Foundation Models

import FoundationModels

struct IntelligentView: View {
    private var model = SystemLanguageModel.default

    var body: some View {
        switch model.availability {
        case .available:
            ContentView()
        case .unavailable(.deviceNotEligible):
            UnsupportedDeviceView()
        case .unavailable(.appleIntelligenceNotEnabled):
            EnableIntelligenceView()
        case .unavailable(.modelNotReady):
            ModelDownloadingView()
        case .unavailable(let reason):
            ErrorView(reason: reason)
        }
    }
}

// Simple session
let session = LanguageModelSession()

// Session with instructions
let session = LanguageModelSession(instructions: """
    You are a helpful cooking assistant.
    Provide concise, practical advice for home cooks.
    """)

let response = try await session.respond(to: "What's a quick dinner idea?")
print(response.content)

[Role] + [Task] + [Style] + [Safety]

let instructions = """
    You are a fitness coach specializing in home workouts.
    Help users create exercise routines based on their equipment and goals.
    Keep responses under 100 words and use bullet points for exercises.
    Decline requests for medical advice and suggest consulting a doctor.
    """

let prompt = "What are three ways to reduce food waste at home?"

let prompt = "Create a weekly meal plan for a family of four, budget-friendly."

let prompt = """
    Extract the following from this email:
    - Sender name
    - Meeting date
    - Action items

    Email: \(emailContent)
    """

let prompt = "Rewrite this text to be more formal: \(casualText)"

@Generable(description: "A recipe suggestion")
struct Recipe {
    var name: String

    @Guide(description: "Cooking time in minutes", .range(5...180))
    var cookingTime: Int

    @Guide(description: "Difficulty level", .options(["Easy", "Medium", "Hard"]))
    var difficulty: String

    @Guide(description: "List of ingredients", .count(3...15))
    var ingredients: [String]

    @Guide(description: "Step-by-step instructions")
    var instructions: [String]
}

let session = LanguageModelSession(instructions: """
    You are a recipe assistant. Generate practical, home-cook friendly recipes.
    """)

let recipe = try await session.respond(
    to: "Suggest a quick pasta dish",
    generating: Recipe.self
)

print("Recipe: \(recipe.content.name)")
print("Time: \(recipe.content.cookingTime) minutes")
print("Ingredients: \(recipe.content.ingredients.joined(separator: ", "))")

@Generable(description: "A travel itinerary")
struct Itinerary {
    var destination: String

    @Guide(description: "Daily activities for the trip")
    var days: [DayPlan]
}

@Generable(description: "Activities for one day")
struct DayPlan {
    var dayNumber: Int

    @Guide(description: "Morning activity")
    var morning: String

    @Guide(description: "Afternoon activity")
    var afternoon: String

    @Guide(description: "Evening activity")
    var evening: String
}

struct WeatherTool: Tool {
    let name = "getWeather"                              // verb, short, no abbreviations
    let description = "Get current weather for a location"  // ~one sentence

    @Generable
    struct Arguments {
        @Guide(description: "City name")
        var location: String
    }

    func call(arguments: Arguments) async throws -> ToolOutput {
        let weather = await WeatherService.shared.fetch(for: arguments.location)
        return ToolOutput("Temperature: \(weather.temp)°F, Conditions: \(weather.conditions)")
    }
}

let weatherTool = WeatherTool()
let session = LanguageModelSession(
    instructions: "You help users plan outdoor activities based on weather.",
    tools: [weatherTool]
)

// Model automatically calls tool when needed
let response = try await session.respond(
    to: "Should I go hiking in San Francisco today?"
)

do {
    let response = try await session.respond(to: prompt)
} catch let error as LanguageModelSession.ToolCallError {
    print("Tool '\(error.tool.name)' failed: \(error.underlyingError)")
} catch {
    print("Generation error: \(error)")
}

