Files
mission-control-v2/backend/routers/system.py
T
Hitonabi 1f4c987652 feat(2.0): Phase 5 — Betrieb, Observability + Politur
Backup: services/backup.py (Memory-SQLite inkl. WAL/SHM + Configs, retain 7)
+ deploy/backup.sh + POST /api/system/backup + GET /api/system/backups.
Services-Health: GET /api/system/services (aggregierte Reachability +
Observability-Links). Frontend: SystemView mit Dienste-Health + Backup-
Button + Links; Theme-Toggle (Hell/Dunkel, persistent).

Lokal verifiziert: Backup-Snapshot + services-Aggregat (TestClient),
Frontend-Build + Browser (Light-Mode bestaetigt via computed styles).
Damit Phasen 0-5 lokal fertig. Docs aktualisiert.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-25 08:29:27 +02:00

90 lines
3.1 KiB
Python

"""System-Endpoints: Live-Status + Wartung (Restart/Self-Update — auf der Box).
Wartung läuft als systemd-USER-Dienst → KEIN sudo/Passwort (Nordstern).
Lokal (Windows) schlagen die Shell-Befehle harmlos fehl und werden als Fehler
zurückgegeben statt zu crashen.
"""
import os
import subprocess
from fastapi import APIRouter, HTTPException
from pydantic import BaseModel
from config import GATEWAY_URL, HERMES_API_URL, HERMES_WEBUI_URL, LLAMA_SWAP_URL
from services import backup as backup_svc
from services.agent import agent_status
from services.gateway import gateway_reachable
from services.llamaswap import engine_reachable
from services.system import system_status
router = APIRouter(prefix="/api")
# Nur diese User-Dienste dürfen neugestartet werden.
ALLOWED_SERVICES = {"mission-control-2", "litellm-gateway", "hermes-webui"}
# Quelle für Self-Update (auf der Box ~/mission-control-v2).
SOURCE_DIR = os.path.expanduser(os.environ.get("MC2_SOURCE_DIR", "~/mission-control-v2"))
@router.get("/system/status")
def status() -> dict:
return system_status()
@router.get("/system/services")
def services() -> dict:
"""Aggregierte Erreichbarkeit aller Stack-Dienste (für die Health-Anzeige)."""
a = agent_status()
return {
"services": [
{"name": "Engine (llama-swap)", "url": LLAMA_SWAP_URL, "ok": engine_reachable()},
{"name": "Gateway (LiteLLM)", "url": GATEWAY_URL, "ok": gateway_reachable()},
{"name": "Hermes-Gateway", "url": HERMES_API_URL, "ok": a["gateway_reachable"]},
{"name": "Hermes-WebUI", "url": HERMES_WEBUI_URL, "ok": a["webui_reachable"]},
],
"links": {
"engine_ui": f"{LLAMA_SWAP_URL}/ui",
"gateway": GATEWAY_URL,
"hermes_webui": HERMES_WEBUI_URL,
},
}
@router.post("/system/backup")
def backup() -> dict:
return backup_svc.backup_now()
@router.get("/system/backups")
def backups() -> dict:
return {"backups": backup_svc.list_backups()}
def _run(cmd: list[str], cwd: str | None = None) -> dict:
try:
p = subprocess.run(cmd, cwd=cwd, capture_output=True, text=True, timeout=180)
return {"ok": p.returncode == 0, "code": p.returncode,
"out": (p.stdout or "")[-2000:], "err": (p.stderr or "")[-2000:]}
except Exception as exc: # noqa: BLE001
return {"ok": False, "code": -1, "out": "", "err": str(exc)}
class RestartReq(BaseModel):
service: str
@router.post("/system/restart")
def restart(req: RestartReq) -> dict:
if req.service not in ALLOWED_SERVICES:
raise HTTPException(400, f"Dienst '{req.service}' nicht erlaubt.")
return _run(["systemctl", "--user", "restart", req.service])
@router.post("/system/self-update")
def self_update() -> dict:
"""git pull (Source) → venv-Deps → Dienst-Restart. Auf der Box; lokal Fehler."""
pull = _run(["git", "fetch", "--all"], cwd=SOURCE_DIR)
reset = _run(["git", "reset", "--hard", "origin/main"], cwd=SOURCE_DIR)
restart_res = _run(["systemctl", "--user", "restart", "mission-control-2"])
return {"pull": pull, "reset": reset, "restart": restart_res}