Persist Agent History Across Sessions in AutoGen Studio

[MrEdwards007]

I tried multiple times to create a bug report, as I see this as a bug, not a feature request but whenever I tried to create a bug report, and repeatedly received error (dont recall the exact verbiage) 'issue, could not be generated', so I will pursue this in another way.

Issue Description:

In AutoGen Studio version 0.4, we’ve observed that agents start each run without access to prior session history. This results in agents behaving as if each session is brand new, with no memory of past interactions.

Use Case:
As a user of AutoGen Studio, I want to ensure that agents can retain context between sessions. In earlier versions, agent memory seemed to persist across sessions in a more integrated way, which allowed for more natural and continuous interactions.

Current Behavior:

• Each new run in AutoGen Studio discards prior history.
• Agents begin conversations from scratch, with no embedded memory or context.

Expected Behavior:

• Agents should be able to recall prior interactions, either through built-in memory persistence or by easily embedding history at the start of each session.

Questions:

• Is there an intended way to embed previous conversation history in each new session?
• Are there recommended patterns for persisting and restoring history in a seamless way?

Related Discussion:

kanika – 3/19/25, 9:33 AM
“I am working on autogen 0.4 version, and in each run the history is not shared so the agents really start the conversation from zero. How to make sure to embed the history to agents in every session?”

MrEdwards – 3/19/25, 3:32 PM
“This is exactly the reason for my coming to this forum. The old autogen studio sessions were known by the agents. Is there a workaround, such as a RAG implementation (not that I want to figure that out) which would hold the context of the previous session?”

I initially thought that RAG might work but then you would lack context, since the entire history would not be present. Chunks of related information would only be available from session to session.

Would something like the pseudo-code below work and if so, how could this be made mainstream.
I'm struggling to obtain value in a one-turn session, rather than a continuation or ongoing conversation.

from autogen_agentchat.agents import AssistantAgent
from autogen_core.memory import ListMemory, MemoryContent, MemoryMimeType
from autogen_ext.models.openai import OpenAIChatCompletionClient

# Initialize memory
user_memory = ListMemory()

# Add previous conversation content to memory
await user_memory.add(MemoryContent(content="Previous conversation content here", mime_type=MemoryMimeType.TEXT))

# Configure the assistant agent with memory
assistant_agent = AssistantAgent(
    name="assistant_agent",
    model_client=OpenAIChatCompletionClient(model="gpt-4o-2024-08-06"),
    memory=[user_memory],
)

Environment:

• AutoGen Studio version: 0.4.x
• Platform: Python / AutoGen SDK
• Deployment: Local and experimental workflow prototyping

[MrEdwards007]

This should have been a bug and I'm now able to create a bug report, where I was not able to do so previously.