I am attempting to use the Barcode Detection enterprise API. I have the necessary entitlements and license file. I'm following the sample code online, and whenever I attempt to run the barcode detection using arKitSession.run I get the following error message: ar_barcode_detection_provider_t <0x300d82130>: Failed to run provider with transient error code: 1 It obviously isn't running the barcode detection, even though it's running in an immersive space in mixed mode. Any idea what might be going on?

When using the new RealityKit Manipulation Component on Entities, indirect input will never translate the entity - no matter what settings are applied. Direct manipulation works as expected for both translation and rotation. Is this intended behaviour? This is different from how indirect manipulation works on Model3D. How else can we get translation from this component? visionOS 26 Beta 2 Build from macOS 26 Beta 2 and Xcode 26 Beta 2 Attached is replicable sample code, I have tried this in other projects with the same results. var body: some View { RealityView { content in // Add the initial RealityKit content if let immersiveContentEntity = try? await Entity(named: "MovieFilmReel", in: reelRCPBundle) { ManipulationComponent.configureEntity(immersiveContentEntity, allowedInputTypes: .all, collisionShapes: [ShapeResource.generateBox(width: 0.2, height: 0.2, depth: 0.2)]) immersiveContentEntity.position.y = 1 immersiveContentEntity.position.z = -0.5 var mc = ManipulationComponent() mc.releaseBehavior = .stay immersiveContentEntity.components.set(mc) content.add(immersiveContentEntity) } } }

I downloaded Xcode 16 and updated my macOS to 15, but I keep getting this error when trying to build the game in simulator or in device [xrsimulator] Exception thrown: The operation couldn’t be completed. (realitytool.RKAssetsCompiler.RKAssetsCompilerError error 3.)

My app for framing and arranging pictures from Photos on visionOS allows users to write the arrangements they create to .reality files using RealityKit entity.write(to:) that they then display to customers on their websites. This works perfectly on visionOS 2, but fails with a fatal protection error on visionOS 26 beta 1 and beta 2 when write(to:) attempts to write to its internal cache: 2025-06-29 14:03:04.688 Failed to write reality file Error Domain=RERealityFileWriterErrorDomain Code=10 "Could not create parent folders for file path /var/mobile/Containers/Data/Application/81E1DDC4-331F-425D-919B-3AB87390479A/Library/Caches/com.GeorgePurvis.Photography.FrameItVision/RealityFileBundleZippingTmp_A049685F-C9B2-479B-890D-CF43D13B60E9/41453BC9-26CB-46C5-ADBE-C0A50253EC27." UserInfo={NSLocalizedDescription=Could not create parent folders for file path /var/mobile/Containers/Data/Application/81E1DDC4-331F-425D-919B-3AB87390479A/Library/Caches/com.GeorgePurvis.Photography.FrameItVision/RealityFileBundleZippingTmp_A049685F-C9B2-479B-890D-CF43D13B60E9/41453BC9-26CB-46C5-ADBE-C0A50253EC27.} Has anyone else encountered this problem? Do you have a workaround? Have you filed a feedback? ChatGPT analysis of the error and my code reports: Why there is no workaround • entity.write(to:) is a black box — you cannot override where it builds its staging bundle • it always tries to create those random folders itself • you cannot supply a parent or working directory to RealityFileWriter • so if the system fails to create that folder, you cannot patch it 👉 This is why you see a fatal error with no recovery. See also feedbacks: FB18494954, FB18036627, FB18063766

Thank you again for pushing the web forward in VisionOS 2, super exciting! The latest WWDC24 video touched on VR experiences for VisionOS2.0 using WebXR, however there was no mention of passthrough AR experiences. Samples such as this one are not supported: https://immersive-web.github.io/webxr-samples/immersive-ar-session.html In Settings > Safari, there is a feature flag for the AR WebXR module, but enabling it did not seem to change anything. Is this the expected behavior at this time? Any developer preview(s) we could try?

