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>

app.py

@@ -21,6 +21,7 @@ import time
 from pathlib import Path
 
 import streamlit as st
+import streamlit.components.v1 as components
 
 from dotenv import load_dotenv
 load_dotenv()
@@ -117,6 +118,10 @@ if "graph" not in st.session_state:
     st.session_state.graph = build_graph()
 if "pending_action" not in st.session_state:
     st.session_state.pending_action = None
+if "chat_attached_files" not in st.session_state:
+    st.session_state.chat_attached_files = []  # [{name, text, type, path}]
+if "_paste_processed_ts" not in st.session_state:
+    st.session_state._paste_processed_ts = 0
 
 if "agent_state" not in st.session_state:
     if url_session_id:
@@ -402,16 +407,21 @@ with st.sidebar:
 
     if selected and session_options.get(selected) != current_session_id:
         new_sid = session_options[selected]
-        data = load_session(new_sid)
-        if data and data.get("agent_state"):
-            _app_log.info(
-                "切换会话",
-                extra={"from_session": current_session_id, "to_session": new_sid},
-            )
-            data["agent_state"]["session_id"] = new_sid
-            st.session_state.agent_state = data["agent_state"]
-            st.session_state.messages = []
-            st.rerun()
+        if st.session_state.get("_last_switched_to") == new_sid:
+            # 防止同一会话重复切换导致的无限 rerun 循环
+            st.session_state._last_switched_to = ""
+        else:
+            data = load_session(new_sid)
+            if data and data.get("agent_state"):
+                _app_log.info(
+                    "切换会话",
+                    extra={"from_session": current_session_id, "to_session": new_sid},
+                )
+                data["agent_state"]["session_id"] = new_sid
+                st.session_state.agent_state = data["agent_state"]
+                st.session_state.messages = []
+                st.session_state._last_switched_to = new_sid
+                st.rerun()
 
     col1, col2 = st.columns(2)
     with col1:
@@ -481,7 +491,7 @@ with st.sidebar:
 
     uploaded = st.file_uploader(
         "选择文件",
-        type=["png", "jpg", "jpeg", "bmp", "webp", "pdf", "docx", "txt", "csv", "json", "xml"],
+        type=["png", "jpg", "jpeg", "bmp", "webp", "pdf", "docx", "xlsx", "txt", "csv", "json", "xml"],
         accept_multiple_files=True,
         key="file_uploader",
         label_visibility="collapsed",
@@ -614,6 +624,95 @@ with st.sidebar:
                     key=f"dl_v{i}",
                 )
 
