@ai-sdk/openai 2.1.0-beta.8 → 3.0.0-beta.17

package/dist/internal/index.d.mts

@@ -1,4 +1,4 @@
-import { LanguageModelV3, EmbeddingModelV3, ImageModelV3, TranscriptionModelV2CallOptions, TranscriptionModelV2, SpeechModelV2 } from '@ai-sdk/provider';
+import { LanguageModelV3, EmbeddingModelV3, ImageModelV3, TranscriptionModelV3CallOptions, TranscriptionModelV3, SpeechModelV3 } from '@ai-sdk/provider';
 import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 import { z } from 'zod/v4';
@@ -129,7 +129,7 @@ declare class OpenAIEmbeddingModel implements EmbeddingModelV3<string> {
     doEmbed({ values, headers, abortSignal, providerOptions, }: Parameters<EmbeddingModelV3<string>['doEmbed']>[0]): Promise<Awaited<ReturnType<EmbeddingModelV3<string>['doEmbed']>>>;
 }
 
-type OpenAIImageModelId = 'gpt-image-1' | 'dall-e-3' | 'dall-e-2' | (string & {});
+type OpenAIImageModelId = 'dall-e-3' | 'dall-e-2' | 'gpt-image-1' | 'gpt-image-1-mini' | (string & {});
 declare const modelMaxImagesPerCall: Record<OpenAIImageModelId, number>;
 declare const hasDefaultResponseFormat: Set<string>;
 
@@ -161,7 +161,7 @@ declare const openAITranscriptionProviderOptions: z.ZodObject<{
 }, z.core.$strip>;
 type OpenAITranscriptionProviderOptions = z.infer<typeof openAITranscriptionProviderOptions>;
 
-type OpenAITranscriptionCallOptions = Omit<TranscriptionModelV2CallOptions, 'providerOptions'> & {
+type OpenAITranscriptionCallOptions = Omit<TranscriptionModelV3CallOptions, 'providerOptions'> & {
     providerOptions?: {
         openai?: OpenAITranscriptionProviderOptions;
     };
@@ -171,14 +171,14 @@ interface OpenAITranscriptionModelConfig extends OpenAIConfig {
         currentDate?: () => Date;
     };
 }
-declare class OpenAITranscriptionModel implements TranscriptionModelV2 {
+declare class OpenAITranscriptionModel implements TranscriptionModelV3 {
     readonly modelId: OpenAITranscriptionModelId;
     private readonly config;
-    readonly specificationVersion = "v2";
+    readonly specificationVersion = "v3";
     get provider(): string;
     constructor(modelId: OpenAITranscriptionModelId, config: OpenAITranscriptionModelConfig);
     private getArgs;
-    doGenerate(options: OpenAITranscriptionCallOptions): Promise<Awaited<ReturnType<TranscriptionModelV2['doGenerate']>>>;
+    doGenerate(options: OpenAITranscriptionCallOptions): Promise<Awaited<ReturnType<TranscriptionModelV3['doGenerate']>>>;
 }
 
 type OpenAISpeechModelId = 'tts-1' | 'tts-1-hd' | 'gpt-4o-mini-tts' | (string & {});
@@ -193,17 +193,17 @@ interface OpenAISpeechModelConfig extends OpenAIConfig {
         currentDate?: () => Date;
     };
 }
-declare class OpenAISpeechModel implements SpeechModelV2 {
+declare class OpenAISpeechModel implements SpeechModelV3 {
     readonly modelId: OpenAISpeechModelId;
     private readonly config;
-    readonly specificationVersion = "v2";
+    readonly specificationVersion = "v3";
     get provider(): string;
     constructor(modelId: OpenAISpeechModelId, config: OpenAISpeechModelConfig);
     private getArgs;
-    doGenerate(options: Parameters<SpeechModelV2['doGenerate']>[0]): Promise<Awaited<ReturnType<SpeechModelV2['doGenerate']>>>;
+    doGenerate(options: Parameters<SpeechModelV3['doGenerate']>[0]): Promise<Awaited<ReturnType<SpeechModelV3['doGenerate']>>>;
 }
 
