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/llm.py

@@ -1,14 +1,15 @@
 import json
+import os
 import re
 import requests
 from datetime import date
 
-from .config import GATEWAY_URL, VOICE_MODEL, AGENT, AGENTS, log
+from .config import AGENTS, log
 from .text import clean_for_speech, find_sentence_end
 from .tts import speak, play_error_sound
 
 SYSTEM_PROMPT = "Отвечай кратко, 1-2 предложения, без markdown, без эмодзи."
-MAX_HISTORY = int(__import__("os").getenv("MAX_HISTORY", "20"))
+MAX_HISTORY = int(os.getenv("MAX_HISTORY", "20"))
 
 RESET_PATTERNS = re.compile(
     r"(начни|начать|создай|открой|давай).{0,10}(новую|новый|чистую|чистый).{0,10}(сессию|сессия|диалог|разговор|чат)"