mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-14 23:21:35 +00:00
PR #17071 drops or errors on reasoning_effort='none' for all GPT models. It doesn't actually allow 'none' to be sent to Azure for gpt-5.1 which supports it according to Azure documentation. See: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning "none is only supported for gpt-5.1" |
||
|---|---|---|
| .. | ||
| test_azure_chat_gpt_transformation.py | ||
| test_azure_chat_o_series_transformation.py | ||
| test_azure_gpt5_transformation.py | ||