wuyang/zk-data-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
287 Commits 2 Branches 0 Tags
89e77140e7e5e902653b74def5fa3eafdff4d2a7
Commit Graph

10 Commits

Author SHA1 Message Date
wangsenhao 89e77140e7 chore(skill): slim down model-iteration skill files (-820 lines) 
SKILL.md: 653→607 lines, program.md: 1757→1187 lines.
Merged duplicate content, replaced verbose explanations with references.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-26 17:03:08 +08:00
wangsenhao 4dbf59116f docs: simplify complex_dev/complex_base, remove cleaned_predict row 
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-26 15:49:23 +08:00
wangsenhao b48032e15c feat: backend gate fallback + metric_diff docs + submit_sft fix 
- Auto-inject human-review gate when agent asks question but forgets gate entry
- Add complex_dev/complex_base field docs to program.md metric_diff table
- Fix submit_sft.sh minor issues
- jupyter_runtime improvements

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-26 15:42:02 +08:00
wangsenhao a09d4afacd fix: pipeline排序/runDic映射/label-master repeatable/达标优先级 
- pipeline items 按 first_ts 自然时间排序，去掉 hardcoded section_order
- augment step-detail 去掉 R{n-1} 偏移，直接用本轮 runDic（与 resolve_run_ids.sh 实际行为对齐）
- 加 BundledSkill.repeatable 字段，label-master 标记 repeatable:true 跳过 duplicate detection
- SKILL.md/program.md: 目标集≥95%最高优先级，未达标前其他集合轻微下降不回滚
- SKILL.md/program.md: 禁止正则脚本替代 label-master 语义复核
- program.md: 每轮 SFT 前必须展示训练数据组成
- resolve_run_ids.sh: 修正注释（SFT_RUNDIC = 当轮 eval workflow id）

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-26 14:10:32 +08:00
hupenglong1 d2bb525e38 修改 2026-05-25 19:34:49 +08:00
hupenglong1 a3ab74b506 refactor: split submit_sft_via_cml.sh into submit_sft.sh + submit_cml_eval.sh 
- submit_sft.sh: pure SFT submission, prints JobID and exits (no embedded watcher)
- submit_cml_eval.sh: pure CML eval, reads workflow_id/version from config.yaml
- jupyter_runtime write_text: rewrite to use Contents API instead of terminal websocket
- SKILL.md: restrict trigger to explicit UI click only
- program.md: update §5.2 docs to reflect two-script workflow

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-25 17:21:42 +08:00
hupenglong1 57f5b60a3e model-iteration: runDic 单一可信源 + label-master 逐条调用 
- 新增 scripts/resolve_run_ids.sh：从 workflow5/ 解析出 SFT_RUNDIC / EVAL_RUNDIC，禁止 agent 心算 +1
- submit_sft_via_cml.sh 拆成 <SFT_RUNDIC> <EVAL_RUNDIC> [PREV_RUNDIC] 三参，yaml 用 SFT_RUNDIC，cml workflow run 用 EVAL_RUNDIC
- program.md §746 / §5.2 / §1.2 同步约束，并加 R2 落盘多 +1 的踩坑案例
- §4.0.1 Step A.5 / §4.5 label-master 复核改逐条调用（≤8 路并发），禁止批量塞多条 query

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
 2026-05-25 11:42:44 +08:00
hupenglong1 5311e6d97c 修改 2026-05-22 19:48:47 +08:00
hupenglong1 20690cdef3 修改 2026-05-20 15:46:36 +08:00
hupenglong1 1a94cec822 修改 2026-05-20 15:04:19 +08:00