使用子智能体构建个人助理 | LangChain 中文文档

概述

主管模式是一种多智能体架构，其中中央主管智能体协调专门的工人智能体。当任务需要不同类型的专业知识时，这种方法表现出色。与其构建一个跨领域管理工具选择的智能体，不如创建由理解整体工作流的主管协调的聚焦专家。

在本教程中，你将构建一个个人助理系统，通过真实的工作流演示这些优势。该系统将协调两个职责根本不同的专家：

一个处理日程安排、可用性检查和事件管理的日历智能体。
一个管理沟通、起草消息和发送通知的邮件智能体。

我们还将加入人在回路（人工介入）审查，允许用户根据需要批准、编辑和拒绝操作（例如外发邮件）。

INFO

如果你正在从 langgraph-supervisor 包迁移，请参阅从 langgraph-supervisor 迁移了解迁移前后的模式，包括中断和恢复流程。

为什么要使用主管？

多智能体架构允许你将工具分配到各个工人中，每个工人都有自己的提示词或指令。设想一个可以直接访问所有日历和邮件 API 的智能体：它必须从许多相似的工具中选择，理解每个 API 的确切格式，并同时处理多个领域。如果性能下降，将相关工具和关联提示词分成逻辑组可能会有所帮助（部分原因是为了管理迭代改进）。

概念

我们将介绍以下概念：

设置

安装

本教程需要 langchain 包：

bash

pip install langchain

bash

conda install langchain -c conda-forge

bash

npm install langchain

bash

yarn add langchain

bash

pnpm add langchain

更多详情，请参阅我们的安装指南。

LangSmith

设置 LangSmith 以检查智能体内部发生的情况。然后设置以下环境变量：

Python · ShellPython · PythonTypeScript · ShellTypeScript · TypeScript

bash

export LANGSMITH_TRACING="true"
export LANGSMITH_API_KEY="..."

python

import getpass
import os

os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass()

bash

export LANGSMITH_TRACING="true"
export LANGSMITH_API_KEY="..."

typescript

process.env.LANGSMITH_TRACING = "true";
process.env.LANGSMITH_API_KEY = "...";

组件

我们需要从 LangChain 的集成套件中选择一个对话模型：

OpenAI

    👉 Read the [OpenAI chat model integration docs](/oss/python/integrations/chat/openai)

bash

pip install -U "langchain[openai]"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["OPENAI_API_KEY"] = "sk-..."

model = init_chat_model("gpt-5.5")

python

import os
from langchain_openai import ChatOpenAI

os.environ["OPENAI_API_KEY"] = "sk-..."

model = ChatOpenAI(model="gpt-5.5")

Anthropic

    👉 Read the [Anthropic chat model integration docs](/oss/python/integrations/chat/anthropic)

bash

pip install -U "langchain[anthropic]"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["ANTHROPIC_API_KEY"] = "sk-..."

model = init_chat_model("claude-sonnet-4-6")

python

import os
from langchain_anthropic import ChatAnthropic

os.environ["ANTHROPIC_API_KEY"] = "sk-..."

model = ChatAnthropic(model="claude-sonnet-4-6")

Azure

    👉 Read the [Azure chat model integration docs](/oss/python/integrations/chat/azure_chat_openai)

bash

pip install -U "langchain[openai]"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["AZURE_OPENAI_API_KEY"] = "..."
os.environ["AZURE_OPENAI_ENDPOINT"] = "..."
os.environ["OPENAI_API_VERSION"] = "2025-03-01-preview"

model = init_chat_model(
    "azure_openai:gpt-5.5",
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
)

python

import os
from langchain_openai import AzureChatOpenAI

os.environ["AZURE_OPENAI_API_KEY"] = "..."
os.environ["AZURE_OPENAI_ENDPOINT"] = "..."
os.environ["OPENAI_API_VERSION"] = "2025-03-01-preview"

model = AzureChatOpenAI(
    model="gpt-5.5",
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"]
)

Google Gemini

    👉 Read the [Google GenAI chat model integration docs](/oss/python/integrations/chat/google_generative_ai)

bash

pip install -U "langchain[google-genai]"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["GOOGLE_API_KEY"] = "..."

model = init_chat_model("google_genai:gemini-2.5-flash-lite")

python

import os
from langchain_google_genai import ChatGoogleGenerativeAI

os.environ["GOOGLE_API_KEY"] = "..."

model = ChatGoogleGenerativeAI(model="gemini-2.5-flash-lite")

AWS Bedrock

    👉 Read the [AWS Bedrock chat model integration docs](/oss/python/integrations/chat/bedrock)

bash

pip install -U "langchain[aws]"

Python · init_chat_modelPython · Model Class

python

from langchain.chat_models import init_chat_model

# Follow the steps here to configure your credentials:
# https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

model = init_chat_model(
    "us.anthropic.claude-sonnet-4-6",
    model_provider="bedrock_converse",
)

python

from langchain_aws import ChatBedrock

model = ChatBedrock(model="us.anthropic.claude-sonnet-4-6")

HuggingFace

    👉 Read the [HuggingFace chat model integration docs](/oss/python/integrations/chat/huggingface)

bash

pip install -U "langchain[huggingface]"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["HUGGINGFACEHUB_API_TOKEN"] = "hf_..."

model = init_chat_model(
    "microsoft/Phi-3-mini-4k-instruct",
    model_provider="huggingface",
    temperature=0.7,
    max_tokens=1024,
)

python

import os
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint

os.environ["HUGGINGFACEHUB_API_TOKEN"] = "hf_..."

llm = HuggingFaceEndpoint(
    repo_id="microsoft/Phi-3-mini-4k-instruct",
    temperature=0.7,
    max_length=1024,
)
model = ChatHuggingFace(llm=llm)

OpenRouter

    👉 Read the [OpenRouter chat model integration docs](/oss/python/integrations/chat/openrouter)

bash

pip install -U "langchain-openrouter"

Python · init_chat_modelPython · Model Class

python

import os
from langchain.chat_models import init_chat_model

os.environ["OPENROUTER_API_KEY"] = "sk-..."

model = init_chat_model(
    "auto",
    model_provider="openrouter",
)

python

import os
from langchain_openrouter import ChatOpenRouter

os.environ["OPENROUTER_API_KEY"] = "sk-..."

model = ChatOpenRouter(model="auto")

OpenAI

    👉 Read the [OpenAI chat model integration docs](/oss/javascript/integrations/chat/openai)

TypeScript · npmTypeScript · pnpmTypeScript · yarnTypeScript · bun

bash

npm install @langchain/openai

bash

pnpm install @langchain/openai

bash

yarn add @langchain/openai

bash

bun add @langchain/openai

TypeScript · initChatModelTypeScript · Model Class

typescript

import { initChatModel } from "langchain";

process.env.OPENAI_API_KEY = "your-api-key";

const model = await initChatModel("gpt-5.5");

typescript

import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({
  model: "gpt-5.5",
  apiKey: "your-api-key"
});

Anthropic

    👉 Read the [Anthropic chat model integration docs](/oss/javascript/integrations/chat/anthropic)

