mission-control-v2/backend/services/maintenance.py

"""
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 re
import subprocess
import time
from datetime import datetime

import httpx
import psutil

from config import ANYTHINGLLM_REPO, ANYTHINGLLM_URL, HERMES_AGENT_REPO
from services import discover, jobengine, llamaswap, system

# 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"}

# Engine-Update: lädt den neuesten Vulkan-Build (deploy/update-engine.sh, läuft als root).
_REPO_ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", ".."))
ENGINE_UPDATE_CMD = os.environ.get(
    "MC_ENGINE_UPDATE_CMD", f"sudo bash {_REPO_ROOT}/deploy/update-engine.sh")
# Engine = offizieller Vulkan-Build von ggml-org/llama.cpp (RADV auf Strix Halo).
ENGINE_PATH = os.environ.get("MC_ENGINE_PATH", "/opt/llamacpp-vulkan")
ENGINE_REPO = os.environ.get("MC_ENGINE_REPO", "ggml-org/llama.cpp")
_engine_cache = {"ts": 0.0, "avail": False}


def _installed_engine_build() -> int | None:
    """Build-Nummer der installierten llama-server-Binary (z.B. 9821), oder None.
    Vulkan-Build braucht LD_LIBRARY_PATH=ENGINE_PATH zum Start von --version."""
    bin_path = os.path.join(ENGINE_PATH, "llama-server")
    if not os.path.exists(bin_path):
        return None
    try:
        env = dict(os.environ, LD_LIBRARY_PATH=ENGINE_PATH)
        out = subprocess.run([bin_path, "--version"], capture_output=True, text=True,
                             timeout=20, env=env)
        txt = (out.stderr or "") + (out.stdout or "")
        if (m := re.search(r"build:\s*\S+\s*\((\d+)\)", txt)) or (m := re.search(r"\bb(\d{3,})\b", txt)):
            return int(m.group(1))
    except Exception:
        return None
    return None


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(f"https://api.github.com/repos/{ENGINE_REPO}/releases/latest",
                        timeout=6, headers={"User-Agent": "MissionControl2"}).json()
        tag = str(rel.get("tag_name", ""))
        latest = int(m.group(1)) if (m := re.search(r"(\d{3,})", tag)) else None
        installed = _installed_engine_build()
        if latest is not None and installed is not None:
            avail = latest > installed          # präziser Build-Nummer-Vergleich
        else:                                   # Fallback: Release-Datum vs. Engine-mtime
            pub = datetime.fromisoformat(rel["published_at"].replace("Z", "+00:00")).timestamp()
            avail = pub > os.path.getmtime(ENGINE_PATH) + 86400
    except Exception:
        avail = False
    _engine_cache.update(ts=now, avail=avail)
    return avail


_comp_cache = {"ts": 0.0, "data": []}


def _gh_latest(repo: str) -> dict | None:
    """Neuestes GitHub-Release {tag, published} oder None."""
    try:
        rel = httpx.get(f"https://api.github.com/repos/{repo}/releases/latest",
                        timeout=6, headers={"User-Agent": "MissionControl2"}).json()
        return {"tag": str(rel.get("tag_name", "")), "published": rel.get("published_at")}
    except Exception:
        return None


def _commit_ts(path: str) -> int | None:
    try:
        p = subprocess.run(["git", "-C", os.path.expanduser(path), "log", "-1", "--format=%ct"],
                           capture_output=True, text=True, timeout=8)
        return int(p.stdout.strip()) if p.returncode == 0 and p.stdout.strip() else None
    except Exception:
        return None


def _hermes_agent_update() -> dict:
    """Hermes-Agent: neuestes Release vs. installiertes git-Commit-Datum."""
    info = {"key": "hermes_agent", "name": "Hermes Agent", "current": None,
            "latest": None, "update": False, "reachable": None}
    git = system.find_hermes_agent_git()
    if git:
        info["current"] = git.get("hash")
    gh = _gh_latest(HERMES_AGENT_REPO)
    if gh:
        info["latest"] = gh["tag"]
        ts = _commit_ts(git["path"]) if (git and git.get("path")) else None
        if gh["published"] and ts:
            try:
                pub = datetime.fromisoformat(gh["published"].replace("Z", "+00:00")).timestamp()
                info["update"] = pub > ts + 86400   # Release > installiertes Commit (+1 Tag Toleranz)
            except Exception:
                pass
    return info


def _anythingllm_update() -> dict:
    """AnythingLLM: erreichbar? + neueste verfügbare Version. Installierte Version ist
    remote nicht unauth. abfragbar → update=None (nur Info: neueste verfügbar)."""
    reachable = False
    try:
        reachable = httpx.get(f"{ANYTHINGLLM_URL}/api/ping", timeout=4).status_code == 200
    except Exception:
        reachable = False
    info = {"key": "anythingllm", "name": "AnythingLLM", "current": None,
            "latest": None, "update": None, "reachable": reachable}
    gh = _gh_latest(ANYTHINGLLM_REPO)
    if gh:
        info["latest"] = gh["tag"]
    return info


