No description provided.

Model-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 —

DSH 图像理解插件：为纯文本模型提供 describe_image 工具——把图片（本地路径 / http(s) URL / 会话附件）交给 OpenAI 兼容视觉端点（Xiaomi MiMo、Qwen-VL、GPT-4o、Ollama 等）分析，只有返回的文本进入对话。移植自 zhu1090093659/dsh-web-ui 的 dsh-tool-describe-image（Apache-2.0）。

MiniMax multimodal bridge for DeepSeek Harness (DSH). One mmx_bridge tool covers describe/image/video/speech/music/cover/search/quota; optional web_search/read_image takeover; built-in client enhancement renders inline players/previews plus a settings-pag

DSH plugin: image understanding via any OpenAI-compatible vision API, paste-to-describe, and an animated whale-buddy desktop pet with status bubbles and a floating settings panel

Model-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 —

DSH Web UI 全家桶聚合插件：一键安装全部功能插件（task-board / git-graph / pet / aionui-panel / describe-image / compat shim）+ 皮肤全家桶（dsh-skins，皮肤资产内置）。设置卡片使用 DSH rc.7 官方 keyed settings slot。

Model-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 —

Git describe information at runtime, with semver support

Visual regression testing tool with cypress

get dimensions of any image file

Pi extension — describe images via vision model when your active model cannot see images directly

A pi extension to describe images using vision models

Format for representing rich text documents and changes.

This package contains shared types of Jest's packages.

Image comparison chai assert (uses ImageMagick).

Display resolution-dependent images using the image-set() function in CSS

This library provides the functionality of PBKDF2 with the ability to use any supported hashing algorithm returned from crypto.getHashes()

Generates an image from a DOM node using HTML5 canvas and SVG.

Underscore mixins for deeply nested objects