feat(analysis): Ground Step 8 Reference Analysis

Improves the competitor reference analysis (Step 8) by replacing the previous LLM-only approach with a grounded, scraping-based method.

- Implemented a new scraper to actively search for and parse competitor reference/case study pages.
- The analysis is now based on actual website content, significantly increasing the accuracy and reliability of the results and preventing model hallucinations.
- Updated documentation to reflect the new 'Grounded References' architecture.

docker-compose.yml

@@ -136,11 +136,16 @@ services:
       dockerfile: Dockerfile
     container_name: competitor-analysis
     restart: unless-stopped
+    dns:
+      - 8.8.8.8
+      - 8.8.4.4
     volumes:
-      # Sideloading: Python Orchestrator
+      # Sideloading: Python Orchestrator ONLY (to preserve built assets in /app/dist)
       - ./competitor-analysis-app/competitor_analysis_orchestrator.py:/app/competitor_analysis_orchestrator.py
       # Keys (passed via environment or file)
       - ./gemini_api_key.txt:/app/gemini_api_key.txt
+      # Logs
+      - ./Log_from_docker:/app/Log_from_docker
     environment:
       - PYTHONUNBUFFERED=1
       - GEMINI_API_KEY_FILE=/app/gemini_api_key.txt