cordis plugin
maxwell-feng/dsh-windows-ocr · skills
windows-ocr DeepSeek Harness (dsh) plugin that lets text-only models accept attached images: every image is recognized locally with the built-in Windows OCR engine () and only the recognized text is sent to the model API.
★ 9GitHub stars
1Forks
2026-08-15Last updated
JavaScriptLanguage
MITLicense
Key features
- Works with any provider/model in dsh
- OCR applies only to text models.
- Genuine vision models (declared image capability) pass images through untouched by default.
- Fail-closedif the plugin is not loaded, models stay text-only and image attachments are refused — nothing can silently leak.
Requirements
- Windows 10/11 (Windows PowerShell 5.1+ ships with the OS
- A Windows OCR-capable language pack for your language (Settings → Time & language → Language).
Install command
dsh plugin --profile web add github:maxwell-feng/dsh-windows-ocr