fix: Instagram data collection pipeline — handle normalization + DB persistence

- Add normalizeInstagramHandle() utility (Edge + browser) to strip URLs, @ prefixes
- generate-report: normalize handles before saving, persist socialHandles in report JSONB
- enrich-channels: normalize Instagram handle before Apify call (defense in depth)
- useReport: recover socialHandles + channelEnrichment from DB on direct URL access
- ReportPage: skip redundant enrichment when data already exists in DB

Fixes: Instagram enrichment failing due to URL-format handles passed to Apify

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

src/hooks/useReport.ts

@@ -2,12 +2,17 @@ import { useState, useEffect } from 'react';
 import { useLocation } from 'react-router';
 import type { MarketingReport } from '../types/report';
 import { fetchReportById } from '../lib/supabase';
-import { transformApiReport } from '../lib/transformReport';
+import { transformApiReport, mergeEnrichment, type EnrichmentData } from '../lib/transformReport';
+import { normalizeInstagramHandle } from '../lib/normalizeHandles';
 
 interface UseReportResult {
   data: MarketingReport | null;
   isLoading: boolean;
   error: string | null;
+  /** True if channelEnrichment was already in the DB — no need to re-enrich */
+  isEnriched: boolean;
+  /** Normalized social handles recovered from DB or API metadata */
+  socialHandles: Record<string, string | null> | null;
 }
 
 interface LocationState {
@@ -27,6 +32,8 @@ export function useReport(id: string | undefined): UseReportResult {
   const [data, setData] = useState<MarketingReport | null>(null);
   const [isLoading, setIsLoading] = useState(true);
   const [error, setError] = useState<string | null>(null);
+  const [isEnriched, setIsEnriched] = useState(false);
+  const [socialHandles, setSocialHandles] = useState<Record<string, string | null> | null>(null);
   const location = useLocation();
 
   useEffect(() => {
@@ -42,6 +49,8 @@ export function useReport(id: string | undefined): UseReportResult {
           state.metadata,
         );
         setData(transformed);
+        setSocialHandles(state.metadata.socialHandles || null);
+        setIsEnriched(false);
         setIsLoading(false);
       } catch (err) {
         setError(err instanceof Error ? err.message : 'Failed to parse report data');
@@ -54,16 +63,45 @@ export function useReport(id: string | undefined): UseReportResult {
     if (id) {
       fetchReportById(id)
         .then((row) => {
+          const reportJson = row.report as Record<string, unknown>;
+          const scrapeData = row.scrape_data as Record<string, unknown> | undefined;
+
           const transformed = transformApiReport(
             row.id,
-            row.report,
+            reportJson,
             {
               url: row.url,
               clinicName: row.clinic_name || '',
               generatedAt: row.created_at,
             },
           );
+
+          // Recover social handles: report.socialHandles > scrape_data.clinic.socialMedia
+          let handles = (reportJson.socialHandles as Record<string, string | null>) || null;
+          if (!handles && scrapeData) {
+            const clinic = scrapeData.clinic as Record<string, unknown> | undefined;
+            const socialMedia = clinic?.socialMedia as Record<string, string> | undefined;
+            if (socialMedia) {
+              handles = {
+                instagram: normalizeInstagramHandle(socialMedia.instagram),
+                youtube: socialMedia.youtube || null,
+                facebook: socialMedia.facebook || null,
+                blog: socialMedia.blog || null,
+              };
+            }
+          }
+          setSocialHandles(handles);
+
+          // If channelEnrichment already exists in DB, merge it immediately
+          const enrichment = reportJson.channelEnrichment as EnrichmentData | undefined;
+          if (enrichment) {
+            const merged = mergeEnrichment(transformed, enrichment);
+            setData(merged);
+            setIsEnriched(true);
+          } else {
             setData(transformed);
+            setIsEnriched(false);
+          }
         })
         .catch((err) => {
           setError(err instanceof Error ? err.message : 'Failed to fetch report');
@@ -77,5 +115,5 @@ export function useReport(id: string | undefined): UseReportResult {
     setIsLoading(false);
   }, [id, location.state]);
 
