docs: update sequence diagram, memory flow, vectorization strategy for StaticEmbedder + CleanTemplateText + three-branch vector

README.md

@@ -17,7 +17,7 @@ homed（内核零 IO） ← PluginSDK → 插件（所有 IO 能力）
 **核心域与应用域分离** — 内核只做 LLM 编排、记忆管理、知识检索；所有 IO 能力（收发消息、读写文件、网络请求、硬件交互）全由插件实现。插件可热加载、独立开发、独立发布。这不是 RPC 框架的微服务拆分，而是 Agent 框架层次的领域划分。
 
 **三层记忆架构** — 解决 Agent 长期运行的记忆衰减问题：
-- **Context 层**：TF-IDF 相关性评分的事件窗口，维护最近 topK 条上下文
+- **Context 层**：预训练词嵌入 / TF-IDF 回退的相关性评分事件窗口，保护最近 10 条，维护 topK 条上下文
 - **Document 层**：临时记忆，冷数据自动下沉，也支持用户主动提交
 - **Graph 层**：SQLite 图数据库，持久化实体关系和语义记忆，支持蒸馏管道从原始对话中提取三元组
 
@@ -40,14 +40,14 @@ sequenceDiagram
     rect lavender
         Note over EV: processTextInput
         EV->>ST: StageOnInput  插件可改写/短路
-        EV->>CTX: Prune(input,topK)  TF-IDF裁剪
+        EV->>CTX: Prune(input,topK)  StaticEmbedder/TF-IDF余弦相似度裁剪
-        CTX->>MEM: 低分事件归档 Document
+        CTX->>MEM: 低分事件归档 Document (原始时间戳)
-        EV->>CTX: Append(input)  5s写盘
+        EV->>CTX: Append(input)  CleanTemplateText→三分支向量→5s写盘
     end
     rect lightgreen
         Note over EV,LLM: process()
-        EV->>MEM: buildMemoryContext  Indexer召回Graph
+        EV->>MEM: buildMemoryContext  Indexer召回Graph(向量+jieba→BFS depth=2)
-        EV->>MEM: buildSystemPrompt  人格+记忆+技能注入
+        EV->>MEM: buildSystemPrompt  DocQuery摘要+Graph记忆索引+人格+技能
         EV->>ST: StagePreAction  插件可预拦截
         loop 工具循环
             LLM->>LLM: drainInterrupts
@@ -99,21 +99,21 @@ flowchart LR
 flowchart TB
     subgraph C[① Context 工作窗口]
         RC[RelevanceContext]
-        A[Append] -->|Vectorize char 1-2gram| RC
+        A[Append] -->|CleanTemplateText→三分支向量| RC
-        P[Prune TF-IDF Cosine] -->|低分| D
+        P[Prune StaticEmbedder/TF-IDF Cosine] -->|低分原始时间戳| D
-        P -->|保留| TL[timeline→system prompt]
+        P -->|保留| TL[timeline→按时间排序→system prompt]
     end
     subgraph D[② Document 文件记忆]
         DS[DocStore JSON+TF-IDF]
-        Q1[Query 自动注入] -->|【相关记忆文档】| SP
+        Q1[Query 摘要自动注入] -->|【相关记忆文档】| SP
-        Q2[doc_query LLM主动] -->|Consume+删除| DS
+        Q2[doc_query LLM主动召回] -->|Consume+删除源| DS
-        Q2 -->|原始时间戳写入| RC
+        Q2 -->|原始时间戳写入上下文| RC
         CD[FindColdDocs 72h] -->|docToTriples| G
     end
     subgraph G[③ Graph 图数据库]
         DB[(SQLite)]
-        IDX[Indexer BFS depth=2] -->|【记忆索引】| SP
+        IDX[Indexer 向量+jieba→BFS depth=2] -->|【记忆索引】| SP
-        MEM[memory_recall/commit]
+        MEM[memory_recall/commit/merge/purge/edit]
         SOC[person_query/set_trait]
     end
     subgraph H[④ 心跳蒸馏]
@@ -160,7 +160,7 @@ cmd/waiter/         CLI 客户端（Unix socket）
 internal/
 ├── agent/core/     Agent 核心：事件循环、LLM 工具循环、7 阶段管道
 ├── agent/api/      LLM Provider + 8 个 Lua 适配器
-├── memory/         三层记忆：Graph(SQLite) / Document(JSON+TF-IDF) / Text(JSONL)
+├── memory/         三层记忆：Graph(SQLite) / Document(JSON+TF-IDF) / Text(JSONL) + StaticEmbedder(预训练词嵌入/TF-IDF回退) + CleanTemplateText(去模版)
 ├── knowledge/      知识库（文件系统 + TF-IDF）
 ├── plugin/         插件注册表 + .so 动态加载器
 ├── plugins/        内置 10 个插件（webui/cli/timer/cmd/mcp/openclaw/agentcli/healthcheck/pluginmgr/files）

