adding a tag on screenshots for mouse_click coordinate actions (#240)

* adding a tag on screenshots for mouse_click coordinate actions

* darglint

* Update src/agentlab/analyze/agent_xray.py

Co-authored-by: Copilot <[email protected]>

* darglint

---------

Co-authored-by: Copilot <[email protected]>

Author: TLSDC

src/agentlab/analyze/agent_xray.py

@@ -14,7 +14,7 @@
 from attr import dataclass
 from langchain.schema import BaseMessage, HumanMessage
 from openai import OpenAI
-from PIL import Image
+from PIL import Image, ImageDraw
 
 from agentlab.analyze import inspect_results
 from agentlab.experiments.exp_utils import RESULTS_DIR
@@ -530,9 +530,47 @@ def wrapper(*args, **kwargs):
     return decorator
 
 
+def tag_screenshot_with_action(screenshot: Image, action: str) -> Image:
+    """
+    If action is a coordinate action, try to render it on the screenshot.
+
+    e.g. mouse_click(120, 130) -> draw a dot at (120, 130) on the screenshot
+
+    Args:
+        screenshot: The screenshot to tag.
+        action: The action to tag the screenshot with.
+
+    Returns:
+        The tagged screenshot.
+
+    Raises:
+        ValueError: If the action parsing fails.
+    """
+    if action.startswith("mouse_click"):
+        try:
+            coords = action[action.index("(") + 1 : action.index(")")].split(",")
+            coords = [c.strip() for c in coords]
+            if len(coords) != 2:
+                raise ValueError(f"Invalid coordinate format: {coords}")
+            if coords[0].startswith("x="):
+                coords[0] = coords[0][2:]
+            if coords[1].startswith("y="):
+                coords[1] = coords[1][2:]
+            x, y = float(coords[0].strip()), float(coords[1].strip())
+            draw = ImageDraw.Draw(screenshot)
+            radius = 5
+            draw.ellipse(
+                (x - radius, y - radius, x + radius, y + radius), fill="red", outline="red"
+            )
+        except (ValueError, IndexError) as e:
+            warning(f"Failed to parse action '{action}': {e}")
+    return screenshot
+
+
 def update_screenshot(som_or_not: str):
     global info
-    return get_screenshot(info, som_or_not=som_or_not)
+    action = info.exp_result.steps_info[info.step].action
+    return tag_screenshot_with_action(get_screenshot(info, som_or_not=som_or_not), action)
 
 
 def get_screenshot(info: Info, step: int = None, som_or_not: str = "Raw Screenshots"):
@@ -549,6 +587,9 @@ def update_screenshot_pair(som_or_not: str):
     global info
     s1 = get_screenshot(info, info.step, som_or_not)
     s2 = get_screenshot(info, info.step + 1, som_or_not)
+
+    if s1 is not None:
+        s1 = tag_screenshot_with_action(s1, info.exp_result.steps_info[info.step].action)
     return s1, s2