package backup

import "time"

// ── R-330: the app-down alarm must not fire for an app the BACKUP ITSELF is holding down ─────────
//
// THE BUG, MEASURED LIVE ON demo-hp 2026-08-30 (controller 0.223.0). Every night both demo boxes
// e-mailed the customer `app_start_failed — "Telepített alkalmazás nem fut: <App>"` about apps that
// were never broken. `DumpAppVolumesSafe` stops a stack (`docker compose down`), tars its volumes and
// starts it again — ~13 s per stack — and the `deadapp-check` scheduler job runs every 30 s. It
// caught whichever stack was mid-cycle. Observed that night, UTC: the `db-dump` leg at 00:30 produced
// three events (Docmost, Paperless-ngx, RomM) and the `offbox-backup` leg at 02:15 produced two, while
// every dead-app scan of the other 23 hours logged `0 currently down`. 61 e-mails had accumulated.
//
// WHY R-97b's WINDOW DID NOT COVER IT. quiesce/suppress.go solves exactly this problem and solves it
// correctly — but it belongs to the QUIESCE LOOP, which stops stacks for the WHOLE-GUEST (vzdump/PBS)
// backup. `classifyRunStates` consults only `Loop.SuppressedStacks()`. The nightly per-app legs stop
// stacks through a different path (`Manager.DumpAppVolumesSafe`), which registered nothing with any
// suppressor. Two mechanisms stop apps; only one told the alarm.
//
// WHY THIS LIVES ON AppStopGuard, and not in a fourth place. The guard already brackets EVERY
// "we stopped this app on purpose" window in the product — `Begin` before the stop, `End` after a
// successful restart — at all three call sites (volume dump, off-site reconstitute, .fab export), and
// main.go hands the SAME guard object to the backup manager and the exporter. The fact the alarm needs
// ("we stopped it, and we have not given it back yet") is already here and has exactly one writer.
// Putting a fourth registry beside it would be the drift this codebase has paid for before.
//
// ── THE TENSION, WHICH IS THE WHOLE DESIGN (inherited from R-97b, and it still binds) ────────────
//
// Suppress while we hold the app and for a grace period after we let go — but an app that GENUINELY
// fails to come back MUST still alarm. Permanent suppression trades a loud false alarm for a silent
// real one, which is F-CRIT-1 and R-88 Scenario D over again. Three independent things stop this
// window from latching:
//
//  1. `ReleaseFailed` — a restart that was ATTEMPTED AND BROKE drops the entry immediately, so the
//     app alarms on the very next scan rather than after any delay at all. This is the primary
//     mechanism and every failure path calls it.
//  2. `Begin` REPLACES the set. The marker file holds one operation, so a new Begin proves the
//     previous one is over; a set stranded by an earlier op cannot survive into a later one.
//  3. `appStopMaxHold` — a backstop for a hold nothing ever released. See its comment.
const (
	// appStopAlarmGrace is how long after a successful restart a stack stays exempt.
	//
	// Deliberately the SAME 180 s as quiesce.quiesceAlarmGrace, and for the same derivation: the
	// deploy flow allows 120 s for a stack to come up healthy, and the slowest catalog healthcheck
	// start_period is Mealie's 60 s, after which a couple of check intervals must still elapse. Two
	// suppression windows over the same alarm that disagreed on how long a restart takes would be a
	// bug waiting to be found on whichever path used the shorter one.
	//
	// It is NOT longer than it needs to be: the dead-app scan runs on its own 30 s cadence, so an app
	// that is genuinely dead alarms on the first scan after the window closes. The cost of this
	// suppression is a BOUNDED DELAY in reporting a real failure, never its loss.
	appStopAlarmGrace = 180 * time.Second