+# ---- 文件粘贴/拖拽全局处理器 ----
+st.html("""
+<script>
+(function() {
+    if (window.__jrxml_drop_paste) return;
+    window.__jrxml_drop_paste = true;
+    var MAX_SIZE = 20 * 1024 * 1024;
+    function handleFiles(files) {
+        var fd = []; var n = 0; var total = Math.min(files.length, 10);
+        for (var i = 0; i < total; i++) {
+            var f = files[i];
+            if (f.size > MAX_SIZE) { n++; continue; }
+            var reader = new FileReader();
+            reader.onload = (function(file) {
+                return function(e) {
+                    fd.push({name: file.name, size: file.size, data: e.target.result});
+                    n++;
+                    if (n === total && fd.length) {
+                        sessionStorage.setItem('_jrxml_paste', JSON.stringify({ts: Date.now(), files: fd}));
+                    }
+                };
+            })(f);
+            reader.readAsDataURL(f);
+        }
+    }
+    document.addEventListener('paste', function(e) {
+        var fs = e.clipboardData && e.clipboardData.files;
+        if (fs && fs.length) { e.preventDefault(); handleFiles(fs); }
+    });
+    document.addEventListener('dragover', function(e) {
+        e.preventDefault(); e.dataTransfer.dropEffect = 'copy';
+    });
+    document.addEventListener('drop', function(e) {
+        var fs = e.dataTransfer && e.dataTransfer.files;
+        if (fs && fs.length) { e.preventDefault(); handleFiles(fs); }
+    });
+})();
+</script>
+""")
+
+# ---- 粘贴桥接组件 ----
+paste_data = components.html("""
+<script>
+(function poll() {
+    var raw = sessionStorage.getItem('_jrxml_paste');
+    if (raw) {
+        try { sessionStorage.removeItem('_jrxml_paste'); Streamlit.setComponentValue(JSON.parse(raw)); return; }
+        catch(e) {}
+    }
+    setTimeout(poll, 800);
+})();
+</script>
+""", height=0, default=0)
+
+if paste_data and paste_data != 0:
+    pts = paste_data.get("ts", 0)
+    if pts > st.session_state._paste_processed_ts:
+        st.session_state._paste_processed_ts = pts
+        import base64, tempfile
+        from backend.file_parser import parse_file
+        from backend.layout_analyzer import analyze_layout
+        for fi in paste_data.get("files", []):
+            if not any(f["name"] == fi["name"] for f in st.session_state.chat_attached_files):
+                header, b64 = fi["data"].split(",", 1)
+                raw = base64.b64decode(b64)
+                suffix = Path(fi["name"]).suffix.lower()
+                with tempfile.NamedTemporaryFile(suffix=suffix, delete=False) as tmp:
+                    tmp.write(raw)
+                    tmp_path = tmp.name
+                result = parse_file(tmp_path, suffix)
+                text = result["text"]
+                file_type = result["file_type"]
+                img_suffixes = (".png", ".jpg", ".jpeg", ".bmp", ".webp")
+                if suffix in img_suffixes and result.get("method") not in ("metadata_only", None):
+                    try:
+                        layout = analyze_layout(tmp_path)
+                        tt = layout.get("template_type", "unknown")
+                        if tt == "full_a4":
+                            text = layout["description"]
+                            file_type = "a4_template"
+                        elif tt == "partial_rows":
+                            file_type = "a4_partial"
+                    except Exception:
+                        pass
+                st.session_state.chat_attached_files.append({
+                    "name": fi["name"], "text": text, "type": file_type, "path": tmp_path
+                })
+        st.rerun()
+
 # ---- 标题 ----
 st.title("📝 JRXML 报表生成器")
 st.caption("用自然语言描述您的报表需求，我将逐步生成可用的 JRXML 模板。")
@@ -633,29 +732,122 @@ for msg in st.session_state.messages:
         else:
             st.markdown(msg["content"])
 
