[31388f42] Deep CE Sync: Support contact creation and automated enrichment workflow

lead-engine/enrich.py

@@ -6,7 +6,8 @@ import sqlite3
 # Füge das Hauptverzeichnis zum Python-Pfad hinzu, damit der Connector gefunden wird
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
 from company_explorer_connector import handle_company_workflow, get_company_details
-from db import get_leads, DB_PATH
+from db import get_leads, DB_PATH, update_lead_metadata
+from lookup_role import lookup_person_role
 
 def update_lead_enrichment(lead_id, data, status):
     """Aktualisiert einen Lead in der Datenbank mit neuen Enrichment-Daten und einem neuen Status."""
@@ -26,18 +27,54 @@ def refresh_ce_data(lead_id, ce_id):
     print(f"Refreshing data for CE ID {ce_id}...")
     ce_data = get_company_details(ce_id)
     
-    # Bestehende Enrichment-Daten holen, um nichts zu überschreiben
-    # (Vereinfachung: Wir bauen das dict neu auf)
-    enrichment_data = {
+    # Bestehende Enrichment-Daten holen
+    leads = get_leads()
+    lead = next((l for l in leads if l['id'] == lead_id), None)
+    
+    enrichment_data = {}
+    if lead and lead.get('enrichment_data'):
+        try:
+            enrichment_data = json.loads(lead['enrichment_data'])
+        except:
+            pass
+            
+    enrichment_data.update({
         "sync_status": "refreshed",
         "ce_id": ce_id,
         "message": "Data refreshed from CE",
         "ce_data": ce_data
-    }
+    })
     
     update_lead_enrichment(lead_id, enrichment_data, status='synced')
     return ce_data
 
+def enrich_contact_role(lead):
+    """
+    Versucht, die Rolle des Kontakts via SerpAPI zu finden und speichert sie in den Metadaten.
+    """
+    meta = {}
+    if lead.get('lead_metadata'):
+        try:
+            meta = json.loads(lead.get('lead_metadata'))
+        except:
+            pass
+            
+    # Skip if we already have a role (and it's not None/Unknown)
+    if meta.get('role') and meta.get('role') != "Unbekannt":
+        return meta.get('role')
+        
+    print(f"Looking up role for {lead['contact_name']} at {lead['company_name']}...")
+    role = lookup_person_role(lead['contact_name'], lead['company_name'])
+    
+    if role:
+        print(f" -> Found role: {role}")
+        meta['role'] = role
+        update_lead_metadata(lead['id'], meta)
+    else:
+        print(" -> No role found.")
+        
+    return role
+
 def run_sync():
     """
     Haupt-Synchronisationsprozess.
@@ -56,15 +93,33 @@ def run_sync():
         company_name = lead['company_name']
         print(f"\n--- Processing Lead ID: {lead['id']}, Company: '{company_name}' ---")
         
-        # Rufe den zentralen Workflow auf, den wir im Connector definiert haben
-        # Diese Funktion kümmert sich um alles: prüfen, erstellen, discovern, pollen, analysieren
-        result = handle_company_workflow(company_name)
+        # 1. Contact Enrichment (Role Lookup via SerpAPI)
+        role = enrich_contact_role(lead)
+        
+        # 2. Prepare Contact Info for CE
+        meta = {}
+        if lead.get('lead_metadata'):
+            try:
+                meta = json.loads(lead.get('lead_metadata'))
+            except:
+                pass
+        
+        contact_info = {
+            "first_name": meta.get('contact_first', ''),
+            "last_name": meta.get('contact_last', lead['contact_name'].split(' ')[-1] if lead['contact_name'] else ''),
+            "email": lead['email'],
+            "job_title": meta.get('role', role), # The raw title or Gemini result
+            "role": meta.get('role', role) # Currently mapped to same field
+        }
+        
+        # 3. Company Enrichment (CE Workflow with Contact)
+        result = handle_company_workflow(company_name, contact_info=contact_info)
         
         # Bereite die Daten für die Speicherung in der DB vor
         enrichment_data = {
             "sync_status": result.get("status"),
             "ce_id": result.get("data", {}).get("id") if result.get("data") else None,
-            "message": result.get("message"),
+            "message": result.get("message", "Sync successful"),
             "ce_data": result.get("data")
         }
         

lead-engine/trading_twins_ingest.py

@@ -111,7 +111,7 @@ def parse_tradingtwins_html(html_body):
 
     return data
 
-def process_leads():
+def process_leads(auto_sync=True):
     init_db()
     new_count = 0
     try:
@@ -120,11 +120,21 @@ def process_leads():
         logger.info(f"Found {len(emails)} Tradingtwins emails.")
         
         for email in emails:
+            # ... (parsing logic remains same)
             body = email.get('body', {}).get('content', '')
-            lead_data = parse_tradingtwins_html(body)
+            received_at_str = email.get('receivedDateTime')
             
-            # Add raw body for reference
+            # Convert ISO string to datetime object
+            received_at = None
+            if received_at_str:
+                try:
+                    received_at = datetime.fromisoformat(received_at_str.replace('Z', '+00:00'))
+                except:
+                    pass
+
+            lead_data = parse_tradingtwins_html(body)
             lead_data['raw_body'] = body
+            lead_data['received_at'] = received_at
             
             company_name = lead_data.get('company')
             if not company_name or company_name == '-':
@@ -132,17 +142,18 @@ def process_leads():
                 lead_data['company'] = company_name
             
             if not company_name:
-                logger.warning(f"Skipping email {email['id']}: No company or contact name found.")
                 continue
                 
-            logger.info(f"Ingesting Lead: {company_name} (ID: {lead_data.get('id')})")
+            lead_data['id'] = lead_data.get('source_id') or f"tt_{int(datetime.now().timestamp())}"
             
-            # Save to local DB (status=new)
             if insert_lead(lead_data):
-                logger.info(f" -> Successfully saved to DB.")
+                logger.info(f" -> Ingested: {company_name}")
                 new_count += 1
-            else:
-                 logger.info(f" -> Lead already exists (skipped).")
+        
+        if new_count > 0 and auto_sync:
+            logger.info(f"Triggering auto-sync for {new_count} new leads...")
+            from enrich import run_sync
+            run_sync()
                  
         return new_count