Upgrade async GPU analysis and workbench UX

backend/app/services/segmentation_service.py

@@ -272,6 +272,8 @@ class SegmentationService:
         dataset_id: uuid.UUID | None = None,
         class_name: str | None = None,
         min_confidence: float | None = None,
+        limit: int | None = None,
+        offset: int = 0,
     ) -> SegmentationListResponse:
         if analysis_run_id is not None:
             run = db.get(AnalysisRun, analysis_run_id)
@@ -284,8 +286,19 @@ class SegmentationService:
             class_name=class_name,
             min_confidence=min_confidence,
         )
-        items = [SegmentationRead.model_validate(row) for row in rows]
-        return SegmentationListResponse(items=items, total=len(items))
+        resolved_limit = DetectionService.DEFAULT_RESULT_LIMIT if limit is None else int(limit)
+        page, total, truncated = DetectionService.paginate(
+            rows,
+            limit=resolved_limit,
+            offset=offset,
+        )
+        return SegmentationListResponse(
+            items=[SegmentationRead.model_validate(row) for row in page],
+            total=total,
+            limit=resolved_limit,
+            offset=max(0, int(offset)),
+            truncated=truncated,
+        )
 
     @staticmethod
     def get_segmentation(db, segmentation_id: uuid.UUID) -> SegmentationRead:
@@ -847,7 +860,6 @@ class SegmentationService:
             "suppressed_segmentation_count": len(candidates) - len(filtered_candidates),
             "duplicate_iou_threshold": float(settings.segmentation_duplicate_iou_threshold),
             "containment_suppression_threshold": float(settings.segmentation_containment_nms_threshold),
-            "duplicate_iou_threshold": float(settings.segmentation_duplicate_iou_threshold),
             "tile_manifest_path": str(Path(tile_manifest_path or "").expanduser()),
             "runtime_model_provenance": runtime_model_provenance.as_dict(),
         }