_VERSION`, `TERMINAL_EMULATOR`                                                        | Terminal identity in system prompt/context                |\n| `KDE_FULL_SESSION`, `XDG_CURRENT_DESKTOP`, `DESKTOP_SESSION`, `XDG_SESSION_DESKTOP`, `GDMSESSION`, `WINDOWMANAGER` | Desktop/window-manager detection in system prompt/context |\n| `KITTY_WINDOW_ID`, `TMUX_PANE`, `TERM_SESSION_ID`, `WT_SESSION`                                                    | Stable per-terminal session breadcrumb IDs                |\n| `SHELL`, `ComSpec`, `TERM_PROGRAM`, `TERM`                                                                         | System info diagnostics                                   |\n| `APPDATA`, `XDG_CONFIG_HOME`                                                                                       | lspmux config path resolution                             |\n| `HOME`                                                                                                             | Path shortening in command UI                         |\n\n---\n\n## 9) TUI runtime flags (shared package, affects coding-agent UX)\n\n| Variable                  | Behavior                                                                              |\n| ------------------------- | ------------------------------------------------------------------------------------- |\n| `GJC_NOTIFICATIONS`        | `off` / `0` / `false` suppress desktop notifications                                  |\n| `GJC_TUI_WRITE_LOG`        | If set, logs TUI writes to file                                                       |\n| `GJC_HARDWARE_CURSOR`      | If `1`, enables hardware cursor mode                                                  |\n| `GJC_CLEAR_ON_SHRINK`      | If `1`, clears empty rows when content shrinks                                        |\n| `GJC_DEBUG_REDRAW`         | If `1`, enables redraw debug logging                                                  |\n| `GJC_TUI_DEBUG`            | If `1`, enables deep TUI debug dump path                                              |\n| `GJC_FORCE_IMAGE_PROTOCOL` | Forces terminal image protocol detection (`kitty`, `iterm2`/`iterm`, `sixel`, `none`) |\n\n---\n\n## 10) Commit generation controls\n\n| Variable                  | Behavior                                                            |\n| ------------------------- | ------------------------------------------------------------------- |\n| `GJC_COMMIT_TEST_FALLBACK` | If `true` (case-insensitive), force commit fallback generation path |\n| `GJC_COMMIT_NO_FALLBACK`   | If `true`, disables fallback when agent returns no proposal         |\n| `GJC_COMMIT_MAP_REDUCE`    | If `false`, disables map-reduce commit analysis path                |\n| `DEBUG`                   | If set, commit agent error stack traces are printed                 |\n\n---\n\n## Security-sensitive variables\n\nTreat these as secrets; do not log or commit them:\n\n- Provider/API keys and OAuth/bearer credentials (all `*_API_KEY`, `*_TOKEN`, OAuth access/refresh tokens)\n- Cloud credentials (`AWS_*`, `GOOGLE_APPLICATION_CREDENTIALS` path may expose service-account material)\n- Search/provider auth vars (`EXA_API_KEY`, `BRAVE_API_KEY`, `PERPLEXITY_API_KEY`, Anthropic search keys)\n- Foundry mTLS material (`ANTHROPIC_MODEL_CODE_CLIENT_CERT`, `ANTHROPIC_MODEL_CODE_CLIENT_KEY`, `NODE_EXTRA_CA_CERTS` when it points to private CA bundles)\n\nPython runtime also explicitly strips many common key vars before spawning kernel subprocesses (`packages/coding-agent/src/eval/py/runtime.ts`).\n",
 	"fs-scan-cache-architecture.md": "# Filesystem Scan Cache Architecture Contract\n\nThis document defines the current contract for the shared filesystem scan cache implemented in Rust (`crates/pi-natives/src/fs_cache.rs`) and consumed by native discovery/search APIs exposed to `packages/coding-agent`.\n\n## What this cache is\n\nThe cache stores full directory-scan entry lists (`GlobMatch[]`) keyed by scan scope and traversal policy, then lets higher-level operations (glob filtering, fuzzy scoring, grep file selection) run against those cached entries.