fix(runner): a secure field's value does not reach state.lastAction either

folio extracts lastAction, and extractor values are persisted as
extractor_changes, so the password still reached the run directory
through the spec after the three render sites were closed.

The wrap sits in the runner rather than in lastActionFields because the
hosts hold the next step's tree, not the one the action was chosen
against: a field that stops being secure between the two would publish
what the trace withheld. Live and replay now agree byte for byte.

internal/runner/redaction_test.go

@@ -2,8 +2,10 @@ package runner
 
 import (
 	"context"
+	"fmt"
 	"strings"
 	"testing"
+	"time"
 
 	mockdriver "github.com/priyanshujain/sanderling/internal/driver/mock"
 
@@ -129,6 +131,67 @@ func TestApplyActionTypesTheRealValueIntoEveryField(t *testing.T) {
 	}
 }
 
+// lastActionExtractorSpec is what examples/folio/sanderling/spec.ts does with
+// the previous step's action: it extracts state.lastAction whole. Extractor
+// values are written to the trace as extractor_changes, so a typed value that
+// reaches state.lastAction.text lands in the run directory through the spec
+// rather than through the runner.
+const lastActionExtractorSpec = `
+import { actions, always, extract, InputText } from "@sanderling/spec";
+const reported = extract("lastAction", state => state.lastAction);
+globalThis.properties = {
+  theActionReachesTheSpec: always(() => reported.current !== undefined),
+};
+globalThis.actions = actions(() => [InputText({ into: "%s", text: "` + typedCredential + `" })]);
+`
+
+func TestTheTraceNeverCarriesATypedSecretThroughALastActionExtractor(t *testing.T) {
+	for _, testCase := range []struct {
+		name     string
+		treeJSON string
+		selector string
+	}{
+		{"ios secure field", iosLoginTreeJSON, "id:LoginPassword"},
+		{"web secure field", webLoginTreeJSON, "id:login-password"},
+		{"android field reported as neither", androidLoginTreeJSON, "id:login_email"},
+	} {
+		t.Run(testCase.name, func(t *testing.T) {
+			fastFocusSettle(t)
+			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)
+			}
+
+			steps := traceSteps(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))
+			}
+			change, ok := steps[1].ExtractorChanges["lastAction"]
+			if !ok {
+				t.Fatalf("step 2 recorded no reading of state.lastAction: %+v", steps[1])
+			}
+			if strings.Contains(string(change.Curr), typedCredential) {
+				t.Errorf("the trace carries the typed value through state.lastAction: %s", change.Curr)
+			}
+			if !strings.Contains(string(change.Curr), verifier.RedactedInputText) {
+				t.Errorf("state.lastAction reported %s, want the typed value redacted in place",
+					change.Curr)
+			}
+		})
+	}
+}
+
 const secureLoginSpec = `
 import { llm, always, actions, InputText, taps, typing, weighted } from "@sanderling/spec";
 globalThis.properties = { ok: always(() => true) };

internal/runner/runner.go

@@ -451,7 +451,7 @@ func Run(ctx context.Context, options Options) (Summary, error) {
 				// 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
+				unconfirmed := verifier.RecordedAction(nextAction, tree)
 				lastAction = &unconfirmed
 			} else if notDispatched != "" {
 				// The action was chosen but nothing reached the driver, so the
@@ -466,7 +466,7 @@ func Run(ctx context.Context, options Options) (Summary, error) {
 				lastAction = nil
 			} else {
 				consecutiveApplyFailures = 0
-				applied := nextAction
+				applied := verifier.RecordedAction(nextAction, tree)
 				applied.Applied = true
 				lastAction = &applied
 			}

internal/verifier/redaction.go

@@ -50,12 +50,30 @@ func RecordedActionText(action Action, tree *hierarchy.Tree) string {
 	return recordedInputText(action.Text, secureFactOf(target))
 }
 
+// RecordedAction is the action as everything downstream of the dispatch sees
+// it. The runner reports the previous step's action to the spec as
+// state.lastAction, and a spec extracting it (examples/folio/sanderling/spec.ts)
+// writes it to the trace, so the copy the runner keeps carries the recorded
+// text rather than the typed one.
+//
+// The decision is made here rather than where the two hosts render
+// state.lastAction because only the caller holds the tree that can answer it.
+// The hosts hold the NEXT step's tree, where the selector may name a different
+// element (a revealed password field reports secure:false) or none at all, and
+// cmd/internal-tools/oracle-reduction replays state.lastAction from the trace's
+// already-recorded text, which redacting here matches exactly.
+func RecordedAction(action Action, tree *hierarchy.Tree) Action {
+	action.Text = RecordedActionText(action, tree)
+	return action
+}
+
 // recordedInputText is the one place a typed value is rendered for a record.
-// The prompt's recent-action memory, the numbered candidate list and the trace
-// all go through it, so a fourth record added later cannot publish a value the
-// other three withhold. The driver dispatch reads Action.Text directly and is
-// the only reader of the real value, which is what keeps the app receiving the
-// keystrokes a user would have produced.
+// The prompt's recent-action memory, the numbered candidate list, the trace and
+// the action the runner reports back as state.lastAction all go through it, so
+// a fifth record added later cannot publish a value the other four withhold.
+// The driver dispatch reads Action.Text directly and is the only reader of the
+// real value, which is what keeps the app receiving the keystrokes a user would
+// have produced.
 //
 // A target the platform reports as a secure entry is redacted, and so is a
 // target carrying no report at all. iOS and web state the fact on every

