test(runner): retire the scaffolding the package grew by copying

Four consolidations, no assertion changed and the same 217 tests passing:

harness gains run and tryRun, retiring 68 copies of context.WithTimeout plus
Run(ctx, Options{}) plus an error check. The seven sites whose error check said
something specific keep their own wording.

mock.FailurePlan retires six wrapper drivers that were the same seven-line
method with a different error constant. The three that need more than an error
on call N stay.

traceStepLine absorbs the 15 local trace-line declarations and readTraceLines is
now the only reader. No local copy disagreed with internal/trace about a JSON
tag. Three raw readers stay on purpose: one decodes a real trace.Step, one
snapshots bytes, one asserts on raw JSON text.

One embeddable base carries the five V8-path methods the five web fakes each
redeclared.

internal/runner/composition_reread_test.go

@@ -1,20 +1,16 @@
 package runner
 
 import (
-	"bytes"
 	"context"
-	"encoding/json"
 	"fmt"
 	"os"
 	"path/filepath"
 	"strings"
 	"sync/atomic"
 	"testing"
-	"time"
 
 	"github.com/priyanshujain/sanderling/internal/driver"
 	mockdriver "github.com/priyanshujain/sanderling/internal/driver/mock"
-	"github.com/priyanshujain/sanderling/internal/trace"
 )
 
 // homeWithRows is one settled route whose list holds rows. A row arriving
@@ -68,19 +64,7 @@ func TestRunner_AStepWhoseTreeChangedBetweenReadsIsNotVerified(t *testing.T) {
 		state := newHarnessWithSpec(t, violationSpec)
 		device := &composesLateDriver{Driver: state.mock, composingReads: composingReads}
 
-		ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
-		defer cancel()
-		summary, err := Run(ctx, Options{
-			Duration:    time.Hour,
-			IdleTimeout: 20 * time.Millisecond,
-			MaxSteps:    3,
-			Driver:      device,
-			Verifier:    state.verifier,
-			TraceWriter: state.writer,
-		})
-		if err != nil {
-			t.Fatalf("Run: %v", err)
-		}
+		summary := state.run(t, Options{MaxSteps: 3, Driver: device})
 		if summary.Steps != 3 {
 			t.Fatalf("steps = %d, want 3", summary.Steps)
 		}
@@ -107,7 +91,7 @@ func TestRunner_AStepWhoseTreeChangedBetweenReadsIsNotVerified(t *testing.T) {
 		}
 		// Skipped is not lost: the step is still recorded, screenshot and all,
 		// so the run can be replayed over the frame nothing judged.
-		steps := traceSteps(t, directory)
+		steps := readTraceLines(t, directory)
 		if len(steps) != 3 {
 			t.Fatalf("trace holds %d step(s), want 3", len(steps))
 		}
@@ -201,19 +185,7 @@ func TestRunner_ASkippedStepDoesNotSwallowTheActionBeforeIt(t *testing.T) {
 			composingRead: composingRead,
 		}
 
-		ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-		defer cancel()
-		summary, err := Run(ctx, Options{
-			Duration:    time.Hour,
-			IdleTimeout: 20 * time.Millisecond,
-			MaxSteps:    3,
-			Driver:      device,
-			Verifier:    state.verifier,
-			TraceWriter: state.writer,
-		})
-		if err != nil {
-			t.Fatalf("Run: %v", err)
-		}
+		summary := state.run(t, Options{MaxSteps: 3, Driver: device})
 		if summary.Steps != 3 {
 			t.Fatalf("steps = %d, want 3", summary.Steps)
 		}
@@ -277,19 +249,7 @@ func TestRunner_ARunOfSkippedStepsReportsEveryActionItApplied(t *testing.T) {
 			composingThrough: 5,
 		}
 
-		ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-		defer cancel()
-		summary, err := Run(ctx, Options{
-			Duration:    time.Hour,
-			IdleTimeout: 20 * time.Millisecond,
-			MaxSteps:    6,
-			Driver:      device,
-			Verifier:    state.verifier,
-			TraceWriter: state.writer,
-		})
-		if err != nil {
-			t.Fatalf("Run: %v", err)
-		}
+		summary := state.run(t, Options{MaxSteps: 6, Driver: device})
 		if summary.Steps != 6 {
 			t.Fatalf("steps = %d, want 6", summary.Steps)
 		}
@@ -341,19 +301,7 @@ func TestRunner_AScreenThatNeverSettlesActsOnNothingAndSaysSo(t *testing.T) {
 	state := newHarnessWithSpec(t, specWithFolioPredicates(t))
 	device := &submitsOnTapDriver{Driver: state.mock, commitsPerTap: 1, everyRead: true}
 
-	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-	defer cancel()
-	summary, err := Run(ctx, Options{
-		Duration:    time.Hour,
-		IdleTimeout: 20 * time.Millisecond,
-		MaxSteps:    5,
-		Driver:      device,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	})
-	if err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	summary := state.run(t, Options{MaxSteps: 5, Driver: device})
 	if summary.Steps != 5 {
 		t.Fatalf("steps = %d, want 5; the run stalled instead of finishing its budget",
 			summary.Steps)
@@ -442,19 +390,7 @@ func TestRunner_OnlyAChangeOfShapeCostsAStepItsVerdict(t *testing.T) {
 				rereadTree:   testCase.reread,
 			}
 
