視覚ツール · DeepSeek Harness プラグイン — 9 ページ

Custom background image plugin for the DeepSeek Harness web GUI: upload a local picture or paste an image URL, and render it behind the whole app surface with adjustable opacity, scrim, panel transparency and frosted-glass blur.

Out-of-tree dsh provider plugin: a DeepSeek gateway route that claims image input and transparently describes pasted images through a configured vision-language model (e.g. Qwen-VL) before the text-only DeepSeek wire sees them.

DSH 侧边栏文件活动插件：按 LRU 记录文件读取/新增/修改事件（最近访问），按绝对路径树形统计（文件统计），点击文件浮窗预览（代码高亮/Markdown/图片/PDF）。DSH web plugin: file activity tracker — LRU recent-access list plus per-file read/create/modify counts in a folder tree, with floating preview.

DSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision × fast/long × 2 slots), and one shared DSH provider carrying both slots' models with four thinking-effort levels.

dsh-mineru: MinerU 文档解析插件 for DeepSeek Harness — 多模态全格式 (PDF/Word/PPT/Excel/HTML/图片) → 结构化 Markdown. 填 Token 走精准解析 API, 留空走 Agent 轻量解析 API.

Dynamic attachment presentation plugin for conversation input, message-image, and trajectory image slots

Feishu (Lark) entry point for DSH: one-command install plugin that lets users drive DSH agents from a Feishu bot over the long-connection event channel, with image/file/video/audio attachments, interactive ask/approval cards, live streaming progress cards with a tool panel, and proactive feishu_send pushes.

Upload images and files to your image host from DeepSeek Harness, powered by PicGo

QQ Bot channel bridge for DeepSeek Harness

File explorer for the DSH dock: browse the active conversation's working directory and open files in the registered file viewers.

DSH skin plugin: built-in skins + custom image skins, pure client plugin (no source patch)

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。

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.

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

Xiaomi MiMo search + multimodal tools for DSH agents: mimo_search/vision/audio/video/asr/tts.

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。

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)

DSH 演示文稿技能 + 工具插件：一句话或一篇 Markdown 文档 → 完整演示文稿（独立 HTML 网页放映 + 可编辑 PPTX 导出），内置 5 套视觉主题与页间转场/要点入场动画（motion 可关），可配置默认主题/语言，中英双语，SKILL.md 薄路由 + references 按需装载，跨 harness。

DeepSeek Harness QoL plugin for the local Qwen3.8 line (27B, Flash-Next): per-request thinking budgets on both llama.cpp and NInfer dialects, vision + tools, and a compaction backend whose summaries stop burning the output cap on thinking.

便签静态插件:对话框右侧空白处的便签面板,可打字记录、勾选完成(删除线),localStorage 持久化,随 web 包常驻。

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

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 外置视觉模型插件：inspect_image 把本地图片或 http(s) 图片 URL 发给任意 OpenAI 兼容端点，视觉模型看图的文字回答直接带回对话；附 Web UI 设置栏。

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