使用子代理构建个人助手

概览

主管模式是一种多代理架构，其中一个中央主管代理协调专门的工作代理。当任务需要不同类型的专业知识时，这种方法表现尤为出色。与其构建一个跨领域管理工具选择的单一代理，不如创建由理解整体工作流的协调者协调的专注型专家代理。在本教程中，你将构建一个个人助手系统，通过一个实际的工作流来展示这些优势。该系统将协调两个职责根本不同的专家代理：

日历代理：负责日程安排、可用时间检查和事件管理。
邮件代理：负责管理通信、起草消息并发送通知。

我们还将引入人工介入审核，允许用户根据需要批准、编辑和拒绝操作（例如外发邮件）。

为什么使用主管模式？

多代理架构允许你将工具分配给各个工作代理，每个工作代理都有其独立的提示或指令。考虑一个直接访问所有日历和邮件 API 的代理：它必须从众多相似工具中进行选择，理解每个 API 的精确格式，并同时处理多个领域。如果性能下降，将相关工具及其关联提示分离到逻辑分组中可能会有所帮助（部分原因是便于管理迭代改进）。

涉及概念

我们将涵盖以下概念：

配置

安装

本教程需要 langchain 包：

pip install langchain

更多详情请参阅安装指南。

LangSmith

配置 LangSmith 以查看代理内部的运行情况。然后设置以下环境变量：

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

组件

我们需要从 LangChain 的集成套件中选择一个聊天模型：

👉 Read the OpenAI chat model integration docs

pip install -U "langchain[openai]"

import os
from langchain.chat_models import init_chat_model

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

model = init_chat_model("gpt-5.2")

👉 Read the Anthropic chat model integration docs

pip install -U "langchain[anthropic]"

import os
from langchain.chat_models import init_chat_model

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

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

👉 Read the Azure chat model integration docs

pip install -U "langchain[openai]"

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-5.2",
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
)

👉 Read the Google GenAI chat model integration docs

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

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")

👉 Read the AWS Bedrock chat model integration docs

pip install -U "langchain[aws]"

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(
    "anthropic.claude-3-5-sonnet-20240620-v1:0",
    model_provider="bedrock_converse",
)

👉 Read the HuggingFace chat model integration docs

pip install -U "langchain[huggingface]"

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,
)

1. 定义工具

首先定义需要结构化输入的工具。在实际应用中，这些工具将调用真实的 API（Google Calendar、SendGrid 等）。在本教程中，你将使用桩函数来演示该模式。

from langchain.tools import tool

@tool
def create_calendar_event(
    title: str,
    start_time: str,       # ISO format: "2024-01-15T14:00:00"
    end_time: str,         # ISO format: "2024-01-15T15:00:00"
    attendees: list[str],  # email addresses
    location: str = ""
) -> str:
    """Create a calendar event. Requires exact ISO datetime format."""
    # Stub: In practice, this would call Google Calendar API, Outlook API, etc.
    return f"Event created: {title} from {start_time} to {end_time} with {len(attendees)} attendees"


@tool
def send_email(
    to: list[str],  # email addresses
    subject: str,
    body: str,
    cc: list[str] = []
) -> str:
    """Send an email via email API. Requires properly formatted addresses."""
    # Stub: In practice, this would call SendGrid, Gmail API, etc.
    return f"Email sent to {', '.join(to)} - Subject: {subject}"


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

2. 创建专门的子代理

接下来，我们将创建处理各自领域的专门子代理。

创建日历代理

日历代理能够理解自然语言日程安排请求，并将其转化为精确的 API 调用。它负责日期解析、可用性检查和事件创建。

from langchain.agents import create_agent


CALENDAR_AGENT_PROMPT = (
    "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. "
    "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,
)

测试日历代理，查看它如何处理自然语言日程安排：

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

for step in calendar_agent.stream(
    {"messages": [{"role": "user", "content": query}]}
):
    for update in step.values():
        for message in update.get("messages", []):
            message.pretty_print()

================================== 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!

代理将”next Tuesday at 2pm”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信息。

创建邮件代理

邮件代理负责消息撰写和发送。它专注于提取收件人信息、拟定合适的主题行和正文，以及管理邮件通信。

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,
)

使用自然语言请求测试邮件代理：

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

for step in email_agent.stream(
    {"messages": [{"role": "user", "content": query}]}
):
    for update in step.values():
        for message in update.get("messages", []):
            message.pretty_print()

================================== 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!