+# ---- 已附加文件预览 ----
+if st.session_state.chat_attached_files:
+    n_files = len(st.session_state.chat_attached_files)
+    chip_cols = st.columns(min(n_files, 4))
+    files_to_remove = []
+    for i, f in enumerate(st.session_state.chat_attached_files):
+        with chip_cols[i % len(chip_cols)]:
+            c1, c2 = st.columns([5, 1])
+            with c1:
+                name = f["name"]
+                short_name = name[:16] + ("…" if len(name) > 16 else "")
+                emoji_map = {"a4_template": "📷", "image": "🖼", "pdf": "📄", "docx": "📝", "xlsx": "📊"}
+                emoji = emoji_map.get(f["type"], "📎")
+                st.caption(f"{emoji} {short_name}")
+            with c2:
+                if st.button("✕", key=f"rm_chip_{i}"):
+                    files_to_remove.append(i)
+    if files_to_remove:
+        for i in sorted(files_to_remove, reverse=True):
+            try:
+                Path(st.session_state.chat_attached_files[i]["path"]).unlink(missing_ok=True)
+            except Exception:
+                pass
+            st.session_state.chat_attached_files.pop(i)
+        st.rerun()
+
+# ---- 对话区域文件上传 ----
+col_fu, col_hint = st.columns([5, 1])
+with col_fu:
+    chat_uploads = st.file_uploader(
+        "附加文件",
+        type=["png", "jpg", "jpeg", "bmp", "webp", "pdf", "docx", "xlsx", "txt", "csv", "json", "xml"],
+        accept_multiple_files=True,
+        key="chat_file_uploader",
+        label_visibility="visible",
+    )
+with col_hint:
+    st.caption("Ctrl+V 粘贴\n或拖拽到页面")
+
+if chat_uploads:
+    newly_added = False
+    import tempfile
+    from backend.file_parser import parse_file
+    from backend.layout_analyzer import analyze_layout
+    for uf in chat_uploads:
+        if not any(f["name"] == uf.name for f in st.session_state.chat_attached_files):
+            suffix = Path(uf.name).suffix.lower()
+            with tempfile.NamedTemporaryFile(suffix=suffix, delete=False) as tmp:
+                tmp.write(uf.getvalue())
+                tmp_path = tmp.name
+            result = parse_file(tmp_path, suffix)
+            text = result["text"]
+            file_type = result["file_type"]
+            img_suffixes = (".png", ".jpg", ".jpeg", ".bmp", ".webp")
+            if suffix in img_suffixes and result.get("method") not in ("metadata_only", None):
+                try:
+                    layout = analyze_layout(tmp_path)
+                    tt = layout.get("template_type", "unknown")
+                    if tt == "full_a4":
+                        text = layout["description"]
+                        file_type = "a4_template"
+                    elif tt == "partial_rows":
+                        file_type = "a4_partial"
+                except Exception:
+                    pass
+            st.session_state.chat_attached_files.append({
+                "name": uf.name, "text": text, "type": file_type, "path": tmp_path
+            })
+            newly_added = True
+    if newly_added:
+        st.session_state.chat_file_uploader = []
+        st.rerun()
+
 # ---- 聊天输入 ----
 if prompt := st.chat_input("描述您的报表需求..."):
-    # 拼接上传文件的文本
-    uploaded_texts = []
-    uploaded_files_info = []
+    # 拼接对话区域附加文件的文本
+    file_texts = []
+    attached_info = []
+    for f in st.session_state.chat_attached_files:
+        file_texts.append(f"[附加文件: {f['name']} ({f['type']})]\n{f['text']}")
+        attached_info.append({"name": f["name"], "type": f["type"], "length": len(f["text"])})
+
+    # 同时拼接侧边栏上传的文件（向后兼容）
     if st.session_state.get("uploaded_files"):
         for f in st.session_state.uploaded_files:
-            uploaded_texts.append(f"[上传文件: {f['name']}]\n{f['text']}")
-            uploaded_files_info.append({"name": f["name"], "type": f["type"], "length": len(f["text"])})
-    if uploaded_texts:
-        full_prompt = "\n\n".join(uploaded_texts) + "\n\n---\n用户需求:\n" + prompt
-        st.session_state.uploaded_files = []  # 用后即清
+            file_texts.append(f"[上传文件: {f['name']}]\n{f['text']}")
+            attached_info.append({"name": f["name"], "type": f["type"], "length": len(f["text"])})
+
+    if file_texts:
+        full_prompt = "\n\n".join(file_texts) + "\n\n---\n用户需求:\n" + prompt
     else:
         full_prompt = prompt
 
+    # 将第一个图片文件的路径传给 agent，供 OCR 字段精确提取
+    for f in st.session_state.chat_attached_files:
+        if f["type"] in ("image", "a4_template", "a4_partial"):
+            st.session_state.agent_state["uploaded_file_path"] = f["path"]
+            break
+
+    # 清理临时文件和状态
+    st.session_state.uploaded_files = []
+    for f in st.session_state.chat_attached_files:
+        try:
+            Path(f["path"]).unlink(missing_ok=True)
+        except Exception:
+            pass
+    st.session_state.chat_attached_files = []
+
     _app_log.info(
         "收到用户输入",
         extra={
             "session_id": current_session_id,
             "prompt_preview": prompt[:200],
             "prompt_length": len(prompt),
-            "has_uploaded_files": bool(uploaded_files_info),
-            "uploaded_files": uploaded_files_info,
+            "has_uploaded_files": bool(attached_info),
+            "uploaded_files": attached_info,
         },
     )