felhom-controller/controller/internal/web/backup_handlers.go

package web

import (
	"context"
	"errors"
	"net/http"
	"strings"
	"time"

	"gitea.dooplex.hu/admin/felhom-controller/internal/agentapi"
	"gitea.dooplex.hu/admin/felhom-controller/internal/backupwindow"
	"gitea.dooplex.hu/admin/felhom-controller/internal/quiesce"
	"gitea.dooplex.hu/admin/felhom-controller/internal/scheduler"
)

// effectiveBackupWindow resolves the active backup-window start (settings > controller.yaml >
// "02:30") for this server. Every nightly-leg display and the DB-dump next-run derive from it.
func (s *Server) effectiveBackupWindow() string {
	return backupwindow.EffectiveWindow(s.settings.GetBackupWindowStart(), s.cfg.Backup.DBDumpSchedule)
}

// backupWindowData injects the customer-configurable-window view onto the Áttekintés page: the
// effective start, the three derived leg times (DB / helyi másolat / távoli mentés), and the
// whole-guest gate span [W+2h, W+6h). The offsets are DERIVED here, never stored.
func (s *Server) backupWindowData(data map[string]interface{}) {
	win := s.effectiveBackupWindow()
	db, tier2, offbox := backupwindow.LegTimes(win)
	from, to := backupwindow.GateWindow(win)
	data["BackupWindow"] = win
	data["BackupLegDB"] = db
	data["BackupLegTier2"] = tier2
	data["BackupLegOffbox"] = offbox
	data["BackupGateFrom"] = from
	data["BackupGateTo"] = to
}

// backupWindowSaveHandler persists a new backup-window start and fans it out to the three daily legs
// live (no restart) via UpdateDaily. POST /backups/window (behind RequireAuth + CsrfProtect). On an
// invalid time nothing is stored and the jobs are untouched.
func (s *Server) backupWindowSaveHandler(w http.ResponseWriter, r *http.Request) {
	_ = r.ParseForm()
	start := strings.TrimSpace(r.FormValue("window_start"))
	if backupwindow.Valid(start) != nil {
		s.backupWindowRedirect(w, r, "", "flash.backup.window_invalid_time")
		return
	}
	if err := s.settings.SetBackupWindowStart(start); err != nil {
		s.logger.Printf("[ERROR] [web] backup window save failed: %v", err)
		s.backupWindowRedirect(w, r, "", "flash.backup.window_save_failed")
		return
	}
	// Fan out to the three daily legs at their fixed offsets — takes effect at the next scheduling
	// pass (no restart). The scheduler wakes each job via its reschedule signal.
	db, tier2, offbox := backupwindow.LegTimes(start)
	if s.scheduler != nil {
		s.scheduler.UpdateDaily("db-dump", db)
		s.scheduler.UpdateDaily("tier2-backup", tier2)
		s.scheduler.UpdateDaily("offbox-backup", offbox)
	}
	// Refresh the cached "next DB dump" so the display updates immediately, not at the next 5m tick.
	if s.backupMgr != nil {
		s.backupMgr.RefreshCache(scheduler.NextDailyRun(db))
	}
	s.logger.Printf("[INFO] [web] backup window set to %s (legs %s/%s/%s)", start, db, tier2, offbox)
	s.backupWindowRedirect(w, r, "flash.backup.window_updated", "")
}

// backupWindowRedirect PRG-redirects back to the Áttekintés page with a success or error flash.
func (s *Server) backupWindowRedirect(w http.ResponseWriter, r *http.Request, flash, flashErr string) {
	dest := "/backups"
	if flashErr != "" {
		dest += "?" + flashQuery("flash_error", flashErr)
	} else if flash != "" {
		dest += "?" + flashQuery("flash", flash)
	}
	http.Redirect(w, r, dest, http.StatusSeeOther)
}

// Whole-guest backup visibility + manual trigger (spec Part 2). The agent owns whole-guest
// vzdump/PBS backup; the controller is a read-only window onto it (GET /backup/{status,due},
// /restore-test/status) plus a "Mentés most" trigger that goes through the quiesce loop (the
// CONTROLLER owns quiescing — stop stacks → POST /backup → resume — so the captured state is
// app-consistent, not the agent's crash-consistent default). Cadence/retention CONFIG is NOT here
// (hub-served policy, slice 10).

