Alexander Payne 72a58f1f49 feat: Multi-modal support with automatic model fallback ...

- Add MultiModalManager with capability detection for vision/audio/tools
- Define fallback chains: vision (llama3.2:3b -> llava:7b -> moondream)
                       tools (llama3.1:8b-instruct -> qwen2.5:7b)
- Update CascadeRouter to detect content type and select appropriate models
- Add model pulling with automatic fallback in agent creation
- Update providers.yaml with multi-modal model configurations
- Update OllamaAdapter to use model resolution with vision support

Tests: All 96 infrastructure tests pass

2026-02-26 22:29:44 -05:00

88 KiB

Raw History

View Raw