[BREAKING] Python: Refactor workflow events to unified discriminated union pattern (#3690)

* Refactor events

* Merge main

* Fixes

* Cleanup

* Update samples and tests

* Remove unused imports

* PR feedback

* Merge main. Add properties for events to help typing

* Formatting

* Cleanup

* use builtins.type to avoid shadowing by WorkflowEvent.type attribute

* Final improvements

python/samples/getting_started/orchestrations/README.md

@@ -57,9 +57,9 @@ from agent_framework.orchestrations import (
 **Sequential orchestration note**: Sequential orchestration uses a few small adapter nodes for plumbing:
 - `input-conversation` normalizes input to `list[ChatMessage]`
 - `to-conversation:<participant>` converts agent responses into the shared conversation
-- `complete` publishes the final `WorkflowOutputEvent`
+- `complete` publishes the final output event (type='output')
 
-These may appear in event streams (ExecutorInvoke/Completed). They're analogous to concurrent's dispatcher and aggregator and can be ignored if you only care about agent activity.
+These may appear in event streams (executor_invoked/executor_completed). They're analogous to concurrent's dispatcher and aggregator and can be ignored if you only care about agent activity.
 
 ## Environment Variables
 

python/samples/getting_started/orchestrations/concurrent_agents.py

@@ -23,7 +23,7 @@ Demonstrates:
 
 Prerequisites:
 - Azure OpenAI access configured for AzureOpenAIChatClient (use az login + env vars)
-- Familiarity with Workflow events (WorkflowOutputEvent)
+- Familiarity with Workflow events (WorkflowEvent)
 """
 
 

python/samples/getting_started/orchestrations/group_chat_agent_manager.py

@@ -7,7 +7,6 @@ from agent_framework import (
     AgentResponseUpdate,
     ChatAgent,
     ChatMessage,
-    WorkflowOutputEvent,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from agent_framework.orchestrations import GroupChatBuilder
@@ -74,7 +73,7 @@ async def main() -> None:
         # The agent orchestrator will intelligently decide when to end before this limit but just in case
         .with_termination_condition(lambda messages: sum(1 for msg in messages if msg.role == "assistant") >= 4)
         # Enable intermediate outputs to observe the conversation as it unfolds
-        # Intermediate outputs will be emitted as WorkflowOutputEvent events
+        # Intermediate outputs will be emitted as WorkflowEvent with type "output" events
         .with_intermediate_outputs()
         .build()
     )
@@ -88,7 +87,7 @@ async def main() -> None:
     # Keep track of the last response to format output nicely in streaming mode
     last_response_id: str | None = None
     async for event in workflow.run(task, stream=True):
-        if isinstance(event, WorkflowOutputEvent):
+        if event.type == "output":
             data = event.data
             if isinstance(data, AgentResponseUpdate):
                 rid = data.response_id
@@ -98,7 +97,7 @@ async def main() -> None:
                     print(f"{data.author_name}:", end=" ", flush=True)
                     last_response_id = rid
                 print(data.text, end="", flush=True)
-            else:
+            elif event.type == "output":
                 # The output of the group chat workflow is a collection of chat messages from all participants
                 outputs = cast(list[ChatMessage], event.data)
                 print("\n" + "=" * 80)

python/samples/getting_started/orchestrations/group_chat_philosophical_debate.py

@@ -8,7 +8,6 @@ from agent_framework import (
     AgentResponseUpdate,
     ChatAgent,
     ChatMessage,
-    WorkflowOutputEvent,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from agent_framework.orchestrations import GroupChatBuilder
@@ -214,7 +213,7 @@ Share your perspective authentically. Feel free to:
         .participants([farmer, developer, teacher, activist, spiritual_leader, artist, immigrant, doctor])
         .with_termination_condition(lambda messages: sum(1 for msg in messages if msg.role == "assistant") >= 10)
         # Enable intermediate outputs to observe the conversation as it unfolds
-        # Intermediate outputs will be emitted as WorkflowOutputEvent events
+        # Intermediate outputs will be emitted as WorkflowEvent with type "output" events
         .with_intermediate_outputs()
         .build()
     )
@@ -241,7 +240,7 @@ Share your perspective authentically. Feel free to:
     # Keep track of the last response to format output nicely in streaming mode
     last_response_id: str | None = None
     async for event in workflow.run(f"Please begin the discussion on: {topic}", stream=True):
-        if isinstance(event, WorkflowOutputEvent):
+        if event.type == "output":
             data = event.data
             if isinstance(data, AgentResponseUpdate):
                 rid = data.response_id
@@ -251,7 +250,7 @@ Share your perspective authentically. Feel free to:
                     print(f"{data.author_name}:", end=" ", flush=True)
                     last_response_id = rid
                 print(data.text, end="", flush=True)
-            else:
+            elif event.type == "output":
                 # The output of the group chat workflow is a collection of chat messages from all participants
                 outputs = cast(list[ChatMessage], event.data)
                 print("\n" + "=" * 80)

python/samples/getting_started/orchestrations/group_chat_simple_selector.py

@@ -7,7 +7,6 @@ from agent_framework import (
     AgentResponseUpdate,
     ChatAgent,
     ChatMessage,
-    WorkflowOutputEvent,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from agent_framework.orchestrations import GroupChatBuilder, GroupChatState
@@ -92,7 +91,7 @@ async def main() -> None:
         # have nothing to add, but for demo purposes we want to see at least one full round of interaction.
         .with_termination_condition(lambda conversation: len(conversation) >= 6)
         # Enable intermediate outputs to observe the conversation as it unfolds
-        # Intermediate outputs will be emitted as WorkflowOutputEvent events
+        # Intermediate outputs will be emitted as WorkflowEvent with type "output" events
         .with_intermediate_outputs()
         .build()
     )
@@ -106,7 +105,7 @@ async def main() -> None:
     # Keep track of the last response to format output nicely in streaming mode
     last_response_id: str | None = None
     async for event in workflow.run(task, stream=True):
-        if isinstance(event, WorkflowOutputEvent):
+        if event.type == "output":
             data = event.data
             if isinstance(data, AgentResponseUpdate):
                 rid = data.response_id
@@ -116,7 +115,7 @@ async def main() -> None:
                     print(f"{data.author_name}:", end=" ", flush=True)
                     last_response_id = rid
                 print(data.text, end="", flush=True)
-            else:
+            elif event.type == "output":
                 # The output of the group chat workflow is a collection of chat messages from all participants
                 outputs = cast(list[ChatMessage], event.data)
                 print("\n" + "=" * 80)

python/samples/getting_started/orchestrations/handoff_autonomous.py

@@ -8,8 +8,6 @@ from agent_framework import (
     AgentResponseUpdate,
     ChatAgent,
     ChatMessage,
-    HandoffSentEvent,
-    WorkflowOutputEvent,
     resolve_agent_id,
 )
 from agent_framework.azure import AzureOpenAIChatClient
@@ -112,9 +110,9 @@ async def main() -> None:
 
     last_response_id: str | None = None
     async for event in workflow.run(request, stream=True):
-        if isinstance(event, HandoffSentEvent):
-            print(f"\nHandoff Event: from {event.source} to {event.target}\n")
-        elif isinstance(event, WorkflowOutputEvent):
+        if event.type == "handoff_sent":
+            print(f"\nHandoff Event: from {event.data.source} to {event.data.target}\n")
+        elif event.type == "output":
             data = event.data
             if isinstance(data, AgentResponseUpdate):
                 if not data.text:
@@ -128,8 +126,8 @@ async def main() -> None:
                     print(f"{data.author_name}:", end=" ", flush=True)
                     last_response_id = rid
                 print(data.text, end="", flush=True)
-            else:
-                # The output of the group chat workflow is a collection of chat messages from all participants
+            elif event.type == "output":
+                # The output of the handoff workflow is a collection of chat messages from all participants
                 outputs = cast(list[ChatMessage], event.data)
                 print("\n" + "=" * 80)
                 print("\nFinal Conversation Transcript:\n")

python/samples/getting_started/orchestrations/handoff_participant_factory.py

@@ -8,16 +8,13 @@ from agent_framework import (
     AgentResponse,
     ChatAgent,
     ChatMessage,
-    RequestInfoEvent,
     Workflow,
     WorkflowEvent,
-    WorkflowOutputEvent,
     WorkflowRunState,
-    WorkflowStatusEvent,
     tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
-from agent_framework.orchestrations import HandoffAgentUserRequest, HandoffBuilder, HandoffSentEvent
+from agent_framework.orchestrations import HandoffAgentUserRequest, HandoffBuilder
 from azure.identity import AzureCliCredential
 
 logging.basicConfig(level=logging.ERROR)
@@ -107,35 +104,35 @@ def create_return_agent() -> ChatAgent:
     )
 
 
-def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
+def _handle_events(events: list[WorkflowEvent]) -> list[WorkflowEvent[HandoffAgentUserRequest]]:
     """Process workflow events and extract any pending user input requests.
 
     This function inspects each event type and:
     - Prints workflow status changes (IDLE, IDLE_WITH_PENDING_REQUESTS, etc.)
     - Displays final conversation snapshots when workflow completes
     - Prints user input request prompts
-    - Collects all RequestInfoEvent instances for response handling
+    - Collects all request_info events for response handling
 
     Args:
         events: List of WorkflowEvent to process
 
     Returns:
-        List of RequestInfoEvent representing pending user input requests
+        List of WorkflowEvent[HandoffAgentUserRequest] representing pending user input requests
     """
-    requests: list[RequestInfoEvent] = []
+    requests: list[WorkflowEvent[HandoffAgentUserRequest]] = []
 
     for event in events:
-        if isinstance(event, HandoffSentEvent):
-            # HandoffSentEvent: Indicates a handoff has been initiated
-            print(f"\n[Handoff from {event.source} to {event.target} initiated.]")
-        elif isinstance(event, WorkflowStatusEvent) and event.state in {
+        if event.type == "handoff_sent":
+            # handoff_sent event: Indicates a handoff has been initiated
+            print(f"\n[Handoff from {event.data.source} to {event.data.target} initiated.]")
+        elif event.type == "status" and event.state in {
             WorkflowRunState.IDLE,
             WorkflowRunState.IDLE_WITH_PENDING_REQUESTS,
         }:
-            # WorkflowStatusEvent: Indicates workflow state changes
+            # Status event: Indicates workflow state changes
             print(f"\n[Workflow Status] {event.state.name}")
-        elif isinstance(event, WorkflowOutputEvent):
-            # WorkflowOutputEvent: Contains contents generated by the workflow
+        elif event.type == "output":
+            # Output event: Contains contents generated by the workflow
             data = event.data
             if isinstance(data, AgentResponse):
                 for message in data.messages:
@@ -144,7 +141,7 @@ def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
                         continue
                     speaker = message.author_name or message.role
                     print(f"- {speaker}: {message.text}")
-            else:
+            elif event.type == "output":
                 # The output of the handoff workflow is a collection of chat messages from all participants
                 conversation = cast(list[ChatMessage], event.data)
                 if isinstance(conversation, list):
@@ -153,11 +150,11 @@ def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
                         speaker = message.author_name or message.role
                         print(f"- {speaker}: {message.text or [content.type for content in message.contents]}")
                     print("===================================")
-        elif isinstance(event, RequestInfoEvent):
-            # RequestInfoEvent: Workflow is requesting user input
+        elif event.type == "request_info":
+            # Request info event: Workflow is requesting user input
             if isinstance(event.data, HandoffAgentUserRequest):
                 _print_handoff_agent_user_request(event.data.agent_response)
-            requests.append(event)
+                requests.append(cast(WorkflowEvent[HandoffAgentUserRequest], event))
 