TypeScript · npmTypeScript · pnpmTypeScript · yarnTypeScript · pnpm

bash

npm install @langchain/anthropic

bash

pnpm install @langchain/anthropic

bash

yarn add @langchain/anthropic

bash

pnpm add @langchain/anthropic

TypeScript · initChatModelTypeScript · Model Class

typescript

import { initChatModel } from "langchain";

process.env.ANTHROPIC_API_KEY = "your-api-key";

const model = await initChatModel("claude-sonnet-4-6");

typescript

import { ChatAnthropic } from "@langchain/anthropic";

const model = new ChatAnthropic({
  model: "claude-sonnet-4-6",
  apiKey: "your-api-key"
});

Azure

    👉 Read the [Azure chat model integration docs](/oss/javascript/integrations/chat/azure)

TypeScript · npmTypeScript · pnpmTypeScript · yarnTypeScript · bun

bash

npm install @langchain/azure

bash

pnpm install @langchain/azure

bash

yarn add @langchain/azure

bash

bun add @langchain/azure

TypeScript · initChatModelTypeScript · Model Class

typescript

import { initChatModel } from "langchain";

process.env.AZURE_OPENAI_API_KEY = "your-api-key";
process.env.AZURE_OPENAI_ENDPOINT = "your-endpoint";
process.env.OPENAI_API_VERSION = "your-api-version";

const model = await initChatModel("azure_openai:gpt-5.5");

typescript

import { AzureChatOpenAI } from "@langchain/openai";

const model = new AzureChatOpenAI({
  model: "gpt-5.5",
  azureOpenAIApiKey: "your-api-key",
  azureOpenAIApiEndpoint: "your-endpoint",
  azureOpenAIApiVersion: "your-api-version"
});

Google Gemini

    👉 Read the [Google GenAI chat model integration docs](/oss/javascript/integrations/chat/google_generative_ai)

TypeScript · npmTypeScript · pnpmTypeScript · yarnTypeScript · bun

bash

npm install @langchain/google-genai

bash

pnpm install @langchain/google-genai

bash

yarn add @langchain/google-genai

bash

bun add @langchain/google-genai

TypeScript · initChatModelTypeScript · Model Class

typescript

import { initChatModel } from "langchain";

process.env.GOOGLE_API_KEY = "your-api-key";

const model = await initChatModel("google-genai:gemini-2.5-flash-lite");

typescript

import { ChatGoogleGenerativeAI } from "@langchain/google-genai";

const model = new ChatGoogleGenerativeAI({
  model: "gemini-2.5-flash-lite",
  apiKey: "your-api-key"
});

Bedrock Converse

    👉 Read the [AWS Bedrock chat model integration docs](/oss/javascript/integrations/chat/bedrock_converse)

TypeScript · npmTypeScript · pnpmTypeScript · yarnTypeScript · bun

bash

npm install @langchain/aws

bash

pnpm install @langchain/aws

bash

yarn add @langchain/aws

bash

bun add @langchain/aws

TypeScript · initChatModelTypeScript · Model Class

typescript

import { initChatModel } from "langchain";

// Follow the steps here to configure your credentials:
// https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

const model = await initChatModel("bedrock:gpt-5.5");

typescript

import { ChatBedrockConverse } from "@langchain/aws";

// Follow the steps here to configure your credentials:
// https://docs.aws.amazon.com/bedrock/latest/userguide/getting-started.html

const model = new ChatBedrockConverse({
  model: "gpt-5.5",
  region: "us-east-2"
});

1. 定义工具

首先定义需要结构化输入的工具。在真实应用中，这些工具会调用实际的 API（Google Calendar、SendGrid 等）。在本教程中，你将使用桩来演示该模式。

python

from langchain.tools import tool

@tool
def create_calendar_event(
    title: str,
    start_time: str,       # ISO 格式："2024-01-15T14:00:00"
    end_time: str,         # ISO 格式："2024-01-15T15:00:00"
    attendees: list[str],  # 电子邮件地址
    location: str = ""
) -> str:
    """Create a calendar event. Requires exact ISO datetime format."""
    # 桩（Stub）：在实际应用中，这会调用 Google Calendar API、Outlook API 等。
    return f"Event created: {title} from {start_time} to {end_time} with {len(attendees)} attendees"

@tool
def send_email(
    to: list[str],  # 电子邮件地址
    subject: str,
    body: str,
    cc: list[str] = []
) -> str:
    """Send an email via email API. Requires properly formatted addresses."""
    # 桩（Stub）：在实际应用中，这会调用 SendGrid、Gmail API 等。
    return f"Email sent to {', '.join(to)} - Subject: {subject}"

@tool
def get_available_time_slots(
    attendees: list[str],
    date: str,  # ISO 格式："2024-01-15"
    duration_minutes: int
) -> list[str]:
    """Check calendar availability for given attendees on a specific date."""
    # 桩（Stub）：在实际应用中，这会查询日历 API
    return ["09:00", "14:00", "16:00"]

typescript

import { tool } from "langchain";
import { z } from "zod";

const createCalendarEvent = tool(
  async ({ title, startTime, endTime, attendees, location }) => {
    // 桩（Stub）：在实际应用中，这会调用 Google Calendar API、Outlook API 等。
    return `Event created: ${title} from ${startTime} to ${endTime} with ${attendees.length} attendees`;
  },
  {
    name: "create_calendar_event",
    description: "Create a calendar event. Requires exact ISO datetime format.",
    schema: z.object({
      title: z.string(),
      startTime: z.string().describe("ISO format: '2024-01-15T14:00:00'"),
      endTime: z.string().describe("ISO format: '2024-01-15T15:00:00'"),
      attendees: z.array(z.string()).describe("email addresses"),
      location: z.string().optional(),
    }),
  }
);

const sendEmail = tool(
  async ({ to, subject, body, cc }) => {
    // 桩（Stub）：在实际应用中，这会调用 SendGrid、Gmail API 等。
    return `Email sent to ${to.join(', ')} - Subject: ${subject}`;
  },
  {
    name: "send_email",
    description: "Send an email via email API. Requires properly formatted addresses.",
    schema: z.object({
      to: z.array(z.string()).describe("email addresses"),
      subject: z.string(),
      body: z.string(),
      cc: z.array(z.string()).optional(),
    }),
  }
);

const getAvailableTimeSlots = tool(
  async ({ attendees, date, durationMinutes }) => {
    // 桩（Stub）：在实际应用中，这会查询日历 API
    return ["09:00", "14:00", "16:00"];
  },
  {
    name: "get_available_time_slots",
    description: "Check calendar availability for given attendees on a specific date.",
    schema: z.object({
      attendees: z.array(z.string()),
      date: z.string().describe("ISO format: '2024-01-15'"),
      durationMinutes: z.number(),
    }),
  }
);

