scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-20 00:11:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 76
litellm/tests/test_litellm/llms/openai_like/messages
History
Exact
mateo-berri 71a951691a fix(anthropic): cap reasoning_effort thinking budget below max_tokens on /v1/messages 
A deployment carrying reasoning_effort in its litellm_params on the
/v1/messages passthrough mapped the effort to a legacy thinking block
whose budget_tokens was forwarded as is, so any request whose max_tokens
sat at or below that budget was rejected upstream with a 400. The mapped
budget now runs through the same cap the adaptive-to-legacy branch and
the chat path already use: it is clamped to max_tokens - 1, and dropped
with a warning when even the minimum budget cannot fit.

The cap helper becomes public since three call sites outside
AnthropicConfig use it.
2026-08-29 15:24:05 -07:00
..
__init__.py feat(messages): passthrough /v1/messages to native endpoints via supported_endpoints (#31685) 2026-06-30 12:17:33 -07:00
test_openai_like_anthropic_messages_transformation.py fix(anthropic): cap reasoning_effort thinking budget below max_tokens on /v1/messages 2026-08-29 15:24:05 -07:00