Auto-restart STT after TTS finishes speaking

Adds logic to detect when voice status transitions from 'speaking' to
'listening' and automatically restarts the speech recognition. This
enables continuous voice conversation flow - after Julia speaks her
response, the app immediately starts listening for the next user input.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

app/(tabs)/_layout.tsx

@@ -122,6 +122,27 @@ export default function TabLayout() {
     }
   }, [sttIsListening, startListening]);
 
+  // Track previous status to detect transition from speaking to listening
+  const prevStatusRef = useRef<typeof status>('idle');
+
+  // Auto-restart STT when TTS finishes (status changes from 'speaking' to 'listening')
+  useEffect(() => {
+    const prevStatus = prevStatusRef.current;
+    prevStatusRef.current = status;
+
+    // When transitioning from speaking to listening, restart STT
+    if (prevStatus === 'speaking' && status === 'listening' && sessionActiveRef.current) {
+      console.log('[TabLayout] TTS finished - auto-restarting STT');
+      // Small delay to ensure TTS cleanup is complete
+      const timer = setTimeout(() => {
+        if (sessionActiveRef.current && !sttIsListening) {
+          startListening();
+        }
+      }, 200);
+      return () => clearTimeout(timer);
+    }
+  }, [status, sttIsListening, startListening]);
+
   // Handle voice FAB press - toggle listening mode
   const handleVoiceFABPress = useCallback(() => {
     if (isListening) {