     return requests
 

python/samples/getting_started/orchestrations/handoff_simple.py

@@ -7,15 +7,12 @@ from agent_framework import (
     AgentResponse,
     ChatAgent,
     ChatMessage,
-    RequestInfoEvent,
     WorkflowEvent,
-    WorkflowOutputEvent,
     WorkflowRunState,
-    WorkflowStatusEvent,
     tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
-from agent_framework.orchestrations import HandoffAgentUserRequest, HandoffBuilder, HandoffSentEvent
+from agent_framework.orchestrations import HandoffAgentUserRequest, HandoffBuilder
 from azure.identity import AzureCliCredential
 
 """Sample: Simple handoff workflow.
@@ -102,35 +99,35 @@ def create_agents(chat_client: AzureOpenAIChatClient) -> tuple[ChatAgent, ChatAg
     return triage_agent, refund_agent, order_agent, return_agent
 
 
-def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
+def _handle_events(events: list[WorkflowEvent]) -> list[WorkflowEvent[HandoffAgentUserRequest]]:
     """Process workflow events and extract any pending user input requests.
 
     This function inspects each event type and:
     - Prints workflow status changes (IDLE, IDLE_WITH_PENDING_REQUESTS, etc.)
     - Displays final conversation snapshots when workflow completes
     - Prints user input request prompts
-    - Collects all RequestInfoEvent instances for response handling
+    - Collects all request_info events for response handling
 
     Args:
         events: List of WorkflowEvent to process
 
     Returns:
-        List of RequestInfoEvent representing pending user input requests
+        List of WorkflowEvent[HandoffAgentUserRequest] representing pending user input requests
     """
-    requests: list[RequestInfoEvent] = []
+    requests: list[WorkflowEvent[HandoffAgentUserRequest]] = []
 
     for event in events:
-        if isinstance(event, HandoffSentEvent):
-            # HandoffSentEvent: Indicates a handoff has been initiated
-            print(f"\n[Handoff from {event.source} to {event.target} initiated.]")
-        elif isinstance(event, WorkflowStatusEvent) and event.state in {
+        if event.type == "handoff_sent":
+            # handoff_sent event: Indicates a handoff has been initiated
+            print(f"\n[Handoff from {event.data.source} to {event.data.target} initiated.]")
+        elif event.type == "status" and event.state in {
             WorkflowRunState.IDLE,
             WorkflowRunState.IDLE_WITH_PENDING_REQUESTS,
         }:
-            # WorkflowStatusEvent: Indicates workflow state changes
-            print(f"\n[Workflow Status] {event.state.name}")
-        elif isinstance(event, WorkflowOutputEvent):
-            # WorkflowOutputEvent: Contains contents generated by the workflow
+            # Status event: Indicates workflow state changes
+            print(f"\n[Workflow Status] {event.state}")
+        elif event.type == "output":
+            # Output event: Contains contents generated by the workflow
             data = event.data
             if isinstance(data, AgentResponse):
                 for message in data.messages:
@@ -139,7 +136,7 @@ def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
                         continue
                     speaker = message.author_name or message.role
                     print(f"- {speaker}: {message.text}")
-            else:
+            elif event.type == "output":
                 # The output of the handoff workflow is a collection of chat messages from all participants
                 conversation = cast(list[ChatMessage], event.data)
                 if isinstance(conversation, list):
@@ -148,11 +145,9 @@ def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
                         speaker = message.author_name or message.role
                         print(f"- {speaker}: {message.text or [content.type for content in message.contents]}")
                     print("===================================")
-        elif isinstance(event, RequestInfoEvent):
-            # RequestInfoEvent: Workflow is requesting user input
-            if isinstance(event.data, HandoffAgentUserRequest):
-                _print_handoff_agent_user_request(event.data.agent_response)
-            requests.append(event)
+        elif event.type == "request_info" and isinstance(event.data, HandoffAgentUserRequest):
+            _print_handoff_agent_user_request(event.data.agent_response)
+            requests.append(cast(WorkflowEvent[HandoffAgentUserRequest], event))
 
     return requests
 

python/samples/getting_started/orchestrations/handoff_with_code_interpreter_file.py

