dsh-image-subagent
Image Subagent
Allow text-only primary models (DeepSeek V4, etc.) to receive image attachments: remove the modality declaration from the text-only route to pass the 0.1.1 admission gate, project images into placeholder text carrying the complete attachmentId, and have the primary model delegate reading to a visual
The plugin will be installed here. Keep web if you are unsure.
npx -y @deepseek-ai/dsh plugin --profile web add github:yuqingsh/dsh-image-subagent#289fdd85a94484ee938d15a497e5e0161d774702Description
Allow text-only primary models (DeepSeek V4, etc.) to receive image attachments: remove the modality declaration from the text-only route to pass the 0.1.1 admission gate, project images into placeholder text carrying the complete attachmentId, and have the primary model delegate reading to a visual sub-agent via read_image.
Compatibility and provenance
Image Subagent is published as dsh-image-subagent and currently resolves to version 0.2.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.
- DSH compatibility
- *
- Runtime surfaces
- any
- Release source
- github
- Registry updated