dsh-better-reasoning-effort
为第三方供应商模型按模型配置思考强度与输入模态：知识库与原始 /models 端点取证融合建议并标注置信度，在官方「模型」页卡片内直接编辑。
Per-model reasoning-effort and input-modality configuration for third-party providers: suggestions fused from a model knowledge base and raw /models endpoint evidence with confidence labels, edited inside the official Models page card.
怎么安装
dsh plugin add dsh-better-reasoning-effort 简介
DSH Better Reasoning Effort **English** | 中文 Reasoning-effort **and input-modality** editing for **third-party models** in DeepSeek Harness — thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models page card. Why The llm-pi-ai adapter of DeepSeek Harness natively supports per-model reasoningEfforts declarations (which thinking levels a model accepts, and the exact string to send on the wire for each). But the official Models page editor **deliberately keeps this field out of reach** …
推荐参考
信息
- 协议
- MIT
- 语言
- TypeScript
- GitHub 星标
- 3
- 月下载
- –
- 最近更新
- 2026-08-24
- 创建于
- 2026-08-19
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
- 主题标签
- automation, deepseek, deepseek-harness, dsh-plugin, llm, plugin, react, reasoning, reasoning-effort, settings, typescript, web
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-codex-subscription
WSL043/dsh-codex-subscription
内置 ChatGPT OAuth 的 Codex 模型提供方：可切换订阅联网搜索，在设置页显示普通 Codex 与 Spark 独立额度；无需 API Key，也不需要另装 Codex。