dsh-reasoning-depth

DeepSeek Harness per-model thinking-depth (reasoning effort) configurator: a settings-page section that auto-reads the configured models from llm-pi-ai and applies a per-model thinking level through the agent/request waterfall — all without modifying DSH itself.

AI 분석

核心用途是精细化控制支持 reasoning_effort 模型的思考时间，平衡回答质量与 API 成本。适合频繁使用深度思考模型、需要按需调整推理强度的用户。

에이전트

패키지: dsh-reasoning-depth
버전: 0.1.0
라이선스: MIT
최근 업데이트: 2026. 8. 24.

설치

검증된 bundle이 없거나 호환성 검사에 실패했습니다. 먼저 저장소 설명을 읽어 주세요. 전체 README 읽기 ↗

문서

전체 README 읽기 ↗

⚙️ Configuration

reasoning-depth:
  default: medium
  perModel:
    ark/deepseek-v4-flash: high
    uu/claude-opus-5: low

A level a model does not declare in its reasoningEfforts is skipped instead of failing the request with UNSUPPORTED_REASONING_EFFORT.