Make dataset audit mandatory for training loop

backend/tests/test_belgium_training_loop.py

@@ -1,6 +1,9 @@
 from __future__ import annotations
 
 import importlib.util
+import json
+import subprocess
+import sys
 from pathlib import Path
 
 
@@ -29,3 +32,35 @@ def test_training_command_is_cuda_deterministic_and_bound_to_frozen_inputs(tmp_p
     assert "seed=42" in command
     assert "epochs=160" in command
     assert f"data={tmp_path / 'dataset.yaml'}" in command
+
+
+def test_loop_refuses_failed_dataset_audit(tmp_path: Path) -> None:
+    audit = tmp_path / "audit.json"
+    audit.write_text(json.dumps({"status": "needs_attention", "low_variance_positive_tile_count": 4}))
+    result = subprocess.run(
+        [
+            sys.executable,
+            str(SCRIPT),
+            "--initial-model",
+            str(tmp_path / "base.pt"),
+            "--train-yaml",
+            str(tmp_path / "dataset.yaml"),
+            "--dataset-audit",
+            str(audit),
+            "--calibration-summary",
+            str(tmp_path / "cal.json"),
+            "--test-summary",
+            str(tmp_path / "test.json"),
+            "--background-summary",
+            str(tmp_path / "background.json"),
+            "--corpus-manifest",
+            str(tmp_path / "manifest.json"),
+            "--output-dir",
+            str(tmp_path / "output"),
+        ],
+        capture_output=True,
+        text=True,
+        check=False,
+    )
+    assert result.returncode != 0
+    assert "Dataset audit is not ok" in result.stderr