litellm

mirror of https://github.com/BerriAI/litellm.git synced 2026-11-13 08:52:02 +00:00

History

Aasif Multani 54260bec88 fix(bedrock): honor unsupported reasoning effort levels for OpenAI GPT models (#44183 ) Bedrock GPT-5.6 rejects reasoning effort minimal with 400 unsupported_value. The model map already sets supports_minimal_reasoning_effort=false for these models, but neither the Converse path nor the native Responses path read it, so the value was forwarded. Drop it under drop_params and raise UnsupportedParamsError otherwise, matching how the OpenAI GPT-5 path treats explicitly disabled effort levels Co-authored-by: Aasif-Multani <20943280+Aasif-Multani@users.noreply.github.com>	2026-10-02 21:03:58 -07:00
..
__init__.py	test: move tests/test_litellm/llms into tests/unit/llms (#43191 )	2026-09-25 12:43:23 -07:00
test_bedrock_openai_responses.py	fix(bedrock): honor unsupported reasoning effort levels for OpenAI GPT models (#44183 )	2026-10-02 21:03:58 -07:00

fix(bedrock): honor unsupported reasoning effort levels for OpenAI GPT models (#44183 )

Bedrock GPT-5.6 rejects reasoning effort minimal with 400 unsupported_value. The model map already
sets supports_minimal_reasoning_effort=false for these models, but neither the Converse path nor the
native Responses path read it, so the value was forwarded. Drop it under drop_params and raise
UnsupportedParamsError otherwise, matching how the OpenAI GPT-5 path treats explicitly disabled
effort levels

Co-authored-by: Aasif-Multani <20943280+Aasif-Multani@users.noreply.github.com>

2026-10-02 21:03:58 -07:00

__init__.py

test: move tests/test_litellm/llms into tests/unit/llms (#43191 )

2026-09-25 12:43:23 -07:00

test_bedrock_openai_responses.py

fix(bedrock): honor unsupported reasoning effort levels for OpenAI GPT models (#44183 )

2026-10-02 21:03:58 -07:00