feat(llm): support incremental Responses WebSocket transport

artemis/config/llm.py

@@ -62,6 +62,9 @@ class LLM(BaseModel):
     provider: LLMProvider = "openai"
     model: str = Field(default_factory=lambda: settings.OPENAI_MODEL)
     api_base: str | None = None
+    transport: Literal["http", "websocket"] = Field(
+        default_factory=lambda: settings.OPENAI_TRANSPORT
+    )
     timeout: float = Field(default_factory=lambda: settings.OPENAI_TIMEOUT_SECONDS, gt=0)
     max_retries: int = Field(default_factory=lambda: settings.OPENAI_MAX_RETRIES, ge=0)
     max_tokens: int | None = Field(default=None, gt=0)