send_answer: dynamic budget, safe HTML splitting, pre/code fixes, HTML comments escaping; agents_: tool routing wording; cleanup (remove dead code)
Update README.md and agents_.py - improvements and modifications
feat(agent): inject runtime UTC context; fix date handling policies; adjust deep_knowledge routing
feat: Add task scheduler system, multiple admins support, GPT-5 integration
- Add complete task scheduling system with CRUD operations
- Support for once/daily/interval task types
- Multiple admins support throughout the system
- GPT-5 integration for Deep Agent with reasoning capabilities
- New AI tools for task management (create, update, delete, list)
- Improved localization with task scheduler messages
- Fixed credit allocation logic for admins
- Enhanced user experience with structured capability descriptions
- Added performance optimizations for MCP servers
chore: update README and agents_tools/agents_.py
feat(agents): enhance instructions and tool routing
Add GPT-5 (o4-mini) deep_agent; refine main-agent policies (CRITICAL DATE HANDLING); clarify file/memory routing.