Swarm 实现了一个团队，其中代理可以根据其能力将任务移交给其他代理。这是 OpenAI 在 Swarm 中首次引入的多代理设计模式。其核心思想是让代理使用特殊的工具调用将任务委派给其他代理，同时所有代理共享相同的消息上下文。这使得代理能够对任务规划做出本地决策，而不是像 SelectorGroupChat 那样依赖中央协调器。

注意

Swarm 是一个高级 API。如果您需要此 API 不支持的更多控制和自定义，您可以查看核心 API 文档中的 Handoff Pattern，并实现您自己的 Swarm 模式版本。

它是如何工作的？

其核心是，Swarm 团队是一个群聊，其中代理轮流生成响应。类似于 SelectorGroupChat 和 RoundRobinGroupChat，参与代理广播其响应，以便所有代理共享相同的消息上下文。

与其他两个群聊团队不同，在每一轮中，发言代理是根据上下文中最近的 HandoffMessage 消息选择的。 这自然要求团队中的每个代理都能够生成 HandoffMessage 以表示它将任务移交给其他哪些代理。

对于 AssistantAgent，您可以设置 handoffs 参数以指定它可以移交给哪些代理。您可以使用 Handoff 来自定义消息内容和移交行为。

整个过程可以总结如下：

1. 每个代理都能够生成 HandoffMessage 以表示它可以移交给其他哪些代理。对于 AssistantAgent，这意味着设置 handoffs 参数。

2. 当团队开始执行任务时，第一个发言代理操作任务并做出关于是否移交以及移交给谁的本地化决策。

3. 当代理生成 HandoffMessage 时，接收代理接管具有相同消息上下文的任务。

4. 该过程继续进行，直到满足终止条件。

注意

AssistantAgent 使用模型的工具调用能力来生成移交。这意味着模型必须支持工具调用。如果模型执行并行工具调用，可能会同时生成多个移交。这可能导致意外行为。为了避免这种情况，您可以通过配置模型客户端来禁用并行工具调用。对于 OpenAIChatCompletionClient 和 AzureOpenAIChatCompletionClient，您可以在配置中设置 parallel_tool_calls=False。

在本节中，我们将向您展示两个如何使用 Swarm 团队的示例：

1. 具有人机协作移交的客户支持团队。

2. 用于内容生成的自主团队。

客户支持示例

该系统通过两个代理实现航班退款场景：

• 旅行代理：处理一般旅行和退款协调。

• 航班退款员：专门使用 refund_flight 工具处理航班退款。

此外，当代理移交给 "user" 时，我们允许用户与代理交互。

工作流程

1. 旅行代理发起对话并评估用户的请求。

2. 根据请求：

   • 对于退款相关任务，旅行代理移交给航班退款员。

   • 对于需要客户提供的信息，任一代理都可以移交给 "user"。

3. 航班退款员在适当时候使用 refund_flight 工具处理退款。

4. 如果代理移交给 "user"，团队执行将停止并等待用户输入响应。

5. 当用户提供输入时，它将作为 HandoffMessage 发送回团队。此消息将定向到最初请求用户输入的代理。

6. 该过程继续进行，直到旅行代理确定任务完成并终止工作流程。

from typing import Any, Dict, List

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.conditions import HandoffTermination, TextMentionTermination
from autogen_agentchat.messages import HandoffMessage
from autogen_agentchat.teams import Swarm
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient

工具

def refund_flight(flight_id: str) -> str:
    """Refund a flight"""
    return f"Flight {flight_id} refunded"

