Spark ran out of context

Resolved 💬 5 comments Opened Feb 21, 2026 by budivoogt Closed May 14, 2026

💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

Got this when working with Spark xhigh. Looks like compaction isn't happening in time nor automatically.

Codex ran out of room in the model's context window.
Start a new thread or clear earlier history before
retrying.

View original on GitHub ↗

5 Comments

github-actions[bot] contributor · 6 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

#11641
#11071
#11723
#10877
#10823

Powered by Codex Action

bahmanpour1980-lab · 6 months ago

#11641
#11071
#11723
#10877
#10823 #12414

etraut-openai contributor · 6 months ago

Please use /feedback to upload the session details and post the thread ID here.

yassirusa · 4 months ago

When will this be worked on. Codex-5.3 and codex-5.3-spark are completely useless and they keep churning tokens without editing any code until they "run out of room"

etraut-openai contributor · 3 months ago

Closing because no response about /feedback.