langgraph-human-in-the-loop

LangGraph 的人机协作模式可让你暂停图执行、向用户展示数据，并根据其输入恢复执行：

• interrupt(value) — 暂停执行，并向调用方展示一个值
• Command(resume=value) — 恢复执行，并将该值传回 interrupt()
• 检查点保存器 — 暂停时保存状态所必需
• 线程 ID — 标识要恢复的暂停执行所必需

---

要求

要使中断正常工作，需要满足以下三项：

1. 检查点保存器 — 使用 checkpointer=InMemorySaver()（开发环境）或 PostgresSaver（生产环境）进行编译
2. 线程 ID — 每次调用 invoke/stream 时都传入 {"configurable": {"thread_id": "..."}}
3. 可序列化为 JSON 的负载 — 传入 interrupt() 的值必须可序列化为 JSON

---

基本中断与恢复

interrupt(value) 会暂停图执行。该值会显示在结果的 __interrupt__ 字段下。Command(resume=value) 会恢复执行，恢复值会成为 interrupt() 的返回值。

关键：图恢复执行时，节点会从开头重新运行——interrupt() 之前的所有代码都会再次运行。

暂停执行以供人工审核，并使用 Command 恢复执行。 ```python from langgraph.types import interrupt, Command from langgraph.checkpoint.memory import InMemorySaver from langgraph.graph import StateGraph, START, END from typing_extensions import TypedDict

class State(TypedDict): approved: bool

def approval_node(state: State): # Pause and ask for approval approved = interrupt("Do you approve this action?") # When resumed, Command(resume=...) returns that value here return {"approved": approved}

checkpointer = InMemorySaver() graph = ( StateGraph(State) .add_node("approval", approval_node) .add_edge(START, "approval") .add_edge("approval", END) .compile(checkpointer=checkpointer) )

config = {"configurable": {"thread_id": "thread-1"}}

Initial run — hits interrupt and pauses

result = graph.invoke({"approved": False}, config) print(result["interrupt"])

[Interrupt(value='Do you approve this action?')]

Resume with the human's response

result = graph.invoke(Command(resume=True), config) print(result["approved"]) # True

</python>
<typescript>
暂停执行以供人工审核，并使用 Command 恢复执行。
```typescript
import { interrupt, Command, MemorySaver, StateGraph, StateSchema, START, END } from "@langchain/langgraph";
import { z } from "zod";

const State = new StateSchema({
  approved: z.boolean().default(false),
});

const approvalNode = async (state: typeof State.State) => {
  // Pause and ask for approval
  const approved = interrupt("Do you approve this action?");
  // When resumed, Command({ resume }) returns that value here
  return { approved };
};

const checkpointer = new MemorySaver();
const graph = new StateGraph(State)
  .addNode("approval", approvalNode)
  .addEdge(START, "approval")
  .addEdge("approval", END)
  .compile({ checkpointer });

const config = { configurable: { thread_id: "thread-1" } };

// Initial run — hits interrupt and pauses
let result = await graph.invoke({ approved: false }, config);
console.log(result.__interrupt__);
// [{ value: 'Do you approve this action?', ... }]

// Resume with the human's response
result = await graph.invoke(new Command({ resume: true }), config);
console.log(result.approved);  // true

---

审批工作流

一种常见模式：通过中断展示草稿，然后根据人工决定进行路由。

中断以供人工审核，然后根据决定路由至发送或结束。 ```python from langgraph.types import interrupt, Command from langgraph.graph import StateGraph, START, END from typing import Literal from typing_extensions import TypedDict

class EmailAgentState(TypedDict): email_content: str draft_response: str classification: dict

def human_review(state: EmailAgentState) -> Command[Literal["send_reply", "end"]]: """Pause for human review using interrupt and route based on decision.""" classification = state.get("classification", {})

# interrupt() must come first — any code before it will re-run on resume
human_decision = interrupt({
    "email_id": state.get("email_content", ""),
    "draft_response": state.get("draft_response", ""),
    "urgency": classification.get("urgency"),
    "action": "Please review and approve/edit this response"
})

# Process the human's decision
if human_decision.get("approved"):
    return Command(
        update={"draft_response": human_decision.get("edited_response", state.get("draft_response", ""))},
        goto="send_reply"
    )
else:
    # Rejection — human will handle directly
    return Command(update={}, goto=END)

</python>
<typescript>
中断以供人工审核，然后根据决定路由至发送或结束。
```typescript
import { interrupt, Command, END, GraphNode } from "@langchain/langgraph";

const humanReview: GraphNode<typeof EmailAgentState> = async (state) => {
  const classification = state.classification!;

  // interrupt() must come first — any code before it will re-run on resume
  const humanDecision = interrupt({
    emailId: state.emailContent,
    draftResponse: state.responseText,
    urgency: classification.urgency,
    action: "Please review and approve/edit this response",
  });

  // Process the human's decision
  if (humanDecision.approved) {
    return new Command({
      update: { responseText: humanDecision.editedResponse || state.responseText },
      goto: "sendReply",
    });
  } else {
    return new Command({ update: {}, goto: END });
  }
};

