feat: Introduce MCP connection timeout handling and enhance configuration

feat: Add Deepgram STT provider support and enhance configuration options

feat: Add NVIDIA TTS provider support and enhance configuration options

feat: Add support for Deepgram TTS provider and related configurations

refactor: Revise assistant instructions and configuration summary formatting

feat: Introduce MCP startup greeting timeout and PocketTTS connection timeout settings

refactor: Consolidate LLM runtime configuration using LLMSettings

feat: Add support for extra MCP server URLs and enhance assistant instructions

feat: Enhance assistant instructions and footer display for LLM providers

feat: Update LLM runtime configuration and tests for thinking behavior

feat: Update Ollama configuration and validation for cloud usage

feat: Enhance assistant behavior and tool feedback mechanisms

feat: Add post-tool response timeout and enhance error handling in channel metrics

refactor: Restructure agent components and remove unused files

[200~feat: Enhance tool tracing and feedback mechanisms

feat: Add soundfile dependency and implement pre-tool feedback mechanism

feat: Implement LLM warm-up functionality and update connection settings

feat: Implement startup greeting monitoring and enhance greeting handling

feat: Add LLM runtime and STT factory implementations

Add MCP runtime support and update configuration: Introduce MCP_ENABLED setting in settings.py and .env.example, enhance README with MCP runtime details, and implement MCP runtime decision logic in agent.py. Update agent instructions and ensure fallback to legacy runtime when MCP is unavailable.