high mem usage

[jdlambert0]

What happened?

High memory usage detected: 7.77 GB. If you experience a crash, please file a bug report
by running /bug
while trying to run two agents on a third

What did you expect to happen?

agents to work

Client information

• CLI Version: 0.19.4
• Git Commit: 9351148
• Session ID: 75ddfafb-88c2-49d0-95f0-7e793a2c7188
• Operating System: win32 v24.11.1
• Sandbox Environment: no sandbox
• Model Version: auto
• Memory Usage: 339.5 MB

Login information

No response

Anything else we need to know?

No response

[neeraj-par]

This issue is caused by the same root cause identified in #19607: GeminiChat.getHistory() was calling structuredClone(history) on every model call, creating O(n) deep-copy allocations per turn that compound into several GB of RSS when running multiple long-context agents concurrently.

That root cause has been fixed in #19608 (perf(core): fix OOM crash in long-running sessions), which replaces structuredClone with a shallow array spread ([...history]). The fix is already merged into main.

This issue can be closed as a duplicate / already fixed.

[neeraj-kumarr]

👋 Hi, I'm neeraj-kumarr — this is my new GitHub account. neeraj-par is my previous account. I will be continuing all contributions and follow-up work from neeraj-kumarr going forward. neeraj-par approves this transition.

[neeraj-par]

👋 Signing off from neeraj-par — this account is no longer active. I've moved to neeraj-kumarr. All future contributions and follow-up work will come from there. Thanks for the collaboration!

[gemini-cli]

Hello! As part of our effort to keep our backlog manageable and focus on the most active issues, we are tidying up older reports.

It looks like this issue hasn't been active for a while, so we are closing it for now. However, if you are still experiencing this bug on the latest stable build, please feel free to comment on this issue or create a new one with updated details.

Thank you for your contribution!