Plugins

DeepSeek-Gehirn plus automatische Bildtranskription: Bilder in der GUI anhängen, jedes wird vor Erreichen des reinen Text-DeepSeek über ein beliebiges OpenAI-kompatibles VLM in Text umgewandelt — ein schlüsselbasierter Fast Path (Standard qwen3.7-flash; DashScope/Zhipu/OpenRouter oder jeder OpenAI-kompatible Endpoint) mit eigenem Key, oder lokales Ollama, automatisch erkannt, ohne Konfiguration.

Multimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.

DeepSeek Harness out-of-tree plugin: give a text-only coding model eyes by routing images to a Qwen-VL (DashScope) route through ctx.llm and returning text.

Adds an image_describe tool backed by the DashScope OpenAI-compatible vision API; on text-only sessions, pasted images are stored as local paths for the model and rendered inline in the chat transcript.

On-demand vision for text-only DeepSeek models: upload images, and the model calls a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).