@dreb/ai 2.56.0 → 2.57.1

package/README.md

@@ -794,7 +794,7 @@ interface OpenAICompletionsCompat {
   requiresToolResultName?: boolean;  // Whether tool results require the `name` field (default: false)
   requiresAssistantAfterToolResult?: boolean; // Whether tool results must be followed by an assistant message (default: false)
   requiresThinkingAsText?: boolean;  // Whether thinking blocks must be converted to text (default: false)
-  thinkingFormat?: 'openai' | 'openrouter' | 'zai' | 'qwen' | 'qwen-chat-template' | 'kimi'; // Format for reasoning param: 'openai' uses reasoning_effort, 'openrouter' uses reasoning: { effort }, 'zai' uses top-level enable_thinking: boolean, 'qwen' uses top-level enable_thinking: boolean, 'qwen-chat-template' uses chat_template_kwargs.enable_thinking, and 'kimi' uses nested thinking: { type, effort? } plus prompt_cache_key (default: openai)
+  thinkingFormat?: 'openai' | 'openrouter' | 'zai' | 'qwen' | 'qwen-chat-template' | 'kimi'; // Format for reasoning param: 'openai' uses reasoning_effort, 'openrouter' uses reasoning: { effort }, 'zai' uses top-level enable_thinking: boolean, 'qwen' uses top-level enable_thinking: boolean, 'qwen-chat-template' uses chat_template_kwargs.enable_thinking plus a top-level mapped reasoning_effort (Qwen3.8+ models default-map dreb levels onto the native low/medium/xhigh tiers), and 'kimi' uses nested thinking: { type, effort? } plus prompt_cache_key (default: openai)
   openRouterRouting?: OpenRouterRouting; // OpenRouter routing preferences (default: {})
   vercelGatewayRouting?: VercelGatewayRouting; // Vercel AI Gateway routing preferences (default: {})
 }

package/dist/models.d.ts

@@ -41,6 +41,11 @@ export declare function findModelInList(pattern: string, models: Model<Api>[]):
 export declare function getProviders(): KnownProvider[];
 export declare function getModels<TProvider extends KnownProvider>(provider: TProvider): Model<ModelApi<TProvider, keyof (typeof MODELS)[TProvider]>>[];
 export declare function calculateCost<TApi extends Api>(model: Model<TApi>, usage: Usage): Usage["cost"];
+/**
+ * Check whether a model id belongs to Qwen 3.8 or a later Qwen generation — the first
+ * Qwen family with graded `reasoning_effort` tiers (low/medium/xhigh, default xhigh).
+ */
+export declare function isQwen38OrLater(modelId: string): boolean;
 /**
  * Check if a model supports xhigh thinking level.
  *
@@ -48,6 +53,7 @@ export declare function calculateCost<TApi extends Api>(model: Model<TApi>, usag
  * - GPT-5.2 through GPT-5.6 model families
  * - 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)
  */
 export declare function supportsXhigh<TApi extends Api>(model: Model<TApi>): boolean;
 /**

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;AAmBD;;;;;;;GAOG;AACH,wBAAgB,aAAa,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,OAAO,CAkB3E;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 * 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 */\nexport function supportsXhigh<TApi extends Api>(model: Model<TApi>): boolean {\n\tif (model.provider === \"kimi-coding-oauth\" && model.id === \"k3\") 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;;;;;;;;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 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"]}

