dsh-reasoning-tiers
在 llm-pi-ai 设置节为第三方模型提供商补齐推理档位（reasoning effort）声明，让 DSH 自带的思考强度选择器对 pi-ai 目录之外的模型真正可用。
Declares per-model reasoning-effort ladders for third-party providers in the llm-pi-ai settings section, so DSH's stock thinking-intensity selector works on models the pi-ai catalog does not describe.
怎么安装
dsh plugin add dsh-reasoning-tiers 简介
dsh-reasoning-tiers **Give third-party models a working reasoning-effort ladder — and editable model capabilities — in DeepSeek Harness.** A DSH plugin that matches third-party model ids against a built-in knowledge table and declares their reasoning tiers in the llm-pi-ai settings section — so the effort selector that ships with DSH finally does something for models the pi-ai catalog does not describe. New in 0.2.0: a browser half that adds a **Model Capabilities** page to the settings panel, where each added model's context window, output cap, and image modality become editable fields. No ad…
推荐参考
信息
- 协议
- MIT
- 语言
- TypeScript
- GitHub 星标
- 0
- 月下载
- –
- 最近更新
- 2026-09-13
- 创建于
- 2026-09-12
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
同类推荐
claude-code-router
musistudio/claude-code-router
每个AI代理的本地控制平面：跨模型路由、融合新能力、编排工具，并始终保持完全控制。
dsh-thinking-effort
hytime/dsh-thinking-effort
为 DSH 自定义模型配置思考档位和子 agent 默认思考强度。