Commit Graph
4 Commits
Author SHA1 Message Date
DottaandPaperclip fce64fe2f2 test(evals): keep CLI guidance inside the original clock
Pass the already established case deadline into the two CLI guidance waits and validate it before and after observation. Preserve command grammar, scoped CLI actor and saved-state oracles.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-11-02 20:18:31 -06:00
Dotta 78d113f3a7 fix(evals): preserve supported CLI task status and owned feedback gate 2026-10-27 07:17:18 -05:00
Dotta b33f3b8b64 test(e2e): author bounded privileged operator journeys 2026-10-26 19:12:54 -05:00
Dotta cada0b6ec4 eval: author owned operator and developer reference cases 2026-10-26 18:18:30 -05:00