Hello, I’ve noticed Siri has undergone significant updates. Previously, the dedicated tools functioned excellently as a separate, independent menu choice. Currently, app intelligence merges with Siri. This integration doesn’t operate reliably, affecting proofreading and the dedicated tools alike. The feature feels entirely unstable—sometimes available, sometimes not—appearing occasionally on the keyboard, at other times on the right-button menu, though it worked well when accessible through settings. Could we restore that setup?

Hi, I have an existing app with AppEntities defined, that works on iOS17+. The AppEntities also have EntityPropertyQuery defined, so they work as 'find intents'. I want to use the new @AssistantEntity which is iOS18+ where possible, while supporting the previous versions. What's the best way to do this? For e.g. I have a 'log' AppEntity: @available(iOS 17.0, *) struct CJLogAppEntity: AppEntity { static var defaultQuery = CJLogAppEntityQuery() .... } struct CJLogAppEntityQuery: EntityPropertyQuery { ... } How do I adopt this with @AssistantEntity(schema: .journal.entry) for iOS18, while maintaining compatibility with iOS17? I don't want to include two different versions of the same AppEntity. Would it just with with the correct @available annotations on both entities?

Hello, I'm evaluating Foundation Models announced at WWDC 2026 and have a question regarding App Store distribution. My understanding is that Foundation Models are only available on supported devices and operating system versions. For apps that rely on Foundation Models as their primary functionality (rather than offering AI as an optional feature), I'm trying to understand the recommended distribution strategy. Currently, iOS provides Required Device Capabilities to prevent users from installing apps that require hardware features such as GPS, ARKit, or NFC. However, I couldn't find an equivalent Required Device Capability for Foundation Models. I also couldn't find a way to limit App Store availability by supported device models. My questions are: What is the recommended way to distribute an app whose primary functionality depends on Foundation Models? Is there currently any supported mechanism to prevent users with unsupported devices from downloading such an app? Is Apple planning to introduce a Required Device Capability (or a similar App Store filtering mechanism) for Foundation Models before public release? Without such a mechanism, users may be able to install the app successfully but then discover that its primary functionality is unavailable on their device. I'd appreciate any guidance on the recommended approach. Thank you.

Hi everyone, I'm working on an iOS app that uses VisionKit and I'm exploring the .visualLookUp feature. Specifically, I want to extract the detailed information that Visual Look Up provides after identifying an object in an image (e.g., if the object is a flower, retrieve its name; if it’s a clothing tag, get the tag's content).

I found I must zoom out the PDF so all area was displayed on the screen before Siri AI could scan the area and outline information from the PDF. If we have two pages, one page would be omitted by Siri AI. I am not sure if this the normal of Siri which it is supposed to be. Screenshot below. PS: Zooming out makes my human eyes unusable.

Hey everyone, If your iPhone is stuck on "Optimizing Search and Siri" / Indexing at around 85-90% and hard resets or leaving it on wireless charging overnight isn't moving the needle, I found a definitive way to kickstart the daemon and force it to 100%. The Root Cause (Analyzed via macOS Console): By plugging the iPhone into a Mac and checking the Console logs, I noticed that spotlightknowledged and biomed get into an endless loop around Resolved entitled set identifiers to enumerate data resources. The system stalls on verifying developer entitlements and Apple Intelligence security tokens for specific app databases over cellular networks or unstable Wi-Fi. The dasd daemon eventually puts the pipeline into a hidden sleep state to protect the battery, making it look like it's doing nothing. The Solution that forced it to 100%: Use a Wired Connection (Ethernet Adapter): Connect your iPhone directly to your fiber optic router/modem using an RJ-45 Ethernet to USB-C adapter. iOS treats a wired Ethernet connection with the highest background priority. Turn off Cellular/Wi-Fi: Go to Control Center and disable Cellular Data and Wi-Fi entirely to force iOS to route 100% of traffic through the reliable, high-speed wired pipeline. (Verify the "Ethernet" tab appears in Settings). Trigger iCloud Token Refresh: Go to Settings -> [Your Name] -> iCloud -> Saved to iCloud and toggle off/on a major asset like iCloud Drive or Messages. This forces Spotlight to dump the stalled identifiers cache. Force Restart on Cable: Perform a Hard Reset (Vol Up, Vol Down, hold Power) while the Ethernet cable is connected. Let it Cook: Keep Low Power Mode OFF, lock the screen, and leave it alone. How to verify it's definitively done: Keep your Mac Console open and filter for completeness. Gdy to się stanie, zobaczysz ostateczny dziennik świętego Graala: fetchPipelineCompleteness: display=hidden days=3 procent=1.000000 Status the ` spent=1.000000 oznacza solidne 100% uzupełnienia. Zaraz po tym, 「dasd bezpiecznie zabije procesy worker (client process exited /connection invalid), telefon w końcu ostygnie, a żywotność baterii wróci do normy. Zaraz potem wyrzuciłem potoki glp i wszystko jest teraz masłem! Mam nadzieję, że pomoże to każdemu, kto utknął w 88% otchłani!

