如何查看和更新过去的图状态¶

一旦您开始检查您的图，您就可以轻松地获取或更新代理在任何时间点的状态。这允许一些事情

1. 您可以在中断期间向用户显示状态，以让他们接受操作。
2. 您可以倒回图以重现或避免问题。
3. 您可以修改状态以将您的代理嵌入到更大的系统中，或让用户更好地控制其操作。

此功能使用的关键方法是

• getState：从目标配置中获取值
• updateState：将给定值应用于目标状态

注意：这需要传入检查点。

这适用于StateGraph及其所有子类，例如MessageGraph。

下面是一个例子。

注意

在本操作指南中，我们将从头开始创建我们的代理以实现透明（但冗长）。您可以使用createReactAgent(model, tools=tool, checkpointer=checkpointer)（API 文档）构造函数来实现类似的功能。如果您习惯使用 LangChain 的AgentExecutor类，这可能更合适。

设置¶

本指南将使用 OpenAI 的 GPT-4o 模型。我们将在可选情况下设置我们的 API 密钥以进行LangSmith 追踪，这将为我们提供一流的可观察性。

在 [1]

// process.env.OPENAI_API_KEY = "sk_...";

// Optional, add tracing in LangSmith
// process.env.LANGCHAIN_API_KEY = "ls__...";
process.env.LANGCHAIN_CALLBACKS_BACKGROUND = "true";
process.env.LANGCHAIN_TRACING_V2 = "true";
process.env.LANGCHAIN_PROJECT = "Time Travel: LangGraphJS";

// process.env.OPENAI_API_KEY = "sk_..."; // 可选，在 LangSmith 中添加追踪 // process.env.LANGCHAIN_API_KEY = "ls__..."; process.env.LANGCHAIN_CALLBACKS_BACKGROUND = "true"; process.env.LANGCHAIN_TRACING_V2 = "true"; process.env.LANGCHAIN_PROJECT = "Time Travel: LangGraphJS";

Time Travel: LangGraphJS

定义状态¶

状态是我们图中所有节点的接口。

在 [2]

import { Annotation } from "@langchain/langgraph";
import { BaseMessage } from "@langchain/core/messages";

const StateAnnotation = Annotation.Root({
  messages: Annotation<BaseMessage[]>({
    reducer: (x, y) => x.concat(y),
  }),
});

import { Annotation } from "@langchain/langgraph"; import { BaseMessage } from "@langchain/core/messages"; const StateAnnotation = Annotation.Root({ messages: Annotation({ reducer: (x, y) => x.concat(y), }), });

设置工具¶

我们首先将定义要使用的工具。对于这个简单的示例，我们将创建一个占位符搜索引擎。但是，创建您自己的工具非常容易 - 请参阅此处的文档了解如何操作。

在 [3]

import { tool } from "@langchain/core/tools";
import { z } from "zod";

const searchTool = tool(async (_) => {
  // This is a placeholder for the actual implementation
  return "Cold, with a low of 13 ℃";
}, {
  name: "search",
  description:
    "Use to surf the web, fetch current information, check the weather, and retrieve other information.",
  schema: z.object({
    query: z.string().describe("The query to use in your search."),
  }),
});

await searchTool.invoke({ query: "What's the weather like?" });

const tools = [searchTool];

import { tool } from "@langchain/core/tools"; import { z } from "zod"; const searchTool = tool(async (_) => { // 这是实际实现的占位符 return "寒冷，最低气温 13 ℃"; }, { name: "search", description: "用于浏览网页、获取当前信息、查看天气和检索其他信息。", schema: z.object({ query: z.string().describe("搜索中使用的查询。"), }), }); await searchTool.invoke({ query: "天气怎么样？" }); const tools = [searchTool];

现在，我们可以将这些工具包装在一个简单的ToolNode中。每当我们的 LLM 调用这些对象时，它实际上都会运行这些工具（函数）。

在 [4]

import { ToolNode } from "@langchain/langgraph/prebuilt";

const toolNode = new ToolNode(tools);

import { ToolNode } from "@langchain/langgraph/prebuilt"; const toolNode = new ToolNode(tools);

