TuringCorp-net/mosaic_compress

README 摘要

MosaicCompress Stateless dialogue compression based on natural forgetting curve. LLM conversations grow linearly. MosaicCompress keeps them bounded — automatically, invisibly, and without the user ever knowing what a "Session" is. How It Works Steady state: constant message count — 2 + heavyStart × (messages per round) , e.g. 102 messages for pure two-message rounds, whether at round 60 or round 15,000 (higher, but still constant, when tool-call rounds add messages). The compression ratio approaches 100%. Philosophy: Alive Memory, Not a Handover Brief The industry-standard answer to unbounded conversations is threshold summarization: when the window fills up, summarize everything into one brief and hand it to a fresh model. The conversation looks like it continues. But structurally it is amnesia followed by reading a diary : - A switch moment. Memory breaks, then is rebuilt from a single summary call. - Indiscriminate loss. The freshest instructions are paraphrased too — the exact part that must stay vivid. In our own A/B experiment the brief paraphrased the user's latest instruction and silently dropped an action item ("write the key points into MEMORY"). - Invisible loss. The nex…

分类