使用 supervisor agents 建置研究協調器

在本指南中，你將建置一個研究協調器，使用 supervisor agents 協調多個專門的 Agents。協調器會將研究任務委派給研究 Agent，將寫作任務委派給寫作 Agent，再將結果整合成詳細報告。

你將設定職責明確的 subagents，並設定 supervisor Agent 來協調它們。你也會使用 delegation hooks 控制執行作業，並透過 scorers 驗證任務是否完成。

先決條件

• 已安裝 Node.js v22.13.0 或更新版本
• 具備支援的 Model Provider 所提供的 API key
• 已有 Mastra 專案（請依照安裝指南設定新專案）

建立研究 Agent

研究 Agent 專門收集任何主題的事實資訊，並以簡潔的條列摘要傳回重要事實與來源。

建立新檔案 src/mastra/agents/research-agent.ts：

src/mastra/agents/research-agent.ts

import { Agent } from '@mastra/core/agent'

export const researchAgent = new Agent({
  id: 'research-agent',
  name: 'Research Specialist',
  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.',
  instructions:
    'You are a research specialist. When given a topic, gather key facts, ' +
    'statistics, and information. Present findings as clear bullet points. ' +
    'Include sources when possible. Focus on accuracy and completeness.',
  model: 'openai/gpt-5-mini',
})

description 欄位非常重要，它能協助 supervisor 判斷何時應將任務委派給此 Agent。清楚的 descriptions 可提高委派準確度。

建立寫作 Agent

寫作 Agent 會將研究資料轉換成結構完善、段落完整且行文流暢的文章。

建立新檔案 src/mastra/agents/writing-agent.ts：

src/mastra/agents/writing-agent.ts

import { Agent } from '@mastra/core/agent'

export const writingAgent = new Agent({
  id: 'writing-agent',
  name: 'Writing Specialist',
  description:
    'Transforms research material into well-structured written content. ' +
    'Produces full paragraphs and complete articles with proper flow. ' +
    'Best used after research has been gathered.',
  instructions:
    'You are a writing specialist. Transform research and information into ' +
    'well-written articles. Use complete paragraphs, clear structure, and ' +
    'engaging language. Maintain a professional yet accessible tone. ' +
    'Ensure the content flows naturally from introduction to conclusion.',
  model: 'openai/gpt-5-mini',
})

建立 supervisor Agent

supervisor 會協調研究與寫作任務。其 instructions 定義委派策略，包括何時使用各個 subagent，以及如何整合結果。Memory 會直接設定在 Agent 上。

建立新檔案 src/mastra/agents/supervisor-agent.ts：

src/mastra/agents/supervisor-agent.ts

import { Agent } from '@mastra/core/agent'
import { Memory } from '@mastra/memory'
import { LibSQLStore } from '@mastra/libsql'
import { researchAgent } from './research-agent'
import { writingAgent } from './writing-agent'

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

Available resources:
- research-agent: Gathers factual data and sources (returns bullet points)
- writing-agent: Transforms research into well-structured articles (returns full paragraphs)

Delegation strategy:
1. For research requests: Delegate to research-agent first to gather facts
2. For writing requests: Delegate to writing-agent with any available research context
3. For comprehensive reports: Delegate to research-agent first, then writing-agent
4. Always ensure you have gathered sufficient information before producing final output

Success criteria:
- All aspects of the user's request are addressed
- Information is accurate and well-sourced
- Final output is well-formatted and complete
- If anything is missing or uncertain, continue gathering information`,
  model: 'openai/gpt-5.6-sol',
  agents: {
    researchAgent,
    writingAgent,
  },
  memory: new Memory({
    storage: new LibSQLStore({
      id: 'mastra-storage',
      url: 'file:mastra.db',
    }),
  }),
  defaultOptions: {
    maxSteps: 10,

    // Monitor progress after each iteration
    onIterationComplete: async context => {
      console.log(`\n✓ Iteration ${context.iteration} complete`)
      console.log(`  Finish reason: ${context.finishReason}`)
      console.log(`  Response length: ${context.text.length} chars\n`)

