fix: search race condition + brand detection + contacts + reassess

- loadDomains(): add generation counter so stale auto-advance fetches
  cannot overwrite a newer user-triggered search result; snapshot filter
  state before the first await so URL reflects what was requested; add
  HTTP status check so backend errors surface as toasts rather than
  silent empty results; auto-advance now calls loadDomains() without
  await so the counter increments correctly per page advance

- beauty_ai: word-boundary regex for short brands (≤5 chars) to stop
  'ref' matching 'reference'/'refresh'/'prefer' etc.; merge phones,
  whatsapp and social_links from site_analyzer directly into result
  (more reliable than AI extraction); add contact_whatsapp and
  contact_social fields to AI JSON schema

- db: add requeue_beauty() for re-assessing already-assessed domains

- beauty_main: /api/beauty/reassess/batch endpoint using requeue_beauty

- index.html: Re-assess Selected bulk button, per-row ↺ button in
  Browse and Pipeline, WhatsApp + social links in Pipeline contact panel

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

app/beauty_ai.py

@@ -128,9 +128,22 @@ BEAUTY_CATEGORIES = [
 # ── Brand detection (fast pre-scan, no AI) ─────────────────────────────────────
 
 def detect_brands_in_text(text: str) -> list[str]:
-    """Find which brands from the universe appear in the scraped page text."""
+    """Find which brands from the universe appear in the scraped page text.
+
+    Short brands (≤5 chars) use word-boundary matching to avoid false positives
+    like 'ref' matching 'reference', 'prefer', 'refresh', etc.
+    """
     tl = text.lower()
-    return [b for b in BEAUTY_BRANDS if b.lower() in tl][:60]
+    result = []
+    for b in BEAUTY_BRANDS:
+        bl = b.lower()
+        if len(bl) <= 5:
+            if re.search(r'(?<![a-zA-Z0-9])' + re.escape(bl) + r'(?![a-zA-Z0-9])', tl):
+                result.append(b)
+        else:
+            if bl in tl:
+                result.append(b)
+    return result[:60]
 
 
 def get_dist_matches(detected: list[str]) -> list[str]:
@@ -247,6 +260,8 @@ Respond ONLY with valid JSON, no markdown, no text outside JSON:
   "dist_matches": ["OurBrand1","OurBrand2"],
   "contact_email": "email or empty string",
   "contact_phone": "phone or empty string",
+  "contact_whatsapp": "whatsapp link or empty string",
+  "contact_social": "primary social profile URL or empty string",
   "b2b_proposal": "1-2 sentence value proposition in Spanish referencing their categories and our matching brands",
   "outreach_subject": "short Spanish subject line referencing their business name",
   "outreach_email": "3-4 sentence ready-to-send email in Spanish. Mention their business, 1-2 specific brands from our portfolio that match their range, and a clear call to action (catálogo, muestra, llamada).",
@@ -336,12 +351,27 @@ async def assess_beauty_domain(analysis: dict) -> dict:
             if not result.get("detected_brands") and detected:
                 result["detected_brands"] = detected
 
+            # Always merge contact data directly from site_analyzer — more reliable
+            # than AI extraction since it uses regex against raw HTML
+            phones      = analysis.get("phones", [])
+            whatsapp    = analysis.get("whatsapp", [])
+            social_links = analysis.get("social_links", [])
+            if phones and not result.get("contact_phone"):
+                result["contact_phone"] = phones[0]
+            if whatsapp:
+                result["contact_whatsapp"] = "; ".join(whatsapp[:2])
+            if social_links:
+                result["contact_social"] = "; ".join(social_links[:3])
+
             logger.info("Beauty AI %s → quality=%s, dist_matches=%s",
                         domain, result.get("lead_quality"), result.get("dist_matches"))
             return result
 
         except Exception as e:
             logger.error("Beauty AI error %s: %s", domain, e)
+            phones   = analysis.get("phones", [])
+            whatsapp = analysis.get("whatsapp", [])
+            social   = analysis.get("social_links", [])
             return {
                 "error": str(e)[:300],
                 "is_relevant": False,
@@ -349,4 +379,7 @@ async def assess_beauty_domain(analysis: dict) -> dict:
                 "dist_matches": dist_match,
                 "detected_brands": detected,
                 "contact_email": "",
+                "contact_phone": phones[0] if phones else "",
+                "contact_whatsapp": "; ".join(whatsapp[:2]) if whatsapp else "",
+                "contact_social": "; ".join(social[:3]) if social else "",
             }

