ocr 53
Persistent vision plugin for DeepSeek Harness: registers the vision_analyze tool backed by a configurable multimodal model, with a settings-page UI. Zero dependencies.
dsh plugin add dsh-vision-helperdsh plugin: recognize attached images with the built-in Windows OCR engine (Windows.Media.Ocr) and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.
dsh plugin add dsh-windows-ocrTransparent image guard + vision analysis for DeepSeek Harness: text-only models read pasted images without the 400 session deadlock.
dsh plugin add dsh-vision-guard