Codex users: a 1M context window in codex.toml kills your cache and burns limits
thursdai_pod · x · 2026-09-27
A practical Codex debugging case from thursdaipod: @altryne's config had a 1M context window set, which disables OpenAI's prompt cache and dramatically increases usage.
The fix:
- Remove the 1M context setting from codex.toml
- Move sub-agents to a cheaper model
Usage returned to normal afterward. If your Codex limits are being eaten unexpectedly, check your codex.toml first.
Related event: Codex users warned: 1M context setting destroys cache and burns quota(3 posts)→
More from coding & agent
- Explosion launches Ellf directory: 52 NLP templates plus multi-agent annotation workflow — _inesmontani · 2026-11-11
- Meme: 'Stochastic AI Agent Architecture' Is Just a Markov Chain in Disguise — PrasoonPratham · 2026-11-11
- OpenCode adds Gemini 4 Carbon and Claude Fable 5.2 support — dean_rie · 2026-11-11
- OpenClaw v2026.11.3 patch fixes cert verification and credential exposure across 56 PRs — dean_rie · 2026-11-11
- Fable 5.2 captured 1 in 4 Claude replies on day one, then growth stalled — dean_rie · 2026-11-11
- QA engineer proposes MCP agent to automate ad postback checks before every app release — Soobhee_Chukwutosin · 2026-11-11