mirror of
https://github.com/microsoft/autogen.git
synced 2025-10-31 17:59:50 +00:00
39321266f9
Please refer to #6123 for full context. That issue outlines several design and behavioral problems with `SocietyOfMindAgent`. This DRAFT PR focuses on resolving the most critical and broken behaviors first. Here is the error list 🔍 SocietyOfMindAgent: Design Issues and Historical Comparison (v0.2 vs v0.4+) ### ✅ P1–P4 Regression Issue Table (Updated with Fixes in PR #6142) | ID | Description | Current v0.4+ Issue | Resolution in PR #6142 | Was it a problem in v0.2? | Notes | |-----|-------------|----------------------|--------------------------|----------------------------|-------| | **P1** | `inner_messages` leaks into outer team termination evaluation | `Response.inner_messages` is appended to the outer team's `_message_thread`, affecting termination conditions. Violates encapsulation. | ✅ `inner_messages` is excluded from `_message_thread`, avoiding contamination of outer termination logic. | ❌ No | Structural boundary is now enforced | | **P2** | Inner team does not execute when outer message history is empty | In chained executions, if no new outer message exists, no task is created and the inner team is skipped entirely | ✅ Detects absence of new outer message and reuses the previous task, passing it via a handoff message. This ensures the inner team always receives a valid task to execute | ❌ No | The issue was silent task omission, not summary failure. Summary succeeds as a downstream effect | | **P3** | Summary LLM prompt is built from external input only | Prompt is constructed using external message history, ignoring internal reasoning | ✅ Prompt construction now uses `final_response.inner_messages`, restoring internal reasoning as the source of summarization | ❌ No | Matches v0.2 internal monologue behavior | | **P4** | External input is included in summary prompt (possibly incorrectly) | Outer messages are used in the final LLM summarization prompt | ✅ Resolved via the same fix as P3; outer messages are no longer used for summary | ❌ No | Redundant with P3, now fully addressed | <!-- Thank you for your contribution! Please review https://microsoft.github.io/autogen/docs/Contribute before opening a pull request. --> <!-- Please add a reviewer to the assignee section when you create a PR. If you don't have the access to it, we will shortly find a reviewer and assign them to your PR. --> ## Why are these changes needed? <!-- Please give a short summary of the change and the problem this solves. --> ## Related issue number resolve #6123 Blocked #6168 (Sometimes SoMA send last whitespace message) related #6187 <!-- For example: "Closes #1234" --> ## 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. --------- Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
116 lines
5.9 KiB
Python
116 lines
5.9 KiB
Python
from typing import AsyncGenerator
|
|
|
|
import pytest
|
|
import pytest_asyncio
|
|
from autogen_agentchat.agents import AssistantAgent, SocietyOfMindAgent
|
|
from autogen_agentchat.conditions import MaxMessageTermination
|
|
from autogen_agentchat.teams import RoundRobinGroupChat
|
|
from autogen_core import AgentRuntime, SingleThreadedAgentRuntime
|
|
from autogen_ext.models.replay import ReplayChatCompletionClient
|
|
|
|
|
|
@pytest_asyncio.fixture(params=["single_threaded", "embedded"]) # type: ignore
|
|
async def runtime(request: pytest.FixtureRequest) -> AsyncGenerator[AgentRuntime | None, None]:
|
|
if request.param == "single_threaded":
|
|
runtime = SingleThreadedAgentRuntime()
|
|
runtime.start()
|
|
yield runtime
|
|
await runtime.stop()
|
|
elif request.param == "embedded":
|
|
yield None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_society_of_mind_agent(runtime: AgentRuntime | None) -> None:
|
|
model_client = ReplayChatCompletionClient(
|
|
["1", "2", "3"],
|
|
)
|
|
agent1 = AssistantAgent("assistant1", model_client=model_client, system_message="You are a helpful assistant.")
|
|
agent2 = AssistantAgent("assistant2", model_client=model_client, system_message="You are a helpful assistant.")
|
|
inner_termination = MaxMessageTermination(3)
|
|
inner_team = RoundRobinGroupChat([agent1, agent2], termination_condition=inner_termination, runtime=runtime)
|
|
society_of_mind_agent = SocietyOfMindAgent("society_of_mind", team=inner_team, model_client=model_client)
|
|
response = await society_of_mind_agent.run(task="Count to 10.")
|
|
assert len(response.messages) == 2
|
|
assert response.messages[0].source == "user"
|
|
assert response.messages[1].source == "society_of_mind"
|
|
|
|
# Test save and load state.
|
|
state = await society_of_mind_agent.save_state()
|
|
assert state is not None
|
|
agent1 = AssistantAgent("assistant1", model_client=model_client, system_message="You are a helpful assistant.")
