GraphFlow (Workflows)#

In diesem Abschnitt lernen Sie, wie Sie einen Multi-Agenten-Workflow mit GraphFlow, kurz „Flow“ genannt, erstellen. Es verwendet eine strukturierte Ausführung und steuert präzise, wie Agenten interagieren, um eine Aufgabe zu erfüllen.

Zuerst zeigen wir Ihnen, wie Sie einen Flow erstellen und ausführen. Anschließend erklären wir, wie Sie das Verhalten von Flows beobachten und debuggen, und besprechen wichtige Operationen zur Steuerung der Ausführung.

AutoGen AgentChat bietet ein Team für die gerichtete Graphausführung

  • GraphFlow: Ein Team, das einem DiGraph folgt, um den Ausführungsfluss zwischen Agenten zu steuern. Unterstützt sequentielle, parallele, bedingte und Schleifenverhaltensweisen.

Hinweis

Wann sollten Sie GraphFlow verwenden?

Verwenden Sie GraphFlow, wenn Sie strenge Kontrolle über die Reihenfolge der Agentenaktionen benötigen oder wenn unterschiedliche Ergebnisse zu unterschiedlichen nächsten Schritten führen müssen. Beginnen Sie mit einem einfachen Team wie RoundRobinGroupChat oder SelectorGroupChat, wenn ein Ad-hoc-Konversationsfluss ausreicht. Wechseln Sie zu einem strukturierten Workflow, wenn Ihre Aufgabe deterministische Steuerung, bedingte Verzweigung oder die Behandlung komplexer mehrstufiger Prozesse mit Zyklen erfordert.

Warnung: GraphFlow ist eine experimentelle Funktion. Seine API, sein Verhalten und seine Fähigkeiten können sich in zukünftigen Versionen ändern.

Erstellen und Ausführen eines Flows#

DiGraphBuilder ist ein flüssiges Dienstprogramm, mit dem Sie einfach Ausführungsgraphen für Workflows erstellen können. Es unterstützt das Erstellen

  • Sequentielle Ketten

  • Parallele Fan-Outs

  • Bedingte Verzweigung

  • Schleifen mit sicheren Abbruchbedingungen

Jeder Knoten im Graphen repräsentiert einen Agenten, und Kanten definieren die zulässigen Ausführungspfade. Kanten können optional Bedingungen haben, die auf Agentennachrichten basieren.

Sequentieller Flow#

Wir beginnen mit der Erstellung eines einfachen Workflows, bei dem ein Autor einen Absatz entwirft und ein Prüfer Feedback gibt. Dieser Graph endet, nachdem der Prüfer den Autor kommentiert hat.

Beachten Sie, dass der Flow automatisch alle Quell- und Blattknoten des Graphen berechnet und die Ausführung an allen Quellknoten im Graphen beginnt und abgeschlossen wird, wenn keine Knoten mehr zur Ausführung anstehen.

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import DiGraphBuilder, GraphFlow
from autogen_ext.models.openai import OpenAIChatCompletionClient

# Create an OpenAI model client
client = OpenAIChatCompletionClient(model="gpt-4.1-nano")

# Create the writer agent
writer = AssistantAgent("writer", model_client=client, system_message="Draft a short paragraph on climate change.")

# Create the reviewer agent
reviewer = AssistantAgent("reviewer", model_client=client, system_message="Review the draft and suggest improvements.")

# Build the graph
builder = DiGraphBuilder()
builder.add_node(writer).add_node(reviewer)
builder.add_edge(writer, reviewer)

# Build and validate the graph
graph = builder.build()

# Create the flow
flow = GraphFlow([writer, reviewer], graph=graph)

# Use `asyncio.run(...)` and wrap the below in a async function when running in a script.
stream = flow.run_stream(task="Write a short paragraph about climate change.")
async for event in stream:  # type: ignore
    print(event)
# Use Console(flow.run_stream(...)) for better formatting in console.

source='user' models_usage=None metadata={} content='Write a short paragraph about climate change.' type='TextMessage'
source='writer' models_usage=RequestUsage(prompt_tokens=28, completion_tokens=95) metadata={} content='Climate change refers to long-term shifts in temperature, precipitation, and other atmospheric patterns, largely driven by human activities such as burning fossil fuels, deforestation, and industrial processes. These changes contribute to rising global temperatures, melting ice caps, more frequent and severe weather events, and adverse impacts on ecosystems and human communities. Addressing climate change requires global cooperation to reduce greenhouse gas emissions, transition to renewable energy sources, and implement sustainable practices to protect the planet for future generations.' type='TextMessage'
source='reviewer' models_usage=RequestUsage(prompt_tokens=127, completion_tokens=144) metadata={} content="The paragraph provides a clear overview of climate change, its causes, and its impacts. To enhance clarity and engagement, consider adding specific examples or emphasizing the urgency of action. Here's a revised version:\n\nClimate change is a long-term alteration of Earth's climate patterns caused primarily by human activities such as burning fossil fuels, deforestation, and industrial emissions. These actions increase greenhouse gases in the atmosphere, leading to rising global temperatures, melting ice caps, and more frequent extreme weather events like hurricanes and droughts. The effects threaten ecosystems, disrupt agriculture, and endanger communities worldwide. Addressing this crisis requires urgent, coordinated global efforts to reduce emissions, adopt renewable energy, and promote sustainable practices to safeguard the planet for future generations." type='TextMessage'
source='DiGraphStopAgent' models_usage=None metadata={} content='Digraph execution is complete' type='StopMessage'
messages=[TextMessage(source='user', models_usage=None, metadata={}, content='Write a short paragraph about climate change.', type='TextMessage'), TextMessage(source='writer', models_usage=RequestUsage(prompt_tokens=28, completion_tokens=95), metadata={}, content='Climate change refers to long-term shifts in temperature, precipitation, and other atmospheric patterns, largely driven by human activities such as burning fossil fuels, deforestation, and industrial processes. These changes contribute to rising global temperatures, melting ice caps, more frequent and severe weather events, and adverse impacts on ecosystems and human communities. Addressing climate change requires global cooperation to reduce greenhouse gas emissions, transition to renewable energy sources, and implement sustainable practices to protect the planet for future generations.', type='TextMessage'), TextMessage(source='reviewer', models_usage=RequestUsage(prompt_tokens=127, completion_tokens=144), metadata={}, content="The paragraph provides a clear overview of climate change, its causes, and its impacts. To enhance clarity and engagement, consider adding specific examples or emphasizing the urgency of action. Here's a revised version:\n\nClimate change is a long-term alteration of Earth's climate patterns caused primarily by human activities such as burning fossil fuels, deforestation, and industrial emissions. These actions increase greenhouse gases in the atmosphere, leading to rising global temperatures, melting ice caps, and more frequent extreme weather events like hurricanes and droughts. The effects threaten ecosystems, disrupt agriculture, and endanger communities worldwide. Addressing this crisis requires urgent, coordinated global efforts to reduce emissions, adopt renewable energy, and promote sustainable practices to safeguard the planet for future generations.", type='TextMessage'), StopMessage(source='DiGraphStopAgent', models_usage=None, metadata={}, content='Digraph execution is complete', type='StopMessage')] stop_reason='Stop message received'

Paralleler Flow mit Join#

Wir erstellen nun einen etwas komplexeren Flow

  • Ein Autor entwirft einen Absatz.