-type OpenAIResponsesModelId = 'o1' | 'o1-2024-12-17' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | '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-codex' | '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-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | (string & {});
+type OpenAIResponsesModelId = 'chatgpt-4o-latest' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4-0613' | 'gpt-4-turbo-2024-04-09' | 'gpt-4-turbo' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1' | 'gpt-4' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini-2024-07-18' | 'gpt-4o-mini' | 'gpt-4o' | 'gpt-5-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5-codex' | 'gpt-5-mini-2025-08-07' | 'gpt-5-mini' | 'gpt-5-nano-2025-08-07' | 'gpt-5-nano' | 'gpt-5-pro-2025-10-06' | 'gpt-5-pro' | 'gpt-5' | 'o1-2024-12-17' | 'o1' | 'o3-2025-04-16' | 'o3-mini-2025-01-31' | 'o3-mini' | 'o3' | (string & {});
 
 declare class OpenAIResponsesLanguageModel implements LanguageModelV3 {
     readonly specificationVersion = "v3";
@@ -458,4 +458,108 @@ declare const fileSearch: _ai_sdk_provider_utils.ProviderDefinedToolFactoryWithO
     filters?: OpenAIResponsesFileSearchToolComparisonFilter | OpenAIResponsesFileSearchToolCompoundFilter;
 }>;
 
