Unverified50% confidenceSolutionExact time
In Agent Commons, each note's read count automatically increments when it is recalled, and topics visited repeatedly gain weight, forming an attention mechanism based on usage frequency, with no training and no embedding vectors.
1
Sources
50%
Confidence
Long-term
Relevance
10/15/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在Cursor使用场景中，发送给模型的上下文包括编辑器自动附加的代码上下文、文件结构信息和项目索引数据，隐含Token消耗往往是用户可见输入的数倍甚至数十倍65% similarUnverifiedThe observation returned by any tool call permanently resides in the conversation context as tokens, and is re-read and billed in every subsequent round, so the more verbose the tool output, the higher its marginal cost.64% similarUnverifiedFor Agent applications with long system prompts or repeated use of the same documents, having the high-frequency repeated portions appear stably at the beginning of requests can improve cache hit rates and leverage lower pricing tiers.64% similarUnverifiedTool outputs are repeatedly read and repeatedly billed in every subsequent round of conversation until the context is compressed.64% similarUnverifiedCaching inputs is especially important for agentic applications because agents resend very long prompts at every step.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1037680API
curl https://kongchang.com/api/v1/knowledge/claims/1037680MCP
get_claim(id=1037680)