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

backend/ocr_extractor.py

@@ -284,13 +284,13 @@ class OcrExtractor:
         try:
             import numpy as np
 
-            easyocr_result = self._try_easyocr(np.array(img))
-            if easyocr_result:
-                return easyocr_result
-
             paddleocr_result = self._try_paddleocr(img, file_path)
             if paddleocr_result:
                 return paddleocr_result
+
+            easyocr_result = self._try_easyocr(np.array(img))
+            if easyocr_result:
+                return easyocr_result
         except Exception:
             pass