> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# INVALID_CONCURRENT_GRAPH_UPDATE

LangGraph 的 [`StateGraph`](https://langchain-ai.github.io/langgraph/reference/graphs/#langgraph.graph.state.StateGraph) 收到了来自多个节点对其状态的并发更新，而该状态属性不支持此类操作。

这种情况可能发生在以下场景：你在图中使用了[扇出（fanout）](/oss/javascript/langgraph/use-graph-api#map-reduce-and-the-send-api)或其他并行执行逻辑，并且定义了类似这样的图：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { StateGraph, StateSchema, START } from "@langchain/langgraph";
import { z } from "zod/v4";  // [!code highlight]

const State = new StateSchema({
  someKey: z.string(),
});

const builder = new StateGraph(State)
  .addNode("node", (state) => {
    return { someKey: "some_string_value" };
  })
  .addNode("otherNode", (state) => {
    return { someKey: "some_string_value" };
  })
  .addEdge(START, "node")
  .addEdge(START, "otherNode");

const graph = builder.compile();
```

如果上述图中的某个节点返回 `{ someKey: "some_string_value" }`，这将用 `"some_string_value"` 覆盖 `someKey` 的状态值。
然而，如果在单个步骤中（例如在扇出操作中）有多个节点返回了 `someKey` 的值，图将抛出此错误，因为无法确定如何更新内部状态。

要解决此问题，你可以定义一个合并多个值的归约器（reducer）：

```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { StateSchema, ReducedValue } from "@langchain/langgraph";
import { z } from "zod/v4";

const State = new StateSchema({  // [!code highlight]
  someKey: new ReducedValue(  // [!code highlight]
    z.array(z.string()).default(() => []),  // [!code highlight]
    {
      inputSchema: z.array(z.string()),
      reducer: (existing, update) => existing.concat(update),  // [!code highlight]
    }
  ),
});
```

这将允许你定义逻辑，以处理从并行执行的多个节点返回的相同键。

## 故障排除

以下方法可能有助于解决此错误：

* 如果你的图并行执行节点，请确保已为相关的状态键定义了归约器。

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\oss\langgraph\errors\INVALID_CONCURRENT_GRAPH_UPDATE.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>