代理

model_client = OpenAIChatCompletionClient(
    model="gpt-4o",
    # api_key="YOUR_API_KEY",
)

travel_agent = AssistantAgent(
    "travel_agent",
    model_client=model_client,
    handoffs=["flights_refunder", "user"],
    system_message="""You are a travel agent.
    The flights_refunder is in charge of refunding flights.
    If you need information from the user, you must first send your message, then you can handoff to the user.
    Use TERMINATE when the travel planning is complete.""",
)

flights_refunder = AssistantAgent(
    "flights_refunder",
    model_client=model_client,
    handoffs=["travel_agent", "user"],
    tools=[refund_flight],
    system_message="""You are an agent specialized in refunding flights.
    You only need flight reference numbers to refund a flight.
    You have the ability to refund a flight using the refund_flight tool.
    If you need information from the user, you must first send your message, then you can handoff to the user.
    When the transaction is complete, handoff to the travel agent to finalize.""",
)

termination = HandoffTermination(target="user") | TextMentionTermination("TERMINATE")
team = Swarm([travel_agent, flights_refunder], termination_condition=termination)

task = "I need to refund my flight."


async def run_team_stream() -> None:
    task_result = await Console(team.run_stream(task=task))
    last_message = task_result.messages[-1]

    while isinstance(last_message, HandoffMessage) and last_message.target == "user":
        user_message = input("User: ")

        task_result = await Console(
            team.run_stream(task=HandoffMessage(source="user", target=last_message.source, content=user_message))
        )
        last_message = task_result.messages[-1]


# Use asyncio.run(...) if you are running this in a script.
await run_team_stream()
await model_client.close()

---------- user ----------
I need to refund my flight.
---------- travel_agent ----------
[FunctionCall(id='call_ZQ2rGjq4Z29pd0yP2sNcuyd2', arguments='{}', name='transfer_to_flights_refunder')]
[Prompt tokens: 119, Completion tokens: 14]
---------- travel_agent ----------
[FunctionExecutionResult(content='Transferred to flights_refunder, adopting the role of flights_refunder immediately.', call_id='call_ZQ2rGjq4Z29pd0yP2sNcuyd2')]
---------- travel_agent ----------
Transferred to flights_refunder, adopting the role of flights_refunder immediately.
---------- flights_refunder ----------
Could you please provide me with the flight reference number so I can process the refund for you?
[Prompt tokens: 191, Completion tokens: 20]
---------- flights_refunder ----------
[FunctionCall(id='call_1iRfzNpxTJhRTW2ww9aQJ8sK', arguments='{}', name='transfer_to_user')]
[Prompt tokens: 219, Completion tokens: 11]
---------- flights_refunder ----------
[FunctionExecutionResult(content='Transferred to user, adopting the role of user immediately.', call_id='call_1iRfzNpxTJhRTW2ww9aQJ8sK')]
---------- flights_refunder ----------
Transferred to user, adopting the role of user immediately.
---------- Summary ----------
Number of messages: 8
Finish reason: Handoff to user from flights_refunder detected.
Total prompt tokens: 529
Total completion tokens: 45
Duration: 2.05 seconds
---------- user ----------
Sure, it's 507811
---------- flights_refunder ----------
[FunctionCall(id='call_UKCsoEBdflkvpuT9Bi2xlvTd', arguments='{"flight_id":"507811"}', name='refund_flight')]
[Prompt tokens: 266, Completion tokens: 18]
---------- flights_refunder ----------
[FunctionExecutionResult(content='Flight 507811 refunded', call_id='call_UKCsoEBdflkvpuT9Bi2xlvTd')]
---------- flights_refunder ----------
Tool calls:
refund_flight({"flight_id":"507811"}) = Flight 507811 refunded
---------- flights_refunder ----------
[FunctionCall(id='call_MQ2CXR8UhVtjNc6jG3wSQp2W', arguments='{}', name='transfer_to_travel_agent')]
[Prompt tokens: 303, Completion tokens: 13]
---------- flights_refunder ----------
[FunctionExecutionResult(content='Transferred to travel_agent, adopting the role of travel_agent immediately.', call_id='call_MQ2CXR8UhVtjNc6jG3wSQp2W')]
---------- flights_refunder ----------
Transferred to travel_agent, adopting the role of travel_agent immediately.
---------- travel_agent ----------
Your flight with reference number 507811 has been successfully refunded. If you need anything else, feel free to let me know. Safe travels! TERMINATE
[Prompt tokens: 272, Completion tokens: 32]
---------- Summary ----------
Number of messages: 8
Finish reason: Text 'TERMINATE' mentioned
Total prompt tokens: 841
Total completion tokens: 63
Duration: 1.64 seconds

