feat(monitor): 网页加 CPU 占用卡（总占用环 + 28 核逐核条），psutil 采样缓存 1 秒；顺便重启控制台让之前的补量进度口径与停止补杀生效

ml/monitor.html

@@ -172,6 +172,7 @@
   <section class="hero">
     <div class="card" id="pipe"></div>
     <div class="card"><h2><span>GPU</span><span class="r" id="gputime"></span></h2><div id="gpu"></div></div>
+    <div class="card"><h2><span>CPU</span><span class="r" id="cputime"></span></h2><div id="cpu"></div></div>
   </section>
 
   <section class="card" id="prog"></section>
@@ -549,6 +550,20 @@ function renderStatus(s) {
       <div class="gname">${g.name}</div>`;
   }).join('<hr style="border:none;border-top:1px solid var(--line);margin:14px 0">') : empty('未检测到 nvidia-smi');
 
+  // CPU（psutil；没装就整块不显示）
+  const CP = s.cpu || {};
+  $('cputime').textContent = CP.n ? '实时' : '';
+  $('cpu').innerHTML = CP.n ? (() => {
+    const tot = CP.total ?? 0, C = 2 * Math.PI * 50, col = tot > 85 ? css('--bad') : tot > 60 ? css('--warn') : css('--ok');
+    const bars = (CP.per || []).map((v, i) => `<div title="核 ${i + 1}: ${v}%" style="flex:1;min-width:0;height:100%;background:${v > 85 ? css('--bad') : v > 60 ? css('--warn') : css('--accent2')};opacity:${0.25 + 0.75 * Math.min(1, v / 100)}"></div>`).join('');
+    return `<div class="gpuwrap"><div class="ring"><svg width="116" height="116"><circle cx="58" cy="58" r="50" stroke="#1b2433" stroke-width="10" fill="none"/>
+      <circle cx="58" cy="58" r="50" stroke="${col}" stroke-width="10" fill="none" stroke-linecap="round" stroke-dasharray="${C}" stroke-dashoffset="${C * (1 - tot / 100)}" style="transition:stroke-dashoffset .6s"/></svg>
+      <div class="c"><div><b>${tot}%</b><span>总占用</span></div></div></div>
+      <div class="gpurows"><div class="gr"><div class="l"><span>核心</span><b>${CP.n} 个</b></div><div class="mini"><div style="width:${Math.min(100, tot)}%;background:${col}"></div></div></div>
+      <div style="display:flex;gap:2px;height:26px;margin-top:6px">${bars}</div></div></div>
+      <div class="gname">每核占用（深色=忙）</div>`;
+  })() : empty('没装 psutil，无法读 CPU');
+
   // 数据
   const D = s.data || {}, st = D.stats, ix = D.index;
   const row = (k, v, cls = '') => `<tr><td>${k}</td><td class="n ${cls}">${v}</td></tr>`;

ml/monitor.py

@@ -68,6 +68,23 @@ def read_log(name, offset):
     return {'records': recs, 'offset': offset + end, 'size': size, 'reset': offset == 0, 'mtime': os.path.getmtime(f)}
 
 
+_CPU_CACHE = {'t': 0.0, 'v': {}}
+
+
+def cpu():
+    """CPU 占用：总百分比 + 每核（psutil 已装；没装就返回空，页面不显示这块）。"""
+    if time.time() - _CPU_CACHE['t'] < 1.0: return _CPU_CACHE['v']
+    try:
+        import psutil
+        per = psutil.cpu_percent(interval=None, percpu=True)
+        out = {'total': round(sum(per) / max(1, len(per)), 1), 'per': [round(x, 0) for x in per], 'n': len(per),
+               'load1': round(os.getloadavg()[0], 2) if hasattr(os, 'getloadavg') else None}
+    except Exception:
+        out = {}
+    _CPU_CACHE.update(t=time.time(), v=out)
+    return out
+
+
 _GPU_CACHE = {'t': 0.0, 'v': []}
 
 
@@ -203,7 +220,7 @@ def status():
     pb = jload(P(RUNS, 'policy_bench.json'))
     if pb: pb = {k: {kk: v.get(kk) for kk in ('n', 'ok', 'reached', 'collisionFrames', 'brakeRate', 'recoveryRate', 'livelock', 'inferMsP99', 'safetyMsP99')}
                  for k, v in pb.items() if isinstance(v, dict) and 'n' in v}
-    return {'now': time.time(), 'gpu': gpu(),
+    return {'now': time.time(), 'gpu': gpu(), 'cpu': cpu(),
             'vram_budget_gb': float(os.environ.get('VRAM_BUDGET_GB', 20)),      # 本机桌面常驻占 4–5 GB，给训练的预算 19–20 GB
             'pipeline': pl, 'check': CHECK.get(), 'lock': lock_info(),   # 2026-10-18 第八轮修：上一版这三项被行尾注释吞掉，网页步骤条/锁状态拿不到
             'stage_meta': [{'id': k, 'name': n, 'est_h': h, 'timeout_h': pstate.TIMEOUT_H[k]} for k, n, h in pstate.STAGES],