---

验证循环

在循环中使用 interrupt() 验证人工输入；如果输入无效，则重新提示。

在循环中验证人工输入，并在输入有效前持续重新提示。 ```python from langgraph.types import interrupt

def get_age_node(state): prompt = "What is your age?"

while True:
    answer = interrupt(prompt)

    # Validate the input
    if isinstance(answer, int) and answer > 0:
        break
    else:
        # Invalid input — ask again with a more specific prompt
        prompt = f"'{answer}' is not a valid age. Please enter a positive number."

return {"age": answer}

每次调用 `Command(resume=...)` 都会提供下一个答案。如果答案无效，循环会再次中断，并显示更清晰的提示。
```python
config = {"configurable": {"thread_id": "form-1"}}
first = graph.invoke({"age": None}, config)
# __interrupt__: "What is your age?"

retry = graph.invoke(Command(resume="thirty"), config)
# __interrupt__: "'thirty' is not a valid age..."

final = graph.invoke(Command(resume=30), config)
print(final["age"])  # 30

在循环中验证人工输入，并在输入有效前持续重新提示。 ```typescript import { interrupt } from "@langchain/langgraph";

const getAgeNode = (state: typeof State.State) => { let prompt = "What is your age?";

while (true) { const answer = interrupt(prompt);

// Validate the input
if (typeof answer === "number" && answer > 0) {
  return { age: answer };
} else {
  // Invalid input — ask again with a more specific prompt
  prompt = `'${answer}' is not a valid age. Please enter a positive number.`;
}

} };

</typescript>
</ex-validation-loop>

---

## 多个中断

当多个并行分支各自调用 `interrupt()` 时，可在一次调用中通过将每个中断 ID 映射到其恢复值，一并恢复所有分支。

<ex-multiple-interrupts>
<python>
通过将中断 ID 映射到相应的值，恢复多个并行中断。
```python
from typing import Annotated, TypedDict
import operator
from langgraph.checkpoint.memory import InMemorySaver
from langgraph.graph import START, END, StateGraph
from langgraph.types import Command, interrupt

class State(TypedDict):
    vals: Annotated[list[str], operator.add]

def node_a(state):
    answer = interrupt("question_a")
    return {"vals": [f"a:{answer}"]}

def node_b(state):
    answer = interrupt("question_b")
    return {"vals": [f"b:{answer}"]}

graph = (
    StateGraph(State)
    .add_node("a", node_a)
    .add_node("b", node_b)
    .add_edge(START, "a")
    .add_edge(START, "b")
    .add_edge("a", END)
    .add_edge("b", END)
    .compile(checkpointer=InMemorySaver())
)

config = {"configurable": {"thread_id": "1"}}

# Both parallel nodes hit interrupt() and pause
result = graph.invoke({"vals": []}, config)
# result["__interrupt__"] contains both Interrupt objects with IDs

# Resume all pending interrupts at once using a map of id -> value
resume_map = {
    i.id: f"answer for {i.value}"
    for i in result["__interrupt__"]
}
result = graph.invoke(Command(resume=resume_map), config)
# result["vals"] = ["a:answer for question_a", "b:answer for question_b"]

通过将中断 ID 映射到相应的值，恢复多个并行中断。 ```typescript import { Command, END, MemorySaver, START, StateGraph, interrupt, isInterrupted, INTERRUPT, Annotation } from "@langchain/langgraph";

const State = Annotation.Root({ vals: Annotation<string[]>({ reducer: (left, right) => left.concat(Array.isArray(right) ? right : [right]), default: () => [], }), });

function nodeA(_state: typeof State.State) { const answer = interrupt("question_a") as string; return { vals: [a:${answer}] }; }

function nodeB(_state: typeof State.State) { const answer = interrupt("question_b") as string; return { vals: [b:${answer}] }; }

const graph = new StateGraph(State) .addNode("a", nodeA) .addNode("b", nodeB) .addEdge(START, "a") .addEdge(START, "b") .addEdge("a", END) .addEdge("b", END) .compile({ checkpointer: new MemorySaver() });

const config = { configurable: { thread_id: "1" } };

const interruptedResult = await graph.invoke({ vals: [] }, config);

// Resume all pending interrupts at once const resumeMap: Record<string, string> = {}; if (isInterrupted(interruptedResult)) { for (const i of interruptedResult[INTERRUPT]) { if (i.id != null) { resumeMap[i.id] = answer for ${i.value}; } } } const result = await graph.invoke(new Command({ resume: resumeMap }), config); // result.vals = ["a:answer for question_a", "b:answer for question_b"]

</typescript>
</ex-multiple-interrupts>

对于用户可修复的错误，可使用 `interrupt()` 暂停执行并收集缺失数据——本技能介绍的就是这种模式。有关完整的 4 层错误处理策略（RetryPolicy、Command 错误循环等），请参阅 **fundamentals** 技能。

