短期记忆 - Docs by LangChain中文

概览

Memory 是一个记住先前交互信息的系统。对于 AI 代理，memory 至关重要，因为它让代理能够记住先前交互、从反馈中学习，并适应用户偏好。随着代理处理包含大量用户交互的更复杂任务，这种能力对效率和用户满意度都变得必不可少。短期记忆让你的应用能够记住单个线程或对话中的先前交互。

线程会组织会话中的多次交互，类似电子邮件将消息分组到单个对话中的方式。

对话历史是最常见的短期记忆形式。长对话会给当今的 LLM 带来挑战；完整历史可能无法放入 LLM 的上下文窗口，从而导致上下文丢失或错误。即使你的模型支持完整上下文长度，大多数 LLM 在长上下文中表现仍然较差。它们会被陈旧或偏离主题的内容“分心”，同时响应更慢、成本更高。聊天模型使用 messages 接收上下文，其中包括指令（system message）和输入（human messages）。在聊天应用中，消息会在人类输入和模型响应之间交替，形成一个随时间增长的消息列表。由于上下文窗口有限，许多应用可以受益于移除或“遗忘”陈旧信息的技术。

需要跨对话记住信息？使用 long-term memory 在不同线程和会话之间存储并召回用户特定或应用级数据。

用法

要向代理添加短期记忆（线程级持久化），需要在创建代理时指定 checkpointer。

LangChain 的代理会将短期记忆作为代理状态的一部分进行管理。通过将这些内容存储在图状态中，代理可以访问给定对话的完整上下文，同时保持不同线程之间的隔离。状态会使用 checkpointer 持久化到数据库（或内存）中，因此线程可以随时恢复。当代理被调用或某个步骤（例如工具调用）完成时，短期记忆会更新，并且每个步骤开始时都会读取状态。

import { createAgent, tool } from "langchain";
import { MemorySaver } from "@langchain/langgraph";
import * as z from "zod";

const getUserInfo = tool(() => "No user profile on file.", {
  name: "get_user_info",
  description: "Look up information about the current user.",
  schema: z.object({}),
});

const checkpointer = new MemorySaver();

const agent = createAgent({
  model: "google-genai:gemini-3.5-flash",
  tools: [getUserInfo],
  checkpointer,
});

const threadConfig = { configurable: { thread_id: "1" } };
let result = await agent.invoke(
  { messages: [{ role: "user", content: "Hi! My name is Bob." }] },
  threadConfig,
);
let response = result.messages.at(-1)?.content;
console.log(response); // "Hi Bob! Nice to see you here. How are you doing?"

result = await agent.invoke(
  { messages: [{ role: "user", content: "What's my name?" }] },
  threadConfig,
);
response = result.messages.at(-1)?.content;
console.log(response); // "You are Bob!"

在生产环境中

在生产环境中，使用由数据库支持的 checkpointer：

import { PostgresSaver } from "@langchain/langgraph-checkpoint-postgres";

const DB_URI = "postgresql://postgres:postgres@localhost:5432/postgres?sslmode=disable";
const checkpointer = PostgresSaver.fromConnString(DB_URI);

如需更多 checkpointer 选项，包括 SQLite、Postgres 和 Azure Cosmos DB，请参阅 Persistence 文档中的 checkpointer libraries 列表。

自定义代理记忆

可以通过创建带有状态 schema 的自定义 middleware 来扩展代理状态。自定义状态 schemas 可以通过 middleware 中的 stateSchema 参数传入。建议使用 StateSchema 类定义状态（也支持普通 Zod 对象）。

import { createAgent, createMiddleware } from "langchain";
import { StateSchema, MemorySaver } from "@langchain/langgraph";
import * as z from "zod";

const CustomState = new StateSchema({
    userId: z.string(),
    preferences: z.record(z.string(), z.any()),
});

const stateExtensionMiddleware = createMiddleware({
    name: "StateExtension",
    stateSchema: CustomState,
});

const checkpointer = new MemorySaver();
const agent = createAgent({
    model: "gpt-5.5",
    tools: [],
    middleware: [stateExtensionMiddleware],
    checkpointer,
});

// Custom state can be passed in invoke
const result = await agent.invoke({
    messages: [{ role: "user", content: "Hello" }],
    userId: "user_123",
    preferences: { theme: "dark" },
});

