dsh-vision-plugin

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.

Packages

Package	Role
@zhangbo-cn/dsh-vision	Service Definition: ctx.vision (registerAdapter, describe, listProviders)
@zhangbo-cn/dsh-vision-openai-compatible	Provider: OpenAI-compatible chat-completions adapter
@zhangbo-cn/dsh-tool-vision	Consumer: view_image tool

Install

pnpm add @zhangbo-cn/dsh-vision @zhangbo-cn/dsh-vision-openai-compatible @zhangbo-cn/dsh-tool-vision

Mount in your cordis.yml:

- id: vision
  name: '@zhangbo-cn/dsh-vision'

- id: vision-openai-compatible
  name: '@zhangbo-cn/dsh-vision-openai-compatible'
  config:
    baseURL: 'https://api.example.com/v1'   # required at request time
    model: 'gpt-4o'                          # required at request time
    apiKeyEnv: 'OPENAI_API_KEY'              # env var holding the key

- id: tool-vision
  name: '@zhangbo-cn/dsh-tool-vision'

Then ask the model: "use view_image to look at ./screenshot.png" — it reads the file, commits the bytes through the attachment seam, and returns a text description from your configured vision model.

How it works