fix: avoid duplicate token usage on llm fallback spans - #7532
Draft
chenghao-mou wants to merge 1 commit into
Draft
chenghao-mou wants to merge 1 commit into
chenghao-mou wants to merge 1 commit into
Conversation
Co-authored-by: Sanjay Kukadiya <43816307+SanjuMLGeek@users.noreply.github.com>
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fallback wrappers repeat token usage from the serving provider request. Record GenAI usage only on the provider span, while preserving LLM metrics.
Adopts @SanjuMLGeek’s usage guard from #7396.
Addresses AGT-3602
Request summary and agent context
Model: GPT-6-Astra
Split the proposed telemetry improvements into focused PRs that are easy to review and revert. Use general problem summaries and omit customer details.