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

runtime/executor.py

@@ -113,10 +113,12 @@ def default_tool_registry(
 ) -> dict[str, ToolCallable]:
     from runtime.describe_screen_semantic import describe_screen_semantic
     from tools.describe_screen import describe_screen
+    from tools.double_tap import double_tap
     from tools.find_icon import find_icon, find_icon_on_screen
     from tools.find_text import find_text, find_text_on_screen
     from tools.input_text import input_text
     from tools.launch_app import launch_app, terminate_app
+    from tools.long_press import long_press
     from tools.screenshot import take_screenshot
     from tools.swipe import swipe
     from tools.tap import tap
@@ -126,6 +128,8 @@ def default_tool_registry(
         "take_screenshot": _bind_manager(take_screenshot, manager),
         "screenshot": _bind_manager(take_screenshot, manager),
         "tap": _bind_manager(tap, manager),
+        "long_press": _bind_manager(long_press, manager),
+        "double_tap": _bind_manager(double_tap, manager),
         "swipe": _bind_manager(swipe, manager),
         "input_text": _bind_manager(input_text, manager),
         "launch_app": _bind_manager(launch_app, manager),

runtime/planner_prompts.py

@@ -26,8 +26,10 @@ Before calling a tool, output a short text block (1-2 sentences):
 Keep this reflection concise and factual.
 
 You must then call exactly one tool:
-- One of `tap`, `swipe`, `input_text`, `launch_app`, `terminate_app` to make
-  progress toward the goal.
+- One of `tap`, `long_press`, `double_tap`, `swipe`, `input_text`,
+  `launch_app`, `terminate_app` to make progress toward the goal. Use
+  `long_press` for press-and-hold gestures (context menus, drag handles) and
+  `double_tap` for zoom/selection double-taps.
 - `finish_task` when the goal has been reached, or when it cannot be reached
   and no further action would help.
 

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,