> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-zh.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# 追踪 OpenAI Agents SDK 应用

OpenAI Agents SDK 允许您构建由 OpenAI 模型驱动的智能体应用。

了解如何使用 LangSmith 追踪基于 OpenAI Agents SDK 的 LLM 应用。

## 安装

<Info>
  需要 Python SDK 版本 `langsmith>=0.3.15`。
</Info>

安装支持 OpenAI Agents 的 LangSmith：

<CodeGroup>
  ```bash pip theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  pip install "langsmith[openai-agents]"
  ```

  ```bash uv theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
  uv add "langsmith[openai-agents]"
  ```
</CodeGroup>

这将同时安装 LangSmith 库和 OpenAI Agents SDK。

## 快速开始

您可以通过使用 `OpenAIAgentsTracingProcessor` 类，将 LangSmith 追踪功能集成到 OpenAI Agents SDK 中。

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
import asyncio
from agents import Agent, Runner, set_trace_processors
from langsmith.integrations.openai_agents_sdk import OpenAIAgentsTracingProcessor

async def main():
    agent = Agent(
        name="Captain Obvious",
        instructions="You are Captain Obvious, the world's most literal technical support agent.",
    )

    question = "Why is my code failing when I try to divide by zero? I keep getting this error message."
    result = await Runner.run(agent, question)
    print(result.final_output)

if __name__ == "__main__":
    set_trace_processors([OpenAIAgentsTracingProcessor()])
    asyncio.run(main())
```

智能体的执行流程，包括所有跨度及其详细信息，都将被记录到 LangSmith 中。

<img src="https://mintcdn.com/hhh-8c10bf0c/dGi5Qyx6ZNfUuqyP/langsmith/images/agent-trace.png?fit=max&auto=format&n=dGi5Qyx6ZNfUuqyP&q=85&s=35deeba0b331188ddd09fd82a87f2f66" alt="LangSmith 中的 OpenAI Agents SDK 追踪" width="2984" height="1782" data-path="langsmith/images/agent-trace.png" />

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/i18n\zh-CN\langsmith\trace-with-openai-agents-sdk.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>