Repository navigation
fix(openai-agents): Record reasoning tokens as metric - #2805
Merged
Abhijeet Prasad (AbhiPrasad) merged 2 commits intoNov 18, 2026
Merged
Abhijeet Prasad (AbhiPrasad) merged 2 commits into
Abhijeet Prasad (AbhiPrasad) merged 2 commits into
Conversation
Abhijeet Prasad (AbhiPrasad)
approved these changes
Nov 18, 2026
Abhijeet Prasad (AbhiPrasad)
enabled auto-merge (squash)
November 18, 2026 19:52
Member
|
thanks for the PR Dylan Pulver (@dylanpulver)! |
Abhijeet Prasad (AbhiPrasad)
merged commit Nov 18, 2026
d0207e3
into
braintrustdata:main
56 checks passed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The Agents SDK's response span carries
usage.output_tokens_details.reasoning_tokens, andparseUsageMetricsin the trace processor never read it, so agent LLM spans had nocompletion_reasoning_tokens. The OpenAI wrapper already records it from the same usage shape (parseMetricsFromUsageinjs/src/openai-utils.ts), and #2393 did the same for LangChain.Zero is recorded, not dropped, matching
prompt_cached_tokens: 0in the existing snapshots. Snapshot churn is 8 added lines, allcompletion_reasoning_tokens, both sides of each span-tree pair, no cassette changes.Ran the instrumentation test file (the new test fails on
mainon its assertion),check:typings,formatting,lint, and the openai-agents e2e scenario twice. Not run: the full unit and e2e suites.