during run evaluation of a test case inferences could be NoneType which has no len attribute and error is

The problem

Reported in Google Agent Development Kit: during run evaluation of a test case inferences could be NoneType which has no len attribute and error is not caught.

The fix

ADK eval crashes with len() on NoneType when a test case's inference failed: in localevalservice.py the code calls len(inferenceresult.inferences) without a None check. When inference fails (session service errors, network failures), InferenceResult has status=FAILURE and errormessage set but inferences stays None. The fix (PR #3805): in evaluate(), filter out failed inferences first, i.e. if inferenceresult.status == InferenceStatus.FAILURE or inferenceresult.inferences is None, log a warning and return EvalStatus.NOT_EVALUATED instead of evaluating. Upgrade ADK past the release containing that fix.

In gh:google/adk-python#2729 (https://github.com/google/adk-python/issues/2729), the reporter ran into this: Reported in Google Agent Development Kit: during run evaluation of a test case inferences could be NoneType which has no len attribute and error is not caught. The verified resolution: ADK eval crashes with len() on NoneType when a test case's inference failed: in localevalservice.py the code calls len(inferenceresult.inferences) without a None check. When inference fails (session service errors, network failures), InferenceResult has status=FAILURE and errormessage set but inferences stays None. The fix (PR #3805): in evaluate(), filter out failed inferences first, i.e. if inferenceresult.status == InferenceStatus.FAILURE or inferenceresult.inferences is None, log a warning and return EvalStatus.NOT_EVALUATED instead of evaluating. Upgrade ADK past the release containing that fix.