Skip to main content
某些工具操作可能比较敏感，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。

​
基础配置

interrupt_on 参数接受一个字典，将工具名称映射到中断配置。每个工具可以配置为：
  • True：启用中断，使用默认行为（允许批准、编辑、拒绝）
  • False：为此工具禁用中断
  • {"allowed_decisions": [...]}：自定义配置，指定允许的决策
import { tool } from "langchain";
import { createDeepAgent } from "deepagents";
import { MemorySaver } from "@langchain/langgraph";
import { z } from "zod";

const deleteFile = tool(
  async ({ path }: { path: string }) => {
    return `Deleted ${path}`;
  },
  {
    name: "delete_file",
    description: "Delete a file from the filesystem.",
    schema: z.object({
      path: z.string(),
    }),
  },
);

const readFile = tool(
  async ({ path }: { path: string }) => {
    return `Contents of ${path}`;
  },
  {
    name: "read_file",
    description: "Read a file from the filesystem.",
    schema: z.object({
      path: z.string(),
    }),
  },
);

const sendEmail = tool(
  async ({ to, subject, body }: { to: string; subject: string; body: string }) => {
    return `Sent email to ${to}`;
  },
  {
    name: "send_email",
    description: "Send an email.",
    schema: z.object({
      to: z.string(),
      subject: z.string(),
      body: z.string(),
    }),
  },
);

// Checkpointer is REQUIRED for human-in-the-loop
const checkpointer = new MemorySaver();

const agent = createDeepAgent({
  model: "claude-sonnet-4-6",
  tools: [deleteFile, readFile, sendEmail],
  interruptOn: {
    delete_file: true,  // Default: approve, edit, reject
    read_file: false,   // No interrupts needed
    send_email: { allowedDecisions: ["approve", "reject"] },  // No editing
  },
  checkpointer,  // Required!
});

​
决策类型

allowed_decisions 列表控制在审查工具调用时人工可以采取的操作：
  • "approve"：使用代理提议的原始参数执行工具
  • "edit"：在执行前修改工具参数
  • "reject"：完全跳过执行此工具调用
您可以为每个工具自定义可用的决策： 
const interruptOn = {
  // 敏感操作：允许所有选项
  delete_file: { allowedDecisions: ["approve", "edit", "reject"] },

  // 中等风险：仅允许批准或拒绝
  write_file: { allowedDecisions: ["approve", "reject"] },

  // 必须批准（不允许拒绝）
  critical_operation: { allowedDecisions: ["approve"] },
};

​
处理中断

当中断被触发时，代理会暂停执行并返回控制权。检查结果中是否有中断，并相应处理。 
import { v4 as uuidv4 } from "uuid";
import { Command } from "@langchain/langgraph";

// 创建包含 thread_id 的配置以持久化状态
const config = { configurable: { thread_id: uuidv4() } };

// 调用代理
let result = await agent.invoke({
  messages: [{ role: "user", content: "Delete the file temp.txt" }],
}, config);

// 检查执行是否被中断
if (result.__interrupt__) {
  // 提取中断信息
  const interrupts = result.__interrupt__[0].value;
  const actionRequests = interrupts.actionRequests;
  const reviewConfigs = interrupts.reviewConfigs;

  // 创建从工具名到审查配置的查找映射
  const configMap = Object.fromEntries(
    reviewConfigs.map((cfg) => [cfg.actionName, cfg])
  );

  // 向用户显示待处理的操作
  for (const action of actionRequests) {
    const reviewConfig = configMap[action.name];
    console.log(`Tool: ${action.name}`);
    console.log(`Arguments: ${JSON.stringify(action.args)}`);
    console.log(`Allowed decisions: ${reviewConfig.allowedDecisions}`);
  }

  // 获取用户决策（每个 actionRequest 一个，按顺序）
  const decisions = [
    { type: "approve" }  // 用户批准了删除操作
  ];

  // 使用决策恢复执行
  result = await agent.invoke(
    new Command({ resume: { decisions } }),
    config  // 必须使用相同的配置！
  );
}

// 处理最终结果
console.log(result.messages[result.messages.length - 1].content);

​
多个工具调用

当代理调用多个需要批准的工具时，所有中断会批量处理在一个中断中。您必须按顺序为每个工具提供决策。 
const config = { configurable: { thread_id: uuidv4() } };

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

if (result.__interrupt__) {
  const interrupts = result.__interrupt__[0].value;
  const actionRequests = interrupts.actionRequests;

  // 两个工具需要批准
  console.assert(actionRequests.length === 2);

  // 按与 actionRequests 相同的顺序提供决策
  const decisions = [
    { type: "approve" },  // 第一个工具：delete_file
    { type: "reject" }    # 第二个工具：send_email
  ];

  result = await agent.invoke(
    new Command({ resume: { decisions } }),
    config
  );
}

