scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-14 09:03:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 214

fix(count_tokens): leave count_tokenizer out of responses that no named tokenizer counted
Some checks failed
Cost map pins recheck / rerun-cost-map-guard (push) Has been cancelled
Details
LiteLLM Rust DB / db-queries (push) Has been cancelled
Details
LiteLLM Rust / rust-lint (push) Has been cancelled
Details
LiteLLM Rust / rust-test (push) Has been cancelled
Details
LiteLLM Rust / rust-wheel (push) Has been cancelled
Details
Terraform Provider / gofmt, vet, build, test (push) Has been cancelled
Details
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Has been cancelled
Details

Browse source
This commit is contained in:
ryan-crabbe-berri 2026-11-02 17:22:59 -08:00
parent 3e0c4f6e5d
commit ee402443f3
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/types/utils.py
View file

@ -4812,7 +4812,7 @@ class TokenCountResponse(LiteLLMPydanticObjectBase):
model_used: str
tokenizer_type: str
count_source: TokenCountSource | None = None
count_tokenizer: LocalTokenizer | None = None
count_tokenizer: LocalTokenizer | None = Field(default=None, exclude_if=lambda tokenizer: tokenizer is None)
original_response: dict | None = None
"""
Original Response from upstream API call - if an API call was made for token counting