4 Commits

Author	SHA1	Message	Date
jxxghp	abd3cea92b	feat(agent): queue steering input during active runs	2026-09-11 05:17:37 +08:00
jxxghp	6b40ada479	feat(agent): add controlled native Codex evaluation runner	2026-09-10 03:23:55 +08:00
jxxghp	1899f63c75	test(agent): run bounded live models through isolated production harness	2026-09-09 22:45:38 +08:00
jxxghp	aca9b00db2	test(agent): add isolated task world and evidence-based evaluation	2026-09-09 22:01:34 +08:00