@dreb/ai 2.64.4 → 2.64.5

package/README.md

@@ -444,7 +444,7 @@ const response = await completeSimple(model, {
   messages: [{ role: 'user', content: 'Solve: 2x + 5 = 13' }]
 }, {
   reasoning: 'medium'  // 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max'
-  // Native normalized 'max' is model-aware (currently GPT-5.6). Claude's established xhigh mapping still emits provider-native 'max'.
+  // Native normalized 'max' is model-aware (currently GPT-5.6 and GPT-6 families). Claude's established xhigh mapping still emits provider-native 'max'.
 });
 
 // Access thinking and text blocks
@@ -571,6 +571,10 @@ if (message.stopReason === 'error' || message.stopReason === 'aborted') {
 }
 ```
 
+### Context Overflow
+
+Use `isContextOverflow(message, model.contextWindow)` to detect recognized provider context-limit errors or successful responses whose full input usage exceeds the configured window. The latter compares `usage.input + usage.cacheRead + usage.cacheWrite`; output tokens do not count toward that input-only check. A conservative registry window can be lower than the server's hard limit (for example, Copilot Opus 4.8 can accept requests above its configured 200K window). Detection does not raise the registry limit or modify the response.
+
 ### Aborting Requests
 
 The abort signal allows you to cancel in-progress requests. Aborted requests have `stopReason === 'aborted'`:
@@ -1014,7 +1018,7 @@ const key = getEnvApiKey('openai');  // checks OPENAI_API_KEY
 
 Several providers require OAuth authentication instead of static API keys:
 
-- **OpenAI Codex** (ChatGPT Plus/Pro subscription, access to GPT-5.x Codex models)
+- **OpenAI Codex** (ChatGPT Plus/Pro subscription, access to GPT-5.x and GPT-6 Codex models)
 - **GitHub Copilot** (Copilot subscription)
 - **Google Gemini CLI** (Gemini 2.0/2.5 via Google Cloud Code Assist; free tier or paid subscription)
 - **Antigravity** (Free Gemini 3, Claude, GPT-OSS via Google Cloud)
@@ -1146,7 +1150,7 @@ const response = await complete(model, {
 
 ### Provider Notes
 
-**OpenAI Codex**: Requires a ChatGPT Plus or Pro subscription. Provides access to GPT-5.x Codex models with extended context windows and reasoning capabilities. The library automatically handles session-based prompt caching when `sessionId` is provided in stream options. You can set `transport` in stream options to `"sse"`, `"websocket"`, or `"auto"` for Codex Responses transport selection. When using WebSocket with a `sessionId`, connections are reused per session and expire after 5 minutes of inactivity.
+**OpenAI Codex**: Requires a ChatGPT Plus or Pro subscription. Provides access to GPT-5.x and GPT-6 Codex models with extended context windows and reasoning capabilities. The library automatically handles session-based prompt caching when `sessionId` is provided in stream options. You can set `transport` in stream options to `"sse"`, `"websocket"`, or `"auto"` for Codex Responses transport selection. When using WebSocket with a `sessionId`, connections are reused per session and expire after 5 minutes of inactivity.
 
 **Azure OpenAI (Responses)**: Uses the Responses API only. Set `AZURE_OPENAI_API_KEY` and either `AZURE_OPENAI_BASE_URL` or `AZURE_OPENAI_RESOURCE_NAME`. Use `AZURE_OPENAI_API_VERSION` (defaults to `v1`) to override the API version if needed. Deployment names are treated as model IDs by default, override with `azureDeploymentName` or `AZURE_OPENAI_DEPLOYMENT_NAME_MAP` using comma-separated `model-id=deployment` pairs (for example `gpt-4o-mini=my-deployment,gpt-4o=prod`). Legacy deployment-based URLs are intentionally unsupported.
 

package/dist/models.d.ts

@@ -51,6 +51,7 @@ export declare function isQwen38OrLater(modelId: string): boolean;
  *
  * Supported today:
  * - GPT-5.6 model families (Sol, Terra, Luna, and the alias)
+ * - GPT-6 model families (Astra and future variants)
  */
 export declare function supportsMax<TApi extends Api>(model: Model<TApi>): boolean;
 /**
@@ -58,6 +59,7 @@ export declare function supportsMax<TApi extends Api>(model: Model<TApi>): boole
  *
  * Supported today:
  * - GPT-5.2 through GPT-5.6 model families
+ * - GPT-6 model families (Astra and future variants)
  * - Claude Opus 4.6–4.x and Claude 5 model families
  * - Kimi Code K3 (xhigh maps to its advertised "max" effort)
  * - Qwen 3.8+ model families (xhigh is their top native effort tier)

package/dist/models.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"models.d.ts","sourceRoot":"","sources":["../src/models.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAE,MAAM,uBAAuB,CAAC;AAC/C,OAAO,KAAK,EAAE,GAAG,EAAE,aAAa,EAAE,KAAK,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAanE,KAAK,QAAQ,CACZ,SAAS,SAAS,aAAa,EAC/B,QAAQ,SAAS,MAAM,CAAC,OAAO,MAAM,CAAC,CAAC,SAAS,CAAC,IAC9C,CAAC,OAAO,MAAM,CAAC,CAAC,SAAS,CAAC,CAAC,QAAQ,CAAC,SAAS;IAAE,GAAG,EAAE,MAAM,IAAI,CAAA;CAAE,GAAG,CAAC,IAAI,SAAS,GAAG,GAAG,IAAI,GAAG,KAAK,CAAC,GAAG,KAAK,CAAC;AAEjH,wBAAgB,QAAQ,CAAC,SAAS,SAAS,aAAa,EAAE,QAAQ,SAAS,MAAM,CAAC,OAAO,MAAM,CAAC,CAAC,SAAS,CAAC,EAC1G,QAAQ,EAAE,SAAS,EACnB,OAAO,EAAE,QAAQ,GACf,KAAK,CAAC,QAAQ,CAAC,SAAS,EAAE,QAAQ,CAAC,CAAC,CAGtC;AAED;;;;;;GAMG;AACH,wBAAgB,YAAY,CAAC,EAAE,EAAE,MAAM,GAAG,OAAO,CAGhD;AAED;;;;;;;;;;;;;;;;GAgBG;AACH,wBAAgB,SAAS,CAAC,QAAQ,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,GAAG,SAAS,CA8BnF;AAED;;;;;;GAMG;AACH,wBAAgB,eAAe,CAAC,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,CAAC,GAAG,CAAC,EAAE,GAAG,KAAK,CAAC,GAAG,CAAC,GAAG,SAAS,CA4B7F;AAED,wBAAgB,YAAY,IAAI,aAAa,EAAE,CAE9C;AAED,wBAAgB,SAAS,CAAC,SAAS,SAAS,aAAa,EACxD,QAAQ,EAAE,SAAS,GACjB,KAAK,CAAC,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC,OAAO,MAAM,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,CAGhE;AAED,wBAAgB,aAAa,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,KAAK,GAAG,KAAK,CAAC,MAAM,CAAC,CAO/F;AAoCD;;;GAGG;AACH,wBAAgB,eAAe,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAIxD;AAED;;;;;GAKG;AACH,wBAAgB,WAAW,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,OAAO,CAGzE;AAED;;;;;;;;GAQG;AACH,wBAAgB,aAAa,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,OAAO,CAmB3E;AAED;;;;GAIG;AACH,wBAAgB,wBAAwB,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,OAAO,CAGtF;AAED;;;GAGG;AACH,wBAAgB,cAAc,CAAC,IAAI,SAAS,GAAG,EAC9C,CAAC,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,IAAI,GAAG,SAAS,EACjC,CAAC,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,IAAI,GAAG,SAAS,GAC/B,OAAO,CAGT","sourcesContent":["import { MODELS } from \"./models.generated.js\";\nimport type { Api, KnownProvider, Model, Usage } from \"./types.js\";\n\nconst modelRegistry: Map<string, Map<string, Model<Api>>> = new Map();\n\n// Initialize registry from MODELS on module load\nfor (const [provider, models] of Object.entries(MODELS)) {\n\tconst providerModels = new Map<string, Model<Api>>();\n\tfor (const [id, model] of Object.entries(models)) {\n\t\tproviderModels.set(id, model as Model<Api>);\n\t}\n\tmodelRegistry.set(provider, providerModels);\n}\n\ntype ModelApi<\n\tTProvider extends KnownProvider,\n\tTModelId extends keyof (typeof MODELS)[TProvider],\n> = (typeof MODELS)[TProvider][TModelId] extends { api: infer TApi } ? (TApi extends Api ? TApi : never) : never;\n\nexport function getModel<TProvider extends KnownProvider, TModelId extends keyof (typeof MODELS)[TProvider]>(\n\tprovider: TProvider,\n\tmodelId: TModelId,\n): Model<ModelApi<TProvider, TModelId>> {\n\tconst providerModels = modelRegistry.get(provider);\n\treturn providerModels?.get(modelId as string) as Model<ModelApi<TProvider, TModelId>>;\n}\n\n/**\n * Check if a model ID looks like an alias (no date suffix).\n * Aliases are preferred over dated versions when fuzzy matching.\n *\n * IDs ending with `-latest` are treated as aliases.\n * IDs ending with a date pattern (`-YYYYMMDD`) are treated as dated versions.\n */\nexport function isModelAlias(id: string): boolean {\n\tif (id.endsWith(\"-latest\")) return true;\n\treturn !/-\\d{8}$/.test(id);\n}\n\n/**\n * Find a model by fuzzy matching against the provider's registered models.