If a developer is eligible for Private Cloud Compute and then crosses the threshold, what happens to PCC calls? Is there a paid program for PCC that you fall back on or does a developer need to already have built into their app another model ready in the wings to take over once that threshold is reached?

When using Dynamic Profiles to switch between the on-device model and Private Cloud Compute mid-session, how is the context window reconciled — if I build up context on PCC (larger window) and then route a turn back to the on-device model, what happens to the entries that exceed the on-device window? — Divya Ravi, Senior iOS Engineer

As a hobbyist developer, I develop apps mostly for my own use, and want to try using private cloud compute. As per https://developer.apple.com/private-cloud-compute I have applied for the App Store Small Business Program. Am I eligible for this and for pcc access if I have no apps in the App Store? I do have one in Test Flight.

The new standalone Siri app keeps conversation history synced via iCloud across iPhone, iPad, and Mac. Can third-party content, results, or an app's agent surface appear inside the Siri app (e.g., as referenced sources or follow-up actions), and can the user deep-link from a Siri-app result back into the originating app with state intact? Is any conversation context from the Siri app exposed to a developer's intent when an action is invoked, so the app can act with the relevant context, and what are the privacy boundaries on that? When the same action is invoked from different surfaces (in-app, system Siri, the Siri app) and across synced devices, how should developers reason about execution location and idempotency to avoid duplicate side effects?

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?

We run a conversational assistant where answers depend on live API data, not just static knowledge. What is Apple’s recommended split between on-device Foundation Models (intent, routing, summarization, privacy-sensitive context) and server-side tool execution? Is there an official pattern for a local planner with a remote executor?

Reports indicate PCC now extends to NVIDIA hardware in Google Cloud datacenters, and the flagship cloud model is refined using Gemini outputs. Now that PCC spans infrastructure outside Apple's own datacenters, what attestation or verifiable transparency is available to developers and users about where a given request was processed, and do the original "data unreachable even by Apple" guarantees hold unchanged across all hardware vendors? For apps with enterprise or regulated users, is there documented data residency behavior for PCC and for third-party model routing, and any contractual/compliance posture (e.g., regional pinning) developers can rely on? Given the EU and China availability gaps at launch, what is the recommended graceful-degradation path for apps that must function in those regions — fall back to on-device only, to a developer-supplied provider, or disable AI features? Does routing to a third-party cloud provider through the framework carry the same PCC privacy guarantees, or are those guarantees specific to Apple's own cloud models?

Entity schemas add app content to the Spotlight semantic index so Siri can find information inside apps. Is the semantic index built and stored entirely on-device, or is any indexed entity content transmitted to Apple or to Private Cloud Compute for embedding/retrieval? How should developers index content that does not live on the device — data that resides on a remote server or is fetched on demand? Is there a provider/just-in-time pattern, or must entities be materialized locally first? What is the freshness/update latency of the index when entities change frequently, and what are the practical limits on entity count and update rate before indexing is throttled? What controls exist to exclude sensitive entities from the semantic index or from Siri's personal-context reach, on a per-entity or per-field basis? How is indexed app content scoped per user/account on shared or multi-account devices, and is it cleared on sign-out?

In the WWDC26 AI Group Lab, it was mentioned as a 'spoiler alert' that the 'weight list applies only to Siri' and not to the Private Cloud Compute (PCC) language model . Could you clarify if there is a technical path for a developer’s custom adapter—running via the Language Model Protocol—to ever be added to this weight list to handle system-originated Siri requests?

App Intents now connect app content and actions to Apple Intelligence, and Siri AI can take action directly inside third-party apps without fixed trigger phrases. Can an app expose a single conversational/agent-style entry point to Siri AI, or must all capabilities be modeled as discrete intents? If discrete, how does Siri AI chain multiple intents to fulfill a compound natural-language request? What is the supported pattern for long-running or asynchronous intents — actions that acknowledge immediately but complete and return a result seconds or minutes later? Is there a progress/continuation/callback model? How are an intent's results rendered — inline in the Siri app, via a snippet/App Intent UI, or by deep-linking into the app? What control do developers have over that presentation? For intents whose parameters are ambiguous, what disambiguation and follow-up affordances does Siri AI provide, and can developers supply candidate resolutions dynamically at runtime? Is there an eligibility or review process for apps to participate in systemwide Siri AI actions, beyond simply adopting App Intents?

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.