2. 创建专门的子智能体

接下来，我们将创建处理每个领域的专门子智能体。

创建日历智能体

日历智能体理解自然语言日程安排请求，并将其转换为精确的 API 调用。它处理日期解析、可用性检查和事件创建。

python

from datetime import date

from langchain.agents import create_agent

CALENDAR_AGENT_PROMPT = (
    f"Today's date is {date.today().isoformat()}. "
    "You are a calendar scheduling assistant. "
    "Parse natural language scheduling requests (e.g., 'next Tuesday at 2pm') "
    "into proper ISO datetime formats. "
    "Use get_available_time_slots to check availability when needed. "
    "If there is no suitable time slot, stop and confirm unavailability in your response. "
    "Use create_calendar_event to schedule events. "
    "Always confirm what was scheduled in your final response."
)

calendar_agent = create_agent(
    model,
    tools=[create_calendar_event, get_available_time_slots],
    system_prompt=CALENDAR_AGENT_PROMPT,
)

typescript

import { createAgent } from "langchain";

const now = new Date();
const today = [
  now.getFullYear(),
  String(now.getMonth() + 1).padStart(2, "0"),
  String(now.getDate()).padStart(2, "0"),
].join("-");

const CALENDAR_AGENT_PROMPT = `
Today's date is ${today}.
You are a calendar scheduling assistant.
Parse natural language scheduling requests (e.g., 'next Tuesday at 2pm')
into proper ISO datetime formats.
Use get_available_time_slots to check availability when needed.
If there is no suitable time slot, stop and confirm unavailability in your response.
Use create_calendar_event to schedule events.
Always confirm what was scheduled in your final response.
`.trim();

const calendarAgent = createAgent({
  model: llm,
  tools: [createCalendarEvent, getAvailableTimeSlots],
  systemPrompt: CALENDAR_AGENT_PROMPT,
});

测试日历智能体，看看它如何处理自然语言日程安排：

python

query = "Schedule a team meeting next Tuesday at 2pm for 1 hour"

stream = calendar_agent.stream_events(
    {"messages": [{"role": "user", "content": query}]},
    version="v3",
)
for kind, item in stream.interleave("messages", "tool_calls"):
    if kind == "messages":
        for token in item.text:
            print(token, end="", flush=True)
    elif kind == "tool_calls":
        print(f"\nTool call: {item.tool_name}({item.input})")
        print(f"Tool result: {item.output}")

typescript

const query = "Schedule a team meeting next Tuesday at 2pm for 1 hour";

const stream = await calendarAgent.streamEvents(
  { messages: [{ role: "user", content: query }] },
  { version: "v3" }
);

await Promise.all([
  (async () => {
    for await (const message of stream.messages) {
      for await (const token of message.text) {
        process.stdout.write(token);
      }
    }
  })(),
  (async () => {
    for await (const call of stream.toolCalls) {
      console.log(`\nTool call: ${call.name}(${JSON.stringify(call.input)})`);
      console.log(`Tool result: ${await call.output}`);
    }
  })(),
]);

================================== Ai Message ==================================
Tool Calls:
  get_available_time_slots (call_EIeoeIi1hE2VmwZSfHStGmXp)
 Call ID: call_EIeoeIi1hE2VmwZSfHStGmXp
  Args:
    attendees: []
    date: 2024-06-18
    duration_minutes: 60
================================= Tool Message =================================
Name: get_available_time_slots

["09:00", "14:00", "16:00"]
================================== Ai Message ==================================
Tool Calls:
  create_calendar_event (call_zgx3iJA66Ut0W8S3NpT93kEB)
 Call ID: call_zgx3iJA66Ut0W8S3NpT93kEB
  Args:
    title: Team Meeting
    start_time: 2024-06-18T14:00:00
    end_time: 2024-06-18T15:00:00
    attendees: []
================================= Tool Message =================================
Name: create_calendar_event

Event created: Team Meeting from 2024-06-18T14:00:00 to 2024-06-18T15:00:00 with 0 attendees
================================== Ai Message ==================================

The team meeting has been scheduled for next Tuesday, June 18th, at 2:00 PM and will last for 1 hour. If you need to add attendees or a location, please let me know!

智能体将"下周二下午 2 点"解析为 ISO 格式（"2024-01-16T14:00:00"），计算结束时间，调用 create_calendar_event，并返回自然语言确认。

创建邮件智能体

邮件智能体处理消息的撰写和发送。它专注于提取收件人信息、撰写适当的主题行和正文，以及管理邮件通信。

python

EMAIL_AGENT_PROMPT = (
    "You are an email assistant. "
    "Compose professional emails based on natural language requests. "
    "Extract recipient information and craft appropriate subject lines and body text. "
    "Use send_email to send the message. "
    "Always confirm what was sent in your final response."
)

email_agent = create_agent(
    model,
    tools=[send_email],
    system_prompt=EMAIL_AGENT_PROMPT,
)

测试邮件智能体，看看它如何处理自然语言请求：

python

query = "Send the design team a reminder about reviewing the new mockups"

stream = email_agent.stream_events(
    {"messages": [{"role": "user", "content": query}]},
    version="v3",
)
for kind, item in stream.interleave("messages", "tool_calls"):
    if kind == "messages":
        for token in item.text:
            print(token, end="", flush=True)
    elif kind == "tool_calls":
        print(f"\nTool call: {item.tool_name}({item.input})")
        print(f"Tool result: {item.output}")

typescript

const EMAIL_AGENT_PROMPT = `
You are an email assistant.
Compose professional emails based on natural language requests.
Extract recipient information and craft appropriate subject lines and body text.
Use send_email to send the message.
Always confirm what was sent in your final response.
`.trim();

const emailAgent = createAgent({
  model: llm,
  tools: [sendEmail],
  systemPrompt: EMAIL_AGENT_PROMPT,
});

测试邮件智能体，看看它如何处理自然语言请求：

typescript

const query = "Send the design team a reminder about reviewing the new mockups";

const stream = await emailAgent.streamEvents(
  { messages: [{ role: "user", content: query }] },
  { version: "v3" }
);

await Promise.all([
  (async () => {
    for await (const message of stream.messages) {
      for await (const token of message.text) {
        process.stdout.write(token);
      }
    }
  })(),
  (async () => {
    for await (const call of stream.toolCalls) {
      console.log(`\nTool call: ${call.name}(${JSON.stringify(call.input)})`);
      console.log(`Tool result: ${await call.output}`);
    }
  })(),
]);

================================== Ai Message ==================================
Tool Calls:
  send_email (call_OMl51FziTVY6CRZvzYfjYOZr)
 Call ID: call_OMl51FziTVY6CRZvzYfjYOZr
  Args:
    to: ['design-team@example.com']
    subject: Reminder: Please Review the New Mockups
    body: Hi Design Team,

This is a friendly reminder to review the new mockups at your earliest convenience. Your feedback is important to ensure that we stay on track with our project timeline.

Please let me know if you have any questions or need additional information.

Thank you!

Best regards,
================================= Tool Message =================================
Name: send_email

Email sent to design-team@example.com - Subject: Reminder: Please Review the New Mockups
================================== Ai Message ==================================

I've sent a reminder to the design team asking them to review the new mockups. If you need any further communication on this topic, just let me know!

智能体从非正式请求中推断出收件人，撰写专业的主题行和正文，调用 send_email，并返回确认。每个子智能体都有狭窄的焦点，配备领域专用工具和提示词，使其能够在特定任务上表现出色。

3. 将子智能体包装为工具

现在将每个子智能体包装为主管可以调用的工具。这是创建分层系统的关键架构步骤。主管将看到"schedule_event"这样的高级工具，而不是"create_calendar_event"这样的低级工具。

python

@tool
def schedule_event(request: str) -> str:
    """Schedule calendar events using natural language.

    Use this when the user wants to create, modify, or check calendar appointments.
    Handles date/time parsing, availability checking, and event creation.

