Empowering Autogen: Enabling Seamless Java Code Execution

sudo apt install openjdk-17-jdk-headless

git clone https://github.com/microsoft/autogen.git

# conversable_agent.py
# @@ -1088,6 +1088,19 @@ class ConversableAgent(Agent):
            elif lang in ["java"]:
                if code.startswith("// filename: "):
                    filename = code[12 : code.find("\n")].strip()
                else:
                    filename = None
                exitcode, logs, image = self.run_code(
                    code,
                    lang="java",
                    filename=filename,
                    **self._code_execution_config,
                )
            elif lang == 'unknown':
                exitcode, logs, image = (0, "Language is unknown.", None)

# code_utils.py
# @@ -83,7 +83,8 @@ def infer_lang(code):
def infer_lang(code):
    """infer the language for the code.
    TODO: make it robust.
    """
    valid_prefixes = ["python ", "pip", "python3 ", "java ", "javac "]
    if any(code.startswith(prefix) for prefix in valid_prefixes):
        return "sh"

# @@ -215,7 +216,7 @@ def timeout_handler(signum, frame):
def _cmd(lang):
    if lang.startswith("python") or lang in ["bash", "sh", "powershell", "java"]:
        return lang
    if lang in ["shell"]:
        return "sh"
    if lang in ["ps1"]:
        return "powershell"
    raise NotImplementedError(f"{lang} not recognized in code execution")

pip install .

import autogen

config_list = [
    {
        'api_key': 'NULL',
        'base_url': 'http://192.168.68.114:1234/v1'
    },
]

llm_config = {
    "cache_seed": 42,
    "temperature": 0,
    "config_list": config_list
}


SYSTEM_MESSAGE = """You are a helpful AI assistant.
Solve tasks using your coding and language skills.
For Java-specific code:
- If you want the user to save the code in a file before executing it, put // filename: <filename> inside the code block as the first line.
- Ensure that the filename matches the class name and has the same capitalization.
In the following cases, suggest python code (in a python coding block) or shell script (in a sh coding block) for the user to execute.
    1. When you need to collect info, use the code to output the info you need, for example, browse or search the web, download/read a file, print the content of a webpage or a file, get the current date/time, check the operating system. After sufficient info is printed and the task is ready to be solved based on your language skill, you can solve the task by yourself.
    2. When you need to perform some task with code, use the code to perform the task and output the result. Finish the task smartly.
Solve the task step by step if you need to. If a plan is not provided, explain your plan first. Be clear which step uses code, and which step uses your language skill.
When using code, you must indicate the script type in the code block. The user cannot provide any other feedback or perform any other action beyond executing the code you suggest. The user can't modify your code. So do not suggest incomplete code which requires users to modify. Don't use a code block if it's not intended to be executed by the user.
If you want the user to save the code in a file before executing it, put # filename: <filename> inside the code block as the first line. Don't include multiple code blocks in one response. Do not ask users to copy and paste the result. Instead, use 'print' function for the output when relevant. Check the execution result returned by the user.
If the result indicates there is an error, fix the error and output the code again. Suggest the full code instead of partial code or code changes. If the error can't be fixed or if the task is not solved even after the code is executed successfully, analyze the problem, revisit your assumption, collect additional info you need, and think of a different approach to try.
When you find an answer, verify the answer carefully. Include verifiable evidence in your response if possible.
Reply "TERMINATE" in the end when everything is done.
"""

assistant = autogen.AssistantAgent(
    name="assistant",
    system_message=SYSTEM_MESSAGE,
    llm_config=llm_config,
    is_termination_msg = lambda x: "TERMINATE" in x.get("content", ""),
)

user_proxy = autogen.UserProxyAgent(
    name="user_proxy", 
    human_input_mode="NEVER",
    max_consecutive_auto_reply=3,
    llm_config=llm_config,
    code_execution_config={
        "work_dir": "coding",
        "use_docker": "openjdk"
    },
    system_message=""""Reply TERMINATE if the task has been solved at full satisfaction or the code executed without issue.
Otherwise, reply CONTINUE, or the reason why the task is not solved yet."""
)

user_proxy.initiate_chat(assistant, message="Write a Hello World application in java")

user_proxy.initiate_chat(assistant, message="Write a Hello World application in python")

user_proxy.initiate_chat(assistant, message="Calculate the first 10 terms of a Fibonacci sequence. Write the java code to generate and print these terms.")

# code_utils.py
# @@ -348,13 +349,20 @@ def execute_code(
    # Prepare image_list based on language and use_docker preference
    if use_docker is True:
        lang = lang.lower()
        if lang in ["java"]:
            image_list = ["openjdk:22-slim-bulleye"]
        elif lang in ["python", "py"]:
            image_list = ["python:3-alpine", "python:3", "python:3-windowsservercore"]
        else:
            # Add more languages or a default image list if needed
            image_list = []
    elif isinstance(use_docker, str):
        image_list = [use_docker]
    else:
        image_list = use_docker

# @@ -399,7 +407,8 @@ def execute_code(
    # tag image based on the lang
    container.commit(repository=lang, tag=tag)

    code_execution_config={
        "work_dir": "coding",
        "use_docker": "openjdk"
    },

user_proxy = autogen.UserProxyAgent(
    name="user_proxy", 
    human_input_mode="NEVER",
    max_consecutive_auto_reply=3,
    llm_config=llm_config,
    code_execution_config={
        "work_dir": "coding",
        "use_docker": "openjdk"
    },
    system_message=""""Reply TERMINATE if the task has been solved at full satisfaction or the code executed without issue.
Otherwise, reply CONTINUE, or the reason why the task is not solved yet."""
)