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/app.py

@@ -13,7 +13,7 @@ from fastapi.staticfiles import StaticFiles
 from starlette.requests import Request
 
 from config import FRONTEND_DIST, VERSION
-from routers import agent, connect, health, memory, models, routing, system
+from routers import agent, connect, gateway_proxy, health, memory, models, routing, system
 
 app = FastAPI(title="Mission Control 2.0", version=VERSION)
 
@@ -41,6 +41,7 @@ app.include_router(system.router)
 app.include_router(connect.router)
 app.include_router(memory.router)
 app.include_router(agent.router)
+app.include_router(gateway_proxy.router)  # OpenAI-kompatibler /v1-Gateway (model:auto)
 
 
 # Prod: gebautes Frontend ausliefern (falls vorhanden). SPA-Fallback auf index.html.