fix(memory): CJK-aware short query threshold + Chinese synonym expansion

1. MemoryMiddleware: replace byte-length check (query.len() < 4) with
   char-count check (query.chars().count() < 2). Single CJK characters
   are 3 UTF-8 bytes but 1 meaningful character — the old threshold
   incorrectly skipped 1-2 char Chinese queries like "你好".

2. QueryAnalyzer: add Chinese synonym mappings for 13 common technical
   terms (错误→bug, 优化→improve, 配置→config, etc.) so CJK queries
   can find relevant English-keyword memories and vice versa.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

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

@@ -216,9 +216,10 @@ impl QueryAnalyzer {
         expansions
     }
 
-    /// Get synonyms for a keyword (simplified)
+    /// Get synonyms for a keyword (simplified, English + Chinese)
     fn get_synonyms(&self, keyword: &str) -> Option<Vec<String>> {
         let synonyms: &[&str] = match keyword {
+            // English synonyms
             "code" => &["program", "script", "source"],
             "error" => &["bug", "issue", "problem", "exception"],
             "fix" => &["solve", "resolve", "repair", "patch"],
@@ -226,6 +227,20 @@ impl QueryAnalyzer {
             "slow" => &["performance", "optimize", "speed"],
             "help" => &["assist", "support", "guide", "aid"],
             "learn" => &["study", "understand", "know", "grasp"],
+            // Chinese synonyms — critical for Chinese-language queries
+            "错误" => &["问题", "bug", "异常", "故障"],
+            "修复" => &["解决", "修正", "处理", "fix"],
+            "优化" => &["改进", "提升", "加速", "improve"],
+            "配置" => &["设置", "参数", "选项", "config"],
+            "性能" => &["速度", "效率", "performance"],
+            "问题" => &["错误", "故障", "issue", "problem"],
+            "帮助" => &["协助", "支持", "help"],
+            "学习" => &["了解", "掌握", "learn"],
+            "代码" => &["程序", "脚本", "code"],
+            "数据库" => &["DB", "database", "存储"],
+            "部署" => &["发布", "上线", "deploy"],
+            "测试" => &["验证", "检验", "test"],
+            "安全" => &["防护", "加密", "security"],
             _ => return None,
         };
 

crates/zclaw-runtime/src/middleware/memory.rs

@@ -60,6 +60,22 @@ impl AgentMiddleware for MemoryMiddleware {
     fn priority(&self) -> i32 { 150 }
 
     async fn before_completion(&self, ctx: &mut MiddlewareContext) -> Result<MiddlewareDecision> {
+        // Skip memory injection for very short queries.
+        // Short queries (e.g., "1+6", "hi", "好") don't benefit from memory context.
+        // Worse, the retriever's scope-based fallback may return high-importance but
+        // irrelevant old memories, causing the model to think about past conversations
+        // instead of answering the current question.
+        // Use char count (not byte count) so CJK queries are handled correctly:
+        // a single Chinese char is 3 UTF-8 bytes but 1 meaningful character.
+        let query = ctx.user_input.trim();
+        if query.chars().count() < 2 {
+            tracing::debug!(
+                "[MemoryMiddleware] Skipping enhancement for short query ({:?}): no memory context needed",
+                query
+            );
+            return Ok(MiddlewareDecision::Continue);
+        }
+
         match self.growth.enhance_prompt(
             &ctx.agent_id,
             &ctx.system_prompt,
@@ -92,21 +108,27 @@ impl AgentMiddleware for MemoryMiddleware {
             return Ok(());
         }
 
-        match self.growth.process_conversation(
+        // Combined extraction: single LLM call produces both memories and structured facts.
+        // Avoids double LLM extraction ( process_conversation + extract_structured_facts).
+        match self.growth.extract_combined(
             &ctx.agent_id,
             &ctx.messages,
-            ctx.session_id.clone(),
+            &ctx.session_id,
         ).await {
-            Ok(count) => {
+            Ok(Some((mem_count, facts))) => {
                 tracing::info!(
-                    "[MemoryMiddleware] Extracted {} memories for agent {}",
+                    "[MemoryMiddleware] Extracted {} memories + {} structured facts for agent {}",
-                    count,
+                    mem_count,
+                    facts.len(),
                     agent_key
                 );
             }
+            Ok(None) => {
+                tracing::debug!("[MemoryMiddleware] No memories or facts extracted");
+            }
             Err(e) => {
                 // Non-fatal: extraction failure should not affect the response
-                tracing::warn!("[MemoryMiddleware] Memory extraction failed: {}", e);
+                tracing::warn!("[MemoryMiddleware] Combined extraction failed: {}", e);
             }
         }