fix(train): 首次正式预训练（21850 步闭环到达 0%）排查后修正——FK/平滑改加在配对去噪估计上（原加在随机噪声一步采样上=回归条件均值，多峰塌成单峰，实测候选标准差 0.030/幅度 0.151）；时间嵌入最高角频率 1000→50、MF 分支 fp32、p_neq 前 5000 步为 0（实测 du/dt 均方根 6–12 vs v 1.1）；增广 40%/3°/12 步收回；新增 dagger 阶段（策略闭环状态请老师重规划 ×2 轮微调）；开训前老师轨迹回放自检；评估加开环误差与候选多样性，best/早停按到达率+开环误差

ml/monitor.html

@@ -208,7 +208,7 @@
   <div class="d">后台执行 <code>bash ml/pipeline.sh all</code>，从对拍一路跑到验收。已完成的步骤自动跳过；训练每 10 分钟存档、生成按条续写，断了再点一次就从断点接着跑。网页和控制台窗口都可以关，训练不受影响。</div>
   <div class="form">
     <label>运行方式<select id="fMode"><option value="resume">续跑：跳过已完成的步骤</option><option value="from">从指定阶段重训（该阶段及之后全部重做）</option><option value="fresh">全部重跑（数据也重新生成）</option></select></label>
-    <label>起始阶段<select id="fFrom"><option value="train">预训练 train（保留数据、样本、门禁）</option><option value="m5">头门禁 m5</option><option value="apg">后训练 apg</option><option value="mine">挖错循环 mine</option><option value="export">导出 export</option><option value="bench">部署评测 bench</option><option value="accept">验收 accept</option><option value="gen">生成数据 gen（重跑约 7 小时）</option><option value="prep">打包样本 prep</option><option value="gate1">一致性门禁 gate1</option><option value="r4">推理延迟 r4</option><option value="kin">对拍 kin</option></select></label>
+    <label>起始阶段<select id="fFrom"><option value="train">预训练 train（保留数据、样本、门禁）</option><option value="dagger">DAgger 纠偏 dagger</option><option value="m5">头门禁 m5</option><option value="apg">后训练 apg</option><option value="mine">挖错循环 mine</option><option value="export">导出 export</option><option value="bench">部署评测 bench</option><option value="accept">验收 accept</option><option value="gen">生成数据 gen（重跑约 7 小时）</option><option value="prep">打包样本 prep</option><option value="gate1">一致性门禁 gate1</option><option value="r4">推理延迟 r4</option><option value="kin">对拍 kin</option></select></label>
     <label>动作头 CFG<select id="fCfg"><option value="ml/configs/base.json">MeanFlow（base，M5 不过自动转 WTA）</option><option value="ml/configs/wta.json">WTA（wta）</option><option value="ml/configs/small.json">小模型 d=128（R4 不过时用）</option></select></label>
     <label>共识过滤 CONSENSUS<select id="fCons"><option value="">按老师门禁自动</option><option value="0">关</option><option value="1">开（生成约慢 5 倍）</option></select></label>
     <label>任务数 N_TASKS<input id="fN" value="50000"></label>
@@ -378,7 +378,7 @@ let logyOn = false, job = null, userPicked = false, conOff = 0;
    下面这份只给示例数据用，数值与 pstate.py 一致。 */
 let STAGE_META = [
   ['setup', '安装依赖', 0.2], ['kin', '对拍', 0.2], ['r4', '推理延迟', 0.2], ['gate1', '一致性门禁', 0.5], ['gen', '生成老师轨迹', 5.0],
-  ['prep', '打包样本', 0.5], ['train', '预训练', 3.0], ['m5', '头门禁', 0.5], ['apg', 'APG 微调', 4.0], ['mine', '挖错循环', 9.0],
+  ['prep', '打包样本', 0.5], ['train', '预训练', 4.5], ['dagger', 'DAgger 纠偏', 3.5], ['m5', '头门禁', 0.5], ['apg', 'APG 微调', 4.0], ['mine', '挖错循环', 9.0],
   ['export', '导出', 0.1], ['bench', '部署评测', 1.0], ['accept', '验收汇总', 0.5]];
 let SM = Object.fromEntries(STAGE_META.map(([k, n, w]) => [k, { n, w, to: Math.max(1, 3 * w) }]));
 function applyStageMeta(m) {
@@ -788,7 +788,7 @@ function demoApi() {
   const mkPipe = (done, cur, curStartH) => { const t = now(); const st = {}, el = {}; let tt = t - curStartH * 3600;
     for (let i = done.length - 1; i >= 0; i--) { const [k, dur] = done[i]; st[k] = { start: tt - dur * 3600, end: tt, rc: 0, info: {} }; el[k] = dur * 3600; tt -= dur * 3600; }
     if (cur) { st[cur] = { start: t - curStartH * 3600, end: null, rc: null, info: {} }; el[cur] = curStartH * 3600; }
-    return { started: tt, plan: ['kin', 'r4', 'gate1', 'gen', 'prep', 'train', 'm5', 'apg', 'mine', 'export', 'bench', 'accept'], stages: st, elapsed: el, current: cur }; };
+    return { started: tt, plan: ['kin', 'r4', 'gate1', 'gen', 'prep', 'train', 'dagger', 'm5', 'apg', 'mine', 'export', 'bench', 'accept'], stages: st, elapsed: el, current: cur }; };
   const CON = {
     train: '$ FROM=kin TO=accept bash ml/pipeline.sh all\n计划：kin r4 gate1 gen prep train m5 apg mine export bench accept\n== node ml/prep/export_kin.cjs\n== node ml/eval/dump_parity.cjs 2000\n== python -m ml.eval.check_parity\n{"PASS": true, "fk_mm": 0.0004, "gap_mm": 0.0011}\n== node ml/gen/consistency.cjs 300 4242\n{"consistentByGateRule": 0.86}\n一致性门禁结果 → CONSENSUS=1\n== bash ml/gen/run_parallel.sh 1786 28 1 --consensus 4\n样本数 1702000 ≥ 目标，完成\n== bash ml/prep/run_prep.sh 28\n== python -m ml.eval.check_r2 --samples ml/data/samples --out ml/data/r2.json\n{"pairs": 250, "label_std_mean": 0.071, "pass": true}\n== python -m ml.train --samples ml/data/samples --out ml/runs/bench_base --steps 2000 --no-eval\nstep 2000  loss 1.912  6150 samples/s\n== python -m ml.train --samples ml/data/samples --out ml/runs/base\n',
     gen: '$ FROM=kin TO=accept bash ml/pipeline.sh all\n计划：kin r4 gate1 gen prep train m5 apg mine export bench accept\n== node ml/prep/export_kin.cjs\n== python -m ml.eval.check_parity\n{"PASS": true}\n== node ml/gen/consistency.cjs 300 4242\n{"consistentByGateRule": 0.86}\n一致性门禁结果 → CONSENSUS=1\n== bash ml/gen/run_parallel.sh 1786 28 1 --consensus 4\n',