Argonaut790/dsh-deepseek-vision

README 摘要

DSH DeepSeek Vision DSH DeepSeek Vision is an open-source DeepSeek Harness (DSH) vision plugin that adds image understanding, full-screen OCR, and persistent visual evidence to text-only DeepSeek models without replacing the parent model. Unlike provider-pool or CLI interception tools, this plugin keeps DeepSeek Harness in charge of models, attachments, sessions, and UI. It adds: - see image with latest, all, and explicit image selection - one conversation-scoped vision analyst with follow-up memory - structured summaries, question answers, exhaustive OCR, and uncertainties - a read-only Evidence tab and per-call evidence cards - a global Vision: … provider/model picker beside Choose Model - live route changes; changing the route starts a new analyst Screenshots Vision-enabled DeepSeek Harness composer The parent DeepSeek model stays in control while the separate Vision route handles image understanding and OCR. Compact vision model selector The global selector makes the active image-capable model visible and lets users change the visual-analysis route without changing the conversation model. GitHub project overview Requirements - Node.js ^22.19.0 or =24 - DeepSeek Harness 0.1.0-rc…

分类