fix(transcription): [2f388f42] finalize and fix AI insights feature

This commit resolves all outstanding issues with the AI Insights feature.

- Corrects the transcript formatting logic in  to properly handle the database JSON structure, ensuring the AI receives the correct context.
- Fixes the Gemini API client by using the correct model name ('gemini-2.0-flash') and the proper client initialization.
- Updates  to securely pass the API key as an environment variable to the container.
- Cleans up the codebase by removing temporary debugging endpoints.
- Adds  script for programmatic updates.
- Updates documentation with troubleshooting insights from the implementation process.

company-explorer/debug_standardization_logic.py

@@ -0,0 +1,48 @@
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+from backend.database import Industry
+from backend.services.classification import ClassificationService
+import logging
+
+# Setup DB connection directly to the file
+# Note: We need to use the absolute path that works inside the container or relative if running locally
+# Assuming we run this via 'docker exec' or locally if paths align. 
+# For safety, I'll use the path from config but typically inside container it's /app/...
+DB_URL = "sqlite:////app/companies_v3_fixed_2.db"
+
+engine = create_engine(DB_URL)
+SessionLocal = sessionmaker(bind=engine)
+db = SessionLocal()
+
+def test_logic():
+    print("--- DEBUGGING STANDARDIZATION LOGIC ---")
+    
+    industry_name = "Healthcare - Hospital"
+    industry = db.query(Industry).filter(Industry.name == industry_name).first()
+    
+    if not industry:
+        print(f"ERROR: Industry '{industry_name}' not found!")
+        return
+
+    print(f"Industry: {industry.name}")
+    print(f"Search Term: {industry.scraper_search_term}")
+    print(f"Standardization Logic (Raw DB Value): '{industry.standardization_logic}'")
+
+    if not industry.standardization_logic:
+        print("CRITICAL: Standardization logic is empty/null! That explains the null result.")
+        return
+
+    # Initialize Service to test the exact method
+    service = ClassificationService()
+    test_value = 352.0
+    
+    print(f"\nTesting calculation with value: {test_value}")
+    
+    try:
+        result = service._parse_standardization_logic(industry.standardization_logic, test_value)
+        print(f"Result: {result}")
+    except Exception as e:
+        print(f"Exception during parsing: {e}")
+
+if __name__ == "__main__":
+    test_logic()