dsh-auto-vision

Bridges images into text for non-vision DSH models: pasted screenshots (and images inside tool results) are described by a configurable vision model and stored as folded context rows, keeping the user message untouched. Auto-declares image input on configured models for zero manual setup.

Install dsh-auto-vision

dsh plugin --profile web add dsh-auto-image

Plugin details

Author
soarguo
Category
Models & Providers
Added
2026-08-24

View the source on GitHub

More models & providers plugins