feat(planner): expose long_press/double_tap to the AI planner

runtime/tool_specs.py

@@ -80,6 +80,40 @@ SWIPE_SPEC = ToolSpec(
     ),
 )
 
+LONG_PRESS_SPEC = ToolSpec(
+    name="long_press",
+    description="Press and hold a point on the screen, given in Scene pixel coordinates.",
+    parameters=_action_parameters(
+        required=["x", "y"],
+        properties={
+            "x": {"type": "number", "description": "X coordinate in Scene pixel space."},
+            "y": {"type": "number", "description": "Y coordinate in Scene pixel space."},
+            "duration_ms": {
+                "type": "integer",
+                "description": "Hold duration in milliseconds (ignored on some platforms).",
+                "default": 1200,
+            },
+        },
+    ),
+)
+
+DOUBLE_TAP_SPEC = ToolSpec(
+    name="double_tap",
+    description="Tap a point twice quickly, given in Scene pixel coordinates.",
+    parameters=_action_parameters(
+        required=["x", "y"],
+        properties={
+            "x": {"type": "number", "description": "X coordinate in Scene pixel space."},
+            "y": {"type": "number", "description": "Y coordinate in Scene pixel space."},
+            "interval_ms": {
+                "type": "integer",
+                "description": "Milliseconds between the two taps.",
+                "default": 80,
+            },
+        },
+    ),
+)
+
 INPUT_TEXT_SPEC = ToolSpec(
     name="input_text",
     description="Type text into the currently focused input field.",
@@ -145,6 +179,8 @@ FINISH_TASK_SPEC = ToolSpec(
 
 ACTION_TOOL_SPECS: list[ToolSpec] = [
     TAP_SPEC,
+    LONG_PRESS_SPEC,
+    DOUBLE_TAP_SPEC,
     SWIPE_SPEC,
     INPUT_TEXT_SPEC,
     LAUNCH_APP_SPEC,