-			ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
-			defer cancel()
-			summary, err := Run(ctx, Options{
-				Duration:    time.Hour,
-				IdleTimeout: 20 * time.Millisecond,
-				MaxSteps:    3,
-				Driver:      device,
-				Verifier:    state.verifier,
-				TraceWriter: state.writer,
-			})
-			if err != nil {
-				t.Fatalf("Run: %v", err)
-			}
+			summary := state.run(t, Options{MaxSteps: 3, Driver: device})
 			if summary.Steps != 3 {
 				t.Fatalf("steps = %d, want 3", summary.Steps)
 			}
@@ -484,26 +420,3 @@ func TestRunner_OnlyAChangeOfShapeCostsAStepItsVerdict(t *testing.T) {
 		})
 	}
 }
-
-type traceLine struct {
-	Step             int                              `json:"step"`
-	Violations       []string                         `json:"violations"`
-	ExtractorChanges map[string]trace.ExtractorChange `json:"extractor_changes"`
-}
-
-func traceSteps(t *testing.T, directory string) []traceLine {
-	t.Helper()
-	body, err := os.ReadFile(filepath.Join(directory, "trace.jsonl"))
-	if err != nil {
-		t.Fatal(err)
-	}
-	var steps []traceLine
-	for _, raw := range bytes.Split(bytes.TrimSpace(body), []byte("\n")) {
-		var line traceLine
-		if err := json.Unmarshal(raw, &line); err != nil {
-			t.Fatalf("decode trace line: %v", err)
-		}
-		steps = append(steps, line)
-	}
-	return steps
-}

internal/runner/element_extractor_trace_test.go

@@ -1,16 +1,9 @@
 package runner
 
 import (
-	"bufio"
-	"context"
 	"encoding/json"
 	"fmt"
-	"os"
-	"path/filepath"
 	"testing"
-	"time"
-
-	"github.com/priyanshujain/sanderling/internal/trace"
 )
 
 // elementExtractorSpec reads a live ax element, the shape every field and
@@ -47,43 +40,14 @@ func TestRunner_TraceRecordsElementValuedExtractors(t *testing.T) {
 	state := newHarnessWithSpec(t, elementExtractorSpec)
 	state.mock.HierarchyJSON = amountFieldTreeJSON
 
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-	summary, err := Run(ctx, Options{
-		Duration:    time.Hour,
-		IdleTimeout: 20 * time.Millisecond,
-		MaxSteps:    2,
-		Driver:      state.mock,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	})
-	if err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	summary := state.run(t, Options{MaxSteps: 2})
 	if !containsProperty(summary.Violations, "noAmountField") {
 		t.Fatalf("noAmountField did not violate, so the element never reached a predicate: %v",
 			summary.Violations)
 	}
 
-	file, err := os.Open(filepath.Join(state.writer.Directory(), "trace.jsonl"))
-	if err != nil {
-		t.Fatal(err)
-	}
-	defer file.Close()
-
-	type traceLine struct {
-		Step             int                              `json:"step"`
-		ExtractorChanges map[string]trace.ExtractorChange `json:"extractor_changes"`
-		Witnesses        map[string]trace.Witness         `json:"witnesses"`
-	}
 	changes, witnesses := 0, 0
-	scanner := bufio.NewScanner(file)
-	scanner.Buffer(make([]byte, 0, 64*1024), 8*1024*1024)
-	for scanner.Scan() {
-		var line traceLine
-		if err := json.Unmarshal(scanner.Bytes(), &line); err != nil {
-			t.Fatalf("trace line decode: %v", err)
-		}
+	for _, line := range readTraceLines(t, state.writer.Directory()) {
 		if change, ok := line.ExtractorChanges["amountField"]; ok {
 			changes++
 			assertAmountField(t, fmt.Sprintf("step %d extractor_changes", line.Step), change.Curr)
@@ -94,9 +58,6 @@ func TestRunner_TraceRecordsElementValuedExtractors(t *testing.T) {
 				witness.Extractors["amountField"])
 		}
 	}
-	if err := scanner.Err(); err != nil {
-		t.Fatalf("scan trace: %v", err)
-	}
 	if changes == 0 {
 		t.Error("amountField never appears in extractor_changes; the element the run read is not in the trace")
 	}

internal/runner/error_surface_trace_test.go

@@ -2,10 +2,6 @@ package runner
 
 import (
 	"context"
-	"encoding/json"
-	"os"
-	"path/filepath"
-	"strings"
 	"testing"
 	"time"
 
@@ -43,34 +39,13 @@ func TestRunner_LogsAndExceptionsLandInTheTrace(t *testing.T) {
 		Message:    "FATAL EXCEPTION: main",
 	}}
 
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-	if _, err := Run(ctx, Options{
-		Duration:    100 * time.Millisecond,
-		IdleTimeout: 20 * time.Millisecond,
-		MaxSteps:    1,
-		Driver:      &throwingDriver{Driver: state.mock},
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	}); err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	state.run(t, Options{
+		Duration: 100 * time.Millisecond,
+		MaxSteps: 1,
+		Driver:   &throwingDriver{Driver: state.mock},
+	})
 