-export { OpenAIChatLanguageModel, type OpenAIChatLanguageModelOptions, type OpenAIChatModelId, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionProviderOptions, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingProviderOptions, OpenAIImageModel, type OpenAIImageModelId, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, type OpenAISpeechCallOptions, OpenAISpeechModel, type OpenAISpeechModelId, type OpenAITranscriptionCallOptions, OpenAITranscriptionModel, type OpenAITranscriptionModelId, type OpenAITranscriptionProviderOptions, codeInterpreter, codeInterpreterArgsSchema, codeInterpreterInputSchema, codeInterpreterOutputSchema, codeInterpreterToolFactory, fileSearch, fileSearchArgsSchema, fileSearchOutputSchema, hasDefaultResponseFormat, modelMaxImagesPerCall, openAITranscriptionProviderOptions, openaiChatLanguageModelOptions, openaiCompletionProviderOptions, openaiEmbeddingProviderOptions };
+declare const imageGenerationArgsSchema: z.ZodObject<{
+    background: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+        opaque: "opaque";
+        transparent: "transparent";
+    }>>;
+    inputFidelity: z.ZodOptional<z.ZodEnum<{
+        low: "low";
+        high: "high";
+    }>>;
+    inputImageMask: z.ZodOptional<z.ZodObject<{
+        fileId: z.ZodOptional<z.ZodString>;
+        imageUrl: z.ZodOptional<z.ZodString>;
+    }, z.core.$strip>>;
+    model: z.ZodOptional<z.ZodString>;
+    moderation: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+    }>>;
+    outputCompression: z.ZodOptional<z.ZodNumber>;
+    outputFormat: z.ZodOptional<z.ZodEnum<{
+        png: "png";
+        jpeg: "jpeg";
+        webp: "webp";
+    }>>;
+    partialImages: z.ZodOptional<z.ZodNumber>;
+    quality: z.ZodOptional<z.ZodEnum<{
+        low: "low";
+        medium: "medium";
+        high: "high";
+        auto: "auto";
+    }>>;
+    size: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+        "1024x1024": "1024x1024";
+        "1024x1536": "1024x1536";
+        "1536x1024": "1536x1024";
+    }>>;
+}, z.core.$strict>;
+declare const imageGenerationOutputSchema: z.ZodObject<{
+    result: z.ZodString;
+}, z.core.$strip>;
+type ImageGenerationArgs = {
+    /**
+     * Background type for the generated image. Default is 'auto'.
+     */
+    background?: 'auto' | 'opaque' | 'transparent';
+    /**
+     * Input fidelity for the generated image. Default is 'low'.
+     */
+    inputFidelity?: 'low' | 'high';
+    /**
+     * Optional mask for inpainting.
+     * Contains image_url (string, optional) and file_id (string, optional).
+     */
+    inputImageMask?: {
+        /**
+         * File ID for the mask image.
+         */
+        fileId?: string;
+        /**
+         * Base64-encoded mask image.
+         */
+        imageUrl?: string;
+    };
+    /**
+     * The image generation model to use. Default: gpt-image-1.
+     */
+    model?: string;
+    /**
+     * Moderation level for the generated image. Default: auto.
+     */
+    moderation?: 'auto';
+    /**
+     * Compression level for the output image. Default: 100.
+     */
+    outputCompression?: number;
+    /**
+     * The output format of the generated image. One of png, webp, or jpeg.
+     * Default: png
+     */
+    outputFormat?: 'png' | 'jpeg' | 'webp';
+    /**
+     * Number of partial images to generate in streaming mode, from 0 (default value) to 3.
+     */
+    partialImages?: number;
+    /**
+     * The quality of the generated image.
+     * One of low, medium, high, or auto. Default: auto.
+     */
+    quality?: 'auto' | 'low' | 'medium' | 'high';
+    /**
+     * The size of the generated image.
+     * One of 1024x1024, 1024x1536, 1536x1024, or auto.
+     * Default: auto.
+     */
+    size?: 'auto' | '1024x1024' | '1024x1536' | '1536x1024';
+};
+declare const imageGeneration: (args?: ImageGenerationArgs) => _ai_sdk_provider_utils.Tool<{}, {
+    /**
+     * The generated image encoded in base64.
+     */
+    result: string;
+}>;
+
+export { OpenAIChatLanguageModel, type OpenAIChatLanguageModelOptions, type OpenAIChatModelId, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionProviderOptions, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingProviderOptions, OpenAIImageModel, type OpenAIImageModelId, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, type OpenAISpeechCallOptions, OpenAISpeechModel, type OpenAISpeechModelId, type OpenAITranscriptionCallOptions, OpenAITranscriptionModel, type OpenAITranscriptionModelId, type OpenAITranscriptionProviderOptions, codeInterpreter, codeInterpreterArgsSchema, codeInterpreterInputSchema, codeInterpreterOutputSchema, codeInterpreterToolFactory, fileSearch, fileSearchArgsSchema, fileSearchOutputSchema, hasDefaultResponseFormat, imageGeneration, imageGenerationArgsSchema, imageGenerationOutputSchema, modelMaxImagesPerCall, openAITranscriptionProviderOptions, openaiChatLanguageModelOptions, openaiCompletionProviderOptions, openaiEmbeddingProviderOptions };

package/dist/internal/index.d.ts

@@ -1,4 +1,4 @@
-import { LanguageModelV3, EmbeddingModelV3, ImageModelV3, TranscriptionModelV2CallOptions, TranscriptionModelV2, SpeechModelV2 } from '@ai-sdk/provider';
+import { LanguageModelV3, EmbeddingModelV3, ImageModelV3, TranscriptionModelV3CallOptions, TranscriptionModelV3, SpeechModelV3 } from '@ai-sdk/provider';
 import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 import { z } from 'zod/v4';
@@ -129,7 +129,7 @@ declare class OpenAIEmbeddingModel implements EmbeddingModelV3<string> {
     doEmbed({ values, headers, abortSignal, providerOptions, }: Parameters<EmbeddingModelV3<string>['doEmbed']>[0]): Promise<Awaited<ReturnType<EmbeddingModelV3<string>['doEmbed']>>>;
 }
 
