From 7d1e2c316407b86c088e3c0ffa711ee465012bcb Mon Sep 17 00:00:00 2001
From: stumpylog <797416+stumpylog@users.noreply.github.com>
Date: Thu, 13 Aug 2026 14:09:10 -0700
Subject: [PATCH] Cheap defensive stuff but I'm not going to try and cover a
 malformed row everywhere

---
 src/paperless_ai/indexing.py | 8 ++++++--
 src/paperless_ai/taxonomy.py | 5 ++++-
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/src/paperless_ai/indexing.py b/src/paperless_ai/indexing.py
index 3041abcda..b36a71db7 100644
--- a/src/paperless_ai/indexing.py
+++ b/src/paperless_ai/indexing.py
@@ -695,7 +695,10 @@ def retrieve_similar_nodes(
     filtered = []
     for node in results:
         document_id = node.metadata.get("document_id")
-        if document_id is None:
+        if document_id is None:  # pragma: no cover
+            # Every node the indexing pipeline builds always sets
+            # document_id; this guards a malformed/partial vec0 row that
+            # shouldn't occur given the current schema.
             continue
         if str(document_id) not in allowed_document_ids:
             continue
@@ -707,7 +710,8 @@ def _node_document_ids(nodes: list["NodeWithScore"]) -> list[int]:
     document_ids: list[int] = []
     for node in nodes:
         document_id = node.metadata.get("document_id")
-        if document_id is None:
+        if document_id is None:  # pragma: no cover
+            # See the matching guard in retrieve_similar_nodes() above.
             continue
         try:
             document_ids.append(int(document_id))
diff --git a/src/paperless_ai/taxonomy.py b/src/paperless_ai/taxonomy.py
index b9412337c..f9a0bd907 100644
--- a/src/paperless_ai/taxonomy.py
+++ b/src/paperless_ai/taxonomy.py
@@ -108,7 +108,10 @@ def _node_document_weights(nodes: list["NodeWithScore"]) -> dict[int, float]:
     weights: dict[int, float] = defaultdict(float)
     for node in nodes:
         document_id = node.metadata.get("document_id")
-        if document_id is None:
+        if document_id is None:  # pragma: no cover
+            # Every node the indexing pipeline builds always sets
+            # document_id; this guards a malformed/partial vec0 row that
+            # shouldn't occur given the current schema.
             continue
         try:
             weights[int(document_id)] += float(node.score or 0.0)