Use Responses API with Luna by default

backend/app/agent/agent.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from agent_framework import Agent
-from agent_framework.openai import OpenAIChatCompletionClient
+from agent_framework.openai import OpenAIChatClient
 
 from app.config import settings
 from app.agent.tools import TOOLS
@@ -83,7 +83,9 @@ Generative UI — render tools:
 
 
 def build_agent() -> Agent:
-    client = OpenAIChatCompletionClient(
+    # Use the Responses API for every configured model. It preserves one tool
+    # transport across model changes and supports Luna's tool-result turns.
+    client = OpenAIChatClient(
         api_key=settings.OPENAI_API_KEY,
         model=settings.AGENT_MODEL,
     )