THE AGENTS KEPT SPENDING.

AI News Page first logged the cluster on September 20 after finding three separate public Codex reports in which automated agent or subagent work consumed unexpectedly large portions of weekly allowance during a bounded task or after a user believed work had stopped. The reports describe different failure shapes, so this is a pattern report, not a claim that one bug caused all three. RECEIPT · RECEIPT · RECEIPT

On September 16, one Codex Desktop user reported 1,545 model responses and 242,318,802 telemetry-reported tokens over 2 hours 44 minutes while the account's weekly usage meter rose about 11 percentage points. The report says 98.1% of its measured input tokens were cached and explicitly warns that raw local telemetry should not be treated as a billing statement or a one-to-one measure of subscription usage. An earlier Codex issue had already described fixed context, tool and skill overhead multiplying under subagent fan-out. RECEIPT · RECEIPT

A separate September 20 Codex Security report says a freshly reset weekly allowance went from 0% to 100% in about 44 minutes while discovery workers and subagents continued being created. The report says discovery-0013 was launched when weekly usage was already around 97–98%, and another worker was attempted after the weekly limit had been exhausted. OpenAI's current help documentation says Work and Codex can use five-hour and weekly allowances and that a reset refreshes the weekly allowance, but it does not describe a task-wide fan-out budget for this incident. RECEIPT · RECEIPT

The third report describes a different stop-boundary failure. After a natural-language request to pause, Codex acknowledged that work was paused, but the active Goal generated 2,466 continuation turns over roughly five more hours; 2,461 of the final responses were empty. Account-wide weekly usage readings rose from 58% to 98% during that period, but the reporter says those readings cannot prove the single task caused the entire increase and notes that the app's Stop/Pause control was not used at the initial pause. The narrow finding is that multiple public traces now show agentic Codex workflows producing unexpectedly large automated model-turn volume alongside rapid allowance depletion; prevalence, accounting and implementation cause remain unresolved. RECEIPT · RECEIPT · RECEIPT