@ai-sdk/openai 2.0.41 → 2.0.42

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @ai-sdk/openai
 
+## 2.0.42
+
+### Patch Changes
+
+- 2a5edd3: enables image_generation capabilities in the Azure provider through the Responses API.
+
 ## 2.0.41
 
 ### Patch Changes

package/dist/index.js

@@ -4074,7 +4074,7 @@ var openaiTranscriptionResponseSchema = import_v419.z.object({
 });
 
 // src/version.ts
-var VERSION = true ? "2.0.41" : "0.0.0-test";
+var VERSION = true ? "2.0.42" : "0.0.0-test";
 
 // src/openai-provider.ts
 function createOpenAI(options = {}) {

package/dist/index.mjs

@@ -4110,7 +4110,7 @@ var openaiTranscriptionResponseSchema = z19.object({
 });
 
 // src/version.ts
-var VERSION = true ? "2.0.41" : "0.0.0-test";
+var VERSION = true ? "2.0.42" : "0.0.0-test";
 
 // src/openai-provider.ts
 function createOpenAI(options = {}) {

package/dist/internal/index.d.mts

@@ -458,4 +458,103 @@ 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.$strip>>;
+    model: z.ZodOptional<z.ZodString>;
+    moderation: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+    }>>;
+    outputCompression: z.ZodOptional<z.ZodNumber>;
+    outputFormat: z.ZodOptional<z.ZodEnum<{
+        png: "png";
+        jpeg: "jpeg";
+        webp: "webp";
+    }>>;
+    quality: z.ZodOptional<z.ZodEnum<{
+        low: "low";
+        medium: "medium";
+        high: "high";
+        auto: "auto";
+    }>>;
+    size: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+        "1024x1024": "1024x1024";
+        "1024x1536": "1024x1536";
+        "1536x1024": "1536x1024";
+    }>>;
+}, z.core.$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';
+    /**
+     * 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

@@ -458,4 +458,103 @@ 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.$strip>>;
+    model: z.ZodOptional<z.ZodString>;
+    moderation: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+    }>>;
+    outputCompression: z.ZodOptional<z.ZodNumber>;
+    outputFormat: z.ZodOptional<z.ZodEnum<{
+        png: "png";
+        jpeg: "jpeg";
+        webp: "webp";
+    }>>;
+    quality: z.ZodOptional<z.ZodEnum<{
+        low: "low";
+        medium: "medium";
+        high: "high";
+        auto: "auto";
+    }>>;
+    size: z.ZodOptional<z.ZodEnum<{
+        auto: "auto";
+        "1024x1024": "1024x1024";
+        "1024x1536": "1024x1536";
+        "1536x1024": "1536x1024";
+    }>>;
+}, z.core.$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';
+    /**
+     * 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,
@@ -2518,6 +2521,9 @@ 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({
@@ -4030,6 +4036,9 @@ var openaiResponsesProviderOptionsSchema = import_v419.z.object({
   fileSearchArgsSchema,
   fileSearchOutputSchema,
   hasDefaultResponseFormat,
+  imageGeneration,
+  imageGenerationArgsSchema,
+  imageGenerationOutputSchema,
   modelMaxImagesPerCall,
   openAITranscriptionProviderOptions,
   openaiChatLanguageModelOptions,