  • Zwei Redakteure bearbeiten unabhängig voneinander Grammatik und Stil (paralleler Fan-Out).

  • Ein abschließender Prüfer konsolidiert deren Bearbeitungen (Join).

Die Ausführung beginnt beim Autor, verzweigt sich gleichzeitig zu editor1 und editor2, und beide fließen dann in den abschließenden Prüfer.

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import DiGraphBuilder, GraphFlow
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient

# Create an OpenAI model client
client = OpenAIChatCompletionClient(model="gpt-4.1-nano")

# Create the writer agent
writer = AssistantAgent("writer", model_client=client, system_message="Draft a short paragraph on climate change.")

# Create two editor agents
editor1 = AssistantAgent("editor1", model_client=client, system_message="Edit the paragraph for grammar.")

editor2 = AssistantAgent("editor2", model_client=client, system_message="Edit the paragraph for style.")

# Create the final reviewer agent
final_reviewer = AssistantAgent(
    "final_reviewer",
    model_client=client,
    system_message="Consolidate the grammar and style edits into a final version.",
)

# Build the workflow graph
builder = DiGraphBuilder()
builder.add_node(writer).add_node(editor1).add_node(editor2).add_node(final_reviewer)

# Fan-out from writer to editor1 and editor2
builder.add_edge(writer, editor1)
builder.add_edge(writer, editor2)

# Fan-in both editors into final reviewer
builder.add_edge(editor1, final_reviewer)
builder.add_edge(editor2, final_reviewer)

# Build and validate the graph
graph = builder.build()

# Create the flow
flow = GraphFlow(
    participants=builder.get_participants(),
    graph=graph,
)

# Run the workflow
await Console(flow.run_stream(task="Write a short paragraph about climate change."))

---------- TextMessage (user) ----------
Write a short paragraph about climate change.
---------- TextMessage (writer) ----------
Climate change refers to long-term shifts in weather patterns and global temperatures, largely driven by human activities such as burning fossil fuels, deforestation, and industrial processes. These activities increase concentrations of greenhouse gases like carbon dioxide and methane in the atmosphere, leading to global warming. The impacts of climate change include more frequent and severe weather events, rising sea levels, melting glaciers, and disruptions to ecosystems and agriculture. Addressing this urgent issue requires international cooperation, significant shifts toward renewable energy sources, and sustainable practices to reduce our carbon footprint and protect the planet for future generations.
---------- TextMessage (editor1) ----------
Climate change refers to long-term shifts in weather patterns and global temperatures, largely driven by human activities such as burning fossil fuels, deforestation, and industrial processes. These activities increase concentrations of greenhouse gases like carbon dioxide and methane in the atmosphere, leading to global warming. The impacts of climate change include more frequent and severe weather events, rising sea levels, melting glaciers, and disruptions to ecosystems and agriculture. Addressing this urgent issue requires international cooperation, significant shifts toward renewable energy sources, and sustainable practices to reduce our carbon footprint and protect the planet for future generations.
---------- TextMessage (editor2) ----------
Climate change involves long-term alterations in weather patterns and global temperatures, primarily caused by human activities like burning fossil fuels, deforestation, and industrial processes. These actions elevate levels of greenhouse gases such as carbon dioxide and methane, resulting in global warming. Its consequences are widespread, including more frequent and intense storms, rising sea levels, melting glaciers, and disturbances to ecosystems and agriculture. Combating this crisis demands international collaboration, a swift transition to renewable energy, and sustainable practices to cut carbon emissions, ensuring a healthier planet for future generations.
---------- TextMessage (final_reviewer) ----------
Climate change involves long-term alterations in weather patterns and global temperatures, primarily caused by human activities such as burning fossil fuels, deforestation, and industrial processes. These actions increase levels of greenhouse gases like carbon dioxide and methane, leading to global warming. Its consequences include more frequent and intense storms, rising sea levels, melting glaciers, and disruptions to ecosystems and agriculture. Addressing this crisis requires international collaboration, a swift transition to renewable energy, and sustainable practices to reduce carbon emissions, ensuring a healthier planet for future generations.
---------- StopMessage (DiGraphStopAgent) ----------
Digraph execution is complete