股票研究示例

该系统旨在通过利用四个代理执行股票研究任务：

• 规划师：中央协调器，根据专业知识将特定任务委派给专业代理。规划师确保每个代理都得到有效利用，并监督整个工作流程。

• 财务分析师：一个专门的代理，负责使用 get_stock_data 等工具分析财务指标和股票数据。

• 新闻分析师：一个专注于使用 get_news 等工具收集和总结与股票相关的最新新闻文章的代理。

• 撰稿人：一个负责将股票和新闻分析结果汇编成一份连贯的最终报告的代理。

工作流程

1. 规划师以循序渐进的方式将任务委派给相应的代理，从而启动研究过程。

2. 每个代理独立执行其任务，并将其工作附加到共享的消息线程/历史记录中。所有代理都向此共享消息历史记录贡献内容并从中读取，而不是直接向规划师返回结果。当代理使用 LLM 生成其工作时，它们可以访问此共享消息历史记录，这提供了上下文并有助于跟踪任务的总体进度。

3. 一旦代理完成其任务，它将控制权移交回规划师。

4. 该过程继续进行，直到规划师确定所有必要的任务都已完成并决定终止工作流程。

工具

async def get_stock_data(symbol: str) -> Dict[str, Any]:
    """Get stock market data for a given symbol"""
    return {"price": 180.25, "volume": 1000000, "pe_ratio": 65.4, "market_cap": "700B"}


async def get_news(query: str) -> List[Dict[str, str]]:
    """Get recent news articles about a company"""
    return [
        {
            "title": "Tesla Expands Cybertruck Production",
            "date": "2024-03-20",
            "summary": "Tesla ramps up Cybertruck manufacturing capacity at Gigafactory Texas, aiming to meet strong demand.",
        },
        {
            "title": "Tesla FSD Beta Shows Promise",
            "date": "2024-03-19",
            "summary": "Latest Full Self-Driving beta demonstrates significant improvements in urban navigation and safety features.",
        },
        {
            "title": "Model Y Dominates Global EV Sales",
            "date": "2024-03-18",
            "summary": "Tesla's Model Y becomes best-selling electric vehicle worldwide, capturing significant market share.",
        },
    ]

model_client = OpenAIChatCompletionClient(
    model="gpt-4o",
    # api_key="YOUR_API_KEY",
)

planner = AssistantAgent(
    "planner",
    model_client=model_client,
    handoffs=["financial_analyst", "news_analyst", "writer"],
    system_message="""You are a research planning coordinator.
    Coordinate market research by delegating to specialized agents:
    - Financial Analyst: For stock data analysis
    - News Analyst: For news gathering and analysis
    - Writer: For compiling final report
    Always send your plan first, then handoff to appropriate agent.
    Always handoff to a single agent at a time.
    Use TERMINATE when research is complete.""",
)

financial_analyst = AssistantAgent(
    "financial_analyst",
    model_client=model_client,
    handoffs=["planner"],
    tools=[get_stock_data],
    system_message="""You are a financial analyst.
    Analyze stock market data using the get_stock_data tool.
    Provide insights on financial metrics.
    Always handoff back to planner when analysis is complete.""",
)

news_analyst = AssistantAgent(
    "news_analyst",
    model_client=model_client,
    handoffs=["planner"],
    tools=[get_news],
    system_message="""You are a news analyst.
    Gather and analyze relevant news using the get_news tool.
    Summarize key market insights from news.
    Always handoff back to planner when analysis is complete.""",
)

writer = AssistantAgent(
    "writer",
    model_client=model_client,
    handoffs=["planner"],
    system_message="""You are a financial report writer.
    Compile research findings into clear, concise reports.
    Always handoff back to planner when writing is complete.""",
)

# Define termination condition
text_termination = TextMentionTermination("TERMINATE")
termination = text_termination

research_team = Swarm(
    participants=[planner, financial_analyst, news_analyst, writer], termination_condition=termination
)

task = "Conduct market research for TSLA stock"
await Console(research_team.run_stream(task=task))
await model_client.close()

