Mecanum Webots via Supervisor kinematic injection

Replace the failing ODE-rolled mecanum chassis dynamics with a
Supervisor.setVelocity call that uses the gym mecanum forward
kinematics formula directly. Wheel motors still spin (visual);
chassis motion comes from the gym model so training and deployment
match by construction.

Results (seed=42, n=10 sheep): BC + RL mecanum pen 10/10 in both
field and field_round. n=5 mecanum cells still 0/5 due to tracker
phantoms anchored to wall corners under the 360° LiDAR — documented
in docs/status.md as the remaining gap.

Cleanup: drop deploy-time hacks (HERDING_HEADING_*, HERDING_OMEGA_CLAMP,
HERDING_TRACKER_*) that were workarounds for the old ODE chaos;
revert the proto inertiaMatrix, roller dampingConstant, and reduced
motor torque since they no longer carry load; refresh comments
around the mecanum config presets.

.gitignore

@@ -24,8 +24,12 @@ herding_runtime.cfg
 # Runtime logs — all of these are produced by training/eval/webots runs
 # and are not useful to track in git. Keep summary docs/markdown only.
 *.log
+*.stdout
 calibrate_mecanum.log
 training/.run_done
 
+# Local-only training backups (never committed).
+_backup_pretrain/
+
 # Tooling
 .claude/