FabledSteward/steward/hosts/service.py

"""Host queries shared by the Hosts pages, dashboard widgets and MCP tools.

Every function takes an open session and returns plain data; none reads
Quart's request context, so the web routes and the /mcp tools (which run
outside Quart's pipeline) call the same code.
"""
from __future__ import annotations
from datetime import datetime, timedelta, timezone

from sqlalchemy import and_, case, func, select

from steward.core.status import _heartbeat_title, _last_n_results, _uptime_by_monitor
from steward.models.hosts import Host
from steward.models.monitors import Monitor, MonitorResult


# Host-level agent metrics read for the at-a-glance views (plus the root
# mount's disk_used_pct, read from the "<host>:/" sub-resource).
AGENT_GLANCE_METRICS = ("cpu_pct", "mem_used_pct", "disk_used_pct", "disk_used_pct_worst", "load_1m")


async def check_name_free(db, name: str, exclude_id: str | None = None) -> None:
    """ValueError when another host already has this name, or it is blank.

    Agent metrics, container metrics and the alert rules on them go by the
    host's name, so two hosts sharing one would share one history.
    """
    if not name:
        raise ValueError("a host needs a name.")
    q = select(Host.id).where(Host.name == name)
    if exclude_id:
        q = q.where(Host.id != exclude_id)
    if (await db.execute(q.limit(1))).first():
        raise ValueError(f"another host is already named {name!r}; pick a different name.")


def agent_stale_after_seconds(config) -> int:
    """The host_agent plugin's freshness window from app config (default 180s)."""
    return int(((config.get("PLUGINS") or {}).get("host_agent") or {})
               .get("stale_after_seconds", 180))


async def compute_uptime(db) -> dict[str, dict]:
    """Per-host uptime % for 24h/7d/30d, aggregated over the host's monitors.

    Returns {host_id: {"24h": float|None, "7d": float|None, "30d": float|None}}.
    """
    now = datetime.now(timezone.utc)
    cutoff_30d = now - timedelta(days=30)
    cutoff_7d  = now - timedelta(days=7)
    cutoff_24h = now - timedelta(hours=24)

    result = await db.execute(
        select(
            Monitor.host_id,
            func.count(MonitorResult.id).label("total_30d"),
            func.sum(case((MonitorResult.is_up.is_(True), 1), else_=0)).label("up_30d"),
            func.sum(case((MonitorResult.checked_at >= cutoff_7d, 1), else_=0)).label("total_7d"),
            func.sum(case(
                (and_(MonitorResult.checked_at >= cutoff_7d, MonitorResult.is_up.is_(True)), 1),
                else_=0,
            )).label("up_7d"),
            func.sum(case((MonitorResult.checked_at >= cutoff_24h, 1), else_=0)).label("total_24h"),
            func.sum(case(
                (and_(MonitorResult.checked_at >= cutoff_24h, MonitorResult.is_up.is_(True)), 1),
                else_=0,
            )).label("up_24h"),
        )
        .join(Monitor, Monitor.id == MonitorResult.monitor_id)
        .where(Monitor.host_id.isnot(None), MonitorResult.checked_at >= cutoff_30d)
        .group_by(Monitor.host_id)
    )

    def _pct(up, total):
        return round(float(up) / float(total) * 100, 2) if total else None

    stats: dict[str, dict] = {}
    for row in result:
        stats[row.host_id] = {
            "24h": _pct(row.up_24h, row.total_24h),
            "7d":  _pct(row.up_7d,  row.total_7d),
            "30d": _pct(row.up_30d, row.total_30d),
        }
    return stats


async def host_status(db, host_ids: list[str]) -> dict[str, dict]:
    """Per-host status rollup from the latest result of each linked monitor.

    {host_id: {"state": "up"|"down"|"pending", "latency_ms": float|None,
               "count": int}}. State is down if ANY linked monitor's latest
    result is down (worst-case), up if at least one is up, else pending.
    """
    if not host_ids:
        return {}
    monitors = (await db.execute(
        select(Monitor.id, Monitor.host_id)
        .where(Monitor.host_id.in_(host_ids), Monitor.enabled.is_(True))
    )).all()
    latest = await _last_n_results(db, [m.id for m in monitors], n=1)
    rows = [(latest[mid][-1], host_id) for mid, host_id in monitors if latest.get(mid)]
    out: dict[str, dict] = {}
    for res, host_id in rows:
        d = out.setdefault(host_id, {"state": "pending", "latency_ms": None, "count": 0})
        d["count"] += 1
        if not res.is_up:
            d["state"] = "down"
        elif d["state"] != "down":
            d["state"] = "up"
        if res.is_up and res.response_ms is not None:
            d["latency_ms"] = (res.response_ms if d["latency_ms"] is None
                               else min(d["latency_ms"], res.response_ms))
    return out


