Preserve explicit passed when handling _result/_label keys#46836
Open
m7md7sien wants to merge 6 commits into
Open
Preserve explicit passed when handling _result/_label keys#46836m7md7sien wants to merge 6 commits into
passed when handling _result/_label keys#46836m7md7sien wants to merge 6 commits into
Conversation
In `_update_metric_value`, the `_result`/`result`/`_label` branch unconditionally derived `passed` from the label value for `azure_ai_evaluator` criteria, overwriting any `passed` already set by an earlier `metric_key == "passed"` iteration. Guard the derivation with `"passed" not in metric_dict` so an explicitly provided `passed` value is preserved.
github-actions
Bot
added
the
Evaluation
Contributor
|
add unit tests |
Contributor
There was a problem hiding this comment.
Pull request overview
This PR fixes a metrics-parsing edge case in azure-ai-evaluation where _update_metric_value could overwrite an explicitly provided passed value while processing *_result / result / *_label keys for azure_ai_evaluator criteria.
Changes:
- Guard
passedderivation in_update_metric_valuewith"passed" not in metric_dictto preserve an explicitly suppliedpassed. - Add unit tests (plus small helper coverage through
_extract_metric_valuesand_process_criteria_metrics) to ensure explicitpassedis preserved and derivation still occurs when absent.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluate/_evaluate.py |
Prevents label-based passed derivation from overwriting an existing passed value for azure_ai_evaluator. |
sdk/evaluation/azure-ai-evaluation/tests/unittests/test_evaluate.py |
Adds regression tests covering preservation of explicit passed and expected derivation behavior when passed is not provided. |
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
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.
Description
In
_update_metric_value, the_result/result/_labelbranch unconditionally derivedpassedfrom the label value forazure_ai_evaluatorcriteria, overwriting anypassedalready set by an earliermetric_key == "passed"iteration.Guard the derivation with
"passed" not in metric_dictso an explicitly providedpassedvalue is preserved.All SDK Contribution checklist:
General Guidelines and Best Practices
Testing Guidelines