	// appStopMaxHold caps an open-ended hold, and exists because of a hazard the quiesce loop does
	// not have. `Loop` always calls markUnquiesced; `AppStopGuard.End()` is called only on a restart
	// that SUCCEEDED, so a failure path that forgets to call `ReleaseFailed` would leave an entry
	// open-ended forever — a silently dead app, which is the exact defect this file must not create
	// while fixing a false alarm.
	//
	// Six hours is chosen to be longer than any real hold and far shorter than "forever": a volume
	// dump holds a stack ~13 s (measured), a .fab export minutes, and even a multi-gigabyte off-site
	// reconstitution is hours at the outside. Exceeding it means something is wrong, and the correct
	// behaviour when something is wrong is to let the alarm through.
	appStopMaxHold = 6 * time.Hour
)

// markStopped records `names` as exempt from app-down alarms for the duration of the current
// operation. The expiry is set at release; until then the entry is open-ended (bounded only by
// appStopMaxHold), because an operation may legitimately run for a long time and an app we are
// holding down that whole time must not alarm halfway through.
//
// It REPLACES the previous set rather than adding to it — see design note 2 above.
func (g *AppStopGuard) markStopped(names []string) {
	if g == nil || len(names) == 0 {
		return
	}
	g.suppressMu.Lock()
	defer g.suppressMu.Unlock()
	g.suppressed = make(map[string]appStopHold, len(names))
	now := g.now()
	for _, n := range names {
		g.suppressed[n] = appStopHold{since: now} // zero `until` = still held
	}
}

// releaseStarted starts the grace clock on every stack still held. Called from End(), which is the
// single "we gave the app back and it started" signal on all three paths.
func (g *AppStopGuard) releaseStarted() {
	if g == nil {
		return
	}
	until := g.now().Add(appStopAlarmGrace)
	g.suppressMu.Lock()
	defer g.suppressMu.Unlock()
	for n, h := range g.suppressed {
		if h.until.IsZero() {
			h.until = until
			g.suppressed[n] = h
		}
	}
}

// ReleaseFailed drops the suppression for stacks whose restart was ATTEMPTED AND BROKE, so they
// alarm on the next dead-app scan instead of being silenced by a window that was only ever meant to
// cover a restart in progress.
//
// Call it on EVERY path that stops an app and then fails to bring it back. It is the counterpart of
// quiesce's noteRestartOutcome, and the same rule applies: the distinguishing fact is not in the
// stack's state — a stack we stopped and could not restart is byte-identical on the Docker side to
// one the customer stopped — it is that WE tried and could not, and only the caller knows that.
//
// Nil-safe and idempotent: releasing a stack that is not suppressed is a no-op, so a caller may call
// it without first checking whether Begin ever ran.
func (g *AppStopGuard) ReleaseFailed(names ...string) {
	if g == nil || len(names) == 0 {
		return
	}
	g.suppressMu.Lock()
	defer g.suppressMu.Unlock()
	for _, n := range names {
		delete(g.suppressed, n)
	}
}

// SuppressedStacks returns the set of stack names currently exempt from app-down alarms: those an
// operation is holding stopped right now, plus those still inside the post-restart grace window.
//
// Nil-safe on a nil *AppStopGuard so the caller needs no branch — a controller with no guard
// suppresses nothing, which is the correct default.
func (g *AppStopGuard) SuppressedStacks() map[string]bool {
	if g == nil {
		return nil
	}
	now := g.now()
	g.suppressMu.Lock()
	defer g.suppressMu.Unlock()
	out := make(map[string]bool, len(g.suppressed))
	for n, h := range g.suppressed {
		switch {
		case !h.until.IsZero() && !now.Before(h.until):
			delete(g.suppressed, n) // grace expired — reap so the map cannot grow without bound
		case h.until.IsZero() && now.Sub(h.since) >= appStopMaxHold:
			// Held open-ended past the backstop. Say so: an alarm that appears because a hold was
			// never released must be explainable, and standing rule 3 wants a positive observable.
			g.logger.Printf("[WARN] [appstop] %s has been held stopped for over %s with no release — dropping the alarm suppression so a genuine outage is not hidden", n, appStopMaxHold)
			delete(g.suppressed, n)
		default:
			out[n] = true
		}
	}
	return out
}

// appStopHold is one suppressed stack: when the hold started (for appStopMaxHold) and when it
// expires (zero while the app is still held).
type appStopHold struct {
	since time.Time
	until time.Time
}