feat: HSAP platform v2 — modular navigation, quality review, audit log, world model simulation

Major changes:
- New frontend (platform/web/): Vite + React 18 + TypeScript + Tailwind
- 4-module navigation: 数据送标 / 模型管理 / 车队管理 / 系统管理
- Data catalog with charts (DMS/ADAS/Lane 3-tab view)
- Quality review workflow (标注质检): Good/Fine/Bad scoring with auto-advance
- Audit enhancements: batch operations, rejection categories, Feishu notifications
- Operation audit log (操作日志)
- World model simulation studio (仿真工坊)
- Dataset version management with snapshots and diff
- ADAS 7-class dataset integration (138K images organized + compressed)
- User management with Feishu integration and pagination
- CRUD/search/filter on all pages, card layout redesign
- PIL-optimized image overlay rendering
- Auto-snapshot on build, in_review workflow stage
- Removed embedded algorithm code (now in workspace)

algorithms/lane_ufld/code.embedded.bak/CLRNet-main/clrnet/models/nets/__init__.py

@@ -0,0 +1 @@
+from .detector import Detector 

algorithms/lane_ufld/code.embedded.bak/CLRNet-main/clrnet/models/nets/detector.py

@@ -0,0 +1,36 @@
+import torch.nn as nn
+import torch
+
+from clrnet.models.registry import NETS
+from ..registry import build_backbones, build_aggregator, build_heads, build_necks
+
+
+@NETS.register_module
+class Detector(nn.Module):
+    def __init__(self, cfg):
+        super(Detector, self).__init__()
+        self.cfg = cfg
+        self.backbone = build_backbones(cfg)
+        self.aggregator = build_aggregator(cfg) if cfg.haskey('aggregator') else None
+        self.neck = build_necks(cfg) if cfg.haskey('neck') else None
+        self.heads = build_heads(cfg)
+    
+    def get_lanes(self):
+        return self.heads.get_lanes(output)
+
+    def forward(self, batch):
+        output = {}
+        fea = self.backbone(batch['img'] if isinstance(batch, dict) else batch)
+
+        if self.aggregator:
+            fea[-1] = self.aggregator(fea[-1])
+
+        if self.neck:
+            fea = self.neck(fea)
+
+        if self.training:
+            output = self.heads(fea, batch=batch)
+        else:
+            output = self.heads(fea)
+
+        return output