You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Event processor migration: Vercel AI event processor #20377
Another tough one: The vercel AI event processor does a lot of post processing:
setting/removing attributes on a single ended span (processEndedVercelAiSpan, applyToolDescriptionsAndTokens) should be easy to port to client.processSpan
We accumulate token usage data on parent spans (accumulateTokensForParent, applyAccumulatedTokens). This can become more dangerous because to guarantee continued correctness, we need a guarantee that the child spans end before their parent so that we can accumulate at end time. This might need careful investigation if its the case. Otherwise we loose accuracy.
A note on this: After talking with @alexander-alderman-webb: Instead of continuing to accumulate the token usage stuff, maybe we can switch already to only record the attributes on the child span level and avoid setting anything on parent spans. This should reduce the complexity for streamed spans.
Activity
linear-code commentedon Apr 17, 2026
JS-2214
Lms24 commentedon Apr 17, 2026
A note on this: After talking with @alexander-alderman-webb: Instead of continuing to accumulate the token usage stuff, maybe we can switch already to only record the attributes on the child span level and avoid setting anything on parent spans. This should reduce the complexity for streamed spans.
feat(core): Migrate Vercel AI event processor to span streaming (#20608)
github-actions commentedon May 7, 2026
A PR closing this issue has just been released 🚀
This issue was referenced by PR #20608, which was included in the 10.52.0 release.