    Input: Natural language scheduling request (e.g., 'meeting with design team
    next Tuesday at 2pm')
    """
    result = calendar_agent.invoke({
        "messages": [{"role": "user", "content": request}]
    })
    return result["messages"][-1].text

@tool
def manage_email(request: str) -> str:
    """Send emails using natural language.

    Use this when the user wants to send notifications, reminders, or any email
    communication. Handles recipient extraction, subject generation, and email
    composition.

    Input: Natural language email request (e.g., 'send them a reminder about
    the meeting')
    """
    result = email_agent.invoke({
        "messages": [{"role": "user", "content": request}]
    })
    return result["messages"][-1].text

typescript

const scheduleEvent = tool(
  async ({ request }) => {
    const result = await calendarAgent.invoke({
      messages: [{ role: "user", content: request }]
    });
    const lastMessage = result.messages[result.messages.length - 1];
    return lastMessage.text;
  },
  {
    name: "schedule_event",
    description: `
Schedule calendar events using natural language.

Use this when the user wants to create, modify, or check calendar appointments.
Handles date/time parsing, availability checking, and event creation.

Input: Natural language scheduling request (e.g., 'meeting with design team next Tuesday at 2pm')
    `.trim(),
    schema: z.object({
      request: z.string().describe("Natural language scheduling request"),
    }),
  }
);

const manageEmail = tool(
  async ({ request }) => {
    const result = await emailAgent.invoke({
      messages: [{ role: "user", content: request }]
    });
    const lastMessage = result.messages[result.messages.length - 1];
    return lastMessage.text;
  },
  {
    name: "manage_email",
    description: `
Send emails using natural language.

Use this when the user wants to send notifications, reminders, or any email communication.
Handles recipient extraction, subject generation, and email composition.

Input: Natural language email request (e.g., 'send them a reminder about the meeting')
    `.trim(),
    schema: z.object({
      request: z.string().describe("Natural language email request"),
    }),
  }
);

工具描述帮助主管决定何时使用每个工具，因此要使其清晰具体。我们只返回子智能体的最终响应，因为主管不需要看到中间的推理或工具调用。

4. 创建主管智能体

现在创建协调子智能体的主管。主管只能看到高级工具，并在领域级别做出路由决策，而不是在单个 API 级别。

python

SUPERVISOR_PROMPT = (
    "You are a helpful personal assistant. "
    "You can schedule calendar events and send emails. "
    "Break down user requests into appropriate tool calls and coordinate the results. "
    "When a request involves multiple actions, use multiple tools in sequence or in parallel as appropriate."
)

supervisor_agent = create_agent(
    model,
    tools=[schedule_event, manage_email],
    system_prompt=SUPERVISOR_PROMPT,
)

typescript

const SUPERVISOR_PROMPT = `
You are a helpful personal assistant.
You can schedule calendar events and send emails.
Break down user requests into appropriate tool calls and coordinate the results.
When a request involves multiple actions, use multiple tools in sequence or in parallel as appropriate.
`.trim();

const supervisorAgent = createAgent({
  model: llm,
  tools: [scheduleEvent, manageEmail],
  systemPrompt: SUPERVISOR_PROMPT,
});

5. 使用主管

现在使用需要跨多个领域协调的复杂请求来测试你的完整系统：

示例 1：简单的单领域请求

python

query = "Schedule a team standup for tomorrow at 9am"

stream = supervisor_agent.stream_events(
    {"messages": [{"role": "user", "content": query}]},
    version="v3",
)
for kind, item in stream.interleave("messages", "tool_calls"):
    if kind == "messages":
        for token in item.text:
            print(token, end="", flush=True)
    elif kind == "tool_calls":
        print(f"\nTool call: {item.tool_name}({item.input})")
        print(f"Tool result: {item.output}")

typescript

const query = "Schedule a team standup for tomorrow at 9am";

const stream = await supervisorAgent.streamEvents(
  { messages: [{ role: "user", content: query }] },
  { version: "v3" }
);

await Promise.all([
  (async () => {
    for await (const message of stream.messages) {
      for await (const token of message.text) {
        process.stdout.write(token);
      }
    }
  })(),
  (async () => {
    for await (const call of stream.toolCalls) {
      console.log(`\nTool call: ${call.name}(${JSON.stringify(call.input)})`);
      console.log(`Tool result: ${await call.output}`);
    }
  })(),
]);

================================== Ai Message ==================================
Tool Calls:
  schedule_event (call_mXFJJDU8bKZadNUZPaag8Lct)
 Call ID: call_mXFJJDU8bKZadNUZPaag8Lct
  Args:
    request: Schedule a team standup for tomorrow at 9am with Alice and Bob.
================================= Tool Message =================================
Name: schedule_event

The team standup has been scheduled for tomorrow at 9:00 AM with Alice and Bob. If you need to make any changes or add more details, just let me know!
================================== Ai Message ==================================

The team standup with Alice and Bob is scheduled for tomorrow at 9:00 AM. If you need any further arrangements or adjustments, please let me know!

主管识别出这是日历任务，调用 schedule_event，由日历智能体处理日期解析和事件创建。

TIP

要完全透明地了解信息流，包括每次对话模型调用的提示词和响应，请查看上述运行的 LangSmith 追踪。

示例 2：复杂的多领域请求

python

query = (
    "Schedule a meeting with the design team next Tuesday at 2pm for 1 hour, "
    "and send them an email reminder about reviewing the new mockups."
)

stream = supervisor_agent.stream_events(
    {"messages": [{"role": "user", "content": query}]},
    version="v3",
)
for kind, item in stream.interleave("messages", "tool_calls"):
    if kind == "messages":
        for token in item.text:
            print(token, end="", flush=True)
    elif kind == "tool_calls":
        print(f"\nTool call: {item.tool_name}({item.input})")
        print(f"Tool result: {item.output}")

typescript

const query =
  "Schedule a meeting with the design team next Tuesday at 2pm for 1 hour, " +
  "and send them an email reminder about reviewing the new mockups.";

const stream = await supervisorAgent.streamEvents(
  { messages: [{ role: "user", content: query }] },
  { version: "v3" }
);

await Promise.all([
  (async () => {
    for await (const message of stream.messages) {
      for await (const token of message.text) {
        process.stdout.write(token);
      }
    }
  })(),
  (async () => {
    for await (const call of stream.toolCalls) {
      console.log(`\nTool call: ${call.name}(${JSON.stringify(call.input)})`);
      console.log(`Tool result: ${await call.output}`);
    }
  })(),
]);

================================== Ai Message ==================================
Tool Calls:
  schedule_event (call_YA68mqF0koZItCFPx0kGQfZi)
 Call ID: call_YA68mqF0koZItCFPx0kGQfZi
  Args:
    request: meeting with the design team next Tuesday at 2pm for 1 hour
  manage_email (call_XxqcJBvVIuKuRK794ZIzlLxx)
 Call ID: call_XxqcJBvVIuKuRK794ZIzlLxx
  Args:
    request: send the design team an email reminder about reviewing the new mockups
================================= Tool Message =================================
Name: schedule_event

Your meeting with the design team is scheduled for next Tuesday, June 18th, from 2:00pm to 3:00pm. Let me know if you need to add more details or make any changes!
================================= Tool Message =================================
Name: manage_email

I've sent an email reminder to the design team requesting them to review the new mockups. If you need to include more information or recipients, just let me know!
================================== Ai Message ==================================

Your meeting with the design team is scheduled for next Tuesday, June 18th, from 2:00pm to 3:00pm.

