fix(channelbridge): IM 发送过滤 action/narration + <p>拆多气泡 + 0.5-2s 间隔

把回复转发给 IM 适配器(sendReply)时剥掉 <action>/<narration> 动作/内心独白(Web 端才渲染灰斜体，IM 只能收纯文本)，并按 <p> 段落拆成多条气泡分别发送；多气泡发送间隔随机 0.5~2s(仅 IM，Web 前端不延迟)。新增 sanitize.go stripNarration/splitBubbles/ bubbleGap + 测试。
2026-09-07 17:50:56 +08:00
1 parent dcb0b33954
commit 5a0c1e2fd1
@@ -597,19 +597,38 @@ func (b *Bridge) sendReply(ctx context.Context, in adapter.UnifiedMessage, a ada
 	if a == nil {
 		return fmt.Errorf("channelbridge: no adapter for platform %q", in.Platform)
 	}
-	out := adapter.UnifiedMessage{
-		Platform:    in.Platform,
-		ChannelType: in.ChannelType,
-		ChannelID:   in.ChannelID,
-		GroupID:     in.GroupID,
-		GroupName:   in.GroupName,
-		SenderID:    in.SenderID,
-		Sender:      in.Sender,
-		Content:     text,
-		ContentType: adapter.ContentText,
-		Timestamp:   time.Now().UTC(),
+	// IM channels receive the reply as one or more bubbles: role-play/action/narration
+	// markup (rendered as muted italic on the Web) is stripped, and each <p> paragraph
+	// becomes its own bubble/message (design/17 §2). A reply that was only an action is
+	// dropped rather than sent empty. A multi-bubble reply spaces its sends 0.5-2s apart
+	// so a burst doesn't flood the channel; the Web frontend has no such delay.
+	bubbles := splitBubbles(text)
+	if len(bubbles) == 0 {
+		b.log.Debug("reply has no plain text, skipped", "platform", in.Platform, "channel", in.ChannelID)
+		return nil
 	}
-	return a.SendMessage(ctx, adapter.UnifiedResponse{Messages: []adapter.UnifiedMessage{out}})
+	for i, content := range bubbles {
+		if i > 0 {
+			time.Sleep(bubbleGap())
+		}
+		out := adapter.UnifiedMessage{
+			Platform:    in.Platform,
+			ChannelType: in.ChannelType,
+			ChannelID:   in.ChannelID,
+			GroupID:     in.GroupID,
+			GroupName:   in.GroupName,
+			SenderID:    in.SenderID,
+			Sender:      in.Sender,
+			Content:     content,
+			ContentType: adapter.ContentText,
+			Timestamp:   time.Now().UTC(),
+		}
+		// Each bubble is its own send so the gap lands between messages.
+		if err := a.SendMessage(ctx, adapter.UnifiedResponse{Messages: []adapter.UnifiedMessage{out}}); err != nil {
+			return fmt.Errorf("channelbridge: send bubble #%d of %d: %w", i+1, len(bubbles), err)
+		}
+	}
+	return nil
 }

 // adapter returns the registered adapter for a platform name, or nil.
@@ -0,0 +1,81 @@
+package channelbridge
+
+import (
+	"math/rand"
+	"regexp"
+	"strings"
+	"time"
+)
+
+// This file holds the chat-reply sanitizer used before a reply is delivered to an
+// IM channel adapter (design/17 §2 + the role-play convention: the Web client
+// renders <action>/<narration> as muted italic; IM channels must receive plain chat
+// text only, with the action/monologue markup removed).
+
+var (
+	// pairedRoleplayRe matches a complete <action>...</action> / <narration>...</narration>
+	// block including its inner text, so an action/monologue is dropped wholesale before
+	// IM delivery. Non-greedy and case-insensitive to tolerate a model that emits <Action>.
+	pairedRoleplayRe = regexp.MustCompile(`(?is)<(action|narration)\b[^>]*?>.*?</(action|narration)\s*>`)
+	// strayRoleplayRe matches any remaining single opening/closing role-play tag (for a
+	// malformed or unpaired emission).
+	strayRoleplayRe = regexp.MustCompile(`(?is)</?(action|narration)\b[^>]*?>`)
+	// paragraphRe matches <p>...</p> / <p/> paragraph markers, keeping the inner text.
+	paragraphRe = regexp.MustCompile(`(?is)</?p\b[^>]*?>`)
+	// blankLinesRe collapses runs of blank lines left behind after stripping.
+	blankLinesRe = regexp.MustCompile(`\n\s*\n+`)
+)
+
+// stripNarration returns the plain chat text of a reply with role-play/action/
+// narration markup removed, paragraph markers flattened and blank-line runs
+// collapsed. It never raises or panics on malformed input; a reply that was only an
+// action/monologue becomes an empty string (caller may then skip the send).
+func stripNarration(text string) string {
+	if strings.TrimSpace(text) == "" {
+		return ""
+	}
+	s := pairedRoleplayRe.ReplaceAllString(text, "")
+	s = strayRoleplayRe.ReplaceAllString(s, "")
+	s = paragraphRe.ReplaceAllString(s, "")
+	s = blankLinesRe.ReplaceAllString(s, "\n")
+	return strings.TrimSpace(s)
+}
+
+// paragraphBlockRe matches an entire <p>...</p> block, capturing its inner text
+// (design: each <p> is one chat bubble; the Web client renders each as its own
+// bubble and the IM adapters deliver each as its own message).