Hi everyone, We are developing a live TV streaming app for tvOS that allows users to watch live channels, replay content, and manage cloud recordings. We are struggling to integrate Siri for a seemingly basic use case: switching the live TV channel by voice (e.g. "Hey Siri, switch to channel X on [our app]"). Here is what we have tried and observed: App Intents — we implemented custom intents, but Siri does not resolve them to our app for channel-switching requests. Shortcuts — we added Shortcuts support, but users have to explicitly configure them; Siri never proactively picks our app. In-app and out-of-app — the issue happens in both contexts. When the user asks Siri to switch to a channel, it either does nothing or suggests other applications, never ours. Our questions: Is there a specific INPlayMediaIntent configuration or domain required to handle live TV channel switching via Siri on tvOS? Is proper Siri integration for live TV gated behind the Apple Video Partner Program? If so, is there any public documentation or a path for apps outside the US to access it? Has anyone successfully implemented voice-driven live channel switching on tvOS outside of the Video Partner Program? Any guidance or pointers to relevant WWDC sessions would be greatly appreciated. Thank you.

Hi everyone, I’m trying to understand the current capabilities of App Intents and Siri when using custom intents and custom entities, without adopting one of Apple’s predefined app schemas. As an example, imagine I have a shopping app for shoes. I might have one intent that lists shoes available for sale, and another intent that can open a specific shoe in the app or add a specific shoe to favourites. What I’m trying to validate is whether Siri can support multi-turn, contextual follow-up requests in this kind of custom-intent-only setup. For example: User: “Show me the shoes available for sale.” Siri/App: returns a list of shoes. User: “Add the third one to my favourites.” Siri understands that “the third one” refers to the third shoe from the previous result list. This kind of follow-up seems to work in some Apple-defined domains. For example, a user can ask to list calendar events and then follow up with something like “open the third one in Calendar,” and Siri appears to understand the reference to the previous list item. My current understanding is that this kind of conversational context, ordinal reference resolution, and follow-up disambiguation may only be available when adopting one of Apple’s app schemas, where Siri has a richer understanding of the domain and entities. If an app only uses custom App Intents and custom App Entities, without adopting an Apple-defined schema, should we expect Siri to support this kind of multi-turn reference resolution? Or is each turn in the conversation which requires a custom intent invocation effectively handled more independently? I’d appreciate any clarification on whether this is expected to work, currently unsupported, or only available through schema-based integrations. Thanks

In the past, for any App Intent developers provide to the AppShortcutsProvider, there needed to be explicit phrases provided to trigger the AppShortcut from Siri -- and if the user try to trigger the Shortcut using a slightly different phrase then the Siri does not work. With Siri AI, will App Intents that don't fit any schemas work without needing every phrase to be explicitly programmed?