\n *\n * Resolution order:\n * 1. Exact match by provider + model ID (via registry Map.get)\n * 2. Case-insensitive substring match against model ID and display name\n * 3. Among matches, prefer aliases (non-dated IDs) over dated versions\n * 4. Among ties, pick the lexicographically highest (latest) ID\n *\n * This is the same matching logic used by the CLI, subagent model resolution,\n * and interactive mode — centralised here so tests can exercise the real path.\n *\n * @example\n * findModel(\"anthropic\", \"sonnet\")  // → latest claude-sonnet alias\n * findModel(\"anthropic\", \"haiku\")   // → latest claude-haiku alias\n * findModel(\"openai\", \"gpt-5\")     // → latest gpt-5 alias\n */\nexport function findModel(provider: string, pattern: string): Model<Api> | undefined {\n\tconst providerModels = modelRegistry.get(provider);\n\tif (!providerModels) return undefined;\n\n\t// Try exact match first\n\tconst exact = providerModels.get(pattern);\n\tif (exact) return exact;\n\n\t// Substring match (case-insensitive)\n\tconst normalizedPattern = pattern.toLowerCase();\n\tconst matches = Array.from(providerModels.values()).filter(\n\t\t(m) => m.id.toLowerCase().includes(normalizedPattern) || m.name?.toLowerCase().includes(normalizedPattern),\n\t);\n\n\tif (matches.length === 0) return undefined;\n\tif (matches.length === 1) return matches[0];\n\n\t// Multiple matches — separate into aliases and dated versions\n\tconst aliases = matches.filter((m) => isModelAlias(m.id));\n\tconst datedVersions = matches.filter((m) => !isModelAlias(m.id));\n\n\tif (aliases.length > 0) {\n\t\t// Prefer alias — if multiple, pick the lexicographically highest\n\t\taliases.sort((a, b) => b.id.localeCompare(a.id));\n\t\treturn aliases[0];\n\t}\n\n\t// All dated — prefer the latest\n\tdatedVersions.sort((a, b) => b.id.localeCompare(a.id));\n\treturn datedVersions[0];\n}\n\n/**\n * Find a model by fuzzy matching against a flat array of models.\n * Same algorithm as findModel() but operates on an arbitrary model list\n * instead of the built-in registry.\n *\n * Used by model-resolver.ts and other code that manages its own model lists.\n */\nexport function findModelInList(pattern: string, models: Model<Api>[]): Model<Api> | undefined {\n\tif (models.length === 0) return undefined;\n\n\tconst normalizedPattern = pattern.toLowerCase();\n\n\t// Exact ID match (case-insensitive)\n\tconst exactById = models.find((m) => m.id.toLowerCase() === normalizedPattern);\n\tif (exactById) return exactById;\n\n\t// Substring match (case-insensitive)\n\tconst matches = models.filter(\n\t\t(m) => m.id.toLowerCase().includes(normalizedPattern) || m.name?.toLowerCase().includes(normalizedPattern),\n\t);\n\n\tif (matches.length === 0) return undefined;\n\tif (matches.length === 1) return matches[0];\n\n\t// Multiple matches — separate into aliases and dated versions\n\tconst aliases = matches.filter((m) => isModelAlias(m.id));\n\tconst datedVersions = matches.filter((m) => !isModelAlias(m.id));\n\n\tif (aliases.length > 0) {\n\t\taliases.sort((a, b) => b.id.localeCompare(a.id));\n\t\treturn aliases[0];\n\t}\n\n\tdatedVersions.sort((a, b) => b.id.localeCompare(a.id));\n\treturn datedVersions[0];\n}\n\nexport function getProviders(): KnownProvider[] {\n\treturn Array.from(modelRegistry.keys()) as KnownProvider[];\n}\n\nexport function getModels<TProvider extends KnownProvider>(\n\tprovider: TProvider,\n): Model<ModelApi<TProvider, keyof (typeof MODELS)[TProvider]>>[] {\n\tconst models = modelRegistry.get(provider);\n\treturn models ? (Array.from(models.values()) as Model<ModelApi<TProvider, keyof (typeof MODELS)[TProvider]>>[]) : [];\n}\n\nexport function calculateCost<TApi extends Api>(model: Model<TApi>, usage: Usage): Usage[\"cost\"] {\n\tusage.cost.input = (model.cost.input / 1000000) * usage.input;\n\tusage.cost.output = (model.cost.output / 1000000) * usage.output;\n\tusage.cost.cacheRead = (model.cost.cacheRead / 1000000) * usage.cacheRead;\n\tusage.cost.cacheWrite = (model.cost.cacheWrite / 1000000) * usage.cacheWrite;\n\tusage.cost.total = usage.cost.input + usage.cost.output + usage.cost.cacheRead + usage.cost.cacheWrite;\n\treturn usage.cost;\n}\n\ninterface ClaudeFamilyVersion {\n\tfamily: \"opus\" | \"sonnet\";\n\tmajor: number;\n\tminor?: number;\n}\n\n/** Parse Claude family versions without mistaking long date suffixes for versions. */\nfunction claudeFamilyVersion(modelId: string): ClaudeFamilyVersion | undefined {\n\tconst match = modelId.match(/(opus|sonnet)-(\\d{1,2})(?:[.-](\\d{1,2}))?(?!