dsh-vision-router
nlqh7
Give DeepSeek Harness text-only models vision: Codex-style drag-and-drop of images into the chat box automatically routes them to the user-configured vision model for text conversion, v4 reads images without switching models. Vision for text-only DSH models: routes chat-box images to a user-configured vision model and returns text descriptions, deepseek-v4-pro reads images without switching.