选择器群聊#

SelectorGroupChat 实现了一个团队成员轮流向所有其他成员广播消息的协作模式。生成模型（如大语言模型）基于共享上下文选择下一位发言者，实现动态、上下文感知的协作。

主要特性包括：

  • 基于模型的发言者选择

  • 可配置的参与者角色和描述

  • 防止同一发言者连续发言（可选）

  • 可自定义的选择提示

  • 可自定义的选择函数以覆盖默认的基于模型的选择

  • 可自定义的候选函数来缩小模型选择的代理范围

备注

SelectorGroupChat 是高级API。如需更多控制和定制，请参考核心API文档中的群聊模式来实现自己的群聊逻辑。

工作原理#

SelectorGroupChat 是与 RoundRobinGroupChat 类似的群聊， 但采用基于模型的下一位发言者选择机制。 当团队通过 run() 或 run_stream() 接收任务时， 将执行以下步骤：

  1. 团队分析当前对话上下文（包括对话历史和参与者的 name 和 description 属性），使用模型确定下一位发言者。默认情况下，团队不会连续选择同一发言者，除非这是唯一可用的代理。可通过设置 allow_repeated_speaker=True 改变此行为。您也可以通过提供自定义选择函数来覆盖模型选择。

  2. 团队提示选定的发言者代理提供响应，然后将其广播给所有其他参与者。

  3. 检查终止条件以确定是否结束对话，如未终止，则从步骤1重复该过程。

  4. 对话结束时，团队返回包含该任务对话历史的 TaskResult。

任务完成后，对话上下文会保留在团队和所有参与者中，因此下一个任务可以延续之前的对话上下文。 您可以通过调用 reset() 重置对话上下文。

本节将通过一个简单的网页搜索和数据分析任务示例演示如何使用 SelectorGroupChat。

示例：网页搜索/分析#

from typing import List, Sequence

from autogen_agentchat.agents import AssistantAgent, UserProxyAgent
from autogen_agentchat.conditions import MaxMessageTermination, TextMentionTermination
from autogen_agentchat.messages import BaseAgentEvent, BaseChatMessage
from autogen_agentchat.teams import SelectorGroupChat
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient

代理配置#

选择器群聊

该系统使用三个专业代理：

  • 规划代理：战略协调者，负责将复杂任务分解为可管理的子任务。

  • 网页搜索代理：信息检索专家，与 search_web_tool 工具交互。

  • 数据分析代理：擅长执行计算的专家代理，配备 percentage_change_tool 工具。

工具 search_web_tool 和 percentage_change_tool 是代理可用来执行任务的外部工具。

# 注意：本示例使用模拟工具而非真实API进行演示
def search_web_tool(query: str) -> str:
    if "2006-2007" in query:
        return """Here are the total points scored by Miami Heat players in the 2006-2007 season:
        Udonis Haslem: 844 points
        Dwayne Wade: 1397 points
        James Posey: 550 points
        ...
        """
    elif "2007-2008" in query:
        return "The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214."
    elif "2008-2009" in query:
        return "The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398."
    return "No data found."


def percentage_change_tool(start: float, end: float) -> float:
    return ((end - start) / start) * 100

让我们使用 AssistantAgent 类创建专用代理。 需要注意的是，代理的 name 和 description 属性会被模型用来决定下一个发言者， 因此建议提供有意义的名称和描述。

model_client = OpenAIChatCompletionClient(model="gpt-4o")

planning_agent = AssistantAgent(
    "PlanningAgent",
    description="An agent for planning tasks, this agent should be the first to engage when given a new task.",
    model_client=model_client,
    system_message="""
    You are a planning agent.
    Your job is to break down complex tasks into smaller, manageable subtasks.
    Your team members are:
        WebSearchAgent: Searches for information
        DataAnalystAgent: Performs calculations

    You only plan and delegate tasks - you do not execute them yourself.

    When assigning tasks, use this format:
    1. <agent> : <task>

    After all tasks are complete, summarize the findings and end with "TERMINATE".
    """,
)

web_search_agent = AssistantAgent(
    "WebSearchAgent",
    description="An agent for searching information on the web.",
    tools=[search_web_tool],
    model_client=model_client,
    system_message="""
    You are a web search agent.
    Your only tool is search_tool - use it to find information.
    You make only one search call at a time.
    Once you have the results, you never do calculations based on them.
    """,
)

data_analyst_agent = AssistantAgent(
    "DataAnalystAgent",
    description="An agent for performing calculations.",
    model_client=model_client,
    tools=[percentage_change_tool],
    system_message="""
    You are a data analyst.
    Given the tasks you have been assigned, you should analyze the data and provide results using the tools provided.
    If you have not seen the data, ask for it.
    """,
)

备注

默认情况下，AssistantAgent 会返回 工具输出作为响应。如果您的工具没有返回格式良好的自然语言字符串， 您可能需要在创建代理时设置 reflect_on_tool_use=True 来添加反思步骤。 这将允许代理对工具输出进行反思并提供自然语言响应。

工作流程#

  1. 任务首先由 SelectorGroupChat 接收，根据代理描述选择最适合处理初始任务的代理（通常是规划代理）。

  2. 规划代理分析任务并将其分解为子任务，使用以下格式分配给最合适的代理： <代理> : <任务>

  3. 根据对话上下文和代理描述，SelectorGroupChat 管理器动态选择下一个代理来处理分配的子任务。

  4. 网络搜索代理依次执行搜索，将结果存储在共享对话历史中。

  5. 数据分析师在被选中时使用可用计算工具处理收集到的信息。

  6. 工作流程持续进行，动态选择代理直到满足以下任一条件：

    • 规划代理确定所有子任务完成并发送"TERMINATE"

    • 达到其他终止条件（例如最大消息数量）

定义代理时，请确保包含有帮助的 description，因为这是决定下一个选择哪个代理的依据。

终止条件#

我们将使用两种终止条件： TextMentionTermination 用于在规划代理发送"TERMINATE"时结束对话， 以及 MaxMessageTermination 将对话限制为25条消息以避免无限循环。

text_mention_termination = TextMentionTermination("TERMINATE")
max_messages_termination = MaxMessageTermination(max_messages=25)
termination = text_mention_termination | max_messages_termination

选择器提示#

SelectorGroupChat 使用模型根据对话上下文选择 下一位发言人。我们将使用自定义选择器提示来与工作流程正确对齐。

selector_prompt = """Select an agent to perform task.