def _components_cached() -> list[dict]:
    """Update-Status von Hermes-Agent + AnythingLLM (1h-Cache → GitHub schonen)."""
    now = time.time()
    if now - _comp_cache["ts"] < 3600 and _comp_cache["data"]:
        return _comp_cache["data"]
    data = [_hermes_agent_update(), _anythingllm_update()]
    _comp_cache.update(ts=now, data=data)
    return data


def _params_of(m: dict) -> float:
    """Größen-bewusste Parameterzahl eines installierten Modells: max aus Namens-Schätzung
    und Dateigröße (fängt namenlose wie 'Qwen3-Coder-Next' UND Split-GGUFs ab)."""
    from services.fit import QUANT_BYTES_PER_PARAM
    caps = m.get("capabilities") or {}
    bpp = QUANT_BYTES_PER_PARAM.get((m.get("quant") or "Q4_K_M").upper(), 0.55)
    size_gb = (m.get("size_bytes") or 0) / (1024 ** 3)
    pb_size = (size_gb / bpp) if size_gb > 1.0 else 0.0
    return max(float(caps.get("params_b") or 0), pb_size, 0.0)


# Familien-Subtyp + Generations-Version aus dem Modellnamen (für „echtes Upgrade?").
_FAM_PATS = (("qwen", r"qwen(\d+(?:\.\d+)?)"), ("gemma", r"gemma[-_ ]?(\d+(?:\.\d+)?)"),
             ("llama", r"llama[-_ ]?(\d+(?:\.\d+)?)"), ("phi", r"phi[-_ ]?(\d+(?:\.\d+)?)"),
             ("mistral", r"mistral"), ("hermes", r"hermes[-_ ]?(\d+(?:\.\d+)?)"))


def _gen_key(name: str):
    """(Familie+Subtyp, Generations-Version) oder None. Z.B. 'Qwen3-VL-2B' → ('qwen-vl', 3.0),
    'Qwen2.5-VL-7B' → ('qwen-vl', 2.5). Nur gleiche Familie ist sinnvoll vergleichbar."""
    low = (name or "").lower()
    sub = "-vl" if any(k in low for k in ("-vl", "vl-", "vision", "llava", "pixtral")) else \
          "-coder" if ("coder" in low or "-code" in low) else ""
    for fam, pat in _FAM_PATS:
        m = re.search(pat, low)
        if m:
            ver = float(m.group(1)) if (m.groups() and m.group(1)) else 0.0
            return (fam + sub, ver)
    return None


def model_upgrades() -> list[dict]:
    """Je Rolle ein ECHTES Upgrade-Vorschlag — nur wenn die Empfehlung wirklich besser ist:
    gleiche Familie UND (neuere Generation ODER größer in gleicher Generation). Verhindert
    Generations-Downgrades (Qwen2.5-VL über Qwen3-VL), Größen-Downgrades (Coder-Next → 30B)
    und Fremd-Familien-Swaps (gpt-oss als „Upgrade" von Qwen)."""
    disc = discover.safe_discover(_ram_gb())
    if not disc:
        return []

    installed = llamaswap.list_models()
    inst_by_role = {m["role"]: m for m in installed if m.get("role")}
    cmds = " ".join(str(s.get("cmd", "")).lower()
                    for s in (llamaswap.read_config().get("models") or {}).values())
    out = []

    for c in disc.get("categories", []):
        role = c["role"]
        im = inst_by_role.get(role)
        if im is None:                        # nur Rollen mit bereits installiertem Modell
            continue
        rec = c.get("recommended")
        if not rec:
            continue
        rec_model = next((x for x in c.get("models", []) if x.get("repo") == rec), None)
        rec_params = float((rec_model or {}).get("params_b") or 0.0)
        inst_params = _params_of(im)

        ig, rg = _gen_key(im["name"]), _gen_key(rec)
        # Upgrade nur bei GLEICHER, erkennbarer Familie:
        if not (ig and rg) or ig[0] != rg[0]:
            continue                          # Fremd-Familie / unbekannt → kein „Upgrade"
        if rg[1] < ig[1] - 1e-6:
            continue                          # ältere Generation → niemals
        if abs(rg[1] - ig[1]) < 1e-6 and rec_params and rec_params < inst_params * 1.05:
            continue                          # gleiche Gen, nicht (deutlich) größer

