@ai-sdk/openai 2.0.141 → 2.0.143

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # @ai-sdk/openai
 
+## 2.0.143
+
+### Patch Changes
+
+- 3f019a6: Support positioned Responses API format updates so changing structured output schemas can preserve earlier reasoning and prompt cache reuse. Add a stable request-level text format override and expose prompt cache comparison diagnostics for generation and streaming results.
+
+## 2.0.142
+
+### Patch Changes
+
+- Updated dependencies [c31e0a2]
+  - @ai-sdk/provider-utils@3.0.46
+
 ## 2.0.141
 
 ### Patch Changes

package/dist/index.d.mts

@@ -1,6 +1,8 @@
+import * as _ai_sdk_provider from '@ai-sdk/provider';
 import { ProviderV2, LanguageModelV2, EmbeddingModelV2, ImageModelV2, TranscriptionModelV2, SpeechModelV2 } from '@ai-sdk/provider';
 import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
 import { InferValidator, FetchFunction } from '@ai-sdk/provider-utils';
+import { z } from 'zod/v4';
 
 type OpenAIChatModelId = 'o1' | 'o1-2024-12-17' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | 'gpt-4.1' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4o' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4-turbo' | 'gpt-4-turbo-2024-04-09' | 'gpt-4' | 'gpt-4-0613' | 'gpt-4.5-preview' | 'gpt-4.5-preview-2025-02-27' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | 'gpt-5' | 'gpt-5-2025-08-07' | 'gpt-5-mini' | 'gpt-5-mini-2025-08-07' | 'gpt-5-nano' | 'gpt-5-nano-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5.1' | 'gpt-5.1-chat-latest' | 'gpt-5.2' | 'gpt-5.2-chat-latest' | 'gpt-5.2-pro' | 'gpt-5.2-pro-2025-12-11' | 'gpt-5.3-chat-latest' | 'gpt-5.4' | 'gpt-5.4-2026-03-05' | 'gpt-5.4-mini' | 'gpt-5.4-mini-2026-03-17' | 'gpt-5.4-nano' | 'gpt-5.4-nano-2026-03-17' | 'gpt-5.4-pro' | 'gpt-5.4-pro-2026-03-05' | 'gpt-5.6' | 'gpt-5.6-luna' | 'gpt-5.6-sol' | 'gpt-5.6-terra' | 'gpt-6-astra' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'gpt-6-sol' | (string & {});
 declare const openaiChatLanguageModelOptions: _ai_sdk_provider_utils.LazyValidator<{
@@ -157,6 +159,13 @@ declare const webSearchToolFactory: _ai_sdk_provider_utils.ProviderDefinedToolFa
     };
 }>;
 