---------- user ----------
Conduct market research for TSLA stock
---------- planner ----------
[FunctionCall(id='call_BX5QaRuhmB8CxTsBlqCUIXPb', arguments='{}', name='transfer_to_financial_analyst')]
[Prompt tokens: 169, Completion tokens: 166]
---------- planner ----------
[FunctionExecutionResult(content='Transferred to financial_analyst, adopting the role of financial_analyst immediately.', call_id='call_BX5QaRuhmB8CxTsBlqCUIXPb')]
---------- planner ----------
Transferred to financial_analyst, adopting the role of financial_analyst immediately.
---------- financial_analyst ----------
[FunctionCall(id='call_SAXy1ebtA9mnaZo4ztpD2xHA', arguments='{"symbol":"TSLA"}', name='get_stock_data')]
[Prompt tokens: 136, Completion tokens: 16]
---------- financial_analyst ----------
[FunctionExecutionResult(content="{'price': 180.25, 'volume': 1000000, 'pe_ratio': 65.4, 'market_cap': '700B'}", call_id='call_SAXy1ebtA9mnaZo4ztpD2xHA')]
---------- financial_analyst ----------
Tool calls:
get_stock_data({"symbol":"TSLA"}) = {'price': 180.25, 'volume': 1000000, 'pe_ratio': 65.4, 'market_cap': '700B'}
---------- financial_analyst ----------
[FunctionCall(id='call_IsdcFUfBVmtcVzfSuwQpeAwl', arguments='{}', name='transfer_to_planner')]
[Prompt tokens: 199, Completion tokens: 337]
---------- financial_analyst ----------
[FunctionExecutionResult(content='Transferred to planner, adopting the role of planner immediately.', call_id='call_IsdcFUfBVmtcVzfSuwQpeAwl')]
---------- financial_analyst ----------
Transferred to planner, adopting the role of planner immediately.
---------- planner ----------
[FunctionCall(id='call_tN5goNFahrdcSfKnQqT0RONN', arguments='{}', name='transfer_to_news_analyst')]
[Prompt tokens: 291, Completion tokens: 14]
---------- planner ----------
[FunctionExecutionResult(content='Transferred to news_analyst, adopting the role of news_analyst immediately.', call_id='call_tN5goNFahrdcSfKnQqT0RONN')]
---------- planner ----------
Transferred to news_analyst, adopting the role of news_analyst immediately.
---------- news_analyst ----------
[FunctionCall(id='call_Owjw6ZbiPdJgNWMHWxhCKgsp', arguments='{"query":"Tesla market news"}', name='get_news')]
[Prompt tokens: 235, Completion tokens: 16]
---------- news_analyst ----------
[FunctionExecutionResult(content='[{\'title\': \'Tesla Expands Cybertruck Production\', \'date\': \'2024-03-20\', \'summary\': \'Tesla ramps up Cybertruck manufacturing capacity at Gigafactory Texas, aiming to meet strong demand.\'}, {\'title\': \'Tesla FSD Beta Shows Promise\', \'date\': \'2024-03-19\', \'summary\': \'Latest Full Self-Driving beta demonstrates significant improvements in urban navigation and safety features.\'}, {\'title\': \'Model Y Dominates Global EV Sales\', \'date\': \'2024-03-18\', \'summary\': "Tesla\'s Model Y becomes best-selling electric vehicle worldwide, capturing significant market share."}]', call_id='call_Owjw6ZbiPdJgNWMHWxhCKgsp')]
---------- news_analyst ----------
Tool calls:
get_news({"query":"Tesla market news"}) = [{'title': 'Tesla Expands Cybertruck Production', 'date': '2024-03-20', 'summary': 'Tesla ramps up Cybertruck manufacturing capacity at Gigafactory Texas, aiming to meet strong demand.'}, {'title': 'Tesla FSD Beta Shows Promise', 'date': '2024-03-19', 'summary': 'Latest Full Self-Driving beta demonstrates significant improvements in urban navigation and safety features.'}, {'title': 'Model Y Dominates Global EV Sales', 'date': '2024-03-18', 'summary': "Tesla's Model Y becomes best-selling electric vehicle worldwide, capturing significant market share."}]
---------- news_analyst ----------
Here are some of the key market insights regarding Tesla (TSLA):

1. **Expansion in Cybertruck Production**: Tesla has increased its Cybertruck production capacity at the Gigafactory in Texas to meet the high demand. This move might positively impact Tesla's revenues if the demand for the Cybertruck continues to grow.

