From 441905bc13b6c27e4f4ddc1016151c6b49a1ca87 Mon Sep 17 00:00:00 2001
From: Paulo Victor Cordeiro <146781332+pvcordeiro@users.noreply.github.com>
Date: Wed, 3 Jun 2026 00:14:10 +0100
Subject: [PATCH] fix: guard AI tidy verdict against non-string LLM output
 (#1486)

The AI document-tidy endpoint parses verdicts from LLM JSON output
and calls .lower().strip() directly. If the model returns null or a
non-string element, this crashes with AttributeError. Coerce to str
so malformed output is treated as 'keep' instead of crashing.
---
 routes/document_routes.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/routes/document_routes.py b/routes/document_routes.py
index 282e358..baf84b2 100644
--- a/routes/document_routes.py
+++ b/routes/document_routes.py
@@ -901,7 +901,7 @@ def setup_document_routes(session_manager, upload_handler=None) -> APIRouter:
             for i, doc in enumerate(batch):
                 if i >= len(verdicts):
                     break
-                verdict = verdicts[i].lower().strip()
+                verdict = str(verdicts[i] or "").lower().strip()
                 if verdict == "junk":
                     doc.tidy_verdict = "junk"
                     db.delete(doc)