Hi community, I have a pair of stereo images, one for each eye. How should I render it on visionOS? I know that for 3D videos, the AVPlayerViewController could display them in fullscreen mode. But I couldn't find any docs relating to 3D stereo images. I guess my question can be brought up in a more general way: Is there any method that we can render different content for each eye? This could also be helpful to someone who only has sight on one eye.

Hello All, I'm desperate to found a solution and I need your help please. I've create a simple cube in Vision OS. I can get it by hand (close my hand on it) and move it pretty where I want. But, I would like to throw it (exemple like a basket ball). Not push it, I want to have it in hand and throw it away of me with a velocity and direction = my hand move (and finger opened to release it). Please put me on the wait to do that. Cheers and thanks Mathis

Hello everyone, I am currently developing an experience for visionOS using RealityKit and I would like to achieve volumetric light effects, such as visible light rays or shafts through fog or dust. I found this GitHub project: https://github.com/robcupisz/LightShafts, which demonstrates the kind of visual style I am aiming for. I would like to know if there is a way to create similar effects using RealityKit on visionOS. So far, I have experimented with DirectionalLight, SpotLight, ImageBasedLight, and custom materials (e.g., additive blending on translucent meshes), but none of these approaches can replicate the volumetric light shaft look shown in the repository above. Questions: Is there a recommended technique or workaround in RealityKit to simulate light shafts or volumetric lighting? Is creating a custom mesh (e.g., cone or volume geometry with gradient alpha and additive blending) the only feasible method? Are there any examples, best practices, or sample projects from Apple or other developers that showcase a similar visual style? Any advice or hints would be greatly appreciated. Thank you in advance!

I'm developing a VisionOS app with bouncing ball physics and struggling to achieve natural bouncing behavior using RealityKit's physics system. Despite following Apple's recommended parameters, the ball loses significant energy on each bounce and doesn't behave like a real basketball, tennis ball, or football would. With identical physics parameters (restitution = 1.0), RealityKit shows significant energy loss. I've had to implement a custom physics system to compensate, but I want to use native RealityKit physics. It's impossible to make it work by applying custom impulses. Ball Physics Setup (Following Apple Forum Recommendations) // From PhysicsManager.swift private func createBallEntityRealityKit() -> Entity { let ballRadius: Float = 0.05 let ballEntity = Entity() ballEntity.name = "bouncingBall" // Mesh and material let mesh = MeshResource.generateSphere(radius: ballRadius) var material = PhysicallyBasedMaterial() material.baseColor = .init(tint: .cyan) material.roughness = .float(0.3) material.metallic = .float(0.8) ballEntity.components.set(ModelComponent(mesh: mesh, materials: [material])) // Physics setup from Apple Developer Forums let physics = PhysicsBodyComponent( massProperties: .init(mass: 0.624), // Seems too heavy for 5cm ball material: PhysicsMaterialResource.generate( staticFriction: 0.8, dynamicFriction: 0.6, restitution: 1.0 // Perfect elasticity, yet still loses energy ), mode: .dynamic ) ballEntity.components.set(physics) ballEntity.components.set(PhysicsMotionComponent()) // Collision setup let collisionShape = ShapeResource.generateSphere(radius: ballRadius) ballEntity.components.set(CollisionComponent(shapes: [collisionShape])) return ballEntity } Ground Plane Physics // From GroundPlaneView.swift let groundPhysics = PhysicsBodyComponent( massProperties: .init(mass: 1000), material: PhysicsMaterialResource.generate( staticFriction: 0.7, dynamicFriction: 0.6, restitution: 1.0 // Perfect bounce ), mode: .static ) entity.components.set(groundPhysics) Wall Physics // From WalledBoxManager.swift let wallPhysics = PhysicsBodyComponent( massProperties: .init(mass: 1000), material: PhysicsMaterialResource.generate( staticFriction: 0.7, dynamicFriction: 0.6, restitution: 0.85 // Slightly less than ground ), mode: .static ) wall.components.set(wallPhysics) Collision Detection // From GroundPlaneView.swift content.subscribe(to: CollisionEvents.Began.self) { event in guard physicsMode == .realityKit else { return } let currentTime = Date().timeIntervalSince1970 guard currentTime - lastCollisionTime > 0.1 else { return } if event.entityA.name == "bouncingBall" || event.entityB.name == "bouncingBall" { let normal = event.collision.normal // Distinguish between wall and ground collisions if abs(normal.y) < 0.3 { // Wall bounce print("Wall collision detected") } else if normal.y > 0.7 { // Ground bounce print("Ground collision detected") } lastCollisionTime = currentTime } } Issues Observed Energy Loss: Despite restitution = 1.0 (perfect elasticity), the ball loses ~20-30% energy per bounce Wall Sliding: Ball tends to slide down walls instead of bouncing naturally No Damping Control: Comments mention damping values but they don't seem to affect the physics Change in mass also doesn't do much. Custom Physics System (Workaround) I've implemented a custom physics system that manually calculates velocities and applies more realistic restitution values: // From BouncingBallComponent.swift struct BouncingBallComponent: Component { var velocity: SIMD3<Float> = .zero var angularVelocity: SIMD3<Float> = .zero var bounceState: BounceState = .idle var lastBounceTime: TimeInterval = 0 var bounceCount: Int = 0 var peakHeight: Float = 0 var totalFallDistance: Float = 0 enum BounceState { case idle case falling case justBounced case bouncing case settled } } Is this energy loss expected behavior in RealityKit, even with perfect restitution (1.0)? Are there additional physics parameters (damping, solver iterations, etc.) that could improve bounce behavior? Would switching to Unity be necessary for more realistic ball physics, or am I missing something in RealityKit? Even in the last video here: https://stepinto.vision/example-code/collisions-physics-physics-material/ bounce of the ball is very unnatural - stops after 3-4 bounces. I apply custom impulses, but then if I have walls around the ball, it's almost impossible to make it look natural. I also saw this post https://developer.apple.com/forums/thread/759422 and ball is still not bouncing naturally.

