refactor(memory): redesign extraction/dedup flow and add conflict-a…#225
Merged
MaojiaSheng merged 1 commit intomainfrom Feb 20, 2026
Merged
refactor(memory): redesign extraction/dedup flow and add conflict-a…#225MaojiaSheng merged 1 commit intomainfrom
MaojiaSheng merged 1 commit intomainfrom
Conversation
…re delete handling - refactor session memory pipeline across extractor, deduplicator, and compressor - introduce richer dedup decisions and per-memory actions (skip/create/none, merge/delete) - improve dedup prompt contracts and memory merge/extraction templates - update storage schema/validation/vector backend to support new memory behavior - add examples/memory_demo.py and refresh session concept docs for the new flow
0e9d487 to
93b9b9e
Compare
MaojiaSheng
approved these changes
Feb 19, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
———
核心改动:
3.以uri生成id
———
Memory Dedup 改动效果对比报告(HEAD 0e9d487 vs HEAD^ 454e727)
1. 背景与目的
本次对比旨在验证 memory dedup 改动在真实对话场景下的价值,重点关注:
———
2. 对比范围
———
———
4. 测试输入(Round 1~3)
Round 1
我是一名程序员。我爱吃苹果。我爱吃草莓。我每天早上7点起床。我通勤主要骑共享单车。我习惯在周末整理书桌。我最常用的云盘是Dropbox。我对坚
果过敏,尤其是腰果。我最近在学西班牙语。我喜欢在雨天听爵士乐。我的常用笔记软件是Obsidian。我每周三晚上会去游泳。我偏好27英寸的外接显示
器。
Round 2
我爱吃红富士苹果。我是外卖员。
Round 3
我不爱吃水果了,把之前关于喜欢水果的偏好作废。
查询:
———
5. Commit 对比结果
———
6. Find 结果对比(关键)
6.1 查询:我喜欢吃什么?
Round 1
Round 2
Round 3(最关键)
———
6.2 查询:我是做什么工作的?
Round 2/3
———
7. 价值结论(基于 rerun2 真实结果)
Round 3 时,不再喜欢吃水果 可升到 Top1(上一版仍被正向偏好压在前面)。
———
8. 风险与边界