Skip to main content

How to use 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.

This article is auto-derived from indexed fields (wiki / faq / compatibility_json), not freshly AI-generated.

This article is derived from the plugin's already-indexed fields (wiki / faq / compatibility_json / readme), not freshly generated by AI. Source field is noted at the end of each section.

Quick start

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.

source: plugins.ai_summary

Install & verify

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

Run the command above in your DSH Web Profile. Then enable the plugin in the plugin list.

source: plugins.install

Pitfalls

Review the upstream repo before installing. This guide is auto-derived from indexed fields and may lag the latest release. If anything contradicts the official docs, treat the upstream source as authoritative.

source: general rule