scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-04 02:31:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 70

fix: clamp max_output_tokens to OpenAI min of 16 in anthropic-to-responses adapter

Browse source
This commit is contained in:
Sipan Petrosyan 2026-04-29 08:23:45 +01:00
parent 6e6b2ca2d8
commit 7fec1b58ea
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/llms/anthropic/experimental_pass_through/responses_adapters/transformation.py
View file

@ -333,8 +333,10 @@ class LiteLLMAnthropicToResponsesAPIAdapter:
responses_kwargs["instructions"] = "\n".join(filter(None, text_parts))
# max_tokens -> max_output_tokens
# OpenAI Responses API requires max_output_tokens >= 16
max_tokens = anthropic_request.get("max_tokens")
if max_tokens:
max_tokens = max(max_tokens, 16)
responses_kwargs["max_output_tokens"] = max_tokens
# temperature / top_p passed through