-  return { data, isLoading, error };
+  return { data, isLoading, error, isEnriched, socialHandles };
 }

src/lib/normalizeHandles.ts

@@ -0,0 +1,32 @@
+/**
+ * Normalize an Instagram handle from various input formats to a pure username.
+ * Browser-side copy of supabase/functions/_shared/normalizeHandles.ts
+ */
+export function normalizeInstagramHandle(
+  raw: string | null | undefined,
+): string | null {
+  if (!raw || typeof raw !== 'string') return null;
+
+  let handle = raw.trim();
+  if (!handle) return null;
+
+  if (handle.includes('instagram.com')) {
+    try {
+      const urlStr = handle.startsWith('http') ? handle : `https://${handle}`;
+      const url = new URL(urlStr);
+      const segments = url.pathname.split('/').filter(Boolean);
+      handle = segments[0] || '';
+    } catch {
+      const match = handle.match(/instagram\.com\/([^/?#]+)/);
+      handle = match?.[1] || '';
+    }
+  }
+
+  if (handle.startsWith('@')) {
+    handle = handle.slice(1);
+  }
+
+  handle = handle.replace(/\/+$/, '');
+
+  return handle || null;
+}

src/pages/ReportPage.tsx

@@ -34,24 +34,32 @@ const REPORT_SECTIONS = [
 export default function ReportPage() {
   const { id } = useParams<{ id: string }>();
   const location = useLocation();
-  const { data: baseData, isLoading, error } = useReport(id);
+  const {
+    data: baseData,
+    isLoading,
+    error,
+    isEnriched,
+    socialHandles: dbSocialHandles,
+  } = useReport(id);
 
-  // Extract enrichment params from location state (socialHandles from API) or base data
+  // Build enrichment params — skip if already enriched (data from DB)
   const enrichmentParams = useMemo(() => {
-    if (!baseData) return null;
+    if (!baseData || isEnriched) return null;
 
+    // Priority: location.state socialHandles > DB socialHandles > transformed data
     const state = location.state as Record<string, unknown> | undefined;
     const metadata = state?.metadata as Record<string, unknown> | undefined;
-    const socialHandles = metadata?.socialHandles as Record<string, string | null> | undefined;
+    const stateSocialHandles = metadata?.socialHandles as Record<string, string | null> | undefined;
+
+    const handles = stateSocialHandles || dbSocialHandles;
 
-    // Priority: API socialHandles > transformed data > undefined
     const igHandle =
-      socialHandles?.instagram ||
+      handles?.instagram ||
       baseData.instagramAudit?.accounts?.[0]?.handle ||
       undefined;
 
     const ytHandle =
-      socialHandles?.youtube ||
+      handles?.youtube ||
       baseData.youtubeAudit?.handle ||
       undefined;
 
@@ -62,7 +70,7 @@ export default function ReportPage() {
       youtubeChannelId: ytHandle || undefined,
       address: baseData.clinicSnapshot.location || undefined,
     };
-  }, [baseData, location.state]);
+  }, [baseData, isEnriched, dbSocialHandles, location.state]);
 
   const { status: enrichStatus, enrichedReport } = useEnrichment(baseData, enrichmentParams);
 