I'm following along with the WWDC video on SpotlightSearchTool and hitting an error - looking for some guidance. I've configured SpotlightSearchTool and I'm sending it to the session. let session = LanguageModelSession(tools: [tool]) { spotlightSearchInstructions } let response = try await session.respond(to: prompt, options: GenerationOptions(toolCallingMode: .required)) I set the tool calling mode to required as a test - without it I don't get errors but the logging makes it seem like it's not calling the search tool and the responses would seem to confirm that (they're not grounded in my data). So, I figured I'd try forcing it to use the tool. When I do that, I get this console error: InferenceError::hostFailed::InferenceError::inferenceFailed::TokenGenerationCore.GuidedGenerationError.invalidConfiguration(errorMessage: "Tool Choice requires tools") in response to ExecuteRequest Error during session.respond. description="The operation couldn’t be completed. (FoundationModels.LanguageModelError error -1.)" Returning empty Spotlight result. elapsedMs=3254 toolReplies=0 totalSearchItems=0 uniqueSearchItems=0 What does that mean? I'm passing in a tool, everything compiles correctly, etc. Not sure how to debug - any advice appreciated! Testing this via the Simulator on beta 3.

Filed as FB23652582. In Xcode 27 beta, this no longer compiles when the deployment target is below iOS 27: @available(iOS 18.0, *) @AppEntity(schema: .photos.asset) struct AssetEntity: IndexedEntity { ... } // error: 'asset' is only available in iOS 27.0 or newer The identical source compiles under Xcode 26. It looks like the @AppEntity(schema:) macro now resolves .photos.asset to a declaration annotated for iOS 27, whereas in Xcode 26 it resolved to the (now-deprecated) iOS 16 declaration. What seems off: the .photos.album entity in the same domain still builds fine at an iOS 18 deployment target — only .asset requires iOS 27. That asymmetry is what makes me think it may be an unintended availability change rather than a deliberate one. Has anyone else hit this? And is this intended — i.e. is .photos.asset now meant to be iOS 27+ only, or should it still be usable from apps that deploy to iOS 18?

Are any Apple engineers aware that in Create ML, when duplicating a model source, the app crashes and does not save any changes that were made?

Use Case I’m currently developing , a hiking and cycling app. I’d like to use Siri AI in iOS/watchOS 27 to create an experience like this: While users are recording an activity in app, they can raise their wrist or invoke Siri on iPhone and simply ask: “How much farther to the destination?” “How far have I already gone?” “How much elevation gain is left?” “How far is it to the next waypoint?” … Siri can then answer based on the app’s current workout context. Since there are many metrics like these, and it’s not convenient to look at the screen while cycling or trail running, this could be a really valuable use case if Siri AI can support it. I defined an AppEntity like this, and then associated it with the UI. But I found that Siri AI doesn’t seem to understand this AppEntity. It can only understand the content it can see on the screen, even though I can see that it did execute ToobooWorkoutSessionQuery, the EntityQuery. This screen has multiple tabs. Siri understood the on-screen values such as “Distance: 0.21 mi” and “Remaining Distance: 0.14 mi”, but it didn’t know the data from the other tabs on the same page, such as heart rate, average speed, and so on. So it seems that Siri is directly reading the screen, instead of retrieving the information from the AppEntity I actually provided. Is this because the AppEntity doesn’t use one of the schemas defined by AppSchemaEntity, so Siri AI can’t understand it? App Intents without a schema seem to have a similar issue. If the AppIntent I define is not within one of those schemas, Siri won’t directly execute it either. My current solution: I defined many Intents and Shortcuts. Siri AI’s ability to parse shortcuts seems to be much smarter in the new system, and it can match them quite easily. Also, shortcuts don’t require the app to be in the foreground. However, when talking to Siri, the shortcut phrase has to include the app name, which feels a bit unnatural. For example: “How far have I traveled in xxx app?”

Since beta 2 I think, it seems Foundation models are not accessible if Siri AI is not enabled. I'm on Mac OS, and not sure how it works on iOS, but does that mean that Foundation Models will not be usable if Siri AI is not enabled (Europe)?

Will there be a wheel published on pypi.org for Python 3.13 on macOS? There is a 3.13 wheel for Linux, but not macOS.