// guestBackupView is the template payload for the "Rendszermentés" section. Times are time.Time so
// the existing fmtTime/timeAgo funcmap helpers format them; size is int64 for fmtBytes.
type guestBackupView struct {
	Available bool   // agent reachable + a status read succeeded
	Note      string // shown when not Available (unprovisioned / unreachable)

	Phase   string // idle | running | snapshotted | done | failed
	Running bool   // a backup job is in progress now

	HasBackup bool
	Success   bool
	StartedAt time.Time
	SizeBytes int64
	Target    string // human label: "Biztonsági szerver – külön hardver (PBS)" / "Helyi tároló (local)"
	Offsite   bool   // the whole-guest backup landed on the PBS offsite tier (separate hardware)
	Archive   string
	Mode      string // snapshot | stop
	StopMode  bool   // mode == stop → full app downtime during the backup (warn)

	Due       bool
	DueReason string
	AgeHours  int64 // age of the newest successful backup, hours (for "X órája")

	HasRestoreTest  bool
	RestorePass     bool
	RestoreVerified string
	RestoreTestedAt time.Time

	CanTrigger bool // a backup trigger (quiesce loop) is wired

	// SizeUnknown (R-517): the shown success was read back from storage after an agent restart, so
	// its size is not known. The tile prints „–", never „0 B" (measured live on 9201, 2026-09-15).
	SizeUnknown bool

	// Tiers (R-517, agent >= v0.131.0) is the per-tier truth. Empty on an older agent — the tile then
	// renders the single latest record as before.
	Tiers []guestTierView
}

// guestTierView is one whole-guest tier as the customer sees it. A failed attempt is shown UNDER the
// newest success, never instead of it ("presence is not success").
type guestTierView struct {
	Target      string
	Label       string // Hungarian tier name
	IsPBS       bool
	NotSetUp    bool // the tier's storage does not exist on the host → „nincs beállítva"
	HasSuccess  bool
	SuccessAt   time.Time
	SizeKnown   bool // false when the success was read back from storage after a restart
	SizeBytes   int64
	Current     bool // newest success is inside the tier's window
	FailedAfter bool // the last attempt failed and is newer than the newest success
	FailedAt    time.Time
}

// tierWindow is how old a tier's newest success may be and still count as current: its cadence plus
// half again (a scheduled run lands inside the nightly window, not on the exact second). A tier with
// no advertised cadence uses a day.
func tierWindow(cadenceSecs int64) time.Duration {
	if cadenceSecs <= 0 {
		cadenceSecs = 24 * 3600
	}
	return time.Duration(cadenceSecs) * time.Second * 3 / 2
}

