egress-proxies-operator/internal/provider/proxmox/fake_test.go

package proxmox

import (
	"context"
	"errors"
	"fmt"
	"io"
	"maps"
	"regexp"
	"slices"
	"strconv"
	"strings"
	"sync"
	"testing"
)

// fakeAPI is the in-memory cluster of spec entry 17: VMs, tasks and ISOs,
// with lock simulation (a clone leaves a nameless locked entry until its
// task completes), task polls, per-method errors and blocking, and a call
// log. Error texts Proxmox was seen to send are reproduced exactly and
// checked against the captures by TestFakeAPI_errorsMatchCaptures; texts
// recon never produced start with "fake:".
type fakeAPI struct {
	mu       sync.Mutex
	vms      map[int]*fakeVM
	tasks    map[string]*fakeTask
	isos     map[string]map[string][]byte // storage, then file name
	nodes    map[string]nodeStatus
	storages map[string]storageStatus
	version  versionInfo
	taskSeq  int

	// hooks returns the error a method fails with before touching state.
	hooks map[string]func() error
	// block makes a method wait on its channel (or ctx) before running.
	block map[string]chan struct{}
	calls map[string]int
	log   []string

	// taskPolls is how many TaskStatus polls answer "running" before a
	// task stops.
	taskPolls int
	// cloneFailsWith, startFailsWith and destroyFailsWith, when set, are
	// the exitstatus of every clone, start or destroy task. A failed clone
	// removes its VM; a failed destroy keeps it.
	cloneFailsWith, startFailsWith, destroyFailsWith string
	// agentNotRunning makes the agent of every running VM with agent=1
	// answer "QEMU guest agent is not running".
	agentNotRunning bool
	// cloneLeavesLock keeps lock=clone after a clone task ends, as an
	// interrupted clone would (F15).
	cloneLeavesLock bool
}

type fakeVM struct {
	node, name, status, qmpstatus, lock string
	// kind is the resource type; empty is "qemu". Any other kind, such as
	// "lxc", is listed but invisible to the qemu endpoints.
	kind     string
	template bool
	config   map[string]string
	ifaces   []agentInterface
}

type fakeTask struct {
	node   string
	polls  int
	exit   string
	onDone func()
	kind   string
	id     string
	done   bool
}

const (
	fakeNode       = "pv1-1"
	fakeISOStorage = "proxy-seeds"
)

var _ api = (*fakeAPI)(nil)

func newFakeAPI() *fakeAPI {
	var node nodeStatus
	node.PVEVersion = "pve-manager/9.2.20/49318c671b82f31e"
	node.CurrentKernel.Release = "7.0.14-17-pve"
	return &fakeAPI{
		vms:      make(map[int]*fakeVM),
		tasks:    make(map[string]*fakeTask),
		isos:     make(map[string]map[string][]byte),
		nodes:    map[string]nodeStatus{fakeNode: node},
		storages: map[string]storageStatus{fakeISOStorage: {Type: "dir", Content: "iso", Active: 1, Enabled: 1, Total: 100 << 30, Used: 10 << 30, Avail: 90 << 30}},
		version:  versionInfo{Version: "9.2.20", Release: "9.2", RepoID: "49318c671b82f31e"},
		hooks:    make(map[string]func() error),
		block:    make(map[string]chan struct{}),
		calls:    make(map[string]int),
	}
}

// addVM places a stopped or running VM cloned from a template like 9001 on
// fakeNode, without a description; tests add the mark they need.
func (f *fakeAPI) addVM(vmid int, name, status string) *fakeVM {
	f.mu.Lock()
	defer f.mu.Unlock()
	vm := &fakeVM{
		node:      fakeNode,
		name:      name,
		status:    status,
		qmpstatus: status,
		config: map[string]string{
			"agent":  "1",
			"boot":   "order=scsi0",
			"cores":  "2",
			"memory": "2048",
			"net0":   "virtio=BC:24:11:48:11:46,bridge=vmbr0",
			"scsi0":  fmt.Sprintf("local-lvm:vm-%d-disk-1,size=3G", vmid),
		},
	}
	f.vms[vmid] = vm
	return vm
}

// addTemplate places a template shaped like 9001 (F19) on fakeNode.
func (f *fakeAPI) addTemplate(vmid int, name string) *fakeVM {
	vm := f.addVM(vmid, name, "stopped")
	f.mu.Lock()
	defer f.mu.Unlock()
	vm.template = true
	vm.config["scsi0"] = fmt.Sprintf("local-lvm:base-%d-disk-1,size=3G", vmid)
	return vm
}

func (f *fakeAPI) failWith(method string, err error) {
	f.hookOn(method, func() error { return err })
}