设置模型¶

现在我们将加载聊天模型。

1. 它应该可以使用消息。我们将以消息的形式表示所有代理状态，因此它需要能够很好地使用它们。
2. 它应该可以使用工具调用，这意味着它可以在其响应中返回函数参数。

注意

这些模型要求不是使用 LangGraph 的通用要求 - 它们只是此特定示例的要求。

在 [5]

import { ChatOpenAI } from "@langchain/openai";

const model = new ChatOpenAI({ model: "gpt-4o" });

import { ChatOpenAI } from "@langchain/openai"; const model = new ChatOpenAI({ model: "gpt-4o" });

完成此操作后，我们应该确保模型知道它可以使用这些工具进行调用。我们可以通过调用bindTools来实现。

在 [6]

const boundModel = model.bindTools(tools);

const boundModel = model.bindTools(tools);

定义图¶

现在我们可以将所有内容放在一起。时间旅行需要检查点来保存状态 - 否则您将无法进行get或update操作。我们将使用MemorySaver，它在内存中“保存”检查点。

在 [7]

import { END, START, StateGraph } from "@langchain/langgraph";
import { AIMessage } from "@langchain/core/messages";
import { RunnableConfig } from "@langchain/core/runnables";
import { MemorySaver } from "@langchain/langgraph";

const routeMessage = (state: typeof StateAnnotation.State) => {
  const { messages } = state;
  const lastMessage = messages[messages.length - 1] as AIMessage;
  // If no tools are called, we can finish (respond to the user)
  if (!lastMessage?.tool_calls?.length) {
    return END;
  }
  // Otherwise if there is, we continue and call the tools
  return "tools";
};

const callModel = async (
  state: typeof StateAnnotation.State,
  config?: RunnableConfig,
) => {
  const { messages } = state;
  const response = await boundModel.invoke(messages, config);
  return { messages: [response] };
};

const workflow = new StateGraph(StateAnnotation)
  .addNode("agent", callModel)
  .addNode("tools", toolNode)
  .addEdge(START, "agent")
  .addConditionalEdges("agent", routeMessage)
  .addEdge("tools", "agent");

// Here we only save in-memory
let memory = new MemorySaver();
const graph = workflow.compile({ checkpointer: memory });

import { END, START, StateGraph } from "@langchain/langgraph"; import { AIMessage } from "@langchain/core/messages"; import { RunnableConfig } from "@langchain/core/runnables"; import { MemorySaver } from "@langchain/langgraph"; const routeMessage = (state: typeof StateAnnotation.State) => { const { messages } = state; const lastMessage = messages[messages.length - 1] as AIMessage; // 如果没有调用工具，我们可以结束（回复用户） if (!lastMessage?.tool_calls?.length) { return END; } // 否则如果有，我们会继续并调用工具 return "tools"; }; const callModel = async ( state: typeof StateAnnotation.State, config?: RunnableConfig, ) => { const { messages } = state; const response = await boundModel.invoke(messages, config); return { messages: [response] }; }; const workflow = new StateGraph(StateAnnotation) .addNode("agent", callModel) .addNode("tools", toolNode) .addEdge(START, "agent") .addConditionalEdges("agent", routeMessage) .addEdge("tools", "agent"); // 在这里我们只在内存中保存 let memory = new MemorySaver(); const graph = workflow.compile({ checkpointer: memory });

与 Agent 交互¶

现在我们可以与代理交互。在交互之间，您可以获取和更新状态。

在 [8]

let config = { configurable: { thread_id: "conversation-num-1" } };
let inputs = { messages: [{ role: "user", content: "Hi I'm Jo." }] };
for await (
  const { messages } of await graph.stream(inputs, {
    ...config,
    streamMode: "values",
  })
) {
  let msg = messages[messages?.length - 1];
  if (msg?.content) {
    console.log(msg.content);
  } else if (msg?.tool_calls?.length > 0) {
    console.log(msg.tool_calls);
  } else {
    console.log(msg);
  }
  console.log("-----\n");
}

let config = { configurable: { thread_id: "conversation-num-1" } }; let inputs = { messages: [{ role: "user", content: "嗨，我是 Jo。" }] }; for await ( const { messages } of await graph.stream(inputs, { ...config, streamMode: "values", }) ) { let msg = messages[messages?.length - 1]; if (msg?.content) { console.log(msg.content); } else if (msg?.tool_calls?.length > 0) { console.log(msg.tool_calls); } else { console.log(msg); } console.log("-----\n"); }

