package backup

import (
	"context"
	"errors"
	"fmt"
	"os"
	"path/filepath"
	"testing"
	"time"

	"gitea.dooplex.hu/admin/felhom-agent/internal/reconcile"
)

// R-86 — the restore-test follows the BACKUP, not the clock.
//
// Every test here DRIVES time (`s.now` is injected and stepped) rather than waiting for it. A test
// that slept could not say anything about a 24-hour rule in under 24 hours, and one that only
// asserted "no error" would pass against a scheduler that never ran anything at all — which is
// precisely the failure mode §8.1's trap produces. So the assertions are: did a test run, on WHICH
// archive, and did a second evaluation correctly run NOTHING.

// ── the fake tier storage ────────────────────────────────────────────────────────────────────

// archiveStub is one archive on a tier: its volid and when it landed.
type archiveStub struct {
	volid  string
	landed time.Time
}

// tierStorage is a TierPicker over per-tier archive lists. It implements the SAME contract as the
// production picker (*BackupRunner).PickSettledRestoreCandidateOn — newest archive that landed at
// or before the cutoff — which is itself covered against a fake PVE API in backup_test.go, and
// end-to-end by the live run. Naming the seam explicitly: everything below is true up to this
// picker; that the real picker obeys the same rule is asserted there, not here.
type tierStorage struct {
	archives map[string][]archiveStub
	err      map[string]error // target → lookup failure
}

func (ts *tierStorage) pick(_ context.Context, target string, notAfter time.Time) (string, time.Time, error) {
	if e, ok := ts.err[target]; ok && e != nil {
		return "", time.Time{}, e
	}
	var best archiveStub
	for _, a := range ts.archives[target] {
		if !notAfter.IsZero() && a.landed.After(notAfter) {
			continue // not settled yet
		}
		if best.volid == "" || a.landed.After(best.landed) {
			best = a
		}
	}
	return best.volid, best.landed, nil
}

// dueHarness is a scheduler with a driven clock over a fake tier storage.
type dueHarness struct {
	s     *Scheduler
	rr    *rotRunner
	st    *RestoreTestState
	ts    *tierStorage
	clock time.Time
	path  string
}

func newDueHarness(t *testing.T, start time.Time, settle time.Duration, pass bool, tiers []string, ts *tierStorage) *dueHarness {
	t.Helper()
	return newDueHarnessAt(t, filepath.Join(t.TempDir(), "rt.json"), start, settle, pass, tiers, ts)
}

func newDueHarnessAt(t *testing.T, statePath string, start time.Time, settle time.Duration, pass bool, tiers []string, ts *tierStorage) *dueHarness {
	t.Helper()
	h := &dueHarness{rr: &rotRunner{pass: pass}, ts: ts, clock: start, path: statePath}
	h.st = NewRestoreTestState(statePath)
	h.s = NewScheduler(SchedulerOptions{
		Runner: h.rr,
		Store:  NewStore(),
		Spec: func(_ context.Context, archive string) reconcile.RestoreTestSpec {
			return reconcile.RestoreTestSpec{RestoreStorage: "local-lvm", ScratchMin: 990000, ScratchMax: 990009}
		},
		Cadence:  time.Hour,
		Settle:   settle,
		Logger:   quiet(),
		Tiers:    tiers,
		TierPick: ts.pick,
		State:    h.st,
		InFlight: &InFlight{},
	})
	h.s.now = func() time.Time { return h.clock }
	return h
}

// advance steps the clock by step, evaluating once at every step — the scheduler's real shape.
func (h *dueHarness) advance(step, total time.Duration) {
	for elapsed := time.Duration(0); elapsed < total; elapsed += step {
		h.clock = h.clock.Add(step)
		h.s.tick(context.Background())
	}
}

var day0 = time.Date(2026, 8, 1, 2, 0, 0, 0, time.UTC)

// dailyArchives lands one archive a day at 02:00 for n days, starting at day0.
func dailyArchives(tier string, n int) []archiveStub {
	out := make([]archiveStub, 0, n)
	for d := 0; d < n; d++ {
		out = append(out, archiveStub{
			volid:  fmt.Sprintf("%s:backup/vzdump-lxc-9201-day%d.tar.zst", tier, d),
			landed: day0.AddDate(0, 0, d),
		})
	}
	return out
}

