- Add ConsensusSnapshot and ConsensusSlot classes for structured consensus state representation.
- Introduce OnlineLanguageLearner for stateful online learning with experience replay and EWC regularization.
- Create WorkspaceEvent and ActionEvent classes for serializable event types.
- Develop InMemoryVectorMemoryStore for storing and querying workspace events.
- Implement ActionPolicy to manage action selection and motor parameterization.
- Establish a unified WorkspaceRuntime for managing the agent's lifecycle and interactions.
- Enhance tests in test_smoke.py to cover new functionalities and ensure correctness.
- Implemented `fetch_corpus.py` to scrape Chinese educational content from Wikipedia, covering subjects like Chinese, Math, English, Chemistry, Politics, History, Geography, Physics, and Biology.
- Developed `fetch_corpus_incremental.py` for incremental fetching of missing entries, with automatic retries for rate limiting and support for resuming interrupted downloads.
- Created `train_chat.py` for training a dialogue model, including corpus cleaning, vocabulary management, and staged training with adaptive learning rates.