feat: Introduce new core components for conversation and speech management

- 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.

src/index.ts

@@ -1,5 +1,5 @@
 // Agents
-export { VoiceAgent, type VoiceAgentOptions } from "./VoiceAgent";
+export { VoiceAgent, type VoiceAgentOptions } from "./VoiceAgent.new";
 export {
     VideoAgent,
     type VideoAgentOptions,
@@ -8,7 +8,7 @@ export {
     type VideoAgentConfig,
     type FrameContext,
     type FrameTriggerReason,
-} from "./VideoAgent";
+} from "./VideoAgent.new";
 
 // Shared types
 export {