代理从非正式请求中推断收件人，拟定专业的主题行和正文，调用 send_email，并返回确认信息。每个子代理都有明确的专注领域，配备领域专用的工具和提示，使其能够在特定任务上表现出色。

3. 将子代理封装为工具

现在将每个子代理封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。主管将看到高级工具（如”schedule_event”），而非底层工具（如”create_calendar_event”）。

@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

工具描述帮助主管决定何时使用每个工具，因此请确保它们清晰具体。我们只返回子代理的最终响应，因为主管不需要查看中间推理或工具调用过程。

4. 创建主管代理

现在创建协调子代理的主管。主管只看到高级工具，并在领域层面做出路由决策，而非在单个 API 层面。

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."
)

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

5. 使用主管

现在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

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

for step in supervisor_agent.stream(
    {"messages": [{"role": "user", "content": query}]}
):
    for update in step.values():
        for message in update.get("messages", []):
            message.pretty_print()

================================== 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!

主管识别出这是一个日历任务，调用 schedule_event，日历代理负责日期解析和事件创建。

如需完整了解信息流，包括每次聊天模型调用的提示和响应，请查看上述运行的 LangSmith 追踪。

示例 2：复杂的多领域请求

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."
)

for step in supervisor_agent.stream(
    {"messages": [{"role": "user", "content": query}]}
):
    for update in step.values():
        for message in update.get("messages", []):
            message.pretty_print()

================================== 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!

主管识别出此请求需要日历和邮件两类操作，先调用 schedule_event 创建会议，再调用 manage_email 发送提醒。每个子代理完成各自的任务后，主管将两个结果综合为一个连贯的响应。

参阅 LangSmith 追踪，查看上述运行的详细信息流，包括各聊天模型的提示和响应。

完整的可运行示例

以下是整合在一起的可运行脚本：

Show 查看完整代码

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

# ============================================================================
# Step 1: Define low-level API tools (stubbed)
# ============================================================================

@tool
def create_calendar_event(
    title: str,
    start_time: str,  # ISO format: "2024-01-15T14:00:00"
    end_time: str,    # ISO format: "2024-01-15T15:00:00"
    attendees: list[str],  # email addresses
    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],      # email addresses
    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 format: "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"]


# ============================================================================
# Step 2: Create specialized sub-agents
# ============================================================================

model = init_chat_model("claude-haiku-4-5-20251001")  # for example

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

# ============================================================================
# Step 3: Wrap sub-agents as tools for the supervisor
# ============================================================================

@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


# ============================================================================
# Step 4: Create the supervisor agent
# ============================================================================

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."
    )
)

# ============================================================================
# Step 5: Use the supervisor
# ============================================================================

if __name__ == "__main__":
    # Example: User request requiring both calendar and email coordination
    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")

    for step in supervisor_agent.stream(
        {"messages": [{"role": "user", "content": user_request}]}
    ):
        for update in step.values():
            for message in update.get("messages", []):
                message.pretty_print()

理解架构

你的系统共有三层。底层包含需要精确格式的刚性 API 工具。中间层包含接受自然语言的子代理，将其转化为结构化 API 调用，并返回自然语言确认。顶层包含路由到高级能力并综合结果的主管。这种关注点分离带来了几个好处：每层都有明确的职责，你可以在不影响现有层的情况下添加新领域，并且可以独立测试和迭代每一层。

6. 添加人工介入审核

对敏感操作引入人工介入审核是明智之举。LangChain 内置了中间件用于审核工具调用，本例中即子代理调用的工具。让我们为两个子代理添加人工介入审核：

我们将 create_calendar_event 和 send_email 工具配置为触发中断，支持所有响应类型（approve、edit、reject）
我们仅在顶层代理添加检查点器。这是暂停和恢复执行所必需的。

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(),
)

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后续访问：

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 = []
for step in supervisor_agent.stream(
    {"messages": [{"role": "user", "content": query}]},
    config,
):
    for update in step.values():
        if isinstance(update, dict):
            for message in update.get("messages", []):
                message.pretty_print()
        else:
            interrupt_ = update[0]
            interrupts.append(interrupt_)
            print(f"\nINTERRUPTED: {interrupt_.id}")

================================== 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

