Fix MCP server reporting wrong model for ADK agents (#56)#57
Merged
Conversation
The server was using the judge's LLM model for the agent_model field instead of querying the actual agent. This caused reports to show all three components (judge, synthetic_user, agent) with the same model even when ADK agents use different models. Changes: - Capture agent.get_model_name() before closing the agent - Pass separate models for judge, synthetic_user, and agent - Extract config resolution into _resolve_scenario_configs helper to keep run_scenario within statement limit
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
When running scenarios via the MCP server, the test results incorrectly showed the judge's LLM model as the agent's model instead of the actual ADK agent's model.
Root Cause
In
server.py, the_build_test_resultfunction was receiving only the judge's model and using it for all three components:Solution
agent.get_model_name()before closing the agent_build_test_resultto accept separate models for judge, synthetic_user, and agent_resolve_scenario_configshelper to stay within statement limitsTest plan
Closes #56