Is anyone else finding model switching a bit disruptive during longer coding sessions? As we start using different models for exploration, implementation and review, having to go through settings interrupts the workflow. I would love to see model and reasoning controls directly inside the Coding Assistant UI.

Are there specific Entitlements (com.apple.security.temporary-exception.files.absolute-path.read-write or network exceptions) required to allow App Intents to talk to local UNIX sockets or loopback interfaces (127.0.0.1) without triggering sandbox violations?

My app uses ImageCreator to allow customers to generate images on-device, and provides a custom experience for doing so. I can see that ImageCreator is now being deprecated without a replacement for programatic image generation. Why has the ability to generate images programatically been removed?

I am a paid apple developer that has been on the AI waitlist since day one of the keynote. How many other paid developers are still waiting like me?

Apple Mail compose field becomes uneditable after using Apple Intelligence rewriting tools on macOS 27 Developer Beta 1 I am seeing a reproducible issue in Apple Mail on macOS 27 Developer Beta 1 where the compose body becomes locked/uneditable after using Apple Intelligence writing tools. Environment Mac: macOS: macOS 27.0 Developer Beta 1 Build: 26A5353q Device: MacBook Pro with Apple Silicon shouldSwitchToCampoMode: false (isEnhancedSiriAvailable=false) App: Apple Mail Compose window Apple Intelligence Writing Tools Summary When composing an email in Apple Mail, if I write some text and then use Apple Intelligence to rewrite it — for example using Friendly, Professional, or Concise — Mail replaces the original text with the rewritten version. After the rewritten text is inserted, the message body becomes unresponsive. I cannot continue typing, edit the rewritten text, delete text, select text normally, or add new content inside the email body. The Apple Intelligence button also becomes unresponsive after this happens. The only actions that still seem to work are sending the email, discarding the draft, or using some toolbar actions such as emoji insertion. Steps to Reproduce Open Apple Mail on macOS 27 Developer Beta 1. Create a new email. Type any text into the email body. Use Apple Intelligence Writing Tools. Choose a rewrite option such as: Friendly Professional Concise Let Apple Intelligence replace/update the email body text. Try to click back into the message body and continue typing or editing. Expected Result After Apple Intelligence rewrites the email body, the compose field should remain fully editable. The user should be able to: Continue typing after the rewritten text Edit or delete the rewritten text Select and modify text Use Apple Intelligence again on the updated content Continue composing the email normally Actual Result After Apple Intelligence inserts the rewritten text: The email body becomes uneditable. Typing no longer works inside the message body. Clicking inside the body does not restore normal editing. Existing text cannot be edited or changed. Apple Intelligence controls become unresponsive. The compose window itself does not fully crash, but the body editor appears stuck. Send and discard still appear to work. Reproducibility This appears to be reproducible after using Apple Intelligence rewriting tools inside Apple Mail’s compose window. It was working before, so this appears to be a regression in macOS 27 Developer Beta 1.

I'm trying to understand the intended relationship between OpenIntent and the new .system.open App Intent schema introduced in iOS 27. From the documentation: OpenIntent (available since iOS 16) is described as an intent that opens an associated item. iOS 27 introduces the .system.open schema, which also appears to represent opening an entity or piece of app content. My questions are: For an app that supports iOS 27+, is .system.open intended to replace OpenIntent, or do the two serve different purposes? For apps that support both iOS 26 and iOS 27+, is the recommended approach to have two structs that implement the same opening logic, one with @AppIntent(schema: .system.open) and the other implementing the OpenIntent protocol? Thanks! References: open protocol OpenIntent

