fix(detection): crawl websites to find Dutchie menus and retry missing platform IDs

CLAUDE.md

@@ -136,6 +136,9 @@
 20) **Never delete or overwrite historical data**
     - Do not delete products/snapshots or overwrite historical records. Always append snapshots for changes (price/stock/qty), and mark missing_from_feed instead of removing records. Historical data must remain intact for analytics.
 
+21) **Deployment via CI/CD only**
+    - Test locally, commit clean changes, and let CI/CD build and deploy to Kubernetes at code.cannabrands.app. Do NOT manually build/push images or tweak prod pods. Deploy backend first, smoke-test APIs, then frontend; roll back via CI/CD if needed.
+
 18) **Per-location cName and platform_dispensary_id resolution**
     - For each dispensary, menu_url and cName must be valid for that exact location; no hardcoded defaults and no sharing platform_dispensary_id across locations.
     - Derive cName from menu_url per store: `/embedded-menu/<cName>` or `/dispensary/<cName>`.

backend/src/dutchie-az/services/menu-detection.ts

@@ -148,6 +148,7 @@ export interface WebsiteCrawlResult {
   provider: MenuProvider;
   foundLinks: string[];
   crawledPages: string[];
+  platformDispensaryId?: string | null;
   error?: string;
 }
 
@@ -293,6 +294,30 @@ export async function crawlWebsiteForMenuLinks(websiteUrl: string): Promise<Webs
 
   result.foundLinks = homepageLinks;
 
+  // Step 2: Try to extract reactEnv.dispensaryId (embedded Dutchie menu) from homepage HTML
+  try {
+    const resp = await fetch(homepage, {
+      headers: {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
+      },
+      redirect: 'follow',
+    });
+    if (resp.ok) {
+      const html = await resp.text();
+      const reactEnvMatch = /window\.reactEnv\s*=\s*\{[^}]*"dispensaryId"\s*:\s*"([a-fA-F0-9]+)"/i.exec(html);
+      if (reactEnvMatch && reactEnvMatch[1]) {
+        result.provider = 'dutchie';
+        result.menuUrl = homepage;
+        result.platformDispensaryId = reactEnvMatch[1];
+        console.log(`[WebsiteCrawl] Found reactEnv.dispensaryId=${reactEnvMatch[1]} on homepage ${homepage}`);
+        return result;
+      }
+    }
+  } catch (err: any) {
+    console.log(`[WebsiteCrawl] reactEnv check failed for ${homepage}: ${err.message}`);
+  }
+
   // Step 2: Check for direct provider matches in homepage links
   for (const link of homepageLinks) {
     for (const { provider, patterns } of PROVIDER_URL_PATTERNS) {
@@ -565,14 +590,13 @@ export async function detectAndResolveDispensary(dispensaryId: number): Promise<
     success: false,
   };
 
-  // For proprietary providers (curaleaf, sol), try website crawl to find an actual menu provider
-  // These sites may have Dutchie embedded menus even though their domain suggests proprietary
-  const PROPRIETARY_DOMAINS = ['curaleaf', 'sol'] as const;
-  const isPotentiallyProprietary = PROPRIETARY_DOMAINS.includes(detectedProvider as any);
+// For domains like curaleaf/sol, crawl the website to find the actual menu provider (often Dutchie)
+const SPECIAL_DOMAINS = ['curaleaf', 'sol'] as const;
+const isSpecialDomain = SPECIAL_DOMAINS.includes(detectedProvider as any);
 
-  if (isPotentiallyProprietary && website && website.trim() !== '') {
-    console.log(`[MenuDetection] ${dispensary.name}: Detected ${detectedProvider} domain - crawling website to find actual menu provider...`);
-    const crawlResult = await crawlWebsiteForMenuLinks(website);
+if (isSpecialDomain && website && website.trim() !== '') {
+  console.log(`[MenuDetection] ${dispensary.name}: Detected ${detectedProvider} domain - crawling website to find actual menu provider (often Dutchie)...`);
+  const crawlResult = await crawlWebsiteForMenuLinks(website);
 
     if (crawlResult.menuUrl && crawlResult.provider !== 'unknown') {
       // Found an actual menu provider (likely Dutchie) - use that instead!
@@ -614,7 +638,30 @@ export async function detectAndResolveDispensary(dispensaryId: number): Promise<
       // If the actual provider is dutchie, continue to platform ID resolution
       if (actualProvider === 'dutchie') {
         result.detectedProvider = 'dutchie';
-        // Fall through to dutchie platform ID resolution below
+        // If platformDispensaryId was captured (e.g., reactEnv on homepage), save it now and return
+        if (crawlResult.platformDispensaryId) {
+          await query(
+            `
+            UPDATE dispensaries SET
+              platform_dispensary_id = $1,
+              provider_detection_data = COALESCE(provider_detection_data, '{}'::jsonb) ||
+                jsonb_build_object(
+                  'platform_id_resolved', true,
+                  'platform_id_resolved_at', NOW(),
+                  'detected_provider', 'dutchie'::text,
+                  'detection_method', 'website_crawl'::text
+                ),
+              updated_at = NOW()
+            WHERE id = $2
+            `,
+            [crawlResult.platformDispensaryId, dispensaryId]
+          );
+          result.platformDispensaryId = crawlResult.platformDispensaryId;
+          result.success = true;
+          console.log(`[MenuDetection] ${dispensary.name}: Resolved platform ID from reactEnv = ${crawlResult.platformDispensaryId}`);
+          return result;
+        }
+        // Fall through to dutchie platform ID resolution below if no platform ID captured
       } else {
         // Found a different provider (treez, jane, etc.) - we're done
         result.detectedProvider = actualProvider;
@@ -883,6 +930,9 @@ export async function runBulkDetection(options: {
     )`;
   } else if (onlyMissingPlatformId) {
     whereClause += ` AND (menu_type = 'dutchie' AND platform_dispensary_id IS NULL)`;
+  } else if (includeDutchieMissingPlatformId) {
+    // Always attempt to resolve dutchie stores missing platform IDs
+    whereClause += ` AND (menu_type = 'dutchie' AND platform_dispensary_id IS NULL)`;
   }
 
   let query_str = `