Python: Fix Eval samples

[eavanvalkenburg]

Motivation and Context

Fixes the samples using evals, both red team and self reflection.

Description

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

This PR fixes the Python evaluation samples (self_reflection and red_teaming) by updating them to use the correct APIs and dependencies.

Changes:

• Updates dependency versions in uv.lock (anthropic, github-copilot-sdk, mem0ai, pandas, uv)
• Migrates self_reflection sample from AzureOpenAIChatClient to AzureOpenAIResponsesClient
• Updates default models from gpt-4.1 to gpt-5.2
• Improves file path handling using Path for better cross-platform compatibility
• Adds async project client support for proper Azure AI Foundry integration
• Updates red_team_agent_sample callback signature to match the expected interface

Reviewed changes

Copilot reviewed 3 out of 4 changed files in this pull request and generated 3 comments.

File	Description
python/uv.lock	Updates package versions: anthropic (0.80.0→0.81.0), github-copilot-sdk (0.1.24→0.1.25), mem0ai (1.0.3→1.0.4), pandas (3.0.0→3.0.1), uv (0.10.3→0.10.4)
python/samples/05-end-to-end/evaluation/self_reflection/self_reflection.py	Migrates from AzureOpenAIChatClient to AzureOpenAIResponsesClient, adds async project client, improves path handling, updates default models
python/samples/05-end-to-end/evaluation/self_reflection/README.md	Updates documentation to reflect AzureOpenAIResponsesClient usage and gpt-5.2 models
python/samples/05-end-to-end/evaluation/red_teaming/red_team_agent_sample.py	Adds PEP 723 metadata, fixes callback signature to match RedTeam API expectations, improves error handling

[markwallace-microsoft]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/core/agent_framework/openai
_responses_client.py	624	78	87%	291–294, 298–299, 302–303, 309–310, 315, 328–334, 355, 363, 386, 549, 552, 607, 611, 613, 615, 617, 693, 703, 708, 751, 832, 849, 862, 1016, 1021, 1025–1027, 1031–1032, 1055, 1124, 1146–1147, 1162–1163, 1181–1182, 1320–1321, 1337, 1339, 1418–1426, 1545, 1600, 1615, 1654–1655, 1657–1659, 1673–1675, 1685–1686, 1692, 1707
TOTAL	21193	3328	84%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
4176	239 💤	0 ❌	0 🔥	1m 13s ⏱️