felhom-agent/internal/reconcile/bringup_test.go

package reconcile

import (
	"context"
	"errors"
	"strings"
	"testing"
	"time"

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

// setParamsFor returns the params of the (last) SetConfig call against vmid, or nil.
func setParamsFor(api *fakeAPI, vmid int) map[string]string {
	var out map[string]string
	for _, s := range api.sets {
		if s.vmid == vmid {
			out = s.params
		}
	}
	return out
}

func TestRunBringUp_ProvisionHappyPath(t *testing.T) {
	const vmid = 8000
	api := &fakeAPI{cfg: map[int]proxmox.GuestConfig{vmid: scratchCfg()}} // empty lxc → vmid free; running default
	e, _, q := newEngine(t, api, EmptyProvider{})
	defer q.Close()

	res := e.RunBringUp(context.Background(), BringUpSpec{
		Mode: ModeProvision, Archive: "local:backup/golden.tar.zst", VMID: vmid,
		RestoreStorage: "local-lvm", Hostname: "felhom-prov-8000",
		Cores: 2, MemoryMB: 2048, RootfsGrowGB: 2,
		Mounts: []GuestMount{{Storage: "local-lvm", SizeGB: 1, MountPoint: "/mnt/data"}},
	})
	if res.Err != nil || !res.Pass {
		t.Fatalf("provision must pass, got %+v", res)
	}
	if res.Verified != "boot+running" {
		t.Errorf("verified = %q", res.Verified)
	}
	// restore issued to the target vmid.
	if len(api.restores) != 1 || api.restores[0].VMID != vmid || api.restores[0].Archive != "local:backup/golden.tar.zst" {
		t.Fatalf("restore not issued correctly: %+v", api.restores)
	}
	// identity: a fresh MAC (net0 set WITHOUT hwaddr) + hostname, coalesced with sizing+mount.
	p := setParamsFor(api, vmid)
	if p == nil {
		t.Fatal("expected a coalesced config PUT")
	}
	if net0, ok := p["net0"]; !ok || strings.Contains(net0, "hwaddr=") {
		t.Errorf("provision must reset MAC: net0 must be set WITHOUT hwaddr, got %q", net0)
	}
	if p["hostname"] != "felhom-prov-8000" {
		t.Errorf("hostname not set: %q", p["hostname"])
	}
	if p["cores"] != "2" || p["memory"] != "2048" {
		t.Errorf("sizing not coalesced: cores=%q memory=%q", p["cores"], p["memory"])
	}
	if p["mp0"] != "local-lvm:1,mp=/mnt/data" {
		t.Errorf("mount not attached: mp0=%q", p["mp0"])
	}
	// rootfs grow is a SEPARATE call (F4).
	if len(api.resizes) != 1 || api.resizes[0].vmid != vmid || api.resizes[0].size != "+2G" {
		t.Errorf("rootfs grow not issued separately: %+v", api.resizes)
	}
	// started link-up.
	if len(api.starts) != 1 || api.starts[0] != vmid {
		t.Errorf("guest not started: %+v", api.starts)
	}
	// THE key difference from the restore-test: the guest is KEPT (no teardown).
	if len(api.destroys) != 0 {
		t.Fatalf("provision success must NOT destroy the guest: %+v", api.destroys)
	}
}

func TestRunBringUp_CompensatingRollback(t *testing.T) {
	const vmid = 8000
	lockBackoffFast(t)

	cases := []struct {
		name  string
		setup func(*fakeAPI)
	}{
		{"restore error", func(a *fakeAPI) { a.restoreErr = errors.New("restore boom") }},
		{"config real error", func(a *fakeAPI) {
			a.setFunc = func(int, map[string]string) (string, error) {
				return "", &proxmox.APIError{StatusCode: 500, Body: "some non-lock internal error"}
			}
		}},
		{"start-task real error", func(a *fakeAPI) {
			a.startUPID = "UPID:demo:start:8000:"
			a.waitFunc = func(upid string) (proxmox.TaskStatus, error) {
				if upid == "UPID:demo:start:8000:" {
					return proxmox.TaskStatus{}, errors.New("start task failed")
				}
				return proxmox.TaskStatus{Status: "stopped", ExitStatus: "OK"}, nil
			}
		}},
		{"waitRunning timeout", func(a *fakeAPI) {
			a.status = map[int]proxmox.Guest{vmid: {VMID: vmid, Status: "stopped"}}
		}},
	}
	for _, tc := range cases {
		t.Run(tc.name, func(t *testing.T) {
			api := &fakeAPI{cfg: map[int]proxmox.GuestConfig{vmid: scratchCfg()}}
			tc.setup(api)
			e, j, q := newEngine(t, api, EmptyProvider{})
			defer q.Close()