I've also sent an email reminder to the design team, asking them to review the new mockups.

Let me know if you'd like to add more details to the meeting or include additional information in the email!

主管识别出这既需要日历操作也需要邮件操作，为会议调用 schedule_event，然后为提醒调用 manage_email。每个子智能体完成自己的任务，主管将两个结果整合为一个连贯的响应。

INFO

默认情况下，主管按顺序将任务分派给子智能体。每个工具调用在前一个完成后才开始。然而，许多 LLM 会在单个响应中发出多个工具调用（如上面的追踪所示，schedule_event 和 manage_email 被一起调用），运行时并行执行这些调用。你还可以配置显式的并行分派。详情请参阅 create_supervisor 参考文档。

TIP

请参阅 LangSmith 追踪查看上述运行的详细信息流，包括每次对话模型的提示词和响应。

完整可运行示例

以下是所有内容整合到可运行脚本中的完整示例：

python

"""
Personal Assistant Supervisor Example

This example demonstrates the tool calling pattern for multi-agent systems.
A supervisor agent coordinates specialized sub-agents (calendar and email)
that are wrapped as tools.
"""

from datetime import date

from langchain.tools import tool
from langchain.agents import create_agent
from langchain.chat_models import init_chat_model

# ============================================================================
# 步骤 1：定义底层 API 工具（桩实现）
# ============================================================================

@tool
def create_calendar_event(
    title: str,
    start_time: str,  # ISO 格式："2024-01-15T14:00:00"
    end_time: str,    # ISO 格式："2024-01-15T15:00:00"
    attendees: list[str],  # 电子邮件地址
    location: str = ""
) -> str:
    """Create a calendar event. Requires exact ISO datetime format."""
    return f"Event created: {title} from {start_time} to {end_time} with {len(attendees)} attendees"

@tool
def send_email(
    to: list[str],      # 电子邮件地址
    subject: str,
    body: str,
    cc: list[str] = []
) -> str:
    """Send an email via email API. Requires properly formatted addresses."""
    return f"Email sent to {', '.join(to)} - Subject: {subject}"

@tool
def get_available_time_slots(
    attendees: list[str],
    date: str,  # ISO 格式："2024-01-15"
    duration_minutes: int
) -> list[str]:
    """Check calendar availability for given attendees on a specific date."""
    return ["09:00", "14:00", "16:00"]

# ============================================================================
# 步骤 2：创建专门的子智能体
# ============================================================================

model = init_chat_model("gpt-5.5")  # 例如

calendar_agent = create_agent(
    model,
    tools=[create_calendar_event, get_available_time_slots],
    system_prompt=(
        f"Today's date is {date.today().isoformat()}. "
        "You are a calendar scheduling assistant. "
        "Parse natural language scheduling requests (e.g., 'next Tuesday at 2pm') "
        "into proper ISO datetime formats. "
        "Use get_available_time_slots to check availability when needed. "
        "If there is no suitable time slot, stop and confirm unavailability in your response. "
        "Use create_calendar_event to schedule events. "
        "Always confirm what was scheduled in your final response."
    )
)

email_agent = create_agent(
    model,
    tools=[send_email],
    system_prompt=(
        "You are an email assistant. "
        "Compose professional emails based on natural language requests. "
        "Extract recipient information and craft appropriate subject lines and body text. "
        "Use send_email to send the message. "
        "Always confirm what was sent in your final response."
    )
)

# ============================================================================
# 步骤 3：将子智能体包装为主管的工具
# ============================================================================

@tool
def schedule_event(request: str) -> str:
    """Schedule calendar events using natural language.

    Use this when the user wants to create, modify, or check calendar appointments.
    Handles date/time parsing, availability checking, and event creation.

    Input: Natural language scheduling request (e.g., 'meeting with design team
    next Tuesday at 2pm')
    """
    result = calendar_agent.invoke({
        "messages": [{"role": "user", "content": request}]
    })
    return result["messages"][-1].text

@tool
def manage_email(request: str) -> str:
    """Send emails using natural language.

    Use this when the user wants to send notifications, reminders, or any email
    communication. Handles recipient extraction, subject generation, and email
    composition.

    Input: Natural language email request (e.g., 'send them a reminder about
    the meeting')
    """
    result = email_agent.invoke({
        "messages": [{"role": "user", "content": request}]
    })
    return result["messages"][-1].text

# ============================================================================
# 步骤 4：创建主管智能体
# ============================================================================

supervisor_agent = create_agent(
    model,
    tools=[schedule_event, manage_email],
    system_prompt=(
        "You are a helpful personal assistant. "
        "You can schedule calendar events and send emails. "
        "Break down user requests into appropriate tool calls and coordinate the results. "
        "When a request involves multiple actions, use multiple tools in sequence or in parallel as appropriate."
    )
)

# ============================================================================
# 步骤 5：使用主管
# ============================================================================

if __name__ == "__main__":
    # 示例：需要同时协调日历与邮件的用户请求
    user_request = (
        "Schedule a meeting with the design team next Tuesday at 2pm for 1 hour, "
        "and send them an email reminder about reviewing the new mockups."
    )

    print("User Request:", user_request)
    print("\n" + "="*80 + "\n")

    stream = supervisor_agent.stream_events(
        {"messages": [{"role": "user", "content": user_request}]},
        version="v3",
    )
    for kind, item in stream.interleave("messages", "tool_calls"):
        if kind == "messages":
            for token in item.text:
                print(token, end="", flush=True)
        elif kind == "tool_calls":
            print(f"\nTool call: {item.tool_name}({item.input})")
            print(f"Tool result: {item.output}")

typescript

/**
 * 个人助理主管示例
 *
 * 本示例演示了多智能体系统的工具调用模式。
 * 主管智能体协调专门的子智能体（日历与邮件），
 * 这些子智能体被包装为工具。
 */

import { tool, createAgent } from "langchain";
import { ChatAnthropic } from "@langchain/anthropic";
import { z } from "zod";

// ============================================================================
// 步骤 1：定义底层 API 工具（桩实现）
// ============================================================================

const createCalendarEvent = tool(
  async ({ title, startTime, endTime, attendees, location }) => {
    // 桩（Stub）：在实际应用中，这会调用 Google Calendar API、Outlook API 等。
    return `Event created: ${title} from ${startTime} to ${endTime} with ${attendees.length} attendees`;
  },
  {
    name: "create_calendar_event",
    description: "Create a calendar event. Requires exact ISO datetime format.",
    schema: z.object({
      title: z.string(),
      startTime: z.string().describe("ISO format: '2024-01-15T14:00:00'"),
      endTime: z.string().describe("ISO format: '2024-01-15T15:00:00'"),
      attendees: z.array(z.string()).describe("email addresses"),
      location: z.string().optional().default(""),
    }),
  }
);

const sendEmail = tool(
  async ({ to, subject, body, cc }) => {
    // 桩（Stub）：在实际应用中，这会调用 SendGrid、Gmail API 等。
    return `Email sent to ${to.join(", ")} - Subject: ${subject}`;
  },
  {
    name: "send_email",
    description:
      "Send an email via email API. Requires properly formatted addresses.",
    schema: z.object({
      to: z.array(z.string()).describe("email addresses"),
      subject: z.string(),
      body: z.string(),
      cc: z.array(z.string()).optional().default([]),
    }),
  }
);

const getAvailableTimeSlots = tool(
  async ({ attendees, date, durationMinutes }) => {
    // 桩（Stub）：在实际应用中，这会查询日历 API
    return ["09:00", "14:00", "16:00"];
  },
  {
    name: "get_available_time_slots",
    description:
      "Check calendar availability for given attendees on a specific date.",
    schema: z.object({
      attendees: z.array(z.string()),
      date: z.string().describe("ISO format: '2024-01-15'"),
      durationMinutes: z.number(),
    }),
  }
);

