fix(batch_rate_limiter): warn when no-op per-model skip key is configured

litellm/proxy/hooks/batch_rate_limiter.py

@@ -98,6 +98,7 @@ class _PROXY_BatchRateLimiter(CustomLogger):
         """
         self.internal_usage_cache = internal_usage_cache
         self.parallel_request_limiter = parallel_request_limiter
+        self._warned_unsupported_model_skip = False
 
     def _get_file_bound_batch_model(self, data: Dict) -> Optional[str]:
         """Resolve the model bound to the batch input file ID.
@@ -209,11 +210,13 @@ class _PROXY_BatchRateLimiter(CustomLogger):
         rate-limit descriptor list computed for the no-limits check, so the
         caller can reuse it for counter enforcement without recomputing.
         """
+        from litellm.proxy.proxy_server import general_settings
+
+        self._warn_if_unsupported_model_skip_configured(general_settings)
+
         if self._key_requires_batch_model_access_check(user_api_key_dict):
             return False, None
 
-        from litellm.proxy.proxy_server import general_settings
-
         if general_settings.get("disable_batch_input_file_rate_limiting") is True:
             return True, None
 
@@ -243,6 +246,26 @@ class _PROXY_BatchRateLimiter(CustomLogger):
 
         return False, descriptors
 
+    def _warn_if_unsupported_model_skip_configured(
+        self, general_settings: Dict
+    ) -> None:
+        """Warn once that ``skip_batch_input_file_rate_limiting_for_models`` is a no-op.
+
+        A per-model skip is intentionally not honored because the model a batch
+        runs on is caller-influenced and can be pointed at a skip-listed
+        deployment while the JSONL routes a different, rate-limited model.
+        """
+        if self._warned_unsupported_model_skip:
+            return
+        if general_settings.get("skip_batch_input_file_rate_limiting_for_models"):
+            self._warned_unsupported_model_skip = True
+            verbose_proxy_logger.warning(
+                "general_settings.skip_batch_input_file_rate_limiting_for_models is not "
+                "supported and has no effect. Use "
+                "skip_batch_input_file_rate_limiting_for_providers or "
+                "disable_batch_input_file_rate_limiting instead."
+            )
+
     @staticmethod
     def _key_requires_batch_model_access_check(
         user_api_key_dict: UserAPIKeyAuth,

tests/test_litellm/proxy/hooks/test_batch_file_validation.py

@@ -708,6 +708,57 @@ def test_should_not_skip_for_skip_listed_top_level_model():
     assert should_skip is False
 
 
+def test_warns_once_for_unsupported_model_skip_setting():
+    """Operators who set the no-op per-model skip key get a single warning so a
+    misconfigured deployment does not silently leave batch limits unenforced."""
+    rate_limiter = _make_rate_limiter()
+    rate_limiter.parallel_request_limiter._create_rate_limit_descriptors.return_value = [
+        {"rate_limit": {"requests_per_unit": 5}}
+    ]
+    user = UserAPIKeyAuth(api_key="sk", models=["*"])
+    with (
+        patch(
+            "litellm.proxy.proxy_server.general_settings",
+            {"skip_batch_input_file_rate_limiting_for_models": ["gpt-4o-mini"]},
+        ),
+        patch(
+            "litellm.proxy.hooks.batch_rate_limiter.verbose_proxy_logger"
+        ) as mock_logger,
+    ):
+        for _ in range(3):
+            rate_limiter._should_skip_batch_input_file_processing(
+                data={"model": "gpt-4o-mini", "input_file_id": "file-abc"},
+                user_api_key_dict=user,
+            )
+    assert mock_logger.warning.call_count == 1
+    assert (
+        "skip_batch_input_file_rate_limiting_for_models"
+        in mock_logger.warning.call_args[0][0]
+    )
+
+
+def test_no_warning_when_model_skip_setting_absent():
+    rate_limiter = _make_rate_limiter()
+    rate_limiter.parallel_request_limiter._create_rate_limit_descriptors.return_value = [
+        {"rate_limit": {"requests_per_unit": 5}}
+    ]
+    user = UserAPIKeyAuth(api_key="sk", models=["*"])
+    with (
+        patch(
+            "litellm.proxy.proxy_server.general_settings",
+            {"skip_batch_input_file_rate_limiting_for_providers": ["openai"]},
+        ),
+        patch(
+            "litellm.proxy.hooks.batch_rate_limiter.verbose_proxy_logger"
+        ) as mock_logger,
+    ):
+        rate_limiter._should_skip_batch_input_file_processing(
+            data={"model": "gpt-4o-mini", "input_file_id": "file-abc"},
+            user_api_key_dict=user,
+        )
+    mock_logger.warning.assert_not_called()
+
+
 def test_should_skip_when_no_rate_limits_configured():
     rate_limiter = _make_rate_limiter()
     rate_limiter.parallel_request_limiter._create_rate_limit_descriptors.return_value = [