Hello again! So, I am trying my best to figure out how to get a simple, fully Immersive scene that is navigable via the PS5 controller to work on Vision Pro. I am even using ChatGPT (both externally AND in Xcode when it makes fix recommendations) however, I seem to be moving around in circles, having to constantly send error messages back to ChatGPT, then try the new "confirmed to work" fixed code, only to have more errors. I also have explicitly let the AI know that I'm using all the current betas, only to learn there has been lots of stuff deprecated (of course!). This is my initial query to ChatGPT: "How can I create a fully immersive VR experience for Apple Vision Pro, using a PS5 game controller to navigate the user via first person view through a 3d scene?" And then down the rabbit hole the past few days. Seriously, I thought AI was supposed to be helpful! LOL Per Xcode logs, I'm seeing thumbstick movement, but simply cannot get the camera to move. Is this even possible?! Is it a camera defined in Reality Composer Pro? Or, does it need to be defined outside. I'm trying to follow along with the AI, but it seems to go back and forth with different solutions. Here is the latest it's spitting out: __ Thanks for this super clear log — and you’re absolutely right: the gamepad input is working, CameraRoot is moving as expected… but your actual camera view is not changing. This strongly suggests the issue is that RealityKit is not using your custom camera (PerspectiveCameraComponent) for rendering the view. ⸻ 🔍 What’s happening Even though CameraRoot is moving (with correct logs), RealityKit will default to its own internal camera unless: 1. You explicitly assign your camera entity to be the one used, or 2. Your camera is the only one and RealityKit picks it up automatically. But in visionOS 2.0 / Xcode 26, there seems to be a bug or behavior change where RealityKit no longer auto-uses your custom PerspectiveCameraComponent in RealityView unless it’s: • properly set with content.camera, or • part of a .usda/Reality Composer camera hierarchy that’s already active. Unfortunately: 🟥 RealityView.camera = .entity(cameraRoot) ❌ Is no longer allowed (we confirmed this breaks with a type error) ⸻ ✅ The Reliable Workaround: Attach your camera to the Immersive scene itself Since we’re loading a .usda scene (Reality Composer Pro), here’s the most reliable path forward: ✔️ Option A: Embed your camera into the Reality Composer Pro scene 1. Open your Reality Composer Pro scene 2. Add a Camera entity directly in your Immersive.usda scene 3. Name it something like "PlayerCamera" 4. Position it at [0, 1.6, 0] 5. Leave it selected as the default camera Then in your Swift code: • Find the camera entity with .findEntity(named:) • Move that entity instead of creating a new one. ⸻ ✔️ Option B: Force RealityKit to use your custom camera (via transform parenting) Since direct camera assignment is unavailable, we can use a trick: Move the whole RealityView scene via a parent entity with a camera. But let’s go with Option A, since you’ve already got a Reality Composer Pro scene. __ Can any developer over there can make a suggestion on how to move forward? I JUST want to create a sandbox template so I can start exploring 3d scenes created in Maya and sent over to headset. I'll deal with animation next, but come on, why is this so difficult to get working? I'm not a programmer, but have been trying to wrap my head around Xcode and SwiftUI. This needs to be much simpler. Or, you need to provide us creatives with better sample templates and non programmer speak on how to set this up properly. Ideally, you HIRE us 3d professionals to work side by side with the programmers to help make these tools useable - especially Reality Composer Pro. Seriously, I am making a concerted effort to use the native tools, even though I would love to be porting Unreal Engine scenes over. If anyone can help point me in the right direction, coming from a 3D Creator/Animator/Modeler perspective, I, and my fellow peers in the XR/AR/VR community would greatly appreciate it. Thank you.

