This example shows how to trace an agent that uses reasoning tools in AgentOS. The traces capture the agent’s reasoning process, including all intermediate steps.
1
Create a Python file
agent_with_reasoning_tools_tracing.py
Copy
Ask AI
from textwrap import dedentfrom agno.agent import Agentfrom agno.db.sqlite import SqliteDbfrom agno.models.openai import OpenAIResponsesfrom agno.os import AgentOSfrom agno.tools.reasoning import ReasoningToolsdb = 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 enabledagent_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)