Python: (samples): adopt AzureOpenAIResponsesClient, reorganize orchestration examples, and fix workflow/orchestration bugs (#3873)

* adopt AzureOpenAIResponsesClient, reorganize orchestration examples, and fix workflow/orchestration bugs

* Updates

* add comment

python/samples/getting_started/workflows/declarative/customer_support/main.py

@@ -23,10 +23,11 @@ The workflow:
 import asyncio
 import json
 import logging
+import os
 import uuid
 from pathlib import Path
 
-from agent_framework.azure import AzureOpenAIChatClient
+from agent_framework.azure import AzureOpenAIResponsesClient
 from agent_framework.declarative import (
     AgentExternalInputRequest,
     AgentExternalInputResponse,
@@ -164,7 +165,11 @@ async def main() -> None:
     plugin = TicketingPlugin()
 
     # Create Azure OpenAI client
-    client = AzureOpenAIChatClient(credential=AzureCliCredential())
+    client = AzureOpenAIResponsesClient(
+        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
+        deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=AzureCliCredential(),
+    )
 
     # Create agents with structured outputs
     self_service_agent = client.as_agent(
@@ -260,7 +265,9 @@ async def main() -> None:
         async for event in stream:
             if event.type == "output":
                 data = event.data
-                source_id = getattr(event, "source_executor_id", "")
+                # source_executor_id is only available on request_info events.
+                # For output events, use executor_id to identify the emitting node.
+                source_id = event.executor_id or ""
 
                 # Check if this is a SendActivity output (activity text from log_ticket, log_route, etc.)
                 if "log_" in source_id.lower():

python/samples/getting_started/workflows/declarative/deep_research/main.py

@@ -22,9 +22,10 @@ Usage:
 """
 
 import asyncio
+import os
 from pathlib import Path
 
-from agent_framework.azure import AzureOpenAIChatClient
+from agent_framework.azure import AzureOpenAIResponsesClient
 from agent_framework.declarative import WorkflowFactory
 from azure.identity import AzureCliCredential
 from pydantic import BaseModel, Field
@@ -122,7 +123,11 @@ class ManagerResponse(BaseModel):
 async def main() -> None:
     """Run the deep research workflow."""
     # Create Azure OpenAI client
-    client = AzureOpenAIChatClient(credential=AzureCliCredential())
+    client = AzureOpenAIResponsesClient(
+        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
+        deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=AzureCliCredential(),
+    )
 
     # Create agents
     research_agent = client.as_agent(

python/samples/getting_started/workflows/declarative/function_tools/main.py

@@ -6,12 +6,13 @@ function tools assigned. Exits the loop when the user enters "exit".
 """
 
 import asyncio
+import os
 from dataclasses import dataclass
 from pathlib import Path
 from typing import Annotated, Any
 
 from agent_framework import FileCheckpointStorage, tool
-from agent_framework.azure import AzureOpenAIChatClient
+from agent_framework.azure import AzureOpenAIResponsesClient
 from agent_framework_declarative import ExternalInputRequest, ExternalInputResponse, WorkflowFactory
 from azure.identity import AzureCliCredential
 from pydantic import Field
@@ -62,7 +63,11 @@ def get_item_price(name: Annotated[str, Field(description="Menu item name")]) ->
 
 async def main():
     # Create agent with tools
-    client = AzureOpenAIChatClient(credential=AzureCliCredential())
+    client = AzureOpenAIResponsesClient(
+        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
+        deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=AzureCliCredential(),
+    )
     menu_agent = client.as_agent(
         name="MenuAgent",
         instructions="Answer questions about menu items, specials, and prices.",

python/samples/getting_started/workflows/declarative/marketing/main.py

@@ -13,9 +13,10 @@ Demonstrates sequential multi-agent pipeline:
 """
 
 import asyncio
+import os
 from pathlib import Path
 
-from agent_framework.azure import AzureOpenAIChatClient
+from agent_framework.azure import AzureOpenAIResponsesClient
 from agent_framework.declarative import WorkflowFactory
 from azure.identity import AzureCliCredential
 
@@ -49,7 +50,11 @@ Return the final polished version."""
 
 async def main() -> None:
     """Run the marketing workflow with real Azure AI agents."""
-    client = AzureOpenAIChatClient(credential=AzureCliCredential())
+    client = AzureOpenAIResponsesClient(
+        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
+        deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=AzureCliCredential(),
+    )
 
     analyst_agent = client.as_agent(
         name="AnalystAgent",

python/samples/getting_started/workflows/declarative/student_teacher/main.py

@@ -15,14 +15,15 @@ The workflow loops until the teacher gives congratulations or max turns reached.
 Prerequisites:
     - Azure OpenAI deployment with chat completion capability
     - Environment variables:
-        AZURE_OPENAI_ENDPOINT: Your Azure OpenAI endpoint
-        AZURE_OPENAI_DEPLOYMENT_NAME: Your deployment name (optional, defaults to gpt-4o)
+        AZURE_AI_PROJECT_ENDPOINT: Your Azure AI Foundry Agent Service (V2) project endpoint
+        AZURE_AI_MODEL_DEPLOYMENT_NAME: Your model deployment name
 """
 
 import asyncio
+import os
 from pathlib import Path
 
-from agent_framework.azure import AzureOpenAIChatClient
+from agent_framework.azure import AzureOpenAIResponsesClient
 from agent_framework.declarative import WorkflowFactory
 from azure.identity import AzureCliCredential
 
@@ -51,7 +52,11 @@ Focus on building understanding, not just getting the right answer."""
 async def main() -> None:
     """Run the student-teacher workflow with real Azure AI agents."""
     # Create chat client
-    client = AzureOpenAIChatClient(credential=AzureCliCredential())
+    client = AzureOpenAIResponsesClient(
+        project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
+        deployment_name=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=AzureCliCredential(),
+    )
 
     # Create student and teacher agents
     student_agent = client.as_agent(