// hookOn runs fn at the start of every call to method, without f.mu held;
// a non-nil result fails the call. A hook that changes state takes f.mu.
func (f *fakeAPI) hookOn(method string, fn func() error) {
	f.mu.Lock()
	defer f.mu.Unlock()
	f.hooks[method] = fn
}

// clearHooks drops every hook, so the faults they injected stop.
func (f *fakeAPI) clearHooks() {
	f.mu.Lock()
	defer f.mu.Unlock()
	clear(f.hooks)
}

func (f *fakeAPI) blockOn(method string) chan struct{} {
	f.mu.Lock()
	defer f.mu.Unlock()
	ch := make(chan struct{})
	f.block[method] = ch
	return ch
}

func (f *fakeAPI) callCount(method string) int {
	f.mu.Lock()
	defer f.mu.Unlock()
	return f.calls[method]
}

func (f *fakeAPI) callLog() []string {
	f.mu.Lock()
	defer f.mu.Unlock()
	return slices.Clone(f.log)
}

// iso returns an uploaded file's content.
func (f *fakeAPI) iso(storage, filename string) ([]byte, bool) {
	f.mu.Lock()
	defer f.mu.Unlock()
	b, ok := f.isos[storage][filename]
	return b, ok
}

// vmSnapshot returns a copy of the VM at vmid, for assertions.
func (f *fakeAPI) vmSnapshot(vmid int) (fakeVM, bool) {
	f.mu.Lock()
	defer f.mu.Unlock()
	vm, ok := f.vms[vmid]
	if !ok {
		return fakeVM{}, false
	}
	c := *vm
	c.config = maps.Clone(vm.config)
	c.ifaces = slices.Clone(vm.ifaces)
	return c, true
}

func fakeErr(status int, msg string) *apiError {
	return &apiError{Status: status, Message: msg}
}

// The 500s recon captured (F2, F4, F5, F7).
func errVMMissing(node string, vmid int) *apiError {
	return fakeErr(500, fmt.Sprintf("Configuration file 'nodes/%s/qemu-server/%d.conf' does not exist", node, vmid))
}

// errNoSuchStorage is the answer for a storage the cluster does not know
// (Phase 10 capture storage_status_missing).
func errNoSuchStorage() *apiError {
	return newAPIError(400, "", []byte(`{"message":"Parameter verification failed.\n","data":null,"errors":{"storage":"No such storage."}}`))
}

func errLocked(lock string) *apiError { return fakeErr(500, "VM is locked ("+lock+")") }

// isLocked and isVMNotRunning recognise two answers the provider leaves to
// classify's Transient default. They live here only to hold the fake's
// wording to the captures. The stopped-VM message is matched whole because
// " is not running" is also a suffix of the agent-not-running answer.
var vmNotRunning = regexp.MustCompile(`^VM [0-9]+ is not running$`)

func isLocked(err error) bool {
	msg, ok := server500(err)
	return ok && strings.HasPrefix(msg, "VM is locked")
}

func isVMNotRunning(err error) bool {
	msg, ok := server500(err)
	return ok && vmNotRunning.MatchString(msg)
}

func errNewIDInUse(vmid int) *apiError {
	return fakeErr(500, fmt.Sprintf("unable to create VM %d: config file already exists", vmid))
}

func errVMNotRunning(vmid int) *apiError {
	return fakeErr(500, fmt.Sprintf("VM %d is not running", vmid))
}

// enter records the call, honours a block and runs the hook. It is called
// without f.mu held; state access happens afterwards under the lock.
func (f *fakeAPI) enter(ctx context.Context, method string) error {
	f.mu.Lock()
	f.calls[method]++
	f.log = append(f.log, method)
	block := f.block[method]
	hook := f.hooks[method]
	f.mu.Unlock()
	if block != nil {
		select {
		case <-block:
		case <-ctx.Done():
			return ctx.Err()
		}
	}
	if hook != nil {
		return hook()
	}
	return nil
}

// vm looks a VM up the way Proxmox does, by node and VMID: a VM on another
// node has no config file on this one.
func (f *fakeAPI) vm(node string, vmid int) (*fakeVM, error) {
	vm, ok := f.vms[vmid]
	if !ok || vm.node != node || vm.kind != "" {
		return nil, errVMMissing(node, vmid)
	}
	return vm, nil
}

