Subagent feature: Launching concurrent subagents instantly drains entire Pro plan usage quota #9748

What version of Codex is running?

0.89.0

What subscription do you have?

Pro

Which model were you using?

gpt-5.2-xhigh

What platform is your computer?

ubuntu

What terminal emulator and version are you using (if applicable)?

vscode

What issue are you seeing?

When using the subagent feature in Codex to launch multiple subagents concurrently, the entire Pro plan 5-hour usage quota is instantly consumed (100% drained), even though the actual compute performed is minimal.

What steps can reproduce the bug?

1. Have an active Pro plan subscription with full/fresh 5-hour usage quota
2. Start a Codex session
3. Launch approximately 6 subagents concurrently (e.g., for parallel codebase exploration)
4. Observe usage meter

What is the expected behavior?

Usage should incrementally increase based on actual tokens processed by each subagent, proportional to the work performed.

Additional information

Actual Behavior

The entire 5-hour Pro plan usage quota is instantly drained to 100% upon launching concurrent subagents, regardless of actual work completed.

Impact

This makes the subagent feature effectively unusable for Pro subscribers, as a single concurrent subagent operation exhausts the entire weekly quota.