-type OpenAIImageModelId = 'gpt-image-1' | 'dall-e-3' | 'dall-e-2' | (string & {});
+type OpenAIImageModelId = 'dall-e-3' | 'dall-e-2' | 'gpt-image-1' | 'gpt-image-1-mini' | (string & {});
 declare const modelMaxImagesPerCall: Record<OpenAIImageModelId, number>;
 declare const hasDefaultResponseFormat: Set<string>;
 
@@ -161,7 +161,7 @@ declare const openAITranscriptionProviderOptions: z.ZodObject<{
 }, z.core.$strip>;
 type OpenAITranscriptionProviderOptions = z.infer<typeof openAITranscriptionProviderOptions>;
 
-type OpenAITranscriptionCallOptions = Omit<TranscriptionModelV2CallOptions, 'providerOptions'> & {
+type OpenAITranscriptionCallOptions = Omit<TranscriptionModelV3CallOptions, 'providerOptions'> & {
     providerOptions?: {
         openai?: OpenAITranscriptionProviderOptions;
     };
@@ -171,14 +171,14 @@ interface OpenAITranscriptionModelConfig extends OpenAIConfig {
         currentDate?: () => Date;
     };
 }
-declare class OpenAITranscriptionModel implements TranscriptionModelV2 {
+declare class OpenAITranscriptionModel implements TranscriptionModelV3 {
     readonly modelId: OpenAITranscriptionModelId;
     private readonly config;
-    readonly specificationVersion = "v2";
+    readonly specificationVersion = "v3";
     get provider(): string;
     constructor(modelId: OpenAITranscriptionModelId, config: OpenAITranscriptionModelConfig);
     private getArgs;
-    doGenerate(options: OpenAITranscriptionCallOptions): Promise<Awaited<ReturnType<TranscriptionModelV2['doGenerate']>>>;
+    doGenerate(options: OpenAITranscriptionCallOptions): Promise<Awaited<ReturnType<TranscriptionModelV3['doGenerate']>>>;
 }
 
 type OpenAISpeechModelId = 'tts-1' | 'tts-1-hd' | 'gpt-4o-mini-tts' | (string & {});
@@ -193,17 +193,17 @@ interface OpenAISpeechModelConfig extends OpenAIConfig {
         currentDate?: () => Date;
     };
 }
-declare class OpenAISpeechModel implements SpeechModelV2 {
+declare class OpenAISpeechModel implements SpeechModelV3 {
     readonly modelId: OpenAISpeechModelId;
     private readonly config;
-    readonly specificationVersion = "v2";
+    readonly specificationVersion = "v3";
     get provider(): string;
     constructor(modelId: OpenAISpeechModelId, config: OpenAISpeechModelConfig);
     private getArgs;
-    doGenerate(options: Parameters<SpeechModelV2['doGenerate']>[0]): Promise<Awaited<ReturnType<SpeechModelV2['doGenerate']>>>;
+    doGenerate(options: Parameters<SpeechModelV3['doGenerate']>[0]): Promise<Awaited<ReturnType<SpeechModelV3['doGenerate']>>>;
 }
 
-type OpenAIResponsesModelId = 'o1' | 'o1-2024-12-17' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | '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-codex' | '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-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | (string & {});
+type OpenAIResponsesModelId = 'chatgpt-4o-latest' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4-0613' | 'gpt-4-turbo-2024-04-09' | 'gpt-4-turbo' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1' | 'gpt-4' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini-2024-07-18' | 'gpt-4o-mini' | 'gpt-4o' | 'gpt-5-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5-codex' | 'gpt-5-mini-2025-08-07' | 'gpt-5-mini' | 'gpt-5-nano-2025-08-07' | 'gpt-5-nano' | 'gpt-5-pro-2025-10-06' | 'gpt-5-pro' | 'gpt-5' | 'o1-2024-12-17' | 'o1' | 'o3-2025-04-16' | 'o3-mini-2025-01-31' | 'o3-mini' | 'o3' | (string & {});
 
 declare class OpenAIResponsesLanguageModel implements LanguageModelV3 {
     readonly specificationVersion = "v3";
@@ -458,4 +458,108 @@ declare const fileSearch: _ai_sdk_provider_utils.ProviderDefinedToolFactoryWithO
     filters?: OpenAIResponsesFileSearchToolComparisonFilter | OpenAIResponsesFileSearchToolCompoundFilter;
 }>;
 
