FEAT: Capture token usage from ChatCompletion response in OpenAIChatTarget#1476
Merged
rlundeen2 merged 3 commits intoAzure:mainfrom Mar 17, 2026
Merged
FEAT: Capture token usage from ChatCompletion response in OpenAIChatTarget#1476rlundeen2 merged 3 commits intoAzure:mainfrom
rlundeen2 merged 3 commits intoAzure:mainfrom
Conversation
…arget Store response.usage (prompt_tokens, completion_tokens, total_tokens, cached_tokens, model_name) in the first response piece's labels under the 'token_usage' key. This enables downstream consumers like azure-ai-evaluation to track per-row token usage when using OpenAIChatTarget as a prompt target. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
rlundeen2
reviewed
Mar 16, 2026
rlundeen2
reviewed
Mar 16, 2026
- Move token_usage storage from labels to prompt_metadata (flat keys with token_usage_ prefix) for type safety with dict[str, Union[str, int]] - Add unit tests: token usage capture, no-usage case, missing attr defaults - Add integration test: validates real API responses contain token usage Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
rlundeen2
approved these changes
Mar 17, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Store response.usage (prompt_tokens, completion_tokens, total_tokens, cached_tokens, model_name) in the first response piece's labels under the 'token_usage' key. This enables downstream consumers like azure-ai-evaluation to track per-row token usage when using OpenAIChatTarget as a prompt target.
Description
Tests and Documentation