我今年18岁。没有机器学习背景，没有上过大学，高中都没去上，没有导师。 几天前我盯着一张纸发呆。突然想：为什么计算机神经网络一定要是2D的？可以模拟生物吗？为什么一定要在平面上算？如果多个平面，岂不是翻倍？如果把六张纸想象成一个魔方，六个面各自承载神经元，八条体对角线变成新的通信通道会怎么样？ 我真的很喜欢折腾这些，然后我立刻制定了详细计划，使用AI工具辅助写下了第一个 kernel。跑崩了。我又重新想了一下，和qq群友分享了我的目标，又写。又崩。连续几十次。没有 PyTorch，没有 TensorFlow，没有 CUDA。只有Swift和Metal。因为我的电脑显卡是AMD Vega 64，没装任何框架辅助，因为我想明白最底层的运行方式是什么原理。 这就是CubeNN。 ##以下为AI的详细解答，内容与架构改动太多，我在这里一次讲不清楚 它是什么 一个用魔方几何作为计算架构的神经网络引擎。 标准 Transformer: 把数据排成一行，O(n²) 地互相看 CubeNN: 把数据分布在 14 个面上，只在该看的地方看 6 个标准面 → 块稀疏注意力（粗看全局 + 细看局部） 8 个 X 面对角线 → 跨面信息桥（不做 Attention，只负责传递） 每轮：6 面算 → 投影到 8 X 面 → 上采样精炼 → 融合回 6 面 最关键的是 Cube Cascade——一个树+链级联推理： 树阶段: 1 个魔方 spawn 8 个 → 8 个 spawn 64 个 → 73 个并行探索 GPU 上同时跑，选最优路径 链阶段: 最优叶子无限深度精炼 3-5 步收敛，方差提升 ~7% 怎么实现的 纯 Swift + Metal。零依赖。零框架。 // 大致代码就是这些 import Metal import Foundation let device = MTLCreateSystemDefaultDevice()! let library = try! device.makeLibrary(filepath: "cube_nn.metallib") // ...12 个 GPU kernel，12,000 次 dispatch 关键技术决策： 单 Command Buffer：整个树阶段 73 个魔方的全部 kernel dispatch 打包进一个 CB，0 次 CPU-GPU 同步 Pipeline State 缓存：编码从 1022ms 降到 42ms Buffer 偏移：所有 73 个魔方的 14 个面存进一个连续 buffer，kernel 通过 buffer(15) 传偏移量 FP16：N≥64 时半精度提速 21% 性能 ##经过测试，但是因设备差异可能不准确，仅参考 AMD Radeon RX Vega 64 (2017 年显卡, 14nm, 295W): 规模 神经元 魔方数 耗时 N=32 6,144 73 (树) 435ms N=64 24,576 21 (树) 817ms N=128 98,304 1 116ms N=32 全连接 Attention 每层 201M FLOP → CubeNN 块稀疏 370K FLOP (544× 减少) N=128 全连接需要 32GB 显存（物理上不存在）→ CubeNN 用 192KB N=256 全连接需要 2.2T FLOP → CubeNN 52M FLOP (42,300× 减少) 代码体积：161KB。 对比 PyTorch 的 800MB。 我经历了什么 这个项目最困难的不是写 kernel，是在没有任何人告诉我"能不能做"的情况下，靠反复试错找到路。 第一次试图跑 73 个魔方，GPU 直接 hang 了。花了 3 天定位到是 Command Buffer 堆叠过多。 改了 single encoder 方案，又碰上 SIGILL——Metal 不允许 makeBuffer(length: 0)，B=0 时创建了零长度 buffer。 想用 threadgroup memory 做 kernel fusion，结果跨 threadgroup 读不到数据，才明白 LDS 是 per-group 的。 N=64 的 FP16 要手动写 float↔half 转换函数，因为 macOS 11 上 Float16 类型被标为 unavailable。 每一次崩溃都教会我一个 Metal 的底层细节。没有人教我，但 Metal 的报错信息就是最好的老师。 为什么发在 Apple 开发者论坛 因为这是为苹果生态而生的项目。CubeNN 从头到尾只用了两个东西：Swift 和 Metal。它不需要移植就能跑在任何 Apple Silicon Mac 上（API兼容）。如果未来能把部分 kernel 映射到 Neural Engine，效率会再翻几倍。 我想问 Apple 的 Metal 工程师和 Core ML 团队： ** 有没有更好的 GPU 任务调度方式？**目前表现仍然欠佳（对于我这个完美主义者来说），可能改得有点乱了 有没有兴趣评估这个架构在 M4 上的表现？ 我手里只有 Vega 64。M4 GPU + ANE方法 跑 CubeNN 会是什么效果？ 源代码 ├── run.swift # 统一 CLI，参数化 N/B/depth ├── src/ │ ├── cube_nn.metal # FP16 kernel │ └── cube_nn_fp32.metal # FP32 kernel └── benchmarks/ # 实测数据 如果你读到了这里——谢谢你。一个门外汉靠痴狂的，纯粹到几乎是妄想的主意和Metal走到了这里。我懂的不是很多，如果这个架构有任何价值，我想让它变得更好。任何建议、批评、或者指教，都非常欢迎。

