Subject: Call Directory Extension Enable Failure for Individual User Dear Apple Developer Support, We are experiencing an issue with our Call Directory Extension where one specific user cannot enable it, while thousands of other users on the same iOS version can enable it successfully. Issue Details: App: 美信 (Midea Connect) Problem: Extension fails to enable with error: "请求'美信'的数据时失败" (Failed to request data from app) Affected: 1 user out of thousands iOS Version: 26.0.1 What Works: All other users can enable the extension normally Same iOS version, no issues App Group and Extension identifier are correctly configured User Has Tried: Reinstall app - No effect Toggle extension off/on - Still fails Restart device - No improvement

Certainly! Here's a concise version of your forum post: Title: Issues Handling Multiple Incoming Calls in CallKit Body: Hello, I'm using CallKit and I am encountering challenges with handling multiple incoming calls. Current Configuration: configuration.maximumCallsPerCallGroup = 5 configuration.maximumCallGroups = 3 This setup aims to allow up to 5 calls per group. Observed Behavior: Despite the configuration, the system UI seems to limit the number of calls per group, often defaulting to "End & Accept" instead of "Hold & Accept" when a third call comes in. Questions: Is there a documented system-imposed limit on the number of calls per group or total calls, even if maximumCallGroups and maximumCallsPerCallGroup are set higher? How does the system UI behave when these limits are exceeded? Are there known UI constraints or fallback behaviors? Are there best practices for handling scenarios where the system UI cannot display all calls, such as gracefully managing incoming calls or providing alternative UI solutions? Any insights or experiences with similar configurations would be greatly appreciated. Thank you. Feel free to copy and paste this directly into the Apple Developer Forums. If you need further assistance or adjustments, let me know!

According to the App Store Server API documentation , https://developer.apple.com/documentation/appstoreserverapi/price the price field "shows the total amount of the transaction for the quantity the customer purchased." However, in actual transaction notifications and responses from App Store Server API, the price field appears to represent the unit price, not the total price. For consumable in-app purchases with quantity > 1, the price field equals the unit price of a single item. The total user payment is only correct after multiplying by the quantity. When quantity > 1, the actual amount paid by the user only matches price × quantity, which contradicts the documentation. Please confirm whether the price field is intended to be: The unit price of a single item (requiring multiplication by quantity), or The total price including all quantities (as currently documented). If the former is correct, please update the documentation to clarify that the value represents the unit price, not the total amount.

TCC Permission Inheritance for Python Process Launched by Swift App in Enterprise Deployment We are developing an enterprise monitoring application that requires a hybrid Swift + Python architecture due to strict JAMF deployment restrictions. We must deploy a macOS application via ABM/App Store Connect, but our core monitoring logic is in a Python daemon. We need to understand the feasibility and best practices for TCC permission inheritance in this specific setup. Architecture Component Bundle ID Role Deployment Swift Launcher com.athena.AthenaSentry Requests TCC permissions, launches Python child process. Deployed via ABM/ASC. Python Daemon com.athena.AthenaSentry.Helper Core monitoring logic using sensitive APIs. Nested in Contents/Helpers/. Both bundles are signed with the same Developer ID and share the same Team ID. Required Permissions The Python daemon needs to access the following sensitive TCC-controlled services: Screen Recording (kTCCServiceScreenCapture) - for capturing screenshots. Input Monitoring (kTCCServiceListenEvent) - for keystroke/mouse monitoring. Accessibility (kTCCServiceAccessibility) - a prerequisite for Input Monitoring. Attempts & Workarounds We have attempted to resolve this using: Entitlement Inheritance: Added com.apple.security.inherit to the Helper's entitlements. Permission Proxy: Swift app maintains active event taps to try and "hold" the permissions for the child. Foreground Flow: Keeping the Swift app in the foreground during permission requests. Questions Is this architecture supported? Can a Swift parent app successfully request TCC permissions that a child process can then use? TCC Inheritance: What are the specific rules for TCC permission inheritance between parent/child processes in enterprise environment? What's the correct approach for this enterprise use case? Should we: Switch to a Single Swift App? (i.e., abandon the Python daemon and rewrite the core logic natively in Swift). Use XPC Services? (instead of launching the child process directly).

