feat: NoMemory/Cleaner memory system + doc update

- _sdk_local/ removed (moved to standalone sdk repo)
- internal/agent/core: NoMemory/Cleaner data-flow breakpoints
- internal/memory: clean_text, document store refactor
- internal/plugin/registry.go: plugin API alignment
- docs: PLUGIN_DEV.md, ARCHITECTURE.md NoMemory/Cleaner docs
- plan.md, review.md: status update

internal/memory/clean_stress_test.go

@@ -7,24 +7,24 @@ import (
 	"testing"
 )
 
-func init() {
-	globalTextCleaner = func(text string) string {
-		reQQGroupSuffix := regexp.MustCompile(`，通过id\d+使用qq_get_message工具获取消息正文。获取内容后使用 output_send\(channel="qq"\) 回复该群聊，content 设为 JSON 字符串：\{[^}]*\}`)
-		reQQPrivateSuffix := regexp.MustCompile(`，通过id\d+使用qq_get_message工具获取消息正文。获取内容后使用 output_send\(channel="qq"\) 回复对方，content 设为 JSON 字符串：\{[^}]*\}`)
-		reQQOldReply := regexp.MustCompile(`通过id\d+使用qq_get_message工具获取消息正文。获取后必须使用[^。]+。`)
-		reQQOldForbid := regexp.MustCompile(`你只能通过qq_get_message先看消息，然后直接用%!s\(MISSING\)send_private_msg回复，中间的思考过程禁止调用任何其他工具\s*→\s*`)
-		reQQGeneral := regexp.MustCompile(`通过id\d+使用qq_get_message工具获取消息正文[。，][^。]*?(?:回复|发送消息)`)
-		reTimestamp := regexp.MustCompile(`\[\d{2}:\d{2}\]\s*`)
-		reMultiSpace := regexp.MustCompile(`\s+`)
-		text = reQQGroupSuffix.ReplaceAllString(text, "")
-		text = reQQPrivateSuffix.ReplaceAllString(text, "")
-		text = reQQOldReply.ReplaceAllString(text, "")
-		text = reQQOldForbid.ReplaceAllString(text, "")
-		text = reQQGeneral.ReplaceAllString(text, "")
-		text = reTimestamp.ReplaceAllString(text, "")
-		text = reMultiSpace.ReplaceAllString(text, " ")
-		return text
-	}
+// cleanQQTemplate 模拟之前由 globalTextCleaner 执行的模板噪音清理，
+// 用于 stress test 中生成 cleanedText。
+func cleanQQTemplate(text string) string {
+	reQQGroupSuffix := regexp.MustCompile(`，通过id\d+使用qq_get_message工具获取消息正文。获取内容后使用 output_send\(channel="qq"\) 回复该群聊，content 设为 JSON 字符串：\{[^}]*\}`)
+	reQQPrivateSuffix := regexp.MustCompile(`，通过id\d+使用qq_get_message工具获取消息正文。获取内容后使用 output_send\(channel="qq"\) 回复对方，content 设为 JSON 字符串：\{[^}]*\}`)
+	reQQOldReply := regexp.MustCompile(`通过id\d+使用qq_get_message工具获取消息正文。获取后必须使用[^。]+。`)
+	reQQOldForbid := regexp.MustCompile(`你只能通过qq_get_message先看消息，然后直接用%!s\(MISSING\)send_private_msg回复对方，中间的思考过程禁止调用任何其他工具\s*→\s*`)
+	reQQGeneral := regexp.MustCompile(`通过id\d+使用qq_get_message工具获取消息正文[。，][^。]*?(?:回复|发送消息)`)
+	reTimestamp := regexp.MustCompile(`\[\d{2}:\d{2}\]\s*`)
+	reMultiSpace := regexp.MustCompile(`\s+`)
+	text = reQQGroupSuffix.ReplaceAllString(text, "")
+	text = reQQPrivateSuffix.ReplaceAllString(text, "")
+	text = reQQOldReply.ReplaceAllString(text, "")
+	text = reQQOldForbid.ReplaceAllString(text, "")
+	text = reQQGeneral.ReplaceAllString(text, "")
+	text = reTimestamp.ReplaceAllString(text, "")
+	text = reMultiSpace.ReplaceAllString(text, " ")
+	return text
 }
 
 type cleanTestEvent struct {
@@ -305,13 +305,14 @@ func genStressEvents(n int) []cleanTestEvent {
 }
 
 func cleanEventText(source, input, response string) string {
+	// 先做基础 CleanText（去空格/逗号），再做模板噪音清理
 	switch {
 	case source == "agent" && response != "":
-		return CleanText(response)
+		return cleanQQTemplate(CleanText(response))
 	case source == "cold_storage":
-		return CleanText(input + " " + response)
+		return cleanQQTemplate(CleanText(input + " " + response))
 	default:
-		return CleanText(input)
+		return cleanQQTemplate(CleanText(input))
 	}
 }
 

internal/memory/clean_text.go

@@ -6,17 +6,7 @@ import (
 	"gitcode.com/JianFeeeee/HomeAgent/internal/memory/vector"
 )
 