// newTask registers a task that stops after f.taskPolls running answers,
// then runs onDone under f.mu. The UPID has the shape parseUPID reads.
func (f *fakeAPI) newTask(node, kind, id, exit string, onDone func()) string {
	f.taskSeq++
	upid := fmt.Sprintf("UPID:%s:%08X:%08X:%08X:%s:%s:proxy-operator@pve!operator:", node, 0x100000+f.taskSeq, 0x2800000+f.taskSeq, 0x6AB37800+f.taskSeq, kind, id)
	f.tasks[upid] = &fakeTask{node: node, exit: exit, onDone: onDone, kind: kind, id: id}
	return upid
}

func (f *fakeAPI) Version(ctx context.Context) (versionInfo, error) {
	if err := f.enter(ctx, "Version"); err != nil {
		return versionInfo{}, err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	return f.version, nil
}

func (f *fakeAPI) NodeStatus(ctx context.Context, node string) (nodeStatus, error) {
	if err := f.enter(ctx, "NodeStatus"); err != nil {
		return nodeStatus{}, err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	s, ok := f.nodes[node]
	if !ok {
		return nodeStatus{}, fakeErr(500, "fake: no such node '"+node+"'")
	}
	return s, nil
}

func (f *fakeAPI) StorageStatus(ctx context.Context, node, storage string) (storageStatus, error) {
	if err := f.enter(ctx, "StorageStatus"); err != nil {
		return storageStatus{}, err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	s, ok := f.storages[storage]
	if !ok {
		return storageStatus{}, errNoSuchStorage()
	}
	return s, nil
}

// ClusterResources lists VMs by VMID. A VM being cloned is listed as F8
// saw it: no name, no tags, lock clone and status unknown.
func (f *fakeAPI) ClusterResources(ctx context.Context) ([]vmResource, error) {
	if err := f.enter(ctx, "ClusterResources"); err != nil {
		return nil, err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	out := make([]vmResource, 0, len(f.vms))
	for _, vmid := range slices.Sorted(maps.Keys(f.vms)) {
		vm := f.vms[vmid]
		r := vmResource{VMID: vmid, Name: vm.name, Node: vm.node, Type: "qemu", Status: vm.status, Lock: vm.lock, Tags: vm.config["tags"]}
		if vm.kind != "" {
			r.Type = vm.kind
		}
		if vm.template {
			r.Template = 1
		}
		if vm.lock == "clone" {
			r.Name, r.Tags, r.Status = "", "", "unknown"
		}
		out = append(out, r)
	}
	return out, nil
}

func (f *fakeAPI) VMConfig(ctx context.Context, node string, vmid int) (vmConfig, error) {
	if err := f.enter(ctx, "VMConfig"); err != nil {
		return nil, err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	vm, err := f.vm(node, vmid)
	if err != nil {
		return nil, err
	}
	cfg := vmConfig(maps.Clone(vm.config))
	if vm.name != "" {
		cfg["name"] = vm.name
	}
	if vm.lock != "" {
		cfg["lock"] = vm.lock
	}
	if vm.template {
		cfg["template"] = "1"
	}
	return cfg, nil
}

// SetVMConfig is refused while the VM is locked (F7). "delete" removes a
// comma-separated list of keys; "name" renames.
func (f *fakeAPI) SetVMConfig(ctx context.Context, node string, vmid int, params map[string]string) error {
	if err := f.enter(ctx, "SetVMConfig"); err != nil {
		return err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	vm, err := f.vm(node, vmid)
	if err != nil {
		return err
	}
	if vm.lock != "" {
		return errLocked(vm.lock)
	}
	for k, v := range params {
		switch k {
		case "delete":
			for key := range strings.SplitSeq(v, ",") {
				delete(vm.config, key)
			}
		case "name":
			vm.name = v
		default:
			vm.config[k] = v
		}
	}
	return nil
}

