This is an unfortunate regression that was introduced during a recent refactoring.
The metrics returned from the Azure AI Foundry Evaluation service have different names than the ones we use in the Safety library. We translate the EvaluationMetric.Name name of the metrics returned by the service to the more display friendly names before returning the metrics to the caller.
While the returned metrics were correctly patched up, the EvaluationResult.Metrics dictionary still stored metrics by the original names returned by the service. Unfortunately, this means EvaluationResult.Get now throws an exception when trying to fetch metric with name ViolenceEvaluator.ViolenceMetricName. The fix would be to patch up the keys in the dictionary as well.