@@ -6,7 +6,7 @@ Handoff Workflow with Code Interpreter File Generation Sample
 This sample demonstrates retrieving file IDs from code interpreter output
 in a handoff workflow context. A triage agent routes to a code specialist
 that generates a text file, and we verify the file_id is captured correctly
-from the streaming WorkflowOutputEvent events.
+from the streaming workflow events.
 
 Verifies GitHub issue #2718: files generated by code interpreter in
 HandoffBuilder workflows can be properly retrieved.
@@ -34,13 +34,9 @@ from agent_framework import (
     AgentResponseUpdate,
     ChatAgent,
     ChatMessage,
-    HandoffSentEvent,
     HostedCodeInterpreterTool,
-    RequestInfoEvent,
     WorkflowEvent,
-    WorkflowOutputEvent,
     WorkflowRunState,
-    WorkflowStatusEvent,
 )
 from agent_framework.orchestrations import HandoffAgentUserRequest, HandoffBuilder
 from azure.identity.aio import AzureCliCredential
@@ -54,30 +50,29 @@ async def _drain(stream: AsyncIterable[WorkflowEvent]) -> list[WorkflowEvent]:
     return [event async for event in stream]
 
 
-def _handle_events(events: list[WorkflowEvent]) -> tuple[list[RequestInfoEvent], list[str]]:
+def _handle_events(events: list[WorkflowEvent]) -> tuple[list[WorkflowEvent[HandoffAgentUserRequest]], list[str]]:
     """Process workflow events and extract file IDs and pending requests.
 
     Returns:
         Tuple of (pending_requests, file_ids_found)
     """
-    requests: list[RequestInfoEvent] = []
+
+    requests: list[WorkflowEvent[HandoffAgentUserRequest]] = []
     file_ids: list[str] = []
 
     for event in events:
-        if isinstance(event, HandoffSentEvent):
-            # HandoffSentEvent: Indicates a handoff has been initiated
-            print(f"\n[Handoff from {event.source} to {event.target} initiated.]")
-        elif isinstance(event, WorkflowStatusEvent) and event.state in {
+        if event.type == "handoff_sent":
+            print(f"\n[Handoff from {event.data.source} to {event.data.target} initiated.]")
+        elif event.type == "status" and event.state in {
             WorkflowRunState.IDLE,
             WorkflowRunState.IDLE_WITH_PENDING_REQUESTS,
         }:
-            # WorkflowStatusEvent: Indicates workflow state changes
-            print(f"\n[Workflow Status] {event.state.name}")
-        elif isinstance(event, WorkflowOutputEvent):
-            # WorkflowOutputEvent: Contains contents generated by the workflow
+            print(f"[status] {event.state.name}")
+        elif event.type == "request_info" and isinstance(event.data, HandoffAgentUserRequest):
+            requests.append(cast(WorkflowEvent[HandoffAgentUserRequest], event))
+        elif event.type == "output":
             data = event.data
             if isinstance(data, AgentResponseUpdate):
-                # AgentResponseUpdate: Intermediate output from an agent
                 for content in data.contents:
                     if content.type == "hosted_file":
                         file_ids.append(content.file_id)  # type: ignore
@@ -87,8 +82,7 @@ def _handle_events(events: list[WorkflowEvent]) -> tuple[list[RequestInfoEvent],
                             file_id = annotation["file_id"]  # type: ignore
                             file_ids.append(file_id)
                             print(f"[Found file annotation: file_id={file_id}]")
-            else:
-                # The output of the handoff workflow is a collection of chat messages from all participants
+            elif event.type == "output":
                 conversation = cast(list[ChatMessage], event.data)
                 if isinstance(conversation, list):
                     print("\n=== Final Conversation Snapshot ===")
@@ -96,9 +90,6 @@ def _handle_events(events: list[WorkflowEvent]) -> tuple[list[RequestInfoEvent],
                         speaker = message.author_name or message.role
                         print(f"- {speaker}: {message.text or [content.type for content in message.contents]}")
                     print("===================================")
-        elif isinstance(event, RequestInfoEvent):
-            # RequestInfoEvent: Workflow is requesting user input
-            requests.append(event)
 