\\d)/);\n\tif (!match) return undefined;\n\treturn {\n\t\tfamily: match[1] as ClaudeFamilyVersion[\"family\"],\n\t\tmajor: Number.parseInt(match[2], 10),\n\t\tminor: match[3] === undefined ? undefined : Number.parseInt(match[3], 10),\n\t};\n}\n\n/**\n * Parse Qwen family versions without mistaking parameter counts for minor versions.\n * Only a dot separates major from minor (qwen3.8-27b, Qwen-3.8); a hyphen after the\n * major version introduces the parameter size (qwen3-32b → 3.0, not 3.32). A capture\n * directly followed by a `b`-suffixed size token is a parameter count, not a version\n * (qwen-32b, Qwen-7B-Chat, deepseek-r1-distill-qwen-32b), and Qwen majors never reach\n * two digits, so only a single digit is accepted.\n */\nfunction qwenFamilyVersion(modelId: string): { major: number; minor: number } | undefined {\n\tconst match = modelId.match(/\\bqwen[\\s_-]*v?(\\d)(?:\\.(\\d+))?(?![\\d.]*b\\b)/i);\n\tif (!match) return undefined;\n\treturn {\n\t\tmajor: Number.parseInt(match[1], 10),\n\t\tminor: match[2] === undefined ? 0 : Number.parseInt(match[2], 10),\n\t};\n}\n\n/**\n * Check whether a model id belongs to Qwen 3.8 or a later Qwen generation — the first\n * Qwen family with graded `reasoning_effort` tiers (low/medium/xhigh, default xhigh).\n */\nexport function isQwen38OrLater(modelId: string): boolean {\n\tconst qwen = qwenFamilyVersion(modelId);\n\tif (!qwen) return false;\n\treturn qwen.major > 3 || (qwen.major === 3 && qwen.minor >= 8);\n}\n\n/**\n * Check if a model supports the native `max` reasoning tier.\n *\n * Supported today:\n * - GPT-5.6 model families (Sol, Terra, Luna, and the alias)\n */\nexport function supportsMax<TApi extends Api>(model: Model<TApi>): boolean {\n\tif (/(?:^|\\/)gpt-5\\.6(?:$|[-.])/.test(model.id.toLowerCase())) return true;\n\treturn false;\n}\n\n/**\n * Check if a model supports xhigh thinking level.\n *\n * Supported today:\n * - GPT-5.2 through GPT-5.6 model families\n * - Claude Opus 4.6–4.x and Claude 5 model families\n * - Kimi Code K3 (xhigh maps to its advertised \"max\" effort)\n * - Qwen 3.8+ model families (xhigh is their top native effort tier)\n */\nexport function supportsXhigh<TApi extends Api>(model: Model<TApi>): boolean {\n\tif (model.provider === \"kimi-coding-oauth\" && model.id === \"k3\") return true;\n\tif (isQwen38OrLater(model.id)) return true;\n\tif (\n\t\tmodel.id.includes(\"gpt-5.2\") ||\n\t\tmodel.id.includes(\"gpt-5.3\") ||\n\t\tmodel.id.includes(\"gpt-5.4\") ||\n\t\tmodel.id.includes(\"gpt-5.5\") ||\n\t\tmodel.id.includes(\"gpt-5.6\")\n\t) {\n\t\treturn true;\n\t}\n\n\tconst claude = claudeFamilyVersion(model.id);\n\tif (!claude) return false;\n\tif (claude.family === \"opus\") {\n\t\treturn claude.major >= 5 || (claude.major === 4 && (claude.minor ?? 0) >= 6);\n\t}\n\treturn claude.major >= 5;\n}\n\n/**\n * Check if a model uses adaptive thinking (Opus/Sonnet 4.6–4.x and Claude 5\n * families), where the `thinkingDisplay` option is honored. Mirrors the\n * per-provider internal checks.\n */\nexport function supportsAdaptiveThinking<TApi extends Api>(model: Model<TApi>): boolean {\n\tconst claude = claudeFamilyVersion(model.id);\n\treturn claude != null && (claude.major >= 5 || (claude.major === 4 && (claude.minor ?? 0) >= 6));\n}\n\n/**\n * Check if two models are equal by comparing both their id and provider.\n * Returns false if either model is null or undefined.\n */\nexport function modelsAreEqual<TApi extends Api>(\n\ta: Model<TApi> | null | undefined,\n\tb: Model<TApi> | null | undefined,\n): boolean {\n\tif (!a || !b) return false;\n\treturn a.id === b.id && a.provider === b.provider;\n}\n"]}
+{"version":3,"file":"models.d.ts","sourceRoot":"","sources":["../src/models.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAE,MAAM,uBAAuB,CAAC;AAC/C,OAAO,KAAK,EAAE,GAAG,EAAE,aAAa,EAAE,KAAK,EAAE,KAAK,EAAE,MAAM,YAAY,CAAC;AAanE,KAAK,QAAQ,CACZ,SAAS,SAAS,aAAa,EAC/B,QAAQ,SAAS,MAAM,CAAC,OAAO,MAAM,CAAC,CAAC,SAAS,CAAC,IAC9C,CAAC,OAAO,MAAM,CAAC,CAAC,SAAS,CAAC,CAAC,QAAQ,CAAC,SAAS;IAAE,GAAG,EAAE,MAAM,IAAI,CAAA;CAAE,GAAG,CAAC,IAAI,SAAS,GAAG,GAAG,IAAI,GAAG,KAAK,CAAC,GAAG,KAAK,CAAC;AAEjH,wBAAgB,QAAQ,CAAC,SAAS,SAAS,aAAa,EAAE,QAAQ,SAAS,MAAM,CAAC,OAAO,MAAM,CAAC,CAAC,SAAS,CAAC,EAC1G,QAAQ,EAAE,SAAS,EACnB,OAAO,EAAE,QAAQ,GACf,KAAK,CAAC,QAAQ,CAAC,SAAS,EAAE,QAAQ,CAAC,CAAC,CAGtC;AAED;;;;;;GAMG;AACH,wBAAgB,YAAY,CAAC,EAAE,EAAE,MAAM,GAAG,OAAO,CAGhD;AAED;;;;;;;;;;;;;;;;GAgBG;AACH,wBAAgB,SAAS,CAAC,QAAQ,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,KAAK,CAAC,GAAG,CAAC,GAAG,SAAS,CA8BnF;AAED;;;;;;GAMG;AACH,wBAAgB,eAAe,CAAC,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,CAAC,GAAG,CAAC,EAAE,GAAG,KAAK,CAAC,GAAG,CAAC,GAAG,SAAS,CA4B7F;AAED,wBAAgB,YAAY,IAAI,aAAa,EAAE,CAE9C;AAED,wBAAgB,SAAS,CAAC,SAAS,SAAS,aAAa,EACxD,QAAQ,EAAE,SAAS,GACjB,KAAK,CAAC,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC,OAAO,MAAM,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,CAGhE;AAED,wBAAgB,aAAa,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,EAAE,KAAK,EAAE,KAAK,GAAG,KAAK,CAAC,MAAM,CAAC,CAO/F;AAoCD;;;GAGG;AACH,wBAAgB,eAAe,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAIxD;AAED;;;;;;GAMG;AACH,wBAAgB,WAAW,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,OAAO,CAKzE;AAED;;;;;;;;;GASG;AACH,wBAAgB,aAAa,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,OAAO,CAoB3E;AAED;;;;GAIG;AACH,wBAAgB,wBAAwB,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,OAAO,CAGtF;AAED;;;GAGG;AACH,wBAAgB,cAAc,CAAC,IAAI,SAAS,GAAG,EAC9C,CAAC,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,IAAI,GAAG,SAAS,EACjC,CAAC,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,IAAI,GAAG,SAAS,GAC/B,OAAO,CAGT","sourcesContent":["import { MODELS } from \"./models.generated.js\";\nimport type { Api, KnownProvider, Model, Usage } from \"./types.js\";\n\nconst modelRegistry: Map<string, Map<string, Model<Api>>> = new Map();\n\n// Initialize registry from MODELS on module load\nfor (const [provider, models] of Object.entries(MODELS)) {\n\tconst providerModels = new Map<string, Model<Api>>();\n\tfor (const [id, model] of Object.entries(models)) {\n\t\tproviderModels.set(id, model as Model<Api>);\n\t}\n\tmodelRegistry.set(provider, providerModels);\n}\n\ntype ModelApi<\n\tTProvider extends KnownProvider,\n\tTModelId extends keyof (typeof MODELS)[TProvider],\n> = (typeof MODELS)[TProvider][TModelId] extends { api: infer TApi } ? (TApi extends Api ? TApi : never) : never;\n\nexport function getModel<TProvider extends KnownProvider, TModelId extends keyof (typeof MODELS)[TProvider]>(\n\tprovider: TProvider,\n\tmodelId: TModelId,\n): Model<ModelApi<TProvider, TModelId>> {\n\tconst providerModels = modelRegistry.get(provider);\n\treturn providerModels?.get(modelId as string) as Model<ModelApi<TProvider, TModelId>>;\n}\n\n/**\n * Check if a model ID looks like an alias (no date suffix).\n * Aliases are preferred over dated versions when fuzzy matching.\n *\n * IDs ending with `-latest` are treated as aliases.\n * IDs ending with a date pattern (`-YYYYMMDD`) are treated as dated versions.\n */\nexport function isModelAlias(id: string): boolean {\n\tif (id.endsWith(\"-latest\")) return true;\n\treturn !/-\\d{8}$/.test(id);\n}\n\n/**\n * Find a model by fuzzy matching against the provider's registered models.\n *\n * Resolution order:\n * 1. Exact match by provider + model ID (via registry Map.get)\n * 2. Case-insensitive substring match against model ID and display name\n * 3. Among matches, prefer aliases (non-dated IDs) over dated versions\n * 4. Among ties, pick the lexicographically highest (latest) ID\n *\n * This is the same matching logic used by the CLI, subagent model resolution,\n * and interactive mode — centralised here so tests can exercise the real path.\n *\n * @example\n * findModel(\"anthropic\", \"sonnet\")  // → latest claude-sonnet alias\n * findModel(\"anthropic\", \"haiku\")   // → latest claude-haiku alias\n * findModel(\"openai\", \"gpt-5\")     // → latest gpt-5 alias\n */\nexport function findModel(provider: string, pattern: string): Model<Api> | undefined {\n\tconst providerModels = modelRegistry.get(provider);\n\tif (!providerModels) return undefined;\n\n\t// Try exact match first\n\tconst exact = providerModels.get(pattern);\n\tif (exact) return exact;\n\n\t// Substring match (case-insensitive)\n\tconst normalizedPattern = pattern.toLowerCase();\n\tconst matches = Array.from(providerModels.values()).filter(\n\t\t(m) => m.id.toLowerCase().includes(normalizedPattern) || m.name?.toLowerCase().includes(normalizedPattern),\n\t);\n\n\tif (matches.length === 0) return undefined;\n\tif (matches.length === 1) return matches[0];\n\n\t// Multiple matches — separate into aliases and dated versions\n\tconst aliases = matches.filter((m) => isModelAlias(m.id));\n\tconst datedVersions = matches.filter((m) => !isModelAlias(m.id));\n\n\tif (aliases.length > 0) {\n\t\t// Prefer alias — if multiple, pick the lexicographically highest\n\t\taliases.sort((a, b) => b.id.localeCompare(a.id));\n\t\treturn aliases[0];\n\t}\n\n\t// All dated — prefer the latest\n\tdatedVersions.sort((a, b) => b.id.localeCompare(a.id));\n\treturn datedVersions[0];\n}\n\n/**\n * Find a model by fuzzy matching against a flat array of models.