			res := e.RunBringUp(context.Background(), BringUpSpec{
				Mode: ModeProvision, Archive: "vol", VMID: vmid, RestoreStorage: "local-lvm",
				Hostname: "h", BootTimeout: 40 * time.Millisecond,
			})
			if res.Pass || res.Err == nil {
				t.Fatalf("must fail, got %+v", res)
			}
			// The adversarial point: the just-created guest was ACTUALLY destroyed.
			if len(api.destroys) != 1 || api.destroys[0] != vmid {
				t.Fatalf("compensating rollback must destroy the guest: destroys=%+v", api.destroys)
			}
			// And the owning entry is terminal (rollback complete) — not left in-flight.
			if len(j.InFlight()) != 0 {
				t.Errorf("owning entry must be terminal after rollback: %+v", j.InFlight())
			}
		})
	}
}

func TestRunBringUp_DRPreservesContinuityIdentity(t *testing.T) {
	const vmid = 8001
	api := &fakeAPI{cfg: map[int]proxmox.GuestConfig{vmid: scratchCfg()}}
	e, _, q := newEngine(t, api, EmptyProvider{})
	defer q.Close()

	res := e.RunBringUp(context.Background(), BringUpSpec{
		Mode: ModeDRGuestLoss, Archive: "local:backup/customer.tar.zst", VMID: vmid,
		RestoreStorage: "local-lvm", Hostname: "ignored-in-dr", KeepMAC: true,
		Cores: 4, // a benign config PUT happens, so we can inspect it has NO identity resets
	})
	if res.Err != nil || !res.Pass {
		t.Fatalf("dr bring-up must pass, got %+v", res)
	}
	p := setParamsFor(api, vmid)
	// DR continuity: MAC kept (no net0 reset) and hostname NOT force-reset.
	if p != nil {
		if _, ok := p["net0"]; ok {
			t.Errorf("dr+KeepMAC must NOT reset net0 (keep the archived MAC): %+v", p)
		}
		if _, ok := p["hostname"]; ok {
			t.Errorf("dr must NOT force-reset hostname (continuity): %+v", p)
		}
		if p["cores"] != "4" {
			t.Errorf("benign sizing should still apply: cores=%q", p["cores"])
		}
	}
	// AssignedMAC reflects the kept archived MAC (from scratchCfg's net0).
	if res.AssignedMAC != "AA:BB:CC:DD:EE:FF" {
		t.Errorf("dr should keep the archived MAC, got %q", res.AssignedMAC)
	}
	if len(api.destroys) != 0 {
		t.Errorf("dr success must not destroy: %+v", api.destroys)
	}
	// The agent performs NO guest-internal host-key op — there is no such API call; host keys
	// are preserved (DR) or regenerated by the baked golden unit (provision).
}

func TestRunBringUp_DRResetMACWhenSourceMayBeLive(t *testing.T) {
	const vmid = 8002
	api := &fakeAPI{cfg: map[int]proxmox.GuestConfig{vmid: scratchCfg()}}
	e, _, q := newEngine(t, api, EmptyProvider{})
	defer q.Close()

	res := e.RunBringUp(context.Background(), BringUpSpec{
		Mode: ModeDRGuestLoss, Archive: "vol", VMID: vmid, RestoreStorage: "local-lvm",
		KeepMAC: false, // a source guest may still be live → reset MAC even in DR
	})
	if res.Err != nil || !res.Pass {
		t.Fatalf("got %+v", res)
	}
	p := setParamsFor(api, vmid)
	if p == nil || strings.Contains(p["net0"], "hwaddr=") {
		t.Errorf("dr with KeepMAC=false must reset MAC (net0 without hwaddr): %+v", p)
	}
}

func TestRunBringUp_LivenessIsTheVerdict(t *testing.T) {
	const vmid = 8000
	const startUPID = "UPID:demo:start:8000:"
	mkAPI := func() *fakeAPI {
		return &fakeAPI{
			cfg:       map[int]proxmox.GuestConfig{vmid: scratchCfg()},
			startUPID: startUPID,
			waitFunc: func(upid string) (proxmox.TaskStatus, error) {
				if upid == startUPID {
					return proxmox.TaskStatus{Status: "stopped", ExitStatus: "WARNINGS: 1"}, nil
				}
				return proxmox.TaskStatus{Status: "stopped", ExitStatus: "OK"}, nil
			},
			logTailFunc: func(string) ([]string, error) {
				return []string{"WARN: Systemd 257 detected. You may need to enable nesting."}, nil
			},
		}
	}

