@Merano, thank you for posting this issue and detailing your steps. I receive a very similar error: 'InferenceError::inferenceFailed::Error Domain=com.apple.UnifiedAssetFramework Code=5000 "There are no underlying assets (neither atomic instance nor asset roots) for consistency token for asset set com.apple.modelcatalog" UserInfo={NSLocalizedFailureReason=There are no underlying assets (neither atomic instance nor asset roots) for consistency token for asset set com.apple.modelcatalog}' This is while running: macOS Sequoia 15.5 Xcode 16 beta iOS Simulator - iPhone 16 iOS 26.0 Per your experiences, I'll try a real device rather than updating to macOS 26.

@DTS Engineer, thanks for actively communicating with us on this. I was able to resolve the issue after updating my machine to macOS Tahoe Version 26.0 Beta (25A5279m)

@Apple Designer, thanks for mentioning Tool. I was originally including text chunks in the instructions but using this approach returns better results. I've been using objectbox as an on-device vector db.

Hi, I wanted to follow up on this. I'm now on Beta 4 for Xcode and macOS but it's still the same issue. Note that I am trying a RAG approach via Tool Calling as mentioned here: // https://developer.apple.com/videos/play/wwdc2025/301/?time=124 // https://developer.apple.com/documentation/foundationmodels/expanding-generation-with-tool-calling var session: LanguageModelSession session = LanguageModelSession( tools: [RetrievalTool(retrieval)], instructions: instructions ) // https://developer.apple.com/documentation/foundationmodels/generationoptions let response = try await session.respond( to: prompt, options: GenerationOptions.init(maximumResponseTokens: 500) ) tools can return a somewhat lengthy document relevant to the prompt but even though the instructions and maximumResponseTokens specifies to return a brief response, response ends up being around the same length of the tools