@Generable
struct StoryIdea {
    var title: String

    @Guide(description: "A brief plot summary")
    var plot: String

    @Guide(description: "Main characters", .count(2...4))
    var characters: [String]
}

struct StreamingView: View {
    @State private var partial: StoryIdea.PartiallyGenerated?
    @State private var isGenerating = false

    var body: some View {
        VStack(alignment: .leading) {
            if let partial {
                if let title = partial.title {
                    Text(title).font(.headline)
                }
                if let plot = partial.plot {
                    Text(plot)
                }
                if let characters = partial.characters {
                    ForEach(characters, id: \.self) { char in
                        Text("• \(char)")
                    }
                }
            }

            Button("Generate Story Idea") {
                Task { await generateStory() }
            }
            .disabled(isGenerating)
        }
    }

    func generateStory() async {
        isGenerating = true
        defer { isGenerating = false }

        let session = LanguageModelSession()
        let stream = session.streamResponse(
            to: "Create a sci-fi story idea",
            generating: StoryIdea.self
        )

        for try await snapshot in stream {
            partial = snapshot
        }
    }
}

@Observable
final class ChatViewModel {
    private var session: LanguageModelSession?
    var messages: [ChatMessage] = []

    func startConversation() {
        session = LanguageModelSession(instructions: """
            You are a helpful assistant. Remember context from earlier in our conversation.
            """)
    }

    func send(_ message: String) async throws {
        guard let session else { return }

        messages.append(ChatMessage(role: .user, content: message))

        let response = try await session.respond(to: message)

        messages.append(ChatMessage(role: .assistant, content: response.content))
    }
}

do {
    let response = try await session.respond(to: prompt)

// ── LanguageModelError — model-level, backend-agnostic (any LanguageModel) ──
} catch LanguageModelError.contextSizeExceeded(let e) {
    // e.contextSize / e.tokenCount — recover by condensing the transcript (below)
} catch LanguageModelError.guardrailViolation {
    // Safety block: proactive features ignore silently;
    // user-initiated features explain + offer alternatives (see safety-and-guardrails.md)
} catch LanguageModelError.refusal(let e) {
    // NOT a safety block — the model declined for its own reasons.
    // e.explanation (and .explanationStream) say why. Surface it; don't retry blindly.
} catch LanguageModelError.rateLimited(let e) {
    // Server-backed models only. e.resetDate tells you when to retry, when known.
} catch LanguageModelError.unsupportedLanguageOrLocale {
    // Also pre-check SystemLanguageModel.default.supportedLanguages before prompting
} catch LanguageModelError.unsupportedCapability(let e) {
    // The backend doesn't do e.capability (tools / vision / reasoning / guided generation).
    // Capabilities are NOT uniform across models — see models-and-agents.md.
} catch LanguageModelError.timeout {

// ── LanguageModelSession.Error — you drove the session wrong ──
} catch LanguageModelSession.Error.concurrentRequests {
    // Gate submit on session.isResponding — one request per session
} catch LanguageModelSession.Error.transcriptMutationWhileResponding {
    // Mutate session.transcript only while isResponding == false

// ── SystemLanguageModel.Error — on-device assets ──
} catch SystemLanguageModel.Error.assetsUnavailable {
    // Model assets not on device — check availability first (see Quick Start)

} catch {
    print("Unexpected error: \(error)")
}

private func newSession(previousSession: LanguageModelSession) -> LanguageModelSession {
    let allEntries = previousSession.transcript.entries
    var condensed = [Transcript.Entry]()
    if let first = allEntries.first {
        condensed.append(first)                          // instructions live here
        if allEntries.count > 1, let last = allEntries.last {
            condensed.append(last)
        }
    }
    return LanguageModelSession(transcript: Transcript(entries: condensed))
}

let model = SystemLanguageModel.default
let contextSize = try await model.contextSize
print("Context size: \(contextSize)")
// 4,096 on the first-generation model; 8,192 on the rebuilt iOS 27 on-device model;
// 32,000 on PrivateCloudComputeLanguageModel (WWDC26 241) — always query, never hardcode

let model = SystemLanguageModel.default

// Measure instruction cost
let instructions = Instructions("You're a helpful assistant that generates haiku.")
let instructionTokens = try await model.tokenUsage(for: instructions)
print(instructionTokens.tokenCount) // 16

// Measure instructions + tools combined
let tools = [MoodTool()]
let combinedTokens = try await model.tokenUsage(for: instructions, tools: tools)
print(combinedTokens.tokenCount) // 79 — tools add significant overhead!

