dsh-vision-plugin

ld-1101

让纯文本模型也能看图：发图自动用视觉模型描述（默认提示词），描述不足时对话模型自动生成更具体的提示词重新解析；系统模型/自定义双模式 + GUI 可视化配置、Key 脱敏安全、针对 DSH 0.1.0-rc.6 的宿主小补丁（见仓库 README）。

Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).