Unverified50% confidenceFactExact time
The compact command makes an additional call to the model to merge and compress conversation messages, retaining only content relevant to the current session in order to free up context.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/6/2026
First Seen
Valid until: 1/4/2027
Sources
Related Entities
Related Claims
UnverifiedThe /compact command works by summarizing and compressing the current session, retaining key decisions and code change records while discarding redundant intermediate discussions.78% similarUnverified本次更新新增面向任意模型的实验性自动压缩（Experimental Auto Compaction）功能，用于长对话场景下的上下文管理77% similarUnverifiedCadenya has a built-in Context Compaction mechanism to automatically manage the context of long conversations.76% similarUnverifiedBefore the context is about to overflow, compressing and summarizing key information and transferring it to a new conversation instance can avoid the cost explosion of long contexts; this pattern is referred to as Context Condensation in AI coding tools such as Cursor and Windsurf.73% similarUnverified将工作拆分为独立工单可缓解LLM对话过长时的上下文遗忘问题，使每个对话的上下文窗口保持精简71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/981597API
curl https://kongchang.com/api/v1/knowledge/claims/981597MCP
get_claim(id=981597)