\n * Same algorithm as findModel() but operates on an arbitrary model list\n * instead of the built-in registry.\n *\n * Used by model-resolver.ts and other code that manages its own model lists.\n */\nexport function findModelInList(pattern: string, models: Model<Api>[]): Model<Api> | undefined {\n\tif (models.length === 0) return undefined;\n\n\tconst normalizedPattern = pattern.toLowerCase();\n\n\t// Exact ID match (case-insensitive)\n\tconst exactById = models.find((m) => m.id.toLowerCase() === normalizedPattern);\n\tif (exactById) return exactById;\n\n\t// Substring match (case-insensitive)\n\tconst matches = models.filter(\n\t\t(m) => m.id.toLowerCase().includes(normalizedPattern) || m.name?.toLowerCase().includes(normalizedPattern),\n\t);\n\n\tif (matches.length === 0) return undefined;\n\tif (matches.length === 1) return matches[0];\n\n\t// Multiple matches — separate into aliases and dated versions\n\tconst aliases = matches.filter((m) => isModelAlias(m.id));\n\tconst datedVersions = matches.filter((m) => !isModelAlias(m.id));\n\n\tif (aliases.length > 0) {\n\t\taliases.sort((a, b) => b.id.localeCompare(a.id));\n\t\treturn aliases[0];\n\t}\n\n\tdatedVersions.sort((a, b) => b.id.localeCompare(a.id));\n\treturn datedVersions[0];\n}\n\nexport function getProviders(): KnownProvider[] {\n\treturn Array.from(modelRegistry.keys()) as KnownProvider[];\n}\n\nexport function getModels<TProvider extends KnownProvider>(\n\tprovider: TProvider,\n): Model<ModelApi<TProvider, keyof (typeof MODELS)[TProvider]>>[] {\n\tconst models = modelRegistry.get(provider);\n\treturn models ? (Array.from(models.values()) as Model<ModelApi<TProvider, keyof (typeof MODELS)[TProvider]>>[]) : [];\n}\n\nexport function calculateCost<TApi extends Api>(model: Model<TApi>, usage: Usage): Usage[\"cost\"] {\n\tusage.cost.input = (model.cost.input / 1000000) * usage.input;\n\tusage.cost.output = (model.cost.output / 1000000) * usage.output;\n\tusage.cost.cacheRead = (model.cost.cacheRead / 1000000) * usage.cacheRead;\n\tusage.cost.cacheWrite = (model.cost.cacheWrite / 1000000) * usage.cacheWrite;\n\tusage.cost.total = usage.cost.input + usage.cost.output + usage.cost.cacheRead + usage.cost.cacheWrite;\n\treturn usage.cost;\n}\n\ninterface ClaudeFamilyVersion {\n\tfamily: \"opus\" | \"sonnet\";\n\tmajor: number;\n\tminor?: number;\n}\n\n/** Parse Claude family versions without mistaking long date suffixes for versions. */\nfunction claudeFamilyVersion(modelId: string): ClaudeFamilyVersion | undefined {\n\tconst match = modelId.match(/(opus|sonnet)-(\\d{1,2})(?:[.-](\\d{1,2}))?(?!\\d)/);\n\tif (!match) return undefined;\n\treturn {\n\t\tfamily: match[1] as ClaudeFamilyVersion[\"family\"],\n\t\tmajor: Number.parseInt(match[2], 10),\n\t\tminor: match[3] === undefined ? undefined : Number.parseInt(match[3], 10),\n\t};\n}\n\n/**\n * Parse Qwen family versions without mistaking parameter counts for minor versions.\n * Only a dot separates major from minor (qwen3.8-27b, Qwen-3.8); a hyphen after the\n * major version introduces the parameter size (qwen3-32b → 3.0, not 3.32). A capture\n * directly followed by a `b`-suffixed size token is a parameter count, not a version\n * (qwen-32b, Qwen-7B-Chat, deepseek-r1-distill-qwen-32b), and Qwen majors never reach\n * two digits, so only a single digit is accepted.\n */\nfunction qwenFamilyVersion(modelId: string): { major: number; minor: number } | undefined {\n\tconst match = modelId.match(/\\bqwen[\\s_-]*v?(\\d)(?:\\.(\\d+))?(?![\\d.]*b\\b)/i);\n\tif (!match) return undefined;\n\treturn {\n\t\tmajor: Number.parseInt(match[1], 10),\n\t\tminor: match[2] === undefined ? 0 : Number.parseInt(match[2], 10),\n\t};\n}\n\n/**\n * Check whether a model id belongs to Qwen 3.8 or a later Qwen generation — the first\n * Qwen family with graded `reasoning_effort` tiers (low/medium/xhigh, default xhigh).\n */\nexport function isQwen38OrLater(modelId: string): boolean {\n\tconst qwen = qwenFamilyVersion(modelId);\n\tif (!qwen) return false;\n\treturn qwen.major > 3 || (qwen.major === 3 && qwen.minor >= 8);\n}\n\n/**\n * Check if a model supports the native `max` reasoning tier.\n *\n * Supported today:\n * - GPT-5.6 model families (Sol, Terra, Luna, and the alias)\n * - GPT-6 model families (Astra and future variants)\n */\nexport function supportsMax<TApi extends Api>(model: Model<TApi>): boolean {\n\tconst id = model.id.toLowerCase();\n\t// Anchored to the id start or a gateway \"/\" prefix so unrelated ids\n\t// (e.g. \"gpt-60\") do not match.