História revízii

Autor SHA1 Správa Dátum
  Darren Hinde 926d68de93 fix(evals): repair deterministic eval baseline (behavioral regressions + tsc build) (#334) 2 týždňov pred
  Alexander Daza e81f71bdac feat: ExecutionBalanceEvaluator and docs (#27) 7 mesiacov pred
  darrenhinde e43eaff317 feat(evals): add BehaviorEvaluator and improve test validation 8 mesiacov pred
  darrenhinde 478c8e3e85 feat: implement SDK-based evaluation framework with real agent testing 8 mesiacov pred