DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed to text via any OpenAI-compatible VLM before reaching the text-only DeepSeek — free anonymous endpoint by default, or a paid fast path (qwen3.7-flash) with your own key (DashScope/Zhipu/Ollama/OpenRouter).
dsh plugin --profile web add github:Flyvhidbwo/dsh-vision-proxy