Fix turn counting, task-aware max steps in inference, explicit conversation reset, openenv.yaml metadata

added automatic attack button in UI and improved roleplay

added frontend for the project

Fix pipeline 0.0 scoring override, resolve test floating-point flakiness, and add readable CLI output for inference.py

wire up the main LLM pipeline — defender + classifiers in one place

add defense scorer — how well did the defender actually handle that?

add attack classifier — did the attacker actually win this turn?

add defender LLM — the AI that holds the line against attacks

add ConversationManager to give the defender a memory

add Groq client setup — one place to rule all API calls

feat(llm): add run_llm_pipeline() stub with correct return shape for Person 3

chore(llm): add llm package __init__.py