You'll notice
Session usage totals now use whichever of two token counts is higher
What
The total token count reported at the end of a run (shown in the run summary as usage.total_tokens / usage.totalTokens) is now calculated by comparing two separate token totals and taking the larger of the two, instead of relying on a single calculation.
Why
This should make the reported usage number more reliable when the two underlying counting methods disagree, since the higher figure is used rather than potentially undercounting.
Names in the bundleusage.total_tokens
Documented inapi/cli-sdks-libraries/libraries/openai-sdk