chore,docs(provider/azure):azure responses image-generation streaming is enabled (#10391)

## Background

The image_generation tool's streaming mode is now available on Microsoft
Azure platform ,

https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/dall-e?view=foundry-classic&tabs=gpt-image-1#streaming

## Summary

After image_generation became enabled with streaming on the Azure side,
streamText worked as expected without requiring any changes to doStream
in the AI SDK.
Therefore, I concluded that we can close this issue by adding examples
and tests for Next.js, and updating the documentation accordingly.

- fix documents.
- rework azure CICD test for image_generation.
- fix example in examples/ai-core.
- add example in examples/next-openai.

## Manual Verification
- add cicd test for package @ai-sdk/azure build.
- streamText with image generation in `examples/ai-core`
  `pnpm tsx src/stream-text/azure-image-generation-tool.ts`
- next.js useChat client test.
  `examples/next-openai/app/test-azure-image-generation/page.tsx`
  `http://localhost:3000/test-azure-image-generation`
<img width="666" height="972" alt="image"
src="https://github.com/user-attachments/assets/4bd1b649-d48e-4b8d-8ccf-d28000ca2280"
/>

## Related Issues

Fixes #9064

---------

Co-authored-by: tsuzaki430 <tsuzaki430@users.noreply.github.com>
Co-authored-by: Gregor Martynus <39992+gr2m@users.noreply.github.com>

Author: tsuzaki430

content/providers/01-ai-sdk-providers/04-azure.mdx

@@ -421,18 +421,9 @@ const result = await generateText({
 
 #### Image Generation Tool
 
-<Note type="warning">
-  Azure OpenAI Responses API
-  [image_generation](https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/responses?tabs=python-secure#image-generation-preview)
-  is now Preview release(Not GA release).Image tool does not currently support
-  streaming mode. You can not use the image tool with `streamText` currently.
-</Note>
-
 Azure OpenAI's Responses API supports multi-modal image generation as a provider-defined tool.
 Availability is restricted to specific models (for example, `gpt-5` variants).
 
-You can use the image tool with `generateText`.
-
 ```ts
 import { createAzure } from '@ai-sdk/azure';
 import { generateText } from 'ai';
@@ -459,6 +450,17 @@ for (const toolResult of result.staticToolResults) {
 }
 ```
 
+<Note>
+  The tool must be named `image_generation` when using Azure OpenAI's image
+  generation functionality. This name is required by Azure OpenAI's API
+  specification and cannot be customized.
+</Note>
+
+<Note>
+  The 'image_generation' tool is only supported with the default responses API,
+  and is not supported when using 'azure.chat' or 'azure.completion'
+</Note>
+
 <Note>
   To use image_generation, you must first create an image generation model. You
   must add a deployment specification to the header

examples/ai-core/src/stream-text/azure-image-generation-tool.ts

@@ -4,27 +4,6 @@ import { presentImages } from '../lib/present-image';
 import { run } from '../lib/run';
 import { convertBase64ToUint8Array } from '../lib/convert-base64';
 
-/**
- *
- * *** NOTICE ***
- * The image_generation function is currently preview(Not GA).
- * Unfortunately ,This example code does not work, now.
- * Because image_generation tool is not supported stream mode on Azure OpenAI, yet.
- * So it doesn't work on streamText function.
- *
- * This example finish error with this message.
- * "ImageGen as a tool is not supported in streaming mode."
- *
- *
- * ` The Responses API image generation tool does not currently support streaming mode. `
- * link:
- * https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/responses?tabs=python-secure#image-generation-preview
- *
- *
- * When updated on Azure , it will work on streamText function in the future.
- * And then this example code will be fixed.
- */
-
 run(async () => {
   const azure = createAzure({
     headers: {

