EmmanuelMartinez/tolten-image-attach ↗★ 0
@tolten/image-attach
One-click MD3 image attachment for the DeepSeek Harness composer, with automatic per-session vision-model routing: attach an image and the session switches to a vision model, then restores your previous model.
AI 分析
核心用途是简化 DSH 的多模态交互流程，实现无缝的图片上传与视觉分析。适合经常需要向 AI 发送截图、设计图并希望自动路由视觉模型的用户。
インストール
検証済み bundle がないか、互換性チェックに失敗しています。先にリポジトリの説明を読んでください。 README 全文を読む ↗
ドキュメント
README 全文を読む ↗🎛️ Configuration
Point it at whatever vision model your provider catalog exposes — edit the two constants
at the top of plugin/client.js:
const VISION_MODEL = 'deepseek-v4-flash-vision-exp'
const VISION_PROVIDER = 'deepseek-official'
Your model must declare image input in the provider catalog
(inputModalities: ["text", "image"]), or the request will be rejected.