npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@chengwd96/dsh-thinking-effort

v0.1.4

Published

DeepSeek Harness plugin: visually configure per-model and per-provider default reasoning-effort for llm-pi-ai, over the settings wire face.

Readme

dsh-thinking-effort

English | 中文

一个 DeepSeek Harness 插件,在 Web GUI 的设置页添加思考程度分页,可按提供商和模型可视化配置 llm-pi-ai 路由的推理档位。

功能

  • 每提供商默认档位芯片选择器(写 providers.<provider>.reasoning)。
  • 全局默认(保存时烘焙进所有未单独设置的提供商)。
  • 每模型推理档位编辑器:三态 —— 不设置 / 不推理 / 自定义档位。
  • 七档平台思考级别:off、minimal、low、medium、high、xhigh、max。
  • 每档可独立编辑线网拼写(即实际发送给端点的 reasoning_effort 字符串)。
  • 恢复默认 / 全选 / 清空、脏标记、粘性头部。
  • 当有效默认档位不被某些已列出模型支持时,内联 ⚠ 风险告警。

前提

  • DeepSeek Harness (dsh),并有 dsh web 的 profile。
  • Node.js ≥ 22。

安装

从 npm 安装(推荐)

dsh plugin add @chengwd96/dsh-thinking-effort

从 GitHub 安装

# 锁定 tag(推荐,可复现)
dsh plugin add github:wenxi96/dsh-thinking-effort#v0.1.4

# pnpm ≥10 要求对 git 依赖的构建脚本单独授权——将以下内容写入
# ~/.dsh/profiles/<profile>/pnpm-workspace.yaml,然后重新运行 add:
onlyBuiltDependencies:
  - '@chengwd96/dsh-thinking-effort'

从本地检出安装

cd dsh-thinking-effort
npm install && npm run build
dsh plugin add .

使用

安装后,需要把 loader 行加入 web profile 的组合配置。推荐方式是编辑 profile 目录下的 cordis.patch.yml(~/.dsh/profiles/<name>/cordis.patch.yml):

# (追加到你已有的列表末尾)
- insert:
    - id: ui-thinking-effort
      name: '@chengwd96/dsh-thinking-effort'

重要: name 的值必须是带引号的完整包名 —— 不带引号的 @ 前缀会导致 YAML 解析或模块找不到错误。

重启 dsh web,然后打开设置 → 思考程度(左侧导航栏的思考图标)。

工作原理

该分页通过浏览器 settings wire face(ctx.remote.settings)读写 llm-pi-ai settings 命名空间,所以无需 host 端 RPC 或重启即可生效。

  • 每提供商默认 → 写 llm-pi-ai.providers.<p>.reasoning(pi-ai 在请求未显式指定档位时用它作为兜底)。
  • 每模型 reasoningEfforts → 写 llm-pi-ai.providers.<p>.models.<id>.reasoningEfforts(可用档位及其线网拼写的能力字典)。
  • 全局默认 → 保存时烘焙进所有未单独设置默认档位的提供商。

许可

MIT