@gajae-code/coding-agent 0.6.0 → 0.6.1

package/CHANGELOG.md

@@ -2,6 +2,12 @@
 
 ## [Unreleased]
 
+## [0.6.1] - 2026-06-18
+
+### Fixed
+
+- Fixed the `computer` tool (and any other `z.union`/discriminated-union tool) shipping a bare top-level `anyOf`/`oneOf`/`allOf` `input_schema` root that strict providers (Amazon Bedrock Converse incl. Kiro/CodeWhisperer relays, OpenAI strict mode, Gemini) reject. Tool schema roots are now flattened to a single `type: "object"` across all providers via the shared `flattenToolRootCombinators`. See `@gajae-code/ai` 0.6.1.
+
 ## [0.6.0] - 2026-06-18
 ### Added
 

package/package.json

@@ -1,7 +1,7 @@
 {
 	"type": "module",
 	"name": "@gajae-code/coding-agent",
-	"version": "0.6.0",
+	"version": "0.6.1",
 	"description": "Gajae Code CLI with read, bash, edit, write tools and session management",
 	"homepage": "https://gaebal-gajae.dev",
 	"author": "Yeachan-Heo",
@@ -51,12 +51,12 @@
 		"@agentclientprotocol/sdk": "0.21.0",
 		"@babel/parser": "^7.29.3",
 		"@mozilla/readability": "^0.6.0",
-		"@gajae-code/stats": "0.6.0",
-		"@gajae-code/agent-core": "0.6.0",
-		"@gajae-code/ai": "0.6.0",
-		"@gajae-code/natives": "0.6.0",
-		"@gajae-code/tui": "0.6.0",
-		"@gajae-code/utils": "0.6.0",
+		"@gajae-code/stats": "0.6.1",
+		"@gajae-code/agent-core": "0.6.1",
+		"@gajae-code/ai": "0.6.1",
+		"@gajae-code/natives": "0.6.1",
+		"@gajae-code/tui": "0.6.1",
+		"@gajae-code/utils": "0.6.1",
 		"@puppeteer/browsers": "^2.13.0",
 		"@types/turndown": "5.0.6",
 		"@xterm/headless": "^6.0.0",

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","bot-integration.md","brand-assets.md","bridge.md","codebase-overview.md","compaction.md","composer-codex-parity.md","computer-use/README.md","environment-variables.md","external-control-readiness.md","fs-scan-cache-architecture.md","gajae-remote.md","geobench.md","gjc-dogfood-skill-template.md","grok-build-provider-design.md","handoff-generation-pipeline.md","hermes-mcp-bridge.md","hotspot-map-successor.md","keybindings.md","lsp-config.md","memory.md","models.md","native-ffi-optimization-policy.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","onboarding-packet.md","onboarding-receipt.md","ooo-bridge-extension-contract.md","openclaw-hermes-rpc-integration.md","perf-profiling-corpus.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","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","telegram-remote.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.md","tools/checkpoint.md","tools/computer.md","tools/cron.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/monitor.md","tools/read.md","tools/recipe.md","tools/render_mermaid.md","tools/resolve.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md"];
+export const EMBEDDED_DOC_FILENAMES: readonly string[] = ["ERRATA-GPT5-HARMONY.md","REBRANDING_PLAN_260525.md","ai-schema-normalize.md","auth-broker-gateway.md","bash-tool-runtime.md","blob-artifact-architecture.md","bot-integration.md","brand-assets.md","bridge.md","codebase-overview.md","compaction.md","composer-codex-parity.md","computer-use/README.md","environment-variables.md","external-control-readiness.md","fs-scan-cache-architecture.md","gajae-remote.md","geobench.md","gjc-dogfood-skill-template.md","grok-build-provider-design.md","handoff-generation-pipeline.md","hermes-mcp-bridge.md","hotspot-map-successor.md","keybindings.md","lsp-config.md","memory.md","models.md","multi-vendor-profiles.md","native-ffi-optimization-policy.md","natives-addon-loader-runtime.md","natives-architecture.md","natives-binding-contract.md","natives-build-release-debugging.md","natives-media-system-utils.md","natives-rust-task-cancellation.md","natives-shell-pty-process.md","natives-text-search-pipeline.md","non-compaction-retry-policy.md","notebook-tool-runtime.md","onboarding-packet.md","onboarding-receipt.md","ooo-bridge-extension-contract.md","openclaw-hermes-rpc-integration.md","perf-profiling-corpus.md","porting-from-pi-mono.md","porting-to-natives.md","provider-streaming-internals.md","python-repl.md","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","telegram-remote.md","theme.md","tools/ask.md","tools/ast-edit.md","tools/ast-grep.md","tools/bash.md","tools/browser.md","tools/calc.md","tools/checkpoint.md","tools/computer.md","tools/cron.md","tools/debug.md","tools/edit.md","tools/eval.md","tools/find.md","tools/github.md","tools/inspect_image.md","tools/irc.md","tools/job.md","tools/lsp.md","tools/monitor.md","tools/read.md","tools/recipe.md","tools/render_mermaid.md","tools/resolve.md","tools/rewind.md","tools/search.md","tools/search_tool_bm25.md","tools/ssh.md","tools/task.md","tools/todo_write.md","tools/web_search.md","tools/write.md","tree.md","ttsr-injection-lifecycle.md","tui-runtime-internals.md"];
 
 export const EMBEDDED_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.",
@@ -29,7 +29,8 @@ export const EMBEDDED_DOCS: Readonly<Record<string, string>> = {
 	"keybindings.md": "# Keybindings\n\nRun `/hotkeys` inside an `gjc` session to see the active chords for your current build. The list reflects any remaps loaded from disk and any bindings added by extensions.\n\n## Customize keybindings\n\nUser remaps live in `~/.gjc/agent/keybindings.json`. The file is a JSON object whose keys are keybinding action IDs and whose values are either one chord string or an array of chord strings. It is not read from `~/.gjc/agent/config.yml`, and there is no nested `keybindings` object.\n\n```json\n{\n  \"app.model.cycleForward\": \"Ctrl+P\",\n  \"app.model.selectTemporary\": \"Alt+P\",\n  \"app.plan.toggle\": \"Alt+Shift+P\"\n}\n```\n\nChord names are case-insensitive and use the same notation shown in the UI, such as `Ctrl+P`, `Alt+Shift+P`, `Shift+Enter`, and `Ctrl+Backspace`.\n\nSet an action to an empty array to disable it:\n\n```json\n{\n  \"app.stt.toggle\": []\n}\n```\n\n## Common action IDs\n\n| Action ID | Default | Meaning |\n| --- | --- | --- |\n| `app.model.cycleForward` | `Ctrl+P` | Cycle role models forward |\n| `app.model.cycleBackward` | `Shift+Ctrl+P` | Cycle role models backward |\n| `app.model.selectTemporary` | `Alt+P` | Pick a model temporarily for this session |\n| `app.model.select` | `Ctrl+L` | Open the model selector and set roles |\n| `app.plan.toggle` | `Alt+Shift+P` | Toggle plan mode |\n| `app.history.search` | `Ctrl+R` | Search prompt history |\n| `app.tools.expand` | `Ctrl+O` | Toggle tool-output expansion |\n| `app.thinking.toggle` | `Ctrl+T` | Toggle thinking-block visibility |\n| `app.thinking.cycle` | `Shift+Tab` | Cycle thinking level |\n| `app.editor.external` | `Ctrl+G` | Edit the draft in `$VISUAL` / `$EDITOR` |\n| `app.message.followUp` | `Ctrl+Enter` | Send a follow-up message |\n| `app.message.queue` | `Alt+Enter` | Explicitly queue a message for the next turn |\n| `app.message.dequeue` | `Alt+Up` | Dequeue a queued message back into the editor |\n| `app.clipboard.copyLine` | `Alt+Shift+L` | Copy the current line |\n| `app.clipboard.copyPrompt` | `Alt+Shift+C` | Copy the whole prompt |\n| `app.stt.toggle` | `Alt+H` | Toggle speech-to-text recording |\n\nOlder unqualified action names are migrated when `keybindings.json` is loaded, but new docs and new configs should use the namespaced action IDs above.\n",
 	"lsp-config.md": "# LSP configuration in GJC\n\nThis guide explains how to configure language servers for the GJC coding agent.\n\nSource of truth in code:\n\n- Server config type: `packages/coding-agent/src/lsp/types.ts` (`ServerConfig`)\n- Config loader: `packages/coding-agent/src/lsp/config.ts`\n- Built-in server definitions: `packages/coding-agent/src/lsp/defaults.json`\n\n## Auto-detection\n\nWhen no LSP config file is present, GJC auto-detects servers by intersecting two conditions:\n\n1. The project directory contains at least one of the server's `rootMarkers`.\n2. The server binary is available — checked in project-local bin directories first (e.g., `node_modules/.bin/`, `.venv/bin/`), then `$PATH`.\n\nNo configuration is required for common setups. The built-in server list covers most popular languages; see [`defaults.json`](../packages/coding-agent/src/lsp/defaults.json) for the full set.\n\n## Config file locations\n\nGJC merges LSP config from multiple files, lowest to highest priority:\n\n| Priority | Location |\n|----------|----------|\n| 5 (lowest) | `~/lsp.json`, `~/.lsp.json`, `~/lsp.yaml`, `~/.lsp.yaml` |\n| 3 | `~/.gjc/agent/lsp.json`, `~/.gjc/agent/lsp.yaml`, `~/.gemini/lsp.*` |\n| 2 | `<project>/.gjc/lsp.json`, `<project>/.gjc/lsp.yaml`, `<project>/.gemini/lsp.*` |\n| 1 (highest) | `<project>/lsp.json`, `<project>/.lsp.json`, `<project>/lsp.yaml` |\n\nEach location accepts both `.json` and `.yaml` / `.yml` variants, as well as hidden-file versions (`.lsp.json`, `.lsp.yaml`). Files are merged in order: higher-priority files override lower-priority fields for the same server. Servers not mentioned in any override file remain at their built-in defaults.\n\n**Recommended locations:**\n\n- User-wide preferences → `~/.gjc/agent/lsp.json`\n- Project-specific overrides → `<project>/.gjc/lsp.json`\n\n> **Note:** The presence of any LSP config file disables auto-detection. When at least one file is found, GJC skips the binary-scan phase and loads all servers that have matching `rootMarkers`, an available binary, and are not explicitly `disabled`.