\n\nPrimary goals:\n\n- avoid repeated filesystem walks for repeated discovery/search calls\n- keep consistency across `glob`, `fuzzyFind`, and `grep` when they share the same scan policy\n- allow explicit staleness recovery for empty results and explicit invalidation after file mutations\n\n## Ownership and public surface\n\n- Cache implementation and policy: `crates/pi-natives/src/fs_cache.rs`\n- Native consumers:\n  - `crates/pi-natives/src/glob.rs`\n  - `crates/pi-natives/src/fd.rs` (`fuzzyFind`)\n  - `crates/pi-natives/src/grep.rs`\n- JS binding/export:\n  - `packages/natives/src/glob/index.ts` (`invalidateFsScanCache`)\n  - `packages/natives/src/glob/types.ts`\n  - `packages/natives/src/grep/types.ts`\n- Coding-agent mutation invalidation helpers:\n  - `packages/coding-agent/src/tools/fs-cache-invalidation.ts`\n\n## Cache key partitioning (hard contract)\n\nEach entry is keyed by:\n\n- canonicalized `root` directory path\n- `include_hidden` boolean\n- `use_gitignore` boolean\n- `skip_node_modules` boolean\n\nImplications:\n\n- Hidden and non-hidden scans do **not** share entries.\n- Gitignore-respecting and ignore-disabled scans do **not** share entries.\n- Scans that prune `node_modules` do **not** share entries with scans that include it.\n- Consumers must pass stable semantics for hidden/gitignore/node_modules behavior; changing any flag creates a different cache partition.\n\n## Scan collection behavior\n\nCache population uses a deterministic walker (`ignore::WalkBuilder`) configured by `include_hidden`, `use_gitignore`, and `skip_node_modules`:\n\n- `follow_links(false)`\n- sorted by file path\n- `.git` is always skipped\n- `node_modules` is pruned at traversal time when `skip_node_modules=true`\n- entry file type + `mtime` are captured via `symlink_metadata`\n\nSearch roots are resolved by `resolve_search_path`:\n\n- relative paths are resolved against current cwd\n- target must be an existing directory\n- root is canonicalized when possible\n\n## Freshness and eviction policy\n\nGlobal policy (environment-overridable):\n\n- `FS_SCAN_CACHE_TTL_MS` (default `1000`)\n- `FS_SCAN_EMPTY_RECHECK_MS` (default `200`)\n- `FS_SCAN_CACHE_MAX_ENTRIES` (default `16`)\n\nBehavior:\n\n- `get_or_scan(...)`\n  - if TTL is `0`: bypass cache entirely, always fresh scan (`cache_age_ms = 0`)\n  - on cache hit within TTL: return cached entries + non-zero `cache_age_ms`\n  - on expired hit: evict key, rescan, store fresh entry\n- max entry enforcement is oldest-first eviction by `created_at`\n\n## Empty-result fast recheck (separate from normal hits)\n\nNormal cache hit:\n\n- a cache hit inside TTL returns cached entries and does nothing else.\n\nEmpty-result fast recheck:\n\n- this is a **caller-side** policy using `ScanResult.cache_age_ms`\n- if filtered/query result is empty and cached scan age is at least `empty_recheck_ms()`, caller performs one `force_rescan(...)` and retries\n- intended to reduce stale-negative results when files were recently added but cache is still within TTL\n\nCurrent consumers:\n\n- `glob`: rechecks when filtered matches are empty and scan age exceeds threshold\n- `fuzzyFind` (`fd.rs`): rechecks only when query is non-empty and scored matches are empty\n- `grep`: rechecks when selected candidate file list is empty\n\n## Consumer defaults and cache usage\n\nCache is opt-in on all exposed APIs (`cache?: boolean`, default `false`).\n\nCurrent defaults in native APIs:\n\n- `glob`: `hidden=false`, `gitignore=true`, `cache=false`, and `node_modules` included only when the pattern mentions `node_modules`\n- `fuzzyFind`: `hidden=false`, `gitignore=true`, `cache=false`, and `node_modules` is skipped\n- `grep`: `hidden=true`, `gitignore=true`, `cache=false`, and `node_modules` included only when the glob mentions `node_modules`\n\nCoding-agent callers today:\n\n- High-volume mention candidate discovery enables cache:\n  - `packages/coding-agent/src/utils/file-mentions.ts`\n  - profile: `hidden=true`, `gitignore=true`, `includeNodeModules=true`, `cache=true`\n- Tool-level `grep` integration currently disables scan cache (`cache: false`):\n  - `packages/coding-agent/src/tools/grep.ts`\n\n## Invalidation contract\n\nNative invalidation entrypoint:\n\n- `invalidateFsScanCache(path?: string)`\n  - with `path`: remove cache entries whose root is a prefix of target path\n  - without path: clear all scan cache entries\n\nPath handling details:\n\n- relative invalidation paths are resolved against cwd\n- invalidation attempts canonicalization\n- if target does not exist (e.g., delete), fallback canonicalizes parent and reattaches filename when possible\n- this preserves invalidation behavior for create/delete/rename where one side may not exist\n\n## Coding-agent mutation flow responsibilities\n\nCoding-agent code must invalidate after successful filesystem mutations.