- Notifications
You must be signed in to change notification settings - Fork 2.3k
Open
Open
Copy link
Labels
services[Component] This issue is related to runtime services, e.g. sessions, memory, artifacts, etc[Component] This issue is related to runtime services, e.g. sessions, memory, artifacts, etcwip[Status] This issue is being worked on. Either there is a pending PR or is planned to be fixed[Status] This issue is being worked on. Either there is a pending PR or is planned to be fixed
Description
** Please make sure you read the contribution guide and file the issues in the right place. **
Contribution guide.
Describe the bug
ADK crashes with the error 'dict' object has no attribute 'start_timestamp' when event compaction is enabled in v1.18.0.
To Reproduce
Please share a minimal code and data to reproduce your problem.
Steps to reproduce the behavior:
- Install google-adk==1.18.0
- Enable event compaction in the ADK configuration, for example:
events_compaction_config=EventsCompactionConfig( compaction_interval=1, overlap_size=0, ) - Start a session and begin chatting.
- After follow-ups exceed the compaction interval, the crash occurs.
Expected behavior
ADK should not crash; chatting should continue normally with event compaction enabled.
Screenshots
Desktop (please complete the following information):
- OS: [e.g. macOS, Linux, Windows]
- Python version(python -V):
- ADK version(pip show google-adk):
Model Information:
- Are you using LiteLLM: Yes/No
- Which model is being used(e.g. gemini-2.5-pro)
Additional context
- As a temporary workaround, I’ve removed the compaction config.
- A PR has been sent to fix this issue: fix(sessions): use model_validate to deserialize nested EventCompaction #3490
Kikketer and hangfei
Metadata
Metadata
Assignees
Labels
services[Component] This issue is related to runtime services, e.g. sessions, memory, artifacts, etc[Component] This issue is related to runtime services, e.g. sessions, memory, artifacts, etcwip[Status] This issue is being worked on. Either there is a pending PR or is planned to be fixed[Status] This issue is being worked on. Either there is a pending PR or is planned to be fixed