\n\n## File shape\n\nBoth JSON and YAML are accepted. The top-level object can use either a `servers` wrapper key or a flat map directly:\n\n```json\n{\n  \"servers\": {\n    \"server-name\": { ... }\n  },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nor (flat, without the `servers` wrapper):\n\n```json\n{\n  \"server-name\": { ... },\n  \"idleTimeoutMs\": 300000\n}\n```\n\nTop-level keys:\n\n- `servers` — map of server name to `ServerConfig` (optional wrapper; flat form is equivalent)\n- `idleTimeoutMs` — shut down idle language servers after this many milliseconds; disabled by default\n\n## ServerConfig fields\n\n| Field | Type | Required | Description |\n|-------|------|----------|-------------|\n| `command` | `string` | yes | Binary name (resolved via PATH/local bins) or absolute path |\n| `args` | `string[]` | no | Arguments passed to the binary |\n| `fileTypes` | `string[]` | yes | File extensions this server handles, e.g. `[\".ts\", \".tsx\"]` |\n| `rootMarkers` | `string[]` | yes | Files/dirs that indicate a project root; glob patterns (e.g. `*.cabal`) are supported |\n| `initOptions` | `object` | no | Sent as `initializationOptions` during LSP handshake |\n| `settings` | `object` | no | Workspace settings pushed via `workspace/didChangeConfiguration` |\n| `disabled` | `boolean` | no | Set to `true` to disable this server entirely |\n| `warmupTimeoutMs` | `number` | no | Startup timeout in ms for this server (overrides the global default) |\n| `isLinter` | `boolean` | no | Mark server as linter/formatter only; excluded from type-intelligence operations (hover, go-to-definition, etc.) |\n| `capabilities` | `object` | no | Opt-in server-specific features; see [Capabilities](#capabilities) |\n\n`resolvedCommand` is populated automatically at runtime — do not set it manually.\n\n### Capabilities\n\nThe `capabilities` object enables optional server-specific features that GJC supports on a per-server basis:\n\n```json\n{\n  \"capabilities\": {\n    \"flycheck\": true,\n    \"ssr\": true,\n    \"expandMacro\": true,\n    \"runnables\": true,\n    \"relatedTests\": true\n  }\n}\n```\n\nAll fields are boolean and optional. They are currently used by `rust-analyzer`.\n\n## Common recipes\n\n### Override a built-in server's settings\n\nPartial overrides are merged onto the built-in defaults. You only need to specify the fields you want to change.\n\n```json\n{\n  \"servers\": {\n    \"typescript-language-server\": {\n      \"args\": [\"--stdio\", \"--log-level\", \"4\"]\n    }\n  }\n}\n```\n\n```yaml\nservers:\n  gopls:\n    settings:\n      gopls:\n        gofumpt: false\n        staticcheck: false\n```\n\n### Disable a built-in server\n\n```json\n{\n  \"servers\": {\n    \"eslint\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\n### Register a custom server\n\nNew servers require `command`, `fileTypes`, and `rootMarkers`. All other fields are optional.\n\n```json\n{\n  \"servers\": {\n    \"my-lsp\": {\n      \"command\": \"my-lsp-server\",\n      \"args\": [\"--stdio\"],\n      \"fileTypes\": [\".xyz\"],\n      \"rootMarkers\": [\".xyz-project\", \".git\"]\n    }\n  }\n}\n```\n\n### Set a global idle timeout\n\nShut down language servers that have been inactive for more than five minutes:\n\n```json\n{\n  \"idleTimeoutMs\": 300000\n}\n```\n\n### Disable a server for one project, keep it globally\n\nPlace the override in `<project>/.gjc/lsp.json`:\n\n```json\n{\n  \"servers\": {\n    \"pylsp\": {\n      \"disabled\": true\n    }\n  }\n}\n```\n\nThe user-level config in `~/.gjc/agent/lsp.json` is unaffected; pylsp is only suppressed in this project.\n\n## Built-in server list\n\nThe following servers ship in `defaults.json` and are eligible for auto-detection:\n\n| Server key | Language(s) | Binary |\n|---|---|---|\n| `rust-analyzer` | Rust | `rust-analyzer` |\n| `clangd` | C, C++, ObjC | `clangd` |\n| `zls` | Zig | `zls` |\n| `gopls` | Go | `gopls` |\n| `typescript-language-server` | TypeScript, JavaScript | `typescript-language-server` |\n| `denols` | TypeScript, JavaScript (Deno) | `deno` |\n| `biome` | TS/JS/JSON (linter) | `biome` |\n| `eslint` | TS/JS/Vue/Svelte (linter) | `vscode-eslint-language-server` |\n| `vscode-html-language-server` | HTML | `vscode-html-language-server` |\n| `vscode-css-language-server` | CSS, SCSS, Less | `vscode-css-language-server` |\n| `vscode-json-language-server` | JSON | `vscode-json-language-server` |\n| `tailwindcss` | HTML, CSS, TS/JS | `tailwindcss-language-server` |\n| `svelte` | Svelte | `svelteserver` |\n| `vue-language-server` | Vue | `vue-language-server` |\n| `astro` | Astro | `astro-ls` |\n| `pyright` | Python | `pyright-langserver` |\n| `basedpyright` | Python | `basedpyright-langserver` |\n| `pylsp` | Python | `pylsp` |\n| `ruff` | Python (linter) | `ruff` |\n| `jdtls` | Java | `jdtls` |\n| `kotlin-lsp` | Kotlin | `kotlin-lsp` |\n| `metals` | Scala | `metals` |\n| `hls` | Haskell | `haskell-language-server-wrapper` |\n| `ocamllsp` | OCaml | `ocamllsp` |\n| `elixirls` | Elixir | `elixir-ls` |\n| `erlangls` | Erlang | `erlang_ls` |\n| `gleam` | Gleam | `gleam` |\n| `solargraph` | Ruby | `solargraph` |\n| `ruby-lsp` | Ruby | `ruby-lsp` |\n| `rubocop` | Ruby (linter) | `rubocop` |\n| `bashls` | Bash, Zsh | `bash-language-server` |\n| `lua-language-server` | Lua | `lua-language-server` |\n| `intelephense` | PHP | `intelephense` |\n| `phpactor` | PHP | `phpactor` |\n| `omnisharp` | C# | `omnisharp` |\n| `yamlls` | YAML | `yaml-language-server` |\n| `terraformls` | Terraform | `terraform-ls` |\n| `dockerls` | Dockerfile | `docker-langserver` |\n| `helm-ls` | Helm | `helm_ls` |\n| `nixd` | Nix | `nixd` |\n| `nil` | Nix | `nil` |\n| `ols` | Odin | `ols` |\n| `dartls` | Dart | `dart` |\n| `marksman` | Markdown | `marksman` |\n| `texlab` | LaTeX | `texlab` |\n| `graphql` | GraphQL | `graphql-lsp` |\n| `prismals` | Prisma | `prisma-language-server` |\n| `vimls` | Vim script | `vim-language-server` |\n| `emmet-language-server` | HTML, CSS, JSX | `emmet-language-server` |\n| `sourcekit-lsp` | Swift | `sourcekit-lsp` |\n| `swiftlint` | Swift (linter) | `swiftlint` |\n| `tlaplus` | TLA+ | `tlapm_lsp` |\n",
 	"memory.md": "# Autonomous Memory\n\nWhen enabled, the agent automatically extracts durable knowledge from past sessions and injects a compact summary into each new session. Over time it builds a project-scoped memory store — technical decisions, recurring workflows, pitfalls — that carries forward without manual effort.\n\nDisabled by default. Enable via `/settings` or `config.yml`:\n\n```yaml\nmemories:\n  enabled: true\n```\n\n## Usage\n\n### What gets injected\n\nAt session start, if a memory summary exists for the current project, it is injected into the system prompt as a **Memory Guidance** block. The agent is instructed to:\n\n- Treat memory as heuristic context — useful for process and prior decisions, not authoritative on current repo state.\n- Pair memory-influenced decisions with current-repo evidence before acting.\n- Prefer repo state and user instruction when they conflict with memory; treat conflicting memory as stale.\n\n### Memory artifacts\n\nGenerated local-memory artifacts are private runtime state, not a public tool or URI surface. They may be summarized into the system prompt when local memory is enabled, but users and model-facing tool docs should not rely on direct `memory://` reads. The legacy internal `memory://` resolver remains only for compatibility with existing persisted guidance and is not part of the public coding harness contract; remove it after legacy local-memory prompts no longer reference it.\n### `/memory` slash command\n\n| Subcommand            | Effect                                         |\n| --------------------- | ---------------------------------------------- |\n| `view`                | Show the current memory injection payload      |\n| `clear` / `reset`     | Delete all memory data and generated artifacts |\n| `enqueue` / `rebuild` | Force consolidation to run at next startup     |\n\n## How it works\n\nMemories are built by a background pipeline that runs at startup or when manually triggered via slash command.\n\n**Phase 1 — per-session extraction:** For each past session that has changed since it was last processed, a model reads the session history and extracts durable signal: technical decisions, constraints, resolved failures, recurring workflows. Sessions that are too recent, too old, or currently active are skipped. Each extraction produces a raw memory block and a short synopsis for that session.\n\n**Phase 2 — consolidation:** After extraction, a second model pass reads all per-session extractions and produces three outputs written to disk:\n\n- `MEMORY.md` — a curated long-term memory document\n- `memory_summary.md` — the compact text injected at session start\n- `skills/` — reusable procedural playbooks, each in its own subdirectory\n\nPhase 2 uses a lease to prevent double-running when multiple processes start simultaneously. Stale skill directories from prior runs are pruned automatically.\n\nAll output is scanned for secrets before being written to disk.\n\n### Extraction behavior\n\nMemory extraction and consolidation behavior is driven by static prompt files in `packages/coding-agent/src/prompts/memories/`.\n\n| File                  | Purpose                                     | Variables                                   |\n| --------------------- | ------------------------------------------- | ------------------------------------------- |\n| `stage_one_system.md` | System prompt for per-session extraction    | —                                           |\n| `stage_one_input.md`  | User-turn template wrapping session content | `{{thread_id}}`, `{{response_items_json}}`  |\n| `consolidation.md`    | Prompt for cross-session consolidation      | `{{raw_memories}}`, `{{rollout_summaries}}` |\n| `read_path.md`        | Memory guidance injected into live sessions | `{{memory_summary}}`                        |\n\n### Model selection\n\nMemory piggybacks on the model role system.\n\n| Phase                   | Role                                                                | Purpose                          |\n| ----------------------- | ------------------------------------------------------------------- | -------------------------------- |\n| Phase 1 (extraction)    | `default`                                                           | Per-session knowledge extraction |\n| Phase 2 (consolidation) | `smol` (falls back to `default`, then current/first registry model) | Cross-session synthesis          |\n\nIf the requested memory role is not configured, memory model resolution falls back to the `default` role, then the active session model, then the first model in the registry.\n\n## Configuration\n\n| Setting                               | Default | Description                                               |\n| ------------------------------------- | ------- | --------------------------------------------------------- |\n| `memories.enabled`                    | `false` | Master switch                                             |\n| `memories.maxRolloutAgeDays`          | `30`    | Sessions older than this are not processed                |\n| `memories.minRolloutIdleHours`        | `12`    | Sessions active more recently than this are skipped       |\n| `memories.maxRolloutsPerStartup`      | `64`    | Cap on sessions processed in a single startup             |\n| `memories.summaryInjectionTokenLimit` | `5000`  | Max tokens of the summary injected into the system prompt |\n\nAdditional tuning knobs (concurrency, lease durations, token budgets) are available in config for advanced use.\n\n## Key files\n\n- `packages/coding-agent/src/memories/index.ts` — pipeline orchestration, injection, slash command handling\n- `packages/coding-agent/src/memories/storage.ts` — SQLite-backed job queue and thread registry\n- `packages/coding-agent/src/prompts/memories/` — memory prompt templates\n- `packages/coding-agent/src/internal-urls/memory-protocol.ts` — legacy non-public `memory://` compatibility handler\n",
