Switch wake word from Porcupine to openwakeword + training pipeline

- Add training/ pipeline (step_1..step_5) and own-samples flow
- record_wav.py with single-shot and long-record modes, RMS-based silence filter
- remove_silent.py to drop silent samples and renumber
- modes.py: openwakeword inference with reset() and quiet predictions; commented Lusya block for later
- stt.py: drop local faster-whisper fallback, Groq-only
- config.py: remove unused STT_PROVIDER/WHISPER_*
- llm.py: replace __import__("os") hack with proper import
- tts.py: remove debug traceback in play_error_sound
- requirements.txt: add openwakeword/sounddevice/scipy, drop faster-whisper
- deploy/setup.sh: validate ELEVENLABS_API_KEY and WAKE_WORD_COSMO presence
- README.md, CLAUDE.md, project_roadmap memory updated to reflect new architecture

satellite/tts.py

@@ -133,9 +133,6 @@ def play_activation_sound():
 
 def play_error_sound():
     """Звук ошибки — 'не получилось'"""
-    import traceback
-    print("🔴 play_error_sound вызван из:")
-    traceback.print_stack()
     try:
         _play_sound_file("Error_Cosmo.mp3")
     except Exception as e: