Fix login data structure and improve voice input UX

- Fix login endpoint to return families as array of objects instead of strings
- Update auth interface to match /auth/me endpoint structure
- Add silence detection to voice input (auto-stop after 1.5s)
- Add comprehensive status messages to voice modal (Listening, Understanding, Saving)
- Unify voice input flow to use MediaRecorder + backend for all platforms
- Add null checks to prevent tracking page crashes from invalid data
- Wait for auth completion before loading family data in HomePage

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

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

maternal-web/app/api/voice/transcribe/route.ts

@@ -16,7 +16,7 @@ export async function POST(request: NextRequest) {
     let transcribedText: string;
 
     if (contentType.includes('application/json')) {
-      // Text input (already transcribed)
+      // Text input (already transcribed) - forward to backend for LLM classification
       const body = await request.json();
       transcribedText = body.text;
 
@@ -29,6 +29,41 @@ export async function POST(request: NextRequest) {
           { status: 400 }
         );
       }
+
+      // Forward text to backend for LLM-based classification
+      const backendUrl = process.env.NEXT_PUBLIC_API_URL || 'http://localhost:3020';
+      const backendResponse = await fetch(`${backendUrl}/api/v1/voice/transcribe`, {
+        method: 'POST',
+        headers: {
+          'Content-Type': 'application/json',
+          // Forward auth token if present
+          ...(request.headers.get('authorization') && {
+            authorization: request.headers.get('authorization')!,
+          }),
+        },
+        body: JSON.stringify({
+          text: transcribedText,
+          language: body.language || 'en',
+          childName: body.childName,
+        }),
+      });
+
+      if (!backendResponse.ok) {
+        const errorData = await backendResponse.json();
+        return NextResponse.json(errorData, { status: backendResponse.status });
+      }
+
+      const result = await backendResponse.json();
+
+      // Backend returns { success, transcript, classification }
+      return NextResponse.json(
+        {
+          success: true,
+          transcript: result.transcript,
+          classification: result.classification,
+        },
+        { status: 200 }
+      );
     } else if (contentType.includes('multipart/form-data')) {
       // Audio file upload - forward to backend for Whisper transcription
       const formData = await request.formData();