// Measure a prompt
let prompt = Prompt("Generate a haiku about Swift")
let promptTokens = try await model.tokenUsage(for: prompt)
print(promptTokens.tokenCount) // 14

// Track cumulative usage in a multi-turn session
let session = LanguageModelSession(model: model, tools: tools, instructions: instructions)
let response = try await session.respond(to: prompt)
let transcriptTokens = try await model.tokenUsage(for: session.transcript)
print(transcriptTokens.tokenCount)

extension SystemLanguageModel.TokenUsage {
    func percent(ofContextSize contextSize: Int) -> Float {
        guard contextSize > 0 else { return 0 }
        return Float(tokenCount) / Float(contextSize)
    }

    func formattedPercent(ofContextSize contextSize: Int) -> String {
        percent(ofContextSize: contextSize)
            .formatted(.percent.precision(.fractionLength(0)).rounded(rule: .down))
    }
}

// Usage
let contextSize = try await model.contextSize
print(instructionTokens.formattedPercent(ofContextSize: contextSize)) // "0%"
print(combinedTokens.formattedPercent(ofContextSize: contextSize))    // "1%"

func canFit(prompt: Prompt, in session: LanguageModelSession, model: SystemLanguageModel) async throws -> Bool {
    let contextSize = try await model.contextSize
    let transcriptTokens = try await model.tokenUsage(for: session.transcript)
    let promptTokens = try await model.tokenUsage(for: prompt)
    let totalNeeded = transcriptTokens.tokenCount + promptTokens.tokenCount
    return totalNeeded < contextSize
}

// Break content into chunks
func processLargeDocument(_ document: String) async throws -> [Summary] {
    let chunks = document.split(every: 10000) // ~2500 tokens per chunk
    var summaries: [Summary] = []

    for chunk in chunks {
        let session = LanguageModelSession() // New session per chunk
        let summary = try await session.respond(
            to: "Summarize this section: \(chunk)",
            generating: Summary.self
        )
        summaries.append(summary.content)
    }

    return summaries
}

// Deterministic output: greedy sampling, not temperature 0
let response = try await session.respond(to: prompt,
    options: GenerationOptions(samplingMode: .greedy))

// Variance dial (scale runs to 2.0 — WWDC25 301)
let lowVariance  = GenerationOptions(temperature: 0.5)
let highVariance = GenerationOptions(temperature: 2.0)

@Generable
struct EventDetails {
    var title: String
    var date: String?
    var time: String?
    var location: String?
    var attendees: [String]
}

let session = LanguageModelSession(instructions: """
    Extract event details from text. Use nil for missing information.
    """)

let event = try await session.respond(
    to: "Extract: Team lunch next Friday at noon in Conference Room B with John and Sarah",
    generating: EventDetails.self
)

let session = LanguageModelSession(instructions: """
    Summarize text concisely. Focus on key points and actionable items.
    Maximum 3 bullet points.
    """)

let response = try await session.respond(
    to: "Summarize this email: \(longEmail)"
)

@Generable
struct Classification {
    @Guide(description: "Category", .options(["Bug", "Feature", "Question", "Other"]))
    var category: String

    @Guide(description: "Priority", .options(["Low", "Medium", "High"]))
    var priority: String

    @Guide(description: "Brief summary")
    var summary: String
}

let result = try await session.respond(
    to: "Classify this support ticket: \(ticketText)",
    generating: Classification.self
)