Python: Common agent invocation API updates

[moonbox3]

Motivation and Context

After this week's release of the common agent invocation API, there are some things that we can do as further improvements.

Description

This PR includes updates for:

• Right now we force any agent invocation to provide some type of input, whether a str, a CMC, or a list of str | CMC. At times, there could be a reason, based on using an existing thread or just providing instructions to the agent, that one doesn't need to provide a message to invoke the agent. Updating to make messages optional. Updating the ABC contracts as well.
• For invoke_stream calls on agents, there's no need to call thread.on_new_message that contains a streaming chunks -- once we move to support memory, this is where the "hook" will be. Removing this call.
• The get_messages(...) methods on the AutoGenConversableAgentThread and the ChatHistoryAgentThread returned concrete ChatHistory objects, whereas the AssistantAgentThread and AzureAIAgentThread returned AsyncIterable[ChatMessageContent]. To align to a common API, the AutoGenConversableAgentThread and ChatHistoryAgentThread's get_messages(...) methods were moved to return AsyncIterable[ChatMessageContent].
• Removing a public facing output_messages for streaming invoke, and replacing it with a callback to get a chat history back of "full" messages. Two samples are added in samples/concepts/agents:
  • azure_ai_agent/azure_ai_agent_streaming_chat_history_callback.py
  • openai_assistant_streaming_chat_history_callback.py
• Update the README for OpenAI Assistants to showcase new thread abstraction.
• Include unit tests for chat history (on_complete) callback.

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
agent.py	160	30	81%	47, 54, 58, 67–78, 125, 130, 135, 140, 145, 149, 153, 157, 192–194, 222–229, 331–333, 390, 404
semantic_kernel/agents/autogen
autogen_conversable_agent.py	122	15	88%	67, 73, 89, 91, 97–101, 286–287, 296–299
semantic_kernel/agents/azure_ai
agent_thread_actions.py	341	129	62%	142, 144, 179–182, 369, 371, 410–411, 437, 440–444, 447–459, 462–493, 499–506, 509–522, 538–569, 613, 616, 647–681, 744, 749–754, 774–781, 812–821, 864–876
azure_ai_agent.py	179	40	78%	93, 104–114, 119–124, 131–140, 151–157, 208, 210, 216, 227–232, 234, 236, 257–260, 330, 431, 529, 595
semantic_kernel/agents/bedrock
bedrock_agent.py	250	54	78%	77–84, 93, 159, 286, 299, 318, 334–337, 343, 345, 348, 353, 383, 396, 428–448, 452, 482, 495, 514–517, 519–522, 564, 575–576, 588, 624–635, 646, 663–676, 693–702
semantic_kernel/agents/chat_completion
chat_completion_agent.py	207	21	90%	69, 79, 85, 101, 103, 109–113, 171, 174, 184, 192–197, 206, 236, 366, 432, 493
semantic_kernel/agents/open_ai
open_ai_assistant_agent.py	233	27	88%	93, 110–111, 119–124, 131–141, 152–158, 315, 328, 364, 527, 631, 732
TOTAL	21257	2470	88%

Python Unit Test Overview

Tests	Skipped	Failures	Errors	Time
3339	5 💤	0 ❌	0 🔥	1m 53s ⏱️