-	body, err := os.ReadFile(
-		filepath.Join(state.writer.Directory(), "trace.jsonl"),
-	)
-	if err != nil {
-		t.Fatal(err)
-	}
-	line := strings.SplitN(strings.TrimSpace(string(body)), "\n", 2)[0]
-	var stored struct {
-		TraceVersion int               `json:"trace_version"`
-		Logs         []trace.LogEntry  `json:"logs"`
-		Exceptions   []trace.Exception `json:"exceptions"`
-	}
-	if err := json.Unmarshal([]byte(line), &stored); err != nil {
-		t.Fatalf("decode trace line: %v\n%s", err, line)
-	}
+	stored := readTraceLines(t, state.writer.Directory())[0]
 	if stored.TraceVersion != trace.TraceVersion {
 		t.Errorf(
 			"trace_version = %d, want %d; an old trace could not be told apart",

internal/runner/foreground_gate_budget_test.go

@@ -96,16 +96,11 @@ func TestRun_AppNeverReachesForegroundEndsTheRun(t *testing.T) {
 	state := newHarness(t)
 	device := &neverDrawsDriver{Driver: state.mock}
 
-	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-	defer cancel()
-	summary, err := Run(ctx, Options{
-		Duration:    time.Hour,
+	summary, err := state.tryRun(t, Options{
 		IdleTimeout: time.Millisecond,
 		MaxSteps:    3,
 		BundleID:    guardedBundleID,
 		Driver:      device,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
 	})
 
 	var notReached ForegroundNotReachedError
@@ -165,19 +160,12 @@ func TestRun_StepsOutsideTheAppAreRecordedInTheTrace(t *testing.T) {
 	state := newHarness(t)
 	device := &leavesForegroundForeverDriver{Driver: state.mock}
 
-	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-	defer cancel()
-	if _, err := Run(ctx, Options{
-		Duration:    time.Hour,
+	state.run(t, Options{
 		IdleTimeout: time.Millisecond,
 		MaxSteps:    2,
 		BundleID:    guardedBundleID,
 		Driver:      device,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	}); err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	})
 
 	records := preconditionRecords(t, state.writer.Directory())
 	if len(records) == 0 {

internal/runner/foreground_guard_last_action_test.go

@@ -6,7 +6,6 @@ import (
 	"path/filepath"
 	"sync/atomic"
 	"testing"
-	"time"
 
 	"github.com/priyanshujain/sanderling/internal/driver"
 	mockdriver "github.com/priyanshujain/sanderling/internal/driver/mock"
@@ -146,20 +145,7 @@ func runTwoSubmitSteps(
 	commitsPerTap int64,
 ) []ViolationRecord {
 	t.Helper()
-	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,
-		BundleID:    guardedBundleID,
-		Driver:      device,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	})
-	if err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	summary := state.run(t, Options{MaxSteps: 2, BundleID: guardedBundleID, Driver: device})
 	if summary.Steps != 2 {
 		t.Fatalf("steps = %d, want 2; the run never reached the step that judges the pair",
 			summary.Steps)
@@ -320,7 +306,7 @@ func runReportingTheGuard(t *testing.T, device committingDevice, state *harness)
 	if violations := runTwoSubmitSteps(t, state, device, 1); len(violations) != 0 {
 		t.Errorf("the spec was told the action ran untouched by any guard: %v", violations)
 	}
-	steps := traceSteps(t, state.writer.Directory())
+	steps := readTraceLines(t, state.writer.Directory())
 	if len(steps) != 2 {
 		t.Fatalf("trace holds %d step(s), want 2", len(steps))
 	}

internal/runner/golden_test.go

@@ -3,7 +3,6 @@ package runner
 import (
 	"bufio"
 	"bytes"
-	"context"
 	"encoding/json"
 	"os"
 	"path/filepath"
@@ -91,19 +90,7 @@ func TestGolden_TraceStreamIsReproducible(t *testing.T) {
 	state.verifier = mustSeededVerifier(t, fixtureSpec, goldenSeed)
 	state.mock.HierarchyJSON = `{"attributes":{"resource-id":"HomeScreen"},"children":[{"attributes":{"resource-id":"next","bounds":"[40,80,240,160]"},"children":[],"clickable":true,"enabled":true}]}`
 
-	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-	defer cancel()
-	_, err := Run(ctx, Options{
-		Duration:    time.Hour,
-		IdleTimeout: 10 * time.Millisecond,
-		MaxSteps:    goldenSteps,
-		Driver:      state.mock,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	})
-	if err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	state.run(t, Options{IdleTimeout: 10 * time.Millisecond, MaxSteps: goldenSteps})
 	raw, err := os.ReadFile(filepath.Join(state.writer.Directory(), "trace.jsonl"))
 	if err != nil {
 		t.Fatal(err)
@@ -119,19 +106,7 @@ func TestGolden_ViolationSummaryIsReproducible(t *testing.T) {
 	state := newHarnessWithSpec(t, violationSpec)
 	state.verifier = mustSeededVerifier(t, violationSpec, goldenSeed)
 
