Refactor L0 quality and diffusion graph gating for balanced recall

modules/story-summary/vector/llm/atom-extraction.js

@@ -63,6 +63,8 @@ const SYSTEM_PROMPT = `你是场景摘要器。从一轮对话中提取1-2个场
 - 只从正文内容中识别角色名，不要把标签名（如 user、assistant）当作角色
 - r 使用动作模板短语：“动作+对象/结果”（例：“提出交易条件”、“拒绝对方请求”、“当众揭露秘密”、“安抚对方情绪”）
 - r 不要写人名，不要复述整句，不要写心理描写或评价词
+- r 正例（合格）：提出交易条件、拒绝对方请求、当众揭露秘密、安抚对方情绪、强行打断发言、转移谈话焦点
+- r 反例（不合格）：我觉得她现在很害怕、他突然非常生气地大喊起来、user开始说话、assistant解释了很多细节
 - 每个锚点 1-3 条
 
 ## where
@@ -87,6 +89,46 @@ const JSON_PREFILL = '{"anchors":[';
 
 const sleep = (ms) => new Promise(r => setTimeout(r, ms));
 
+const ACTION_STRIP_WORDS = [
+    '突然', '非常', '有些', '有点', '轻轻', '悄悄', '缓缓', '立刻',
+    '马上', '然后', '并且', '而且', '开始', '继续', '再次', '正在',
+];
+
+function clamp(v, min, max) {
+    return Math.max(min, Math.min(max, v));
+}
+
+function sanitizeActionPhrase(raw) {
+    let text = String(raw || '')
+        .normalize('NFKC')
+        .replace(/[\u200B-\u200D\uFEFF]/g, '')
+        .trim();
+    if (!text) return '';
+
+    text = text
+        .replace(/[，。！？、；：,.!?;:"'“”‘’()（）[\]{}<>《》]/g, '')
+        .replace(/\s+/g, '');
+
+    for (const word of ACTION_STRIP_WORDS) {
+        text = text.replaceAll(word, '');
+    }
+
+    text = text.replace(/(地|得|了|着|过)+$/g, '');
+
+    if (text.length < 2) return '';
+    if (text.length > 12) text = text.slice(0, 12);
+    return text;
+}
+
+function calcAtomQuality(scene, edges, where) {
+    const sceneLen = String(scene || '').length;
+    const sceneScore = clamp(sceneLen / 80, 0, 1);
+    const edgeScore = clamp((edges?.length || 0) / 3, 0, 1);
+    const whereScore = where ? 1 : 0;
+    const quality = 0.55 * sceneScore + 0.35 * edgeScore + 0.10 * whereScore;
+    return Number(quality.toFixed(3));
+}
+
 // ============================================================================
 // 清洗与构建
 // ============================================================================
@@ -103,7 +145,7 @@ function sanitizeEdges(raw) {
         .map(e => ({
             s: String(e.s || '').trim(),
             t: String(e.t || '').trim(),
-            r: String(e.r || '').trim().slice(0, 30),
+            r: sanitizeActionPhrase(e.r),
         }))
         .filter(e => e.s && e.t && e.r)
         .slice(0, 3);
@@ -127,6 +169,7 @@ function anchorToAtom(anchor, aiFloor, idx) {
     if (scene.length < 15) return null;
     const edges = sanitizeEdges(anchor.edges);
     const where = String(anchor.where || '').trim();
+    const quality = calcAtomQuality(scene, edges, where);
 
     return {
         atomId: `atom-${aiFloor}-${idx}`,
@@ -139,6 +182,7 @@ function anchorToAtom(anchor, aiFloor, idx) {
         // ═══ 图结构层（扩散的 key） ═══
         edges,
         where,
+        quality,
     };
 }