{roles}

Current conversation context:
{history}

Read the above conversation, then select an agent from {participants} to perform the next task.
Make sure the planner agent has assigned tasks before other agents start working.
Only select one agent.
"""

选择器提示中可用的字符串变量包括：

  • {participants}：候选人的名称列表。格式为 ["<名称1>", "<名称2>", ...]。

  • {roles}：以换行符分隔的候选人代理名称和描述列表。每行格式为："<名称> : <描述>"。

  • {history}：以双换行符分隔的对话历史记录，包含名称和消息内容。每条消息格式为："<名称> : <消息内容>"。

小技巧

尽量避免在选择器提示中给模型过多指令。

多少算过多？这取决于您使用的模型能力。 对于 GPT-4o 及同等模型，您可以使用包含每个发言人选择条件的提示。 对于 Phi-4 等较小模型，应保持选择器提示尽可能简单， 例如本示例中使用的提示。

通常，如果您发现自己为每个代理编写多个条件， 这表明您应该考虑使用自定义选择函数， 或者将任务分解为由单独代理或团队处理的更小顺序任务。

运行团队#

让我们创建包含代理、终止条件和自定义选择器提示的团队。

team = SelectorGroupChat(
    [planning_agent, web_search_agent, data_analyst_agent],
    model_client=model_client,
    termination_condition=termination,
    selector_prompt=selector_prompt,
    allow_repeated_speaker=True,  # 允许一个代理连续多次发言。
)

现在我们运行团队执行一个查找 NBA 球员信息的任务。

task = "Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?"

# 如果在脚本中运行，请使用 asyncio.run(...)。
await Console(team.run_stream(task=task))

---------- user ----------
Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?
---------- PlanningAgent ----------
To complete this task, we need to perform the following subtasks:

1. Find out which Miami Heat player had the highest points in the 2006-2007 season.
2. Gather data on this player's total rebounds for the 2007-2008 season.
3. Gather data on this player's total rebounds for the 2008-2009 season.
4. Calculate the percentage change in the player's total rebounds between the 2007-2008 and 2008-2009 seasons.

I'll assign these tasks accordingly:

1. WebSearchAgent: Search for the Miami Heat player with the highest points in the 2006-2007 NBA season.
2. WebSearchAgent: Find the total rebounds for this player in the 2007-2008 NBA season.
3. WebSearchAgent: Find the total rebounds for this player in the 2008-2009 NBA season.
4. DataAnalystAgent: Calculate the percentage change in total rebounds from the 2007-2008 season to the 2008-2009 season for this player.
---------- WebSearchAgent ----------
[FunctionCall(id='call_89tUNHaAM0kKQYPJLleGUKK7', arguments='{"query":"Miami Heat player highest points 2006-2007 season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', name='search_web_tool', call_id='call_89tUNHaAM0kKQYPJLleGUKK7', is_error=False)]
---------- WebSearchAgent ----------
Here are the total points scored by Miami Heat players in the 2006-2007 season:
        Udonis Haslem: 844 points
        Dwayne Wade: 1397 points
        James Posey: 550 points
        ...
        
---------- WebSearchAgent ----------
The Miami Heat player with the highest points in the 2006-2007 season was Dwyane Wade, with 1,397 points.

Next, I will search for Dwyane Wade's total rebounds for the 2007-2008 season.
---------- WebSearchAgent ----------
[FunctionCall(id='call_RC55TkSjG3JXRuVOTPrcE1RL', arguments='{"query":"Dwyane Wade total rebounds 2007-2008 season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', name='search_web_tool', call_id='call_RC55TkSjG3JXRuVOTPrcE1RL', is_error=False)]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.
---------- WebSearchAgent ----------
[FunctionCall(id='call_pBXoABrErDow0rZjw3tjOZol', arguments='{"query":"Dwyane Wade total rebounds 2008-2009 season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', name='search_web_tool', call_id='call_pBXoABrErDow0rZjw3tjOZol', is_error=False)]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.
---------- DataAnalystAgent ----------
[FunctionCall(id='call_qMxxXtcJsiK8KFSSCx3zm0is', arguments='{"start":214,"end":398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', name='percentage_change_tool', call_id='call_qMxxXtcJsiK8KFSSCx3zm0is', is_error=False)]
---------- DataAnalystAgent ----------
85.98130841121495
---------- PlanningAgent ----------
The player with the highest points for the Miami Heat in the 2006-2007 NBA season was Dwyane Wade, who scored 1,397 points. The percentage change in Dwyane Wade's total rebounds from 214 in the 2007-2008 season to 398 in the 2008-2009 season is approximately 85.98%.