-	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-	defer cancel()
-	summary, err := Run(ctx, Options{
-		Duration:    time.Hour,
-		IdleTimeout: 10 * time.Millisecond,
-		MaxSteps:    goldenSteps,
-		Driver:      state.mock,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	})
-	if err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	summary := state.run(t, Options{IdleTimeout: 10 * time.Millisecond, MaxSteps: goldenSteps})
 
 	var rendered bytes.Buffer
 	RenderSummary(&rendered, summary, "android")

internal/runner/llm_source_test.go

@@ -493,7 +493,7 @@ func newSeededVerifier(t *testing.T) *verifier.Verifier {
 func TestPickSourcesRejectsLLMWithoutSpecConfig(t *testing.T) {
 	for name, activeDriver := range map[string]driver.DeviceDriver{
 		"native": nil,
-		"web":    &webMockDriver{Driver: mockdriver.New()},
+		"web":    &webMockDriver{webDriverBase: webDriverBase{Driver: mockdriver.New()}},
 	} {
 		t.Run(name, func(t *testing.T) {
 			action, extractor, err := pickSources(Options{
@@ -523,7 +523,7 @@ func TestPickSourcesOnWebComposesLLMWithWebExtractors(t *testing.T) {
 	fake := newFakeOpenRouter(t)
 	_, verifierInstance := newLLMSource(t, fake)
 	action, extractor, err := pickSources(Options{
-		Driver:    &webMockDriver{Driver: mockdriver.New()},
+		Driver:    &webMockDriver{webDriverBase: webDriverBase{Driver: mockdriver.New()}},
 		Verifier:  verifierInstance,
 		Generator: "llm",
 		Logger:    slog.New(slog.NewTextHandler(io.Discard, nil)),
@@ -541,7 +541,7 @@ func TestPickSourcesOnWebComposesLLMWithWebExtractors(t *testing.T) {
 
 func TestPickSourcesOnWebSeededKeepsBothOnV8(t *testing.T) {
 	action, extractor, err := pickSources(Options{
-		Driver:    &webMockDriver{Driver: mockdriver.New()},
+		Driver:    &webMockDriver{webDriverBase: webDriverBase{Driver: mockdriver.New()}},
 		Verifier:  newSeededVerifier(t),
 		Generator: "seeded",
 		Logger:    slog.New(slog.NewTextHandler(io.Discard, nil)),
@@ -768,22 +768,13 @@ func TestRunner_EveryModelCallFailingIsNotACleanRun(t *testing.T) {
 	state := newHarnessWithSpec(t, llmFixtureSpec)
 	state.mock.HierarchyJSON = llmTreeJSON
 
-	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-	defer cancel()
-	summary, err := Run(ctx, Options{
+	summary := state.run(t, Options{
 		Duration:    30 * time.Second,
-		IdleTimeout: 20 * time.Millisecond,
 		MaxSteps:    3,
-		Driver:      state.mock,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
 		Generator:   "llm",
 		LabelSource: verifier.LabelSourceVisibleText,
 		Logger:      slog.New(slog.NewTextHandler(io.Discard, nil)),
 	})
-	if err != nil {
-		t.Fatalf("Run: %v", err)
-	}
 
 	calls := readLLMCalls(t, state.writer.Directory())
 	if len(calls) != 3 {
@@ -845,22 +836,13 @@ func TestRunner_SetupActionsAreNotTheGeneratorDrivingTheApp(t *testing.T) {
 	state := newHarnessWithSpec(t, llmLoginSetupSpec)
 	state.mock.HierarchyJSON = llmTreeJSON
 
-	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-	defer cancel()
-	summary, err := Run(ctx, Options{
+	summary := state.run(t, Options{
 		Duration:    30 * time.Second,
-		IdleTimeout: 20 * time.Millisecond,
 		MaxSteps:    4,
-		Driver:      state.mock,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
 		Generator:   "llm",
 		LabelSource: verifier.LabelSourceVisibleText,
 		Logger:      slog.New(slog.NewTextHandler(io.Discard, nil)),
 	})
-	if err != nil {
-		t.Fatalf("Run: %v", err)
-	}
 
 	wantOutcomes := []string{
 		trace.LLMOutcomeSetupAction, trace.LLMOutcomeSetupAction,
@@ -933,22 +915,13 @@ func TestRunner_SetupAndGeneratorBothDrivingIsAHealthyRun(t *testing.T) {
 	fake.choice = tap.Index
 	fake.chosenAction = tap.Description
 
-	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-	defer cancel()
-	summary, err := Run(ctx, Options{
+	summary := state.run(t, Options{
 		Duration:    30 * time.Second,
-		IdleTimeout: 20 * time.Millisecond,
 		MaxSteps:    4,
-		Driver:      state.mock,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
 		Generator:   "llm",
 		LabelSource: verifier.LabelSourceVisibleText,
 		Logger:      slog.New(slog.NewTextHandler(io.Discard, nil)),
 	})
-	if err != nil {
-		t.Fatalf("Run: %v", err)
-	}
 
 	if summary.DispatchedActions != 4 {
 		t.Errorf("DispatchedActions = %d, want 4: every step drove the app",

internal/runner/navigation_trace_test.go

@@ -1,17 +1,12 @@
 package runner
 
 import (
-	"bufio"
 	"context"
-	"encoding/json"
-	"os"
-	"path/filepath"
 	"testing"
 	"time"
 
