> Discover all available pages from the documentation index: https://mastra.zisheng.pro/zh-HK/llms.txt

# toAISdkStream()

將 Mastra 串流（Agent、網絡或 Workflow）轉換成 AI SDK 兼容串流。當你需要手動轉換 Mastra 串流，以配合 AI SDK 的 `createUIMessageStream()` 及 `createUIMessageStreamResponse()` 使用時，請使用此函數。

在 Mastra 所提供的 [`chatRoute()`](https://mastra.zisheng.pro/zh-HK/reference/ai-sdk/chat-route) 或 [`workflowRoute()`](https://mastra.zisheng.pro/zh-HK/reference/ai-sdk/workflow-route) 等路由輔助函數以外建立自訂串流端點時，此函數尤其有用。

`toAISdkStream()` 保留現有的 AI SDK v5／預設行為。如果你的應用程式以 AI SDK v6 型別為準，請在選項物件中傳入 `version: 'v6'`。

## UI 串流中的結構化輸出

當來源 Agent 串流包含最終結構化輸出物件時，`toAISdkStream()` 會將其作為自訂 AI SDK UI 資料部分輸出：

```json
{
  "type": "data-structured-output",
  "data": {
    "object": {}
  }
}
```

`object` 欄位包含完整的結構化輸出值。這會將 Mastra 的最終結構化輸出區塊對應至 AI SDK UI 串流。系統不會輸出部分結構化輸出區塊。

## 使用範例

Next.js App Router 範例：

```typescript
import { mastra } from '../../mastra'
import { createUIMessageStream, createUIMessageStreamResponse } from 'ai'
import { toAISdkStream } from '@mastra/ai-sdk'

export async function POST(req: Request) {
  const { messages } = await req.json()
  const myAgent = mastra.getAgent('weatherAgent')
  const stream = await myAgent.stream(messages)

  const uiMessageStream = createUIMessageStream({
    originalMessages: messages,
    execute: async ({ writer }) => {
      for await (const part of toAISdkStream(stream, { from: 'agent' })) {
        await writer.write(part)
      }
    },
  })

  return createUIMessageStreamResponse({
    stream: uiMessageStream,
  })
}
```

> **提示:** 在 `createUIMessageStream()` 中將 `messages` 傳給 `originalMessages`，以免 UI 出現重複的助手訊息。詳情請參閱[疑難排解：重複的助手訊息](https://ai-sdk.dev/docs/troubleshooting/repeated-assistant-messages)。

## 參數

第一個參數是要轉換的 Mastra 串流，可以是以下其中一種：

- `MastraModelOutput` - 來自 `agent.stream()` 的 Agent 串流
- `MastraAgentNetworkStream` - 來自 `agent.network()` 的網絡串流
- `MastraWorkflowStream` 或 `WorkflowRunOutput` - Workflow 串流

第二個參數是選項物件：

**version** (`'v5' | 'v6'`): 選擇要輸出的 AI SDK 串流合約。省略此項或傳入 'v5'，即可使用現有的預設行為。當你的應用程式以 AI SDK v6 回應輔助函數的型別為準時，請傳入 'v6'。 (Default: `'v5'`)

**from** (`'agent' | 'network' | 'workflow'`): 正在轉換的 Mastra 串流類型。 (Default: `'agent'`)

**lastMessageId** (`string`): （僅限 Agent）對話中最後一則訊息的 ID。

**sendStart** (`boolean`): （僅限 Agent）是否在串流中傳送開始事件。 (Default: `true`)

**sendFinish** (`boolean`): （僅限 Agent）是否在串流中傳送完成事件。 (Default: `true`)

**sendReasoning** (`boolean`): （僅限 Agent）是否在串流中包含 reasoning-delta 區塊。設為 true，可串流支援延伸思考模型的推理內容。 (Default: `false`)

**sendSources** (`boolean`): （僅限 Agent）是否在輸出中包含來源引文。 (Default: `false`)

**includeTextStreamParts** (`boolean`): （僅限 Workflow）是否在輸出中包含文字串流部分。 (Default: `true`)

**messageMetadata** (`(options: { part: UIMessageStreamPart }) => Record<string, unknown> | undefined`): （僅限 Agent）接收目前串流部分，並傳回要附加至開始及完成區塊的中繼資料之函數。

**onError** (`(error: unknown) => string`): （僅限 Agent）用於處理串流轉換期間錯誤的函數。此函數會接收錯誤，並應傳回其字串表示。

## 範例

### 轉換 Workflow 串流

```typescript
import { mastra } from '../../mastra'
import { createUIMessageStream, createUIMessageStreamResponse } from 'ai'
import { toAISdkStream } from '@mastra/ai-sdk'

export async function POST(req: Request) {
  const { input } = await req.json()
  const workflow = mastra.getWorkflow('myWorkflow')
  const run = workflow.createRun()
  const stream = await run.stream({ inputData: input })

  const uiMessageStream = createUIMessageStream({
    execute: async ({ writer }) => {
      for await (const part of toAISdkStream(stream, { from: 'workflow' })) {
        await writer.write(part)
      }
    },
  })

  return createUIMessageStreamResponse({
    stream: uiMessageStream,
  })
}
```

