From d7a6cadbe2e2d69be9a67bb46e8150bad10207fc Mon Sep 17 00:00:00 2001
From: red person <redpersoncoding@gmail.com>
Date: Wed, 3 Jun 2026 08:07:00 +0300
Subject: [PATCH] Skip invalid memory extractor rows (#1535)

---
 services/memory/memory_extractor.py | 10 ++++++++--
 tests/test_memory_extractor_rows.py | 25 +++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 2 deletions(-)
 create mode 100644 tests/test_memory_extractor_rows.py

diff --git a/services/memory/memory_extractor.py b/services/memory/memory_extractor.py
index f31dc7c..32412e6 100644
--- a/services/memory/memory_extractor.py
+++ b/services/memory/memory_extractor.py
@@ -34,7 +34,7 @@ def _fingerprint_entries(entries) -> str:
     only on id+text+category. Any add/edit/delete invalidates it."""
     items = sorted(
         (str(e.get("id", "")), e.get("text", ""), e.get("category", ""))
-        for e in entries
+        for e in _memory_dicts(entries)
     )
     h = hashlib.sha256()
     for triple in items:
@@ -42,6 +42,12 @@ def _fingerprint_entries(entries) -> str:
     return h.hexdigest()
 
 
+def _memory_dicts(entries):
+    for entry in entries or []:
+        if isinstance(entry, dict):
+            yield entry
+
+
 def _load_tidy_state(memory_manager) -> dict:
     path = _tidy_state_path(memory_manager)
     try:
@@ -211,7 +217,7 @@ def _is_text_duplicate(new_text: str, existing: list, threshold: float = 0.6) ->
     new_tokens = set(new_text.lower().split())
     if not new_tokens:
         return False
-    for entry in existing:
+    for entry in _memory_dicts(existing):
         old_tokens = set(entry.get("text", "").lower().split())
         if not old_tokens:
             continue
diff --git a/tests/test_memory_extractor_rows.py b/tests/test_memory_extractor_rows.py
new file mode 100644
index 0000000..7ff8d47
--- /dev/null
+++ b/tests/test_memory_extractor_rows.py
@@ -0,0 +1,25 @@
+from services.memory import memory_extractor
+
+
+def test_fingerprint_entries_skips_invalid_rows():
+    value = memory_extractor._fingerprint_entries([
+        {"id": "1", "text": "User likes small PRs.", "category": "preference"},
+        "bad-row",
+        None,
+    ])
+
+    expected = memory_extractor._fingerprint_entries([
+        {"id": "1", "text": "User likes small PRs.", "category": "preference"},
+    ])
+
+    assert value == expected
+
+
+def test_duplicate_check_skips_invalid_rows():
+    existing = [
+        "bad-row",
+        {"text": "User likes small pull requests."},
+        None,
+    ]
+
+    assert memory_extractor._is_text_duplicate("User likes small pull requests.", existing)