---

## 中断前的副作用必须具备幂等性

图恢复执行时，节点会从**开头**重新运行——`interrupt()` 之前的所有代码都会再次运行。在子图中，父节点和子图节点都会重新执行。

<idempotency-rules>

**应该：**
- 在 `interrupt()` 之前使用 **upsert** 操作（而非 insert）
- 使用**创建前检查**模式
- 尽可能将副作用放在 `interrupt()` **之后**
- 将副作用拆分到独立节点中

**不要：**
- 在 `interrupt()` 之前创建新记录——每次恢复都会产生重复记录
- 在 `interrupt()` 之前向列表追加内容——每次恢复都会产生重复条目

</idempotency-rules>

<ex-idempotent-patterns>
<python>
中断前的幂等操作与非幂等操作（错误示例）。
```python
# GOOD: Upsert is idempotent — safe before interrupt
def node_a(state: State):
    db.upsert_user(user_id=state["user_id"], status="pending_approval")
    approved = interrupt("Approve this change?")
    return {"approved": approved}

# GOOD: Side effect AFTER interrupt — only runs once
def node_a(state: State):
    approved = interrupt("Approve this change?")
    if approved:
        db.create_audit_log(user_id=state["user_id"], action="approved")
    return {"approved": approved}

# BAD: Insert creates duplicates on each resume!
def node_a(state: State):
    audit_id = db.create_audit_log({  # Runs again on resume!
        "user_id": state["user_id"],
        "action": "pending_approval",
    })
    approved = interrupt("Approve this change?")
    return {"approved": approved}

中断前的幂等操作与非幂等操作（错误示例）。 ```typescript // GOOD: Upsert is idempotent — safe before interrupt const nodeA = async (state: typeof State.State) => { await db.upsertUser({ userId: state.userId, status: "pending_approval" }); const approved = interrupt("Approve this change?"); return { approved }; };

// GOOD: Side effect AFTER interrupt — only runs once const nodeA = async (state: typeof State.State) => { const approved = interrupt("Approve this change?"); if (approved) { await db.createAuditLog({ userId: state.userId, action: "approved" }); } return { approved }; };

// BAD: Insert creates duplicates on each resume! const nodeA = async (state: typeof State.State) => { await db.createAuditLog({ // Runs again on resume! userId: state.userId, action: "pending_approval", }); const approved = interrupt("Approve this change?"); return { approved }; };

</typescript>
</ex-idempotent-patterns>

<subgraph-interrupt-re-execution>
### 恢复时重新执行子图

当子图中包含 `interrupt()` 时，恢复操作会重新执行父节点（调用子图的节点）和子图节点（调用 `interrupt()` 的节点）：

<python>
```python
def node_in_parent_graph(state: State):
    some_code()  # <-- Re-executes on resume
    subgraph_result = subgraph.invoke(some_input)
    # ...

def node_in_subgraph(state: State):
    some_other_code()  # <-- Also re-executes on resume
    result = interrupt("What's your name?")
    # ...

```typescript async function nodeInParentGraph(state: State) { someCode(); // <-- Re-executes on resume const subgraphResult = await subgraph.invoke(someInput); // ... }

async function nodeInSubgraph(state: State) { someOtherCode(); // <-- Also re-executes on resume const result = interrupt("What's your name?"); // ... }

</typescript>
</subgraph-interrupt-re-execution>

---

## Command(resume) 警告

`Command(resume=...)` 是唯一适合作为 `invoke()`/`stream()` 输入的 Command 模式。切勿将 `Command(update=...)` 作为输入传入——它会从最新检查点恢复，导致图看起来卡住。完整的反模式说明请参阅 fundamentals 技能。

---

## 修复方法

<fix-checkpointer-required-for-interrupts>
<python>
中断功能需要检查点保存器。
```python
# WRONG
graph = builder.compile()

# CORRECT
graph = builder.compile(checkpointer=InMemorySaver())

中断功能需要检查点保存器。 ```typescript // WRONG const graph = builder.compile();

// CORRECT const graph = builder.compile({ checkpointer: new MemorySaver() });

</typescript>
</fix-checkpointer-required-for-interrupts>

<fix-resume-with-command>
<python>
使用 Command 从中断处恢复（普通字典会重新启动图）。
```python
# WRONG
graph.invoke({"resume_data": "approve"}, config)

# CORRECT
graph.invoke(Command(resume="approve"), config)

使用 Command 从中断处恢复（普通对象会重新启动图）。 ```typescript // WRONG await graph.invoke({ resumeData: "approve" }, config);

// CORRECT await graph.invoke(new Command({ resume: "approve" }), config);

</typescript>
</fix-resume-with-command>

<boundaries>
### 请勿执行以下操作

- 在没有检查点保存器的情况下使用中断——这会失败
- 使用不同的 thread_id 恢复——这会新建线程，而不是恢复原线程
- 将 `Command(update=...)` 作为 invoke 输入传入——图看起来会卡住（请使用普通字典）
- 在 `interrupt()` 之前执行非幂等副作用——恢复时会产生重复操作
- 认为 `interrupt()` 之前的代码只会运行一次——每次恢复时都会重新运行
</boundaries>