 Darren Hinde
|
699b2d7769
ci(security): phase-1 CI hardening — affected-area tests, least privilege, action pinning, dependency governance (#336)
|
3 nedēļas atpakaļ |
|
Darren Hinde
|
926d68de93
fix(evals): repair deterministic eval baseline (behavioral regressions + tsc build) (#334)
|
3 nedēļas atpakaļ |
|
Darren Hinde
|
784ffadf92
chore: verify and stabilize main branch (#42)
|
7 mēneši atpakaļ |
 Alexander Daza
|
e81f71bdac
feat: ExecutionBalanceEvaluator and docs (#27)
|
7 mēneši atpakaļ |
|
Darren Hinde
|
fc29fa3dc4
feat: add PR template and automated doc sync workflow (#40)
|
7 mēneši atpakaļ |
|
Darren Hinde
|
4103805270
Add build validation system and OpenAgent evaluation framework (#26)
|
8 mēneši atpakaļ |
|
darrenhinde
|
e43eaff317
feat(evals): add BehaviorEvaluator and improve test validation
|
8 mēneši atpakaļ |
|
darrenhinde
|
478c8e3e85
feat: implement SDK-based evaluation framework with real agent testing
|
8 mēneši atpakaļ |
|
darrenhinde
|
f4b3d56aa2
Add evaluation framework structure and OpenCode logging documentation
|
8 mēneši atpakaļ |
