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/lead_agent/agent.py

@@ -4,6 +4,7 @@ from langchain_core.runnables import RunnableConfig
 
 from src.agents.lead_agent.prompt import apply_prompt_template
 from src.agents.middlewares.clarification_middleware import ClarificationMiddleware
+from src.agents.middlewares.memory_middleware import MemoryMiddleware
 from src.agents.middlewares.thread_data_middleware import ThreadDataMiddleware
 from src.agents.middlewares.title_middleware import TitleMiddleware
 from src.agents.middlewares.uploads_middleware import UploadsMiddleware
@@ -175,6 +176,8 @@ Being proactive with task management demonstrates thoroughness and ensures all r
 # UploadsMiddleware should be after ThreadDataMiddleware to access thread_id
 # SummarizationMiddleware should be early to reduce context before other processing
 # TodoListMiddleware should be before ClarificationMiddleware to allow todo management
+# TitleMiddleware generates title after first exchange
+# MemoryMiddleware queues conversation for memory update (after TitleMiddleware)
 # ViewImageMiddleware should be before ClarificationMiddleware to inject image details before LLM
 # ClarificationMiddleware should be last to intercept clarification requests after model calls
 def _build_middlewares(config: RunnableConfig):
@@ -202,6 +205,9 @@ def _build_middlewares(config: RunnableConfig):
     # Add TitleMiddleware
     middlewares.append(TitleMiddleware())
 
+    # Add MemoryMiddleware (after TitleMiddleware)
+    middlewares.append(MemoryMiddleware())
+
     # Add ViewImageMiddleware only if the current model supports vision
     model_name = config.get("configurable", {}).get("model_name") or config.get("configurable", {}).get("model")
     from src.config import get_app_config