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-vision-tool

v0.1.2

Published

vision tool for DeepSeek Harness agents: describe local images via any OpenAI-compatible vision endpoint you configure (no built-in keys, optional multi-model cross-check)

Readme

dsh-vision 插件

给 dsh agent 注册 vision 工具:把本地图片发送到你配置的 OpenAI 兼容视觉模型端点返回文字描述——用于当前会话模型不支持图像输入的场景。

插件没有任何内置默认值:provider、凭据、模型全部在安装时由你配置。未配置完整时插件正常加载但不会注册 vision 工具(日志提示缺项),不会影响宿主。

安装(配置在安装时完成)

cd dsh-vision-install

# 方式 A:交互式——直接运行,按提示逐项输入 baseURL / 模型 / 凭据
bash install.sh --restart

# 方式 B:参数式——一键传参(适合脚本化/重复部署)
bash install.sh --restart \
  --vision-base-url https://opencode.ai/zen/go/v1 \
  --vision-api-key-env OPENCODE_GO_API_KEY \
  --vision-model mimo-v2.5 \
  --vision-models mimo-v2.5,qwen3.8-max,kimi-k3 \
  --vision-max-tokens 2000

安装参数(--vision-*)

| 参数 | 必填 | 说明 | |---|---|---| | --vision-base-url | ✅ | OpenAI 兼容 chat/completions 端点(任何厂商) | | --vision-model | ✅ | 默认视觉模型 | | --vision-api-key | 二选一 | 直接填 API key | | --vision-api-key-env | 二选一 | 环境变量名(也尝试 ~/.dsh/.credentials.yaml 同名键) | | --vision-models | 可选 | cross_check=true 时的核对模型列表(逗号分隔) | | --vision-max-tokens | 可选 | 不配则请求不带 max_tokens |

未提供参数且是交互终端 → 引导式逐项询问; 未提供参数且非交互 → 写入空配置(工具不注册),可重跑传参,或编辑 ~/.dsh/profiles/web/cordis.patch.yml 的 dsh-vision config 段。

使用(agent 内)

vision image_path=/tmp/shot.png
vision image_path=/tmp/shot.png question="图里有什么文字?"
vision image_path=/tmp/shot.png model=gpt-4o
vision image_path=/tmp/shot.png cross_check=true   # 需安装时配置了 --vision-models

安全说明

  • 插件不含任何内置密钥;密钥只来自你的安装参数/环境/凭据文件
  • 凭据文件 ~/.dsh/.credentials.yaml 权限建议 chmod 600

常见问题

  • 工具不出现:日志有 [dsh-vision] 未配置 ...——重跑 install.sh 传 --vision-* 参数后重启
  • 凭据解析失败:apiKeyapiKeyEnv(含凭据文件同名键)至少其一
  • 端点不兼容:确认 baseURL 是 OpenAI 兼容的 /chat/completions,鉴权 Authorization: Bearer
  • reasoning 模型输出为空:配置 --vision-max-tokens 2000 以上