Aegis structure message

[abhinav-aegis]

Why are these changes needed?

Related issue number

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

Added support for structured message component using the Json to Pydantic utility functions. Note: also adding the ability to use a format string for structured messages.

[abhinav-aegis]

The StructuredMessageFactory code is largely hidden from the User and is taken care of automatically in the background. So this code below works out of the box with the user not being aware of how the StructuredMessageComponent is being serialized and deserialized in the background. Notice how in the code below we can run the dump_component/load_component and it seems to work fine for me:

from pydantic import BaseModel, ValidationError
from typing import Literal

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.base import TaskResult
from autogen_agentchat.conditions import TextMentionTermination
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient

# Create an OpenAI model client.
model_client = OpenAIChatCompletionClient(
    model="gpt-4o-2024-08-06",
)

class Critique(BaseModel):
    score: int
    review: str
    approved: Literal["APPROVE", "REJECT"]

# Create the primary agent.
primary_agent = AssistantAgent(
    "primary",
    model_client=model_client,
    system_message="You are a helpful AI assistant.",
)
format_string = "Score: {score}/10\nReview: {review},\n Approved: {approved}"

# Create the critic agent.
critic_agent = AssistantAgent(
    "critic",
    model_client=model_client,
    system_message="Provide constructive feedback with a score, review and approved or not in json fromat. Respond with approved:"APPROVED" when your feedbacks are addressed.",
    output_content_type=Critique,
    format_string=format_string,
)

# Define a termination condition that stops the task if the critic approves.
text_termination = TextMentionTermination("APPROVE")

# Create a team with the primary and critic agents.
team = RoundRobinGroupChat([primary_agent, critic_agent], termination_condition=text_termination, max_turns=10)

config = team.dump_component()
loaded_team = RoundRobinGroupChat.load_component(config)

async def main() -> None:
    await Console(loaded_team.run_stream(task="tell me a poem"))

[ekzhu]

Looks great! I think we still need to fix various CI errors.

You may need to change your local uv version to 0.5.18.

uv self update 0.5.18

And then run uv sync --all-extras to fix the uv.lock file or revert it to the main version.

[codecov]

Codecov Report

Attention: Patch coverage is 90.80000% with 23 lines in your changes missing coverage. Please review.

Project coverage is 77.48%. Comparing base (8bd162f) to head (2d3f83b).
Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
...n-core/src/autogen_core/utils/_json_to_pydantic.py	89.84%	20 Missing ⚠️
...en_agentchat/teams/_group_chat/_base_group_chat.py	71.42%	2 Missing ⚠️
...utogen-agentchat/src/autogen_agentchat/messages.py	96.87%	1 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #6289      +/-   ##
==========================================
+ Coverage   77.24%   77.48%   +0.23%     
==========================================
  Files         200      202       +2     
  Lines       14473    14717     +244     
==========================================
+ Hits        11180    11403     +223     
- Misses       3293     3314      +21     

Flag	Coverage Δ
unittests	77.48% <90.80%> (+0.23%)	⬆️

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.