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
from pydantic import BaseModel

import httpx

from config import GATEWAY_URL, HERMES_API_URL, LLAMA_SWAP_URL, MEM0_SERVICE_URL, V1_UPSTREAM, VOICE_SERVICE_URL
from services import backup as backup_svc
from services import maintenance
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")

# 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


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


def _user_unit_active(unit: str) -> bool:
    """systemd-User-Unit ohne eigenen HTTP-Port (z. B. mc2-steward) — Zustand via is-active.
    Auf Windows/Dev schlägt das harmlos fehl (False)."""
    if os.name != "posix":
        return False
    try:
        r = subprocess.run(["systemctl", "--user", "is-active", unit],
                           capture_output=True, text=True, timeout=3)
        return r.stdout.strip() == "active"
    except Exception:  # noqa: BLE001
        return False


@router.get("/system/services")
def services() -> dict:
    """Aggregierte Erreichbarkeit aller Stack-Dienste — die EINE Quelle für Cockpit-Kachel,
    Schubladen-Liste und Log-Auswahl (Frontend rendert diese Liste, keine UI-Kopie mehr).
    `scope`: user|system (Restart-Weg), `unit`: echter systemd-Name (Restart/Logs/Matching)."""
    a = agent_status()
    gw_url = f"{GATEWAY_URL}/v1"
    rows = [
        {"name": "Engine (llama-swap)", "unit": "llama-swap", "url": LLAMA_SWAP_URL,
         "ok": engine_reachable(), "scope": "system"},
    ]
    # Seit UMBAU v3 P1 ist der LLM-Gateway ein EIGENER Prozess — ohne diese Zeile war er
    # in der Dienste-Ampel unsichtbar (Kachel "6/6 grün" bei totem Denkpfad).
    if V1_UPSTREAM:
        rows.append({"name": "LLM-Gateway (Denkpfad)", "unit": "mc2-gateway", "url": V1_UPSTREAM,
                     "ok": gateway_reachable(), "scope": "user"})
        # MC2 selbst antwortet gerade auf diesen Request — ok=True ist hier ehrlich;
        # die Zeile existiert für Restart/Logs, nicht als Erreichbarkeits-Orakel.
        rows.append({"name": "Steuerpult (MC2)", "unit": "mission-control-2", "url": gw_url,
                     "ok": True, "scope": "user"})
    else:
        rows.append({"name": "Gateway (integriert)", "unit": "mission-control-2", "url": gw_url,
                     "ok": gateway_reachable(), "scope": "user"})
    rows += [
        {"name": "Wächter (Steward)", "unit": "mc2-steward", "url": "",
         "ok": _user_unit_active("mc2-steward"), "scope": "user"},
        {"name": "Hermes-Gateway", "unit": "hermes-gateway", "url": HERMES_API_URL,
         "ok": a["gateway_reachable"], "scope": "user"},
        {"name": "Hermes-GUI (Desktop-Gateway)", "unit": "hermes-builtin-ui", "url": a["hermes_ui_url"],
         "ok": a["hermes_ui_reachable"], "scope": "user"},
        {"name": "Mem0 (Gedächtnis)", "unit": "mem0-service", "url": MEM0_SERVICE_URL,
         "ok": _mem0_reachable(), "scope": "user"},
        {"name": "Voice (STT/TTS)", "unit": "voice-service", "url": VOICE_SERVICE_URL,
         "ok": _voice_reachable(), "scope": "user"},
    ]
    return {
        "services": rows,
        "links": {
            "engine_ui": f"{LLAMA_SWAP_URL}/ui",
            "gateway": gw_url,
            "hermes_ui": a["hermes_ui_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:
    """Dienst neustarten. Delegiert an den Wartungs-Service (EINE Allowlist-Wahrheit):
    der kennt System-Dienste (llama-swap, via sudo -n) UND User-Dienste und wird auch von
    der UI (/api/maintenance/restart) genutzt. Vorher lag hier eine zweite, veraltete Liste
    (ohne llama-swap/hermes-terminal, mit Geist-Eintrag hermes-webui) → Engine-Neustart per
    Sprache/MCP schlug fehl."""
    return maintenance.restart_service(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)