mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-17 09:34:48 +00:00
test(spend): drop the module docstring from the text completion stream usage test
This commit is contained in:
parent
cc6b89bb64
commit
2bee13d569
1 changed files with 0 additions and 8 deletions
|
|
@ -1,11 +1,3 @@
|
|||
"""A streamed /v1/completions bills its tokens without the client asking for stream_options.include_usage.
|
||||
|
||||
The scripted OpenAI-compatible upstream sends a usage chunk only when the request asks for one, the way OpenAI
|
||||
does, so the proxy has to ask on the client's behalf and keep the answer to itself: the spend row of a streamed
|
||||
text completion with no stream_options equals the include_usage variant's and the non-streamed twin's, and the
|
||||
client gets no usage frame it did not ask for
|
||||
"""
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Final
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue