perf(android): replace flutter_gemma with llamadart — 150 MB → 42 MB APK

.github/workflows/release.yml

@@ -34,8 +34,10 @@ jobs:
       - name: Generate ObjectBox bindings
         run: dart run build_runner build --delete-conflicting-outputs
 
-      - name: Build release APK
-        run: flutter build apk --release --split-per-abi --target-platform android-arm64,android-x64
+      - name: Build release APKs
+        run: |
+          flutter build apk --flavor lite -t lib/main_lite.dart --release --split-per-abi --target-platform android-arm64,android-x64
+          flutter build apk --flavor full -t lib/main_full.dart --release --split-per-abi --target-platform android-arm64,android-x64
 
       - name: Rename APKs with version
         run: |

android/app/build.gradle.kts

@@ -20,10 +20,7 @@ android {
     }
 
     defaultConfig {
-        // TODO: Specify your own unique Application ID (https://developer.android.com/studio/build/application-id.html).
         applicationId = "dev.koshika.koshika"
-        // You can update the following values to match your application needs.
-        // For more information, see: https://flutter.dev/to/review-gradle-config.
         minSdk = flutter.minSdkVersion
         targetSdk = flutter.targetSdkVersion
         versionCode = flutter.versionCode
@@ -32,8 +29,6 @@ android {
 
     buildTypes {
         release {
-            // TODO: Add your own signing config for the release build.
-            // Signing with the debug keys for now, so `flutter run --release` works.
             signingConfig = signingConfigs.getByName("debug")
             isMinifyEnabled = true
             isShrinkResources = true
@@ -48,6 +43,32 @@ android {
             excludes += "**/libimagegenerator_gpu.so"
         }
     }
+
+    flavorDimensions += "appType"
+    productFlavors {
+        create("lite") {
+            dimension = "appType"
+            applicationIdSuffix = ".lite"
+            versionNameSuffix = "-lite"
+        }
+        create("full") {
+            dimension = "appType"
+        }
+    }
+}
+
+// Strip llama.cpp native libs from the lite flavor APK.
+// This runs after packaging to remove AI inference libraries,
+// keeping the lite APK small (~15MB smaller).
+androidComponents {
+    onVariants(selector().withFlavor("appType" to "lite")) { variant ->
+        variant.packaging.jniLibs.excludes.addAll(listOf(
+            "**/libllama.so",
+            "**/libggml*.so",
+            "**/libmtmd.so",
+            "**/libllamadart.so",
+        ))
+    }
 }
 
 flutter {

android/app/proguard-rules.pro

@@ -1,7 +1,3 @@
-# MediaPipe optional proto classes (not needed at runtime)
--dontwarn com.google.mediapipe.proto.**
--dontwarn com.google.mediapipe.framework.GraphProfiler
-
 # ML Kit optional language model classes (only Latin script is used)
 -dontwarn com.google.mlkit.vision.text.chinese.**
 -dontwarn com.google.mlkit.vision.text.devanagari.**

lib/constants/ai_prompts.dart

@@ -3,12 +3,11 @@
 /// Keeping prompts here (rather than inlined in service files) makes them
 /// easy to review, iterate, and A/B test without touching service logic.
 abstract final class AiPrompts {
-  /// System prompt for the Gemma chat model.
+  /// System prompt injected before every user query.
   ///
-  /// Injected as a [Message.systemInfo] turn before every user query.
   /// Lab data context is added separately to the user turn so that
   /// small (1B-param) models cannot ignore it.
-  static const String gemmaSystemPrompt = '''
+  static const String systemPrompt = '''
 You are Koshika AI, a helpful on-device health assistant built into the Koshika app. You help users understand their lab report results.
 
 CRITICAL RULES:

lib/main.dart

@@ -1,7 +1,6 @@
 import 'dart:ui';
 
 import 'package:flutter/material.dart';
-import 'package:flutter_gemma/flutter_gemma.dart';
 
 import 'screens/chat_screen.dart';
 import 'screens/dashboard_screen.dart';
@@ -11,25 +10,67 @@ import 'screens/settings_screen.dart';
 import 'screens/splash_screen.dart';
 import 'services/objectbox_store.dart';
 import 'services/biomarker_dictionary.dart';
-import 'services/embedding_service.dart';
-import 'services/gemma_service.dart';
+import 'services/llm_embedding_service.dart';
+import 'services/llm_service.dart';
 import 'services/vector_store_service.dart';
 import 'theme/app_colors.dart';
 import 'theme/koshika_design_system.dart';
 
 /// Global references — initialized in SplashScreen before navigation.
 late ObjectBoxStore objectbox;
 late BiomarkerDictionary biomarkerDictionary;
-late GemmaService gemmaService;
-late EmbeddingService embeddingService;
+late LlmService llmService;
+late LlmEmbeddingService embeddingService;
 late VectorStoreService vectorStoreService;
+Future<void>? _embeddingMigrationTask;
 
