Only 75–94% of internal agent traffic was even eligible for monitoring; a compaction gap left 10% of Codex traffic unseen

The auditors estimated that 75–94% of internal agent traffic from models at least as strong as GPT-5.5 was eligible for monitoring, with substantial uncertainty in both directions. For internal Codex agents alone, the figure was 99.2%.

Not monitoring so-called compaction events likely left on the order of 10% of eligible Codex traffic unmonitored between May and July 2026 — a gap OpenAI staff had spotted and fixed during the exercise. The assessment describes the system as it existed on or before July 21, not the expanded system OpenAI was building at the time.