app/beauty_main.py

@@ -22,7 +22,7 @@ load_dotenv()
 from app.db import (
     SQLITE_PATH, init_db, get_stats, get_domains, get_enriched,
     build_duckdb_index, index_status,
-    queue_beauty, get_beauty_queue_status, save_beauty_assessment, get_beauty_leads,
+    queue_beauty, requeue_beauty, get_beauty_queue_status, save_beauty_assessment, get_beauty_leads,
     save_prescreen_results,
 )
 from app.validator import start_validator, stop_validator, get_validator_status
@@ -277,6 +277,17 @@ async def beauty_assess_batch(body: dict):
     return {"queued": len(domains_list)}
 
 
+@app.post("/api/beauty/reassess/batch")
+async def beauty_reassess_batch(body: dict):
+    """Re-queue domains for fresh assessment, resetting any existing result."""
+    domains_list = body.get("domains", [])
+    if not domains_list:
+        return JSONResponse({"error": "no domains provided"}, status_code=400)
+    await requeue_beauty(domains_list)
+    _start_beauty_worker()
+    return {"requeued": len(domains_list)}
+
+
 @app.post("/api/beauty/worker/restart")
 async def beauty_worker_restart():
     _start_beauty_worker()

app/db.py

@@ -540,6 +540,19 @@ async def queue_beauty(domains: list[str]):
         await db.commit()
 
 
+async def requeue_beauty(domains: list[str]):
+    """Re-queue domains for fresh assessment even if already assessed."""
+    async with aiosqlite.connect(SQLITE_PATH, timeout=30) as db:
+        await db.executemany(
+            """INSERT INTO beauty_queue (domain, status)
+               VALUES (?, 'pending')
+               ON CONFLICT(domain) DO UPDATE SET
+                 status='pending', completed_at=NULL, error=NULL""",
+            [(d,) for d in domains],
+        )
+        await db.commit()
+
+
 async def get_beauty_queue_status():
     async with aiosqlite.connect(SQLITE_PATH, timeout=30) as db:
         async with db.execute("SELECT status, COUNT(*) FROM beauty_queue GROUP BY status") as cur:

app/static/beauty/index.html

@@ -180,6 +180,10 @@ textarea{width:100%;resize:vertical;font-family:monospace;font-size:12px}
       <span x-show="prescreening">Screening…</span>
     </button>
     <button class="btn-primary btn-sm" @click="assessSelected()">B2B Assess Selected</button>
+    <button class="btn-secondary btn-sm" @click="reassessSelected()" :disabled="reassessing">
+      <span x-show="!reassessing">Re-assess Selected</span>
+      <span x-show="reassessing">Re-queuing…</span>
+    </button>
     <button class="btn-secondary btn-sm" @click="selected=[]">Clear</button>
   </div>
 
