Expired85% confidenceFactTime unknown
When the context is full, Codex automatically compresses and clears unimportant information to continue working.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Codex桌面端使用教程：安装配置到界面功能完整拆解
bilibili跟着阿亮学AI
Related Entities
Related Claims
UnverifiedCodex has a built-in automatic compression mechanism that automatically organizes long conversations into concise summaries to free up space when the context is nearly full.79% similarUnverifiedCodex now supports automatic session compression, which uses a summarization algorithm to distill conversation history into key information, freeing up window space without losing core context.72% similarUnverifiedCodex has a built-in automatic compression feature for historical context that controls token consumption through summarization and importance filtering, allowing continuous conversation within the same session window for weeks.71% similarUnverifiedCodex uses a 'sliding window + summary compression' strategy to condense earlier conversation content into brief summaries, controlling actual token count per turn.70% similarUnverifiedThe new version of Codex has optimized the memory feature, compressing sessions more thoroughly rather than simply reusing threads to carry over existing conversations66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/17764API
curl https://kongchang.com/api/v1/knowledge/claims/17764MCP
get_claim(id=17764)