Files
sanderling/internal/verifier/spec_integration_test.go
T
pj 7493945251 feat: LTL operators, sampling, and default generators (#17)
* feat(ltl): add Now/Next/Eventually/Implies/Or/And/Not formulas

Replace the fold-with-latch evaluator with a residual-formula reducer.
Each Observe() instantiates a fresh obligation from the root (stripping
an outer Always), reduces each pending obligation against current state,
latches Violated on first failure, and surfaces Pending verdicts for
deferred obligations. Existing Always/Pure/Thunk tests continue to pass.

* feat(ltl): support relative duration for eventually().within()

* feat(proto): add Swipe, PressKey, RecentLogs RPCs

* feat(verifier,runner): formula handles, new action kinds, rich state

- verifier: add formula-spec registry; bindNow/bindNext/bindEventually with
  chainable .implies/.or/.and/.not and .within(n,unit) on eventually; bindFrom
  for uniform sampling. bindAlways keeps accepting plain predicates.
- verifier: store lastTree, lastAction, step time, logs, exceptions on the
  Verifier; SnapshotInput replaces the (snapshots, tree) pair. stateObject now
  produces state.lastAction/time/logs/exceptions matching the TS State type.
- verifier: make taps/swipes/waitOnce/pressKey built-in generators actually
  fire; taps picks a clickable, enabled element from the last hierarchy.
- agent: add exceptions field to Message wire format.
- driver: add Swipe/PressKey/RecentLogs to Driver interface; wire maestro
  client and mock driver. LogEntry exposed for runner consumption.
- runner: apply Swipe/PressKey/Wait actions; collect logcat and exceptions;
  pass lastAction and step time into PushSnapshot.

* feat(spec-api): LTL operators, new actions, richer State

- ltl.ts exports now/next/eventually; always overload accepts a Formula
- types.ts: Formula gains implies/or/and/not; EventuallyFormula adds .within;
  State gains lastAction/time/logs/exceptions; Swipe/PressKey/Wait action types
- actions.ts: Swipe/PressKey/Wait/from constructors; waitOnce + pressKey
  default generators
- tests exercise the chaining, sampling, and new actions through a recorded
  fake runtime

* feat(sidecar): add swipe, pressKey, recentLogs RPC handlers

* feat(sdk-android): capture uncaught exceptions

Install a default uncaught handler on Uatu.start, chained with any
existing handler so Android's crash reporter still runs. Expose
Uatu.reportError for callers to forward caught throwables. A bounded
circular buffer (default 50) drains into each STATE message's new
exceptions field. Protocol.kt serializes/deserializes the field,
matching the Go wire format added to internal/agent/protocol.go.

* feat(spec-api): add @uatu/spec/defaults/properties bundle

* feat(sample-app): exercise new LTL operators + defaults

spec.ts now imports eventually/next/now/from from @uatu/spec and
noUncaughtExceptions from @uatu/spec/defaults/properties. It declares
three properties that exercise the new surface:

- accountCountNonNegative: plain always() safety
- addAccountAdvances: always(now(x).implies(next(y)))
- eventuallyLoggedIn: eventually(p).within(30, "seconds")
- noUncaughtExceptions: imported default

The weighted actions root uses from() for random phone/name sampling
and entries for taps/swipes/waitOnce/pressKey built-ins.

SampleApplication gains a debug hook gated on the system property
uatu.inject_error so the e2e run can synthesize an Uatu.reportError and
verify noUncaughtExceptions violates.

cmd/uatu/test_run.go adds a subpath alias so specs importing
"@uatu/spec/defaults/properties" resolve against the in-tree source
when running from the uatu checkout. The spec-integration tests swap
the old click-counter fixtures for the new login hierarchy.

* feat(trace): record swipe/key/wait details + exceptions

trace.Step gains an Exceptions array so the trace captures the
class/message/stackTrace for each SDK-reported throwable in a step.
trace.Action gains FromX/FromY/ToX/ToY/Key/DurationMillis so the full
payload of Swipe/PressKey/Wait actions is visible in trace.jsonl.

sample-app's debug error hook now gates on ApplicationInfo.DEBUGGABLE
instead of a system property (adb setprop fails on non-rooted
emulators).
2026-04-20 02:19:39 +07:00