TaskResult(messages=[TextMessage(source='user', models_usage=None, metadata={}, content='Write a short paragraph about climate change.', type='TextMessage'), TextMessage(source='writer', models_usage=RequestUsage(prompt_tokens=28, completion_tokens=113), metadata={}, content='Climate change refers to long-term shifts in weather patterns and global temperatures, largely driven by human activities such as burning fossil fuels, deforestation, and industrial processes. These activities increase concentrations of greenhouse gases like carbon dioxide and methane in the atmosphere, leading to global warming. The impacts of climate change include more frequent and severe weather events, rising sea levels, melting glaciers, and disruptions to ecosystems and agriculture. Addressing this urgent issue requires international cooperation, significant shifts toward renewable energy sources, and sustainable practices to reduce our carbon footprint and protect the planet for future generations.', type='TextMessage'), TextMessage(source='editor1', models_usage=RequestUsage(prompt_tokens=144, completion_tokens=113), metadata={}, content='Climate change refers to long-term shifts in weather patterns and global temperatures, largely driven by human activities such as burning fossil fuels, deforestation, and industrial processes. These activities increase concentrations of greenhouse gases like carbon dioxide and methane in the atmosphere, leading to global warming. The impacts of climate change include more frequent and severe weather events, rising sea levels, melting glaciers, and disruptions to ecosystems and agriculture. Addressing this urgent issue requires international cooperation, significant shifts toward renewable energy sources, and sustainable practices to reduce our carbon footprint and protect the planet for future generations.', type='TextMessage'), TextMessage(source='editor2', models_usage=RequestUsage(prompt_tokens=263, completion_tokens=107), metadata={}, content='Climate change involves long-term alterations in weather patterns and global temperatures, primarily caused by human activities like burning fossil fuels, deforestation, and industrial processes. These actions elevate levels of greenhouse gases such as carbon dioxide and methane, resulting in global warming. Its consequences are widespread, including more frequent and intense storms, rising sea levels, melting glaciers, and disturbances to ecosystems and agriculture. Combating this crisis demands international collaboration, a swift transition to renewable energy, and sustainable practices to cut carbon emissions, ensuring a healthier planet for future generations.', type='TextMessage'), TextMessage(source='final_reviewer', models_usage=RequestUsage(prompt_tokens=383, completion_tokens=104), metadata={}, content='Climate change involves long-term alterations in weather patterns and global temperatures, primarily caused by human activities such as burning fossil fuels, deforestation, and industrial processes. These actions increase levels of greenhouse gases like carbon dioxide and methane, leading to global warming. Its consequences include more frequent and intense storms, rising sea levels, melting glaciers, and disruptions to ecosystems and agriculture. Addressing this crisis requires international collaboration, a swift transition to renewable energy, and sustainable practices to reduce carbon emissions, ensuring a healthier planet for future generations.', type='TextMessage'), StopMessage(source='DiGraphStopAgent', models_usage=None, metadata={}, content='Digraph execution is complete', type='StopMessage')], stop_reason='Stop message received')

Nachrichtenfilterung#

Ausführungsgraph vs. Nachrichten-Graph#

In GraphFlow wird der Ausführungsgraph mit DiGraph definiert, der die Reihenfolge der Agentenausführung steuert. Der Ausführungsgraph steuert jedoch nicht, welche Nachrichten ein Agent von anderen Agenten erhält. Standardmäßig werden alle Nachrichten an alle Agenten im Graphen gesendet.

Nachrichtenfilterung ist eine separate Funktion, die es Ihnen ermöglicht, die von jedem Agenten empfangenen Nachrichten zu filtern und ihren Modellkontext auf die relevanten Informationen zu beschränken. Die Menge der Nachrichtenfilter definiert den Nachrichten-Graph im Flow.

Die Angabe des Nachrichten-Graphen kann helfen bei

  • Reduzierung von Halluzinationen

  • Kontrolle der Speicherauslastung

  • Fokussierung von Agenten nur auf relevante Informationen

Sie können MessageFilterAgent zusammen mit MessageFilterConfig und PerSourceFilter verwenden, um diese Regeln zu definieren.

from autogen_agentchat.agents import AssistantAgent, MessageFilterAgent, MessageFilterConfig, PerSourceFilter
from autogen_agentchat.teams import DiGraphBuilder, GraphFlow
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient

# Model client
client = OpenAIChatCompletionClient(model="gpt-4.1-nano")

# Create agents
researcher = AssistantAgent(
    "researcher", model_client=client, system_message="Summarize key facts about climate change."
)
analyst = AssistantAgent("analyst", model_client=client, system_message="Review the summary and suggest improvements.")
presenter = AssistantAgent(
    "presenter", model_client=client, system_message="Prepare a presentation slide based on the final summary."
)

# Apply message filtering
filtered_analyst = MessageFilterAgent(
    name="analyst",
    wrapped_agent=analyst,
    filter=MessageFilterConfig(per_source=[PerSourceFilter(source="researcher", position="last", count=1)]),
)

filtered_presenter = MessageFilterAgent(
    name="presenter",
    wrapped_agent=presenter,
    filter=MessageFilterConfig(per_source=[PerSourceFilter(source="analyst", position="last", count=1)]),
)

# Build the flow
builder = DiGraphBuilder()
builder.add_node(researcher).add_node(filtered_analyst).add_node(filtered_presenter)
builder.add_edge(researcher, filtered_analyst).add_edge(filtered_analyst, filtered_presenter)

# Create the flow
flow = GraphFlow(
    participants=builder.get_participants(),
    graph=builder.build(),
)

# Run the flow
await Console(flow.run_stream(task="Summarize key facts about climate change."))

---------- TextMessage (user) ----------
Summarize key facts about climate change.

---------- TextMessage (researcher) ----------
Certainly! Here are some key facts about climate change:

1. **Global Warming**: Earth's average surface temperature has increased significantly over the past century, primarily due to human activities.
2. **Greenhouse Gas Emissions**: The main contributors are carbon dioxide (CO₂), methane (CH₄), and nitrous oxide (N₂O), resulting from burning fossil fuels, deforestation, and industrial processes.
3. **Impacts on Weather and Climate**: Climate change leads to more frequent and severe heatwaves, storms, droughts, and heavy rainfall.
4. **Rising Sea Levels**: Melting polar ice caps and glaciers, along with thermal expansion of seawater, are causing sea levels to rise.
5. **Effects on Ecosystems**: Altered habitats threaten plant and animal species, leading to biodiversity loss.
6. **Human Health and Societies**: Climate change contributes to health issues, food and water insecurity, and displacement of populations.
7. **Global Response**: International efforts like the Paris Agreement aim to limit temperature rise, promote renewable energy, and reduce emissions.
8. **Urgency**: Addressing climate change requires immediate, concerted actions to mitigate further damage and adapt to changes.

Let me know if you want more detailed information on any of these points!
---------- TextMessage (analyst) ----------
Your summary effectively covers the fundamental aspects of climate change and presents them clearly. Here are some suggestions to improve clarity, depth, and engagement:

1. Enhance structure with subheadings: Organize points into thematic sections (e.g., Causes, Effects, Responses) for easier navigation.
2. Add recent context or data: Incorporate the latest statistics or notable recent events to emphasize urgency.
3. Emphasize solutions: Briefly mention specific mitigation and adaptation strategies beyond international agreements.
4. Use more precise language: For example, specify the amount of temperature increase globally (~1.2°C since pre-industrial times).
5. Incorporate the importance of individual actions: Highlight how personal choices contribute to climate efforts.
6. Mention climate feedback loops: Briefly note how certain effects (like melting ice) can accelerate warming.