### 轉換網絡串流

```typescript
import { mastra } from '../../mastra'
import { createUIMessageStream, createUIMessageStreamResponse } from 'ai'
import { toAISdkStream } from '@mastra/ai-sdk'

export async function POST(req: Request) {
  const { messages } = await req.json()
  const routingAgent = mastra.getAgent('routingAgent')
  const stream = await routingAgent.network(messages)

  const uiMessageStream = createUIMessageStream({
    execute: async ({ writer }) => {
      for await (const part of toAISdkStream(stream, { from: 'network' })) {
        await writer.write(part)
      }
    },
  })

  return createUIMessageStreamResponse({
    stream: uiMessageStream,
  })
}
```

### 轉換已啟用推理的 Agent 串流

```typescript
import { mastra } from '../../mastra'
import { createUIMessageStream, createUIMessageStreamResponse } from 'ai'
import { toAISdkStream } from '@mastra/ai-sdk'

export async function POST(req: Request) {
  const { messages } = await req.json()
  const reasoningAgent = mastra.getAgent('reasoningAgent')
  const stream = await reasoningAgent.stream(messages, {
    providerOptions: {
      openai: { reasoningEffort: 'high' },
    },
  })

  const uiMessageStream = createUIMessageStream({
    originalMessages: messages,
    execute: async ({ writer }) => {
      for await (const part of toAISdkStream(stream, {
        from: 'agent',
        sendReasoning: true,
      })) {
        await writer.write(part)
      }
    },
  })

  return createUIMessageStreamResponse({
    stream: uiMessageStream,
  })
}
```

### 為 AI SDK v6 轉換 Agent 串流

```typescript
import { mastra } from '../../mastra'
import { createUIMessageStream, createUIMessageStreamResponse } from 'ai'
import { toAISdkStream } from '@mastra/ai-sdk'

export async function POST(req: Request) {
  const { messages } = await req.json()
  const myAgent = mastra.getAgent('weatherAgent')
  const stream = await myAgent.stream(messages)

  const uiMessageStream = createUIMessageStream({
    originalMessages: messages,
    execute: async ({ writer }) => {
      for await (const part of toAISdkStream(stream, {
        from: 'agent',
        version: 'v6',
      })) {
        await writer.write(part)
      }
    },
  })

  return createUIMessageStreamResponse({
    stream: uiMessageStream,
  })
}
```

### 使用 `messageMetadata`

```typescript
import { mastra } from '../../mastra'
import { createUIMessageStream, createUIMessageStreamResponse } from 'ai'
import { toAISdkStream } from '@mastra/ai-sdk'

export async function POST(req: Request) {
  const { messages } = await req.json()
  const myAgent = mastra.getAgent('weatherAgent')
  const stream = await myAgent.stream(messages)

  const uiMessageStream = createUIMessageStream({
    originalMessages: messages,
    execute: async ({ writer }) => {
      for await (const part of toAISdkStream(stream, {
        from: 'agent',
        messageMetadata: ({ part }) => ({
          timestamp: Date.now(),
          partType: part.type,
        }),
      })) {
        await writer.write(part)
      }
    },
  })

  return createUIMessageStreamResponse({
    stream: uiMessageStream,
  })
}
```

### 客戶端串流轉換

如果你在客戶端使用 Mastra client SDK（`@mastra/client-js`），並希望將串流轉換成 AI SDK 格式：

```typescript
import { MastraClient } from '@mastra/client-js'
import { createUIMessageStream } from 'ai'
import { toAISdkStream } from '@mastra/ai-sdk'
import type { ChunkType, MastraModelOutput } from '@mastra/core/stream'

const client = new MastraClient({
  baseUrl: 'http://localhost:4111',
})

const agent = client.getAgent('weatherAgent')
const response = await agent.stream('What is the weather in Tokyo?')

// Convert the client SDK stream to a ReadableStream<ChunkType>
const chunkStream = new ReadableStream<ChunkType>({
  async start(controller) {
    await response.processDataStream({
      onChunk: async chunk => {
        controller.enqueue(chunk)
      },
    })
    controller.close()
  },
})

// Transform to AI SDK format
const uiMessageStream = createUIMessageStream({
  execute: async ({ writer }) => {
    for await (const part of toAISdkStream(chunkStream as unknown as MastraModelOutput, {
      from: 'agent',
    })) {
      await writer.write(part)
    }
  },
})

for await (const part of uiMessageStream) {
  console.log(part)
}
```