refactor(backend): update document parsers for DOCX and PDF

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

backend/app/utils/docx_parser.py

@@ -1,17 +1,10 @@
 from __future__ import annotations
 
-from typing import Optional
-Document = None
-
-
-def _ensure_docx_imported():
-    global Document
-    if Document is None:
 try:
-            from docx import Document as _Doc  # type: ignore
+    from docx import Document as _Doc
     Document = _Doc
-        except Exception as exc:  # pragma: no cover - missing optional dep
+except Exception:
-            raise ValueError("DOCX library is not installed") from exc
+    Document = None
 
 
 def parse_docx(file_path: str) -> str:
@@ -23,9 +16,9 @@ def parse_docx(file_path: str) -> str:
     Raises:
         ValueError: If the file is not a valid DOCX document or cannot be read.
     """
+    if Document is None:
+        raise ValueError("DOCX library is not installed")
     try:
-        _ensure_docx_imported()
-        assert Document is not None
         doc = Document(file_path)
     except Exception as exc:  # pragma: no cover - surface invalid DOCX
         raise ValueError(f"Invalid DOCX file: {exc}") from exc

backend/app/utils/pdf_parser.py

@@ -1,6 +1,3 @@
-from __future__ import annotations
-
-from typing import Optional
 from pypdf import PdfReader