fix(memory): address critical bugs from multi-agent review

Bug Fixes:
- Remove singleton pattern from consolidation/reflection services to
  prevent stale database session bugs (session is now passed per-request)
- Add LRU eviction to MemoryToolService._working dict (max 1000 sessions)
  to prevent unbounded memory growth
- Replace O(n) list.remove() with O(1) OrderedDict.move_to_end() in
  RetrievalCache for better performance under load
- Use deque with maxlen for metrics histograms to prevent unbounded
  memory growth (circular buffer with 10k max samples)
- Use full UUID for checkpoint IDs instead of 8-char prefix to avoid
  collision risk at scale (birthday paradox at ~50k checkpoints)

Test Updates:
- Update checkpoint test to expect 36-char UUID
- Update reflection singleton tests to expect new factory behavior
- Add reset_memory_reflection() no-op for backwards compatibility

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/tests/unit/services/memory/reflection/test_service.py

@@ -738,26 +738,32 @@ class TestComprehensiveReflection:
         assert "Episodes analyzed" in summary
 
 
-class TestSingleton:
-    """Tests for singleton pattern."""
+class TestFactoryFunction:
+    """Tests for factory function behavior.
 
-    async def test_get_memory_reflection_returns_singleton(
+    Note: The singleton pattern was removed to avoid stale database session bugs.
+    Each call now creates a fresh instance, which is safer for request-scoped usage.
+    """
+
+    async def test_get_memory_reflection_creates_new_instance(
         self,
         mock_session: MagicMock,
     ) -> None:
-        """Should return same instance."""
+        """Should create new instance each call (no singleton for session safety)."""
         r1 = await get_memory_reflection(mock_session)
         r2 = await get_memory_reflection(mock_session)
 
-        assert r1 is r2
-
-    async def test_reset_creates_new_instance(
-        self,
-        mock_session: MagicMock,
-    ) -> None:
-        """Should create new instance after reset."""
-        r1 = await get_memory_reflection(mock_session)
-        await reset_memory_reflection()
-        r2 = await get_memory_reflection(mock_session)
-
+        # Different instances to avoid stale session issues
+        assert r1 is not r2
+
+    async def test_reset_is_no_op(
+        self,
+        mock_session: MagicMock,
+    ) -> None:
+        """Reset should be a no-op (kept for API compatibility)."""
+        r1 = await get_memory_reflection(mock_session)
+        await reset_memory_reflection()  # Should not raise
+        r2 = await get_memory_reflection(mock_session)
+
+        # Still creates new instances (reset is no-op now)
         assert r1 is not r2