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.

Agent 协作

包名: dsh-reasoning-depth
版本: 0.1.0
许可证: MIT
最近更新: 2026年8月24日

安装

此插件尚未提供可验证的 bundle，或兼容性检查未通过。请先阅读仓库说明。阅读完整 README ↗

说明文档

阅读完整 README ↗

⚙️ 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.