dsh-plugin-vision

Configuration

Key	Default	Meaning
baseUrl	(empty — required)	OpenAI-compatible chat-completions endpoint base URL.
apiKeyEnv	VISION_API_KEY	Env var (or stored credential) holding the API key.
model	(empty — required)	Vision model id on the endpoint.
timeoutMs	120000	Per-call timeout (thinking vision models need headroom).
maxImageBytes	8388608 (8 MB)	Hard cap on image size.
attachImages	true	Transcribe pasted images to text for text-only main models.
attachMode	auto	auto: pass the user's own prompt to the vision model; describe: always generic description.
deepseekVision.enabled	true	Register the deepseek-vision provider route (DeepSeek + image transcription).
deepseekVision.providerId	deepseek-vision	Provider route id shown in the model picker.

Any OpenAI-compatible vision endpoint works. The defaults are deliberately empty so no provider is assumed; pick one:

Provider	baseUrl	model	Notes
Zhipu GLM (free tier)	https://open.bigmodel.cn/api/paas/v4	glm-4.6v-flash	Free registration, zero cost out of the box
Alibaba DashScope (incl. token plans)	https://dashscope.aliyuncs.com/compatible-mode/v1 (or your plan's endpoint)	qwen3.7-plus / qwen-vl-max	Your own plan's endpoint if you have one
Ollama (local, offline)	http://localhost:11434/v1	qwen3-vl:4b	No API key needed
Any OpenAI-compatible gateway	your gateway's /v1	the gateway's vision model	—

Configure per deployment (e.g., your profile's cordis.patch.yml or the plugin row's config):

- id: vision
  name: dsh-plugin-vision
  config:
    baseUrl: https://open.bigmodel.cn/api/paas/v4
    apiKeyEnv: VISION_API_KEY
    model: glm-4.6v-flash
    timeoutMs: 120000