From 4495447b8598dce7cf484c829be1aa826f109e8e Mon Sep 17 00:00:00 2001
From: jianf <2198972886@qq.com>
Date: Sun, 19 Jul 2026 14:21:04 +0800
Subject: [PATCH] fix(document memory): dedup graph sync, filter terminal
 output from archive, add min relevance threshold

---
 internal/agent/core/agent.go    | 19 ++++++++++++++++---
 internal/agent/core/context.go  | 13 ++++++++++---
 internal/memory/vector/store.go |  2 +-
 3 files changed, 27 insertions(+), 7 deletions(-)

diff --git a/internal/agent/core/agent.go b/internal/agent/core/agent.go
index 8b72946..f133203 100644
--- a/internal/agent/core/agent.go
+++ b/internal/agent/core/agent.go
@@ -1532,11 +1532,15 @@ func (a *Agent) executeDocTool(tc agentAPI.ToolCall) string {
 				parts = append(parts, "  标签: "+strings.Join(d.Tags, ", "))
 			}
 			// 每个文档按原始时间写入 context 事件，确保时序正确
+			content := d.Content
+			if len(content) > 2000 {
+				content = content[:2000] + "..."
+			}
 			a.context.Append(ContextEvent{
 				Timestamp: d.CreatedAt,
 				Source:    "cold_storage",
 				Input:     fmt.Sprintf("加载文档记忆: %s", query),
-				Response:  d.Content,
+				Response:  content,
 			})
 			refs = append(refs, fmt.Sprintf("#%d(%s)", i+1, d.Summary))
 		}
@@ -2306,9 +2310,18 @@ func (a *Agent) syncGraphToDocs() {
 		}
 	}
 
+	summary := fmt.Sprintf("图记忆索引 (%d 实体, %d 关系)", len(result.Entities), len(result.Relations))
+	content := strings.Join(summaryParts, "\n")
+
+	// 去重：如果最近一篇 graph 文档内容相同，跳过
+	recent := a.docStore.RecentDocs(1)
+	if len(recent) > 0 && recent[0].Source == "graph" && recent[0].Content == content {
+		return
+	}
+
 	doc := &document.Doc{
-		Summary:  fmt.Sprintf("图记忆索引 (%d 实体, %d 关系)", len(result.Entities), len(result.Relations)),
-		Content:  strings.Join(summaryParts, "\n"),
+		Summary:  summary,
+		Content:  content,
 		Tags:     []string{"graph_memory", "auto_sync"},
 		Entities: extractEntityNames(result.Entities),
 		Source:   "graph",
diff --git a/internal/agent/core/context.go b/internal/agent/core/context.go
index 53ac36c..cc97728 100644
--- a/internal/agent/core/context.go
+++ b/internal/agent/core/context.go
@@ -191,8 +191,15 @@ func (c *RelevanceContext) Prune(currentInput string, topK int, docStore *docume
 
 	archived := 0
 	if docStore != nil && len(archive) > 0 {
-		entries := make([]document.ContextEntry, len(archive))
-		for i, s := range archive {
+		var filtered []scored
+		for _, s := range archive {
+			if s.event.Source == "agentcli" || s.event.Source == "terminal" {
+				continue
+			}
+			filtered = append(filtered, s)
+		}
+		entries := make([]document.ContextEntry, len(filtered))
+		for i, s := range filtered {
 			entries[i] = document.ContextEntry{
 				Timestamp: s.event.Timestamp,
 				Source:    s.event.Source,
@@ -202,7 +209,7 @@ func (c *RelevanceContext) Prune(currentInput string, topK int, docStore *docume
 		}
 		doc, err := docStore.ContextToDoc("context_archived", entries, c.embedder)
 		if err == nil && doc != nil {
-			archived = len(archive)
+			archived = len(filtered)
 		}
 	}
 
diff --git a/internal/memory/vector/store.go b/internal/memory/vector/store.go
index 3f3b422..9011dda 100644
--- a/internal/memory/vector/store.go
+++ b/internal/memory/vector/store.go
@@ -84,7 +84,7 @@ func (s *Store) Search(query Vector, topK int) []DocVector {
 		for _, d := range s.docs {
 			if d.ID == id {
 				score := CosineSimilarity(query, d.Vector)
-				if score > 0 {
+				if score > 0.05 {
 					results = append(results, scored{d, score})
 				}
 				break