Add mood-specific selectable chip answers to guided reflection flow

Reduces friction in the guided reflection by offering predefined tappable
chip answers tailored to each mood category's therapeutic framework:
- Positive (Behavioral Activation): savoring emotions + reinforcing actions
- Neutral (ACT Cognitive Defusion): ambivalent feelings + defusion reframes + values
- Negative (CBT Thought Record): automatic negative thoughts + compassionate reframes + grounding actions

Chips appear between the question and text editor. Tapping toggles selection
and auto-fills the text field. "More" expander reveals additional options.
Free text always remains available alongside chips.

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

Shared/Views/GuidedReflectionView.swift

@@ -185,6 +185,15 @@ struct GuidedReflectionView: View {
                     .accessibilityIdentifier(AccessibilityID.GuidedReflection.questionLabel(step: currentStep))
                     .id("question_\(currentStep)")
 
+                if let chips = QuestionChips.chips(for: reflection.moodCategory, questionIndex: currentStep) {
+                    ChipSelectionView(
+                        chips: chips,
+                        accentColor: moodTint.color(forMood: entry.mood),
+                        selectedChips: $reflection.responses[currentStep].selectedChips,
+                        textAnswer: $reflection.responses[currentStep].answer
+                    )
+                }
+
                 TextEditor(text: $reflection.responses[currentStep].answer)
                     .focused($isTextFieldFocused)
                     .frame(minHeight: 120, maxHeight: 200)