dsh-paste-to-path
A universal path-backed attachment dock for DeepSeek Harness.
5 results
A universal path-backed attachment dock for DeepSeek Harness.
DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.
自包含的 DeepSeek Harness 视觉系统:DeepSeek 视觉孪生路由(原生图片体验 + 视觉桥请求层拦截)+ 本地 Ollama Agentic Vision 工具(describe/OCR/结构化扫描/区域查询/元素定位/双图对比/剪贴板)+ 粘贴分流(paste-to-path)。安装即用,无本机路径依赖。
dsh bundle: subagent_vision — delegate image reading to a vision-capable model from a text-only session, plus paste-to-path so pasted images reach the subagent as file paths.
DeepSeek Harness 插件:通过本地 Doubao Relay 提供 doubao_ask 联网搜索/图片生成/多模态识图工具,并支持粘贴图片转本地路径(paste-to-path)。