README_EN.md

@@ -17,7 +17,7 @@ homed (kernel, zero IO) ← PluginSDK → plugins (all IO capabilities)
 **Separation of Core Domain and Application Domain** — The kernel only handles LLM orchestration, memory management, and knowledge retrieval; all IO capabilities (sending/receiving messages, reading/writing files, network requests, hardware interaction) are implemented by plugins. Plugins can be hot-loaded, independently developed, and independently released. This is not a microservice split of an RPC framework, but a domain-level separation in Agent framework design.
 
 **Three-Layer Memory Architecture** — Solves the memory decay problem for long-running agents:
-- **Context Layer**: TF-IDF relevance-scored event window, maintains recent topK context entries
+- **Context Layer**: Pretrained word embedding / TF-IDF fallback relevance-scored event window, protects last 10 entries, maintains topK context entries
 - **Document Layer**: Temporary memory with automatic cold data sinking, also supports user-initiated submissions
 - **Graph Layer**: SQLite graph database, persists entity relationships and semantic memory, supports distillation pipelines to extract triples from conversations
 
@@ -40,14 +40,14 @@ sequenceDiagram
     rect lavender
         Note over EV: processTextInput
         EV->>ST: StageOnInput  Plugin can rewrite/short-circuit
-        EV->>CTX: Prune(input,topK)  TF-IDF pruning
+        EV->>CTX: Prune(input,topK)  StaticEmbedder/TF-IDF cosine pruning
-        CTX->>MEM: Low-score events archived to Document
+        CTX->>MEM: Low-score events archived to Document (original timestamp)
-        EV->>CTX: Append(input)  5s debounce write
+        EV->>CTX: Append(input)  CleanTemplateText→three-branch vector→5s write
     end
     rect lightgreen
         Note over EV,LLM: process()
-        EV->>MEM: buildMemoryContext  Indexer recalls from Graph
+        EV->>MEM: buildMemoryContext  Indexer recalls from Graph (vector+jieba→BFS depth=2)
-        EV->>MEM: buildSystemPrompt  Persona+Memory+Skills injection
+        EV->>MEM: buildSystemPrompt  DocQuery summary+Graph memory index+Persona+Skills
         EV->>ST: StagePreAction  Plugin can pre-intercept
         loop Tool loop
             LLM->>LLM: drainInterrupts
@@ -99,21 +99,21 @@ flowchart LR
 flowchart TB
     subgraph C[① Context Working Window]
         RC[RelevanceContext]
-        A[Append] -->|Vectorize char 1-2gram| RC
+        A[Append] -->|CleanTemplateText→three-branch vector| RC
-        P[Prune TF-IDF Cosine] -->|Low score| D
+        P[Prune StaticEmbedder/TF-IDF Cosine] -->|Low score original timestamp| D
-        P -->|Keep| TL[timeline→system prompt]
+        P -->|Keep| TL[timeline→chronological→system prompt]
     end
     subgraph D[② Document File Memory]
         DS[DocStore JSON+TF-IDF]
-        Q1[Query auto-inject] -->|[Related Memory Docs]| SP
+        Q1[Query summary auto-inject] -->|[Related Memory Docs]| SP
-        Q2[doc_query LLM active] -->|Consume+delete| DS
+        Q2[doc_query LLM active recall] -->|Consume+delete source| DS
-        Q2 -->|Original timestamp write| RC
+        Q2 -->|Original timestamp write to context| RC
         CD[FindColdDocs 72h] -->|docToTriples| G
     end
     subgraph G[③ Graph Database]
         DB[(SQLite)]
-        IDX[Indexer BFS depth=2] -->|[Memory Index]| SP
+        IDX[Indexer vector+jieba→BFS depth=2] -->|[Memory Index]| SP
-        MEM[memory_recall/commit]
+        MEM[memory_recall/commit/merge/purge/edit]
         SOC[person_query/set_trait]
     end
     subgraph H[④ Heartbeat Distillation]
@@ -160,7 +160,7 @@ cmd/waiter/         CLI client (Unix socket)
 internal/
 ├── agent/core/     Agent core: event loop, LLM tool loop, 7-stage pipeline
 ├── agent/api/      LLM Provider + 8 Lua adapters
-├── memory/         Three-layer memory: Graph(SQLite) / Document(JSON+TF-IDF) / Text(JSONL)
+├── memory/         Three-layer memory: Graph(SQLite) / Document(JSON+TF-IDF) / Text(JSONL) + StaticEmbedder(pretrained word embedding/TF-IDF fallback) + CleanTemplateText(de-template)
 ├── knowledge/      Knowledge base (filesystem + TF-IDF)
 ├── plugin/         Plugin registry + .so/.dll dynamic loader
 ├── plugins/        10 built-in plugins (webui/cli/timer/cmd/mcp/openclaw/agentcli/healthcheck/pluginmgr/files)