Hi I'm Jo.
-----

Hello, Jo! How can I assist you today?
-----

在此处查看 LangSmith 示例运行https://smith.langchain.com/public/b3feb09b-bcd2-4ad5-ad1d-414106148448/r

在这里您可以看到“agent”节点已运行，然后我们的边返回了__end__，因此图在此处停止了执行。

让我们检查当前的图状态。

在 [9]

let checkpoint = await graph.getState(config);
checkpoint.values;

let checkpoint = await graph.getState(config); checkpoint.values;

{
  messages: [
    { role: 'user', content: "Hi I'm Jo." },
    AIMessage {
      "id": "chatcmpl-A3FGf3k3QQo9q0QjT6Oc5h1XplkHr",
      "content": "Hello, Jo! How can I assist you today?",
      "additional_kwargs": {},
      "response_metadata": {
        "tokenUsage": {
          "completionTokens": 12,
          "promptTokens": 68,
          "totalTokens": 80
        },
        "finish_reason": "stop",
        "system_fingerprint": "fp_fde2829a40"
      },
      "tool_calls": [],
      "invalid_tool_calls": []
    }
  ]
}

当前状态是我们上面看到的两条消息，1. 我们发送的 HumanMessage，2. 我们从模型收到的 AIMessage。

next值为空，因为图已终止（转换到__end__）。

在 [10]

checkpoint.next;

checkpoint.next;

[]

让它执行工具¶

当我们再次调用图时，它将在每个内部执行步骤之后创建一个检查点。让我们让它运行一个工具，然后查看检查点。

在 [11]

inputs = { messages: [{ role: "user", content: "What's the weather like in SF currently?" }] };
for await (
  const { messages } of await graph.stream(inputs, {
    ...config,
    streamMode: "values",
  })
) {
  let msg = messages[messages?.length - 1];
  if (msg?.content) {
    console.log(msg.content);
  } else if (msg?.tool_calls?.length > 0) {
    console.log(msg.tool_calls);
  } else {
    console.log(msg);
  }
  console.log("-----\n");
}

inputs = { messages: [{ role: "user", content: "目前旧金山的 天气怎么样？" }] }; for await ( const { messages } of await graph.stream(inputs, { ...config, streamMode: "values", }) ) { let msg = messages[messages?.length - 1]; if (msg?.content) { console.log(msg.content); } else if (msg?.tool_calls?.length > 0) { console.log(msg.tool_calls); } else { console.log(msg); } console.log("-----\n"); }

What's the weather like in SF currently?
-----

[
  {
    name: 'search',
    args: { query: 'current weather in San Francisco' },
    type: 'tool_call',
    id: 'call_ZtmtDOyEXDCnXDgowlit5dSd'
  }
]
-----

Cold, with a low of 13 ℃
-----

The current weather in San Francisco is cold, with a low of 13°C.
-----

在此处查看上述执行的跟踪：https://smith.langchain.com/public/0ef426fd-0da1-4c02-a50b-64ae1e68338e/r我们可以看到它计划了工具执行（即“agent”节点），然后“should_continue”边返回“continue”，因此我们继续执行“action”节点，该节点执行了工具，然后“agent”节点发出了最终响应，这使得“should_continue”边返回“end”。让我们看看我们如何可以更好地控制它。

在工具之前暂停¶

如果您注意到下面，我们现在将添加interruptBefore=["action"] - 这意味着在采取任何操作之前，我们将暂停。这是一个让用户更正和更新状态的好时机！当您希望让人机交互来验证（并可能更改）要采取的操作时，这非常有用。

