up

reme2/config/reme_todo.md

@@ -0,0 +1,86 @@
+ReMe重构
+1. 根目录
+  a. vault_root 改回 working dir @sen
+2. file_parser
+  a. 抽象基类 parse: @jinli
+    ⅰ. 输入是path：相对路径 
+    ⅱ. 输出是FileMetadata & list[FileChunks] & list[FileEdge]
+  b. default parser 兼容老方案 @jinli 
+    ⅰ. 带overlap的chunking策略 ，不输出FileEdge
+  c. markdown parser @sen
+    ⅰ. 根据markdown ast做chunk，不需要overlap
+    ⅱ. 增加一个索引的chunk chunk_type @锦鲤 file_chunk_type content/index
+    ⅲ. 增加link的正则解析：predicate:: [[path#anchor]]
+3. file_store @sen
+  a. 抽象存储：
+    ⅰ. filenode = file + path + st_mtime + metadata + list[FileEdge]
+    ⅱ. graph=dict[str, filenode] 内存+json
+    ⅲ. list[FileChunk] 存db
+  b. 抽象基类
+    ⅰ. graph：fellow dict的操作 update/get/set
+    ⅱ. chunks 	dict[str, list[chunk]]
+      1. delete_chunks_by_path
+      2. update_chunks_by_path
+      3. list_chunks_by_path
+      4. vector_search/keyword_search
+    ⅲ. 手写一个bm25检索
+    ⅳ. 【核心】检索机制 vector bm25 graph 如何进行融合
+4. file_watcher @jinli
+  a. 抽象基类
+    ⅰ. on_start: 
+      1. file_store 的start 在前，加载graph，file_watcher在后，递归扫描目录
+        a. 通过ms_time对比graph，on_change 进行改动
+    ⅱ. on_change:
+      1. 更新/增加: 
+        a. delete_chunks_by_path 更新数据库
+        b. upate_chunks_by_path 更新数据库
+        c. 更新graph
+      2. 删除
+        a. delete_chunks_by_path 更新数据库
+
+MemorySchema
+1. markdown文件结构 @sen
+  a. formatter：
+    ⅰ. title
+    ⅱ. desc
+    ⅲ. tags
+    ⅳ. 
+2. memory文件结构目录
+  a. MEMORY.md
+  b. msg/files -> daily/YYYYMMDD/YYYYMMDD.md + xxxx.md
+    ⅰ. YYYYMMDD.md
+      1. xxx -> xxxx.md
+      2. xxx -> xxxd.md
+    ⅱ. 
+  c. daily -> topic/topic_l1/topic_l1.md + xxx.md + topic_l2
+  d. proactive
+
+steps:
+1. 治理（算法+LLM）：
+  a. 节点关联P0：现有的链接做补充，挖掘新的LLM的link
+    ⅰ. /Users/yuli/workspace/ReMe/reme2/component/edge_extractor/llm_edge_extractor.py
+    ⅱ. 移动到steps
+  b. 节点整合/节点拆分/节点归档
+  c. 健康度检查
+2. retrieve 调用store的检索
+3. 原子steps：reme edit
+4. 组合steps：总结：
+  a. - freq (every_n_turn、compact) -> daily_summarizer
+  b. topic (/dream ) -> topic_summarizer(daily_xx -> topic_xx)
+  c. proactive -> proactive_summarizer(personal_xxx -> proactive_query - pre_query
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Qwenpaw

reme2/memory/schema/memory.py

@@ -213,8 +213,6 @@ class Memory(BaseModel):
     title: str = Field(default="")
     description: str = Field(default="")
     tags: list[str] = Field(default_factory=list)
-    created: date | None = None
-    updated: date | None = None
 
     # -- The four behavioral axes ------------------------------------------
 
@@ -225,9 +223,6 @@ class Memory(BaseModel):
 
     # -- Cross-cutting graph fields ----------------------------------------
 
-    topics: list[str] = Field(default_factory=list, description="Outbound wikilinks to class memories.")
-    parent: str | None = Field(default=None, description="Wikilink to owning memory (e.g. material → event).")
-
     # -- Role / lifecycle / source-conditional fields ----------------------
 
     confidence: Confidence | None = Field(
@@ -238,11 +233,6 @@ class Memory(BaseModel):
         default=None,
         description="Lifecycle state. Meaningful only when lifecycle == streaming.",
     )
-    origin_session_id: str | None = Field(
-        default=None,
-        alias="originSessionId",
-        description="Capture session id. Set when source == auto.",
-    )
 
     # -- Migration: pre-validate hook --------------------------------------
 

reme2/schema/file_chunk.py

@@ -9,6 +9,7 @@ class FileChunk(BaseNode):
     path: str = Field(...)
     start_line: int = Field(...)
     end_line: int = Field(...)
+
     hash: str = Field(...)
     scores: dict[str, float] = Field(default_factory=dict)
 

reme2/schema/file_metadata.py

@@ -1,8 +0,0 @@
-from pydantic import BaseModel, Field
-
-
-class FileMetadata(BaseModel):
-    file: str = Field(...)
-    path: str = Field(...)
-    st_mtime: float = Field(...)
-    metadata: dict = Field(default_factory=dict)

reme2/schema/file_node.py

@@ -0,0 +1,28 @@
+from pydantic import BaseModel, Field, ConfigDict
+
+from reme.core.schema import FileMetadata
+
+
+class FileNode(BaseModel):
+    model_config = ConfigDict(extra="allow")
+
+    path: str = Field(...)
+    st_mtime: float = Field(...)
+    edges: list[FileEdge] = Field(default_factory=list)
+
+    @property
+    def file(self):
+        ...
+
+
+
+class FileMetadata(BaseModel):
+    # FileNode -> FileMetadata
+    path: str = Field(...)
+
+    edges: list[FileEdge] = Field(default_factory=list)
+
+    title: str = Field(default="")
+    description: str = Field(default="")
+    tags: list[str] = Field(default_factory=list)
+