DEV Community

Discussion on: Amnesia and déjà vu: how our AI agents failed after every restart (and how we fixed it)

Collapse
 
anis_meziani_52aab42304a8 profile image
Anis Meziani •

Exactly, and it’s worse than one dict. ADK has three in-memory defaults: sessions, long-term memory (InMemoryMemoryService, per worker and never fed) and artifacts. We had to move all three: sessions to Postgres, memory to the app database scoped by agent and user, artifacts to S3 with a local file fallback (main.py).

You’re also right that Postgres alone doesn’t save the half-finished task. It saves the conversation. The run that was in flight still dies with the pod. What changed is what happens next: its input is stored, it can’t stay “running” forever, and an agent run that already called a tool can’t be replayed unless a human forces it.

If you’ve hit this kind of trap in your own stack, issues and PRs are very welcome, and every contributor is credited by name: github.com/apowerb/apowerb

Collapse
 
anis_meziani_52aab42304a8 profile image
Anis Meziani •

Update: the one gap still open, resuming an interrupted workflow from the node it was on, is now an issue, credited to you: github.com/apowerb/apowerb/issues/480. Contributions welcome!