常见模式

启用短期记忆后，长对话可能超过 LLM 的上下文窗口。常见解决方案包括：

裁剪消息

移除最前或最后 N 条消息（在调用 LLM 前）

删除消息

从 LangGraph 状态中永久删除消息

总结消息

总结历史中的较早消息，并用摘要替换它们

自定义策略

自定义策略（例如消息过滤等）

这让代理能够跟踪对话，同时不超过 LLM 的上下文窗口。

裁剪消息

大多数 LLM 都有最大支持上下文窗口（以 tokens 计）。决定何时截断消息的一种方法是统计消息历史中的 tokens，并在接近限制时截断。如果你使用 LangChain，可以使用 trim messages 工具，并指定要从列表中保留的 token 数，以及用于处理边界的 strategy（例如保留最后 maxTokens）。要在代理中裁剪消息历史，请使用带 beforeModel hook 的 createMiddleware：

import { RemoveMessage } from "@langchain/core/messages";
import { createAgent, createMiddleware } from "langchain";
import { MemorySaver, REMOVE_ALL_MESSAGES } from "@langchain/langgraph";

const trimMessages = createMiddleware({
  name: "TrimMessages",
  beforeModel: (state) => {
    const messages = state.messages;

    if (messages.length <= 3) {
      return; // No changes needed
    }

    const firstMsg = messages[0];
    const recentMessages =
      messages.length % 2 === 0 ? messages.slice(-3) : messages.slice(-4);
    const newMessages = [firstMsg, ...recentMessages];

    return {
      messages: [
        new RemoveMessage({ id: REMOVE_ALL_MESSAGES }),
        ...newMessages,
      ],
    };
  },
});

const checkpointer = new MemorySaver();
const agent = createAgent({
  model: "gpt-5.5",
  tools: [...],
  middleware: [trimMessages],
  checkpointer,
});

删除消息

可以从图状态中删除消息来管理消息历史。当你想移除特定消息或清空整个消息历史时，这很有用。要从图状态中删除消息，可以使用 RemoveMessage。要让 RemoveMessage 工作，需要使用带 messagesStateReducer reducer 的状态键，例如 MessagesValue。要移除特定消息：

import { RemoveMessage } from "@langchain/core/messages";

const deleteMessages = (state) => {
    const messages = state.messages;
    if (messages.length > 2) {
        // remove the earliest two messages
        return {
        messages: messages
            .slice(0, 2)
            .map((m) => new RemoveMessage({ id: m.id })),
        };
    }
};

删除消息时，务必确保生成的消息历史有效。检查所用 LLM provider 的限制。例如：

有些 providers 要求消息历史以 user 消息开始
大多数 providers 要求带工具调用的 assistant 消息后面跟着对应的 tool 结果消息。

import { RemoveMessage } from "@langchain/core/messages";
import { createAgent, createMiddleware } from "langchain";
import { MemorySaver } from "@langchain/langgraph";

const deleteOldMessages = createMiddleware({
  name: "DeleteOldMessages",
  afterModel: (state) => {
    const messages = state.messages;
    if (messages.length > 2) {
      // remove the earliest two messages
      return {
        messages: messages
          .slice(0, 2)
          .map((m) => new RemoveMessage({ id: m.id! })),
      };
    }
    return;
  },
});

const agent = createAgent({
  model: "gpt-5.5",
  tools: [],
  systemPrompt: "Please be concise and to the point.",
  middleware: [deleteOldMessages],
  checkpointer: new MemorySaver(),
});

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

const streamA = await agent.stream(
  { messages: [{ role: "user", content: "hi! I'm bob" }] },
  { ...config, streamMode: "values" }
);
for await (const event of streamA) {
  const messageDetails = event.messages.map((message) => [
    message.getType(),
    message.content,
  ]);
  console.log(messageDetails);
}

const streamB = await agent.stream(
  { messages: [{ role: "user", content: "write a short poem about cats" }] },
  { ...config, streamMode: "values" }
);
for await (const event of streamB) {
  const messageDetails = event.messages.map((message) => [
    message.getType(),
    message.content,
  ]);
  console.log(messageDetails);
}

const streamC = await agent.stream(
  { messages: [{ role: "user", content: "what's my name?" }] },
  { ...config, streamMode: "values" }
);
for await (const event of streamC) {
  const messageDetails = event.messages.map((message) => [
    message.getType(),
    message.content,
  ]);
  console.log(messageDetails);
}

