feat: v4 multimodal chat input, multi-format support, and annotation detection

- Replace st.chat_input with st-multimodal-chatinput (Ctrl+V paste, drag-drop, file button)
- Extract _process_uploaded_file() shared handler (eliminates ~70 duplicated lines)
- Add XLSX (openpyxl), XLS (xlrd), DOC (olefile) parsers to file_parser.py
- Add backend/annotation_detector.py: circle detection (HoughCircles) + arrow detection (HoughLinesP clustering) + OCR correlation + LLM context formatting
- Add annotation_result field to AgentState with session persistence
- Wire annotation detection into process_input and _format_ocr_context
- Add 11 new tests: 7 annotation detector + 4 multi-format parser
- Update all docs: CLAUDE.md, README.md, CODE_GUIDE.md, ROADMAP.md

agent/state.py

@@ -44,3 +44,6 @@ class AgentState(TypedDict, total=False):
     # 需求7：OCR 单据字段精确提取结果
     ocr_extraction_result: dict
     uploaded_file_path: str
+
+    # 需求8：图片批注检测（圈选/箭头标记）
+    annotation_result: dict