// ── SCENARIO A — a daily tier is proved daily, on its own archive ────────────────────────────
//
// THE TRAP THIS PINS (§8.1). R-86 reads "trigger a tier ~24 h after its own newest archive", and
// the literal implementation of that — *due when the newest archive is at least `settle` old* — is
// NEVER true on a daily tier: a new archive lands every day, so the newest archive's age resets to
// zero long before it reaches 24 h. The literal reading silently switches restore-testing OFF for
// the tier that matters most.
//
// COMPANION RED-PROOF (observed 2026-08-03). In Scheduler.evaluateTier, the per-archive comparison
// was replaced by the naive age rule:
//
//	-	if ok && proven == archive { … not due … }
//	+	if s.now().Sub(landed) < s.settle { … not due … }   // and the proven-archive check deleted
//
// and the picker cutoff was removed (`cutoff := time.Time{}`), i.e. exactly "is the newest archive
// old enough". Result:
//
//	--- FAIL: TestDue_DailyTierIsProvedDailyOnItsOwnArchive
//	    restoretest_due_test.go: a daily tier must be proved once per day; got 0 run(s) over 5 days
//
// Zero runs — restore-testing off. Restored immediately afterwards.
func TestDue_DailyTierIsProvedDailyOnItsOwnArchive(t *testing.T) {
	ts := &tierStorage{archives: map[string][]archiveStub{"local": dailyArchives("local", 6)}}
	h := newDueHarness(t, day0.Add(time.Hour), 24*time.Hour, true, []string{"local"}, ts)

	// Five days, evaluated hourly.
	h.advance(time.Hour, 5*24*time.Hour)

	got := h.rr.seen()
	if len(got) != 5 {
		t.Fatalf("a daily tier must be proved once per day; got %d run(s) over 5 days: %v", len(got), got)
	}
	// And each run must be on the archive that settled that day — day0's on day 1, and so on.
	for i, a := range got {
		want := fmt.Sprintf("local:backup/vzdump-lxc-9201-day%d.tar.zst", i)
		if a != want {
			t.Fatalf("run %d tested %q, want %q — the test is not following the archive", i+1, a, want)
		}
	}
	// The newest archive is NEVER the one tested: it has not settled.
	if last := got[len(got)-1]; last == "local:backup/vzdump-lxc-9201-day5.tar.zst" {
		t.Fatal("the still-settling archive was tested — the settle cutoff is not being applied")
	}
}

// ── SCENARIO B — a weekly tier is proved weekly, not every other day ─────────────────────────
func TestDue_WeeklyTierIsProvedOncePerArchive(t *testing.T) {
	ts := &tierStorage{archives: map[string][]archiveStub{"felhom-pbs": {
		{volid: "felhom-pbs:backup/ct/9201/w0", landed: day0},
		{volid: "felhom-pbs:backup/ct/9201/w1", landed: day0.AddDate(0, 0, 7)},
		{volid: "felhom-pbs:backup/ct/9201/w2", landed: day0.AddDate(0, 0, 14)},
	}}}
	h := newDueHarness(t, day0.Add(time.Hour), 24*time.Hour, true, []string{"felhom-pbs"}, ts)

	// Three weeks, evaluated every 6 hours — 84 evaluations.
	h.advance(6*time.Hour, 21*24*time.Hour)

	got := h.rr.seen()
	want := []string{
		"felhom-pbs:backup/ct/9201/w0",
		"felhom-pbs:backup/ct/9201/w1",
		"felhom-pbs:backup/ct/9201/w2",
	}
	if len(got) != len(want) {
		t.Fatalf("a weekly tier must be proved ONCE PER ARCHIVE (3 archives over 3 weeks); got %d run(s): %v", len(got), got)
	}
	for i := range want {
		if got[i] != want[i] {
			t.Fatalf("run %d tested %q, want %q", i+1, got[i], want[i])
		}
	}
}

