scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-03 02:22:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 81

feat: expose requested vs response model mismatch in proxy logs (#29680)

Browse source
This commit is contained in:
Het1819 2026-06-04 17:02:48 -04:00
parent 1c881eee5d
commit 4cf9229dfb
2 changed files with 604 additions and 1021 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1600
litellm/litellm_core_utils/litellm_logging.py
View file

File diff suppressed because it is too large Load diff

25
litellm/types/utils.py
View file

@ -39,7 +39,7 @@ from pydantic import (
PrivateAttr,
field_validator,
)
from typing_extensions import Required, TypedDict
from typing_extensions import Required, TypedDict, NotRequired
from litellm._uuid import uuid
from litellm.types.llms.base import (
@ -2727,25 +2727,9 @@ class StandardLoggingPayloadErrorInformation(TypedDict, total=False):
llm_provider: Optional[str]
traceback: Optional[str]
error_message: Optional[str]
# error_rate_limit_category:
# For 429 / rate-limit errors, the source of the rate limit. One of the
# string values defined by `litellm.exceptions.RateLimitErrorCategory`
# (vendor_rate_limit, vendor_batch_rate_limit, litellm_rate_limit,
# litellm_batch_rate_limit). None for non-rate-limit exceptions.
# Surfaced here so custom callbacks / metrics consumers can switch on
# the rate-limit source without reaching for the raw exception.
error_rate_limit_category: Optional[str]
# error_rate_limit_type:
# For 429 / rate-limit errors, the dimension that was exceeded. One of
# the string values defined by `litellm.exceptions.RateLimitType`
# (requests, tokens, concurrent_requests, budget, max_iterations).
# None for non-rate-limit exceptions and for rate-limit exceptions that
# did not classify the failure (e.g. legacy vendor 429 with no header
# hints). Lets dashboards split rate-limit failures by cause without
# parsing free-text error messages.
error_rate_limit_type: Optional[str]
class GuardrailMode(TypedDict, total=False):
tags: Optional[Dict[str, Union[str, List[str]]]]
default: Optional[Union[str, List[str]]]
@ -2980,7 +2964,12 @@ class StandardLoggingPayload(TypedDict):
hidden_params: StandardLoggingHiddenParams
guardrail_information: Optional[List[StandardLoggingGuardrailInformation]]
standard_built_in_tools_params: Optional[StandardBuiltInToolsParams]
# Add these 5 lines for Issue #29680:
requested_model: NotRequired[str]
resolved_model: NotRequired[str]
response_model: NotRequired[str]
model_mismatch: NotRequired[Union[str, bool]]
usage_source: NotRequired[str]
from typing import AsyncIterator, Iterator