2. **Advancements in Full Self-Driving (FSD) Technology**: The recent beta release of Tesla's Full Self-Driving software shows significant advancements, particularly in urban navigation and safety. Progress in this area could enhance Tesla's competitive edge in the autonomous driving sector.

3. **Dominance of Model Y in EV Sales**: Tesla's Model Y has become the best-selling electric vehicle globally, capturing a substantial market share. Such strong sales performance reinforces Tesla's leadership in the electric vehicle market.

These developments reflect Tesla's ongoing innovation and ability to capture market demand, which could positively influence its stock performance and market position. 

I will now hand off back to the planner.
[Prompt tokens: 398, Completion tokens: 203]
---------- news_analyst ----------
[FunctionCall(id='call_pn7y6PKsBspWA17uOh3AKNMT', arguments='{}', name='transfer_to_planner')]
[Prompt tokens: 609, Completion tokens: 12]
---------- news_analyst ----------
[FunctionExecutionResult(content='Transferred to planner, adopting the role of planner immediately.', call_id='call_pn7y6PKsBspWA17uOh3AKNMT')]
---------- news_analyst ----------
Transferred to planner, adopting the role of planner immediately.
---------- planner ----------
[FunctionCall(id='call_MmXyWuD2uJT64ZdVI5NfhYdX', arguments='{}', name='transfer_to_writer')]
[Prompt tokens: 722, Completion tokens: 11]
---------- planner ----------
[FunctionExecutionResult(content='Transferred to writer, adopting the role of writer immediately.', call_id='call_MmXyWuD2uJT64ZdVI5NfhYdX')]
---------- planner ----------
Transferred to writer, adopting the role of writer immediately.
---------- writer ----------
[FunctionCall(id='call_Pdgu39O6GMYplBiB8jp3uyN3', arguments='{}', name='transfer_to_planner')]
[Prompt tokens: 599, Completion tokens: 323]
---------- writer ----------
[FunctionExecutionResult(content='Transferred to planner, adopting the role of planner immediately.', call_id='call_Pdgu39O6GMYplBiB8jp3uyN3')]
---------- writer ----------
Transferred to planner, adopting the role of planner immediately.
---------- planner ----------
TERMINATE
[Prompt tokens: 772, Completion tokens: 4]
---------- Summary ----------
Number of messages: 27
Finish reason: Text 'TERMINATE' mentioned
Total prompt tokens: 4130
Total completion tokens: 1102
Duration: 17.74 seconds