-export { OpenAIChatLanguageModel, type OpenAIChatLanguageModelOptions, type OpenAIChatModelId, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionProviderOptions, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingProviderOptions, OpenAIImageModel, type OpenAIImageModelId, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, type OpenAISpeechCallOptions, OpenAISpeechModel, type OpenAISpeechModelId, type OpenAITranscriptionCallOptions, OpenAITranscriptionModel, type OpenAITranscriptionModelId, type OpenAITranscriptionProviderOptions, codeInterpreter, codeInterpreterArgsSchema, codeInterpreterInputSchema, codeInterpreterOutputSchema, codeInterpreterToolFactory, fileSearch, fileSearchArgsSchema, fileSearchOutputSchema, hasDefaultResponseFormat, modelMaxImagesPerCall, openAITranscriptionProviderOptions, openaiChatLanguageModelOptions, openaiCompletionProviderOptions, openaiEmbeddingProviderOptions };
+declare const imageGenerationArgsSchema: z.ZodObject<{
+    background: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+        opaque: "opaque";
+        transparent: "transparent";
+    }>>;
+    inputFidelity: z.ZodOptional<z.ZodEnum<{
+        low: "low";
+        high: "high";
+    }>>;
+    inputImageMask: z.ZodOptional<z.ZodObject<{
+        fileId: z.ZodOptional<z.ZodString>;
+        imageUrl: z.ZodOptional<z.ZodString>;
+    }, z.core.$strip>>;
+    model: z.ZodOptional<z.ZodString>;
+    moderation: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+    }>>;
+    outputCompression: z.ZodOptional<z.ZodNumber>;
+    outputFormat: z.ZodOptional<z.ZodEnum<{
+        png: "png";
+        jpeg: "jpeg";
+        webp: "webp";
+    }>>;
+    partialImages: z.ZodOptional<z.ZodNumber>;
+    quality: z.ZodOptional<z.ZodEnum<{
+        low: "low";
+        medium: "medium";
+        high: "high";
+        auto: "auto";
+    }>>;
+    size: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+        "1024x1024": "1024x1024";
+        "1024x1536": "1024x1536";
+        "1536x1024": "1536x1024";
+    }>>;
+}, z.core.$strict>;
+declare const imageGenerationOutputSchema: z.ZodObject<{
+    result: z.ZodString;
+}, z.core.$strip>;
+type ImageGenerationArgs = {
+    /**
+     * Background type for the generated image. Default is 'auto'.
+     */
+    background?: 'auto' | 'opaque' | 'transparent';
+    /**
+     * Input fidelity for the generated image. Default is 'low'.
+     */
+    inputFidelity?: 'low' | 'high';
+    /**
+     * Optional mask for inpainting.
+     * Contains image_url (string, optional) and file_id (string, optional).
+     */
+    inputImageMask?: {
+        /**
+         * File ID for the mask image.
+         */
+        fileId?: string;
+        /**
+         * Base64-encoded mask image.
+         */
+        imageUrl?: string;
+    };
+    /**
+     * The image generation model to use. Default: gpt-image-1.
+     */
+    model?: string;
+    /**
+     * Moderation level for the generated image. Default: auto.
+     */
+    moderation?: 'auto';
+    /**
+     * Compression level for the output image. Default: 100.
+     */
+    outputCompression?: number;
+    /**
+     * The output format of the generated image. One of png, webp, or jpeg.
+     * Default: png
+     */
+    outputFormat?: 'png' | 'jpeg' | 'webp';
+    /**
+     * Number of partial images to generate in streaming mode, from 0 (default value) to 3.
+     */
+    partialImages?: number;
+    /**
+     * The quality of the generated image.
+     * One of low, medium, high, or auto. Default: auto.
+     */
+    quality?: 'auto' | 'low' | 'medium' | 'high';
+    /**
+     * The size of the generated image.
+     * One of 1024x1024, 1024x1536, 1536x1024, or auto.
+     * Default: auto.
+     */
+    size?: 'auto' | '1024x1024' | '1024x1536' | '1536x1024';
+};
+declare const imageGeneration: (args?: ImageGenerationArgs) => _ai_sdk_provider_utils.Tool<{}, {
+    /**
+     * The generated image encoded in base64.
+     */
+    result: string;
+}>;
+
+export { OpenAIChatLanguageModel, type OpenAIChatLanguageModelOptions, type OpenAIChatModelId, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionProviderOptions, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingProviderOptions, OpenAIImageModel, type OpenAIImageModelId, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, type OpenAISpeechCallOptions, OpenAISpeechModel, type OpenAISpeechModelId, type OpenAITranscriptionCallOptions, OpenAITranscriptionModel, type OpenAITranscriptionModelId, type OpenAITranscriptionProviderOptions, codeInterpreter, codeInterpreterArgsSchema, codeInterpreterInputSchema, codeInterpreterOutputSchema, codeInterpreterToolFactory, fileSearch, fileSearchArgsSchema, fileSearchOutputSchema, hasDefaultResponseFormat, imageGeneration, imageGenerationArgsSchema, imageGenerationOutputSchema, modelMaxImagesPerCall, openAITranscriptionProviderOptions, openaiChatLanguageModelOptions, openaiCompletionProviderOptions, openaiEmbeddingProviderOptions };

