[30388f42] Infrastructure Hardening: Repaired CE/Connector DB schema, fixed frontend styling build, implemented robust echo shield in worker v2.1.1, and integrated Lead Engine into gateway.

company-explorer/backend/database.py

@@ -1,11 +1,22 @@
-from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, ForeignKey, Float, Boolean, JSON
+from sqlalchemy import create_engine, Column, Integer, String, Text, DateTime, ForeignKey, Float, Boolean, JSON, event
 from sqlalchemy.ext.declarative import declarative_base
 from sqlalchemy.orm import sessionmaker, relationship
 from datetime import datetime
 from .config import settings
 
 # Setup
-engine = create_engine(settings.DATABASE_URL, connect_args={"check_same_thread": False})
+engine = create_engine(
+    settings.DATABASE_URL, 
+    connect_args={"check_same_thread": False, "timeout": 30}
+)
+
+# Disable mmap to avoid Docker volume issues on Synology
+@event.listens_for(engine, "connect")
+def set_sqlite_pragma(dbapi_connection, connection_record):
+    cursor = dbapi_connection.cursor()
+    cursor.execute("PRAGMA mmap_size=0") 
+    cursor.close()
+
 SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
 Base = declarative_base()
 
@@ -34,6 +45,8 @@ class Company(Base):
     industry_ai = Column(String, nullable=True)  # The AI suggested industry
     
     # Location (Golden Record)
+    street = Column(String, nullable=True) # NEW: Street + Number
+    zip_code = Column(String, nullable=True) # NEW: Postal Code
     city = Column(String, nullable=True)
     country = Column(String, default="DE")
     
@@ -68,6 +81,11 @@ class Company(Base):
     metric_source_url = Column(Text, nullable=True)          # URL where the proof was found
     metric_confidence = Column(Float, nullable=True)         # 0.0 - 1.0
     metric_confidence_reason = Column(Text, nullable=True)   # Why is it high/low?
+
+    # NEW: AI-generated Marketing Openers
+    ai_opener = Column(Text, nullable=True)
+    ai_opener_secondary = Column(Text, nullable=True)
+    research_dossier = Column(Text, nullable=True)
     
     # Relationships
     signals = relationship("Signal", back_populates="company", cascade="all, delete-orphan")
@@ -100,6 +118,9 @@ class Contact(Base):
     role = Column(String) # Operativer Entscheider, etc.
     status = Column(String, default="") # Marketing Status
     
+    # New field for unsubscribe functionality
+    unsubscribe_token = Column(String, unique=True, index=True, nullable=True)
+
     is_primary = Column(Boolean, default=False)
     
     created_at = Column(DateTime, default=datetime.utcnow)
@@ -130,6 +151,7 @@ class Industry(Base):
     notes = Column(Text, nullable=True)
     priority = Column(String, nullable=True) # Replaces old status concept ("Freigegeben")
     ops_focus_secondary = Column(Boolean, default=False)
+    strategy_briefing = Column(Text, nullable=True) # NEW: Strategic context (Miller Heiman)
 
     # NEW SCHEMA FIELDS (from MIGRATION_PLAN)
     metric_type = Column(String, nullable=True) # Unit_Count, Area_in, Area_out
@@ -150,17 +172,63 @@ class Industry(Base):
     created_at = Column(DateTime, default=datetime.utcnow)
 
 
-class JobRoleMapping(Base):
+class JobRolePattern(Base):
     """
-    Maps job title patterns (regex or simple string) to Roles.
+    Maps job title patterns (regex or exact string) to internal Roles.
     """
-    __tablename__ = "job_role_mappings"
+    __tablename__ = "job_role_patterns"
 
     id = Column(Integer, primary_key=True, index=True)
-    pattern = Column(String, unique=True) # e.g. "%CTO%" or "Technischer Leiter"
-    role = Column(String) # The target Role
+    
+    pattern_type = Column(String, default="exact", index=True) # 'exact' or 'regex'
+    pattern_value = Column(String, unique=True) # e.g. "Technischer Leiter" or "(?i)leiter.*technik"
+    role = Column(String, index=True) # The target Role, maps to Persona.name
+    priority = Column(Integer, default=100) # Lower number means higher priority
+    
+    is_active = Column(Boolean, default=True)
+    created_by = Column(String, default="system") # 'system', 'user', 'llm'
     
     created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+
+class RawJobTitle(Base):
+    """
+    Stores raw unique job titles imported from CRM to assist in pattern mining.
+    Tracks frequency to prioritize high-impact patterns.
+    """
+    __tablename__ = "raw_job_titles"
+
+    id = Column(Integer, primary_key=True, index=True)
+    title = Column(String, unique=True, index=True) # The raw string, e.g. "Senior Sales Mgr."
+    count = Column(Integer, default=1) # How often this title appears in the CRM
+    source = Column(String, default="import")
+    
+    # Status Flags
+    is_mapped = Column(Boolean, default=False) # True if a pattern currently covers this title
+    
+    created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+
+class Persona(Base):
+    """
+    Represents a generalized persona/role (e.g. 'Geschäftsführer', 'IT-Leiter')
+    independent of the specific job title pattern.
+    Stores the strategic messaging components.
+    """
+    __tablename__ = "personas"
+
+    id = Column(Integer, primary_key=True, index=True)
+    name = Column(String, unique=True, index=True) # Matches the 'role' string in JobRolePattern
+    
+    description = Column(Text, nullable=True) # NEW: Role description / how they think
+    pains = Column(Text, nullable=True) # JSON list or multiline string
+    gains = Column(Text, nullable=True) # JSON list or multiline string
+    convincing_arguments = Column(Text, nullable=True) # NEW: What convinces them
+    typical_positions = Column(Text, nullable=True) # NEW: Typical titles
+    kpis = Column(Text, nullable=True) # NEW: Relevant KPIs
+    
+    created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
 
 
 class Signal(Base):
@@ -254,8 +322,8 @@ class ReportedMistake(Base):
 
 class MarketingMatrix(Base):
     """
-    Stores the static marketing texts for Industry x Role combinations.
-    Source: Notion (synced).
+    Stores the static marketing texts for Industry x Persona combinations.
+    Source: Generated via AI.
     """
     __tablename__ = "marketing_matrix"
 
@@ -263,7 +331,8 @@ class MarketingMatrix(Base):
     
     # The combination keys
     industry_id = Column(Integer, ForeignKey("industries.id"), nullable=False)
-    role_id = Column(Integer, ForeignKey("job_role_mappings.id"), nullable=False)
+    persona_id = Column(Integer, ForeignKey("personas.id"), nullable=False)
+    campaign_tag = Column(String, default="standard", index=True) # NEW: Allows multiple variants (e.g. "standard", "messe_2026", "warmup")
     
     # The Content
     subject = Column(Text, nullable=True)
@@ -273,7 +342,7 @@ class MarketingMatrix(Base):
     updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
     
     industry = relationship("Industry")
-    role = relationship("JobRoleMapping")
+    persona = relationship("Persona")
 
 
 # ==============================================================================
@@ -329,4 +398,4 @@ def get_db():
     try:
         yield db
     finally:
-        db.close()
+        db.close()