fix(growth,runtime,desktop): E2E 验证 4 项 Bug 修复

P1 BUG-1: SemanticScorer CJK 分词缺失导致 TF-IDF 相似度为 0
- 新增 CJK bigram 分词: "北京工作" → ["北京","京工","工作","北京工作"]
- 非CJK文本保持原有分割逻辑
- 3 个新测试: bigram 生成 + 混合文本 + CJK 相似度>0

P1 BUG-2: streamStore lifecycle:end 未记录 token 使用量
- AgentStreamDelta 增加 input_tokens/output_tokens 字段
- lifecycle:end 处理中检查并调用 addTokenUsage

P2 BUG-3: NlScheduleParser "X点半" 解析为整点
- 所有时间正则增加可选的 (半) 捕获组
- extract_minute 辅助函数: 半 → 30

P2 BUG-4: NlScheduleParser "工作日每天" 未转为 1-5
- RE_WORKDAY_EXACT 支持 (每天|每日)? 中缀
- try_workday 优先级提升至 try_every_day 之前

E2E 报告: docs/E2E_TEST_REPORT_2026_04_19.md
测试: 806 passed / 0 failed (含 9 个新增测试)

crates/zclaw-growth/src/retrieval/semantic.rs

@@ -122,13 +122,65 @@ impl SemanticScorer {
         .collect()
     }
 
-    /// Tokenize text into words
+    /// Tokenize text into words with CJK-aware bigram support.
+    ///
+    /// For ASCII/latin text, splits on non-alphanumeric boundaries as before.
+    /// For CJK text, generates character-level bigrams (e.g. "北京工作" → ["北京", "京工", "工作"])
+    /// so that TF-IDF cosine similarity works for CJK queries.
     fn tokenize(text: &str) -> Vec<String> {
-        text.to_lowercase()
-            .split(|c: char| !c.is_alphanumeric())
-            .filter(|s| !s.is_empty() && s.len() > 1)
-            .map(|s| s.to_string())
-            .collect()
+        let lower = text.to_lowercase();
+        let mut tokens = Vec::new();
+
+        // Split into segments: each segment is either pure CJK or non-CJK
+        let mut cjk_buf = String::new();
+        let mut latin_buf = String::new();
+
+        let flush_latin = |buf: &mut String, tokens: &mut Vec<String>| {
+            if !buf.is_empty() {
+                for word in buf.split(|c: char| !c.is_alphanumeric()) {
+                    if !word.is_empty() && word.len() > 1 {
+                        tokens.push(word.to_string());
+                    }
+                }
+                buf.clear();
+            }
+        };
+
+        let flush_cjk = |buf: &mut String, tokens: &mut Vec<String>| {
+            if buf.is_empty() {
+                return;
+            }
+            let chars: Vec<char> = buf.chars().collect();
+            // Generate bigrams for CJK
+            if chars.len() >= 2 {
+                for i in 0..chars.len() - 1 {
+                    tokens.push(format!("{}{}", chars[i], chars[i + 1]));
+                }
+            }
+            // Also include the full CJK segment as a single token for exact-match bonus
+            if chars.len() > 1 {
+                tokens.push(buf.clone());
+            }
+            buf.clear();
+        };
+
+        for c in lower.chars() {
+            if is_cjk_char(c) {
+                flush_latin(&mut latin_buf, &mut tokens);
+                cjk_buf.push(c);
+            } else if c.is_alphanumeric() {
+                flush_cjk(&mut cjk_buf, &mut tokens);
+                latin_buf.push(c);
+            } else {
+                // Non-alphanumeric, non-CJK: flush both
+                flush_latin(&mut latin_buf, &mut tokens);
+                flush_cjk(&mut cjk_buf, &mut tokens);
+            }
+        }
+        flush_latin(&mut latin_buf, &mut tokens);
+        flush_cjk(&mut cjk_buf, &mut tokens);
+
+        tokens
     }
 
     /// Remove stop words from tokens
@@ -409,6 +461,20 @@ impl Default for SemanticScorer {
     }
 }
 
+/// Check if a character is a CJK ideograph
+fn is_cjk_char(c: char) -> bool {
+    matches!(c,
+        '\u{4E00}'..='\u{9FFF}' |
+        '\u{3400}'..='\u{4DBF}' |
+        '\u{20000}'..='\u{2A6DF}' |
+        '\u{2A700}'..='\u{2B73F}' |
+        '\u{2B740}'..='\u{2B81F}' |
+        '\u{2B820}'..='\u{2CEAF}' |
+        '\u{F900}'..='\u{FAFF}' |
+        '\u{2F800}'..='\u{2FA1F}'
+    )
+}
+
 /// Index statistics
 #[derive(Debug, Clone)]
 pub struct IndexStats {
@@ -430,6 +496,42 @@ mod tests {
         assert_eq!(tokens, vec!["hello", "world", "this", "is", "test"]);
     }
 
+    #[test]
+    fn test_tokenize_cjk_bigrams() {
+        // CJK text should produce bigrams + full segment token
+        let tokens = SemanticScorer::tokenize("北京工作");
+        assert!(tokens.contains(&"北京".to_string()), "should contain bigram 北京");
+        assert!(tokens.contains(&"京工".to_string()), "should contain bigram 京工");
+        assert!(tokens.contains(&"工作".to_string()), "should contain bigram 工作");
+        assert!(tokens.contains(&"北京工作".to_string()), "should contain full segment");
+    }
+
+    #[test]
+    fn test_tokenize_mixed_cjk_latin() {
+        // Mixed CJK and latin should handle both
+        let tokens = SemanticScorer::tokenize("我在北京工作，用Python写脚本");
+        // CJK bigrams
+        assert!(tokens.contains(&"我在".to_string()));
+        assert!(tokens.contains(&"北京".to_string()));
+        // Latin word
+        assert!(tokens.contains(&"python".to_string()));
+    }
+
+    #[test]
+    fn test_cjk_similarity() {
+        let mut scorer = SemanticScorer::new();
+
+        let entry = MemoryEntry::new(
+            "test", MemoryType::Preference, "test",
+            "用户在北京工作，做AI产品经理".to_string(),
+        );
+        scorer.index_entry(&entry);
+
+        // Query "北京" should have non-zero similarity after bigram fix
+        let score = scorer.score_similarity("北京", &entry);
+        assert!(score > 0.0, "CJK query should score > 0 after bigram tokenization, got {}", score);
+    }
+
     #[test]
     fn test_stop_words_removal() {
         let scorer = SemanticScorer::new();