package/dist/internal/index.js

@@ -36,6 +36,9 @@ __export(internal_exports, {
   fileSearchArgsSchema: () => fileSearchArgsSchema,
   fileSearchOutputSchema: () => fileSearchOutputSchema,
   hasDefaultResponseFormat: () => hasDefaultResponseFormat,
+  imageGeneration: () => imageGeneration,
+  imageGenerationArgsSchema: () => imageGenerationArgsSchema,
+  imageGenerationOutputSchema: () => imageGenerationOutputSchema,
   modelMaxImagesPerCall: () => modelMaxImagesPerCall,
   openAITranscriptionProviderOptions: () => openAITranscriptionProviderOptions,
   openaiChatLanguageModelOptions: () => openaiChatLanguageModelOptions,
@@ -75,6 +78,7 @@ function convertToOpenAIChatMessages({
   prompt,
   systemMessageMode = "system"
 }) {
+  var _a;
   const messages = [];
   const warnings = [];
   for (const { role, content } of prompt) {
@@ -113,7 +117,7 @@ function convertToOpenAIChatMessages({
         messages.push({
           role: "user",
           content: content.map((part, index) => {
-            var _a, _b, _c;
+            var _a2, _b, _c;
             switch (part.type) {
               case "text": {
                 return { type: "text", text: part.text };
@@ -126,7 +130,7 @@ function convertToOpenAIChatMessages({
                     image_url: {
                       url: part.data instanceof URL ? part.data.toString() : `data:${mediaType};base64,${(0, import_provider_utils2.convertToBase64)(part.data)}`,
                       // OpenAI specific extension: image detail
-                      detail: (_b = (_a = part.providerOptions) == null ? void 0 : _a.openai) == null ? void 0 : _b.imageDetail
+                      detail: (_b = (_a2 = part.providerOptions) == null ? void 0 : _a2.openai) == null ? void 0 : _b.imageDetail
                     }
                   };
                 } else if (part.mediaType.startsWith("audio/")) {
@@ -223,6 +227,9 @@ function convertToOpenAIChatMessages({
             case "error-text":
               contentValue = output.value;
               break;
+            case "execution-denied":
+              contentValue = (_a = output.reason) != null ? _a : "Tool execution denied.";
+              break;
             case "content":
             case "json":
             case "error-json":
@@ -1605,9 +1612,13 @@ var import_v48 = require("zod/v4");
 var modelMaxImagesPerCall = {
   "dall-e-3": 1,
   "dall-e-2": 10,
-  "gpt-image-1": 10
+  "gpt-image-1": 10,
+  "gpt-image-1-mini": 10
 };
-var hasDefaultResponseFormat = /* @__PURE__ */ new Set(["gpt-image-1"]);
+var hasDefaultResponseFormat = /* @__PURE__ */ new Set([
+  "gpt-image-1",
+  "gpt-image-1-mini"
+]);
 
