perf+exp(closed_loop): 解析雅可比 DLS（消除 float32 差分数值噪声）——commit3 到达 36.3→46.5%，commit2 49.2%（n=512），DLS n1 9.3→7.1ms

- Kin.jac 几何雅可比，与 autograd 逐项一致（FD 自身 rel 误差 3.58%）
- dls_steps(analytic=True) 默认；每步少 6 次批量 FK
- 新增 ml/eval/eval_cl.py（部署口径小规模评估）与 check_dls.py（对拍+延迟）
- 积分反馈 fb_ki 脚手架（默认 0，未启用）

ml/eval/eval_cl.py

@@ -0,0 +1,75 @@
+"""小规模闭环评估（部署口径）：
+  python -m ml.eval.eval_cl --n 256 --commit 3 --fb 1.8 --partial [--ki 0.1 --select consist]
+输出：到达 / 碰撞 / ratio2s / 刹停 / 精修接管 / 墙钟。直接调 rollout，参数与部署一致。"""
+import argparse, functools, json, time
+import torch
+
+from ml.common.ckpt import load_policy
+from ml.common.kin_torch import Kin
+from ml.data import load_tasks
+from ml.sim.closed_loop import rollout
+import ml.sim.closed_loop as clmod
+
+
+def run(model, kin, tasks, device, bs=256, **kw):
+    agg, per = {}, []
+    for i in range(0, len(tasks), bs):
+        r, p = rollout(model, kin, tasks[i:i + bs], device, **kw)
+        per.append((r, p, len(tasks[i:i + bs])))
+    n = sum(w for _, _, w in per)
+    for r, _, w in per:
+        for k, v in r.items():
+            if k in ('n', 'time_budget') or v is None: continue
+            agg[k] = agg.get(k, 0.0) + v * w
+    out = {k: v / n for k, v in agg.items()}; out['n'] = n
+    out['goal_ratio_2s'] = torch.cat([p['goal_ratio_2s'] for _, p, _ in per]).median().item()
+    out['err_fail_med'] = torch.cat([p['err'] for _, p, _ in per])[~torch.cat([p['ok'] for _, p, _ in per])].median().item()
+    out['dls_share'] = torch.cat([p['dls_it'] for _, p, _ in per]).ge(0).float().mean().item()
+    out['time_budget'] = per[0][0]['time_budget']
+    return out
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument('--ckpt', default='ml/runs/base_dag2_dag1/best.pt')
+    ap.add_argument('--samples', default='ml/data/samples')
+    ap.add_argument('--tasks', default=None)
+    ap.add_argument('--split', default='val')
+    ap.add_argument('--n', type=int, default=256)
+    ap.add_argument('--K', type=int, default=8)
+    ap.add_argument('--commit', type=int, default=3)
+    ap.add_argument('--fb', type=float, default=1.8)
+    ap.add_argument('--ki', type=float, default=0.0)
+    ap.add_argument('--kdecay', type=float, default=0.9)
+    ap.add_argument('--kimax', type=float, default=0.5)
+    ap.add_argument('--select', default='consist')
+    ap.add_argument('--replan', default='r3')
+    ap.add_argument('--safety', type=int, default=1, help='1=安全层+部分前缀；0=关')
+    ap.add_argument('--partial', type=int, default=1)
+    ap.add_argument('--max_sec', type=float, default=None)
+    ap.add_argument('--seed', type=int, default=0)
+    ap.add_argument('--dls', default='analytic', choices=['analytic', 'fd'])
+    ap.add_argument('--device', default='cuda' if torch.cuda.is_available() else 'cpu')
+    a = ap.parse_args()
+    if a.dls == 'fd':
+        clmod.dls_steps = functools.partial(clmod.dls_steps, analytic=False)
+    model, ck = load_policy(a.ckpt, a.device)
+    kin = Kin(device=a.device)
+    assert ck.get('fp') in (None, kin.fp)
+    tasks = ([json.loads(l) for l in open(a.tasks, encoding='utf-8') if l.strip()] if a.tasks
+             else [t for t in load_tasks([a.samples]) if t['split'] == a.split])
+    tasks = tasks[:a.n]
+    t0 = time.perf_counter()
+    r = run(model, kin, tasks, a.device, K=a.K, safety=bool(a.safety), seed=a.seed, max_sec=a.max_sec,
+            safety_partial=(a.commit if (a.safety and a.partial) else 0), commit_n=a.commit,
+            select=a.select, replan=a.replan, fb_gain=a.fb, fb_ki=a.ki, fb_decay=a.kdecay, fb_imax=a.kimax)
+    wall = time.perf_counter() - t0
+    print('ckpt=%s n=%d K=%d commit=%d fb=%.2f ki=%.2f select=%s replan=%s safety=%d' %
+          (a.ckpt, r['n'], a.K, a.commit, a.fb, a.ki, a.select, a.replan, a.safety))
+    print('success %.3f  time_ok_1p3 %.3f  coll %.3f  ratio2s %.3f  brakes %.1f  dls_share %.3f  err_fail %.2f  wall %.1fs (%.0f ms/题)'
+          % (r['success'], r['time_ok_1p3'] or 0, r['collision_rate'], r['goal_ratio_2s'], r['brakes_mean'],
+             r['dls_share'], r['err_fail_med'], wall, wall / max(1, len(tasks)) * 1000))
+
+
+if __name__ == '__main__':
+    main()