// ============================================================================
// 步骤 2：创建专门的子智能体
// ============================================================================

const llm = new ChatAnthropic({
  model: "gpt-5.5",
});

const now = new Date();
const today = [
  now.getFullYear(),
  String(now.getMonth() + 1).padStart(2, "0"),
  String(now.getDate()).padStart(2, "0"),
].join("-");

const calendarAgent = createAgent({
  model: llm,
  tools: [createCalendarEvent, getAvailableTimeSlots],
  systemPrompt: `
Today's date is ${today}.
You are a calendar scheduling assistant.
Parse natural language scheduling requests (e.g., 'next Tuesday at 2pm')
into proper ISO datetime formats.
Use get_available_time_slots to check availability when needed.
If there is no suitable time slot, stop and confirm unavailability in your response.
Use create_calendar_event to schedule events.
Always confirm what was scheduled in your final response.
  `.trim(),
});

const emailAgent = createAgent({
  model: llm,
  tools: [sendEmail],
  systemPrompt: `
You are an email assistant.
Compose professional emails based on natural language requests.
Extract recipient information and craft appropriate subject lines and body text.
Use send_email to send the message.
Always confirm what was sent in your final response.
  `.trim(),
});

// ============================================================================
// 步骤 3：将子智能体包装为主管的工具
// ============================================================================

const scheduleEvent = tool(
  async ({ request }) => {
    const result = await calendarAgent.invoke({
      messages: [{ role: "user", content: request }],
    });
    const lastMessage = result.messages[result.messages.length - 1];
    return lastMessage.text;
  },
  {
    name: "schedule_event",
    description: `
Schedule calendar events using natural language.

Use this when the user wants to create, modify, or check calendar appointments.
Handles date/time parsing, availability checking, and event creation.

Input: Natural language scheduling request (e.g., 'meeting with design team next Tuesday at 2pm')
    `.trim(),
    schema: z.object({
      request: z.string().describe("Natural language scheduling request"),
    }),
  }
);

const manageEmail = tool(
  async ({ request }) => {
    const result = await emailAgent.invoke({
      messages: [{ role: "user", content: request }],
    });
    const lastMessage = result.messages[result.messages.length - 1];
    return lastMessage.text;
  },
  {
    name: "manage_email",
    description: `
Send emails using natural language.

Use this when the user wants to send notifications, reminders, or any email communication.
Handles recipient extraction, subject generation, and email composition.

Input: Natural language email request (e.g., 'send them a reminder about the meeting')
    `.trim(),
    schema: z.object({
      request: z.string().describe("Natural language email request"),
    }),
  }
);

// ============================================================================
// 步骤 4：创建主管智能体
// ============================================================================

const supervisorAgent = createAgent({
  model: llm,
  tools: [scheduleEvent, manageEmail],
  systemPrompt: `
You are a helpful personal assistant.
You can schedule calendar events and send emails.
Break down user requests into appropriate tool calls and coordinate the results.
When a request involves multiple actions, use multiple tools in sequence.
  `.trim(),
});

// ============================================================================
// 步骤 5：使用主管
// ============================================================================

// 示例：需要同时协调日历与邮件的用户请求
const userRequest =
  "Schedule a meeting with the design team next Tuesday at 2pm for 1 hour, " +
  "and send them an email reminder about reviewing the new mockups.";

console.log("User Request:", userRequest);
console.log(`\n${"=".repeat(80)}\n`);

const stream = await supervisorAgent.streamEvents(
  { messages: [{ role: "user", content: userRequest }] },
  { version: "v3" }
);

await Promise.all([
  (async () => {
    for await (const message of stream.messages) {
      for await (const token of message.text) {
        process.stdout.write(token);
      }
    }
  })(),
  (async () => {
    for await (const call of stream.toolCalls) {
      console.log(`\nTool call: ${call.name}(${JSON.stringify(call.input)})`);
      console.log(`Tool result: ${await call.output}`);
    }
  })(),
]);

理解架构

你的系统有三层。底层包含要求精确格式的刚性 API 工具。中间层包含接受自然语言、将其转换为结构化 API 调用并返回自然语言确认的子智能体。顶层包含主管，它路由到高级功能并整合结果。

这种关注点分离带来几个好处：每层都有聚焦的职责，你可以在不影响现有领域的情况下添加新领域，并且可以独立测试和迭代每一层。

6. 添加人在回路（人工介入）审查

对敏感操作加入人在回路（人工介入）审查是审慎的做法。LangChain 包含用于审查工具调用的内置中间件，在本例中即由子智能体调用的工具。

让我们为两个子智能体都添加人在回路（人工介入）审查：

我们配置 create_calendar_event 和 send_email 工具在调用时中断，允许所有响应类型（approve、edit、reject）
我们只给顶层智能体添加检查点。这是暂停和恢复执行所必需的。

python

from langchain.agents import create_agent
from langchain.agents.middleware import HumanInTheLoopMiddleware 
from langgraph.checkpoint.memory import InMemorySaver 

calendar_agent = create_agent(
    model,
    tools=[create_calendar_event, get_available_time_slots],
    system_prompt=CALENDAR_AGENT_PROMPT,
    middleware=[ 
        HumanInTheLoopMiddleware( 
            interrupt_on={"create_calendar_event": True}, 
            description_prefix="Calendar event pending approval", 
        ), 
    ], 
)

email_agent = create_agent(
    model,
    tools=[send_email],
    system_prompt=EMAIL_AGENT_PROMPT,
    middleware=[ 
        HumanInTheLoopMiddleware( 
            interrupt_on={"send_email": True}, 
            description_prefix="Outbound email pending approval", 
        ), 
    ], 
)

supervisor_agent = create_agent(
    model,
    tools=[schedule_event, manage_email],
    system_prompt=SUPERVISOR_PROMPT,
    checkpointer=InMemorySaver(), 
)

typescript

import { createAgent, humanInTheLoopMiddleware } from "langchain"; 
import { MemorySaver } from "@langchain/langgraph"; 

const calendarAgent = createAgent({
  model: llm,
  tools: [createCalendarEvent, getAvailableTimeSlots],
  systemPrompt: CALENDAR_AGENT_PROMPT,
  middleware: [ 
    humanInTheLoopMiddleware({ 
      interruptOn: { create_calendar_event: true }, 
      descriptionPrefix: "Calendar event pending approval", 
    }), 
  ], 
});

const emailAgent = createAgent({
  model: llm,
  tools: [sendEmail],
  systemPrompt: EMAIL_AGENT_PROMPT,
  middleware: [ 
    humanInTheLoopMiddleware({ 
      interruptOn: { send_email: true }, 
      descriptionPrefix: "Outbound email pending approval", 
    }), 
  ], 
});

const supervisorAgent = createAgent({
  model: llm,
  tools: [scheduleEvent, manageEmail],
  systemPrompt: SUPERVISOR_PROMPT,
  checkpointer: new MemorySaver(), 
});

