feat(ai): implement agent-redesign plan with enhanced AI travel features

Phase 1 - Configuration Infrastructure (WS1):
- Add instance-level AI env vars (VOYAGE_AI_PROVIDER, VOYAGE_AI_MODEL, VOYAGE_AI_API_KEY)
- Implement fallback chain: user key → instance key → error
- Add UserAISettings model for per-user provider/model preferences
- Enhance provider catalog with instance_configured and user_configured flags
- Optimize provider catalog to avoid N+1 queries

Phase 1 - User Preference Learning (WS2):
- Add Travel Preferences tab to Settings page
- Improve preference formatting in system prompt with emoji headers
- Add multi-user preference aggregation for shared collections

Phase 2 - Day-Level Suggestions Modal (WS3):
- Create ItinerarySuggestionModal with 3-step flow (category → filters → results)
- Add AI suggestions button to itinerary Add dropdown
- Support restaurant, activity, event, and lodging categories
- Backend endpoint POST /api/chat/suggestions/day/ with context-aware prompts

Phase 3 - Collection-Level Chat Improvements (WS4):
- Inject collection context (destination, dates) into chat system prompt
- Add quick action buttons for common queries
- Add 'Add to itinerary' button on search_places results
- Update chat UI with travel-themed branding and improved tool result cards

Phase 3 - Web Search Capability (WS5):
- Add web_search agent tool using DuckDuckGo
- Support location_context parameter for biased results
- Handle rate limiting gracefully

Phase 4 - Extensibility Architecture (WS6):
- Implement decorator-based @agent_tool registry
- Convert existing tools to use decorators
- Add GET /api/chat/capabilities/ endpoint for tool discovery
- Refactor execute_tool() to use registry pattern

backend/server/integrations/views/__init__.py

@@ -4,3 +4,4 @@ from .strava_view import StravaIntegrationView
 from .wanderer_view import WandererIntegrationViewSet
 from .user_api_key_view import UserAPIKeyViewSet
 from .recommendation_profile_view import UserRecommendationPreferenceProfileViewSet
+from .ai_settings_view import UserAISettingsViewSet

backend/server/integrations/views/ai_settings_view.py

@@ -0,0 +1,39 @@
+from rest_framework import status, viewsets
+from rest_framework.permissions import IsAuthenticated
+from rest_framework.response import Response
+
+from integrations.models import UserAISettings
+from integrations.serializers import UserAISettingsSerializer
+
+
+class UserAISettingsViewSet(viewsets.ModelViewSet):
+    serializer_class = UserAISettingsSerializer
+    permission_classes = [IsAuthenticated]
+
+    def get_queryset(self):
+        return UserAISettings.objects.filter(user=self.request.user)
+
+    def list(self, request, *args, **kwargs):
+        instance = self.get_queryset().first()
+        if not instance:
+            return Response([], status=status.HTTP_200_OK)
+        serializer = self.get_serializer(instance)
+        return Response([serializer.data], status=status.HTTP_200_OK)
+
+    def perform_create(self, serializer):
+        existing = UserAISettings.objects.filter(user=self.request.user).first()
+        if existing:
+            for field, value in serializer.validated_data.items():
+                setattr(existing, field, value)
+            existing.save()
+            self._upserted_instance = existing
+            return
+
+        self._upserted_instance = serializer.save(user=self.request.user)
+
+    def create(self, request, *args, **kwargs):
+        serializer = self.get_serializer(data=request.data)
+        serializer.is_valid(raise_exception=True)
+        self.perform_create(serializer)
+        output = self.get_serializer(self._upserted_instance)
+        return Response(output.data, status=status.HTTP_200_OK)