Fix stream iterator

[enyst]

• Include this change in the Release Notes. If checked, you must provide an end-user friendly description for your change below

End-user friendly description of the problem this fixes or functionality that this introduces.
Fix issue that was slowing agent responses as the conversation got longer

---

Give a summary of what the PR does, explaining any non-trivial design decisions.

Fix iteration - it was going through the whole stream to make a list. 🤦

---

To run this PR locally, use the following command:

docker run -it --rm   -p 3000:3000   -v /var/run/docker.sock:/var/run/docker.sock   --add-host host.docker.internal:host-gateway   -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:59d3869-nikolaik   --name openhands-app-59d3869   docker.all-hands.dev/all-hands-ai/openhands:59d3869

[malhotra5]

Nice catch!

[malhotra5]

It seems like there's similar logic here to fetch first user message: https://github.com/All-Hands-AI/OpenHands/blob/2bd60c87c6b962f9eab97986e67cfff69372c766/openhands/controller/agent_controller.py#L944-#L957

Could possibly de-dup?

[enyst]

Good point! Lets see

[enyst]

It seems like there's similar logic here to fetch first user message: https://github.com/All-Hands-AI/OpenHands/blob/2bd60c87c6b962f9eab97986e67cfff69372c766/openhands/controller/agent_controller.py#L944-#L957

Could possibly de-dup?

I moved the dedup here:

• Fix truncation state persistence bug #7212

That PR fixes a bug in the same area. I'll test them both. The reason why that PR is waiting is that I want to make a more complex test with two sessions restored in succession, and for some reason that proved tricky. But I'll finish it asap.