supabase/functions/_shared/normalizeHandles.ts

@@ -0,0 +1,48 @@
+/**
+ * Normalize an Instagram handle from various input formats to a pure username.
+ *
+ * Handles these formats:
+ *  - "https://www.instagram.com/banobagi_ps/"      → "banobagi_ps"
+ *  - "https://instagram.com/banobagi_ps?hl=en"     → "banobagi_ps"
+ *  - "http://instagram.com/banobagi_ps"             → "banobagi_ps"
+ *  - "instagram.com/banobagi_ps"                    → "banobagi_ps"
+ *  - "@banobagi_ps"                                 → "banobagi_ps"
+ *  - "banobagi_ps"                                  → "banobagi_ps"
+ *  - null / undefined / ""                          → null
+ */
+export function normalizeInstagramHandle(
+  raw: string | null | undefined,
+): string | null {
+  if (!raw || typeof raw !== "string") return null;
+
+  let handle = raw.trim();
+  if (!handle) return null;
+
+  // If it contains "instagram.com", extract the first path segment
+  if (handle.includes("instagram.com")) {
+    try {
+      // Add protocol if missing so URL constructor works
+      const urlStr = handle.startsWith("http")
+        ? handle
+        : `https://${handle}`;
+      const url = new URL(urlStr);
+      // pathname is like "/banobagi_ps/" or "/banobagi_ps"
+      const segments = url.pathname.split("/").filter(Boolean);
+      handle = segments[0] || "";
+    } catch {
+      // URL parsing failed — try regex fallback
+      const match = handle.match(/instagram\.com\/([^/?#]+)/);
+      handle = match?.[1] || "";
+    }
+  }
+
+  // Strip leading @
+  if (handle.startsWith("@")) {
+    handle = handle.slice(1);
+  }
+
+  // Strip trailing slash
+  handle = handle.replace(/\/+$/, "");
+
+  return handle || null;
+}

supabase/functions/enrich-channels/index.ts

@@ -1,5 +1,6 @@
 import "@supabase/functions-js/edge-runtime.d.ts";
 import { createClient } from "https://esm.sh/@supabase/supabase-js@2";
+import { normalizeInstagramHandle } from "../_shared/normalizeHandles.ts";
 
 const corsHeaders = {
   "Access-Control-Allow-Origin": "*",
@@ -58,12 +59,13 @@ Deno.serve(async (req) => {
     const tasks = [];
 
     // 1. Instagram Profile
-    if (instagramHandle) {
+    const cleanIgHandle = normalizeInstagramHandle(instagramHandle);
+    if (cleanIgHandle) {
       tasks.push(
         (async () => {
           const items = await runApifyActor(
             "apify~instagram-profile-scraper",
-            { usernames: [instagramHandle], resultsLimit: 12 },
+            { usernames: [cleanIgHandle], resultsLimit: 12 },
             APIFY_TOKEN
           );
           const profile = (items as Record<string, unknown>[])[0];

supabase/functions/generate-report/index.ts

@@ -1,5 +1,6 @@
 import "@supabase/functions-js/edge-runtime.d.ts";
 import { createClient } from "https://esm.sh/@supabase/supabase-js@2";
+import { normalizeInstagramHandle } from "../_shared/normalizeHandles.ts";
 
 const corsHeaders = {
   "Access-Control-Allow-Origin": "*",
@@ -153,6 +154,18 @@ ${JSON.stringify(analyzeResult.data?.analysis || {}, null, 2)}
       report = { raw: reportText, parseError: true };
     }
 
+    // Normalize social handles from scrape data
+    const socialMedia = clinic.socialMedia || {};
+    const normalizedHandles = {
+      instagram: normalizeInstagramHandle(socialMedia.instagram),
+      youtube: socialMedia.youtube || null,
+      facebook: socialMedia.facebook || null,
+      blog: socialMedia.blog || null,
+    };
+
+    // Embed normalized handles in report for DB persistence
+    report.socialHandles = normalizedHandles;
+
     // Save to Supabase
     const supabase = createClient(supabaseUrl, supabaseKey);
     const { data: saved, error: saveError } = await supabase
@@ -167,9 +180,6 @@ ${JSON.stringify(analyzeResult.data?.analysis || {}, null, 2)}
       .select("id")
       .single();
 
-    // Extract social handles from scrape data for frontend enrichment
-    const socialMedia = clinic.socialMedia || {};
-
     return new Response(
       JSON.stringify({
         success: true,
@@ -184,12 +194,7 @@ ${JSON.stringify(analyzeResult.data?.analysis || {}, null, 2)}
             marketAnalysis: analyzeResult.success,
             aiGeneration: !report.parseError,
           },
-          socialHandles: {
-            instagram: socialMedia.instagram || null,
-            youtube: socialMedia.youtube || null,
-            facebook: socialMedia.facebook || null,
-            blog: socialMedia.blog || null,
-          },
+          socialHandles: normalizedHandles,
           address,
           services,
         },