luxueliu/luxueliu-reasoning-efforts ↗★ 0

luxueliu-reasoning-efforts

Reasoning-effort ladders for every non-ds model on a local LLM gateway route in DeepSeek Harness: declares selectable thinking levels (off/low/medium/high/xhigh/max) for hand-declared gateway models that would otherwise show no reasoning control at all, and re-applies them to the live profile settings after DSH upgrades overwrite node_modules. Ships the route-level reasoningEfforts source patch (llm-pi-ai), the 20-alias gold ladder table (efforts.json), and a check/re-apply command (/efforts).

AI Analysis

核心用途是为原本不支持思考控制的网关模型强制启用思考强度调节。适合使用本地或第三方网关并希望微调推理深度的用户。

other

Package: luxueliu-reasoning-efforts
Version: 0.1.0
License: MIT
Last updated: Aug 21, 2026

Install

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:luxueliu/luxueliu-reasoning-efforts

README

Read the full README ↗

配置

插件的 cordis.patch.yml 已带默认配置，可在 profile 的 cordis.patch.yml 覆盖：

- insert:
    - id: luxueliu-reasoning-efforts
      name: luxueliu-reasoning-efforts
      config:
        settingsPath: ""        # live settings.yaml；留空自动探测 ~/.dsh/settings.yaml
        checkOnStart: true      # 启动时检查档位漂移并提示
        applyOnStart: false     # 启动时自动重打（默认关，先 check）
        effortsFile: "efforts.json"