Python: Fix Chat History Agent format instructions regression.

[moonbox3]

Motivation and Context

The chat history agent templating was inadvertently broken. This PR restores the functionality to be able to use templating with a Chat Completion Agent.

Description

Fix the templating for a Chat Completion Agent. Add unit tests for more coverage.

• Fix a unit test fixture that was annotated to return an AsyncMock, but it's actually returning an async generator function.

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/agents/azure_ai
agent_content_generation.py	145	20	86%	68–71, 89, 91, 286, 338–370
agent_thread_actions.py	338	128	62%	139, 141, 176–179, 364, 366, 405–406, 432, 435–439, 442–454, 457–488, 494–501, 504–517, 533–564, 608, 637–671, 734, 739–744, 764–771, 802–811, 854–864
semantic_kernel/agents/bedrock
bedrock_agent.py	184	33	82%	106, 120, 124, 126, 173–186, 252, 276, 293, 325, 360–363, 366, 369, 371, 403, 420–421, 423–424, 466, 477–478, 490, 526–537, 548, 565–578
semantic_kernel/agents/chat_completion
chat_completion_agent.py	110	7	94%	82, 85, 94–99, 124, 192
semantic_kernel/agents/group_chat
agent_chat.py	125	2	98%	80, 173
agent_group_chat.py	115	13	89%	73, 163, 213, 217–228
semantic_kernel/agents/open_ai
assistant_content_generation.py	159	12	92%	94–97, 115, 118–119, 351–359, 405
open_ai_assistant_base.py	528	14	97%	195, 204–209, 289, 305–306, 774, 828, 1035, 1043, 1113, 1128, 1192
TOTAL	18774	2230	88%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
3198	5 💤	0 ❌	0 🔥	2m 9s ⏱️

[moonbox3]

Will push some pending changes soon - typing improvements.

[eavanvalkenburg]

couple of nits