当你使用 LangChain 构建和运行代理时，需要了解它们的行为：调用了哪些工具、生成了什么提示词，以及如何做出决策。使用 createAgent 构建的 LangChain 代理会自动支持通过 LangSmith 进行跟踪。LangSmith 是一个用于捕获、调试、评估和监控 LLM 应用行为的平台。 Traces 会记录代理执行的每一步，从最初的用户输入到最终响应，包括所有工具调用、模型交互和决策点。这些执行数据可帮助你调试问题、评估不同输入下的性能，并监控生产环境中的使用模式。 本指南介绍如何为 LangChain 代理启用跟踪，并使用 LangSmith 分析其执行过程。

​
前提条件

开始之前，请确保具备以下内容：

​
启用跟踪

所有 LangChain 代理都会自动支持 LangSmith 跟踪。若要启用它，请设置以下环境变量： 
export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY=<your-api-key>

​
快速入门

无需额外代码即可将跟踪记录到 LangSmith。像平常一样运行你的代理代码即可： 
import { createAgent } from "@langchain/agents";

function sendEmail(to: string, subject: string, body: string): string {
    // ... email sending logic
    return `Email sent to ${to}`;
}

function searchWeb(query: string): string {
    // ... web search logic
    return `Search results for: ${query}`;
}

const agent = createAgent({
    model: "gpt-5.4",
    tools: [sendEmail, searchWeb],
    systemPrompt: "You are a helpful assistant that can send emails and search the web."
});

// Run the agent - all steps will be traced automatically
const response = await agent.invoke({
    messages: [{ role: "user", content: "Search for the latest AI news and email a summary to john@example.com" }]
});
默认情况下，跟踪会记录到名为 default 的项目中。若要配置自定义项目名称，请参阅记录到项目。

​
Trace selectively

You may opt to trace specific invocations or parts of your application using LangSmith’s tracing_context context manager: 
import { LangChainTracer } from "@langchain/core/tracers/tracer_langchain";

// This WILL be traced
const tracer = new LangChainTracer();
await agent.invoke(
  {
    messages: [{role: "user", content: "Send a test email to alice@example.com"}]
  },
  { callbacks: [tracer] }
);

// This will NOT be traced (if LANGSMITH_TRACING is not set)
await agent.invoke(
  {
    messages: [{role: "user", content: "Send another email"}]
  }
);

​
Log to a project

You can set a custom project name for your entire application by setting the LANGSMITH_PROJECT environment variable:
export LANGSMITH_PROJECT=my-agent-project
You can set the project name programmatically for specific operations:
import { LangChainTracer } from "@langchain/core/tracers/tracer_langchain";

const tracer = new LangChainTracer({ projectName: "email-agent-test" });
await agent.invoke(
  {
    messages: [{role: "user", content: "Send a test email to alice@example.com"}]
  },
  { callbacks: [tracer] }
);

​
Add metadata to traces

You can annotate your traces with custom metadata and tags: 
import { LangChainTracer } from "@langchain/core/tracers/tracer_langchain";

const tracer = new LangChainTracer({ projectName: "email-agent-test" });
await agent.invoke(
  {
    messages: [{role: "user", content: "Send a test email to alice@example.com"}]
  },
  {
    tags: ["production", "email-assistant", "v1.0"],
    metadata: {
      userId: "user123",
      sessionId: "session456",
      environment: "production"
    }
  },
);
This custom metadata and tags will be attached to the trace in LangSmith.
To learn more about how to use traces to debug, evaluate, and monitor your agents, see the LangSmith documentation.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.
Edit this page on GitHub or file an issue.