- Remove Zep Cloud dependency entirely (zep_entity_reader, zep_graph_memory_updater, zep_tools, zep_paging)
- Add local SQLite-based graph store with LLM-powered entity extraction
- Add local embeddings utility and graph tools service
- Translate all backend docstrings, LLM prompts, and UI to English
- Set English as default language, remove Chinese locale (zh.json)
- Add Ollama setup guide and configure .env.example for Ollama
- Add AGENTS.md for AI agent context
- Fix pyright type errors in models/services
- Add Nedbank Africa expansion preset
- Clean up Docker configuration and README
- Added a new Interview module to facilitate interactions with agents post-simulation, allowing for single and batch interviews.
- Introduced IPC communication mechanism for command and response handling between the Flask backend and simulation scripts.
- Updated README.md to include detailed instructions on the new Interview functionality, including API endpoints and usage examples.
- Enhanced simulation scripts to support waiting for commands after completion, improving user control over the simulation environment.
- Implemented error handling and logging for interview processes, ensuring robust operation and traceability.