-	"models.md": "# Model and Provider Configuration (`models.yml`)\n\nThis document describes how the coding-agent currently loads models, applies overrides, resolves credentials, and chooses models at runtime.\n\n## What controls model behavior\n\nPrimary implementation files:\n\n- `src/config/model-registry.ts` — loads built-in + custom models, provider overrides, runtime discovery, auth integration\n- `src/config/model-resolver.ts` — parses model patterns and selects models for the default and agent roles\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.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    cacheRetention: short  # none | short | long; model entries and modelOverrides can override this\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n        cacheRetention: long\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        cacheRetention: none\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\nmodelBindings:\n  modelRoles:\n    default: my-provider/some-model-id:high\n  agentModelOverrides:\n    executor: my-provider/some-model-id\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `bedrock-converse-stream`\n- `anthropic-messages`\n- `bedrock-converse-stream`\n- `google-generative-ai`\n- `google-vertex`\n- `google-gemini-cli`\n- `ollama-chat`\n- `cursor-agent`\n\n\n### First-class Azure OpenAI and Amazon Bedrock examples\n\nAzure OpenAI uses canonical OpenAI model IDs in GJC and resolves those IDs to Azure deployment names at request time. Set `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` to avoid assuming model id equals deployment name:\n\n```yaml\nproviders:\n  azure-openai:\n    baseUrl: https://my-resource.openai.azure.com/openai/v1\n    apiKeyEnv: AZURE_OPENAI_API_KEY\n    api: azure-openai-responses\n    models:\n      - id: gpt-4.1\n      - id: o3\n```\n\n```sh\nexport AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-4.1=gpt-41-prod,o3=o3-reasoning-prod'\n```\n\nAmazon Bedrock uses the native `bedrock-converse-stream` transport and AWS credential chain auth. Do not put AWS access keys in `models.yml`; configure `AWS_REGION` / `AWS_PROFILE` or standard static AWS credential environment variables instead:\n\n```yaml\nproviders:\n  amazon-bedrock:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com\n    api: bedrock-converse-stream\n    models:\n      - id: us.anthropic.claude-opus-4-6-v1\n      - id: anthropic.claude-3-5-sonnet-20241022-v2:0\n```\n\n### MiniMax and GLM custom provider examples\n\nFor common MiniMax and GLM/zAI setup, prefer the provider presets so the OpenAI-compatible API, base URL, env var, model id, and compatibility flags are written together:\n\n```sh\ngjc setup provider --preset minimax\ngjc setup provider --preset minimax-cn\ngjc setup provider --preset glm\n```\n\nThe same presets are available inside the TUI:\n\n```text\n/provider add --preset minimax\n/provider add --preset glm\n/provider add zai\n```\n\nPresets only write `models.yml` entries that reference documented environment variable names (`MINIMAX_CODE_API_KEY`, `MINIMAX_CODE_CN_API_KEY`, or `ZAI_API_KEY`); they do not store or validate real credentials. The GLM preset aliases (`glm`, `zai`, `z-ai`) write an OpenAI-compatible custom provider named `glm-proxy` and do not replace the first-class `zai` provider.\n\n## Model profiles (`--mpreset`)\n\nModel profiles are optional top-level `profiles:` entries in `~/.gjc/agent/models.yml`. A profile can require provider credentials before activation and can map one or more model roles; omitted roles inherit from the active defaults.\n\n```yaml\nprofiles:\n  team-standard:\n    required_providers: [openai, anthropic]\n    model_mapping:\n      default: openai/gpt-5.2\n      executor: anthropic/claude-sonnet-4-6:medium\n      architect: openai/o3:high\n      planner: openai/o3:high\n      critic: openai/o3:high\n```\n\n`model_mapping` keys are role names (`default`, `executor`, `architect`, `planner`, `critic`). Each role maps to exactly one model selector in the form `provider/modelId[:effort]`; comma-separated fallback chains are not supported in a single role value.\n`required_providers` is the aggregate set of providers required across the profile's mapped roles, not a per-role fallback chain.\n\nBuilt-in profiles are grouped by provider mix and tier:\n\n- `codex-{eco,medium,pro}` — all roles on `openai-codex/gpt-5.5`, differing only by per-role reasoning effort\n- `opencodego` — single OpenCode Go preset (Kimi default, DeepSeek executor/architect, Qwen planner, MiMo critic)\n- `claude-opus` — Anthropic OAuth preset centered on `claude-opus-4-8`\n- Single-provider tiers: `glm-{eco,medium,pro}`, `kimi-coding-plan-{eco,medium,pro}`, `mimo-{eco,medium,pro}`, `grok-{eco,medium,pro}`, `cursor-{eco,medium,pro}`, `minimax-{eco,medium,pro}`\n- Combos: `opus-codex` (Claude main agent with Codex support roles), `codex-opencodego` (Codex orchestrator/architect with OpenCode Go workers)\n\nThe `eco` tier favors cheaper/faster defaults, `medium` matches normal production defaults, and `pro` raises reasoning for architect, critic, and planner roles. Effort suffixes are clamped to each model's supported thinking range at preview and activation time (for example `codex-eco`'s executor `:minimal` resolves to effective `low` on `gpt-5.5`). Single-provider tiers pin each provider's current flagship (`zai/glm-5.2`, `kimi-code/kimi-k2.7-code`, `xiaomi/mimo-v2.5-pro`, `xai/grok-4.3`, `cursor/composer-1.5`, `minimax-code/minimax-m3`). User-defined profiles override built-ins by exact profile name.\n\n\nUse `gjc --mpreset <name>` to activate a profile for the current session only. Activation hard-blocks when any provider listed in `required_providers` lacks credentials. Add `--default` to persist the selected profile as `modelProfile.default` in `config.yml`, so it applies at startup:\n\n```sh\ngjc --mpreset codex-medium\ngjc --mpreset opencodego --default\n```\n\nThe `/model` command opens to a preset landing view: presets are grouped by provider with live auth marks (✓/✗), highlighting a group expands its tiers, and selecting a tier shows the full role→model preview before applying for the session or as default. Typing jumps straight to model search, and `Browse all models` opens the classic tabbed model selector. In `/login`, `Add custom provider` is the first option for configuring credentials needed by custom or profile-required providers; after a successful provider login, the matching preset is recommended automatically.\n\nMiniMax's OpenAI-compatible endpoint rejects multiple system messages and emits thinking in `reasoning_content`, so pin the public-safe compatibility fields when hand-authoring a custom provider:\n\n```yaml\nproviders:\n  minimax-custom:\n    baseUrl: https://api.minimax.io/v1\n    apiKeyEnv: MINIMAX_API_KEY\n    api: openai-completions\n    compat:\n      supportsStore: false\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n      reasoningContentField: reasoning_content\n    models:\n      - id: MiniMax-M2.5\n```\n\nGLM via z.ai is available as the first-class `zai` provider. For a private GLM-compatible proxy, keep secrets in an env var and disable OpenAI-only request fields as needed:\n\n```yaml\nproviders:\n  glm-proxy:\n    baseUrl: https://api.z.ai/api/paas/v4\n    apiKeyEnv: ZAI_API_KEY\n    api: openai-completions\n    compat:\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n    models:\n      - id: glm-4.6\n```\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `models.yml` is strict: unknown provider/model keys fail validation before provider dispatch, so stale keys such as `requestTransform` or `wireModelId` only work where this document lists them.\n- `discovery.type`: `ollama`, `llama.cpp`, or `lm-studio`\n- `cacheRetention`: `none`, `short`, or `long`; request-time options win over model/modelOverride values, then provider values, then `GJC_CACHE_RETENTION`, then the runtime default. The runtime default is `short` for most providers, but the Anthropic provider defaults to `long` (`ttl: \"1h\"`) because the ~5m default is too fragile for long-running subagent workflows. The 1h marker is only emitted on the canonical Anthropic API (`api.anthropic.com`) for models advertising `supportsLongCacheRetention`; proxies, gateways, and incapable models fall back to the default ephemeral (~5m) breakpoint. For OpenAI Responses, this controls `prompt_cache_retention` only; it does not disable `prompt_cache_key` when a stable session id exists.