- Added ConversationManager for managing conversation history with configurable limits.
- Implemented InputQueue for serial processing of input items.
- Created SpeechManager for handling text-to-speech generation and streaming.
- Developed StreamProcessor for processing LLM streams and forwarding events.
- Added TranscriptionManager for audio transcription using AI SDK.
- Introduced WebSocketManager for managing WebSocket connections and messaging.
- Updated VoiceAgent to support new architecture and improved socket handling.
- Refactored index files to export new core components.
- Added a new WebSocket server implementation in `ws-server-2.ts` that utilizes the `VoiceAgent` for handling voice interactions.
- Integrated weather and time tools using the `ai` library for enhanced responses.
- Refactored existing `ws-server.ts` to streamline the connection handling and event logging.
- Enhanced `VoiceAgent` to support streaming speech generation with improved chunk handling and interruption capabilities.
- Introduced new event listeners for better logging and handling of speech-related events.
- Added graceful shutdown handling for the WebSocket server.