-var globalTextCleaner func(string) string
-
-func SetTextCleaner(fn func(string) string) {
-	globalTextCleaner = fn
-}
-
 func CleanText(text string) string {
-	if globalTextCleaner != nil {
-		text = globalTextCleaner(text)
-	}
-
 	text = strings.TrimSpace(text)
 
 	if text == "" {

internal/memory/clean_text_test.go

@@ -5,10 +5,6 @@ import (
 )
 
 func TestCleanTextTrim(t *testing.T) {
-	prev := globalTextCleaner
-	globalTextCleaner = nil
-	defer func() { globalTextCleaner = prev }()
-
 	tests := []struct {
 		input    string
 		expected string
@@ -29,55 +25,3 @@ func TestCleanTextTrim(t *testing.T) {
 		}
 	}
 }
-
-func TestCleanTextWithRegisteredCleaner(t *testing.T) {
-	prev := globalTextCleaner
-	globalTextCleaner = func(text string) string {
-		return "prefix_" + text
-	}
-	defer func() { globalTextCleaner = prev }()
-
-	got := CleanText("  hello  ")
-	if got != "prefix_  hello" {
-		t.Errorf("CleanText with cleaner = %q, want %q", got, "prefix_  hello")
-	}
-}
-
-func TestCleanTextCleanerChain(t *testing.T) {
-	prev := globalTextCleaner
-	globalTextCleaner = func(text string) string {
-		text = text + "_step1"
-		text = text + "_step2"
-		return text
-	}
-	defer func() { globalTextCleaner = prev }()
-
-	got := CleanText("test")
-	if got != "test_step1_step2" {
-		t.Errorf("CleanText chain = %q, want %q", got, "test_step1_step2")
-	}
-}
-
-func TestSetTextCleanerReplace(t *testing.T) {
-	prev := globalTextCleaner
-	globalTextCleaner = func(text string) string { return "old_" + text }
-
-	SetTextCleaner(func(text string) string { return "new_" + text })
-	defer func() { globalTextCleaner = prev }()
-
-	got := CleanText("x")
-	if got != "new_x" {
-		t.Errorf("after SetTextCleaner = %q, want %q", got, "new_x")
-	}
-}
-
-func TestCleanTextEmptyAfterCleaner(t *testing.T) {
-	prev := globalTextCleaner
-	globalTextCleaner = func(text string) string { return "" }
-	defer func() { globalTextCleaner = prev }()
-
-	got := CleanText("something")
-	if got != "" {
-		t.Errorf("expected empty, got %q", got)
-	}
-}

internal/memory/document/document.go

@@ -124,25 +124,34 @@ func (s *Store) Insert(doc *Doc) error {
 }
 
 // ContextToDoc — 将一段上下文对话历史提炼为文档（带内容去重）
-func (s *Store) ContextToDoc(source string, entries []ContextEntry, vec vector.Vectorizer) (*Doc, error) {
+// cleanFn 可选，用于在计算层（摘要/标签/实体提取）前过滤文本，不影响原文存储。
+func (s *Store) ContextToDoc(source string, entries []ContextEntry, vec vector.Vectorizer, cleanFn ...func(string) string) (*Doc, error) {
 	if len(entries) == 0 {
 		return nil, nil
 	}
 
+	cleanText := func(text string) string { return text }
+	if len(cleanFn) > 0 && cleanFn[0] != nil {
+		cleanText = cleanFn[0]
+	}
+
 	var parts []string
 	for _, e := range entries {
 		line := fmt.Sprintf("[%s] %s: %s", e.Timestamp.Format("15:04"), e.Source, e.Content)
 		if e.Response != "" {
 			line += fmt.Sprintf(" → %s", truncate(e.Response, 100))
 		}
+		for _, tr := range e.ToolResults {
+			line += fmt.Sprintf("\n  [工具] %s: %s", tr.Name, truncate(tr.Output, 200))
+		}
 		parts = append(parts, line)
 	}
 	content := strings.Join(parts, "\n")
 	contentHash := simpleHash(content)
 
