autogen

autogen copied to clipboard

changed 'workbench' from list to dict to match AssistantAgentConfig schema

2

## Why are these changes needed? This fixes schema validation error caused by incorrectly setting "workbench" as a list in team.json. The framework expects "workbench" to be a dictionary. ##...

sanjiv27

[DRAFT] Add OpenAI Client Error Handler

8

## Why are these changes needed? This PR introduces an error handler decorator on the openai client. The implementation allow users to specify error callbacks in case the client fails....

lspinheiro

GraphFlow doesn't follow conditions, ends after a single node step

3

### What happened? **Describe the bug** The GraphFlow terminates early, seemingly ignoring edges and edge conditions. **To Reproduce** Steps to reproduce the behavior. The below is a slightly modified version...

smpurkis

Bumps [form-data](https://github.com/form-data/form-data) from 4.0.3 to 4.0.4. Changelog Sourced from form-data's changelog. v4.0.4 - 2025-07-16 Commits [meta] add auto-changelog 811f682 [Tests] handle predict-v8-randomness failures in node < 17 and node >...

dependabot[bot]

Function calling reflection error

2

### What happened? **path:venv\Lib\site-packages\autogen_agentchat\agents\_assistant_agent.py** RuntimeError("Reflect on tool use produced no valid text response.") When "reflection_result.content" is a Function_calls LIST. The situation occurs in consecutive multiple tool calls. **For example** Task...

inspire-boy

fix: SocietyOfMindAgent should save its response into context

4

## Why are these changes needed? Currently SocietyOfMindAgent doesn't save its own response message into context, so in a multi round chat scenario, when this SocietyOfMindAgent is picked by upstream...

dason8

### What happened? **Describe the bug** Using AutoGen with Open AI client linked to OpenRouter for Kimi K2, I often get ill-formatted tool-call responses and thus hardly usable agent. **To...

katossky