From adb0b2329e8cf328e2a569f4ab9b6df6a3afdab9 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Fri, 6 Feb 2026 22:35:30 +0000
Subject: [PATCH] Address code review feedback

- Replace LIKE queries with exact matches in fallback lookups
- Add comments clarifying fallback queries should not be needed
- Fix duplicate comment in embed_metadata_into_pdf
- Add missing file_id parameter to log_task_progress call

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
---
 app/tasks/embed_metadata_into_pdf.py   | 9 ++++-----
 app/tasks/finalize_document_storage.py | 8 +++++---
 app/tasks/send_to_all.py               | 6 ++++--
 3 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/app/tasks/embed_metadata_into_pdf.py b/app/tasks/embed_metadata_into_pdf.py
index 2ae1cacc..9c3e8da4 100644
--- a/app/tasks/embed_metadata_into_pdf.py
+++ b/app/tasks/embed_metadata_into_pdf.py
@@ -64,23 +64,22 @@ def embed_metadata_into_pdf(self, local_file_path: str, extracted_text: str, met
     logger.info(f"[{task_id}] Starting metadata embedding for: {local_file_path}")
     log_task_progress(task_id, "embed_metadata_into_pdf", "in_progress", f"Embedding metadata into {os.path.basename(local_file_path)}", file_id=file_id)
     
-    # Get file_id from database if not provided
+    # Get file_id from database if not provided (fallback only, prefer passing file_id explicitly)
     if file_id is None:
         with SessionLocal() as db:
             file_record = db.query(FileRecord).filter_by(local_filename=local_file_path).first()
             if file_record:
                 file_id = file_record.id
+    
+    # Check for file existence; if not found, try the known shared tmp directory.
     if not os.path.exists(local_file_path):
         alt_path = os.path.join(settings.workdir, "tmp", os.path.basename(local_file_path))
         if os.path.exists(alt_path):
             local_file_path = alt_path
         else:
             logger.error(f"[{task_id}] Local file {local_file_path} not found, cannot embed metadata.")
-            log_task_progress(task_id, "embed_metadata_into_pdf", "failure", "File not found")
+            log_task_progress(task_id, "embed_metadata_into_pdf", "failure", "File not found", file_id=file_id)
             return {"error": "File not found"}
-    
-    
-    # Check for file existence; if not found, try the known shared tmp directory.
 
     # Work on a safe copy in a secure temporary directory
     original_file = local_file_path
diff --git a/app/tasks/finalize_document_storage.py b/app/tasks/finalize_document_storage.py
index c3f7b23e..05ad24e1 100644
--- a/app/tasks/finalize_document_storage.py
+++ b/app/tasks/finalize_document_storage.py
@@ -26,12 +26,14 @@ def finalize_document_storage(self, original_file: str, processed_file: str, met
     logger.info(f"[{task_id}] Finalizing document storage for {processed_file}")
     log_task_progress(task_id, "finalize_document_storage", "in_progress", f"Finalizing: {os.path.basename(processed_file)}", file_id=file_id)
     
-    # Get file_id from database if not provided
+    # Get file_id from database if not provided (fallback only, prefer passing file_id explicitly)
     if file_id is None:
         with SessionLocal() as db:
-            # Try to find by the original file path
+            # Only as a last resort, try to find by exact match on local_filename
+            # This should not be needed if file_id is passed correctly through the chain
+            tmp_path = os.path.join(settings.workdir, "tmp", os.path.basename(original_file))
             file_record = db.query(FileRecord).filter(
-                FileRecord.local_filename.like(f"%{os.path.basename(original_file)}%")
+                FileRecord.local_filename == tmp_path
             ).first()
             if file_record:
                 file_id = file_record.id
diff --git a/app/tasks/send_to_all.py b/app/tasks/send_to_all.py
index 465a7058..1f284c82 100644
--- a/app/tasks/send_to_all.py
+++ b/app/tasks/send_to_all.py
@@ -128,11 +128,13 @@ def send_to_all_destinations(self, file_path: str, use_validator=True, file_id:
     logger.info(f"[{task_id}] Sending {file_path} to all configured destinations")
     log_task_progress(task_id, "send_to_all_destinations", "in_progress", f"Distributing: {os.path.basename(file_path)}", file_id=file_id)
     
-    # Get file_id from database if not provided
+    # Get file_id from database if not provided (fallback only, prefer passing file_id explicitly)
     if file_id is None:
         with SessionLocal() as db:
+            # Only as a last resort, try to find by basename match
+            # This should not be needed if file_id is passed correctly through the chain
             file_record = db.query(FileRecord).filter(
-                FileRecord.local_filename.like(f"%{os.path.basename(file_path)}%")
+                FileRecord.local_filename == os.path.join(settings.workdir, "tmp", os.path.basename(file_path))
             ).first()
             if file_record:
                 file_id = file_record.id