feat: add gesture sequences and calibrated pixel drags

artemis/utils/visualization.py

@@ -517,14 +517,20 @@ def crop_and_annotate_target(
     return out_buf.getvalue()
 
 
-def _resolve_coordinates(coord: Any, width: int, height: int) -> tuple[int, int] | None:
+def _resolve_coordinates(
+    coord: Any, width: int, height: int, coordinate_space: str | None = None
+) -> tuple[int, int] | None:
     """Helper to safely parse coordinates into pixel space."""
     if not isinstance(coord, (list, tuple)) or len(coord) < 2:
         return None
     try:
         x, y = float(coord[0]), float(coord[1])
         # If coordinates are normalized (0.0 <= x <= 1.0)
-        if 0.0 <= x <= 1.0 and 0.0 <= y <= 1.0:
+        if coordinate_space == "pixel":
+            px, py = int(round(x)), int(round(y))
+        elif coordinate_space == "normalized":
+            px, py = int(round(x * width / 1000)), int(round(y * height / 1000))
+        elif 0.0 <= x <= 1.0 and 0.0 <= y <= 1.0:
             px = int(round(x * width))
             py = int(round(y * height))
         elif 0 <= x <= 1000 and 0 <= y <= 1000 and (width > 1000 or height > 1000):
@@ -563,6 +569,17 @@ def draw_action_overlay_on_image(
     if not image_bytes:
         return image_bytes
 
+    if action_name == "action_sequence":
+        receipts = action_args.get("sequence_results")
+        annotated = image_bytes
+        for member in receipts if isinstance(receipts, list) else []:
+            if (
+                isinstance(member, dict)
+                and member.get("execution") == "completed"
+                and member.get("action") in {"click", "drag"}
+            ):
+                annotated = draw_action_overlay_on_image(annotated, member["action"], member)
+        return annotated
     try:
         img = Image.open(io.BytesIO(image_bytes))
         if img.mode in ("RGBA", "P"):
@@ -584,7 +601,7 @@ def draw_action_overlay_on_image(
                 or action_args.get("coordinates")
                 or action_args.get("point")
             )
-            pt = _resolve_coordinates(coord, width, height)
+            pt = _resolve_coordinates(coord, width, height, action_args.get("coordinate_space"))
             if pt:
                 x, y = pt
                 # Outer white aura
@@ -637,7 +654,9 @@ def draw_action_overlay_on_image(
             if isinstance(sequence, list):
                 pts = []
                 for coord in sequence:
-                    pt = _resolve_coordinates(coord, width, height)
+                    pt = _resolve_coordinates(
+                        coord, width, height, action_args.get("coordinate_space")
+                    )
                     if pt:
                         pts.append(pt)
 
@@ -703,8 +722,12 @@ def draw_action_overlay_on_image(
             start_pt, end_pt = None, None
 
             if kind == "coords" and isinstance(target, list) and len(target) == 4:
-                start_pt = _resolve_coordinates(target[:2], width, height)
-                end_pt = _resolve_coordinates(target[2:], width, height)
+                start_pt = _resolve_coordinates(
+                    target[:2], width, height, action_args.get("coordinate_space")
+                )
+                end_pt = _resolve_coordinates(
+                    target[2:], width, height, action_args.get("coordinate_space")
+                )
             elif kind == "direction" and isinstance(target, str):
                 direction = target.lower()
                 cx, cy = width // 2, height // 2
@@ -758,7 +781,7 @@ def draw_action_overlay_on_image(
         elif action in ("input_text", "type"):
             coord = action_args.get("target") or action_args.get("coordinates")
             if coord:
-                pt = _resolve_coordinates(coord, width, height)
+                pt = _resolve_coordinates(coord, width, height, action_args.get("coordinate_space"))
                 if pt:
                     x, y = pt
                     box_w = max(60, int(base_dim * 0.15))
@@ -805,9 +828,21 @@ def overlay_action_on_screenshot(image_bytes: bytes, action_obj: Any) -> bytes |
         "sequence",
         "targets",
         "normalized_coordinates",
+        "coordinate_space",
+        "sequence_results",
     ):
         if key in action and key not in action_args:
             action_args[key] = action[key]
+    if (
+        act_name == "drag"
+        and isinstance(action.get("coordinates"), list)
+        and len(action["coordinates"]) == 4
+    ):
+        action_args.update(
+            start=action["coordinates"][:2],
+            end=action["coordinates"][2:],
+            coordinate_space=action.get("coordinate_space"),
+        )
     annotated = draw_action_overlay_on_image(
         image_bytes=image_bytes, action_name=act_name, action_args=action_args
     )