From 8c034e6e32ecd3b0902bc1910585a87183d7ca39 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Wed, 25 Feb 2026 14:34:46 +0000
Subject: [PATCH 1/2] Initial plan


From db581ba355834a514606717fb5f8f9673fc0dce6 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Wed, 25 Feb 2026 14:37:56 +0000
Subject: [PATCH 2/2] fix(database): add runtime migrations for ocr_text,
 ai_metadata, document_title columns

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
---
 app/database.py        | 19 ++++++++++++++++++
 tests/test_database.py | 45 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 64 insertions(+)

diff --git a/app/database.py b/app/database.py
index 8a73f71b..8272a973 100644
--- a/app/database.py
+++ b/app/database.py
@@ -103,6 +103,25 @@ def _run_schema_migrations(engine: Any) -> None:
                 conn.execute(text("ALTER TABLE files ADD COLUMN duplicate_of_id INTEGER"))
             logger.info("Migration complete: 'duplicate_of_id' column added to files")
 
+        # Migration: Add search/OCR fields to files table
+        if "ocr_text" not in columns:
+            logger.info("Migrating files: adding 'ocr_text' column")
+            with engine.begin() as conn:
+                conn.execute(text("ALTER TABLE files ADD COLUMN ocr_text TEXT"))
+            logger.info("Migration complete: 'ocr_text' column added to files")
+
+        if "ai_metadata" not in columns:
+            logger.info("Migrating files: adding 'ai_metadata' column")
+            with engine.begin() as conn:
+                conn.execute(text("ALTER TABLE files ADD COLUMN ai_metadata TEXT"))
+            logger.info("Migration complete: 'ai_metadata' column added to files")
+
+        if "document_title" not in columns:
+            logger.info("Migrating files: adding 'document_title' column")
+            with engine.begin() as conn:
+                conn.execute(text("ALTER TABLE files ADD COLUMN document_title VARCHAR"))
+            logger.info("Migration complete: 'document_title' column added to files")
+
         # Migration: Drop unique index on filehash to allow duplicate records
         try:
             indexes = inspector.get_indexes("files")
diff --git a/tests/test_database.py b/tests/test_database.py
index 008b1d7e..4c11b57f 100644
--- a/tests/test_database.py
+++ b/tests/test_database.py
@@ -186,6 +186,48 @@ class TestSchemaMigrations:
         assert "duplicate_of_id" in columns
         assert columns["duplicate_of_id"]["type"].__class__.__name__ in ("INTEGER", "Integer")
 
+        assert "ocr_text" in columns
+        assert "ai_metadata" in columns
+        assert "document_title" in columns
+
+        engine.dispose()
+
+    def test_migration_adds_search_fields(self, tmp_path):
+        """Test that _run_schema_migrations adds ocr_text, ai_metadata, document_title to files table."""
+        from sqlalchemy import create_engine, text
+
+        from app.database import _run_schema_migrations
+
+        # Create a database with the old schema (no search fields)
+        db_path = str(tmp_path / "migration_search_fields_test.db")
+        engine = create_engine(f"sqlite:///{db_path}")
+        with engine.begin() as conn:
+            conn.execute(
+                text(
+                    "CREATE TABLE files ("
+                    "id INTEGER PRIMARY KEY, "
+                    "filename VARCHAR, "
+                    "filehash VARCHAR, "
+                    "original_file_path VARCHAR, "
+                    "processed_file_path VARCHAR, "
+                    "is_duplicate BOOLEAN DEFAULT FALSE NOT NULL, "
+                    "duplicate_of_id INTEGER)"
+                )
+            )
+
+        # Run migrations
+        _run_schema_migrations(engine)
+
+        # Verify search columns were added
+        from sqlalchemy import inspect
+
+        inspector = inspect(engine)
+        columns = {col["name"]: col for col in inspector.get_columns("files")}
+
+        assert "ocr_text" in columns
+        assert "ai_metadata" in columns
+        assert "document_title" in columns
+
         engine.dispose()
 
     def test_migration_drops_unique_filehash_index(self, tmp_path):
@@ -299,6 +341,9 @@ class TestSchemaMigrations:
         assert "processed_file_path" in files_columns
         assert "is_duplicate" in files_columns
         assert "duplicate_of_id" in files_columns
+        assert "ocr_text" in files_columns
+        assert "ai_metadata" in files_columns
+        assert "document_title" in files_columns
 
         engine.dispose()