SongChiyoung

Results 31 comments of SongChiyoung

@ekzhu I found at blame https://github.com/microsoft/autogen/commit/59e392cd0f5e6075d2f6f5b527a0914825049286 That SelectorGroupChat downgrade SystemMessage to UserMessage, It not for multiple system message issue. So, Now only `SocietyOfMindAgent` has multiple group chat. --> however, when...

@ekzhu Cool. I found that in my environment, each Docker build takes about 10 seconds. In `packages/autogen-ext/tests/code_executors/test_docker_commandline_code_executor.py`, there are 13 calls to `DockerCommandLineCodeExecutor` and 5 calls to the `executor_and_temp_dir` fixture....

@ekzhu I think it’s nice solution for this case. Yes we have some issues of real implement of it however it’s just technical issue.

@gmivan I hope everything is going well. Please feel free to tag me if I can assist in any way.

Hi, I’d like to highlight a compatibility issue we encountered when trying to support the Mistral family. Currently, some parts of the codebase use startswith() checks on model_family or model_name...

@nicsuzor Thanks for the feedback! I believe the current behavior still supports the default fallback logic. In particular, `ModelFamily.UNKNOWN` is explicitly handled via: ```python for model in __unknown_models: register_transformer("openai", model,...

@nicsuzor Thanks again — I took a deeper dive and I believe I’ve now identified exactly what you were referring to. Just to confirm, is this the case you meant?...

@nicsuzor Yup! after #6213 your test case is work well~ ``` family == 'gemini-2.5-pro':The capital of France is **Paris**. family == 'gemini-1.5-pro':The capital of France is **Paris**. ``` Thanks for...

I believe this could be an important improvement for SoMA. However, since there is no linked issue for this bug, it’s difficult to assess its severity. It would be helpful...

How about change like it? Now we have `Workbench` instead of tools. ```python import asyncio import dotenv import os from pathlib import Path from autogen_ext.models.openai import OpenAIChatCompletionClient from autogen_ext.tools.mcp import...