EvalReport
What runEvals returns and `threads eval --out` writes: per-case results, counts, the one-line summary, model calls and cost.
No timestamps, so an offline report is byte-stable in both languages.
type EvalReport = EvalReport;What runEvals returns and `threads eval --out` writes: per-case results, counts, the one-line summary, model calls and cost.
No timestamps, so an offline report is byte-stable in both languages.
type EvalReport = EvalReport;