Expired85% confidenceFactTime unknown
In Codex, each Thread maintains independent conversation history, file operation records, and intermediate states, and the AI memory between different Threads is completely isolated.
1
Sources
85%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026(expired)
Sources
Related Entities
Related Claims
Partially VerifiedCodex's memory feature is divided into two levels: project memory (Agent.md) and global memory71% 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.66% similarUnverifiedCodex Memory的脱敏处理主要依赖正则表达式匹配和语义识别两种手段协同工作65% similarUnverifiedThe new version of Codex has optimized the memory feature, compressing sessions more thoroughly rather than simply reusing threads to carry over existing conversations63% 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.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/19923API
curl https://kongchang.com/api/v1/knowledge/claims/19923MCP
get_claim(id=19923)