Hello, There are three issues I am running into with a default template project + additional minimal code changes: the Sphere_Left entity always overlaps the Sphere_Right entity. when I release the Sphere_Left entity, it does not remain sticking to the Sphere_Right entity when I release the Sphere_Left entity, it distances itself from the Sphere_Right entity When I manipulate the Sphere_Right entity, these above 3 issues do not occur: I get a correct and expected behavior. These issues are simple to replicate: Create a new project in XCode Choose visionOS -> App, then click Next Name your project, and leave all other options as defaults: Initial Scene: Window, Immersive Space Renderer: RealityKit, Immersive Space: Mixed, then click Next Save you project anywhere... Replace the entire ImmersiveView.swift file with the below code. Run. Try to manipulate the left sphere, you should get the same issues I mentioned above If you restart the project, and manipulate only the right sphere, you should get the correct expected behaviors, and no issues. I am running this in macOS 26, XCode 26, on visionOS 26, all released lately. ImmersiveView Code: // // ImmersiveView.swift // import OSLog import SwiftUI import RealityKit import RealityKitContent struct ImmersiveView: View { private let logger = Logger(subsystem: "com.testentitiessticktogether", category: "ImmersiveView") @State var collisionBeganUnfiltered: EventSubscription? var body: some View { RealityView { content in // Add the initial RealityKit content if let immersiveContentEntity = try? await Entity(named: "Immersive", in: realityKitContentBundle) { content.add(immersiveContentEntity) // Add manipulation components setupManipulationComponents(in: immersiveContentEntity) collisionBeganUnfiltered = content.subscribe(to: CollisionEvents.Began.self) { collisionEvent in Task { @MainActor in handleCollision(entityA: collisionEvent.entityA, entityB: collisionEvent.entityB) } } } } } private func setupManipulationComponents(in rootEntity: Entity) { logger.info("\(#function) \(#line) ") let sphereNames = ["Sphere_Left", "Sphere_Right"] for name in sphereNames { guard let sphere = rootEntity.findEntity(named: name) else { logger.error("\(#function) \(#line) Failed to find \(name) entity") assertionFailure("Failed to find \(name) entity") continue } ManipulationComponent.configureEntity(sphere) var manipulationComponent = ManipulationComponent() manipulationComponent.releaseBehavior = .stay sphere.components.set(manipulationComponent) } logger.info("\(#function) \(#line) Successfully set up manipulation components") } private func handleCollision(entityA: Entity, entityB: Entity) { logger.info("\(#function) \(#line) Collision between \(entityA.name) and \(entityB.name)") guard entityA !== entityB else { return } if entityB.isAncestor(of: entityA) { logger.debug("\(#function) \(#line) \(entityA.name) already under \(entityB.name); skipping reparent") return } if entityA.isAncestor(of: entityB) { logger.info("\(#function) \(#line) Skip reparent: \(entityA.name) is an ancestor of \(entityB.name)") return } reparentEntities(child: entityA, parent: entityB) entityA.components[ParticleEmitterComponent.self]?.burst() } private func reparentEntities(child: Entity, parent: Entity) { let childBounds = child.visualBounds(relativeTo: nil) let parentBounds = parent.visualBounds(relativeTo: nil) let maxEntityWidth = max(childBounds.extents.x, parentBounds.extents.x) let childPosition = child.position(relativeTo: nil) let parentPosition = parent.position(relativeTo: nil) let currentDistance = distance(childPosition, parentPosition) child.setParent(parent, preservingWorldTransform: true) logger.info("\(#function) \(#line) Set \(child.name) parent to \(parent.name)") child.components.remove(ManipulationComponent.self) logger.info("\(#function) \(#line) Removed ManipulationComponent from child \(child.name)") if currentDistance > maxEntityWidth { let direction = normalize(childPosition - parentPosition) let newPosition = parentPosition + direction * maxEntityWidth child.setPosition(newPosition - parentPosition, relativeTo: parent) logger.info("\(#function) \(#line) Adjusted position: distance was \(currentDistance), now \(maxEntityWidth)") } } } fileprivate extension Entity { func isAncestor(of other: Entity) -> Bool { var current: Entity? = other.parent while let node = current { if node === self { return true } current = node.parent } return false } } #Preview(immersionStyle: .mixed) { ImmersiveView() .environment(AppModel()) }

