Hitonabi
45d635afae
Nach dem Hirn-Wechsel auf fast (Qwen3.6) zeigte der Wächter noch auf "hermes" (Hermes-4-14B) -> er haette das aus dem Warm-Set entfernte Modell wieder geladen. warmer._brain_model() liest jetzt Hermes' model.default (Fallback fast); Startup-Warmup BRAINS default "fast". Passt sich kuenftigen Hirn-Wechseln automatisch an. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
91 lines
3.0 KiB
Python
91 lines
3.0 KiB
Python
"""
|
|
Mission Control 2.0 — dünner FastAPI-Einstieg.
|
|
|
|
Hängt die Router ein, liefert (in Prod) das gebaute React-Frontend aus und
|
|
setzt eine no-cache-Middleware. Im Dev läuft das Frontend über den Vite-Dev-
|
|
Server (proxyt /api hierher), daher CORS für localhost offen.
|
|
"""
|
|
|
|
import asyncio
|
|
import logging
|
|
import os
|
|
from contextlib import asynccontextmanager
|
|
|
|
from fastapi import FastAPI
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from fastapi.responses import FileResponse
|
|
from fastapi.staticfiles import StaticFiles
|
|
from starlette.requests import Request
|
|
|
|
from config import FRONTEND_DIST, VERSION
|
|
from routers import agent, connect, gateway_proxy, health, maintenance, memory, models, routing, system
|
|
from services import warmer
|
|
|
|
# Zentrales Logging — Level via MC_LOG_LEVEL (INFO default). Eine Konfiguration
|
|
# für alle Module (logging.getLogger(__name__)).
|
|
logging.basicConfig(
|
|
level=os.environ.get("MC_LOG_LEVEL", "INFO").upper(),
|
|
format="%(asctime)s %(levelname)-7s %(name)s: %(message)s",
|
|
)
|
|
log = logging.getLogger(__name__)
|
|
|
|
@asynccontextmanager
|
|
async def lifespan(app: FastAPI):
|
|
"""Hintergrund-Tasks an den App-Lebenszyklus binden: Re-Warm-Wächter fürs Agent-Hirn."""
|
|
task = asyncio.create_task(warmer.rewarm_loop()) if warmer.ENABLED else None
|
|
if task:
|
|
log.info("Hirn-Re-Warm-Wächter aktiv (Intervall %ss, Hirn dynamisch aus Hermes-Config)", warmer.INTERVAL)
|
|
try:
|
|
yield
|
|
finally:
|
|
if task:
|
|
task.cancel()
|
|
|
|
|
|
app = FastAPI(title="Mission Control 2.0", version=VERSION, lifespan=lifespan)
|
|
|
|
# Dev: Vite-Dev-Server (5173) ruft das Backend per /api auf.
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=["http://localhost:5173", "http://127.0.0.1:5173"],
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
|
|
@app.middleware("http")
|
|
async def no_cache(request: Request, call_next):
|
|
resp = await call_next(request)
|
|
if request.url.path.startswith("/api"):
|
|
resp.headers["Cache-Control"] = "no-cache"
|
|
return resp
|
|
|
|
|
|
app.include_router(health.router)
|
|
app.include_router(models.router)
|
|
app.include_router(routing.router)
|
|
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)
|
|
app.include_router(maintenance.router)
|
|
|
|
|
|
# Prod: gebautes Frontend ausliefern (falls vorhanden). SPA-Fallback auf index.html.
|
|
if FRONTEND_DIST.exists():
|
|
app.mount("/assets", StaticFiles(directory=FRONTEND_DIST / "assets"), name="assets")
|
|
|
|
@app.get("/{full_path:path}")
|
|
def spa(full_path: str):
|
|
# Falls die Datei direkt in FRONTEND_DIST liegt (z.B. manifest.webmanifest, favicon.ico), liefere sie aus
|
|
target = FRONTEND_DIST / full_path
|
|
if target.is_file():
|
|
return FileResponse(target)
|
|
|
|
index = FRONTEND_DIST / "index.html"
|
|
if index.exists():
|
|
return FileResponse(index)
|
|
return {"detail": "frontend not built"}
|
|
|