\n\nCentral helpers:\n\n- `invalidateFsScanAfterWrite(path)`\n- `invalidateFsScanAfterDelete(path)`\n- `invalidateFsScanAfterRename(oldPath, newPath)` (invalidates both sides when paths differ)\n\nCurrent mutation tool callsites:\n\n- `packages/coding-agent/src/tools/write.ts`\n- `packages/coding-agent/src/patch/index.ts` (hashline/patch/replace flows)\n\nRule: if a flow mutates filesystem content or location and bypasses these helpers, cache staleness bugs are expected.\n\n## Adding a new cache consumer safely\n\nWhen introducing cache use in a new scanner/search path:\n\n1. **Use stable scan policy inputs**\n   - decide hidden/gitignore/node_modules semantics first\n   - pass them consistently to `get_or_scan`/`force_rescan` so cache partitions are intentional\n\n2. **Treat cache data as pre-filtered only by traversal policy**\n   - apply tool-specific filtering (glob patterns, type filters, scoring) after retrieval\n   - never assume cached entries already reflect your higher-level filters\n\n3. **Implement empty-result fast recheck only for stale-negative risk**\n   - use `scan.cache_age_ms >= empty_recheck_ms()`\n   - retry once with `force_rescan(..., store=true, ...)`\n   - keep this path separate from normal cache-hit logic\n\n4. **Respect no-cache mode explicitly**\n   - when caller disables cache, call `force_rescan(..., store=false, ...)`\n   - do not populate shared cache in a no-cache request path\n\n5. **Wire mutation invalidation for any new write path**\n   - after successful write/edit/delete/rename, call the coding-agent invalidation helper\n   - for rename/move, invalidate both old and new paths\n\n6. **Do not add per-call TTL knobs**\n   - current contract is global policy only (env-configured), no per-request TTL override\n\n## Known boundaries\n\n- Cache scope is process-local in-memory (`DashMap`), not persisted across process restarts.\n- Cache stores scan entries, not final tool results.\n- `glob`/`fuzzyFind`/`grep` share scan entries only when key dimensions (`root`, `hidden`, `gitignore`, `skip_node_modules`) match.\n- `.git` is always excluded at scan collection time regardless of caller options.\n",
+	"gjc-dogfood-skill-template.md": "# GJC dogfood local skill template\n\nIssue #93 requested a gaebal-gajae/operator dogfood skill. The live issue has no comment approving a fifth bundled default workflow skill, so this stays a local template instead of changing the default workflow surface. Operators can copy it into a user or project override when they want GJC-first session guidance:\n\n```sh\nmkdir -p ~/.gjc/skills/gjc-dogfood\ncp docs/gjc-dogfood-skill-template.md ~/.gjc/skills/gjc-dogfood/SKILL.md\n```\n\nFor a single project, copy it to `<project>/.gjc/skills/gjc-dogfood/SKILL.md` instead. Do not commit that project `.gjc` copy unless the project explicitly wants a local override.\n\n---\nname: gjc-dogfood\ndescription: Use when running or reviewing work through GJC sessions, dogfooding Gajae-Code, or migrating an operator workflow from OMX to GJC.\n---\n\n# GJC Dogfood Operator Workflow\n\nUse GJC first for coding, review, planning, and follow-up sessions. Treat OMX as a fallback only when GJC is unavailable, broken, or missing a required capability.\n\n## Locate and launch GJC\n\n- Installed CLI: run `command -v gjc` and then launch with `gjc --tmux`.\n- Repository checkout: from the gajae-code repo, prefer `bun packages/coding-agent/src/cli.ts --tmux` when testing source changes before install.\n- Worktree isolation: for branch-specific work, launch from or point at the branch worktree with `gjc --tmux --worktree <path>`.\n- Name sessions explicitly with the project and issue, for example `gajae-code-93-dogfood-skill`, so tmux panes, logs, and exports remain traceable.\n\n## Start the session\n\n- Put git operations inside the GJC session: fetch, branch/worktree setup, focused commits, pushes, and PR creation should be visible in-session.\n- Submit the initial prompt with the issue URL, target branch, acceptance criteria, verification limits, and any existing plan/spec link.\n- Verify the prompt was accepted: the TUI should show the user prompt, an active assistant turn, or a tool/action request. If the session silently idles, resend once with a shorter prompt and capture the failure.\n- Verify working state before leaving the session unattended: confirm the target cwd/worktree, branch, and issue scope are visible in the transcript or command output.\n\n## During work\n\n- Keep session names and branch names issue-scoped.\n- Prefer GJC workflow skills only when they fit: `deep-interview` for unclear requirements, `ralplan` for planning, `ultragoal` for durable ledgers, and `team` for coordinated tmux execution.