ml: 数据生成 + 可微运动学对拍 + MeanFlow/WTA 策略与闭环仿真 + APG/挖错/ONNX 导出与运行手册

- M1 数据生成器：采样/老师/距离下界认证/时间律/统计/一致性门禁；确定性老师（碰撞次数计时 + resetSession）、pos 任务冻结 J6、--consensus 邻域共识过滤、Dr 类。
- 全流程代码与运行手册：数据打包/可微运动学与对拍/MeanFlow+WTA 模型/闭环仿真/APG/挖错循环/ONNX 导出；webapp 策略运行时 ik-policy.js、?policy=1 接入、tests/policy_bench.cjs；ik-solver 增 pairList/clusterExport/criticalPairs/pairGap/leverTable。

ml/mining/gate.py

@@ -0,0 +1,53 @@
+"""门禁（方案 §7.2 第 6 步）：新模型须 ①门禁集到达率不降 ②A 类降幅 ≤ 0.5 个百分点 ③上一轮修好的错题 95% 仍对。
+  python -m ml.mining.gate --old cur.pt --new cand.pt --tasks ml/runs/gate_tasks.jsonl --out gate.json [--fixed prev_fixed.jsonl]
+通过则把 cand 复制为 --current（默认 ml/runs/current.pt）。gate.json 含 accept / gain_pp，loop.sh 据此决定继续或停止。"""
+import argparse, json, shutil
+import torch
+
+from ml.common.kin_torch import Kin
+from ml.model.policy import build
+from ml.sim.closed_loop import evaluate
+
+
+def load(path, dev):
+    ck = torch.load(path, map_location=dev)
+    m = build(ck['cfg']).to(dev); m.load_state_dict(ck['model']); return m.eval()
+
+
+def per_task_success(pers):
+    return torch.cat([p['done'] & (p['col'] == 0) for _, p in pers]).tolist()
+
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument('--old', required=True); ap.add_argument('--new', required=True); ap.add_argument('--tasks', required=True)
+    ap.add_argument('--fixed', default=None); ap.add_argument('--out', required=True); ap.add_argument('--current', default='ml/runs/current.pt')
+    ap.add_argument('--device', default='cuda' if torch.cuda.is_available() else 'cpu')
+    a = ap.parse_args()
+    kin = Kin(device=a.device)
+    tasks = [json.loads(l) for l in open(a.tasks) if l.strip()]
+    ro, po = evaluate(load(a.old, a.device), kin, tasks, a.device)
+    rn, pn = evaluate(load(a.new, a.device), kin, tasks, a.device)
+    so, sn = per_task_success(po), per_task_success(pn)
+    acc = lambda s, c: (sum(x for x, t in zip(s, tasks) if t['cat'] == c) / max(1, sum(t['cat'] == c for t in tasks)))
+    gain = (sum(sn) - sum(so)) / len(tasks) * 100
+    a_drop = (acc(so, 'A') - acc(sn, 'A')) * 100
+    keep = None
+    if a.fixed:
+        ft = [json.loads(l) for l in open(a.fixed) if l.strip()]
+        if ft:
+            r2, p2 = evaluate(load(a.new, a.device), kin, ft, a.device)
+            keep = sum(per_task_success(p2)) / len(ft)
+    accept = gain >= 0 and a_drop <= 0.5 and (keep is None or keep >= 0.95)
+    out = {'old': ro, 'new': rn, 'gain_pp': gain, 'A_drop_pp': a_drop, 'fixed_kept': keep, 'accept': accept}
+    # 本轮新修好的题（旧错新对）留给下一轮做"仍对"检查
+    fixed_now = [t for t, x, y in zip(tasks, so, sn) if (not x) and y]
+    with open(a.out.replace('.json', '_fixed.jsonl'), 'w') as f:
+        for t in fixed_now: f.write(json.dumps(t) + '\n')
+    json.dump(out, open(a.out, 'w'), indent=1)
+    if accept: shutil.copy(a.new, a.current)
+    print(json.dumps({k: out[k] for k in ('gain_pp', 'A_drop_pp', 'fixed_kept', 'accept')}))
+
+
+if __name__ == '__main__':
+    main()