ManoloRemiddi/dsh-adaptive-reasoning ↗★ 0
dsh-adaptive-reasoning
按需自动调整特定路由的模型推理深度 适合需要优化推理成本和速度的用户，在无需分类器模型的情况下动态控制思考强度。
同名套件的其他儲存庫
安裝
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ManoloRemiddi/dsh-adaptive-reasoning說明文件
閱讀完整 README ↗Configuration
enabled: boolean, default true.textOnly: boolean, default true.presets: exact preset allowlist; empty means inactive.routes: exact provider/model pairs with aneffortsmapping foroff,low,medium,high. The existing Qwen maps high toxhigh.
Automatic mode owns per-request effort on allowlisted routes. Explicit requests to think deeply remain high. Unsupported effort strings fail DSH's adapter validation before inference. Unrecognised languages retain high reasoning.