|
|
c9c3eedd82
|
feat: 移除实验性间隔思考模式，推理强度前置到前端
- 彻底移除「每 N 次请求强制思考」的间隔调度机制（思考/非思考交替导致缓存命中率极低）
- 运行模式收敛为 fast/thinking：原 deep 改名 thinking，历史数据读取时映射
- 新增推理强度五档滑块（low/medium/high/xhigh/max + 默认不传参），置于模型/模式弹窗
- 模型配置新增 reasoning_effort 开关；档位会话级持久化到对话 meta，随对话保存/恢复
- 个人空间新增「默认推理强度」；新用户默认运行模式改为 thinking
- 滑块交互：JS 插值驱动（点击/拖动/吸附全程平滑），首帧档位语义定位无闪烁
- 保存链路：前端防抖 600ms + conversation_id 兜底，修复 /new 发消息丢档位、切对话恢复错误
|
2026-07-21 13:47:53 +08:00 |
|
|
|
90233690ad
|
feat: add json-based extensible model registry and dynamic model UI
|
2026-04-09 20:56:54 +08:00 |
|
|
|
08bc08b35f
|
feat: update model support and multimodal
|
2026-02-25 01:41:05 +08:00 |
|
|
|
d0197c38c3
|
fix: expand workspace file access and paginate convo index
|
2026-01-25 16:13:32 +08:00 |
|
|
|
f7034a3047
|
fix: enforce personalization tool disables in api flows
|
2026-01-25 13:44:52 +08:00 |
|
|
|
6e0df78fef
|
feat(api): multi-workspace endpoints and container cleanup
|
2026-01-24 18:29:30 +08:00 |
|
|
|
9f7b443268
|
feat: add prompt/personalization selection and conversation APIs
|
2026-01-24 13:33:50 +08:00 |
|
|
|
82e7d0680a
|
feat: add api v1 bearer auth and polling docs
|
2026-01-24 02:35:07 +08:00 |
|