[["human", "hi! I'm bob"]]
[["human", "hi! I'm bob"], ["ai", "Hi Bob! Nice to meet you. How can I help you today? I can answer questions, brainstorm ideas, draft text, explain things, or help with code."]]
[["human", "hi! I'm bob"], ["ai", "Hi Bob! Nice to meet you. How can I help you today? I can answer questions, brainstorm ideas, draft text, explain things, or help with code."], ["human", "write a short poem about cats"]]
[["human", "hi! I'm bob"], ["ai", "Hi Bob! Nice to meet you. How can I help you today? I can answer questions, brainstorm ideas, draft text, explain things, or help with code."], ["human", "write a short poem about cats"], ["ai", "There once was a cat on a wall, Who barely moved at all..."]]
[["human", "write a short poem about cats"], ["ai", "There once was a cat on a wall, Who barely moved at all..."]]
[["human", "write a short poem about cats"], ["ai", "There once was a cat on a wall, Who barely moved at all..."], ["human", "what's my name?"]]
[["human", "write a short poem about cats"], ["ai", "There once was a cat on a wall, Who barely moved at all..."], ["human", "what's my name?"], ["ai", "I don't know your name - you haven't told me!"]]
[["human", "what's my name?"], ["ai", "I don't know your name - you haven't told me!"]]

总结消息

如上所示，裁剪或移除消息的问题在于，你可能会因为削减消息队列而丢失信息。因此，一些应用可以受益于更复杂的方法：使用聊天模型总结消息历史。 Summary

要在代理中总结消息历史，请使用内置 summarizationMiddleware：

import { createAgent, summarizationMiddleware } from "langchain";
import { MemorySaver } from "@langchain/langgraph";

const checkpointer = new MemorySaver();

const agent = createAgent({
  model: "gpt-5.5",
  tools: [],
  middleware: [
    summarizationMiddleware({
      model: "gpt-5.4-mini",
      trigger: { tokens: 4000 },
      keep: { messages: 20 },
    }),
  ],
  checkpointer,
});

const config = { configurable: { thread_id: "1" } };
await agent.invoke({ messages: "hi, my name is bob" }, config);
await agent.invoke({ messages: "write a short poem about cats" }, config);
await agent.invoke({ messages: "now do the same but for dogs" }, config);
const finalResponse = await agent.invoke({ messages: "what's my name?" }, config);

console.log(finalResponse.messages.at(-1)?.content);
// Your name is Bob!

更多配置选项请参阅 summarizationMiddleware。

访问 memory

可以通过多种方式访问和修改代理的短期记忆（状态）：

Tools

在工具中读取短期记忆

在工具中使用 runtime 参数（类型为 ToolRuntime）访问短期记忆（状态）。 runtime 参数对工具签名隐藏（因此模型看不到它），但工具可以通过它访问状态。

import { createAgent, tool, type ToolRuntime } from "langchain";
import { StateSchema } from "@langchain/langgraph";
import * as z from "zod";

const CustomState = new StateSchema({
  userId: z.string(),
});

const getUserInfo = tool(
  async (_, config: ToolRuntime<typeof CustomState.State>) => {
    const userId = config.state.userId;
    return userId === "user_123" ? "John Doe" : "Unknown User";
  },
  {
    name: "get_user_info",
    description: "Get user info",
    schema: z.object({}),
  }
);

const agent = createAgent({
  model: "gpt-5-nano",
  tools: [getUserInfo],
  stateSchema: CustomState,
});

const result = await agent.invoke(
  {
    messages: [{ role: "user", content: "what's my name?" }],
    userId: "user_123",
  },
  {
    context: {},
  }
);

console.log(result.messages.at(-1)?.content);
// Outputs: "Your name is John Doe."

从工具写入短期记忆

要在执行期间修改代理的短期记忆（状态），可以直接从工具返回状态更新。这适合持久化中间结果，或让后续工具或 prompts 可以访问某些信息。

import { tool, createAgent, ToolMessage, type ToolRuntime } from "langchain";
import { Command, StateSchema } from "@langchain/langgraph";
import * as z from "zod";

const CustomState = new StateSchema({
  userId: z.string().optional(),
});

const updateUserInfo = tool(
  async (_, config: ToolRuntime<typeof CustomState.State>) => {
    const userId = config.state.userId;
    const name = userId === "user_123" ? "John Smith" : "Unknown user";
    return new Command({
      update: {
        userName: name,
        // update the message history
        messages: [
          new ToolMessage({
            content: "Successfully looked up user information",
            tool_call_id: config.toolCall?.id ?? "",
          }),
        ],
      },
    });
  },
  {
    name: "update_user_info",
    description: "Look up and update user info.",
    schema: z.object({}),
  }
);

const greet = tool(
  async (_, config) => {
    const userName = config.context?.userName;
    return `Hello ${userName}!`;
  },
  {
    name: "greet",
    description: "Use this to greet the user once you found their info.",
    schema: z.object({}),
  }
);

const agent = createAgent({
  model: "openai:gpt-5-mini",
  tools: [updateUserInfo, greet],
  stateSchema: CustomState,
});

const result = await agent.invoke({
  messages: [{ role: "user", content: "greet the user" }],
  userId: "user_123",
});

console.log(result.messages.at(-1)?.content);
// Output: "Hello! I’m here to help — what would you like to do today?"

