Files
sanderling/internal/driver/mock/mock.go
T
pj 410602d2e1 Fix action-system audit findings (#60)
* fix(replay-ui): size overlay viewBox from hierarchy root bounds

Tap points are recorded in the hierarchy's coordinate space (iOS points,
Android pixels, web CSS px) while screenshots are device pixels, so the
overlay rendered at 1/3 position on iOS 3x screens. Derive the viewBox
from the root element bounds; natural image size stays the fallback.

* fix(runner): derive trace tap point from resolveCoordinates

stampSelectorTarget preferred possibly-stale action X/Y while dispatch
preferred the fresh tree-resolved center, so the trace could record a
different point than the one tapped. Both now share resolveCoordinates.

* fix(runner): settle after InputText focus tap before key events

The focus tap raises the keyboard; with no settle the keyboard
animation races the erase/type key events on iOS, landing them in the
wrong field or dropping them. Wait for idle after a successful focus
tap, bounded by the run's idle timeout.

* fix(driver): skip pre-erase for replace-on-input drivers

The web driver's InputText already replaces content via select-all, so
the runner's unconditional EraseText was a redundant round-trip on
every InputText. A new optional TextReplacer capability lets a driver
assert replace semantics; the runner skips the erase when asserted.

* fix(hierarchy): rank spatial-fallback matches by specificity

The bounds-containment fallback returned the first pre-order match, so
a screen-sized container could win over the intended small element.
Matches are now ordered smallest-area first; equal-area matches keep
pre-order, preserving the iOS-flat equal-bounds sibling pattern.

* fix(runner): treat an unchanging transitional tree as settled

A UI persistently showing two route-level Screen ids (overlay, both
route ids alive at rest) burned the full retry budget every step and
skipped the verifier forever. A tree byte-identical to the previous
attempt now breaks the retry loop as settled; genuine cross-fades
differ between attempts and keep the retry/skip behavior.

* fix(replay-ui): skip synthetic zero-bounds root in deviceSpaceOf

The iOS hierarchy prepends a zero-bounds node before the real root
window, so elements[0] returned undefined and the overlay fell back to
the screenshot's pixel size. Take the first element with positive
extent instead; pre-order puts the root window before any content.
Verified against a real iOS trace in the replay UI.

* fix(sidecar): never replay non-idempotent actions after reconnect

A dropped connection mid-action (e.g. a read timeout while the device
is still typing) re-ran the whole block after reconnecting, typing the
text twice and double-firing taps. Non-idempotent actions now reconnect
for the next RPC's benefit but surface UNAVAILABLE, which the runner
already treats as transient; idempotent reads keep the replay.

* fix(sidecar): land the second double-tap sequentially on gesture collision

The overlapped second tap can hit the XCTest runner while the first
gesture is still executing ('only one gesture can be performed at a
time'), failing the step. The second tap now waits the first out and
retries once, keeping the tight gap on the happy path.

* fix(sidecar): map non-Exception throwables to INTERNAL status

The vendored iOS client throws failures that do not extend Exception;
runRpc missed them, killing the RPC as a channel-level Unknown the
runner cannot classify. Catch Throwable instead.

* feat(sidecar): close the driver and app under test on shutdown

* test(sidecar): cover service shutdown paths

* fix(testrun): stop the sidecar with SIGTERM before killing

* fix(sidecar): reap orphaned XCTest runner sessions at iOS init

* fix(sidecar): probe channel liveness before restarting the XCTest runner

* test(sidecar): cover WdaRecovery restart and retry policy

* fix(sidecar): absorb first-leg double-tap collision sequentially

* fix(runner): scope WDA-drop detection and cap consecutive transient failures

* chore(sidecar): silence vendored loggers on expected failure paths

* fix(runner): absorb one-off apply errors; only an unbroken streak aborts

* fix(folio): install the current build before the Android fuzz run

* chore(sidecar): silence absorbed view-hierarchy poll noise in Android runs

The driver logs an ERROR for every on-device view-hierarchy fetch that the
device-side server cancels or times out while the UI animates. The stability
poll fetches the hierarchy on a sub-second cadence and swallows those throws
to keep polling, so each line is advisory with no effect on the run. Real
failures still reach the runner as gRPC status errors, so nothing is lost.
2026-06-06 12:21:11 +05:30

