dsh-vision-bridge

仓库内包含的插件

• @goodandready/dsh-vision-bridgev0.2.2✓

  Universal vision bridge for DeepSeek Harness: pick how images are processed — auto-rewrite via a vision LLM, explicit tools, or hybrid. Multi-channel endpoint (DSH catalog / OpenAI-compatible / Ollama / custom), LRU description cache, settings card with channels editor and test button.

  homepage

  https://github.com/GooDAnDReaDY/dsh-vision-bridge ↗

  package.json

  package.json

  dsh.bundle.patch

  cordis.patch.yml

  官方核心包 (7)

  • @deepseek-ai/cordis^4.0.1共享
  • @deepseek-ai/dsh-agent^0.1.0-rc.6共享
  • @deepseek-ai/dsh-attachment^0.1.0-rc.6共享
  • @deepseek-ai/dsh-host-webserver^0.1.0-rc.6共享
  • @deepseek-ai/dsh-llm^0.1.0-rc.6共享
  • @deepseek-ai/dsh-tools^0.1.0-rc.6共享
  • @deepseek-ai/schemastery^3.18.1共享

路径固定于提交 c7d130adc845

概览

Vision bridge for DeepSeek Harness: images are described by the vision model you pick, so a text-only chat model never fails a turn on a picture