Add output_format to AssistantAgent for structured output

[ekzhu]

Resolves #5934

This PR adds ability for AssistantAgent to generate a StructuredMessage[T] where T is the content type in base model.

How to use?

from typing import Literal

from pydantic import BaseModel

from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_agentchat.ui import Console

# The response format for the agent as a Pydantic base model.
class AgentResponse(BaseModel):
    thoughts: str
    response: Literal["happy", "sad", "neutral"]


# Create an agent that uses the OpenAI GPT-4o model which supports structured output.
model_client = OpenAIChatCompletionClient(model="gpt-4o")
agent = AssistantAgent(
    "assistant",
    model_client=model_client,
    system_message="Categorize the input as happy, sad, or neutral following the JSON format.",
    # Setting the output format to AgentResponse to force the agent to produce a JSON string as response.
    output_content_type=AgentResponse,
)

result = await Console(agent.run_stream(task="I am happy."))

# Check the last message in the result, validate its type, and print the thoughts and response.
assert isinstance(result.messages[-1], StructuredMessage)
assert isinstance(result.messages[-1].content, AgentResponse)
print("Thought: ", result.messages[-1].content.thoughts)
print("Response: ", result.messages[-1].content.response)
await model_client.close()

---------- user ----------
I am happy.
---------- assistant ----------
{
  "thoughts": "The user explicitly states they are happy.",
  "response": "happy"
}
Thought:  The user explicitly states they are happy.
Response:  happy

[codecov]

Codecov Report

Attention: Patch coverage is 92.00000% with 2 lines in your changes missing coverage. Please review.

Project coverage is 76.99%. Comparing base (7487687) to head (ddbdd47).

Files with missing lines	Patch %	Lines
...t/src/autogen_agentchat/agents/_assistant_agent.py	92.00%	2 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #6071      +/-   ##
==========================================
+ Coverage   76.96%   76.99%   +0.03%     
==========================================
  Files         192      192              
  Lines       13438    13455      +17     
==========================================
+ Hits        10342    10360      +18     
+ Misses       3096     3095       -1     

Flag	Coverage Δ
unittests	76.99% <92.00%> (+0.03%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[a-holm]

Perhaps consider adding a note to the docstring mentioning that using output_content_type currently prevents the agent state from being saved/loaded via the declarative configuration mechanism (due to the check in _to_config). This would help manage user expectations.

Otherwise a very well-documented and clean PR that has tests and everything.