// buildTierViews turns the agent's per-tier state into page rows and derives the three legacy tile
// fields from SUCCESSES only: HasBackup/Success/Size/Target/StartedAt from the primary tier's newest
// success; Due when any set-up tier has no current success; Offsite only on a current PBS success.
func buildTierViews(v *guestBackupView, tiers []agentapi.TierBackupState, cadence map[string]int64, now time.Time, msg func(key string, a ...interface{}) string) {
	v.Tiers = nil
	v.Due, v.Offsite, v.HasBackup = false, false, false
	var newestOK time.Time
	for _, t := range tiers {
		tv := guestTierView{Target: t.Target, IsPBS: strings.Contains(strings.ToLower(t.Target), "pbs")}
		if tv.IsPBS {
			tv.Label = msg("backup.tier.pbs")
		} else {
			tv.Label = msg("backup.tier.local", t.Target)
		}
		tv.NotSetUp = t.Storage == "absent"
		if t.LastSuccess != nil {
			if ts, err := time.Parse(time.RFC3339, t.LastSuccess.StartedAt); err == nil {
				tv.HasSuccess, tv.SuccessAt = true, ts
				tv.SizeKnown = t.LastSuccessSource != "storage"
				tv.SizeBytes = t.LastSuccess.SizeBytes
				tv.Current = now.Sub(ts) <= tierWindow(cadence[t.Target])
			}
		}
		if a := t.LastAttempt; a != nil && !a.Success {
			if ts, err := time.Parse(time.RFC3339, a.StartedAt); err == nil && (!tv.HasSuccess || ts.After(tv.SuccessAt)) {
				tv.FailedAfter, tv.FailedAt = true, ts
			}
		}
		if !tv.NotSetUp && !tv.Current {
			v.Due = true
		}
		if tv.IsPBS && tv.Current && !tv.NotSetUp {
			v.Offsite = true
		}
		if tv.HasSuccess && (t.Primary || !v.HasBackup) && (t.Primary || tv.SuccessAt.After(newestOK)) {
			v.HasBackup, v.Success = true, true
			v.StartedAt, v.SizeBytes, v.Target = tv.SuccessAt, tv.SizeBytes, tv.Label
			v.SizeUnknown = !tv.SizeKnown
			newestOK = tv.SuccessAt
		}
		v.Tiers = append(v.Tiers, tv)
	}
	if v.Due {
		v.DueReason = "tier_not_current"
	}
	if v.HasBackup {
		v.AgeHours = int64(now.Sub(v.StartedAt).Hours())
	}
}

// loadGuestBackup fetches the agent's whole-guest backup view (best-effort). Returns a view with
// Available=false (+ a note) when the agent isn't configured/reachable — the page still renders.
func (s *Server) loadGuestBackup(ctx context.Context, lang string) *guestBackupView {
	msg := func(key string, a ...interface{}) string { return s.msgLang(lang, key, a...) }
	v := &guestBackupView{CanTrigger: s.backupTrigger != nil}
	client, err := s.agentClient()
	if err != nil {
		v.Note = msg("backup.guest.agent_unconfigured")
		return v
	}
	st, err := client.BackupStatus(ctx)
	if err != nil {
		v.Note = msg("backup.guest.agent_unreachable")
		return v
	}
	v.Available = true
	v.Phase = st.Phase
	v.Running = st.Phase == agentapi.PhaseRunning || st.Phase == "snapshotted"
	if st.Backup != nil {
		v.HasBackup = true
		v.Success = st.Backup.Success
		v.SizeBytes = st.Backup.SizeBytes
		v.Archive = st.Backup.Archive
		v.Mode = st.Backup.Mode
		v.StopMode = st.Backup.Mode == "stop"
		v.Target = backupTargetLabel(st.Backup, msg)
		v.Offsite = backupIsPBS(st.Backup)
		if t, perr := time.Parse(time.RFC3339, st.Backup.StartedAt); perr == nil {
			v.StartedAt = t
		}
	}
	// Due window (best-effort; a failure just leaves the due fields zero).
	if due, derr := client.BackupDue(ctx); derr == nil {
		v.Due = due.Due
		v.DueReason = due.Reason
		if due.AgeSecs != nil {
			v.AgeHours = *due.AgeSecs / 3600
		}
	}
	// R-517: an agent that speaks per tier replaces the single-record fields with per-tier truth.
	// Done AFTER the legacy fill so an older agent keeps exactly the old rendering.
	if len(st.Tiers) > 0 {
		cadence := map[string]int64{}
		if tr, terr := client.BackupTiers(ctx); terr == nil {
			for _, t := range tr.Tiers {
				cadence[t.Target] = t.CadenceSeconds
			}
		}
		buildTierViews(v, st.Tiers, cadence, time.Now(), msg)
	}
	// Restore-test (the "verified restorable" trust signal; nil until one runs).
	if rt, rerr := client.RestoreTestStatus(ctx); rerr == nil && rt != nil {
		v.HasRestoreTest = true
		v.RestorePass = rt.Pass
		v.RestoreVerified = rt.Verified
		if t, perr := time.Parse(time.RFC3339, rt.TestedAt); perr == nil {
			v.RestoreTestedAt = t
		}
	}
	return v
}

