Give your DSH agent eyes via any OpenAI-compatible vision model - 11 provider presets (Doubao/Qwen-VL/GLM-V/OpenAI/Gemini/Ollama...), capability checkboxes that inject live prompt guidance, and analysis of images the user drops into the chat; the agent writes its own observation prompt, and base64 never enters its context.
Give your DeepSeek Harness agent eyes. dsh-client-vision is a screen-capture + external image-recognition plugin for DeepSeek Harness: the agent takes a screenshot (or points at any image), hands it to a vision-capable model through a pluggable channel, and gets back plain text it can actually act on — no multimodal model required.
Model-facing read_tiff tool for DeepSeek Harness: decodes TIFF/TIF images (multi-page, LZW/Deflate/PackBits/CCITT/JPEG compression, bilevel, 8/16-bit and float) into viewable PNGs with full header metadata, plus optional vision-model description.
Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, and GUI automation, through layered evidence memory and cache.
A native DeepSeek Harness (DSH) Cordis plugin that analyzes images through the reverse-engineered chat.deepseek.com vision mode (model_type=vision) — free, no third-party vision API key required. DeepSeek Harness(DSH)原生 Cordis 插件:通过逆向 chat.deepseek.com 识图模式(model_type=vision)分析图片,免费、无需第三方视觉 API key。
DeepSeek Harness plugin: transcodes images to a base64-safe format (PNG) before a vision request, so gateways like LM Studio (which only accept PNG/JPEG/GIF data URLs) do not reject WebP images.
Unofficial fork of computer-user: fixes the silent load failure on DSH >= 0.1.2, and returns screenshots as real images to vision models with an exact image->screen coordinate mapping.
Eyes for text-only DeepSeek: view_image tool (local Ollama or any OpenAI-compatible VLM) + chat image-attachment bridge — paste/drop images in the chat and the model can see them.
Attach an image to the DeepSeek Harness composer and the session model switches itself to a vision model — then restores your previous model when the image is removed. Material Design 3 button, native file picker, thumbnails. MIT.