> ## 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.

# LangSmith 可观测性

当你使用 LangChain 构建和运行智能体时，你需要了解它们的行为方式：它们调用了哪些[工具](/oss/python/langchain/tools)、生成了什么提示词，以及如何做出决策。使用 [`create_agent`](https://reference.langchain.com/python/langchain/agents/factory/create_agent) 构建的 LangChain 智能体通过 [LangSmith](/langsmith/home) 自动支持追踪，LangSmith 是一个用于捕获、调试、评估和监控大语言模型(LLM)应用行为的平台。

[*追踪*](/langsmith/observability-concepts#traces)记录了智能体执行的每一步，从初始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。这些执行数据帮助你调试问题、评估不同输入的性能，并监控生产环境中的使用模式。

本指南向你展示如何为 LangChain 智能体启用追踪，并使用 LangSmith 分析其执行过程。

## 前提条件

开始之前，请确保你拥有以下条件：

* **LangSmith 账户**：在 [smith.langchain.com](https://smith.langchain.com?utm_source=docs\&utm_medium=cta\&utm_campaign=langsmith-signup\&utm_content=oss-langchain-observability) 注册（免费）或登录。
* **LangSmith API 密钥**：按照[创建 API 密钥](/langsmith/create-account-api-key)指南操作。

## 启用追踪

所有 LangChain 智能体自动支持 LangSmith 追踪。要启用它，设置以下环境变量：

```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY=<your-api-key>
```

## 快速入门

无需额外代码即可将追踪记录到 LangSmith。只需像平常一样运行你的智能体代码：

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain.agents import create_agent


def send_email(to: str, subject: str, body: str):
    """向收件人发送邮件。"""
    # ... 邮件发送逻辑
    return f"Email sent to {to}"

def search_web(query: str):
    """在网络上搜索信息。"""
    # ... 网页搜索逻辑
    return f"Search results for: {query}"

agent = create_agent(
    model="gpt-5.4",
    tools=[send_email, search_web],
    system_prompt="You are a helpful assistant that can send emails and search the web."
)

# 运行智能体 - 所有步骤将自动被追踪
response = 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，追踪将记录到名为 `default` 的项目中。要配置自定义项目名称，请参阅[记录到项目](/langsmith/log-traces-to-project)。

## Trace selectively

You may opt to trace specific invocations or parts of your application using LangSmith's `tracing_context` context manager:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import langsmith as ls

# This WILL be traced
with ls.tracing_context(enabled=True):
    agent.invoke({"messages": [{"role": "user", "content": "Send a test email to alice@example.com"}]})

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

## Log to a project

<Accordion title="Statically">
  You can set a custom project name for your entire application by setting the `LANGSMITH_PROJECT` environment variable:

  ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  export LANGSMITH_PROJECT=my-agent-project
  ```
</Accordion>

<Accordion title="Dynamically">
  You can set the project name programmatically for specific operations:

  ```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  import langsmith as ls

  with ls.tracing_context(project_name="email-agent-test", enabled=True):
      response = agent.invoke({
          "messages": [{"role": "user", "content": "Send a welcome email"}]
      })
  ```
</Accordion>

## Add metadata to traces

You can annotate your traces with custom metadata and tags:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
response = agent.invoke(
    {"messages": [{"role": "user", "content": "Send a welcome email"}]},
    config={
        "tags": ["production", "email-assistant", "v1.0"],
        "metadata": {
            "user_id": "user_123",
            "session_id": "session_456",
            "environment": "production"
        }
    }
)
```

`tracing_context` also accepts tags and metadata for fine-grained control:

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
with ls.tracing_context(
    project_name="email-agent-test",
    enabled=True,
    tags=["production", "email-assistant", "v1.0"],
    metadata={"user_id": "user_123", "session_id": "session_456", "environment": "production"}):
    response = agent.invoke(
        {"messages": [{"role": "user", "content": "Send a welcome email"}]}
    )
```

This custom metadata and tags will be attached to the trace in LangSmith.

<Tip>
  要了解更多关于 how to use traces to debug, evaluate, and monitor your agents, see the [LangSmith documentation](/langsmith/home).
</Tip>

***

<div className="source-links">
  <Callout icon="terminal-2">
    [将这些文档连接](/use-these-docs)到 Claude、VSCode 等工具，通过 MCP 获取实时答案。
  </Callout>

  <Callout icon="edit">
    [在 GitHub 上编辑此页面](https://github.com/langchain-ai/docs/edit/main/src/oss/langchain/observability.mdx)或[提交问题](https://github.com/langchain-ai/docs/issues/new/choose)。
  </Callout>
</div>