reasoning-slider
Codex-style reasoning-effort slider embedded in the DSH model selector
14 results
Codex-style reasoning-effort slider embedded in the DSH model selector
DeepSeek Harness 统一推理等级插件:一个 llm-reasoning 设置项动态配置 DSH 所有模型的默认推理等级(思考等级)——自动为手写声明的模型补齐推理能力、按路由设置默认等级(仅当全部模型支持)、同步 DeepSeek 官方路由,改设置即生效。
DSH 动态思维链插件: 按当前子任务难度自动为 DeepSeek 选择推理等级 (off/low/high/max)。大任务拆分出的每个小任务、每个子代理各自按难度动态分配思维深度。
Replace the DSH Web reasoning-effort chooser with a compact animated FX slider that scales with effort level.
Codex 风格 6 档性能滑杆:每档绑定模型 + 推理等级,并切换 31 张本地人物背景。 / Codex-style 6-level performance slider for DeepSeek Harness (dsh web).
DSH plugin: model reasoning levels plus CLI request mimic, with a unified Daily Optimization settings section.
DSH reasoning effort slider with 7 levels and cool visual effects
A DeepSeek Harness plugin with a vertical model list and an animated Three.js particle reasoning-effort control.
Grant official-style reasoning-effort selection to hand-declared pi-ai models (DeepSeek relays and the like) in the chat box
在 dsh 模型目录的每一行直接设置该模型的思考强度范围与支持的输入模态 (Per-model reasoning-effort range and accepted input modalities, right in the dsh Models catalog)
Expose per-model thinking levels (reasoningEfforts) inside the Models settings card for a custom model API route.
Reasoning-effort setup page for DeepSeek Harness: detects models that expose no thinking levels and edits their llm-pi-ai reasoningEfforts declaration from a settings page
QQbridge plus — 基于 DeepSeek Harness 与 qq-bridge 的插件:以水鱼(舞萌DX)查分为主(QQ 内 #查分 查 B50、出带曲绘的成绩图,OAuth 授权、不限管理员、不依赖桥接),另附聊天拓展功能(余额与自动关机、推理档位按 DeepSeek 计费峰谷自动切换、节假日表覆盖检查与自动维护、开机/关机提示词、#余额/#关机 管理命令、#功能 开关、#帮助)。判定逻辑直接复用 qq-bridge 的纯模块,不重复实现。
Per-model reasoning effort levels in Settings → Models: a levels editor beside context window and input types that converts each selection into the model's reasoningEfforts in the profile's cordis.patch.yml.