Add AI-powered mental wellness features: Reflection Companion, Pattern Tags, Weekly Digest

Three new Foundation Models features to deepen user engagement with mental wellness:

1. AI Reflection Companion — personalized feedback after completing guided reflections,
   referencing the user's actual words with personality-pack-adapted tone
2. Mood Pattern Tags — auto-extracts theme tags (work, family, stress, etc.) from notes
   and reflections, displayed as colored pills on entries
3. Weekly Emotional Digest — BGTask-scheduled Sunday digest with headline, summary,
   highlight, and intention; shown as card in Insights tab with notification

All features: on-device (zero cost), premium-gated, iOS 26+ with graceful degradation.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Shared/Services/FoundationModelsReflectionService.swift

@@ -0,0 +1,128 @@
+//
+//  FoundationModelsReflectionService.swift
+//  Reflect
+//
+//  Generates personalized AI feedback after a user completes a guided reflection.
+//
+
+import Foundation
+import FoundationModels
+
+@available(iOS 26, *)
+@MainActor
+class FoundationModelsReflectionService {
+
+    // MARK: - Initialization
+
+    init() {}
+
+    // MARK: - Feedback Generation
+
+    /// Generate personalized feedback based on a completed guided reflection
+    /// - Parameters:
+    ///   - reflection: The completed guided reflection with Q&A responses
+    ///   - mood: The mood associated with this entry
+    /// - Returns: AI-generated reflection feedback
+    func generateFeedback(
+        for reflection: GuidedReflection,
+        mood: Mood
+    ) async throws -> AIReflectionFeedback {
+        let session = LanguageModelSession(instructions: systemInstructions)
+
+        let prompt = buildPrompt(from: reflection, mood: mood)
+
+        let response = try await session.respond(
+            to: prompt,
+            generating: AIReflectionFeedback.self
+        )
+
+        return response.content
+    }
+
+    // MARK: - System Instructions
+
+    private var systemInstructions: String {
+        let personalityPack = UserDefaultsStore.personalityPackable()
+
+        switch personalityPack {
+        case .Default:
+            return defaultInstructions
+        case .MotivationalCoach:
+            return coachInstructions
+        case .ZenMaster:
+            return zenInstructions
+        case .BestFriend:
+            return bestFriendInstructions
+        case .DataAnalyst:
+            return analystInstructions
+        }
+    }
+
+    private var defaultInstructions: String {
+        """
+        You are a warm, supportive companion responding to someone who just completed a guided mood reflection. \
+        Validate their effort, reflect their own words back to them, and offer a gentle takeaway. \
+        Be specific — reference what they actually wrote. Keep each field to 1 sentence. \
+        SF Symbols: sparkles, heart.fill, star.fill, sun.max.fill, leaf.fill
+        """
+    }
+
+    private var coachInstructions: String {
+        """
+        You are a HIGH ENERGY motivational coach responding to someone who just completed a guided mood reflection! \
+        Celebrate their self-awareness, pump them up about the growth they showed, and give them a power move for tomorrow. \
+        Reference what they actually wrote. Keep each field to 1 sentence. Use exclamations! \
+        SF Symbols: trophy.fill, flame.fill, bolt.fill, star.fill, figure.run
+        """
+    }
+
+    private var zenInstructions: String {
+        """
+        You are a calm, mindful guide responding to someone who just completed a guided mood reflection. \
+        Acknowledge their practice of self-awareness with gentle wisdom. Use nature metaphors. \
+        Reference what they actually wrote. Keep each field to 1 sentence. Speak with serene clarity. \
+        SF Symbols: leaf.fill, moon.fill, drop.fill, sunrise.fill, wind
+        """
+    }
+
+    private var bestFriendInstructions: String {
+        """
+        You are their supportive best friend responding after they completed a guided mood reflection. \
+        Be warm, casual, and validating. Use conversational tone. \
+        Reference what they actually wrote. Keep each field to 1 sentence. \
+        SF Symbols: heart.fill, hand.thumbsup.fill, sparkles, star.fill, face.smiling.fill
+        """
+    }
+
+    private var analystInstructions: String {
+        """
+        You are a clinical data analyst providing feedback on a completed mood reflection. \
+        Note the cognitive patterns observed, the technique application quality, and a data-informed recommendation. \
+        Reference what they actually wrote. Keep each field to 1 sentence. Be objective but encouraging. \
+        SF Symbols: chart.bar.fill, brain.head.profile, doc.text.magnifyingglass, chart.line.uptrend.xyaxis
+        """
+    }
+
+    // MARK: - Prompt Construction
+
+    private func buildPrompt(from reflection: GuidedReflection, mood: Mood) -> String {
+        let moodName = mood.widgetDisplayName
+        let technique = reflection.moodCategory.techniqueName
+
+        let qaPairs = reflection.responses
+            .filter { !$0.answer.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty }
+            .map { response in
+                let chips = response.selectedChips.isEmpty ? "" : " [themes: \(response.selectedChips.joined(separator: ", "))]"
+                return "Q: \(response.question)\nA: \(response.answer)\(chips)"
+            }
+            .joined(separator: "\n\n")
+
+        return """
+        The user logged their mood as "\(moodName)" and completed a \(technique) reflection:
+
+        \(qaPairs)
+
+        Respond with personalized feedback that references their specific answers.
+        """
+    }
+}