feat: sync core logic from main (cache fix, intent analyzer, engine improvements)

- core/cache.py: fix GET/SET key mismatch, use coarse-grained kb_version keys
- core/intent_analyzer.py: add cache_type tagging, enhance history parsing
- core/engine.py: adaptive topk score source fix, BM25 top-3 preservation, section cluster boost

core/intent_analyzer.py

@@ -316,7 +316,8 @@ class IntentAnalyzer:
 
             if cache_emb is not None:
                 cached = cache.get(cache_emb)
-                if cached:
+                # 确保缓存条目是意图分析结果（非 RAG 回答缓存）
+                if cached and cached.get("cache_type") != "rag_answer":
                     logger.info(f"意图分析缓存命中: {cached.get('reason', '')[:50]}")
                     return IntentAnalysis.from_dict(cached)
                 else:
@@ -386,9 +387,11 @@ class IntentAnalyzer:
                     intent=intent_type
                 )
 
-                # 存入语义缓存
+                # 存入语义缓存（标记类型，避免与 RAG 回答缓存混淆）
                 if cache and cache_emb is not None:
-                    cache.set(cache_emb, analysis.to_dict())
+                    cache_data = analysis.to_dict()
+                    cache_data["cache_type"] = "intent_analysis"
+                    cache.set(cache_emb, cache_data)
 
                 # 存入精确匹配缓存
                 if len(self._exact_cache) < self._exact_cache_max:
@@ -446,6 +449,7 @@ class IntentAnalyzer:
         if not history:
             return "（无历史对话）"
 
+        import re
         parts = []
 
         # 提取最近 3 轮对话
@@ -454,6 +458,7 @@ class IntentAnalyzer:
         for msg in recent_history:
             role = "用户" if msg.get("role") == "user" else "助手"
             content = msg.get("content", "")
+            original_content = content  # 保留原始内容用于结构化提取
 
             # 截断过长的内容
             if len(content) > 500:
@@ -461,9 +466,10 @@ class IntentAnalyzer:
 
             parts.append(f"【{role}】{content}")
 
-            # 提取图片信息
+            # 提取结构化信息（从 assistant 消息中提取章节、表格、来源等）
             metadata = msg.get("metadata", {})
             if isinstance(metadata, dict):
+                # 已有的图片提取
                 images = metadata.get("images", [])
                 if images:
                     for img in images[:3]:
@@ -472,6 +478,43 @@ class IntentAnalyzer:
                             img_type = img.get("type", "图片")
                             parts.append(f"  └─ {img_type}: {desc}")
 
+                # 来源文件提取
+                sources = metadata.get("sources", [])
+                if sources:
+                    source_names = []
+                    for s in sources[:3]:
+                        if isinstance(s, dict):
+                            name = s.get("source", "") or s.get("name", "")
+                            if name:
+                                source_names.append(name)
+                        elif isinstance(s, str):
+                            source_names.append(s)
+                    if source_names:
+                        parts.append(f"  └─ 来源文件: {', '.join(source_names)}")
+
+                # collections（检索知识库）提取
+                colls = metadata.get("collections", [])
+                if colls:
+                    parts.append(f"  └─ 检索知识库: {', '.join(colls)}")
+
+            # 从 assistant 原始内容中提取章节路径和表格结构
+            if role == "助手" and original_content:
+                # 提取章节路径：━ xxx ━ 格式
+                sections = re.findall(r'━\s*(.+?)\s*━', original_content)
+                if sections:
+                    unique_sections = list(dict.fromkeys(sections))  # 去重保序
+                    parts.append(f"  └─ 涉及章节: {'; '.join(unique_sections[:3])}")
+
+                # 提取表格列名：| A | B | C | 格式的表头行
+                table_headers = re.findall(r'^\|\s*(.+?)\s*\|', original_content, re.MULTILINE)
+                if table_headers:
+                    # 取第一个表格的列名
+                    first_header = table_headers[0]
+                    cols = [c.strip() for c in first_header.split('|') if c.strip()]
+                    # 排除分隔符行（--- 格式）
+                    if cols and not all(re.match(r'^[-:]+$', c) for c in cols):
+                        parts.append(f"  └─ 含表格，列名: {', '.join(cols[:6])}")
+
         # 添加图片上下文
         if context_images:
             parts.append("\n【上下文中的图片】")