\n\n## OpenAI-compatible proxy configuration\n\nOpenAI-compatible proxy providers should use schema-supported provider keys first:\n\n```yaml\nproviders:\n  proxy-provider:\n    baseUrl: https://api.proxy.example/v1\n    apiKeyEnv: PROXY_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: local-gpt\n        name: Local GPT\n        reasoning: true\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n```\n\nUse provider-level `headers` for proxy-required headers. Keep the provider `api` set to `openai-completions` when the proxy exposes Chat Completions-compatible `/v1/chat/completions` semantics. `auth: apiKey` sends the resolved token as bearer auth; use `auth: none` only for trusted local/no-auth endpoints.\n\n`requestTransform` and `wireModelId` remain supported for request-body shaping, but they are not needed for ordinary OpenAI-compatible proxies whose local model id is already the upstream wire id. Unknown config keys fail validation before a provider request is sent.\n\nWhen request shaping is needed:\n\n- `requestTransform.profile: openai-proxy` strips OpenAI SDK/Stainless telemetry and beta headers at final fetch time and sets a generic 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`, `cacheRetention`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (schema v3) with a `static_fingerprint` column that hashes the\nstatic catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process via a WeakMap keyed by the static-models array\nreference, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `anthropic-model-opus-4-6`\n- `anthropic-model-haiku-4-5`\n- `gpt-5.3-openai-code`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: openai-code\n        name: Zenmux OpenAI code\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/openai-code: gpt-5.3-openai-code\n    p-openai-code/openai-code: gpt-5.3-openai-code\n  exclude:\n    - demo/openai-code-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `input`, `cost`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL` or `http://127.0.0.1:11434`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `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` plus the agent assignment targets `executor`, `architect`, `planner`, `critic`\n\nRole aliases like `pi/default` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI code provider transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-openai-code` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - anthropic-model-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/anthropic-model-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `--list-models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `--list-models` prints a canonical section plus the concrete provider rows\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error. It is **off by default** (`contextPromotion.enabled` is `false`); opt in to enable it.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI code provider websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for Spark -> non-Spark on the same provider:\n\n```yaml\nproviders:\n  openai-code:\n    modelOverrides:\n      gpt-5.3-openai-code-spark:\n        contextPromotionTarget: openai-code/gpt-5.3-openai-code\n```\n\nThe built-in model generator also assigns this automatically for `*-spark` models when a same-provider base model exists.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/ai/src/providers/openai-completions-compat.ts`. It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/model-registry.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/ai/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok and zAI).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true  # if the proxy doesn't support strict tool schemas\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/anthropic-model-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.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 models for the default and agent roles\n- `src/config/settings-schema.ts` — model-related settings (`modelRoles`, provider transport preferences)\n- `src/session/auth-storage.ts` — API key + OAuth resolution order\n- `packages/ai/src/models.ts` and `packages/ai/src/types.ts` — built-in providers/models and `Model`/`compat` types\n\n## Config file location and legacy behavior\n\nDefault config path:\n\n- `~/.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    cacheRetention: short  # none | short | long; model entries and modelOverrides can override this\n    discovery:\n      type: ollama\n    modelOverrides:\n      some-model-id:\n        name: Renamed model\n        cacheRetention: long\n    models:\n      - id: some-model-id\n        name: Some Model\n        api: openai-completions\n        reasoning: false\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 128000\n        maxTokens: 16384\n        headers:\n          X-Model: value\n        cacheRetention: none\n        thinking:\n          minLevel: low\n          maxLevel: xhigh\n          mode: effort\n          defaultLevel: high\n          levels: [low, medium, high, xhigh]\n        compat:\n          supportsStore: true\n          supportsDeveloperRole: true\n          supportsReasoningEffort: true\n          maxTokensField: max_completion_tokens\n          openRouterRouting:\n            only: [anthropic]\n          vercelGatewayRouting:\n            order: [anthropic, openai]\n          extraBody:\n            gateway: m1-01\n            controller: mlx\nmodelBindings:\n  modelRoles:\n    default: my-provider/some-model-id:high\n  agentModelOverrides:\n    executor: my-provider/some-model-id\n```\n\n### Allowed provider/model `api` values\n\n- `openai-completions`\n- `openai-responses`\n- `openai-codex-responses`\n- `azure-openai-responses`\n- `bedrock-converse-stream`\n- `anthropic-messages`\n- `bedrock-converse-stream`\n- `google-generative-ai`\n- `google-vertex`\n- `google-gemini-cli`\n- `ollama-chat`\n- `cursor-agent`\n\n\n### First-class Azure OpenAI and Amazon Bedrock examples\n\nAzure OpenAI uses canonical OpenAI model IDs in GJC and resolves those IDs to Azure deployment names at request time. Set `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` to avoid assuming model id equals deployment name:\n\n```yaml\nproviders:\n  azure-openai:\n    baseUrl: https://my-resource.openai.azure.com/openai/v1\n    apiKeyEnv: AZURE_OPENAI_API_KEY\n    api: azure-openai-responses\n    models:\n      - id: gpt-4.1\n      - id: o3\n```\n\n```sh\nexport AZURE_OPENAI_DEPLOYMENT_NAME_MAP='gpt-4.1=gpt-41-prod,o3=o3-reasoning-prod'\n```\n\nAmazon Bedrock uses the native `bedrock-converse-stream` transport and AWS credential chain auth. Do not put AWS access keys in `models.yml`; configure `AWS_REGION` / `AWS_PROFILE` or standard static AWS credential environment variables instead:\n\n```yaml\nproviders:\n  amazon-bedrock:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com\n    api: bedrock-converse-stream\n    models:\n      - id: us.anthropic.claude-opus-4-6-v1\n      - id: anthropic.claude-3-5-sonnet-20241022-v2:0\n```\n\n### MiniMax and GLM custom provider examples\n\nFor common MiniMax and GLM/zAI setup, prefer the provider presets so the OpenAI-compatible API, base URL, env var, model id, and compatibility flags are written together:\n\n```sh\ngjc setup provider --preset minimax\ngjc setup provider --preset minimax-cn\ngjc setup provider --preset glm\n```\n\nThe same presets are available inside the TUI:\n\n```text\n/provider add --preset minimax\n/provider add --preset glm\n/provider add zai\n```\n\nPresets only write `models.yml` entries that reference documented environment variable names (`MINIMAX_CODE_API_KEY`, `MINIMAX_CODE_CN_API_KEY`, or `ZAI_API_KEY`); they do not store or validate real credentials. The GLM preset aliases (`glm`, `zai`, `z-ai`) write an OpenAI-compatible custom provider named `glm-proxy` and do not replace the first-class `zai` provider.\n\n## Model profiles (`--mpreset`)\n\nModel profiles are optional top-level `profiles:` entries in `~/.gjc/agent/models.yml`. A profile can require provider credentials before activation and can map one or more model roles; omitted roles inherit from the active defaults.\n\n> See also: [Cross-vendor role-based profiles](./multi-vendor-profiles.md) — a curated multi-vendor `profiles:` recipe and verified selector notes that build on the mechanism described here.\n\n```yaml\nprofiles:\n  team-standard:\n    required_providers: [openai, anthropic]\n    model_mapping:\n      default: openai/gpt-5.2\n      executor: anthropic/claude-sonnet-4-6:medium\n      architect: openai/o3:high\n      planner: openai/o3:high\n      critic: openai/o3:high\n```\n\n`model_mapping` keys are role names (`default`, `executor`, `architect`, `planner`, `critic`). Each role maps to exactly one model selector in the form `provider/modelId[:effort]`; comma-separated fallback chains are not supported in a single role value.\n`required_providers` is the aggregate set of providers required across the profile's mapped roles, not a per-role fallback chain.\n\nBuilt-in profiles are grouped by provider mix and tier:\n\n- `codex-{eco,medium,pro}` — all roles on `openai-codex/gpt-5.5`, differing only by per-role reasoning effort\n- `opencodego` — single OpenCode Go preset (Kimi default, DeepSeek executor/architect, Qwen planner, MiMo critic)\n- `claude-opus` — Anthropic OAuth preset centered on `claude-opus-4-8`\n- Single-provider tiers: `glm-{eco,medium,pro}`, `kimi-coding-plan-{eco,medium,pro}`, `mimo-{eco,medium,pro}`, `grok-{eco,medium,pro}`, `cursor-{eco,medium,pro}`, `minimax-{eco,medium,pro}`\n- Combos: `opus-codex` (Claude main agent with Codex support roles), `codex-opencodego` (Codex orchestrator/architect with OpenCode Go workers)\n\nThe `eco` tier favors cheaper/faster defaults, `medium` matches normal production defaults, and `pro` raises reasoning for architect, critic, and planner roles. Effort suffixes are clamped to each model's supported thinking range at preview and activation time (for example `codex-eco`'s executor `:minimal` resolves to effective `low` on `gpt-5.5`). Single-provider tiers pin each provider's current flagship (`zai/glm-5.2`, `kimi-code/kimi-k2.7-code`, `xiaomi/mimo-v2.5-pro`, `xai/grok-4.3`, `cursor/composer-1.5`, `minimax-code/minimax-m3`). User-defined profiles override built-ins by exact profile name.