Merge branch 'google-ai-edge:main' into main

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,5 +1,5 @@
 ---
-name: Bug report
+name: 🐛 Bug report
 about: Create a report to help us improve
 title: ''
 labels: ''
@@ -7,16 +7,16 @@ assignees: ''
 
 ---
 
-**Describe the bug**
+**Describe the bug:**    
 A clear and concise description of what the bug is.
 
-**To Reproduce**
+**To Reproduce:**      
 Steps to reproduce the behavior:
 
-**Expected behavior**
+**Expected behavior:**        
 A clear and concise description of what you expected to happen.
 
-**Screenshots**
+**Screenshots:**    
 If applicable, add screenshots to help explain your problem.
 
 **Desktop (please complete the following information):**
@@ -30,5 +30,5 @@ If applicable, add screenshots to help explain your problem.
  - Browser [e.g. stock browser, safari]
  - Version [e.g. 22]
 
-**Additional context**
+**Additional context:**    
 Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -1,5 +1,5 @@
 ---
-name: Feature request
+name: ✨ Feature request
 about: Suggest an idea for this project
 title: ''
 labels: ''

.github/ISSUE_TEMPLATE/support_request.md

@@ -0,0 +1,46 @@
+---
+name: 🆘 Support Request
+about: Ask a question or get help with usage.
+title: "[Support]: "
+labels: ["support", "question"]
+assignees: []
+---
+
+<!--
+Thanks for reaching out for help! To assist you efficiently, please provide as much detail as possible.
+-->
+
+**What do you need help with?**
+
+Is this a question about how to do something, a configuration problem, or a general issue you can't solve?
+
+**Describe the issue/question:**
+
+Clearly describe what you are trying to achieve, what problem you are facing, or what question you have.
+
+**What have you tried so far? (Optional):**
+
+List any steps you've already taken to troubleshoot, find information, or attempt a solution.
+
+**Expected outcome (Optional):**
+
+If applicable, what did you hope would happen, or what solution are you looking for?
+
+**Screenshots/Videos (Optional):**
+
+If applicable, add screenshots or a short video that might help explain your situation.
+
+**Environment & Details:**
+
+Please provide details about your operating environment, relevant URLs, or any messages you see.
+
+- **Operating System:**
+- **Browser & Version (if applicable):**
+- **Any relevant messages (e.g., from UI, console):**
+    ```
+    PASTE_ANY_MESSAGES_HERE
+    ```
+
+**Any additional context?:**
+
+Is there anything else that might be useful for us to know?

Android/src/app/build.gradle.kts

@@ -31,7 +31,7 @@ android {
     minSdk = 26
     targetSdk = 36
     versionCode = 1
-    versionName = "1.0.2"
+    versionName = "1.0.3"
 
     // Needed for HuggingFace auth workflows.
     manifestPlaceholders["appAuthRedirectScheme"] = "com.google.ai.edge.gallery.oauth"

Android/src/app/src/main/java/com/google/ai/edge/gallery/ui/common/chat/MessageInputText.kt

@@ -23,6 +23,8 @@ import android.graphics.Bitmap
 import android.graphics.BitmapFactory
 import android.graphics.Matrix
 import android.net.Uri
+import android.util.Log
+import android.util.Size
 import androidx.activity.compose.rememberLauncherForActivityResult
 import androidx.activity.result.PickVisualMediaRequest
 import androidx.activity.result.contract.ActivityResultContracts
@@ -31,6 +33,9 @@ import androidx.camera.core.CameraControl
 import androidx.camera.core.CameraSelector
 import androidx.camera.core.ImageCapture
 import androidx.camera.core.ImageProxy
+import androidx.camera.core.resolutionselector.AspectRatioStrategy
+import androidx.camera.core.resolutionselector.ResolutionSelector
+import androidx.camera.core.resolutionselector.ResolutionStrategy
 import androidx.camera.lifecycle.ProcessCameraProvider
 import androidx.camera.lifecycle.awaitInstance
 import androidx.camera.view.PreviewView
@@ -75,9 +80,11 @@ import androidx.compose.material3.TextField
 import androidx.compose.material3.TextFieldDefaults
 import androidx.compose.material3.rememberModalBottomSheetState
 import androidx.compose.runtime.Composable
+import androidx.compose.runtime.DisposableEffect
 import androidx.compose.runtime.LaunchedEffect
 import androidx.compose.runtime.collectAsState
 import androidx.compose.runtime.getValue
+import androidx.compose.runtime.mutableIntStateOf
 import androidx.compose.runtime.mutableStateOf
 import androidx.compose.runtime.remember
 import androidx.compose.runtime.rememberCoroutineScope
@@ -104,6 +111,8 @@ import com.google.ai.edge.gallery.ui.theme.GalleryTheme
 import kotlinx.coroutines.launch
 import java.util.concurrent.Executors
 