在 [12]

memory = new MemorySaver();
const graphWithInterrupt = workflow.compile({
  checkpointer: memory,
  interruptBefore: ["tools"],
});

inputs = { messages: [{ role: "user", content: "What's the weather like in SF currently?" }] };
for await (
  const { messages } of await graphWithInterrupt.stream(inputs, {
    ...config,
    streamMode: "values",
  })
) {
  let msg = messages[messages?.length - 1];
  if (msg?.content) {
    console.log(msg.content);
  } else if (msg?.tool_calls?.length > 0) {
    console.log(msg.tool_calls);
  } else {
    console.log(msg);
  }
  console.log("-----\n");
}

memory = new MemorySaver(); const graphWithInterrupt = workflow.compile({ checkpointer: memory, interruptBefore: ["tools"], }); inputs = { messages: [{ role: "user", content: "目前旧金山的 天气怎么样？" }] }; for await ( const { messages } of await graphWithInterrupt.stream(inputs, { ...config, streamMode: "values", }) ) { let msg = messages[messages?.length - 1]; if (msg?.content) { console.log(msg.content); } else if (msg?.tool_calls?.length > 0) { console.log(msg.tool_calls); } else { console.log(msg); } console.log("-----\n"); }

What's the weather like in SF currently?
-----

[
  {
    name: 'search',
    args: { query: 'current weather in San Francisco' },
    type: 'tool_call',
    id: 'call_OsKnTv2psf879eeJ9vx5GeoY'
  }
]
-----

获取状态¶

您可以使用getState(config)获取最新的图检查点。

在 [13]

let snapshot = await graphWithInterrupt.getState(config);
snapshot.next;

let snapshot = await graphWithInterrupt.getState(config); snapshot.next;

[ 'tools' ]

恢复¶

您可以通过使用null输入运行图来恢复。检查点被加载，并且没有新的输入，它将执行，就好像没有发生中断一样。

在 [14]

for await (
  const { messages } of await graphWithInterrupt.stream(null, {
    ...snapshot.config,
    streamMode: "values",
  })
) {
  let msg = messages[messages?.length - 1];
  if (msg?.content) {
    console.log(msg.content);
  } else if (msg?.tool_calls?.length > 0) {
    console.log(msg.tool_calls);
  } else {
    console.log(msg);
  }
  console.log("-----\n");
}

for await ( const { messages } of await graphWithInterrupt.stream(null, { ...snapshot.config, streamMode: "values", }) ) { let msg = messages[messages?.length - 1]; if (msg?.content) { console.log(msg.content); } else if (msg?.tool_calls?.length > 0) { console.log(msg.tool_calls); } else { console.log(msg); } console.log("-----\n"); }

Cold, with a low of 13 ℃
-----

Currently, it is cold in San Francisco, with a temperature around 13°C (55°F).
-----

查看完整历史¶

让我们浏览一下此线程的历史记录，从最新到最旧。

在 [15] 中

let toReplay;
const states = await graphWithInterrupt.getStateHistory(config);
for await (const state of states) {
  console.log(state);
  console.log("--");
  if (state.values?.messages?.length === 2) {
    toReplay = state;
  }
}
if (!toReplay) {
  throw new Error("No state to replay");
}

let toReplay; const states = await graphWithInterrupt.getStateHistory(config); for await (const state of states) { console.log(state); console.log("--"); if (state.values?.messages?.length === 2) { toReplay = state; } } if (!toReplay) { throw new Error("No state to replay"); }

