refactor: pluginize text cleaning and tool NoMemory control

- SDK: ToolDef.NoMemory field, PluginSDK.RegisterTextCleaner/TextCleaners
- Registry: aggregate text cleaners from plugins, expose CleanText()
- Memory: replace hardcoded QQ regex CleanTemplateText with dynamic CleanText/SetTextCleaner
- StageHost: add ToolDef(name) lookup
- eventloop: check ToolDef.NoMemory before emitMemoryCandidate
- context/Prune: replace hardcoded agentcli/terminal source filter with ToolsUsed NoMemory check
- agentcli/cmd: mark tools with NoMemory: true
- main.go: wire memory.SetTextCleaner(pluginReg.CleanText)

internal/memory/bilingual_test.go

@@ -180,7 +180,7 @@ func TestBilingualVectorizeClean(t *testing.T) {
 		cleanVec := e.VectorizeClean(inp)
 		sim := cosineSim(rawVec, cleanVec)
 		rawTokens := len(e.tokenize(inp))
-		cleanTokens := len(e.tokenize(CleanTemplateText(inp)))
+		cleanTokens := len(e.tokenize(CleanText(inp)))
 		t.Logf("[%d] sim(raw,clean)=%.4f  tokens: raw=%d clean=%d", i, sim, rawTokens, cleanTokens)
 	}
 }
@@ -236,8 +236,8 @@ func genBilingualEvents() []bilingualEvent {
 func textForBilingual(ev bilingualEvent, modelPaths []string) string {
 	switch {
 	case ev.source == "agent" && ev.text != "":
-		return CleanTemplateText(ev.text)
+		return CleanText(ev.text)
 	default:
-		return CleanTemplateText(ev.text)
+		return CleanText(ev.text)
 	}
 }

internal/memory/clean_stress_test.go

@@ -2,10 +2,31 @@ package memory
 
 import (
 	"fmt"
+	"regexp"
 	"sort"
 	"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
+	}
+}
+
 type cleanTestEvent struct {
 	idx     int
 	source  string
@@ -173,7 +194,7 @@ func TestCleanVectorConsistency(t *testing.T) {
 	}
 
 	for _, tmpl := range templates {
-		cleaned := CleanTemplateText(tmpl)
+		cleaned := CleanText(tmpl)
 		t.Logf("template {%q} → {%q} (%d chars)", trimLen(tmpl, 60), cleaned, len(cleaned))
 	}
 
@@ -286,11 +307,11 @@ func genStressEvents(n int) []cleanTestEvent {
 func cleanEventText(source, input, response string) string {
 	switch {
 	case source == "agent" && response != "":
-		return CleanTemplateText(response)
+		return CleanText(response)
 	case source == "cold_storage":
-		return CleanTemplateText(input + " " + response)
+		return CleanText(input + " " + response)
 	default:
-		return CleanTemplateText(input)
+		return CleanText(input)
 	}
 }
 

internal/memory/clean_text.go

@@ -1,45 +1,22 @@
 package memory
 
 import (
-	"regexp"
 	"strings"
 
 	"gitcode.com/JianFeeeee/HomeAgent/internal/memory/vector"
 )
 
-var (
-	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*`,
-	)
-	reAgentPrefix = regexp.MustCompile(
-		`冷知识|注意|提示|核心要求|规则`,
-	)
-	reMultiSpace = regexp.MustCompile(`\s+`)
-)
+var globalTextCleaner func(string) string
+
+func SetTextCleaner(fn func(string) string) {
+	globalTextCleaner = fn
+}
+
+func CleanText(text string) string {
+	if globalTextCleaner != nil {
+		text = globalTextCleaner(text)
+	}
 
