Codex CLI Reportedly Burns Through Quotas via Polling
ssh4net · x · 2026-07-10
A user highlighted a bug in Codex CLI (and potentially the app): during wait/polling phases, it repeatedly resends roughly 170,000 tokens of context, rapidly draining usage quotas.
The poster believes this stems from a design flaw in code-mode's wait/yield or a regression in model/tool policy, rather than standard model inference costs.
Related event: Codex CLI Bug Burns Quota by Repeatedly Polling 170k Tokens(2 posts)→
More from coding & agent
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11