Merge branch 'runner-uncertain-last-action' into pr-73-followups

internal/runner/runner.go

@@ -298,11 +298,18 @@ func Run(ctx context.Context, options Options) (Summary, error) {
 				logger.Warn("apply error; marking step transitional", "step", stepIndex, "err", err)
 				transitional = true
 				applySkipped = true
-				lastAction = nil
+				// The error says the call failed, not that the gesture never
+				// reached the app: a deadline that fires after dispatch leaves
+				// the effect committed. Reporting no action here would let a
+				// property convict the app for an effect with no cause, so the
+				// action is reported with its fate unknown instead.
+				unconfirmed := nextAction
+				lastAction = &unconfirmed
 			} else {
 				consecutiveApplyFailures = 0
-				actionCopy := nextAction
-				lastAction = &actionCopy
+				applied := nextAction
+				applied.Applied = true
+				lastAction = &applied
 			}
 		} else {
 			lastAction = nil

internal/runner/uncertain_last_action_test.go

@@ -0,0 +1,150 @@
+package runner
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"path/filepath"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/priyanshujain/sanderling/internal/driver"
+	mockdriver "github.com/priyanshujain/sanderling/internal/driver/mock"
+)
+
+// An apply error is not proof that nothing landed. An RPC deadline that fires
+// after the tap was dispatched leaves the transaction committed, and a runner
+// that reports "no action" for it hands
+// submitCommitsOneTransactionPerAction a rise of one transaction against a
+// window of zero submits: a conviction manufactured out of the runner's own
+// uncertainty, on the property carrying most of the detection on android.
+//
+// The spec below is the real folio predicate pair, imported from the example,
+// so what this asserts is the verdict the shipped property reaches.
+const uncertainApplySpecTemplate = `
+import { actions, always, extract, next, Tap } from "@sanderling/spec";
+import {
+  committedTransactionsExceedSubmits,
+  countSubmitsInWindow,
+} from "%s";
+
+let submits = 0;
+const submitsInWindow = extract("submitsInWindow", state => {
+  const window = countSubmitsInWindow({
+    previousCount: submits,
+    lastAction: state.lastAction,
+    fresh: true,
+  });
+  submits = window.next;
+  return window.reported;
+});
+
+const counts = extract("counts", state => {
+  const text = state.ax.find("id:TxnCount")?.text;
+  return text ? { Travel: parseInt(text, 10) } : null;
+});
+
+globalThis.properties = {
+  submitCommitsOneTransactionPerAction: always(
+    next(() =>
+      !committedTransactionsExceedSubmits({
+        countsBefore: counts.previous ?? null,
+        countsAfter: counts.current,
+        submitsInWindow: submitsInWindow.current,
+      }),
+    ),
+  ),
+};
+globalThis.actions = actions(() => [Tap({ on: "id:TxnSubmit" })]);
+`
+
+const homeWithTxnCount = `{"attributes":{"resource-id":"HomeScreen"},"children":[
+	{"attributes":{"resource-id":"TxnCount","text":"%d"},"children":[]},
+	{"attributes":{"resource-id":"TxnSubmit","bounds":"[40,80,240,160]"},"children":[],"clickable":true,"enabled":true}
+]}`
+
+// dispatchThenFailDriver is the device condition the runner cannot see through:
+// the tap reaches the app and commits, then the call the runner is waiting on
+// times out. Every later hierarchy read shows the committed transactions.
+type dispatchThenFailDriver struct {
+	*mockdriver.Driver
+	commitsPerTap int64
+	committed     atomic.Int64
+}
+
+func (d *dispatchThenFailDriver) Tap(context.Context, int, int) error {
+	return d.dispatchThenFail()
+}
+
+func (d *dispatchThenFailDriver) TapSelector(context.Context, string) error {
+	return d.dispatchThenFail()
+}
+
+func (d *dispatchThenFailDriver) dispatchThenFail() error {
+	d.committed.Add(d.commitsPerTap)
+	return errors.New("rpc error: code = DeadlineExceeded desc = context deadline exceeded")
+}
+
+func (d *dispatchThenFailDriver) Snapshot(context.Context) (string, driver.Image, error) {
+	return fmt.Sprintf(homeWithTxnCount, d.committed.Load()), driver.Image{}, nil
+}
+
+func TestRunner_ApplyErrorAfterDispatchDoesNotConvictTheSubmitCountingProperty(t *testing.T) {
+	predicates, err := filepath.Abs("../../examples/folio/sanderling/predicates.ts")
+	if err != nil {
+		t.Fatal(err)
+	}
+	spec := fmt.Sprintf(uncertainApplySpecTemplate, predicates)
+
+	run := func(t *testing.T, commitsPerTap int64) []ViolationRecord {
+		t.Helper()
+		state := newHarnessWithSpec(t, spec)
+		device := &dispatchThenFailDriver{Driver: state.mock, commitsPerTap: commitsPerTap}
+
+		ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+		defer cancel()
+		summary, err := Run(ctx, Options{
+			Duration:    time.Hour,
+			IdleTimeout: 20 * time.Millisecond,
+			MaxSteps:    2,
+			Driver:      device,
+			Verifier:    state.verifier,
+			TraceWriter: state.writer,
+		})
+		if err != nil {
+			t.Fatalf("Run: %v", err)
+		}
+		if summary.Steps != 2 {
+			t.Fatalf("steps = %d, want 2; the run never reached the step that judges the pair", summary.Steps)
+		}
+		if got := device.committed.Load(); got != commitsPerTap*2 {
+			t.Fatalf("the device committed %d transaction(s), want %d; the taps never reached it",
+				got, commitsPerTap*2)
+		}
+		return summary.Violations
+	}
+
+	t.Run("one transaction per tap is not a double submit", func(t *testing.T) {
+		if violations := run(t, 1); len(violations) != 0 {
+			t.Errorf("the counting property convicted a healthy app: %v\n"+
+				"one transaction rose against a submit the runner dispatched but "+
+				"could not confirm, and the spec was told no action happened",
+				violations)
+		}
+	})
+
+	// The control. Without it a green above proves nothing: a property that
+	// never sees a comparable pair is silently vacuous and reports the same
+	// empty violation list.
+	t.Run("two transactions per tap still convicts", func(t *testing.T) {
+		violations := run(t, 2)
+		if len(violations) == 0 {
+			t.Fatal("the counting property missed a double submit; the harness never " +
+				"put the property in a position to fire, so the case above proves nothing")
+		}
+		if violations[0].Properties[0] != "submitCommitsOneTransactionPerAction" {
+			t.Errorf("violated %v, want submitCommitsOneTransactionPerAction", violations[0].Properties)
+		}
+	})
+}

