Merge branch 'dev' of https://github.com/EmergenceAI/Agent-E into dev

Author: ruhanaazam

ae/core/autogen_wrapper.py

@@ -101,13 +101,16 @@ def trigger_nested_chat(manager: autogen.ConversableAgent):
             content:str=manager.last_message()["content"] # type: ignore
             content_json=parse_response(content)
             next_step = content_json.get('next_step', None)
+            plan = content_json.get('plan', None)
+            if plan is not None:
+                print_message_from_planner("Plan: "+ plan)
             print(f"Next Step: {next_step}")
             if next_step is None: 
                 print_message_from_planner("Received no response, terminating..") # type: ignore
                 print("Trigger nested chat returned False")
                 return False
             else:
-                print_message_from_planner("Next Step: "+ next_step) # type: ignore
+                print_message_from_planner(next_step) # type: ignore
                 return True 
 
 

ae/core/prompts.py

@@ -56,19 +56,21 @@
 Your reply: {"terminate":"yes", "final_response": "Here is the Nothing phone 2 price list: <price list>. The cheapest store is <store name> with price <price>."}
 
 Example 2:
-Task: Find the cheapest flight from Helsinki to Stockholm on 15 March. Current page: www.skyscanner.com
+Task: Find the cheapest premium economy flights from Helsinki to Stockholm on 15 March. Current page: www.skyscanner.com
 {"plan":"1. List the interaction options available on skyscanner page relevant for flight reservation along with their default values.
 2. Select the journey option to one-way (if not default).
 3. Set number of passengers to 1 (if not default).
 4. Set the departure date to 15 March 2025 (since 15 March 2024 is already past).
+5. Set ticket type to Economy Premium. 
 5. Set from airport to ""Helsinki".
-6. Set destination airport tas Stockhokm
+6. Set destination airport to Stockhokm
 7. Confirm that current values in the source airport, destination airport and departure date fields are Helsinki, Stockholm and 15 August 2024 respectively.
 8. Click on the search button to get the search results.
 9. Confirm that you are on the search results page.
 10. Extract the price of the cheapest flight from Helsinki to Stokchol from the search results.", 
 "next_step": "List all interaction options available on this skyscanner page relevant for flight reservation. This could be source airport, destination aiport etc. Also provide the current default values of the fields.",
 "terminate":"no"},
+Notice above how there is confrimation after each step and how interaction with each element is a seperate step. Follow same pattern.
 
 Remember: you are a very very persistent planner who will try every possible strategy to accomplish the task perfectly.
 Revise search query if needed, ask for more information if needed, and always verify the results before terminating the task.""",

ae/core/skills/click_using_selector.py

@@ -52,7 +52,7 @@ def detect_dom_changes(changes:str): # type: ignore
     await asyncio.sleep(0.1) # sleep for 100ms to allow the mutation observer to detect changes
     unsubscribe(detect_dom_changes)
     await browser_manager.take_screenshots(f"{function_name}_end", page)
-    await browser_manager.notify_user(result["summary_message"])
+    #await browser_manager.notify_user(result["summary_message"])
 
     if dom_changes_detected:
         return f"Success: {result['summary_message']}.\n As a consequence of this action, new elements have appeared in view: {dom_changes_detected}. This means that the action to click {selector} is not yet executed and needs further interaction. Get all_fields DOM to complete the interaction."

ae/core/skills/enter_text_using_selector.py

@@ -15,7 +15,6 @@
 from ae.utils.logger import logger
 
 
-
 @dataclass
 class EnterTextEntry:
     """
@@ -127,7 +126,7 @@ def detect_dom_changes(changes:str): # type: ignore
 
     await browser_manager.take_screenshots(f"{function_name}_end", page)
 
-    await browser_manager.notify_user(result["summary_message"])
+    #await browser_manager.notify_user(result["summary_message"])
     if dom_changes_detected:
         return f"{result['detailed_message']}.\n As a consequence of this action, new elements have appeared in view: {dom_changes_detected}. This means that the action of entering text {text_to_enter} is not yet executed and needs further interaction. Get all_fields DOM to complete the interaction."
     return result["detailed_message"]

ae/core/skills/get_dom_with_content_type.py

@@ -70,7 +70,7 @@ async def get_dom_with_content_type(
 
     elapsed_time = time.time() - start_time
     logger.info(f"Get DOM Command executed in {elapsed_time} seconds")
-    await browser_manager.notify_user(user_success_message)
+    #await browser_manager.notify_user(user_success_message)
     return extracted_data # type: ignore
 
 

ae/core/system_orchestrator.py

@@ -108,13 +108,25 @@ async def process_command(self, command: str):
             start_time = time.time()
             current_url = await self.browser_manager.get_current_url() if self.browser_manager else None
             self.browser_manager.log_user_message(command) # type: ignore
-
+            result = None
             if self.autogen_wrapper:
-                await self.autogen_wrapper.process_command(command, current_url)
+                result=await self.autogen_wrapper.process_command(command, current_url)
             end_time = time.time()
             elapsed_time = round(end_time - start_time, 2)
             logger.info(f"Command \"{command}\" took: {elapsed_time} seconds.")
-            await self.save_chat_messages()
+            #await self.save_chat_messages()
+            print("Checking Result:", result)
+            if result is not None:
+                print("Result:", result)
+                chat_history=result.get("chat_history")
+                print("Chat history:", chat_history)
+                last_message = chat_history[-1] if chat_history else None
+                print("Last message:", last_message)
+                if last_message and "terminate" in last_message and last_message["terminate"]=="yes":
+                    print("Notifying the user and Terminating the session")
+                    await self.browser_manager.notify_user(last_message)
+
+              
             await self.browser_manager.notify_user(f"Completed ({elapsed_time}s).") # type: ignore
             await self.browser_manager.command_completed(command, elapsed_time) # type: ignore
             self.is_running = False