	// start exits WARNINGS + guest reaches running → PASS, warnings surfaced + recognized.
	t.Run("warnings + running -> pass", func(t *testing.T) {
		api := mkAPI()
		e, _, q := newEngine(t, api, EmptyProvider{})
		defer q.Close()
		res := e.RunBringUp(context.Background(), BringUpSpec{
			Mode: ModeProvision, Archive: "v", VMID: vmid, RestoreStorage: "s", Hostname: "h",
		})
		if !res.Pass || res.Err != nil {
			t.Fatalf("warnings+running must pass: %+v", res)
		}
		if len(res.StartWarnings) != 1 || !res.WarningsRecognized {
			t.Errorf("warnings must be surfaced+recognized: %+v recognized=%v", res.StartWarnings, res.WarningsRecognized)
		}
		if len(api.destroys) != 0 {
			t.Errorf("a passed bring-up must not destroy: %+v", api.destroys)
		}
	})

	// same warnings but guest NEVER reaches running → FAIL (verdict is liveness), guest destroyed.
	t.Run("warnings + not-running -> fail", func(t *testing.T) {
		api := mkAPI()
		api.status = map[int]proxmox.Guest{vmid: {VMID: vmid, Status: "stopped"}}
		e, _, q := newEngine(t, api, EmptyProvider{})
		defer q.Close()
		res := e.RunBringUp(context.Background(), BringUpSpec{
			Mode: ModeProvision, Archive: "v", VMID: vmid, RestoreStorage: "s", Hostname: "h",
			BootTimeout: 40 * time.Millisecond,
		})
		if res.Pass || res.Err == nil {
			t.Fatalf("not-running must fail regardless of warnings: %+v", res)
		}
		if len(api.destroys) != 1 {
			t.Errorf("a failed bring-up must roll back (destroy): %+v", api.destroys)
		}
	})
}

func TestRunBringUp_F4_ConfigLockRetry(t *testing.T) {
	const vmid = 8000
	lockBackoffFast(t)

	t.Run("transient lock-500 then 200 -> retries and proceeds", func(t *testing.T) {
		api := &fakeAPI{cfg: map[int]proxmox.GuestConfig{vmid: scratchCfg()}}
		var calls int
		api.setFunc = func(int, map[string]string) (string, error) {
			calls++
			if calls == 1 {
				return "", &proxmox.APIError{StatusCode: 500, Body: "can't lock file '/run/lock/lxc/pve-config-8000.lock' - got timeout"}
			}
			return "", nil
		}
		e, _, q := newEngine(t, api, EmptyProvider{})
		defer q.Close()
		res := e.RunBringUp(context.Background(), BringUpSpec{
			Mode: ModeProvision, Archive: "v", VMID: vmid, RestoreStorage: "s", Hostname: "h",
		})
		if res.Err != nil || !res.Pass {
			t.Fatalf("lock-500 then 200 must succeed: %+v", res)
		}
		if calls < 2 {
			t.Errorf("expected a retry on the transient lock-500, calls=%d", calls)
		}
	})

	t.Run("non-lock 500 -> fails without retry", func(t *testing.T) {
		api := &fakeAPI{cfg: map[int]proxmox.GuestConfig{vmid: scratchCfg()}}
		var calls int
		api.setFunc = func(int, map[string]string) (string, error) {
			calls++
			return "", &proxmox.APIError{StatusCode: 500, Body: "internal error: disk full"}
		}
		e, _, q := newEngine(t, api, EmptyProvider{})
		defer q.Close()
		res := e.RunBringUp(context.Background(), BringUpSpec{
			Mode: ModeProvision, Archive: "v", VMID: vmid, RestoreStorage: "s", Hostname: "h",
		})
		if res.Pass || res.Err == nil {
			t.Fatalf("a non-lock 500 must fail: %+v", res)
		}
		if calls != 1 {
			t.Errorf("a real error must NOT be retried, calls=%d", calls)
		}
	})
}

func TestRunBringUp_JournalsOwningEntryBeforeRestore(t *testing.T) {
	const vmid = 8000
	api := &fakeAPI{cfg: map[int]proxmox.GuestConfig{vmid: scratchCfg()}}
	e, j, q := newEngine(t, api, EmptyProvider{})
	defer q.Close()

