Python: Support Declarative Spec for OpenAIAssistantAgent & OpenAIResponsesAgent

[moonbox3]

Motivation and Context

This PR builds on the initial work/abstractions from #11982. The AzureAssistantAgent / OpenAIAssistantAgent as well as the AzureResponsesAgent / OpenAIResponsesAgent now support declarative specs. Several examples on how to declare the spec are shown in the respective dirs in samples/concepts/agents, as well as a simple getting started example for each agent type.

To further simplify working with these two agents, the setup_resources() methods for each agent type have been marked with a deprecation tag. The new method to use is OpenAIAssistantAgent.create_client() or OpenAIResponsesAgent.create_client(). Further, when one needs to access the underlying setting's, it's simple to do so with a settings object and accessing the attribute.

In the previous PR for the AzureAIAgent, it lacked support for templating - this is included in this current PR.

Description

Bring in support for the declarative single agent spec for these agent types.

• Add samples
• Add unit tests
• Add support for prompt templates for all current agent types
• Closes Python: Support Declarative Agent Spec for OpenAIAssistantAgent & OpenAIResponsesAgent #11979

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
__init__.py	4	0	100%
agents
__init__.py	10	2	80%	60, 64
agent.py	336	49	85%	122, 129, 142–143, 146–148, 151–153, 204, 209, 214, 219, 224, 228, 232, 236, 277–279, 307–308, 310, 314, 434, 436, 501, 515, 571, 573, 598, 612, 625, 677, 684–685, 688–689, 708, 755, 812, 897–898, 900–901, 955, 1016, 1031
agents/azure_ai
azure_ai_agent.py	352	170	51%	98, 100–103, 105–107, 109–114, 116, 118, 120–122, 124, 141–143, 145–146, 151–152, 157–160, 165–169, 171–174, 176–182, 187, 189–192, 194–196, 198–201, 203, 205, 215–216, 218–221, 223–224, 229, 231–237, 239, 272, 283–284, 289–290, 293, 298–303, 310–311, 313, 318–319, 330–336, 388, 390, 396, 407, 410, 412, 414, 416, 450, 481–483, 485, 487–488, 490–493, 495–496, 499, 502–511, 513, 522–523, 526–528, 530–531, 541–542, 544, 562, 564, 567, 569–570, 572–573, 575, 584–585, 587, 589–592, 595, 597, 600–602, 606, 675, 781, 885, 958
agents/channels
open_ai_assistant_channel.py	57	0	100%
agents/open_ai
assistant_thread_actions.py	338	56	83%	107, 110, 116, 195, 197, 236–242, 416, 474, 500, 599–600, 602–603, 609–610, 612–613, 615–618, 620–621, 623–624, 626–627, 641–645, 648–650, 697, 699–700, 704–708, 710–711, 725–726, 797, 802, 834
azure_assistant_agent.py	89	25	71%	34, 104, 108, 174–175, 185–186, 188, 194, 197–198, 202–207, 209–210, 212–213, 215, 245, 265, 275
azure_responses_agent.py	91	61	32%	38, 91–92, 102–103, 105, 111, 114–115, 119–124, 126–127, 129–130, 132, 142, 181–182, 192–193, 195, 201, 204–205, 209–214, 216–217, 219–220, 222, 241, 243, 246, 248–249, 251–252, 254, 264–265, 267, 269–272, 275, 277, 280–282, 286
openai_assistant_agent.py	360	69	80%	74, 110–113, 118, 122–123, 156, 173–174, 182–187, 194–195, 198, 203–204, 215–221, 399–400, 407–408, 410–411, 413–414, 416–421, 423, 470, 473, 476–485, 487, 497, 521–522, 560, 576, 586, 602, 615, 651, 795, 904, 1011
openai_responses_agent.py	407	102	74%	65, 94, 113–116, 124, 128–129, 161–165, 169, 174, 179, 184, 190, 195–196, 199, 202, 207–212, 217–218, 220–221, 227–230, 236, 238–239, 243–247, 338, 342, 346, 348, 354, 367, 369, 371, 375, 470–471, 478–479, 481–482, 484–485, 487–492, 494, 541, 586, 602, 612, 646, 654, 657, 661, 663, 666, 689, 692–696, 706, 746, 771, 782, 873, 993, 1034, 1036, 1110, 1150–1151, 1153–1157, 1176
responses_agent_thread_actions.py	343	107	68%	167, 184, 195, 206–207, 374–376, 390, 395, 402, 420–421, 425, 469–471, 474, 492–493, 502–504, 508, 512–513, 517–519, 530–532, 554, 556–557, 564–565, 567–568, 570, 572–573, 575–576, 659–661, 673–674, 676–680, 682–688, 690–699, 701–702, 704–707, 714–716, 721, 723, 782–785, 826–827, 831–833, 835, 860–861, 863–867, 869, 879–880, 888, 892, 899, 905, 969
TOTAL	26991	4568	83%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
3616	18 💤	0 ❌	0 🔥	1m 56s ⏱️