> ## Documentation Index
> Fetch the complete documentation index at: https://nvd-54.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# 运行时
## 概述
LangChain 的 `createAgent` 底层运行在 LangGraph 的运行时之上。
LangGraph 暴露了一个 [`Runtime`](https://reference.langchain.com/javascript/langchain/index/Runtime) 对象，包含以下信息：
1. **上下文**：静态信息，如用户 ID、数据库连接或智能体调用的其他依赖
2. **存储**：一个用于[长期记忆](/oss/javascript/langchain/long-term-memory)的 [BaseStore](https://reference.langchain.com/javascript/langchain-core/stores/BaseStore) 实例
3. **流写入器**：一个用于通过 `"custom"` 流模式流式传输信息的对象
4. **执行信息**：当前执行的身份和重试信息（线程 ID、运行 ID、尝试次数）
5. **服务器信息**：在 LangGraph Server 上运行时的服务器特定元数据（助手 ID、图 ID、已认证用户）
运行时上下文是你在智能体中传递数据的方式。与其将数据存储在全局状态中，你可以将值——如数据库连接、用户会话或配置——附加到上下文中，并在工具和中间件中访问它们。这保持了无状态、可测试和可复用。
你可以在[工具](#在工具中)和[中间件](#在中间件中)中访问运行时信息。
## 访问
使用 `createAgent` 创建智能体时，你可以指定 `contextSchema` 来定义存储在智能体 [`Runtime`](https://reference.langchain.com/javascript/langchain/index/Runtime) 中的 `context` 的结构。
调用智能体时，传递带有相关运行配置的 `context` 参数：
```ts theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import * as z from "zod";
import { createAgent } from "langchain";
const contextSchema = z.object({ // [!code highlight]
userName: z.string(), // [!code highlight]
}); // [!code highlight]
const agent = createAgent({
model: "gpt-5.4",
tools: [
/* ... */
],
contextSchema, // [!code highlight]
});
const result = await agent.invoke(
{ messages: [{ role: "user", content: "What's my name?" }] },
{ context: { userName: "John Smith" } } // [!code highlight]
);
```
### 在工具中
你可以在工具中访问运行时信息以：
* 访问上下文
* 读写长期记忆
* 写入[自定义流](/oss/javascript/langchain/streaming#custom-updates)（例如工具进度/更新）
使用 `runtime` 参数访问工具中的 [`Runtime`](https://reference.langchain.com/javascript/langchain/index/Runtime) 对象。
```ts theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import * as z from "zod";
import { tool } from "langchain";
import { type ToolRuntime } from "@langchain/core/tools"; // [!code highlight]
const contextSchema = z.object({
userName: z.string(),
});
const fetchUserEmailPreferences = tool(
async (_, runtime: ToolRuntime) => { // [!code highlight]
const userName = runtime.context?.userName; // [!code highlight]
if (!userName) {
throw new Error("userName is required");
}
let preferences = "The user prefers you to write a brief and polite email.";
if (runtime.store) { // [!code highlight]
const memory = await runtime.store?.get(["users"], userName); // [!code highlight]
if (memory) {
preferences = memory.value.preferences;
}
}
return preferences;
},
{
name: "fetch_user_email_preferences",
description: "Fetch the user's email preferences.",
schema: z.object({}),
}
);
```
### 在工具中访问执行信息和服务器信息
通过 `runtime.executionInfo` 访问执行身份（线程 ID、运行 ID），通过 `runtime.serverInfo` 在 LangGraph Server 上运行时访问服务器特定元数据（助手 ID、已认证用户）：
```ts theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { tool } from "langchain";
import * as z from "zod";
const contextAwareTool = tool(
async (_input, runtime) => {
// 访问线程和运行 ID
const info = runtime.executionInfo;
console.log(`Thread: ${info.threadId}, Run: ${info.runId}`); // [!code highlight]
// 访问服务器信息（仅在 LangGraph Server 上可用）
const server = runtime.serverInfo;
if (server != null) {
console.log(`Assistant: ${server.assistantId}`); // [!code highlight]
if (server.user != null) {
console.log(`User: ${server.user.identity}`); // [!code highlight]
}
}
return "done";
},
{
name: "context_aware_tool",
description: "A tool that uses execution and server info.",
schema: z.object({}),
}
);
```
`serverInfo` 在非 LangGraph Server 环境（例如本地开发）下为 `null`。
需要 `deepagents>=1.9.0`（或 `@langchain/langgraph>=1.2.8`）以使用 `runtime.executionInfo` 和 `runtime.serverInfo`。
### 在中间件中
你可以在中间件中访问运行时信息，以创建动态提示、修改消息或根据用户上下文控制智能体行为。
使用 `runtime` 参数访问中间件中的 [`Runtime`](https://reference.langchain.com/javascript/langchain/index/Runtime) 对象。
```ts theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import * as z from "zod";
import { createAgent, createMiddleware, SystemMessage } from "langchain";
const contextSchema = z.object({
userName: z.string(),
});
// 动态提示中间件
const dynamicPromptMiddleware = createMiddleware({
name: "DynamicPrompt",
contextSchema,
beforeModel: (state, runtime) => { // [!code highlight]
const userName = runtime.context?.userName; // [!code highlight]
if (!userName) {
throw new Error("userName is required");
}
const systemMsg = `You are a helpful assistant. Address the user as ${userName}.`;
return {
messages: [new SystemMessage(systemMsg), ...state.messages],
};
},
});
// 日志中间件
const loggingMiddleware = createMiddleware({
name: "Logging",
contextSchema,
beforeModel: (state, runtime) => { // [!code highlight]
console.log(`Processing request for user: ${runtime.context?.userName}`); // [!code highlight]
return;
},
afterModel: (state, runtime) => { // [!code highlight]
console.log(`Completed request for user: ${runtime.context?.userName}`); // [!code highlight]
return;
},
});
const agent = createAgent({
model: "gpt-5.4",
tools: [
/* ... */
],
middleware: [dynamicPromptMiddleware, loggingMiddleware], // [!code highlight]
contextSchema,
});
const result = await agent.invoke(
{ messages: [{ role: "user", content: "What's my name?" }] },
{ context: { userName: "John Smith" } }
);
```
### 在中间件中访问执行信息和服务器信息
中间件钩子也可以访问 `runtime.executionInfo` 和 `runtime.serverInfo`：
```ts theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import { createMiddleware } from "langchain";
const authGate = createMiddleware({
name: "AuthGate",
beforeModel: (state, runtime) => {
const server = runtime.serverInfo;
if (server != null && server.user == null) { // [!code highlight]
throw new Error("Authentication required");
}
console.log(`Thread: ${runtime.executionInfo.threadId}`); // [!code highlight]
return;
},
});
```
需要 `deepagents>=1.9.0`（或 `@langchain/langgraph>=1.2.8`）。
***
[将这些文档连接](/use-these-docs)到 Claude、VSCode 等，通过 MCP 获取实时答案。
[在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/langchain/runtime.mdx)或[提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。