// Clone creates the VM at once, locked and nameless in the listing, and a
// task that clears the lock, or removes the VM when cloneFailsWith is set.
// A taken newid fails synchronously (F4).
func (f *fakeAPI) Clone(ctx context.Context, node string, vmid int, p cloneParams) (string, error) {
	if err := f.enter(ctx, "Clone"); err != nil {
		return "", err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	src, err := f.vm(node, vmid)
	if err != nil {
		return "", err
	}
	if _, taken := f.vms[p.NewID]; taken {
		return "", errNewIDInUse(p.NewID)
	}
	target := node
	if p.Target != "" {
		target = p.Target
	}
	cfg := maps.Clone(src.config)
	for k, v := range cfg {
		cfg[k] = strings.ReplaceAll(v, fmt.Sprintf("base-%d-", vmid), fmt.Sprintf("vm-%d-", p.NewID))
	}
	if p.Description != "" {
		cfg["description"] = p.Description
	}
	vm := &fakeVM{node: target, name: p.Name, status: "stopped", qmpstatus: "stopped", lock: "clone", config: cfg}
	f.vms[p.NewID] = vm
	exit := "OK"
	if f.cloneFailsWith != "" {
		exit = f.cloneFailsWith
	}
	leaveLock := f.cloneLeavesLock
	return f.newTask(node, "qmclone", strconv.Itoa(vmid), exit, func() {
		switch {
		case exit != "OK":
			if f.vms[p.NewID] == vm {
				delete(f.vms, p.NewID)
			}
		case !leaveLock:
			vm.lock = ""
		}
	}), nil
}

// Resize runs as a task (F20): the same size is a no-op, a smaller one
// fails inside the task with the captured exitstatus.
func (f *fakeAPI) Resize(ctx context.Context, node string, vmid int, disk, size string) (string, error) {
	if err := f.enter(ctx, "Resize"); err != nil {
		return "", err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	vm, err := f.vm(node, vmid)
	if err != nil {
		return "", err
	}
	if vm.lock != "" {
		return "", errLocked(vm.lock)
	}
	cur, ok := vm.config[disk]
	if !ok {
		return "", fakeErr(500, "fake: disk '"+disk+"' does not exist")
	}
	curBytes, ok := fakeParseSize(diskSizeOption(cur))
	if !ok {
		return "", fakeErr(500, "fake: disk '"+disk+"' has no size")
	}
	want, ok := fakeParseSize(strings.TrimPrefix(size, "+"))
	if !ok {
		return "", fakeErr(400, "fake: bad size '"+size+"'")
	}
	if strings.HasPrefix(size, "+") {
		want += curBytes
	}
	exit := "OK"
	if want < curBytes {
		exit = "shrinking disks is not supported"
	}
	return f.newTask(node, "resize", strconv.Itoa(vmid), exit, func() {
		if exit == "OK" {
			vm.config[disk] = strings.Replace(cur, "size="+diskSizeOption(cur), "size="+fakeFormatSize(want), 1)
		}
	}), nil
}

// Start is accepted even while a clone holds the lock (F3).
func (f *fakeAPI) Start(ctx context.Context, node string, vmid int) (string, error) {
	if err := f.enter(ctx, "Start"); err != nil {
		return "", err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	vm, err := f.vm(node, vmid)
	if err != nil {
		return "", err
	}
	exit := "OK"
	if f.startFailsWith != "" {
		exit = f.startFailsWith
	}
	return f.newTask(node, "qmstart", strconv.Itoa(vmid), exit, func() {
		if exit == "OK" {
			vm.status, vm.qmpstatus = "running", "running"
		}
	}), nil
}

func (f *fakeAPI) Stop(ctx context.Context, node string, vmid int) (string, error) {
	if err := f.enter(ctx, "Stop"); err != nil {
		return "", err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	vm, err := f.vm(node, vmid)
	if err != nil {
		return "", err
	}
	return f.newTask(node, "qmstop", strconv.Itoa(vmid), "OK", func() {
		vm.status, vm.qmpstatus = "stopped", "stopped"
	}), nil
}

func (f *fakeAPI) VMStatus(ctx context.Context, node string, vmid int) (vmStatus, error) {
	if err := f.enter(ctx, "VMStatus"); err != nil {
		return vmStatus{}, err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	vm, err := f.vm(node, vmid)
	if err != nil {
		return vmStatus{}, err
	}
	return vmStatus{Status: vm.status, QMPStatus: vm.qmpstatus, Name: vm.name, Lock: vm.lock}, nil
}

