dsh-visionary
Give text-only DeepSeek models eyes — a DeepSeek Harness plugin that transparently converts chat images into OCR text + vision-model descriptions before they reach the LLM. Configure vision backends (GLM-4V, Qwen-VL, Gemini, Ollama…) right in the Models settings page; multi-backend fallback chain, double-layer caching, no config files.
功能介绍
Give text-only DeepSeek models eyes — a DeepSeek Harness plugin that transparently converts chat images into OCR text + vision-model descriptions before they reach the LLM. Configure vision backends (GLM-4V, Qwen-VL, Gemini, Ollama…) right in the Models settings page; multi-backend fallback chain, double-layer caching, no config files.
安装
dsh plugin --profile web add github:zhuiyueya/dsh-visionaryInstall method: GitHub · 尚未在容器中测试 (L3+)
兼容性
| DSH Version | Status |
|---|---|
| not stated | Declared — not tested |
要求
- • Node.js: not stated
- • DSH: declared "not stated"
- • External credentials: none detected
安全报告
自动静态扫描，非人工审核。
暂无该插件的扫描记录。新收录插件由每日流水线扫描。
——f7c654f9f5b7扫描结果仅对「扫描版本」有效。若当前版本不同，徽章将显示 outdated，直到每日流水线重新扫描。
免责声明：这是自动化静态分析，不构成安全保证。安装前请自行审查。
• 静态启发式扫描：待扫描
• 依赖漏洞：—
• 硬编码密钥：—
• 供应链风险：—
活跃度
最近提交 2026-08-14 · 活跃度：活跃
• 仓库创建: 2026-08-18
• 星标: ★ 0 · 复刻: 0
• 健康度: 活跃 — 近 30 天有提交