Plugins

Reconocimiento de imágenes configurable para modelos DSH solo de texto: los mensajes de imagen se transcriben primero mediante un modelo de visión compatible con OpenAI (URL base, ID de modelo y clave API configurados en una sección de Ajustes) y luego se pasan al modelo principal como texto, mientras se anuncia la compatibilidad con entrada de imágenes. El esquema de autenticación de la clave API es seleccionable (cabeceras de petición estilo OpenAI, Anthropic, Gemini o Azure) y se notifica la falta de una clave antes de enviar cualquier petición.

Panel de gestión de atención de tokens para DeepSeek Harness: seguimiento de uso y coste de tokens por tarea/día/semana/mes (aciertos/fallos de entrada, salida, razonamiento), precios punta/valle de DeepSeek, reconocimiento del tipo de tarea y consejos sobre cuándo cambiar de sesión, escribir un traspaso o compactar el contexto.

Kit de visión para DeepSeek solo de texto: herramienta `vision` invocable por el modelo, adaptadores contenedores para deepseek/opencode-go (v4 flash/pro), cuota de Antigravity IDE (default, flash/pro) / cualquier VLM compatible con OpenAI / Gemini / canales locales de Ollama, memoria de evidencias con rehidratación por compactación, caché de hash de contenido y un panel de cliente bilingüe.

Drive your local DSH from WeChat: a self-hosted iLink bridge over a persistent ACP session (context lives in DSH and is resumable), phone conversations grouped into the desktop workspace, with image recognition, file messages (Excel/Word/PDF, parsed by the agent itself) and voice transcripts. Access defaults to strict (only registered devices are served); the phone channel's permission preset is wide by design - see the README security section before sharing the bot.

Local-first voice conversations for DSH, with local speech recognition and synthesis and optional external providers.

DeepSeek Harness (Cordis) plugin — bi-temporal VSA memory + cognition engine + BLAKE3 provenance, exposed as a DSH storage+session plugin. End-to-end tested with a real Python subprocess.

Johari cognition-quadrant dialog prompt composer — adds a button above the composer that opens a 2×2 quadrant panel (known/unknown × AI-known/AI-unknown) to groom conversation context into a structured prompt written back into the draft.

Free vision OCR with adaptive tile recognition for long documents and Markdown/Word/PNG/Excel export.

A microphone button for DeepSeek Harness that writes browser speech recognition into the composer draft.

Screen capture and external vision recognition: take_screenshot, list_windows, analyze_image and view_image tools with a configurable GPT vision channel (gpt-5.5 / gpt-5.6-sol / gpt-5.6-terra), API key via the credentials service, and a settings card; view_image shows the screenshot in the Web UI while the model context keeps text only.

DeepSeek Harness (dsh) plugin that bridges the local 'Screen Automation Helper' desktop platform (Windows/macOS) into the Agent tool system. Exposes status, capabilities, workflow list/run/stop, run management, screen capture, local recognition primitives

Reutiliza el modo de visión integrado de DeepSeek web para modelos solo de texto: la herramienta deepseek_vision controla la automatización de navegador local deepseek-vision-cli (ayuda de inicio de sesión manual, deep-think activado, cierre automático del navegador) y devuelve descripciones de imágenes como texto.

Large-image recognition for vision-exp models: lossless 800×800 tile recognition (smart/pipeline/full), local OCR with preprocessing & handwriting routing, optional multi-vendor GPU (DirectML/CUDA/OpenVINO) with auto CPU fallback.

Minimal English-only voice input for the DeepSeek Harness Web UI: a mic button in the composer that transcribes speech into the draft via the browser's native SpeechRecognition API. No dependencies, no subprocess, no network calls beyond whatever the brow

Adds image input and recognition through configured DSH providers or an OpenAI-compatible endpoint.

Deterministic Reasoning Engine (DRE) for dsh: dre__* tools for knowledge verification (three-stage discrimination), deterministic cognition loops, constraint solving, mental models and synapse memory - strengthens information certainty.

Browser Web Speech dictation for the Composer: recognition needs no dedicated ASR server, key, or model download; reuses Session text and a configured DSH model for contextual phrase hints and optional transcript polishing.

明眸 VisionBridge - Puente visual propio: cuando un modelo ciego recibe imágenes, llama automáticamente a un modelo visual para reconocerlas y devuelve el texto reconocido al modelo principal; transparente, configurable y sin pérdidas al actualizar.

DeepSeek Harness OCR plugin — offline image text recognition powered by PaddleOCR-json (primary) and RapidOCR-json (fallback). 让 DeepSeek Harness 直接识别图片中的文字，无需视觉模型、完全本地离线运行。

Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.

Project memory for coding agents on DeepSeek Harness: similar past edits surface as precedents, out-of-scope edits are blocked, and cognition persists across sessions (47 upstream-verified fixes, gold-free 20-task run).