test: improve multiturn conversation eval test - #1836

Merged

myhoai merged 5 commits into

QA-29448-multiturn-context-eval

Oct 1, 2026

Commits on Oct 1, 2026

fix(gooddata-eval): do not retry a turn that hit the iteration limit
myhoai
committed
26f2813
fix(gooddata-eval): keep metrics the agent only updated during cleanup
myhoai
committed
4a64094
feat(gooddata-eval): grade conversations on keeping context
myhoai
committed
f9b198e
test(gooddata-eval): cover the clarification judge and simulated user
myhoai
committed
c66ac11
test(gooddata-eval): annotate the conversation tests, drop the openai patches
myhoai
committed
ee39a75