**Improved Version:**

---

**Overview of Climate Change**

**Causes:**
- Human activities, especially burning fossil fuels, deforestation, and industrial processes, have led to increased concentrations of greenhouse gases such as carbon dioxide (CO₂), methane (CH₄), and nitrous oxide (N₂O).
- Since the late 19th century, Earth's average surface temperature has risen by approximately 1.2°C, with the past decade being the warmest on record.

**Impacts:**
- The changing climate causes more frequent and intense heatwaves, storms, droughts, and heavy rainfall events.
- Melting polar ice caps and glaciers, along with thermal expansion, are raising sea levels, threatening coastal communities.
- Ecosystems are shifting, leading to habitat loss and risking biodiversity, with some species facing extinction.
- Human health and societies are affected through increased heat-related illnesses, food and water insecurity, and displacement due to extreme weather events.

**Global Response and Solutions:**
- International agreements like the Paris Agreement aim to limit global temperature rise well below 2°C.
- Strategies include transitioning to renewable energy sources, increasing energy efficiency, reforestation, and sustainable land use.
- Community and individual actions—reducing carbon footprints, supporting sustainable policies, and raising awareness—are essential components.

**Urgency and Call to Action:**
- Immediate, coordinated efforts are critical to mitigate irreversible damage and adapt to ongoing changes.
- Every sector, from government to individual, has a role to play in creating a sustainable future.

---

Let me know if you'd like a more detailed explanation of any section or additional statistical data!
---------- TextMessage (presenter) ----------
**Slide Title:**  
**Climate Change: Causes, Impacts & Solutions**

**Causes:**  
- Emissions from burning fossil fuels, deforestation, industrial activities  
- Greenhouse gases (CO₂, CH₄, N₂O) have increased significantly  
- Global temperature has risen by ~1.2°C since pre-industrial times  

**Impacts:**  
- More frequent heatwaves, storms, droughts, and heavy rainfall  
- Melting ice caps and rising sea levels threaten coastal areas  
- Habitat loss and decreased biodiversity  
- Health risks and societal disruptions  

**Responses & Solutions:**  
- International efforts like the Paris Agreement aim to limit warming  
- Transitioning to renewable energy, energy efficiency, reforestation  
- Community and individual actions: reducing carbon footprints and raising awareness  

**Urgency:**  
- Immediate, coordinated action is essential to prevent irreversible damage  
- Everyone has a role in building a sustainable future
---------- StopMessage (DiGraphStopAgent) ----------
Digraph execution is complete

TaskResult(messages=[TextMessage(source='user', models_usage=None, metadata={}, content='Summarize key facts about climate change.', type='TextMessage'), TextMessage(source='researcher', models_usage=RequestUsage(prompt_tokens=30, completion_tokens=267), metadata={}, content="Certainly! Here are some key facts about climate change:\n\n1. **Global Warming**: Earth's average surface temperature has increased significantly over the past century, primarily due to human activities.\n2. **Greenhouse Gas Emissions**: The main contributors are carbon dioxide (CO₂), methane (CH₄), and nitrous oxide (N₂O), resulting from burning fossil fuels, deforestation, and industrial processes.\n3. **Impacts on Weather and Climate**: Climate change leads to more frequent and severe heatwaves, storms, droughts, and heavy rainfall.\n4. **Rising Sea Levels**: Melting polar ice caps and glaciers, along with thermal expansion of seawater, are causing sea levels to rise.\n5. **Effects on Ecosystems**: Altered habitats threaten plant and animal species, leading to biodiversity loss.\n6. **Human Health and Societies**: Climate change contributes to health issues, food and water insecurity, and displacement of populations.\n7. **Global Response**: International efforts like the Paris Agreement aim to limit temperature rise, promote renewable energy, and reduce emissions.\n8. **Urgency**: Addressing climate change requires immediate, concerted actions to mitigate further damage and adapt to changes.\n\nLet me know if you want more detailed information on any of these points!", type='TextMessage'), TextMessage(source='analyst', models_usage=RequestUsage(prompt_tokens=287, completion_tokens=498), metadata={}, content="Your summary effectively covers the fundamental aspects of climate change and presents them clearly. Here are some suggestions to improve clarity, depth, and engagement:\n\n1. Enhance structure with subheadings: Organize points into thematic sections (e.g., Causes, Effects, Responses) for easier navigation.\n2. Add recent context or data: Incorporate the latest statistics or notable recent events to emphasize urgency.\n3. Emphasize solutions: Briefly mention specific mitigation and adaptation strategies beyond international agreements.\n4. Use more precise language: For example, specify the amount of temperature increase globally (~1.2°C since pre-industrial times).\n5. Incorporate the importance of individual actions: Highlight how personal choices contribute to climate efforts.\n6. Mention climate feedback loops: Briefly note how certain effects (like melting ice) can accelerate warming.\n\n**Improved Version:**\n\n---\n\n**Overview of Climate Change**\n\n**Causes:**\n- Human activities, especially burning fossil fuels, deforestation, and industrial processes, have led to increased concentrations of greenhouse gases such as carbon dioxide (CO₂), methane (CH₄), and nitrous oxide (N₂O).\n- Since the late 19th century, Earth's average surface temperature has risen by approximately 1.2°C, with the past decade being the warmest on record.\n\n**Impacts:**\n- The changing climate causes more frequent and intense heatwaves, storms, droughts, and heavy rainfall events.\n- Melting polar ice caps and glaciers, along with thermal expansion, are raising sea levels, threatening coastal communities.\n- Ecosystems are shifting, leading to habitat loss and risking biodiversity, with some species facing extinction.\n- Human health and societies are affected through increased heat-related illnesses, food and water insecurity, and displacement due to extreme weather events.\n\n**Global Response and Solutions:**\n- International agreements like the Paris Agreement aim to limit global temperature rise well below 2°C.\n- Strategies include transitioning to renewable energy sources, increasing energy efficiency, reforestation, and sustainable land use.\n- Community and individual actions—reducing carbon footprints, supporting sustainable policies, and raising awareness—are essential components.\n\n**Urgency and Call to Action:**\n- Immediate, coordinated efforts are critical to mitigate irreversible damage and adapt to ongoing changes.\n- Every sector, from government to individual, has a role to play in creating a sustainable future.\n\n---\n\nLet me know if you'd like a more detailed explanation of any section or additional statistical data!", type='TextMessage'), TextMessage(source='presenter', models_usage=RequestUsage(prompt_tokens=521, completion_tokens=192), metadata={}, content='**Slide Title:**  \n**Climate Change: Causes, Impacts & Solutions**\n\n**Causes:**  \n- Emissions from burning fossil fuels, deforestation, industrial activities  \n- Greenhouse gases (CO₂, CH₄, N₂O) have increased significantly  \n- Global temperature has risen by ~1.2°C since pre-industrial times  \n\n**Impacts:**  \n- More frequent heatwaves, storms, droughts, and heavy rainfall  \n- Melting ice caps and rising sea levels threaten coastal areas  \n- Habitat loss and decreased biodiversity  \n- Health risks and societal disruptions  \n\n**Responses & Solutions:**  \n- International efforts like the Paris Agreement aim to limit warming  \n- Transitioning to renewable energy, energy efficiency, reforestation  \n- Community and individual actions: reducing carbon footprints and raising awareness  \n\n**Urgency:**  \n- Immediate, coordinated action is essential to prevent irreversible damage  \n- Everyone has a role in building a sustainable future', type='TextMessage'), StopMessage(source='DiGraphStopAgent', models_usage=None, metadata={}, content='Digraph execution is complete', type='StopMessage')], stop_reason='Stop message received')