     return requests, file_ids
 

python/samples/getting_started/orchestrations/magentic.py

@@ -9,12 +9,11 @@ from agent_framework import (
     AgentResponseUpdate,
     ChatAgent,
     ChatMessage,
-    GroupChatRequestSentEvent,
     HostedCodeInterpreterTool,
-    WorkflowOutputEvent,
+    WorkflowEvent,
 )
 from agent_framework.openai import OpenAIChatClient, OpenAIResponsesClient
-from agent_framework.orchestrations import MagenticBuilder, MagenticOrchestratorEvent, MagenticProgressLedger
+from agent_framework.orchestrations import GroupChatRequestSentEvent, MagenticBuilder, MagenticProgressLedger
 
 logging.basicConfig(level=logging.WARNING)
 logger = logging.getLogger(__name__)
@@ -85,7 +84,7 @@ async def main() -> None:
             max_reset_count=2,
         )
         # Enable intermediate outputs to observe the conversation as it unfolds
-        # Intermediate outputs will be emitted as WorkflowOutputEvent events
+        # Intermediate outputs will be emitted as WorkflowEvent events
         .with_intermediate_outputs()
         .build()
     )
@@ -104,41 +103,44 @@ async def main() -> None:
 
     # Keep track of the last executor to format output nicely in streaming mode
     last_response_id: str | None = None
+    output_event: WorkflowEvent | None = None
     async for event in workflow.run(task, stream=True):
-        if isinstance(event, MagenticOrchestratorEvent):
-            print(f"\n[Magentic Orchestrator Event] Type: {event.event_type.name}")
-            if isinstance(event.data, ChatMessage):
-                print(f"Please review the plan:\n{event.data.text}")
-            elif isinstance(event.data, MagenticProgressLedger):
-                print(f"Please review progress ledger:\n{json.dumps(event.data.to_dict(), indent=2)}")
+        if event.type == "output" and isinstance(event.data, AgentResponseUpdate):
+            response_id = event.data.response_id
+            if response_id != last_response_id:
+                if last_response_id is not None:
+                    print("\n")
+                print(f"- {event.executor_id}:", end=" ", flush=True)
+                last_response_id = response_id
+            print(event.data, end="", flush=True)
+
+        elif event.type == "magentic_orchestrator":
+            print(f"\n[Magentic Orchestrator Event] Type: {event.data.event_type.name}")
+            if isinstance(event.data.content, ChatMessage):
+                print(f"Please review the plan:\n{event.data.content.text}")
+            elif isinstance(event.data.content, MagenticProgressLedger):
+                print(f"Please review progress ledger:\n{json.dumps(event.data.content.to_dict(), indent=2)}")
             else:
-                print(f"Unknown data type in MagenticOrchestratorEvent: {type(event.data)}")
+                print(f"Unknown data type in MagenticOrchestratorEvent: {type(event.data.content)}")
 
             # Block to allow user to read the plan/progress before continuing
             # Note: this is for demonstration only and is not the recommended way to handle human interaction.
             # Please refer to `with_plan_review` for proper human interaction during planning phases.
             await asyncio.get_event_loop().run_in_executor(None, input, "Press Enter to continue...")
 
