I'm seeing this error a lot in my console log of my iPhone 15 Pro (Apple Intelligence enabled): com.apple.modelcatalog.catalog sync: connection error during call: Error Domain=NSCocoaErrorDomain Code=4099 "The connection to service named com.apple.modelcatalog.catalog was invalidated: failed at lookup with error 159 - Sandbox restriction." UserInfo={NSDebugDescription=The connection to service named com.apple.modelcatalog.catalog was invalidated: failed at lookup with error 159 - Sandbox restriction.} reached max num connection attempts: 1 Are there entitlements / permissions I need to enable in Xcode that I forgot to do? Code example Here's how I'm initializing the language model session: private func setupLanguageModelSession() { if #available(iOS 26.0, *) { let instructions = """ my instructions """ do { languageModelSession = try LanguageModelSession(instructions: instructions) print("Foundation Models language model session initialized") } catch { print("Error creating language model session: \(error)") languageModelSession = nil } } else { print("Device does not support Foundation Models (requires iOS 26.0+)") languageModelSession = nil } }

Originally, I set my iOS deployment target to 18.1, but now that I'm integrating Foundational Models, I set it to iOS 26.0. Is this ok?

I'm using Xcode 26 Beta 5 and get errors on any generation I try, however harmless, when wrapped in the #Playground macro. #Playground { let session = LanguageModelSession() let topic = "pandas" let prompt = "Write a safe and respectful story about (topic)." let response = try await session.respond(to: prompt) Not seeing any issues on simulator or device. Anyone else seeing this or have any ideas? Thanks for any help! Version 26.0 beta 5 (17A5295f) macOS 26.0 Beta (25A5316i)

Encountered a few times when the answer get "stuck" (I am now at beta 6). This is an example.

Hi, I have trained a basic adapter using the adapter training toolkit. I am trying a very basic example of loading it and running inference with it, but am getting the following error: Passing along InferenceError::inferenceFailed::loadFailed::Error Domain=com.apple.TokenGenerationInference.E5Runner Code=0 "Failed to load model: ANE adapted model load failure: createProgramInstanceWithWeights:modelToken:qos:baseModelIdentifier:owningPid:numWeightFiles:error:: Program load new instance failure (0x170006)." UserInfo={NSLocalizedDescription=Failed to load model: ANE adapted model load failure: createProgramInstanceWithWeights:modelToken:qos:baseModelIdentifier:owningPid:numWeightFiles:error:: Program load new instance failure (0x170006).} in response to ExecuteRequest Any ideas / direction? For testing I am including the .fmadapter file inside the app bundle. This is where I load it: @State private var session: LanguageModelSession? // = LanguageModelSession() func loadAdapter() async throws { if let assetURL = Bundle.main.url(forResource: "qasc---afm---4-epochs-adapter", withExtension: "fmadapter") { print("Asset URL: \(assetURL)") let adapter = try SystemLanguageModel.Adapter(fileURL: assetURL) let adaptedModel = SystemLanguageModel(adapter: adapter) session = LanguageModelSession(model: adaptedModel) print("Loaded adapter and updated session") } else { print("Asset not found in the main bundle.") } } This seems to work fine as I get to the log Loaded adapter and updated session. However when the below inference code runs I get the aforementioned error: func sendMessage(_ msg: String) { self.loading = true if let session = session { Task { do { let modelResponse = try await session.respond(to: msg) DispatchQueue.main.async { self.response = modelResponse.content self.loading = false } } catch { print("Error: \(error)") DispatchQueue.main.async { self.loading = false } } } } }

Hello, My app fully relies on the new Foundation Models. Since Foundation Models require Apple Intelligence, I want to ensure that only devices capable of running Apple Intelligence can install my app. When checking the UIRequiredDeviceCapabilities property for a suitable value, I found that iphone-performance-gaming-tier seems the closest match. Based on my research: On iPhone, this effectively limits installation to iPhone 15 Pro or later. On iPad, it ensures M1 or newer devices. This exactly matches the hardware requirements for Apple Intelligence. However, after setting iphone-performance-gaming-tier, I noticed that on iPad, Game Mode (Game Overlay) is automatically activated, and my app is treated as a game. My questions are: Is there a more appropriate UIRequiredDeviceCapabilities value that would enforce the same Apple Intelligence hardware requirements without triggering Game Mode? If not, is there another way to restrict installation to devices meeting Apple Intelligence requirements? Is there a way to prevent Game Mode from appearing for my app while still using this capability restriction? Thanks in advance for your help.

