@anionex/dsh-vision-toolkit
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
520 results
DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.
DSH Web内目前最无感的消息撤回、重编辑插件,原版体验,兼容性强,功能简单可开关,设置丰富,现代化轻量ui框架。The most seamless message recall & re-edit plugin for DSH Web — native experience, strong compatibility, simple toggles, rich settings, modern lightweight UI. DSH Web で最もシームレスなメッセージ撤回・再編集プラグイン——ネイティブ体験、高い互換性、シンプルなトグル、充実した設定、モダンで軽量な UI。
Design I/O for coding agents: controllable UI generation via declarations (spec/domain/craft/design/components/template) and contracts (skill/evaluator). Use for product UI—console, dashboard, agent-ops, CJK-first apps.
AI image generation plugin for the dsh web GUI: text-to-image and image-to-image through configurable provider channels (gpt-image-2 / grok-imagine-image / nanobanana series / seedream-5.0-pro / dall-e-3, with native xAI Grok Imagine, Google Nano Banana and ByteDance Seedream request shaping), per-channel model catalogs, a three-column studio beside the native conversation, an infinite canvas with node-graph workflows (annotation boxes with attached prompt cards, local background removal, AI layer split, per-node model choice, file nodes with any-file upload, and a canvas skill system covering skill-driven next steps on every node: text polish, image description, content extraction, and long-running headless-agent pipelines such as image-to-editable-ppt, with a local skill library that installs and removes skills from URLs or uploaded archives), an ecommerce product-set mode and a prompt template library.
DeepSeek Harness (DSH) plugin: one-click prompt enhancement (✨) and voice recognition (💬, cloud/local dual engines) for the composer
A whale-girl Kanban Musume mascot for DeepSeek Harness
喵丝滑:dsh 前端行为增强——输入框失焦折叠高度 + 窄屏选中 Session 自动收起侧边栏(纯 client 插件,零 dsh 本体改动)
Accessibility-first macOS Computer Use capability for DeepSeek Harness with stale-observation protection, app leases, confirmations, screenshots, and Web diagnostics
DSH web plugin: terminal-style input for the composer — bash-like Up/Down prompt history with prefix search and Ctrl+R, selection toolbar with copy and quote (Codex-style > blockquote), right-click paste, toggleable draggable chat TOC, fully international
客制化DSH(Custom DSH): web-surface theming (wallpaper, frosted glass, accent, translucent surfaces), configurable keyboard shortcuts (new conversation / model / thinking effort / composer gestures / usage panel), an app-usage panel, and entrance motion for conversations, the sidebar, and new conversations. Zero shell edits.
DSH 专属语音输入插件:点按或按住 Alt 说话、松开/再点按转文字,支持热词替换表(hot.txt)、自定义润色提示词、录音电平指示。默认本地离线识别(SenseVoice,零配置零 key、音频不出本机),自动回退浏览器 Web Speech,可选云端 ASR 与润色(复用 DSH 模型)。Voice input for DeepSeek Harness: tap or hold Alt to talk, get text in the composer — local SenseVoice by default, zero config, zero API key.
DSH Web GUI skill picker: a button beside the composer opens a searchable list of installed skills; picking one inserts the official `/skill-name` gesture into the input box, so the skill loads with your message (WorkBuddy-style skill invocation for DeepSeek Harness).
Gomoku (five-in-a-row) for the dsh web GUI: AI move routes, model catalog, and default prompt (node half) plus the conversation-view tab with the board (browser half)
Session-state notification plugin for the dsh web GUI: session completed/failed, question-asked, and permission-requested alerts with configurable built-in or custom sounds and browser notifications, plus a Notifications settings section
Hot-pluggable Hakurei Shrine (Touhou Project) skin for the dsh web GUI: shrine day/night backdrops, Reimu figures, framed sidebar & composer, transparent paper UI
Official, proxy-compatible, or locally accounted balance and session-cost readout for the DSH web GUI.
Import pi / opencode sessions, chat history, and agents into DeepSeek Harness (dsh): slash commands, session-start migration prompt, and a one-click Sync button in the composer.
DSH web plugin: VSCode Remote-SSH-like remote development (SSH to supercomputers/servers, remote workspace, file explorer, integrated terminal), integrated with dsh-better-sidebar and DSH settings.
Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace-scoped recall, and fully configurable keys — plus sliding-context awareness (compaction summaries join recall/search, a compaction notice with one-click /compact fill) layered on the ordinary composer draft only.
Agent 运行中也能实时插入修改要求:composer 上方弹出「修改要求」输入条,与底部输入框左对齐,输入框随内容自动换行扩展,发送后注入正在运行的 agent 的下一个决策步骤,无需停止对话。运行时状态文案采用 100 条 Deep 短语池轮换,按钮为 ➤ 旋转 90° 的向上箭头。
DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.
A SillyTavern compatibility plugin that keeps DSH authoritative over sessions and execution, with frontend and backend APIs for composing Tavern capabilities with native DSH features.
Windows computer use for DeepSeek Harness: an MCP stdio server + PowerShell UIA backend, bridged into DSH via @deepseek-ai/dsh-mcp-client. Read/act on real Windows desktop apps (UI Automation tree, screenshots, typed input, OCR, window management).
Drop or paste images, PDFs, office docs, zips, videos and audio into the DSH composer as workspace file paths instead of model attachments — lets a text-only model agent read them via vision tools.