Python: Fix samples discovered by auto validation pipeline

[TaoChenOSU]

Motivation and Context

We have discovered many failing samples by the auto sample validation pipeline.

Description

This PR fixes a few of those sample and add the correct OpenAI key to the pipeline.

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.

[Copilot]

Pull request overview

Fixes failing samples discovered by the auto sample validation pipeline by aligning sample code and configuration with current client APIs and CI secret naming.

Changes:

• Update the DevUI in-memory sample to use AzureOpenAIChatClient(endpoint=..., deployment_name=...) parameters.
• Fix the custom chat client sample to pass Sequence[Message] into get_response() (instead of a raw string).
• Normalize OpenAI API key environment variable naming in declarative sample YAML and in the Python sample validation workflow.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

File	Description
python/samples/02-agents/devui/in_memory_mode.py	Updates Azure OpenAI chat client initialization and minor formatting changes.
python/samples/02-agents/chat_client/custom_chat_client.py	Fixes direct get_response() invocation to use message objects and improves formatting.
agent-samples/openai/OpenAIResponses.yaml	Updates declarative sample to reference OPENAI_API_KEY env var.
.github/workflows/python-sample-validation.yml	Switches workflow to use the OPENAI__APIKEY secret while still exporting OPENAI_API_KEY.