added final_answer agent; improved reasoner; fixed minor issues; tweaked the prompts;

fixed tool calling bug; added no_think param and current_time to researcher; updated design diagram; no output guard for researcher

bugfixing; fixed toolbox; isolated [Base|AI|Human]Message crap logic to the agent interface; implemented tests

minor refactoring

implemented graph.py, agents, guard; reduced image and video node to viewer node; renamed system prompts

embracing langgraph; addapted LLMFactory, Args.LLMInterface, IAgent, Toolbox and agents.py; simplified graph: removed math and encryption agents while promoting the reasoner

New approach: langgraph only

Added logger; Optimized query flow; Fixed DuckDuckGo tools; Tweaked system prompts.

built management agents with llama_index, recursive self call for task breakdown, fixed LLMFactory to create LLMs from different interfaces

setup project structure: getting ready to build my agents