From 150616c1a14dff39369dcd33216c0587370dfa8f Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Mon, 11 May 2026 22:43:00 +0000 Subject: [PATCH] feat(exceptions): add RateLimitErrorCategory + headers/detail fields on RateLimitError LiteLLM previously surfaced rate-limit conditions through several unrelated error classes (RateLimitError, FastAPI HTTPException(429), BaseLLMException). This commit adds the data model needed to consolidate them under a single class: * RateLimitErrorCategory enum exposing four categorical values (vendor_rate_limit, vendor_batch_rate_limit, litellm_rate_limit, litellm_batch_rate_limit) so callers can switch on the rate-limit source. * New optional fields on RateLimitError: - category (defaults to vendor_rate_limit, preserving today's behavior for every existing call site in exception_mapping_utils); - headers (preserves retry-after / rate_limit_type / reset_at across the proxy boundary instead of dropping them on the floor); - detail (mirrors FastAPI HTTPException.detail so the same instance can be serialized through both paths). litellm.RateLimitErrorCategory is re-exported at the package root to match the existing exception-export pattern. LIT-2968 Co-authored-by: Mateo Wang --- litellm/__init__.py | 1 + litellm/exceptions.py | 63 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 63 insertions(+), 1 deletion(-) diff --git a/litellm/__init__.py b/litellm/__init__.py index e1b367fb234..3ffb2124956 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -1255,6 +1255,7 @@ from .exceptions import ( NotFoundError, PermissionDeniedError, RateLimitError, + RateLimitErrorCategory, ServiceUnavailableError, BadGatewayError, OpenAIError, diff --git a/litellm/exceptions.py b/litellm/exceptions.py index 8b005291556..6c48b5bdb9d 100644 --- a/litellm/exceptions.py +++ b/litellm/exceptions.py @@ -9,13 +9,45 @@ ## LiteLLM versions of the OpenAI Exception Types -from typing import Any, Dict, Optional +import enum +from typing import Any, Dict, Optional, Union import httpx import openai from litellm.types.utils import LiteLLMCommonStrings + +class RateLimitErrorCategory(str, enum.Enum): + """ + Category of a rate limit error, allowing callers to distinguish where the rate + limit originated. Exposed on every :class:`RateLimitError` instance via the + ``category`` attribute. + + Use these values to switch on the rate limit source, e.g.:: + + try: + ... + except litellm.RateLimitError as e: + if e.category == RateLimitErrorCategory.LITELLM_RATE_LIMIT: + ... # litellm's own limiter (key/team/user/model RPM/TPM/budget) + elif e.category == RateLimitErrorCategory.VENDOR_RATE_LIMIT: + ... # the upstream LLM provider returned 429 + """ + + VENDOR_RATE_LIMIT = "vendor_rate_limit" + """The upstream LLM provider returned a rate-limit response (e.g. OpenAI 429).""" + + VENDOR_BATCH_RATE_LIMIT = "vendor_batch_rate_limit" + """The upstream LLM provider returned a rate-limit response on a batch endpoint.""" + + LITELLM_RATE_LIMIT = "litellm_rate_limit" + """LiteLLM's own rate limiter (key/team/user/model RPM/TPM, budget, parallel-requests, etc.) blocked the request.""" + + LITELLM_BATCH_RATE_LIMIT = "litellm_batch_rate_limit" + """LiteLLM's own batch rate limiter (token/request budget across a batch input file) blocked the request.""" + + _MINIMAL_ERROR_RESPONSE: Optional[httpx.Response] = None @@ -321,6 +353,18 @@ class PermissionDeniedError(openai.PermissionDeniedError): # type: ignore class RateLimitError(openai.RateLimitError): # type: ignore + """ + Unified rate-limit error. + + Every rate-limit condition surfaced by litellm — whether it originated from + an upstream LLM provider, a vendor batch endpoint, or one of litellm's own + proxy-side limiters (parallel-requests, dynamic-rate, batch-rate, budget, + max-iterations, etc.) — is raised as an instance of this class. + + The :attr:`category` attribute lets callers distinguish the source. See + :class:`RateLimitErrorCategory` for the available values. + """ + def __init__( self, message, @@ -330,6 +374,11 @@ class RateLimitError(openai.RateLimitError): # type: ignore litellm_debug_info: Optional[str] = None, max_retries: Optional[int] = None, num_retries: Optional[int] = None, + category: Union[str, RateLimitErrorCategory] = ( + RateLimitErrorCategory.VENDOR_RATE_LIMIT + ), + headers: Optional[Dict[str, str]] = None, + detail: Any = None, ): self.status_code = 429 self.message = "litellm.RateLimitError: {}".format(message) @@ -338,9 +387,21 @@ class RateLimitError(openai.RateLimitError): # type: ignore self.litellm_debug_info = litellm_debug_info self.max_retries = max_retries self.num_retries = num_retries + self.category = ( + category.value if isinstance(category, RateLimitErrorCategory) else category + ) + # Headers carried with the error (e.g. retry-after, rate_limit_type, + # reset_at). Preserved across the proxy boundary so clients can react + # appropriately. _response_headers = ( getattr(response, "headers", None) if response is not None else None ) + self.headers: Optional[Dict[str, str]] = ( + {k: str(v) for k, v in headers.items()} if headers else None + ) or (dict(_response_headers) if _response_headers else None) + # Mirrors FastAPI HTTPException.detail so the same instance can be + # serialized through both the ProxyException and HTTPException paths. + self.detail = detail if detail is not None else self.message self.response = httpx.Response( status_code=429, headers=_response_headers,