wangwensheng/AM516
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: paginate candidate model recommendations

Browse Source
This commit is contained in:
ar51
2026-09-01 09:48:01 +08:00
parent d97b788e0e
commit 8a695900f3
9 changed files with 598 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
capabilities/am516-delivery-prediction/skills/joint-module-model-recommendation/SKILL.md
View File

@@ -62,8 +62,10 @@ Allowed upgrades:
- Encoder options are directional: `S -> M/HS/HM`, `M -> HS/HM`, `HS -> HM`, and `HM` has no further automatic upgrade.
- Include the original model separately as the baseline and deduplicate all generated models.
- Never generate a brake, encoder, sensor, or grease downgrade.
- Query every generated candidate through the controlled delivery-prediction script.
- Show candidates with usable lead-time summaries in full; summarize missing or unsupported models under `不可用候选`.
- Preserve the complete deduplicated candidate pool in rule order so the lead-time capability can page through it deterministically.
- The original model is a baseline and does not count toward the four recommended candidate models in a batch.
- When used by the lead-time capability, pass only the first four candidates on the initial query. A same-conversation human request for more candidates passes the next four, without repeating or reordering earlier candidates.
- This recommendation Skill does not call the delivery-prediction API itself. The lead-time capability queries only the current candidate batch and summarizes missing or unsupported models under `不可用候选`.
## Output