EmmanuelMartinez/tolten-image-attach0

@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 Analysis

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。

Package
@tolten/image-attach
Version
0.1.0
License
MIT
Last updated
Sep 10, 2026

Install

This plugin has no verified bundle, or compatibility checks failed. Read the repository notes first. Read the full README ↗

🎛️ 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.