mission-control-v2/backend/routers/system.py

"""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 logging
import os
import subprocess

from fastapi import APIRouter, HTTPException
from pydantic import BaseModel

import httpx

from config import GATEWAY_URL, HERMES_API_URL, LLAMA_SWAP_URL, MEM0_SERVICE_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, list_models
from services.pricing import compute_savings
from services.system import system_status
from services.token_stats import get_stats

log = logging.getLogger(__name__)

router = APIRouter(prefix="/api")

# Nur diese User-Dienste dürfen neugestartet werden.
ALLOWED_SERVICES = {"mission-control-2", "hermes-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()


def _mem0_reachable() -> bool:
    try:
        return httpx.get(f"{MEM0_SERVICE_URL}/health", timeout=2).status_code == 200
    except Exception:
        return False


@router.get("/system/services")
def services() -> dict:
    """Aggregierte Erreichbarkeit aller Stack-Dienste (für die Health-Anzeige)."""
    a = agent_status()
    gw_url = f"{GATEWAY_URL}/v1"
    return {
        "services": [
            {"name": "Engine (llama-swap)", "url": LLAMA_SWAP_URL, "ok": engine_reachable()},
            {"name": "Gateway (integriert)", "url": gw_url, "ok": gateway_reachable()},
            {"name": "Hermes-Gateway", "url": HERMES_API_URL, "ok": a["gateway_reachable"]},
            {"name": "Hermes-Terminal", "url": a["terminal_url"], "ok": a["terminal_reachable"]},
            {"name": "Mem0 (Gedächtnis)", "url": MEM0_SERVICE_URL, "ok": _mem0_reachable()},
        ],
        "links": {
            "engine_ui": f"{LLAMA_SWAP_URL}/ui",
            "gateway": gw_url,
            "hermes_terminal": a["terminal_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}


@router.get("/system/token-stats")
def token_stats() -> dict:
    """Token-Verbrauch + Cloud-Ersparnis. Logik im pricing-Service (SSoT)."""
    # Rolle je Modell/Alias (lowercase) für die Tarif-Auflösung auflösen.
    role_map: dict[str, str | None] = {}
    try:
        for m in list_models():
            role_map[m["name"].lower()] = m.get("role")
            for alias in m.get("aliases", []):
                role_map[alias.lower()] = m.get("role")
    except Exception:
        log.warning("token_stats: list_models fehlgeschlagen, Tarife per Name", exc_info=True)
    return compute_savings(get_stats(), role_map)