pydantic
Support Google agents ADK tracing
Description
Do you support agents adk for tracing? If not, is it possible to add support?
Yes: https://logfire.pydantic.dev/docs/integrations/llms/openai/#openai-agents
Do you think this needs to be more discoverable in the docs somehow?
Yes: https://logfire.pydantic.dev/docs/integrations/llms/openai/#openai-agents
Do you think this needs to be more discoverable in the docs somehow?
Sorry I mean the Google agents ADK
The ADK comes with built in OpenTelemetry tracing. Therefore all you need is to call logfire.configure(). Here's some sample code to demo it working:
import asyncio
from google.adk import Agent, Runner
from google.adk.sessions import InMemorySessionService
from google.genai import types
import logfire
logfire.configure()
# 1. ‘say_hello’ tool
def say_hello():
return {'greeting': 'Hello 👋'}
agent = Agent(
name='hello_agent',
model='gemini-2.0-flash',
instruction='Always greet using the say_hello tool.',
tools=[say_hello],
)
# 2. session service + runner
session_service = InMemorySessionService()
APP_NAME = 'hello_app'
USER_ID = 'demo-user'
SESSION_ID = 'demo-session' # any string; UUIDs work too
# create the session once
async def main():
await session_service.create_session(app_name=APP_NAME, user_id=USER_ID, session_id=SESSION_ID)
runner = Runner(agent=agent, app_name=APP_NAME, session_service=session_service)
# 3. single‑turn run
user_msg = types.Content(role='user', parts=[types.Part(text='hi')])
async for event in runner.run_async(user_id=USER_ID, session_id=SESSION_ID, new_message=user_msg):
if event.is_final_response():
print(event.content.parts[0].text)
if __name__ == '__main__':
asyncio.run(main())
But I see that the attributes are not quite in the format needed to be displayed nicely in our UI. We can fix that.