​
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.__interrupt__) {
  const interrupts = result.__interrupt__[0].value;
  const actionRequest = interrupts.actionRequests[0];

  // 来自代理的原始参数
  console.log(actionRequest.args);  // { to: "everyone@company.com", ... }

  // 用户决定编辑收件人
  const decisions = [{
    type: "edit",
    editedAction: {
      name: actionRequest.name,  // 必须包含工具名称
      args: { to: "team@company.com", subject: "...", body: "..." }
    }
  }];

  result = await agent.invoke(
    new Command({ resume: { decisions } }),
    config
  );
}

​
子代理中断

使用子代理时，您可以在工具调用时和工具调用内部使用中断。

​
工具调用时的中断

每个子代理可以有自己的 interrupt_on 配置，覆盖主代理的设置： 
const agent = createDeepAgent({
  tools: [deleteFile, readFile],
  interruptOn: {
    delete_file: true,
    read_file: false,
  },
  subagents: [{
    name: "file-manager",
    description: "Manages file operations",
    systemPrompt: "You are a file management assistant.",
    tools: [deleteFile, readFile],
    interruptOn: {
      // 覆盖：在此子代理中读取也需要批准
      delete_file: true,
      read_file: true,  // 与主代理不同！
    }
  }],
  checkpointer
});
当子代理触发中断时，处理方式相同——检查结果中的 interrupts 并使用 Command 恢复。

​
工具调用内部的中断

子代理工具可以直接调用 interrupt() 来暂停执行并等待批准： 
import { createAgent, tool } from "langchain";
import { ChatOpenAI } from "@langchain/openai";
import { HumanMessage } from "@langchain/core/messages";
import { MemorySaver, Command, interrupt } from "@langchain/langgraph";
import { createDeepAgent } from "deepagents";
import { z } from "zod";

const requestApproval = tool(
  async ({ actionDescription }: { actionDescription: string }) => {
    const approval = interrupt({
      type: "approval_request",
      action: actionDescription,
      message: `Please approve or reject: ${actionDescription}`,
    }) as { approved?: boolean; reason?: string };

    if (approval.approved) {
      return `Action '${actionDescription}' was APPROVED. Proceeding...`;
    } else {
      return `Action '${actionDescription}' was REJECTED. Reason: ${
        approval.reason || "No reason provided"
      }`;
    }
  },
  {
    name: "request_approval",
    description: "Request human approval before proceeding with an action.",
    schema: z.object({
      actionDescription: z
        .string()
        .describe("The action that requires approval"),
    }),
  }
);

async function main() {
  const checkpointer = new MemorySaver();
  const model = new ChatOpenAI({
    model: "gpt-4o-mini",
    maxTokens: 4096,
  });

  const compiledSubagent = createAgent({
    model: model,
    tools: [requestApproval],
    name: "approval-agent",
  });

  const parentAgent = await createDeepAgent({
    checkpointer: checkpointer,
    subagents: [
      {
        name: "approval-agent",
        description: "An agent that can request approvals",
        runnable: compiledSubagent as any,
      },
    ],
  });

  const threadId = "test_interrupt_directly";
  const config = { configurable: { thread_id: threadId } };

  console.log("Invoking agent - sub-agent will use request_approval tool...");

  let result = await parentAgent.invoke(
    {
      messages: [
        new 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
  );

  if (result.__interrupt__) {
    const interruptValue = result.__interrupt__[0].value as {
      type?: string;
      action?: string;
      message?: string;
    };
    console.log("\nInterrupt received!");
    console.log(`  Type: ${interruptValue.type}`);
    console.log(`  Action: ${interruptValue.action}`);
    console.log(`  Message: ${interruptValue.message}`);

    console.log("\nResuming with Command(resume={'approved': true})...");
    const result2 = await parentAgent.invoke(
      new Command({ resume: { approved: true } }),
      config
    );

    if (!result2.__interrupt__) {
      console.log("\nExecution completed!");
      // Find the tool response
      const toolMsgs = result2.messages?.filter((m) => m.type === "tool") || [];
      if (toolMsgs.length > 0) {
        const lastToolMsg = toolMsgs[toolMsgs.length - 1];
        console.log(`  Tool result: ${lastToolMsg.content}`);
      }
    } else {
      console.log("\nAnother interrupt occurred");
    }
  } else {
    console.log(
      "\n  No interrupt - the model may not have called request_approval"
    );
  }
}

main().catch(console.error);
运行时，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: Approval for "deploying to production" has been granted. You can proceed with the deployment.

​
最佳实践

​
始终使用检查点

人机协同需要一个检查点来在中断和恢复之间持久化代理状态：

​
使用相同的线程 ID

恢复时，必须使用具有相同 thread_id 的相同配置：

​
决策顺序与操作匹配

决策列表的顺序必须与 action_requests 的顺序匹配：

​
根据风险定制配置

根据风险级别配置不同的工具：
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.