fix: 添加yaw补偿（向左5度），修复机器人偏向用户右边的问题

fix: 修正pitch补偿方向（正值向下看）

fix: 添加人脸追踪pitch偏移补偿（向下7度）

refactor: 使用SDK的compose_world_offset进行正确的pose组合

fix: 修复euler顺序和Sendspin音频播放

fix: 修复Sendspin音频播放和人脸追踪平滑

fix: 修复人脸追踪偏上问题

debug: 添加最终pose日志

debug: 暂时禁用face tracking smoothing进行调试

fix: 反转pitch方向，修复机器人向上看的问题

debug: 添加人脸追踪调试日志，移除Y偏移，增加smoothing factor

fix: Noise suppression启动时设置为15% (PP_MIN_NS=0.85)

fix: Noise suppression默认值改为15%

fix: 人脸追踪Y轴偏移补偿，看向眼睛而非脸部中心

fix: Sendspin PLAYER角色需要player_support参数

fix: Sendspin使用固定client_id和PLAYER角色，恢复原版人脸追踪参数

fix: 人脸追踪添加平滑过渡，避免抽搐式转头

fix: 人脸追踪Y轴偏移补偿，移除Sendspin发送逻辑

feat: Sendspin自动发现，无需用户配置

fix: IDLE state should be completely still, restore face tracking fps

fix: reduce control loop frequency to prevent daemon crash in IDLE state

feat: add Sendspin multi-room audio support (Phase 13)

combined all reference-doc as one folder

update __version__

v0.4.0: Daemon stability fixes and microphone optimization

chore: bump version to 0.3.0

fix: enable face tracking by default and improve tap detection logging

refactor(movement): use SDK compose_world_offset for proper pose composition

refactor: optimize based on SDK analysis and conversation_app reference

fix: restore tap continue feedback sound (preserve functionality)

fix: reduce noise suppression for better microphone sensitivity

fix: tap-to-wake blocking and microphone sensitivity issues

feat: add tap sensitivity slider entity for Home Assistant

feat: 优化人脸追踪和修复Music Assistant兼容性

Revert "v0.2.21: Fix daemon crash - reduce control loop to 2Hz, pause during audio"

v0.2.21: Fix daemon crash - reduce control loop to 2Hz, pause during audio

v0.2.20: Revert audio/satellite/voice_assistant/models/main to v0.2.9 working state

v0.2.19: Force localhost connection mode to prevent WebRTC errors

v0.2.18: Fix audio playback - restore wakeup sound, use push_audio_sample

v0.2.17: Remove head_joints/passive_joints, move error_message to diagnostic

v0.2.16: Fix TTS playback - pause recording during playback

v0.2.15: Use play_sound() instead of push_audio_sample() for TTS

v0.2.14: Pause audio recording during TTS playback to prevent GStreamer conflicts

v0.2.13: Don't manually start/stop media - let SDK/daemon manage it

v0.2.12: Disable breathing animation to prevent serial port overflow

fix: Remove unnecessary import and sleep

fix: Remove redundant import time

v0.2.11: Disable wakeup sound to prevent daemon crash + add debug logging

v0.2.10: Add debug logging for motion init + fix audio fallback samplerate

fix: Use gstreamer media_backend + add debug logging for motion init