跳到主要内容

文档索引

在以下地址获取完整的文档索引：https://docs.langchain.org.cn/llms.txt

在进一步探索之前，请使用此文件发现所有可用页面。

某些工具操作可能很敏感，需要在执行前获得人工批准。Deep Agents 通过 LangGraph 的中断功能支持人机协同工作流。您可以使用 interrupt_on 参数来配置哪些工具需要审批。

​
基本配置

interrupt_on 参数接受一个字典，将工具名称映射到中断配置。每个工具都可以配置为：
  • True：启用中断并使用默认行为（允许批准、编辑、拒绝、响应）
  • False：禁用此工具的中断
  • {"allowed_decisions": [...]}：具有特定允许决策的自定义配置
from langchain.tools import tool
from deepagents import create_deep_agent
from langgraph.checkpoint.memory import MemorySaver

@tool
def delete_file(path: str) -> str:
    """Delete a file from the filesystem."""
    return f"Deleted {path}"

@tool
def read_file(path: str) -> str:
    """Read a file from the filesystem."""
    return f"Contents of {path}"

@tool
def send_email(to: str, subject: str, body: str) -> str:
    """Send an email."""
    return f"Sent email to {to}"

# Checkpointer is REQUIRED for human-in-the-loop
checkpointer = MemorySaver()

agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    tools=[delete_file, read_file, send_email],
    interrupt_on={
        "delete_file": True,  # Default: approve, edit, reject, respond
        "read_file": False,   # No interrupts needed
        "send_email": {"allowed_decisions": ["approve", "reject"]},  # No editing
    },
    checkpointer=checkpointer  # Required!
)

​
决策类型

allowed_decisions 列表控制人工在审查工具调用时可以采取的操作
  • "approve"：使用智能体提议的原始参数执行工具
  • "edit"：在执行前修改工具参数
  • "reject"：完全跳过此工具调用的执行
  • "respond"：直接将人类的消息作为工具结果返回，跳过执行——适用于“询问用户”类型的工具
您可以自定义每个工具可用的决策 
interrupt_on = {
    # Sensitive operations: allow all options
    "delete_file": {"allowed_decisions": ["approve", "edit", "reject"]},

    # Moderate risk: approval or rejection only
    "write_file": {"allowed_decisions": ["approve", "reject"]},

    # Must approve (no rejection allowed)
    "critical_operation": {"allowed_decisions": ["approve"]},
}

​
处理中断

当中断触发时，智能体暂停执行并交出控制权。检查结果中的中断并相应地进行处理。 
from langchain_core.utils.uuid import uuid7
from langgraph.types import Command

# Create config with thread_id for state persistence
config = {"configurable": {"thread_id": str(uuid7())}}

# Invoke the agent
result = agent.invoke(
    {"messages": [{"role": "user", "content": "Delete the file temp.txt"}]},
    config=config,
    version="v2",
)

# Check if execution was interrupted
if result.interrupts:
    # Extract interrupt information
    interrupt_value = result.interrupts[0].value  
    action_requests = interrupt_value["action_requests"]
    review_configs = interrupt_value["review_configs"]

    # Create a lookup map from tool name to review config
    config_map = {cfg["action_name"]: cfg for cfg in review_configs}

    # Display the pending actions to the user
    for action in action_requests:
        review_config = config_map[action["name"]]
        print(f"Tool: {action['name']}")
        print(f"Arguments: {action['args']}")
        print(f"Allowed decisions: {review_config['allowed_decisions']}")

    # Get user decisions (one per action_request, in order)
    decisions = [
        {"type": "approve"}  # User approved the deletion
    ]

    # Resume execution with decisions
    result = agent.invoke(
        Command(resume={"decisions": decisions}),
        config=config,  # Must use the same config!
        version="v2",
    )

# Process final result
print(result.value["messages"][-1].content)

​
多次工具调用

当智能体调用多个需要审批的工具时，所有中断都会合并在一次中断中。您必须按顺序为每一个提供决策。 
config = {"configurable": {"thread_id": str(uuid7())}}

result = agent.invoke(
    {"messages": [{
        "role": "user",
        "content": "Delete temp.txt and send an email to admin@example.com"
    }]},
    config=config,
    version="v2",
)

if result.interrupts:
    interrupt_value = result.interrupts[0].value  
    action_requests = interrupt_value["action_requests"]

    # Two tools need approval
    assert len(action_requests) == 2

    # Provide decisions in the same order as action_requests
    decisions = [
        {"type": "approve"},  # First tool: delete_file
        {"type": "reject"}    # Second tool: send_email
    ]

    result = agent.invoke(
        Command(resume={"decisions": decisions}),
        config=config,
        version="v2",
    )

​
编辑工具参数

当 "edit" 在允许的决策中时，您可以在执行前修改工具参数 
if result.interrupts:
    interrupt_value = result.interrupts[0].value  
    action_request = interrupt_value["action_requests"][0]

    # Original args from the agent
    print(action_request["args"])  # {"to": "everyone@company.com", ...}

    # User decides to edit the recipient
    decisions = [{
        "type": "edit",
        "edited_action": {
            "name": action_request["name"],  # Must include the tool name
            "args": {"to": "team@company.com", "subject": "...", "body": "..."}
        }
    }]

    result = agent.invoke(
        Command(resume={"decisions": decisions}),
        config=config,
        version="v2",
    )

