Add date in system prompt and precisions on scroll tool

app.py

@@ -774,23 +774,6 @@ _Please note that we store the task logs by default so **do not write any person
     def set_logs_source(session_state):
         session_state["replay_log"] = "udupp2fyavq_1743170323"
 
-    # replay_btn.click(
-    #     fn=clear_and_set_view_only,
-    #     inputs=[task_input],
-    #     outputs=[sandbox_html]
-    # ).then(
-    #     set_logs_source,
-    #     inputs=[session_state]
-    # ).then(
-    #     agent_ui.interact_with_agent,
-    #     inputs=[task_input, stored_messages, session_state, session_hash_state],
-    #     outputs=[chatbot_display]
-    # ).then(
-    #     fn=set_interactive,
-    #     inputs=[],
-    #     outputs=[sandbox_html]
-    # )
-
     demo.load(
         fn=lambda: True,  # dummy to trigger the load
         outputs=[is_interactive],

e2bqwen.py

@@ -16,8 +16,10 @@ from smolagents.agents import populate_template
 from smolagents.monitoring import LogLevel
 from smolagents.agent_types import AgentImage
 from PIL import ImageDraw
+from datetime import datetime
 
 E2B_SYSTEM_PROMPT_TEMPLATE = """You are a desktop automation assistant that can control a remote desktop environment.
+The current date is <<current_date>>.
 <action process>
 You will be given a task to solve in several steps. At each step you will perform an action.
 After each action, you'll receive an updated screenshot. 
@@ -142,7 +144,7 @@ Always analyze the latest screenshot carefully before performing actions.
 Desktop menus usually expand with more options, the tiny triangle next to some text in a menu means that menu expands. For example in Office in the Applications menu expands showing presentation or writing applications. 
 NEVER CLICK THE WEB BROWSER ICON TO OPEN THE WEB BROWSER: use open_url
 </general_guidelines>
-"""
+""".replace("<<current_date>>", datetime.now().strftime("%A, %d-%B-%Y"))
 
 
 def draw_marker_on_image(image_copy, click_coordinates):
@@ -419,7 +421,7 @@ REMEMBER TO ALWAYS CLICK IN THE MIDDLE OF THE TEXT, NOT ON THE SIDE, NOT UNDER.
             Args:
                 x: The x coordinate (horizontal position) of the element to scroll/zoom
                 y: The y coordinate (vertical position) of the element to scroll/zoom
-                direction: The direction to scroll ("up" or "down"), defaults to "down"
+                direction: The direction to scroll ("up" or "down"), defaults to "down". For zoom, "up" zooms in, "down" zooms out.
                 amount: The amount to scroll. A good amount is 1 or 2.
             """
             self.desktop.move_mouse(x, y)

eval.py

@@ -347,7 +347,7 @@ def main():
         "commute": "Check the commuting time between Bern and Zurich on Google maps",
         "hello": "Write 'Hello World' in a text editor",
         "wiki": "When was Temple Grandin introduced to the American Academy of Arts and Sciences, according to Wikipedia?",
-        "flight": "Search a flight Rome - Berlin for tomorrow",
+        "flight": "Search a flight from Rome to Berlin for May 3rd, 2025.",
         "pond": "What's the name of the pond just south of Château de Fontainebleau in Google maps?",
         "flux": "Go on the Hugging Face Hub, find a Space for FLUX1.dev, and generate a picture of the Golden Gate bridge.",
         "hf": "Download me a picture of a puppy from Google, then head to Hugging Face, find a Space dedicated to background removal, and use it to remove the puppy picture's background",