        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                          # schon installiert
        out.append({"role": role, "title": c["title"], "repo": rec})
    return out


def _last_apt_update() -> float | None:
    for path in ["/var/lib/apt/periodic/update-success-stamp", "/var/cache/apt/pkgcache.bin"]:
        if os.path.exists(path):
            try:
                return os.path.getmtime(path)
            except Exception:
                pass
    return None


def updates() -> dict:
    ups = model_upgrades()
    return {"os": _os_upgradable(), "engine": 1 if _engine_update_available() else 0,
            "models": len(ups), "model_list": ups, "last_check": _last_apt_update(),
            "components": _components_cached()}


def _run(cmd: list[str], sudo_password: str | None = None) -> dict:
    actual_cmd = list(cmd)
    has_sudo = False
    
    if cmd and cmd[0] == "sudo":
        has_sudo = True
        # If we have a password, use -S instead of -n
        if sudo_password is not None:
            if "-n" in actual_cmd:
                actual_cmd = [x for x in actual_cmd if x != "-n"]
            if "-S" not in actual_cmd:
                actual_cmd.insert(1, "-S")
        else:
            # Force -n to fail cleanly if password is required
            if "-S" in actual_cmd:
                actual_cmd = [x for x in actual_cmd if x != "-S"]
            if "-n" not in actual_cmd:
                actual_cmd.insert(1, "-n")

    try:
        input_data = (sudo_password + "\n") if (has_sudo and sudo_password is not None) else None
        p = subprocess.run(actual_cmd, input=input_data, capture_output=True, text=True, timeout=120)
        
        err_msg = p.stderr or ""
        if p.returncode != 0 and ("a password is required" in err_msg or "password" in err_msg.lower() or "sudo:" in err_msg):
            if sudo_password is not None:
                return {"ok": False, "status": "incorrect_password", "out": p.stdout or "", "err": "Falsches Sudo-Passwort."}
            return {"ok": False, "status": "password_required", "out": p.stdout or "", "err": "Sudo-Passwort erforderlich."}
            
        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 check_sudo_needs_password(sudo_password: str | None = None) -> dict | None:
    """Checks if sudo needs a password. Returns error dict if password required/incorrect, else None."""
    res = _run(["sudo", "true"], sudo_password=sudo_password)
    if not res["ok"]:
        return res
    return None


def restart_service(name: str, sudo_password: str | None = None) -> dict:
    if name in SYSTEM_SERVICES:
        if err := check_sudo_needs_password(sudo_password):
            return err
        return _run(["sudo", "systemctl", "restart", name], sudo_password=sudo_password)
    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, sudo_password: str | None = None) -> dict:
    lines = max(1, min(lines, 1000))
    if service in USER_SERVICES:
        r = _run(["journalctl", "--user", "-u", service, "-n", str(lines), "--no-pager"])
        return {"ok": r["ok"], "text": r["out"] or r["err"]}
    if service in SYSTEM_SERVICES:
        # Journal-Lesen braucht i.d.R. KEIN sudo (User ist in Gruppe adm/systemd-journal).
        # Erst ohne sudo versuchen; nur bei fehlenden Rechten auf sudo zurückfallen.
        r = _run(["journalctl", "-u", service, "-n", str(lines), "--no-pager"])
        if r["ok"]:
            return {"ok": True, "text": r["out"] or "(keine Log-Einträge)"}
        if err := check_sudo_needs_password(sudo_password):
            return err
        r = _run(["sudo", "journalctl", "-u", service, "-n", str(lines), "--no-pager"],
                 sudo_password=sudo_password)
        return {"ok": r["ok"], "text": r["out"] or r["err"]}
    return {"ok": False, "text": "", "err": "Dienst nicht erlaubt."}

def check_updates_job(sudo_password: str | None = None) -> dict:
    if err := check_sudo_needs_password(sudo_password):
        return err
    
    def on_done():
        _engine_cache.update(ts=0.0, avail=False)
        
    cmd = "sudo apt-get update"
    job_id = jobengine.start_job(["bash", "-c", cmd], "Nach Updates suchen", on_done=on_done, sudo_password=sudo_password)
    return {"ok": True, "job_id": job_id}


def os_update_job(sudo_password: str | None = None) -> dict:
    if err := check_sudo_needs_password(sudo_password):
        return err
    cmd = "sudo apt-get update && sudo DEBIAN_FRONTEND=noninteractive apt-get upgrade -y"
    job_id = jobengine.start_job(["bash", "-c", cmd], "OS-Update (apt)", sudo_password=sudo_password)
    return {"ok": True, "job_id": job_id}


def engine_update_job(sudo_password: str | None = None) -> dict | None:
    if not ENGINE_UPDATE_CMD:
        return None
    if err := check_sudo_needs_password(sudo_password):
        return err
    # update-engine.sh läuft via sudo als root und startet llama-swap am Ende selbst neu.
    job_id = jobengine.start_job(["bash", "-c", ENGINE_UPDATE_CMD],
                                 "Engine-Update (llama.cpp Vulkan)", sudo_password=sudo_password)
    return {"ok": True, "job_id": job_id}


def reboot(sudo_password: str | None = None) -> dict:
    if err := check_sudo_needs_password(sudo_password):
        return err
    return _run(["sudo", "reboot"], sudo_password=sudo_password)