6364fb437c
Normalize product data prompt formatting
2026-05-28 14:31:34 +08:00
2dc941d6d8
Update vehicle control complexity rules
2026-05-27 21:06:40 +08:00
85ce8c0e69
fix: session resume, config_set schema, metrics chart, subagent logging
...
- Fix session resume: remove messages.length>1 guard so sessionStorage
ID is used as resumeSessionId on first message (prevents new session
creation when user sends "继续")
- Fix config_set tool schema: add missing `items: {}` to array type in
oneOf (Azure OpenAI strict validation rejects it otherwise)
- Metrics chart: use actual target set filename from trigger text
instead of generic "target_subset" key
- Add sub-agent skill call logging to agent_runtime.py (full
prompt/response, no truncation)
- Various metric enrichment and dedup fixes in server.py
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-05-27 17:02:24 +08:00
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
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
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
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
d2bb525e38
修改
2026-05-25 19:34:49 +08:00
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
d8741a3489
Merge remote-tracking branch 'origin/main' into wsh_dev
...
# Conflicts:
# backend/api/server.py
2026-05-25 11:46:44 +08:00
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
362321c460
修改
2026-05-22 20:56:57 +08:00
5311e6d97c
修改
2026-05-22 19:48:47 +08:00
a3a4cdca14
Add model labeling skill
2026-05-21 19:10:06 +08:00
20690cdef3
修改
2026-05-20 15:46:36 +08:00
1a94cec822
修改
2026-05-20 15:04:19 +08:00
5684df3caf
Add intervention data skill
2026-05-19 11:59:49 +08:00
87dd67c76a
Use prompt history for online mining records
2026-05-14 17:42:08 +08:00
f1dc7e4b91
Fix online mining session lookup
2026-05-14 17:25:51 +08:00
c6b3233769
Improve online mining record conversion
2026-05-14 17:19:23 +08:00
a48c86501a
Remove legacy online mining tools
2026-05-12 18:03:39 +08:00
6dad2cc4b3
Add online mining v2 skill
2026-05-12 17:01:43 +08:00
c517d93034
Align label output target formats
2026-05-12 12:06:39 +08:00
6143f876d3
Refine label complexity knowledge
2026-05-12 11:50:52 +08:00
e515d5e224
Update navigation complexity inheritance rules
2026-05-12 11:34:25 +08:00
c78586f5ba
update
2026-05-12 11:20:43 +08:00
1505e5e684
Fix map navigation complexity context rules
2026-05-12 11:13:53 +08:00
69e9dddbbe
update md
2026-05-12 11:04:03 +08:00
26fe0f6a9d
update md
2026-05-12 10:51:01 +08:00
c4427bbd07
Improve long product-data generation runs
2026-05-11 20:26:06 +08:00
4c29ce21f1
Make product-data generation resumable
2026-05-11 20:13:08 +08:00
952eba4b93
Restore product-data write_file guidance
2026-05-11 19:59:39 +08:00
41eb36a704
Avoid draft files in product-data generation
2026-05-11 19:56:29 +08:00
7dc7fa2e52
Migrate product-data exports to skill scripts
2026-05-11 19:43:17 +08:00
f22de8a40b
Fix product data eval export format
2026-05-11 15:27:11 +08:00
be731caed7
Add training and planning eval exports
2026-05-11 14:50:00 +08:00
8cca3793e0
Avoid top-level composition in tool schemas
2026-05-11 11:51:11 +08:00
0e2a00990f
Stabilize product data export flow
2026-05-11 11:46:09 +08:00
1752c81913
Refine label complexity knowledge
2026-05-11 11:08:36 +08:00
ca2f6f36fc
Make product-data skill portable
2026-05-11 10:58:35 +08:00
010dc1a88d
Add label master skill
2026-05-09 17:49:53 +08:00
84b715a293
update model-iteration
2026-05-09 15:21:57 +08:00
6a58eb55fe
Add model iteration skill
2026-05-09 12:18:06 +08:00
0bbba2b936
Enforce session workspace boundaries
2026-05-08 17:09:07 +08:00
5b14f55736
update
2026-05-08 15:34:11 +08:00
6720cafa48
Constrain online mining skill outputs
2026-05-08 15:24:31 +08:00
bd2f260b9f
Add skill enable controls and data factory SQL skill
2026-05-08 14:56:32 +08:00
37fc367304
Unify skills under repository root
2026-05-08 10:54:27 +08:00
wuyang6