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

# 從 `.network()` 遷移至 supervisor Agent

使用 `Agent.stream()` 及 `Agent.generate()` 的 supervisor Agent 是協調多個 Agent 的建議方式，並取代較舊的 `.network()` API。本指南會帶你完成遷移的每個步驟。

> **棄用 .network():** `.network()` 已棄用，並會在日後版本移除。在此之前，現有程式碼仍可繼續運作，但開發重點現已轉向 supervisor Agent。請盡快遷移至 supervisor Agent。

## 以 `.stream()` 或 `.generate()` 取代 `.network()`

核心變更是以 `.stream()`（串流）或 `.generate()`（非串流）取代 `.network()` 呼叫。Agent 設定維持不變，你仍會在 Agent 上定義 `agents`、`workflows`、`tools` 及 `memory`。差別在於呼叫方式及處理結果的方式。

使用 `.network()` 時，你會反覆處理 `network-execution-event-step-finish` 等自訂事件類型。使用 `.stream()` 時，則會使用標準 `textStream` 或 `fullStream` 迭代器。

**遷移前：**

```typescript
const result = await routingAgent.network('Research AI in education')

for await (const chunk of result) {
  if (chunk.type === 'network-execution-event-step-finish') {
    console.log(chunk.payload.result)
  }
}
```

**遷移後：**

```typescript
const stream = await supervisorAgent.stream('Research AI in education', {
  maxSteps: 10,
})

for await (const chunk of stream.textStream) {
  process.stdout.write(chunk)
}
```

`maxSteps` 選項限制 supervisor 可執行的迭代次數，取代 `.network()` 的隱含迭代上限。

非串流使用情境可使用 `generate()`，並傳入相同選項：

```typescript
const result = await supervisorAgent.generate('Research AI in education', {
  maxSteps: 10,
})

console.log(result.text)
```

## 撰寫清晰的 supervisor 指示

使用 `.network()` 時，routing Agent 依靠一般指示及基本元件描述，決定要呼叫甚麼。supervisor Agent 的運作方式相同，但清晰具體的指示可提高委派準確度。

supervisor 的 `instructions` 應列明可用資源及各資源的使用時機，也應說明如何協調這些資源，以及如何判斷工作已完成。

**遷移前：**

```typescript
const routingAgent = new Agent({
  id: 'routing-agent',
  instructions: 'You are a network of researchers and writers...',
  agents: { researchAgent, writingAgent },
  memory: new Memory(),
})
```

**遷移後：**

```typescript
const supervisorAgent = new Agent({
  id: 'supervisor-agent',
  instructions: `You coordinate research and writing tasks using specialized agents.

Available resources:
- researchAgent: Gathers factual data and sources (returns bullet points)
- writingAgent: Transforms research into narrative content (returns full paragraphs)

Delegation strategy:
1. For research requests: Delegate to researchAgent first
2. For writing requests: Delegate to writingAgent (provide research if available)
3. For complex requests: Delegate to researchAgent first, then writingAgent

Success criteria:
- All user questions are fully answered
- Response is well-formatted and complete
- If information is incomplete, continue iterating`,
  agents: { researchAgent, writingAgent },
  memory: new Memory(),
})
```

## 為 subagent 加入描述

每個 subagent 都應有 `description` 欄位，說明其用途及傳回格式。描述也應列明何時使用該 subagent。supervisor 會根據這些描述，決定將工作委派給哪個 Agent。

```typescript
const researchAgent = new Agent({
  id: 'research-agent',
  description: `Specializes in gathering factual information and data on any topic.
    Returns concise bullet-point summaries with key facts and sources.
    Does not write full articles or narrative content.`,
})

const writingAgent = new Agent({
  id: 'writing-agent',
  description: `Transforms research material into well-structured written content.
    Produces full paragraphs and complete articles.
    Best used after research has been gathered.`,
})
```

## 更新事件處理

如果你曾處理特定 `.network()` 事件，請改為使用標準串流區塊類型：

| `.network()` 事件                       | Supervisor Agent 區塊                    |
| ------------------------------------- | -------------------------------------- |
| `routing-agent-start`                 | `step-start`                           |
| `routing-agent-end`                   | `step-finish`                          |
| `agent-execution-start`               | `step-start`（委派時）                      |
| `agent-execution-event-text-delta`    | `text-delta`                           |
| `agent-execution-event-finish`        | `step-finish`                          |
| `network-execution-event-step-finish` | `step-finish` + `finishReason: 'stop'` |
| `network-object`                      | `object-delta`（配合 structuredOutput）    |
| `network-object-result`               | `object`（配合 structuredOutput）          |