+declare const openaiResponsesPromptCacheDiagnosticsSchema: () => z.ZodObject<{
+    type: z.ZodString;
+    reason: z.ZodOptional<z.ZodNullable<z.ZodString>>;
+    cache_missed_tokens: z.ZodOptional<z.ZodNullable<z.ZodNumber>>;
+    comparison_reusable_tokens: z.ZodOptional<z.ZodNullable<z.ZodNumber>>;
+}, z.core.$strip>;
+type OpenAIResponsesPromptCacheDiagnostics = z.infer<ReturnType<typeof openaiResponsesPromptCacheDiagnosticsSchema>>;
 /**
  * A filter used to compare a specified attribute key to a given value using a defined comparison operation.
  */
@@ -231,6 +240,12 @@ declare const openaiResponsesChunkSchema: _ai_sdk_provider_utils.LazyValidator<{
                 orchestration_output_tokens?: number | null | undefined;
             } | null | undefined;
         };
+        prompt_cache_diagnostics?: {
+            type: string;
+            reason?: string | null | undefined;
+            cache_missed_tokens?: number | null | undefined;
+            comparison_reusable_tokens?: number | null | undefined;
+        } | null | undefined;
         incomplete_details?: {
             reason: string;
         } | null | undefined;
@@ -625,6 +640,7 @@ declare const openaiResponsesProviderOptionsSchema: _ai_sdk_provider_utils.LazyV
     previousResponseId?: string | null | undefined;
     promptCacheKey?: string | null | undefined;
     promptCacheOptions?: {
+        comparisonResponseId?: string | undefined;
         mode?: "explicit" | "implicit" | undefined;
         ttl?: "30m" | undefined;
     } | undefined;
@@ -639,11 +655,29 @@ declare const openaiResponsesProviderOptionsSchema: _ai_sdk_provider_utils.LazyV
     store?: boolean | null | undefined;
     strictJsonSchema?: boolean | null | undefined;
     textVerbosity?: "low" | "medium" | "high" | null | undefined;
+    textFormat?: {
+        type: "text";
+    } | {
+        type: "json_schema";
+        name: string;
+        schema: Record<string, _ai_sdk_provider.JSONValue>;
+        description?: string | undefined;
+        strict?: boolean | undefined;
+    } | undefined;
     truncation?: "auto" | "disabled" | null | undefined;
     user?: string | null | undefined;
 }>;
 type OpenAIResponsesProviderOptions = InferValidator<typeof openaiResponsesProviderOptionsSchema>;
 declare const openaiResponsesSystemMessageOptionsSchema: _ai_sdk_provider_utils.LazyValidator<{
+    textFormatUpdate?: {
+        type: "text";
+    } | {
+        type: "json_schema";
+        name: string;
+        schema: Record<string, _ai_sdk_provider.JSONValue>;
+        description?: string | undefined;
+        strict?: boolean | undefined;
+    } | undefined;
     reasoningEffortUpdate?: "low" | "medium" | "high" | "xhigh" | "max" | undefined;
 }>;
 type OpenAIResponsesSystemMessageOptions = InferValidator<typeof openaiResponsesSystemMessageOptionsSchema>;
@@ -756,6 +790,7 @@ type ResponsesProviderMetadata = {
     logprobs?: Array<OpenAIResponsesLogprobs>;
     serviceTier?: string;
     reasoningContext?: string;
+    promptCacheDiagnostics?: OpenAIResponsesPromptCacheDiagnostics;
     /**
      * Provider-specific token usage details, including prompt cache writes and
      * orchestration usage. Surfaced here so downstream consumers can bill it.

package/dist/index.d.ts

@@ -1,6 +1,8 @@
+import * as _ai_sdk_provider from '@ai-sdk/provider';
 import { ProviderV2, LanguageModelV2, EmbeddingModelV2, ImageModelV2, TranscriptionModelV2, SpeechModelV2 } from '@ai-sdk/provider';
 import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
 import { InferValidator, FetchFunction } from '@ai-sdk/provider-utils';
+import { z } from 'zod/v4';
 
 type OpenAIChatModelId = 'o1' | 'o1-2024-12-17' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | 'gpt-4.1' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4o' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4-turbo' | 'gpt-4-turbo-2024-04-09' | 'gpt-4' | 'gpt-4-0613' | 'gpt-4.5-preview' | 'gpt-4.5-preview-2025-02-27' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | 'gpt-5' | 'gpt-5-2025-08-07' | 'gpt-5-mini' | 'gpt-5-mini-2025-08-07' | 'gpt-5-nano' | 'gpt-5-nano-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5.1' | 'gpt-5.1-chat-latest' | 'gpt-5.2' | 'gpt-5.2-chat-latest' | 'gpt-5.2-pro' | 'gpt-5.2-pro-2025-12-11' | 'gpt-5.3-chat-latest' | 'gpt-5.4' | 'gpt-5.4-2026-03-05' | 'gpt-5.4-mini' | 'gpt-5.4-mini-2026-03-17' | 'gpt-5.4-nano' | 'gpt-5.4-nano-2026-03-17' | 'gpt-5.4-pro' | 'gpt-5.4-pro-2026-03-05' | 'gpt-5.6' | 'gpt-5.6-luna' | 'gpt-5.6-sol' | 'gpt-5.6-terra' | 'gpt-6-astra' | 'gpt-6.1-sol' | 'gpt-6-luna' | 'gpt-6-sol' | (string & {});
 declare const openaiChatLanguageModelOptions: _ai_sdk_provider_utils.LazyValidator<{
@@ -157,6 +159,13 @@ declare const webSearchToolFactory: _ai_sdk_provider_utils.ProviderDefinedToolFa
     };
 }>;
 