// Destroy refuses a locked or running VM and removes it when its task
// ends.
func (f *fakeAPI) Destroy(ctx context.Context, node string, vmid int) (string, error) {
	if err := f.enter(ctx, "Destroy"); err != nil {
		return "", err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	vm, err := f.vm(node, vmid)
	if err != nil {
		return "", err
	}
	// A hibernated VM is destroyed like a stopped one (Phase 10 captures
	// destroy_hibernated_response and task_status_destroy_hibernated).
	if vm.lock != "" && vm.lock != lockSuspended {
		return "", errLocked(vm.lock)
	}
	if vm.status == "running" {
		return "", fakeErr(500, fmt.Sprintf("fake: VM %d is running - destroy failed", vmid))
	}
	exit := "OK"
	if f.destroyFailsWith != "" {
		exit = f.destroyFailsWith
	}
	return f.newTask(node, "qmdestroy", strconv.Itoa(vmid), exit, func() {
		if exit == "OK" && f.vms[vmid] == vm {
			delete(f.vms, vmid)
		}
	}), nil
}

// TaskStatus answers running for f.taskPolls polls, then stopped with the
// task's exitstatus, running its effect once.
func (f *fakeAPI) TaskStatus(ctx context.Context, node, upid string) (taskStatus, error) {
	if err := f.enter(ctx, "TaskStatus"); err != nil {
		return taskStatus{}, err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	t, ok := f.tasks[upid]
	if !ok || t.node != node {
		return taskStatus{}, fakeErr(500, "fake: no such task '"+upid+"'")
	}
	t.polls++
	s := taskStatus{UPID: upid, Type: t.kind, ID: t.id, Node: t.node, Status: "running"}
	if !t.done && t.polls > f.taskPolls {
		t.done = true
		if t.onDone != nil {
			t.onDone()
		}
	}
	if t.done {
		s.Status, s.ExitStatus = "stopped", t.exit
	}
	return s, nil
}

// AgentNetworkInterfaces answers with the three messages of F5 in the
// order Proxmox checks them.
func (f *fakeAPI) AgentNetworkInterfaces(ctx context.Context, node string, vmid int) ([]agentInterface, error) {
	if err := f.enter(ctx, "AgentNetworkInterfaces"); err != nil {
		return nil, err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	vm, err := f.vm(node, vmid)
	if err != nil {
		return nil, err
	}
	if agent := vm.config["agent"]; agent != "1" && !strings.HasPrefix(agent, "1,") && !strings.Contains(agent, "enabled=1") {
		return nil, fakeErr(500, msgAgentNotConfigured)
	}
	if vm.status != "running" {
		return nil, errVMNotRunning(vmid)
	}
	if f.agentNotRunning {
		return nil, fakeErr(500, msgAgentNotRunning)
	}
	return slices.Clone(vm.ifaces), nil
}

// UploadISO records the bytes and overwrites an existing file silently
// (F12). A body that disagrees with size fails, as the real Content-Length
// would.
func (f *fakeAPI) UploadISO(ctx context.Context, node, storage, filename string, r io.Reader, size int64) (string, error) {
	if err := f.enter(ctx, "UploadISO"); err != nil {
		return "", err
	}
	var content []byte
	if r != nil {
		var err error
		if content, err = io.ReadAll(r); err != nil {
			return "", err
		}
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	if _, ok := f.storages[storage]; !ok {
		return "", fakeErr(500, "fake: storage '"+storage+"' does not exist")
	}
	if int64(len(content)) != size {
		return "", fakeErr(400, fmt.Sprintf("fake: body has %d bytes, size says %d", len(content), size))
	}
	if f.isos[storage] == nil {
		f.isos[storage] = make(map[string][]byte)
	}
	f.isos[storage][filename] = content
	return f.newTask(node, "imgcopy", "", "OK", nil), nil
}

// DeleteVolume is a task that ends OK whether or not the volume exists
// (F13).
func (f *fakeAPI) DeleteVolume(ctx context.Context, node, storage, volid string) (string, error) {
	if err := f.enter(ctx, "DeleteVolume"); err != nil {
		return "", err
	}
	f.mu.Lock()
	defer f.mu.Unlock()
	if _, ok := f.storages[storage]; !ok {
		return "", fakeErr(500, "fake: storage '"+storage+"' does not exist")
	}
	filename := strings.TrimPrefix(volid, storage+":iso/")
	return f.newTask(node, "imgdel", storage, "OK", func() {
		delete(f.isos[storage], filename)
	}), nil
}

// diskSizeOption returns the size= option of a disk value.
func diskSizeOption(disk string) string {
	for opt := range strings.SplitSeq(disk, ",") {
		if v, ok := strings.CutPrefix(opt, "size="); ok {
			return v
		}
	}
	return ""
}