-	summary := summarizeEntries(entries)
-	tags := extractTags(entries)
-	entities := extractEntities(entries)
+	summary := summarizeEntries(entries, cleanText)
+	tags := extractTags(entries, cleanText)
+	entities := extractEntities(entries, cleanText)
 
 	s.mu.Lock()
 
@@ -417,23 +426,38 @@ func (s *Store) flush() {
 	s.dirty = false
 }
 
-type ContextEntry struct {
-	Timestamp time.Time
-	Source    string
-	Content   string
-	Response  string
+type ToolResultItem struct {
+	Name   string
+	Output string
 }
 
-func summarizeEntries(entries []ContextEntry) string {
+type ContextEntry struct {
+	Timestamp   time.Time
+	Source      string
+	Content     string
+	Response    string
+	ToolResults []ToolResultItem
+}
+
+func summarizeEntries(entries []ContextEntry, cleanText ...func(string) string) string {
 	if len(entries) == 0 {
 		return ""
 	}
+	clean := func(text string) string { return text }
+	if len(cleanText) > 0 && cleanText[0] != nil {
+		clean = cleanText[0]
+	}
 	sources := make(map[string]int)
 	var topics []string
 	for _, e := range entries {
 		sources[e.Source]++
-		words := memory.ExtractKeywords(e.Content)
+		words := memory.ExtractKeywords(clean(e.Content))
 		topics = append(topics, words...)
+		for _, tr := range e.ToolResults {
+			cleaned := clean(tr.Output)
+			toolWords := memory.ExtractKeywords(cleaned)
+			topics = append(topics, toolWords...)
+		}
 	}
 
 	summary := fmt.Sprintf("来自 %d 个来源的 %d 条对话", len(sources), len(entries))
@@ -461,12 +485,21 @@ func summarizeEntries(entries []ContextEntry) string {
 	return summary
 }
 
-func extractTags(entries []ContextEntry) []string {
+func extractTags(entries []ContextEntry, cleanText ...func(string) string) []string {
+	clean := func(text string) string { return text }
+	if len(cleanText) > 0 && cleanText[0] != nil {
+		clean = cleanText[0]
+	}
 	tagSet := make(map[string]bool)
 	for _, e := range entries {
-		for _, kw := range memory.ExtractKeywords(e.Content) {
+		for _, kw := range memory.ExtractKeywords(clean(e.Content)) {
 			tagSet[kw] = true
 		}
+		for _, tr := range e.ToolResults {
+			for _, kw := range memory.ExtractKeywords(clean(tr.Output)) {
+				tagSet[kw] = true
+			}
+		}
 	}
 	var tags []string
 	for t := range tagSet {
@@ -478,17 +511,29 @@ func extractTags(entries []ContextEntry) []string {
 	return tags
 }
 
-func extractEntities(entries []ContextEntry) []string {
+func extractEntities(entries []ContextEntry, cleanText ...func(string) string) []string {
 	// 简易实体提取：提取引号内的内容、粗体/标记词
+	clean := func(text string) string { return text }
+	if len(cleanText) > 0 && cleanText[0] != nil {
+		clean = cleanText[0]
+	}
 	var entities []string
 	seen := make(map[string]bool)
 	for _, e := range entries {
-		for _, kw := range memory.ExtractKeywords(e.Content) {
+		for _, kw := range memory.ExtractKeywords(clean(e.Content)) {
 			if len(kw) >= 2 && !seen[kw] {
 				seen[kw] = true
 				entities = append(entities, kw)
 			}
 		}
+		for _, tr := range e.ToolResults {
+			for _, kw := range memory.ExtractKeywords(clean(tr.Output)) {
+				if len(kw) >= 2 && !seen[kw] {
+					seen[kw] = true
+					entities = append(entities, kw)
+				}
+			}
+		}
 	}
 	if len(entities) > 20 {
 		entities = entities[:20]

internal/memory/real_context_test.go

@@ -53,7 +53,7 @@ func TestCleanText(t *testing.T) {
 	}
 
 	for i, c := range cases {
-		got := CleanText(c.input)
+		got := cleanQQTemplate(CleanText(c.input))
 		if c.expected != "" && got != c.expected {
 			t.Errorf("case %d:\n  input:    %q\n  expected: %q\n  got:      %q", i, trimLen(c.input, 60), c.expected, got)
 		}