// backupIsPBS reports whether a whole-guest backup landed on the PBS offsite tier (separate
// hardware), inferred from the target id / archive volid ("felhom-pbs"/"pbs:" ⇒ PBS).
func backupIsPBS(b *agentapi.BackupRecord) bool {
	id := strings.ToLower(b.TargetID)
	arc := strings.ToLower(b.Archive)
	return strings.Contains(id, "pbs") || strings.HasPrefix(arc, "felhom-pbs") || strings.Contains(arc, "pbs:")
}

// backupTargetLabel maps the agent's backup target to a customer-facing Hungarian label. The PBS
// case calls out that the backup is on SEPARATE HARDWARE (real disaster recovery — survives a host
// disk/hardware failure), which is the whole point of re-pointing the backup offsite.
func backupTargetLabel(b *agentapi.BackupRecord, msg func(key string, a ...interface{}) string) string {
	if backupIsPBS(b) {
		return msg("backup.tier.pbs")
	}
	if b.TargetID != "" {
		return msg("backup.tier.local", b.TargetID)
	}
	return msg("backup.tier.local_plain")
}

// ServeBackupAPI dispatches /api/guest-backup/* (whole-guest manual trigger + status poll). A
// distinct prefix from apiRouter's app-data /api/backup/{run,status}. Wired behind RequireAuth +
// CsrfProtect in main.go.
func (s *Server) ServeBackupAPI(w http.ResponseWriter, r *http.Request) {
	switch {
	case r.URL.Path == "/api/guest-backup/trigger" && r.Method == http.MethodPost:
		s.handleBackupTriggerAPI(w, r)
	case r.URL.Path == "/api/guest-backup/status" && r.Method == http.MethodGet:
		s.handleBackupStatusAPI(w, r)
	default:
		http.NotFound(w, r)
	}
}

// handleBackupTriggerAPI starts an app-consistent whole-guest backup NOW via the quiesce loop. It
// returns immediately (the backup runs async, minutes); the page polls /api/backup/status.
func (s *Server) handleBackupTriggerAPI(w http.ResponseWriter, r *http.Request) {
	if s.backupTrigger == nil {
		writeDiskJSON(w, http.StatusServiceUnavailable, false, s.msg(r, "backup.guest.err.unavailable"), nil)
		return
	}
	if err := s.backupTrigger.TriggerNow(); err != nil {
		if errors.Is(err, quiesce.ErrBackupInProgress) {
			writeDiskJSON(w, http.StatusConflict, false, s.msg(r, "backup.guest.err.in_progress"), nil)
			return
		}
		s.logger.Printf("[ERROR] [web] backup trigger failed: %v", err)
		writeDiskJSON(w, http.StatusBadGateway, false, s.errText(r, err), nil)
		return
	}
	s.logger.Printf("[INFO] [web] manual whole-guest backup triggered (quiesce loop)")
	writeDiskJSON(w, http.StatusOK, true, "", map[string]any{"started": true})
}

// handleBackupStatusAPI proxies the agent's GET /backup/status for the page's progress poll.
func (s *Server) handleBackupStatusAPI(w http.ResponseWriter, r *http.Request) {
	client, err := s.agentClient()
	if err != nil {
		writeDiskJSON(w, http.StatusServiceUnavailable, false, s.errText(r, err), nil)
		return
	}
	st, err := client.BackupStatus(r.Context())
	if err != nil {
		writeDiskJSON(w, http.StatusBadGateway, false, s.errText(r, err), nil)
		return
	}
	writeDiskJSON(w, http.StatusOK, true, "", map[string]any{
		"phase": st.Phase, "job_id": st.JobID, "error": st.Error, "backup": st.Backup,
	})
}