text-only-llm 3

dsh-vision-toolkit v0.1.39 Đã xác minh Giao diện web 834

DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.

dsh plugin add @anionex/dsh-vision-toolkit
dsh-vision-bridge v1.0.0 Đã xác minh Giao diện web 6

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

dsh plugin add @dsh-extension/dsh-vision-bridge
dsh-plugin-qwen-image v0.3.1 Đã xác minh Giao diện web 2

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.

dsh plugin add dsh-plugin-qwen-image