> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent with Reasoning Tools Tracing

> Trace agents with reasoning tools in AgentOS.

Trace an agent that uses reasoning tools in AgentOS. The traces capture the agent's reasoning process, including all intermediate steps.

<Steps>
  <Step title="Create a Python file">
    ```python agent_with_reasoning_tools_tracing.py theme={null}
    from textwrap import dedent

    from agno.agent import Agent
    from agno.db.sqlite import SqliteDb
    from agno.models.openai import OpenAIResponses
    from agno.os import AgentOS
    from agno.tools.reasoning import ReasoningTools

    db = SqliteDb(db_file="tmp/traces.db")

    reasoning_agent = Agent(
        model=OpenAIResponses(id="gpt-5.2"),
        tools=[ReasoningTools(add_instructions=True)],
        instructions=dedent("""\
            You are an expert problem-solving assistant with strong analytical skills! 🧠

            Your approach to problems:
            1. First, break down complex questions into component parts
            2. Clearly state your assumptions
            3. Develop a structured reasoning path
            4. Consider multiple perspectives
            5. Evaluate evidence and counter-arguments
            6. Draw well-justified conclusions

            When solving problems:
            - Use explicit step-by-step reasoning
            - Identify key variables and constraints
            - Explore alternative scenarios
            - Highlight areas of uncertainty
            - Explain your thought process clearly
            - Consider both short and long-term implications
            - Evaluate trade-offs explicitly

            For quantitative problems:
            - Show your calculations
            - Explain the significance of numbers
            - Consider confidence intervals when appropriate
            - Identify source data reliability

            For qualitative reasoning:
            - Assess how different factors interact
            - Consider psychological and social dynamics
            - Evaluate practical constraints
            - Address value considerations
            \
        """),
        add_datetime_to_context=True,
        stream_events=True,
        markdown=True,
        db=db,
    )

    # Setup AgentOS with tracing enabled
    agent_os = AgentOS(
        description="Example app for reasoning agent with tracing",
        agents=[reasoning_agent],
        tracing=True,
    )
    app = agent_os.get_app()

    if __name__ == "__main__":
        agent_os.serve(app="agent_with_reasoning_tools_tracing:app", reload=True)
    ```
  </Step>

  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U openai "agno[os]" opentelemetry-api opentelemetry-sdk openinference-instrumentation-agno
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run AgentOS">
    ```bash theme={null}
    python agent_with_reasoning_tools_tracing.py
    ```

    Your AgentOS will be available at `http://localhost:7777`. View traces in the AgentOS dashboard.
  </Step>
</Steps>