Repository navigation
Fix Azure OpenAI trace attribution and expose content-filter rejections - #542
Merged
Merged
Conversation
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Foundry chat-completion calls were labeled azure-ocr, and Tempo showed only HTTP 400 without the rejection reason. Recognize Azure OpenAI paths on Cognitive Services hosts and label these calls azure-openai.
Message and reaction triage spans now display Azure content-filter rejection and the category/severity in their names and status descriptions, with searchable reason attributes. The reason is attached to the enclosing triage span because the HTTP child has already finished when the SDK exposes the response body.
Validation: all 133 Vahter container-free tests passed; mandatory comment-ratio hook and diff checks passed. Applies to new traces after deployment.