-func CleanTemplateText(text string) string {
-	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, " ")
 	text = strings.TrimSpace(text)
 
 	if text == "" {
@@ -53,5 +30,5 @@ func CleanTemplateText(text string) string {
 }
 
 func (e *StaticEmbedder) VectorizeClean(text string) vector.Vector {
-	return e.Vectorize(CleanTemplateText(text))
+	return e.Vectorize(CleanText(text))
 }

internal/memory/clean_text_test.go

@@ -0,0 +1,83 @@
+package memory
+
+import (
+	"testing"
+)
+
+func TestCleanTextTrim(t *testing.T) {
+	prev := globalTextCleaner
+	globalTextCleaner = nil
+	defer func() { globalTextCleaner = prev }()
+
+	tests := []struct {
+		input    string
+		expected string
+	}{
+		{"  hello  ", "hello"},
+		{"，hello", "hello"},
+		{"，，hello", "hello"},
+		{"  ，，hello  ", "hello"},
+		{"", ""},
+		{"   ", ""},
+		{"，", ""},
+		{"，x", "x"},
+	}
+	for _, tt := range tests {
+		got := CleanText(tt.input)
+		if got != tt.expected {
+			t.Errorf("CleanText(%q) = %q, want %q", tt.input, got, tt.expected)
+		}
+	}
+}
+
+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/cut.go

@@ -93,7 +93,7 @@ var stopWords = map[string]bool{
 }
 
 func ExtractKeywords(text string) []string {
-	text = CleanTemplateText(text)
+	text = CleanText(text)
 	x := GetJieba()
 	if x == nil {
 		return nil
@@ -120,7 +120,7 @@ func ExtractKeywords(text string) []string {
 
 // CutExact 精确模式分词：返回去停用词后的所有有义项（不限数量），用于 doc→graph 蒸馏
 func CutExact(text string) []string {
-	text = CleanTemplateText(text)
+	text = CleanText(text)
 	x := GetJieba()
 	if x == nil {
 		return nil

internal/memory/cut_test.go

@@ -101,7 +101,7 @@ func TestCutExactRemoveTimestamp(t *testing.T) {
 	got := CutExact("[15:04] 今天天气不错")
 	for _, g := range got {
 		if g == "15" || g == "04" || g == "15:04" {
-			t.Errorf("timestamp should be removed by CleanTemplateText, got %q in %v", g, got)
+			t.Errorf("timestamp should be removed by CleanText, got %q in %v", g, got)
 		}
 	}
 }

internal/memory/indexer.go

@@ -90,7 +90,7 @@ func (idx *Indexer) BuildContext(userInput string) *InjectedContext {
 		return &InjectedContext{Summary: ""}
 	}
 
-	input := CleanTemplateText(userInput)
+	input := CleanText(userInput)
 
 	// 1. 向量搜索：从实体名向量索引中找到相关实体
 	vectorEntities := idx.vectorSearchEntities(input)

internal/memory/real_context_test.go

@@ -16,7 +16,7 @@ type realEvent struct {
 	Response  string    `json:"response"`
 }
 
-func TestCleanTemplateText(t *testing.T) {
+func TestCleanText(t *testing.T) {
 	cases := []struct {
 		input    string
 		expected string
@@ -53,7 +53,7 @@ func TestCleanTemplateText(t *testing.T) {
 	}
 
 	for i, c := range cases {
-		got := CleanTemplateText(c.input)
+		got := 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)
 		}
@@ -91,11 +91,11 @@ func TestRealContextPerSourceVector(t *testing.T) {
 	clean := func(ev realEvent) string {
 		switch {
 		case ev.Source == "agent" && ev.Response != "":
-			return CleanTemplateText(ev.Response)
+			return CleanText(ev.Response)
 		case ev.Source == "cold_storage":
-			return CleanTemplateText(ev.Input + " " + ev.Response)
+			return CleanText(ev.Input + " " + ev.Response)
 		default:
-			return CleanTemplateText(ev.Input)
+			return CleanText(ev.Input)
 		}
 	}
 
@@ -275,11 +275,11 @@ func TestRealContextEmbedderStats(t *testing.T) {
 		var text string
 		switch {
 		case ev.Source == "agent" && ev.Response != "":
-			text = CleanTemplateText(ev.Response)
+			text = CleanText(ev.Response)
 		case ev.Source == "cold_storage":
-			text = CleanTemplateText(ev.Input + " " + ev.Response)
+			text = CleanText(ev.Input + " " + ev.Response)
 		default:
-			text = CleanTemplateText(ev.Input)
+			text = CleanText(ev.Input)
 		}
 		vec := e.Vectorize(text)
 		origLen := len(ev.Input + ev.Response)