visual-review
by wang-bool · wang-bool/visual-review
★ 3 Stars
⑂ 0 Forks
↓ 105 Downloads/week
Updated: Aug 18, 2026
MIT
JavaScript
Original language: English
About
Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.
Compatibility
Versions
| Latest version | Published | Size |
|---|---|---|
| 1.0.1 | — | — |
Similar plugins
by 123cdxcc
A DeepSeek Harness plugin that lets DeepSeek see screenshots and local images via MindSee. DeepSeek Harness 插件:通过 MindSee 把截图和本地图片转成文字,让 DeepSeek 能看图作答。
★ 0
MIT
TypeScript
Aug 17, 2026
dsh plugin --profile web add dsh-mindseeby dickpy
DSH (DeepSeek Harness) Web GUI AI image generation plugin: text-to-image & image-to-image via OpenAI-compatible endpoints (gpt-image-2), with shared cross-device history.
★ 71
Apache-2.0
TypeScript
Sep 11, 2026
dsh plugin --profile web add @dickpy/dsh-imagegenby GXX182
DeepSeek Harness plugin that bridges session images to pluggable vision APIs while keeping DeepSeek as the primary model.
★ 4
MIT
TypeScript
Aug 18, 2026
dsh plugin --profile web add dsh-vision-bridgeby Favio8
DeepEye vision plugin for DeepSeek Harness (DSH): image description, OCR, VQA, UI layout, and clipboard analysis.
★ 3
MIT
TypeScript
Aug 17, 2026
dsh plugin --profile web add dsh-plugin-deepeyeby c-ling
【已停止维护】DeepSeek Harness 视觉桥接插件:新版 Harness 已原生支持图片识别,请使用原生能力,本仓库仅作历史参考。
★ 3
MIT
JavaScript
Aug 21, 2026
dsh plugin --profile web add dsh-plugin-vision-bridgeOn-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).
★ 0
dsh plugin --profile web add dsh-eyes