I can add a WorldAnchor to a WorldTrackingProvider. The next time I start my app, the WorldAnchor is added back, and then is immediately removed: dataProviderStateChanged(dataProviders: [WorldTrackingProvider(0x0000000300bc8370, state: running)], newState: running, error: nil) AnchorUpdate(event: added, timestamp: 43025.248134708, anchor: WorldAnchor(id: C0A1AE95-F156-45F5-9030-895CAABF16E9, isTracked: true, originFromAnchorTransform: <translation=(0.048458 0.000108 -0.317565) rotation=(0.00° 15.44° -0.00°)>)) AnchorUpdate(event: removed, timestamp: 43025.348131208, anchor: WorldAnchor(id: C0A1AE95-F156-45F5-9030-895CAABF16E9, isTracked: false, originFromAnchorTransform: <translation=(0.000000 0.000000 0.000000) rotation=(-0.00° 0.00° 0.00°)>)) It always leaves me with zero anchors in .allAnchors...the ARKitSession is still active at this point

Starting in visionOS 26, users can snap windows to surfaces. These windows are locked in place and are later restored by visionOS. We can access the snapped data with surfaceSnappingInfo docs. Users can also lock a free-floating (unsnapped) window from a context menu in the window controls. Is there a way to tell when a window has been locked without being snapped to a surface?

I am getting the error "Initializing hosting entity without a context" in the console when I build and run my game in XCode 16.0 beta, targeting Vision Pro OS 2.0 (22N5252n). Not sure where the error is originating.

