From 8c9a58948ba7c05552448ee29994757a62e11217 Mon Sep 17 00:00:00 2001
From: Jens <jens@localhost>
Date: Wed, 29 Jul 2026 17:21:18 +0200
Subject: [PATCH] Support governed train-only corpus shards

---
 ...st_sprint130_operator_yolo_tile_dataset.py |  9 +++++++
 scripts/export_operator_yolo_tile_dataset.py  | 26 ++++++++++++++++---
 2 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/backend/tests/test_sprint130_operator_yolo_tile_dataset.py b/backend/tests/test_sprint130_operator_yolo_tile_dataset.py
index a813c6a6..ce4432bf 100644
--- a/backend/tests/test_sprint130_operator_yolo_tile_dataset.py
+++ b/backend/tests/test_sprint130_operator_yolo_tile_dataset.py
@@ -142,6 +142,15 @@ def test_manifest_sample_selection_keeps_external_holdouts_out_of_targeted_datas
         module.select_manifest_samples(samples, {"geel", "missing"})
 
 
+def test_train_only_shard_requires_explicit_opt_in() -> None:
+    module = load_tile_exporter()
+    samples = [{"sample_slug": "new-train-aoi", "recommended_split": "train"}]
+
+    with pytest.raises(SystemExit, match="must include at least one"):
+        module.validate_validation_split(samples, set())
+    assert module.validate_validation_split(samples, set(), allow_empty=True) == set()
+
+
 def test_validation_coverage_reports_holdouts_without_retained_tiles() -> None:
     module = load_tile_exporter()
     coverage = module.validation_sample_coverage(
diff --git a/scripts/export_operator_yolo_tile_dataset.py b/scripts/export_operator_yolo_tile_dataset.py
index 1dbccef6..bc772f7d 100644
--- a/scripts/export_operator_yolo_tile_dataset.py
+++ b/scripts/export_operator_yolo_tile_dataset.py
@@ -110,6 +110,14 @@ def parse_args() -> argparse.Namespace:
             "Defaults to all documented validation samples."
         ),
     )
+    parser.add_argument(
+        "--allow-empty-validation",
+        action="store_true",
+        help=(
+            "Allow a train-only export shard with no validation AOI. This is only for later "
+            "composition into a dataset whose independent validation split is supplied separately."
+        ),
+    )
     parser.add_argument(
         "--negative-keep-ratio",
         type=float,
@@ -210,13 +218,20 @@ def select_manifest_samples(
     return selected, excluded
 
 
-def validate_validation_split(samples: list[dict[str, Any]], val_slugs: set[str]) -> set[str]:
+def validate_validation_split(
+    samples: list[dict[str, Any]],
+    val_slugs: set[str],
+    *,
+    allow_empty: bool = False,
+) -> set[str]:
     sample_slugs = {
         str(sample.get("sample_slug") or "").strip().lower()
         for sample in samples
         if str(sample.get("sample_slug") or "").strip()
     }
     if not val_slugs:
+        if allow_empty:
+            return set()
         raise SystemExit("YOLO validation split must include at least one sample")
     unknown = val_slugs - sample_slugs
     if unknown:
@@ -625,7 +640,11 @@ def main() -> int:
         manifest_samples,
         split_slugs(args.samples),
     )
-    val_slugs = validate_validation_split(samples, split_slugs(args.val_samples))
+    val_slugs = validate_validation_split(
+        samples,
+        split_slugs(args.val_samples),
+        allow_empty=args.allow_empty_validation,
+    )
     exported_tiles: list[dict[str, Any]] = []
     for sample in samples:
         exported_tiles.extend(
@@ -650,7 +669,7 @@ def main() -> int:
     kept_tiles = [tile for tile in exported_tiles if tile["kept"]]
     if not any(tile["split"] == "train" for tile in kept_tiles):
         raise SystemExit("YOLO tile dataset export produced no training tiles")
-    if not any(tile["split"] == "val" for tile in kept_tiles):
+    if not args.allow_empty_validation and not any(tile["split"] == "val" for tile in kept_tiles):
         raise SystemExit("YOLO tile dataset export produced no validation tiles")
     dataset_yaml = write_dataset_yaml(args.output_dir, class_name)
     positive_tiles = [tile for tile in kept_tiles if not tile["is_negative"]]
@@ -684,6 +703,7 @@ def main() -> int:
         ),
         "excluded_sample_slugs": excluded_sample_slugs,
         "validation_sample_slugs": sorted(val_slugs),
+        "train_only_shard": args.allow_empty_validation,
         **validation_coverage,
         "tile_count": len(kept_tiles),
         "positive_tile_count": len(positive_tiles),