feat(2.0): Phase 6c — eingebauter OpenAI-Gateway (model:auto) statt LiteLLM

LiteLLM baut auf Python 3.14 nicht (orjson-Pin ohne cp314-Wheel). Stattdessen
eingebauter Gateway in MC2: routers/gateway_proxy.py (/v1/chat/completions,
/completions, /models) + services/router_logic.py (Komplexitaets-Routing
fast<->heavy, Streaming-Passthrough). gateway.py/routing.py/connect.py auf
builtin umgestellt (Endpunkt = MC :PORT/v1). Gleicher OpenAI-Vertrag,
spaeter gegen LiteLLM austauschbar.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

backend/routers/routing.py

@@ -1,7 +1,6 @@
-"""Routing-Endpoints: Gateway-Übersicht (welcher Alias = fast/heavy/…) + Mapping setzen."""
+"""Routing-Endpoint: zeigt den eingebauten Gateway (model:auto fast↔heavy)."""
 
-from fastapi import APIRouter, HTTPException
-from pydantic import BaseModel
+from fastapi import APIRouter
 
 from services import gateway
 
@@ -11,18 +10,3 @@ router = APIRouter(prefix="/api")
 @router.get("/routing")
 def routing() -> dict:
     return {**gateway.routing_summary(), "gateway_reachable": gateway.gateway_reachable()}
-
-
-class RouteReq(BaseModel):
-    name: str          # Gateway-Modellname, z.B. "fast" / "heavy" / "vision" / "coder"
-    target_alias: str  # llama-swap-Alias, der bedient wird
-    api_base: str = "http://127.0.0.1:8080/v1"
-
-
-@router.put("/routing/route")
-def set_route(req: RouteReq) -> dict:
-    try:
-        gateway.set_route(req.name, req.target_alias, api_base=req.api_base)
-    except Exception as exc:  # noqa: BLE001
-        raise HTTPException(500, str(exc))
-    return {"ok": True}