\n\treturn /(?:^|\\/)gpt-5\\.6(?:$|[-.])/.test(id) || /(?:^|\\/)gpt-6(?:$|[-.])/.test(id);\n}\n\n/**\n * Check if a model supports xhigh thinking level.\n *\n * Supported today:\n * - GPT-5.2 through GPT-5.6 model families\n * - GPT-6 model families (Astra and future variants)\n * - Claude Opus 4.6–4.x and Claude 5 model families\n * - Kimi Code K3 (xhigh maps to its advertised \"max\" effort)\n * - Qwen 3.8+ model families (xhigh is their top native effort tier)\n */\nexport function supportsXhigh<TApi extends Api>(model: Model<TApi>): boolean {\n\tif (model.provider === \"kimi-coding-oauth\" && model.id === \"k3\") return true;\n\tif (isQwen38OrLater(model.id)) return true;\n\tif (\n\t\tmodel.id.includes(\"gpt-5.2\") ||\n\t\tmodel.id.includes(\"gpt-5.3\") ||\n\t\tmodel.id.includes(\"gpt-5.4\") ||\n\t\tmodel.id.includes(\"gpt-5.5\") ||\n\t\tmodel.id.includes(\"gpt-5.6\") ||\n\t\tmodel.id.includes(\"gpt-6\")\n\t) {\n\t\treturn true;\n\t}\n\n\tconst claude = claudeFamilyVersion(model.id);\n\tif (!claude) return false;\n\tif (claude.family === \"opus\") {\n\t\treturn claude.major >= 5 || (claude.major === 4 && (claude.minor ?? 0) >= 6);\n\t}\n\treturn claude.major >= 5;\n}\n\n/**\n * Check if a model uses adaptive thinking (Opus/Sonnet 4.6–4.x and Claude 5\n * families), where the `thinkingDisplay` option is honored. Mirrors the\n * per-provider internal checks.\n */\nexport function supportsAdaptiveThinking<TApi extends Api>(model: Model<TApi>): boolean {\n\tconst claude = claudeFamilyVersion(model.id);\n\treturn claude != null && (claude.major >= 5 || (claude.major === 4 && (claude.minor ?? 0) >= 6));\n}\n\n/**\n * Check if two models are equal by comparing both their id and provider.\n * Returns false if either model is null or undefined.\n */\nexport function modelsAreEqual<TApi extends Api>(\n\ta: Model<TApi> | null | undefined,\n\tb: Model<TApi> | null | undefined,\n): boolean {\n\tif (!a || !b) return false;\n\treturn a.id === b.id && a.provider === b.provider;\n}\n"]}

package/dist/models.generated.d.ts

@@ -850,6 +850,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "global.xai.grok-4.6": {
+            id: string;
+            name: string;
+            api: "bedrock-converse-stream";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "google.gemma-3-27b-it": {
             id: string;
             name: string;
@@ -1955,6 +1972,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "us.xai.grok-4.6": {
+            id: string;
+            name: string;
+            api: "bedrock-converse-stream";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "writer.palmyra-x4-v1:0": {
             id: string;
             name: string;
@@ -3032,14 +3066,14 @@ export declare const MODELS: {
         };
     };
     readonly cerebras: {
-        readonly "gemma-4-31b": {
+        readonly "gpt-oss-120b": {
             id: string;
             name: string;
             api: "openai-completions";
             provider: string;
             baseUrl: string;
             reasoning: true;
-            input: ("image" | "text")[];
+            input: "text"[];
             cost: {
                 input: number;
                 output: number;
@@ -3049,14 +3083,14 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "gpt-oss-120b": {
+        readonly "qwen-3.8-27b": {
             id: string;
             name: string;
             api: "openai-completions";
             provider: string;
             baseUrl: string;
             reasoning: true;
-            input: "text"[];
+            input: ("image" | "text")[];
             cost: {
                 input: number;
                 output: number;
@@ -3594,7 +3628,7 @@ export declare const MODELS: {
         readonly "gpt-6-astra": {
             id: string;
             name: string;
-            api: "openai-completions";
+            api: "openai-responses";
             provider: string;
             baseUrl: string;
             headers: {
@@ -3603,11 +3637,6 @@ export declare const MODELS: {
                 "Editor-Plugin-Version": string;
                 "Copilot-Integration-Id": string;
             };
-            compat: {
-                supportsStore: false;
-                supportsDeveloperRole: false;
-                supportsReasoningEffort: false;
-            };
             reasoning: true;
             input: ("image" | "text")[];
             cost: {
@@ -7680,92 +7709,7 @@ export declare const MODELS: {
         };
     };
     readonly "openai-codex": {
