fix(ci): restore release gates and contract baseline (fixes #4)

backend/tests/test_sprint134_guided_detection_calibration_runner.py

@@ -1,4 +1,5 @@
 from pathlib import Path
+from tests.frontend_contract import read_feature
 
 
 ROOT = Path(__file__).resolve().parents[2]
@@ -7,12 +8,11 @@ ROOT = Path(__file__).resolve().parents[2]
 def test_detection_lab_has_guided_threshold_calibration_runner() -> None:
     hook = ROOT / "frontend" / "src" / "hooks" / "useDetectionWorkflow.ts"
     lab = ROOT / "frontend" / "src" / "components" / "detection" / "DetectionLab.tsx"
-    app = ROOT / "frontend" / "src" / "App.tsx"
     todo = ROOT / "docs" / "TODO.md"
 
     hook_source = hook.read_text(encoding="utf-8")
     lab_source = lab.read_text(encoding="utf-8")
-    app_source = app.read_text(encoding="utf-8")
+    app_source = read_feature("shell")
     todo_source = todo.read_text(encoding="utf-8")
 
     assert "interface DetectionCalibrationRunRow" in hook_source
@@ -22,22 +22,22 @@ def test_detection_lab_has_guided_threshold_calibration_runner() -> None:
     assert "detectionCalibrationRows" in hook_source
     assert "detectionCalibrationError" in hook_source
     assert "runDetectionCalibration" in hook_source
-    assert "detectionApi.run({" in hook_source
+    assert "executeDetection(" in hook_source
     # Every requested threshold is reported, but from one inference pass at the
     # lowest cut: detections above a higher cut are a subset of it, and
     # suppression walks candidates in descending confidence, so the kept set
     # above a cut does not depend on the threshold the run used. Asserting the
     # old per-threshold loop pinned N GPU passes that produced identical numbers.
-    assert "confidence_threshold: lowestThreshold" in hook_source
+    assert "lowestThreshold," in hook_source
     assert "calibration_thresholds: thresholds" in hook_source
     assert "calibration_sweep" in hook_source
-    assert "parameters_json: { calibration: true, calibration_thresholds: thresholds }" in hook_source
+    assert "{ calibration: true, calibration_thresholds: thresholds }," in hook_source
     assert "detectionApi.compareWithReference(result.analysis_run_id" in hook_source
-    assert "reference_dataset_id: detectionReferenceDatasetId" in hook_source
-    assert "Select a reference dataset before calibration" in hook_source
-    assert "Provide at least one valid threshold between 0 and 1" in hook_source
-    assert "Configured YOLO calibration requires a tile manifest" in hook_source
-    assert "Select a local model asset before calibration" in hook_source
+    assert "reference_dataset_id: referenceDatasetId" in hook_source
+    assert "Kies eerst een referentiebron om te kalibreren" in hook_source
+    assert "Geef minstens één geldige drempel tussen 0 en 1 op" in hook_source
+    assert "Kalibratie met YOLO vereist een beeldtegelmanifest" in hook_source
+    assert "Kies eerst een lokaal modelbestand om te kalibreren" in hook_source
 
     assert "Modelkalibratie voor beheerders" in lab_source
     assert "Voert het lokale model en een kwaliteitscontrole uit" in lab_source