Refactors the GTM orchestrator prompts (phases 2-9) to use a question-based strategic framework derived from the internal marketing blueprint. This new 'Meta-Framework' approach ensures strategic depth and prevents content pollution from irrelevant examples when analyzing new product categories.
- Updates orchestrator prompts in .
- Adds documentation in explaining how to modify the new strategy logic.
- Includes minor fixes to the Node.js and dependency updates in .
- Fixed TypeError in SessionBrowser by adding defensive checks for the sessions array.
- Implemented mandatory URL persistence: The research URL is now saved in DB, shown in UI, and included in reports.
- Added 'Start New Analysis' button to the session browser for better UX flow.
- Updated documentation to reflect v2.6.1 changes.
- Reverts docker-compose.yml to use volume mount for gemini_api_key.txt, due to format constraints.
- Restores and refines Config.load_api_keys() in config.py.
- **Crucially, calls Config.load_api_keys() at the start of gtm_architect_orchestrator.py to ensure keys are loaded.**
- Adjusts _get_gemini_api_key in helpers.py to prioritize keys from Config.API_KEYS.
- This definitively addresses the 'API Key missing' error by guaranteeing key initialization.
- Adds a version and timestamp to the orchestrator's startup logs to verify code deployment.
- Introduces extensive debug logging in config.py and helpers.py to trace the API key loading process, including exact file paths and environment variable checks. This will help diagnose the persistent 'API Key missing' error.
- Refactors the gtm-architect Dockerfile for a flat, more efficient build process.
- Implements robust web scraping via BeautifulSoup in helpers.py for URL analysis in phase1.
- Makes shared library imports (gspread, pandas, etc.) in helpers.py optional to prevent ModuleNotFoundErrors in microservices.
- Implements the main execution logic in the orchestrator to handle command-line arguments.
- Updates documentation to reflect the new architecture, scraping feature, and dependency handling.
- Refactor Docker build process for gtm-app to ensure reliability
- Correct volume mounts and build context in docker-compose.yml to prevent stale code
- Fix frontend 404 error by using relative paths in index.html
- Ensure API key is correctly mounted into the container
- Stabilize Node.js to Python data passing via explicit --data argument
- Update gtm_architect_documentation.md with extensive troubleshooting guide
