Fresh weekly Codex/Work allowance exhausted in ~44 minutes by security-scan worker fan-out

Environment

ChatGPT Desktop for Windows
Windows 11
Codex / Work
GPT-5.6 Sol
Local Codex host on Windows
Issue observed with multi-agent security scan / subagent orchestration

Bug:

I’m investigating what looks like abnormal Work/Codex usage behaviour after a full weekly reset.

Plan:
ChatGPT Pro

Incident:
20 September 2026, BST

What happened:

  • I used a full Work/Codex reset at approximately 00:17 BST.
  • Local Codex rollout telemetry confirms the fresh weekly window started at 0% used.
  • The same telemetry shows a 10,080-minute (7-day) primary window.
  • The weekly counter reached 100% roughly 44 minutes later.
  • An explicit usage_limit_exceeded error followed seconds later.

The important part is what was running during that period.

I had requested one comprehensive local security assessment of a Java web application.

The Codex security workflow expanded into a large worker/subagent tree under one scan ID:

50e37f7f-6173-4df2-87bd-7daaf26bb9d7

The recovered rollout logs show numbered Standard discovery workers from discovery-0001 through discovery-0014.

Workers 0001-0004 existed before the reset.

After the reset, additional discovery workers continued being created, including discovery-0013 very close to weekly exhaustion.

Each Standard discovery worker configuration included:
subagents = 3

The logs also show many additional subagent sessions.

Across the reset-to-exhaustion window I identified dozens of new Codex sessions, mostly security_scan and subagent sessions.

One particularly concerning detail:
discovery-0013 was launched when the weekly allowance was already around 97-98% used, yet it was still instructed to run another Standard scan with subagents.

After the weekly limit had reached 100%, the orchestration later attempted to create discovery-0014. That attempt was blocked by the usage limit.

The local telemetry also reveals a reporting issue.

A diagnostic task eventually told me:

“Current Codex allowance is healthy: 6% used when checked.”

However, that 6% figure came from an earlier reading.

By the time that same task completed, its own rate-limit telemetry showed approximately 69% used.

So the user-facing status was materially stale while concurrent agentic activity was still running.

Another detail I’m trying to understand:
the captured rate-limit telemetry consistently shows:

primary.window_minutes = 10080
secondary = null

I had expected some shorter/5-hour safeguard to limit a runaway burst before an entire weekly allowance could disappear in under an hour.

I am not claiming that no real usage occurred. The logs clearly show substantial model activity.

My concern is that one requested security assessment expanded into a very large automatically orchestrated worker/subagent tree, with continued worker creation right up to the weekly limit.

Questions for OpenAI / other users:

  1. Is this level of discovery-worker fan-out expected for one Standard security scan?
  2. Should a security workflow continue spawning new workers when weekly usage is already above 95%?
  3. Is secondary = null expected for this type of Work/Codex usage?
  4. Are interrupted/retried/replacement workers all charged independently?
  5. Has anyone else seen a fresh weekly allowance disappear this quickly because of multi-agent worker fan-out?
  6. Is there currently any supported usage guardrail or warning threshold for multi-agent Codex tasks?

I already have an open Support case and have provided them a sanitised evidence pack with timestamps, worker IDs, quota progression and hashes of the original rollout logs.

I’m posting here to see whether this is a known orchestration/usage issue and whether others have experienced similar behaviour.

I’m deliberately not posting raw rollout logs because they contain private project data.

Welcome to the forum!

The forum is not the official issue tracker. If the problem needs to be formally reported and tracked by the Codex maintainers, the official place is the OpenAI Codex GitHub issue tracker.

There are several open issues but your post lacks enough detail to select one.

Consider searching the existing Codex issues for a match. If you cannot find one, consider opening a new issue and include as much relevant information as possible, such as your Codex version, operating system, environment, reproduction steps, expected behavior, actual behavior, and any relevant logs or error messages.

The bit about workers 0001-0004 already being live before the reset feels like the key. A quota reset isn’t the same as a task-tree cancellation; if the counter just got zeroed while the existing worker tree kept running, those in-flight workers would keep spawning subagents and the new sessions would be billed against the fresh allowance.

That would make 44 minutes to 100% less of a billing anomaly and more of a fan-out still running across the reset boundary. Worth checking whether the orchestrator sent any cancel to those pre-existing workers at 00:17, or only reset the counter.

Thanks — I’ve now filed this in the official OpenAI Codex GitHub issue tracker as:

openai/codex issue #46819

It includes the detailed telemetry and a sanitised evidence PDF. The recovered local logs confirm the fresh weekly reset went from 0% to 100% in approximately 44 minutes while the Codex Security workflow continued creating discovery workers/subagents.