Triple3h/dsh-reasoning-effort1

dsh-reasoning-effort

Per-model reasoning-effort editor with embedded slider for DeepSeek Harness custom providers.

AI 분석

核心用途是便捷调节支持该特性的推理模型的思考深度。适合使用自定义 API 接入推理模型、并希望在界面上直观控制模型思考强度的用户。

패키지
dsh-reasoning-effort
버전
0.2.0
라이선스
MIT
최근 업데이트
2026. 8. 23.

설치

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Triple3h/dsh-reasoning-effort

Configuration shape

The plugin edits this part of the llm-pi-ai namespace:

providers:
  my-gateway:
    models:
      - id: my-reasoning-model
        reasoningEfforts:
          off: null
          low: low
          high: high

The selected model's reasoningEfforts map determines which effort levels the slider can offer. The plugin uses the existing value for a level when one is already present; a newly enabled level is initialized with its canonical name.