- Fix remaining datetime timezone errors across all database operations
- Implement dynamic vector database backend (Qdrant/ChromaDB) based on install.py configuration
- Add LLM timeout handling with immediate fallback responses for slow self-hosted models
- Use proper install.py configuration (2000 max tokens, 5min timeout, correct LLM endpoint)
- Fix PostgreSQL schema to use timezone-aware columns throughout
- Implement async LLM request handling with background processing
- Add configurable prompt limits and conversation history controls
- Start missing database services (PostgreSQL, Redis) automatically
- Fix environment variable mapping between install.py and application code
- Resolve all timezone-naive vs timezone-aware datetime conflicts
System now properly uses Qdrant vector database as specified in install.py instead of hardcoded ChromaDB.
Characters respond immediately with fallback messages during long LLM processing times.
All database timezone errors resolved with proper timestamptz columns.
- Update docker-start.sh to force correct profiles (qdrant, admin)
- Fix PostgreSQL port mapping from 5432 to 15432 across all configs
- Resolve MCP import conflicts by renaming src/mcp to src/mcp_servers
- Fix admin interface StaticFiles mount syntax error
- Update LLM client to support both Ollama and OpenAI-compatible APIs
- Configure host networking for Discord bot container access
- Correct database connection handling for async context managers
- Update environment variables and Docker compose configurations
- Add missing production dependencies and Dockerfile improvements
- Enhanced install.py with Docker detection and automatic service setup
- Added docker-compose.services.yml for standalone database services
- Created docker-services.sh management script for easy service control
- Added DOCKER.md documentation with complete setup instructions
- Updated requirements.txt for Python 3.13 compatibility
- Added multiple test scripts and configuration files
- Enhanced collaborative creative projects with proper database integration
- Fixed SQLAlchemy metadata field conflicts in database models
- Added comprehensive quickstart and testing guides
Services now available:
- PostgreSQL with Docker
- Redis with Docker
- ChromaDB vector database
- Qdrant vector database (recommended)
- PgAdmin for database administration
The setup script now automatically detects Docker and offers streamlined
installation with one-command service deployment.
Major Features Added:
• Cross-character memory sharing with trust-based permissions (Basic 30%, Personal 50%, Intimate 70%, Full 90%)
• Complete collaborative creative projects system with MCP integration
• Database persistence for all creative project data with proper migrations
• Trust evolution system based on interaction quality and relationship development
• Memory sharing MCP server with 6 autonomous tools for character decision-making
• Creative projects MCP server with 8 tools for autonomous project management
• Enhanced character integration with all RAG and MCP capabilities
• Demo scripts showcasing memory sharing and creative collaboration workflows
System Integration:
• Main application now initializes memory sharing and creative managers
• Conversation engine upgraded to use EnhancedCharacter objects with full RAG access
• Database models added for creative projects, collaborators, contributions, and invitations
• Complete prompt construction pipeline enriched with RAG insights and trust data
• Characters can now autonomously propose projects, share memories, and collaborate creatively
