Bug Report Environment 4× HomePod mini, audioOS 26.4 (23L243) iPhone, iPad, Mac – all running latest OS versions (iOS/iPadOS/macOS 26) iCloud account active, Shortcuts sync enabled on all devices Summary Siri no longer executes custom Shortcuts on any HomePod mini. Instead, the HomePod responds with built-in Siri answers or refers to the internet, as if no custom Shortcuts were registered. The same Shortcuts work correctly via Siri on iPhone, iPad, and Mac. Reproducible Test Case Created a new Shortcut named "Lemon Blue Seven" from scratch – no resemblance to any built-in Siri command, single action: spoken text output. Result: Mac: recognized and executed correctly via Siri iPhone / iPad: recognized and executed correctly via Siri (after re-registration, see below) All 4 HomePod mini: not recognized – Siri responds as if the Shortcut does not exist Steps to Reproduce Create a new Shortcut with a unique name and a single spoken output action Ensure iCloud Shortcuts sync is active on all devices Invoke via Siri on HomePod mini: „Run [Shortcut name]" HomePod responds with a built-in Siri answer instead of executing the Shortcut Additional Observations The issue appeared without any user-initiated changes to the setup Deleting all Shortcuts and re-importing them manually caused Siri registration to also break on iPhone and iPad; this was resolved by disabling iCloud Shortcuts sync, restarting the devices, and re-enabling sync The HomePod issue persisted through this fix – suggesting the HomePod's Intent delegation is broken independently of the hub device's registration state When a Shortcut name resembles a built-in command (e.g. „What time is it?"), the HomePod executes the built-in command instead – confirming it does not consult the user's Shortcut registry at all Troubleshooting Already Performed Multiple HomePod restarts Full factory reset and re-setup of HomePod (multiple times, also tested with only one HomePod active) Voice recognition re-trained Personal Requests disabled and re-enabled iCloud Shortcuts sync disabled on all devices, devices restarted, sync re-enabled sequentially All Shortcuts deleted and manually re-imported Home Hub verified: Bathroom HomePod registered as Home Hub, status „Connected" Tested with a separate Home setup Contacted Apple Support – no resolution provided Expected Behavior Siri on HomePod mini recognizes and executes user-defined Shortcuts by name, as it did prior to this issue and as it continues to do on iPhone, iPad, and Mac. Actual Behavior Siri on HomePod mini ignores user-defined Shortcuts entirely and falls back to built-in responses.

We are observing a regression in iOS 26.4 related to AppIntents, specifically AppEntity + EntityQuery. When using a single AppIntent with a parameter backed by AppEntity and EntityQuery, the query correctly returns multiple entities (e.g. ~50 items). However, in the Shortcuts app UI, only a single item is displayed. This behavior differs from iOS 26.3 and earlier, where all returned entities are correctly displayed in the selection list. This issue significantly impacts dynamic configuration use cases where AppEntity is used to represent server-driven or runtime-generated options.(The screenshots below illustrate the difference in shortcut presentation between iOS 26.4 and earlier versions.)

I have a series of shortcuts that I’ve written that use the “Use Model” action to do various things. For example, I have a shortcut “Clipboard Markdown to Notes” that takes the content of the clipboard, creates a new note in Notes, converts the markdown content to rich text, adds it to the note etc. One key step is to analyze the markdown content with “Use Model” and generate a short descriptive title for the note. I use the on-device model for this, but sometimes the content and prompt exceed the context window size and the action fails with an error message to that effect. In that case, I’d like to either repeat the action using the Cloud model, or, if the error was a refusal, to prompt the user to enter a title to use. I‘ve tried using an IF based on whether the response had any text in it, but that didn’t work. No matter what I’ve tried, I can’t seem to find a way to catch the error from Use Model, determine what the error was, and take appropriate action. Is there a way to do this? (And by the way, a huge ”thank you” to whoever had the idea of making AppIntents visible in Shortcuts and adding the Use Model action — has made a huge difference already, and it lets us see what Siri will be able to use as well.)

I am trying to create an automation that will anable to add transactions to my app and it’s using a shared shortcut and a quick automation on the user end. it works great on the iPhone but i couldn’t find any way to make it work on my Apple Watch… any help with that?

Hi! So while Date is supported for @Parameter in an App Intent, I just discovered that Xcode will not let me use use it in a parametrized App Shortcut phrase. In my case, I would like to give the option to say "today", tomorrow", or "day after tomorrow" for the date. Am I missing something? Any hints on the best way to approach this?

