FanXi1230/fanxi--plugins-dsh-reasoning-effort-dock ↗★ 0
dsh-reasoning-effort-dock
A draggable off / low / high / max reasoning-effort slider in the DeepSeek Harness composer model row, bound to the real per-session model selection. 适合需要频繁调整模型思考深度以平衡速度与质量的用户。
설치
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:FanXi1230/fanxi#66b5df16b2a7b44a6620969092afc5f7e9ae749e&path:plugins/dsh-reasoning-effort-dockUsage
- Start a new conversation or open an existing one.
- Move the slider to
off,low,high, ormax. - Send the next message. The selected level is the reasoning effort used for the request; the native model menu shows the same level.
The model's native four-level effort metadata is the only source of stops. If a model does not advertise all four, the slider is hidden instead of sending an unsupported value.