feat(company-explorer): add wikipedia integration, robotics settings, and manual overrides

- Ported robust Wikipedia extraction logic (categories, first paragraph) from legacy system.
- Implemented database-driven Robotics Category configuration with frontend settings UI.
- Updated Robotics Potential analysis to use Chain-of-Thought infrastructure reasoning.
- Added Manual Override features for Wikipedia URL (with locking) and Website URL (with re-scrape trigger).
- Enhanced Inspector UI with Wikipedia profile, category tags, and action buttons.

company-explorer/backend/database.py

@@ -77,13 +77,30 @@ class EnrichmentData(Base):
     id = Column(Integer, primary_key=True, index=True)
     company_id = Column(Integer, ForeignKey("companies.id"))
     
-    source_type = Column(String) # "website_scrape", "wikipedia_api", "google_serp"
+    source_type = Column(String) # "website_scrape", "wikipedia", "google_serp"
     content = Column(JSON)       # The raw data
+    is_locked = Column(Boolean, default=False) # Manual override flag
     
     created_at = Column(DateTime, default=datetime.utcnow)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
     
     company = relationship("Company", back_populates="enrichment_data")
 
+
+class RoboticsCategory(Base):
+    """
+    Stores definitions for robotics categories to allow user customization via UI.
+    """
+    __tablename__ = "robotics_categories"
+
+    id = Column(Integer, primary_key=True, index=True)
+    key = Column(String, unique=True, index=True) # e.g. "cleaning", "service"
+    name = Column(String) # Display Name
+    description = Column(Text) # The core definition used in LLM prompts
+    reasoning_guide = Column(Text) # Instructions for the Chain-of-Thought
+    
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+
 class ImportLog(Base):
     """
     Logs bulk imports (e.g. from Excel lists).
@@ -104,6 +121,47 @@ class ImportLog(Base):
 
 def init_db():
     Base.metadata.create_all(bind=engine)
+    init_robotics_defaults()
+
+def init_robotics_defaults():
+    """Seeds the database with default robotics categories if empty."""
+    db = SessionLocal()
+    try:
+        if db.query(RoboticsCategory).count() == 0:
+            defaults = [
+                {
+                    "key": "cleaning",
+                    "name": "Cleaning Robots",
+                    "description": "Does the company manage large floors, hospitals, hotels, or public spaces? (Keywords: Hygiene, Cleaning, SPA, Facility Management)",
+                    "reasoning_guide": "High (80-100): Large industrial floors, shopping malls, hospitals, airports. Medium (40-79): Mid-sized production, large offices, supermarkets. Low (0-39): Small offices, software consultancies."
+                },
+                {
+                    "key": "transport",
+                    "name": "Intralogistics / Transport",
+                    "description": "Do they move goods internally? (Keywords: Warehouse, Intralogistics, Production line, Hospital logistics)",
+                    "reasoning_guide": "High: Manufacturing, E-Commerce fulfillment, Hospitals. Low: Pure service providers, law firms."
+                },
+                {
+                    "key": "security",
+                    "name": "Security & Surveillance",
+                    "description": "Do they have large perimeters, solar parks, wind farms, or night patrols? (Keywords: Werkschutz, Security, Monitoring)",
+                    "reasoning_guide": "High: Critical infrastructure, large open-air storage, factories with valuable assets, 24/7 operations. Medium: Standard corporate HQs. Low: Offices in shared buildings."
+                },
+                {
+                    "key": "service",
+                    "name": "Service / Waiter Robots",
+                    "description": "Do they operate restaurants, nursing homes, or event venues where food/items need to be served to people?",
+                    "reasoning_guide": "High: Restaurants, Hotels (Room Service), Nursing Homes (Meal delivery). Low: B2B manufacturing, closed offices, pure installation services."
+                }
+            ]
+            for d in defaults:
+                db.add(RoboticsCategory(**d))
+            db.commit()
+            print("Seeded Robotics Categories.")
+    except Exception as e:
+        print(f"Error seeding robotics defaults: {e}")
+    finally:
+        db.close()
 
 def get_db():
     db = SessionLocal()