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

@leonhardthust/dsh-decision-engine

v1.15.1

Published

dsh-decision-engine: a cheap judgement layer for DeepSeek Harness — a small decision model answers structured questions before the main model acts, so calls can be allowed, escalated, rerouted to a cheaper model, or skipped. All eight decision points (too

Readme

dsh-decision-engine

本分支发布包:@leonhardthust/dsh-decision-engine,基于 zuosus 上游 的 MIT 代码。不要同时启用原包与本分支;安装与发布方法见 发布说明。

dsh-decision-engine — DeepSeek Harness 决策引擎

提供免费决策模型

网站 · config.example.yml · DECISIONS.md

English

给 DeepSeek Harness 的决策层:主模型动手之前,用一个便宜的决策小模型做结构化判断。

隐私

本分支已完全移除匿名使用上报:不再生成安装 ID,不发送安装事件或每日心跳,也不读取或更新旧的 analytics.json。旧的 telemetryLevel / telemetryEndpoint 配置不再生效。决策历史和「统计与对比」仅使用本地记录,继续保留;按用户配置调用决策服务与免费模型下发端点不受影响。

功能

八个决策点

  • 工具授权
  • 模型路由
  • 子任务分派
  • 上下文压缩
  • 轮次延续
  • 检索必要性
  • 技能选择
  • 思维链翻译

三态:关闭 · 观察 · 生效

决策服务:system one · bamboonode · 硅基流动 SiliconFlow(国内 / 国际)· 阿里云百炼 · TokenHub · Perplexity · OpenRouter · 自定义 base URL

安全档位(询问频率):不问 · 少问 · 默认 · 多问(四档都不改变权限强制的人工批准与拒绝)

界面:配置页(四个可折叠分组)· 决策历史标签页 · 统计与对比 · 审批卡正文可读化 · 决策日志分文件(按日期 / 会话 / 工作区)与自动清理

| 配置页 | 决策历史 | |---|---| | 配置页 | 决策历史 |

截图拍于分组折叠(DEC-051)之前的版式,当前界面为四个可折叠分组。

省 token:精确缓存 · 只读工具放行 · state 截断

安全分层:可信宿主上下文 → 工具副作用 → 强制权限策略 → 模型建议 → 软审核容忍度 → 宿主结果审计。 未知高影响操作不再异常放行;自动审查保留决策模型,并将软性“人工决定”交给所选 Fallback。

自动审查 Fallback:指定宿主模型(含 reasoning effort)· 沿用会话模型 · 全部允许 · 全部阻止。 “全部允许”只影响软审查,不能覆盖强制拒绝或必需的真人批准。

详见 安全修订与验证说明。默认仍未启用插件,观察模式不提供拦截保护。

许可证

MIT