feat(2.0): W8 — Wartung (OS/Engine/Modell-Updates, Restart, Reboot, Logs)

services/maintenance.py + routers/maintenance.py: updates-Badge (apt/Engine-
Release/dyn. Modell-Upgrades via discover), os-update + engine-update als
jobengine-Jobs, system-/user-aware Restart (llama-swap via sudo -n NOPASSWD),
reboot, logs (journalctl). Frontend: Wartungs-Block in SystemView mit Badge,
Buttons + Modell-Upgrade-Vorschlaegen. Passwortfrei (sudo -n).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
2026-06-25 17:43:53 +02:00
parent 2ea3d01b58
commit 1f391644ca
9 changed files with 455 additions and 190 deletions
+2 -1
View File
@@ -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, gateway_proxy, health, memory, models, routing, system
from routers import agent, connect, gateway_proxy, health, maintenance, memory, models, routing, system
app = FastAPI(title="Mission Control 2.0", version=VERSION)
@@ -42,6 +42,7 @@ 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.
+1 -1
View File
@@ -52,7 +52,7 @@ PORT = int(os.environ.get("MC_PORT", "9000"))
FRONTEND_DIST = Path(os.environ.get("MC_FRONTEND_DIST", str(Path(__file__).resolve().parent.parent / "frontend" / "dist")))
# Version (Phase 0 — Greenfield-Skeleton).
VERSION = "2.0.0-w1"
VERSION = "2.0.0-w8"
# Gemeinsame YAML-Instanz (preserve_quotes hält Kommentare/Quotes in config.yaml).
yaml = YAML()
+45
View File
@@ -0,0 +1,45 @@
"""Wartungs-Endpoints: Update-Badge, OS-/Engine-Update, Reboot, Restart, Logs."""
from fastapi import APIRouter, HTTPException
from pydantic import BaseModel
from services import maintenance
router = APIRouter(prefix="/api")
@router.get("/maintenance/updates")
def updates() -> dict:
return maintenance.updates()
@router.post("/maintenance/os-update")
def os_update() -> dict:
return {"job_id": maintenance.os_update_job()}
@router.post("/maintenance/engine-update")
def engine_update() -> dict:
job = maintenance.engine_update_job()
if not job:
raise HTTPException(400, "Kein Engine-Update-Befehl gesetzt (MC_ENGINE_UPDATE_CMD).")
return {"job_id": job}
@router.post("/maintenance/reboot")
def reboot() -> dict:
return maintenance.reboot()
class RestartReq(BaseModel):
service: str
@router.post("/maintenance/restart")
def restart(body: RestartReq) -> dict:
return maintenance.restart_service(body.service)
@router.get("/maintenance/logs")
def logs(service: str, lines: int = 200) -> dict:
return maintenance.logs(service, lines)
+127
View File
@@ -0,0 +1,127 @@
"""
Wartung: Updates (OS/Engine/Modelle), Dienst-Neustart (system- vs user-aware),
Reboot, Logs. Portiert/modernisiert aus Mission Control v1 (routers/maintenance.py).
Passwortfrei über NOPASSWD-Whitelist (sudo -n). OS-Update/Reboot brauchen einmalig
erweiterte sudoers (siehe docs/BEDIENUNG.md). Lange Ops laufen als jobengine-Job.
"""
