 cflmyandCursor
|
5fffb800f9
|
P4(b) 收口:mimo-v2.6-pro 两跑均端点 infra 不可评估,判据以 deepseek-flash 为准
- perf-validation-report §3 记录重跑终局(12/12→11/12 infra),(b) 判据判定不改
- three-problems-plan Phase 4 落地记录同步
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-23 13:10:28 +08:00 |
|
 cflmyandCursor
|
1a729eb9ec
|
P4 验证执行:(a)锚点消融✅/(c)契约消融✅/(d)防漂移✅/(e)守卫演练✅;(b)盲测 deepseek-flash 完成未达标、mimo-v2.6-pro 重跑中
- perf-validation.md:五实验协议/判据/材料(2026-09-23 自设计)
- perf-validation-report-2026-09-23.md:汇总报告(判据逐项对照 + 诚实结论)
- tests/blind_experiment.rs + tests/blind/:盲测 harness(查询通道/修复回路/usage 计量)+ 冻结材料(6 任务书 + docs-bundle)
- tests/contract_ablation.rs:四边界×三情形消融(拦截 100%/误报 0%/零回归)
- tests/drift_drill.rs:9 漂移必报 + 2 负对照
- src/mlsp.rs:syntax 卡片自持化(semantics/rule/sample/doc_quote)
- three-problems.md §5.1 判据矩阵逐行判定(问题 1✅ 2✅ 3❌);three-problems-plan.md Phase 4 落地记录
- 全量干净回归零失败
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-23 05:06:30 +08:00 |
|
 cflmyandCursor
|
00c763300e
|
test(repair): mimo-v2.6-flash cross-check + measurement-side hardening
mimo-v2.6-flash 终测:anchor 臂一轮 20/20=100%、plain 90%(最终 95%);
三轮双臂一轮修复率全部 >=85%(目标 >=80%),护栏 0 越界。
'测试不稳定'定性为三类测量端问题并全部加固(与 Marqdo 语义无关):
- 网关空体抖动 -> curl --retry + 5s 退避(加固后 0 次失败)
- 推理模型 reasoning_content 吃光 token 预算 -> max_tokens 2000->8000
- 模型输出格式畸形 -> parse_edits 容错(数组/单对象/NDJSON 多对象流/
字符串化元素/字符串型行号/围栏/数字后多余引号的确定性修补 unquote_line_nums)
报告按模型分文件(repair-experiment-<date>-<model>.md),cflmy/mimo 双报告并存;
计划记录更新为三轮对照表。干净环境 cargo test 444/444 全绿(零回归);
ext_llm_*/ext_agent_*_live 为环境开关型实况测试,与本期无关。
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-23 01:27:01 +08:00 |
|
 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 |
|
 cflmyandCursor
|
81d26a265a
|
docs(roadmap): 落地记录 —— T3.4 修复回路工程项完成(护栏 + golden 20 例);T3.3 编号归位
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-22 20:14:32 +08:00 |
|
 cflmyandCursor
|
18d89d6cf2
|
docs(roadmap): 落地记录更新 —— T3.4 完成;T3.3 golden 实验待做
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-22 19:47:19 +08:00 |
|
 cflmyandCursor
|
db5f0e830b
|
feat(mlsp): Phase 3 MLSP for AI —— locate/syntax/validate/repair_targets/schema(T3.1/T3.2 + T2.6)
- src/mlsp.rs: 行分隔 JSON 协议 + 五 handler;语法唯一事实来源 = CORE_CONSTRUCTS(只加检索别名)
- repair_targets 带有界护栏策略(anchored-local / 越界必拒 abstain / max_attempts=2)
- schema 契约导出(T2.6):形参/返回/字段契约 + 升参清单 + 锚点
- marqdo mlsp 子命令:stdio 行分隔 JSON 服务
- tests/mlsp.rs 7 例全绿;全量回归零失败(含 262 gold)
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-22 19:44:35 +08:00 |
|
 cflmyandCursor
|
7a449c40b1
|
feat(contract): Phase 2 渐进式契约层 —— 契约表提取 + 四边界校验 + marqdo check 防漂移(T2.1–T2.5)
- src/contract.rs: 类型词汇(渐进标注)、参数/返回/字段三形状契约表解析、合并、四边界校验诊断
- src/parse/mod.rs: extract_function_contract —— 位置+形状双重判定,在升参推断之前提取;
绑定表/普通文档表绝不吃(P1 零回归),契约表从 body 移除(元数据永不执行)
- src/interp.rs: 四边界校验 —— 调用实参(3 条调用路径)/返回/表绑定/字段访问
- src/check.rs + marqdo check [--json]: 漂移双向互查、未知类型名(附建议)、错位契约
- src/load.rs: label_error 保留结构化诊断(错误出口唯一,不拍平成字符串)
- T2.4: 全部契约诊断带 doc_anchor/doc_quote/contract_ref
- tests/contracts.rs 12 例全绿;全量回归零失败(含 262 gold)
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-22 19:40:08 +08:00 |
|
 cflmyandCursor
|
a49592a3ba
|
docs: 三大问题设计移出 doc/next/ → roadmap/three-problems.md;新增落地计划 three-problems-plan.md
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-09-22 17:46:09 +08:00 |
|