視覚ツール · DeepSeek Harness プラグイン — 22 ページ

Browser automation toolset for dsh-tui agents: Playwright-driven browser control with deepseek-v4-flash-vision-exp visual understanding.

Customize the DeepSeek Harness web UI: theme color presets (main area, sidebar, message bubble, send button) and a full-page background image. All reversible and light/dark aware.

Full DIY theme plugin for DSH web: color palettes, fonts, background image (upload/URL), glassmorphism, border radius.

DeepSeek Harness plugin that turns UI screenshots into implementation-grade web specs using OCR, deterministic geometry, scene graphs, assets, and render comparison.

让 dsh Web GUI 支持把任意文件上传进对话：composer 附件按钮（SVG 图标 + 多选）+ 待发送文件条（类图片上传）+ OS 文件拖拽上传 + 会话内文件卡片 + 宿主端持久化存储 + read_uploaded_file 模型工具（无需构建，纯 JS，中英双语文案）。

DSH user addons: file drop-upload, archived-session manager, model/token usage dashboard (auto-loads with the web profile)

Veneer — a lightweight visual editor to reskin the DeepSeek Harness UI: edit background surfaces (color/image/opacity) with theme persistence.

给纯文本模型自动配眼:图片消息自动桥接为视觉模型描述(日志内表面替换,不改写人类转录),附带 see_image 追问工具

Local vision bridge for DeepSeek Harness

DeepSeek Harness 全能插件：识别/生图/改图一体化，无需切换模型——用常规 DeepSeek 模型即可自动调用视觉与生图模型（gemini_vision / gemini_generate_image / gemini_optimize_image）。多后端：Gemini 原生 + 任意 OpenAI 兼容服务（GPT-4o、Qwen-VL、GLM-4V、Moonshot、gpt-image、DALL-E、Flux、Stable Diffusion、OpenRouter、硅基流动、各类中转等），生成后自动视觉自检反馈，优于 modlens。

DeepSeek Harness adapter that exposes each configured vision model as a selectable DeepSeek composite in Web UI.

DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.

vqa_ask 双模型视觉问答插件:主模型调用 vqa_ask 向视觉模型提问(图片字节真实送达),UI 实时展示"主模型提问 → 视觉模型回答"的 QA 过程,并在主设置提供多模态视觉模型选择页。

DSH web plugin: change the whole-app background image. Curated anime wallpaper library, online search, local import, right-click actions.

Web-enhanced plugin for DeepSeek Harness: task board with cron scheduling, git graph, preview/files/SCM right panel, DeepSeek balance line, and image understanding for text-only models

DeepSeek Harness native vision, gpt-image-2 image generation, and Seedance video generation via Xiapan Cloud.

图邮：让 DSH 助手把图片直接发到聊天里给你看，也支持生图和识图。

DSH plugin: pixel-to-text image reading for text-only models. Downscales and color-quantizes PNG/JPEG/GIF/BMP and feeds the coarse pixel grid to the model so DeepSeek can 'see' layout, colors and rough shapes without a vision model.

Vision sidecar for text-only coding agents.

便签 (sticky notes) client plugin for the dsh webui: floating, resizable post-it notes with markdown text and image notes, per-conversation binding, archived in browser localStorage.

DSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.

Screenshot-to-input for DeepSeek Harness: composer camera button + global hotkey (Alt+A) + listener bound to the app lifecycle, configurable in settings. 截图自动粘贴到 DSH 输入框：相机按钮 + 全局快捷键 + 生命周期绑定 + 设置页配置。

Screenshot-to-input for DeepSeek Harness: composer camera button + global hotkey (Alt+A) + listener bound to the app lifecycle, configurable in settings. 截图自动粘贴到 DSH 输入框：相机按钮 + 全局快捷键 + 生命周期绑定 + 设置页配置。

Warp-inspired image-to-theme plugin for the DeepSeek Harness web client.