\n- Keep evidence in the session: issue reads, focused tests/checks, screenshots only when visual behavior matters, and PR URLs.\n- When GJC is weaker than OMX, finish the urgent work with the smallest safe fallback and file a gajae-code follow-up issue with the missing capability, exact command/session context, expected behavior, and evidence.\n\n## Fallback policy\n\nUse OMX or another operator path only when:\n\n- `gjc` cannot be located or launched after checking installed and repo-local commands;\n- authentication, model routing, tmux, or prompt submission is broken;\n- GJC lacks a required capability that OMX already has;\n- an urgent production/review deadline would be missed by debugging GJC first.\n\nRecord the fallback reason and create or link the gajae-code issue that would make GJC sufficient next time.\n\n## Evidence checklist\n\nReport:\n\n- project, issue, branch/worktree, and session name;\n- whether GJC was installed or repo-local;\n- prompt acceptance and working-state evidence;\n- git operations performed in-session;\n- focused verification commands and results;\n- PR/issue URLs;\n- follow-up gajae-code issues for any GJC gap or fallback.\n",
 	"handoff-generation-pipeline.md": "# `/handoff` generation pipeline\n\nThis document describes how the coding-agent implements `/handoff`: trigger path, oneshot generation, session switch, context reinjection, persistence, and UI behavior.\n\n## Scope\n\nCovers:\n\n- Interactive `/handoff` command dispatch\n- `AgentSession.handoff()` lifecycle and state transitions\n- `generateHandoff(...)` request shape\n- How old/new sessions persist handoff data differently\n- UI behavior for success, cancel, and failure\n\nDoes not cover:\n\n- Generic tree navigation/branch internals\n- Non-handoff session commands (`/new`, `/fork`, `/resume`)\n\n## Implementation files\n\n- [`../src/modes/controllers/input-controller.ts`](../packages/coding-agent/src/modes/controllers/input-controller.ts)\n- [`../src/modes/controllers/command-controller.ts`](../packages/coding-agent/src/modes/controllers/command-controller.ts)\n- [`../src/session/agent-session.ts`](../packages/coding-agent/src/session/agent-session.ts)\n- [`packages/agent/src/compaction/compaction.ts`](../packages/agent/src/compaction/compaction.ts)\n- [`../src/session/session-manager.ts`](../packages/coding-agent/src/session/session-manager.ts)\n- [`../src/extensibility/slash-commands.ts`](../packages/coding-agent/src/extensibility/slash-commands.ts)\n\n## Trigger path\n\n1. `/handoff` is declared in builtin slash command metadata (`slash-commands.ts`) with optional inline hint: `[focus instructions]`.\n2. In interactive input handling (`InputController`), submit text matching `/handoff` or `/handoff ...` is intercepted before normal prompt submission.\n3. The editor is cleared and `handleHandoffCommand(customInstructions?)` is called.\n4. `CommandController.handleHandoffCommand` performs a preflight guard using current entries:\n   - Counts `type === \"message\"` entries.\n   - If `< 2`, it warns: `Nothing to hand off (no messages yet)` and returns.\n\nThe same minimum-content guard exists again inside `AgentSession.handoff()` and throws if violated. This duplicates safety at both UI and session layers.\n\n## End-to-end lifecycle\n\n### 1) Start handoff generation\n\n`AgentSession.handoff(customInstructions?)`:\n\n- Reads current branch entries (`sessionManager.getBranch()`).\n- Validates minimum message count (`>= 2`).\n- Creates `#handoffAbortController` and links any caller-provided abort signal to it.\n- Resolves the current model API key through `ModelRegistry`.\n- Calls `generateHandoff(...)` with:\n  - live agent messages (`agent.state.messages`),\n  - the current model and API key,\n  - the base system prompt (`#baseSystemPrompt`),\n  - the live tool array (`agent.state.tools`),\n  - optional focus instructions,\n  - coding-agent message conversion (`convertToLlm`),\n  - provider metadata and `initiatorOverride: \"agent\"`.\n\n`generateHandoff(...)` lives in `packages/agent/src/compaction/compaction.ts` next to summarization. It renders `packages/agent/src/compaction/prompts/handoff-document.md` via `renderHandoffPrompt(...)` with optional `additionalFocus`.\n\n### 2) Generate and capture output\n\n`generateHandoff(...)` converts the existing `AgentMessage[]` history to real LLM `Message[]` history, then appends one trailing agent-attributed `user` message containing the rendered handoff prompt.