{
  values: {
    messages: [
      [Object],
      AIMessage {
        "id": "chatcmpl-A3FGhKzOZs0GYZ2yalNOCQZyPgbcp",
        "content": "",
        "additional_kwargs": {
          "tool_calls": [
            {
              "id": "call_OsKnTv2psf879eeJ9vx5GeoY",
              "type": "function",
              "function": "[Object]"
            }
          ]
        },
        "response_metadata": {
          "tokenUsage": {
            "completionTokens": 17,
            "promptTokens": 72,
            "totalTokens": 89
          },
          "finish_reason": "tool_calls",
          "system_fingerprint": "fp_fde2829a40"
        },
        "tool_calls": [
          {
            "name": "search",
            "args": {
              "query": "current weather in San Francisco"
            },
            "type": "tool_call",
            "id": "call_OsKnTv2psf879eeJ9vx5GeoY"
          }
        ],
        "invalid_tool_calls": []
      },
      ToolMessage {
        "content": "Cold, with a low of 13 ℃",
        "name": "search",
        "additional_kwargs": {},
        "response_metadata": {},
        "tool_call_id": "call_OsKnTv2psf879eeJ9vx5GeoY"
      },
      AIMessage {
        "id": "chatcmpl-A3FGiYripPKtQLnAK1H3hWLSXQfOD",
        "content": "Currently, it is cold in San Francisco, with a temperature around 13°C (55°F).",
        "additional_kwargs": {},
        "response_metadata": {
          "tokenUsage": {
            "completionTokens": 21,
            "promptTokens": 105,
            "totalTokens": 126
          },
          "finish_reason": "stop",
          "system_fingerprint": "fp_fde2829a40"
        },
        "tool_calls": [],
        "invalid_tool_calls": []
      }
    ]
  },
  next: [],
  tasks: [],
  metadata: { source: 'loop', writes: { agent: [Object] }, step: 3 },
  config: {
    configurable: {
      thread_id: 'conversation-num-1',
      checkpoint_ns: '',
      checkpoint_id: '1ef69ab6-9c3a-6bd1-8003-d7f030ff72b2'
    }
  },
  createdAt: '2024-09-03T04:17:20.653Z',
  parentConfig: {
    configurable: {
      thread_id: 'conversation-num-1',
      checkpoint_ns: '',
      checkpoint_id: '1ef69ab6-9516-6200-8002-43d2c6dc603f'
    }
  }
}
--
{
  values: {
    messages: [
      [Object],
      AIMessage {
        "id": "chatcmpl-A3FGhKzOZs0GYZ2yalNOCQZyPgbcp",
        "content": "",
        "additional_kwargs": {
          "tool_calls": [
            {
              "id": "call_OsKnTv2psf879eeJ9vx5GeoY",
              "type": "function",
              "function": "[Object]"
            }
          ]
        },
        "response_metadata": {
          "tokenUsage": {
            "completionTokens": 17,
            "promptTokens": 72,
            "totalTokens": 89
          },
          "finish_reason": "tool_calls",
          "system_fingerprint": "fp_fde2829a40"
        },
        "tool_calls": [
          {
            "name": "search",
            "args": {
              "query": "current weather in San Francisco"
            },
            "type": "tool_call",
            "id": "call_OsKnTv2psf879eeJ9vx5GeoY"
          }
        ],
        "invalid_tool_calls": []
      },
      ToolMessage {
        "content": "Cold, with a low of 13 ℃",
        "name": "search",
        "additional_kwargs": {},
        "response_metadata": {},