|
|
agent2 = AssistantAgent("assistant2", model_client=model_client, system_message="You are a helpful assistant.")
|
|
inner_termination = MaxMessageTermination(3)
|
|
inner_team = RoundRobinGroupChat([agent1, agent2], termination_condition=inner_termination, runtime=runtime)
|
|
society_of_mind_agent2 = SocietyOfMindAgent("society_of_mind", team=inner_team, model_client=model_client)
|
|
await society_of_mind_agent2.load_state(state)
|
|
state2 = await society_of_mind_agent2.save_state()
|
|
assert state == state2
|
|
|
|
# Test serialization.
|
|
soc_agent_config = society_of_mind_agent.dump_component()
|
|
assert soc_agent_config.provider == "autogen_agentchat.agents.SocietyOfMindAgent"
|
|
|
|
# Test deserialization.
|
|
loaded_soc_agent = SocietyOfMindAgent.load_component(soc_agent_config)
|
|
assert isinstance(loaded_soc_agent, SocietyOfMindAgent)
|
|
assert loaded_soc_agent.name == "society_of_mind"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_society_of_mind_agent_empty_messges(runtime: AgentRuntime | None) -> None:
|
|
model_client = ReplayChatCompletionClient(
|
|
["1", "2", "3", "4", "5", "6", "7", "8", "9", "10"],
|
|
)
|
|
agent1 = AssistantAgent("assistant1", model_client=model_client, system_message="You are a helpful assistant.")
|
|
agent2 = AssistantAgent("assistant2", model_client=model_client, system_message="You are a helpful assistant.")
|
|
inner_termination = MaxMessageTermination(3)
|
|
inner_team = RoundRobinGroupChat([agent1, agent2], termination_condition=inner_termination, runtime=runtime)
|
|
society_of_mind_agent = SocietyOfMindAgent("society_of_mind", team=inner_team, model_client=model_client)
|
|
response = await society_of_mind_agent.run()
|
|
assert len(response.messages) == 1
|
|
assert response.messages[0].source == "society_of_mind"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_society_of_mind_agent_no_response(runtime: AgentRuntime | None) -> None:
|
|
model_client = ReplayChatCompletionClient(
|
|
["1", "2", "3"],
|
|
)
|
|
agent1 = AssistantAgent("assistant1", model_client=model_client, system_message="You are a helpful assistant.")
|
|
agent2 = AssistantAgent("assistant2", model_client=model_client, system_message="You are a helpful assistant.")
|
|
inner_termination = MaxMessageTermination(1) # Set to 1 to force no response.
|
|
inner_team = RoundRobinGroupChat([agent1, agent2], termination_condition=inner_termination, runtime=runtime)
|
|
society_of_mind_agent = SocietyOfMindAgent("society_of_mind", team=inner_team, model_client=model_client)
|
|
response = await society_of_mind_agent.run(task="Count to 10.")
|
|
assert len(response.messages) == 2
|
|
assert response.messages[0].source == "user"
|
|
assert response.messages[1].source == "society_of_mind"
|
|
assert response.messages[1].to_text() == "No response."
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_society_of_mind_agent_multiple_rounds(runtime: AgentRuntime | None) -> None:
|
|
model_client = ReplayChatCompletionClient(
|
|
["1", "2", "3", "4", "5", "6", "7", "8", "9", "10"],
|
|
)
|
|
agent1 = AssistantAgent("assistant1", model_client=model_client, system_message="You are a helpful assistant.")
|
|
agent2 = AssistantAgent("assistant2", model_client=model_client, system_message="You are a helpful assistant.")
|
|
inner_termination = MaxMessageTermination(3)
|
|
inner_team = RoundRobinGroupChat([agent1, agent2], termination_condition=inner_termination, runtime=runtime)
|
|
society_of_mind_agent = SocietyOfMindAgent("society_of_mind", team=inner_team, model_client=model_client)
|
|
response = await society_of_mind_agent.run(task="Count to 10.")
|
|
assert len(response.messages) == 2
|
|
assert response.messages[0].source == "user"
|
|
assert response.messages[1].source == "society_of_mind"
|
|
|
|
# Continue.
|
|
response = await society_of_mind_agent.run()
|
|
assert len(response.messages) == 1
|
|
assert response.messages[0].source == "society_of_mind"
|
|
|
|
# Continue.
|
|
response = await society_of_mind_agent.run()
|
|
assert len(response.messages) == 1
|
|
assert response.messages[0].source == "society_of_mind"
|