internal/runner/web_last_action_test.go

@@ -3,6 +3,7 @@ package runner
 import (
 	"context"
 	"encoding/json"
+	"errors"
 	"testing"
 	"time"
 
@@ -71,7 +72,47 @@ func TestRunner_WebInstallsLastActionInThePage(t *testing.T) {
 	// Every later step carries what the runner actually applied. The shape is
 	// the goja host's (internal/verifier/marshal.go lastActionFields), pinned
 	// against it by TestLastAction_WebJSONMatchesTheGojaObject.
-	const want = `{"kind":"Tap","on":"id:TxnSubmit"}`
+	const want = `{"kind":"Tap","applied":true,"on":"id:TxnSubmit"}`
+	if web.installed[1] != want {
+		t.Errorf("step 2 installed %s, want %s", web.installed[1], want)
+	}
+}
+
+// failingTapWebDriver dispatches the tap and then fails the call, the shape an
+// RPC deadline takes: the page has the click, the runner has an error.
+type failingTapWebDriver struct {
+	*tappingWebDriver
+}
+
+func (d *failingTapWebDriver) Tap(context.Context, int, int) error {
+	return errors.New("rpc error: code = DeadlineExceeded desc = context deadline exceeded")
+}
+
+// The web leg of the same three states the goja host reports. "applied":null is
+// not "no action": a property gated on the last action still sees the tap and
+// decides for itself, which it cannot do if the page is handed a bare null.
+func TestRunner_WebInstallsAnUnconfirmedActionWithItsFateUnknown(t *testing.T) {
+	state := newHarnessWithSpec(t, lastActionSpec)
+	web := &failingTapWebDriver{tappingWebDriver: &tappingWebDriver{Driver: state.mock}}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+	if _, err := Run(ctx, Options{
+		Duration:    time.Hour,
+		IdleTimeout: 20 * time.Millisecond,
+		MaxSteps:    2,
+		Driver:      web,
+		Verifier:    state.verifier,
+		TraceWriter: state.writer,
+	}); err != nil {
+		t.Fatalf("Run: %v", err)
+	}
+
+	if len(web.installed) < 2 {
+		t.Fatalf("the page was handed lastAction %d time(s); the web path never installed it",
+			len(web.installed))
+	}
+	const want = `{"kind":"Tap","applied":null,"on":"id:TxnSubmit"}`
 	if web.installed[1] != want {
 		t.Errorf("step 2 installed %s, want %s", web.installed[1], want)
 	}