让我们重复该查询。注意，我们将中断事件收集到列表中，以便在后续访问：

python

query = (
    "Schedule a meeting with the design team next Tuesday at 2pm for 1 hour, "
    "and send them an email reminder about reviewing the new mockups."
)

config = {"configurable": {"thread_id": "6"}}

interrupts = []
stream = supervisor_agent.stream_events(
    {"messages": [{"role": "user", "content": query}]},
    config,
    version="v3",
)
for kind, item in stream.interleave("messages", "tool_calls"):
    if kind == "messages":
        for token in item.text:
            print(token, end="", flush=True)
    elif kind == "tool_calls":
        print(f"\nTool call: {item.tool_name}({item.input})")
if stream.interrupted:
    for interrupt_ in stream.interrupts:
        interrupts.append(interrupt_)
        print(f"\nINTERRUPTED: {interrupt_.id}")

typescript

const query =
  "Schedule a meeting with the design team next Tuesday at 2pm for 1 hour, " +
  "and send them an email reminder about reviewing the new mockups.";

const config = { configurable: { thread_id: "6" } };

const interrupts: any[] = [];
const stream = await supervisorAgent.streamEvents(
  { messages: [{ role: "user", content: query }] },
  { ...config, version: "v3" }
);

await Promise.all([
  (async () => {
    for await (const message of stream.messages) {
      for await (const token of message.text) {
        process.stdout.write(token);
      }
    }
  })(),
  (async () => {
    for await (const call of stream.toolCalls) {
      console.log(`\nTool call: ${call.name}(${JSON.stringify(call.input)})`);
    }
  })(),
]);
if (stream.interrupted) {
  for (const interrupt of stream.interrupts) {
    interrupts.push(interrupt);
    console.log(`\nINTERRUPTED: ${interrupt.interruptId}`);
  }
}

================================== Ai Message ==================================
Tool Calls:
  schedule_event (call_t4Wyn32ohaShpEZKuzZbl83z)
 Call ID: call_t4Wyn32ohaShpEZKuzZbl83z
  Args:
    request: Schedule a meeting with the design team next Tuesday at 2pm for 1 hour.
  manage_email (call_JWj4vDJ5VMnvkySymhCBm4IR)
 Call ID: call_JWj4vDJ5VMnvkySymhCBm4IR
  Args:
    request: Send an email reminder to the design team about reviewing the new mockups before our meeting next Tuesday at 2pm.

INTERRUPTED: 4f994c9721682a292af303ec1a46abb7

INTERRUPTED: 2b56f299be313ad8bc689eff02973f16

这一次我们中断了执行。让我们检查中断事件：

python

for interrupt_ in interrupts:
    for request in interrupt_.value["action_requests"]:
        print(f"INTERRUPTED: {interrupt_.id}")
        print(f"{request['description']}\n")

typescript

for (const interrupt of interrupts) {
  for (const request of interrupt.payload.actionRequests) {
    console.log(`INTERRUPTED: ${interrupt.interruptId}`);
    console.log(`${request.description}\n`);
  }
}

INTERRUPTED: 4f994c9721682a292af303ec1a46abb7
Calendar event pending approval

Tool: create_calendar_event
Args: {'title': 'Meeting with the Design Team', 'start_time': '2024-06-18T14:00:00', 'end_time': '2024-06-18T15:00:00', 'attendees': ['design team']}

INTERRUPTED: 2b56f299be313ad8bc689eff02973f16
Outbound email pending approval

Tool: send_email
Args: {'to': ['designteam@example.com'], 'subject': 'Reminder: Review New Mockups Before Meeting Next Tuesday at 2pm', 'body': "Hello Team,\n\nThis is a reminder to review the new mockups ahead of our meeting scheduled for next Tuesday at 2pm. Your feedback and insights will be valuable for our discussion and next steps.\n\nPlease ensure you've gone through the designs and are ready to share your thoughts during the meeting.\n\nThank you!\n\nBest regards,\n[Your Name]"}

我们可以通过使用 Command 引用其 ID 来为每个中断指定决策。更多详情请参阅人在回路（人工介入）指南。出于演示目的，这里我们将批准日历事件，但编辑外发邮件的主题：

python

from langgraph.types import Command 

resume = {}
for interrupt_ in interrupts:
    if interrupt_.id == "2b56f299be313ad8bc689eff02973f16":
        # 编辑邮件
        edited_action = interrupt_.value["action_requests"][0].copy()
        edited_action["args"]["subject"] = "Mockups reminder"
        resume[interrupt_.id] = {
            "decisions": [{"type": "edit", "edited_action": edited_action}]
        }
    else:
        resume[interrupt_.id] = {"decisions": [{"type": "approve"}]}

interrupts = []
stream = supervisor_agent.stream_events(
    Command(resume=resume), 
    config,
    version="v3",
)
for kind, item in stream.interleave("messages", "tool_calls"):
    if kind == "messages":
        for token in item.text:
            print(token, end="", flush=True)
    elif kind == "tool_calls":
        print(f"\nTool call: {item.tool_name}({item.input})")
if stream.interrupted:
    for interrupt_ in stream.interrupts:
        interrupts.append(interrupt_)
        print(f"\nINTERRUPTED: {interrupt_.id}")

typescript

import { Command } from "@langchain/langgraph"; 

const resume: Record<string, any> = {};
for (const interrupt of interrupts) {
  const actionRequest = interrupt.payload.actionRequests[0];
  if (actionRequest.name === "send_email") {
    // 编辑邮件
    const editedAction = { ...actionRequest };
    editedAction.args.subject = "Mockups reminder";
    resume[interrupt.interruptId] = {
      decisions: [{ type: "edit", editedAction }]
    };
  } else {
    resume[interrupt.interruptId] = { decisions: [{ type: "approve" }] };
  }
}

const resumeStream = await supervisorAgent.streamEvents(
  new Command({ resume }), 
  { ...config, version: "v3" }
);

await Promise.all([
  (async () => {
    for await (const message of resumeStream.messages) {
      for await (const token of message.text) {
        process.stdout.write(token);
      }
    }
  })(),
  (async () => {
    for await (const call of resumeStream.toolCalls) {
      console.log(`\nTool call: ${call.name}(${JSON.stringify(call.input)})`);
    }
  })(),
]);

================================= Tool Message =================================
Name: schedule_event

Your meeting with the design team has been scheduled for next Tuesday, June 18th, from 2:00 pm to 3:00 pm.
================================= Tool Message =================================
Name: manage_email

Your email reminder to the design team has been sent. Here’s what was sent:

- Recipient: designteam@example.com
- Subject: Mockups reminder
- Body: A reminder to review the new mockups before the meeting next Tuesday at 2pm, with a request for feedback and readiness for discussion.

