fix: Memory update system has cache corruption, data loss, and thread-safety bugs (#2251)

* fix(memory): cache corruption, thread-safety, and caller mutation bugs

Bug 1 (updater.py): deep-copy current_memory before passing to
_apply_updates() so a subsequent save() failure cannot leave a
partially-mutated object in the storage cache.

Bug 3 (storage.py): add _cache_lock (threading.Lock) to
FileMemoryStorage and acquire it around every read/write of
_memory_cache, fixing concurrent-access races between the background
timer thread and HTTP reload calls.

Bug 4 (storage.py): replace in-place mutation
  memory_data["lastUpdated"] = ...
with a shallow copy
  memory_data = {**memory_data, "lastUpdated": ...}
so save() no longer silently modifies the caller's dict.

Regression tests added for all three bugs in test_memory_storage.py
and test_memory_updater.py.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* style: format test_memory_updater.py with ruff

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* style: remove stale bug-number labels from code comments and docstrings

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

backend/packages/harness/deerflow/agents/memory/storage.py

@@ -67,6 +67,8 @@ class FileMemoryStorage(MemoryStorage):
         # Per-agent memory cache: keyed by agent_name (None = global)
         # Value: (memory_data, file_mtime)
         self._memory_cache: dict[str | None, tuple[dict[str, Any], float | None]] = {}
+        # Guards all reads and writes to _memory_cache across concurrent callers.
+        self._cache_lock = threading.Lock()
 
     def _validate_agent_name(self, agent_name: str) -> None:
         """Validate that the agent name is safe to use in filesystem paths.
@@ -115,14 +117,17 @@ class FileMemoryStorage(MemoryStorage):
         except OSError:
             current_mtime = None
 
-        cached = self._memory_cache.get(agent_name)
+        with self._cache_lock:
+            cached = self._memory_cache.get(agent_name)
+            if cached is not None and cached[1] == current_mtime:
+                return cached[0]
 
-        if cached is None or cached[1] != current_mtime:
-            memory_data = self._load_memory_from_file(agent_name)
+        memory_data = self._load_memory_from_file(agent_name)
+
+        with self._cache_lock:
             self._memory_cache[agent_name] = (memory_data, current_mtime)
-            return memory_data
 
-        return cached[0]
+        return memory_data
 
     def reload(self, agent_name: str | None = None) -> dict[str, Any]:
         """Reload memory data from file, forcing cache invalidation."""
@@ -134,7 +139,8 @@ class FileMemoryStorage(MemoryStorage):
         except OSError:
             mtime = None
 
-        self._memory_cache[agent_name] = (memory_data, mtime)
+        with self._cache_lock:
+            self._memory_cache[agent_name] = (memory_data, mtime)
         return memory_data
 
     def save(self, memory_data: dict[str, Any], agent_name: str | None = None) -> bool:
@@ -143,7 +149,10 @@ class FileMemoryStorage(MemoryStorage):
 
         try:
             file_path.parent.mkdir(parents=True, exist_ok=True)
-            memory_data["lastUpdated"] = utc_now_iso_z()
+            # Shallow-copy before adding lastUpdated so the caller's dict is not
+            # mutated as a side-effect, and the cache reference is not silently
+            # updated before the file write succeeds.
+            memory_data = {**memory_data, "lastUpdated": utc_now_iso_z()}
 
             temp_path = file_path.with_suffix(f".{uuid.uuid4().hex}.tmp")
             with open(temp_path, "w", encoding="utf-8") as f:
@@ -156,7 +165,8 @@ class FileMemoryStorage(MemoryStorage):
             except OSError:
                 mtime = None
 
-            self._memory_cache[agent_name] = (memory_data, mtime)
+            with self._cache_lock:
+                self._memory_cache[agent_name] = (memory_data, mtime)
             logger.info("Memory saved to %s", file_path)
             return True
         except OSError as e:

backend/packages/harness/deerflow/agents/memory/updater.py

@@ -3,6 +3,7 @@
 import asyncio
 import atexit
 import concurrent.futures
+import copy
 import json
 import logging
 import math
@@ -380,7 +381,9 @@ class MemoryUpdater:
             response_text = "\n".join(lines[1:-1] if lines[-1] == "```" else lines[1:])
 
         update_data = json.loads(response_text)
-        updated_memory = self._apply_updates(current_memory, update_data, thread_id)
+        # Deep-copy before in-place mutation so a subsequent save() failure
+        # cannot corrupt the still-cached original object reference.
+        updated_memory = self._apply_updates(copy.deepcopy(current_memory), update_data, thread_id)
         updated_memory = _strip_upload_mentions_from_memory(updated_memory)
         return get_memory_storage().save(updated_memory, agent_name)