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

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.

good progress: finalized the llama index agents (except for the image and video handlers); finalized the toolbox; fixed bugs; designed great 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