131 lines
4.2 KiB
Go

package verifier
import (
"encoding/json"
"path/filepath"
"testing"
"github.com/priyanshujain/uatu/internal/bundler"
"github.com/priyanshujain/uatu/internal/hierarchy"
"github.com/priyanshujain/uatu/internal/ltl"
)
const sampleAppHierarchyXML = `<?xml version="1.0" encoding="UTF-8"?>
<hierarchy rotation="0">
<node index="0" class="android.widget.FrameLayout" package="dev.uatu.sample" bounds="[0,0][1080,2400]">
<node index="0" class="android.widget.LinearLayout" bounds="[64,96][1016,2336]">
<node index="0" class="android.widget.TextView" text="Sign in" bounds="[100,200][900,300]" />
<node index="1" class="android.widget.EditText" content-desc="phone_field" clickable="true" enabled="true" bounds="[100,400][900,520]" />
<node index="2" class="android.widget.Button" text="Continue" clickable="true" enabled="true" bounds="[400,800][680,920]" />
</node>
</node>
</hierarchy>`
// bundleSampleAppSpec bundles examples/sample-app/spec.ts via the real
// @uatu/spec API so the integration test exercises the same path the CLI uses.
func bundleSampleAppSpec(t *testing.T) string {
t.Helper()
specPath, err := filepath.Abs("../../examples/sample-app/spec.ts")
if err != nil {
t.Fatal(err)
}
apiPath, err := filepath.Abs("../../pkg/spec-api/src/index.ts")
if err != nil {
t.Fatal(err)
}
defaultsPath, err := filepath.Abs("../../pkg/spec-api/src/defaults/properties.ts")
if err != nil {
t.Fatal(err)
}
bundle, err := bundler.Bundle(bundler.Options{
EntryFile: specPath,
Aliases: map[string]string{
"@uatu/spec": apiPath,
"@uatu/spec/defaults/properties": defaultsPath,
},
})
if err != nil {
t.Fatal(err)
}
return string(bundle.JavaScript)
}
// TestSampleAppSpecFiresLoginActions verifies the bundled sample-app spec
// emits Tap/InputText actions targeting the login screen elements when they
// are present in the hierarchy.
func TestSampleAppSpecFiresLoginActions(t *testing.T) {
v := newVerifier(t)
if err := v.Load(bundleSampleAppSpec(t)); err != nil {
t.Fatal(err)
}
tree, err := hierarchy.Parse(sampleAppHierarchyXML)
if err != nil {
t.Fatal(err)
}
snapshots := Snapshots{
"route": json.RawMessage(`"login"`),
"logged_in": json.RawMessage(`false`),
"account_count": json.RawMessage(`0`),
}
if err := v.PushSnapshot(SnapshotInput{Snapshots: snapshots, Tree: tree}); err != nil {
t.Fatal(err)
}
tapContinueHits := 0
typePhoneHits := 0
for range 400 {
action, err := v.NextAction()
if err != nil {
continue
}
switch {
case action.Kind == ActionKindTap && action.On == "text:Continue":
tapContinueHits++
case action.Kind == ActionKindInputText && action.On == "desc:phone_field":
typePhoneHits++
}
}
if tapContinueHits == 0 {
t.Fatal("tapContinue never fired on sample-app hierarchy")
}
if typePhoneHits == 0 {
t.Fatal("typePhone never fired on sample-app hierarchy")
}
}
// TestSampleAppSpecPropertiesEvaluate checks the properties declared in the
// sample-app spec evaluate sensibly across a small snapshot sequence. The
// spec mixes safety and liveness properties; Pending verdicts are expected
// for liveness properties that haven't had time to resolve yet.
func TestSampleAppSpecPropertiesEvaluate(t *testing.T) {
v := newVerifier(t)
if err := v.Load(bundleSampleAppSpec(t)); err != nil {
t.Fatal(err)
}
tree, err := hierarchy.Parse(sampleAppHierarchyXML)
if err != nil {
t.Fatal(err)
}
snapshots := Snapshots{
"route": json.RawMessage(`"login"`),
"logged_in": json.RawMessage(`false`),
"account_count": json.RawMessage(`0`),
}
if err := v.PushSnapshot(SnapshotInput{Snapshots: snapshots, Tree: tree}); err != nil {
t.Fatal(err)
}
verdicts := v.EvaluateProperties()
if verdicts["accountCountNonNegative"] != ltl.VerdictHolds {
t.Errorf("accountCountNonNegative: got %v, want holds", verdicts["accountCountNonNegative"])
}
if verdicts["noUncaughtExceptions"] != ltl.VerdictHolds {
t.Errorf("noUncaughtExceptions: got %v, want holds", verdicts["noUncaughtExceptions"])
}
// Liveness: eventuallyLoggedIn hasn't resolved yet.
if verdicts["eventuallyLoggedIn"] != ltl.VerdictPending {
t.Errorf("eventuallyLoggedIn: got %v, want pending", verdicts["eventuallyLoggedIn"])
}
}