feat: (maybe) stop response when new user message

If we get a new message before the LLM is done responding, interrupt it.

ref: N25B-452

src/control_backend/core/config.py

@@ -117,6 +117,7 @@ class LLMSettings(BaseModel):
 
     local_llm_url: str = "http://localhost:1234/v1/chat/completions"
     local_llm_model: str = "gpt-oss"
+    api_key: str = ""
     chat_temperature: float = 1.0
     code_temperature: float = 0.3
     n_parallel: int = 4