// ── SCENARIO C — an agent restart does not change the schedule ───────────────────────────────
//
// This is the defect a person actually notices: today every deploy restarts the ticker, so a
// restore-test runs one interval after each deploy regardless of what has already been proven.
//
// COMPANION RED-PROOF (observed 2026-08-03): revert the state to per-tier TIME by making
// ProvenArchive ignore the stored archive —
//
//	-	if !ok || p.Archive == "" { return "", false }
//	+	return "", false     // per-tier time only, the pre-R-86 state
//
// →	--- FAIL: TestDue_RestartRunsNothing
//	    restoretest_due_test.go:226: an agent restart must not trigger a restore-test; 2 restart(s)
//	    produced 4 run(s)
//
// Four: the same already-proven archive re-tested on EVERY evaluation after EVERY restart, which is
// today's behaviour with the ticker's phase reset by the deploy. Restored.
func TestDue_RestartRunsNothing(t *testing.T) {
	dir := t.TempDir()
	path := filepath.Join(dir, "rt.json")
	ts := &tierStorage{archives: map[string][]archiveStub{"local": dailyArchives("local", 2)}}
	start := day0.AddDate(0, 0, 1).Add(time.Hour) // day 1, 03:00 — day0's archive has settled

	h := newDueHarnessAt(t, path, start, 24*time.Hour, true, []string{"local"}, ts)
	h.s.tick(context.Background())
	if n := len(h.rr.seen()); n != 1 {
		t.Fatalf("precondition: the settled archive should have been proved once; got %d run(s)", n)
	}

	// --- two restarts: brand-new scheduler + brand-new state object over the SAME file ---
	total := 0
	for i := 0; i < 2; i++ {
		h2 := newDueHarnessAt(t, path, start.Add(time.Duration(i+1)*time.Hour), 24*time.Hour, true, []string{"local"}, ts)
		h2.s.tick(context.Background())
		h2.s.tick(context.Background())
		total += len(h2.rr.seen())
	}
	if total != 0 {
		t.Fatalf("an agent restart must not trigger a restore-test; 2 restart(s) produced %d run(s)", total)
	}
}

// ── SCENARIO D — a new archive makes a tier due even if it was tested yesterday ──────────────
func TestDue_NewSettledArchiveMakesAProvedTierDueAgain(t *testing.T) {
	ts := &tierStorage{archives: map[string][]archiveStub{"local": dailyArchives("local", 2)}}
	h := newDueHarness(t, day0.AddDate(0, 0, 1).Add(time.Hour), 24*time.Hour, true, []string{"local"}, ts)

	h.s.tick(context.Background()) // proves day0's archive
	h.s.tick(context.Background()) // nothing new has settled → nothing
	if n := len(h.rr.seen()); n != 1 {
		t.Fatalf("want exactly 1 run before the new archive settles, got %d: %v", n, h.rr.seen())
	}

	// Day 2, 03:00 — day1's archive has now settled.
	h.clock = day0.AddDate(0, 0, 2).Add(time.Hour)
	h.s.tick(context.Background())

	got := h.rr.seen()
	if len(got) != 2 {
		t.Fatalf("a newly settled archive must make the tier due again; got %v", got)
	}
	if got[1] != "local:backup/vzdump-lxc-9201-day1.tar.zst" {
		t.Fatalf("the NEW archive must be the one tested; got %q", got[1])
	}
}

// ── SCENARIO E — a failing tier keeps being retried, and earns no proof ──────────────────────
//
// COMPANION RED-PROOF (observed 2026-08-03): give credit on failure in Scheduler.tick —
//
//	-	if rt.Pass && s.rtState != nil && target != "" {
//	+	if s.rtState != nil && target != "" {
//
// →	--- FAIL: TestDue_FailingTierIsRetriedAndNeverProven
//	    restoretest_due_test.go: a failing tier must keep being retried; got 1 run(s) over 3
//	    evaluations
//
// A single failure would have retired the archive as proven — a permanently broken DR tier looking
// freshly verified, which is the loudest signal this system produces going silent. Restored.
func TestDue_FailingTierIsRetriedAndNeverProven(t *testing.T) {
	ts := &tierStorage{archives: map[string][]archiveStub{"local": dailyArchives("local", 1)}}
	h := newDueHarness(t, day0.AddDate(0, 0, 1).Add(time.Hour), 24*time.Hour, false, []string{"local"}, ts)

	for i := 0; i < 3; i++ {
		h.s.tick(context.Background())
	}

	got := h.rr.seen()
	if len(got) != 3 {
		t.Fatalf("a failing tier must keep being retried; got %d run(s) over 3 evaluations: %v", len(got), got)
	}
	if _, ok := h.st.ProvenArchive("local"); ok {
		t.Fatal("a FAILED restore-test must not record the archive as proven")
	}
	if _, ok := h.st.LastSuccess("local"); ok {
		t.Fatal("a FAILED restore-test must not stamp the tier as proven")
	}
}

