feat: lora2r adapter (rank-2r PiSSA-init LoRA) + SGTM three-way hard routing

Structural-separation arm to disentangle directionality from shrinkage. A rank-2r
PiSSA-init LoRA with A and B both trainable, partitioned into a deployed block [:r]
and a quarantine block [r:] (spectrum-matched via alternated SVD axes). Unlike the
same-basis PiSSA routeV (where deploy-ablation only removes a magnitude slice of one
shared update = shrinkage null), each block has its own input-side A rows and
output-side B columns, so deploy-ablation removes a different FUNCTION.

Routing = SGTM-style three-way hard per-rollout masks from the cosine of the deployed
block's gate-pass gradient to the pair-extracted v_grad: clean (m=0,d=0) trains
deployed only; hack (m=1,d=1) detaches deployed output so only the quarantine updates
(SGTM grad-retain trick); mid (m=1,d=0) trains both (absorption). Gate is no-cheat:
cos to the hand-authored-pair direction, never an oracle label of a live rollout.

verify_lora2r_routing.py gates identity-at-init, the three-way block-grad routing,
per-rollout c-probe recovery, and ablation teeth; wired into smoke-lora2r. Additive:
PiSSA / lora_frozen_b paths untouched.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

src/vgrout/tablelog.py

@@ -74,7 +74,7 @@ class StepLogger:
                  show_ablate: bool = False) -> None:
         # Erase reports projection diagnostics; routeV reports routing diagnostics below.
         projects = arm == "projected"
-        is_route = arm in ("routingV", "routingV_per_token")
+        is_route = arm in ("routingV", "routingV_per_token", "routingV_lora2r")
         cols: list[_Col] = [
             _Col("step",   4, "step",    "d",    "GRPO step"),
             _Col("ref_eq", 6, "ref_eq",  ".2f",  "vanilla-equiv step (cum_gens/256)"),