第五轮：锁/续跑/超时/自动分支/R4 探针与 encode-once/控制台加固；阶段内断点续跑（gen 按条、prep 按 shard、训练与 APG 定时原子存档+体面停止）；分歧以实现方意见为准

ml/sim/closed_loop.py

@@ -13,6 +13,8 @@ from ml.common.features import features, STEP, H, GAP_CAP, D2R, wrap180
 DT = 0.02
 
 
+FIRST_DEG = 5.0   # R7 首次方向判定阈值（度）：小于它的抖动不算选边
+
 def tasks_to_tensors(tasks, device):
     q0 = torch.tensor([t['q0'] for t in tasks], dtype=torch.float32, device=device)
     T = torch.tensor([t['T'] for t in tasks], dtype=torch.float32, device=device)
@@ -80,6 +82,7 @@ def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None,
     traj = [q.clone()] if return_traj else None
     n_start = int(round(0.5 / DT)); moved_start = None          # R2 起步失败：0.5 s 内关节总行程 < 1°
     j1_acc = torch.zeros(B, device=device); j1_max = torch.zeros(B, device=device); j1_min = torch.zeros(B, device=device)
+    j1_first = torch.zeros(B, device=device)   # 2026-10-18 第五轮（审查 N-3）：J1 累计偏离首次超过 FIRST_DEG 时的方向（真正的"首次方向"）
     cold = True
     for it in range(nmax):
         tnow = it * DT
@@ -146,6 +149,7 @@ def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None,
         qp = q; q = kin.clamp_box(q + d)
         travel += d.abs().sum(-1)
         j1_acc = j1_acc + d[:, 0]; j1_max = torch.maximum(j1_max, j1_acc); j1_min = torch.minimum(j1_min, j1_acc)
+        j1_first = torch.where((j1_first == 0) & (j1_acc.abs() >= FIRST_DEG), torch.sign(j1_acc), j1_first)
         if it + 1 == n_start: moved_start = travel.clone()
         if return_traj: traj.append(q.clone())
         mid = qp + 0.5 * (q - qp)
@@ -169,7 +173,8 @@ def rollout(model, kin, tasks, device, K=8, safety=False, seed=0, max_sec=None,
            'start_fail': start_fail.float().mean().item(),
            'time_budget': 'teacher×2(≥3 s)' if bool(has_ref.all()) else ('fixed %.0f s' % (max_sec or NOREF_SEC) if not has_ref.any() else 'mixed')}
     # 绕行侧：J1 累计位移的正向/负向极值哪个更大（+1 / −1），供 R7 左右比例门禁
-    side = torch.where(j1_max >= -j1_min, torch.ones_like(j1_max), -torch.ones_like(j1_max))
+    # 首次方向；全程没偏离到 FIRST_DEG 的（基本不绕 J1）退回净方向
+    side = torch.where(j1_first != 0, j1_first, torch.where(j1_max >= -j1_min, torch.ones_like(j1_max), -torch.ones_like(j1_max)))
     per = {'done': done.cpu(), 't_done': t_done.cpu(), 'col': col.cpu(), 'travel': travel.cpu(), 'err': e_end.cpu(),
            'side': side.cpu(), 'start_fail': start_fail.cpu(), 'brakes': brakes.cpu()}
     if return_traj: per['traj'] = torch.stack(traj, 1).cpu()
@@ -217,7 +222,8 @@ def main():
         k = t.get('cat', '?') + '/' + t.get('mode', '?'); b = by.setdefault(k, [0, 0, 0]); b[0] += 1; b[1] += int(d); b[2] += int(c > 0)
     res['by_cat_mode'] = {k: {'n': v[0], 'success': v[1] / v[0], 'collision': v[2] / v[0]} for k, v in by.items()}
     s = json.dumps(res, indent=1); print(s)
-    if a.out: open(a.out, 'w').write(s)
+    if a.out:                                    # 先写 .tmp 再改名：中断不会留下半截结果被当成已完成（M5 续跑按文件存在跳过）
+        open(a.out + '.tmp', 'w').write(s); os.replace(a.out + '.tmp', a.out)
 
 
 if __name__ == '__main__':