339 lines
9.1 KiB
Go

// Package mock provides an in-memory device driver that records actions for tests.
package mock
import (
"context"
"sync"
"time"
"github.com/priyanshujain/sanderling/internal/driver"
)
type ActionKind string
const (
ActionLaunch ActionKind = "launch"
ActionTerminate ActionKind = "terminate"
ActionTap ActionKind = "tap"
ActionTapSelector ActionKind = "tap_selector"
ActionDoubleTap ActionKind = "double_tap"
ActionDoubleTapSelector ActionKind = "double_tap_selector"
ActionInputText ActionKind = "input_text"
ActionEraseText ActionKind = "erase_text"
ActionSwipe ActionKind = "swipe"
ActionPressKey ActionKind = "press_key"
ActionLongPress ActionKind = "long_press"
ActionHierarchy ActionKind = "hierarchy"
ActionScreenshot ActionKind = "screenshot"
ActionSnapshot ActionKind = "snapshot"
ActionRecentLogs ActionKind = "recent_logs"
ActionWaitForIdle ActionKind = "wait_for_idle"
ActionHealth ActionKind = "health"
ActionMetrics ActionKind = "metrics"
)
type Action struct {
Kind ActionKind
BundleID string
ClearState bool
X, Y int
FromX, FromY int
ToX, ToY int
Duration time.Duration
Selector string
Text string
CharacterCount int
Key string
LogLevel string
LogSince time.Time
Idle time.Duration
}
// Driver is an in-memory Driver implementation for unit tests.
// Tests can program HierarchyJSON, ImageData, HealthInfo, and per-method
// Failures, and read back Actions to assert what the runner asked for.
type Driver struct {
mutex sync.Mutex
actions []Action
HierarchyJSON string
ImageData driver.Image
HealthInfo driver.Health
LogEntries []driver.LogEntry
MetricsData driver.Metrics
Failures map[ActionKind]error
// ReplacesText makes the mock assert the TextReplacer capability, so
// tests cover both the erase-before-type and replace-on-input paths.
ReplacesText bool
// ForegroundResults is consumed one entry per ForegroundApp call (the
// last entry repeats). Empty yields "", which disables the runner's
// app-scope guard so tests that don't care are unaffected.
ForegroundResults []string
foregroundIndex int
// FocusedWindowResults is consumed one entry per FocusedWindowApp call
// (the last entry repeats). When empty, FocusedWindowApp mirrors the
// last ForegroundApp result, so the startup gate treats the window as
// already drawn and tests that don't care are unaffected.
FocusedWindowResults []string
focusedWindowIndex int
focusedWindowCalls int
lastForeground string
}
func New() *Driver {
return &Driver{
Failures: map[ActionKind]error{},
HealthInfo: driver.Health{
Ready: true,
Version: "mock",
Platform: "android",
},
HierarchyJSON: `{"children":[]}`,
ImageData: driver.Image{PNG: []byte{}, Width: 0, Height: 0},
}
}
func (d *Driver) Actions() []Action {
d.mutex.Lock()
defer d.mutex.Unlock()
return append([]Action(nil), d.actions...)
}
func (d *Driver) record(action Action) {
d.mutex.Lock()
defer d.mutex.Unlock()
d.actions = append(d.actions, action)
}
func (d *Driver) failure(kind ActionKind) error {
d.mutex.Lock()
defer d.mutex.Unlock()
return d.Failures[kind]
}
func (d *Driver) Launch(_ context.Context, bundleID string, clearState bool, _ map[string]string) error {
if err := d.failure(ActionLaunch); err != nil {
return err
}
d.record(Action{Kind: ActionLaunch, BundleID: bundleID, ClearState: clearState})
return nil
}
func (d *Driver) ForegroundApp(_ context.Context) (string, error) {
d.mutex.Lock()
defer d.mutex.Unlock()
if len(d.ForegroundResults) == 0 {
d.lastForeground = ""
return "", nil
}
index := d.foregroundIndex
if index >= len(d.ForegroundResults) {
index = len(d.ForegroundResults) - 1
}
d.foregroundIndex++
d.lastForeground = d.ForegroundResults[index]
return d.lastForeground, nil
}
func (d *Driver) FocusedWindowApp(_ context.Context) (string, error) {
d.mutex.Lock()
defer d.mutex.Unlock()
d.focusedWindowCalls++
if len(d.FocusedWindowResults) == 0 {
return d.lastForeground, nil
}
index := d.focusedWindowIndex
if index >= len(d.FocusedWindowResults) {
index = len(d.FocusedWindowResults) - 1
}
d.focusedWindowIndex++
return d.FocusedWindowResults[index], nil
}
// FocusedWindowCalls reports how many times FocusedWindowApp has been called.
func (d *Driver) FocusedWindowCalls() int {
d.mutex.Lock()
defer d.mutex.Unlock()
return d.focusedWindowCalls
}
func (d *Driver) Terminate(ctx context.Context) error {
if err := d.failure(ActionTerminate); err != nil {
return err
}
d.record(Action{Kind: ActionTerminate})
