feat: 对话区域文件上传(粘贴/拖拽) + XLSX支持 + 会话切换无限循环修复

- 对话区域: st.file_uploader + 全局 paste/drop 事件监听 + sessionStorage 桥接
- 文件预览芯片: 上传后显示在对话区域，可逐文件移除
- OCR 双层解析全面接入: file_parser(文字) + ocr_extractor(字段提取)
- XLSX 解析: openpyxl 逐工作表/逐行读取
- 修复: create_session 强制写入 agent_state.session_id
- 修复: load_session_node 不再从磁盘覆盖 session_id
- 修复: 切换会话 _last_switched_to 哨兵防止无限 rerun

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend/file_parser.py

@@ -51,6 +51,7 @@ def parse_file(file_path: str, file_type: str = "") -> dict:
         ".webp": _parse_image,
         ".pdf":  _parse_pdf,
         ".docx": _parse_docx,
+        ".xlsx": _parse_xlsx,
     }
 
     parser = parsers.get(suffix)
@@ -195,6 +196,37 @@ def _parse_docx(path: Path) -> dict:
             "error": "DOCX 解析需要安装 python-docx"}
 
 
+def _parse_xlsx(path: Path) -> dict:
+    """提取 Excel (.xlsx) 表格内容为文本。"""
+    try:
+        import openpyxl
+        wb = openpyxl.load_workbook(path, read_only=True, data_only=True)
+        sheets_text = []
+        for sheet_name in wb.sheetnames:
+            ws = wb[sheet_name]
+            rows = []
+            for row in ws.iter_rows(values_only=True):
+                cells = [str(c) if c is not None else "" for c in row]
+                if any(c.strip() for c in cells):
+                    rows.append(" | ".join(cells))
+            if rows:
+                sheets_text.append(f"--- 工作表: {sheet_name} ---\n" + "\n".join(rows))
+        wb.close()
+        if sheets_text:
+            return {
+                "text": "\n\n".join(sheets_text),
+                "file_type": "xlsx",
+                "method": "openpyxl",
+                "error": None,
+            }
+    except ImportError:
+        pass
+    except Exception:
+        pass
+    return {"text": "", "file_type": "xlsx", "method": "none",
+            "error": "XLSX 解析需要安装 openpyxl"}
+
+
 def _parse_text(path: Path) -> dict:
     """读取纯文本文件。"""
     try:

backend/session.py

@@ -38,12 +38,14 @@ def create_session(name: str = "", agent_state: Optional[dict] = None) -> dict:
     _ensure_dir()
     sid = generate_session_id()
     now = _now_iso()
+    agent_state = agent_state or {}
+    agent_state["session_id"] = sid
     data = {
         "session_id": sid,
         "session_name": name or f"新建报表 {now[:10]}",
         "created_at": now,
         "updated_at": now,
-        "agent_state": agent_state or {},
+        "agent_state": agent_state,
     }
     with open(_session_path(sid), "w", encoding="utf-8") as f:
         json.dump(data, f, ensure_ascii=False, indent=2)