Zhangbo-cn/dsh-vision-plugin

README excerpt

dsh-vision-plugin Vision capability for DeepSeek Harness: lets a text-only model "understand" an image by routing to an external OpenAI-compatible multimodal API . Built as a standalone dsh-plugin from the official vision capability seam proposal. Packages Package Role @zhangbo-cn/dsh-vision Service Definition: ctx.vision ( registerAdapter , describe , listProviders ) @zhangbo-cn/dsh-vision-openai-compatible Provider: OpenAI-compatible chat-completions adapter @zhangbo-cn/dsh-tool-vision Consumer: view image tool Install Mount in your cordis.yml : Then ask the model: "use view image to look at ./screenshot.png" — it reads the file, commits the bytes through the attachment seam, and returns a text description from your configured vision model. How it works Image input reuses the durable ImageAttachmentRef from the attachment seam; output is text (no ImageBlock ), so it is independent of whether the harness LLM route itself accepts images. Requirements - DeepSeek Harness with an attachment store ( dsh-attachment-local ) and filesystem ( dsh-fs-local ). - A configured OpenAI-compatible multimodal endpoint (any OpenAI-chat-completions-compatible vision model). Development Tests include…

Category