🔁 Fortgeschrittenes Beispiel: Bedingte Schleife + Gefilterte Zusammenfassung#

Dieses Beispiel demonstriert

  • Eine Schleife zwischen Generator und Prüfer (die abbricht, wenn der Prüfer „APPROVE“ sagt)

  • Ein Zusammenfassungsagent, der nur die erste Benutzereingabe und die letzte Nachricht des Prüfers sieht

from autogen_agentchat.agents import AssistantAgent, MessageFilterAgent, MessageFilterConfig, PerSourceFilter
from autogen_agentchat.teams import (
    DiGraphBuilder,
    GraphFlow,
)
from autogen_agentchat.conditions import MaxMessageTermination
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

# Agents
generator = AssistantAgent("generator", model_client=model_client, system_message="Generate a list of creative ideas.")
reviewer = AssistantAgent(
    "reviewer",
    model_client=model_client,
    system_message="Review ideas and provide feedbacks, or just 'APPROVE' for final approval.",
)
summarizer_core = AssistantAgent(
    "summary", model_client=model_client, system_message="Summarize the user request and the final feedback."
)

# Filtered summarizer
filtered_summarizer = MessageFilterAgent(
    name="summary",
    wrapped_agent=summarizer_core,
    filter=MessageFilterConfig(
        per_source=[
            PerSourceFilter(source="user", position="first", count=1),
            PerSourceFilter(source="reviewer", position="last", count=1),
        ]
    ),
)

# Build graph with conditional loop
builder = DiGraphBuilder()
builder.add_node(generator).add_node(reviewer).add_node(filtered_summarizer)
builder.add_edge(generator, reviewer)
builder.add_edge(reviewer, filtered_summarizer, condition=lambda msg: "APPROVE" in msg.to_model_text())
builder.add_edge(reviewer, generator, condition=lambda msg: "APPROVE" not in msg.to_model_text())
builder.set_entry_point(generator)  # Set entry point to generator. Required if there are no source nodes.
graph = builder.build()

termination_condition = MaxMessageTermination(10)

# Create the flow
flow = GraphFlow(
    participants=builder.get_participants(),
    graph=graph,
    termination_condition=termination_condition
)

# Run the flow and pretty print the output in the console
await Console(flow.run_stream(task="Brainstorm ways to reduce plastic waste."))

---------- TextMessage (user) ----------
Brainstorm ways to reduce plastic waste.
---------- TextMessage (generator) ----------
Here are some creative ideas to help reduce plastic waste:

1. **Refill Stations**: Create refill stations for common household liquids (like soaps, shampoos, and detergents) where people can bring their own containers to fill up.

2. **DIY Kits**: Offer DIY kits for making eco-friendly products, such as beeswax wraps, reusable bags, or natural cleaning solutions.

3. **Community Swap Events**: Organize swap events where people can bring unwanted items, including clothing and household products, to exchange instead of purchasing new items.

4. **Plastic-Free Challenge**: Launch a community-wide challenge encouraging residents to go plastic-free for a month, sharing tips and experiences on social media.

5. **Incentivize Businesses**: Create incentives for local businesses that implement sustainable practices, like providing discounts to customers who bring their own containers or bags.

6. **Educational Campaigns**: Partner with schools to educate children about the impact of plastic waste and encourage them to take home messages to their families.

7. **Plastic-Free Shopping Zones**: Designate certain areas in town as plastic-free zones where businesses agree to eliminate single-use plastics.

8. **Upcycling Workshops**: Host workshops teaching people how to upcycle plastic waste into art, furniture, or home decor.

9. **Composting Competition**: Encourage households to compost food waste and offer a competition for the best composting garden to foster eco-awareness.

10. **Zero-Waste Stores**: Support or start zero-waste stores that sell bulk goods, allowing customers to shop with their own containers.

11. **Mobile Recycling Units**: Implement mobile recycling units that visit neighborhoods to educate residents on recycling properly and collect recyclables.

12. **Plastic Offset Programs**: Create programs that allow individuals and companies to offset their plastic usage through donations to initiatives that remove plastic from oceans.

13. **Collaboration with Influencers**: Partner with social media influencers to spread the message about reducing plastic waste and promote sustainable alternatives.

14. **Sustainable Product Market**: Organize a market dedicated exclusively to sustainable products and services, showcasing local vendors who prioritize eco-friendly practices.

15. **Plastic Waste Art Installations**: Collaborate with artists to create public installations made from recycled plastic, raising awareness of the plastic problem in a visually impactful way.

16. **Interactive Apps**: Develop apps that track plastic usage and provide personalized tips for reducing plastic consumption based on user habits.

17. **Corporate Partnerships**: Work with businesses to develop corporate responsibility programs focused on reducing plastic use in their operations and packaging.

18. **Legislation Advocacy**: Promote local policies that restrict single-use plastics or support more effective recycling programs.

19. **Public Transportation Awareness**: Encourage public transportation usage by providing eco-friendly incentives for those who walk, bike, or use buses instead of cars.

20. **Create a Local Plastic Waste Repository**: Start a community hub where individuals and artists can drop off plastic waste for reuse in projects or art pieces.

By implementing these ideas, communities can take significant steps toward reducing plastic waste and fostering a sustainable future.
---------- TextMessage (reviewer) ----------
These ideas present a comprehensive and practical approach to reducing plastic waste within communities. Here’s some feedback and considerations for each suggestion:

1. **Refill Stations**: Great idea; consider partnering with local health and wellness shops for broader adoption.
   
