Simulator using structured outputs for conversation and conversation ID

[nagkumar91]

Description

Please add an informative description that covers that changes made by the pull request and link all relevant issues.

If an SDK is being regenerated based on a new swagger spec, a link to the pull request containing these swagger spec changes has been included above.

All SDK Contribution checklist:

• The pull request does not introduce [breaking changes]
• CHANGELOG is updated for new features, bug fixes or other significant changes.
• I have read the contribution guidelines.

General Guidelines and Best Practices

• Title of the pull request is clear and informative.
• There are a small number of commits, each of which have an informative message. This means that previously merged commits do not appear in the history of the PR. For more information on cleaning up the commits in your PR, see this page.

Testing Guidelines

• Pull request includes test coverage for the included changes.

[Copilot]

Copilot reviewed 5 out of 6 changed files in this pull request and generated 2 comments.

Files not reviewed (1)

• sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/simulator/_adversarial_simulator.py: Evaluated as low risk

Comments suppressed due to low confidence (5)

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/simulator/_conversation/init.py:129

• Remove commented-out print statements to keep the code clean.

print(self.persona_template_args)

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/simulator/_conversation/init.py:135

• Remove commented-out print statements to keep the code clean.

print(f"Conversation starter content: {conversation_starter_content}")

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/simulator/_conversation/init.py:140

• Remove commented-out print statements to keep the code clean.

print("Successfully created a Jinja2 template for the conversation starter.")

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/simulator/_conversation/init.py:141

• Remove commented-out print statements to keep the code clean.

print(f"Template syntax error: {e}. Using raw content.")

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/simulator/_conversation/_conversation.py:177

• [nitpick] The logger warning message could be more descriptive.

logger.warning("Error: %s", str(e))

[Copilot]

Avoid using broad exception handling. Handle specific exceptions instead.

Suggested change

	except Exception: # pylint: disable=broad-except
	except SomeSpecificException: # Replace SomeSpecificException with the actual exception type

[Copilot]

Avoid using broad exception handling. Handle specific exceptions instead.

Suggested change

	except Exception: # pylint: disable=broad-except
	except (TimeoutError, ValueError): # pylint: disable=broad-except

[azure-sdk]

API change check

API changes are not detected in this pull request.

[Copilot]

Copilot reviewed 5 out of 8 changed files in this pull request and generated 1 comment.

Files not reviewed (3)

• sdk/evaluation/azure-ai-evaluation/tests/unittests/test_synthetic_conversation_bot.py: Evaluated as low risk
• sdk/evaluation/azure-ai-evaluation/CHANGELOG.md: Evaluated as low risk
• sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/simulator/_conversation/init.py: Evaluated as low risk

Comments suppressed due to low confidence (1)

sdk/evaluation/azure-ai-evaluation/azure/ai/evaluation/simulator/_model_tools/models.py:618

• Returning a hardcoded "id": "unknown" could lead to confusion when debugging or tracking conversations. Consider logging a warning or raising an exception if the id is not found in the response data.

return {"samples": [response_data], "finish_reason": ["completed"], "id": "unknown"}

[Copilot]

The parameter 'conversation_id' is added but not used in the '_setup_bot' method. It should be either removed or utilized properly.

Suggested change

	conversation_id: Optional[str] = None,
	scenario: Union[AdversarialScenario, AdversarialScenarioJailbreak],