package/dist/models.generated.d.ts

@@ -3267,6 +3267,34 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "gemini-3.7-flash": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            headers: {
+                "User-Agent": string;
+                "Editor-Version": string;
+                "Editor-Plugin-Version": string;
+                "Copilot-Integration-Id": string;
+            };
+            compat: {
+                supportsStore: false;
+                supportsDeveloperRole: false;
+                supportsReasoningEffort: false;
+            };
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "gpt-4.1": {
             id: string;
             name: string;
@@ -3576,6 +3604,34 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "grok-4.6": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            headers: {
+                "User-Agent": string;
+                "Editor-Version": string;
+                "Editor-Plugin-Version": string;
+                "Copilot-Integration-Id": string;
+            };
+            compat: {
+                supportsStore: false;
+                supportsDeveloperRole: false;
+                supportsReasoningEffort: false;
+            };
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "kimi-k2.7-code": {
             id: string;
             name: string;
@@ -3962,6 +4018,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "gemini-3.7-flash": {
+            id: string;
+            name: string;
+            api: "google-generative-ai";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "gemini-flash-latest": {
             id: string;
             name: string;
@@ -4718,6 +4791,26 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "Qwen/Qwen2.5-Coder-32B-Instruct": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            compat: {
+                supportsDeveloperRole: false;
+            };
+            reasoning: false;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "Qwen/Qwen3-235B-A22B": {
             id: string;
             name: string;
@@ -4778,6 +4871,26 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "Qwen/Qwen3-30B-A3B": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            compat: {
+                supportsDeveloperRole: false;
+            };
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "Qwen/Qwen3-32B": {
             id: string;
             name: string;
@@ -5158,6 +5271,26 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "deepseek-ai/DeepSeek-V3-0324": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            compat: {
+                supportsDeveloperRole: false;
+            };
+            reasoning: false;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "deepseek-ai/DeepSeek-V3.1": {
             id: string;
             name: string;
@@ -5258,6 +5391,26 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "deepseek-ai/DeepSeek-V4-Pro-0813": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            compat: {
+                supportsDeveloperRole: false;
+            };
+            reasoning: true;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "google/gemma-4-26B-A4B-it": {
             id: string;
             name: string;
@@ -5298,6 +5451,26 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "meta-llama/Llama-3.1-8B-Instruct": {
+            id: string;
+            name: string;
+            api: "openai-completions";
+            provider: string;
+            baseUrl: string;
+            compat: {
+                supportsDeveloperRole: false;
+            };
+            reasoning: false;
+            input: "text"[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "meta-llama/Llama-3.3-70B-Instruct": {
             id: string;
             name: string;
@@ -7782,6 +7955,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "gemini-3.7-flash": {
+            id: string;
+            name: string;
+            api: "google-generative-ai";
+            provider: string;
+            baseUrl: string;
+            reasoning: true;
+            input: ("image" | "text")[];
+            cost: {
+                input: number;
+                output: number;
+                cacheRead: number;
+                cacheWrite: number;
+            };
+            contextWindow: number;
+            maxTokens: number;
+        };
         readonly "glm-5": {
             id: string;
             name: string;
@@ -8309,14 +8499,14 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "ling-3.0-tiny-free": {
+        readonly "mimo-v2.5-free": {
             id: string;
             name: string;
             api: "openai-completions";
             provider: string;
             baseUrl: string;
             reasoning: true;
-            input: "text"[];
+            input: ("image" | "text")[];
             cost: {
                 input: number;
                 output: number;
@@ -8326,14 +8516,14 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "mimo-v2.5-free": {
+        readonly "minimax-m2.5": {
             id: string;
             name: string;
             api: "openai-completions";
             provider: string;
             baseUrl: string;
             reasoning: true;
-            input: ("image" | "text")[];
+            input: "text"[];
             cost: {
                 input: number;
                 output: number;
@@ -8343,7 +8533,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "minimax-m2.5": {
+        readonly "minimax-m2.7": {
             id: string;
             name: string;
             api: "openai-completions";
@@ -8360,14 +8550,14 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "minimax-m2.7": {
+        readonly "minimax-m3": {
             id: string;
             name: string;
             api: "openai-completions";
             provider: string;
             baseUrl: string;
             reasoning: true;
-            input: "text"[];
+            input: ("image" | "text")[];
             cost: {
                 input: number;
                 output: number;
@@ -8377,10 +8567,10 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "minimax-m3": {
+        readonly "muse-spark-1.2": {
             id: string;
             name: string;
-            api: "openai-completions";
+            api: "openai-responses";
             provider: string;
             baseUrl: string;
             reasoning: true;
@@ -8532,6 +8722,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "glm-5.3": {
+            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 "gpt-5.6-luna": {
             id: string;
             name: string;
@@ -9809,6 +10016,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "dots-studio/dots-3-note-preview: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 "google/gemini-2.5-flash": {
             id: string;
             name: string;
@@ -10200,6 +10424,40 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "google/gemini-3.7-flash": {
+            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 "google/gemini-3.7-flash:batch": {
+            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 "google/gemma-3-12b-it": {
             id: string;
             name: string;
@@ -10387,23 +10645,6 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "inclusionai/ling-3.0-tiny: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 "inclusionai/ring-2.6-1t": {
             id: string;
             name: string;
@@ -11339,6 +11580,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "nvidia/nemotron-3.5-lightning": {
+            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 "nvidia/nemotron-3.5-lightning:free": {
             id: string;
             name: string;
@@ -13804,6 +14062,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "qwen/qwen3.8-27b": {
+            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 "qwen/qwen3.8-max": {
             id: string;
             name: string;
@@ -15030,6 +15305,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "alibaba/qwen3.8-2.4t-a95b": {
+            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 "alibaba/qwen3.8-max": {
             id: string;
             name: string;
@@ -15778,7 +16070,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "google/gemma-4-26b-a4b-it": {
+        readonly "google/gemini-3.7-flash": {
             id: string;
             name: string;
             api: "anthropic-messages";
@@ -15795,7 +16087,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "google/gemma-4-31b-it": {
+        readonly "google/gemma-4-26b-a4b-it": {
             id: string;
             name: string;
             api: "anthropic-messages";
@@ -15812,14 +16104,14 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "inception/mercury-2": {
+        readonly "google/gemma-4-31b-it": {
             id: string;
             name: string;
             api: "anthropic-messages";
             provider: string;
             baseUrl: string;
             reasoning: true;
-            input: "text"[];
+            input: ("image" | "text")[];
             cost: {
                 input: number;
                 output: number;
@@ -15829,13 +16121,13 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "inception/mercury-coder-small": {
+        readonly "inception/mercury-2": {
             id: string;
             name: string;
             api: "anthropic-messages";
             provider: string;
             baseUrl: string;
-            reasoning: false;
+            reasoning: true;
             input: "text"[];
             cost: {
                 input: number;
@@ -15846,13 +16138,13 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "inclusionai/ling-3.0-flash": {
+        readonly "inception/mercury-coder-small": {
             id: string;
             name: string;
             api: "anthropic-messages";
             provider: string;
             baseUrl: string;
-            reasoning: true;
+            reasoning: false;
             input: "text"[];
             cost: {
                 input: number;
@@ -15863,7 +16155,7 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
-        readonly "inclusionai/ling-3.0-tiny-free": {
+        readonly "inclusionai/ling-3.0-flash": {
             id: string;
             name: string;
             api: "anthropic-messages";
@@ -17689,7 +17981,7 @@ export declare const MODELS: {
             provider: string;
             baseUrl: string;
             reasoning: true;
-            input: "text"[];
+            input: ("image" | "text")[];
             cost: {
                 input: number;
                 output: number;