"""The swarm's health as three figures an alert rule can watch (#5788).

Every manager's agent reports the whole swarm, so the figures are swarm-wide,
on one resource, `swarm`, and are recorded at most once every RECORD_EVERY
whichever manager sent them: three managers then read as one series, and one
manager going silent doesn't silence it.

- swarm_services_short: services running fewer tasks than they want. A
  service scaled to 0 wants none and is never short.
- swarm_nodes_down: nodes whose status isn't ready, other than drained ones.
  A drained node is one taken out of service on purpose (VDNT-Util01 always;
  any node during its maintenance), so its going away is expected. Its host's
  own "Agent offline" rule still covers it.
- swarm_managers_unreachable: managers the swarm can't reach (agent 1.19.0
  sends ManagerStatus.Reachability; before that, a manager whose status
  isn't ready), drained ones aside for the same reason. With three managers
  one can be lost and the swarm keeps working; two, and it can't change.

A maintenance job on a swarm node holds these rules' notifications in its
window (host_agent maintenance._swarm_window), since draining and rebooting a
node is exactly what moves them.
"""
from __future__ import annotations

from datetime import datetime, timedelta

RESOURCE = "swarm"
SWARM_METRICS = ("swarm_services_short", "swarm_nodes_down", "swarm_managers_unreachable")
RECORD_EVERY = timedelta(seconds=30)

_last_recorded: datetime | None = None


def figures(swarm: dict) -> dict[str, float]:
    """The three figures from one manager's swarm report."""
    services = swarm.get("services") or []
    nodes = swarm.get("nodes") or []
    short = sum(1 for s in services
                if int(s.get("desired") or 0) > 0 and int(s.get("running") or 0) < int(s.get("desired") or 0))
    in_service = [n for n in nodes if (n.get("availability") or "active") != "drain"]
    down = sum(1 for n in in_service if (n.get("status") or "unknown") != "ready")
    managers = [n for n in in_service if n.get("role") == "manager"]
    unreachable = sum(1 for n in managers
                      if (n["reachability"] != "reachable" if n.get("reachability")
                          else (n.get("status") or "unknown") != "ready"))
    return {"swarm_services_short": float(short), "swarm_nodes_down": float(down),
            "swarm_managers_unreachable": float(unreachable)}


def due(now: datetime) -> bool:
    """Whether this report should be recorded: the first in RECORD_EVERY,
    whichever manager it came from."""
    global _last_recorded
    if _last_recorded is not None and now - _last_recorded < RECORD_EVERY:
        return False
    _last_recorded = now
    return True