The Kimi Code usages endpoint returns resetTime on each limit's detail
object, while window carries only duration/timeUnit. buildWindow() only
reads window fields, so the 5h row parsed to a window with durationMs but
no resetsAt — and omp usage renders "resets in …" only when
window.resetsAt is set. The Total quota row worked because toUsageLimit
falls back to row.resetsAt when no window exists, but the row.window ??
short-circuit bypassed that fallback for the 5h row.
Carry the row-level reset onto the window when the window itself has
none; an explicit window resetTime still wins.
iacore
85e122cece