\n\n\nUse `gjc --mpreset <name>` to activate a profile for the current session only. Activation hard-blocks when any provider listed in `required_providers` lacks credentials. Add `--default` to persist the selected profile as `modelProfile.default` in `config.yml`, so it applies at startup:\n\n```sh\ngjc --mpreset codex-medium\ngjc --mpreset opencodego --default\n```\n\nThe `/model` command opens to a preset landing view: presets are grouped by provider with live auth marks (✓/✗), highlighting a group expands its tiers, and selecting a tier shows the full role→model preview before applying for the session or as default. Typing jumps straight to model search, and `Browse all models` opens the classic tabbed model selector. In `/login`, `Add custom provider` is the first option for configuring credentials needed by custom or profile-required providers; after a successful provider login, the matching preset is recommended automatically.\n\nMiniMax's OpenAI-compatible endpoint rejects multiple system messages and emits thinking in `reasoning_content`, so pin the public-safe compatibility fields when hand-authoring a custom provider:\n\n```yaml\nproviders:\n  minimax-custom:\n    baseUrl: https://api.minimax.io/v1\n    apiKeyEnv: MINIMAX_API_KEY\n    api: openai-completions\n    compat:\n      supportsStore: false\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n      reasoningContentField: reasoning_content\n    models:\n      - id: MiniMax-M2.5\n```\n\nGLM via z.ai is available as the first-class `zai` provider. For a private GLM-compatible proxy, keep secrets in an env var and disable OpenAI-only request fields as needed:\n\n```yaml\nproviders:\n  glm-proxy:\n    baseUrl: https://api.z.ai/api/paas/v4\n    apiKeyEnv: ZAI_API_KEY\n    api: openai-completions\n    compat:\n      supportsDeveloperRole: false\n      supportsReasoningEffort: false\n    models:\n      - id: glm-4.6\n```\n### Allowed auth/discovery values\n\n- `auth`: `apiKey` (default), `none`, or `oauth`; for `models.yml` custom models, `oauth` is accepted by schema but does not waive the `apiKey` requirement\n- `models.yml` is strict: unknown provider/model keys fail validation before provider dispatch, so stale keys such as `requestTransform` or `wireModelId` only work where this document lists them.\n- `discovery.type`: `ollama`, `llama.cpp`, or `lm-studio`\n- `cacheRetention`: `none`, `short`, or `long`; request-time options win over model/modelOverride values, then provider values, then `GJC_CACHE_RETENTION`, then the runtime default. The runtime default is `short` for most providers, but the Anthropic provider defaults to `long` (`ttl: \"1h\"`) because the ~5m default is too fragile for long-running subagent workflows. The 1h marker is only emitted on the canonical Anthropic API (`api.anthropic.com`) for models advertising `supportsLongCacheRetention`; proxies, gateways, and incapable models fall back to the default ephemeral (~5m) breakpoint. For OpenAI Responses, this controls `prompt_cache_retention` only; it does not disable `prompt_cache_key` when a stable session id exists.\n\n## OpenAI-compatible proxy configuration\n\nOpenAI-compatible proxy providers should use schema-supported provider keys first:\n\n```yaml\nproviders:\n  proxy-provider:\n    baseUrl: https://api.proxy.example/v1\n    apiKeyEnv: PROXY_API_KEY\n    api: openai-completions\n    auth: apiKey\n    headers:\n      User-Agent: curl/8.7.1\n    models:\n      - id: local-gpt\n        name: Local GPT\n        reasoning: true\n        input: [text]\n        cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }\n        contextWindow: 400000\n        maxTokens: 128000\n```\n\nUse provider-level `headers` for proxy-required headers. Keep the provider `api` set to `openai-completions` when the proxy exposes Chat Completions-compatible `/v1/chat/completions` semantics. `auth: apiKey` sends the resolved token as bearer auth; use `auth: none` only for trusted local/no-auth endpoints.\n\n`requestTransform` and `wireModelId` remain supported for request-body shaping, but they are not needed for ordinary OpenAI-compatible proxies whose local model id is already the upstream wire id. Unknown config keys fail validation before a provider request is sent.\n\nWhen request shaping is needed:\n\n- `requestTransform.profile: openai-proxy` strips OpenAI SDK/Stainless telemetry and beta headers at final fetch time and sets a generic 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`, `cacheRetention`) to built-in models.\n4. Apply `modelOverrides` (per provider + model id).\n5. Merge custom `models`:\n   - same `provider + id` replaces existing\n   - otherwise append\n6. Load cached/runtime-discovered models (Ollama, llama.cpp, LM Studio, plus built-in provider managers), then re-apply model overrides.\n\n### Provider-model cache and static fingerprint\n\nCached per-provider model lists are persisted in the model-cache SQLite\ndatabase (schema v3) with a `static_fingerprint` column that hashes the\nstatic catalog slice merged into the row. When `resolveProviderModels`\nskips the network fetch and the fingerprint of the in-memory static\ncatalog matches the cached one, the cached rows are returned verbatim —\nthe static + dynamic merge is bypassed entirely. The fingerprint is\nmemoized per process via a WeakMap keyed by the static-models array\nreference, so repeated cold-start calls do not re-hash.\n\n## Canonical model equivalence and coalescing\n\nThe registry keeps every concrete provider model and then builds a canonical layer above them.\n\nCanonical ids are official upstream ids only, for example:\n\n- `anthropic-model-opus-4-6`\n- `anthropic-model-haiku-4-5`\n- `gpt-5.3-openai-code`\n\n### `models.yml` equivalence config\n\nExample:\n\n```yaml\nproviders:\n  zenmux:\n    baseUrl: https://api.zenmux.example/v1\n    apiKey: ZENMUX_API_KEY\n    api: openai-codex-responses\n    models:\n      - id: openai-code\n        name: Zenmux OpenAI code\n        reasoning: true\n        input: [text]\n        cost:\n          input: 0\n          output: 0\n          cacheRead: 0\n          cacheWrite: 0\n        contextWindow: 200000\n        maxTokens: 32768\n\nequivalence:\n  overrides:\n    zenmux/openai-code: gpt-5.3-openai-code\n    p-openai-code/openai-code: gpt-5.3-openai-code\n  exclude:\n    - demo/openai-code-preview\n```\n\nBuild order for canonical grouping:\n\n1. exact user override from `equivalence.overrides`\n2. bundled official-id matches from built-in model metadata\n3. conservative heuristic normalization for gateway/provider variants\n4. fallback to the concrete model's own id\n\nCurrent heuristics are intentionally narrow:\n\n- embedded upstream prefixes can be stripped when present, for example `anthropic/...` or `openai/...`\n- dotted and dashed version variants can normalize only when they map to an existing official id, for example `4.6 -> 4-6`\n- ambiguous families or versions are not merged without a bundled match or explicit override\n\n### Canonical resolution behavior\n\nWhen multiple concrete variants share a canonical id, resolution uses:\n\n1. availability and auth\n2. `config.yml` `modelProviderOrder`\n3. existing registry/provider order if `modelProviderOrder` is unset\n\nDisabled or unauthenticated providers are skipped.\n\nSession state and transcripts continue to record the concrete provider/model that actually executed the turn.\n\nProvider defaults vs per-model overrides:\n\n- Provider `headers` are baseline.\n- Model `headers` override provider header keys.\n- `modelOverrides` can override model metadata (`name`, `reasoning`, `input`, `cost`, `contextWindow`, `maxTokens`, `headers`, `compat`, `contextPromotionTarget`).\n- `compat` is deep-merged for nested routing blocks (`openRouterRouting`, `vercelGatewayRouting`, `extraBody`).\n\n## Runtime discovery integration\n\n### Implicit Ollama discovery\n\nIf `ollama` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `ollama`\n- api: `openai-responses`\n- base URL: `OLLAMA_BASE_URL` or `http://127.0.0.1:11434`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls Ollama endpoints and normalizes discovered OpenAI-compatible models to `openai-responses`.\n\n### Implicit llama.cpp discovery\n\nIf `llama.cpp` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `llama.cpp`\n- api: `openai-responses`\n- base URL: `LLAMA_CPP_BASE_URL` or `http://127.0.0.1:8080`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery calls llama.cpp model endpoints and synthesizes model entries with local defaults.\n\n### Implicit LM Studio discovery\n\nIf `lm-studio` is not explicitly configured, registry adds an implicit discoverable provider:\n\n- provider: `lm-studio`\n- api: `openai-completions`\n- base URL: `LM_STUDIO_BASE_URL` or `http://127.0.0.1:1234/v1`\n- auth mode: keyless (`auth: none` behavior)\n\nRuntime discovery fetches models (`GET /models`) and synthesizes model entries with local defaults.\n\n### Explicit provider discovery\n\nYou can configure discovery yourself:\n\n```yaml\nproviders:\n  ollama:\n    baseUrl: http://127.0.0.1:11434\n    api: openai-responses\n    auth: none\n    discovery:\n      type: ollama\n\n  llama.cpp:\n    baseUrl: http://127.0.0.1:8080\n    api: openai-responses\n    auth: none\n    discovery:\n      type: llama.cpp\n```\n\n### Extension provider registration\n\nExtensions can register providers at runtime (`pi.registerProvider(...)`), including:\n\n- model replacement/append for a provider\n- custom stream handler registration for new API IDs\n- custom OAuth provider registration\n\n## Auth and API key resolution order\n\nWhen requesting a key for a provider, effective order is:\n\n1. Runtime override (CLI `--api-key`)\n2. Stored API key credential in `agent.db`\n3. Stored OAuth credential in `agent.db` (with refresh)\n4. Environment variable mapping (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, etc.)