scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-30 01:52:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 70

refactor(proxy): keep tag rate limit helpers within type discipline budget

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-09-18 12:20:18 +00:00
parent e45d65a0e9
commit f94d3ea4a1
1 changed files with 12 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
litellm/proxy/hooks/parallel_request_limiter_v3.py
View file

@ -557,7 +557,17 @@ class TagRateLimit:
tpm_limit: int | None
TagRateLimitResolver: TypeAlias = Callable[[Sequence[str]], Awaitable[Mapping[str, TagRateLimit]]]
class TagRateLimitResolver(Protocol):
def __call__(self, tag_names: Sequence[str], /) -> Awaitable[Mapping[str, TagRateLimit]]: ...
def _tag_rate_limit_descriptor(tag: str, limit: TagRateLimit, window_size: int) -> RateLimitDescriptor:
rate_limit: Final[RateLimitDescriptorRateLimitObject] = {
"requests_per_unit": limit.rpm_limit,
"tokens_per_unit": limit.tpm_limit,
"window_size": window_size,
}
return RateLimitDescriptor(key="tag", value=tag, rate_limit=rate_limit)
async def resolve_tag_rate_limits_from_db(tag_names: Sequence[str]) -> Mapping[str, TagRateLimit]:
@ -2727,15 +2737,7 @@ class _PROXY_MaxParallelRequestsHandler_v3(CustomLogger):
return ()
tag_limits: Final = await self._tag_rate_limit_resolver(tags)
return tuple(
RateLimitDescriptor(
key="tag",
value=tag,
rate_limit={
"requests_per_unit": limit.rpm_limit,
"tokens_per_unit": limit.tpm_limit,
"window_size": self.window_size,
},
)
_tag_rate_limit_descriptor(tag, limit, self.window_size)
for tag in tags
if (limit := tag_limits.get(tag)) is not None
)