- Add HybridModelManager with singleton pattern to prevent duplicate model loads
- Implement triple-fallback model downloading (CDN → GitHub → Hugging Face)
- Fix soft-delete filtering to only apply when metadata filters are present
- Enhance model initialization with environment-specific optimizations
- Fix vitest configuration to use correct setup file
- Ensure consistent 384-dimensional embeddings across all operations
This release combines the best of both approaches:
- Singleton pattern prevents multiple ONNX model loads in memory
- Multi-source fallback ensures model availability even if CDN is down
- Soft deletes work correctly without breaking pure vector searches
- All core functionality preserved with enhanced reliability
- Fix soft delete functionality by filtering out deleted items in search results
- Add support for encrypted configuration storage and retrieval
- Copy test suite and vitest config to ensure all functionality works
- Maintain all core brainy functionality during repository cleanup