I'm a bit new to the LLM stuff and with Foundation Models. My understanding is that there is a token limit of around 4K. I want to process the contents of files which may be quite large. I first tried going the Tool route but that didn't work out so I then tried manually chunking the text to keep things under the limit. It mostly works except that every now and then it'll exceed the limit. This happens even when the chunks are less than 100 characters. Instructions themselves are about 500 characters but still overall, well below 1000 characters per prompt, all told, which, in my limited understanding, should not result in 4K tokens being parsed. Any ideas on what is going on here?

The 2026 framework lets apps call cloud models like Claude and Gemini (or "any provider that conforms to Apple's Language Model protocol") through the same Swift API as the on-device model. What exactly must a provider implement to conform to the Language Model protocol, and can developers register a custom/self-hosted endpoint and their own API keys, or is routing limited to an Apple-curated provider list? Does the unified API normalize provider-specific capabilities — tool/function calling formats, system-prompt handling, streaming tokens, JSON/structured output, multi-turn state — or do these degrade to a lowest common denominator across providers? When a request is routed to a third-party cloud model, what is the data path and privacy boundary? Does it transit Private Cloud Compute, or go direct to the provider, and what is disclosed to the user about where their prompt is processed? If an app supplies a conforming provider, does that provider become selectable by Siri AI for system actions, or is custom-provider routing confined to in-app LanguageModelSession use only? With the framework slated to open-source this summer, will the provider/protocol surface be stable enough to build against now, or should developers expect breaking changes between the beta and the open-source release?

For example: I have a list of to-dos, each with a unique id (a GUID). I want to feed them to the LLM model and have the model rewrite the items so they start with an action verb. I'd like to get them back and identify which rewritten item corresponds to which original item. I obviously can't compare the text, as it has changed. I've tried passing the original GUIDs in with each to-do, but the extra GUID characters pollutes the input and confuses the model. I've tried numbering them in order and adding an originalSortOrder field to my generable type, but it doesn't work reliably. Any suggestions? I could do them one at a time, but I also have a use case where I'm asking for them to be organized in sections, and while I've instructed the model not to rename anything, it still happens. It's just all very nondeterministic.

Dear Apple Foundation Models Development Team, I am a developer integrating Apple Foundation Models (AFM) into my app and encountered the exceededContextWindowSize error when exceeding the 4096-token limit. Proposal: I suggest Apple develop a tool to estimate the token count of a prompt before sending it to the model. This tool could be integrated into FoundationModels Framework for ease of use. Benefits: A token estimation tool would help developers manage the context window limit and optimize performance. I hope Apple considers this proposal soon. Thank you!

Problem: We trained a LoRA adapter for Apple's FoundationModels framework using their TAMM (Training Adapter for Model Modification) toolkit v0.2.0 on macOS 26 beta 4. The adapter trains successfully but fails to load with: "Adapter is not compatible with the current system base model." TAMM 2.0 contains export/constants.py with: BASE_SIGNATURE = "9799725ff8e851184037110b422d891ad3b92ec1" Findings: Adapter Export Process: In export_fmadapter.py def write_metadata(...): self_dict[MetadataKeys.BASE_SIGNATURE] = BASE_SIGNATURE # Hardcoded value The Compatibility Check: - When loading an adapter, Apple's system compares the adapter's baseModelSignature with the current system model - If they don't match: compatibleAdapterNotFound error - The error doesn't reveal the expected signature Questions: - How is BASE_SIGNATURE derived from the base model? - Is it SHA-1 of base-model.pt or some other computation? - Can we compute the correct signature for beta 4? - Or do we need Apple to release TAMM v0.3.0 with updated signature?

Last year after Apple foundation models framework was introduced, I begin working on a separate test Playground project to see how to use the foundation model framework to create an AI computer in my app that only has knowledge of in universe content that comes from within my app. Now with the OS 27 updates released I’m going back to work on that. I believe I can use the on-device system foundation model framework comfortably because I don’t think there’s a lot of content in my app that the AI has to know about Do you have any advice for using instructions to tell the model to focus on only the knowledge boundaries from within my app universe or might there be new tools this year in using foundation models framework that might help me achieve the limited knowledge scope that I want the AI to recognize and respond to for my app users.