@@ -227,6 +231,7 @@ textarea{width:100%;resize:vertical;font-family:monospace;font-size:12px}
             <td style="white-space:nowrap;display:flex;gap:4px">
               <button class="btn-secondary btn-sm" @click="prescreenOne(row.domain)" title="HTTP check + niche classify">Screen</button>
               <button class="btn-primary btn-sm"   @click="assessOne(row.domain)"    title="Beauty B2B AI assessment">Assess</button>
+              <button x-show="row.beauty_lead_quality" class="btn-secondary btn-sm" @click="reassessOne(row.domain)" title="Re-run B2B assessment">↺</button>
             </td>
           </tr>
         </template>
@@ -338,6 +343,7 @@ textarea{width:100%;resize:vertical;font-family:monospace;font-size:12px}
                 x-text="(row._beauty||{}).contact_email||row.emails||'—'"></td>
             <td @click.stop style="white-space:nowrap;display:flex;gap:4px">
               <button class="btn-secondary btn-sm" @click="copyOutreach(row)">Copy email</button>
+              <button class="btn-secondary btn-sm" @click="reassessOne(row.domain)" title="Re-run B2B assessment">↺</button>
             </td>
           </tr>
           <!-- Expanded detail -->
@@ -371,14 +377,20 @@ textarea{width:100%;resize:vertical;font-family:monospace;font-size:12px}
                 </div>
                 <div class="detail-box">
                   <h4>Contact Details</h4>
-                  <p style="font-size:12px;line-height:1.7">
+                  <p style="font-size:12px;line-height:1.8">
                     <template x-if="(row._beauty||{}).contact_email">
                       <span>Email: <a :href="'mailto:'+(row._beauty||{}).contact_email" x-text="(row._beauty||{}).contact_email"></a><br></span>
                     </template>
                     <template x-if="(row._beauty||{}).contact_phone">
                       <span>Phone: <span x-text="(row._beauty||{}).contact_phone"></span><br></span>
                     </template>
-                    <template x-if="row.emails">
+                    <template x-if="(row._beauty||{}).contact_whatsapp">
+                      <span>WhatsApp: <a :href="(row._beauty||{}).contact_whatsapp" target="_blank" x-text="(row._beauty||{}).contact_whatsapp"></a><br></span>
+                    </template>
+                    <template x-if="(row._beauty||{}).contact_social">
+                      <span style="color:var(--muted)">Social: <span x-text="(row._beauty||{}).contact_social"></span><br></span>
+                    </template>
+                    <template x-if="row.emails && !(row._beauty||{}).contact_email">
                       <span style="color:var(--muted);font-size:11px">On-site: <span x-text="row.emails"></span></span>
                     </template>
                   </p>
@@ -446,7 +458,8 @@ function app() {
     valSt: {running:false,processed:0,live:0,dead:0,error:0,parked:0,redirect:0,skipped:0,offset:0,rate:0},
     valTld: '', valRescan: false,
     toasts: [],
-    prescreening: false, validating: false,
+    prescreening: false, validating: false, reassessing: false,
+    _loadGen: 0,  // incremented on every loadDomains() call; stale responses are discarded
     exportQuality: '', exportCountry: '',
     f: {keyword:'', tld:'', prescreen_status:'live', niche:'beauty_cosmetics',
         site_type:'ecommerce', country:'', assessed:'', alpha_only:false, no_sld:false, limit:'100', page:1},
@@ -491,52 +504,72 @@ function app() {
     goSearch() { this.f.page=1; this.loadDomains(); },
 
     async loadDomains() {
+      // Generation counter: if a newer call starts while this one is awaiting the
+      // network, this call's result is stale and must be discarded.  This prevents
+      // auto-advance's background fetches from overwriting a fresh user-triggered
+      // search that completes after the stale fetch returns.
+      const gen = ++this._loadGen;
       this.loading = true;
       try {
-        const p = new URLSearchParams({page: this.f.page, limit: this.f.limit});
-        if (this.f.keyword)    p.set('keyword',    this.f.keyword.trim());
-        if (this.f.tld)        p.set('tld',        this.f.tld.trim());
-        if (this.f.alpha_only) p.set('alpha_only', 'true');
-        if (this.f.no_sld)     p.set('no_sld',     'true');
+        // Snapshot filter state NOW (before any await), so the URL we build
+        // matches the filters the user actually requested.
+        const snap = {...this.f};
+        const p = new URLSearchParams({page: snap.page, limit: snap.limit});
+        if (snap.keyword)    p.set('keyword',    snap.keyword.trim());
+        if (snap.tld)        p.set('tld',        snap.tld.trim());
+        if (snap.alpha_only) p.set('alpha_only', 'true');
+        if (snap.no_sld)     p.set('no_sld',     'true');
 
