概览
dsh-omni-workstation
源码级技术说明Omni-modal workstation plugin for DeepSeek Harness: analyze_image + 6 vision toolkit tools (zoom/sample_colors/image_diff/ocr/detect/show), generate_image, and generate_video (t2v/i2v async-task). Backed by an ordered multi-card list (OpenAI/Anthropic/Gemini protocols; Custom/Ollama plus 28 built-in fixed providers), Tabbed settings (VLM / Image Gen / Video / Mirror / Fallback), single-request failover, mirror model routing, JPEG->PNG re-encode fallback, and an auto-saving web settings page.收起技术说明
Omni-modal workstation plugin for DeepSeek Harness: analyze_image + 6 vision toolkit tools (zoom/sample_colors/image_diff/ocr/detect/show), generate_image, and generate_video (t2v/i2v async-task). Backed by an ordered multi-card list (OpenAI/Anthropic/Gemini protocols; Custom/Ollama plus 28 built-in fixed providers), Tabbed settings (VLM / Image Gen / Video / Mirror / Fallback), single-request failover, mirror model routing, JPEG->PNG re-encode fallback, and an auto-saving web settings page.
README / ZH
插件文档
目录摘要
Omni-modal workstation plugin for DeepSeek Harness: analyze_image + 6 vision toolkit tools (zoom/sample_colors/image_diff/ocr/detect/show), generate_image, and generate_video (t2v/i2v async-task). Backed by an ordered multi-card list (OpenAI/Anthropic/Gemini protocols; Custom/Ollama plus 28 built-in fixed providers), Tabbed settings (VLM / Image Gen / Video / Mirror / Fallback), single-request failover, mirror model routing, JPEG->PNG re-encode fallback, and an auto-saving web settings page.
dsh.pub 核对固定版本的组合包契约、运行时事实与分发语义；完整 README 请查看源仓库。
在 GitHub 阅读完整 README