	// At the moment RestoreLXC is called, the owning Rollback entry must already be in-flight —
	// so a crash here is recoverable (Recover reaps the half-built guest).
	var ownedAtRestore bool
	api.restoreHook = func() {
		for _, en := range j.InFlight() {
			if en.VMID == vmid && en.Rollback {
				ownedAtRestore = true
			}
		}
	}
	res := e.RunBringUp(context.Background(), BringUpSpec{
		Mode: ModeProvision, Archive: "v", VMID: vmid, RestoreStorage: "s", Hostname: "h",
	})
	if res.Err != nil {
		t.Fatalf("setup: %+v", res)
	}
	if !ownedAtRestore {
		t.Fatal("the owning Rollback entry MUST be journaled before the restore (crash-safety)")
	}
}

func TestRunBringUp_RejectsReservedAndExistingVMID(t *testing.T) {
	e, _, q := newEngine(t, &fakeAPI{}, EmptyProvider{})
	defer q.Close()
	for _, id := range []int{9999, 990000, 990005} {
		res := e.RunBringUp(context.Background(), BringUpSpec{Mode: ModeProvision, Archive: "v", VMID: id, RestoreStorage: "s"})
		if res.Err == nil {
			t.Errorf("VMID %d is reserved and must be refused", id)
		}
	}
	// existing VMID → refuse (restore-over-existing is a signed op, not this benign path).
	api := &fakeAPI{lxc: []proxmox.Guest{{VMID: 8000}}}
	e2, _, q2 := newEngine(t, api, EmptyProvider{})
	defer q2.Close()
	res := e2.RunBringUp(context.Background(), BringUpSpec{Mode: ModeProvision, Archive: "v", VMID: 8000, RestoreStorage: "s"})
	if res.Err == nil {
		t.Error("bring-up over an existing guest must be refused")
	}
	if len(api.restores) != 0 || len(api.destroys) != 0 {
		t.Error("a refused bring-up must not restore or destroy anything")
	}
}

func TestRecover_HalfBuiltBringUpRolledBack(t *testing.T) {
	const vmid = 8000
	// The guest still exists at startup (agent crashed mid-bring-up) → Recover destroys it.
	api := &fakeAPI{lxc: []proxmox.Guest{{VMID: vmid, Status: "running"}}}
	e, j, _ := newEngine(t, api, EmptyProvider{})
	if err := j.Append(JournalEntry{OpID: "bring-up-8000-1", VMID: vmid, Kind: bringUpKind, Rollback: true, State: OpTaskRunning, At: time.Now().UTC()}); err != nil {
		t.Fatal(err)
	}
	res := e.Recover(context.Background())
	if res.BringUpRolledBack != 1 {
		t.Fatalf("half-built bring-up must be rolled back, got %+v", res)
	}
	if len(api.destroys) != 1 || api.destroys[0] != vmid {
		t.Fatalf("DestroyLXC not called for the half-built guest: %+v", api.destroys)
	}
	if len(j.InFlight()) != 0 {
		t.Errorf("resolved rollback entry must not be in-flight: %+v", j.InFlight())
	}
}

func TestRecover_HalfBuiltBringUpAlreadyGone(t *testing.T) {
	const vmid = 8000
	// Crash after the restore POST failed (no guest) → idempotent clean, no destroy.
	api := &fakeAPI{lxc: []proxmox.Guest{{VMID: 9001}}} // 8000 absent
	e, j, _ := newEngine(t, api, EmptyProvider{})
	j.Append(JournalEntry{OpID: "bring-up-8000-1", VMID: vmid, Kind: bringUpKind, Rollback: true, State: OpStarted, At: time.Now().UTC()})
	res := e.Recover(context.Background())
	if res.BringUpClean != 1 || len(api.destroys) != 0 {
		t.Fatalf("already-gone bring-up must be clean with no destroy: res=%+v destroys=%+v", res, api.destroys)
	}
	if len(j.InFlight()) != 0 {
		t.Errorf("entry must be resolved: %+v", j.InFlight())
	}
}

// lockBackoffFast shrinks the F4 retry backoff for tests and restores it after.
func lockBackoffFast(t *testing.T) {
	t.Helper()
	prev := configLockBackoff
	configLockBackoff = time.Millisecond
	t.Cleanup(func() { configLockBackoff = prev })
}