// fakeParseSize reads Proxmox's <n>[KMGT] sizes into bytes.
func fakeParseSize(s string) (int64, bool) {
	if s == "" {
		return 0, false
	}
	shift := map[byte]uint{'K': 10, 'M': 20, 'G': 30, 'T': 40}
	unit, ok := shift[s[len(s)-1]]
	if ok {
		s = s[:len(s)-1]
	}
	n, err := strconv.ParseInt(s, 10, 64)
	if err != nil || n < 0 {
		return 0, false
	}
	return n << unit, true
}

func fakeFormatSize(b int64) string {
	if b%(1<<30) == 0 {
		return strconv.FormatInt(b>>30, 10) + "G"
	}
	return strconv.FormatInt(b>>20, 10) + "M"
}

// TestFakeAPI_errorsMatchCaptures keeps the fake's error texts equal to
// what Proxmox sent, so the provider's matchers are exercised against real
// wording in every test that goes through the fake.
func TestFakeAPI_errorsMatchCaptures(t *testing.T) {
	t.Parallel()
	tests := []struct {
		capture string
		fake    *apiError
		matcher func(error) bool
	}{
		{capture: "err_vm_missing", fake: errVMMissing("pv1-1", 999999), matcher: isNotExist},
		{capture: "err_destroy_missing", fake: errVMMissing("pv1-1", 199999), matcher: isNotExist},
		{capture: "err_config_while_clone_locked", fake: errLocked("clone"), matcher: isLocked},
		{capture: "err_newid_in_use", fake: errNewIDInUse(199999), matcher: isAlreadyExists},
		{capture: "storage_status_missing", fake: errNoSuchStorage(), matcher: isNoSuchStorage},
		{capture: "err_agent_vm_stopped_agent_enabled", fake: errVMNotRunning(199999), matcher: isVMNotRunning},
		{capture: "err_agent_not_running", fake: fakeErr(500, msgAgentNotRunning), matcher: isAgentNotRunning},
		{capture: "err_agent_vm_stopped", fake: fakeErr(500, msgAgentNotConfigured), matcher: isAgentNotConfigured},
	}
	for _, tc := range tests {
		t.Run(tc.capture, func(t *testing.T) {
			t.Parallel()
			want := loadAPIError(t, tc.capture)
			if tc.fake.Status != want.Status || tc.fake.Message != want.Message || !maps.Equal(tc.fake.Errors, want.Errors) {
				t.Errorf("fake error = %d %q %v, capture = %d %q %v", tc.fake.Status, tc.fake.Message, tc.fake.Errors, want.Status, want.Message, want.Errors)
			}
			if !tc.matcher(tc.fake) {
				t.Errorf("matcher does not accept the fake's %q", tc.fake.Message)
			}
		})
	}
}

// pollTask polls a fake task until it stops and returns its exitstatus.
func pollTask(t *testing.T, f *fakeAPI, upid string) string {
	t.Helper()
	for range 10 {
		s, err := f.TaskStatus(context.Background(), fakeNode, upid)
		if err != nil {
			t.Fatalf("TaskStatus(%s) error = %v", upid, err)
		}
		if s.Status == "stopped" {
			return s.ExitStatus
		}
	}
	t.Fatalf("task %s still running after 10 polls", upid)
	return ""
}

func resourceByID(t *testing.T, f *fakeAPI, vmid int) (vmResource, bool) {
	t.Helper()
	rs, err := f.ClusterResources(context.Background())
	if err != nil {
		t.Fatalf("ClusterResources error = %v", err)
	}
	for _, r := range rs {
		if r.VMID == vmid {
			return r, true
		}
	}
	return vmResource{}, false
}

