
cflmyandCursor
224b3d4a66
test(repair): §5.2(a) 模型在环修复实验 —— 锚点消融:anchor 100%(20/20) vs plain 85%,≥80% 目标达成
- tests/repair_experiment.rs:真实消费 validate → repair_targets → 模型行编辑 → repair_apply(越界必拒)
→ 复验 的完整闭环(≤2 轮;容错重试;cflmy @ llm.cflmy.cn,.env 读取,#[ignore] 不进常规回归)
- 双臂消融:anchor(诊断带 doc_anchor/doc_quote/suggestion)vs plain(剥掉)——
anchor 一轮修复 20/20=100%;plain 17/20=85%(3 例失败均为网络空体抖动)
- tests/common/mod.rs:golden 20 例与诊断/应用共享件抽出(repair_loop + experiment 同源)
- parse_edits 容错(数组/单对象/字符串化元素/围栏);越界必拒/abstain 由 repair_loop 硬断言覆盖
- 报告:doc/roadmap/repair-experiment-2026-09-22.md;.gitignore 补 .env(密钥不入库)
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-22 21:10:03 +08:00
..
2026-08-11 09:45:08 +08:00
2026-09-04 08:46:05 +08:00
2026-09-04 09:11:36 +08:00
2026-09-04 10:13:28 +08:00
2026-09-04 08:46:05 +08:00
2026-09-14 10:16:48 +08:00
2026-09-04 11:24:50 +08:00
2026-09-07 22:14:51 +08:00
2026-09-07 16:13:22 +08:00
2026-08-28 15:46:02 +08:00
2026-09-07 22:14:51 +08:00
2026-09-01 10:06:56 +08:00
2026-09-14 13:39:12 +08:00
2026-09-14 16:05:29 +08:00
2026-09-09 09:42:13 +08:00
2026-08-10 11:58:26 +08:00
2026-08-11 10:07:03 +08:00
2026-09-22 21:10:03 +08:00
2026-09-09 09:42:13 +08:00
2026-09-09 09:04:29 +08:00
2026-09-14 10:44:18 +08:00
2026-09-22 21:10:03 +08:00
2026-09-22 17:46:09 +08:00