Skip to main content
Automatically capture agent runs, model calls, and tool executions from Microsoft Agent Framework through its built-in OpenTelemetry emission — no manual instrumentation of the framework required.

​
Setup

import traceroot
from traceroot import Integration

traceroot.initialize(integrations=[Integration.AGENT_FRAMEWORK])
Initialize TraceRoot before importing agent_framework, so the OpenTelemetry instrumentation is wired up before the framework emits its first span.

​
Usage

Once initialized, every agent invocation, model call, and tool execution is captured automatically: 
import asyncio

import traceroot
from traceroot import Integration

traceroot.initialize(integrations=[Integration.AGENT_FRAMEWORK])

# Import after initialize() so tracing is already active.
from agent_framework import Agent
from agent_framework.openai import OpenAIChatClient


def get_weather(city: str) -> str:
    """Return a short weather forecast for a city."""
    return f"{city}: 18°C, partly cloudy."


agent = Agent(
    OpenAIChatClient(model="gpt-4o-mini"),
    "You are a helpful travel concierge. Use the weather tool when relevant.",
    name="Concierge",
    tools=[get_weather],
)


async def main():
    # The agent run, the model call, and the get_weather tool call are all traced.
    response = await agent.run("What's the weather in Tokyo?")
    print(response.text)


asyncio.run(main())
Tools are plain functions — Agent Framework already emits an execute_tool span for each call, so they don’t need manual decoration.

​
What Gets Captured

AttributeDescription
Agent runEach agent invocation as a span (nested for delegated agents)
ModelThe chat model used for each call
Tool callsAn execute_tool span per tool execution, with arguments
ResponseGenerated text and tool outputs
TokensInput and output token counts
CostCalculated from token usage and model pricing
LatencyRequest duration

​
Run the example

Clone the repo and run a complete multi-agent example end-to-end.

Python

Run the Python example