OG T
3256142d29
feat(api): ADR-030 Phase 5 持續學習迴圈
從執行結果中學習，持續優化決策：
1. learning_service.py - 持續學習服務
- process_execution_result(): 處理執行結果
- process_human_feedback(): 處理人工反饋
- 自動調整信任度 (成功+1 / 失敗歸零)
- 更新 Playbook 統計
- 成功案例自動萃取 Playbook
2. approval_execution.py - 整合學習觸發
- 執行成功後觸發學習
- 執行失敗後觸發學習
- _trigger_learning(): 非阻塞呼叫學習服務
學習流程:
執行完成 → LearningService.process_execution_result()
├─ 成功: TrustEngine +1 分 + Playbook 統計更新
└─ 失敗: TrustEngine 歸零 + 記錄失敗原因
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-26 22:19:41 +08:00
..
2026-03-25 16:08:49 +08:00
2026-03-25 09:26:58 +08:00
2026-03-26 19:25:52 +08:00
2026-03-26 16:06:20 +08:00
2026-03-26 16:03:16 +08:00
2026-03-26 15:32:52 +08:00
2026-03-25 21:26:23 +08:00
2026-03-26 22:19:41 +08:00
2026-03-26 22:13:10 +08:00
2026-03-26 16:06:20 +08:00
2026-03-26 16:06:20 +08:00
2026-03-26 15:32:52 +08:00
2026-03-24 09:20:56 +08:00
2026-03-23 23:51:37 +08:00
2026-03-26 22:13:10 +08:00
2026-03-26 21:55:50 +08:00
2026-03-22 18:57:44 +08:00
2026-03-26 16:03:16 +08:00
2026-03-26 16:06:20 +08:00
2026-03-25 09:26:58 +08:00
2026-03-26 10:08:54 +08:00
2026-03-24 12:57:36 +08:00
2026-03-24 12:57:36 +08:00
2026-03-26 19:25:52 +08:00
2026-03-26 12:49:30 +08:00
2026-03-25 15:41:42 +08:00
2026-03-26 13:06:47 +08:00
2026-03-26 15:32:52 +08:00
2026-03-26 21:55:50 +08:00
2026-03-26 19:34:37 +08:00
2026-03-26 22:19:41 +08:00
2026-03-26 10:01:57 +08:00
2026-03-26 15:32:52 +08:00
2026-03-26 12:49:30 +08:00
2026-03-26 21:55:50 +08:00
2026-03-25 23:00:03 +08:00
2026-03-26 22:08:15 +08:00
2026-03-26 22:08:15 +08:00
2026-03-24 10:48:15 +08:00
2026-03-26 16:03:16 +08:00
2026-03-26 16:06:20 +08:00
2026-03-26 12:49:30 +08:00
2026-03-26 16:06:20 +08:00
2026-03-26 13:06:47 +08:00
2026-03-26 15:32:52 +08:00
2026-03-26 16:06:20 +08:00
2026-03-26 22:10:52 +08:00
2026-03-24 09:20:56 +08:00
2026-03-26 16:06:20 +08:00
2026-03-26 22:13:10 +08:00