Clarify documentation: anomaly signal explainer, GRPO scope notes

Move blog to root as BLOG.md (per Meta mentor guidance)

Fix prompt truncation in inference_eval.py: max_seq_length 768 -> 2048

Fix max_new_tokens for CoT format + add eval-only HF Jobs script

Algorithm Distillation: grader v2 with belief_accuracy + SFT pipeline

client: surface ALL observation fields (was dropping deltas, anomalies, last_action, step_history)

iter4: fix the 'constant belief = free reward' bug + 6 other deep issues

iter3: align reward with grader + belief-first format + exploration shaping

iter2: fix mode collapse + 3 deeper bugs from code review

tune: GRPO hyperparameter fixes from ML reviewer

feat: HF Jobs training script + plot generator

fix: notebook plot cell syntax error (newline in string literal)

notebook: add belief-accuracy + reward-components plots

env: meta-RL refactor (continuous profiles, action+belief, adaptation grader)

fix: correct GRPO training hyperparameters to prevent KL explosion

fix: rename kl_coef to beta (correct param name in TRL GRPOConfig)

fix: reduce kl_coef to prevent training instability

Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline