feat: eval benchmark + cloud-trained models replace train/

- eval/: 统一推理评估框架 (infer_train.py, infer_reproduce.py, viz_flow.py,
  viz_signals.py, generate_report.py, run_all.sh, scene_manifest.py)
- train/: 替换为云端正式训练产出，覆盖 11 个场景
  - Karman: Re100 (5 seeds), Re60/200/400 transfer
  - VarDist: d075/d15/d2 scratch
  - Illusion: 0.75L/1.0L/1.5L/2.0L scratch
- train_karman.py: 新增 --resume-from 断点续训支持
- calibrations: 17 组标定数据 (kar/ill 命名规范)
- scripts/: 7 个自动化训练脚本
- 清理旧 calibrations/shell scripts/visualize

Co-authored-by: Cursor <cursoragent@cursor.com>

src/drl_pinball/train/calibrations/kar_d075_tr/calibration.json

@@ -0,0 +1,50 @@
+{
+  "case": "kar_d075_tr",
+  "dist_radius": 0.75,
+  "grid": {
+    "nx": 2000,
+    "ny": 600
+  },
+  "config_path": "/home/frank14f/DynamisLab/configs/config_lbm_karman_2000x600.json",
+  "SI": 800,
+  "FIFO_LEN": 150,
+  "CONV_LEN": 30,
+  "SENSOR_CC": 78.0,
+  "FORCE_SCALE": 0.0018,
+  "SENS_SCALE": 0.84,
+  "dtw_norm_scale": 0.146,
+  "SIM_BP": [
+    0.0,
+    0.25,
+    0.79,
+    0.88,
+    0.94,
+    1.0
+  ],
+  "SIM_VAL": [
+    0.0,
+    0.2,
+    0.5,
+    0.8,
+    0.9,
+    1.0
+  ],
+  "K_CD": 50.0,
+  "K_CL": 100.0,
+  "W_CD": 0.3,
+  "W_CL": 0.3,
+  "W_SIM": 0.4,
+  "FLOOR_CD": 0.1,
+  "FLOOR_CL": 0.1,
+  "FLOOR_SIM": 0.1,
+  "FLOOR_PENALTY": 0.05,
+  "ACTION_SCALE": 12.0,
+  "ACTION_BIAS": [
+    0.0,
+    0.0,
+    0.0
+  ],
+  "U0": 0.01,
+  "RADIUS": 10.0,
+  "L0": 20.0
+}