docs/en/ARCHITECTURE.md

@@ -75,42 +75,44 @@ Setting `ctx.Response` at any stage jumps to `after_output`.
 ```
 ① Context (Working Window)
    RelevanceContext — In-memory events[] + JSON persistence
-   Append: Each input, Vectorize(char 1-2gram TF-IDF)
+   Append: Each input, CleanTemplateText → three-branch vector(textForVector)
-   Prune:  TF-IDF CosineSimilarity, keep topK + last 10
+           agent→Response, user→Input, cold_storage→Input+Response
-       ├── Keep → timeline → system prompt (sorted by time)
+           StaticEmbedder pretrained word embedding / TF-IDF fallback
-       └── Low score → Document layer archive (ContextToDoc)
+   Prune:  StaticEmbedder CosineSimilarity, keep topK + last 10
+       ├── Keep → timeline → chronologically sorted → system prompt
+       └── Low score → Document layer archive (original timestamp)
    Save: 5s debounce write to disk
 
-        ↓ Prune archive                       ↑ LLM active recall
+         ↓ Prune archive                       ↑ LLM active recall
 
 ② Document (File Memory)
    DocStore — JSON files + TF-IDF InvertedIndex
    Write: Prune archive / doc_commit / Graph snapshot (syncGraphToDocs)
    Read:
-       ├── Auto-inject: Query(input, top3) → [Related Memory Docs] → system prompt (read-only, update AccessCount)
+       ├── Auto-inject: Query(input, top3) → similarity summary → [Related Memory Docs] → system prompt (read-only)
        └── LLM active:  doc_query → Consume(read and delete)
                          → context.Append{Timestamp: d.CreatedAt, Source: "cold_storage"} per doc
                          → Docs written to context timeline with original timestamps, deleted from docStore
    Cold: FindColdDocs(72h, ≤2 accesses) → docToTriples → Graph
 
-        ↓ Cold doc distillation               ↑ Auto recall
+         ↓ Cold doc distillation               ↑ Auto recall
 
 ③ Graph (Graph Database)
    SQLite — entities + relations tables
-   Write: memory_commit / cold doc distillation / Pipeline rule distillation
+   Write: memory_commit / cold doc distillation / Pipeline rule distillation / memory_merge
    Read:
        ├── Auto recall: Indexer.BuildContext(input)
-       │     → TF-IDF entity name search → BFS depth=2
+       │     → CleanTemplateText → vector entity search + jieba keywords → SQLite LIKE + BFS depth=2
        │     → [Memory Index] → system prompt
-       └── LLM active: memory_recall / doc_query
+       └── LLM active: memory_recall / memory_merge / memory_purge / memory_edit / memory_delete_entity
    Social: person_query / set_trait / relate (wraps GraphDB)
 
 ④ Distillation Pipeline (30min heartbeat)
    distillContext → window > 2×maxSize → force Prune
    syncGraphToDocs → Graph snapshot to Document (cross-layer searchable)
    reorgGraph:
-       Step1: indexer.Sync — rebuild entity TF-IDF vector index
+       Step1: indexer.Sync — rebuild entity vector index
-       Step2: docStore.Reindex — rebuild document TF-IDF vector index
+       Step2: docStore.Reindex — rebuild document vector index
        Step3: Cold docs → docToTriples → GraphDB.Commit
        Step4: Entity similarity (Bigram Jaccard > 0.75) → consolidation → LLM decides merge
        Step5: evaluateGraphQuality → LLM decides keep/delete
@@ -121,36 +123,35 @@ Setting `ctx.Response` at any stage jumps to `after_output`.
      → triples → GraphDB.Commit
 ```
 