+private const val TAG = "AGMessageInputText"
+
 /**
  * Composable function to display a text input field for composing chat messages.
  *
@@ -135,7 +144,7 @@ fun MessageInputText(
   var showAddContentMenu by remember { mutableStateOf(false) }
   var showTextInputHistorySheet by remember { mutableStateOf(false) }
   var showCameraCaptureBottomSheet by remember { mutableStateOf(false) }
-  var cameraCaptureSheetState = rememberModalBottomSheetState(skipPartiallyExpanded = true)
+  val cameraCaptureSheetState = rememberModalBottomSheetState(skipPartiallyExpanded = true)
   var tempPhotoUri by remember { mutableStateOf(value = Uri.EMPTY) }
   var pickedImages by remember { mutableStateOf<List<Bitmap>>(listOf()) }
   val updatePickedImages: (Bitmap) -> Unit = { bitmap ->
@@ -150,21 +159,6 @@ fun MessageInputText(
     checkFrontCamera(context = context, callback = { hasFrontCamera = it })
   }
 
-  // launches camera
-  val cameraLauncher =
-    rememberLauncherForActivityResult(ActivityResultContracts.TakePicture()) { isImageSaved ->
-      if (isImageSaved) {
-        handleImageSelected(
-          context = context,
-          uri = tempPhotoUri,
-          onImageSelected = { bitmap ->
-            updatePickedImages(bitmap)
-          },
-          rotateForPortrait = true,
-        )
-      }
-    }
-
   // Permission request when taking picture.
   val takePicturePermissionLauncher = rememberLauncherForActivityResult(
     ActivityResultContracts.RequestPermission()
@@ -173,7 +167,6 @@ fun MessageInputText(
       showAddContentMenu = false
       tempPhotoUri = context.createTempPictureUri()
       showCameraCaptureBottomSheet = true
-//      cameraLauncher.launch(tempPhotoUri)
     }
   }
 
@@ -270,7 +263,6 @@ fun MessageInputText(
                   showAddContentMenu = false
                   tempPhotoUri = context.createTempPictureUri()
                   showCameraCaptureBottomSheet = true
-//                  cameraLauncher.launch(tempPhotoUri)
                 }
 
                 // Otherwise, ask for permission
@@ -416,20 +408,32 @@ fun MessageInputText(
 
       val lifecycleOwner = LocalLifecycleOwner.current
       val previewUseCase = remember { androidx.camera.core.Preview.Builder().build() }
-      val imageCaptureUseCase = remember { ImageCapture.Builder().build() }
+      val imageCaptureUseCase = remember {
+        // Try to limit the image size.
+        val preferredSize = Size(512, 512)
+        val resolutionStrategy = ResolutionStrategy(
+          preferredSize,
+          ResolutionStrategy.FALLBACK_RULE_CLOSEST_HIGHER_THEN_LOWER
+        )
+        val resolutionSelector = ResolutionSelector.Builder()
+          .setResolutionStrategy(resolutionStrategy)
+          .setAspectRatioStrategy(AspectRatioStrategy.RATIO_4_3_FALLBACK_AUTO_STRATEGY)
+          .build()
+
+        ImageCapture.Builder().setResolutionSelector(resolutionSelector).build()
+      }
       var cameraProvider by remember { mutableStateOf<ProcessCameraProvider?>(null) }
       var cameraControl by remember { mutableStateOf<CameraControl?>(null) }
       val localContext = LocalContext.current
-      var cameraSide by remember { mutableStateOf(CameraSelector.LENS_FACING_BACK) }
+      var cameraSide by remember { mutableIntStateOf(CameraSelector.LENS_FACING_BACK) }
-
       val executor = remember { Executors.newSingleThreadExecutor() }
-      val capturedImageUri = remember { mutableStateOf<Uri?>(null) }
 