         // 'none' (Not checked) = domains never in the pipeline → DuckDB search.
         // Any real status (live/dead/…), niche, site_type, country, or assessed
         // requires the SQLite enriched_domains table (all server-side).
-        const hasEnrichFilter = (this.f.prescreen_status && this.f.prescreen_status !== 'none')
-                               || this.f.niche || this.f.site_type || this.f.country || this.f.assessed;
+        const hasEnrichFilter = (snap.prescreen_status && snap.prescreen_status !== 'none')
+                               || snap.niche || snap.site_type || snap.country || snap.assessed;
         let endpoint;
         if (hasEnrichFilter) {
-          if (this.f.prescreen_status) p.set('prescreen_status', this.f.prescreen_status);
-          if (this.f.niche)            p.set('niche',            this.f.niche);
-          if (this.f.site_type)        p.set('site_type',        this.f.site_type);
-          if (this.f.country)          p.set('country',          this.f.country.trim().toUpperCase());
-          if (this.f.assessed)         p.set('assessed',         this.f.assessed);
+          if (snap.prescreen_status) p.set('prescreen_status', snap.prescreen_status);
+          if (snap.niche)            p.set('niche',            snap.niche);
+          if (snap.site_type)        p.set('site_type',        snap.site_type);
+          if (snap.country)          p.set('country',          snap.country.trim().toUpperCase());
+          if (snap.assessed)         p.set('assessed',         snap.assessed);
           endpoint = '/api/enriched';
         } else {
           endpoint = '/api/domains';
         }
 
-        const d = await fetch(endpoint + '?' + p).then(r=>r.json());
+        const d = await fetch(endpoint + '?' + p).then(r => {
+          if (!r.ok) throw new Error(`Server error ${r.status}`);
+          return r.json();
+        });
+
+        // Discard if a newer search was started while this one was in-flight
+        if (gen !== this._loadGen) return;
+
         this.domainsTotal = d.total || 0;
         let rows = d.results || [];
 
         // 'Not checked': DuckDB returns all domains joined with enriched data;
         // keep only those with no prescreen_status yet (truly unprocessed).
-        if (this.f.prescreen_status === 'none') rows = rows.filter(r => !r.prescreen_status);
+        if (snap.prescreen_status === 'none') rows = rows.filter(r => !r.prescreen_status);
 
         // Auto-advance: current DuckDB page was fully processed → try next page
         // (prevents "0 results" after bulk-validating a page of Not checked domains)
-        if (rows.length === 0 && this.f.prescreen_status === 'none'
-            && (d.results||[]).length > 0 && this.f.page < 500) {
-          this.f.page++;
-          this.loading = false;
-          await this.loadDomains();
+        if (rows.length === 0 && snap.prescreen_status === 'none'
+            && (d.results||[]).length > 0 && snap.page < 500) {
+          this.f.page = snap.page + 1;
+          // Do NOT await — start the next page search as a fresh call so the
+          // generation counter works correctly; this call ends immediately.
+          this.loadDomains();
           return;
         }
 
         this.domains = rows;
-      } catch(e) { this.notify('Failed to load: '+e.message, 'error'); }
-      finally { this.loading = false; }
+      } catch(e) {
+        if (gen !== this._loadGen) return;
+        this.notify('Failed to load: '+e.message, 'error');
+      } finally {
+        if (gen === this._loadGen) this.loading = false;
+      }
     },
 
     async loadLeads() {
@@ -644,6 +677,30 @@ function app() {
       } catch(e) { this.notify('Failed: '+e.message, 'error'); }
     },
 
+    async reassessSelected() {
+      if (!this.selected.length || this.reassessing) return;
+      this.reassessing = true;
+      try {
+        const d = await fetch('/api/beauty/reassess/batch', {
+          method:'POST', headers:{'Content-Type':'application/json'},
+          body: JSON.stringify({domains: this.selected}),
+        }).then(r=>r.json());
+        this.notify(`Re-queued ${d.requeued} domains for fresh B2B assessment`, 'success');
+        this.selected = [];
+      } catch(e) { this.notify('Re-assess failed: '+e.message, 'error'); }
+      finally { this.reassessing = false; }
+    },
+
+    async reassessOne(domain) {
+      try {
+        await fetch('/api/beauty/reassess/batch', {
+          method:'POST', headers:{'Content-Type':'application/json'},
+          body: JSON.stringify({domains:[domain]}),
+        });
+        this.notify(`${domain} re-queued for fresh assessment`, 'success');
+      } catch(e) { this.notify('Failed: '+e.message, 'error'); }
+    },
+
     toggleLead(domain) {
       this.expandedLead = this.expandedLead===domain ? null : domain;
     },