-### Vectorization: Two Strategies
+### Vectorization: Pretrained Word Embedding + TF-IDF Fallback
 
-Vectorization is used in 4 independent locations with different strategies:
+All vectorization unified under `StaticEmbedder` (`internal/memory/static_embedder.go`):
 
-**Strategy A — Local Word Embedding** (`LocalWordEmbedder`, `internal/memory/embedder.go`), used by Context layer:
+**Primary Strategy — Pretrained Word Embedding (aligned 300d)**
-
+- Model sources: ConceptNet Numberbatch (77-language aligned) / fastText Chinese / fastText English
-- **jieba tokenization** → removes stop words and single characters
+- Configured via `core.agent.embedding_model_path` (comma-separated multi-model)
-- **TF-IDF** as base word weight
+- Path containing `numberbatch` → auto-download ConceptNet; `cc.zh.` → fastText Chinese; `cc.en.` → fastText English
-- **Sliding window (size=5)** counts word co-occurrence → **PMI (Pointwise Mutual Information)** → keeps top 50
+- Falls back to ConceptNet by default if no match
-- **Vectorization**: `vec[ctx] += TF-IDF × PMI` + self-tag `__w__` + TF-IDF
+- **Pre-processing**: `CleanTemplateText` strips QQ tool-call templates and timestamp noise
-
+- **Three-branch vector source**: agent→Response, user→Input, cold_storage→Input+Response
-**Strategy B — char-bigram TF-IDF + jieba keyword extraction** (`TFIDFVectorizer` + `ExtractKeywords`), used by Document and Indexer layers:
+- **TF-IDF fallback**: auto-fallback to bag-of-words TF-IDF if model download fails or not configured
-
-- **char bigram tokenization** (1-2 gram) for entity name vector search
-- **jieba tokenization** for keyword extraction, paired with SQLite LIKE + BFS traversal
-- **TF-IDF weights** + **inverted index**
 
 | Location | File | Purpose | Algorithm |
 |----------|------|---------|-----------|
-| Context Prune | `context.go:161` | Trim low-relevance context events | LocalWordEmbedder → CosineSimilarity(queryVec, evt.Vector) |
+| Context Prune | `context.go:155` | Trim low-relevance context events | VectorizeClean → CosineSimilarity(queryVec, evt.Vector) |
-| DocStore Query | `document.go:198` | Recall related content from document memory | char-bigram TF-IDF + jieba keywords → InvertedIndex + CosineSimilarity |
+| DocStore Query | `document.go:206` | Recall from document memory | TF-IDF Vectorize → vec.Search |
-| Indexer Entity Search | `indexer.go:149` | Recall related entities from Graph | char-bigram TF-IDF vector search + jieba keywords → InvertedIndex + CosineSimilarity + SQLite BFS |
+| Indexer Entity Search | `indexer.go:96+111` | Recall from Graph | vector entity search + jieba keywords → SQLite LIKE + BFS |
-| Entity Similarity Detection | `agent.go:2297` | Detect similar entities in Graph | Bigram Jaccard (>0.75 → consolidation) |
+| Entity Similarity Detection | `agent.go` | Detect similar entities in Graph | Bigram Jaccard (>0.75 → consolidation) |
 