On iOS 18 and lower version, my application supports automatically switching to [System settings - Personal Hotspot] directly. But on iOS 26, my application will be redirected to [System settings- Apps]. Does iOS 26 disable the behavior of directly jumping to the system hotspot page? If support, could you share the API for iOS 26?

My iPhone VoIP app, which I'm developing, uses Apple Push Notification service (APNs). I have a question regarding the following statement found in "[Overview of app transfer > Apps using push notifications]" Overview of app transfer You must manually reestablish push notification services if transferring an app that uses the Apple Push Notifications service (APNs). The recipient must create a new client SSL certificate using their developer account, as associated client SSL certificates, TLS certificates, and authentication tokens aren’t transferred. Question Let's say the recipient of the app transfer creates a "new SSL certificates, TLS certificates, and authentication tokens." Afterward, we need to verify that the Apple Push Notification service (APNs) works correctly when combining the transferred app with this "new SSL certificates, TLS certificates, and authentication tokens." However, until the recipient finishes verifying that it works correctly, the transferor want to keep the app available for download as before and be able to use the Apple Push Notification service. Is this possible? More specifically, can the recipient test the app to be transferred on TestFlight "before the transfer is completed"? I want to combine it with the "new SSL certificates, TLS certificates, and authentication tokens." and test it on TestFlight. Reading "[Initiate an app transfer]," it mentions the existence of a "Pending App Transfer" status. During this "Pending App Transfer" status, can the recipient test the app on TestFlight? Initiate an app transfer After you initiate the transfer, the app stays in its previous status, with the Pending App Transfer status added, until the recipient accepts it or the transfer expires after 60 days. Also, if there are any documents describing these procedures, I would appreciate it if you could share them. Thank you very much.

Are the Wifi-Aware's WAEndpoint's discovered ephemeral? I'm trying to understand what's the best way to reconnect a disconnected WifiAware connection - Can I just cache the endpoint and start a new connection with the same endpoint or do I need to browse again and get a new WAEndpoint? My use case requires both WifiAware connection to another device and the devices also need to be connected to infrastructure wifi most of the time. I'm concerned about the WifiAware's connection having any impact on infrastructure wifi. What is the impact on the infrastructure wifi here in comparison to using the Apple peer to peer wifi(That Multipeer framework or Network framework use)?

On macOS 26, I've run into a situation when a user “customizes” a folder icon with Finder by assigning/changing an SF Symbol or an emoji, QLThumbnailGenerator keeps returning the stale initially retrieved folder icon (no matter whether it had been customized or not) until my app quits. After the app is re-launched, the icon is correctly retrieved once again. let generator = QLThumbnailGenerator.shared let size: CGSize = CGSize(width: 64, height: 64) let request = QLThumbnailGenerator.Request(fileAt: url, size: size, scale: NSScreen.main!.backingScaleFactor, representationTypes: .icon) request.iconMode = true do { let thumb = try await generator.generateBestRepresentation(for: request) thumb.nsImage.size = size return thumb.nsImage } catch { print("generateThumbnail: \(error)") return nil } It seems like the QuickLook Thumbnailing cache does not invalidate automatically upon folder customization. Is there any way to manually invalidate the QuickLook Thumbnailing cache?

