dashitongzhi b2e9d33164 feat: add multimodal vision expert for image analysis and code generation ...

- VisionExpert class: image analysis + code generation from images
- Anthropic Messages API integration (mimo-v2-omni model)
- Gate classifier: new 'vision' expert type
- Orchestrator: vision pipeline with image_paths support
- CLI: /paste (clipboard) and /image (file) commands
- Optional deps: pip install kwcode[multimodal] (Pillow + pyperclip)
- Architecture diagram in docs/

2026-04-30 11:46:49 +08:00

..

kwcode_architecture.png

feat: add multimodal vision expert for image analysis and code generation

2026-04-30 11:46:49 +08:00