Python: Introduce the OpenAI Responses Agent

[moonbox3]

Motivation and Context

OpenAI recently released their Responses API, which is their newest core API and an agentic API primitive, combining the simplicity of Chat Completions with the ability to do more agentic tasks. Azure OpenAI also recently released the Responses API, with close-to feature parity with OpenAI's SDK. It gives us enough to introduce an AzureResponsesAgent and an OpenAIResponsesAgent to Semantic Kernel.

Description

This PR introduces:

• The AzureResponsesAgent and OpenAIResponsesAgent
• Allows use of the web search tool with OpenAI (Azure OpenAI currently doesn't support this).
• Allows use of the file search tool with both OpenAI and Azure OpenAI.
• Provides getting started samples for both agent types.

TODO:

• Add unit test coverage for the ResponsesAgentThreadActions class.
• Add support for the computer user agent tool.
• Improve typing in the ResponsesAgentThreadActions class.
• Closes Python: OpenAI Response Agent #11026

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 😄

[markwallace-microsoft]

Python Test Coverage Report •

File	Stmts	Miss	Cover	Missing
semantic_kernel
kernel.py	202	47	77%	143, 154, 158, 308–311, 427, 441–484
semantic_kernel/agents
__init__.py	10	2	80%	34, 38
semantic_kernel/agents/open_ai
azure_responses_agent.py	37	37	0%	3–118
openai_responses_agent.py	300	71	76%	92–96, 100, 105, 110, 115, 121, 126–133, 138–143, 148–152, 158–170, 174–178, 270, 274, 278, 280, 286, 299, 301, 303, 305, 307, 400, 408, 411, 415, 417, 420, 443–450, 460, 500, 525, 536, 625, 742, 779, 856, 897–900, 915
responses_agent_thread_actions.py	302	85	72%	158, 175, 186, 194, 226–227, 359, 373–385, 403–408, 449–452, 455, 473–484, 505–527, 608–672, 754–763, 793–794, 802–806, 813–819, 883
semantic_kernel/connectors/ai
function_calling_utils.py	50	3	94%	66, 181, 186
semantic_kernel/connectors/ai/open_ai/settings
azure_open_ai_settings.py	27	4	85%	126–129
semantic_kernel/contents
annotation_content.py	47	1	98%	64
function_call_content.py	110	4	96%	124, 201, 229–230
function_result_content.py	90	1	99%	94
TOTAL	21671	2671	88%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
3363	5 💤	0 ❌	0 🔥	1m 37s ⏱️

[TaoChenOSU]

I see a mix of Responses Agent and Response Agent in code and comments. We should probably fix them.