data-gap(chat): 输出落点选择器与改派建议均无真实数据源(D8 剩余两项,需产品设计+后端)
- Dominant language
- TypeScript
- Stars
- 0
- Forks
- 0
- Avg merge
- 1h 7m
- Merged PRs (30d)
- 969
Description
## 背景
`chat-main-fidelity-rubric.md` D8 参照图输入区还有两项本仓完全没有对应数据源的能力(见 #2277 调查):
1. **输出落点**(参照图"输出落到「假设树」")—— 本仓没有"技能结构化输出槽位"这个概念。`landAsArtifact` 是通用的"把这条消息落地为产物"动作,产物类型不挂靠具体技能契约。要做需要:技能契约新增"这个技能产出什么类型的结构化输出"字段 + 落地时按该字段路由到对应展示/存储形态——是一次产品设计 + 契约扩展,不是纯前端能补的空缺。
2. **改派建议**("这条更适合 Scout 处理,改派/忽略")—— 契约里没有任何"改派建议"相关的操作或字段。要做需要一整条新推荐逻辑(可能要接模型判断"这条消息更适合哪个 agent"),属于新功能而非保真修复。
两项都需要人类/coord-architecture 判断是否值得做、按哪种方案做,不是当前 sprint 的保真度修复范围。本 issue 只记录数据缺口,不实现、不伪造。
## 关联
总览:#2268;同批调查:#2277
Contributor guide
No contributing guide indexed for this repository
Research direction
Read chat-main-fidelity-rubric.md at D8 and the findings in #2277; then inspect the existing landAsArtifact path and skill-contract definitions. Confirm the two missing data sources and document the product or architecture decision needed before implementation. Done means an agreed scope and design, not a fabricated UI or data source.
Written by the indexing model from the issue text.
Assessment
- Domain
- backend-api-design
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100