AutoGen 多智能体实战：Coder、Reviewer、Executor 自动跑完一次代码评审

 pip install pyautogen matplotlib pandas

 import autogen
import os

# -------------------------------------------------------
# 第 1 步：配置 LLM 后端
# AutoGen 支持 OpenAI、Azure、Anthropic 以及本地模型。
# 这里使用环境变量，避免把密钥写入代码。
# -------------------------------------------------------
config_list = [
    {
        "model": "gpt-4o",
        "api_key": os.environ.get("OPENAI_API_KEY"),
    }
]

llm_config = {
    "config_list": config_list,
    "temperature": 0.2,       # 较低的 temperature = 更确定、更精确的代码
    "cache_seed": 42,         # 可复现的结果，便于调试
}

# -------------------------------------------------------
# 第 2 步：定义 AssistantAgent（编码者）
# 该智能体接收任务指令并编写代码。
# 它本身不执行代码，执行工作交给另一个智能体。
# -------------------------------------------------------
assistant = autogen.AssistantAgent(
    name="DataAnalystAgent",
    llm_config=llm_config,
    system_message="""
    You are an expert Python data analyst.
    When given a data task, write clean, well-commented Python code.
    Always save any generated charts as PNG files.
    Respond with ONLY the code block. Do not explain unless asked.
    When the task is complete, reply with TERMINATE.
    """,
)

# -------------------------------------------------------
# 第 3 步：定义 UserProxyAgent（执行者）
# 该智能体代理人类角色。在 NEVER 模式下，
# 它完全自主运行，不需要人类输入。
# 代码执行通过本地 Docker 容器或当前 Python 环境进行沙箱化。
# -------------------------------------------------------
user_proxy = autogen.UserProxyAgent(
    name="ExecutorAgent",
    human_input_mode="NEVER",           # 完全自主执行
    max_consecutive_auto_reply=10,       # 自动回复次数的安全上限
    is_termination_msg=lambda msg: "TERMINATE" in msg.get("content", ""),
    code_execution_config={
        "work_dir": "agent_workspace",   # 代码在该目录下运行
        "use_docker": False,             # 生产环境建议设为 True 以实现隔离
    },
    llm_config=False,                   # 执行者不使用 LLM
)

# -------------------------------------------------------
# 第 4 步：用一个具体任务发起对话
# UserProxy 把任务发送给 AssistantAgent。
# AutoGen 会自动处理来回的对话过程。
# -------------------------------------------------------
task = """
Generate a synthetic sales dataset with 100 rows containing:
- 'month' (Jan to Dec, repeated)
- 'product' (randomly from ['Widget A', 'Widget B', 'Widget C'])
- 'revenue' (random float between 1000 and 50000)
- 'units_sold' (random int between 10 and 500)

Then:
1. Compute total revenue and average units sold per product.
2. Plot a bar chart of total revenue by product.
3. Save the chart as 'revenue_by_product.png'.
4. Print the summary statistics to the console.
"""

user_proxy.initiate_chat(
    recipient=assistant,
    message=task,
    clear_history=True,
)

 print("Agent task completed. Check agent_workspace/ for output files.")

 # 增加一个 ReviewerAgent，在执行前对代码进行评审
reviewer = autogen.AssistantAgent(
    name="ReviewerAgent",
    llm_config=llm_config,
    system_message="""
    You are a senior Python code reviewer.
    Review code for correctness, efficiency, and security.
    If the code is acceptable, reply: 'APPROVED: proceed.'
    If not, explain what to fix clearly and concisely.
    """,
)

# GroupChat 让三个智能体以圆桌方式相互交流
group_chat = autogen.GroupChat(
    agents=[user_proxy, assistant, reviewer],
    messages=[],
    max_round=15,
    speaker_selection_method="auto",   # AutoGen 根据上下文选择下一位发言者
)

manager = autogen.GroupChatManager(
    groupchat=group_chat,
    llm_config=llm_config,
)

# 启动小组工作流
user_proxy.initiate_chat(
    recipient=manager,
    message=task,
    clear_history=True,
 )