func TestFakeAPI_cloneLocksUntilTaskEnds(t *testing.T) {
	t.Parallel()
	ctx := context.Background()
	f := newFakeAPI()
	f.addTemplate(9001, "debian-13-template")
	f.taskPolls = 1
	upid, err := f.Clone(ctx, fakeNode, 9001, cloneParams{NewID: 150042, Name: "proxy-x", Description: "d"})
	if err != nil {
		t.Fatalf("Clone error = %v", err)
	}
	if r, _ := resourceByID(t, f, 150042); r.Name != "" || r.Lock != "clone" || r.Status != "unknown" {
		t.Errorf("mid-clone entry = %+v, want nameless, lock clone, status unknown (F8)", r)
	}
	if err := f.SetVMConfig(ctx, fakeNode, 150042, map[string]string{"cores": "1"}); !isLocked(err) {
		t.Errorf("SetVMConfig mid-clone error = %v, want the lock answer (F7)", err)
	}
	if _, err := f.Clone(ctx, fakeNode, 9001, cloneParams{NewID: 150042, Name: "proxy-y"}); !isAlreadyExists(err) {
		t.Errorf("second Clone onto 150042 error = %v, want config file already exists (F4)", err)
	}
	if s, _ := f.TaskStatus(ctx, fakeNode, upid); s.Status != "running" {
		t.Errorf("first poll = %+v, want running with taskPolls 1", s)
	}
	if exit := pollTask(t, f, upid); exit != "OK" {
		t.Errorf("clone exitstatus = %q, want OK", exit)
	}
	r, _ := resourceByID(t, f, 150042)
	if r.Name != "proxy-x" || r.Lock != "" || r.Status != "stopped" || r.Template != 0 {
		t.Errorf("cloned entry = %+v, want named, unlocked, stopped", r)
	}
	cfg, err := f.VMConfig(ctx, fakeNode, 150042)
	if err != nil || cfg["description"] != "d" || cfg["scsi0"] != "local-lvm:vm-150042-disk-1,size=3G" || cfg["template"] != "" {
		t.Errorf("clone config = %v, %v", cfg, err)
	}
}

func TestFakeAPI_cloneFailureAndLeftLock(t *testing.T) {
	t.Parallel()
	ctx := context.Background()
	t.Run("failed clone removes the VM", func(t *testing.T) {
		t.Parallel()
		f := newFakeAPI()
		f.addTemplate(9001, "debian-13-template")
		f.cloneFailsWith = "clone failed: out of space"
		upid, _ := f.Clone(ctx, fakeNode, 9001, cloneParams{NewID: 150042, Name: "proxy-x"})
		if exit := pollTask(t, f, upid); exit != "clone failed: out of space" {
			t.Errorf("exitstatus = %q", exit)
		}
		if _, ok := resourceByID(t, f, 150042); ok {
			t.Error("failed clone left its VM")
		}
	})
	t.Run("interrupted clone keeps the lock", func(t *testing.T) {
		t.Parallel()
		f := newFakeAPI()
		f.addTemplate(9001, "debian-13-template")
		f.cloneLeavesLock = true
		upid, _ := f.Clone(ctx, fakeNode, 9001, cloneParams{NewID: 150042, Name: "proxy-x"})
		pollTask(t, f, upid)
		if r, _ := resourceByID(t, f, 150042); r.Lock != "clone" {
			t.Errorf("entry = %+v, want lock clone kept", r)
		}
	})
}

func TestFakeAPI_powerAgentAndDestroy(t *testing.T) {
	t.Parallel()
	ctx := context.Background()
	f := newFakeAPI()
	vm := f.addVM(150042, "proxy-x", "stopped")
	vm.ifaces = []agentInterface{{Name: "ens18", IPAddresses: []agentIP{{Address: "192.168.4.147", Type: "ipv4", Prefix: 24}}}}

	if _, err := f.AgentNetworkInterfaces(ctx, fakeNode, 150042); !isVMNotRunning(err) {
		t.Errorf("agent on a stopped VM error = %v, want VM is not running", err)
	}
	upid, _ := f.Start(ctx, fakeNode, 150042)
	pollTask(t, f, upid)
	if s, _ := f.VMStatus(ctx, fakeNode, 150042); s.Status != "running" || s.QMPStatus != "running" {
		t.Errorf("status after start = %+v", s)
	}
	f.agentNotRunning = true
	if _, err := f.AgentNetworkInterfaces(ctx, fakeNode, 150042); !isAgentNotRunning(err) {
		t.Errorf("agent error = %v, want agent not running", err)
	}
	f.agentNotRunning = false
	if ifaces, err := f.AgentNetworkInterfaces(ctx, fakeNode, 150042); err != nil || firstIPv4(ifaces) != "192.168.4.147" {
		t.Errorf("agent = %v, %v", ifaces, err)
	}
	if _, err := f.Destroy(ctx, fakeNode, 150042); err == nil {
		t.Error("Destroy of a running VM succeeded")
	}
	upid, _ = f.Stop(ctx, fakeNode, 150042)
	pollTask(t, f, upid)
	upid, err := f.Destroy(ctx, fakeNode, 150042)
	if err != nil {
		t.Fatalf("Destroy error = %v", err)
	}
	pollTask(t, f, upid)
	if _, err := f.VMConfig(ctx, fakeNode, 150042); !isNotExist(err) {
		t.Errorf("VMConfig after destroy error = %v, want does not exist", err)
	}
	if _, err := f.VMStatus(ctx, "pv1-2", 150042); !isNotExist(err) {
		t.Errorf("lookup on another node error = %v, want does not exist", err)
	}
}