2. **DIY Kits**: Ensure kits include clear instructions and safety guidance to promote user-friendliness.

3. **Community Swap Events**: Promote these as regular events to build a sense of community and reinforce sustainable habits.

4. **Plastic-Free Challenge**: Consider creating a dedicated hashtag to track participants’ journeys and foster engagement online.

5. **Incentivize Businesses**: Work on a simple certification system for sustainable businesses to encourage participation and recognition.

6. **Educational Campaigns**: Tailor content to different age groups to maximize impact across the community.

7. **Plastic-Free Shopping Zones**: Consider involving local government for support and promotion, which can increase visibility and compliance.

8. **Upcycling Workshops**: Source materials locally for workshops to decrease transportation emissions and support local businesses.

9. **Composting Competition**: Collaborate with gardening clubs for expert insights and to broaden participation in community gardening.

10. **Zero-Waste Stores**: Explore online sales options to enhance accessibility while retaining the focus on zero-waste practices.

11. **Mobile Recycling Units**: Train volunteers for effective community engagement and education during visits.

12. **Plastic Offset Programs**: Emphasize transparency in how donations are used to build trust within the community.

13. **Collaboration with Influencers**: Ensure influencers have a genuine commitment to sustainability to ensure credible messaging.

14. **Sustainable Product Market**: Regularly invite new vendors to keep the market fresh and encourage innovation in sustainable products.

15. **Plastic Waste Art Installations**: Consider educational plaques accompanying installations that inform viewers about the issues of plastic waste.

16. **Interactive Apps**: Include gamification elements to encourage increased user engagement and sharing among friends.

17. **Corporate Partnerships**: Develop case studies or success stories to showcase the benefits of reduced plastic use for businesses.

18. **Legislation Advocacy**: Mobilize community members to become advocates themselves, creating a grass-roots effort for policy change.

19. **Public Transportation Awareness**: Explore partnerships with public transit systems for eco-friendly promotions.

20. **Create a Local Plastic Waste Repository**: Establish partnerships with local craft schools or organizations to enhance creativity and use of the repository.

Overall, these ideas have high potential for impactful implementation. Emphasizing community engagement, education, and ongoing support will help ensure their success. **APPROVE**.
---------- TextMessage (summary) ----------
The user requested brainstorming ideas to reduce plastic waste, looking for practical and impactful solutions. The reviewer provided detailed feedback on each suggested idea, indicating strengths and considerations for improvement, such as involving local businesses, enhancing community engagement, and promoting educational initiatives. The final feedback indicates that the suggestions have great potential and emphasizes the importance of community involvement and education for successful implementation, culminating in an overall approval of the ideas presented.

TaskResult(messages=[TextMessage(id='eca90b4f-a8cc-4f06-9b42-d8387caf338e', source='user', models_usage=None, metadata={}, created_at=datetime.datetime(2025, 7, 15, 1, 48, 51, 648989, tzinfo=datetime.timezone.utc), content='Brainstorm ways to reduce plastic waste.', type='TextMessage'), TextMessage(id='29767cbd-ae8d-4dfb-be57-7f982aaddc4b', source='generator', models_usage=RequestUsage(prompt_tokens=27, completion_tokens=627), metadata={}, created_at=datetime.datetime(2025, 7, 15, 1, 49, 6, 788238, tzinfo=datetime.timezone.utc), content='Here are some creative ideas to help reduce plastic waste:\n\n1. **Refill Stations**: Create refill stations for common household liquids (like soaps, shampoos, and detergents) where people can bring their own containers to fill up.\n\n2. **DIY Kits**: Offer DIY kits for making eco-friendly products, such as beeswax wraps, reusable bags, or natural cleaning solutions.\n\n3. **Community Swap Events**: Organize swap events where people can bring unwanted items, including clothing and household products, to exchange instead of purchasing new items.\n\n4. **Plastic-Free Challenge**: Launch a community-wide challenge encouraging residents to go plastic-free for a month, sharing tips and experiences on social media.\n\n5. **Incentivize Businesses**: Create incentives for local businesses that implement sustainable practices, like providing discounts to customers who bring their own containers or bags.\n\n6. **Educational Campaigns**: Partner with schools to educate children about the impact of plastic waste and encourage them to take home messages to their families.\n\n7. **Plastic-Free Shopping Zones**: Designate certain areas in town as plastic-free zones where businesses agree to eliminate single-use plastics.\n\n8. **Upcycling Workshops**: Host workshops teaching people how to upcycle plastic waste into art, furniture, or home decor.\n\n9. **Composting Competition**: Encourage households to compost food waste and offer a competition for the best composting garden to foster eco-awareness.\n\n10. **Zero-Waste Stores**: Support or start zero-waste stores that sell bulk goods, allowing customers to shop with their own containers.\n\n11. **Mobile Recycling Units**: Implement mobile recycling units that visit neighborhoods to educate residents on recycling properly and collect recyclables.\n\n12. **Plastic Offset Programs**: Create programs that allow individuals and companies to offset their plastic usage through donations to initiatives that remove plastic from oceans.\n\n13. **Collaboration with Influencers**: Partner with social media influencers to spread the message about reducing plastic waste and promote sustainable alternatives.\n\n14. **Sustainable Product Market**: Organize a market dedicated exclusively to sustainable products and services, showcasing local vendors who prioritize eco-friendly practices.\n\n15. **Plastic Waste Art Installations**: Collaborate with artists to create public installations made from recycled plastic, raising awareness of the plastic problem in a visually impactful way.\n\n16. **Interactive Apps**: Develop apps that track plastic usage and provide personalized tips for reducing plastic consumption based on user habits.\n\n17. **Corporate Partnerships**: Work with businesses to develop corporate responsibility programs focused on reducing plastic use in their operations and packaging.\n\n18. **Legislation Advocacy**: Promote local policies that restrict single-use plastics or support more effective recycling programs.\n\n19. **Public Transportation Awareness**: Encourage public transportation usage by providing eco-friendly incentives for those who walk, bike, or use buses instead of cars.\n\n20. **Create a Local Plastic Waste Repository**: Start a community hub where individuals and artists can drop off plastic waste for reuse in projects or art pieces.\n\nBy implementing these ideas, communities can take significant steps toward reducing plastic waste and fostering a sustainable future.', type='TextMessage'), TextMessage(id='54e02028-0239-4809-8163-af60745e6b9d', source='reviewer', models_usage=RequestUsage(prompt_tokens=671, completion_tokens=532), metadata={}, created_at=datetime.datetime(2025, 7, 15, 1, 49, 17, 327641, tzinfo=datetime.timezone.utc), content='These ideas present a comprehensive and practical approach to reducing plastic waste within communities. Here’s some feedback and considerations for each suggestion:\n\n1. **Refill Stations**: Great idea; consider partnering with local health and wellness shops for broader adoption.\n   \n2. **DIY Kits**: Ensure kits include clear instructions and safety guidance to promote user-friendliness.\n\n3. **Community Swap Events**: Promote these as regular events to build a sense of community and reinforce sustainable habits.\n\n4. **Plastic-Free Challenge**: Consider creating a dedicated hashtag to track participants’ journeys and foster engagement online.\n\n5. **Incentivize Businesses**: Work on a simple certification system for sustainable businesses to encourage participation and recognition.\n\n6. **Educational Campaigns**: Tailor content to different age groups to maximize impact across the community.\n\n7. **Plastic-Free Shopping Zones**: Consider involving local government for support and promotion, which can increase visibility and compliance.\n\n8. **Upcycling Workshops**: Source materials locally for workshops to decrease transportation emissions and support local businesses.\n\n9. **Composting Competition**: Collaborate with gardening clubs for expert insights and to broaden participation in community gardening.\n\n10. **Zero-Waste Stores**: Explore online sales options to enhance accessibility while retaining the focus on zero-waste practices.\n\n11. **Mobile Recycling Units**: Train volunteers for effective community engagement and education during visits.\n\n12. **Plastic Offset Programs**: Emphasize transparency in how donations are used to build trust within the community.\n\n13. **Collaboration with Influencers**: Ensure influencers have a genuine commitment to sustainability to ensure credible messaging.\n\n14. **Sustainable Product Market**: Regularly invite new vendors to keep the market fresh and encourage innovation in sustainable products.\n\n15. **Plastic Waste Art Installations**: Consider educational plaques accompanying installations that inform viewers about the issues of plastic waste.\n\n16. **Interactive Apps**: Include gamification elements to encourage increased user engagement and sharing among friends.\n\n17. **Corporate Partnerships**: Develop case studies or success stories to showcase the benefits of reduced plastic use for businesses.\n\n18. **Legislation Advocacy**: Mobilize community members to become advocates themselves, creating a grass-roots effort for policy change.\n\n19. **Public Transportation Awareness**: Explore partnerships with public transit systems for eco-friendly promotions.\n\n20. **Create a Local Plastic Waste Repository**: Establish partnerships with local craft schools or organizations to enhance creativity and use of the repository.\n\nOverall, these ideas have high potential for impactful implementation. Emphasizing community engagement, education, and ongoing support will help ensure their success. **APPROVE**.', type='TextMessage'), TextMessage(id='55409dc3-9766-4071-ab85-0b3125cb59c7', source='summary', models_usage=RequestUsage(prompt_tokens=570, completion_tokens=82), metadata={}, created_at=datetime.datetime(2025, 7, 15, 1, 49, 19, 442276, tzinfo=datetime.timezone.utc), content='The user requested brainstorming ideas to reduce plastic waste, looking for practical and impactful solutions. The reviewer provided detailed feedback on each suggested idea, indicating strengths and considerations for improvement, such as involving local businesses, enhancing community engagement, and promoting educational initiatives. The final feedback indicates that the suggestions have great potential and emphasizes the importance of community involvement and education for successful implementation, culminating in an overall approval of the ideas presented.', type='TextMessage')], stop_reason='Digraph execution is complete')

