視覚ツール · DeepSeek Harness プラグイン — 24 ページ

Focus Mode for the dsh web GUI: a full-screen reading overlay that hides chrome and folds the AI tool-call flow into summaries, reusing the official Markdown / image primitives.

Galgame generator for DeepSeek Harness (DSH): give it a script document plus character/background/BGM assets in the workspace (img_human/, img_bg/, audio/) and it builds a playable visual-novel web page with 9-slot save/load, speaker-following sprites, BGM control and if-line branching. DSH Galgame 生成器：提供剧本文档 + 立绘/背景/音乐素材即可生成可玩视觉小说（9 槽位存档、自动立绘、BGM、if 条件线）。

游戏素材大师：DSH 插件，包含八方向图生成、图片生成、序列帧生成三个游戏素材模块。火山方舟 Seedream 生图 + MiniMax 图生视频 + 本地抠绿幕合成。

dsh plugin: generate/edit images via the locally installed OpenAI Codex CLI

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.

控制已登录的网页版 ChatGPT 生成图片并下载到本地 — DSH bundle 插件。

DeepSeek Harness plugin: Grok Imagine image generation as a model tool (subscription)

Unofficial community plugin for DeepSeek Harness: use a SuperGrok / X Premium subscription via OAuth, with grok-4.6 chat, fused server-side web/X search, and Imagine

DSH 鸿蒙投屏控制插件（静态 npm 包版 v2）：设备发现 / 实时投屏 / 触控操作 / 系统按键 / hilog 日志 / AI 截图识别

图解教学（Illustrated Teaching）：DeepSeek Harness 插件，把任何知识点自动渲染成精美图解画廊——8 套模板、真实图片检索、一键导出，专为本科阶段学习设计

Image generation plugin for DeepSeek Harness that calls gpt-image-2 through any OpenAI Images compatible endpoint, with in-conversation previews and a configurable settings card.

让 AI 助手能在会话里直接"看到"本地图片：/ws/<绝对路径> 把磁盘上任何位置的文件变成会话 markdown 可渲染的同源 http URL。Show any local file in DSH web sessions — no staging directory, any drive.

Region & sticker image skin for the DSH (DeepSeek Harness) web UI - paint the window, center, sidebar, welcome, right panel and composer with your own images, GIFs or videos, plus two draggable stickers, from a settings submenu.

图片皮肤插件：导入 PNG/JPG/WebP 自动生成主题配色（背景/强调色/高亮跟随图片主色调），并可选生成 Q 版宠物（程序化或 AI 生图）

Let DSH text-only-model conversations accept dragged/pasted images: save them into the session workspace and insert the file path as text, bypassing the webui attachment channel that otherwise rejects image parts.

Multi-provider image generation and editing tools for DeepSeek Harness

DSH host plugin: automatically sends images in user messages to a vision model (default mimo-v2.5 on opencode-go) and feeds the returned text description to the main text model (e.g. deepseek-v4-pro), without touching the visible chat transcript.

Local image editing toolkit for DeepSeek Harness: one image_edit tool for deterministic edits — cutout (quick flood-fill or rembg AI), trim, flip, rotate, brightness/contrast/saturation, blur, sharpen, rounded corners, border, canvas resize+center, sprite sheets, and PNG/JPEG/WebP export. Also ships as a skill (SKILL.md + CLI scripts).

DeepSeek Harness plugin: a third-party image-generation relay. Adds the 生图配置 card (Settings → Plugins → 插件配置) for configuring an OpenAI-compatible (/v1/images/generations + /v1/images/edits), DashScope (通义万相 async-task), Replicate or fal.ai image API; registers image_generate (文生图/图生图/局部重绘/指令编辑), imagegen_status, imagegen_test, imagegen_configure tools; installs a 生图 skill so the model auto-triggers on 生图/画图 mentions.

Give text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。

Text-to-image for DeepSeek Harness: a `draw_image` model tool, an input-bar 生图 button with a prompt popup (async generation, 4-grid results, download / keep / delete), an /imgdraw image route, and persisted history. Backends: DashScope wan2.7-image (free default) and SiliconFlow Qwen-Image.

DeepSeek Harness web plugin: paste files into the composer, store under session workspace/inbox/, read via read_inbox / list_inbox tools.

Codex OAuth provider with native compaction and image input support for DeepSeek Harness.

长任务编排：Codex 规划/打分/审核 + DSH 执行 + Kimi 补充（视觉验收/摘要/交叉验证）