 // src/image/openai-image-model.ts
 var OpenAIImageModel = class {
@@ -1788,7 +1799,7 @@ var OpenAITranscriptionModel = class {
   constructor(modelId, config) {
     this.modelId = modelId;
     this.config = config;
-    this.specificationVersion = "v2";
+    this.specificationVersion = "v3";
   }
   get provider() {
     return this.config.provider;
@@ -1928,7 +1939,7 @@ var OpenAISpeechModel = class {
   constructor(modelId, config) {
     this.modelId = modelId;
     this.config = config;
-    this.specificationVersion = "v2";
+    this.specificationVersion = "v3";
   }
   get provider() {
     return this.config.provider;
@@ -2069,7 +2080,7 @@ async function convertToOpenAIResponsesInput({
   store,
   hasLocalShellTool = false
 }) {
-  var _a, _b, _c, _d, _e, _f, _g, _h, _i;
+  var _a, _b, _c, _d, _e, _f, _g, _h, _i, _j;
   const input = [];
   const warnings = [];
   for (const { role, content } of prompt) {
@@ -2272,6 +2283,9 @@ async function convertToOpenAIResponsesInput({
             case "error-text":
               contentValue = output.value;
               break;
+            case "execution-denied":
+              contentValue = (_j = output.reason) != null ? _j : "Tool execution denied.";
+              break;
             case "content":
             case "json":
             case "error-json":
@@ -2506,6 +2520,7 @@ var imageGenerationArgsSchema = import_v418.z.object({
   moderation: import_v418.z.enum(["auto"]).optional(),
   outputCompression: import_v418.z.number().int().min(0).max(100).optional(),
   outputFormat: import_v418.z.enum(["png", "jpeg", "webp"]).optional(),
+  partialImages: import_v418.z.number().int().min(0).max(3).optional(),
   quality: import_v418.z.enum(["auto", "low", "medium", "high"]).optional(),
   size: import_v418.z.enum(["1024x1024", "1024x1536", "1536x1024", "auto"]).optional()
 }).strict();
@@ -2518,6 +2533,9 @@ var imageGenerationToolFactory = (0, import_provider_utils15.createProviderDefin
   inputSchema: import_v418.z.object({}),
   outputSchema: imageGenerationOutputSchema
 });
+var imageGeneration = (args = {}) => {
+  return imageGenerationToolFactory(args);
+};
 