Let me know if you need any further assistance!
================================== Ai Message ==================================

- Your meeting with the design team has been scheduled for next Tuesday, June 18th, from 2:00 pm to 3:00 pm.
- An email reminder has been sent to the design team about reviewing the new mockups before the meeting.

Let me know if you need any further assistance!

运行按照我们的输入继续进行。

7. 高级：控制信息流

默认情况下，子智能体只从主管接收请求字符串。你可能希望传递额外的上下文，例如对话历史或用户偏好。

向子智能体传递额外的对话上下文

python

from langchain.tools import tool, ToolRuntime

@tool
def schedule_event(
    request: str,
    runtime: ToolRuntime
) -> str:
    """Schedule calendar events using natural language."""
    # 自定义子智能体接收的上下文
    original_user_message = next(
        message for message in runtime.state["messages"]
        if message.type == "human"
    )
    prompt = (
        "You are assisting with the following user inquiry:\n\n"
        f"{original_user_message.text}\n\n"
        "You are tasked with the following sub-request:\n\n"
        f"{request}"
    )
    result = calendar_agent.invoke({
        "messages": [{"role": "user", "content": prompt}],
    })
    return result["messages"][-1].text

typescript

import { getCurrentTaskInput } from "@langchain/langgraph";
import { type BuiltInState, HumanMessage } from "langchain";

const scheduleEvent = tool(
  async ({ request }, config) => {
    // 自定义子智能体接收的上下文
    // 从 config 中访问完整的线程消息
    const currentMessages = getCurrentTaskInput<BuiltInState>(config).messages;
    const originalUserMessage = currentMessages.find(HumanMessage.isInstance);
    const prompt = `
You are assisting with the following user inquiry:

${originalUserMessage?.content || "No context available"}

You are tasked with the following sub-request:

${request}
    `.trim();

    const result = await calendarAgent.invoke({
      messages: [{ role: "user", content: prompt }],
    });
    const lastMessage = result.messages[result.messages.length - 1];
    return lastMessage.text;
  },
  {
    name: "schedule_event",
    description: "Schedule calendar events using natural language.",
    schema: z.object({
      request: z.string().describe("Natural language scheduling request"),
    }),
  }
);

这允许子智能体看到完整的对话上下文，这对于解决"明天同一时间安排"这样的歧义（引用之前的对话）很有用。

TIP

你可以在 LangSmith 追踪的对话模型调用中查看子智能体接收到的完整上下文。

控制主管接收的内容

你还可以自定义流回主管的信息：

python

import json

@tool
def schedule_event(request: str) -> str:
    """Schedule calendar events using natural language."""
    result = calendar_agent.invoke({
        "messages": [{"role": "user", "content": request}]
    })

    # 选项 1：只返回确认消息
    return result["messages"][-1].text

    # 选项 2：返回结构化数据
    # return json.dumps({
    #     "status": "success",
    #     "event_id": "evt_123",
    #     "summary": result["messages"][-1].text
    # })

typescript

const scheduleEvent = tool(
  async ({ request }) => {
    const result = await calendarAgent.invoke({
      messages: [{ role: "user", content: request }]
    });

    const lastMessage = result.messages[result.messages.length - 1];

    // 选项 1：只返回确认消息
    return lastMessage.text;

    // 选项 2：返回结构化数据
    // return JSON.stringify({
    //   status: "success",
    //   event_id: "evt_123",
    //   summary: lastMessage.text
    // });
  },
  {
    name: "schedule_event",
    description: "Schedule calendar events using natural language.",
    schema: z.object({
      request: z.string().describe("Natural language scheduling request"),
    }),
  }
);

重要提示： 确保子智能体的提示词强调其最终消息应包含所有相关信息。一个常见的失败模式是子智能体执行了工具调用，但没有在最终响应中包含结果。

TIP

有关演示带人在回路（人工介入）审查和高级信息流控制的完整主管模式的完整可运行示例，请查看 LangChain.js 示例中的 supervisor_complete.ts。

8. 关键要点

主管模式创建了抽象层，每层都有清晰的职责。在设计主管系统时，从清晰的领域边界开始，为每个子智能体提供聚焦的工具和提示词。为主管编写清晰的工具描述，在集成前独立测试每一层，并根据你的具体需求控制信息流。

TIP

何时使用主管模式

当你拥有多个不同的领域（日历、邮件、CRM、数据库）、每个领域都有多个工具或复杂逻辑、想要集中的工作流控制，并且子智能体不需要直接与用户对话时，请使用主管模式。

对于只有少量工具的较简单场景，请使用单个智能体。当智能体需要与用户对话时，请改用交接。对于智能体之间的对等协作，请考虑其他多智能体模式。

后续步骤

了解用于智能体间对话的交接，探索上下文工程以微调信息流，阅读多智能体概述以比较不同模式，并使用 LangSmith 调试和监控你的多智能体系统。

Patterns

Integrations

Multi-agent

Test

概述

为什么要使用主管？

概念

设置

安装

LangSmith

组件

OpenAI

Anthropic

Azure

Google Gemini

AWS Bedrock

HuggingFace

OpenRouter

OpenAI

Anthropic

Azure

Google Gemini

Bedrock Converse

1. 定义工具

2. 创建专门的子智能体

创建日历智能体

创建邮件智能体

3. 将子智能体包装为工具

4. 创建主管智能体

5. 使用主管

示例 1：简单的单领域请求

示例 2：复杂的多领域请求

完整可运行示例

理解架构

6. 添加人在回路（人工介入）审查

7. 高级：控制信息流

向子智能体传递额外的对话上下文

控制主管接收的内容

8. 关键要点

后续步骤

概述 ​

为什么要使用主管？ ​

概念 ​

设置 ​

安装 ​

LangSmith ​

组件 ​

OpenAI ​

Anthropic ​

Azure ​

Google Gemini ​

AWS Bedrock ​

HuggingFace ​

OpenRouter ​

OpenAI ​

Anthropic ​

Azure ​

Google Gemini ​

Bedrock Converse ​

1. 定义工具 ​

2. 创建专门的子智能体 ​

创建日历智能体 ​

创建邮件智能体 ​

3. 将子智能体包装为工具 ​

4. 创建主管智能体 ​

5. 使用主管 ​

示例 1：简单的单领域请求 ​

示例 2：复杂的多领域请求 ​

完整可运行示例 ​

理解架构 ​

6. 添加人在回路（人工介入）审查 ​

7. 高级：控制信息流 ​

向子智能体传递额外的对话上下文 ​

控制主管接收的内容 ​

8. 关键要点 ​

后续步骤 ​

概述

为什么要使用主管？

概念

设置

安装

LangSmith

组件

OpenAI

Anthropic

Azure

Google Gemini

AWS Bedrock

HuggingFace

OpenRouter

OpenAI

Anthropic

Azure

Google Gemini

Bedrock Converse

1. 定义工具

2. 创建专门的子智能体

创建日历智能体

创建邮件智能体

3. 将子智能体包装为工具

4. 创建主管智能体

5. 使用主管

示例 1：简单的单领域请求

示例 2：复杂的多领域请求

完整可运行示例

理解架构

6. 添加人在回路（人工介入）审查

7. 高级：控制信息流

向子智能体传递额外的对话上下文

控制主管接收的内容

8. 关键要点

后续步骤