autogen

Tree: eca80ff663

History

EeS 39321266f9 Improve SocietyOfMindAgent message handling (#6142 ) 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>		1 year ago
..
test_assistant_agent.py	Add output_format to AssistantAgent for structured output (#6071)	1 year ago

test_code_executor_agent.py	Make FileSurfer and CodeExecAgent Declarative (#5765)	1 year ago

test_declarative_components.py	Fix token limited model context (#6137)	1 year ago

test_group_chat.py	Stop run when an error occured in a group chat (#6141)	1 year ago

test_group_chat_endpoint.py	Rename to use BaseChatMessage and BaseAgentEvent. Bring back union types. (#6144)	1 year ago

test_group_chat_pause_resume.py	Rename to use BaseChatMessage and BaseAgentEvent. Bring back union types. (#6144)	1 year ago

test_magentic_one_group_chat.py	Rename to use BaseChatMessage and BaseAgentEvent. Bring back union types. (#6144)	1 year ago

test_messages.py	Rename to use BaseChatMessage and BaseAgentEvent. Bring back union types. (#6144)	1 year ago

test_sequential_routed_agent.py	feat: Pause and Resume for AgentChat Teams and Agents (#5887)	1 year ago

test_society_of_mind_agent.py	Improve SocietyOfMindAgent message handling (#6142)	1 year ago

test_termination_condition.py	feat: Add FunctionCallTermination condition (#5808)	1 year ago

test_userproxy_agent.py	Rename to use BaseChatMessage and BaseAgentEvent. Bring back union types. (#6144)	1 year ago

test_utils.py	Assistant agent drop images when not provided with a vision-capable model. (#5351)	1 year ago

utils.py	Remove logging from autogen agentchat (#4510)	1 year ago

This is a mirror of AutoGen from GitHub. AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks.

Python SVG Jupyter Notebook C# TSX other

jackgerrits@users.noreply.github.com ekzhu@users.noreply.github.com wang.chi@microsoft.com rysweet@microsoft.com bigmiao.zhang@gmail.com victordibia@microsoft.com adamfo@microsoft.com gagb@users.noreply.github.com bnujli@gmail.com qingyun.wu@psu.edu liususan091219@users.noreply.github.com kostapetan@gmail.com jack@jackgerrits.com jaalber@microsoft.com davor@airt.ai 49209570+peterychang@users.noreply.github.com shaokunzhang529@gmail.com griffinbassman@gmail.com 32823396+kevin666aa@users.noreply.github.com adam.fourney@gmail.com leosantospinheiro@gmail.com qw2ky@virginia.edu 49699333+dependabot[bot]@users.noreply.github.com 66362098+marklysze@users.noreply.github.com hahahah2021@163.com

Contributors (25+) All

Contributors (25+)
All