litellm/tests/test_litellm/llms/azure_ai/chat
mateo-berri fffe0bb0dc test(azure_ai): pin the tier the messages bridge sends when astra refuses max
The /v1/messages adapter lowers a tier the entry does not accept, so dropping max from the astra
rows moves that path from Foundry's 400 to a request at xhigh. Nothing pinned that, and the guard
test's docstring named gpt-6-astra as the only gpt-5 name with an azure_ai row, which 11 rows
contradict.
2026-09-05 23:18:25 -07:00
..
test_azure_ai_transformation.py test(azure_ai): pin the tier the messages bridge sends when astra refuses max 2026-09-05 23:18:25 -07:00