"""The two measurement-side fixes, judged by cos(EP,BPTT) on the near-edge s2000 operator:
(1) DEEP ANCHOR — relax 400 instead of 150 before measuring (anchor res 2.65 -> 0.046: if the
    anchor error is the dominant amplified delta, cos jumps). Matched BPTT reference at same T1.
(2) KAPPA BRAKE — nbrake Tikhonov leak on the nudged dynamics only (shifts the measurement
    spectrum left by kappa, clips the non-normal transient): cos vs kappa at T1=150.
bsub kept small for the BPTT unroll memory."""
import torch
import lt_ep_train as L
from diag_cos import cos_ep_bptt

torch.manual_seed(0)
blk = L.EQBlock(512, 16, 256, 256, c=1.0, attn_mode='thick'); blk.qknorm = True
ck = torch.load('runs/redx_traj/s2000.pt', map_location=L.dev)
with torch.no_grad():
    for p, w in zip(blk.allp, ck['allp']):
        p.copy_(w.to(L.dev))
blk.track = True
torch.manual_seed(11)
batches = [L.get_batch('train', 24, 256) for _ in range(2)]

print("(1) deep anchor: cos at matched T1", flush=True)
for T1, bs in ((150, 4), (400, 3)):
    cs = []
    for idx, y in batches:
        try:
            c, r = cos_ep_bptt(blk, idx, y, T1, 20, 0.1, 0.02, holo=2, hr=0.02, t2sel=40, bsub=bs)
        except torch.cuda.OutOfMemoryError:
            torch.cuda.empty_cache()
            c, r = cos_ep_bptt(blk, idx, y, T1, 20, 0.1, 0.02, holo=2, hr=0.02, t2sel=40, bsub=2)
        cs.append(c)
    print(f"  T1={T1:<4} cos={' '.join(f'{c:.4f}' for c in cs)}  mean={sum(cs)/len(cs):.4f} (res~{r:.1e})", flush=True)

print("(2) kappa brake at T1=150:", flush=True)
for kap in (0.0, 0.02, 0.05, 0.1, 0.2):
    blk.nbrake = kap
    cs = []
    for idx, y in batches:
        c, _ = cos_ep_bptt(blk, idx, y, 150, 20, 0.1, 0.02, holo=2, hr=0.02, t2sel=40, bsub=4)
        cs.append(c)
    print(f"  kappa={kap:<5} cos={' '.join(f'{c:.4f}' for c in cs)}  mean={sum(cs)/len(cs):.4f}", flush=True)
blk.nbrake = 0.0
print("FIX_PROBE_DONE", flush=True)