internal/verifier/redaction_test.go

@@ -3,6 +3,8 @@ package verifier
 import (
 	"strings"
 	"testing"
+
+	"github.com/priyanshujain/sanderling/internal/hierarchy"
 )
 
 // typedCredential stands in for what a login setup types. Nothing rendered for
@@ -109,3 +111,86 @@ func TestCandidatesRedactTextTypedIntoAnAndroidElementHandle(t *testing.T) {
 			candidates[0].Action.Text)
 	}
 }
+
+// lastActionOnBothHosts reports what a spec reading state.lastAction sees on
+// each host for an action the runner has recorded: the goja host stringifies
+// its own object, the web host receives EncodeLastAction's JSON and installs
+// the parsed value in the page.
+func lastActionOnBothHosts(t *testing.T, action Action, treeJSON string) (string, string) {
+	t.Helper()
+	tree, err := hierarchy.Parse(treeJSON)
+	if err != nil {
+		t.Fatalf("parse tree: %v", err)
+	}
+	recorded := RecordedAction(action, tree)
+	verifier := newVerifier(t)
+	mustLoad(t, verifier, `
+		globalThis.last = __sanderling__.extract(state => JSON.stringify(state.lastAction));
+	`)
+	if err := verifier.PushSnapshot(SnapshotInput{
+		Snapshots:  Snapshots{},
+		Tree:       tree,
+		LastAction: &recorded,
+	}); err != nil {
+		t.Fatalf("PushSnapshot: %v", err)
+	}
+	handle := verifier.runtime.GlobalObject().Get("last").ToObject(verifier.runtime)
+	return handle.Get("current").String(), string(EncodeLastAction(&recorded))
+}
+
+func typedInto(selector, text string) Action {
+	return Action{Kind: ActionKindInputText, On: selector, Text: text}
+}
+
+// A spec extracting state.lastAction (examples/folio/sanderling/spec.ts) writes
+// what it reads into the trace, so state.lastAction is a record like the other
+// three and carries the same rule on both hosts.
+func TestStateLastActionRedactsATypedValueTheTargetCannotClear(t *testing.T) {
+	for _, testCase := range []struct {
+		name     string
+		treeJSON string
+		selector string
+	}{
+		{"secure field", secureLoginTreeJSON, "id:LoginPassword"},
+		{"android field reported as neither", androidLoginTreeJSON, "id:login_email"},
+		{"android password field", androidLoginTreeJSON, "id:login_password"},
+	} {
+		t.Run(testCase.name, func(t *testing.T) {
+			goja, web := lastActionOnBothHosts(
+				t, typedInto(testCase.selector, typedCredential), testCase.treeJSON)
+			for _, host := range []struct{ name, reported string }{
+				{"goja", goja},
+				{"web", web},
+			} {
+				if strings.Contains(host.reported, typedCredential) {
+					t.Errorf("the %s host publishes the typed value in state.lastAction: %s",
+						host.name, host.reported)
+				}
+				if !strings.Contains(host.reported, RedactedInputText) {
+					t.Errorf("the %s host reports state.lastAction as %s, want the typed value "+
+						"redacted in place", host.name, host.reported)
+				}
+			}
+			if goja != web {
+				t.Errorf("the two hosts disagree on state.lastAction\n goja: %s\n  web: %s", goja, web)
+			}
+		})
+	}
+}
+
+func TestStateLastActionKeepsATypedValueForAFieldReportedNotSecure(t *testing.T) {
+	const address = "[email protected]"
+	goja, web := lastActionOnBothHosts(t, typedInto("id:LoginEmail", address), secureLoginTreeJSON)
+	for _, host := range []struct{ name, reported string }{
+		{"goja", goja},
+		{"web", web},
+	} {
+		if !strings.Contains(host.reported, address) {
+			t.Errorf("the %s host reports state.lastAction as %s, want the typed value on a "+
+				"field reported not secure", host.name, host.reported)
+		}
+	}
+	if goja != web {
+		t.Errorf("the two hosts disagree on state.lastAction\n goja: %s\n  web: %s", goja, web)
+	}
+}