-Future<void> main() async {
+/// Whether AI features are enabled. Set by the entry point
+/// (main_full.dart vs main_lite.dart).
+bool kAiEnabled = true;
+
+/// Default entry point — full flavor with AI enabled.
+/// For flavor-specific builds, use main_full.dart or main_lite.dart.
+Future<void> main() async => appMain(aiEnabled: true);
+
+/// Shared app bootstrap — called from entry-point files.
+Future<void> appMain({required bool aiEnabled}) async {
   WidgetsFlutterBinding.ensureInitialized();
-  await FlutterGemma.initialize(maxDownloadRetries: 5);
+  kAiEnabled = aiEnabled;
   runApp(const KoshikaApp());
 }
 
+Future<void> migrateEmbeddingsIfNeeded() {
+  if (!kAiEnabled || !embeddingService.isLoaded) {
+    return Future.value();
+  }
+
+  return _embeddingMigrationTask ??= _runEmbeddingMigration().whenComplete(() {
+    _embeddingMigrationTask = null;
+  });
+}
+
+Future<void> _runEmbeddingMigration() async {
+  try {
+    final allResults = objectbox.biomarkerResultBox.getAll();
+    if (allResults.isEmpty) return;
+
+    final needsMigration = allResults.any(
+      (result) =>
+          result.embedding == null ||
+          result.embedding!.isEmpty ||
+          result.embedding!.length != 384,
+    );
+    if (!needsMigration) return;
+
+    debugPrint(
+      'KoshikaApp: migrating ${allResults.length} embeddings to 384-dim',
+    );
+    await vectorStoreService.rebuildIndex(allResults);
+  } catch (e) {
+    debugPrint('Embedding migration failed (non-fatal): $e');
+  }
+}
+
 class KoshikaApp extends StatelessWidget {
   const KoshikaApp({super.key});
 
@@ -123,19 +164,19 @@ class HomeScreen extends StatefulWidget {
 class _HomeScreenState extends State<HomeScreen> {
   int _currentIndex = 0;
 
+  /// Screens available depends on whether AI is enabled.
+  List<Widget> get _screens => kAiEnabled
+      ? const [
+          DashboardScreen(),
+          ReportsScreen(),
+          ChatScreen(),
+          SettingsScreen(),
+        ]
+      : const [DashboardScreen(), ReportsScreen(), SettingsScreen()];
+
   Widget _buildCurrentScreen() {
-    switch (_currentIndex) {
-      case 0:
-        return const DashboardScreen();
-      case 1:
-        return const ReportsScreen();
-      case 2:
-        return const ChatScreen();
-      case 3:
-        return const SettingsScreen();
-      default:
-        return const DashboardScreen();
-    }
+    if (_currentIndex < _screens.length) return _screens[_currentIndex];
+    return const DashboardScreen();
   }
 
   @override
@@ -175,21 +216,23 @@ class _HomeScreenState extends State<HomeScreen> {
                       label: 'Reports',
                       onTap: () => setState(() => _currentIndex = 1),
                     ),
+                    if (kAiEnabled)
+                      _NavItem(
+                        index: 2,
+                        currentIndex: _currentIndex,
+                        icon: Icons.chat_outlined,
+                        activeIcon: Icons.chat,
+                        label: 'Chat',
+                        onTap: () => setState(() => _currentIndex = 2),
+                      ),
                     _NavItem(
-                      index: 2,
-                      currentIndex: _currentIndex,
-                      icon: Icons.chat_outlined,
-                      activeIcon: Icons.chat,
-                      label: 'Chat',
-                      onTap: () => setState(() => _currentIndex = 2),
-                    ),
-                    _NavItem(
-                      index: 3,
+                      index: kAiEnabled ? 3 : 2,
                       currentIndex: _currentIndex,
                       icon: Icons.settings_outlined,
                       activeIcon: Icons.settings,
                       label: 'Settings',
-                      onTap: () => setState(() => _currentIndex = 3),
+                      onTap: () =>
+                          setState(() => _currentIndex = kAiEnabled ? 3 : 2),
                     ),
                   ],
                 ),

lib/main_full.dart

@@ -0,0 +1,4 @@
+import 'main.dart';
+
+/// Entry point for the full flavor — includes all AI features.
+Future<void> main() async => appMain(aiEnabled: true);

lib/main_lite.dart

@@ -0,0 +1,4 @@
+import 'main.dart';
+
+/// Entry point for the lite flavor — no AI, no model downloads.
+Future<void> main() async => appMain(aiEnabled: false);

lib/models/biomarker_result.dart

@@ -61,8 +61,9 @@ class BiomarkerResult {
   @Index()
   DateTime testDate;
 
-  /// Embedding vector for RAG (stored as float list, used with HNSW later)
+  /// Embedding vector for RAG (384-dim from bge-small-en-v1.5).
   @Property(type: PropertyType.floatVector)
+  @HnswIndex(dimensions: 384)
   List<double>? embedding;
 
   BiomarkerResult({