Python: Allow tool_choice: required in OpenAI Clients when using allowed_tools

[cecheta]

Motivation & Context

Description & Review Guide

Allow both auto and required for tool_choice in OpenAI clients, when using allowed_tools.
Tested using FoundryChatClient.

Related Issue

Fixes #7023

Contribution Checklist

• The code builds clean without any errors or warnings
• All unit tests pass, and I have added new tests where possible
• The PR follows the Contribution Guidelines
• This PR is linked to an issue and there is no other open PR for this issue (see Related Issue above).
• This is not a breaking change. If it is a breaking change, add the breaking change label (or add "[BREAKING]" to the title prefix, before or after any language prefix) — a workflow keeps the label and title prefix in sync automatically.

[Copilot]

Pull request overview

This PR fixes a behavior gap in the Python OpenAI Responses client by allowing tool_choice.mode: "required" to be used together with allowed_tools, matching the agent_framework core tool-choice contract and addressing issue #7023.

Changes:

• Update OpenAIChatClient._prepare_options to preserve/translate allowed_tools for both tool_choice.mode = "auto" and "required".
• Add unit tests covering allowed_tools with "required" mode (single and multiple tools) and confirming "required" without allowed_tools remains a plain string.

Show a summary per file

File	Description
python/packages/openai/agent_framework_openai/_chat_client.py	Extends tool-choice conversion logic so allowed_tools is honored for "required" mode, not only "auto".
python/packages/openai/tests/openai/test_openai_chat_client.py	Adds regression tests ensuring _prepare_options produces the expected OpenAI Responses API tool_choice shape for "required" + allowed_tools.

Review details

• Files reviewed: 2/2 changed files
• Comments generated: 0
• Review effort level: Low

[github-actions]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
packages/openai/agent_framework_openai
_chat_client.py	1277	127	90%	307, 320, 670–674, 682–685, 691–695, 745–752, 754–756, 763–765, 823, 831, 854, 972, 1071, 1130, 1132, 1134, 1136, 1202, 1216, 1296, 1306, 1311, 1354, 1465–1466, 1481, 1705, 1710, 1714–1716, 1720–1721, 1804, 1814, 1841, 1847, 1857, 1863, 1868, 1874, 1879–1880, 1960, 2004, 2007–2010, 2024, 2026, 2034–2035, 2047, 2089, 2154, 2171, 2174, 2201–2203, 2242, 2259, 2262, 2324, 2331, 2355–2356, 2391, 2429–2430, 2448–2449, 2492, 2619–2620, 2638, 2721–2729, 2759, 2904, 2919, 2968–2971, 2981–2983, 3010–3012, 3022–3023, 3029, 3044, 3166–3167
TOTAL	44093	5274	88%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
8828	33 💤	0 ❌	0 🔥	2m 35s ⏱️