Pass is_reasoning_model through QAEvaluator

[nagkumar91]

Fixes #43842

• QAEvaluator now forwards is_reasoning_model to its LLM-based sub-evaluators (Groundedness/Relevance/Coherence/Fluency/Similarity), preventing max_tokens from being sent to reasoning models.
• Added unit tests to verify propagation.

Tests:

• python -m pytest sdk/evaluation/azure-ai-evaluation/tests/unittests/test_qa_evaluator.py -q

[Copilot]

Pull request overview

This pull request addresses issue #43842 by enabling the QAEvaluator to forward the is_reasoning_model parameter to its LLM-based sub-evaluators. This prevents max_tokens from being sent to reasoning models (o1/o3) which don't support that parameter.

Changes:

• Modified QAEvaluator to extract is_reasoning_model from kwargs and pass it to all LLM-based sub-evaluators (Groundedness, Relevance, Coherence, Fluency, Similarity)
• Added comprehensive unit tests to verify the parameter is correctly propagated to sub-evaluators
• Added an unrelated change to set a default value for image_tag in AzureOpenAIPythonGrader

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

File	Description
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_evaluators/_qa/_qa.py	Extracts is_reasoning_model from kwargs and forwards it to all LLM-based sub-evaluators
sdk/evaluation/azure-ai-evaluation/tests/unittests/test_qa_evaluator.py	Adds unit tests verifying is_reasoning_model propagation to sub-evaluators
sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/_aoai/python_grader.py	Unrelated change: adds default value "2025-05-08" for image_tag parameter
sdk/evaluation/azure-ai-evaluation/tests/unittests/test_aoai_python_grader.py	Unrelated change: adds test for image_tag default value

[Copilot]

This change appears unrelated to the main PR purpose of passing is_reasoning_model through QAEvaluator. The addition of a default value for image_tag should ideally be in a separate PR. Additionally, the default date "2025-05-08" appears to be in the past (current date is January 2026), which may indicate this is an outdated value or there's a version/tag naming convention that isn't immediately clear.

[github-actions]

API Change Check

APIView identified API level changes in this PR and created the following API reviews

azure-ai-evaluation