 // src/responses/openai-responses-prepare-tools.ts
 function prepareResponsesTools({
@@ -2602,11 +2620,12 @@ function prepareResponsesTools({
                 image_url: args.inputImageMask.imageUrl
               } : void 0,
               model: args.model,
-              size: args.size,
-              quality: args.quality,
               moderation: args.moderation,
+              partial_images: args.partialImages,
+              quality: args.quality,
+              output_compression: args.outputCompression,
               output_format: args.outputFormat,
-              output_compression: args.outputCompression
+              size: args.size
             });
             break;
           }
@@ -3342,7 +3361,8 @@ var OpenAIResponsesLanguageModel = class {
                 controller.enqueue({
                   type: "tool-input-start",
                   id: value.item.id,
-                  toolName: webSearchToolName != null ? webSearchToolName : "web_search"
+                  toolName: webSearchToolName != null ? webSearchToolName : "web_search",
+                  providerExecuted: true
                 });
               } else if (value.item.type === "computer_call") {
                 ongoingToolCalls[value.output_index] = {
@@ -3352,7 +3372,8 @@ var OpenAIResponsesLanguageModel = class {
                 controller.enqueue({
                   type: "tool-input-start",
                   id: value.item.id,
-                  toolName: "computer_use"
+                  toolName: "computer_use",
+                  providerExecuted: true
                 });
               } else if (value.item.type === "code_interpreter_call") {
                 ongoingToolCalls[value.output_index] = {
@@ -3365,7 +3386,8 @@ var OpenAIResponsesLanguageModel = class {
                 controller.enqueue({
                   type: "tool-input-start",
                   id: value.item.id,
-                  toolName: "code_interpreter"
+                  toolName: "code_interpreter",
+                  providerExecuted: true
                 });
                 controller.enqueue({
                   type: "tool-input-delta",
@@ -3565,6 +3587,17 @@ var OpenAIResponsesLanguageModel = class {
                   delta: value.delta
                 });
               }
+            } else if (isResponseImageGenerationCallPartialImageChunk(value)) {
+              controller.enqueue({
+                type: "tool-result",
+                toolCallId: value.item_id,
+                toolName: "image_generation",
+                result: {
+                  result: value.partial_image_b64
+                },
+                providerExecuted: true,
+                preliminary: true
+              });
             } else if (isResponseCodeInterpreterCallCodeDeltaChunk(value)) {
               const toolCall = ongoingToolCalls[value.output_index];
               if (toolCall != null) {
@@ -3837,6 +3870,12 @@ var responseFunctionCallArgumentsDeltaSchema = import_v419.z.object({
   output_index: import_v419.z.number(),
   delta: import_v419.z.string()
 });
+var responseImageGenerationCallPartialImageSchema = import_v419.z.object({
+  type: import_v419.z.literal("response.image_generation_call.partial_image"),
+  item_id: import_v419.z.string(),
+  output_index: import_v419.z.number(),
+  partial_image_b64: import_v419.z.string()
+});
 var responseCodeInterpreterCallCodeDeltaSchema = import_v419.z.object({
   type: import_v419.z.literal("response.code_interpreter_call_code.delta"),
   item_id: import_v419.z.string(),
@@ -3886,6 +3925,7 @@ var openaiResponsesChunkSchema = import_v419.z.union([
   responseOutputItemAddedSchema,
   responseOutputItemDoneSchema,
   responseFunctionCallArgumentsDeltaSchema,
+  responseImageGenerationCallPartialImageSchema,
   responseCodeInterpreterCallCodeDeltaSchema,
   responseCodeInterpreterCallCodeDoneSchema,
   responseAnnotationAddedSchema,
@@ -3913,6 +3953,9 @@ function isResponseCreatedChunk(chunk) {
 function isResponseFunctionCallArgumentsDeltaChunk(chunk) {
   return chunk.type === "response.function_call_arguments.delta";
 }
+function isResponseImageGenerationCallPartialImageChunk(chunk) {
+  return chunk.type === "response.image_generation_call.partial_image";
+}
 function isResponseCodeInterpreterCallCodeDeltaChunk(chunk) {
   return chunk.type === "response.code_interpreter_call_code.delta";
 }
@@ -4030,6 +4073,9 @@ var openaiResponsesProviderOptionsSchema = import_v419.z.object({
   fileSearchArgsSchema,
   fileSearchOutputSchema,
   hasDefaultResponseFormat,
+  imageGeneration,
+  imageGenerationArgsSchema,
+  imageGenerationOutputSchema,
   modelMaxImagesPerCall,
   openAITranscriptionProviderOptions,
   openaiChatLanguageModelOptions,