fix: Added GPT-4o compatibility for screenshot actions with text parameter

libs/python/agent/agent/computers/base.py

@@ -19,8 +19,12 @@ async def get_dimensions(self) -> tuple[int, int]:
         """Get screen dimensions as (width, height)."""
         ...
 
-    async def screenshot(self) -> str:
-        """Take a screenshot and return as base64 string."""
+    async def screenshot(self, text: Optional[str] = None) -> str:
+        """Take a screenshot and return as base64 string.
+
+        Args:
+            text: Optional descriptive text (for compatibility with GPT-4o models, ignored)
+        """
         ...
 
     async def click(self, x: int, y: int, button: str = "left") -> None:

libs/python/agent/agent/computers/cua.py

@@ -33,8 +33,12 @@ async def get_dimensions(self) -> tuple[int, int]:
         screen_size = await self.interface.get_screen_size()
         return screen_size["width"], screen_size["height"]
 
-    async def screenshot(self) -> str:
-        """Take a screenshot and return as base64 string."""
+    async def screenshot(self, text: Optional[str] = None) -> str:
+        """Take a screenshot and return as base64 string.
+
+        Args:
+            text: Optional descriptive text (for compatibility with GPT-4o models, ignored)
+        """
         assert self.interface is not None
         screenshot_bytes = await self.interface.screenshot()
         return base64.b64encode(screenshot_bytes).decode('utf-8')

libs/python/agent/agent/computers/custom.py

@@ -120,8 +120,12 @@ async def get_dimensions(self) -> tuple[int, int]:
 
         return self._last_screenshot_size
 
-    async def screenshot(self) -> str:
-        """Take a screenshot and return as base64 string."""
+    async def screenshot(self, text: Optional[str] = None) -> str:
+        """Take a screenshot and return as base64 string.
+
+        Args:
+            text: Optional descriptive text (for compatibility with GPT-4o models, ignored)
+        """
         result = await self._call_function(self.functions['screenshot'])
         b64_str = self._to_b64_str(result) # type: ignore