feat(chat): 动作/旁白格式统一——兼容星号(*…*/*…) + 人设强制 XML
模型常漂移成 *动作:弯起眼睛*(星号),前端/后端只认 <action>/<narration>,导致星号版 没被剥成灰斜体注记/没从 IM 剥除→裸出在气泡、上下文不连贯。 - parseContent.ts(新): 把 XML <action>/<narration>、全角*…*(带'动作/旁白/内心/神态/轻声' 关键词或整段≤40字)、半角*词…*(仅关键词前缀)统一解析成 ContentPart,剥出正文进 BubbleNotes 灰斜体注记(*动作:…*); 超长无关键词*…*保留为文本; <p>拆气泡不变 - sanitize.go: stripNarration 同样剥星号动作(与 XML 一致); splitBubbles 不变 - cyrene.yaml: 新增格式铁律——动作/旁白必须用 <action>/<narration>,禁用*/Markdown等 验收: 后端 build/vet/test 全绿 + 前端 build 绿 + Node parseContent/splitBubble 实测(5组)
This commit is contained in:
1 parent
06fd2f4aaf
commit
817f1e6355
4 files changed
+197
-20
No files matched your search
@@ -5,6 +5,7 @@ import (
|
||||
"regexp"
|
||||
"strings"
|
||||
"time"
|
||||
"unicode/utf8"
|
||||
)
|
||||
|
||||
// This file holds the chat-reply sanitizer used before a reply is delivered to an
|
||||
@@ -24,8 +25,21 @@ var (
|
||||
paragraphRe = regexp.MustCompile(`(?is)</?p\b[^>]*?>`)
|
||||
// blankLinesRe collapses runs of blank lines left behind after stripping.
|
||||
blankLinesRe = regexp.MustCompile(`\n\s*\n+`)
|
||||
// starRoleplayRe matches a full-width star-wrapped block *...* — the drift
|
||||
// form when the model forgets the <action>/<narration> XML tags. The body is
|
||||
// captured so a non-role-play full-width emphasis can be left alone.
|
||||
starRoleplayRe = regexp.MustCompile(`(?s)*([\s\S]*?)*`)
|
||||
// halfStarRoleplayRe matches a half-width star block that clearly carries a
|
||||
// role-play keyword (动作/旁白/内心/神态/轻声), so *动作:弯起眼睛* is stripped
|
||||
// while plain markdown *emphasis* is left untouched.
|
||||
halfStarRoleplayRe = regexp.MustCompile(`(?s)\*((?:动作|旁白|内心|神态|轻声)\s*[::]?[\s\S]*?)\*`)
|
||||
)
|
||||
|
||||
// shortRoleplayRunes caps how long a keyword-less full-width star block may be
|
||||
// and still be treated as a role-play remark (design §9.5: conservative — a long
|
||||
// keyword-less *...* paragraph is left as text rather than dropped wholesale).
|
||||
const shortRoleplayRunes = 40
|
||||
|
||||
// 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
|
||||
@@ -36,11 +50,43 @@ func stripNarration(text string) string {
|
||||
}
|
||||
s := pairedRoleplayRe.ReplaceAllString(text, "")
|
||||
s = strayRoleplayRe.ReplaceAllString(s, "")
|
||||
s = starRoleplayRe.ReplaceAllStringFunc(s, func(m string) string {
|
||||
if isStarRoleplay(strings.TrimSpace(strings.TrimSuffix(strings.TrimPrefix(m, "*"), "*"))) {
|
||||
return ""
|
||||
}
|
||||
return m
|
||||
})
|
||||
s = halfStarRoleplayRe.ReplaceAllString(s, "")
|
||||
s = paragraphRe.ReplaceAllString(s, "")
|
||||
s = blankLinesRe.ReplaceAllString(s, "\n")
|
||||
return strings.TrimSpace(s)
|
||||
}
|
||||
|
||||
// isStarRoleplay reports whether a full-width star block *...* holds a role-play
|
||||
// remark: it carries a role-play keyword, or it is a short stand-alone fragment
|
||||
// (no newline, no long body) — the drift shape *弯起眼睛*. A long keyword-less
|
||||
// paragraph wrapped in stars is kept so a real message is not dropped.