       fun rebindCameraProvider() {
         cameraProvider?.let { cameraProvider ->
           val cameraSelector = CameraSelector.Builder()
             .requireLensFacing(cameraSide)
             .build()
+          try {
             cameraProvider.unbindAll()
             val camera = cameraProvider.bindToLifecycle(
               lifecycleOwner = lifecycleOwner,
@@ -438,6 +442,9 @@ fun MessageInputText(
               imageCaptureUseCase
             )
             cameraControl = camera.cameraControl
+          } catch (e: Exception) {
+            Log.d(TAG, "Failed to bind camera", e)
+          }
         }
       }
 
@@ -450,31 +457,25 @@ fun MessageInputText(
         rebindCameraProvider()
       }
 
-//      val cameraController = remember {
+      DisposableEffect(Unit) { // Or key on lifecycleOwner if it makes more sense
-//        LifecycleCameraController(context).apply {
+        onDispose {
-//          bindToLifecycle(lifecycleOwner)
+          cameraProvider?.unbindAll() // Unbind all use cases from the camera provider
-//        }
+          if (!executor.isShutdown) {
-//      }
+            executor.shutdown()     // Shut down the executor service
+          }
+        }
+      }
 
       Box(modifier = Modifier.fillMaxSize()) {
         // PreviewView for the camera feed.
         AndroidView(
           modifier = Modifier.fillMaxSize(),
           factory = { ctx ->
-            PreviewView(context).also {
+            PreviewView(ctx).also {
               previewUseCase.surfaceProvider = it.surfaceProvider
               rebindCameraProvider()
             }
-//            PreviewView(ctx).apply {
-//              scaleType = PreviewView.ScaleType.FILL_START
-//              implementationMode = PreviewView.ImplementationMode.COMPATIBLE
-//              controller = cameraController // Attach the lifecycle-aware camera controller.
-//            }
           },
-//          onRelease = {
-//            // Called when the PreviewView is removed from the composable hierarchy
-//            cameraController.unbind() // Unbinds the camera to free up resources
-//          }
         )
 
         // Close button.
@@ -508,25 +509,31 @@ fun MessageInputText(
             .size(64.dp)
             .border(2.dp, MaterialTheme.colorScheme.onPrimary, CircleShape),
           onClick = {
-            scope.launch {
             val callback = object : ImageCapture.OnImageCapturedCallback() {
               override fun onCaptureSuccess(image: ImageProxy) {
+                try {
                   var bitmap = image.toBitmap()
                   val rotation = image.imageInfo.rotationDegrees
                   bitmap = if (rotation != 0) {
                     val matrix = Matrix().apply {
                       postRotate(rotation.toFloat())
                     }
+                    Log.d(TAG, "image size: ${bitmap.width}, ${bitmap.height}")
                     Bitmap.createBitmap(bitmap, 0, 0, bitmap.width, bitmap.height, matrix, true)
                   } else bitmap
                   updatePickedImages(bitmap)
+                } catch (e: Exception) {
+                  Log.e(TAG, "Failed to process image", e)
+                } finally {
                   image.close()
-                }
+                  scope.launch {
-              }
-              imageCaptureUseCase.takePicture(executor, callback)
                     cameraCaptureSheetState.hide()
                     showCameraCaptureBottomSheet = false
                   }
+                }
+              }
+            }
+            imageCaptureUseCase.takePicture(executor, callback)
           },
         ) {
           Icon(
@@ -601,7 +608,7 @@ private fun rotateImageIfNecessary(bitmap: Bitmap, rotateForPortrait: Boolean =
 
 private fun checkFrontCamera(context: Context, callback: (Boolean) -> Unit) {
   val cameraProviderFuture = ProcessCameraProvider.getInstance(context)
-  cameraProviderFuture.addListener(Runnable {
+  cameraProviderFuture.addListener({
     val cameraProvider = cameraProviderFuture.get()
     try {
       // Attempt to select the default front camera