FabledSteward/steward/monitors/service.py

"""Monitor queries and validation shared by the monitors pages and the MCP tools.

Each function takes an open session (or plain values), with no Quart request
context, so the routes and the /mcp tools (which run outside Quart's
pipeline) call the same code and refuse the same input for the same reasons.
"""
from __future__ import annotations

import json
from collections.abc import Mapping
from datetime import datetime, timezone

from sqlalchemy import func, select

from steward.core.formatting import status_class
from steward.core.status import _heartbeat_title, _last_n_results, _uptime_by_monitor
from steward.core.time_range import parse_range
from steward.models.monitors import MONITOR_TYPE_VALUES, Monitor, MonitorResult, MonitorType

HTTP_METHODS = ("GET", "HEAD", "POST")
# The config keys each type takes (models/monitors.py documents their meaning).
CONFIG_KEYS: dict[str, tuple[str, ...]] = {
    MonitorType.icmp.value: (),
    MonitorType.tcp.value: ("port",),
    MonitorType.dns.value: ("expected_ip",),
    MonitorType.http.value: ("method", "expected_status", "content_match", "headers",
                             "timeout_seconds", "follow_redirects", "verify_ssl"),
}


def _whole(name: str, value, default: int, lo: int, hi: int | None = None) -> int:
    if value is None or value == "":
        return default
    if isinstance(value, bool):
        raise ValueError(f"{name} must be a whole number, got {value!r}.")
    try:
        n = int(value)
    except (TypeError, ValueError):
        raise ValueError(f"{name} must be a whole number, got {value!r}.") from None
    if n < lo or (hi is not None and n > hi):
        bounds = f"between {lo} and {hi}" if hi is not None else f"at least {lo}"
        raise ValueError(f"{name} must be {bounds}, got {n}.")
    return n


def _headers(value) -> dict:
    if value is None or value == "":
        return {}
    if isinstance(value, str):
        try:
            value = json.loads(value)
        except ValueError:
            raise ValueError("headers must be a JSON object of name: value strings.") from None
    if not isinstance(value, dict) or not all(isinstance(k, str) and isinstance(v, str)
                                              for k, v in value.items()):
        raise ValueError("headers must be an object of name: value strings.")
    return value


def normalise_target(mtype: str, target: str) -> str:
    """For http, default a bare host to https://; others pass through."""
    target = (target or "").strip()
    if mtype == MonitorType.http.value and target and not target.startswith(("http://", "https://")):
        return "https://" + target
    return target


def build_config(mtype: str, opts: Mapping) -> dict:
    """The type-specific config from already-typed or form-string values.

    Missing keys take their defaults; a key the type does not take, or a
    value out of range, raises ValueError saying which and why.
    """
    unknown = sorted(set(opts) - set(CONFIG_KEYS[mtype]))
    if unknown:
        allowed = ", ".join(CONFIG_KEYS[mtype]) or "no config"
        raise ValueError(f"a {mtype} monitor does not take {', '.join(unknown)}; it takes {allowed}.")
    if mtype == MonitorType.tcp.value:
        return {"port": _whole("port", opts.get("port"), 80, 1, 65535)}
    if mtype == MonitorType.dns.value:
        return {"expected_ip": (str(opts.get("expected_ip") or "").strip() or None)}
    if mtype == MonitorType.http.value:
        method = str(opts.get("method") or "GET").strip().upper()
        if method not in HTTP_METHODS:
            raise ValueError(f"method {method!r} is not one of {', '.join(HTTP_METHODS)}.")
        return {
            "method": method,
            "expected_status": _whole("expected_status", opts.get("expected_status"), 200, 100, 599),
            "content_match": str(opts.get("content_match") or "").strip(),
            "headers": _headers(opts.get("headers")),
            "timeout_seconds": _whole("timeout_seconds", opts.get("timeout_seconds"), 10, 1, 60),
            "follow_redirects": bool(opts.get("follow_redirects", True)),
            "verify_ssl": bool(opts.get("verify_ssl", True)),
        }
    return {}  # icmp


def monitor_fields(mtype: str, *, target: str, name: str = "", check_interval_seconds=0,
                   opts: Mapping | None = None) -> dict:
    """Validated column values for a new or edited monitor; ValueError says why not."""
    mtype = (mtype or "").strip().lower()
    if mtype not in MONITOR_TYPE_VALUES:
        raise ValueError(f"type {mtype!r} is not one of {', '.join(MONITOR_TYPE_VALUES)}.")
    target = normalise_target(mtype, target)
    if not target:
        raise ValueError("a monitor needs a target: an address, or a URL for http.")
    if len(target) > 2048:
        raise ValueError("target is longer than 2048 characters.")
    return {
        "type": mtype,
        "target": target,
        "name": ((name or "").strip() or target)[:128],
        "config_json": json.dumps(build_config(mtype, opts or {})),
        "check_interval_seconds": _whole("check_interval_seconds", check_interval_seconds, 0, 0),
    }


async def check_name_free(db, mtype: str, name: str, exclude_id: str | None = None) -> None:
    """ValueError when another monitor of this type already has this name.

    A monitor's checks are recorded, and its alert rules watch it, by
    (type, name), so two monitors sharing both would share one history.
    """
    q = select(Monitor.id).where(Monitor.type == mtype, Monitor.name == name)
    if exclude_id:
        q = q.where(Monitor.id != exclude_id)
    if (await db.execute(q.limit(1))).first():
        raise ValueError(f"another {mtype} monitor is already named {name!r}; its checks and "
                         "alert rules go by that name, so pick a different one.")