TERMINATE

TaskResult(messages=[TextMessage(source='user', models_usage=None, metadata={}, content='Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?', type='TextMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=161, completion_tokens=220), metadata={}, content="To complete this task, we need to perform the following subtasks:\n\n1. Find out which Miami Heat player had the highest points in the 2006-2007 season.\n2. Gather data on this player's total rebounds for the 2007-2008 season.\n3. Gather data on this player's total rebounds for the 2008-2009 season.\n4. Calculate the percentage change in the player's total rebounds between the 2007-2008 and 2008-2009 seasons.\n\nI'll assign these tasks accordingly:\n\n1. WebSearchAgent: Search for the Miami Heat player with the highest points in the 2006-2007 NBA season.\n2. WebSearchAgent: Find the total rebounds for this player in the 2007-2008 NBA season.\n3. WebSearchAgent: Find the total rebounds for this player in the 2008-2009 NBA season.\n4. DataAnalystAgent: Calculate the percentage change in total rebounds from the 2007-2008 season to the 2008-2009 season for this player.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=368, completion_tokens=27), metadata={}, content=[FunctionCall(id='call_89tUNHaAM0kKQYPJLleGUKK7', arguments='{"query":"Miami Heat player highest points 2006-2007 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', name='search_web_tool', call_id='call_89tUNHaAM0kKQYPJLleGUKK7', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, metadata={}, content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', type='ToolCallSummaryMessage'), ThoughtEvent(source='WebSearchAgent', models_usage=None, metadata={}, content="The Miami Heat player with the highest points in the 2006-2007 season was Dwyane Wade, with 1,397 points.\n\nNext, I will search for Dwyane Wade's total rebounds for the 2007-2008 season.", type='ThoughtEvent'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=460, completion_tokens=83), metadata={}, content=[FunctionCall(id='call_RC55TkSjG3JXRuVOTPrcE1RL', arguments='{"query":"Dwyane Wade total rebounds 2007-2008 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', name='search_web_tool', call_id='call_RC55TkSjG3JXRuVOTPrcE1RL', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, metadata={}, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', type='ToolCallSummaryMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=585, completion_tokens=28), metadata={}, content=[FunctionCall(id='call_pBXoABrErDow0rZjw3tjOZol', arguments='{"query":"Dwyane Wade total rebounds 2008-2009 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', name='search_web_tool', call_id='call_pBXoABrErDow0rZjw3tjOZol', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, metadata={}, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', type='ToolCallSummaryMessage'), ToolCallRequestEvent(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=496, completion_tokens=21), metadata={}, content=[FunctionCall(id='call_qMxxXtcJsiK8KFSSCx3zm0is', arguments='{"start":214,"end":398}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='85.98130841121495', name='percentage_change_tool', call_id='call_qMxxXtcJsiK8KFSSCx3zm0is', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, metadata={}, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=528, completion_tokens=80), metadata={}, content="The player with the highest points for the Miami Heat in the 2006-2007 NBA season was Dwyane Wade, who scored 1,397 points. The percentage change in Dwyane Wade's total rebounds from 214 in the 2007-2008 season to 398 in the 2008-2009 season is approximately 85.98%.\n\nTERMINATE", type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")

可以看到，在网页搜索代理完成必要搜索且数据分析代理完成必要计算后，我们发现德怀恩·韦德是2006-2007赛季迈阿密热火队得分最高的球员，他在2007-2008赛季和2008-2009赛季之间的总篮板数变化百分比为85.98%！

自定义选择器函数#

通常我们需要对选择过程有更好的控制。 为此，我们可以通过设置selector_func参数来使用自定义选择器函数，覆盖默认基于模型的选择。 这允许我们实现更复杂的选择逻辑和基于状态的转换。

例如，我们希望规划代理在任何专业代理之后立即发言以检查进度。

备注

从自定义选择器函数返回None将使用默认的基于模型的选择。

def selector_func(messages: Sequence[BaseAgentEvent | BaseChatMessage]) -> str | None:
    if messages[-1].source != planning_agent.name:
        return planning_agent.name
    return None


# 重置之前的团队并使用选择器函数再次运行聊天。
await team.reset()
team = SelectorGroupChat(
    [planning_agent, web_search_agent, data_analyst_agent],
    model_client=model_client,
    termination_condition=termination,
    selector_prompt=selector_prompt,
    allow_repeated_speaker=True,
    selector_func=selector_func,
)

await Console(team.run_stream(task=task))

---------- user ----------
Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?
---------- PlanningAgent ----------
To answer this question, we need to follow these steps: 

1. Identify the Miami Heat player with the highest points in the 2006-2007 season.
2. Retrieve the total rebounds of that player for the 2007-2008 and 2008-2009 seasons.
3. Calculate the percentage change in his total rebounds between the two seasons.

Let's delegate these tasks:

1. WebSearchAgent: Find the Miami Heat player with the highest points in the 2006-2007 NBA season.
2. WebSearchAgent: Retrieve the total rebounds for the identified player during the 2007-2008 NBA season.
3. WebSearchAgent: Retrieve the total rebounds for the identified player during the 2008-2009 NBA season.
4. DataAnalystAgent: Calculate the percentage change in total rebounds between the 2007-2008 and 2008-2009 seasons for the player found.
---------- WebSearchAgent ----------
[FunctionCall(id='call_Pz82ndNLSV4cH0Sg6g7ArP4L', arguments='{"query":"Miami Heat player highest points 2006-2007 season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', call_id='call_Pz82ndNLSV4cH0Sg6g7ArP4L')]
---------- WebSearchAgent ----------
Here are the total points scored by Miami Heat players in the 2006-2007 season:
        Udonis Haslem: 844 points
        Dwayne Wade: 1397 points
        James Posey: 550 points
        ...
        
---------- PlanningAgent ----------
Great! Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season. Now, let's continue with the next tasks:

2. WebSearchAgent: Retrieve the total rebounds for Dwyane Wade during the 2007-2008 NBA season.
3. WebSearchAgent: Retrieve the total rebounds for Dwyane Wade during the 2008-2009 NBA season.
---------- WebSearchAgent ----------
[FunctionCall(id='call_3qv9so2DXFZIHtzqDIfXoFID', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 season"}', name='search_web_tool'), FunctionCall(id='call_Vh7zzzWUeiUAvaYjP0If0k1k', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_3qv9so2DXFZIHtzqDIfXoFID'), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_Vh7zzzWUeiUAvaYjP0If0k1k')]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.
The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.
---------- PlanningAgent ----------
Now let's calculate the percentage change in total rebounds between the 2007-2008 and 2008-2009 seasons for Dwyane Wade.

4. DataAnalystAgent: Calculate the percentage change in total rebounds for Dwyane Wade between the 2007-2008 and 2008-2009 seasons.
---------- DataAnalystAgent ----------
[FunctionCall(id='call_FXnPSr6JVGfAWs3StIizbt2V', arguments='{"start":214,"end":398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', call_id='call_FXnPSr6JVGfAWs3StIizbt2V')]
---------- DataAnalystAgent ----------
85.98130841121495
---------- PlanningAgent ----------
Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring a total of 1397 points. The percentage change in his total rebounds from the 2007-2008 season (214 rebounds) to the 2008-2009 season (398 rebounds) is approximately 86.0%.