 ### Context Layer
 
 `internal/agent/core/context.go` — `RelevanceContext`
 - Maintains recent event list, writes JSON on each Append/Prune to prevent data loss
-- Word embedding relevance scoring on user input (LocalWordEmbedder → CosineSimilarity), keeps topK
+- Pre-vectorization pipeline runs through `CleanTemplateText` to remove template noise
+- Three-branch `textForVector`: agent events → Response, user events → Input, cold_storage → Input+Response
+- Pretrained word embedding `StaticEmbedder` → CosineSimilarity, auto-fallback to TF-IDF if unavailable
 - Protects last 10 events from eviction; excess candidates are sorted by relevance and archived to document memory
+- Archived events retain original timestamps; on `doc_query` recall they re-insert into the context timeline at their original position
 
 ### Document Layer
 
@@ -171,6 +172,10 @@ Vectorization is used in 4 independent locations with different strategies:
 |------|---------|
 | `memory_recall` | Recall from Graph |
 | `memory_commit` | Write triples to Graph |
+| `memory_merge` | Merge two entity nodes |
+| `memory_purge` | Delete entity node |
+| `memory_edit` | Edit existing entity/relation |
+| `memory_delete_entity` | Delete entity and all its relations |
 | `memory_introspect` | View memory statistics |
 | `doc_query` | Search from Document |
 | `doc_commit` | Write to Document |

docs/en/OVERVIEW.md

@@ -37,7 +37,7 @@ Code is in the project root, implemented in Go.
 - Maintains a message loop (`eventLoop`), queuing input from the IO layer
 - Each input goes through the full processing pipeline: memory recall → persona injection → LLM call → tool execution → output delivery
 - LLM calls abstracted through Provider interface, supports 8 LLM sources with automatic fallback
-- Context management (`context.go`) based on word embedding scoring (LocalWordEmbedder → CosineSimilarity), automatic pruning of low-relevance events
+- Context management (`context.go`) based on pretrained word embedding scoring (StaticEmbedder → CosineSimilarity, TF-IDF fallback), automatic pruning of low-relevance events
 