-        elif isinstance(event, GroupChatRequestSentEvent):
-            print(f"\n[REQUEST SENT ({event.round_index})] to agent: {event.participant_name}")
+        elif event.type == "group_chat" and isinstance(event.data, GroupChatRequestSentEvent):
+            print(f"\n[REQUEST SENT ({event.data.round_index})] to agent: {event.data.participant_name}")
 
-        elif isinstance(event, WorkflowOutputEvent):
-            data = event.data
-            if isinstance(data, AgentResponseUpdate):
-                response_id = data.response_id
-                if response_id != last_response_id:
-                    if last_response_id is not None:
-                        print("\n")
-                    print(f"- {event.executor_id}:", end=" ", flush=True)
-                    last_response_id = response_id
-                print(event.data, end="", flush=True)
-            else:
-                # The output of the magentic workflow is a collection of chat messages from all participants
-                outputs = cast(list[ChatMessage], event.data)
-                print("\n" + "=" * 80)
-                print("\nFinal Conversation Transcript:\n")
-                for message in outputs:
-                    print(f"{message.author_name or message.role}: {message.text}\n")
+        elif event.type == "output":
+            output_event = event
+
+    if output_event:
+        # The output of the magentic workflow is a collection of chat messages from all participants
+        outputs = cast(list[ChatMessage], output_event.data)
+        print("\n" + "=" * 80)
+        print("\nFinal Conversation Transcript:\n")
+        for message in outputs:
+            print(f"{message.author_name or message.role}: {message.text}\n")
 
 
 if __name__ == "__main__":

python/samples/getting_started/orchestrations/magentic_checkpoint.py

@@ -9,11 +9,9 @@ from agent_framework import (
     ChatAgent,
     ChatMessage,
     FileCheckpointStorage,
-    RequestInfoEvent,
     WorkflowCheckpoint,
-    WorkflowOutputEvent,
+    WorkflowEvent,
     WorkflowRunState,
-    WorkflowStatusEvent,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from agent_framework.orchestrations import MagenticBuilder, MagenticPlanReviewRequest
@@ -105,16 +103,16 @@ async def main() -> None:
     print("\n=== Stage 1: run until plan review request (checkpointing active) ===")
     workflow = build_workflow(checkpoint_storage)
 
-    # Run the workflow until the first RequestInfoEvent is surfaced. The event carries the
+    # Run the workflow until the first  is surfaced. The event carries the
     # request_id we must reuse on resume. In a real system this is where the UI would present
     # the plan for human review.
     plan_review_request: MagenticPlanReviewRequest | None = None
     async for event in workflow.run(TASK, stream=True):
-        if isinstance(event, RequestInfoEvent) and event.request_type is MagenticPlanReviewRequest:
+        if event.type == "request_info" and event.request_type is MagenticPlanReviewRequest:
             plan_review_request = event.data
             print(f"Captured plan review request: {event.request_id}")
 
-        if isinstance(event, WorkflowStatusEvent) and event.state is WorkflowRunState.IDLE_WITH_PENDING_REQUESTS:
+        if event.type == "status" and event.state is WorkflowRunState.IDLE_WITH_PENDING_REQUESTS:
             break
 
     if plan_review_request is None:
@@ -147,9 +145,9 @@ async def main() -> None:
     approval = plan_review_request.approve()
 
     # Resume execution and capture the re-emitted plan review request.
-    request_info_event: RequestInfoEvent | None = None
+    request_info_event: WorkflowEvent | None = None
     async for event in resumed_workflow.run(checkpoint_id=resume_checkpoint.checkpoint_id, stream=True):
-        if isinstance(event, RequestInfoEvent) and isinstance(event.data, MagenticPlanReviewRequest):
+        if event.type == "request_info" and isinstance(event.data, MagenticPlanReviewRequest):
             request_info_event = event
 
     if request_info_event is None:
@@ -158,9 +156,9 @@ async def main() -> None:
     print(f"Resumed plan review request: {request_info_event.request_id}")
 
     # Supply the approval and continue to run to completion.
-    final_event: WorkflowOutputEvent | None = None
+    final_event: WorkflowEvent | None = None
     async for event in resumed_workflow.send_responses_streaming({request_info_event.request_id: approval}):
-        if isinstance(event, WorkflowOutputEvent):
+        if event.type == "output":
             final_event = event
 
     if final_event is None:
@@ -218,12 +216,12 @@ async def main() -> None:
     if pending_messages == 0:
         print("Checkpoint has no pending messages; no additional work expected on resume.")
 
