視覚ツール · DeepSeek Harness プラグイン — 21 ページ

DeepSeek Harness plugin for OpenAI Codex OAuth, pooled accounts, model awareness, official docs, web search, and image generation

Paste/drop non-image files or folders into the DSH chat composer: paste inserts native @path references, drop inserts absolute paths.

PixLuna image source tools for DeepSeek Harness

DeepSeek Harness 界面背景图片插件：网络/本地图片与预设渐变背景，支持图片不透明度、沉浸式全屏/仅对话区域、毛玻璃模糊与分区不透明度调节。

One-key ClawRouters plugin for DeepSeek Harness: chat, image generation, video generation, and web search

Local image/voice/music/SFX for DeepSeek Harness with asset consistency: the same character stays the same character across calls, degenerate output is refused, and the GPU is untouched when idle.

DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev

Upload an image as the whole-page background wallpaper with adjustable dark scrim / opacity / blur, surfaced in Settings → 自定义主题

DSH 常驻绘图插件：固定 ComfyUI 工作流文生图面板

Adds opt-in image-capable sibling routes for text-only providers and converts image blocks into budgeted, locally enhanced OCR, color-statistics, pixel-scan, and metadata evidence before delegation.

【(绘图)千问 · @奇迹与你】让 DeepSeek Harness 在对话里直接调用本机 ComfyUI（千问 Qwen-Image 模型）画图：说一句「画一只猫」就出图，图片落盘到千问1生图目录并在聊天框里直接显示。只走本机 127.0.0.1，不出网、不花钱、不需要任何 API Key。

DeepSeek Harness 插件：静默 Chrome 扫码登录，自动给 QQ 空间发说说，支持配图、每日上限、主动发。

DSV4.1 reasoning support with multimodal context and bounded artifact acceptance for DeepSeek Harness

Hides the DSH window, lets you drag a rectangle over the screen, and drops the cropped PNG straight into the composer as a draft image.

ShotTagGo DSH — full-frame screenshot annotation for DeepSeek Harness. Numbered red boxes and comments inserted into the composer.

Show a local image or short video inside the current DeepSeek Harness conversation card, with click-to-preview. Does not replace the official read_image model path.

Plug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.

DeepSeek Harness appearance skin: minimal themes, accent/text/region colors, image skins, named presets, durable settings.

DeepSeek Harness plugin that compacts long chats by rendering history into compact bitmap frames a vision model can read, while keeping exact head/tail text and a searchable archive.

Themes and personalisation for DeepSeek Harness: 18 themes, a theme editor (moods, one colour, any word or any image; locks, fine-tune sliders, variations, undo, colour-blindness preview), a theme per workspace, a community gallery of themes and prompt packs, liquid-glass panels, wallpapers (Bing daily, slideshow, video), fonts, saved looks on a time or sunrise/sunset schedule, Windows accent colours, layout and focus mode, AI modes, task-finished alerts, a usage and cost dashboard with spending alerts, chat export to Markdown and PDF, accessibility options, smarter saved prompts, settings sync via a private GitHub Gist, a Ctrl+K quick switcher, and 19 languages

Think Ultra v0.1.0 — heavy local reasoning layer for the official DeepSeek Harness. Native max-effort base with isolated Flash/Vision/Pro depth controls, isolated velocity/apex mode profiles, reasoning toolboxes and an offline Rust core. The client bundle is delivered hardened/obfuscated; commercial operation is allowed, reverse analysis, modification, extraction and re-upload are not - see LICENSE.

Switchable model/reasoning UI for the DSH composer; reasoning levels come from the system model catalog.

Local vision 'eyes' for DeepSeek Harness (DSH): screen tool (capture screen or image -> local OpenAI-compatible VLM description) and ocr tool (Windows built-in OCR, zero model / GPU / cloud).

DSH 视觉原语工具：参考 DeepSeek《Thinking with Visual Primitives》论文，将图片路由到外部视觉模型并返回带视觉基元的文本分析。纯文本循环，对话模型无需原生视觉能力即可'看见'图片。