Python: Respect FunctionChoiceBehavior filters in OpenAI responses agent tools

[ymuichiro]

issue: #13234

Summary

• honor FunctionChoiceBehavior filters when retrieving kernel function metadata

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the SK Contribution Guidelines and the pre-submission formatting script raises no violations
• All unit tests pass, and I have added new tests where possible
• I didn't break anyone 😄

[Copilot]

Pull Request Overview

This PR ensures that FunctionChoiceBehavior filters are properly respected when retrieving kernel function metadata in OpenAI responses agent tools. Previously, the code was ignoring these filters and always returning all available functions.

• Replaced the TODO comment with proper implementation of FunctionChoiceBehavior filter handling
• Added early returns for cases where kernel functions are disabled or no plugins exist
• Used conditional logic to apply filters when retrieving function metadata

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[moonbox3]

@ymuichiro Thanks for the contribution. Please have a look at a failing test, thanks: https://github.com/microsoft/semantic-kernel/actions/runs/18583595889/job/52983055182?pr=13235#step:5:445

[ymuichiro]

@moonbox3
Fixed! I suspected the problem was in the test code, so I only changed the test code.

[markwallace-microsoft]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
agents/open_ai
responses_agent_thread_actions.py	440	128	70%	177, 194, 207, 218–219, 227, 234, 247, 407–408, 410, 424, 429, 436, 451–452, 462, 469, 471–472, 481, 488, 490–491, 502, 509, 511–512, 522, 529, 534–535, 539, 551, 585–587, 590, 608–609, 620–622, 626, 630–631, 635–637, 648–650, 672, 674–675, 682–683, 685–686, 688, 690–691, 693–694, 792, 797, 805–806, 808, 814, 819, 824–826, 832–834, 839–840, 842–847, 849, 853–854, 856, 860, 864, 869–870, 875, 878–879, 939–942, 965, 1011–1014, 1055–1056, 1060–1062, 1064, 1089–1090, 1092–1096, 1098, 1108–1109, 1117, 1121, 1128, 1134, 1210, 1213, 1216
TOTAL	27296	4562	83%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
3759	23 💤	0 ❌	0 🔥	1m 35s ⏱️