- write_trajectory now takes primary_key (passed from cfg.demo in run.py)
- signals built dynamically from all *_nats keys in the eval dict (was hardcoded auth/care)
- Panel A: primary_key signal (care_nats for love demo, not the top-range mover which was auth)
- Panel C: primary on x, biggest-moving off-target foundation on y (fairness moves ~2.5 nats
here, bigger than auth ~1.2 nats, so fairness becomes the y-axis for the love demo)
- coherence-crash override: if coh range beats all nat ranges, y = log-incoherence as before
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
- plot: Panel A now tracks top-moving trait (care for love demo, auth for authority)
instead of hardcoded auth_nats; Panel C already did this, Panel A now consistent
- README: update table with new run (lam decay extends saturation r4→r6), refresh diary
from new run's outputs, update trajectory plot
- AGENTS.md: correct gotchas -- tau<operating_KL is the key constraint (tau=2.0 not 4.0);
QLoRA + bs=3 ga=2 is the right default for better heal gradient estimates
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
Day 6/7 steered (pure !!! loop and fragmentary loop) + Night 7 healed
(care -0.76, coh=0.987). Plot now covers all 17 stages (base+8 pairs).
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
care_nats base -1.30 -> -0.60 at r4 (slow creep, barrier holds coh >=0.990).
Steered gens degrade to !!! loops by r3 but healed adapter stays coherent.
docs/love_loop.png = trajectory.png from the 7-round love run.
Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
wassname
