- **Compatibility Enhancements**:
- Added support to detect and inject missing `"format"` field in `model.json` files for TensorFlow.js compatibility.
- Modified model loading logic to handle both `tfjs-graph-model` and `tfjs-layers-model` formats.
- **New Features**:
- Introduced additional fallback paths for locating models to increase reliability in varying environments.
- Added support for mock implementations of the Universal Sentence Encoder in test environments.
- **Bug Fixes**:
- Fixed module loading resolution in `FileSystemStorage` with improved initialization and error handling for Node.js environments.
- Resolved issues with test assertions to improve validation logic in core tests.
**Purpose**: Improve model loading reliability, expand compatibility with TensorFlow.js models, and enhance test environment support.
- Introduced new documentation files under `docs/`:
- `model-bundling-analysis.md`: Provides detailed analysis of current, bundled, hybrid, and dynamic model loading approaches, including pros, cons, and recommendations.
- `model-management.md`: Explains how Brainy manages Universal Sentence Encoder models, including setup, usage, and troubleshooting.
- `optional-model-bundling.md`: Details the `@soulcraft/brainy-models` package for offline reliability with pre-bundled models.
- Added `src/utils/robustModelLoader.ts`:
- Implements enhanced model loading with retry mechanisms, timeout handling, fallback URLs, and optional local model bundling.
- Supports Node.js and browser environments with exponential backoff logic.
- Key Updates:
- **Hybrid Loading Strategy**: Recommended for balancing reliability and flexibility via hybrid online/offline mechanisms.
- **Enhanced Fallback Scenarios**: Robust loader improves network-dependent reliability for embedding workflows.
- **Offline Reliability Support**: Optional model bundling eliminates dependency on external services, supporting air-gapped and edge environments.
**Purpose**: Introduce a hybrid model loading approach with robust options for
