Skip to content

Google ADK

Coralogix's AI Observability integration for Google ADK (Agent Development Kit) provides production-ready tracing for agent workflows built on Gemini. Instrument your ADK agents with a single call to gain full visibility into prompts, completions, tool calls, and performance metrics.

Requirements

Installation

Run the following command.

pip install "llm-tracekit-google-adk"

Authentication

Authentication data is passed during OTel Span Exporter definition:

  1. Choose the ingress.:443 endpoint that corresponds to your Coralogix domain using the domain selector at the top of the page.
  2. Use your customized API key in the authorization request header.
  3. Provide the application and subsystem names.
from llm_tracekit.google_adk import setup_export_to_coralogix

setup_export_to_coralogix(
    coralogix_token=<your_coralogix_token>,
    coralogix_endpoint="ingress.:443",
    service_name="ai-service",
    application_name="ai-application",
    subsystem_name="ai-subsystem",
    capture_content=True,
)

Note

All of the authentication parameters can also be provided through environment variables (CX_TOKEN, CX_ENDPOINT, etc.).

Usage

This section describes how to set up instrumentation for Google ADK.

Set up tracing

Automatic

Use the setup_export_to_coralogix function to set up tracing and export traces to Coralogix. See the code snippet in the Authentication section.

Manual

Alternatively, you can set up tracing manually.

from opentelemetry import trace
from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.resources import SERVICE_NAME, Resource
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import SimpleSpanProcessor

tracer_provider = TracerProvider(
    resource=Resource.create({SERVICE_NAME: "ai-service"}),
)
exporter = OTLPSpanExporter()
span_processor = SimpleSpanProcessor(exporter)
tracer_provider.add_span_processor(span_processor)
trace.set_tracer_provider(tracer_provider)

Instrument

To instrument all clients, call the instrument method.

from llm_tracekit.google_adk import GoogleADKInstrumentor

GoogleADKInstrumentor().instrument()

Uninstrument

To uninstrument clients, call the uninstrument method.

GoogleADKInstrumentor().uninstrument()

Full example

import asyncio
from google.adk import Agent, Runner
from google.adk.sessions import InMemorySessionService
from google.genai import types
from llm_tracekit.google_adk import GoogleADKInstrumentor, setup_export_to_coralogix

# Optional: Configure sending spans to Coralogix
# Reads Coralogix connection details from the following environment variables:
# - CX_TOKEN
# - CX_ENDPOINT
setup_export_to_coralogix(
    service_name="ai-service",
    application_name="ai-application",
    subsystem_name="ai-subsystem",
    capture_content=True,
)

# Activate instrumentation
GoogleADKInstrumentor().instrument()


async def main():
    agent = Agent(
        name="MyAgent",
        model="gemini-2.0-flash",
        instruction="You are a helpful assistant.",
    )

    session_service = InMemorySessionService()
    runner = Runner(agent=agent, app_name="my_app", session_service=session_service)

    session = await session_service.create_session(app_name="my_app", user_id="user_1")

    async for event in runner.run_async(
        user_id="user_1",
        session_id=session.id,
        new_message=types.Content(role="user", parts=[types.Part(text="Hello!")]),
    ):
        if event.content and event.content.parts:
            for part in event.content.parts:
                if part.text:
                    print(part.text, end="")


if __name__ == "__main__":
    asyncio.run(main())

Enable message content capture

By default, message content — prompt contents, completions, function arguments, and return values — is not captured. To capture message content as span attributes:

  • Pass capture_content=True when calling setup_export_to_coralogix.
  • Set the environment variable OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT to true.

Most Coralogix AI evaluations require message contents to function properly, so enabling message capture is strongly recommended.

Semantic conventions

AttributeTypeDescriptionExample
gen_ai.prompt.<message_number>.rolestringRole of message author for user message <message_number>system, user, assistant, tool
gen_ai.prompt.<message_number>.contentstringContents of user message <message_number>What's the weather in Paris?
gen_ai.prompt.<message_number>.tool_calls.<tool_call_number>.idstringID of tool call in user message <message_number>call_O8NOz8VlxosSASEsOY7LDUcP
gen_ai.prompt.<message_number>.tool_calls.<tool_call_number>.typestringType of tool call in user message <message_number>function
gen_ai.prompt.<message_number>.tool_calls.<tool_call_number>.function.namestringThe name of the function used in tool call within user message <message_number>get_current_weather
gen_ai.prompt.<message_number>.tool_calls.<tool_call_number>.function.argumentsstringArguments passed to the function used in tool call within user message <message_number>{"location": "Seattle, WA"}
gen_ai.prompt.<message_number>.tool_call_idstringTool call ID in user message <message_number>call_mszuSIzqtI65i1wAUOE8w5H4
gen_ai.completion.<choice_number>.rolestringRole of message author for choice <choice_number> in model responseassistant
gen_ai.completion.<choice_number>.finish_reasonstringFinish reason for choice <choice_number> in model responsestop, tool_calls, error
gen_ai.completion.<choice_number>.contentstringContents of choice <choice_number> in model responseThe weather in Paris is rainy and overcast, with temperatures around 57°F
gen_ai.completion.<choice_number>.tool_calls.<tool_call_number>.idstringID of tool call in choice <choice_number>call_O8NOz8VlxosSASEsOY7LDUcP
gen_ai.completion.<choice_number>.tool_calls.<tool_call_number>.typestringType of tool call in choice <choice_number>function
gen_ai.completion.<choice_number>.tool_calls.<tool_call_number>.function.namestringThe name of the function used in tool call within choice <choice_number>get_current_weather
gen_ai.completion.<choice_number>.tool_calls.<tool_call_number>.function.argumentsstringArguments passed to the function used in tool call within choice <choice_number>{"location": "Seattle, WA"}
gen_ai.request.tools.<tool_number>.typestringType of tool entry in tools listfunction
gen_ai.request.tools.<tool_number>.function.namestringThe name of the function to use in tool callsget_current_weather
gen_ai.request.tools.<tool_number>.function.descriptionstringDescription of the functionGet the current weather in a given location
gen_ai.request.userstringA unique identifier representing the end user (from the user_id passed to session_service.create_session(...))[email protected]

Next steps

Once your integration is set up, explore the AI Center Overview to monitor performance, costs, quality issues, and security across all your AI applications — and to set up Guardrails for real-time policy enforcement.