darrenhinde
|
8581a423a9
feat(cli): run on plain Node so npm i -g works without Bun
|
2 weeks ago |
darrenhinde
|
597fa75b9a
chore(repo): move every package to the @controlstack scope
|
2 weeks ago |
darrenhinde
|
2dba195a7f
chore(workspace): migrate repository development to pnpm
|
2 weeks ago |
darrenhinde
|
5881767df1
chore(release): reconcile all manifests to single version 1.1.0
|
2 weeks ago |
Darren Hinde
|
699b2d7769
ci(security): phase-1 CI hardening — affected-area tests, least privilege, action pinning, dependency governance (#336)
|
2 weeks ago |
Darren Hinde
|
926d68de93
fix(evals): repair deterministic eval baseline (behavioral regressions + tsc build) (#334)
|
2 weeks ago |
Darren Hinde
|
784ffadf92
chore: verify and stabilize main branch (#42)
|
7 months ago |
Alexander Daza
|
e81f71bdac
feat: ExecutionBalanceEvaluator and docs (#27)
|
7 months ago |
Darren Hinde
|
fc29fa3dc4
feat: add PR template and automated doc sync workflow (#40)
|
7 months ago |
Darren Hinde
|
4103805270
Add build validation system and OpenAgent evaluation framework (#26)
|
8 months ago |
darrenhinde
|
e43eaff317
feat(evals): add BehaviorEvaluator and improve test validation
|
8 months ago |
darrenhinde
|
478c8e3e85
feat: implement SDK-based evaluation framework with real agent testing
|
8 months ago |
darrenhinde
|
f4b3d56aa2
Add evaluation framework structure and OpenCode logging documentation
|
8 months ago |