-        readonly "gpt-5.1": {
-            id: string;
-            name: string;
-            api: "openai-codex-responses";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
-        readonly "gpt-5.1-codex-max": {
-            id: string;
-            name: string;
-            api: "openai-codex-responses";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
-        readonly "gpt-5.1-codex-mini": {
-            id: string;
-            name: string;
-            api: "openai-codex-responses";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
-        readonly "gpt-5.3-codex": {
-            id: string;
-            name: string;
-            api: "openai-codex-responses";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
-        readonly "gpt-5.3-codex-spark": {
-            id: string;
-            name: string;
-            api: "openai-codex-responses";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: "text"[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
-        readonly "gpt-5.4": {
+        readonly "gpt-5.4-mini": {
             id: string;
             name: string;
             api: "openai-codex-responses";
@@ -7782,7 +7726,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "gpt-5.4-mini": {
+        readonly "gpt-5.5": {
             id: string;
             name: string;
             api: "openai-codex-responses";
@@ -7799,7 +7743,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "gpt-5.5": {
+        readonly "gpt-5.6-luna": {
             id: string;
             name: string;
             api: "openai-codex-responses";
@@ -7816,7 +7760,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "gpt-5.6-luna": {
+        readonly "gpt-5.6-sol": {
             id: string;
             name: string;
             api: "openai-codex-responses";
@@ -7833,7 +7777,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "gpt-5.6-sol": {
+        readonly "gpt-5.6-terra": {
             id: string;
             name: string;
             api: "openai-codex-responses";
@@ -7850,7 +7794,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "gpt-5.6-terra": {
+        readonly "gpt-6-astra": {
             id: string;
             name: string;
             api: "openai-codex-responses";
@@ -11596,23 +11540,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "minimax/minimax-m2.7:free": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: "text"[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "minimax/minimax-m3": {
             id: string;
             name: string;
@@ -11647,23 +11574,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "minimax/minimax-m3:free": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "mistralai/codestral-2508": {
             id: string;
             name: string;
@@ -12106,40 +12016,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "nex-agi/nex-n2-mini": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
-        readonly "nex-agi/nex-n2-pro": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "nvidia/nemotron-3-nano-30b-a3b": {
             id: string;
             name: string;
@@ -15387,23 +15263,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "z-ai/glm-5.2:free": {
-            id: string;
-            name: string;
-            api: "openai-completions";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: "text"[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "z-ai/glm-5.3": {
             id: string;
             name: string;
@@ -17514,23 +17373,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "minimax/minimax-m2.7-free": {
-            id: string;
-            name: string;
-            api: "anthropic-messages";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: "text"[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "minimax/minimax-m2.7-highspeed": {
             id: string;
             name: string;
@@ -17565,23 +17407,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "minimax/minimax-m3-free": {
-            id: string;
-            name: string;
-            api: "anthropic-messages";
-            provider: string;
-            baseUrl: string;
-            reasoning: true;
-            input: ("image" | "text")[];
-            cost: {
-                input: number;
-                output: number;
-                cacheRead: number;
-                cacheWrite: number;
-            };
-            contextWindow: number;
-            maxTokens: number;
-        };
         readonly "mistral/codestral": {
             id: string;
             name: string;