 	"github.com/priyanshujain/sanderling/internal/driver"
 	mockdriver "github.com/priyanshujain/sanderling/internal/driver/mock"
-	"github.com/priyanshujain/sanderling/internal/trace"
 )
 
 // navigatingDriver reports one navigation per step, the way a page that submits
@@ -33,46 +28,20 @@ func TestRunner_TheTraceRecordsThatThePageNavigated(t *testing.T) {
 	const url = "http://127.0.0.1/index.html?"
 	navigating := &navigatingDriver{Driver: state.mock, url: url}
 
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-	if _, err := Run(ctx, Options{
-		Duration:    100 * time.Millisecond,
-		IdleTimeout: 20 * time.Millisecond,
-		MaxSteps:    3,
-		Driver:      navigating,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	}); err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	state.run(t, Options{Duration: 100 * time.Millisecond, MaxSteps: 3, Driver: navigating})
 	if err := state.writer.Close(); err != nil {
 		t.Fatalf("close trace: %v", err)
 	}
 
-	file, err := os.Open(filepath.Join(state.writer.Directory(), "trace.jsonl"))
-	if err != nil {
-		t.Fatal(err)
-	}
-	defer file.Close()
-
 	recorded := 0
-	scanner := bufio.NewScanner(file)
-	scanner.Buffer(make([]byte, 0, 64*1024), 8*1024*1024)
-	for scanner.Scan() {
-		var step struct {
-			Index       int                `json:"step"`
-			Navigations []trace.Navigation `json:"navigations"`
-		}
-		if err := json.Unmarshal(scanner.Bytes(), &step); err != nil {
-			t.Fatalf("trace line decode: %v", err)
-		}
+	for _, step := range readTraceLines(t, state.writer.Directory()) {
 		for _, navigation := range step.Navigations {
 			recorded++
 			if navigation.URL != url {
-				t.Errorf("step %d records navigation to %q, want %q", step.Index, navigation.URL, url)
+				t.Errorf("step %d records navigation to %q, want %q", step.Step, navigation.URL, url)
 			}
 			if navigation.UnixMillis == 0 {
-				t.Errorf("step %d records a navigation with no timestamp", step.Index)
+				t.Errorf("step %d records a navigation with no timestamp", step.Step)
 			}
 		}
 	}

internal/runner/redaction_test.go

@@ -5,7 +5,6 @@ import (
 	"fmt"
 	"strings"
 	"testing"
-	"time"
 
 	mockdriver "github.com/priyanshujain/sanderling/internal/driver/mock"
 
@@ -160,20 +159,9 @@ func TestTheTraceNeverCarriesATypedSecretThroughALastActionExtractor(t *testing.
 			state := newHarnessWithSpec(t, fmt.Sprintf(lastActionExtractorSpec, testCase.selector))
 			state.mock.HierarchyJSON = testCase.treeJSON
 
-			ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
-			defer cancel()
-			if _, err := Run(ctx, Options{
-				Duration:    time.Hour,
-				IdleTimeout: 20 * time.Millisecond,
-				MaxSteps:    2,
-				Driver:      state.mock,
-				Verifier:    state.verifier,
-				TraceWriter: state.writer,
-			}); err != nil {
-				t.Fatalf("Run: %v", err)
-			}
+			state.run(t, Options{MaxSteps: 2})
 
-			steps := traceSteps(t, state.writer.Directory())
+			steps := readTraceLines(t, state.writer.Directory())
 			if len(steps) < 2 {
 				t.Fatalf("trace holds %d step(s), want the step that reports the action back", len(steps))
 			}

internal/runner/uncertain_last_action_test.go

@@ -7,7 +7,6 @@ import (
 	"path/filepath"
 	"sync/atomic"
 	"testing"
-	"time"
 
 	"github.com/priyanshujain/sanderling/internal/driver"
 	mockdriver "github.com/priyanshujain/sanderling/internal/driver/mock"
@@ -106,19 +105,7 @@ func TestRunner_ApplyErrorAfterDispatchDoesNotConvictTheSubmitCountingProperty(t
 		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)
-		}
+		summary := state.run(t, Options{MaxSteps: 2, Driver: device})
 		if summary.Steps != 2 {
 			t.Fatalf("steps = %d, want 2; the run never reached the step that judges the pair", summary.Steps)
 		}

internal/runner/web_carrier_test.go

@@ -6,15 +6,11 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"os"
-	"path/filepath"
 	"strconv"
 	"testing"
 	"time"
 
 	"github.com/priyanshujain/sanderling/internal/driver"
-	mockdriver "github.com/priyanshujain/sanderling/internal/driver/mock"
-	"github.com/priyanshujain/sanderling/internal/trace"
 )
 