 **Memory System** (`internal/memory/`):
 - **GraphDB** (`graph.go`) — SQLite, entities + relations tables, BFS traversal

docs/zh/ARCHITECTURE.md

@@ -75,42 +75,44 @@ eventLoop() → processTextInput()
 ```
 ① Context (工作窗口)
    RelevanceContext — 内存 events[] + JSON持久化
-   Append: 每次输入, Vectorize(char 1-2gram TF-IDF)
+   Append: 每次输入, CleanTemplateText → 三分支向量(textForVector)
-   Prune:  TF-IDF CosineSimilarity, 保留 topK + 最近10条
+            agent事件→Response, 用户事件→Input, cold_storage→Input+Response
-       ├── 保留 → timeline → system prompt (按时间排序)
+            StaticEmbedder 预训练词嵌入 / TF-IDF 回退
-       └── 低分 → Document 层归档 (ContextToDoc)
+   Prune:  StaticEmbedder CosineSimilarity, 保留 topK + 最近10条
+       ├── 保留 → timeline → 按时间排序 → system prompt
+       └── 低分 → Document 层归档 (原始时间戳)
    Save: 5s debounce 写盘
 
-        ↓ Prune 归档                          ↑ LLM 主动召回
+         ↓ Prune 归档                          ↑ LLM 主动召回
 
 ② Document (文件记忆)
    DocStore — JSON文件 + TF-IDF InvertedIndex
    写入: Prune归档 / doc_commit / Graph快照(syncGraphToDocs)
    读取:
-       ├── 自动注入: Query(input, top3) → 【相关记忆文档】→ system prompt (只读, 更新 AccessCount)
+       ├── 自动注入: Query(input, top3) → 相似度摘要 → 【相关记忆文档】→ system prompt (只读)
        └── LLM主动:  doc_query → Consume(读取并删除)
                          → 逐条 context.Append{Timestamp: d.CreatedAt, Source: "cold_storage"}
                          → 文档以原始时间戳写入 context 时间线, 从 docStore 删除
    冷化: FindColdDocs(72h, ≤2次访问) → docToTriples → Graph
 
-        ↓ 冷文档蒸馏                           ↑ 自动召回
+         ↓ 冷文档蒸馏                           ↑ 自动召回
 
 ③ Graph (图数据库)
    SQLite — entities + relations 表
-   写入: memory_commit / 冷文档蒸馏 / Pipeline 规则蒸馏
+   写入: memory_commit / 冷文档蒸馏 / Pipeline 规则蒸馏 / memory_merge
    读取:
        ├── 自动召回: Indexer.BuildContext(input)
-       │     → TF-IDF 实体名搜索 → BFS depth=2
+       │     → CleanTemplateText → 向量实体搜索 + jieba关键词 → SQLite LIKE + BFS depth=2
        │     → 【记忆索引】→ system prompt
-       └── LLM主动: memory_recall / doc_query
+       └── LLM主动: memory_recall / memory_merge / memory_purge / memory_edit / memory_delete_entity
    Social: person_query / set_trait / relate (包装 GraphDB)
 
 ④ 蒸馏管道 (每30min心跳)
    distillContext → 窗口>2×maxSize → 强制Prune
    syncGraphToDocs → Graph 快照写入 Document(跨层可搜索)
    reorgGraph:
-       Step1: indexer.Sync — 重建实体TF-IDF向量索引
+       Step1: indexer.Sync — 重建实体向量索引
-       Step2: docStore.Reindex — 重建文档TF-IDF向量索引
+       Step2: docStore.Reindex — 重建文档向量索引
        Step3: 冷文档 → docToTriples → GraphDB.Commit
        Step4: 实体相似度(Bigram Jaccard>0.75) → consolidation → LLM判断合并
        Step5: evaluateGraphQuality → LLM判断保留/删除
@@ -121,36 +123,35 @@ eventLoop() → processTextInput()
      → 三元组 → GraphDB.Commit
 ```
 
-### 向量化算法：两种策略
+### 向量化：预训练词嵌入 + TF-IDF 回退
 
-向量化在 4 个独立位置以不同方式使用：
+所有向量化统一使用 `StaticEmbedder`（`internal/memory/static_embedder.go`）：
 
-**策略 A — 局部词嵌入**（`LocalWordEmbedder`, `internal/memory/embedder.go`），用于 Context 层：
+**主策略 — 预训练词嵌入（词对齐 300 维）**
-
+- 模型来源：ConceptNet Numberbatch（77 语对齐）/ fastText 中文 / fastText 英文
-- **jieba 分词** → 去除停用词和单字
+- 通过 `core.agent.embedding_model_path` 配置（逗号分隔多模型）
-- **TF-IDF** 作为基础词权重
+- 路径名含 `numberbatch` → 自动下载 ConceptNet，含 `cc.zh.` → fastText 中文，含 `cc.en.` → fastText 英文
-- **滑动窗口（size=5）** 统计词对共现 → **PMI（点互信息）** → 保留 top 50
+- 不匹配则默认 ConceptNet
-- **向量化**：`vec[ctx] += TF-IDF × PMI` + 自身上标 `__w__` + TF-IDF
+- **前处理**：`CleanTemplateText` 剥离 QQ 工具调用模版、时间戳噪声，避免垃圾干扰相似度
-
+- **三分支向量来源**：agent→Response，用户→Input，cold_storage→Input+Response
-**策略 B — char-bigram TF-IDF + jieba 关键词提取**（`TFIDFVectorizer` + `ExtractKeywords`），用于 Document 和 Indexer 层：
+- **TF-IDF 回退**：模型下载失败或未配置时自动回退词袋 TF-IDF，服务不中断
-
-- **char bigram 分词**（1-2 gram）用于实体名向量搜索
-- **jieba 分词**用于关键词提取，配合 SQLite LIKE + BFS 遍历
-- **TF-IDF 权重** + **倒排索引**
 
