fix(ai-sdk): Make sure tokens are not double counted between parent/child spans#1379
Merged
Abhijeet Prasad (AbhiPrasad) merged 3 commits intomainfrom Feb 19, 2026
Merged
Conversation
When the model is wrapped by wrapAISDK, child doGenerate/doStream spans already carry per-step token counts and estimated_cost. Previously, the parent span (generateText, streamText, generateObject, streamObject, and agent wrappers) also logged the same aggregated metrics, causing the Braintrust backend to double-count both tokens and cost. This change omits all token/cost metrics from the parent span when the model is wrapped (i.e. child spans exist), so that metrics are only reported once on the leaf LLM call spans. Updated tests to assert that parent spans no longer carry token metrics and that child doGenerate/doStream spans do. Co-authored-by: Cursor <cursoragent@cursor.com>
Abhijeet Prasad (AbhiPrasad)
changed the title
4 tasks
Stephen Belanger (Qard)
approved these changes
Feb 18, 2026
Abhijeet Prasad (AbhiPrasad)
added a commit
that referenced
this pull request
Feb 19, 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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
fixes https://linear.app/braintrustdata/issue/BRA-4144
supercedes #1377
Big thanks to Andrei Dorobantu (@andrewdoro) for the original PR! This is just their fix, cleaned up a bit to reduce redundant code.