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

dsh-bundle-vision

v0.1.0

Published

Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes

Readme

dsh-bundle-vision

给 DeepSeek Harness 提供零核心改动的视觉能力,以一个可安装的 npm 包同时充当 profile bundle 与插件:

  • 插件注册面向模型的 describe_image 工具;
  • bundle patch 把该插件挂载到任意 profile。

工具读取本地 PNG/JPEG/WebP/GIF 文件,把字节经随附的附件服务落盘,再用一次直接的 LLM 请求询问调用参数指定的多模态路由(provider / model 是工具参数)。结果只有文本——图像块绝不进入调用会话,因此纯文本主模型无需对 dsh 做任何改动即可获得视觉能力。

工作原理(全部走随附的公开 seam)

工具用到的一切都随每个 dsh profile 发布:

  • ctx.fs(有界字节读取、按会话工作区解析)——文件系统能力;
  • ctx.attachmentssaveImage、图像限额、魔数校验)——持久图像存储;
  • ctx.llmresolveModelInfo + stream)配合 pi-ai 多提供方适配器——多模态请求本身。

唯一的逐部署前提与 dsh 的任何视觉用法相同:多模态模型必须在 llm-pi-ai 设置段声明图像输入,例如:

llm-pi-ai:
  providers:
    my-vision:
      apiKeyEnv: MY_VISION_API_KEY
      api: openai-completions
      baseURL: https://example.invalid/v1
      models:
        - id: my-vision-model
          input: [text, image]

(在 Models 页已有输入模态控件的发布版上,这一声明就是一个下拉选择。)

安装(已装 dsh、非源码用户)

从 npm registry:

dsh plugin --profile <name> add dsh-bundle-vision

或从打包好的 tarball(例如首次发布前、或需要固定版本时):

dsh plugin --profile <name> add ./dsh-bundle-vision-0.1.0.tgz

dsh plugin 会把参数转发给 profile 目录里的 pnpm,并自动调和 profile 的 bundle 层列表——声明了 dsh.bundle 的依赖自动加入层栈。重启 dsh <name>;工具对每个 agent 可见(profile 根作用域的注册对所有 preset 作用域可见)。

使用

让主模型带上路由调用:

用 describe_image,file_path 填 /path/to/photo.jpg,provider 填 my-vision,model 填 my-vision-model,prompt 填"OCR 图片中的文字"。

主模型按次指定 provider/model——配置多条多模态路由即可按次切换,无需改 profile。每种拒绝都会点名具体门禁(未知扩展名、部署媒体类型、模型未声明图像输入、文件缺失、类型不匹配、流错误)。

版本下限

包对 dsh seam 包声明 >=0.1.0-rc.6 的 peer 依赖。若后续发布版本有要求,请同步抬升下限。

开发

npm install          # 开发依赖从 npm registry 解析 seam 包
npm run typecheck    # tsc --noEmit(src + tests)
npm test             # vitest
npm run build        # tsdown(lib/index.js)+ tsc 声明(lib/types)
npm pack             # 生成可安装 tarball