// ── SCENARIO F — two tiers due at once do not run at once ────────────────────────────────────
func TestDue_TwoDueTiersRunOneAtATime(t *testing.T) {
	ts := &tierStorage{archives: map[string][]archiveStub{
		"local":      {{volid: "local:backup/a.tar.zst", landed: day0}},
		"felhom-pbs": {{volid: "felhom-pbs:backup/ct/9201/a", landed: day0}},
	}}
	h := newDueHarness(t, day0.AddDate(0, 0, 1).Add(time.Hour), 24*time.Hour, true, []string{"local", "felhom-pbs"}, ts)

	// Both tiers are due at this instant.
	due := h.s.EvaluateDue(context.Background())
	if len(due) != 2 || !due[0].Due || !due[1].Due {
		t.Fatalf("precondition: both tiers should be due; got %v", due)
	}

	h.s.tick(context.Background())
	if n := len(h.rr.seen()); n != 1 {
		t.Fatalf("ONE evaluation must start ONE restore-test, never two multi-GB restores over one link; got %d: %v", n, h.rr.seen())
	}

	// The other tier was DEFERRED, not cancelled: it is still due and runs on the next evaluation.
	h.s.tick(context.Background())
	got := h.rr.seen()
	if len(got) != 2 || got[0] == got[1] {
		t.Fatalf("the deferred tier must run on the NEXT evaluation, on its own archive; got %v", got)
	}
}

// The heavy-operation gate still holds, and a tier deferred behind a backup stays DUE.
func TestDue_DeferredBehindABackupStaysDue(t *testing.T) {
	ts := &tierStorage{archives: map[string][]archiveStub{"local": {{volid: "local:backup/a.tar.zst", landed: day0}}}}
	h := newDueHarness(t, day0.AddDate(0, 0, 1).Add(time.Hour), 24*time.Hour, true, []string{"local"}, ts)

	gate := &InFlight{}
	h.s.inFlight = gate
	release, _, _ := gate.TryAcquire("backup:felhom-pbs")

	h.s.tick(context.Background())
	if n := len(h.rr.seen()); n != 0 {
		t.Fatalf("the restore-test must DEFER while a backup holds the gate; got %d run(s)", n)
	}
	if due := h.s.EvaluateDue(context.Background()); !due[0].Due {
		t.Fatal("a deferred tier must remain DUE — deferral is not dismissal")
	}
	release()
	h.s.tick(context.Background())
	if n := len(h.rr.seen()); n != 1 {
		t.Fatalf("must resume once the gate frees; got %d run(s)", n)
	}
}

// ── SCENARIO H — a newborn box is UNKNOWN, not stale and not a fault ─────────────────────────
func TestDue_NewbornTierIsNotDueAndNotAnError(t *testing.T) {
	ts := &tierStorage{archives: map[string][]archiveStub{"felhom-pbs": nil}}
	h := newDueHarness(t, day0, 24*time.Hour, true, []string{"felhom-pbs"}, ts)

	due := h.s.EvaluateDue(context.Background())
	if len(due) != 1 {
		t.Fatalf("want one verdict, got %v", due)
	}
	v := due[0]
	if v.Due || v.Err != nil || v.Archive != "" {
		t.Fatalf("a tier with no archive is UNKNOWN — not due, not an error; got %+v", v)
	}
	if v.Reason == "" {
		t.Fatal("every verdict must carry a reason — a due-check that cannot say why is a quiet path")
	}
	h.s.tick(context.Background())
	if n := len(h.rr.seen()); n != 0 {
		t.Fatalf("a newborn tier must not be restore-tested; got %d run(s)", n)
	}
}

// An archive that exists but has NOT settled yet is not a candidate — and that is not an error.
func TestDue_UnsettledArchiveIsNotACandidate(t *testing.T) {
	ts := &tierStorage{archives: map[string][]archiveStub{"local": {{volid: "local:backup/fresh.tar.zst", landed: day0}}}}
	h := newDueHarness(t, day0.Add(2*time.Hour), 24*time.Hour, true, []string{"local"}, ts)

	if v := h.s.EvaluateDue(context.Background())[0]; v.Due || v.Archive != "" {
		t.Fatalf("an archive 2h old must not be a candidate under a 24h settle lag; got %+v", v)
	}
	h.s.tick(context.Background())
	if n := len(h.rr.seen()); n != 0 {
		t.Fatalf("nothing settled → no run; got %d", n)
	}
}

