felhom-agent/internal/backup/backup_test.go

package backup

import (
	"context"
	"encoding/json"
	"errors"
	"io"
	"log/slog"
	"testing"
	"time"

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

func quiet() *slog.Logger { return slog.New(slog.NewTextHandler(io.Discard, nil)) }

// fakeBackupAPI is a synthetic BackupAPI.
type fakeBackupAPI struct {
	vzdumpUPID string
	vzdumpErr  error
	waitErr    error
	cfg        proxmox.GuestConfig
	cfgErr     error
	content    []proxmox.StorageContent
	contentErr error
	storages   []proxmox.Storage // returned by ListStorage (the local-prune scope gate)
	storageErr error
	vzdumps    []proxmox.VzdumpOptions
	logLines   []string      // returned by TaskLogTail (e.g. "INFO: backup mode: stop")
	waitGate   chan struct{} // if non-nil, WaitTask blocks until closed (8B.2 watcher timing)
}

func (f *fakeBackupAPI) Vzdump(_ context.Context, o proxmox.VzdumpOptions) (string, error) {
	f.vzdumps = append(f.vzdumps, o)
	return f.vzdumpUPID, f.vzdumpErr
}
func (f *fakeBackupAPI) WaitTask(_ context.Context, _ string, _ proxmox.WaitOptions) (proxmox.TaskStatus, error) {
	if f.waitGate != nil {
		<-f.waitGate
	}
	return proxmox.TaskStatus{Status: "stopped", ExitStatus: "OK"}, f.waitErr
}
func (f *fakeBackupAPI) GuestConfig(_ context.Context, _ int) (proxmox.GuestConfig, error) {
	return f.cfg, f.cfgErr
}
func (f *fakeBackupAPI) StorageContent(_ context.Context, _ string) ([]proxmox.StorageContent, error) {
	return f.content, f.contentErr
}
func (f *fakeBackupAPI) ListStorage(_ context.Context) ([]proxmox.Storage, error) {
	return f.storages, f.storageErr
}
func (f *fakeBackupAPI) TaskLogTail(_ context.Context, _ string, _ int) ([]string, error) {
	return f.logLines, nil
}

// guestCfgWithMounts builds a GuestConfig whose Extra carries the given mpN strings.
func guestCfgWithMounts(mps map[string]string) proxmox.GuestConfig {
	extra := map[string]json.RawMessage{}
	for k, v := range mps {
		b, _ := json.Marshal(v)
		extra[k] = b
	}
	return proxmox.GuestConfig{Extra: extra}
}

func TestBackup_SuccessResolvesArchiveAndBulkGap(t *testing.T) {
	api := &fakeBackupAPI{
		vzdumpUPID: "UPID:vzdump:1",
		cfg: guestCfgWithMounts(map[string]string{
			"mp0": "local-lvm:8,mp=/mnt/bulk,backup=0", // explicit opt-out → uncovered
			"mp1": "local-lvm:4,mp=/mnt/db,backup=1",   // covered
			"mp2": "local-lvm:2,mp=/mnt/scratch",       // UNSET → uncovered (opt-in default)
		}),
		content: []proxmox.StorageContent{
			{VolID: "local:backup/old-9001.tar.zst", Content: "backup", VMID: 9001, Size: 100, CTime: 100},
			{VolID: "local:backup/new-9001.tar.zst", Content: "backup", VMID: 9001, Size: 524288000, CTime: 200},
			{VolID: "local:backup/other-9002.tar.zst", Content: "backup", VMID: 9002, Size: 7, CTime: 999},
		},
	}
	r := NewBackupRunner(api, "local", "", "felhom test", "", quiet())
	rec, err := r.Backup(context.Background(), 9001)
	if err != nil {
		t.Fatalf("Backup: %v", err)
	}
	if !rec.Success || !rec.CrashConsistent {
		t.Errorf("record = %+v, want success + crash_consistent", rec)
	}
	if rec.Archive != "local:backup/new-9001.tar.zst" || rec.SizeBytes != 524288000 {
		t.Errorf("resolved wrong archive/size: %+v", rec)
	}
	if rec.Mode != string(proxmox.ModeSnapshot) {
		t.Errorf("mode = %q, want snapshot (default)", rec.Mode)
	}
	// Bulk gap: mp0 (backup=0) AND mp2 (unset) are uncovered; mp1 (backup=1) is NOT.
	if got := rec.UncoveredVolumes; len(got) != 2 || !has(got, "/mnt/bulk") || !has(got, "/mnt/scratch") {
		t.Errorf("uncovered = %v, want [/mnt/bulk /mnt/scratch] (unset is uncovered too)", got)
	}
	if has(rec.UncoveredVolumes, "/mnt/db") {
		t.Error("backup=1 mountpoint must NOT be reported uncovered")
	}
	// Notes-template threaded through.
	if len(api.vzdumps) != 1 || api.vzdumps[0].Notes != "felhom test" {
		t.Errorf("vzdump opts = %+v", api.vzdumps)
	}
}

func TestBackup_ReportsActualModeFromTaskLog(t *testing.T) {
	// Requested snapshot, but PVE used stop (stopped guest) — the report must reflect ACTUAL.
	api := &fakeBackupAPI{
		vzdumpUPID: "UPID:vzdump:1",
		content:    []proxmox.StorageContent{{VolID: "v", Content: "backup", VMID: 9001, Size: 10, CTime: 1}},
		logLines:   []string{"INFO: CT Name: spike", "INFO: backup mode: stop", "INFO: Finished"},
	}
	r := NewBackupRunner(api, "local", proxmox.ModeSnapshot, "", "", quiet())
	rec, err := r.Backup(context.Background(), 9001)
	if err != nil {
		t.Fatal(err)
	}
	if rec.Mode != "stop" {
		t.Errorf("mode = %q, want the ACTUAL %q from the task log (not the requested snapshot)", rec.Mode, "stop")
	}
}

