Files
crewAI/lib/crewai/tests
Devin AI 33ed0a2ad5 fix: detect Azure OpenAI models by endpoint, not just deployment name
Fixes #4478. The is_openai_model flag was only set based on model name
prefixes (gpt-, o1-, text-), but Azure deployment names can be anything
(e.g. gpt5nano). Now is_openai_model is also True when the endpoint is
an Azure OpenAI endpoint (openai.azure.com/openai/deployments/), ensuring
response_model, tool calling, and structured output work regardless of
the deployment name.

Co-Authored-By: João <joao@crewai.com>
2026-02-13 12:31:38 +00:00
..
2026-02-11 15:52:03 -08:00
2025-10-20 14:10:19 -07:00
2025-12-04 16:53:19 -05:00
2025-10-20 14:10:19 -07:00
2025-10-20 14:10:19 -07:00
2025-12-04 13:34:29 -08:00
2025-12-05 13:23:26 -05:00
2026-02-11 15:52:03 -08:00
2025-10-20 14:10:19 -07:00
2025-12-01 18:56:56 -05:00
2025-10-20 14:10:19 -07:00
2025-10-20 14:10:19 -07:00
2025-10-20 14:10:19 -07:00