DSH Plugins Marketplace

DSH Plugins

dsh-vision-fallback

by · 1HelloMan1/dsh-vision-fallback

Manifest valid

0 Stars

0 Forks

Install

dsh plugin --profile web add dsh-vision-fallback
GitHubnpm

Original language: English

UI (client)hasBundlePatch

About

Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.

Similar plugins

dsh-vision-recognizer

Vision provider route that transcribes attached images to text through a configurable model (15+ OpenAI-compatible and Anthropic vendors) while DeepSeek keeps answering.

Vision & MultimodalManifest valid

0

dsh plugin --profile web add dsh-vision-recognizer

by sfyyy

On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Manifest valid

6

MIT

JavaScript

Aug 16, 2026

dsh plugin --profile web add @dsh-extension/dsh-vision-bridge

On-demand vision for text-only DeepSeek models: upload images, and the model calls a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).

Vision & MultimodalManifest valid

0

dsh plugin --profile web add dsh-eyes

Configurable image recognition for text-only DSH models: image messages are first transcribed by an OpenAI-compatible vision model (Base URL, model ID and API key set in a Settings section) and then p

Vision & MultimodalManifest valid

0

dsh plugin --profile web add @lp181818/dsh-vision-plugin

Auto-switch the DeepSeek route to the vision model on demand: flash main session switches (A), pro keeps deep reasoning and delegates image reading to a vision subagent (B), subagents always switch, w

Vision & MultimodalManifest valid

0

dsh plugin --profile web add dsh-auto-vision

Model-facing image_describe (识图) tool over the DashScope OpenAI-compatible API (qwen3.7-flash), plus a paste bridge: on text-only sessions, pasted images auto-convert to file paths at send time and re

Vision & MultimodalManifest valid

0

dsh plugin --profile web add dsh-tool-vision