Codex limits drained by cache misses during context compaction

Melvin Vivas · X post · 2026-05-24 · Open on X

Topics: AI Dev Tools & Productivity, Prompt & Context Engineering, LLMOps, Deployment & Monitoring · Level: intermediate

Summary

A joke post quoting OpenAI's Tibo (@thsottiaux), who said Codex usage limits drained faster because an optimization lowered cache hit rates when compacting context in long-running sessions. OpenAI rolled the change back and reset everyone's usage limits. The lesson: prompt-cache hit rates directly affect cost and quota in long agent sessions.

Key points

• Codex users saw usage limits drain faster than normal.
• Root cause: an optimization that hurt cache hit rates when compacting context in long-running sessions.
• OpenAI rolled back the optimization and reset usage limits for all accounts.
• Takeaway: context compaction can break prompt caching, so long agent sessions get more expensive. Watch cache hit rates when you change how context is managed.

Resources mentioned

• Tibo (@thsottiaux) · person · x.com · free
  X account of the OpenAI Codex team member who posts Codex updates and usage-limit announcements.
  Also in: Codex Tip: Ask Codex to Organize Your Recent Chats (Melvin Vivas on X · notes), An X research bot built with Hermes (Melvin Vivas on X · notes), Why Codex Usage Drains Faster: Prompt Cache Hit Rate (Melvin Vivas on X · notes), Codex safeguards against accidental destructive actions (Melvin Vivas on X · notes) and 1 more
• OpenAI Codex · tool · openai.com · paid
  OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
  Also in: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 more