TaskResult(messages=[TextMessage(source='user', models_usage=None, content='Conduct market research for TSLA stock', type='TextMessage'), ToolCallRequestEvent(source='planner', models_usage=RequestUsage(prompt_tokens=169, completion_tokens=166), content=[FunctionCall(id='call_BX5QaRuhmB8CxTsBlqCUIXPb', arguments='{}', name='transfer_to_financial_analyst')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='planner', models_usage=None, content=[FunctionExecutionResult(content='Transferred to financial_analyst, adopting the role of financial_analyst immediately.', call_id='call_BX5QaRuhmB8CxTsBlqCUIXPb')], type='ToolCallExecutionEvent'), HandoffMessage(source='planner', models_usage=None, target='financial_analyst', content='Transferred to financial_analyst, adopting the role of financial_analyst immediately.', type='HandoffMessage'), ToolCallRequestEvent(source='financial_analyst', models_usage=RequestUsage(prompt_tokens=136, completion_tokens=16), content=[FunctionCall(id='call_SAXy1ebtA9mnaZo4ztpD2xHA', arguments='{"symbol":"TSLA"}', name='get_stock_data')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='financial_analyst', models_usage=None, content=[FunctionExecutionResult(content="{'price': 180.25, 'volume': 1000000, 'pe_ratio': 65.4, 'market_cap': '700B'}", call_id='call_SAXy1ebtA9mnaZo4ztpD2xHA')], type='ToolCallExecutionEvent'), TextMessage(source='financial_analyst', models_usage=None, content='Tool calls:\nget_stock_data({"symbol":"TSLA"}) = {\'price\': 180.25, \'volume\': 1000000, \'pe_ratio\': 65.4, \'market_cap\': \'700B\'}', type='TextMessage'), ToolCallRequestEvent(source='financial_analyst', models_usage=RequestUsage(prompt_tokens=199, completion_tokens=337), content=[FunctionCall(id='call_IsdcFUfBVmtcVzfSuwQpeAwl', arguments='{}', name='transfer_to_planner')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='financial_analyst', models_usage=None, content=[FunctionExecutionResult(content='Transferred to planner, adopting the role of planner immediately.', call_id='call_IsdcFUfBVmtcVzfSuwQpeAwl')], type='ToolCallExecutionEvent'), HandoffMessage(source='financial_analyst', models_usage=None, target='planner', content='Transferred to planner, adopting the role of planner immediately.', type='HandoffMessage'), ToolCallRequestEvent(source='planner', models_usage=RequestUsage(prompt_tokens=291, completion_tokens=14), content=[FunctionCall(id='call_tN5goNFahrdcSfKnQqT0RONN', arguments='{}', name='transfer_to_news_analyst')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='planner', models_usage=None, content=[FunctionExecutionResult(content='Transferred to news_analyst, adopting the role of news_analyst immediately.', call_id='call_tN5goNFahrdcSfKnQqT0RONN')], type='ToolCallExecutionEvent'), HandoffMessage(source='planner', models_usage=None, target='news_analyst', content='Transferred to news_analyst, adopting the role of news_analyst immediately.', type='HandoffMessage'), ToolCallRequestEvent(source='news_analyst', models_usage=RequestUsage(prompt_tokens=235, completion_tokens=16), content=[FunctionCall(id='call_Owjw6ZbiPdJgNWMHWxhCKgsp', arguments='{"query":"Tesla market news"}', name='get_news')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='news_analyst', models_usage=None, content=[FunctionExecutionResult(content='[{\'title\': \'Tesla Expands Cybertruck Production\', \'date\': \'2024-03-20\', \'summary\': \'Tesla ramps up Cybertruck manufacturing capacity at Gigafactory Texas, aiming to meet strong demand.\'}, {\'title\': \'Tesla FSD Beta Shows Promise\', \'date\': \'2024-03-19\', \'summary\': \'Latest Full Self-Driving beta demonstrates significant improvements in urban navigation and safety features.\'}, {\'title\': \'Model Y Dominates Global EV Sales\', \'date\': \'2024-03-18\', \'summary\': "Tesla\'s Model Y becomes best-selling electric vehicle worldwide, capturing significant market share."}]', call_id='call_Owjw6ZbiPdJgNWMHWxhCKgsp')], type='ToolCallExecutionEvent'), TextMessage(source='news_analyst', models_usage=None, content='Tool calls:\nget_news({"query":"Tesla market news"}) = [{\'title\': \'Tesla Expands Cybertruck Production\', \'date\': \'2024-03-20\', \'summary\': \'Tesla ramps up Cybertruck manufacturing capacity at Gigafactory Texas, aiming to meet strong demand.