\n5. ModelRegistry fallback resolver (provider `apiKey` from `models.yml`, env-name-or-literal semantics)\n\n`models.yml` `apiKey` behavior:\n\n- Value is first treated as an environment variable name.\n- If no env var exists, the literal string is used as the token.\n\nIf `authHeader: true` and provider `apiKey` is set, models get:\n\n- `Authorization: Bearer <resolved-key>` header injected.\n\nKeyless providers:\n\n- Providers marked `auth: none` are treated as available without credentials.\n- `getApiKey*` returns `kNoAuth` for them.\n\n### Broker mode\n\nWhen `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` plus the agent assignment targets `executor`, `architect`, `planner`, `critic`\n\nRole aliases like `pi/default` expand through `settings.modelRoles`. Each role value can also append a thinking selector such as `:minimal`, `:low`, `:medium`, or `:high`.\n\nIf a role points at another role, the target model still inherits normally and any explicit suffix on the referring role wins for that role-specific use.\n\nRelated settings:\n\n- `modelRoles` (record)\n- `enabledModels` (scoped pattern list)\n- `modelProviderOrder` (global canonical-provider precedence)\n- `providers.kimiApiFormat` (`openai` or `anthropic` request format)\n- `providers.openaiWebsockets` (`auto|off|on` websocket preference for OpenAI code provider transport)\n\n`modelRoles` may store either:\n\n- `provider/modelId` to pin a concrete provider variant\n- a canonical id such as `gpt-5.3-openai-code` to allow provider coalescing\n\nFor `enabledModels` and CLI `--models`:\n\n- exact canonical ids expand to all concrete variants in that canonical group\n- explicit `provider/modelId` entries stay exact\n- globs and fuzzy matches still operate on concrete models\n\nGlobal `enabledModels` and `disabledProviders` entries may also be scoped to a path prefix:\n\n```yaml\nenabledModels:\n  - anthropic-model-sonnet-4-5\n  - path: ~/work\n    models:\n      - anthropic/anthropic-model-opus-4-5\ndisabledProviders:\n  - ollama\n  - path: ~/private\n    providers:\n      - anthropic\n```\n\nString entries apply everywhere. Scoped entries apply when the current working directory is the configured path or one of its subdirectories. Use `path`, `paths`, `pathPrefix`, or `pathPrefixes`; use `models` for `enabledModels`, `providers` for `disabledProviders`, or `values` for either.\n\n## `/model` and `--list-models`\n\nBoth surfaces keep provider-prefixed models visible and selectable.\n\nThey now also expose canonical/coalesced models:\n\n- `/model` includes a canonical view alongside provider tabs\n- `--list-models` prints a canonical section plus the concrete provider rows\n\nSelecting a canonical entry stores the canonical selector. Selecting a provider row stores the explicit `provider/modelId`.\n\n## Context promotion (model-level fallback chains)\n\nContext promotion is an overflow recovery mechanism for small-context variants (for example `*-spark`) that automatically promotes to a larger-context sibling when the API rejects a request with a context length error. It is **off by default** (`contextPromotion.enabled` is `false`); opt in to enable it.\n\n### Trigger and order\n\nWhen a turn fails with a context overflow error (e.g. `context_length_exceeded`), `AgentSession` attempts promotion **before** falling back to compaction:\n\n1. If `contextPromotion.enabled` is true, resolve a promotion target (see below).\n2. If a target is found, switch to it and retry the request — no compaction needed.\n3. If no target is available, fall through to auto-compaction on the current model.\n\n### Target selection\n\nSelection is model-driven, not role-driven:\n\n1. `currentModel.contextPromotionTarget` (if configured)\n2. smallest larger-context model on the same provider + API\n\nCandidates are ignored unless credentials resolve (`ModelRegistry.getApiKey(...)`).\n\n### OpenAI code provider websocket handoff\n\nIf switching from/to `openai-codex-responses`, session provider state key `openai-codex-responses` is closed before model switch. This drops websocket transport state so the next turn starts clean on the promoted model.\n\n### Persistence behavior\n\nPromotion uses temporary switching (`setModelTemporary`):\n\n- recorded as a temporary `model_change` in session history\n- does not rewrite saved role mapping\n\n### Configuring explicit fallback chains\n\nConfigure fallback directly in model metadata via `contextPromotionTarget`.\n\n`contextPromotionTarget` accepts either:\n\n- `provider/model-id` (explicit)\n- `model-id` (resolved within current provider)\n\nExample (`models.yml`) for Spark -> non-Spark on the same provider:\n\n```yaml\nproviders:\n  openai-code:\n    modelOverrides:\n      gpt-5.3-openai-code-spark:\n        contextPromotionTarget: openai-code/gpt-5.3-openai-code\n```\n\nThe built-in model generator also assigns this automatically for `*-spark` models when a same-provider base model exists.\n\n## Compatibility and routing fields\n\nThe `compat` block on a provider or model overrides the URL-based auto-detection in `packages/ai/src/providers/openai-completions-compat.ts`. It is validated by `OpenAICompatSchema` in `packages/coding-agent/src/config/model-registry.ts` and consumed by every `openai-completions` transport (`packages/ai/src/providers/openai-completions.ts`). The canonical type is `OpenAICompat` in `packages/ai/src/types.ts`.\n\n`models.yml` accepts the following keys (all optional; unset falls back to URL detection):\n\nRequest shaping:\n\n- `supportsStore` — emit `store: false` on requests. Default: auto (off for non-standard endpoints).\n- `supportsDeveloperRole` — use the `developer` system role for reasoning models instead of `system`. Default: auto.\n- `supportsUsageInStreaming` — send `stream_options: { include_usage: true }` to receive token usage on streaming responses. Default: `true`.\n- `maxTokensField` — `\"max_completion_tokens\"` or `\"max_tokens\"`. Default: auto.\n- `supportsToolChoice` — emit the `tool_choice` parameter when the caller forces a specific tool. Default: `true`. Set `false` for endpoints that 400 on `tool_choice` (e.g. DeepSeek when reasoning is on).\n- `disableReasoningOnForcedToolChoice` — drop `reasoning_effort` / OpenRouter `reasoning` whenever `tool_choice` forces a call. Default: auto (Kimi/Anthropic-fronted endpoints).\n- `extraBody` — extra top-level fields merged into every request body (gateway hints, controller selectors, etc.).\n\nReasoning / thinking:\n\n- `supportsReasoningEffort` — accept `reasoning_effort`. Default: auto (off for Grok and zAI).\n- `reasoningEffortMap` — partial map from internal effort levels (`minimal|low|medium|high|xhigh`) to provider-specific strings (e.g. DeepSeek maps `xhigh -> \"max\"`).\n- `thinkingFormat` — request shape for thinking: `\"openai\"` (`reasoning_effort`), `\"openrouter\"` (`reasoning: { effort }`), `\"zai\"` (`thinking: { type: \"enabled\" }`), `\"qwen\"` (top-level `enable_thinking`), or `\"qwen-chat-template\"` (`chat_template_kwargs.enable_thinking`). Default: `\"openai\"`.\n- `reasoningContentField` — assistant field carrying chain-of-thought: `\"reasoning_content\"`, `\"reasoning\"`, or `\"reasoning_text\"`. Default: auto.\n- `requiresReasoningContentForToolCalls` — assistant tool-call turns must round-trip the reasoning field (DeepSeek-R1, Kimi, OpenRouter when reasoning is on). Default: `false`.\n- `requiresAssistantContentForToolCalls` — assistant tool-call turns must include non-empty text content (Kimi). Default: `false`.\n\nTool / message normalization:\n\n- `requiresToolResultName` — tool-result messages need a `name` field (Mistral). Default: auto.\n- `requiresAssistantAfterToolResult` — a user message after a tool result needs an assistant turn in between. Default: auto.\n- `requiresThinkingAsText` — convert thinking blocks to text wrapped in `<thinking>` delimiters (Mistral). Default: auto.\n- `requiresMistralToolIds` — normalize tool-call ids to exactly 9 alphanumeric chars. Default: auto.\n- `supportsStrictMode` — accept the per-tool `strict` field on tool schemas. Default: conservative auto-detect per provider/baseUrl.\n- `toolStrictMode` — `\"all_strict\"` forces strict on every tool, `\"none\"` forces it off; unset keeps the existing per-tool mixed behavior.\n\nGateway routing (only applied when `baseUrl` matches the gateway):\n\n- `openRouterRouting.only` / `openRouterRouting.order` — provider routing on `openrouter.ai` (see <https://openrouter.ai/docs/provider-routing>).\n- `vercelGatewayRouting.only` / `vercelGatewayRouting.order` — provider routing on `ai-gateway.vercel.sh` (see <https://vercel.com/docs/ai-gateway/models-and-providers/provider-options>).\n\nProvider-level `compat` is the baseline; per-model `compat` is deep-merged on top, with `openRouterRouting`, `vercelGatewayRouting`, and `extraBody` merged as nested objects.\n\n### Anthropic compatibility (`anthropic-messages`)\n\nFor `anthropic-messages` models the runtime uses a separate `AnthropicCompat` shape (`packages/ai/src/types.ts`). The `models.yml` schema currently exposes only the strict-tools opt-out as a top-level provider field (see below); the remaining Anthropic-side knobs (`disableAdaptiveThinking`, `supportsEagerToolInputStreaming`, `supportsLongCacheRetention`) are set by built-in catalog metadata and are not user-configurable from `models.yml`.\n\n### Strict tool schemas (`disableStrictTools`)\n\nAnthropic's API supports a `strict` field on tool definitions that forces the model to always follow the provided schema exactly. This is enabled by default for all `anthropic-messages` providers because it guarantees schema conformance in agentic systems.