\n\nThe request uses `completeSimple(...)` directly:\n\n```ts\nawait completeSimple(\n  model,\n  {\n    systemPrompt,\n    messages: requestMessages,\n    tools,\n  },\n  {\n    apiKey,\n    signal,\n    reasoning: Effort.High,\n    toolChoice: \"none\",\n    initiatorOverride,\n    metadata,\n  },\n);\n```\n\nImportant generation properties:\n\n- The request preserves the live provider cache prefix by reusing the same system prompt, tool definitions, and real message history shape as the active agent.\n- The handoff instruction is a trailing `user` message, not a developer message, so the cached prefix remains aligned with the prior turn.\n- `toolChoice: \"none\"` prevents intentional tool dispatch.\n- The returned assistant content is filtered to text blocks and joined with `\\n`; stray tool-call blocks are ignored if a provider does not honor `toolChoice: \"none\"`.\n- `stopReason === \"error\"` throws a generation error.\n\nNo agent-loop events are used for capture. The handoff path no longer waits for `agent_end` and no longer scans the latest assistant message.\n\n### 3) Cancellation checks\n\nCancellation throws `Error(\"Handoff cancelled\")`; a completed generation with no text returns `undefined`.\n\n- caller signal aborts `#handoffAbortController`\n- `completeSimple(...)` receives the abort signal\n- aborted handoff signal or provider `AbortError` is normalized to `Error(\"Handoff cancelled\")`\n- empty generated text returns `undefined`\n\n`AgentSession.handoff()` always clears `#handoffAbortController` in `finally`.\n\n### 4) New session creation\n\nIf text was generated and not aborted:\n\n1. Flush current session writer (`sessionManager.flush()`).\n2. Cancel session-owned async jobs.\n3. Start a brand-new session with `parentSession` pointing at the previous session file when one exists.\n4. Reset in-memory agent state (`agent.reset()`).\n5. Rebind `agent.sessionId` to the new session id.\n6. Rekey/reset hindsight state for the new session.\n7. Clear queued context arrays (`#steeringMessages`, `#followUpMessages`, `#pendingNextTurnMessages`) and any scheduled hidden next-turn generation.\n8. Reset todo reminder counter.\n\n### 5) Handoff-context injection\n\nThe generated handoff document is wrapped by coding-agent session glue and appended to the new session as a `custom_message` entry:\n\n```text\n<handoff-context>\n...handoff text...\n</handoff-context>\n\nThe above is a handoff document from a previous session. Use this context to continue the work seamlessly.\n```\n\nInsertion call:\n\n```ts\nthis.sessionManager.appendCustomMessageEntry(\"handoff\", handoffContent, true, undefined, \"agent\");\n```\n\nSemantics:\n\n- `customType`: `\"handoff\"`\n- `display`: `true` (visible in TUI rebuild)\n- attribution: `\"agent\"`\n- Entry type: `custom_message` (participates in LLM context)\n\n### 6) Rebuild active agent context\n\nAfter injection:\n\n1. `buildDisplaySessionContext()` resolves message list for current leaf.\n2. `agent.replaceMessages(sessionContext.messages)` makes the injected handoff message active context.\n3. Todo phases are synchronized from the new branch.\n4. Method returns `{ document: handoffText, savedPath? }`.\n\nAt this point, the active LLM context in the new session contains the injected handoff message, not the old transcript.\n\n## Persistence model: old session vs new session\n\n### Old session\n\nHandoff generation is a oneshot request, not a visible agent turn. The generated handoff text is not appended to the old session as an assistant message.\n\nResult: the original session keeps its prior transcript unchanged except for data already persisted before handoff began.\n\n### New session\n\nAfter session reset, handoff is persisted as `custom_message` with `customType: \"handoff\"`.\n\n`buildSessionContext()` converts this entry into a runtime custom/user-context message via `createCustomMessage(...)`, so it is included in future prompts from the new session.\n\nAuto-triggered handoffs can additionally write a timestamped `handoff-*.md` artifact under the session artifacts directory when `compaction.handoffSaveToDisk` is enabled. Manual `/handoff` does not write that artifact.\n\n## Controller/UI behavior\n\n`CommandController.handleHandoffCommand` behavior:\n\n- Shows a status loader: `Generating handoff… (esc to cancel)`.\n- Calls `await session.handoff(customInstructions)`.\n- If result is `undefined`: `showError(\"Handoff cancelled\")`.