feat: add global memory mechanism for personalized conversations

Implement a memory system that stores user context and conversation history
in memory.json, uses LLM to summarize conversations, and injects relevant
context into system prompts for personalized responses.

Key components:
- MemoryConfig for configuration management
- MemoryUpdateQueue with debounce for batch processing
- MemoryUpdater for LLM-based memory extraction
- MemoryMiddleware to queue conversations after agent execution
- Memory injection into lead agent system prompt

Note: Add memory section to config.yaml to enable (see config.example.yaml)

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

backend/src/agents/memory/__init__.py

@@ -0,0 +1,44 @@
+"""Memory module for DeerFlow.
+
+This module provides a global memory mechanism that:
+- Stores user context and conversation history in memory.json
+- Uses LLM to summarize and extract facts from conversations
+- Injects relevant memory into system prompts for personalized responses
+"""
+
+from src.agents.memory.prompt import (
+    FACT_EXTRACTION_PROMPT,
+    MEMORY_UPDATE_PROMPT,
+    format_conversation_for_update,
+    format_memory_for_injection,
+)
+from src.agents.memory.queue import (
+    ConversationContext,
+    MemoryUpdateQueue,
+    get_memory_queue,
+    reset_memory_queue,
+)
+from src.agents.memory.updater import (
+    MemoryUpdater,
+    get_memory_data,
+    reload_memory_data,
+    update_memory_from_conversation,
+)
+
+__all__ = [
+    # Prompt utilities
+    "MEMORY_UPDATE_PROMPT",
+    "FACT_EXTRACTION_PROMPT",
+    "format_memory_for_injection",
+    "format_conversation_for_update",
+    # Queue
+    "ConversationContext",
+    "MemoryUpdateQueue",
+    "get_memory_queue",
+    "reset_memory_queue",
+    # Updater
+    "MemoryUpdater",
+    "get_memory_data",
+    "reload_memory_data",
+    "update_memory_from_conversation",
+]