\n\nThird-party providers that front the Anthropic API (AWS Bedrock, Azure, self-hosted proxies) do not always implement this field and will reject requests that include it. Set `disableStrictTools: true` at the provider level to opt out:\n\n```yaml\nproviders:\n  bedrock-anthropic:\n    baseUrl: https://bedrock-runtime.us-east-1.amazonaws.com/anthropic\n    apiKey: AWS_BEARER_TOKEN\n    api: anthropic-messages\n    disableStrictTools: true\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Bedrock)\n        input: [text, image]\n        contextWindow: 200000\n        maxTokens: 16384\n        cost:\n          input: 3.00\n          output: 15.00\n          cacheRead: 0.30\n          cacheWrite: 3.75\n```\n\n`disableStrictTools` is a provider-level flag that applies to all models in the provider.\n\nTool schemas going on the wire are normalized by the unified flow in\n`packages/ai/src/utils/schema/normalize.ts` (Google/CCA/MCP dispatchers\nplus the OpenAI strict-mode sanitize+enforce pipeline). See\n[`ai-schema-normalize.md`](./ai-schema-normalize.md) for the strict-mode\nedge cases (local `$ref` inlining, single-item `allOf` collapse,\n`anyOf`-wrapper description hoist, enum/const primitive-type inference)\nand the per-provider dispatcher mapping.\n## Practical examples\n\n### Local OpenAI-compatible endpoint (no auth)\n\n```yaml\nproviders:\n  local-openai:\n    baseUrl: http://127.0.0.1:8000/v1\n    auth: none\n    api: openai-completions\n    models:\n      - id: Qwen/Qwen2.5-Coder-32B-Instruct\n        name: Qwen 2.5 Coder 32B (local)\n```\n\n### Hosted proxy with env-based key\n\n```yaml\nproviders:\n  anthropic-proxy:\n    baseUrl: https://proxy.example.com/anthropic\n    apiKey: ANTHROPIC_PROXY_API_KEY\n    api: anthropic-messages\n    authHeader: true\n    disableStrictTools: true  # if the proxy doesn't support strict tool schemas\n    models:\n      - id: anthropic-model-sonnet-4-20250514\n        name: Anthropic model Sonnet 4 (Proxy)\n        reasoning: true\n        input: [text, image]\n```\n\n### Override built-in provider route + model metadata\n\n```yaml\nproviders:\n  openrouter:\n    baseUrl: https://my-proxy.example.com/v1\n    headers:\n      X-Team: platform\n    modelOverrides:\n      anthropic/anthropic-model-sonnet-4:\n        name: Sonnet 4 (Corp)\n        compat:\n          openRouterRouting:\n            only: [anthropic]\n```\n\n## Legacy consumer caveat\n\nMost model configuration now flows through `models.yml` via `ModelRegistry`. Explicit `.json` / `.jsonc` paths remain supported only when passed programmatically to `ModelRegistry`; the default user config is `~/.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",
+	"multi-vendor-profiles.md": "# Choosing models in GJC: role-based profiles\n\nA practical guide to picking models for GJC's roles, for every subscription situation — one vendor, two vendors, or the full multi-vendor set. It adds curated cross-vendor `profiles:` for `~/.gjc/agent/models.yml` and verified selector notes on top of the mechanism in [Model profiles](./models.md#model-profiles---mpreset). Everything here is **user config**; it complements the built-in `--mpreset` presets and overrides a built-in only when it shares its exact name.\n\n> Selectors, prices, and \"axis leaders\" are catalog- and time-sensitive (observed 2026-06 on the current bundled catalog). Re-verify any selector with `gjc -p --no-session --no-tools --model <selector> \"Reply OK\"`.\n\n## The five roles\n\n`default` runs the main loop and most turns; `executor` / `architect` / `planner` / `critic` are the four bundled task agents, delegated only when the work calls for it.\n\n| Role | What it optimizes for |\n| --- | --- |\n| `default` | tool-calling reliability + honesty (it routes — its quality bounds the whole system) |\n| `executor` | real coding (SWE-bench Verified) |\n| `planner` | reasoning + sequencing (GPQA / ARC-AGI-2) |\n| `architect` | large-context + multimodal review |\n| `critic` | independent adversarial review (different family from what it reviews) |\n\n## Pick by what you subscribe to\n\n| You have | Use |\n| --- | --- |\n| **One vendor** | the built-in preset for that vendor — `claude-opus` (Anthropic), `codex-{eco,medium,pro}` (OpenAI/Codex), `opencodego` (OpenCode Go), or a single-vendor flagship tier (`zai/glm-5.2`, `kimi-code/...`, `xiaomi/...`, `xai/grok-4.3`, `minimax-code/...`). These already map all five roles inside one vendor. |\n| **Claude + Codex** | the built-in `opus-codex` (Claude main loop + Codex support roles). |\n| **Three or more / all five** | the cross-vendor profiles below — each role on its axis leader, `critic` kept cross-family. |\n\nThe single guiding rule across all of these: **keep `default` on the strongest router you have** (Anthropic Opus when available). A weak `default` caps quality regardless of the delegated models.\n\n## Cross-vendor profiles (3+ vendors)\n\nNo single vendor leads every axis, so these put each role on its axis leader and keep `critic` on a different family from the `executor` it reviews.\n\n```yaml\nprofiles:\n\n  daily:                 # everyday balance\n    required_providers: [anthropic, openai-codex, google-antigravity, xai]\n    model_mapping:\n      default:   anthropic/claude-opus-4-8:medium\n      executor:  openai-codex/gpt-5.4:high\n      planner:   google-antigravity/gemini-3.1-pro-low:high\n      architect: google-antigravity/gemini-3.1-pro-low:high\n      critic:    xai/grok-4.3:medium\n\n  ultimate:              # cost-no-object, best per role\n    required_providers: [anthropic, openai-codex, google-antigravity, xai]\n    model_mapping:\n      default:   anthropic/claude-opus-4-8:high\n      executor:  anthropic/claude-opus-4-8:max\n      planner:   openai-codex/gpt-5.5:xhigh\n      architect: google-antigravity/gemini-3.1-pro-low:high\n      critic:    xai/grok-4.3:high\n\n  eco:                   # cheapest delegated work; main loop stays on Opus\n    required_providers: [anthropic, opencode-go, google-antigravity, xai]\n    model_mapping:\n      default:   anthropic/claude-opus-4-8:low\n      executor:  opencode-go/deepseek-v4-flash\n      planner:   xai/grok-4-1-fast:high\n      architect: google-antigravity/gemini-3.1-pro-low\n      critic:    google-antigravity/gemini-3.5-flash\n\n  monorepo:              # huge codebases (openai-codex excluded: 272k context cap)\n    required_providers: [anthropic, google-antigravity, opencode-go]\n    model_mapping:\n      default:   anthropic/claude-opus-4-8:medium\n      executor:  anthropic/claude-opus-4-8:high\n      planner:   google-antigravity/gemini-3.1-pro-low:high\n      architect: anthropic/claude-opus-4-8:high\n      critic:    opencode-go/glm-5.2\n```\n\n## Model cheatsheet (by need)\n\nCurrent axis leaders and the cheaper second option, with metered price ($/1M in/out; Gemini via Antigravity runs on the Google AI subscription):\n\n| Need | First pick | Cheaper option |\n| --- | --- | --- |\n| Router / tool-calling (`default`) | `anthropic/claude-opus-4-8` (5/25) | `anthropic/claude-sonnet-4-6` (3/15) |\n| Coding (`executor`) | `anthropic/claude-opus-4-8` — SWE-bench Verified ~88.6 (5/25) | `openai-codex/gpt-5.4` (2.5/15) · `opencode-go/deepseek-v4-flash` (0.14/0.28) |\n| Reasoning (`planner`) | `openai-codex/gpt-5.5` (ARC-AGI-2) / `google-antigravity/gemini-3.1-pro-low:high` (GPQA) | `xai/grok-4-1-fast` (0.2/0.5) |\n| Large context (`architect`) | `anthropic/claude-opus-4-8` (effective long-context) | `xai/grok-4-fast` (2M nominal, 0.2/0.5) |\n| Multimodal review (`architect`) | `google-antigravity/gemini-3.1-pro-low:high` | `google-antigravity/gemini-3.5-flash` |\n| Independent critic | `xai/grok-4.3` (1.25/2.5) | `opencode-go/glm-5.2` · `google-antigravity/gemini-3.5-flash` |\n\nOn standard tasks, all current frontier models in the catalog are accurate; **pick by cost, latency, and role fit, not by raw accuracy on easy prompts.** As an indicative GJC-routed latency reference (`gjc -p`, identical coding + reasoning prompts, all correct): `grok-4.3` and `glm-5.2` ≈ 2–3s, `deepseek-v4-pro` ≈ 3–4s, `claude-opus-4-8` / `gpt-5.5` ≈ 4–7s, `gemini-3.1-pro-low:high` ≈ 7s.\n\n## Verified selector notes (current catalog)\n\nObserved via live `gjc -p` calls; useful when wiring the profiles above:\n\n- **Antigravity Gemini, high reasoning** → use `google-antigravity/gemini-3.1-pro-low:high`. The id `gemini-3.1-pro-high` returns HTTP 400 (no matching backend model); `thinkingLevel` is a per-request parameter, so raising it on `gemini-3.1-pro-low` invokes the model's native high-reasoning mode rather than a degraded one.\n- **openai-codex on a ChatGPT account** serves base GPT only (`gpt-5.5`, `gpt-5.4`). Standalone `-codex` variants (`gpt-5.3-codex`, `gpt-5.2-codex`, `gpt-5.1-codex-max` / `-mini`) return `not supported when using Codex with a ChatGPT account`.\n- **Single-message input limit is separate from the context window.** `claude-opus-4-8` runs with a 1M window via multi-turn accumulation, but a single `@file` message above ~400k tokens returns 400 on `anthropic` / `google-antigravity`; `xai` / `opencode-go` accept larger single messages. Chunk very large inputs across turns instead of pasting one block.\n- **Some selectors come from a provider's live catalog, not the bundled snapshot.** `opencode-go/glm-5.2` and `google-antigravity/gemini-3.5-flash` resolved in `gjc -p` tests but are **not** in `packages/ai/src/models.json`; they appear only after the provider's online model discovery has populated the registry. `required_providers` verifies credentials at activation — it does **not** guarantee fresh, non-stale discovery — so activation can still fail with `selector did not resolve` until discovery runs (re-login or retry to refresh). If you hit that, substitute a bundled id: `opencode-go/deepseek-v4-pro` for the critic, or `zai/glm-5.2` (add `zai` to `required_providers`) for GLM 5.2.\n\n## Activation\n\n```bash\ngjc --mpreset daily               # this session only\ngjc --mpreset ultimate --default  # persist as the startup default (config.yml)\n```\n\nActivation hard-blocks when any provider in `required_providers` lacks credentials, so log in first: `/login anthropic`, `/login openai-codex`, `/login google-antigravity`, `/login xai` (and `opencode-go` via `OPENCODE_API_KEY`).\n",