|
||||
func isStarRoleplay(inner string) bool {
|
||||
t := strings.TrimSpace(inner)
|
||||
if t == "" {
|
||||
return false
|
||||
}
|
||||
if hasRoleplayPrefix(t) {
|
||||
return true
|
||||
}
|
||||
return !strings.Contains(t, "\n") && utf8.RuneCountInString(t) <= shortRoleplayRunes
|
||||
}
|
||||
|
||||
// hasRoleplayPrefix reports whether the block starts with a role-play keyword.
|
||||
func hasRoleplayPrefix(t string) bool {
|
||||
for _, p := range []string{"动作", "旁白", "内心", "神态", "轻声"} {
|
||||
if strings.HasPrefix(t, p) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// 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).
|
||||
|
||||
@@ -89,3 +89,72 @@ func TestSplitBubbles_OnlyActionIsEmpty(t *testing.T) {
|
||||
t.Errorf("splitBubbles = %#v, want empty", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStripNarration_StripsFullStarRoleplay(t *testing.T) {
|
||||
t.Parallel()
|
||||
in := "*动作:弯起眼睛笑了*\n当然看得到呀,亲爱的。"
|
||||
got := stripNarration(in)
|
||||
want := "当然看得到呀,亲爱的。"
|
||||
if got != want {
|
||||
t.Errorf("stripNarration = %q, want %q", got, want)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStripNarration_StripsKeywordHalfStarRoleplay(t *testing.T) {
|
||||
t.Parallel()
|
||||
in := "*旁白:心里有点甜*\n这是正文。"
|
||||
got := stripNarration(in)
|
||||
want := "这是正文。"
|
||||
if got != want {
|
||||
t.Errorf("stripNarration = %q, want %q", got, want)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStripNarration_KeepsPlainEmphasis(t *testing.T) {
|
||||
t.Parallel()
|
||||
in := "这是一段 *强调* 文字,不是动作。"
|
||||
if got := stripNarration(in); got != in {
|
||||
t.Errorf("stripNarration stripped emphasis: %q -> %q", in, got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStripNarration_MixedStarAndXml(t *testing.T) {
|
||||
t.Parallel()
|
||||
in := "<action>拍拍肩膀</action> *旁白:其实有点开心* 你来了呀。对了 *强调*。"
|
||||
got := stripNarration(in)
|
||||
for _, leaked := range []string{"action", "旁白", "拍拍", "其实有点开心"} {
|
||||
if strings.Contains(got, leaked) {
|
||||
t.Errorf("stripNarration left role-play %q: %q", leaked, got)
|
||||
}
|
||||
}
|
||||
if !strings.Contains(got, "你来了呀") || !strings.Contains(got, "*强调*") {
|
||||
t.Errorf("stripNarration dropped chat/emphasis: %q", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStripNarration_OnlyStarActionBecomesEmpty(t *testing.T) {
|
||||
t.Parallel()
|
||||
if got := stripNarration("*弯起眼睛*"); got != "" {
|
||||
t.Errorf("stripNarration = %q, want empty", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestStripNarration_KeepsLongKeywordlessFullStar(t *testing.T) {
|
||||
t.Parallel()
|
||||
in := "*这是一段很长的全角星号包裹的普通段落,足足有几十个字,超过阈值所以应当被保留而不是被剥掉。*"
|
||||
if got := stripNarration(in); got != in {
|
||||
t.Errorf("stripNarration dropped long full-width star text: %q -> %q", in, got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestSplitBubbles_StripsStarRoleplayInParagraphs(t *testing.T) {
|
||||
t.Parallel()
|
||||
in := "<p>*动作:弯起眼睛*当然看得到呀。</p><p>*旁白:心里甜* 好。</p>"
|
||||
got := splitBubbles(in)
|
||||
if len(got) != 2 || got[0] != "当然看得到呀。" {
|
||||
t.Errorf("splitBubbles = %#v", got)
|
||||
}
|
||||
if got[1] != "好。" {
|
||||
t.Errorf("splitBubbles[1] = %q, want 好。", got[1])
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user