@mariozechner/pi-ai 0.58.0 → 0.58.2

package/README.md

@@ -729,6 +729,29 @@ const response = await stream(ollamaModel, context, {
 });
 ```
 
+Some OpenAI-compatible servers do not understand the `developer` role used for reasoning-capable models. For those providers, set `compat.supportsDeveloperRole` to `false` so the system prompt is sent as a `system` message instead. If the server also does not support `reasoning_effort`, set `compat.supportsReasoningEffort` to `false` too.
+
+This commonly applies to Ollama, vLLM, SGLang, and similar OpenAI-compatible servers. You can set `compat` at the provider level or per model.
+
+```typescript
+const ollamaReasoningModel: Model<'openai-completions'> = {
+  id: 'gpt-oss:20b',
+  name: 'GPT-OSS 20B (Ollama)',
+  api: 'openai-completions',
+  provider: 'ollama',
+  baseUrl: 'http://localhost:11434/v1',
+  reasoning: true,
+  input: ['text'],
+  cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+  contextWindow: 131072,
+  maxTokens: 32000,
+  compat: {
+    supportsDeveloperRole: false,
+    supportsReasoningEffort: false,
+  }
+};
+```
+
 ### OpenAI Compatibility Settings
 
 The `openai-completions` API is implemented by many providers with minor differences. By default, the library auto-detects compatibility settings based on `baseUrl` for a small set of known OpenAI-compatible providers (Cerebras, xAI, Chutes, DeepSeek, zAi, OpenCode, etc.). For custom proxies or unknown endpoints, you can override these settings via the `compat` field. For `openai-responses` models, the compat field only supports Responses-specific flags.

package/dist/models.d.ts

@@ -12,7 +12,7 @@ export declare function calculateCost<TApi extends Api>(model: Model<TApi>, usag
  *
  * Supported today:
  * - GPT-5.2 / GPT-5.3 / GPT-5.4 model families
- * - Anthropic Messages API Opus 4.6 models (xhigh maps to adaptive effort "max")
+ * - Opus 4.6 models (xhigh maps to adaptive effort "max" on Anthropic-compatible providers)
  */
 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,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;AAED;;;;;;GAMG;AACH,wBAAgB,aAAa,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,OAAO,CAU3E;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\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\n/**\n * Check if a model supports xhigh thinking level.\n *\n * Supported today:\n * - GPT-5.2 / GPT-5.3 / GPT-5.4 model families\n * - Anthropic Messages API Opus 4.6 models (xhigh maps to adaptive effort \"max\")\n */\nexport function supportsXhigh<TApi extends Api>(model: Model<TApi>): boolean {\n\tif (model.id.includes(\"gpt-5.2\") || model.id.includes(\"gpt-5.3\") || model.id.includes(\"gpt-5.4\")) {\n\t\treturn true;\n\t}\n\n\tif (model.api === \"anthropic-messages\") {\n\t\treturn model.id.includes(\"opus-4-6\") || model.id.includes(\"opus-4.6\");\n\t}\n\n\treturn false;\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,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;AAED;;;;;;GAMG;AACH,wBAAgB,aAAa,CAAC,IAAI,SAAS,GAAG,EAAE,KAAK,EAAE,KAAK,CAAC,IAAI,CAAC,GAAG,OAAO,CAU3E;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\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\n/**\n * Check if a model supports xhigh thinking level.\n *\n * Supported today:\n * - GPT-5.2 / GPT-5.3 / GPT-5.4 model families\n * - Opus 4.6 models (xhigh maps to adaptive effort \"max\" on Anthropic-compatible providers)\n */\nexport function supportsXhigh<TApi extends Api>(model: Model<TApi>): boolean {\n\tif (model.id.includes(\"gpt-5.2\") || model.id.includes(\"gpt-5.3\") || model.id.includes(\"gpt-5.4\")) {\n\t\treturn true;\n\t}\n\n\tif (model.id.includes(\"opus-4-6\") || model.id.includes(\"opus-4.6\")) {\n\t\treturn true;\n\t}\n\n\treturn false;\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

@@ -7847,6 +7847,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "minimax/minimax-m2.5: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 "mistralai/codestral-2508": {
             id: string;
             name: string;
@@ -9418,7 +9435,7 @@ export declare const MODELS: {
             provider: string;
             baseUrl: string;
             reasoning: true;
-            input: "text"[];
+            input: ("image" | "text")[];
             cost: {
                 input: number;
                 output: number;
@@ -10686,6 +10703,23 @@ export declare const MODELS: {
             contextWindow: number;
             maxTokens: number;
         };
+        readonly "z-ai/glm-5-turbo": {
+            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 "vercel-ai-gateway": {
         readonly "alibaba/qwen-3-14b": {