How do you force quit apps on the Vision Pro simulator? I've read online you can double press the digital crown on a real Vision Pro device but there is no such button on the simulator. So far I've tried Pressing the home button twice (⇧⌘H) Pressing the Siri button twice (⌥⇧⌘H) None of them works I'm on Xcode 15.0 beta 5 (15A5209g) &amp; visionOS 1.0 beta 2 (21N5207e)

Hello Community, I am currently developing an experimental VisionOS app, to investigate the social effects of the new Spatial Persona feature, for my bachelor thesis. My setup includes a simple board game for the participants, in which they can engage with their persona avatars. I tried to use the TabletopKit for this setup, but ran into issues when starting the SharePlay session. When I testes my app, I couldn't see the other spatial persona anymore, despite the green SharePlay button indicating the session started. The other person can see my actions in their version of the app on the board, but can not interact with anything. Also, we are both seat on the default side of the seat. I tried to remove the environment I added, because it doesn't seem to synch with the other player. When I tried the FaceTime feature in the simulator without the environment, I could then see the test robot avatar, but at a totally wrong place. It's seems like it isn't just my environment occluding the seats, but a flaw in the seating process as well. When I tried the FaceTime feature in the simulator on the official test scene (TabletopKit Sample), I got the same incorrect placement and the warning "role(for:inSeatNumber:): The provided role identifier does not match a role in the current template." So my questions are: What needs to be changed so the TabletopKit can handle seating correctly? How can I correctly use immersive scenes in combination with the TabletopKit? I tried to keep the implementation of the TabletopKit example as close as possible, so I think it will enough to look into this codebase for now. I debugged the position of seats and they are placed correctly in front of their equipment. The personas are just not placed on them.

I am working on a project that requires access to the main camera on the Vision Pro. My main account holder applied for the necessary enterprise entitlement and we were approved and received the Enterprise.license file by email. I have added the Enterprise.license file to my project, and manually added the com.apple.developer.arkit.main-camera-access.allow entitlement to the entitlement file and set it to true since it was not available in the list when I tried to use the + Capability button in the Signing & Capabilites tab. I am getting an error: Provisioning profile "iOS Team Provisioning Profile: " doesn't include the com.apple.developer.arkit.main-camera-access.allow entitlement. I have checked the provisioning profile settings online, and there is no manual option for adding the main camera access entitlement, and it does not seem to be getting the approval from the license.

How do we author a Reality File like the ones under Examples with animations at https://developer.apple.com/augmented-reality/quick-look/ ?? For example, "The Hab" : https://developer.apple.com/augmented-reality/quick-look/models/hab/hab_en.reality Tapping on various buttons in this experience triggers various complex animations. I don't see any way to accomplish this in Reality Composer. And I don't see any way to export/compile to a "reality file" from within Xcode. How can I use multiple animations within a single GLTF file? How can I set up multiple "tap target" on a single object, where each one triggers a different action? How do we author something similar? What tools do we use? Thanks

Hi there! I´m trying to make a 360 image carousel in RealityView/SwiftUI with very large textures. I´ve managed to load one 12K 360 image and showing it on a inverted sphere with a ShaderMaterialGraph made in Reality Composer Pro. When I try to load the next image I get an out of memory error. The carousel works fine with smaller textures. My question is. How do I release the memory from the current texture before loading the next? In theory the garbagecollector should erase it eventually? Hope someone can help =) Thanks in advance! Best regards, Kim

My VisionOS App (Travel Immersive) has two interface windows: a main 2D interface window and a 3D Earth window. If the user first closes the main interface window and then the Earth window, clicking the app icon again will only launch the Earth window while failing to display the main interface window. However, if the user closes the Earth window first and then the main interface window, the app restarts normally‌. Below is the code of import SwiftUI @main struct Travel_ImmersiveApp: App { @StateObject private var appModel = AppModel() var body: some Scene { WindowGroup(id: "MainWindow") { ContentView() .environmentObject(appModel) .onDisappear { appModel.closeEarthWindow = true } } .windowStyle(.automatic) .defaultSize(width: 1280, height: 825) WindowGroup(id: "Earth") { if !appModel.closeEarthWindow { Globe3DView() .environmentObject(appModel) .onDisappear { appModel.isGlobeWindowOpen = false } } else { EmptyView() // 关闭时渲染空视图 } } .windowStyle(.volumetric) .defaultSize(width: 0.8, height: 0.8, depth: 0.8, in: .meters) ImmersiveSpace(id: "ImmersiveView") { ImmersiveView() .environmentObject(appModel) } } }