DeepSeek Harness 플러그인 — 395 페이지

A conservative intent compiler for Vibe Coders in DeepSeek Harness: clarify messy drafts without inventing details, then fill the result back into the composer.

Transactional data-only DSH configuration packs with integrity, ownership, and rollback

The Codex-governed Vibe experience for DeepSeek Harness, with optional bounded DeepSeek execution.

The provider-neutral Vibeify editorial experience for DeepSeek Harness.

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

Floating, draggable, resizable video scene player for DeepSeek Harness. Plays scene-per-MP4 clips from a Stash-style scene server, plus best-effort YouTube / Twitch / Jellyfin / custom links.

Inline video preview for dsh-better-sidebar: plays .mp4/.webm/.mov/.mkv/.avi etc. in the sidebar editor with HTTP Range (seeking) support via a dedicated /video host route

DSH 视频皮肤：一段短片循环铺成整个界面的聊天背景（无声、可调透明度），另一段做有声的开机动画（片尾交叉溶解进界面、点击画面随时跳过）。零依赖。

Plays a vanilla Minecraft villager "hmm" whenever the model hums inside its reasoning chain.

DeepSeek Harness Cordis plugin: drive Vimina Windows GUI automation via stdio (serve/call). Registers 26 vimina_* tools (scan/click/input/key/VMA scripts/screenshot/window/mouse).

毒蛇复盘 (viper recap): roast — or toast — the current session from its real event log. A model tool + a viperRecap projection + a 🐍 composer button and floating card.

Vision bridge for text-only models: describe attached images via another vision model or system OCR

Model-facing analyze_image tool for the DeepSeek Harness: multi-modal image understanding via any OpenAI- or Anthropic-compatible vision API, with 8 analysis modes, local path / http(s) URL / data URL input, and a Web UI hint that guides image-incapable models to the reliable local-path route.

DSH 插件：可接入识图模型 API（本地大模型识图工具 + 设置界面）。配置 OpenAI 兼容的识图接口（LM Studio / vLLM / Ollama 等），接口留空即不启用识图模型。

DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.

DSH 识图桥接插件：让 DeepSeek 等纯文本模型会话也能发送图片——图片在进入模型前自动交给外部视觉模型（阿里云百炼 qwen-vl）识别，识别结果以文字形式喂给当前模型。

Vision bridge: 拦截粘贴/拖入/导入的图片，交给 OpenAI 兼容视觉模型识别为文字并自动发送进对话；主模型可通过 vision_ask 工具复核追问。

Give a text-only dsh model eyes: pasted images are recognized into text via an OpenAI-compatible vision endpoint (Zhipu free by default) before the message reaches the model.

DSH 视觉插件（Edge 豆包桥接）：通用识图 + 数学建模图专项（几何图形/流程图/图表/表格/公式）+ 不确定项澄清闭环。零成本，免 API Key。

DSH 静默视觉增强：主模型照常选择，图片自动交给固定视觉模型后以隐藏上下文返回主模型。

Persistent vision plugin for DeepSeek Harness: registers the vision_analyze tool backed by a configurable multimodal model, with a settings-page UI. Zero dependencies.

DeepSeek Harness plugin: (1) installs an image-input (input modalities) checkbox into the Models settings catalog so a custom model can declare input:[text,image] and DSH passes images straight to it — the core feature; (2) optionally registers an OpenAI-compatible vision relay provider + vision_analyze/vision_status/vision_test/vision_configure tools. Host-only bundle (no settings card).

dsh-vision-plugin: give DeepSeek Harness text-only models a pair of eyes — pasted images are transcribed by a vision model before they reach a text-only main model, plus the vision_analyze tool and a bilingual settings page.

Native interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid, zoom, annotate, measure, diff, color, OCR) + MiMo V2.5 multimodal backend, with zero external MCP servers.