dsh-math-thinking-teacher
A selectable high-school mathematics teacher Agent preset for DeepSeek Harness
32 results
A selectable high-school mathematics teacher Agent preset for DeepSeek Harness
Expose per-model thinking levels (reasoningEfforts) inside the Models settings card for a custom model API route.
DeepSeek Harness 插件:给单步思考一个字数预算,连续几步没有可见结论时强制先给结论再继续
Per-route context window, compaction threshold, and per-model thinking-effort controls for DSH models. · DSH 模型上下文窗口、压缩阈值与思考强度设置。
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
Chain-of-thought keyword counting and highlighting: per-word count chips with a click-to-suppress switch, per-word colour, text colour and text size, whole-word matching, and a dedicated settings section
dsh 插件 · 智囊团:思维模型全方位分析:内置 161 个经典思维模型库(决策/战略/认知/心理/沟通/学习/系统/创新/执行九大分类),输入一个问题即可用选中的多个模型并行 AI 分析,产出含共识/分歧/盲区/行动清单的综合报告页;支持自动分析与提示词往返导入两种模式。
DSH plugin: set the agent's reasoning language (Settings → General)