Codex desk · usage policy · Codex · Policy
Codex and Work improve effective usage through caching
Tibo says context reuse, longer cache retention and better routing increase effective usage. He did not announce a quota reset or a larger allowance.
Day 12/ We’ve made improvements to Codex & Work that increase the effective usage you get. We achieved this by reusing context across subagents, keeping context cached longer, and improved request routing that allows us to increase cache hits.
“increase the effective usage you get.”
Tibo says Codex and ChatGPT Work now deliver more effective usage by reusing and caching context more often. The original post describes efficiency changes, without announcing a reset or a larger plan allowance.
In his Day 12 update at 23:55 UTC on October 16, Tibo said Codex and Work have improved the effective usage users get. He attributed the change to context reuse across subagents, longer cache retention and improved request routing that raises cache hits. X syndication verifies the complete original post, author and timestamp.
A cache hit can reduce repeated processing, but the post supplies no measured percentage or guarantee for any account. It does not specify plans, models, rollout timing or whether every user has received the improvement.
Tibo did not promise a full or banked reset, clear usage counters, or announce a new numeric allowance. This article is usage-policy coverage and does not enter confirmed reset history, calendars or subscriber reset alerts. The separate Day 10 reset remains provider-reported complete with its scope and mechanics unknown.
What it means
- Tibo reports more effective usage from reusing context across subagents, keeping context cached longer and routing requests for more cache hits.
- The post does not quantify the gain, name eligible plans or say that usage counters were cleared or allowances increased.
- This is a usage-efficiency change, not a full or banked reset. It stays outside reset history, calendars and subscriber reset alerts.