I a using the current RC version of iOS on both my iPhone and iPad. I and developing an iCloud based app and it works correctly on iOS 18. When I upgraded to iOS 26 the iCloud functions work correctly but the push notifications do not work. The issue appears to be creating subscriptions. The following code should create a subscription and does not get an error, but it did to create a subscription under iOS 26. func subscribeToNotifications(recordType: String, subscriptionID: String, notification: CKSubscription.NotificationInfo) { let subscriptionIDForType = "\(subscriptionID)-\(recordType)" let predicate = NSPredicate(value: true) let subscription = CKQuerySubscription(recordType: recordType, predicate: predicate, subscriptionID: subscriptionIDForType, options: [.firesOnRecordCreation, .firesOnRecordUpdate, .firesOnRecordDeletion]) let notification = CKSubscription.NotificationInfo() subscription.notificationInfo = notification CKContainer.default().publicCloudDatabase.save(subscription) { (returnedSubscription, error) in if let error = error { print("Error saving subscription: \(error)") } else { print("Successfully saved subscription: recordType: " + recordType + " subscriptionID: " + subscriptionIDForType) } } } Print results: Successfully saved subscription: recordType: folder subscriptionID: folderName-folder

I have an swift command line tool that changes proxy settings in system preferences via SystemConfiguration framework, does some stuff, and in the end reverts proxy settings back to original. Here is simplified code: var authorization: AuthorizationRef? let status = AuthorizationCreate(nil, nil, [], &authorization) let prefs = SCPreferencesCreateWithAuthorization(nil, "myapp" as CFString, nil, authorization) // change proxy setttings // do some stuff let prefs2 = SCPreferencesCreateWithAuthorization(nil, "myapp" as CFString, nil, authorization) // change proxy settings back to original When I try to change settings for the first time, the system dialog appears requesting permission to change network settings. If I try to change settings again within а short period of time, the dialog does not appear again. However, if it takes more than several minutes after first change, the dialog does appear again. Is there a way to create authorization, so that the dialog appears only once per app launch, no matter how much time passed since the first dialog?

We are trying to figure out a strange issue. Our app has not changed for at least 10 months but my devices and the QA tester device have all stopped receiving push/call notifications for twilio voip The twilio credential and apple voip services certificate are in date and valid It is pointing to the correct bundle id and topic (not changed configuration for years) token passed in to TwilioVoiceSDK.register() is retrieved from PKPushRegistry as per guide Running locally the Twilio Voice SDK successfully registers and retrieves APNs token What is interesting is if I log in with exactly the same client account on an iOS 18.5 device (and an older iPad) call notifications work perfectly (I have made sure all focus modes/dnd are off and notification settings are identical) The only changes myself and QA have made recently is minor iOS 18 version updates - 18.6.2 and 18.7.1 These now receive Invalid device token from APNs when Twilio attempts to create a call/voip notification for the user identity Our devices sometimes switch environments test/prod so I installed the app cleanly on a borrowed 18.6.2 device and got the exact same issue We have tested on these devices most of the year with no issues. I have been in touch with twilio support and added code to explicitly unregister and re register on an affected device to clear any bindings but it didn't help. Have apple made any changes in PushKit or token behaviour for later versions of iOS 18? Thanks

