Codex context auto-compaction loop rereads files, loses progress, and burns paid credits

A long-running Codex project chat on GPT-5.6 Sol entered a context auto-compaction loop. After each 'Context automatically compacted' event, Codex retained the broad project objective but appeared to lose execution progress. It repeatedly reread the same files, reloaded the same skills or memory files, restated that it had found the exact defect, promised the next update would contain the completed change, then compacted again before completing the edit. The requested implementation was never completed, and the loop consumed roughly 10%-15% of the user's available paid Codex usage. Context was 93% full at 240,000 / 258,000 tokens when captured.

What this means for youIf you use AI coding agents on long projects, watch your usage meter, and stop a session that keeps rereading the same files or repeating itself. At work, ask whether usage caps or spending alerts are set before a long agent run.