-    final_event_post: WorkflowOutputEvent | None = None
+    final_event_post: WorkflowEvent | None = None
     post_emitted_events = False
     post_plan_workflow = build_workflow(checkpoint_storage)
     async for event in post_plan_workflow.run(checkpoint_id=post_plan_checkpoint.checkpoint_id, stream=True):
         post_emitted_events = True
-        if isinstance(event, WorkflowOutputEvent):
+        if event.type == "output":
             final_event_post = event
 
     if final_event_post is None:

python/samples/getting_started/orchestrations/magentic_human_plan_review.py

@@ -9,9 +9,7 @@ from agent_framework import (
     AgentResponseUpdate,
     ChatAgent,
     ChatMessage,
-    RequestInfoEvent,
     WorkflowEvent,
-    WorkflowOutputEvent,
 )
 from agent_framework.openai import OpenAIChatClient
 from agent_framework.orchestrations import MagenticBuilder, MagenticPlanReviewRequest, MagenticPlanReviewResponse
@@ -46,10 +44,10 @@ async def process_event_stream(stream: AsyncIterable[WorkflowEvent]) -> dict[str
 
     requests: dict[str, MagenticPlanReviewRequest] = {}
     async for event in stream:
-        if isinstance(event, RequestInfoEvent) and event.request_type is MagenticPlanReviewRequest:
+        if event.type == "request_info" and event.request_type is MagenticPlanReviewRequest:
             requests[event.request_id] = cast(MagenticPlanReviewRequest, event.data)
 
-        if isinstance(event, WorkflowOutputEvent):
+        if event.type == "output":
             data = event.data
             if isinstance(data, AgentResponseUpdate):
                 rid = data.response_id
@@ -68,7 +66,7 @@ async def process_event_stream(stream: AsyncIterable[WorkflowEvent]) -> dict[str
                 # To make the type checker happy, we cast event.data to the expected type
                 outputs = cast(list[ChatMessage], event.data)
                 for msg in outputs:
-                    speaker = msg.author_name or msg.role.value
+                    speaker = msg.author_name or msg.role
                     print(f"[{speaker}]: {msg.text}")
 
     responses: dict[str, MagenticPlanReviewResponse] = {}
@@ -129,7 +127,7 @@ async def main() -> None:
         # Request human input for plan review
         .with_plan_review()
         # Enable intermediate outputs to observe the conversation as it unfolds
-        # Intermediate outputs will be emitted as WorkflowOutputEvent events
+        # Intermediate outputs will be emitted as WorkflowEvent with type "output"
         .with_intermediate_outputs()
         .build()
     )

python/samples/getting_started/orchestrations/sequential_agents.py

@@ -3,7 +3,7 @@
 import asyncio
 from typing import cast
 
-from agent_framework import ChatMessage, WorkflowOutputEvent
+from agent_framework import ChatMessage
 from agent_framework.azure import AzureOpenAIChatClient
 from agent_framework.orchestrations import SequentialBuilder
 from azure.identity import AzureCliCredential
@@ -48,7 +48,7 @@ async def main() -> None:
     # 3) Run and collect outputs
     outputs: list[list[ChatMessage]] = []
     async for event in workflow.run("Write a tagline for a budget-friendly eBike.", stream=True):
-        if isinstance(event, WorkflowOutputEvent):
+        if event.type == "output":
             outputs.append(cast(list[ChatMessage], event.data))
 
     if outputs: