Define agent integration tests framework#100
Merged
Merged
Conversation
kalenkevich
force-pushed
the
chore/integration_tests
branch
4 times, most recently
from
ddc0c5b to
cb3b454
Compare
ScottMansfield
approved these changes
Feb 2, 2026
Member
ScottMansfield
left a comment
ScottMansfield
left a comment
There was a problem hiding this comment.
Approved after an offline conversation. This is good for now as a stopgap but we will be integrating with the conformance testing soon so some of this will be redone.
kalenkevich
force-pushed
the
chore/integration_tests
branch
from
cb3b454 to
f9aa502
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
This PR introduces an integration testing framework for agents, enabling deterministic testing with mocked model responses.
Key Changes:
Testing Utilities (tests/integration/agents/test_case_utils.ts):
Implemented
MockGenAIClientandGeminiWithMockResponsesto simulate LLM interactions using predefinedGenerateContentResponseobjects.Added
runTestCasehelper to execute agent flows, verify expected ADK Event sequences, and validate event structure (ignoring non-deterministic fields like IDs and timestamps).Reference Integration Test (
tests/integration/agents/simple_agent_with_tools/):LlmAgent("weather_time_agent") with get_weather and get_current_time tools to serve as a test subject.agent_test.ts) that runs a multi-turn conversation.This infrastructure allows for reliable, offline integration testing of agent behaviors and tool execution flows.