TERMINATE

TaskResult(messages=[TextMessage(source='user', models_usage=None, content='Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?', type='TextMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=161, completion_tokens=192), content="To answer this question, we need to follow these steps: \n\n1. Identify the Miami Heat player with the highest points in the 2006-2007 season.\n2. Retrieve the total rebounds of that player for the 2007-2008 and 2008-2009 seasons.\n3. Calculate the percentage change in his total rebounds between the two seasons.\n\nLet's delegate these tasks:\n\n1. WebSearchAgent: Find the Miami Heat player with the highest points in the 2006-2007 NBA season.\n2. WebSearchAgent: Retrieve the total rebounds for the identified player during the 2007-2008 NBA season.\n3. WebSearchAgent: Retrieve the total rebounds for the identified player during the 2008-2009 NBA season.\n4. DataAnalystAgent: Calculate the percentage change in total rebounds between the 2007-2008 and 2008-2009 seasons for the player found.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=340, completion_tokens=27), content=[FunctionCall(id='call_Pz82ndNLSV4cH0Sg6g7ArP4L', arguments='{"query":"Miami Heat player highest points 2006-2007 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', call_id='call_Pz82ndNLSV4cH0Sg6g7ArP4L')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=420, completion_tokens=87), content="Great! Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season. Now, let's continue with the next tasks:\n\n2. WebSearchAgent: Retrieve the total rebounds for Dwyane Wade during the 2007-2008 NBA season.\n3. WebSearchAgent: Retrieve the total rebounds for Dwyane Wade during the 2008-2009 NBA season.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=525, completion_tokens=71), content=[FunctionCall(id='call_3qv9so2DXFZIHtzqDIfXoFID', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 season"}', name='search_web_tool'), FunctionCall(id='call_Vh7zzzWUeiUAvaYjP0If0k1k', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_3qv9so2DXFZIHtzqDIfXoFID'), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_Vh7zzzWUeiUAvaYjP0If0k1k')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.\nThe number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=569, completion_tokens=68), content="Now let's calculate the percentage change in total rebounds between the 2007-2008 and 2008-2009 seasons for Dwyane Wade.\n\n4. DataAnalystAgent: Calculate the percentage change in total rebounds for Dwyane Wade between the 2007-2008 and 2008-2009 seasons.", type='TextMessage'), ToolCallRequestEvent(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=627, completion_tokens=21), content=[FunctionCall(id='call_FXnPSr6JVGfAWs3StIizbt2V', arguments='{"start":214,"end":398}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, content=[FunctionExecutionResult(content='85.98130841121495', call_id='call_FXnPSr6JVGfAWs3StIizbt2V')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=659, completion_tokens=76), content='Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring a total of 1397 points. The percentage change in his total rebounds from the 2007-2008 season (214 rebounds) to the 2008-2009 season (398 rebounds) is approximately 86.0%.\n\nTERMINATE', type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")

从对话日志中可以看出，规划代理总是在专业代理之后立即发言。

小技巧

每个参与代理在每一轮中只执行一个步骤（执行工具、生成响应等）。 如果您希望 AssistantAgent 重复执行 直到它不再返回 ToolCallSummaryMessage （当它完成运行所有需要运行的工具时），您可以通过 检查最后一条消息并在它是 ToolCallSummaryMessage 时返回代理来实现。

自定义候选函数#

另一个可能的需求是从过滤后的代理列表中自动选择下一个发言者。 为此，我们可以设置 candidate_func 参数，使用自定义候选函数来筛选每轮群聊中潜在的发言代理列表。

这使我们能够在特定代理之后将发言者选择限制在一组特定的代理中。

备注

candidate_func 仅在未设置 selector_func 时有效。 从自定义候选函数返回 None 或空列表 [] 会引发 ValueError。

def candidate_func(messages: Sequence[BaseAgentEvent | BaseChatMessage]) -> List[str]:
    # 保持规划代理作为第一个制定任务的代理
    if messages[-1].source == "user":
        return [planning_agent.name]

    # 如果前一个代理是规划代理，
    # 并且它明确要求 web_search_agent 或 data_analyst_agent 或两者（在重新规划或重新分配任务的情况下），
    # 则返回这些特定的代理
    last_message = messages[-1]
    if last_message.source == planning_agent.name:
        participants = []
        if web_search_agent.name in last_message.to_text():
            participants.append(web_search_agent.name)
        if data_analyst_agent.name in last_message.to_text():
            participants.append(data_analyst_agent.name)
        if participants:
            return participants  # SelectorGroupChat 将从剩余的两个代理中选择。

    # 我们可以假设一旦 web_search_agent 和 data_analyst_agent 完成了它们的回合，
    # 任务就完成了，
    # 因此我们派 planning_agent 来终止聊天
    previous_set_of_agents = set(message.source for message in messages)
    if web_search_agent.name in previous_set_of_agents and data_analyst_agent.name in previous_set_of_agents:
        return [planning_agent.name]

    # 如果没有满足任何条件，则返回所有代理
    return [planning_agent.name, web_search_agent.name, data_analyst_agent.name]


# 重置之前的团队并使用选择器函数再次运行聊天。
await team.reset()
team = SelectorGroupChat(
    [planning_agent, web_search_agent, data_analyst_agent],
    model_client=model_client,
    termination_condition=termination,
    candidate_func=candidate_func,
)

await Console(team.run_stream(task=task))

---------- user ----------
Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?
---------- PlanningAgent ----------
To answer this question, we'll break it down into two main subtasks:

1. Identify the Miami Heat player with the highest points in the 2006-2007 season.
2. Calculate the percentage change in that player's total rebounds between the 2007-2008 and 2008-2009 seasons.