Hi, I have been recently debugging the BGContinuedProcessingTask API and encountered some of the following issues. I hope you can provide some answers: First, let me explain my understanding of this API. I believe its purpose is to allow an app to trigger tasks that can be represented with progress indicators and require a certain amount of time to complete. After entering the background, these tasks can continue to be completed through the BGContinuedProcessingTask, preventing the system from terminating them before they are finished. In the launchHandler of the registration process, we only need to do a few things: Determine whether the actual business processing is still ongoing. Update the progress, title, and subtitle. Handle the expirationHandler. Set the task as completed. Here are some issues I encountered during my debugging process: After I called register and submit, the BGContinuedProcessingTask could not be triggered. The return values from my API calls were all normal. I tried different device models, and some could trigger the task normally, such as the 15 Pro Max and 12 Pro Max. However, there were also some models, such as the 17 Pro, 15 Pro, and 15, that could not trigger the task properly. Moreover, there was no additional error information to help locate the issue. The background task failed unexpectedly, but my app was still running normally. As I mentioned above, my launchHandler only retrieves the actual business status and updates it. If a background task fails unexpectedly while the app is still running normally, it can mislead users and degrade the user experience of the app. Others have also mentioned the issue of inconsistent behavior on devices that do not support Dynamic Island. On devices that support Dynamic Island, when a task is triggered in the foreground, the app does not immediately display a pop-up notification within the app. However, on devices that do not support Dynamic Island, the app directly displays a pop-up notification within the app, and this notification does not disappear when switching between different screens within the same app. The user needs to actively swipe up to dismiss it. I think this experience is too intrusive for users. I would like to know whether this will be maintained in the future or if there is a plan to fix it. On devices that do not support Dynamic Island, using the beta version 26.1 of the system, if the system is in dark mode but the app triggers a business interface in white, the pop-up notification will have the same color as the current page, making it difficult to read the content inside the pop-up. Users can actively stop background tasks by using the stop button, or the system can also stop tasks automatically when resources are insufficient or when a task is abnormal. However, according to the current API, all these actions are triggered through the expirationHandler. Currently, there is no way to distinguish whether the task was stopped by the user, by the system due to resource insufficiency, or due to an abnormal task. I would like to know whether there will be more information provided in the future to help distinguish these different scenarios. I believe that the user experience issues mentioned in points 2 and 3 are the most important. Please help to answer the questions and concerns above. Thank you!

Hi Guys, I've been wanting to make a bettermouse-like tool for some time now, but I can't figure out how to modify mouse events to do it. I've managed to get mouse events, like the cursor moving, but I can't seem to modify them. What I try either creates a feedback loop, does absolutely nothing, or makes the cursor have a seizure. Any help is appreciated!

Hello all, I am new to implementing payments in an app, and thus completely at sea here. I have created a small app that I have set a one-time (non-consumable) payment for a premium version. In the Xcode simulator (on all platforms) and on any physical test devices I have tried, the payment works as expected. I have a sandbox account and various test accounts, both dummy and actual real accounts (friends and family). Everywhere everything works perfectly fine. Yet, when I submit for review I get a rejection with this contents: We found that your in-app purchase products exhibited one or more bugs which create a poor user experience. Specifically, the app still failed to load the in-app purchase. Please review the details and resources below and complete the next steps. Review device details: Device type: iPad Air (5th generation) OS version: iPadOS 18.6 Next Steps When validating receipts on your server, your server needs to be able to handle a production-signed app getting its receipts from Apple’s test environment. The recommended approach is for your production server to always validate receipts against the production App Store first. If validation fails with the error code "Sandbox receipt used in production," you should validate against the test environment instead. Additionally, note that the Account Holder must accept the Paid Apps Agreement in the Business section of App Store Connect before paid in-app purchases will function. Resources Learn how to set up and test in-app purchase products in >the sandbox environment. Learn more about validating receipts with the App Store. Steps I have done: I have signed all agreements and all bank account details are in order. Everything in the In-app-purchases section of the AppStoreConnect in an Active state. I have triple checked that the configuration of the in-app purchases is correct (product IDs, amounts, etc.) I have created test accounts and tested in sandbox What I don't understand from the reviewer's response is what receipts validation are they talking about? I have no payment servers (the whole concept of using Apple's in-app-purchases service is to not have to deal with my own payment implementation). The StoreKit documentation specifically reads: For each transaction that represents a current purchase, your app delivers the purchased products. To validate purchases, you can verify transactions on your server, or rely on StoreKit’s verification. So now I am confused. The reviewer's response is so vague, and so completely deprived of details that I have no idea what to do... Does the problem concern the product purchase trigger and the that in production environment it does not trigger? Is it that I haven't implemented a receipt validation? Do I need to? Although the documentation mentions that it can be done by StoreKit, I couldn't find anything concerning how to do it :( Can someone give me a hand please? Cheers, Alex

Since integrating MapKit JS, we’ve begun receiving production error reports with the following message: Uncaught DataCloneError: Failed to execute 'postMessage' on 'DedicatedWorkerGlobalScope': ArrayBuffer is not detachable and could not be cloned. It appears that MapKit JS’s internal worker occasionally calls postMessage() with an ArrayBuffer that cannot be detached under Chrome 120+. This causes the structured clone to fail and the error surfaces uncaught from within the worker. MapKit JS Version: 5.79.109 Browser: Chrome 120.0+ OS: Windows 10 Is this a known issue with MapKit JS? If so, are there recommended workarounds or planned fixes?