      // Continue until task is complete
      return { continue: true }
    },

    // Control delegations
    delegation: {
      onDelegationStart: async context => {
        console.log(`→ Delegating to: ${context.primitiveId}`)

        // Add context for specific agents
        if (context.primitiveId === 'research-agent') {
          return {
            proceed: true,
            modifiedPrompt: `${context.prompt}\n\nFocus on recent developments (2024-2025) and include statistics.`,
          }
        }

        return { proceed: true }
      },

      onDelegationComplete: async context => {
        console.log(`✓ Completed: ${context.primitiveId}\n`)

        // Handle errors: bail to stop execution and provide feedback
        if (context.error) {
          console.error('Delegation failed:', context.error)
          context.bail() // Stop further delegations
          return {
            feedback: `Delegation to ${context.primitiveId} failed: ${context.error}. Try a different approach.`,
          }
        }
      },

      // Only pass last 10 messages to subagents
      messageFilter: ({ messages }) => {
        return messages.slice(-10)
      },
    },
  },
})

在 src/mastra/index.ts 中向 Mastra 註冊 supervisor：

src/mastra/index.ts

import { Mastra } from '@mastra/core'
import { supervisorAgent } from './agents/supervisor-agent'

export const mastra = new Mastra({
  agents: { supervisorAgent },
})

supervisor Agent 上的 defaultOptions 會設定 delegation hooks 與 iteration monitoring：

• onDelegationStart 會修改研究 Agent 的 prompt，要求提供近期資料
• onDelegationComplete 會記錄完成狀態、在發生錯誤時停止，然後提供 feedback
• messageFilter 會將情境限制為最後 10 則訊息，以提升效率
• onIterationComplete 會在每次 iteration 後監控進度

測試基本 supervisor

建立 src/index.ts 檔案，與 supervisor 互動：

src/index.ts

import { supervisorAgent } from './mastra/agents/supervisor-agent'

async function main() {
  const topic = 'artificial intelligence in education'
  console.log(`\nTopic: ${topic}\n`)

  const stream = await supervisorAgent.stream(
    `Research ${topic} and write a comprehensive article about it`,
  )

  // Stream the response
  console.log('📝 Final Report:\n')
  for await (const chunk of stream.textStream) {
    process.stdout.write(chunk)
  }
  console.log('\n')
}

main()

supervisor 會使用 defaultOptions 中設定的 delegation hooks 與 iteration monitoring。

加入任務完成評分

任務完成 scorers 會自動驗證任務是否完成，避免 supervisor 過早結束。

在 src/mastra/scorers/task-complete-scorer.ts 中建立 scorer：

src/mastra/scorers/task-complete-scorer.ts

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

export const taskCompleteScorer = createScorer({
  id: 'task-complete',
  name: 'Task Completeness',
  description: 'Checks if the research and writing task has been fully completed',
}).generateScore(async context => {
  const text = (context.run.output || '').toString()

  // Check if response contains required elements
  const hasSubstantialContent = text.length > 500
  const hasStructure = text.includes('\n\n') // Multiple paragraphs
  const hasContext = /\d{4}/.test(text) // Contains years/dates

  // Return 1 if complete, 0 if not
  if (hasSubstantialContent && hasStructure && hasContext) {
    return 1
  }

  return 0
})

安裝 evals 套件：

npm

npm install @mastra/evals

pnpm

pnpm add @mastra/evals

Yarn

yarn add @mastra/evals

Bun

bun add @mastra/evals

更新 supervisor Agent，在 src/mastra/agents/supervisor-agent.ts 的 defaultOptions 中加入任務完成評分：

src/mastra/agents/supervisor-agent.ts

import { Agent } from '@mastra/core/agent'
import { Memory } from '@mastra/memory'
import { LibSQLStore } from '@mastra/libsql'
import { researchAgent } from './research-agent'
import { writingAgent } from './writing-agent'
import { taskCompleteScorer } from '../scorers/task-complete-scorer'