func TestFakeAPI_resizeIsATask(t *testing.T) {
	t.Parallel()
	tests := []struct {
		name     string
		size     string
		wantExit string
		wantDisk string
	}{
		{name: "grow absolute", size: "8G", wantExit: "OK", wantDisk: "local-lvm:vm-150042-disk-1,size=8G"},
		{name: "grow relative", size: "+1G", wantExit: "OK", wantDisk: "local-lvm:vm-150042-disk-1,size=4G"},
		{name: "same size", size: "3G", wantExit: "OK", wantDisk: "local-lvm:vm-150042-disk-1,size=3G"},
		{name: "shrink fails in the task", size: "2G", wantExit: loadTaskExit(t, "task_status_stopped_error"), wantDisk: "local-lvm:vm-150042-disk-1,size=3G"},
	}
	for _, tc := range tests {
		t.Run(tc.name, func(t *testing.T) {
			t.Parallel()
			f := newFakeAPI()
			f.addVM(150042, "proxy-x", "stopped")
			upid, err := f.Resize(context.Background(), fakeNode, 150042, "scsi0", tc.size)
			if err != nil {
				t.Fatalf("Resize error = %v", err)
			}
			if exit := pollTask(t, f, upid); exit != tc.wantExit {
				t.Errorf("exitstatus = %q, want %q", exit, tc.wantExit)
			}
			if vm, _ := f.vmSnapshot(150042); vm.config["scsi0"] != tc.wantDisk {
				t.Errorf("scsi0 = %q, want %q", vm.config["scsi0"], tc.wantDisk)
			}
		})
	}
}

func loadTaskExit(t *testing.T, name string) string {
	t.Helper()
	return decodeData[taskStatus](t, name).ExitStatus
}

func TestFakeAPI_uploadOverwritesAndDeleteIsIdempotent(t *testing.T) {
	t.Parallel()
	ctx := context.Background()
	f := newFakeAPI()
	for _, body := range []string{"first", "second"} {
		upid, err := f.UploadISO(ctx, fakeNode, fakeISOStorage, "proxy-x-seed.iso", strings.NewReader(body), int64(len(body)))
		if err != nil {
			t.Fatalf("UploadISO error = %v", err)
		}
		pollTask(t, f, upid)
	}
	if b, _ := f.iso(fakeISOStorage, "proxy-x-seed.iso"); string(b) != "second" {
		t.Errorf("iso = %q, want the second upload (F12 overwrite)", b)
	}
	if _, err := f.UploadISO(ctx, fakeNode, fakeISOStorage, "x.iso", strings.NewReader("abc"), 4); err == nil {
		t.Error("UploadISO with a wrong size succeeded")
	}
	for range 2 {
		upid, err := f.DeleteVolume(ctx, fakeNode, fakeISOStorage, seedVolID(fakeISOStorage, "proxy-x"))
		if err != nil {
			t.Fatalf("DeleteVolume error = %v", err)
		}
		if exit := pollTask(t, f, upid); exit != "OK" {
			t.Errorf("delete exitstatus = %q, want OK even when absent (F13)", exit)
		}
	}
	if _, ok := f.iso(fakeISOStorage, "proxy-x-seed.iso"); ok {
		t.Error("iso still present after delete")
	}
}

func TestFakeAPI_hooksBlocksAndLog(t *testing.T) {
	t.Parallel()
	f := newFakeAPI()
	boom := errors.New("boom")
	f.failWith("Version", boom)
	if _, err := f.Version(context.Background()); !errors.Is(err, boom) {
		t.Errorf("Version error = %v, want the hook's", err)
	}
	f.blockOn("ClusterResources")
	ctx, cancel := context.WithCancel(context.Background())
	cancel()
	if _, err := f.ClusterResources(ctx); !errors.Is(err, context.Canceled) {
		t.Errorf("blocked call with ended ctx error = %v, want context.Canceled", err)
	}
	if got := f.callLog(); !slices.Equal(got, []string{"Version", "ClusterResources"}) {
		t.Errorf("call log = %v", got)
	}
	if f.callCount("Version") != 1 {
		t.Errorf("Version count = %d, want 1", f.callCount("Version"))
	}
}