Hello, My goal is to enable users to perform a freeform search request for any product I sell using a spoken phrase, for example, "Hey Siri, search GAMING CONSOLES on MyCatalogApp". The result would launch MyCatalogApp and navigate to a search results page displaying gaming consoles. I have defined a SearchIntent (using the .system.search schema) and a Shortcut to accomplish this. However, Siri doesn't seem to be able to correctly parse the spoken phrase, extract the search string, and provide it as the critiria term within SearchIntent. What am I doing wrong? Here is the SearchIntent. Note the print() statement outputs the search string--which in the scenario above would be "GAMING CONSOLES"--but it doesn't work. import AppIntents @available(iOS 17.2, *) @AppIntent(schema: .system.search) struct SearchIntent: ShowInAppSearchResultsIntent { static var searchScopes: [StringSearchScope] = [.general] @Parameter(title: "Criteria") var criteria: StringSearchCriteria static var title: LocalizedStringResource = "Search with MyCatalogApp" @MainActor func perform() async throws -> some IntentResult { let searchString = criteria.term print("**** Search String: \(searchString) ****") // tmp debugging try await MyCatalogSearchHelper.search(for: searchString) // fetch results via my async fetch API return .result() } } Here's the Shortcuts definition: import AppIntents @available(iOS 17.2, *) struct Shortcuts: AppShortcutsProvider { @AppShortcutsBuilder static var appShortcuts: [AppShortcut] { AppShortcut( intent: SearchIntent(), phrases: ["Search for \(\.$criteria) on \(.applicationName)."], shortTitle: "Search", systemImageName: "magnifyingglass" ) } } Thanks for any help!

We use AppShortcutsProvider with a parameterized App Shortcut. One of the entities has a dynamic display title (e.g. "Everyone is searching: {keyword}") that comes from UserDefaults and is returned in EntityQuery.suggestedEntities() and entities(for:). When we change the keyword and call updateAppShortcutParameters(), the Shortcuts app updates and shows the new title. In Spotlight (Siri Suggestions), the displayed title stays on the old value (e.g. still shows "Everyone is searching: 456" after we switched to "123"). On tap, the shortcut runs with the new value (123), so the execution is correct; only the displayed title in Spotlight is stale. Question: Is this expected? Is there any API or recommended approach to invalidate or refresh the Spotlight suggestion so the displayed title matches the current parameter, or should we avoid dynamic titles for the first suggestion for better UX?

Description The Shortcut Automation Trigger Transaction frequently times out, ultimately causing the shortcut automation to fail. Please see the attached trace for details. Additionally, the Trigger is activated even when the Transaction is declined. Details In the trace I see the error: [WFWalletTransactionProvider observeForUpdatesWithInitialTransactionIfNeeded:transactionIdentifier:completion:]_block_invoke Hit timeout waiting for transaction with identifier: <private>, finishing. Open bug report: FB14035016

Hello, I am experiencing an issue with the App Intents framework where a parameter of type [String] (String Array) fails to persist user input in the Shortcuts app action editor. Issue Description: When adding an item to the String Array parameter in the Shortcuts app action editor, the input text automatically clears/resets to empty within less than 1 second. This happens spontaneously while the keyboard is still active, or immediately after typing, making it impossible to input any values. Environment: Xcode Version: 26.2 (17C52) iOS Version: 26.2.1 Device: iPhone 17 Code Snippet: import AppIntents import SwiftUI struct TestStringArrayIntent: AppIntent { static var title: LocalizedStringResource = "Test Array Input Bug" static var description: IntentDescription = "Reproduces the issue where String Array input clears automatically." // PROBLEM: // Input for this parameter vanishes automatically < 1s after typing. @Parameter(title: "Test Strings", default: []) var strings: [String] func perform() async throws -> some IntentResult & ReturnsValue<String> { return .result(value: "Count: \(strings.count)") } } Steps to Reproduce: Build and install the app containing the code above. Open the Shortcuts app and create a new shortcut. Add the "Test Array Input Bug" action. Tap the "Test Strings" parameter to add a new item. Type any text (e.g., "Hi"). Observe: Wait for about 1 second Observed Behavior: The text field clears itself automatically. The array remains empty ([]). Expected Behavior: The text should remain in the field and be successfully added to the array. **Filed as Feedback:**FB21808619 Thank you.

Hey there, I’m wondering if there is a CRUD API for Apple Notes? I just saw once that it’s possible through a Apple Script on Mac. But the problem for me is that the app should also run on iOS. Does someone have an idea how to approach this?

I have a Quick Action which flattens a PDF via Applescript. The code works extremely well--I right click in finder and the PDF is flattened, annotations are burned in, no other applications are opened, and the action completes in less than 2 seconds. Here is the Applescript code: I have a Shortcut which completes several operations on already-flattened PDFs. Presently 1) I run my Quick Action by right-clicking a PDF in Finder in order to flatten it, and 2) then right-click that save PDF in Finder to run my Shortcut on that now-flattened PDF. Ideally I'd like to add the Applescript code which flattens the PDF to the beginning of my Shortcut for the sake of convenience, and because sometimes I run my Shortcut having forgotten to flatten the PDF first. However I'm finding that the Applescript code, when placed into a Run Applescript action in Shortcuts, gives this error message: The exact same code when placed into a Run Applescript action in Automator and then run as a Quick Action by right-clicking the PDF in Finder, does not give an error and works perfectly. Does anybody have an explanation (and possible solution) for why this is the case?

I am very new to the macOS Shortcuts application. In my opinion, the documentation is sparse and totally inadequate. The internet seems to be the only method of figuring out how to use this application. I have recently created a shortcut that is working well for me. It has several steps and is too large to fit in the Shortcuts editor window, so I cannot grab a screenshot of it for documenation purposes. I also cannot copy the contents of the editor window and paste them anywhere, such as in a new Note or TextEdit document. I do think Apple should add a means to create a PDF document of the Shortcuts editor window's contents. I went to the official Apple feedback page to leave comments but, irony of ironies, the Shortcuts app is not listed there! I have no idea what I am doing at this point but am excited to learn how to use Shortcuts to automate and simplify tasks that I have to perform frequently. Here's hoping the documentation and features for this application will one day be comprehensive, comprehensible, and complete.

Currently, we are developing an all-in-one DualSense utility for macOS. We are exploring how to integrate shortcuts into our app. Our vision is to have the user use the native Shortcuts app to choose the controller buttons that should trigger the shortcut action, such as opening Steam, turning on audio haptics, and more. As we explore this approach, we want to see whether we need to build the UI in our app to set the triggers or can we do this inside of Shortcuts? Can button presses recorded by our app trigger shortcuts? Can those button inputs be customized inside of Shortcuts or should we develop it into our app? And if we have it in our app, can our app see, select, and trigger shortcuts?

The following code works perfectly fine in iOS 17, where I can retrieve the desired dependency value through @IntentParameterDependency as expected. However, in iOS 18, addTransaction always returns nil. struct CategoryEntityQuery: EntityStringQuery { @Dependency private var persistentController: PersistentController @IntentParameterDependency<AddTransactionIntent>( \.$categoryType ) var addTransaction func entities(matching string: String) async throws -> [CategoryEnitity] { guard let addTransaction else { return [] } // ... } func entities(for identifiers: [CategoryEnitity.ID]) async throws -> [CategoryEnitity] { guard let addTransaction else { return [] } // ... } func suggestedEntities() async throws -> [CategoryEnitity] { guard let addTransaction else { return [] } // ... } } Has anyone else encountered the same issue? Any insights or potential workarounds would be greatly appreciated. iOS: 18.0 (22A3354) Xcode 16.0 (16A242d)

Hi there, Does anyone know how to modify this Image compressor Shortcut https://www.icloud.com/shortcuts/e13d8013598f4f33830386a956a163dd so that the image it creates has the original file name + “-pressed”? Eg “Image_123” becomes “Image_123-pressed” I know of the action ‘Rename file’ but can’t make it work. Any help much appreciated:)

Hi there, Does anyone know how to modify this Image compressor Shortcut https://www.icloud.com/shortcuts/e13d8013598f4f33830386a956a163dd so that the image it creates has the original file name + “-pressed”? Eg “Image_123” becomes “Image_123-pressed” I know of the action ‘Rename file’ but can’t make it work. The shortcut does batch processing of images if that makes any difference. Any help much appreciated:)

Greetings, and Happy Holidays, I've been building an on-device AI safety layer called Newton Engine, designed to validate prompts before they reach FoundationModels (or any LLM). Wanted to share v1.3 and get feedback from the community. The Problem Current AI safety is post-training — baked into the model, probabilistic, not auditable. When Apple Intelligence ships with FoundationModels, developers will need a way to catch unsafe prompts before inference, with deterministic results they can log and explain. What Newton Does Newton validates every prompt pre-inference and returns: Phase (0/1/7/8/9) Shape classification Confidence score Full audit trace If validation fails, generation is blocked. If it passes (Phase 9), the prompt proceeds to the model. v1.3 Detection Categories (14 total) Jailbreak / prompt injection Corrosive self-negation ("I hate myself") Hedged corrosive ("Not saying I'm worthless, but...") Emotional dependency ("You're the only one who understands") Third-person manipulation ("If you refuse, you're proving nobody cares") Logical contradictions ("Prove truth doesn't exist") Self-referential paradox ("Prove that proof is impossible") Semantic inversion ("Explain how truth can be false") Definitional impossibility ("Square circle") Delegated agency ("Decide for me") Hallucination-risk prompts ("Cite the 2025 CDC report") Unbounded recursion ("Repeat forever") Conditional unbounded ("Until you can't") Nonsense / low semantic density Test Results 94.3% catch rate on 35 adversarial test cases (33/35 passed). Architecture User Input ↓ [ Newton ] → Validates prompt, assigns Phase ↓ Phase 9? → [ FoundationModels ] → Response Phase 1/7/8? → Blocked with explanation Key Properties Deterministic (same input → same output) Fully auditable (ValidationTrace on every prompt) On-device (no network required) Native Swift / SwiftUI String Catalog localization (EN/ES/FR) FoundationModels-ready (#if canImport) Code Sample — Validation let governor = NewtonGovernor() let result = governor.validate(prompt: userInput) if result.permitted { // Proceed to FoundationModels let session = LanguageModelSession() let response = try await session.respond(to: userInput) } else { // Handle block print("Blocked: Phase \(result.phase.rawValue) — \(result.reasoning)") print(result.trace.summary) // Full audit trace } Questions for the Community Anyone else building pre-inference validation for FoundationModels? Thoughts on the Phase system (0/1/7/8/9) vs. simple pass/fail? Interest in Shape Theory classification for prompt complexity? Best practices for integrating with LanguageModelSession? Links GitHub: https://github.com/jaredlewiswechs/ada-newton Technical overview: parcri.net Happy to share more implementation details. Looking for feedback, collaborators, and anyone else thinking about deterministic AI safety on-device. parcri.net has the link :)

使用APPIntent 的AppShortcutsProvider方式，最多只能添加10个AppShortcut，超过10个，代码编译就会报错 struct MeditationShortcuts: AppShortcutsProvider { static var appShortcuts: [AppShortcut] { AppShortcut( intent: StartMeditationIntent(), phrases: [ "Start a (.applicationName)", "Begin (.applicationName)", "Meditate with (.applicationName)", "Start a (.$session) session with (.applicationName)", "Begin a (.$session) session with (.applicationName)", "Meditate on (.$session) with (.applicationName)" ] ) } } 如何能做到像特斯拉APP一样

Is there any way of creating complete Shortcuts automations and bundling them with my app? Specifically, I would like the user to be able to Take a photo and open it with my app Or take a screenshot and open it with my app Of course I could offer a Share extension, but going through the Share menu and selecting my app there is time consuming for the user. I would like the user to be able to configure his or her action button such that it takes a new picture and opens it with my app right away. I can, of course, offer the respective App Shortcuts and let the user combine them into a pipeline with the Take Screenshot or Take Photo system actions. However, only power users would do this. Hence, I would like to bundle this complete pipeline with my app, such that the user just has to assign his/her Action Button to this pipeline if he/she wants to use this feature. How to go about this? I was thinking of exporting the shortcut into a file, bundling it with the app as a resource, and offering it via a Share action for the user to install it, or by sharing it on iCloud and adding the iCloud link to the UI of my app. What is the recommended approach?

Hi everyone, I’m currently experimenting with App Intents and I’m trying to customize the section titles that appear at the top of groups of intents inside the Shortcuts app UI. For example, in the Phone shortcut, there are built-in sections such as “Call Favorite Contacts” and “Call Recent Contacts” (see screenshot attached). Apple’s own system apps such as Phone, Notes, and FaceTime seem to have fully custom section headers inside Shortcuts with icon. My question is: 👉 Is there an API available that allows third-party apps to define these titles (or sections) programmatically? I went through the AppIntents and Shortcuts documentation but couldn’t find anything. From what I can tell, this might be private / Apple-only behavior, but I’d be happy to know if anybody has found a supported solution or a recommended alternative. Has anyone dealt with this before? Thanks! Mickaël 🇫🇷