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

Available resources:
- research-agent: Gathers factual data and sources (returns bullet points)
- writing-agent: Transforms research into well-structured articles (returns full paragraphs)

Delegation strategy:
1. For research requests: Delegate to research-agent first to gather facts
2. For writing requests: Delegate to writing-agent with any available research context
3. For comprehensive reports: Delegate to research-agent first, then writing-agent
4. Always ensure you have gathered sufficient information before producing final output

Success criteria:
- All aspects of the user's request are addressed
- Information is accurate and well-sourced
- Final output is well-formatted and complete
- If anything is missing or uncertain, continue gathering information`,
  model: 'openai/gpt-5.6-sol',
  agents: {
    researchAgent,
    writingAgent,
  },
  memory: new Memory({
    storage: new LibSQLStore({
      id: 'mastra-storage',
      url: 'file:mastra.db',
    }),
  }),
  defaultOptions: {
    maxSteps: 10,

    onIterationComplete: async context => {
      console.log(`\n✓ Iteration ${context.iteration} complete`)
      console.log(`  Finish reason: ${context.finishReason}`)
      console.log(`  Response length: ${context.text.length} chars\n`)
      return { continue: true }
    },

    delegation: {
      onDelegationStart: async context => {
        console.log(`→ Delegating to: ${context.primitiveId}`)

        if (context.primitiveId === 'research-agent') {
          return {
            proceed: true,
            modifiedPrompt: `${context.prompt}\n\nFocus on recent developments (2024-2025) and include statistics.`,
          }
        }

        return { proceed: true }
      },

      onDelegationComplete: async context => {
        console.log(`✓ Completed: ${context.primitiveId}\n`)

        if (context.error) {
          console.error('Delegation failed:', context.error)
          context.bail() // Stop further delegations
          return {
            feedback: `Delegation to ${context.primitiveId} failed: ${context.error}. Try a different approach.`,
          }
        }
      },

      messageFilter: ({ messages }) => {
        return messages.slice(-10)
      },
    },

    // Validate task completion
    isTaskComplete: {
      scorers: [taskCompleteScorer],
      strategy: 'all',
      onComplete: async result => {
        console.log('\n🎯 Completion Check:')
        console.log(`  Complete: ${result.complete}`)
        console.log(`  Score: ${result.scorers[0]?.score}\n`)
      },
    },
  },
})

scorer 會檢查內容是否充實、結構是否適當，以及是否包含情境資訊。如果任務尚未完成，supervisor 會繼續 iteration。現在所有 hooks 與任務完成評分都設定在 Agent 的 defaultOptions 中，因此會自動套用至每次呼叫。

測試研究協調器

執行協調器，查看其實際運作：

npx tsx src/index.ts

你會看到 supervisor 先將任務委派給研究 Agent，再委派給寫作 Agent；log 會顯示委派流程：

Topic: artificial intelligence in education

→ Delegating to: research-agent
✓ Iteration 1 complete
  Finish reason: tool-calls
  Response length: 0 chars

✓ Completed: research-agent

→ Delegating to: writing-agent
✓ Iteration 2 complete
  Finish reason: tool-calls
  Response length: 0 chars

✓ Completed: writing-agent

🎯 Completion Check:
  Complete: true
  Score: 1

✓ Iteration 3 complete
  Finish reason: stop
  Response length: 1247 chars

📝 Final Report:

Artificial Intelligence in Education: Transforming Learning in 2024-2025

[The coordinator will produce a comprehensive article combining research findings with well-structured writing...]

由於 Agent 回應並非確定性輸出，你的結果可能不同，但委派模式會保持一致。

後續步驟

你可以透過下列方式擴充此研究協調器：

• 加入更多專門的 Agents（fact-checker、editor、citation-formatter）
• 為品質指標（readability、source quality）實作自訂 scorers
• 加入用於網頁搜尋或資料庫存取的 tools
• 為複雜的多步驟研究流程建立 Workflows
• 使用 structured output，以特定格式產生報告

深入了解：

• Supervisor Agents
• Agent.stream() 參考文件