Implement ML Anomaly Detection

Introduce statistical anomaly detection for metrics via edge function, hooks, and UI components. Adds detection algorithms (z-score, moving average, rate of change), anomaly storage, auto-alerts, and dashboard rendering of detected anomalies with run-once trigger and scheduling guidance.

src/hooks/admin/useAnomalyDetection.ts

@@ -0,0 +1,101 @@
+import { useQuery, useMutation, useQueryClient } from '@tanstack/react-query';
+import { supabase } from '@/lib/supabaseClient';
+import { queryKeys } from '@/lib/queryKeys';
+import { toast } from 'sonner';
+
+export interface AnomalyDetection {
+  id: string;
+  metric_name: string;
+  metric_category: string;
+  anomaly_type: 'spike' | 'drop' | 'trend_change' | 'outlier' | 'pattern_break';
+  severity: 'critical' | 'high' | 'medium' | 'low';
+  baseline_value: number;
+  anomaly_value: number;
+  deviation_score: number;
+  confidence_score: number;
+  detection_algorithm: string;
+  time_window_start: string;
+  time_window_end: string;
+  detected_at: string;
+  alert_created: boolean;
+  alert_id?: string;
+  alert_message?: string;
+  alert_resolved_at?: string;
+}
+
+export function useAnomalyDetections() {
+  return useQuery({
+    queryKey: queryKeys.monitoring.anomalyDetections(),
+    queryFn: async () => {
+      const { data, error } = await supabase
+        .from('recent_anomalies_view')
+        .select('*')
+        .order('detected_at', { ascending: false })
+        .limit(50);
+
+      if (error) throw error;
+      return (data || []) as AnomalyDetection[];
+    },
+    staleTime: 30000,
+    refetchInterval: 60000,
+  });
+}
+
+export function useRunAnomalyDetection() {
+  const queryClient = useQueryClient();
+
+  return useMutation({
+    mutationFn: async () => {
+      const { data, error } = await supabase.functions.invoke('detect-anomalies', {
+        method: 'POST',
+      });
+
+      if (error) throw error;
+      return data;
+    },
+    onSuccess: (data) => {
+      queryClient.invalidateQueries({ queryKey: queryKeys.monitoring.anomalyDetections() });
+      queryClient.invalidateQueries({ queryKey: queryKeys.monitoring.groupedAlerts() });
+      
+      if (data.anomalies_detected > 0) {
+        toast.success(`Detected ${data.anomalies_detected} anomalies`);
+      } else {
+        toast.info('No anomalies detected');
+      }
+    },
+    onError: (error) => {
+      console.error('Failed to run anomaly detection:', error);
+      toast.error('Failed to run anomaly detection');
+    },
+  });
+}
+
+export function useRecordMetric() {
+  return useMutation({
+    mutationFn: async ({
+      metricName,
+      metricCategory,
+      metricValue,
+      metadata,
+    }: {
+      metricName: string;
+      metricCategory: string;
+      metricValue: number;
+      metadata?: any;
+    }) => {
+      const { error } = await supabase
+        .from('metric_time_series')
+        .insert({
+          metric_name: metricName,
+          metric_category: metricCategory,
+          metric_value: metricValue,
+          metadata,
+        });
+
+      if (error) throw error;
+    },
+    onError: (error) => {
+      console.error('Failed to record metric:', error);
+    },
+  });
+}