Promote focused small-building detector

backend/tests/test_sprint130_operator_yolo_tile_dataset.py

@@ -69,6 +69,7 @@ def test_operator_yolo_tile_dataset_export_help_does_not_require_gis_dependencie
     assert "Export operator real-data samples to a tile-level YOLO detection dataset" in result.stdout
     assert "--tile-size" in result.stdout
     assert "--stride" in result.stdout
+    assert "--samples" in result.stdout
     assert "--negative-keep-ratio" in result.stdout
     assert "--min-label-visible-ratio" in result.stdout
     assert "--background-negative-repeat" in result.stdout
@@ -84,10 +85,19 @@ def test_default_validation_split_is_explicit_and_rejects_holdout_leakage() -> N
         {"sample_slug": "retie", "recommended_split": "val"},
         {"sample_slug": "westerlo", "recommended_split": "val"},
         {"sample_slug": "arendonk_heide", "recommended_split": "val"},
+        {"sample_slug": "vosselaar_center", "recommended_split": "val"},
+        {"sample_slug": "grobbendonk_center", "recommended_split": "val"},
     ]
 
     assert module.DEFAULT_VALIDATION_SAMPLE_SLUGS == frozenset(
-        {"turnhout", "retie", "westerlo", "arendonk_heide"}
+        {
+            "turnhout",
+            "retie",
+            "westerlo",
+            "arendonk_heide",
+            "vosselaar_center",
+            "grobbendonk_center",
+        }
     )
     assert module.validate_validation_split(
         samples,
@@ -100,6 +110,35 @@ def test_default_validation_split_is_explicit_and_rejects_holdout_leakage() -> N
         module.validate_validation_split(samples, {"turnhout", "missing"})
 
 
+def test_manifest_sample_selection_keeps_external_holdouts_out_of_targeted_dataset() -> None:
+    module = load_tile_exporter()
+    samples = [
+        {"sample_slug": "geel", "recommended_split": "train"},
+        {"sample_slug": "beerse_center", "recommended_split": "train"},
+        {"sample_slug": "vosselaar_center", "recommended_split": "val"},
+        {"sample_slug": "turnhout", "recommended_split": "val"},
+        {"sample_slug": "retie", "recommended_split": "val"},
+        {"sample_slug": "westerlo", "recommended_split": "val"},
+    ]
+
+    selected, excluded = module.select_manifest_samples(
+        samples,
+        {"geel", "beerse_center", "vosselaar_center"},
+    )
+
+    assert [sample["sample_slug"] for sample in selected] == [
+        "geel",
+        "beerse_center",
+        "vosselaar_center",
+    ]
+    assert excluded == ["retie", "turnhout", "westerlo"]
+    assert module.validate_validation_split(selected, {"vosselaar_center"}) == {
+        "vosselaar_center"
+    }
+    with pytest.raises(SystemExit, match="unknown samples"):
+        module.select_manifest_samples(samples, {"geel", "missing"})
+
+
 def test_validation_coverage_reports_holdouts_without_retained_tiles() -> None:
     module = load_tile_exporter()
     coverage = module.validation_sample_coverage(