feat: Implement remote audio management and diagnostics

refactor: Remove observed total latency from metrics calculations

feat: Add new report and turn metrics functions in test_analyze_traces

refactor: Remove LLM to TTS handoff latency from metrics and UI

feat: Enhance metrics collection and turn tracing for assistant responses

feat: Enhance metrics collection and tracing for assistant text

feat: Enhance metrics collection and assistant item correlation

feat: Enhance turn tracing and metrics collection

codex fixex

feat: Add unit tests for analyze_traces module

feat: Introduce MCP connection timeout handling and enhance configuration

feat: Enhance voice activity detection and turn tracing features

chore: Update .gitignore to exclude codex-skills directory

docs: Refine README.md structure and content

docs: Update README.md for improved structure and clarity

feat: Implement NVIDIA TTS stream patch for improved synthesis handling

feat: Add Deepgram STT provider support and enhance configuration options

feat: Add NVIDIA TTS provider support and enhance configuration options

feat: Implement dynamic TTS footer component and enhance footer HTML generation

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

feat: Enhance LiveKit worker configuration and documentation

chore: Remove unused demo GIF file from assets directory

chore: Update demo GIF in README and remove old demo file

refactor: Consolidate LLM runtime configuration using LLMSettings

feat: Update Ollama configuration for cloud and local usage

refactor: Simplify MCP startup greeting for improved user interaction

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 and PocketTTS connection options in session management

feat: Update default Ollama model and enhance trace history management

feat: Add Langfuse tracing support and UI enhancements

feat: Update LLM runtime configuration and tests for thinking behavior

feat: Enhance turn pipeline summary with partial updates and tool activity tracking

feat: Introduce turn pipeline summary and enhance tool execution metrics

feat: Update Ollama configuration and validation for cloud usage

feat: Enhance metrics collection with event timestamps for assistant interactions

feat: Enhance assistant behavior and tool feedback mechanisms

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

feat: Enhance metrics collection and tracing with speech_id support

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: Enhance telemetry with tool call tracing and metrics collection

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.

Update dependencies for Langchain and Livekit: Modify pyproject.toml to include 'openai' extra for livekit-agents and update langchain-nvidia-ai-endpoints to version 1.1.0. Add langchain-ollama as a new dependency with version 1.0.1 in uv.lock.