feat: implement table cell boxes extraction with SLANeXt

Phase 1-3 implementation of extract-table-cell-boxes proposal:

- Add enable_table_cell_boxes_extraction config option
- Implement lazy-loaded SLANeXt model caching in PPStructureEnhanced
- Add _extract_cell_boxes_with_slanet() method for direct model invocation
- Supplement PPStructureV3 table processing with SLANeXt cell boxes
- Add _compute_table_grid_from_cell_boxes() for column width calculation
- Modify draw_table_region() to use cell_boxes for accurate layout

Key features:
- Auto-detect table type (wired/wireless) using PP-LCNet classifier
- Convert 8-point polygon bbox to 4-point rectangle
- Graceful fallback to equal distribution when cell_boxes unavailable
- Proper coordinate transformation with scaling support

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

backend/app/core/config.py

@@ -161,6 +161,14 @@ class Settings(BaseSettings):
         description="Cell detection model for borderless tables. RT-DETR-L provides best accuracy."
     )
 
+    # Table Cell Boxes Extraction - supplement PPStructureV3 with direct SLANeXt calls
+    # When enabled, directly invokes SLANeXt models to extract cell bounding boxes
+    # which are not exposed by the PPStructureV3 high-level API
+    enable_table_cell_boxes_extraction: bool = Field(
+        default=True,
+        description="Enable direct SLANeXt model calls to extract table cell bounding boxes for accurate PDF layout."
+    )
+
     # Formula Recognition Model Configuration (Stage 4)
     # Available models:
     # - "PP-FormulaNet_plus-L": Best for Chinese formulas (90.64% Chinese, 92.22% English BLEU)