Python: Add thread_id to assistant message to avoid duplication (#11221)

### Motivation and Context

The current OpenAI assistant get_response and invoke methods don't add
the current thread_id to the CMC's metadata, therefore during a
`thread.on_new_message(...)` call, the assistant's message will get
added again.

<!-- Thank you for your contribution to the semantic-kernel repo!
Please help reviewers and future users, providing the following
information:
  1. Why is this change required?
  2. What problem does it solve?
  3. What scenario does it contribute to?
  4. If it fixes an open issue, please link to the issue here.
-->

### Description

Add the `thread_id` to the metadata so we don't add the assistant's
response again.

**Todo**: add agent integration tests and check messages so we have
coverage for this.

<!-- Describe your changes, the overall approach, the underlying design.
These notes will help understanding how your code works. Thanks! -->

### Contribution Checklist

<!-- Before submitting this PR, please make sure: -->

- [X] The code builds clean without any errors or warnings
- [X] The PR follows the [SK Contribution
Guidelines](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
and the [pre-submission formatting
script](https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md#development-scripts)
raises no violations
- [X] All unit tests pass, and I have added new tests where possible
- [X] I didn't break anyone 😄

Author: moonbox3

python/semantic_kernel/agents/open_ai/assistant_thread_actions.py

@@ -554,7 +554,10 @@ async def _handle_streaming_requires_action(
 
     @classmethod
     async def get_messages(
-        cls: type[_T], client: AsyncOpenAI, thread_id: str, sort_order: Literal["asc", "desc"] = "desc"
+        cls: type[_T],
+        client: AsyncOpenAI,
+        thread_id: str,
+        sort_order: Literal["asc", "desc"] | None = None,
     ) -> AsyncIterable["ChatMessageContent"]:
         """Get messages from the thread.
 
@@ -572,7 +575,7 @@ async def get_messages(
         while True:
             messages = await client.beta.threads.messages.list(
                 thread_id=thread_id,
-                order=sort_order,
+                order=sort_order,  # type: ignore
                 after=last_id,
             )
 

python/semantic_kernel/agents/open_ai/open_ai_assistant_agent.py

@@ -140,7 +140,7 @@ async def _on_new_message(self, new_message: str | ChatMessageContent) -> None:
             assert self._id is not None  # nosec
             await AssistantThreadActions.create_message(self._client, self._id, new_message)
 
-    async def get_messages(self, sort_order: Literal["asc", "desc"] = "desc") -> AsyncIterable[ChatMessageContent]:
+    async def get_messages(self, sort_order: Literal["asc", "desc"] | None = None) -> AsyncIterable[ChatMessageContent]:
         """Get the messages in the thread.
 
         Args:
@@ -556,6 +556,7 @@ async def get_response(
             **run_level_params,  # type: ignore
         ):
             if is_visible and response.metadata.get("code") is not True:
+                response.metadata["thread_id"] = thread.id
                 response_messages.append(response)
 
         if not response_messages:
@@ -650,16 +651,17 @@ async def invoke(
         }
         run_level_params = {k: v for k, v in run_level_params.items() if v is not None}
 
-        async for is_visible, message in AssistantThreadActions.invoke(
+        async for is_visible, response in AssistantThreadActions.invoke(
             agent=self,
             thread_id=thread.id,
             kernel=kernel,
             arguments=arguments,
             **run_level_params,  # type: ignore
         ):
             if is_visible:
-                await thread.on_new_message(message)
-                yield AgentResponseItem(message=message, thread=thread)
+                response.metadata["thread_id"] = thread.id
+                await thread.on_new_message(response)
+                yield AgentResponseItem(message=response, thread=thread)
 
     @trace_agent_invocation
     @override