47 Commits

Author	SHA1	Message	Date
jxxghp	3ffc64cfd6	feat(agent): complete integrated evaluation ... Validate persistent recall, learning carry-over, and controlled read-only Python orchestration in real graphs and isolated model scenarios.	2026-09-30 20:53:19 +08:00
jxxghp	b964ed21e7	test(agent): preserve native collaboration evidence	2026-09-12 07:10:21 +08:00
jxxghp	e0e1598681	test(agent): verify multiple steering boundaries	2026-09-12 06:44:03 +08:00
jxxghp	da33988c50	test(agent): evaluate shared parent terminals	2026-09-12 06:10:06 +08:00
jxxghp	a84f04aa51	test(agent): stabilize native pty completion evidence	2026-09-12 05:13:55 +08:00
jxxghp	918ba46e50	docs(agent): record repeated harness evidence	2026-09-12 04:49:04 +08:00
jxxghp	e66aec60fb	test(evaluation): require native terminal input events	2026-09-12 04:37:02 +08:00
jxxghp	c3d5941fc1	docs(agent): record terminal pipe recovery boundary	2026-09-12 04:19:25 +08:00
jxxghp	c0a67d4f40	test(agent): cover subagent cancellation recovery	2026-09-12 03:56:26 +08:00
jxxghp	380106b77a	fix(agent): preserve assistant identity across web stream events	2026-09-12 03:13:56 +08:00
jxxghp	c6aa22670f	docs(agent): record final steering commits	2026-09-12 02:50:15 +08:00
jxxghp	2d6027e393	fix(agent): verify steering boundary in evaluation	2026-09-12 02:36:59 +08:00
jxxghp	18e91b996d	docs(agent): record steering boundary CI	2026-09-12 00:25:45 +08:00
jxxghp	42a6ec6a9c	docs(agent): record applied steering boundary	2026-09-12 00:22:48 +08:00
jxxghp	b893ec38a4	docs(agent): record text boundary ordering	2026-09-12 00:07:49 +08:00
jxxghp	015bae4a9e	docs(agent): record final steering boundary	2026-09-12 00:01:44 +08:00
jxxghp	69d93dcb10	docs(agent): record queued event boundary	2026-09-11 23:56:27 +08:00
jxxghp	d6c9a4e184	docs(agent): record native browser boundary	2026-09-11 22:56:31 +08:00
jxxghp	17480cdc32	docs(agent): record third subagent parity run	2026-09-11 22:34:47 +08:00
jxxghp	7fcf6aace5	docs(agent): update steering evidence	2026-09-11 22:21:35 +08:00
jxxghp	46d80a7c6a	docs(agent): record repeated subagent parity	2026-09-11 22:12:18 +08:00
jxxghp	8170eadf62	feat(agent): validate delegated read-only subtasks	2026-09-11 21:58:30 +08:00
jxxghp	8fb15324e1	fix(agent): preserve exact identifiers in final reports	2026-09-11 21:39:02 +08:00
jxxghp	9f43816be5	docs(agent): record steering display order	2026-09-11 21:03:54 +08:00
jxxghp	30ff41968a	docs(agent): record repeated native parity evidence	2026-09-11 20:22:49 +08:00
jxxghp	0cfa92b888	docs(agent): record steering render parity fix	2026-09-11 20:04:23 +08:00
jxxghp	2b5cb07547	test(agent): close native pty evaluation parity	2026-09-11 19:26:32 +08:00
jxxghp	961c7b91c7	docs(agent): refresh terminal parity evidence	2026-09-11 19:02:34 +08:00
jxxghp	8704088ad5	docs(agent): record app-server terminal evidence	2026-09-11 18:46:44 +08:00
jxxghp	643efea1aa	fix(agent): preserve WebAgent event timeline	2026-09-11 16:44:05 +08:00
jxxghp	6fe5bb42c2	fix(agent): preserve queued messages and long context	2026-09-11 14:27:27 +08:00
jxxghp	c534665b8f	eval: add terminal session parity evidence	2026-09-11 12:18:57 +08:00
jxxghp	e7b1e2c6e1	fix(architecture): close module endpoint type ratchet	2026-09-11 11:36:35 +08:00
jxxghp	3cfbf9dbcf	eval: add command and browser parity evidence	2026-09-11 11:16:28 +08:00
jxxghp	0e26fe0dc9	eval: align native collaboration discovery	2026-09-11 10:23:26 +08:00
jxxghp	cca0dd4a6c	eval: add Codex OAuth parity comparison	2026-09-11 09:50:56 +08:00
jxxghp	556543023f	eval: switch live benchmark to native Gemini 3	2026-09-11 08:41:10 +08:00
jxxghp	27cb5d94ba	docs(agent): record skill loading and input feedback evidence	2026-09-11 08:08:30 +08:00
jxxghp	e288222bff	docs(agent): record latest Gemini evaluation evidence	2026-09-11 07:30:42 +08:00
jxxghp	a731cc0ce6	docs(agent): record Gemini evaluation and harness boundaries	2026-09-11 07:22:37 +08:00
jxxghp	b1639b25b6	docs(agent): record general subagent rollout	2026-09-11 06:10:53 +08:00
jxxghp	fb6859cc11	docs(agent): record latest provider evaluation round	2026-09-11 05:56:21 +08:00
jxxghp	34ec415d90	docs(agent): record final provider evaluation evidence	2026-09-11 05:24:10 +08:00
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