feat: Refactor data processing pipeline with AI cost tracking and enhanced session management

- Updated environment configuration to include Postgres database settings.
- Enhanced import processing to minimize field copying and rely on AI for analysis.
- Implemented detailed AI processing request tracking, including token usage and costs.
- Added new models for Question and SessionQuestion to manage user inquiries separately.
- Improved session processing scheduler with AI cost reporting functionality.
- Created a test script to validate the refactored pipeline and display processing statistics.
- Updated Prisma schema and migration files to reflect new database structure and relationships.

.env.local.example

@@ -17,6 +17,10 @@ SESSION_PROCESSING_INTERVAL="0 * * * *"      # Every hour (cron format) - AI pro
 SESSION_PROCESSING_BATCH_SIZE="0"            # 0 = process all sessions, >0 = limit number
 SESSION_PROCESSING_CONCURRENCY="5"           # Number of sessions to process in parallel
 
+# Postgres Database Configuration
+DATABASE_URL_TEST="postgresql://" 
+DATABASE_URL="postgresql://"
+
 # Example configurations:
 # - For development (no schedulers): SCHEDULER_ENABLED=false
 # - For testing (every 5 minutes): CSV_IMPORT_INTERVAL=*/5 * * * *