Let's assign these tasks:

1. WebSearchAgent: Search for the Miami Heat player with the highest points in the 2006-2007 NBA season.
2. WebSearchAgent: Find the total rebound statistics for that identified player for both the 2007-2008 and 2008-2009 NBA seasons.
3. DataAnalystAgent: Calculate the percentage change in the player's total rebounds between the 2007-2008 and 2008-2009 seasons once the data is retrieved.
---------- WebSearchAgent ----------
[FunctionCall(id='call_WtR5KTfEIxs3jIO25gjAw7dF', arguments='{"query":"Miami Heat highest points scorer 2006-2007 NBA season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', name='search_web_tool', call_id='call_WtR5KTfEIxs3jIO25gjAw7dF', is_error=False)]
---------- WebSearchAgent ----------
Here are the total points scored by Miami Heat players in the 2006-2007 season:
        Udonis Haslem: 844 points
        Dwayne Wade: 1397 points
        James Posey: 550 points
        ...
        
---------- DataAnalystAgent ----------
[FunctionCall(id='call_9HA3DEacUl4WuG2G2PtRkXAO', arguments='{"start": 432, "end": 527}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='21.99074074074074', name='percentage_change_tool', call_id='call_9HA3DEacUl4WuG2G2PtRkXAO', is_error=False)]
---------- DataAnalystAgent ----------
21.99074074074074
---------- PlanningAgent ----------
It seems we've missed some context there, so let's assign the subtasks again for clarity:

Based on the search results, Dwyane Wade had the highest points for the Miami Heat in the 2006-2007 season with 1397 points.

Now, let's find the necessary rebound statistics:

2. WebSearchAgent: Find Dwyane Wade's total rebound statistics for both the 2007-2008 and 2008-2009 NBA seasons.
3. DataAnalystAgent: Once the data is retrieved, calculate the percentage change in Dwyane Wade's total rebounds between the 2007-2008 and 2008-2009 seasons.
---------- WebSearchAgent ----------
[FunctionCall(id='call_3i1wTDSjkGg6Ev8YKYWkZK55', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 NBA season"}', name='search_web_tool'), FunctionCall(id='call_NRAs6jHxXRi8zsvpW5WlHAaU', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 NBA season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', name='search_web_tool', call_id='call_3i1wTDSjkGg6Ev8YKYWkZK55', is_error=False), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', name='search_web_tool', call_id='call_NRAs6jHxXRi8zsvpW5WlHAaU', is_error=False)]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.
The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.
---------- PlanningAgent ----------
The total rebounds for Dwyane Wade in the 2007-2008 season were 214, and in the 2008-2009 season, they were 398.

Now, let's calculate the percentage change.

3. DataAnalystAgent: Calculate the percentage change in Dwyane Wade's total rebounds from the 2007-2008 season to the 2008-2009 season.
---------- DataAnalystAgent ----------
[FunctionCall(id='call_XECA7ezz7VIKbf8IbZYSCSpI', arguments='{"start":214,"end":398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', name='percentage_change_tool', call_id='call_XECA7ezz7VIKbf8IbZYSCSpI', is_error=False)]
---------- DataAnalystAgent ----------
85.98130841121495
---------- PlanningAgent ----------
The Miami Heat player with the highest points in the 2006-2007 season was Dwyane Wade, with 1397 points. The percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons was approximately 85.98%.

TERMINATE

TaskResult(messages=[TextMessage(source='user', models_usage=None, metadata={}, content='Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?', type='TextMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=161, completion_tokens=169), metadata={}, content="To answer this question, we'll break it down into two main subtasks:\n\n1. Identify the Miami Heat player with the highest points in the 2006-2007 season.\n2. Calculate the percentage change in that player's total rebounds between the 2007-2008 and 2008-2009 seasons.\n\nLet's assign these tasks:\n\n1. WebSearchAgent: Search for the Miami Heat player with the highest points in the 2006-2007 NBA season.\n2. WebSearchAgent: Find the total rebound statistics for that identified player for both the 2007-2008 and 2008-2009 NBA seasons.\n3. DataAnalystAgent: Calculate the percentage change in the player's total rebounds between the 2007-2008 and 2008-2009 seasons once the data is retrieved.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=324, completion_tokens=28), metadata={}, content=[FunctionCall(id='call_WtR5KTfEIxs3jIO25gjAw7dF', arguments='{"query":"Miami Heat highest points scorer 2006-2007 NBA season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', name='search_web_tool', call_id='call_WtR5KTfEIxs3jIO25gjAw7dF', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, metadata={}, content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', type='ToolCallSummaryMessage'), ToolCallRequestEvent(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=390, completion_tokens=37), metadata={}, content=[FunctionCall(id='call_9HA3DEacUl4WuG2G2PtRkXAO', arguments='{"start": 432, "end": 527}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='21.99074074074074', name='percentage_change_tool', call_id='call_9HA3DEacUl4WuG2G2PtRkXAO', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, metadata={}, content='21.99074074074074', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=413, completion_tokens=137), metadata={}, content="It seems we've missed some context there, so let's assign the subtasks again for clarity:\n\nBased on the search results, Dwyane Wade had the highest points for the Miami Heat in the 2006-2007 season with 1397 points.\n\nNow, let's find the necessary rebound statistics:\n\n2. WebSearchAgent: Find Dwyane Wade's total rebound statistics for both the 2007-2008 and 2008-2009 NBA seasons.\n3. DataAnalystAgent: Once the data is retrieved, calculate the percentage change in Dwyane Wade's total rebounds between the 2007-2008 and 2008-2009 seasons.", type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=576, completion_tokens=73), metadata={}, content=[FunctionCall(id='call_3i1wTDSjkGg6Ev8YKYWkZK55', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 NBA season"}', name='search_web_tool'), FunctionCall(id='call_NRAs6jHxXRi8zsvpW5WlHAaU', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 NBA season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', name='search_web_tool', call_id='call_3i1wTDSjkGg6Ev8YKYWkZK55', is_error=False), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', name='search_web_tool', call_id='call_NRAs6jHxXRi8zsvpW5WlHAaU', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, metadata={}, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.\nThe number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=612, completion_tokens=84), metadata={}, content="The total rebounds for Dwyane Wade in the 2007-2008 season were 214, and in the 2008-2009 season, they were 398.\n\nNow, let's calculate the percentage change.\n\n3. DataAnalystAgent: Calculate the percentage change in Dwyane Wade's total rebounds from the 2007-2008 season to the 2008-2009 season.", type='TextMessage'), ToolCallRequestEvent(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=720, completion_tokens=21), metadata={}, content=[FunctionCall(id='call_XECA7ezz7VIKbf8IbZYSCSpI', arguments='{"start":214,"end":398}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, metadata={}, content=[FunctionExecutionResult(content='85.98130841121495', name='percentage_change_tool', call_id='call_XECA7ezz7VIKbf8IbZYSCSpI', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, metadata={}, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=718, completion_tokens=63), metadata={}, content='The Miami Heat player with the highest points in the 2006-2007 season was Dwyane Wade, with 1397 points. The percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons was approximately 85.98%.\n\nTERMINATE', type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")