## 加入委派 hook

supervisor Agent 讓你接入委派生命週期，以監察、修改或拒絕委派。這些 hook 可在 Agent 的 `defaultOptions` 中設定，亦可在每次呼叫時傳入。

`onDelegationStart` 會在 supervisor 委派給 subagent 前呼叫。你可以修改提示或限制 subagent 的步驟數目，hook 亦可完全拒絕委派：

```typescript
const stream = await supervisorAgent.stream('Research AI in education', {
  maxSteps: 10,
  delegation: {
    onDelegationStart: async context => {
      console.log(`Delegating to: ${context.primitiveId}`)

      if (context.primitiveId === 'research-agent') {
        return {
          proceed: true,
          modifiedPrompt: `${context.prompt}\n\nFocus on 2024-2025 data.`,
          modifiedMaxSteps: 5,
        }
      }

      if (context.iteration > 8) {
        return {
          proceed: false,
          rejectionReason: 'Max iterations reached. Synthesize current findings.',
        }
      }

      return { proceed: true }
    },
  },
})
```

`onDelegationComplete` 會在委派完成後呼叫。檢查結果，並在應停止 supervisor 迴圈時呼叫 `context.bail()`。你亦可傳回意見，儲存至 supervisor 的記憶體：

```typescript
const stream = await supervisorAgent.stream('Research AI in education', {
  maxSteps: 10,
  delegation: {
    onDelegationComplete: async context => {
      if (context.error) {
        context.bail() // Stop further delegations
        return {
          feedback: `Delegation to ${context.primitiveId} failed: ${context.error}. Try a different approach.`,
        }
      }
    },
  },
})
```

## 加入訊息篩選

根據預設設定，subagent 會從 supervisor 接收完整對話內容。使用 `messageFilter` 控制分享哪些訊息，例如移除敏感資料或限制訊息數目：

```typescript
const stream = await supervisorAgent.stream('Research AI in education', {
  maxSteps: 10,
  delegation: {
    messageFilter: ({ messages, primitiveId, prompt }) => {
      return messages
        .filter(msg => {
          const content =
            typeof msg.content === 'string' ? msg.content : JSON.stringify(msg.content)
          return !content.includes('confidential')
        })
        .slice(-10)
    },
  },
})
```

## 加入迭代監察

`onIterationComplete` 會在 supervisor 迴圈每次迭代後呼叫。你可用它記錄進度，或提供意見以引導 Agent。此 hook 亦可提早停止執行：

```typescript
const stream = await supervisorAgent.stream('Research AI in education', {
  maxSteps: 10,
  onIterationComplete: async context => {
    console.log(`Iteration ${context.iteration}/${context.maxIterations}`)

    if (!context.text.includes('recommendations')) {
      return {
        continue: true,
        feedback: 'Please include specific recommendations in your analysis.',
      }
    }

    if (context.text.length > 1000 && context.finishReason === 'stop') {
      return { continue: false }
    }

    return { continue: true }
  },
})
```

## 加入工作完成度評分

工作完成度 scorer 會自動驗證工作是否完成。如果驗證失敗，supervisor 會繼續迭代。失敗 scorer 的意見會包含在對話內容中，讓 subagent 了解遺漏了甚麼：

```typescript
import { createScorer } from '@mastra/core/evals'

const taskCompleteScorer = createScorer({
  id: 'task-complete',
  name: 'Task Completeness',
}).generateScore(async context => {
  const text = (context.run.output || '').toString()
  const hasAnalysis = text.includes('analysis')
  const hasRecommendations = text.includes('recommendation')
  return hasAnalysis && hasRecommendations ? 1 : 0
})

const stream = await supervisorAgent.stream('Research AI in education', {
  maxSteps: 10,
  isTaskComplete: {
    scorers: [taskCompleteScorer],
    strategy: 'all',
    onComplete: async result => {
      console.log('Task complete:', result.complete)
    },
  },
})
```

## 另請參閱

- [Supervisor Agent](https://mastra.zisheng.pro/zh-HK/docs/capabilities/subagents)
- [Agent 網絡](https://mastra.zisheng.pro/zh-HK/docs/agents/networks)
- [Agent.stream() 參考](https://mastra.zisheng.pro/zh-HK/reference/streaming/agents/stream)
- [Agent.generate() 參考](https://mastra.zisheng.pro/zh-HK/reference/agents/generate)
- [Agent 核准](https://mastra.zisheng.pro/zh-HK/docs/agents/agent-approval)
- [指南：研究協調器](https://mastra.zisheng.pro/zh-HK/guides/guide/research-coordinator)