I have a M3 Ultra Mac Studio running RDMA. However, the system is unable to connect all 6 thunderbolt ports when the ethernet cable is also connected. Can anyone help?

I have a photo editing app that owns no photo library. I want a user viewing an image in another app (e.g. Photos) to say "filter this image in MyApp" and have Siri hand that on‑screen image to my intent. Targeting iOS 27. What I've tried, and the result in each case: • App Shortcut + @Parameter var image: IntentFile — Siri resolves my other parameters (a filter AppEnum) by voice, but never binds the image; the run fails. • @AppIntent(schema: .photos.setFilter) with a .photos.asset entity — never routes from Photos. • @AppIntent(schema: .system.open): OpenIntent with a custom AppEntity target — "Open this image in MyApp" just launches the app by name; perform() is never called, and the entity query never runs. My understanding from WWDC26 "Build intelligent Siri experiences with App Schemas" (session 240) and "Discover new capabilities in the App Intents framework" (session 345): • Cross‑app content transfer (Transferable + IntentValueRepresentation) seems limited to system value types (IntentPerson, PlaceDescriptor); IntentFile is not a _SystemIntentValue, so an image can't ride that rail. • Onscreen awareness (NSUserActivity.appEntityIdentifier, View Annotations) appears to expose only the foreground app's own content — which here is Photos, not me. Question: Is there a supported way for a third‑party app to receive another app's on‑screen image (vs. a contact/place) through Siri/App Intents today? If so, which API carries the pixels — an IntentFile parameter, @UnionValue, IntentValueQuery, something else — and what must the source app do to make it available? Or is asking "do X to this image in <third‑party app>" simply not supported yet outside Shortcuts?

I have a health app on the App Store that uses Foundation Models to generate brief narrative summaries from the user's own glucose and menstrual cycle data. No medical advice, just supportive summaries of their own numbers. This has been working reliably on iOS 26.x since early 2026. After updating to iOS 27 beta 2, every prompt is refused. The error is LanguageModelError ("The model refused to answer" / "May contain sensitive content"), not GenerationError.guardrailViolation. I've confirmed: Same device, same code, same prompts. Worked on iOS 26.x, fails on iOS 27 beta 2. Two independent features with different prompt structures and different service architectures are both affected. Using SystemLanguageModel(guardrails: .permissiveContentTransformations) does not help. The classifier passes. The model itself refuses. The prompts contain terms like "luteal phase," "progesterone," "glucose," "time in range," and "diabetes" in the system instructions. This appears to be a model-level sensitivity change in the iOS 27 on-device model that broadly blocks health/medical terminology, even when the use case is summarizing the user's own data. Filed as FB23513774 with the full prompt text, instructions, and source file attached. Is anyone else seeing model-level refusals (not guardrailViolation) on iOS 27 beta for health or medical content? Related threads from iOS 26 betas: Model Guardrails Too Restrictive? Model w/ Guardrails Disabled Still Refusing Using Past Versions of Foundation Models As They Progress

Hello Team, I am writing to seek clarification regarding an issue I am encountering while integrating App Intents within my application. I have configured an App Intent designed to accept an IntentFile as a parameter for processing. When testing this functionality via the Siri interface, I attach the image file and provide the trigger phrase as expected. However, Siri does not seem to recognize or associate the attached image as the required IntentFile. Consequently, the interaction fails to proceed, and Siri continues to prompt me to select a file. Could you please advise if there is a specific configuration requirement or a known limitation regarding how Siri handles file attachments for IntentFile parameters? I would appreciate any guidance on whether this is an issue with my current implementation or if I am missing a necessary step in the setup process. Thanks & Regards Suresh