internal/verifier/marshal.go

@@ -344,7 +344,19 @@ func lastActionFields(action *Action) []actionField {
 	point := func(x, y int) []actionField {
 		return []actionField{{key: "x", value: x}, {key: "y", value: y}}
 	}
-	fields := []actionField{{key: "kind", value: string(action.Kind)}}
+	// An action whose apply call failed is not an action that did not happen:
+	// the dispatch may have landed before the error. That is unknown, and
+	// unknown is null here for the same reason every other absence in the spec
+	// surface is, so a property decides for itself instead of being handed a
+	// "nothing happened" the runner cannot vouch for.
+	var applied any
+	if action.Applied {
+		applied = true
+	}
+	fields := []actionField{
+		{key: "kind", value: string(action.Kind)},
+		{key: "applied", value: applied},
+	}
 	if action.On != "" {
 		fields = append(fields, actionField{key: "on", value: action.On})
 	}
@@ -397,7 +409,7 @@ func objectFromFields(runtime *goja.Runtime, fields []actionField) *goja.Object
 // has no Go-side state object to read: the runner pushes this JSON into the
 // page before each extractor evaluation. A nil action encodes as JSON null,
 // the same value the goja host reports on the first step of a run and after a
-// step whose action was never applied.
+// step whose action was never dispatched.
 func EncodeLastAction(action *Action) json.RawMessage {
 	if action == nil {
 		return json.RawMessage("null")

internal/verifier/marshal_test.go

@@ -168,6 +168,7 @@ func TestLastAction_WebJSONMatchesTheGojaObject(t *testing.T) {
 	}{
 		{"nil", nil},
 		{"Tap", &Action{Kind: ActionKindTap, On: "id:TxnSubmit", X: 12, Y: 34}},
+		{"TapApplied", &Action{Kind: ActionKindTap, On: "id:TxnSubmit", Applied: true}},
 		{"TapWithoutSelector", &Action{Kind: ActionKindTap, X: 12, Y: 34}},
 		{"DoubleTap", &Action{Kind: ActionKindDoubleTap, On: `desc:say "hi" <b>`}},
 		{"InputText", &Action{Kind: ActionKindInputText, On: "id:field", Text: "50"}},
@@ -193,3 +194,42 @@ func TestLastAction_WebJSONMatchesTheGojaObject(t *testing.T) {
 		})
 	}
 }
+
+// A spec has to be able to tell three things apart: no action ran, an action
+// ran, and an action was dispatched whose fate the runner cannot vouch for.
+// The third used to be reported as the first, which is how a property that
+// reasons "an effect landed with no action to cause it" convicts an app over
+// an RPC deadline.
+func TestLastAction_SeparatesNoActionFromAnActionOfUnknownFate(t *testing.T) {
+	verifier := newVerifier(t)
+	mustLoad(t, verifier, `
+		globalThis.fate = __sanderling__.extract(state =>
+			state.lastAction === null ? "no action"
+			: state.lastAction.applied === true ? "applied"
+			: state.lastAction.applied === null ? "unknown"
+			: "unreadable");
+	`)
+
+	for _, testCase := range []struct {
+		name   string
+		action *Action
+		want   string
+	}{
+		{"nothing ran", nil, "no action"},
+		{"dispatch confirmed", &Action{Kind: ActionKindTap, On: "id:TxnSubmit", Applied: true}, "applied"},
+		{"dispatch unconfirmed", &Action{Kind: ActionKindTap, On: "id:TxnSubmit"}, "unknown"},
+	} {
+		t.Run(testCase.name, func(t *testing.T) {
+			if err := verifier.PushSnapshot(SnapshotInput{
+				Snapshots:  Snapshots{},
+				LastAction: testCase.action,
+			}); err != nil {
+				t.Fatal(err)
+			}
+			handle := verifier.runtime.GlobalObject().Get("fate").ToObject(verifier.runtime)
+			if got := handle.Get("current").String(); got != testCase.want {
+				t.Errorf("the spec read %q, want %q", got, testCase.want)
+			}
+		})
+	}
+}

internal/verifier/types.go

@@ -33,6 +33,11 @@ type Action struct {
 	// Direction is the scroll direction for ActionKindScroll: one of "up",
 	// "down", "left", "right". Empty for every other kind.
 	Direction string
+	// Applied is meaningful only on the action a step reports to the spec as
+	// state.lastAction: true when the runner saw the dispatch succeed, false
+	// when the apply call failed and nothing can say whether the action
+	// reached the app. The spec is told which of the two it is.
+	Applied bool
 }
 
 // LogEntry mirrors a logcat line captured between steps.