Add operator YOLO training dataset tooling

backend/tests/test_sprint129_operator_yolo_training_dataset.py

@@ -0,0 +1,68 @@
+from pathlib import Path
+import subprocess
+import sys
+
+
+ROOT = Path(__file__).resolve().parents[2]
+
+
+def test_operator_yolo_dataset_export_script_contract() -> None:
+    script_path = ROOT / "scripts" / "export_operator_yolo_dataset.py"
+    readiness = (ROOT / "scripts" / "run_readiness_check.sh").read_text(encoding="utf-8")
+
+    assert script_path.exists()
+    script = script_path.read_text(encoding="utf-8")
+
+    assert "py_compile scripts/export_operator_yolo_dataset.py" in readiness
+    assert "operator_samples_manifest.json" in script
+    assert "dataset.yaml" in script
+    assert "images/train" in script
+    assert "labels/train" in script
+    assert "images/val" in script
+    assert "labels/val" in script
+    assert "building" in script
+    assert "reference_feature_count" in script
+    assert "source_name" in script
+    assert "reference_layer_name" in script
+    assert "rasterio" in script
+    assert "Transformer" in script
+    assert "demo/workflow" not in script
+    assert "fixture_mode" not in script
+    assert "will_download_models" not in script
+
+
+def test_operator_yolo_dataset_export_help_does_not_require_gis_dependencies() -> None:
+    script_path = ROOT / "scripts" / "export_operator_yolo_dataset.py"
+
+    result = subprocess.run(
+        [sys.executable, str(script_path), "--help"],
+        check=False,
+        capture_output=True,
+        text=True,
+    )
+
+    assert result.returncode == 0
+    assert "Export operator real-data samples to a YOLO detection dataset" in result.stdout
+    assert "--manifest-path" in result.stdout
+    assert "--val-samples" in result.stdout
+
+
+def test_operator_yolo_train_smoke_script_contract() -> None:
+    script_path = ROOT / "scripts" / "train_operator_yolo_detector.sh"
+    readiness = (ROOT / "scripts" / "run_readiness_check.sh").read_text(encoding="utf-8")
+
+    assert script_path.exists()
+    script = script_path.read_text(encoding="utf-8")
+
+    assert "bash -n scripts/train_operator_yolo_detector.sh" in readiness
+    assert "OPERATOR_YOLO_DATASET_DIR" in script
+    assert "YOLO_BASE_MODEL_PATH" in script
+    assert "TRAIN_MODEL_OUTPUT_PATH" in script
+    assert "TRAIN_EPOCHS" in script
+    assert "TRAIN_IMGSZ" in script
+    assert "dataset.yaml" in script
+    assert "from ultralytics import YOLO" in script
+    assert "model.train" in script
+    assert "training_summary.json" in script
+    assert "download" not in script.lower()
+    assert "fixture_mode" not in script