func TestBackup_VzdumpFailureReturnsFailedRecord(t *testing.T) {
	api := &fakeBackupAPI{vzdumpErr: errors.New("vzdump boom")}
	r := NewBackupRunner(api, "local", "", "", "", quiet())
	rec, err := r.Backup(context.Background(), 9001)
	if err == nil {
		t.Fatal("expected error")
	}
	if rec.Success || rec.Error == "" {
		t.Errorf("failed backup must produce a Success=false record with an Error: %+v", rec)
	}
}

func TestPickRestoreCandidate_NewestOrEmpty(t *testing.T) {
	const big = 4 << 30 // a plausible whole-guest archive
	api := &fakeBackupAPI{content: []proxmox.StorageContent{
		{VolID: "a", Content: "backup", CTime: 10, Size: big},
		{VolID: "b", Content: "backup", CTime: 99, Size: big},
		{VolID: "iso", Content: "iso", CTime: 999, Size: big}, // not a backup → ignored
	}}
	r := NewBackupRunner(api, "local", "", "", "", quiet())
	vol, err := r.PickRestoreCandidate(context.Background())
	if err != nil || vol != "b" {
		t.Fatalf("pick = %q,%v want newest 'b'", vol, err)
	}
	// no backups → "".
	api.content = []proxmox.StorageContent{{VolID: "iso", Content: "iso"}}
	if vol, _ := r.PickRestoreCandidate(context.Background()); vol != "" {
		t.Errorf("no backup → empty, got %q", vol)
	}
}

// R-86: the NEWEST entry is not a candidate if it cannot be a complete archive. An incomplete
// artefact (F-CRIT-2's 1-byte phantom, which server-side prune does not collect) would otherwise be
// picked forever, fail its restore forever, never earn proof, and so leave the tier due at every
// evaluation — turning the evaluation interval into the retry rate for a multi-GB restore.
//
// COMPANION RED-PROOF (observed): drop the `archivePlausiblyComplete` guard from
// PickSettledRestoreCandidateOn and this fails with
// `pick = "phantom" want the newest COMPLETE archive 'real'`.
func TestPickRestoreCandidate_SkipsImplausibleArchives(t *testing.T) {
	api := &fakeBackupAPI{content: []proxmox.StorageContent{
		{VolID: "real", Content: "backup", CTime: 10, Size: 4 << 30},
		{VolID: "phantom", Content: "backup", CTime: 99, Size: 1}, // newest, and impossible
	}}
	r := NewBackupRunner(api, "local", "", "", "", quiet())
	vol, err := r.PickRestoreCandidate(context.Background())
	if err != nil || vol != "real" {
		t.Fatalf("pick = %q,%v want the newest COMPLETE archive 'real'", vol, err)
	}
}

// --- scheduler ---

type fakeRTRunner struct {
	res  reconcile.RestoreTestResult
	runs int
}

func (f *fakeRTRunner) RunRestoreTest(_ context.Context, _ reconcile.RestoreTestSpec) reconcile.RestoreTestResult {
	f.runs++
	return f.res
}

func TestScheduler_TickRunsAndRecords(t *testing.T) {
	store := NewStore()
	rt := &fakeRTRunner{res: reconcile.RestoreTestResult{Archive: "vol", Pass: true, Verified: "boot+running", Duration: time.Second}}
	s := NewScheduler(SchedulerOptions{
		Runner: rt,
		Pick:   func(context.Context) (string, error) { return "vol", nil },
		Store:  store,
		Spec: func(context.Context, string) reconcile.RestoreTestSpec {
			return reconcile.RestoreTestSpec{RestoreStorage: "local-lvm", ScratchMin: 990000, ScratchMax: 990009}
		},
		Cadence: time.Hour,
		Logger:  quiet(),
	})
	s.tick(context.Background())
	if rt.runs != 1 {
		t.Fatalf("tick should run the restore-test once, got %d", rt.runs)
	}
	got := store.RestoreTests(context.Background())
	if len(got) != 1 || !got[0].Pass || got[0].SourceArchive != "vol" {
		t.Fatalf("store should have the recorded result: %+v", got)
	}
}

func TestScheduler_TickNoBackupNoOp(t *testing.T) {
	rt := &fakeRTRunner{}
	s := NewScheduler(SchedulerOptions{
		Runner: rt, Pick: func(context.Context) (string, error) { return "", nil },
		Store: NewStore(), Cadence: time.Hour, Logger: quiet(),
	})
	s.tick(context.Background())
	if rt.runs != 0 {
		t.Errorf("no backup available → no restore-test run, got %d", rt.runs)
	}
}

func TestScheduler_DisabledRunReturnsOnCancel(t *testing.T) {
	s := NewScheduler(SchedulerOptions{Cadence: 0, Logger: quiet()})
	ctx, cancel := context.WithCancel(context.Background())
	done := make(chan error, 1)
	go func() { done <- s.Run(ctx) }()
	cancel()
	select {
	case err := <-done:
		if err != nil {
			t.Fatalf("disabled scheduler Run should return nil on cancel, got %v", err)
		}
	case <-time.After(time.Second):
		t.Fatal("disabled scheduler did not return on cancel")
	}
}

func TestStore_Reporters(t *testing.T) {
	s := NewStore()
	if len(s.Backups(context.Background())) != 0 || len(s.RestoreTests(context.Background())) != 0 {
		t.Fatal("empty store must report empty (non-nil) slices")
	}
}

func has(ss []string, want string) bool {
	for _, s := range ss {
		if s == want {
			return true
		}
	}
	return false
}