add ablation experiments: truncation baseline + tag removal analysis

add: before/after thinking comparison graph — untrained vs trained

add: real training curves from 200-step GRPO run + improvement panel

fix: Red Team tab SSR crash + incremental training curves + storytelling polish

v2.3: right-size training budget + add red-team safeguards + tighter pitch

v2: calibrated metacognition as RL + inference-time budget + transfer eval