feat(google-adk): add ADK instrumentation and e2e coverage

[Abhijeet Prasad (AbhiPrasad)]

resolves #1477

Add Braintrust instrumentation for @google/adk with auto-instrumentation support by default when users run with Braintrust's loader hook.

This adds tracing for:

• Runner.runAsync
• BaseAgent.runAsync and subclasses
• FunctionTool.runAsync

It also adds Google ADK e2e coverage for both hook-driven and wrapped execution.

Because ADK uses @google/genai under the hood, underlying LLM spans continue to come from the existing Google GenAI instrumentation.

Recommended usage: auto-instrumentation

The primary way users should adopt this is via Braintrust auto-instrumentation:

node --import braintrust/hook.mjs app.mjs

Then they can use @google/adk normally and Braintrust will trace supported ADK operations automatically.

Example:

import * as adk from "@google/adk";
import { initLogger } from "braintrust";

initLogger({ projectName: "my-google-adk-app" });

const agent = new adk.LlmAgent({
  name: "weather_agent",
  model: "gemini-2.5-flash-lite",
  instruction: "Answer weather questions",
});

const runner = new adk.InMemoryRunner({ agent, appName: "weather-app" });

await runner.sessionService.createSession({
  appName: runner.appName,
  userId: "user-1",
  sessionId: "session-1",
});

for await (const event of runner.runAsync({
  userId: "user-1",
  sessionId: "session-1",
  newMessage: {
    role: "user",
    parts: [{ text: "What's the weather in Paris?" }],
  },
})) {
  console.log(event);
}

If needed, it can be disabled with:

BRAINTRUST_DISABLE_INSTRUMENTATION=google-adk node --import braintrust/hook.mjs app.mjs

Manual usage

Manual wrapping is also available for cases where users want explicit control:

import * as adk from "@google/adk";
import { wrapGoogleADK } from "braintrust";

const wrapped = wrapGoogleADK(adk);

Testing

• added Google ADK plugin/unit coverage
• added Google ADK e2e scenario and snapshots
• validated both auto-hook and wrapped execution paths

[socket-security]

Review the following changes in direct dependencies. Learn more about Socket for GitHub.

Diff	Package	Supply Chain Security	Vulnerability	Quality	Maintenance	License
	next@​14.2.34 ⏵ 15.5.15	-19	+26	-3	+47
	jest@​29.7.0
	@​types/​uuid@​10.0.0 ⏵ 9.0.8
	@​temporalio/​ai-sdk@​1.15.0
	@​temporalio/​envconfig@​1.15.0
	@​ai-sdk/​openai@​2.0.53 ⏵ 3.0.52	+2		+4
	@​ai-sdk/​mcp@​1.0.35
	@​ai-sdk/​provider@​3.0.2 ⏵ 3.0.8	+1		+2	+1
	@​braintrust/​temporal@​0.1.1-rc.0
	@​types/​jest@​29.5.14
	ts-node@​10.9.2
	tsx@​3.14.0
	ai@​5.0.76 ⏵ 6.0.154	+4
	react-dom@​18.3.1 ⏵ 19.2.5	+8		+1
	ts-jest@​29.4.9
	@​opentelemetry/​sdk-node@​0.201.1 ⏵ 0.53.0	+1
	@​modelcontextprotocol/​sdk@​1.29.0
	@​playwright/​test@​1.59.1
	react@​19.2.4 ⏵ 19.2.5	+1		+17	+4

View full report

[Abhijeet Prasad (AbhiPrasad)]

wait this need some more work. I realized the parent child relationships are wrong 😢

[Luca Forstner (lforst)]

The tests in this entire file seem rather shallow. Would honestly just remove them to spare our clankers from using context for them.

[Luca Forstner (lforst)]

Let's also add the google-adk scenarios to the e2e test summary for CI. I've used that quite a bit.

[Luca Forstner (lforst)]

wait this need some more work. I realized the parent child relationships are wrong 😢

I honestly don't know why this is so painful in this SDK. Tracing channels make it harder because they are event based. It should honestly just be a simple wrapping call imo.