+declare const openaiResponsesPromptCacheDiagnosticsSchema: () => z.ZodObject<{
+    type: z.ZodString;
+    reason: z.ZodOptional<z.ZodNullable<z.ZodString>>;
+    cache_missed_tokens: z.ZodOptional<z.ZodNullable<z.ZodNumber>>;
+    comparison_reusable_tokens: z.ZodOptional<z.ZodNullable<z.ZodNumber>>;
+}, z.core.$strip>;
+type OpenAIResponsesPromptCacheDiagnostics = z.infer<ReturnType<typeof openaiResponsesPromptCacheDiagnosticsSchema>>;
 /**
  * A filter used to compare a specified attribute key to a given value using a defined comparison operation.
  */
@@ -231,6 +240,12 @@ declare const openaiResponsesChunkSchema: _ai_sdk_provider_utils.LazyValidator<{
                 orchestration_output_tokens?: number | null | undefined;
             } | null | undefined;
         };
+        prompt_cache_diagnostics?: {
+            type: string;
+            reason?: string | null | undefined;
+            cache_missed_tokens?: number | null | undefined;
+            comparison_reusable_tokens?: number | null | undefined;
+        } | null | undefined;
         incomplete_details?: {
             reason: string;
         } | null | undefined;
@@ -625,6 +640,7 @@ declare const openaiResponsesProviderOptionsSchema: _ai_sdk_provider_utils.LazyV
     previousResponseId?: string | null | undefined;
     promptCacheKey?: string | null | undefined;
     promptCacheOptions?: {
+        comparisonResponseId?: string | undefined;
         mode?: "explicit" | "implicit" | undefined;
         ttl?: "30m" | undefined;
     } | undefined;
@@ -639,11 +655,29 @@ declare const openaiResponsesProviderOptionsSchema: _ai_sdk_provider_utils.LazyV
     store?: boolean | null | undefined;
     strictJsonSchema?: boolean | null | undefined;
     textVerbosity?: "low" | "medium" | "high" | null | undefined;
+    textFormat?: {
+        type: "text";
+    } | {
+        type: "json_schema";
+        name: string;
+        schema: Record<string, _ai_sdk_provider.JSONValue>;
+        description?: string | undefined;
+        strict?: boolean | undefined;
+    } | undefined;
     truncation?: "auto" | "disabled" | null | undefined;
     user?: string | null | undefined;
 }>;
 type OpenAIResponsesProviderOptions = InferValidator<typeof openaiResponsesProviderOptionsSchema>;
 declare const openaiResponsesSystemMessageOptionsSchema: _ai_sdk_provider_utils.LazyValidator<{
+    textFormatUpdate?: {
+        type: "text";
+    } | {
+        type: "json_schema";
+        name: string;
+        schema: Record<string, _ai_sdk_provider.JSONValue>;
+        description?: string | undefined;
+        strict?: boolean | undefined;
+    } | undefined;
     reasoningEffortUpdate?: "low" | "medium" | "high" | "xhigh" | "max" | undefined;
 }>;
 type OpenAIResponsesSystemMessageOptions = InferValidator<typeof openaiResponsesSystemMessageOptionsSchema>;
@@ -756,6 +790,7 @@ type ResponsesProviderMetadata = {
     logprobs?: Array<OpenAIResponsesLogprobs>;
     serviceTier?: string;
     reasoningContext?: string;
+    promptCacheDiagnostics?: OpenAIResponsesPromptCacheDiagnostics;
     /**
      * Provider-specific token usage details, including prompt cache writes and
      * orchestration usage. Surfaced here so downstream consumers can bill it.