Google ADK | Respan Docs

Google Agent Development Kit (ADK) is a Python framework for building production-grade agents with tool use, planning, and orchestration on Google Cloud. Respan gives you full observability over every agent run, tool call, and LLM generation — and gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Install packages

$ pip install respan-ai openinference-instrumentation-google-adk google-adk

Set environment variables

$ export GOOGLE_API_KEY="YOUR_GOOGLE_API_KEY"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

GOOGLE_API_KEY is used for LLM requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 from google.adk.agents import Agent
2 from google.adk.runners import Runner
3 from google.adk.sessions import InMemorySessionService
4 from respan import Respan
5 from openinference.instrumentation.google_adk import GoogleADKInstrumentor
6 
7 respan = Respan(instrumentations=[GoogleADKInstrumentor()])
8 
9 agent = Agent(
10     name="assistant",
11     model="gemini-2.0-flash",
12     instruction="You are a helpful assistant.",
13 )
14 
15 session_service = InMemorySessionService()
16 runner = Runner(agent=agent, app_name="demo", session_service=session_service)
17 
18 session = session_service.create_session(app_name="demo", user_id="user_1")
19 for event in runner.run(user_id="user_1", session_id=session.id, new_message="Hello"):
20     print(event)
21 respan.flush()

View your trace

Open the Traces page to see your Google ADK workflow with agent runs, tool executions, and LLM calls.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `GoogleADKInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

Set defaults at initialization — these apply to all spans.

1 from respan import Respan
2 from openinference.instrumentation.google_adk import GoogleADKInstrumentor
3 
4 respan = Respan(
5     instrumentations=[GoogleADKInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "adk-api", "version": "1.0.0"},
8 )

With propagate_attributes

Override per-request using a context scope.

1 from respan import Respan, propagate_attributes
2 from openinference.instrumentation.google_adk import GoogleADKInstrumentor
3 
4 respan = Respan(instrumentations=[GoogleADKInstrumentor()])
5 
6 def handle_request(user_id: str, message: str):
7     with propagate_attributes(
8         customer_identifier=user_id,
9         thread_identifier="conv_abc_123",
10         metadata={"plan": "pro"},
11     ):
12         for event in runner.run(user_id=user_id, session_id=session.id, new_message=message):
13             print(event)

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.