From 11ee5089112ed2e1d48e638c126f587ae606d5ba Mon Sep 17 00:00:00 2001 From: Ankit Singhal Date: Thu, 17 Sep 2026 21:59:15 -0700 Subject: [PATCH] [Evaluation] Prepare azure-ai-evaluation 1.18.6 release Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> --- sdk/evaluation/azure-ai-evaluation/CHANGELOG.md | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/sdk/evaluation/azure-ai-evaluation/CHANGELOG.md b/sdk/evaluation/azure-ai-evaluation/CHANGELOG.md index 2be0093f9027..b0633c6f4e7a 100644 --- a/sdk/evaluation/azure-ai-evaluation/CHANGELOG.md +++ b/sdk/evaluation/azure-ai-evaluation/CHANGELOG.md @@ -1,14 +1,15 @@ # Release History -## 1.18.6 (Unreleased) +## 1.18.6 (2026-09-17) ### Features Added -### Breaking Changes +- Added the `aoai_output_items_page_size` keyword argument to `evaluate` to configure the number of native Azure OpenAI grader output items requested per page. Accepts integers from 1 to 100 and defaults to 100; all result pages are still retrieved. ### Bugs Fixed -### Other Changes +- Improved native Azure OpenAI grader result retrieval by retrying output-item requests with a smaller page size after timeouts or retryable HTTP 408 and 504 responses. + [#49034](https://github.com/Azure/azure-sdk-for-python/pull/49034) ## 1.18.5 (2026-09-02)