fix(memory): ignore malformed history entries (#4315)

nanobot/agent/memory.py

@@ -61,6 +61,7 @@ class MemoryStore:
         self._cursor_file = self.memory_dir / ".cursor"
         self._dream_cursor_file = self.memory_dir / ".dream_cursor"
         self._corruption_logged = False  # rate-limit non-int cursor warning
+        self._malformed_entry_logged = False  # rate-limit bad history shape warning
         self._oversize_logged = False  # rate-limit oversized-entry warning
         self._append_lock = threading.Lock()  # serialize cursor allocation + append
         self._git = GitStore(workspace, tracked_files=[
@@ -295,8 +296,9 @@ class MemoryStore:
         return value
 
     def _iter_valid_entries(self) -> Iterator[tuple[dict[str, Any], int]]:
-        """Yield ``(entry, cursor)`` for entries with int cursors; warn once on corruption."""
+        """Yield ``(entry, cursor)`` for well-formed entries; warn once on corruption."""
         poisoned: Any = None
+        malformed_cursor: int | None = None
         for entry in self._read_entries():
             raw = entry.get("cursor")
             if raw is None:
@@ -305,6 +307,9 @@ class MemoryStore:
             if cursor is None:
                 poisoned = raw
                 continue
+            if not self._valid_history_payload(entry):
+                malformed_cursor = cursor
+                continue
             yield entry, cursor
         if poisoned is not None and not self._corruption_logged:
             self._corruption_logged = True
@@ -313,6 +318,22 @@ class MemoryStore:
                 "Usually caused by an external writer; further occurrences suppressed.",
                 poisoned,
             )
+        if malformed_cursor is not None and not self._malformed_entry_logged:
+            self._malformed_entry_logged = True
+            logger.warning(
+                "history.jsonl contains a malformed entry at cursor {}; dropping it. "
+                "Usually caused by an external writer; further occurrences suppressed.",
+                malformed_cursor,
+            )
+
+    @staticmethod
+    def _valid_history_payload(entry: dict[str, Any]) -> bool:
+        if not isinstance(entry.get("timestamp"), str):
+            return False
+        if not isinstance(entry.get("content"), str):
+            return False
+        session_key = entry.get("session_key")
+        return session_key is None or isinstance(session_key, str)
 
     def _next_cursor(self) -> int:
         """Read the current cursor counter and return the next value."""

tests/agent/test_dream.py

@@ -87,6 +87,21 @@ class TestBuildDreamPrompt:
         assert "entry-21" in next_prompt
         assert "entry-25" in next_prompt
 
+    def test_skips_malformed_history_entries(self, store):
+        """Dream prompt building should tolerate externally corrupted JSONL rows."""
+        store.history_file.write_text(
+            '{"cursor": 1, "timestamp": "2026-04-01 10:00"}\n'
+            '{"cursor": 2, "timestamp": "2026-04-01 10:01", "content": "usable memory"}\n',
+            encoding="utf-8",
+        )
+
+        result = store.build_dream_prompt()
+
+        assert result is not None
+        prompt, cursor = result
+        assert cursor == 2
+        assert "usable memory" in prompt
+
     def test_dream_prompt_consumes_consolidator_attribute_tags(self):
         prompt = render_template(
             "agent/dream.md",

tests/agent/test_memory_store.py

@@ -171,6 +171,23 @@ class TestHistoryWithCursor:
         entries = store.read_unprocessed_history(since_cursor=0)
         assert [e["cursor"] for e in entries] == [2, 3]
 
+    def test_read_unprocessed_skips_malformed_history_payloads(self, store):
+        """Externally edited JSONL can keep an int cursor but miss required payload fields."""
+        store.history_file.write_text(
+            '{"cursor": 1, "timestamp": "2026-04-01 10:00", "content": "valid"}\n'
+            '{"cursor": 2, "timestamp": "2026-04-01 10:01"}\n'
+            '{"cursor": 3, "content": "missing timestamp"}\n'
+            '{"cursor": 4, "timestamp": "2026-04-01 10:03", "content": 123}\n'
+            '{"cursor": 5, "timestamp": "2026-04-01 10:04", "content": "bad session", "session_key": 42}\n'
+            '{"cursor": 6, "timestamp": "2026-04-01 10:05", "content": "also valid", "session_key": "telegram:chat-1"}\n',
+            encoding="utf-8",
+        )
+
+        entries = store.read_unprocessed_history(since_cursor=0)
+
+        assert [e["cursor"] for e in entries] == [1, 6]
+        assert [e["content"] for e in entries] == ["valid", "also valid"]
+
     def test_next_cursor_falls_back_when_last_entry_has_no_cursor(self, store):
         """Regression: _next_cursor should not KeyError on entries without cursor."""
         store.history_file.write_text(