Python: Create/Get Agent API - fixes and example improvements

[dmytrostruk]

Motivation and Context

Resolves: #3228
Resolves: #3229

Fixes for model and strict parameters.

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the Contribution Guidelines
• All unit tests pass, and I have added new tests where possible
• Is this a breaking change? If yes, add "[BREAKING]" prefix to the title of the PR.

[markwallace-microsoft]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/azure-ai/agent_framework_azure_ai
_project_provider.py	92	13	85%	128–129, 205, 212, 277, 321, 354, 403–405, 409–411
_shared.py	277	102	63%	118, 120, 122, 124, 169, 257–260, 263–265, 268–269, 279, 286–288, 314–323, 370, 386–388, 390–407, 415–418, 421–422, 425–432, 437–438, 444–446, 449–450, 452, 464, 466–467, 469–470, 472–473, 475–483, 485, 521, 523–526, 528, 534, 540, 544, 559, 562–563, 565
packages/core/agent_framework/openai
_assistants_client.py	273	34	87%	60, 353, 367, 370, 372–373, 376, 379, 382–383, 394, 419, 421, 423, 425, 427, 432, 435, 438, 442, 453, 538, 557–558, 561, 569, 621, 656, 691–694, 746, 763
TOTAL	17361	2653	84%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
3143	213 💤	0 ❌	0 🔥	1m 4s ⏱️

[Copilot]

Pull request overview

This PR fixes issues with model and strict parameters in the Agent API and improves sample code to demonstrate both default and runtime response format configuration.

Changes:

• Added strict=True when converting Pydantic models to JSON schema format for structured outputs
• Fixed missing model_deployment_name parameter when creating ChatAgent from Azure AI agent details
• Enhanced sample examples to demonstrate both default_options at creation time and runtime overrides

Reviewed changes

Copilot reviewed 9 out of 9 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
python/packages/core/agent_framework/openai/_assistants_client.py	Added strict=True to Pydantic response format conversion
python/packages/core/tests/openai/test_openai_assistants_client.py	Added unit test for strict parameter with Pydantic models
python/packages/azure-ai/agent_framework_azure_ai/_shared.py	Added strict=True to Azure AI Pydantic response format conversion
python/packages/azure-ai/agent_framework_azure_ai/_project_provider.py	Added missing model_deployment_name parameter to AzureAIClient
python/packages/azure-ai/tests/test_provider.py	Enhanced test to verify AzureAIClient initialization and added test for strict parameter
python/samples/getting_started/agents/openai/openai_assistants_with_response_format.py	Enhanced example to show both default and runtime response format override
python/samples/getting_started/agents/azure_ai_agent/azure_ai_with_response_format.py	Enhanced example to show both default and runtime response format override
python/samples/getting_started/agents/azure_ai/azure_ai_with_runtime_json_schema.py	Fixed to use default_options instead of direct parameter
python/samples/getting_started/agents/azure_ai/azure_ai_with_response_format.py	Updated comment for clarity