🔁 Fortgeschrittenes Beispiel: Zyklen mit Aktivierungsgruppen-Beispielen#

Die folgenden Beispiele zeigen, wie activation_group und activation_condition verwendet werden können, um komplexe Abhängigkeitsmuster in zyklischen Graphen zu handhaben, insbesondere wenn mehrere Pfade zum selben Zielknoten führen.

Beispiel 1: Schleife mit mehreren Pfaden – „Alle“-Aktivierung (A→B→C→B)#

In diesem Szenario haben wir A → B → C → B, wobei B zwei eingehende Kanten hat (von A und von C). Standardmäßig benötigt B, dass alle seine Abhängigkeiten erfüllt sind, bevor es ausgeführt wird.

Dieses Beispiel zeigt eine Überprüfungsschleife, bei der sowohl die anfängliche Eingabe (A) als auch das Feedback (C) verarbeitet werden müssen, bevor B erneut ausgeführt werden kann.

from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import DiGraphBuilder, GraphFlow
from autogen_agentchat.conditions import MaxMessageTermination
from autogen_agentchat.ui import Console
from autogen_ext.models.openai import OpenAIChatCompletionClient

# Model client
client = OpenAIChatCompletionClient(model="gpt-4o-mini")

# Create agents for A→B→C→B→E scenario
agent_a = AssistantAgent("A", model_client=client, system_message="Start the process and provide initial input.")
agent_b = AssistantAgent(
    "B",
    model_client=client,
    system_message="Process input from A or feedback from C. Say 'CONTINUE' if it's from A or 'STOP' if it's from C.",
)
agent_c = AssistantAgent("C", model_client=client, system_message="Review B's output and provide feedback.")
agent_e = AssistantAgent("E", model_client=client, system_message="Finalize the process.")

# Build the graph with activation groups
builder = DiGraphBuilder()
builder.add_node(agent_a).add_node(agent_b).add_node(agent_c).add_node(agent_e)

# A → B (initial path)
builder.add_edge(agent_a, agent_b, activation_group="initial")

# B → C
builder.add_edge(agent_b, agent_c, condition="CONTINUE")

# C → B (loop back - different activation group)
builder.add_edge(agent_c, agent_b, activation_group="feedback")

# B → E (exit condition)
builder.add_edge(agent_b, agent_e, condition="STOP")

termination_condition = MaxMessageTermination(10)
# Build and create flow
graph = builder.build()
flow = GraphFlow(participants=[agent_a, agent_b, agent_c, agent_e], graph=graph, termination_condition=termination_condition)

print("=== Example 1: A→B→C→B with 'All' Activation ===")
print("B will exit when it receives a message from C")
# await Console(flow.run_stream(task="Start a review process for a document."))

