@ai-sdk/openai 4.0.68 → 4.0.69

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # @ai-sdk/openai
 
+## 4.0.69
+
+### Patch Changes
+
+- d4d96bf: Add experimental Choice, Score, and Boolean evaluations through `openai.evaluationModel()` and a shared structured language-model evaluation adapter in `@ai-sdk/provider-utils/experimental-evaluation`. Preserve exact labels and metadata, validate score bounds, and return prompted Boolean P(true) estimates validated to be in [0, 1]. Boolean estimates are not guaranteed to be calibrated; application code chooses thresholds.
+- Updated dependencies [215b25e]
+- Updated dependencies [d4d96bf]
+- Updated dependencies [a7dd893]
+- Updated dependencies [3456e2c]
+- Updated dependencies [c4e76de]
+  - @ai-sdk/provider-utils@5.0.43
+  - @ai-sdk/provider@4.0.17
+
 ## 4.0.68
 
 ### Patch Changes

package/dist/index.d.ts

@@ -1,5 +1,5 @@
 import * as _ai_sdk_provider from '@ai-sdk/provider';
-import { JSONValue, Experimental_RealtimeModelV4, Experimental_RealtimeModelV4ClientSecretOptions, Experimental_RealtimeModelV4ClientSecretResult, Experimental_RealtimeModelV4ServerEvent, Experimental_RealtimeModelV4ClientEvent, Experimental_RealtimeModelV4SessionConfig, Experimental_RealtimeFactoryV4, ProviderV4, LanguageModelV4, EmbeddingModelV4, ImageModelV4, TranscriptionModelV4, Experimental_SpeechTranslationModelV4, SpeechModelV4, FilesV4, SkillsV4, Experimental_BatchV4, JSONObject, Experimental_SpeechTranslationModelV4StreamOptions } from '@ai-sdk/provider';
+import { JSONValue, Experimental_RealtimeModelV4, Experimental_RealtimeModelV4ClientSecretOptions, Experimental_RealtimeModelV4ClientSecretResult, Experimental_RealtimeModelV4ServerEvent, Experimental_RealtimeModelV4ClientEvent, Experimental_RealtimeModelV4SessionConfig, Experimental_RealtimeFactoryV4, ProviderV4, LanguageModelV4, Experimental_EvaluationModelV4, EmbeddingModelV4, ImageModelV4, TranscriptionModelV4, Experimental_SpeechTranslationModelV4, SpeechModelV4, FilesV4, SkillsV4, Experimental_BatchV4, JSONObject, Experimental_SpeechTranslationModelV4StreamOptions } from '@ai-sdk/provider';
 import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
 import { InferSchema, FetchFunction, WebSocketConstructor, WORKFLOW_SERIALIZE, WORKFLOW_DESERIALIZE } from '@ai-sdk/provider-utils';
 import { z } from 'zod/v4';
@@ -1575,6 +1575,8 @@ type OpenAISpeechTranslationModelOptions = InferSchema<typeof openAISpeechTransl
 
 interface OpenAIProvider extends ProviderV4 {
     (modelId: OpenAIResponsesModelId): LanguageModelV4;
+    /** Creates an experimental Choice/Score/Boolean evaluation model using the Responses API. */
+    evaluationModel(modelId: OpenAIResponsesModelId): Experimental_EvaluationModelV4;
     /**
      * Creates an OpenAI model for text generation.
      */

package/dist/index.js

@@ -6,6 +6,7 @@ import {
   withoutTrailingSlash,
   withUserAgentSuffix
 } from "@ai-sdk/provider-utils";
+import { Experimental_EvaluationLanguageModel as EvaluationLanguageModel } from "@ai-sdk/provider-utils/experimental-evaluation";
 
 // src/chat/openai-chat-language-model.ts
 import {
@@ -11944,7 +11945,7 @@ var OpenAISkills = class {
 };
 
 // src/version.ts
-var VERSION = true ? "4.0.68" : "0.0.0-test";
+var VERSION = true ? "4.0.69" : "0.0.0-test";
 
 // src/openai-provider.ts
 function createOpenAI(options = {}) {
@@ -12066,6 +12067,10 @@ function createOpenAI(options = {}) {
   provider.chat = createChatModel;
   provider.completion = createCompletionModel;
   provider.responses = createResponsesModel;
+  provider.evaluationModel = (modelId) => new EvaluationLanguageModel({
+    model: createResponsesModel(modelId),
+    provider: `${providerName}.evaluation`
+  });
   provider.embedding = createEmbeddingModel;
   provider.embeddingModel = createEmbeddingModel;
   provider.textEmbedding = createEmbeddingModel;