从对话日志中可以看到，Planning Agent 在 Web Search Agent 和 Data Analyst Agent 完成它们的回合后重新加入对话，发现任务没有按预期完成，于是再次调用 WebSearchAgent 获取反弹值，然后调用 DataAnalysetAgent 获取百分比变化。

用户反馈#

我们可以将 UserProxyAgent 添加到团队中， 以便在运行期间提供用户反馈。 有关 UserProxyAgent 的更多详情， 请参阅人机交互。

要在网页搜索示例中使用 UserProxyAgent， 我们只需将其添加到团队中，并更新选择器函数， 使其在规划代理发言后始终检查用户反馈。 如果用户回复 "APPROVE"，对话将继续，否则 规划代理会再次尝试，直到用户批准为止。

user_proxy_agent = UserProxyAgent("UserProxyAgent", description="A proxy for the user to approve or disapprove tasks.")


def selector_func_with_user_proxy(messages: Sequence[BaseAgentEvent | BaseChatMessage]) -> str | None:
    if messages[-1].source != planning_agent.name and messages[-1].source != user_proxy_agent.name:
        # 规划代理应在收到新任务时首先参与，或检查进度。
        return planning_agent.name
    if messages[-1].source == planning_agent.name:
        if messages[-2].source == user_proxy_agent.name and "APPROVE" in messages[-1].content.upper():  # type: ignore
            # 用户已批准计划，继续执行下一个代理。
            return None
        # 使用用户代理获取用户批准以继续执行。
        return user_proxy_agent.name
    if messages[-1].source == user_proxy_agent.name:
        # 如果用户不同意，则返回规划代理。
        if "APPROVE" not in messages[-1].content.upper():  # type: ignore
            return planning_agent.name
    return None


# 重置之前的代理，并使用用户代理和选择器函数重新运行聊天。
await team.reset()
team = SelectorGroupChat(
    [planning_agent, web_search_agent, data_analyst_agent, user_proxy_agent],
    model_client=model_client,
    termination_condition=termination,
    selector_prompt=selector_prompt,
    selector_func=selector_func_with_user_proxy,
    allow_repeated_speaker=True,
)

await Console(team.run_stream(task=task))

---------- user ----------
Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?

---------- PlanningAgent ----------
To address the user's query, we will need to perform the following tasks:

1. Identify the Miami Heat player with the highest points in the 2006-2007 season.
2. Find the total rebounds for that player in the 2007-2008 season.
3. Find the total rebounds for that player in the 2008-2009 season.
4. Calculate the percentage change in the total rebounds between the 2007-2008 and 2008-2009 seasons.

Let's assign these tasks:

1. **WebSearchAgent**: Identify the Miami Heat player with the highest points in the 2006-2007 season.
   
(Task 2 and 3 depend on the result of Task 1. We'll proceed with Tasks 2 and 3 once Task 1 is complete.)
---------- UserProxyAgent ----------
approve
---------- WebSearchAgent ----------
[FunctionCall(id='call_0prr3fUnG5CtisUG7QeygW0w', arguments='{"query":"Miami Heat highest points scorer 2006-2007 NBA season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', call_id='call_0prr3fUnG5CtisUG7QeygW0w')]
---------- WebSearchAgent ----------
Here are the total points scored by Miami Heat players in the 2006-2007 season:
        Udonis Haslem: 844 points
        Dwayne Wade: 1397 points
        James Posey: 550 points
        ...
        
---------- PlanningAgent ----------
Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring 1397 points.

Next, we need to find Dwyane Wade's total rebounds for the 2007-2008 and 2008-2009 seasons:

2. **WebSearchAgent**: Find Dwyane Wade's total rebounds for the 2007-2008 season.
3. **WebSearchAgent**: Find Dwyane Wade's total rebounds for the 2008-2009 season.
---------- UserProxyAgent ----------
approve
---------- WebSearchAgent ----------
[FunctionCall(id='call_fBZe80NaBfruOVGwRWbhXyRm', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 NBA season"}', name='search_web_tool'), FunctionCall(id='call_cURYibna4fGxySiL7IYt0c3s', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 NBA season"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_fBZe80NaBfruOVGwRWbhXyRm'), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_cURYibna4fGxySiL7IYt0c3s')]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.
The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.
---------- PlanningAgent ----------
Now that we have Dwyane Wade's total rebounds for both seasons, we can calculate the percentage change:

4. **DataAnalystAgent**: Calculate the percentage change in Dwyane Wade's total rebounds from the 2007-2008 season (214 rebounds) to the 2008-2009 season (398 rebounds).
---------- UserProxyAgent ----------
approve
---------- DataAnalystAgent ----------
[FunctionCall(id='call_z3uog7t2x0z1Suzl5hACF9hY', arguments='{"start":214,"end":398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', call_id='call_z3uog7t2x0z1Suzl5hACF9hY')]
---------- DataAnalystAgent ----------
85.98130841121495
---------- PlanningAgent ----------
Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring 1397 points. His total rebounds increased from 214 in the 2007-2008 season to 398 in the 2008-2009 season, which is a percentage change of approximately 85.98%.

