Mu-scorpio/dsh-reasoning-effort ↗★ 0
dsh-reasoning-effort
Provider-aware reasoning effort settings for DeepSeek Harness.
AI 분석
核心用途是精细化控制支持推理模型的思考强度。适合需要根据任务复杂度或成本预算调整模型推理深度的用户。
설치
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Mu-scorpio/dsh-reasoning-effortConfiguration rules
| Field | Meaning |
|---|---|
api | Selects the default wire-value map for a provider protocol. |
reasoning | Sets a provider-level default reasoning level when one is missing. |
efforts | Overrides the values sent for the generic Harness levels. |
models..efforts | Overrides the map for one model. |
models..disabled | Explicitly marks one model as non-reasoning. |
The available Harness levels are off, minimal, low, medium, high,
xhigh, and max. The built-in protocol maps cover the five common levels
from low through max; custom gateways can provide their own values.
Providers must already exist in the
llm-pi-aisettings. The plugin enhances an existing provider; it does not recreate one that has been removed.