Beispiel 2: Schleife mit mehreren Pfaden – „Beliebige“-Aktivierung (A→B→(C1,C2)→B)#

In diesem komplexeren Szenario haben wir A → B → (C1, C2) → B, wobei

  • B parallel in C1 und C2 verzweigt

  • Sowohl C1 als auch C2 führen zurück zu B

  • B verwendet „beliebige“ Aktivierung, was bedeutet, dass es ausgeführt wird, sobald entweder C1 oder C2 abgeschlossen ist

Dies ist nützlich für Szenarien, in denen Sie möchten, dass die schnellste Antwort den nächsten Schritt auslöst.

# Create agents for A→B→(C1,C2)→B scenario
agent_a2 = AssistantAgent("A", model_client=client, system_message="Initiate a task that needs parallel processing.")
agent_b2 = AssistantAgent(
    "B",
    model_client=client,
    system_message="Coordinate parallel tasks. Say 'PROCESS' to start parallel work or 'DONE' to finish.",
)
agent_c1 = AssistantAgent("C1", model_client=client, system_message="Handle task type 1. Say 'C1_COMPLETE' when done.")
agent_c2 = AssistantAgent("C2", model_client=client, system_message="Handle task type 2. Say 'C2_COMPLETE' when done.")
agent_e = AssistantAgent("E", model_client=client, system_message="Finalize the process.")

# Build the graph with "any" activation
builder2 = DiGraphBuilder()
builder2.add_node(agent_a2).add_node(agent_b2).add_node(agent_c1).add_node(agent_c2).add_node(agent_e)

# A → B (initial)
builder2.add_edge(agent_a2, agent_b2)

# B → C1 and B → C2 (parallel fan-out)
builder2.add_edge(agent_b2, agent_c1, condition="PROCESS")
builder2.add_edge(agent_b2, agent_c2, condition="PROCESS")

# B → E (exit condition)
builder2.add_edge(agent_b2, agent_e, condition=lambda msg: "DONE" in msg.to_model_text())

# C1 → B and C2 → B (both in same activation group with "any" condition)
builder2.add_edge(
    agent_c1, agent_b2, activation_group="loop_back_group", activation_condition="any", condition="C1_COMPLETE"
)

builder2.add_edge(
    agent_c2, agent_b2, activation_group="loop_back_group", activation_condition="any", condition="C2_COMPLETE"
)

# Build and create flow
graph2 = builder2.build()
flow2 = GraphFlow(participants=[agent_a2, agent_b2, agent_c1, agent_c2, agent_e], graph=graph2)

print("=== Example 2: A→B→(C1,C2)→B with 'Any' Activation ===")
print("B will execute as soon as EITHER C1 OR C2 completes (whichever finishes first)")
# await Console(flow2.run_stream(task="Start a parallel processing task."))

Beispiel 3: Gemischte Aktivierungsgruppen#

Dieses Beispiel zeigt, wie verschiedene Aktivierungsgruppen im selben Graphen koexistieren können. Wir haben ein Szenario, in dem

  • Knoten D Eingaben von mehreren Quellen mit unterschiedlichen Aktivierungsanforderungen erhält

  • Einige Abhängigkeiten verwenden „alle“-Aktivierung (müssen auf alle Eingaben warten)

  • Andere Abhängigkeiten verwenden „beliebige“-Aktivierung (Fortschritt bei der ersten Eingabe)

Dieses Muster ist nützlich für komplexe Workflows, bei denen unterschiedliche Arten von Abhängigkeiten unterschiedliche Dringlichkeitsstufen aufweisen.

# Create agents for mixed activation scenario
agent_a3 = AssistantAgent("A", model_client=client, system_message="Provide critical input that must be processed.")
agent_b3 = AssistantAgent("B", model_client=client, system_message="Provide secondary critical input.")
agent_c3 = AssistantAgent("C", model_client=client, system_message="Provide optional quick input.")
agent_d3 = AssistantAgent("D", model_client=client, system_message="Process inputs based on different priority levels.")

# Build graph with mixed activation groups
builder3 = DiGraphBuilder()
builder3.add_node(agent_a3).add_node(agent_b3).add_node(agent_c3).add_node(agent_d3)

# Critical inputs that must ALL be present (activation_group="critical", activation_condition="all")
builder3.add_edge(agent_a3, agent_d3, activation_group="critical", activation_condition="all")
builder3.add_edge(agent_b3, agent_d3, activation_group="critical", activation_condition="all")

# Optional input that can trigger execution on its own (activation_group="optional", activation_condition="any")
builder3.add_edge(agent_c3, agent_d3, activation_group="optional", activation_condition="any")

# Build and create flow
graph3 = builder3.build()
flow3 = GraphFlow(participants=[agent_a3, agent_b3, agent_c3, agent_d3], graph=graph3)

print("=== Example 3: Mixed Activation Groups ===")
print("D will execute when:")
print("- BOTH A AND B complete (critical group with 'all' activation), OR")
print("- C completes (optional group with 'any' activation)")
print("This allows for both required dependencies and fast-path triggers.")
# await Console(flow3.run_stream(task="Process inputs with mixed priority levels."))

Wichtige Erkenntnisse für Aktivierungsgruppen#

  1. activation_group: Gruppiert Kanten, die auf denselben Zielknoten zeigen, und ermöglicht es Ihnen, verschiedene Abhängigkeitsmuster zu definieren.

  2. activation_condition:

    • "all" (Standard): Der Zielknoten wartet darauf, dass ALLE Kanten in der Gruppe erfüllt sind

    • "any": Der Zielknoten wird ausgeführt, sobald EINE Kante in der Gruppe erfüllt ist

  3. Anwendungsfälle:

    • Zyklen mit mehreren Einstiegspunkten: Unterschiedliche Aktivierungsgruppen verhindern Konflikte

    • Prioritätsbasierte Ausführung: Mischen von „alle“- und „beliebige“-Bedingungen für unterschiedliche Dringlichkeitsstufen

    • Parallele Verarbeitung mit vorzeitigem Abbruch: Verwenden Sie „beliebige“, um mit dem schnellsten Ergebnis fortzufahren

  4. Best Practices:

    • Verwenden Sie aussagekräftige Gruppennamen ("critical", "optional", "feedback" usw.)

    • Halten Sie Aktivierungsbedingungen innerhalb derselben Gruppe konsistent

    • Testen Sie Ihre Graphlogik mit verschiedenen Ausführungspfaden

Diese Muster ermöglichen eine hochentwickelte Workflow-Steuerung bei gleichzeitiger Beibehaltung klarer, verständlicher Ausführungssemantik.