Skip to content

fix(eval): preserve custom eval metadata#5908

Open
he-yufeng wants to merge 1 commit into
google:mainfrom
he-yufeng:fix/eval-model-extra-metadata
Open

fix(eval): preserve custom eval metadata#5908
he-yufeng wants to merge 1 commit into
google:mainfrom
he-yufeng:fix/eval-model-extra-metadata

Conversation

@he-yufeng
Copy link
Copy Markdown
Contributor

Summary

  • allow eval models to carry custom metadata fields instead of rejecting them as extras
  • cover both top-level EvalCase metadata and nested SessionInput metadata in serialization

Fixes #5906

To verify

  • PYTHONUTF8=1 uv run --with pytest pytest tests/unittests/evaluation/test_eval_case.py -q
  • PYTHONUTF8=1 uv run ruff check src/google/adk/evaluation/common.py tests/unittests/evaluation/test_eval_case.py
  • PYTHONUTF8=1 uv run pyright src/google/adk/evaluation/common.py
  • PYTHONUTF8=1 uv run python -m py_compile src/google/adk/evaluation/common.py tests/unittests/evaluation/test_eval_case.py
  • git diff --check

@adk-bot adk-bot added the eval [Component] This issue is related to evaluation label May 30, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

eval [Component] This issue is related to evaluation

Projects

None yet

Development

Successfully merging this pull request may close these issues.

EvalBaseModel extra='forbid' rejects custom fields in session_input and eval cases

2 participants