DeepSeek Harness Plugin Hub
← Plugins

dsh-plugin-image-tools

Plugin Image Tools

DSH image plugin with three tools for three scenarios: ask_user_choice for image/image-and-text mixed selection cards (rendered in the Web GUI, with zoomable viewing) + show_images for embedding images in replies (mixed text and images) + save_received_images for receiving images from vision-incapab

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:Pasumao/dsh-plugin-image-tools#f87f5d14cb247f7acbe4a4959b85b53477ba3e6a

Description

DSH image plugin with three tools for three scenarios: ask_user_choice for image/image-and-text mixed selection cards (rendered in the Web GUI, with zoomable viewing) + show_images for embedding images in replies (mixed text and images) + save_received_images for receiving images from vision-incapable models and saving them as workspace files; all images in the chat panel can be clicked to zoom, with mouse-wheel scaling and drag panning. Sources support local paths / http(s) URLs / base64 data URIs. Zero-token local rendering, implemented purely as a plugin without modifying the core package.

Compatibility and provenance

Plugin Image Tools is published as dsh-plugin-image-tools and currently resolves to version 0.6.6. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated

Versions

0.6.6stable
0.6.5stable
0.6.4stable
Show 6 more versionsCollapse versions
0.6.3stable
0.6.2stable
0.6.1stable
0.4.1stable
0.4.0stable
0.3.1stable

Related plugins

More verified plugins in vision-media.

Tool Describe Image@linxin666/dsh-tool-describe-imageModel-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable — Modlens@liustack/modlensPlug-in vision for text-only LLMs, powered by the free Antigravity CLIVision Routerdsh-vision-routerEyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary toolVision Toolkit@anionex/dsh-vision-toolkitDeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.