# Where each state sorts on the Monitors page: what needs looking at first.
STATE_ORDER = {"down": 0, "degraded": 1, "pending": 2, "up": 3, "paused": 4}


def row_state(monitor: Monitor, latest, uptime_pct, thresholds: dict) -> str:
    """paused, pending (never checked), down, degraded or up.

    Degraded is up but worth a look: uptime over the window at or below its
    warning cutoff, or the latest response time past its critical one
    (Settings → Thresholds). A slow-but-tolerable reply is coloured, not sorted.
    """
    if not monitor.enabled:
        return "paused"
    if latest is None:
        return "pending"
    if not latest.is_up:
        return "down"
    if (status_class(uptime_pct, "uptime", thresholds) in ("warn", "crit")
            or status_class(latest.response_ms, "latency", thresholds) == "crit"):
        return "degraded"
    return "up"


def down_reason(latest) -> str | None:
    """Why a failed check failed, in a few words: the probe's error, else the
    HTTP status, else a content mismatch; None when the result says nothing."""
    if latest is None:
        return None
    if latest.error_msg:
        return latest.error_msg
    if latest.status_code:
        return f"HTTP {latest.status_code}"
    if latest.content_matched is False:
        return "expected content not found"
    return None


def problems_first(rows: list[dict]) -> list[dict]:
    """Down, then degraded, then pending, up and paused; by name within each."""
    return sorted(rows, key=lambda d: (STATE_ORDER[d["state"]], d["monitor"].name.lower()))


async def monitor_rows(db, range_key: str, thresholds: dict):
    """Per-monitor state: latest result, heartbeat strip, uptime and TLS days,
    problems first.

    Returns (rows, counts, range_key). `counts` has up (degraded included),
    degraded, down, pending and paused. `range_key` picks the uptime window
    surfaced (24h/7d/30d; anything else falls back to 24h) and comes back
    normalised.
    """
    _since, range_key = parse_range(range_key)
    monitors = list((await db.execute(select(Monitor).order_by(Monitor.name))).scalars())
    ids = [m.id for m in monitors]
    recent = await _last_n_results(db, ids)
    uptime = await _uptime_by_monitor(db, ids)

    # Map the selected range to the uptime bucket we surface in the list.
    bucket = {"24h": "24h", "7d": "7d", "30d": "30d"}.get(range_key, "24h")
    now = datetime.now(timezone.utc)
    data = []
    for m in monitors:
        rows = recent.get(m.id, [])
        latest = rows[-1] if rows else None
        uptime_pct = uptime.get(m.id, {}).get(bucket)
        tls_days = None
        if latest and latest.tls_expires_at:
            tls_days = (latest.tls_expires_at - now).total_seconds() / 86400.0
        data.append({
            "monitor": m,
            "latest": latest,
            "state": row_state(m, latest, uptime_pct, thresholds),
            "heartbeat": [{"state": "up" if r.is_up else "down",
                           "title": _heartbeat_title(m.type, r)} for r in rows],
            "uptime_pct": uptime_pct,
            "tls_days": tls_days,
            "down_since": None,
            "down_reason": down_reason(latest) if latest is not None and not latest.is_up else None,
        })
    # When each down monitor went down (a query per down monitor: few, and indexed).
    for d in data:
        if d["state"] == "down":
            d["down_since"] = await down_since(db, d["monitor"].id)
    counts = {k: sum(d["state"] == k for d in data) for k in STATE_ORDER}
    counts["up"] += counts["degraded"]
    return problems_first(data), counts, range_key


async def down_since(db, monitor_id: str):
    """When the monitor's current run of failures began, or None if its latest check is up.

    The first failed check after the last success; if it has never succeeded,
    its first check.
    """
    last_up = (await db.execute(
        select(func.max(MonitorResult.checked_at))
        .where(MonitorResult.monitor_id == monitor_id, MonitorResult.is_up.is_(True))
    )).scalar()
    stmt = select(func.min(MonitorResult.checked_at)).where(MonitorResult.monitor_id == monitor_id)
    if last_up is not None:
        stmt = stmt.where(MonitorResult.checked_at > last_up)
    return (await db.execute(stmt)).scalar()


async def monitor_states(db, monitors: list[Monitor]) -> dict[str, dict]:
    """{monitor_id: {latest, recent, uptime, down_since}} for the given monitors.

    `recent` is the last HEARTBEAT_COUNT results oldest-first; `uptime` is
    {"24h","7d","30d"} percentages; `down_since` is set only for a monitor
    whose latest check failed.
    """
    ids = [m.id for m in monitors]
    recent = await _last_n_results(db, ids)
    uptime = await _uptime_by_monitor(db, ids)
    out: dict[str, dict] = {}
    for m in monitors:
        rows = recent.get(m.id, [])
        latest = rows[-1] if rows else None
        out[m.id] = {
            "latest": latest,
            "recent": rows,
            "uptime": uptime.get(m.id, {}),
            "down_since": None,
        }
        if latest is not None and not latest.is_up:
            out[m.id]["down_since"] = await down_since(db, m.id)
    return out


async def recent_failures(db, monitor_id: str, limit: int = 10) -> list[MonitorResult]:
    """The monitor's latest failed checks, newest first."""
    return list((await db.execute(
        select(MonitorResult)
        .where(MonitorResult.monitor_id == monitor_id, MonitorResult.is_up.is_(False))
        .order_by(MonitorResult.checked_at.desc())
        .limit(limit)
    )).scalars())