Our users speak proper nouns and domain terms (place names, product jargon) that change frequently. What’s the best practice for improving recognition accuracy: dynamic contextual strings, on-device custom language resources, periodic vocabulary sync, or something else in the current Speech APIs?

I've tried creating a Lora adapter using the example dataset, scripts as part of the adapter_training_toolkit_v26_0_0 (last available) on MacOs 26 Beta 6. import SwiftUI import FoundationModels import Playgrounds #Playground { // The absolute path to your adapter. let localURL = URL(filePath: "/Users/syl/Downloads/adapter_training_toolkit_v26_0_0/train/test-lora.fmadapter") // Initialize the adapter by using the local URL. let adapter = try SystemLanguageModel.Adapter(fileURL: localURL) // An instance of the the system language model using your adapter. let customAdapterModel = SystemLanguageModel(adapter: adapter) // Create a session and prompt the model. let session = LanguageModelSession(model: customAdapterModel) let response = try await session.respond(to: "hello") } I get Adapter assets are invalid error. I've added the entitlements Is adapter_training_toolkit_v26_0_0 up to date?

While we now know about the continued-processing.gpu entitlement for background tasks, is there a similar NPU-specific entitlement or priority flag to ensure that an on-device foundation model isn't preempted by system-level Apple Intelligence features while the app is in the background?

What’s the supported integration path for Foundation Models and Apple Intelligence from a React Native app — thin Swift native module, App Intents only, or are these features effectively Swift-first?

I've run into an issue with a small Foundation Models test with Generable. I'm getting a strange error message with this Generable. I was able to get simpler ones to work. Is this because the Generable is recursive with a property of [HTMLDiv]? The error message is: FoundationModels/SchemaAugmentor.swift:209: Fatal error: 'try!' expression unexpectedly raised an error: FoundationModels.GenerationSchema.SchemaError.undefinedReferences(schema: Optional("SafeResponse<HTMLDiv>"), references: ["HTMLDiv"], context: FoundationModels.GenerationSchema.SchemaError.Context(debugDescription: "Undefined types: [HTMLDiv]", underlyingErrors: [])) The code is: import FoundationModels import Playgrounds @Generable struct HTMLDiv { @Guide(description: "Optional named ID, useful for nicknames") var id: String? = nil @Guide(description: "Optional visible HTML text") var textContent: String? = nil @Guide(description: "Any child elements", .count(0...10)) var children: [HTMLDiv] = [] static var sample: HTMLDiv { HTMLDiv( id: "profileToolbar", children: [ HTMLDiv(textContent: "Log in"), HTMLDiv(textContent: "Sign up"), ] ) } } #Playground { do { let session = LanguageModelSession { "Your job is to generate simple HTML markup" "Here is an example response to the prompt: 'Make a profile toolbar':" HTMLDiv.sample } let response = try await session.respond( to: "Make a sign up form", generating: HTMLDiv.self ) print(response.content) } catch { print(error) } }

I'm experimenting with downloading an audio file of spoken content, using the Speech framework to transcribe it, then using FoundationModels to clean up the formatting to add paragraph breaks and such. I have this code to do that cleanup: private func cleanupText(_ text: String) async throws -> String? { print("Cleaning up text of length \(text.count)...") let session = LanguageModelSession(instructions: "The content you read is a transcription of a speech. Separate it into paragraphs by adding newlines. Do not modify the content - only add newlines.") let response = try await session.respond(to: .init(text), generating: String.self) return response.content } The content length is about 29,000 characters. And I get this error: InferenceError::inferenceFailed::Failed to run inference: Context length of 4096 was exceeded during singleExtend.. Is 4096 a reference to a max input length? Or is this a bug? This is running on an M1 iPad Air, with iPadOS 26 Seed 1.

When the @Generable is applied toward a Swift struct declared within another struct, and when said nested struct is defined as the type of one of the properties of another @Generable type, which is in turn defined as the output format of Foundation Model session, Foundation Model can stuck in a loop trying to create a infinitely nested response, until the context window limit exceeded error is triggered. I have filed feedback FB19987191 with a demo project. Is this expected behavior?

What’s Apple’s guidance for using on-device models to turn structured JSON (time series, metrics, units) into a one-line natural-language summary without inventing values?