Commit Graph

205 Commits

Author SHA1 Message Date
jxxghp
1cb1f02f19 fix(auth): normalize site authentication parameters 2026-09-14 13:24:14 +08:00
jxxghp
c60949ffff Merge branch 'v3' into feat/plugin-instance-config-logging 2026-09-13 14:30:42 +08:00
jxxghp
8072b7d78f Refactor application architecture and compatibility boundaries 2026-09-13 12:53:00 +08:00
Aqr-K
d6509f092c chore(plugin): 技能表目录登记补进生成脚本并补迁移往返验证
技能文档 skills/database-operation/SKILL.md 的核心表清单是
scripts/generate_agent_skill_docs.py 里 DATABASE_TABLE_GUIDES 的生成物,
前面两笔改动却是手改产物登记 plugininstance,任何人重跑生成器都会把它弄丢。
把条目补进字典,再用生成器重出该文档。

同时补上 agentinvocation:官方 v3 已有该表但字典里没有,生成器因此直接抛
ValueError,不补就根本跑不起来。它的说明照抄文档里现有的那份手写文案,
避免登记动作反而把已有描述改瘦。

迁移测试原本只按单个 revision 直接调 upgrade(),绕过了 Alembic 自己的版本
解析与记账,链接错的 down_revision、少写的 downgrade、重复升级时的重复建表
都测不出来。新增用例改走 alembic.command,在落盘的临时库上从官方 head
b2d4f6a8c1e3 升到链尾 487f7e681955 再降回去,验证配置与描述符确实落到
plugininstance、旧 plugin.* 键就地移除而 PluginInstances 键按回滚依据保留。
2026-09-12 19:48:57 -04:00
jxxghp
509eac75fc test(agent): hydrate native child thread history 2026-09-12 11:56:44 +08:00
jxxghp
b6ba20371e test(agent): infer native subagent terminal scopes 2026-09-12 07:12:16 +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
e66aec60fb test(evaluation): require native terminal input events 2026-09-12 04:37:02 +08:00
jxxghp
c0a67d4f40 test(agent): cover subagent cancellation recovery 2026-09-12 03:56:26 +08:00
jxxghp
2d6027e393 fix(agent): verify steering boundary in evaluation 2026-09-12 02:36:59 +08:00
jxxghp
ee52ca0705 test(agent): wire native browser harness 2026-09-12 00:50:00 +08:00
jxxghp
8170eadf62 feat(agent): validate delegated read-only subtasks 2026-09-11 21:58:30 +08:00
jxxghp
2b5cb07547 test(agent): close native pty evaluation parity 2026-09-11 19:26:32 +08:00
jxxghp
d22fa746fd fix(agent): ignore expected app-server reader cancellation 2026-09-11 18:57:03 +08:00
jxxghp
2149dce8cc feat(agent): drive terminal parity through app-server 2026-09-11 18:42:17 +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
3cfbf9dbcf eval: add command and browser parity evidence 2026-09-11 11:16:28 +08:00
jxxghp
ae1187bd3f feat(module): add dynamic module switches and catalogs 2026-09-11 10:31:53 +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
0f8aa4dfa9 fix(agent): return operation input contracts on errors 2026-09-11 08:07:54 +08:00
jxxghp
13b4fe1128 merge: sync remote skill loading optimization 2026-09-11 07:54:02 +08:00
jxxghp
f5bc72ff44 fix(agent): load split skill docs through read_skill 2026-09-11 07:50:18 +08:00
jxxghp
c5a5eb0da0 feat(evaluation): capture tool catalog implementation evidence 2026-09-11 07:47:19 +08:00
jxxghp
b4cf40d46a Merge remote-tracking branch 'origin/v3' into codex/agent-evaluation-20260909
# Conflicts:
#	skills/moviepilot-api/api/download.md
2026-09-11 07:32:54 +08:00
jxxghp
a731cc0ce6 docs(agent): record Gemini evaluation and harness boundaries 2026-09-11 07:22:37 +08:00
jxxghp
7195a29c33 fix(evaluation): scope skill file reads to temp agent 2026-09-11 07:08:48 +08:00
jxxghp
a2f40ceecc refactor(agent): expose split skill files in evaluation 2026-09-11 07:03:12 +08:00
jxxghp
74db54f067 refactor(agent): keep one general subagent profile 2026-09-11 06:48:00 +08:00
jxxghp
7ab8cddccb feat(evaluation): support chat completions providers 2026-09-11 06:26:26 +08:00
jxxghp
1a1aa59838 docs(architecture): move refactor documents 2026-09-11 06:20:59 +08:00
jxxghp
abd3cea92b feat(agent): queue steering input during active runs 2026-09-11 05:17:37 +08:00
jxxghp
d32d17568a fix(runtime): apply configuration changes without restart 2026-09-11 00:12:05 +08:00
jxxghp
d096a1380d docs(agent): split moviepilot api skill contracts 2026-09-10 23:00:16 +08:00
jxxghp
f383a8a5a3 feat(agent): 接入媒体自动分类策略 API 2026-09-10 22:36:50 +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
yanjunpu
89917a7baf docs: classify music library status route 2026-09-09 17:01:12 +08:00
jxxghp
5a214afc19 fix(subscribe): keep scheduled searches progressing across site retries 2026-09-09 16:45:42 +08:00
jxxghp
658cd4a9be fix(music): preserve track identity and normalize resource metadata 2026-09-09 15:52:16 +08:00
jxxghp
9e1c25124b fix(transfer): restore regression and architecture gates 2026-09-09 13:40:35 +08:00
jxxghp
a69c9073cb feat(transfer): implement recovery commands for discarding corrupt tasks 2026-09-08 23:15:38 +08:00
jxxghp
c41dc69596 fix: remove stale runtime profile import 2026-09-06 22:15:36 +08:00