Use unique user_id per ADK agent to prevent session leakage#63
Merged
Conversation
Generate a unique user_id (using uuid4) for each GeminiADKAgent instance and regenerate it on reset(). This prevents any potential ADK-side caching or session state leakage when the same underlying LlmAgent is shared across test scenarios.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
user_idfor eachGeminiADKAgentinstance and onreset()to prevent ADK-side caching or session state leakage between test scenariosProblem
Agent responses sometimes contained content from different scenarios (e.g., asked about "Find Phoenix Race" but got tire degradation analysis). Root cause: shared
LlmAgentsingleton + hardcodeduser_id = "mcprobe_user"allowed ADK session state to leak across scenarios.Test plan