examples/next-openai/agent/azure-image-generation-agent.ts

@@ -0,0 +1,24 @@
+import { createAzure, azure } from '@ai-sdk/azure';
+import { InferAgentUIMessage, ToolLoopAgent } from 'ai';
+
+export const azureImageGenerationAgent = new ToolLoopAgent({
+  model: createAzure({
+    headers: {
+      'x-ms-oai-image-generation-deployment': 'gpt-image-1', // use your own image model deployment
+    },
+  })('gpt-4.1-mini'),
+  tools: {
+    image_generation: azure.tools.imageGeneration({
+      partialImages: 3,
+      quality: 'low',
+      size: '1024x1024',
+    }),
+  },
+  onStepFinish: ({ request }) => {
+    console.log(JSON.stringify(request.body, null, 2));
+  },
+});
+
+export type AzureImageGenerationMessage = InferAgentUIMessage<
+  typeof azureImageGenerationAgent
+>;

examples/next-openai/app/api/chat-azure-image-generation/route.ts

@@ -0,0 +1,11 @@
+import { createAgentUIStreamResponse } from 'ai';
+import { azureImageGenerationAgent } from '@/agent/azure-image-generation-agent';
+
+export async function POST(req: Request) {
+  const body = await req.json();
+
+  return createAgentUIStreamResponse({
+    agent: azureImageGenerationAgent,
+    uiMessages: body.messages,
+  });
+}

examples/next-openai/app/test-azure-image-generation/page.tsx

@@ -0,0 +1,40 @@
+'use client';
+
+import { AzureImageGenerationMessage } from '@/agent/azure-image-generation-agent';
+import ChatInput from '@/components/chat-input';
+import ImageGenerationView from '@/components/tool/openai-image-generation-view';
+import { useChat } from '@ai-sdk/react';
+import { DefaultChatTransport } from 'ai';
+
+export default function TestOpenAIImageGeneration() {
+  const { status, sendMessage, messages } =
+    useChat<AzureImageGenerationMessage>({
+      transport: new DefaultChatTransport({
+        api: '/api/chat-azure-image-generation',
+      }),
+    });
+
+  return (
+    <div className="flex flex-col py-24 mx-auto w-full max-w-md stretch">
+      <h1 className="mb-4 text-xl font-bold">
+        Azure OpenAI Image Generation Test
+      </h1>
+
+      {messages.map(message => (
+        <div key={message.id} className="whitespace-pre-wrap">
+          {message.role === 'user' ? 'User: ' : 'AI: '}
+          {message.parts.map((part, index) => {
+            switch (part.type) {
+              case 'text':
+                return <div key={index}>{part.text}</div>;
+              case 'tool-image_generation':
+                return <ImageGenerationView key={index} invocation={part} />;
+            }
+          })}
+        </div>
+      ))}
+
+      <ChatInput status={status} onSubmit={text => sendMessage({ text })} />
+    </div>
+  );
+}

packages/azure/src/__fixtures__/azure-image-generation-tool.1.chunks.txt

@@ -1252,7 +1252,7 @@ describe('responses', () => {
     let result: LanguageModelV3GenerateResult;
 
     beforeEach(async () => {
-      prepareJsonFixtureResponse('openai-image-generation-tool.1');
+      prepareJsonFixtureResponse('azure-image-generation-tool.1');
 
       result = await createModel('test-deployment').doGenerate({
         prompt: TEST_PROMPT,
@@ -1764,4 +1764,24 @@ describe('responses', () => {
       ).toMatchSnapshot();
     });
   });
+  describe('image generation tool', () => {
+    it('should stream image generation tool results include', async () => {
+      prepareChunksFixtureResponse('azure-image-generation-tool.1');
+      const result = await createModel('test-deployment').doStream({
+        prompt: TEST_PROMPT,
+        tools: [
+          {
+            type: 'provider',
+            id: 'openai.image_generation',
+            name: 'image_generation',
+            args: {},
+          },
+        ],
+      });
+
+      expect(
+        await convertReadableStreamToArray(result.stream),
+      ).toMatchSnapshot();
+    });
+  });
 });