Bugfix/19481 num retries env var type (#19507)

* Enhance error handling for num_retries in Router class to support string values. Add test case to verify conversion from string to int for deployment num_retries.

* Refactor Router class for improved readability by formatting long lines and enhancing exception handling tests for num_retries. Ensure consistent style in test cases for better maintainability.

* Update exception handling for num_retries in Router class to suppress mypy warnings. Add type ignore comment for clarity in type conversion from string to int.

litellm/router.py

@@ -1696,8 +1696,11 @@ class Router:
 
         litellm_params = deployment.get("litellm_params", {})
         dep_num_retries = litellm_params.get("num_retries")
-        if dep_num_retries is not None and isinstance(dep_num_retries, int):
-            exception.num_retries = dep_num_retries  # type: ignore
+        if dep_num_retries is not None:
+            try:
+                exception.num_retries = int(dep_num_retries)  # type: ignore  # Handle both int and str
+            except (ValueError, TypeError):
+                pass  # Skip if value can't be converted to int
 
     def _update_kwargs_with_default_litellm_params(
         self, kwargs: dict, metadata_variable_name: Optional[str] = "metadata"
@@ -4692,9 +4695,12 @@ class Router:
                 # get num_retries from retry policy
                 # Use the model_group captured at the start of the function, or get it from metadata
                 # kwargs.get("model") at this point is the deployment model, not the model_group
-                _model_group_for_retry_policy = model_group or _metadata.get("model_group") or kwargs.get("model")
+                _model_group_for_retry_policy = (
+                    model_group or _metadata.get("model_group") or kwargs.get("model")
+                )
                 _retry_policy_retries = self.get_num_retries_from_retry_policy(
-                    exception=original_exception, model_group=_model_group_for_retry_policy
+                    exception=original_exception,
+                    model_group=_model_group_for_retry_policy,
                 )
                 if _retry_policy_retries is not None:
                     num_retries = _retry_policy_retries
@@ -5879,7 +5885,10 @@ class Router:
             )
             # done reading model["litellm_params"]
             # Check if provider is supported: either in enum or JSON-configured
-            if custom_llm_provider not in litellm.provider_list and not JSONProviderRegistry.exists(custom_llm_provider):
+            if (
+                custom_llm_provider not in litellm.provider_list
+                and not JSONProviderRegistry.exists(custom_llm_provider)
+            ):
                 raise Exception(f"Unsupported provider - {custom_llm_provider}")
 
         #### DEPLOYMENT NAMES INIT ########

tests/test_litellm/test_router_per_deployment_num_retries.py

@@ -32,17 +32,17 @@ class TestPerDeploymentNumRetries:
         )
 
         deployment = router.model_list[0]
-        
+
         # Create a mock exception without num_retries
         class MockException(Exception):
             pass
-        
+
         exc = MockException("test error")
         assert not hasattr(exc, "num_retries") or exc.num_retries is None
-        
+
         # Call the helper
         router._set_deployment_num_retries_on_exception(exc, deployment)
-        
+
         # Verify num_retries was set from deployment
         assert exc.num_retries == 5
 
@@ -66,16 +66,16 @@ class TestPerDeploymentNumRetries:
         )
 
         deployment = router.model_list[0]
-        
+
         # Create an exception that already has num_retries
         class MockException(Exception):
             num_retries = 10  # Already set
-        
+
         exc = MockException("test error")
-        
+
         # Call the helper
         router._set_deployment_num_retries_on_exception(exc, deployment)
-        
+
         # Verify num_retries was NOT overridden
         assert exc.num_retries == 10
 
@@ -99,15 +99,15 @@ class TestPerDeploymentNumRetries:
         )
 
         deployment = router.model_list[0]
-        
+
         class MockException(Exception):
             pass
-        
+
         exc = MockException("test error")
-        
+
         # Call the helper
         router._set_deployment_num_retries_on_exception(exc, deployment)
-        
+
         # Verify num_retries was not set (deployment has no num_retries)
         assert not hasattr(exc, "num_retries") or exc.num_retries is None
 
@@ -155,3 +155,36 @@ class TestPerDeploymentNumRetries:
         kwargs = {}
         router._update_kwargs_before_fallbacks(model="test-model", kwargs=kwargs)
         assert kwargs["num_retries"] == 7  # Uses global
+
+    def test_set_deployment_num_retries_with_string_value(self):
+        """
+        Test that _set_deployment_num_retries_on_exception handles string values
+        from environment variables correctly.
+        GitHub Issue: #19481
+        """
+        router = Router(
+            model_list=[
+                {
+                    "model_name": "test-model",
+                    "litellm_params": {
+                        "model": "openai/gpt-4",
+                        "api_key": "test-key",
+                        "num_retries": "6",  # String value (as from env var)
+                    },
+                },
+            ],
+            num_retries=0,  # Global setting
+        )
+
+        deployment = router.model_list[0]
+
+        class MockException(Exception):
+            pass
+
+        exc = MockException("test error")
+
+        # Call the helper
+        router._set_deployment_num_retries_on_exception(exc, deployment)
+
+        # Verify num_retries was converted from string to int
+        assert exc.num_retries == 6