Update frontend assets.

Add echo cancellation toggle in UI and update project dependencies

Remove `speech_monitor` dependency from `asr_worker` service definition.

Add echo cancellation and VAD toggle support in service factories and routes

Fix help text for `--disable-echo-cancellation` to clarify the default behavior is not disabled

Refactor threading in `launcher.py` to standardize worker initialization, enforce daemon mode, and improve naming consistency.

Handle overflow errors in audio capture by adding `exception_on_overflow=False` and skip processing when no data is available.

Add `--disable-echo-cancellation` CLI option and update audio pipeline to support toggling echo cancellation and VAD

Integrate `SileroVAD` into `SpeechMonitor` for optional voice activity detection. Add `_detect_speech()` method and update queue handling logic. Implement `SileroVAD` as a singleton for efficient model management.

Add `silero-vad` as a dependency in `pyproject.toml` and update `uv.lock`

Increase queue timeout in audio and text processing services for smoother task handling

Refactor audio processing pipeline to normalize data in `SpeechMonitor` and streamline queuing in `AudioCapture`

Update `AudioCapture` to support both PyAudio and macOS native AEC＋VAD libraries

Add PyAudio as a dependency in `pyproject.toml` and update `uv.lock`

Refactor to replace `EchoCancellingAudioCapture` with `AudioCapture` across the codebase for improved clarity and flexibility

frontend

Clean input text in MoYoYo TTS by removing punctuation for better processing

Refactor LlamaCpp initialization to simplify parameter handling and remove unused callback manager

Enable debug mode with global configuration and detailed task logging when active

Reset task ID in speech recognizer for empty transcriptions to prevent errors

Add new voice model "Doubao" to MoYoYo configuration

Update performance logging format in TTS player for improved structure and readability

Enhance launcher startup log formatting for improved readability and visual appeal

Remove commented-out performance logging code from TTS player

Add new voice model "Ellen" to MoYoYo configuration

Update MoYoYo TTS prompt text for improved relevance and clarity

Improve speech recognizer to handle empty transcriptions

Add `tests/tts_test_output` to `.gitignore` to exclude test artifacts

Add unit tests for TTS audio generator

Update reference audio for MoYoYo TTS model

Simplify system prompts for test dialogue in Chinese and English

Simplify system prompts for text generation in Chinese and English

Refactor `test_llm_dialogue.py` for improved pipeline creation and streamlined testing

Refactor `test_llm_dialogue.py` to enhance multi-dataset testing for LLM dialogue

Add new voice model "Juniper" to MoYoYo configuration

Standardize punctuation for system prompts in both Chinese and English text generation modules.

Enhance WebSocket handling for connection management and reliability

Add session validation checks to `player.py` and `generator.py`

Change log level from `debug` to `info` for Python process stdout in `utils.js`

Refactor WebSocket handling with connection manager

Add `loguru` to hidden imports in `hook-voice_dialogue.py`

Replace `logging` with centralized `loguru`-based logger across all modules.

Add `loguru` dependency to `pyproject.toml` and update `uv.lock` files

Refactor response generation logic in `generator.py`

Add dynamic library path setup for `TestLLMDialogue`

Bump version to 1.0.1 in `package.json`

Remove unused conditional logic for second answer handling in `player.py` and `generator.py`

Adjust context window allocation logic based on memory tiers in `apple_silicon.py`

Comment out unused Kokoro TTS voice configurations

Add Maple and Cove voice models to MoYoYo TTS configuration