 | 位置 | 文件 | 用途 | 算法 |
 |------|------|------|------|
-| Context Prune | `context.go:161` | 裁剪低相关性上下文事件 | LocalWordEmbedder → CosineSimilarity(queryVec, evt.Vector) |
+| Context Prune | `context.go:155` | 裁剪低相关性上下文事件 | VectorizeClean → CosineSimilarity(queryVec, evt.Vector) |
-| DocStore Query | `document.go:198` | 从文档记忆召回相关内容 | char-bigram TF-IDF + jieba 关键词 → InvertedIndex + CosineSimilarity |
+| DocStore Query | `document.go:206` | 文档记忆召回 | TF-IDF Vectorize → vec.Search |
-| Indexer 实体搜索 | `indexer.go:149` | 从Graph召回相关实体 | char-bigram TF-IDF 向量搜索 + jieba 关键词 → InvertedIndex + CosineSimilarity + SQLite BFS |
+| Indexer 实体搜索 | `indexer.go:96+111` | Graph实体召回 | 向量实体搜索 + jieba关键词 → SQLite LIKE + BFS |
-| 实体相似度检测 | `agent.go:2297` | 检测Graph中相似实体 | Bigram Jaccard (>0.75 → consolidation) |
+| 实体相似度检测 | `agent.go` | Graph中相似实体 | Bigram Jaccard (>0.75 → consolidation) |
 
 ### Context 层
 
 `internal/agent/core/context.go` — `RelevanceContext`
 - 维护最近事件列表，每次 Append/Prune 写入 JSON 防丢
-- 用户输入时做词嵌入相关性评分（LocalWordEmbedder → CosineSimilarity），保留 topK
+- 向量化前统一经 `CleanTemplateText` 去模版噪声
+- 三分支 `textForVector`：agent 事件用 Response、用户事件用 Input、cold_storage 用 Input+Response
+- 预训练词嵌入 `StaticEmbedder` → CosineSimilarity，模型不可用时自动回退 TF-IDF
 - 保护最近 10 条记录免于淘汰，超出部分按相关性排序归档到文档记忆
+- 归档事件以原始时间戳写入文档记忆，后续 `doc_query` 召回时按原始时间戳插回时序
 
 ### Document 层
 
@@ -171,6 +172,10 @@ eventLoop() → processTextInput()
 |------|------|
 | `memory_recall` | 从 Graph 召回 |
 | `memory_commit` | 写入 Graph 三元组 |
+| `memory_merge` | 合并两个实体节点 |
+| `memory_purge` | 删除指定实体 |
+| `memory_edit` | 编辑已有实体/关系 |
+| `memory_delete_entity` | 删除实体及其所有关系 |
 | `memory_introspect` | 查看记忆统计 |
 | `doc_query` | 从 Document 搜索 |
 | `doc_commit` | 写入 Document |

docs/zh/OVERVIEW.md

@@ -37,7 +37,7 @@ HomeAgent 是一个持续运行的个人智能 Agent 框架。
 - 维护一个消息循环（`eventLoop`），从 IO 层排队接收输入
 - 每次输入走完整的处理管道：记忆召回 → 人格注入 → LLM 调用 → 工具执行 → 输出发送
 - LLM 调用通过 Provider 接口抽象，支持 8 个 LLM 源自动降级
-- 上下文管理（`context.go`）基于词嵌入评分（LocalWordEmbedder → CosineSimilarity），自动剪枝低相关性事件
+- 上下文管理（`context.go`）基于预训练词嵌入评分（StaticEmbedder → CosineSimilarity，TF-IDF回退），自动剪枝低相关性事件
 
 **记忆系统** (`internal/memory/`)：
 - **GraphDB** (`graph.go`) — SQLite，entities + relations 表，BFS 遍历