Azure/azure-sdk-for-python azure-ai-evaluation_1.18.2

on GitHub

1.18.2 (2026-07-21)

Features Added

• Added support for admin-connected (BYO) judge models in prompty-based evaluators. Models configured
  with byo_model and project_endpoint are routed through the Foundry project Responses API, which
  resolves the connection and its authentication.

Bugs Fixed

• Updated TaskNavigationEfficiencyEvaluator validation errors to name both accepted input aliases:
  response / actions and ground_truth / expected_actions.