fix: keep Cua foreground actions on the target window

plugins/cua-driver/foreground_test.go

@@ -0,0 +1,95 @@
+package main
+
+import (
+	"errors"
+	"reflect"
+	"testing"
+)
+
+func TestForegroundActivatesBeforeInputAndDoesNotRestore(t *testing.T) {
+	var calls []string
+	foreground := int64(10) // The user's foreground app, e.g. Codex.
+	call := func(name string, args obj) (obj, error) {
+		calls = append(calls, name)
+		if name == "bring_to_front" {
+			if len(args) != 2 || num(args["window_id"]) != 20 {
+				t.Fatal("activation changed the target or forwarded input arguments")
+			}
+			foreground = 20
+			return obj{"structuredContent": obj{"landed_on_target": true}}, nil
+		}
+		// Simulate upstream's activate/act/restore: it now saves the target,
+		// not the user's previous app, as its restore destination.
+		previous := foreground
+		foreground = 20
+		foreground = previous
+		return obj{"structuredContent": obj{"effect": "unverifiable"}}, nil
+	}
+	r, err := callWithForeground(call, "press_key", obj{"pid": 2, "window_id": 20, "key": "t", "delivery_mode": "foreground"}, func() int64 { return foreground })
+	if err != nil || r["isError"] == true || foreground != 20 || !reflect.DeepEqual(calls, []string{"bring_to_front", "press_key"}) {
+		t.Fatalf("foreground handoff failed: %v %v %v %v", calls, foreground, r, err)
+	}
+}
+
+func TestUnconfirmedActivationNeverSendsInput(t *testing.T) {
+	for _, mode := range []string{"refused", "raised_only", "lost_focus", "transport"} {
+		t.Run(mode, func(t *testing.T) {
+			calls := 0
+			r, err := callWithForeground(func(name string, _ obj) (obj, error) {
+				calls++
+				if name != "bring_to_front" {
+					t.Fatal("input sent without focus")
+				}
+				if mode == "transport" {
+					return nil, errors.New("disconnected")
+				}
+				return obj{"isError": mode == "refused", "structuredContent": obj{"raised": true, "landed_on_target": mode != "raised_only"}}, nil
+			}, "click", obj{"pid": 2, "window_id": 20, "delivery_mode": "foreground"}, func() int64 {
+				if mode == "lost_focus" {
+					return 10
+				}
+				return 20
+			})
+			rec := object(object(r["structuredContent"])["artemis"])
+			if err != nil || calls != 1 || r["isError"] != true || rec["execution"] != "not_started" || rec["retryable"] != false {
+				t.Fatalf("unsafe activation handling: %v %v", r, err)
+			}
+		})
+	}
+}
+
+func TestBackgroundAndObservationsNeverActivate(t *testing.T) {
+	for _, name := range []string{"get_window_state", "verify_state", "save_screenshot", "click"} {
+		var calls []string
+		_, err := callWithForeground(func(tool string, _ obj) (obj, error) {
+			calls = append(calls, tool)
+			return obj{}, nil
+		}, name, obj{"pid": 2, "window_id": 20}, func() int64 { t.Fatal("unexpected focus probe"); return 0 })
+		if err != nil || !reflect.DeepEqual(calls, []string{name}) {
+			t.Fatal(calls, err)
+		}
+	}
+}
+
+func TestUncertainInputIsNotReplayed(t *testing.T) {
+	calls := 0
+	_, err := callWithForeground(func(name string, _ obj) (obj, error) {
+		calls++
+		if name == "bring_to_front" {
+			return obj{"structuredContent": obj{"landed_on_target": true}}, nil
+		}
+		return nil, errors.New("input reply lost")
+	}, "type_text", obj{"pid": 2, "window_id": 20, "delivery_mode": "foreground"}, func() int64 { return 20 })
+	if calls != 2 || err == nil {
+		t.Fatal(calls, err)
+	}
+}
+
+func TestCaptureRecordsFocusWithoutHidingBackgroundEvidence(t *testing.T) {
+	r := obj{"content": []any{obj{"type": "image", "data": "original"}}}
+	annotateCaptureFocus(r, 20, 20, 10)
+	s := object(object(r["structuredContent"])["capture_focus"])
+	if s["changed_during_capture"] != true || s["target_foreground_after"] != false || len(items(r["content"])) != 2 || object(items(r["content"])[0])["data"] != "original" {
+		t.Fatal(r)
+	}
+}