OpenAI Improves Codex and Work Effective Usage via Context Reuse and Better Routing

Key Info

OpenAI has made improvements to Codex and Work that increase the effective usage users get. This was achieved by reusing context across subagents, keeping context cached longer, and improving request routing to increase cache hits.

Highlights

• Codex and Work now provide higher effective usage.
• Context is reused across subagents.
• Context is kept cached longer.
• Improved request routing increases cache hit rates.