scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-11 03:38:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 84

fix(router): keep the cast-ok suppression on the cast line for the type discipline gate

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
yassin 2026-10-02 05:06:53 +00:00
parent 0d7c17d32e
commit 19c5790a91
1 changed files with 1 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/router_strategy/lowest_tpm_rpm_v2.py
View file

@ -423,10 +423,8 @@ class LowestTPMLoggingHandler_v2(BaseRoutingStrategy, CustomLogger):
for idx, key in enumerate(rpm_keys):
rpm_dict[rpm_keys[idx].split(":")[0]] = rpm_values[idx]
deployments: Final = cast(Sequence[Mapping[str, object]], healthy_deployments) # cast-ok: untyped dicts
input_tokens = 0
deployments: Final = cast(
Sequence[Mapping[str, object]], healthy_deployments
) # cast-ok: router deployments are untyped dicts at this boundary
if any(_declares_tpm_limit(deployment) for deployment in deployments):
try:
input_tokens = token_counter(messages=messages, text=input)