// A tier whose archives cannot be LISTED is UNKNOWN — never silently "not due", and never silent.
// Treating a lookup failure as "not due" would retire a tier the moment its storage stopped
// answering, which is the same absence-is-not-evidence error this monitor family keeps making.
func TestDue_LookupFailureIsUnknownNotNotDue(t *testing.T) {
	boom := errors.New("storage unreachable")
	ts := &tierStorage{
		archives: map[string][]archiveStub{"local": {{volid: "local:backup/a.tar.zst", landed: day0}}},
		err:      map[string]error{"felhom-pbs": boom},
	}
	h := newDueHarness(t, day0.AddDate(0, 0, 1), 24*time.Hour, true, []string{"local", "felhom-pbs"}, ts)

	var pbs DueVerdict
	for _, v := range h.s.EvaluateDue(context.Background()) {
		if v.Target == "felhom-pbs" {
			pbs = v
		}
	}
	if pbs.Err == nil {
		t.Fatal("a lookup failure must travel in the verdict, not be swallowed")
	}
	if pbs.Due {
		t.Fatal("a tier we could not list must not be reported DUE — we have no archive to test")
	}
	if pbs.Reason == "" {
		t.Fatal("the failure must be explained, not merely flagged")
	}

	// And the OTHER tier still runs: one tier's storage being unreadable must not cost the other
	// tier its proof.
	h.s.tick(context.Background())
	if got := h.rr.seen(); len(got) != 1 || got[0] != "local:backup/a.tar.zst" {
		t.Fatalf("the readable tier must still be proved; got %v", got)
	}
}

// ── the state's migration (§8.2) ─────────────────────────────────────────────────────────────

// A pre-R-86 state file carries a TIME and no archive. It must keep its time (rotation ordering
// survives the upgrade) and yield NO proven archive, so each tier is due exactly once. Reading a
// legacy time as proof of the CURRENT archive would mark an unproven archive proven — a guarantee
// invented by a migration.
func TestRestoreTestState_LegacyFileMigratesToNothingProven(t *testing.T) {
	path := filepath.Join(t.TempDir(), "rt.json")
	legacy := `{"local":"2026-08-01T02:00:00Z","felhom-pbs":"2026-07-30T02:00:00Z"}`
	if err := writeFileForTest(path, legacy); err != nil {
		t.Fatal(err)
	}

	st := NewRestoreTestState(path)
	if _, ok := st.ProvenArchive("local"); ok {
		t.Fatal("a legacy record names no archive — it must NOT be read as proof of the current one")
	}
	at, ok := st.LastSuccess("local")
	if !ok || !at.Equal(time.Date(2026, 8, 1, 2, 0, 0, 0, time.UTC)) {
		t.Fatalf("the legacy TIME must survive (rotation ordering depends on it); got %v ok=%v", at, ok)
	}
	// Ordering still works off the legacy times.
	if got := st.OldestFirst([]string{"local", "felhom-pbs"}); got[0] != "felhom-pbs" {
		t.Fatalf("oldest-first must still order legacy records; got %v", got)
	}
}

// The new shape round-trips, archive and all.
func TestRestoreTestState_ArchiveRoundTrips(t *testing.T) {
	path := filepath.Join(t.TempDir(), "rt.json")
	now := time.Now().UTC().Truncate(time.Second)
	st := NewRestoreTestState(path)
	if err := st.RecordSuccess("felhom-pbs", "felhom-pbs:backup/ct/9201/x", now); err != nil {
		t.Fatal(err)
	}
	re := NewRestoreTestState(path)
	got, ok := re.ProvenArchive("felhom-pbs")
	if !ok || got != "felhom-pbs:backup/ct/9201/x" {
		t.Fatalf("the proven ARCHIVE must survive a restart; got %q ok=%v", got, ok)
	}
	at, ok := re.LastSuccess("felhom-pbs")
	if !ok || !at.Equal(now) {
		t.Fatalf("the proven TIME must survive too; got %v ok=%v", at, ok)
	}
}

// writeFileForTest is a tiny helper so the legacy-migration fixture reads clearly above.
func writeFileForTest(path, content string) error {
	return os.WriteFile(path, []byte(content), 0o600)
}