시각 도구 · DeepSeek Harness 플러그인 — 14 페이지

Markdown viewer for the dock file explorer: renders .md/.markdown/.mdx files with a one-click switch to the text editor.

Android phone test automation for the dsh web GUI: persist phone-agent devices (~/.dsh/dsh-phone.json), keep WebSocket connections to the on-phone agent, drive JSON-RPC methods (openApp / tap / inputText / swipe / screenshot / getUI) from the web panel, and expose phone testing tools to agents (phone_list, phone_rpc, phone_open_app, phone_tap, phone_input, phone_swipe, phone_keyevent, phone_screenshot, phone_get_ui, phone_ui_find, phone_ui_tap, phone_ui_input, phone_ui_back). Hot-pluggable — mounted via ~/.dsh/cordis.patch.yml + a profile node_modules symlink, no dsh source changes.

Drag-and-drop file and folder attachments for the DeepSeek Harness Web UI

CLIProxyAPI provider for DeepSeek Harness with local auto-discovery, dynamic model sync, and native model switching.

Codex-backed web search, image generation, and image understanding tools for the DeepSeek Harness.

Multi-agent collaboration suite for DeepSeek Harness: a user-configured specialist roster with on-demand dispatch (team_call / roundtable), model comparison, and a multimodal vision bridge — models come from the official provider flow, no bundled adapters.

Windows computer use for the DeepSeek Harness: screenshot, click, type, scroll, read windows and the clipboard, plus an on-screen indicator the human sees and stops with ESC. No dependencies, no driver to install.

Image understanding, OCR, and persistent visual evidence for text-only DeepSeek Harness models

Unified image generation router for DeepSeek Harness (DSH). Auto-discovers image models from any OpenAI-compatible endpoint. Supports SenseNova, StepFun, Agnes, Qwen, Tongyi Wanxiang, Jimeng/Seedream, Hunyuan, GPT Image, Flux, Stable Diffusion, Imagen, and more. | DeepSeek Harness 统一绘图路由器：自动识别任意 OpenAI 兼容端点的绘图模型，支持商汤、阶跃〃Agnes、千问、通义万相、即梦、混元、GPT Image、Flux、Stable Diffusion、Imagen 等。

FileLens — right-column file explorer for DeepSeek Harness: lazy directory tree, multi-format preview (Markdown/JSON/CSV/diff/log/hex/image), search & grep, tabs, inline editing with containment + version-guarded writes.

DeepSeek Harness vision enhancer: raises image limits to official values and provides high-resolution tiled image reading via a dedicated tool.

Multi-engine reverse image search aggregator for DeepSeek Harness. Turn one public image URL into Google Lens / Baidu / Yandex / TinEye / SauceNAO / IQDB / Ascii2d search links.

对话内联图片:LLM 回复中输出的本地图片路径直接在消息正文内渲染为图片,支持 9 种格式、点击放大灯箱、可调尺寸

DeepSeek Harness bundle for a Windows desktop UI context picker and MCP server for Codex, DeepSeek Harness, and AI agents

AX-first computer use on macOS for DeepSeek Harness: accessibility-tree targeting instead of screenshot coordinate guessing, window-scoped input, action read-back verification, blank-frame-checked screenshots, and optional Jev (TypeSafe System One) semantic guards before irreversible actions — bridged to the macos-cu CLI.

Per-model reasoning-effort and vision capability editor for DSH pi-ai provider profiles.

Modellix Design, LLM, and Web providers for DeepSeek Harness

Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.

OCR via OpenAI/Anthropic vision APIs for dsh: ocr_recognize tool (percent coords + two-diagonal-point boxes, auto region re-read on low confidence), a collapsible settings card in Settings → Plugins (API format / URL / Key / Model, fetch model list, test connection). Hot-pluggable — mounted via ~/.dsh/profiles/web/cordis.patch.yml + a profile node_modules symlink, no dsh source changes.

Omni-modal workstation plugin for DeepSeek Harness: analyze_image + 6 vision toolkit tools (zoom/sample_colors/image_diff/ocr/detect/show), generate_image, and generate_video (t2v/i2v async-task). Backed by an ordered multi-card list (OpenAI/Anthropic/Gemini protocols; Custom/Ollama plus 28 built-in fixed providers), Tabbed settings (VLM / Image Gen / Video / Mirror / Fallback), single-request failover, mirror model routing, JPEG->PNG re-encode fallback, and an auto-saving web settings page.

A lightweight DeepSeek Harness vision delegation tool for text-only routes, with native OpenAI Responses, Chat Completions, and Anthropic Messages adapters.

Open Eyes for DeepSeek Harness: delegate images to a configurable multimodal model through OpenAI Responses, Chat Completions, or Anthropic Messages.

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

PixLuna image source tools for DeepSeek Harness