The documented template for @AppEntity(schema: .messages.message) at Integrating your messaging app with Apple Intelligence and on the MessagesEntity.message reference page shows: var reaction: <#ReadReaction#>? with <#ReadReaction#> rendered as a placeholder (the Xcode placeholder syntax). A natural reading is "fill in your own type that you want to use here". I tried several: Tapback? where Tapback is @AppEnum(schema: .messages.customReaction) MessageReaction? (same, renamed) MessageReaction? with manual AppEnum conformance (no schema decoration) AttributedString? AttributedString (non-optional) field omitted entirely Each variant produced one of: error: Property 'reaction' type does not match required AppSchemaEntity property type 'ReadReactionCases:(Schema<Tapback> | AttributedString)' error: Required AppSchemaEntity property 'reaction' must be optional error: Missing required property 'reaction' from AppSchemaEntity 'messages.message' The phrase ReadReactionCases:(Schema<Tapback> | AttributedString) is opaque — ReadReactionCases isn't a public type, Schema<Tapback> isn't constructable from outside, and the documentation doesn't mention @UnionValue in this context. The actual working pattern, which I only found by downloading the UnicornChat sample and reading MessageEntity.swift, is: @UnionValue enum MessageReaction: Sendable { case customReaction(CustomReaction) } @AppEnum(schema: .messages.customReaction) enum CustomReaction: String, AppEnum { case sticker static let caseDisplayRepresentations: [Self: DisplayRepresentation] = [ .sticker: "Sticker" ] } Two suggestions: Update the schema-template comment in the docs to either name MessageReaction explicitly with a @UnionValue annotation, or include a one-line note: "The reaction field is a @UnionValue enum wrapping the customReaction schema enum — see UnicornChat sample." The current placeholder <#ReadReaction#> plus the prose suggesting "you can generate the properties... with the @AppEntity(.messages.message) Swift macro" reads as if the developer just supplies any AppEnum-conformer. Improve the diagnostic. Property type does not match required AppSchemaEntity property type 'ReadReactionCases:(Schema<Tapback> | AttributedString)' is unhelpful because ReadReactionCases doesn't appear in any reachable type. Either rename to something developer-facing, or include a fix-it that suggests @UnionValue. iOS 27.0 beta, Xcode 27 beta, macOS Tahoe 26.4.

Our app already has a huge set of App Intents and Entities. Conceptually, our entities and intents matches well to the existing schemas (like the Notes schema). But because we have existing intents, we ran into two problems: Our existing intents/entities used different property names in the past and some properties are slightly different then the schema. Our existing intents are already used on older Versions of macOS / iOS. But the schema domain is only available on OS27 and later. What can we do to adopt the schema? Should we just duplicate all Intents / Entities and mark them as isAssistantOnly and limit their availability to OS27 and later?

I am concerned how easy they make it to generate photos of real people. And because it is so easy, people will likely just try it on people without their consent. At the WWDC26 keynote, they demonstrated how you can use any photo of a person to create a new photorealistic image based on modifications described using natural language. I would even describe this as creepy. Anyone who can find a photo of me online, can create a photo of me doing whatever they want! And of course, I have no control over who they share that with. I believe Apple could do better than the other AI companies. At minimum, they could display some warnings about the ethical considerations when using this feature.

Hi everybody! Yesterday I requested for New siri in ios27, but nobody accepted my request yet. Can you help me pls?

Hello, I recently learned about Private Cloud Compute (PCC): https://developer.apple.com/private-cloud-compute/ I am currently using a standard Developer Program account, and it seems that I cannot apply for the program directly. Is there an alternative? Also, is there any additional fee for using this service? If I want to call PCC in the app, for example, using the following code: let session = LanguageModelSession( model: PrivateCloudComputeLanguageModel() ) Do I need to apply for a specific plan to ensure that my App is successfully published on the App Store and available to users? Thank you!

I gave Xcode 27 Beta 1 + Claude Agent my app codebase and set it to work on reviewing the SwiftUI related codebase and suggest improvements in the areas view performance and SwiftUI conformance. I am extremely happy with the results I got. From my experience the Xcode backed Claude Agent is far more versed in SwiftUI related task than pure Claude Code or Claude Code + SwiftUI skill extensions. I was able to visibly increase the performance of several complex views in my app. In addition the Xcode backed agent solved a Liquid Glass related bug with view tinting that I was not able to solve with Claude Code before on its first try. However, in Beta 1 Claude Agent BURNS through tokens at a mind boggling speed. I perceive the agent as a bit to verbose in telling me what it is doing. Allowing the agent to start a simulator and use the app for exploration is setting tokens on fire. I hope that we see refinements in these areas before Xcode 27 is released.

For intents that return complex markdown, code snippets, or structured layouts, what are the rendering capabilities and resource constraints of custom SwiftUI views returned via Snippet inside the Siri voice overlay? Are interactive controls (like buttons, copy-to-clipboard, or scroll views) supported inside the Siri-overlay SwiftUI container?

