item 31 pre-registered (Nils's design): synthetic memory tokens — burst states → per-band-layer KV prefix via KVMemoryAdapter (in-place attention wrap, bit-exact disarmed, gated silent init); composed with frozen item-29 arm-1; +29 tf+fr in-flight note (30.5, FR term hurts)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

scripts/eval_carry_cot.py

@@ -40,11 +40,25 @@ def main():
                     help="load a lora_*_e*.pt loop-only band-LoRA checkpoint")
     ap.add_argument("--inner-iters", type=int, default=0, metavar="M",
                     help="M in-place band iterations at the last pause")
+    ap.add_argument("--kvmem", default=None, metavar="KVMEM_PT",
+                    help="KVMemoryAdapter checkpoint: burst states become "
+                     "band-layer KV prefix entries at generation")
     args = ap.parse_args()
 
     model, tok = load_model(dtype=torch.bfloat16)
     tok.padding_side = "left"
     looper = BandLooper(model)
+    kvmem = None
+    if args.kvmem:
+        from kv_memory import install, KVMemoryAdapter
+        from loop_common import BAND
+        install(model)
+        sd = torch.load(args.kvmem, map_location="cuda")
+        code = sd["trunk.1.weight"].shape[0]
+        kvmem = KVMemoryAdapter(model, band=BAND, code=code).cuda()
+        kvmem.load_state_dict(sd)
+        kvmem.eval()
+        print(f"kv-memory loaded: {args.kvmem} (code={code})", flush=True)
     if args.bandlora:
         from lora_band import inject_band_lora
         ck = torch.load(args.bandlora, map_location="cuda")
@@ -86,7 +100,11 @@ def main():
                                        enc["attention_mask"], k, p,
                                        max_new_tokens=args.max_new,
                                        feedforward=args.feedforward,
-                                       inner_iters=args.inner_iters)
+                                       inner_iters=args.inner_iters,
+                                       kvmem=kvmem)
+                if kvmem is not None:
+                    from kv_memory import arm_memory
+                    arm_memory(None)
             for j, it in enumerate(chunk):
                 txt = tok.decode(gen[j, enc["input_ids"].shape[1]:],
                                  skip_special_tokens=True)