deepseek-eyes：DeepSeek Harness 插件

概览

deepseek-eyes

deepseek-eyes：给 DeepSeek Harness 的纯文本模型装上眼睛——把粘贴的图片经 OpenAI 兼容视觉 API 转成文字描述，再转发给真实的文本模型（Give text-only models in DeepSeek Harness eyes: describe pasted images via an OpenAI-compatible vision API, then forward to the real provider. Not affiliated with DeepSeek.）

社区 · Topic 自动分析 — 通过 GitHub dsh-plugin Topic 自动发现。静态检查在不执行第三方代码的前提下，验证了固定公开版本的根目录 bundle 契约与已提交文件；这不等于人工审核、安全审计、运行时冒烟测试、发布者身份验证或官方背书。

安装

从 GitHub 安装此组合包

CLI 会验证组合包、调用原生 DSH 安装，成功后才上报完成。

npx dshpub add fryghost/deepseek-eyes --ref a0abfaad1401a3ee83ec53db272ed98cde3f2531

能力

它贡献了什么

HostCordis loadable未核对

Client / UIWeb UI未核对

Model tools未核对未核对

Profile stateconditional未核对

README / ZH

插件文档

给 DeepSeek Harness 里的纯文本模型装上眼睛——然后直接粘贴图片就行。

LIMITATIONS

已知限制

- The text model receives a **description**, not pixels: fine-grained geometry, exact colors, and pixel-level layout are out of scope (use dsh-vision-toolkit alongside). - The delegated call is intentionally unmarked, so sessions on the bridge route lose adapter replay state for cached-response replay (correctness is unaffected; replayed responses fall back to a fresh provider call). - Only PNG / JPEG / WebP / GIF image parts admitted by the DSH attachment path are handled; the vision endpoint must accept the chosen formats. - Descriptions are generated per image block, sequentially, inside the request path: budget `vision.timeoutMs` accordingly. - The in-memory cache is process-local and clears on restart.