 	"native-ffi-optimization-policy.md": "# ADR: Native FFI Optimization Policy\n\n- Status: Accepted\n- Scope: `crates/pi-natives` algorithmic ports proposed for performance reasons\n- Related: [`porting-to-natives.md`](./porting-to-natives.md), [`natives-architecture.md`](./natives-architecture.md), [`natives-binding-contract.md`](./natives-binding-contract.md), [`cpu-hotspot-map.json`](./cpu-hotspot-map.json), [`hotspot-map-successor.md`](./hotspot-map-successor.md)\n\n## Decision\n\nA new native (Rust N-API / FFI) port proposed **to optimize a leftover hot path** does not land unless **all** of the following gates pass:\n\n1. **Corpus evidence** — a profiling-corpus trace shows the path has user-visible latency or RSS impact on a representative workload (not just a static complexity argument).\n2. **Self-time attribution** — a `profilerSelfTime` artifact identifies the proposed hotspot, **or** fallback-toggle evidence proves an end-to-end benefit without byte changes. Wall-clock proxy timing alone is never sufficient.\n3. **Measured FFI overhead** — the N-API call/marshalling overhead is measured against the JS/TS baseline, not assumed away.\n4. **Representative win** — a representative p50/p95 win exists on realistic inputs, not only microbenchmark seed results.\n5. **Byte parity** — a byte-identical corpus covers rendered, persisted, and provider-visible bytes for the changed path.\n6. **Operational cost** — fallback, packaging, and rollback costs are documented.\n\nThis policy governs **speculative algorithmic ports**. It does **not** re-litigate already-native platform/system surfaces (see [Scope boundary](#scope-boundary)).\n\n## Context\n\nThe CPU/memory hotspot program (Optimization Suites v1–v3, tracked in [`cpu-hotspot-map.json`](./cpu-hotspot-map.json)) is closed out. Its prioritization was a **static structural ranking** (algorithmic complexity × trigger frequency), and the map's own `method` field records that real CPU self-time was \"to be measured by the agreed profiling corpus during optimization.\" That corpus is being built separately; until its evidence exists, new native ports for leftover hotspots would repeat the same evidence gap.\n\nThe suites already produced concrete decisions that this policy codifies so they are not re-discovered:\n\n- **v2 (#530)** measured and **rejected the five remaining Rust port candidates** per the FFI cost gates after shipping only `diffLines` (H03) natively. Native overhead did not beat the JS/TS baseline for those candidates on realistic inputs.\n- **v3 (#558) rejected a native word-diff (H04)** \"without a fresh FFI gate\" — the TS fast paths were retained instead; a native port would need to re-clear gates 1–6 above.\n- **Hunt-Szymanski LCS (H05)** was implemented as a native/algorithmic replacement, then **reverted** because it produced byte-different rendered diffs (reproduced by red-team). Byte parity is the gate, not raw speed.\n- **The custom JSON length counter (H08)** was implemented, made exact, then **deleted** — an exact JS reimplementation was not faster than native `JSON.stringify`. \"More native\" is not automatically \"faster.\"\n\nThese four precedents share a root cause: a plausible algorithmic/native win that failed a real gate (cost, byte parity, or end-to-end benefit). The policy makes those gates a precondition rather than a post-hoc discovery.\n\n## Evidence taxonomy\n\nNative-port claims must classify their evidence using the same separated classes as the profiling corpus. These classes must never be conflated:\n\n- **`wallClockPhase`** — elapsed timing around a phase or operation. Useful for perceived-latency and regression detection; **insufficient** to confirm CPU self-time or to justify a port on its own.\n- **`processCpuUsage`** — `process.cpuUsage()` user/system deltas, optionally normalized by elapsed time. Indicates process-level CPU pressure; **cannot** attribute self-time to a specific hotspot.\n- **`profilerSelfTime`** — profiler (or equivalent sampled/trace) attribution of self-time to a function, module, or native symbol. **Required** before a hotspot may be called \"CPU-self-time confirmed.\"\n\nA native-optimization proposal that cites only `wallClockPhase` or `processCpuUsage` is **not** CPU-self-time confirmed and does not clear gate 2.\n\n## Approval checklist\n\nBefore opening a native-optimization PR, confirm and attach evidence for each:\n\n- [ ] Corpus trace shows user-visible latency or RSS impact for the path (gate 1).\n- [ ] `profilerSelfTime` artifact identifies the hotspot, **or** fallback-toggle before/after evidence proves end-to-end benefit without byte changes (gate 2).\n- [ ] FFI/marshalling overhead measured vs the JS/TS baseline in the same benchmark run (gate 3).\n- [ ] Representative p50/p95 win on realistic inputs, not only seeded microbench results (gate 4).\n- [ ] Byte-identical corpus covers rendered, persisted, and provider-visible bytes (gate 5).\n- [ ] Fallback, packaging (platform variants / embedded addon), and rollback costs documented (gate 6).\n\nIf any box is unchecked, keep the work in TypeScript or hold it as a tracked candidate; do not switch callsites. This mirrors the existing **Rule of thumb** in [`porting-to-natives.md`](./porting-to-natives.md): if native is not faster *and* behavior-compatible, do not switch callsites.\n\n## Scope boundary\n\nThis policy targets **speculative algorithmic ports**, not the established native surface. The following are **already native** by design and are explicitly out of scope (see `alreadyNativeExcluded` in [`cpu-hotspot-map.json`](./cpu-hotspot-map.json)):\n\n`grep`, `fd`/`glob`, text width/wrap/truncate/slice, syntax highlighting, HTML→Markdown, token counting, AST, summary, process/PTY/shell, SIXEL, clipboard, `Bun.hash.xxHash32/64`, and `JSON.parse`/`JSON.stringify`.\n\nThese are native because they are I/O, OS/process integration, or platform primitives — the criteria in [`porting-to-natives.md`](./porting-to-natives.md#when-to-port). Distinguishing them from algorithmic ports matters: a leftover algorithmic hotspot must clear gates 1–6, whereas adding a new OS/process/native-primitive binding follows the standard porting guide.\n\n## Consequences\n\n- New native algorithmic ports require profiling-corpus evidence and a measured cost gate before review; this slows speculative optimization but prevents byte-parity regressions and dead native code.\n- The default answer for a leftover hotspot is \"keep it in TypeScript\" until the corpus proves it matters.\n- Already-native platform/system primitives and new OS/process bindings are unaffected; they follow [`porting-to-natives.md`](./porting-to-natives.md) as before.\n- Reviewers can reject a native-optimization PR purely on a missing gate, citing this ADR, without re-deriving the rationale.\n\n## Follow-ups\n\n- Held native candidates (H04 word-diff, H05 LCS, and other v2-rejected candidates) stay held unless a future PR clears gates 1–6 with fresh corpus evidence.\n- When the profiling corpus lands, link its threshold/evidence ledger here so native-port proposals can cite concrete corpus artifacts.\n",
 	"natives-addon-loader-runtime.md": "# Natives Addon Loader Runtime\n\nThis document covers the runtime loader shipped by `@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-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. Performance-motivated native ports of leftover algorithmic hot paths are additionally gated by [`native-ffi-optimization-policy.md`](./native-ffi-optimization-policy.md).\n\n## Implementation files\n\n- `packages/natives/native/index.js`\n- `packages/natives/native/index.d.ts`\n- `packages/natives/native/loader-state.js`\n- `packages/natives/native/embedded-addon.js`\n- `packages/natives/scripts/build-native.ts`\n- `packages/natives/scripts/embed-native.ts`\n- `packages/natives/scripts/gen-enums.ts`\n- `packages/natives/package.json`\n- `crates/pi-natives/src/lib.rs`\n\n## Package entrypoint and public surface\n\n`packages/natives/package.json` points directly at generated native bindings:\n\n- `main`: `./native/index.js`\n- `types`: `./native/index.d.ts`\n- `exports[\".\"].types`: `./native/index.d.ts`\n- `exports[\".\"].import`: `./native/index.js`\n\nThere is no current `packages/natives/src` TypeScript wrapper layer. Consumers import functions/classes/enums directly from `@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}-${process.arch}`.\n- Supported tags are currently:\n  - `linux-x64`\n  - `linux-arm64`\n  - `darwin-arm64`\n  - `win32-x64`\n- x64 can use CPU variants:\n  - `modern` (AVX2-capable)\n  - `baseline` (fallback)\n- Non-x64 uses the default filename without a variant suffix.\n\nFilename strategy:\n\n- Default: `pi_natives.<platform>-<arch>.node`\n- x64 variant: `pi_natives.<platform>-<arch>-modern.node` or `...-baseline.node`\n- x64 runtime fallback includes the unsuffixed default filename after variant candidates.\n\n### Platform-specific variant detection\n\nFor x64, variant selection uses:\n\n- Linux: `/proc/cpuinfo`\n- macOS: `sysctl -n machdep.cpu.leaf7_features`, then `machdep.cpu.features`\n- Windows: PowerShell check for `System.Runtime.Intrinsics.X86.Avx2`\n\n`GJC_NATIVE_VARIANT` can force `modern` or `baseline`; invalid values are ignored.\n\n### Binary distribution and extraction model\n\n`packages/natives/package.json` publishes `native/`, which contains the loader, generated declarations, generated enum patch, embedded-addon manifest stub, and prebuilt `.node` artifacts.\n\nFor compiled binaries, loader behavior is:\n\n1. Check versioned user cache path: `<getNativesDir()>/<packageVersion>/...`.\n2. Check legacy compiled-binary location:\n   - Windows: `%LOCALAPPDATA%/gjc` (fallback `%USERPROFILE%/AppData/Local/gjc`)\n   - non-Windows: `~/.local/bin`\n3. Fall back to packaged `native/` and executable directory candidates.\n\n`getNativesDir()` uses `$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",