Fix raising wrong 429 error on wrong exception (#16482)

* fix raising wrong 429 error on wrong exception

* remove double re import

litellm/litellm_core_utils/exception_mapping_utils.py

@@ -3,6 +3,7 @@ import traceback
 from typing import Any, Optional
 
 import httpx
+import re
 
 import litellm
 from litellm._logging import verbose_logger
@@ -45,13 +46,20 @@ class ExceptionCheckers:
         if not isinstance(error_str, str):
             return False
 
-        if "429" in error_str or "rate limit" in error_str.lower():
+        # Only treat 429 as a rate limit signal when it appears as a standalone token
+        if re.search(r"\b429\b", error_str):
+            return True
+
+        _error_str_lower = error_str.lower()
+
+        # Match "rate limit" (including variations like rate-limit / rate_limit)
+        if re.search(r"rate[\s_\-]*limit", _error_str_lower):
             return True
 
         #######################################
         # Mistral API returns this error string
         #########################################
-        if "service tier capacity exceeded" in error_str.lower():
+        if "service tier capacity exceeded" in _error_str_lower:
             return True
 
         return False
@@ -155,9 +163,6 @@ def _get_response_headers(original_exception: Exception) -> Optional[httpx.Heade
     return _response_headers
 
 
-import re
-
-
 def extract_and_raise_litellm_exception(
     response: Optional[Any],
     error_str: str,

tests/test_litellm/litellm_core_utils/test_exception_mapping_utils.py

@@ -57,6 +57,20 @@ def test_is_error_str_context_window_exceeded(error_str, expected):
 class TestExceptionCheckers:
     """Test the ExceptionCheckers utility methods"""
 
+    def test_is_error_str_rate_limit_ignores_embedded_numbers(self):
+        """An arbitrary 429 inside user-provided payload must not trigger rate-limit detection"""
+
+        error_str = "Invalid user message={'role': 'user', 'content': [{'text': 'payload429snippet'}]}"
+        result = ExceptionCheckers.is_error_str_rate_limit(error_str)
+        assert result is False
+
+    def test_is_error_str_rate_limit_detects_true_rate_limit(self):
+        """A real rate-limit error string should still be detected"""
+
+        error_str = "RateLimitError: OpenAIException - You exceeded your current quota. (status code 429)"
+        result = ExceptionCheckers.is_error_str_rate_limit(error_str)
+        assert result is True
+
     def test_is_azure_content_policy_violation_error_with_policy_violation_text(self):
         """Test detection of Azure content policy violation with explicit policy violation text"""