 // carrierSpec registers one extractor whose value the page supplies. It stands
@@ -33,7 +29,7 @@ globalThis.actions = actions(() => []);
 // whose page-side extractor advances a counter on every evaluation - exactly
 // what a spec-authored carrier does in V8.
 type carrierWebDriver struct {
-	*mockdriver.Driver
+	webDriverBase
 	transitional bool
 	snapshots    int
 	reads        int
@@ -53,8 +49,6 @@ func (d *carrierWebDriver) Snapshot(ctx context.Context) (string, driver.Image,
 	]}`, d.snapshots), image, err
 }
 
-func (d *carrierWebDriver) InstallBundle(context.Context, []byte) error { return nil }
-
 // A web target says so. The runner's per-step hierarchy reread is android-only,
 // and a fake claiming android would take a path no chrome run takes.
 func (d *carrierWebDriver) Health(context.Context) (driver.Health, error) {
@@ -73,10 +67,6 @@ func (d *carrierWebDriver) NextActionFromV8(context.Context) (json.RawMessage, e
 	return json.RawMessage(`{"kind":"Tap","x":5,"y":5}`), nil
 }
 
-func (d *carrierWebDriver) SetLastAction(context.Context, json.RawMessage) error { return nil }
-
-func (d *carrierWebDriver) SetLogs(context.Context, json.RawMessage) error { return nil }
-
 // TestRunner_TransitionalStepNeverAdvancesThePageCarrier pins the ordering the
 // web path depends on. The page-side extractors must run only on steps the
 // verifier accepts: their getters advance spec state every time they evaluate,
@@ -86,41 +76,16 @@ func (d *carrierWebDriver) SetLogs(context.Context, json.RawMessage) error { ret
 // convicts an app that did nothing wrong.
 func TestRunner_TransitionalStepNeverAdvancesThePageCarrier(t *testing.T) {
 	state := newHarnessWithSpec(t, carrierSpec)
-	web := &carrierWebDriver{Driver: state.mock}
+	web := &carrierWebDriver{webDriverBase: webDriverBase{Driver: state.mock}}
 
-	ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
-	defer cancel()
-	summary, err := Run(ctx, Options{
-		Duration:    30 * time.Second,
-		IdleTimeout: 20 * time.Millisecond,
-		MaxSteps:    5,
-		Driver:      web,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	})
-	if err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	summary := state.run(t, Options{Duration: 30 * time.Second, MaxSteps: 5, Driver: web})
 	if summary.Steps != 5 {
 		t.Fatalf("steps = %d, want 5", summary.Steps)
 	}
 
-	type traceLine struct {
-		Step             int                              `json:"step"`
-		Transitional     bool                             `json:"transitional"`
-		ExtractorChanges map[string]trace.ExtractorChange `json:"extractor_changes"`
-	}
-	body, err := os.ReadFile(filepath.Join(state.writer.Directory(), "trace.jsonl"))
-	if err != nil {
-		t.Fatal(err)
-	}
 	verified, transitional := 0, 0
 	previous := 0
-	for _, raw := range bytes.Split(bytes.TrimSpace(body), []byte("\n")) {
-		var line traceLine
-		if err := json.Unmarshal(raw, &line); err != nil {
-			t.Fatalf("decode trace line: %v", err)
-		}
+	for _, line := range readTraceLines(t, state.writer.Directory()) {
 		if line.Transitional {
 			transitional++
 			continue
@@ -157,11 +122,9 @@ func TestRunner_TransitionalStepNeverAdvancesThePageCarrier(t *testing.T) {
 // lastAction: an older published @sanderling/spec runtime, a bundle that never
 // installed, a tab that navigated away from it.
 type installFailsWebDriver struct {
-	*mockdriver.Driver
+	webDriverBase
 }
 
-func (d *installFailsWebDriver) InstallBundle(context.Context, []byte) error { return nil }
-
 func (d *installFailsWebDriver) EvaluateExtractors(context.Context) (map[int]json.RawMessage, error) {
 	return map[int]json.RawMessage{0: json.RawMessage(`1`)}, nil
 }
@@ -174,8 +137,6 @@ func (d *installFailsWebDriver) SetLastAction(context.Context, json.RawMessage)
 	return errors.New("__sanderlingSetLastAction__ is not a function")
 }
 
-func (d *installFailsWebDriver) SetLogs(context.Context, json.RawMessage) error { return nil }
-
 // TestRunner_LastActionInstallFailureFailsTheRun covers the other half of the
 // same trust boundary. A run that cannot install lastAction in the page cannot
 // apply the page's extractor values either, so the step keeps goja's
@@ -184,18 +145,9 @@ func (d *installFailsWebDriver) SetLogs(context.Context, json.RawMessage) error
 // green run reporting a violation nobody can reproduce.
 func TestRunner_LastActionInstallFailureFailsTheRun(t *testing.T) {
 	state := newHarnessWithSpec(t, carrierSpec)
-	web := &installFailsWebDriver{Driver: state.mock}
+	web := &installFailsWebDriver{webDriverBase: webDriverBase{Driver: state.mock}}
 
