dsh-effort-tweak

A compact per-model reasoning effort editor for DeepSeek Harness custom providers.

AI 分析

核心用于精细化控制支持推理的模型。适合需要根据任务复杂度，在 DSH 界面快速切换模型推理努力程度（如高/低/关）的用户。

other

パッケージ: dsh-effort-tweak
バージョン: 0.1.1
ライセンス: MIT
最終更新: 2026/08/13

インストール

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

ドキュメント

README 全文を読む ↗

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 DSH model picker 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.