\n- On success:\n  - `rebuildChatFromMessages()` (loads new session context, including injected handoff)\n  - invalidates status line and editor top border\n  - reloads todos\n  - appends success chat line: `New session started with handoff context`\n- On exception:\n  - if message is `\"Handoff cancelled\"` or error name is `AbortError`: `showError(\"Handoff cancelled\")`\n  - otherwise: `showError(\"Handoff failed: <message>\")`\n- Stops the loader, restores the previous Escape handler, and requests render at end.\n\nManual `/handoff` no longer streams the generated document into chat. A cancellable loader remains visible while the oneshot request runs, and the chat is rebuilt after generation completes.\n\n## Cancellation semantics\n\n### Session-level cancellation primitive\n\n`AgentSession` exposes:\n\n- `abortHandoff()` → aborts `#handoffAbortController`\n- `isGeneratingHandoff` → true while controller exists\n\nWhen this abort path is used, the abort signal is passed to `completeSimple(...)`; `handoff()` normalizes the cancellation to `Error(\"Handoff cancelled\")`, and command controller maps it to cancellation UI.\n\n### Interactive `/handoff` path\n\nThe command controller installs a temporary Escape handler for `/handoff` while the loader is visible. Pressing Escape calls `session.abortHandoff()`, which aborts the `completeSimple(...)` request through `#handoffAbortController`.\n\n## Aborted vs failed handoff\n\nCurrent UI classification:\n\n- **Aborted/cancelled**\n  - `abortHandoff()` path triggers `\"Handoff cancelled\"`, or\n  - thrown `AbortError`\n  - UI shows `Handoff cancelled`\n- **Failed**\n  - any other thrown error from `handoff()` / `generateHandoff()` / provider request path\n  - UI shows `Handoff failed: ...`\n\nAdditional nuance: if generation completes but no text is returned, `handoff()` returns `undefined` and controller currently reports **cancelled**, not **failed**.\n\n## Short-session and minimum-content guardrails\n\nTwo guards prevent low-signal handoffs:\n\n- UI layer (`handleHandoffCommand`): warns and returns early for `< 2` message entries\n- Session layer (`handoff()`): throws the same condition as an error\n\nThis avoids creating a new session with empty/near-empty handoff context.\n\n## State transition summary\n\nHigh-level state flow:\n\n1. Interactive slash command intercepted.\n2. Preflight message-count guard.\n3. `#handoffAbortController` created (`isGeneratingHandoff = true`).\n4. `generateHandoff(...)` issues one `completeSimple(...)` request with live system prompt, tools, message history, and trailing handoff prompt.\n5. Assistant response text blocks are joined; tool-call blocks are discarded.\n6. If missing text → return `undefined`; if aborted → cancellation error path.\n7. If present:\n   - flush old session\n   - cancel async jobs\n   - create new empty session with previous session as parent\n   - reset runtime queues/counters\n   - append `custom_message(handoff)`\n   - optionally save an auto-triggered handoff document under the session artifacts directory when `compaction.handoffSaveToDisk` is enabled\n8. Controller rebuilds chat UI and announces success.\n9. `#handoffAbortController` cleared (`isGeneratingHandoff = false`).\n\n## Known assumptions and limitations\n\n- No structural validation checks that generated markdown follows the requested section format.\n- Missing generated text is reported as cancellation in controller UX.\n- Manual handoff has no streaming visibility; a cancellable loader is shown until the UI updates after generation completes.\n- Auto-triggered handoffs can write a timestamped `handoff-*.md` artifact when `compaction.handoffSaveToDisk` is enabled; write failure is logged and does not fail the handoff.\n",
 	"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        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\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-code-responses`\n- `azure-openai-responses`\n- `anthropic-messages`\n- `google-generative-ai`\n- `google-vertex`\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- `discovery.type`: `ollama`, `llama.cpp`, or `lm-studio`\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- `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\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`, `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-code-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-code-responses`, session provider state key `openai-code-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\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",
 	"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",