fix(memory): case-insensitive fact deduplication and positive reinforcement detection (#1804)

* fix(memory): case-insensitive fact deduplication and positive reinforcement detection

Two fixes to the memory system:

1. _fact_content_key() now lowercases content before comparison, preventing
   semantically duplicate facts like "User prefers Python" and "user prefers
   python" from being stored separately.

2. Adds detect_reinforcement() to MemoryMiddleware (closes #1719), mirroring
   detect_correction(). When users signal approval ("yes exactly", "perfect",
   "完全正确", etc.), the memory updater now receives reinforcement_detected=True
   and injects a hint prompting the LLM to record confirmed preferences and
   behaviors with high confidence.

   Changes across the full signal path:
   - memory_middleware.py: _REINFORCEMENT_PATTERNS + detect_reinforcement()
   - queue.py: reinforcement_detected field in ConversationContext and add()
   - updater.py: reinforcement_detected param in update_memory() and
     update_memory_from_conversation(); builds reinforcement_hint alongside
     the existing correction_hint

Tests: 11 new tests covering deduplication, hint injection, and signal
detection (Chinese + English patterns, window boundary, conflict with correction).

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

* fix(memory): address Copilot review comments on reinforcement detection

- Tighten _REINFORCEMENT_PATTERNS: remove 很好, require punctuation/end-of-string boundaries on remaining patterns, split this-is-good into stricter variants
- Suppress reinforcement_detected when correction_detected is true to avoid mixed-signal noise
- Use casefold() instead of lower() for Unicode-aware fact deduplication
- Add missing test coverage for reinforcement_detected OR merge and forwarding in queue

---------

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

backend/tests/test_memory_queue.py

@@ -47,4 +47,45 @@ def test_process_queue_forwards_correction_flag_to_updater() -> None:
         thread_id="thread-1",
         agent_name="lead_agent",
         correction_detected=True,
+        reinforcement_detected=False,
+    )
+
+
+def test_queue_add_preserves_existing_reinforcement_flag_for_same_thread() -> None:
+    queue = MemoryUpdateQueue()
+
+    with (
+        patch("deerflow.agents.memory.queue.get_memory_config", return_value=_memory_config(enabled=True)),
+        patch.object(queue, "_reset_timer"),
+    ):
+        queue.add(thread_id="thread-1", messages=["first"], reinforcement_detected=True)
+        queue.add(thread_id="thread-1", messages=["second"], reinforcement_detected=False)
+
+    assert len(queue._queue) == 1
+    assert queue._queue[0].messages == ["second"]
+    assert queue._queue[0].reinforcement_detected is True
+
+
+def test_process_queue_forwards_reinforcement_flag_to_updater() -> None:
+    queue = MemoryUpdateQueue()
+    queue._queue = [
+        ConversationContext(
+            thread_id="thread-1",
+            messages=["conversation"],
+            agent_name="lead_agent",
+            reinforcement_detected=True,
+        )
+    ]
+    mock_updater = MagicMock()
+    mock_updater.update_memory.return_value = True
+
+    with patch("deerflow.agents.memory.updater.MemoryUpdater", return_value=mock_updater):
+        queue._process_queue()
+
+    mock_updater.update_memory.assert_called_once_with(
+        messages=["conversation"],
+        thread_id="thread-1",
+        agent_name="lead_agent",
+        correction_detected=False,
+        reinforcement_detected=True,
     )