Hello, We use the Network API in our macOS ObjectiveC applications to create a small web server. With macOS Sequoia or Tahoe (not with Sonoma), downloading files from another computer using the built-in ethernet port is way too slow. Steps to reproduce: Computer A (using macOS Tahoe or Sonoma), run an application using the Network APIs to create a webserver Make sure that this computer connects to the network using the Ethernet port, there is no issue when using WiFi On computer B, make an HTTP request to download a 20MB file => it will take about 30 seconds to download => way too slow... We tested with: if on computer A you run a web server using the GCD API instead of Network, it takes 0.2 seconds to download the file => no issue on computer A disable TSO, it improves the results, but that's not a long term solution as it doesn't hold when rebooting I can provide sample code to demonstrate this if needed. This is a new issue as it's been a while we use that code, and only noticed it recently, and macOS Sonoma is not impacted. Thank you for the help you can provide. Pierre

Hi all, I work on a smart product that, for setup, uses a captive portal to allow users to connect and configure the device. It emits a WiFi network and runs a captive portal - an HTTP server operates at 10.0.0.1, and a DNS server responds to all requests with 10.0.0.1 to direct "any and all" request to the server. When iOS devices connect, they send a request to captive.apple.com/hotspot-detect.html; if it returns success, that means they're on the internet; if not, the typical behavior in the past has been to assume you're connected to a captive portal and display what's being served. I serve any requests to /hotspot-detect.html with my captive portal page (index.html). This has worked reliably on iOS18 for a long time (user selects my products WiFi network, iOS detects portal and opens it). But almost everyone who's now trying with iOS26 is having the "automatic pop up" behavior fail - usually it says "Error opening page - Hotspot login cannot open the page because the network connection was lost." However, if opening safari and navigating to any URL (or 10.0.0.1) the portal loads - it's just the iOS auto-detect and open that's not working iOS18 always succeeds; iOS26 always fails. Anybody have any idea what changes may have been introduced in iOS26 on this front, or anything I can do to help prompt or coax iOS26 into loading the portal? It typically starts reading, but then stops mid-read.

Our app is unable to write to its own sandbox container on macOS when run via “My Mac (Designed for iPad)”. This is not an issue when the app runs on iPhone or on iPad. This seems to affect all attempts to write to the file system including: UserDefaults Core Data (SQLite) Firebase (Analytics, Crashlytics, Sessions) File creation (PDFs, temp files, etc.) We're seeing the following errors in the console: Operation not permitted / NSCocoaErrorDomain Code=513: Permissions error when writing to disk. CFPrefsPlistSource: Path not accessible: Failure to write to UserDefaults. Cannot synchronize user defaults to disk: UserDefaults write blocked. CoreData: No permissions to create file: Core Data SQLite store can't be created. Firebase: Failed to open database: Firebase can't initialize local storage. CGDataConsumerCreateWithFilename: failed to open ... for writing: PDF generation fails due to temp directory access issues. Created a test project to try and reproduce the issue but unable to do so in the test project, even when setting all the build settings the same as the project having issues.

I want to turn off this effect and maintain the style before iOS18. Do I need to add content about iOS26 to the info.plist? Specifically, which content is it? I want to turn off the glass effect on the button

Hi, I’ve built an app that includes a Contacts Provider Extension (CPE). On iOS 18, I observed the expected behavior — when the main app is uninstalled, the corresponding CPE entry is also removed from the Contacts list. However, on iOS 26, this no longer happens. After uninstalling the app, the CPE remains visible and active in the Contacts list, even though the app is gone.