視覚ツール · DeepSeek Harness プラグイン — 13 ページ

DSH 的 ComfyUI 工作台：把 ComfyUI 生成的图片与其它产物收进资产库（浏览、检索、删除、批量导出），并支持执行任意 API 格式工作流；工作流对用户只暴露输入与输出，详细节点配置留给模型按需查看与调参。

DSH 电脑操作插件（web_ui 家族框架）：截屏/录屏 + Xiaomi MIMO 视觉分析 + 真实鼠标键盘/窗口/程序控制 + computer_use 自主循环，临时截图与录屏帧自动清理。

拖拽非图片文件：桌面壳直取原始路径 / 拖拽自带路径直取 / 普通文件上传到工作区换取路径

GLM Mode: a fully tuned coding agent preset for zhipuai/glm-5.3-flash in DeepSeek Harness — PTC/Code Mode tool presentation, GLM-specific auto-compaction (75%/22%), native multimodal, and a guard family (reasoning loop guard + tool spin guard). The preset installs/uninstalls with the plugin.

Guide Dog for DSH, powered by MiniMax — multimodal plugin: image/video/music/speech generation, vision inspection tools, voice mode, microphone voice input and real-time voice call mode.

DeepSeek Harness plugin: let text-only models receive pasted images, and analyze them with a built-in OpenAI-compatible vision tool

Matter-aware legal workspace dashboard and document agent tools for DeepSeek Harness

Workspace-bound arbitrary file upload, reading, OCR, and rendering for DeepSeek Harness.

DeepSeek Harness (DSH) 插件：在设置页新增「OpenCode Go 模型同步」，一键拉取服务端全部模型、实测可用性与视觉能力并写回 llm-pi-ai 配置（补齐 dsh 内置「获取可用模型」静态快照的缺口）。

把高清截屏与录屏装进 DSH：按物理像素采集，网页按目标尺寸光栅化。

DeepSeek Harness 原生视觉 Bundle：粘贴或拖入图片，通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。

A virtual pet companion for the DeepSeek Harness web GUI: mood animations driven by live agent state, built-in sprites, custom image upload, Codex-style multi-frame spritesheet import, and a local companionship growth system with intimacy/level/EXP, interactions, achievements, and stats.

DeepSeek Harness 第三方订阅接入插件:登录第三方订阅账户即可使用订阅内的模型(当前支持 OpenAI / ChatGPT 订阅,更多订阅服务规划中;支持图片理解与对话内图片生成、编辑)

DeepSeek Harness Web provider quick configuration, model discovery and media utilities.

Qwen-MM-Plugins integration for DeepSeek Harness: 12 MCP multimodal tools (vision/OCR/grounding/ASR/AV), a Web settings page (paste a Qwen API Key), bundled skills, and a one-command installer.

(绘图)千问 · 优化版 —— 面向 DeepSeek Harness 的本地图像生成插件。经由本机 ComfyUI 调用 Qwen-Image 2.1 完成文生图与图生图，图像落盘保存并在会话中直接呈现；全部网络流量限于 127.0.0.1，无需联网与 API 密钥。本优化版在推理链路性能、显卡厂商适配（NVIDIA / Intel Arc / AMD RDNA2·3·4）与操作系统兼容（Windows / Linux）三方面进行了系统性增强。原作者 @奇迹与你，优化版 @yanfei0725。

Customize DSH Web thinking status with custom flowing text, animated GIF/APNG/WebP, or combined image-and-text modes.

Standalone ocr tool plugin for DeepSeek Harness (dsh) — local image text recognition via the newbee-ocr (nbocr) engine, for models without vision input

see_image tool for DSH: route image files to a configurable vision model (OpenAI-compatible API) and relay its description back to a text-only model

DeepSeek Harness plugin that bridges images to external vision APIs and returns text-only analysis

Image understanding for text-only models via OpenRouter free vision models

Add no-key hosted or OpenAI-compatible vision to DeepSeek Harness while keeping the configured reasoning model

Wallpaper skin for the DeepSeek Harness web UI: image background with opacity, mask and blur controls.

Windows desktop automation for DeepSeek Harness — plugs CursorTouch/Windows-MCP (screenshot, UI automation, input, clipboard, processes, registry) into DSH through the official MCP client bridge.