Hello everyone, I’m working on a project to automate software controls inside non-standard macOS applications—specifically custom-drawn audio plugins (like the Roland TR-909 VST). The Challenge: These VST interfaces do not expose their buttons, knobs, or dials via the standard macOS Accessibility tree (NSAccessibility / event taps). Because they are custom-rendered, standard automation tools are blind to them. My Current Hybrid Approach: I am combining two of Apple's local machine learning technologies to solve this without sending data to the cloud: Step 1: Text-Based Layout Mapping (Vision Framework) I capture a screenshot of the targeted window using Quartz Window Services and run a local VNRecognizeTextRequest to extract coordinates for all text labels. This works exceptionally well for text buttons like "OPTION" or "ABOUT". Step 2: Contextual & Non-Text Element Interpretation (FoundationModels Framework) For controls that lack text labels (such as blank step sequencer buttons, parameter knobs, or toggle light states), I pass the screenshot as an Attachment into the new local LanguageModelSession. I ask the model to ground coordinates relative to the text landmarks mapped in Step 1. Here is a simplified snippet of how I am feeding the visual context into the local model: import Foundation import FoundationModels import Cocoa func analyzePluginInterface(cgImage: CGImage) async { guard SystemLanguageModel.default.isAvailable else { print("Local model not downloaded or available.") return } let instructions = """ You are a screen-aware assistant. Your job is to locate GUI controls on a custom 1024x802 VST window. """ let session = LanguageModelSession(instructions: instructions) do { let response = try await session.respond { "Look at this screenshot of the VST window." Attachment(cgImage) "Locate the blank step-sequencer buttons located below the instrument channel labels." "What are the center coordinates (X, Y) for the first active step?" } print("Model Grounding Output: \(response.content)") } catch { print("Inference failed: \(error)") } } My Questions for the Community: Performance & Latency: The local LanguageModelSession.respond call takes several seconds to run on device. For real-time DAW automation, this is a bottleneck. Has anyone experimented with using a custom LoRA adapter or a smaller model profile to speed up spatial coordinate inference? Coordinate Stability: Multimodal models can sometimes hallucinate coordinates (bounding box values). What strategies are you using to constrain the model output to precise pixel boundaries on varying display scaling configurations (Retina vs non-Retina)? Alternative Solutions: Are there newer on-device vision APIs (perhaps in CoreML or Vision) that are better suited for bounding-box grounding of abstract graphics (like dials/knobs) than a general language model session? Would love to hear how others are approaching screen-aware GUI interpretation with these new frameworks! Thanks!

Thank the elders for their knowledge and teachings. Is there a consensus regarding Siri’s utilization for the Agentic and/ or Copilot version control systems. For example the Copilot within, Edge Browser, the stand alone App, the Xbox copilot, and the M365 copilot App. Does the team have a standardized approach for the’start’ feature that can be prompted whilst utilizing Copilot’s build and generate capabilities? Thank you all and best regards.

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!

Using SpotlightSearchTool with a custom LanguageModel backend (Apple’s ChatCompletionsLanguageModel from foundation-models-utilities, pointed at an OpenAI-compatible server), every tool call fails with ToolCallError → "Failed to parse generated content." The model follows the tool’s documented "Call format" and emits { root, modelComposition, … }. But the generated parameters schema (FullArguments) requires { "query": { "type": "search", "value": { root, modelComposition, … } } }. Query is a QueryType union and a search must be wrapped in DiscriminatedSearch. Wrapping the args manually makes it parse and search correctly. So the description omits the query + type:"search" envelope the schema demands, which makes the tool uninvokable by any model that follows the documentation (it presumably works only with the on-device model trained on the real format). Is this a known issue / intended? Anyone gotten SpotlightSearchTool working with a non-Apple model? Secondary: CoreSpotlightSource.fetchAttributes seems to have no effect on returned attributes. kMDItemDescription only comes back when the in-query fetchAttributes requests it. Bug or expected?

theres a MLX, a MLX LM and a MLX LM Server mentioned. Is there a Bootstrap GitHub repo out there that can be used to directly, and quickly, set up an example of this, without the hassle of setting up, kind of like a bootstrap for "us mere mortals"? And what is the feasibility of using these on a M3 Pro with 18Gb of memory? - can these be bounced between a local M3 Pro and a Tailscale-linked M2 Pro with 36Gb memory? Do both need to be on macOS27 for it to work?

I created a tiny sample: provided a session with a tiny tool to tell the date and time to the model. Asked the model to stream response to "What time is it" and just get this error: The operation couldn’t be completed. (FoundationModels.LanguageModelError error -1.) There is no relevant output on Xcode console. And profiling with the new Foundation Models instrument brings zero more insight into the issue. I know it could be many things, but it there may be more information the tools could surface in debug?

The LanguageModelSession.GenerationErrors seems to be deprecated in favor of LanguageModelError for the most part. Now... when iterating through the ResponseStream<String> of a LanguageModelSession.streamResponse(to:options:), with a good old for await, the async iterator .next() can throws. Leaving aside that it is not very conspicuous at the call site it will throw... in the do/catch, the error thrown does not see to be able to be pattern matched to the new LanguageModelError with something like catch let error as LanguageModelError. It was able to patten match the GenerationErrors before just fine, so may be an oversight/bug?