这次我们中断了执行。让我们查看中断事件：

for interrupt_ in interrupts:
    for request in interrupt_.value["action_requests"]:
        print(f"INTERRUPTED: {interrupt_.id}")
        print(f"{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 Command 引用其 ID 来为每个中断指定决策。更多详情请参阅人工介入指南。出于演示目的，这里我们接受日历事件，但编辑外发邮件的主题：

from langgraph.types import Command 

resume = {}
for interrupt_ in interrupts:
    if interrupt_.id == "2b56f299be313ad8bc689eff02973f16":
        # Edit email
        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 = []
for step in supervisor_agent.stream(
    Command(resume=resume),
    config,
):
    for update in step.values():
        if isinstance(update, dict):
            for message in update.get("messages", []):
                message.pretty_print()
        else:
            interrupt_ = update[0]
            interrupts.append(interrupt_)
            print(f"\nINTERRUPTED: {interrupt_.id}")

================================= 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!

运行继续执行，采用了我们的输入。

7. 进阶：控制信息流

默认情况下，子代理仅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。

向子代理传递额外的对话上下文

from langchain.tools import tool, ToolRuntime

@tool
def schedule_event(
    request: str,
    runtime: ToolRuntime
) -> str:
    """Schedule calendar events using natural language."""
    # Customize context received by sub-agent
    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

这样子代理就可以看到完整的对话上下文，对于解决歧义（例如”明天同一时间安排”这类引用前一次对话的请求）非常有用。

你可以在 LangSmith 追踪的聊天模型调用中查看子代理接收到的完整上下文。

控制主管接收的内容

你还可以自定义回传给主管的信息：

import json

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

    # Option 1: Return just the confirmation message
    return result["messages"][-1].text

    # Option 2: Return structured data
    # return json.dumps({
    #     "status": "success",
    #     "event_id": "evt_123",
    #     "summary": result["messages"][-1].text
    # })

重要提示： 确保子代理的系统提示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代理执行了工具调用，但在最终响应中未包含结果。

8. 关键要点

主管模式创建了多层抽象，每层都有明确的职责。在设计主管系统时，从清晰的领域边界入手，为每个子代理提供专注的工具和提示。为主管编写清晰的工具描述，在集成前独立测试每一层，并根据具体需求控制信息流。

何时使用主管模式当你有多个不同的领域（日历、邮件、CRM、数据库），每个领域有多个工具或复杂逻辑，需要集中的工作流控制，且子代理不需要直接与用户对话时，使用主管模式。对于只有少量工具的简单场景，使用单一代理。当代理需要与用户对话时，改用交接。对于代理间的点对点协作，考虑其他多代理模式。

下一步

了解用于代理间对话的交接，探索上下文工程以精细调整信息流，阅读多代理概览以对比不同模式，并使用 LangSmith 调试和监控你的多代理系统。

在 GitHub 上编辑此页面或提交问题。

将这些文档连接到 Claude、VSCode 等，通过 MCP 获取实时解答。

Tutorials

Conceptual overviews

Additional resources

概览

为什么使用主管模式？

涉及概念

配置

安装

LangSmith

组件

1. 定义工具

2. 创建专门的子代理

创建日历代理

创建邮件代理

3. 将子代理封装为工具

4. 创建主管代理

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

完整的可运行示例

理解架构

6. 添加人工介入审核

7. 进阶：控制信息流

向子代理传递额外的对话上下文

控制主管接收的内容

8. 关键要点

下一步

Tutorials

Conceptual overviews

Additional resources

​概览

​为什么使用主管模式？

​涉及概念

​配置

​安装

​LangSmith

​组件

​1. 定义工具

​2. 创建专门的子代理

​创建日历代理

​创建邮件代理

​3. 将子代理封装为工具

​4. 创建主管代理

​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

​完整的可运行示例

​理解架构

​6. 添加人工介入审核

​7. 进阶：控制信息流

​向子代理传递额外的对话上下文

​控制主管接收的内容

​8. 关键要点

​下一步

概览

为什么使用主管模式？

涉及概念

配置

安装

LangSmith

组件

1. 定义工具

2. 创建专门的子代理

创建日历代理

创建邮件代理

3. 将子代理封装为工具

4. 创建主管代理

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

完整的可运行示例

理解架构

6. 添加人工介入审核

7. 进阶：控制信息流

向子代理传递额外的对话上下文

控制主管接收的内容

8. 关键要点

下一步