imkingjh999/dsh-tool-accurate-vision

README excerpt

dsh-tool-accurate-vision Model-facing accurate vision tool for DeepSeek Harness: precise spatial reasoning over an image file via an OpenAI-compatible vision model. Ported from pi-accurate-vision . A vision model reads the image and returns a structured note plus bounding-box primitives normalised to 0–1000 ; this tool formats them as a block the next model turn reads — giving a text-only agent exact object positions, layout, and OCR without losing spatial fidelity. English 中文 Install Or from source: Set the vision API key (separate from DEEPSEEK API KEY ): How it works The pure vision core ( src/bridge.ts ) is provider-agnostic: any OpenAI-compatible multimodal chat/completions endpoint works. The Cordis host ( src/index.ts ) owns config, credential resolution, and the registered tool. Every call also writes a self-contained SVG — the original image with every bounding box and label drawn on it — returned as the annotatedImage path, so the boxes can be eyeballed instead of trusted blind (set annotate: false to skip it). Case study: rigorous distance computation Ask an image question with a checkable answer — in this hand-drawn physicists network, which node sits physically closest…

Category