From 3b6e415d06bd597f1b7cf0ec6f4f26967d92a4d8 Mon Sep 17 00:00:00 2001 From: Nagkumar Arkalgud Date: Mon, 9 Mar 2026 09:06:02 -0700 Subject: [PATCH] Update CHANGELOG.md for azure-ai-evaluation 1.15.3 with missing entry Add missing changelog entry for PR #45522: graceful handling of unresolvable relative image paths from Document Intelligence indexed PDFs in agent tool output. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --- sdk/evaluation/azure-ai-evaluation/CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/sdk/evaluation/azure-ai-evaluation/CHANGELOG.md b/sdk/evaluation/azure-ai-evaluation/CHANGELOG.md index 8b1059c8c086..7a57ed1e49d3 100644 --- a/sdk/evaluation/azure-ai-evaluation/CHANGELOG.md +++ b/sdk/evaluation/azure-ai-evaluation/CHANGELOG.md @@ -10,6 +10,7 @@ - Fixed metadata leak of internal scorer fields (attack_success, attack_strategy, score) into results.json. - Improved error logging with run_id, display_name, and full stack traces for red team scan failures. - Fixed httpx read timeout errors during red team scans by configuring explicit HTTP timeout on PyRIT OpenAIChatTarget instances (default: 180s, configurable via `_http_timeout` scan kwarg). +- Fixed `InvalidInputError` crash when evaluating agent tool output containing unresolvable relative image paths from Document Intelligence indexed PDFs, by gracefully falling back to text representation. ## 1.15.2 (2026-02-23)