+var paragraphBlockRe = regexp.MustCompile(`(?is)<p\b[^>]*?>(.*?)</p\s*>`)
+
+// splitBubbles turns a reply into the list of chat bubbles it carries, in order.
+// Each <p>...</p> block is one bubble, with role-play/action/narration stripped from
+// its text; empty bubbles are dropped. A reply with no <p> markers is treated as a
+// single bubble (newlines preserved). A pure action/monologue yields an empty slice.
+func splitBubbles(text string) []string {
+	if !strings.Contains(strings.ToLower(text), "<p") {
+		if c := stripNarration(text); c != "" {
+			return []string{c}
+		}
+		return nil
+	}
+	out := make([]string, 0)
+	for _, m := range paragraphBlockRe.FindAllStringSubmatch(text, -1) {
+		if c := stripNarration(m[1]); c != "" {
+			out = append(out, c)
+		}
+	}
+	if len(out) == 0 {
+		// <p> markers present but no well-formed block — fall back to whole text.
+		if c := stripNarration(text); c != "" {
+			out = append(out, c)
+		}
+	}
+	return out
+}
+
+// bubbleGap returns a randomized 0.5s..2s delay used between IM outbound bubbles so a
+// burst of paragraphs doesn't flood the channel (design/17 §2). The Web frontend is
+// not affected — it renders all bubbles from the persisted stream without any delay.
+// It is only consulted when a reply carries more than one bubble.
+func bubbleGap() time.Duration {
+	return 500*time.Millisecond + time.Duration(rand.Float64()*1500)*time.Millisecond
+}
@@ -0,0 +1,91 @@
+package channelbridge
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestStripNarration_RemovesActionBlock(t *testing.T) {
+	t.Parallel()
+	in := "<action>弯起眼睛笑了</action>\n当然看得到呀，亲爱的。\n怎么突然这么问，是想我了吗？"
+	got := stripNarration(in)
+	want := "当然看得到呀，亲爱的。\n怎么突然这么问，是想我了吗？"
+	if got != want {
+		t.Errorf("stripNarration = %q, want %q", got, want)
+	}
+}
+
+func TestStripNarration_RemovesNarrationAndParagraphs(t *testing.T) {
+	t.Parallel()
+	in := "<p>你好呀</p>\n<narration>心里有点甜</narration>\n<p>今天天气不错</p>"
+	got := stripNarration(in)
+	// Paragraph markers flattened to newlines; narration block dropped entirely.
+	if got != "你好呀\n今天天气不错" {
+		t.Errorf("stripNarration = %q, want %q", got, "你好呀\n今天天气不错")
+	}
+}
+
+func TestStripNarration_PureChatKept(t *testing.T) {
+	t.Parallel()
+	in := "就是普通一句话，没有动作。\n第二行。"
+	if got := stripNarration(in); got != in {
+		t.Errorf("stripNarration changed plain text: %q -> %q", in, got)
+	}
+}
+
+func TestStripNarration_OnlyActionBecomesEmpty(t *testing.T) {
+	t.Parallel()
+	in := "<action>拍拍你</action>"
+	if got := stripNarration(in); got != "" {
+		t.Errorf("stripNarration = %q, want empty", got)
+	}
+}
+
+func TestStripNarration_CaseAndStrayTags(t *testing.T) {
+	t.Parallel()
+	in := "<Action>扑上来</Action> 你好 <narration/> 世界"
+	got := stripNarration(in)
+	if strings.Contains(got, "action") || strings.Contains(got, "narration") || strings.Contains(got, "扑上来") {
+		t.Errorf("stripNarration left role-play markup: %q", got)
+	}
+	if !strings.Contains(got, "你好") || !strings.Contains(got, "世界") {
+		t.Errorf("stripNarration dropped chat text: %q", got)
+	}
+}
+
+func TestSplitBubbles_Paragraphs(t *testing.T) {
+	t.Parallel()
+	in := "<p>晚上好呀，亲爱的♪</p><p>怎么突然这么问，是想我了吗？</p>"
+	got := splitBubbles(in)
+	if len(got) != 2 || got[0] != "晚上好呀，亲爱的♪" || got[1] != "怎么突然这么问，是想我了吗？" {
+		t.Errorf("splitBubbles = %#v", got)
+	}
+}
+
+func TestSplitBubbles_StripsRoleplayAndDropsEmpty(t *testing.T) {
+	t.Parallel()
+	in := "<p><action>弯起眼睛笑了</action>当然看得到呀。</p><p>❤</p>"
+	got := splitBubbles(in)
+	if len(got) != 2 || got[0] != "当然看得到呀。" {
+		t.Errorf("splitBubbles = %#v", got)
+	}
+	if got[1] != "❤" {
+		t.Errorf("splitBubbles[1] = %q, want ❤", got[1])
+	}
+}
+
+func TestSplitBubbles_NoParagraphIsSingleBubble(t *testing.T) {
+	t.Parallel()
+	in := "就是普通一句话\n带个换行。"
+	got := splitBubbles(in)
+	if len(got) != 1 || got[0] != in {
+		t.Errorf("splitBubbles = %#v", got)
+	}
+}
+
+func TestSplitBubbles_OnlyActionIsEmpty(t *testing.T) {
+	t.Parallel()
+	if got := splitBubbles("<action>拍拍你</action>"); len(got) != 0 {
+		t.Errorf("splitBubbles = %#v, want empty", got)
+	}
+}