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
- Freebuff launches ad-funded free coding agent offering GPT-6 Luna at $0 — pbaylies · 2026-09-27
- DHH rewrites ttfx in asm with AI, hitting 8x mean speedup on an Intel 135U — olcan · 2026-09-27
- Developers are switching services over missing APIs and MCP support — aronchick · 2026-09-27
- Cloudflare Workers adds gradual deployment annotations on metrics charts — irvinebroque · 2026-09-27
- Dev sponsors BookStack monthly to let AI agents read project knowledge bases — airesearch12 · 2026-09-27
- Indie dev rebuilds his Obsidian tooling with Codex, open-sources it for ~$15 in tips — vista8 · 2026-09-27