        "tool_call_id": "call_OsKnTv2psf879eeJ9vx5GeoY"
      }
    ]
  },
  next: [ 'agent' ],
  tasks: [
    {
      id: '612efffa-3b16-530f-8a39-fd01c31e7b8b',
      name: 'agent',
      interrupts: []
    }
  ],
  metadata: { source: 'loop', writes: { tools: [Object] }, step: 2 },
  config: {
    configurable: {
      thread_id: 'conversation-num-1',
      checkpoint_ns: '',
      checkpoint_id: '1ef69ab6-9516-6200-8002-43d2c6dc603f'
    }
  },
  createdAt: '2024-09-03T04:17:19.904Z',
  parentConfig: {
    configurable: {
      thread_id: 'conversation-num-1',
      checkpoint_ns: '',
      checkpoint_id: '1ef69ab6-9455-6410-8001-1c78a97f63e6'
    }
  }
}
--
{
  values: {
    messages: [
      [Object],
      AIMessage {
        "id": "chatcmpl-A3FGhKzOZs0GYZ2yalNOCQZyPgbcp",
        "content": "",
        "additional_kwargs": {
          "tool_calls": [
            {
              "id": "call_OsKnTv2psf879eeJ9vx5GeoY",
              "type": "function",
              "function": "[Object]"
            }
          ]
        },
        "response_metadata": {
          "tokenUsage": {
            "completionTokens": 17,
            "promptTokens": 72,
            "totalTokens": 89
          },
          "finish_reason": "tool_calls",
          "system_fingerprint": "fp_fde2829a40"
        },
        "tool_calls": [
          {
            "name": "search",
            "args": {
              "query": "current weather in San Francisco"
            },
            "type": "tool_call",
            "id": "call_OsKnTv2psf879eeJ9vx5GeoY"
          }
        ],
        "invalid_tool_calls": []
      }
    ]
  },
  next: [ 'tools' ],
  tasks: [
    {
      id: '767116b0-55b6-5af4-8f74-ce45fb6e31ed',
      name: 'tools',
      interrupts: []
    }
  ],
  metadata: { source: 'loop', writes: { agent: [Object] }, step: 1 },
  config: {
    configurable: {
      thread_id: 'conversation-num-1',
      checkpoint_ns: '',
      checkpoint_id: '1ef69ab6-9455-6410-8001-1c78a97f63e6'
    }
  },
  createdAt: '2024-09-03T04:17:19.825Z',
  parentConfig: {
    configurable: {
      thread_id: 'conversation-num-1',
      checkpoint_ns: '',
      checkpoint_id: '1ef69ab6-8c4b-6261-8000-c51e5807fbcd'
    }
  }
}
--
{
  values: { messages: [ [Object] ] },
  next: [ 'agent' ],
  tasks: [
    {
      id: '5b0ed7d1-1bb7-5d78-b4fc-7a8ed40e7291',
      name: 'agent',
      interrupts: []
    }
  ],
  metadata: { source: 'loop', writes: null, step: 0 },
  config: {
    configurable: {
      thread_id: 'conversation-num-1',
      checkpoint_ns: '',
      checkpoint_id: '1ef69ab6-8c4b-6261-8000-c51e5807fbcd'
    }
  },
  createdAt: '2024-09-03T04:17:18.982Z',
  parentConfig: {
    configurable: {
      thread_id: 'conversation-num-1',
      checkpoint_ns: '',
      checkpoint_id: '1ef69ab6-8c4b-6260-ffff-6ec582916c42'
    }
  }
}
--
{
  values: {},
  next: [ '__start__' ],
  tasks: [
    {
      id: 'a4250d5c-d025-5da1-b588-cae2b3f4a8c7',
      name: '__start__',
      interrupts: []
    }
  ],
  metadata: { source: 'input', writes: { messages: [Array] }, step: -1 },
  config: {
    configurable: {
      thread_id: 'conversation-num-1',
      checkpoint_ns: '',
      checkpoint_id: '1ef69ab6-8c4b-6260-ffff-6ec582916c42'
    }
  },
  createdAt: '2024-09-03T04:17:18.982Z',
  parentConfig: undefined
}
--