Prompt

在 middleware 中访问短期记忆（状态），以基于对话历史或自定义状态字段创建动态 prompts。

import * as z from "zod";
import { createAgent, tool, dynamicSystemPromptMiddleware } from "langchain";

const contextSchema = z.object({
  userName: z.string(),
});
type ContextSchema = z.infer<typeof contextSchema>;

const getWeather = tool(
  async ({ city }) => {
    return `The weather in ${city} is always sunny!`;
  },
  {
    name: "get_weather",
    description: "Get user info",
    schema: z.object({
      city: z.string(),
    }),
  }
);

const agent = createAgent({
  model: "gpt-5-nano",
  tools: [getWeather],
  contextSchema,
  middleware: [
    dynamicSystemPromptMiddleware<ContextSchema>((_, config) => {
      return `You are a helpful assistant. Address the user as ${config.context?.userName}.`;
    }),
  ],
});

const result = await agent.invoke(
  {
    messages: [{ role: "user", content: "What is the weather in SF?" }],
  },
  {
    context: {
      userName: "John Smith",
    },
  }
);

for (const message of result.messages) {
  console.log(message);
}
/**
 * HumanMessage {
 *   "content": "What is the weather in SF?",
 *   // ...
 * }
 * AIMessage {
 *   // ...
 *   "tool_calls": [
 *     {
 *       "name": "get_weather",
 *       "args": {
 *         "city": "San Francisco"
 *       },
 *       "type": "tool_call",
 *       "id": "call_tCidbv0apTpQpEWb3O2zQ4Yx"
 *     }
 *   ],
 *   // ...
 * }
 * ToolMessage {
 *   "content": "The weather in San Francisco is always sunny!",
 *   "tool_call_id": "call_tCidbv0apTpQpEWb3O2zQ4Yx"
 *   // ...
 * }
 * AIMessage {
 *   "content": "John Smith, here's the latest: The weather in San Francisco is always sunny!\n\nIf you'd like more details (temperature, wind, humidity) or a forecast for the next few days, I can pull that up. What would you like?",
 *   // ...
 * }
 */

Before model

import { RemoveMessage } from "@langchain/core/messages";
import { createAgent, createMiddleware, trimMessages } from "langchain";
import { MemorySaver } from "@langchain/langgraph";
import { REMOVE_ALL_MESSAGES } from "@langchain/langgraph";

const trimMessageHistory = createMiddleware({
  name: "TrimMessages",
  beforeModel: async (state) => {
    const trimmed = await trimMessages(state.messages, {
      maxTokens: 384,
      strategy: "last",
      startOn: "human",
      endOn: ["human", "tool"],
      tokenCounter: (msgs) => msgs.length,
    });
    return {
      messages: [new RemoveMessage({ id: REMOVE_ALL_MESSAGES }), ...trimmed],
    };
  },
});

const checkpointer = new MemorySaver();
const agent = createAgent({
  model: "gpt-5-nano",
  tools: [],
  middleware: [trimMessageHistory],
  checkpointer,
});

After model

import { RemoveMessage } from "@langchain/core/messages";
import { createAgent, createMiddleware } from "langchain";
import { REMOVE_ALL_MESSAGES } from "@langchain/langgraph";

const validateResponse = createMiddleware({
  name: "ValidateResponse",
  afterModel: (state) => {
    const lastMessage = state.messages.at(-1)?.content;
    if (
      typeof lastMessage === "string" &&
      lastMessage.toLowerCase().includes("confidential")
    ) {
      return {
        messages: [
          new RemoveMessage({ id: REMOVE_ALL_MESSAGES }),
        ],
      };
    }
    return;
  },
});

const agent = createAgent({
  model: "gpt-5-nano",
  tools: [],
  middleware: [validateResponse],
});

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.

​概览

​用法

​在生产环境中

​自定义代理记忆

​常见模式

裁剪消息

删除消息

总结消息

自定义策略

​裁剪消息

​删除消息

​总结消息

​访问 memory

​Tools

​在工具中读取短期记忆

​从工具写入短期记忆

​Prompt

​Before model

​After model

概览

用法

在生产环境中

自定义代理记忆

常见模式

裁剪消息

删除消息

总结消息

访问 memory

Tools

在工具中读取短期记忆

从工具写入短期记忆

Prompt

Before model

After model