import os
import subprocess
import time
from datetime import datetime
import httpx
import psutil
from services import discover, jobengine, llamaswap
# System-Dienste (root, via sudo -n NOPASSWD) vs. User-Dienste (systemctl --user).
SYSTEM_SERVICES = {"llama-swap"}
USER_SERVICES = {"mission-control-2", "hermes-gateway", "hermes-dashboard", "hermes-webui", "litellm-gateway"}
ENGINE_UPDATE_CMD = os.environ.get("MC_ENGINE_UPDATE_CMD", "")
ENGINE_PATH = os.environ.get("MC_ENGINE_PATH", "/opt/llamacpp")
_engine_cache = {"ts": 0.0, "avail": False}
def _ram_gb() -> float:
return psutil.virtual_memory().total / (1024 ** 3)
def _os_upgradable() -> int:
try:
out = subprocess.run(
["bash", "-c", "apt list --upgradable 2>/dev/null | grep -c upgradable || true"],
capture_output=True, text=True, timeout=10)
return int((out.stdout or "0").strip() or 0)
except Exception:
return 0
def _engine_update_available() -> bool:
now = time.time()
if now - _engine_cache["ts"] < 3600:
return _engine_cache["avail"]
avail = False
try:
rel = httpx.get("https://api.github.com/repos/lemonade-sdk/llamacpp-rocm/releases/latest",
timeout=6, headers={"User-Agent": "MissionControl2"}).json()
pub = datetime.fromisoformat(rel["published_at"].replace("Z", "+00:00")).timestamp()
inst = os.path.getmtime(ENGINE_PATH)
avail = pub > inst + 86400
except Exception:
avail = False
_engine_cache.update(ts=now, avail=avail)
return avail
def model_upgrades() -> list[dict]:
"""Dynamisch: je discover-Kategorie das empfohlene Modell, das NOCH NICHT installiert ist
→ Upgrade-Vorschlag für diese Rolle. Self-updating (kein Hardcode wie v1)."""
disc = discover.safe_discover(_ram_gb())
if not disc:
return []
cmds = " ".join(str(s.get("cmd", "")).lower()
for s in (llamaswap.read_config().get("models") or {}).values())
out = []
for c in disc.get("categories", []):
rec = c.get("recommended")
if not rec:
continue
base = rec.split("/")[-1].lower()
stem = base[:-5] if base.endswith("-gguf") else base
if base in cmds or (stem and stem in cmds):
continue
out.append({"role": c["role"], "title": c["title"], "repo": rec})
return out
def updates() -> dict:
ups = model_upgrades()
return {"os": _os_upgradable(), "engine": 1 if _engine_update_available() else 0,
"models": len(ups), "model_list": ups}
def _run(cmd: list[str]) -> dict:
try:
p = subprocess.run(cmd, capture_output=True, text=True, timeout=120)
return {"ok": p.returncode == 0, "out": (p.stdout or "")[-4000:], "err": (p.stderr or "")[-2000:]}
except Exception as exc: # noqa: BLE001
return {"ok": False, "out": "", "err": str(exc)}
def restart_service(name: str) -> dict:
if name in SYSTEM_SERVICES:
return _run(["sudo", "-n", "systemctl", "restart", name])
if name in USER_SERVICES:
return _run(["systemctl", "--user", "restart", name])
return {"ok": False, "err": f"Dienst '{name}' nicht erlaubt."}
def logs(service: str, lines: int = 200) -> dict:
lines = max(1, min(lines, 1000))
if service in SYSTEM_SERVICES:
cmd = ["sudo", "-n", "journalctl", "-u", service, "-n", str(lines), "--no-pager"]
elif service in USER_SERVICES:
cmd = ["journalctl", "--user", "-u", service, "-n", str(lines), "--no-pager"]
else:
return {"ok": False, "text": "", "err": "Dienst nicht erlaubt."}
r = _run(cmd)
return {"ok": r["ok"], "text": r["out"] or r["err"]}
def os_update_job() -> str:
cmd = "sudo -n apt-get update && sudo -n DEBIAN_FRONTEND=noninteractive apt-get upgrade -y"
return jobengine.start_job(["bash", "-c", cmd], "OS-Update (apt)")
def engine_update_job() -> str | None:
if not ENGINE_UPDATE_CMD:
return None
cmd = f"{ENGINE_UPDATE_CMD} && sudo -n systemctl restart llama-swap"
return jobengine.start_job(["bash", "-c", cmd], "Engine-Update (llama.cpp)")
def reboot() -> dict:
return _run(["sudo", "-n", "reboot"])