@omdp/dsh-vision-bridge
Vision Bridge
DSH Vision Bridge plugin: Automatically distinguishes multimodal and text models. Multimodal models view images directly; text models use a configurable multimodal endpoint (baseUrl + apiKey + model) to view them on their behalf. Supports pasted images, the read_image tool, and converting images int
The plugin will be installed here. Keep web if you are unsure.
npx -y @deepseek-ai/dsh plugin --profile web add @omdp/dsh-vision-bridge@0.1.12Description
DSH Vision Bridge plugin: Automatically distinguishes multimodal and text models. Multimodal models view images directly; text models use a configurable multimodal endpoint (baseUrl + apiKey + model) to view them on their behalf. Supports pasted images, the read_image tool, and converting images into evidence during requests.
Compatibility and provenance
Vision Bridge is published as @omdp/dsh-vision-bridge and currently resolves to version 0.1.12. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.
- DSH compatibility
- *
- Runtime surfaces
- web
- Release source
- npm
- Registry updated