回放过去的状态¶

要从这个位置回放，我们只需要将它的配置传回给代理。

在 [16] 中

for await (
  const { messages } of await graphWithInterrupt.stream(null, {
    ...toReplay.config,
    streamMode: "values",
  })
) {
  let msg = messages[messages?.length - 1];
  if (msg?.content) {
    console.log(msg.content);
  } else if (msg?.tool_calls?.length > 0) {
    console.log(msg.tool_calls);
  } else {
    console.log(msg);
  }
  console.log("-----\n");
}

for await ( const { messages } of await graphWithInterrupt.stream(null, { ...toReplay.config, streamMode: "values", }) ) { let msg = messages[messages?.length - 1]; if (msg?.content) { console.log(msg.content); } else if (msg?.tool_calls?.length > 0) { console.log(msg.tool_calls); } else { console.log(msg); } console.log("-----\n"); }

Cold, with a low of 13 ℃
-----

The current weather in San Francisco is cold, with a low of 13°C.
-----

从过去的状态分支¶

使用 LangGraph 的检查点功能，您可以做的不仅仅是回放过去的状态。您可以从先前的位置分支出来，让代理探索替代轨迹，或者让用户“版本控制”工作流中的更改。

首先，更新先前的检查点¶

更新状态将通过将更新应用于先前的检查点来创建一个**新的**快照。让我们**添加一条工具消息**来模拟调用工具。

在 [17] 中

const tool_calls =
  toReplay.values.messages[toReplay.values.messages.length - 1].tool_calls;
const branchConfig = await graphWithInterrupt.updateState(
  toReplay.config,
  {
    messages: [
      { role: "tool", content: "It's sunny out, with a high of 38 ℃.", tool_call_id: tool_calls[0].id },
    ],
  },
  // Updates are applied "as if" they were coming from a node. By default,
  // the updates will come from the last node to run. In our case, we want to treat
  // this update as if it came from the tools node, so that the next node to run will be
  // the agent.
  "tools",
);

const branchState = await graphWithInterrupt.getState(branchConfig);
console.log(branchState.values);
console.log(branchState.next);

const tool_calls = toReplay.values.messages[toReplay.values.messages.length - 1].tool_calls; const branchConfig = await graphWithInterrupt.updateState( toReplay.config, { messages: [ { role: "tool", content: "It's sunny out, with a high of 38 ℃.", tool_call_id: tool_calls[0].id }, ], }, // Updates are applied "as if" they were coming from a node. By default, // the updates will come from the last node to run. In our case, we want to treat // this update as if it came from the tools node, so that the next node to run will be // the agent. "tools", ); const branchState = await graphWithInterrupt.getState(branchConfig); console.log(branchState.values); console.log(branchState.next);

{
  messages: [
    {
      role: 'user',
      content: "What's the weather like in SF currently?"
    },
    AIMessage {
      "id": "chatcmpl-A3FGhKzOZs0GYZ2yalNOCQZyPgbcp",
      "content": "",
      "additional_kwargs": {
        "tool_calls": [
          {
            "id": "call_OsKnTv2psf879eeJ9vx5GeoY",
            "type": "function",
            "function": "[Object]"
          }
        ]
      },
      "response_metadata": {
        "tokenUsage": {
          "completionTokens": 17,
          "promptTokens": 72,
          "totalTokens": 89
        },
        "finish_reason": "tool_calls",
        "system_fingerprint": "fp_fde2829a40"
      },
      "tool_calls": [
        {
          "name": "search",
          "args": {
            "query": "current weather in San Francisco"
          },
          "type": "tool_call",
          "id": "call_OsKnTv2psf879eeJ9vx5GeoY"
        }
      ],
      "invalid_tool_calls": []
    },
    {
      role: 'tool',
      content: "It's sunny out, with a high of 38 ℃.",
      tool_call_id: 'call_OsKnTv2psf879eeJ9vx5GeoY'
    }
  ]
}
[ 'agent' ]

现在您可以从此分支运行¶

只需使用更新的配置（包含新的检查点 ID）。轨迹将遵循新的分支。

在 [18] 中

for await (
  const { messages } of await graphWithInterrupt.stream(null, {
    ...branchConfig,
    streamMode: "values",
  })
) {
  let msg = messages[messages?.length - 1];
  if (msg?.content) {
    console.log(msg.content);
  } else if (msg?.tool_calls?.length > 0) {
    console.log(msg.tool_calls);
  } else {
    console.log(msg);
  }
  console.log("-----\n");
}

for await ( const { messages } of await graphWithInterrupt.stream(null, { ...branchConfig, streamMode: "values", }) ) { let msg = messages[messages?.length - 1]; if (msg?.content) { console.log(msg.content); } else if (msg?.tool_calls?.length > 0) { console.log(msg.tool_calls); } else { console.log(msg); } console.log("-----\n"); }

The current weather in San Francisco is sunny, with a high of 38°C.
-----