Plugins

Docker tools for agents: ps/images/logs/inspect/exec/manage with JSON output, env-configurable CLI path, approval-gated exec and zero runtime dependencies.

Customizable brand area for the Web UI: replace the whale logo and DeepSeek wordmark with local images, and edit the HARNESS badge text (double-click to change, right-click to reset).

Drag & drop or click to attach any non-image file (PDF/Word/Excel/ZIP/text) into the composer: in the desktop shell it resolves the real Finder path instantly; otherwise it uploads to the workspace and inserts the path.

Compañero de sesión con cuatro módulos: exportación inteligente de conversaciones (Markdown/PDF/JSON/imagen larga PNG, con redacción de privacidad y ZIP por lotes), resúmenes de traspaso de contexto con guardado/importación de plantillas, optimización del coste de la API (precios oficiales en vivo, programación en horas pico/valle, presupuestos diarios/mensuales, enrutamiento de modelos), y búsqueda global de conversaciones con búsqueda dentro del chat (Ctrl+F, CSS Custom Highlight API).

DSH Pet Corner: una mascota flotante, un proxy de imágenes de mascotas sin clave, favoritos y una API de ajustes propia del plugin

Plugin de DeepSeek Harness que conecta las imágenes de la sesión con APIs de visión conectables, manteniendo a DeepSeek como el modelo principal.

Herramientas `web_search`, `image_gen` e `image_vision` respaldadas por Codex para DeepSeek Harness, reutilizando el estado de inicio de sesión OAuth de ChatGPT.

Puente de visión nativo del proveedor LLM: las imágenes pegadas en el chat son descritas por un modelo de visión (Qwen3-VL vía pi-ai/llama.cpp) y esa descripción de texto se envía a DeepSeek de solo texto para la respuesta; la admisión de imágenes, el enrutamiento y la compactación pasan por mecanismos nativos del harness, con una caché LRU de descripciones y reintento en 503.

Las imágenes adjuntas en el editor se transcriben a texto mediante un modelo de visión compatible con OpenAI antes de llegar a los modelos de DeepSeek de solo texto.

Renderiza rutas de imágenes locales de las respuestas del asistente directamente en el cuerpo del mensaje (9 formatos, lightbox con zoom al hacer clic, tamaño ajustable).

Discord-native remote controller for DeepSeek Harness: drive persisted coding-agent sessions from DMs, mention-gated guild channels, and threads, with slash commands, progress updates, approvals, structured questions, and image and text attachments.

In-chat preview for produced files: click a produced-file chip to render Markdown (server-side markdown-it + highlight.js), images, or plain text right in the conversation; system-app open and reveal-in-folder stay one click away.

Preview Mermaid diagrams as images via local rendering in DSH Web when the chat message contains a Mermaid fenced code block, and also allow integration with external rendering servers.

Universal image generation for DeepSeek Harness: auto-discovers image models from any OpenAI-compatible endpoint (SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more), with agent tools and REST API.

Renders pasted/uploaded images inline in the DSH Web chat and gives text-only models vision: the model-invokable visual_review tool calls any OpenAI-compatible multimodal API first, falling back to a local Qwen3-VL worker.

Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.

Full vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.

Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

GPT Image 2 `image_gen` with Codex subscription OAuth by default or explicit API-key mode: developing card, up to three live API partials, durable attachment replay/lightbox/download, text-only model output, and bounded credential-safe requests.

Vision bridge for text-only DeepSeek routes that analyzes attached and local images through configurable OpenAI Responses, Chat Completions, or Anthropic Messages endpoints while leaving image-capable routes native.

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

Free vision bridge for text-only models: image understanding, OCR, UI and debug analysis via free-tier providers (Qwen3-VL-Flash, Doubao, DeepSeek-OCR) with a settings GUI.

Sticker/emoji expression for assistants: emotion-driven auto-matching, library management, AI image tagging, dialects, style mimicry, and chat-based tag refinement.