Fix: use langgraph.prebuilt.create_react_agent for state_modifier support

langchain.agents.create_agent does not accept state_modifier or checkpointer;
those are LangGraph-only params available on create_react_agent.

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

blueprints/conversation/agents.py

@@ -3,9 +3,9 @@ from typing import cast
 
 import httpx
 from dotenv import load_dotenv
-from langchain.agents import create_agent
 from langchain.chat_models import BaseChatModel
 from langchain.tools import tool
+from langgraph.prebuilt import create_react_agent
 from langchain_core.messages import SystemMessage
 from langchain_core.runnables import RunnableConfig, RunnableLambda
 from langchain_openai import ChatOpenAI
@@ -1264,7 +1264,7 @@ main_agent = None
 def build_agent(checkpointer=None):
     """Compile the LangGraph agent, optionally with a checkpointer."""
     global main_agent
-    main_agent = create_agent(
+    main_agent = create_react_agent(
         model=model_with_fallback,
         tools=tools,
         state_modifier=_inject_system_prompt,