perf+exp: gm_groups 只算特征 8 组（数值一致，features 10.4→7.1ms）；混合节奏负结论（执行反馈无提升）；浏览器部署 dag2 ONNX + fbGain/commit 参数（bench 刹车 47% 待调）；实时口径改为异步规划+tick

webapp/js/ik-policy-glue.js

@@ -55,7 +55,9 @@ async function boot() {
     }
     if (!sess) sess = await ort.InferenceSession.create(MODEL, { executionProviders: ep, graphOptimizationLevel: 'all' });
     const infer = ArmPolicy.ortInfer(ort, sess, { encOnce: !!meta.enc_once, featDyn: !!meta.feat_dyn });
-    runner = new ArmPolicy.Runner(S, infer, { actScale: meta.act_scale || 1 });   // 2026-10-19：动作尺度随模型（旧模型无此字段 = 1）
+    const FB = qs.get('fb') === null ? 1.8 : +qs.get('fb');        // 2026-10-20：全程目标反馈（fb=0 关闭）
+    const COMMIT = qs.get('commit') === null ? 3 : Math.max(1, +qs.get('commit'));   // 部署节奏：commit=1 每步规划
+    runner = new ArmPolicy.Runner(S, infer, { actScale: meta.act_scale || 1, fbGain: FB, commit: COMMIT });   // 2026-10-19：动作尺度随模型（旧模型无此字段 = 1）
     /* 预热：首次推理有编译开销 */
     await infer(new Float32Array(8 * ArmPolicy.F_DIM), new Float32Array(8 * ArmPolicy.H * 6), 8);
     const tick = URL.createObjectURL(new Blob(['let h=null;onmessage=e=>{clearInterval(h);if(e.data>0)h=setInterval(()=>postMessage(0),e.data)}'], { type: 'text/javascript' }));

webapp/js/ik-policy.js

@@ -179,7 +179,7 @@ class Runner {
     this.o = Object.assign({ K: 8, commit: 3, margin: 5,   /* 2026-10-18：运行时投影余量保持 5 mm（真机护栏，不迁就数据分布）；数据侧另行过滤认证间隙 < 3 mm 的老师轨迹，APG 训练余量 3 mm */
        projMax: 0.5, refineMm: 5, arriveMm: 1, arriveDeg: 0.5,
       stuckPlans: 5, lockSec: 1.0, subReachDeg: 5, subTimeout: 1.5, subRule: 'cross', subLeadSec: 0.02, seed: 12345, lookahead: true,
-      actScale: 1, certBudget: 40, safetyMs: 30, firstMs: 45 }, opts || {});
+      actScale: 1, certBudget: 40, safetyMs: 30, firstMs: 45, fbGain: 0 }, opts || {});
     /* 2026-10-19：actScale = 模型 meta.act_scale（动作标签按 act_scale·STEP 归一化，旧模型 1）；增量 = clamp(act, ±1)·actScale·STEP，
        与 ml/sim/closed_loop.py 同口径。subRule：'cross'（默认，越过顶点即切，与训练标签同口径；见 _subAdvance）/ 'timeout'（旧：< subReachDeg 或 subTimeout 超时）。 */   // 每条候选最多 40 次距离查询；安全层总预算 30 ms，第 1 条候选可用到 45 ms（超出按刹停处理）
     this.cert = makeCert(S, { leverTable: this.o.leverTable, cap: 20 });
@@ -307,8 +307,11 @@ class Runner {
     }
     /* 候选：去掉前缀后的提交步，投影，打分 */
     const cands = [], near = S.criticalPairs(qe, o.margin + 10).slice(0, 64);
+    // 2026-10-20：全程目标反馈（与 ml/sim/closed_loop.py 的 fb_gain 一致）——一次 DLS，加到所有候选所有步
+    const fbStep = (o.fbGain > 0 && this.goal) ? refineStep(S, qe, this.goal.T, this.goal.R, 0.3).dq : null;
     for (let k = 0; k < K; k++) {
       const inc = this._cand(out.act, k, r);
+      if (fbStep) for (let s = 0; s < H; s++) for (let j = 0; j < 6; j++) inc[s][j] += o.fbGain * fbStep[j];
       let steps = inc.slice(r, r + o.commit), q = qe.slice();
       const adj = [];
       for (const d of steps) {