Merge 2259ded1e6 into 2dccc0dc79

litellm/integrations/prometheus.py

@@ -3531,13 +3531,17 @@ class PrometheusLogger(CustomLogger):
         """
         increment metric when litellm.Router / load balancing logic places a deployment in cool down
         """
-        self.litellm_deployment_cooled_down.labels(
-            _sanitize_prometheus_label_value(litellm_model_name),
-            _sanitize_prometheus_label_value(model_id),
-            _sanitize_prometheus_label_value(api_base),
-            _sanitize_prometheus_label_value(api_provider),
-            _sanitize_prometheus_label_value(exception_status),
-        ).inc()
+        _labels: Final = prometheus_label_factory(
+            supported_enum_labels=self.get_labels_for_metric(metric_name="litellm_deployment_cooled_down"),
+            enum_values=UserAPIKeyLabelValues(
+                litellm_model_name=litellm_model_name,
+                model_id=model_id,
+                api_base=api_base,
+                api_provider=api_provider,
+                exception_status=exception_status,
+            ),
+        )
+        self.litellm_deployment_cooled_down.labels(**_labels).inc()
 
     def increment_callback_logging_failure(
         self,

tests/enterprise/litellm_enterprise/enterprise_callbacks/test_prometheus_logging_callbacks.py

@@ -1222,7 +1222,11 @@ def test_increment_deployment_cooled_down(prometheus_logger):
     )
 
     prometheus_logger.litellm_deployment_cooled_down.labels.assert_called_once_with(
-        "gpt-5-mini", "model-123", "https://api.openai.com", "openai", "429"
+        litellm_model_name="gpt-5-mini",
+        model_id="model-123",
+        api_base="https://api.openai.com",
+        api_provider="openai",
+        exception_status="429",
     )
     mock_chain.inc.assert_called_once()
 

tests/test_litellm/integrations/test_prometheus_custom_metadata_label_counts.py

@@ -157,3 +157,29 @@ def test_virtual_key_rate_limit_metrics_preserve_zero_remaining_values(
     assert any(sample.value == 0 for sample in token_samples)
     assert not any(sample.value == sys.maxsize for sample in request_samples)
     assert not any(sample.value == sys.maxsize for sample in token_samples)
+
+
+def test_increment_deployment_cooled_down_accepts_custom_metadata_labels(
+    monkeypatch: pytest.MonkeyPatch, caplog: pytest.LogCaptureFixture
+):
+    prometheus_logger = _create_prometheus_logger_with_custom_labels(monkeypatch)
+
+    with caplog.at_level(logging.ERROR):
+        prometheus_logger.increment_deployment_cooled_down(
+            litellm_model_name="gpt-4o-mini",
+            model_id="model-123",
+            api_base="https://api.openai.com",
+            api_provider="openai",
+            exception_status="429",
+        )
+
+    assert "Incorrect label count" not in caplog.text
+    samples = _metric_samples("litellm_deployment_cooled_down_total")
+    assert any(
+        sample.labels.get("litellm_model_name") == "gpt-4o-mini"
+        and sample.labels.get("exception_status") == "429"
+        and "metadata_department" in sample.labels
+        and "metadata_environment" in sample.labels
+        and sample.value == 1
+        for sample in samples
+    )