TERMINATE

TaskResult(messages=[TextMessage(source='user', models_usage=None, content='Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?', type='TextMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=161, completion_tokens=166), content="To address the user's query, we will need to perform the following tasks:\n\n1. Identify the Miami Heat player with the highest points in the 2006-2007 season.\n2. Find the total rebounds for that player in the 2007-2008 season.\n3. Find the total rebounds for that player in the 2008-2009 season.\n4. Calculate the percentage change in the total rebounds between the 2007-2008 and 2008-2009 seasons.\n\nLet's assign these tasks:\n\n1. **WebSearchAgent**: Identify the Miami Heat player with the highest points in the 2006-2007 season.\n   \n(Task 2 and 3 depend on the result of Task 1. We'll proceed with Tasks 2 and 3 once Task 1 is complete.)", type='TextMessage'), UserInputRequestedEvent(source='UserProxyAgent', models_usage=None, request_id='2a433f88-f886-4b39-a078-ea1acdcb2f9d', content='', type='UserInputRequestedEvent'), TextMessage(source='UserProxyAgent', models_usage=None, content='approve', type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=323, completion_tokens=28), content=[FunctionCall(id='call_0prr3fUnG5CtisUG7QeygW0w', arguments='{"query":"Miami Heat highest points scorer 2006-2007 NBA season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', call_id='call_0prr3fUnG5CtisUG7QeygW0w')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=403, completion_tokens=112), content="Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring 1397 points.\n\nNext, we need to find Dwyane Wade's total rebounds for the 2007-2008 and 2008-2009 seasons:\n\n2. **WebSearchAgent**: Find Dwyane Wade's total rebounds for the 2007-2008 season.\n3. **WebSearchAgent**: Find Dwyane Wade's total rebounds for the 2008-2009 season.", type='TextMessage'), UserInputRequestedEvent(source='UserProxyAgent', models_usage=None, request_id='23dd4570-2391-41e9-aeea-86598499792c', content='', type='UserInputRequestedEvent'), TextMessage(source='UserProxyAgent', models_usage=None, content='approve', type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=543, completion_tokens=73), content=[FunctionCall(id='call_fBZe80NaBfruOVGwRWbhXyRm', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 NBA season"}', name='search_web_tool'), FunctionCall(id='call_cURYibna4fGxySiL7IYt0c3s', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 NBA season"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_fBZe80NaBfruOVGwRWbhXyRm'), FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_cURYibna4fGxySiL7IYt0c3s')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.\nThe number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=586, completion_tokens=70), content="Now that we have Dwyane Wade's total rebounds for both seasons, we can calculate the percentage change:\n\n4. **DataAnalystAgent**: Calculate the percentage change in Dwyane Wade's total rebounds from the 2007-2008 season (214 rebounds) to the 2008-2009 season (398 rebounds).", type='TextMessage'), UserInputRequestedEvent(source='UserProxyAgent', models_usage=None, request_id='e849d193-4ab3-4558-8560-7dbc062a0aee', content='', type='UserInputRequestedEvent'), TextMessage(source='UserProxyAgent', models_usage=None, content='approve', type='TextMessage'), ToolCallRequestEvent(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=655, completion_tokens=21), content=[FunctionCall(id='call_z3uog7t2x0z1Suzl5hACF9hY', arguments='{"start":214,"end":398}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, content=[FunctionExecutionResult(content='85.98130841121495', call_id='call_z3uog7t2x0z1Suzl5hACF9hY')], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='PlanningAgent', models_usage=RequestUsage(prompt_tokens=687, completion_tokens=74), content='Dwyane Wade was the Miami Heat player with the highest points in the 2006-2007 season, scoring 1397 points. His total rebounds increased from 214 in the 2007-2008 season to 398 in the 2008-2009 season, which is a percentage change of approximately 85.98%.\n\nTERMINATE', type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")

现在，用户的反馈已融入对话流程中， 用户可以批准或拒绝规划代理的决策。

使用推理模型#

在之前的示例中，我们使用了 gpt-4o 模型。像 gpt-4o 和 gemini-1.5-flash 这样的模型擅长遵循指令，因此你可以 在团队的选择器提示和每个代理的系统消息中包含相对详细的指令来指导它们的行为。

然而，如果你使用的是像 o3-mini 这样的推理模型，你需要 尽量保持选择器提示和系统消息简洁明了。 这是因为推理模型已经擅长根据提供的上下文自行生成指令。

这也意味着我们不再需要规划代理来分解任务， 因为使用推理模型的 SelectorGroupChat 可以自行完成这一工作。

在下面的示例中，我们将使用 o3-mini 作为代理和团队的模型， 并且不会使用规划代理。 此外，我们会尽量保持选择器提示和系统消息的简洁性。

model_client = OpenAIChatCompletionClient(model="o3-mini")

web_search_agent = AssistantAgent(
    "WebSearchAgent",
    description="An agent for searching information on the web.",
    tools=[search_web_tool],
    model_client=model_client,
    system_message="""Use web search tool to find information.""",
)

data_analyst_agent = AssistantAgent(
    "DataAnalystAgent",
    description="An agent for performing calculations.",
    model_client=model_client,
    tools=[percentage_change_tool],
    system_message="""Use tool to perform calculation. If you have not seen the data, ask for it.""",
)

user_proxy_agent = UserProxyAgent(
    "UserProxyAgent",
    description="A user to approve or disapprove tasks.",
)

selector_prompt = """Select an agent to perform task.

{roles}

Current conversation context:
{history}

Read the above conversation, then select an agent from {participants} to perform the next task.
When the task is complete, let the user approve or disapprove the task.
"""

team = SelectorGroupChat(
    [web_search_agent, data_analyst_agent, user_proxy_agent],
    model_client=model_client,
    termination_condition=termination,  # 使用与之前相同的终止条件。
    selector_prompt=selector_prompt,
    allow_repeated_speaker=True,
)

await Console(team.run_stream(task=task))

---------- user ----------
Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?
---------- WebSearchAgent ----------
[FunctionCall(id='call_hl7EP6Lp5jj5wEdxeNHTwUVG', arguments='{"query": "Who was the Miami Heat player with the highest points in the 2006-2007 season Miami Heat statistics Dwyane Wade rebounds percentage change 2007-2008 2008-2009 seasons"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', call_id='call_hl7EP6Lp5jj5wEdxeNHTwUVG', is_error=False)]
---------- WebSearchAgent ----------
Here are the total points scored by Miami Heat players in the 2006-2007 season:
        Udonis Haslem: 844 points
        Dwayne Wade: 1397 points
        James Posey: 550 points
        ...
        
---------- DataAnalystAgent ----------
I found that in the 2006–2007 season the player with the highest points was Dwyane Wade (with 1,397 points). Could you please provide Dwyane Wade’s total rebounds for the 2007–2008 and the 2008–2009 seasons so I can calculate the percentage change?
---------- WebSearchAgent ----------
[FunctionCall(id='call_lppGTILXDvO9waPwKO66ehK6', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 and 2008-2009 seasons for Miami Heat"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_lppGTILXDvO9waPwKO66ehK6', is_error=False)]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.
---------- DataAnalystAgent ----------
Could you please provide Dwyane Wade’s total rebounds in the 2008-2009 season?
---------- WebSearchAgent ----------
[FunctionCall(id='call_r8DBcbJtQfdtugLtyTrqOvoK', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 season Miami Heat"}', name='search_web_tool')]
---------- WebSearchAgent ----------
[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_r8DBcbJtQfdtugLtyTrqOvoK', is_error=False)]
---------- WebSearchAgent ----------
The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.
---------- DataAnalystAgent ----------
[FunctionCall(id='call_4jejv1wM7V1osbBCxJze8aQM', arguments='{"start": 214, "end": 398}', name='percentage_change_tool')]
---------- DataAnalystAgent ----------
[FunctionExecutionResult(content='85.98130841121495', call_id='call_4jejv1wM7V1osbBCxJze8aQM', is_error=False)]
---------- DataAnalystAgent ----------
85.98130841121495
---------- DataAnalystAgent ----------
Dwyane Wade was the Miami Heat player with the highest total points (1,397) during the 2006-2007 season. His total rebounds increased by approximately 86% from 214 in the 2007-2008 season to 398 in the 2008-2009 season.
---------- UserProxyAgent ----------
Approve. TERMINATE

TaskResult(messages=[TextMessage(source='user', models_usage=None, content='Who was the Miami Heat player with the highest points in the 2006-2007 season, and what was the percentage change in his total rebounds between the 2007-2008 and 2008-2009 seasons?', type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=103, completion_tokens=384), content=[FunctionCall(id='call_hl7EP6Lp5jj5wEdxeNHTwUVG', arguments='{"query": "Who was the Miami Heat player with the highest points in the 2006-2007 season Miami Heat statistics Dwyane Wade rebounds percentage change 2007-2008 2008-2009 seasons"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', call_id='call_hl7EP6Lp5jj5wEdxeNHTwUVG', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='Here are the total points scored by Miami Heat players in the 2006-2007 season:\n        Udonis Haslem: 844 points\n        Dwayne Wade: 1397 points\n        James Posey: 550 points\n        ...\n        ', type='ToolCallSummaryMessage'), TextMessage(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=183, completion_tokens=1038), content='I found that in the 2006–2007 season the player with the highest points was Dwyane Wade (with 1,397 points). Could you please provide Dwyane Wade’s total rebounds for the 2007–2008 and the 2008–2009 seasons so I can calculate the percentage change?', type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=299, completion_tokens=109), content=[FunctionCall(id='call_lppGTILXDvO9waPwKO66ehK6', arguments='{"query": "Dwyane Wade total rebounds 2007-2008 and 2008-2009 seasons for Miami Heat"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', call_id='call_lppGTILXDvO9waPwKO66ehK6', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2007-2008 is 214.', type='ToolCallSummaryMessage'), TextMessage(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=291, completion_tokens=224), content='Could you please provide Dwyane Wade’s total rebounds in the 2008-2009 season?', type='TextMessage'), ToolCallRequestEvent(source='WebSearchAgent', models_usage=RequestUsage(prompt_tokens=401, completion_tokens=37), content=[FunctionCall(id='call_r8DBcbJtQfdtugLtyTrqOvoK', arguments='{"query": "Dwyane Wade total rebounds 2008-2009 season Miami Heat"}', name='search_web_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='WebSearchAgent', models_usage=None, content=[FunctionExecutionResult(content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', call_id='call_r8DBcbJtQfdtugLtyTrqOvoK', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='WebSearchAgent', models_usage=None, content='The number of total rebounds for Dwayne Wade in the Miami Heat season 2008-2009 is 398.', type='ToolCallSummaryMessage'), ToolCallRequestEvent(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=353, completion_tokens=158), content=[FunctionCall(id='call_4jejv1wM7V1osbBCxJze8aQM', arguments='{"start": 214, "end": 398}', name='percentage_change_tool')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='DataAnalystAgent', models_usage=None, content=[FunctionExecutionResult(content='85.98130841121495', call_id='call_4jejv1wM7V1osbBCxJze8aQM', is_error=False)], type='ToolCallExecutionEvent'), ToolCallSummaryMessage(source='DataAnalystAgent', models_usage=None, content='85.98130841121495', type='ToolCallSummaryMessage'), TextMessage(source='DataAnalystAgent', models_usage=RequestUsage(prompt_tokens=394, completion_tokens=138), content='Dwyane Wade was the Miami Heat player with the highest total points (1,397) during the 2006-2007 season. His total rebounds increased by approximately 86% from 214 in the 2007-2008 season to 398 in the 2008-2009 season.', type='TextMessage'), UserInputRequestedEvent(source='UserProxyAgent', models_usage=None, request_id='b3b05408-73fc-47d4-b832-16c9f447cd6e', content='', type='UserInputRequestedEvent'), TextMessage(source='UserProxyAgent', models_usage=None, content='Approve. TERMINATE', type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")

小技巧

如需获取关于如何提示推理模型的更多指导，请参阅 Azure AI 服务博客中的文章 OpenAI O1 和 O3-mini 推理模型的提示工程