Hi, I joined the New Siri waitlist on June 8 (the day of WWDC 2026) and as of June 12, I have still not been granted access on iPhone or iPad — that's 4 days with no activation. I used the Terminal workaround on macOS 27 Golden Gate Beta (EnhancedSiriWaitlist → Enabled = NO), which successfully activated New Siri on my Mac. However, it has not synced to my other devices despite being on the same Apple ID with iCloud Siri sync enabled. Device details: Mac mini (macOS 27 Golden Gate Beta) — New Siri active ✓ iPhone (iOS 27.0 Developer Beta 1) — Joined Waitlist since June 8 iPad (iPadOS 27.0 Developer Beta 1) — Joined Waitlist since June 8 Steps already attempted: Multiple restarts on iPhone and iPad Toggled iCloud Siri sync off/on Toggled Siri off/on multiple times iCloud storage sufficient (200GB plan, 53GB used) 4 days seems far beyond normal rollout time. Is this a known issue? Is there anything on the account side that could be blocking activation? Thank you.

I installed the new MacOS Beta 1 on Monday, June 8 and Siri was requested. It is now Thursday, June 11 and I am still on the wait list. The conference is almost over with any interactive sessions. I am concerned that my configuration may be causing a bug. The AppleID I am logged in on the Mac (M4, 24GBs RAM, 512GB storage-130GB free) is not the same as my paid Developer AppleID used to download Xcode, etc. (it is however a Developer ID). This has never been a problem before. Could this be causing an issue? Related question, since I have not gotten the "New Siri" will this actually change the Foundation Models?

Hi everyone, Since today, all my Codex requests have been failing in both Xcode 26.5 and Xcode 27 beta. The Codex integration appears to be connected and authenticated correctly, but every request fails immediately with the error shown in the attached screenshot. Error message: The data couldn’t be read because it isn’t in the correct format.

Hello. I have a problem with the FoundationModels adapter and the Apple-hosted managed asset pack via TestFlight. I have created an adapter that works fine locally by creating a model via (fileURL: URL) on a real device, but I cannot create a model using background assets by downloading the adapter via TestFlight. Every time I try to get an adapter, the creation of the adapter is interrupted by the compatibleAdapterNotFound error. The aar. archive i created using a special command - xcrun ba-package foundation-models package --adapter-path aurelius1.fmadapter --asset-pack-id fmadapter-aurelius1-9799725 --output-path ./aurelius1.aar --platforms iOS --on-demand\ after that, I replaced "OnDemand": null with "OnDemand": {} in the manifest so that the Transporter could send my archive to the App Store Connect. I followed all the recommendations in this topic - https://origin-devforums.apple.com/forums/thread/823148 ...but unfortunately unsuccessfully I would appreciate any help in solving this problem. here is the code that I use in my app -

SystemLanguageModel.contextSize is back-deployed, but SystemLanguageModel.tokenCount is not. The custom adapter toolkit ships with a ~2.7MB tokenizer with a ~150,000 vocabulary size, but the LICENSE.rtf exclusively permits it's use for training LoRAs. Is it possible to back-deploy tokenCount or for Apple to permit the use of the tokenizer.model for counting tokens? This is important to avoiding context overflow errors.

During the Keynote (at 30m:20s) Craig Federighi mentions the second, "even more powerful version of our on-device model" and that this model lets supported products understand and generate speech. Is there any public API for generating speech using this model?

Hi everyone, I’m working with the WWDC26 Foundation Models framework and would like to know how to precisely control which model is used. Specifically: On-Device: How can I force SystemLanguageModel() to use AFM 3 Core Advanced (the 20B sparse multimodal variant) instead of automatically falling back to the 3B Core? Is there an API to query or explicitly specify the on-device model variant? Private Cloud Compute (PCC): When using PrivateCloudComputeLanguageModel(), how can I ensure it uses AFM 3 Cloud Pro instead of the regular Cloud model? Does setting ContextOptions.reasoningLevel = .deep guarantee the Pro model, or is it still determined automatically by the backend? So far I can only check model.capabilities, but there’s no clear way to confirm which exact model variant is actually running. Are there more granular APIs, DynamicProfile modifiers, or Instruments methods to achieve precise control? Any insights, official documentation, or WWDC session references would be greatly appreciated!