dsh-vision-plugin

仓库内包含的插件

• dsh-vision-pluginv0.1.0

  Vision capability seam for DeepSeek Harness: service, OpenAI-compatible provider, and view_image tool.

  package.json

  package.json

  dsh.bundle.patch

  —

• @zhangbo-cn/dsh-tool-visionv0.1.0

  Model-facing view_image tool over the DeepSeek Harness vision seam (ctx.vision): reads an image file, commits its bytes durably, and returns a text description from an external vision provider.

  package.json

  packages/tool-vision/package.json

  dsh.bundle.patch

  —

  官方核心包 (7)

  • @deepseek-ai/cordis^4.0.1共享
  • @deepseek-ai/dsh-attachment>=0.1.0-rc.6共享
  • @deepseek-ai/dsh-fs>=0.1.0-rc.6共享
  • @deepseek-ai/dsh-invariants>=0.1.0-rc.6共享
  • @deepseek-ai/dsh-system-prompt>=0.1.0-rc.6共享
  • @deepseek-ai/dsh-tools>=0.1.0-rc.6共享
  • @deepseek-ai/schemastery^3.18.1私有副本
• @zhangbo-cn/dsh-vision-openai-compatiblev0.1.0

  OpenAI-compatible chat-completions vision provider for the DeepSeek Harness vision seam (ctx.vision).

  package.json

  packages/vision-openai-compatible/package.json

  dsh.bundle.patch

  —

  官方核心包 (4)

  • @deepseek-ai/cordis^4.0.1共享
  • @deepseek-ai/dsh-attachment>=0.1.0-rc.6共享
  • @deepseek-ai/dsh-invariants>=0.1.0-rc.6共享
  • @deepseek-ai/schemastery^3.18.1私有副本
• @zhangbo-cn/dsh-visionv0.1.0

  Vision capability seam for DeepSeek Harness: a provider registry with auto-selecting describe() execution, letting a text-only model 'understand' an image.

  package.json

  packages/vision/package.json

  dsh.bundle.patch

  —

  官方核心包 (3)

  • @deepseek-ai/cordis^4.0.1共享
  • @deepseek-ai/dsh-attachment>=0.1.0-rc.6共享
  • @deepseek-ai/dsh-invariants>=0.1.0-rc.6共享

路径固定于提交 8da9a9b940fa

概览

Vision capability for DeepSeek Harness: lets a text-only model "understand" an image by routing to an external OpenAI-compatible multimodal API. Built as a standalone dsh-plugin from the official vision capability seam proposal.