Google ADK
Trace a Google ADK agent with Neatlogs (Python).
Capture a Google ADK agent's runs, model calls, and tool calls. In Python you wrap the Runner and its runs are traced automatically.
Go ADK auto-instrumentation is deprecated. The Go SDK now uses a private OpenTelemetry provider and never registers the global one, so ADK-Go — which binds to the global provider — no longer flows through. The contrib/adk module (WrapModel, the A2A helpers) is quarantined and non-functional. In Go, instrument the model calls and boundaries your agent makes explicitly with StartLLMSpan, StartSpan, and StartToolSpanFromHeaders — see the Go SDK.
Prerequisites
pip install -U "neatlogs[google-adk]" google-adkUsage
import os
import neatlogs
neatlogs.init(api_key=os.environ["NEATLOGS_API_KEY"], workflow_name="google-adk-demo")
from google.adk.runners import Runner
# `my_agent` and `session_service` are your existing ADK objects.
runner = neatlogs.wrap(Runner(agent=my_agent, app_name="my-app", session_service=session_service))
# Drive the runner as usual — its runs are now traced.The ADK run becomes a WORKFLOW/AGENT trace root automatically, with nested AGENT, LLM, and TOOL spans.
Sessions & end-user
Say your Google ADK agent fires off a handful of runs in a single back-and-forth and you'd like them filed under one session, tied to whoever's chatting — that's a quick win. Wrap the run in identify() and ADK's spans inherit that identity through the identity processor:
# Same session_id every turn → one session; end_user_id attributes it to your user.
with neatlogs.identify(session_id=f"conv_{conversation_id}", end_user_id=user_id):
# drive the runner as usual — its spans inherit the neatlogs session + end-user
runner.run(...)Not every run is a conversation. A standalone workflow — a one-off job, not a back-and-forth — is a single trace with no turns to group. You still attribute it to the customer it ran for, sourcing the id and any metadata from your own user or request object:
A standalone workflow must not carry a session_id. Omit it entirely — Neatlogs sets session_id = trace_id, so the run is its own single-turn session, fully attributed to the end-user. Reusing one session_id across unrelated runs wrongly folds them into a single multi-turn conversation.
def run_agent(request, user):
# Standalone workflow — attribute to the end-user; do NOT pass session_id.
with neatlogs.identify(
end_user_id=str(user.id),
end_user_metadata={"plan": user.plan},
):
# drive the runner as usual — its spans carry the end-user
return runner.run(request)For the whole picture, see Sessions and End-User Identity.