def worst_uptime_first(hosts, uptime: dict) -> list:
    """Hosts by their 24h uptime, worst first, then 7d and 30d to break ties;
    hosts with no uptime yet (no monitors) last, by name."""
    def key(h):
        u = uptime.get(h.id) or {}
        windows = [u.get(w) for w in ("24h", "7d", "30d")]
        known = [w for w in windows if w is not None]
        return (not known, *[101.0 if w is None else w for w in windows], h.name.lower())
    return sorted(hosts, key=key)


def host_rank(status: dict | None, agent: dict | None) -> int:
    """Where a host sorts in the Hosts list: a down monitor first, then an
    agent gone quiet, then monitors not yet checked, then the healthy; a host
    with neither monitors nor agent last."""
    if status and status["state"] == "down":
        return 0
    if agent and not agent.get("fresh"):
        return 1
    if status and status["state"] == "pending":
        return 2
    if status or agent:
        return 3
    return 4


async def host_monitors(db, host_id: str) -> list[dict]:
    """Display rows for the monitors linked to one host (host hub section)."""
    monitors = (await db.execute(
        select(Monitor).where(Monitor.host_id == host_id).order_by(Monitor.name)
    )).scalars().all()
    ids = [m.id for m in monitors]
    recent = await _last_n_results(db, ids)
    uptime = await _uptime_by_monitor(db, ids)
    data = []
    from steward.monitors.service import down_reason, down_since
    for m in monitors:
        mrows = recent.get(m.id, [])
        latest = mrows[-1] if mrows else None
        state = ("paused" if not m.enabled else "pending" if latest is None
                 else "up" if latest.is_up else "down")
        data.append({
            "monitor": m, "latest": latest, "state": state,
            "heartbeat": [{"state": "up" if r.is_up else "down",
                           "title": _heartbeat_title(m.type, r)} for r in mrows],
            "uptime_pct": uptime.get(m.id, {}).get("24h"),
            "down_since": await down_since(db, m.id) if state == "down" else None,
            "down_reason": down_reason(latest) if state == "down" else None,
        })
    # Problems first: down, then not yet checked, then up, paused last.
    order = {"down": 0, "pending": 1, "up": 2, "paused": 3}
    return sorted(data, key=lambda d: (order[d["state"]], d["monitor"].name.lower()))


async def agent_overview_by_host(
    db, host_names: list[str], stale_after_seconds: int = 180,
) -> dict[str, dict]:
    """Per-host agent glance (cpu/mem/disk + freshness) from plugin_metric_latest.

    {host_name: {cpu_pct, mem_used_pct, disk_used_pct_worst, disk_root, load_1m,
                 last_at, fresh}} for each host with any agent samples.

    Core-safe (no host_agent import). Freshness compares the latest host-level
    sample against the host_agent plugin's stale window (stale_after_seconds;
    callers pass agent_stale_after_seconds(app.config)). A host whose agent has
    gone quiet keeps its last values with fresh=False (#5208).
    """
    from steward.core.metric_series import latest_by_resource
    if not host_names:
        return {}
    now = datetime.now(timezone.utc)
    stale_after = int(stale_after_seconds)
    latest = await latest_by_resource(
        db, "host_agent", list(host_names) + [h + ":/" for h in host_names],
        set(AGENT_GLANCE_METRICS) | {"disk_used_pct"})
    out: dict[str, dict] = {}
    for name in host_names:
        own = {m: r for m, r in latest.get(name, {}).items() if m in AGENT_GLANCE_METRICS}
        root = latest.get(name + ":/", {}).get("disk_used_pct")
        if not own and root is None:
            continue
        d = {m: r.value for m, r in own.items()}
        if root is not None:
            d["disk_root"] = root.value
        ts = max((r.recorded_at for r in own.values()), default=None)
        d["last_at"] = ts
        d["fresh"] = bool(ts and (now - ts).total_seconds() <= stale_after)
        out[name] = d
    return out


async def agent_cpu_sparks_by_host(db, host_names: list[str], hours: int = 1) -> dict[str, str]:
    """{host_name: inline-SVG cpu sparkline} over the last `hours` (core-safe).

    A tiny at-a-glance trend in each row — the host-view sparkline, on the widget.
    """
    from steward.models.metrics import PluginMetric
    from steward.core.status import sparkline_svg
    if not host_names:
        return {}
    cutoff = datetime.now(timezone.utc) - timedelta(hours=hours)
    rows = (await db.execute(
        select(PluginMetric.resource_name, PluginMetric.value, PluginMetric.recorded_at)
        .where(
            PluginMetric.source_module == "host_agent",
            PluginMetric.metric_name == "cpu_pct",
            PluginMetric.resource_name.in_(host_names),
            PluginMetric.recorded_at >= cutoff,
        )
        .order_by(PluginMetric.recorded_at)
    )).all()
    by_host: dict[str, list[float]] = {}
    for r in rows:
        by_host.setdefault(r.resource_name, []).append(r.value)
    # Amber line to read as "CPU"; only draw when there are a couple of points.
    return {
        name: sparkline_svg(vals[-40:], width=64, height=18, stroke="#c8a840")
        for name, vals in by_host.items() if len(vals) >= 2
    }