Feat: Hermes Voice Client (Wake Word + STT + Vision + TTS)

Windows-Desktop-Script: Energy VAD + Whisper Wake Detection,
faster-whisper STT, mss Screen Capture, MC2 Vision/Chat API,
Edge TTS Ausgabe, pystray System Tray. Kein Account nötig —
Wake Word frei konfigurierbar via WAKE_WORDS in config.py.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

client/hermes-voice/screen_capture.py

@@ -0,0 +1,19 @@
+import base64
+import io
+import mss
+from PIL import Image
+from config import SCREENSHOT_MONITOR, SCREENSHOT_WIDTH, SCREENSHOT_HEIGHT
+
+
+def capture_screen() -> str:
+    """Screenshot des primären Monitors als base64-JPEG."""
+    with mss.mss() as sct:
+        monitor = sct.monitors[SCREENSHOT_MONITOR]
+        raw = sct.grab(monitor)
+        img = Image.frombytes("RGB", raw.size, raw.bgra, "raw", "BGRX")
+
+    img = img.resize((SCREENSHOT_WIDTH, SCREENSHOT_HEIGHT), Image.LANCZOS)
+
+    buf = io.BytesIO()
+    img.save(buf, format="JPEG", quality=80)
+    return base64.b64encode(buf.getvalue()).decode("utf-8")