\'}, {\'title\': \'Tesla FSD Beta Shows Promise\', \'date\': \'2024-03-19\', \'summary\': \'Latest Full Self-Driving beta demonstrates significant improvements in urban navigation and safety features.\'}, {\'title\': \'Model Y Dominates Global EV Sales\', \'date\': \'2024-03-18\', \'summary\': "Tesla\'s Model Y becomes best-selling electric vehicle worldwide, capturing significant market share."}]', type='TextMessage'), TextMessage(source='news_analyst', models_usage=RequestUsage(prompt_tokens=398, completion_tokens=203), content="Here are some of the key market insights regarding Tesla (TSLA):\n\n1. **Expansion in Cybertruck Production**: Tesla has increased its Cybertruck production capacity at the Gigafactory in Texas to meet the high demand. This move might positively impact Tesla's revenues if the demand for the Cybertruck continues to grow.\n\n2. **Advancements in Full Self-Driving (FSD) Technology**: The recent beta release of Tesla's Full Self-Driving software shows significant advancements, particularly in urban navigation and safety. Progress in this area could enhance Tesla's competitive edge in the autonomous driving sector.\n\n3. **Dominance of Model Y in EV Sales**: Tesla's Model Y has become the best-selling electric vehicle globally, capturing a substantial market share. Such strong sales performance reinforces Tesla's leadership in the electric vehicle market.\n\nThese developments reflect Tesla's ongoing innovation and ability to capture market demand, which could positively influence its stock performance and market position. \n\nI will now hand off back to the planner.", type='TextMessage'), ToolCallRequestEvent(source='news_analyst', models_usage=RequestUsage(prompt_tokens=609, completion_tokens=12), content=[FunctionCall(id='call_pn7y6PKsBspWA17uOh3AKNMT', arguments='{}', name='transfer_to_planner')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='news_analyst', models_usage=None, content=[FunctionExecutionResult(content='Transferred to planner, adopting the role of planner immediately.', call_id='call_pn7y6PKsBspWA17uOh3AKNMT')], type='ToolCallExecutionEvent'), HandoffMessage(source='news_analyst', models_usage=None, target='planner', content='Transferred to planner, adopting the role of planner immediately.', type='HandoffMessage'), ToolCallRequestEvent(source='planner', models_usage=RequestUsage(prompt_tokens=722, completion_tokens=11), content=[FunctionCall(id='call_MmXyWuD2uJT64ZdVI5NfhYdX', arguments='{}', name='transfer_to_writer')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='planner', models_usage=None, content=[FunctionExecutionResult(content='Transferred to writer, adopting the role of writer immediately.', call_id='call_MmXyWuD2uJT64ZdVI5NfhYdX')], type='ToolCallExecutionEvent'), HandoffMessage(source='planner', models_usage=None, target='writer', content='Transferred to writer, adopting the role of writer immediately.', type='HandoffMessage'), ToolCallRequestEvent(source='writer', models_usage=RequestUsage(prompt_tokens=599, completion_tokens=323), content=[FunctionCall(id='call_Pdgu39O6GMYplBiB8jp3uyN3', arguments='{}', name='transfer_to_planner')], type='ToolCallRequestEvent'), ToolCallExecutionEvent(source='writer', models_usage=None, content=[FunctionExecutionResult(content='Transferred to planner, adopting the role of planner immediately.', call_id='call_Pdgu39O6GMYplBiB8jp3uyN3')], type='ToolCallExecutionEvent'), HandoffMessage(source='writer', models_usage=None, target='planner', content='Transferred to planner, adopting the role of planner immediately.', type='HandoffMessage'), TextMessage(source='planner', models_usage=RequestUsage(prompt_tokens=772, completion_tokens=4), content='TERMINATE', type='TextMessage')], stop_reason="Text 'TERMINATE' mentioned")

《AI提示工程必知必会》为读者提供了丰富的AI提示工程知识与实战技能。《AI提示工程必知必会》主要内容包括各类提示词的应用，如问答式、指令式、状态类、建议式、安全类和感谢类提示词，以及如何通过实战演练掌握提示词的使用技巧；使用提示词进行文本摘要、改写重述、语法纠错、机器翻译等语言处理任务，以及在数据挖掘、程序开发等领域的应用；AI在绘画创作上的应用，百度文心一言和阿里通义大模型这两大智能平台的特性与功能，以及市场调研中提示词的实战应用。通过阅读《AI提示工程必知必会》，读者可掌握如何有效利用AI提示工程提升工作效率，创新工作流程，并在职场中脱颖而出。