Overview
dsh-vision-opencode
DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.
README / EN
Package documentation
Registry summary
DeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.
dsh.pub verifies the pinned bundle contract, runtime facts, and distribution semantics. The complete README remains in the source repository.
Read the full README on GitHub