feat: enhance run_coact.py and related agents with improved task handling and configuration

- Updated TASK_DESCRIPTION in run_coact.py to clarify task-solving steps and requirements.
- Modified configuration parameters for provider name and client password for better security and flexibility.
- Enhanced OrchestratorUserProxyAgent to include user instruction in the auto-reply and improved screenshot handling.
- Adjusted coding_agent.py to ensure proper verification of results before saving changes.
- Improved CUA agent prompts to maintain application state and handle user instructions more effectively.
- Ensured existing code logic remains unchanged while enhancing functionality and usability.

mm_agents/coact/coding_agent.py

@@ -7,22 +7,20 @@ from .autogen.agentchat.contrib.multimodal_conversable_agent import MultimodalCo
 
 
 CODER_SYSTEM_MESSAGE = """# Your role
-You are a coding assistant, you need to solve a task step-by-step given by the user. 
-You can write code in ```bash...``` code blocks for bash scripts, and ```python...``` code blocks for python code. 
-
-# Important notes
-- Once you complete the task, reply ONLY with "TERMINATE" to end the task.
-- DO NOT mix the TERMINATE with any other words or code blocks in your reply.
-- When you write code, you must identify the language (whether it is python or bash) of the code.
+- You are a programmer, you need to solve a task step-by-step given by the user. 
+- You can write code in ```bash...``` code blocks for bash scripts, and ```python...``` code blocks for python code. 
 - Your linux username is "user".
-- Wrap all your code in ONE code block. DO NOT let user save the code as a file and execute it for you.
 - If you want to use sudo, follow the format: "echo {CLIENT_PASSWORD} | sudo -S [YOUR COMMANDS]" (no quotes for the word "{CLIENT_PASSWORD}").
-- Ignore the error: "sudo: /etc/sudoers.d is world writable".
-- Your python code will be sent line-by-line into a interactive python terminal. Do not include __main__ in your code.
-- When import a package, you need to check if the package is installed. If not, you need to install it yourself.
+
+# Requirements
+- You MUST verify the result before save the changes.
+- When you write code, you must identify the language (whether it is python or bash) of the code.
+- Wrap all your code in ONE code block. DO NOT let user save the code as a file and execute it for you.
+- Do not include __main__ in your python code.
+- When you modify a spreadsheet, **make sure every value is in the expected cell**.
+- When importing a package, you need to check if the package has been installed. If not, you need to install it yourself.
 - You need to print the progressive and final result.
 - If you met execution error, you need to analyze the error message and try to fix the error.
-- IMPORTANT: If you modified a file like spreadsheet, you should close and reopen the file by operating the GUI, so that I can see what you changed.
 """
 
 class TerminalProxyAgent(MultimodalConversableAgent):
@@ -62,15 +60,15 @@ class TerminalProxyAgent(MultimodalConversableAgent):
                 exitcode = 0
                 logs = output_dict["output"]
             else:
-                exitcode = -1
+                exitcode = 0
                 logs = output_dict["output"]
         elif lang in PYTHON_VARIANTS:
             output_dict = self.env.controller.run_python_script(code)
             if output_dict["status"] == "error":
-                exitcode = -1
+                exitcode = 0
                 logs = output_dict["output"]
             else:
-                exitcode = -1
+                exitcode = 0
                 logs = output_dict["message"]
         else:
             exitcode = -1