-	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
-	defer cancel()
-	_, err := Run(ctx, Options{
-		Duration:    2 * time.Second,
-		IdleTimeout: 20 * time.Millisecond,
-		MaxSteps:    3,
-		Driver:      web,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	})
+	_, err := state.tryRun(t, Options{Duration: 2 * time.Second, MaxSteps: 3, Driver: web})
 	if err == nil {
 		t.Fatal("Run succeeded with a page that cannot take lastAction; the run " +
 			"reported green while its extractor values came from two engines")
@@ -229,19 +181,10 @@ func (d *logInstallFailsWebDriver) SetLogs(context.Context, json.RawMessage) err
 func TestRunner_LogInstallFailureFailsTheRun(t *testing.T) {
 	state := newHarnessWithSpec(t, carrierSpec)
 	web := &logInstallFailsWebDriver{
-		installFailsWebDriver: &installFailsWebDriver{Driver: state.mock},
+		installFailsWebDriver: &installFailsWebDriver{webDriverBase: webDriverBase{Driver: state.mock}},
 	}
 
-	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
-	defer cancel()
-	_, err := Run(ctx, Options{
-		Duration:    2 * time.Second,
-		IdleTimeout: 20 * time.Millisecond,
-		MaxSteps:    3,
-		Driver:      web,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	})
+	_, err := state.tryRun(t, Options{Duration: 2 * time.Second, MaxSteps: 3, Driver: web})
 	if err == nil {
 		t.Fatal("Run succeeded with a page that cannot take the step's logs; " +
 			"every property reading the log stream ran against an empty array")

internal/runner/web_extractor_trace_test.go

@@ -1,17 +1,11 @@
 package runner
 
 import (
-	"bufio"
 	"context"
 	"encoding/json"
-	"os"
-	"path/filepath"
 	"strings"
 	"testing"
 	"time"
-
-	mockdriver "github.com/priyanshujain/sanderling/internal/driver/mock"
-	"github.com/priyanshujain/sanderling/internal/trace"
 )
 
 // engineDisagreementSpec makes the two runtimes disagree on purpose: the
@@ -31,24 +25,14 @@ globalThis.actions = actions(() => []);
 // takes the V8 path, where extractor values come from the page rather than
 // from goja.
 type webMockDriver struct {
-	*mockdriver.Driver
+	webDriverBase
 	overrides map[int]json.RawMessage
 }
 
-func (d *webMockDriver) InstallBundle(context.Context, []byte) error { return nil }
-
 func (d *webMockDriver) EvaluateExtractors(context.Context) (map[int]json.RawMessage, error) {
 	return d.overrides, nil
 }
 
-func (d *webMockDriver) NextActionFromV8(context.Context) (json.RawMessage, error) {
-	return nil, nil
-}
-
-func (d *webMockDriver) SetLastAction(context.Context, json.RawMessage) error { return nil }
-
-func (d *webMockDriver) SetLogs(context.Context, json.RawMessage) error { return nil }
-
 // TestRunner_TraceRecordsTheValueTheVerdictUsed fails if the trace and the
 // verdict disagree about an extractor. A witness is only an explanation of a
 // violation if it holds the state the violated property was evaluated against.
@@ -56,46 +40,18 @@ func TestRunner_TraceRecordsTheValueTheVerdictUsed(t *testing.T) {
 	state := newHarnessWithSpec(t, engineDisagreementSpec)
 	const pageValue = `"v8"`
 	web := &webMockDriver{
-		Driver:    state.mock,
-		overrides: map[int]json.RawMessage{0: json.RawMessage(pageValue)},
+		webDriverBase: webDriverBase{Driver: state.mock},
+		overrides:     map[int]json.RawMessage{0: json.RawMessage(pageValue)},
 	}
 
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-	summary, err := Run(ctx, Options{
-		Duration:    100 * time.Millisecond,
-		IdleTimeout: 20 * time.Millisecond,
-		Driver:      web,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	})
-	if err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	summary := state.run(t, Options{Duration: 100 * time.Millisecond, Driver: web})
 	if !containsProperty(summary.Violations, "ranInGoja") {
 		t.Fatalf("ranInGoja did not violate, so the page value never reached the verdict: %v",
 			summary.Violations)
 	}
 
-	file, err := os.Open(filepath.Join(state.writer.Directory(), "trace.jsonl"))
-	if err != nil {
-		t.Fatal(err)
-	}
-	defer file.Close()
-
-	type traceLine struct {
-		Step             int                              `json:"step"`
-		ExtractorChanges map[string]trace.ExtractorChange `json:"extractor_changes"`
-		Witnesses        map[string]trace.Witness         `json:"witnesses"`
-	}
 	changes, witnesses := 0, 0
-	scanner := bufio.NewScanner(file)
-	scanner.Buffer(make([]byte, 0, 64*1024), 8*1024*1024)
-	for scanner.Scan() {
-		var line traceLine
-		if err := json.Unmarshal(scanner.Bytes(), &line); err != nil {
-			t.Fatalf("trace line decode: %v", err)
-		}
+	for _, line := range readTraceLines(t, state.writer.Directory()) {
 		if change, ok := line.ExtractorChanges["engine"]; ok {
 			changes++
 			if got := string(change.Curr); got != pageValue {
@@ -111,9 +67,6 @@ func TestRunner_TraceRecordsTheValueTheVerdictUsed(t *testing.T) {
 			}
 		}
 	}
-	if err := scanner.Err(); err != nil {
-		t.Fatalf("scan trace: %v", err)
-	}
 	if changes == 0 {
 		t.Error("no extractor change reached the trace; nothing was compared")
 	}
@@ -143,20 +96,11 @@ globalThis.actions = actions(() => []);
 func TestRunner_PartialExtractorTableIsFatal(t *testing.T) {
 	state := newHarnessWithSpec(t, splitTableSpec)
 	web := &webMockDriver{
-		Driver:    state.mock,
-		overrides: map[int]json.RawMessage{0: json.RawMessage(`"v8"`)},
+		webDriverBase: webDriverBase{Driver: state.mock},
+		overrides:     map[int]json.RawMessage{0: json.RawMessage(`"v8"`)},
 	}
 
