refactor(simple_metrics): extract threshold_breaches helper (SIENTIAPDE-2191)

laborious/activities/model_metrics.py

@@ -26,6 +26,28 @@ warnings.filterwarnings(
 )
 
 
+def threshold_breaches(
+    rows: list[dict[str, Any]], thresholds: dict[str, float] | None
+) -> list[str]:
+    """
+    Breach messages for metric rows outside their configured thresholds.
+
+    Convention: `<metric>_max` breaches when value > threshold, `<metric>_min` when value <
+    threshold. Shared by the breach alert and the adaptive-state rule so both agree on what a
+    breach is.
+    """
+    thresholds = thresholds or {}
+    breaches = []
+    for row in rows:
+        metric_name, value = row['metric'], row['value']
+        max_key, min_key = f'{metric_name}_max', f'{metric_name}_min'
+        if max_key in thresholds and value > thresholds[max_key]:
+            breaches.append(f'{metric_name}={value} exceeds {max_key}={thresholds[max_key]}')
+        elif min_key in thresholds and value < thresholds[min_key]:
+            breaches.append(f'{metric_name}={value} below {min_key}={thresholds[min_key]}')
+    return breaches
+
+
 class ModelMetrics(SientiaMonitoring):
     """
     Metrics and statistical analysis activities for the Laborious pipeline.
@@ -430,23 +452,7 @@ class ModelMetrics(SientiaMonitoring):
         self._debug_dataframe(f'Simple metrics dataframe: Size {data.shape}', data, metadata)
 
         # Threshold alerting (optional — no crash when absent)
-        thresholds = input_data.get('thresholds')
+        for breach_msg in threshold_breaches(output_data, input_data.get('thresholds')):
-        if thresholds:
-            # Convention: _max thresholds breach when value > threshold,
-            #             _min thresholds breach when value < threshold.
-            for row in output_data:
-                metric_name = row['metric']
-                value = row['value']
-                max_key = f'{metric_name}_max'
-                min_key = f'{metric_name}_min'
-
-                breach_msg = None
-                if max_key in thresholds and value > thresholds[max_key]:
-                    breach_msg = f'{metric_name}={value} exceeds {max_key}={thresholds[max_key]}'
-                elif min_key in thresholds and value < thresholds[min_key]:
-                    breach_msg = f'{metric_name}={value} below {min_key}={thresholds[min_key]}'
-
-                if breach_msg:
             message = (
                 f'Threshold breach for model {model_id} '
                 f'(window {interval_minutes} min): {breach_msg}'

tests/laborious/activities/test_model_metrics.py

@@ -7,7 +7,7 @@ from sientia_do.observability.metrics_controller import MetricsController
 from sientia_do.temporal.constants import DATETIME_FORMAT_WITH_TZ
 from sientia_model.analytics.drift_analysis import DriftInsufficientDataError
 
-from laborious.activities.model_metrics import ModelMetrics
+from laborious.activities.model_metrics import ModelMetrics, threshold_breaches
 
 
 @fixture
@@ -1221,3 +1221,24 @@ def test_to_naive_utc_keeps_naive_timestamps():
 
     assert result.dt.tz is None
     assert result.tolist() == [Timestamp('2024-01-01 06:00:00')]
+
+
+@mark.parametrize(
+    'rows, thresholds, expected_count',
+    [
+        ([{'metric': 'rmse', 'value': 2.0}], {'rmse_max': 1.0}, 1),
+        ([{'metric': 'rmse', 'value': 0.5}], {'rmse_max': 1.0}, 0),
+        ([{'metric': 'r2', 'value': 0.5}], {'r2_min': 0.9}, 1),
+        ([{'metric': 'r2', 'value': 0.95}], {'r2_min': 0.9}, 0),
+        ([{'metric': 'mae', 'value': 99.0}], {'rmse_max': 1.0}, 0),
+        ([{'metric': 'rmse', 'value': 99.0}], None, 0),
+        ([], {'rmse_max': 1.0}, 0),
+        (
+            [{'metric': 'rmse', 'value': 2.0}, {'metric': 'r2', 'value': 0.1}],
+            {'rmse_max': 1.0, 'r2_min': 0.9},
+            2,
+        ),
+    ],
+)
+def test_threshold_breaches(rows, thresholds, expected_count):
+    assert len(threshold_breaches(rows, thresholds)) == expected_count