EvalCaseResult

One case's status (passed, failed, stale, skipped, error, not_run), its reason and each check that ran.

type EvalCaseResult = EvalCaseResult;

EvalReport

What runEvals returns and `threads eval --out` writes: per-case results, counts, the one-line summary, model calls and cost.

Verdict

The judge's verdict on one rubric criterion, numbered from 1.