​
子智能体中断

使用子智能体时，您可以使用工具调用中断和工具调用内部中断。

​
工具调用中断

每个子智能体可以有自己的 interrupt_on 配置，该配置会覆盖主智能体的设置 
agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    tools=[delete_file, read_file],
    interrupt_on={
        "delete_file": True,
        "read_file": False,
    },
    subagents=[{
        "name": "file-manager",
        "description": "Manages file operations",
        "system_prompt": "You are a file management assistant.",
        "tools": [delete_file, read_file],
        "interrupt_on": {
            # Override: require approval for reads in this subagent
            "delete_file": True,
            "read_file": True,  # Different from main agent!
        }
    }],
    checkpointer=checkpointer
)
当子智能体触发中断时，处理方式是一样的——检查结果上的 interrupts 并使用 Command 恢复。

​
工具调用内部中断

子智能体工具可以直接调用 interrupt() 来暂停执行并等待审批 
from langchain.agents import create_agent
from langchain_anthropic import ChatAnthropic
from langchain.messages import HumanMessage
from langchain.tools import tool
from langgraph.checkpoint.memory import InMemorySaver
from langgraph.types import Command, interrupt

from deepagents.graph import create_deep_agent
from deepagents.middleware.subagents import CompiledSubAgent


@tool(description="Request human approval before proceeding with an action.")
def request_approval(action_description: str) -> str:
    """Request human approval using the interrupt() primitive."""
    # interrupt() pauses execution and returns the value passed to Command(resume=...)
    approval = interrupt({
        "type": "approval_request",
        "action": action_description,
        "message": f"Please approve or reject: {action_description}",
    })

    if approval.get("approved"):
        return f"Action '{action_description}' was APPROVED. Proceeding..."
    else:
        return f"Action '{action_description}' was REJECTED. Reason: {approval.get('reason', 'No reason provided')}"


def main():
    checkpointer = InMemorySaver()
    model = ChatAnthropic(
        model_name="claude-sonnet-4-6",
        max_tokens=4096,
    )

    compiled_subagent = create_agent(
        model=model,
        tools=[request_approval],
        name="approval-agent",
    )

    parent_agent = create_deep_agent(
        model="google_genai:gemini-3.1-pro-preview",
        checkpointer=checkpointer,
        subagents=[
            CompiledSubAgent(
                name="approval-agent",
                description="An agent that can request approvals",
                runnable=compiled_subagent,
            )
        ],
    )

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

    print("Invoking agent - sub-agent will use request_approval tool...")

    result = parent_agent.invoke(
        {
            "messages": [
                HumanMessage(
                    content="Use the task tool to launch the approval-agent sub-agent. "
                    "Tell it to use the request_approval tool to request approval for 'deploying to production'."
                )
            ]
        },
        config=config,
        version="v2",
    )

    # Check for interrupt
    if result.interrupts:
        interrupt_value = result.interrupts[0].value  
        print(f"\nInterrupt received!")
        print(f"  Type: {interrupt_value.get('type')}")
        print(f"  Action: {interrupt_value.get('action')}")
        print(f"  Message: {interrupt_value.get('message')}")

        print("\nResuming with Command(resume={'approved': True})...")
        result2 = parent_agent.invoke(
            Command(resume={"approved": True}),
            config=config,
            version="v2",
        )

        if not result2.interrupts:
            print("\nExecution completed!")
            # Find the tool response
            tool_msgs = [m for m in result2.value.get("messages", []) if m.type == "tool"]
            if tool_msgs:
                print(f"  Tool result: {tool_msgs[-1].content}")
        else:
            print("\nAnother interrupt occurred")
    else:
        print("\n  No interrupt - the model may not have called request_approval")


if __name__ == "__main__":
    main()
运行时，这会产生以下输出 
Invoking agent - sub-agent will use request_approval tool...

Interrupt received!
  Type: approval_request
  Action: deploying to production
  Message: Please approve or reject: deploying to production

Resuming with Command(resume={'approved': True})...

Execution completed!
  Tool result: Great! The approval request has been processed. The action **"deploying to production"** was **APPROVED**. You can now proceed with the production deployment.

​
最佳实践

​
始终使用检查点 (checkpointer)

人机协同需要一个检查点 (checkpointer) 来在中断和恢复之间持久化智能体状态 
from langgraph.checkpoint.memory import MemorySaver

checkpointer = MemorySaver()
agent = create_deep_agent(
    model="google_genai:gemini-3.1-pro-preview",
    tools=[...],
    interrupt_on={...},
    checkpointer=checkpointer  # Required for HITL
)

​
使用相同的线程 ID

恢复时，必须使用带有相同 thread_id 的相同配置 
# First call
config = {"configurable": {"thread_id": "my-thread"}}
result = agent.invoke(input, config=config, version="v2")

# Resume (use same config)
result = agent.invoke(Command(resume={...}), config=config, version="v2")

​
匹配决策顺序与动作

决策列表必须与 action_requests 的顺序相匹配 
if result.interrupts:
    interrupt_value = result.interrupts[0].value  
    action_requests = interrupt_value["action_requests"]

    # Create one decision per action, in order
    decisions = []
    for action in action_requests:
        decision = get_user_decision(action)  # Your logic
        decisions.append(decision)

    result = agent.invoke(
        Command(resume={"decisions": decisions}),
        config=config,
        version="v2",
    )

​
根据风险定制配置

根据风险等级配置不同的工具 
interrupt_on = {
    # High risk: full control (approve, edit, reject)
    "delete_file": {"allowed_decisions": ["approve", "edit", "reject"]},
    "send_email": {"allowed_decisions": ["approve", "edit", "reject"]},

    # Medium risk: no editing allowed
    "write_file": {"allowed_decisions": ["approve", "reject"]},

    # Low risk: no interrupts
    "read_file": False,
    "list_files": False,
}
将这些文档连接到 Claude、VSCode 等，以获得实时答案。
在 GitHub 上编辑此页面 或 提交问题。
© . This site is unofficial and not affiliated with LangChain, Inc.