return nil
}
func (d *Driver) Tap(ctx context.Context, x, y int) error {
if err := d.failure(ActionTap); err != nil {
return err
}
d.record(Action{Kind: ActionTap, X: x, Y: y})
return nil
}
func (d *Driver) LongPress(ctx context.Context, x, y int) error {
if err := d.failure(ActionLongPress); err != nil {
return err
}
d.record(Action{Kind: ActionLongPress, X: x, Y: y})
return nil
}
func (d *Driver) TapSelector(ctx context.Context, selector string) error {
if err := d.failure(ActionTapSelector); err != nil {
return err
}
d.record(Action{Kind: ActionTapSelector, Selector: selector})
return nil
}
func (d *Driver) DoubleTap(ctx context.Context, x, y int) error {
if err := d.failure(ActionDoubleTap); err != nil {
return err
}
d.record(Action{Kind: ActionDoubleTap, X: x, Y: y})
return nil
}
func (d *Driver) DoubleTapSelector(ctx context.Context, selector string) error {
if err := d.failure(ActionDoubleTapSelector); err != nil {
return err
}
d.record(Action{Kind: ActionDoubleTapSelector, Selector: selector})
return nil
}
func (d *Driver) InputText(ctx context.Context, text string) error {
if err := d.failure(ActionInputText); err != nil {
return err
}
d.record(Action{Kind: ActionInputText, Text: text})
return nil
}
func (d *Driver) ReplacesTextOnInput() bool {
d.mutex.Lock()
defer d.mutex.Unlock()
return d.ReplacesText
}
func (d *Driver) EraseText(ctx context.Context, characterCount int) error {
if err := d.failure(ActionEraseText); err != nil {
return err
}
d.record(Action{Kind: ActionEraseText, CharacterCount: characterCount})
return nil
}
func (d *Driver) Swipe(ctx context.Context, fromX, fromY, toX, toY int, duration time.Duration) error {
if err := d.failure(ActionSwipe); err != nil {
return err
}
d.record(Action{
Kind: ActionSwipe,
FromX: fromX,
FromY: fromY,
ToX: toX,
ToY: toY,
Duration: duration,
})
return nil
}
func (d *Driver) PressKey(ctx context.Context, key string) error {
if err := d.failure(ActionPressKey); err != nil {
return err
}
d.record(Action{Kind: ActionPressKey, Key: key})
return nil
}
func (d *Driver) RecentLogs(ctx context.Context, since time.Time, minLevel string) ([]driver.LogEntry, error) {
if err := d.failure(ActionRecentLogs); err != nil {
return nil, err
}
d.record(Action{Kind: ActionRecentLogs, LogSince: since, LogLevel: minLevel})
d.mutex.Lock()
defer d.mutex.Unlock()
return append([]driver.LogEntry(nil), d.LogEntries...), nil
}
func (d *Driver) Hierarchy(ctx context.Context) (string, error) {
if err := d.failure(ActionHierarchy); err != nil {
return "", err
}
d.record(Action{Kind: ActionHierarchy})
d.mutex.Lock()
defer d.mutex.Unlock()
return d.HierarchyJSON, nil
}
func (d *Driver) Screenshot(ctx context.Context) (driver.Image, error) {
if err := d.failure(ActionScreenshot); err != nil {
return driver.Image{}, err
}
d.record(Action{Kind: ActionScreenshot})
d.mutex.Lock()
defer d.mutex.Unlock()
return d.ImageData, nil
}
// Snapshot returns the hierarchy + screenshot pair atomically, mirroring
// the real driver's contract. It records a single ActionSnapshot so tests
// can assert the runner reached for the paired RPC instead of racing the
// two reads.
func (d *Driver) Snapshot(ctx context.Context) (string, driver.Image, error) {
if err := d.failure(ActionSnapshot); err != nil {
return "", driver.Image{}, err
}
d.record(Action{Kind: ActionSnapshot})
d.mutex.Lock()
defer d.mutex.Unlock()
return d.HierarchyJSON, d.ImageData, nil
}
func (d *Driver) WaitForIdle(ctx context.Context, duration time.Duration) error {
if err := d.failure(ActionWaitForIdle); err != nil {
return err
}
d.record(Action{Kind: ActionWaitForIdle, Idle: duration})
if duration <= 0 {
return nil
}
timer := time.NewTimer(duration)
defer timer.Stop()
select {
case <-ctx.Done():
return ctx.Err()
case <-timer.C:
return nil
}
}
func (d *Driver) Health(ctx context.Context) (driver.Health, error) {
if err := d.failure(ActionHealth); err != nil {
return driver.Health{}, err
}
d.record(Action{Kind: ActionHealth})
d.mutex.Lock()
defer d.mutex.Unlock()
return d.HealthInfo, nil
}
func (d *Driver) Metrics(ctx context.Context, bundleID string) (driver.Metrics, error) {
if err := d.failure(ActionMetrics); err != nil {
return driver.Metrics{}, err
}
d.record(Action{Kind: ActionMetrics, BundleID: bundleID})
d.mutex.Lock()
defer d.mutex.Unlock()
return d.MetricsData, nil
}
var _ driver.DeviceDriver = (*Driver)(nil)