DeepSeek Harness Plugin: computer-user-vision
`computer-user-vision` is an unofficial plugin designed specifically for DeepSeek Harness (DSH) on the Windows platform. It aims to fix the silent loading failure issue in the original version with DSH 0.1.2+ and return screenshots as actual image data rather than paths, enabling visual models to read them accurately. The plugin enhances UI Automation support by providing features such as window management, element clicking, secure input checking, and DPI awareness, filling the gap in Windows visual automation scenarios for DSH.
Read Morebeijingwahw/dsh-computer-use-plugin: DSH-based pure vision Computer Use plugin
`beijingwahw/dsh-computer-use-plugin` is a pure vision Computer Use plugin within the DeepSeek Harness (DSH) ecosystem. It abandons traditional UI tree or Accessibility API dependencies, understanding the interface through screenshots and supporting cross-platform desktop operations such as clicking, inputting, scrolling, and dragging on Windows, macOS, and Linux. The plugin's core capabilities include Set-of-Mark-based visual localization assistance, a three-stage state anchor protocol, long-task orchestration using the Planner-Actor architecture, and OCR semantic verification (supporting both Chinese and English). To ensure stability and security, it incorporates built-in behavioral verification, infinite loop prevention, budget control, and sensitive credential input blocking.
Read More