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-	_, err := Run(ctx, Options{
-		Duration:    time.Hour,
-		IdleTimeout: 20 * time.Millisecond,
-		MaxSteps:    2,
-		Driver:      web,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	})
+	_, err := state.tryRun(t, Options{MaxSteps: 2, Driver: web})
 	if err == nil {
 		t.Fatal("the run completed on a page that reported 1 of 2 extractors; " +
 			"the second extractor silently kept goja's value")

internal/runner/web_last_action_test.go

@@ -8,7 +8,6 @@ import (
 	"log/slog"
 	"strings"
 	"testing"
-	"time"
 
 	"github.com/priyanshujain/sanderling/internal/driver"
 	mockdriver "github.com/priyanshujain/sanderling/internal/driver/mock"
@@ -29,17 +28,11 @@ globalThis.properties = {};
 // tappingWebDriver is a web target whose V8 picker always taps one named
 // control, so the runner has a real applied action to report on the next step.
 type tappingWebDriver struct {
-	*mockdriver.Driver
+	webDriverBase
 	installed     []string
 	installedLogs []string
 }
 
-func (d *tappingWebDriver) InstallBundle(context.Context, []byte) error { return nil }
-
-func (d *tappingWebDriver) EvaluateExtractors(context.Context) (map[int]json.RawMessage, error) {
-	return nil, nil
-}
-
 func (d *tappingWebDriver) NextActionFromV8(context.Context) (json.RawMessage, error) {
 	return json.RawMessage(`{"kind":"Tap","x":12,"y":34,"selector":"id:TxnSubmit"}`), nil
 }
@@ -56,20 +49,9 @@ func (d *tappingWebDriver) SetLogs(_ context.Context, encoded json.RawMessage) e
 
 func TestRunner_WebInstallsLastActionInThePage(t *testing.T) {
 	state := newHarnessWithSpec(t, lastActionSpec)
-	web := &tappingWebDriver{Driver: state.mock}
+	web := &tappingWebDriver{webDriverBase: webDriverBase{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:    3,
-		Driver:      web,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-	}); err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	state.run(t, Options{MaxSteps: 3, Driver: web})
 
 	if len(web.installed) < 2 {
 		t.Fatalf("the page was handed lastAction %d time(s); the web path never installed it",
@@ -97,20 +79,9 @@ func TestRunner_WebInstallsTheStepsLogsInThePage(t *testing.T) {
 	state.mock.LogEntries = []driver.LogEntry{
 		{UnixMillis: 1700000000123, Level: "E", Tag: "console", Message: "boom from the page"},
 	}
-	web := &tappingWebDriver{Driver: state.mock}
+	web := &tappingWebDriver{webDriverBase: webDriverBase{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)
-	}
+	state.run(t, Options{MaxSteps: 2, Driver: web})
 
 	if len(web.installedLogs) == 0 {
 		t.Fatal("the page was never handed the step's logs; every property reading " +
@@ -135,19 +106,7 @@ func TestRunner_ReportsALogFetchItCouldNotMake(t *testing.T) {
 	var buffer bytes.Buffer
 	logger := slog.New(slog.NewTextHandler(&buffer, &slog.HandlerOptions{Level: slog.LevelWarn}))
 
-	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:      state.mock,
-		Verifier:    state.verifier,
-		TraceWriter: state.writer,
-		Logger:      logger,
-	}); err != nil {
-		t.Fatalf("Run: %v", err)
-	}
+	state.run(t, Options{MaxSteps: 2, Logger: logger})
 
 	if !strings.Contains(buffer.String(), "adb: device offline") {
 		t.Errorf("the run never reported the failed log fetch, so noLogcatErrors "+
@@ -170,21 +129,12 @@ func (d *failingTapWebDriver) Tap(context.Context, int, int) error {
 // 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)
+	web := &failingTapWebDriver{
+		tappingWebDriver: &tappingWebDriver{webDriverBase: webDriverBase{Driver: state.mock}},
 	}
 
+	state.run(t, Options{MaxSteps: 2, Driver: web})
+
 	if len(web.installed) < 2 {
 		t.Fatalf("the page was handed lastAction %d time(s); the web path never installed it",
 			len(web.installed))