Python: name changes executed (#607)

* name changes executed

* updated adr to accepted

* renamed openai base config

* renamed openai config to mixin

* added renames in user docs

* reverted mcperror

* fix tests

* remove sse from tests

python/samples/getting_started/workflow/step_01_basic_workflow_sequential.py

@@ -58,7 +58,7 @@ async def main():
 
     # Step 3: Run the workflow with an initial message.
     completion_event = None
-    async for event in workflow.run_streaming("hello world"):
+    async for event in workflow.run_stream("hello world"):
         print(f"Event: {event}")
         if isinstance(event, WorkflowCompletedEvent):
             # The WorkflowCompletedEvent contains the final result.

python/samples/getting_started/workflow/step_02_basic_workflow_condition.py

@@ -110,7 +110,7 @@ async def main():
     )
 
     # Step 3: Run the workflow with an input message.
-    async for event in workflow.run_streaming("This is a spam."):
+    async for event in workflow.run_stream("This is a spam."):
         print(f"Event: {event}")
 
 

python/samples/getting_started/workflow/step_03_basic_workflow_loop.py

@@ -105,7 +105,7 @@ async def main():
 
     # Step 3: Run the workflow and print the events.
     iterations = 0
-    async for event in workflow.run_streaming(NumberSignal.INIT):
+    async for event in workflow.run_stream(NumberSignal.INIT):
         if isinstance(event, ExecutorCompletedEvent) and event.executor_id == guess_number_executor.id:
             iterations += 1
         print(f"Event: {event}")

python/samples/getting_started/workflow/step_04_basic_group_chat.py

@@ -2,7 +2,7 @@
 
 import asyncio
 
-from agent_framework import ChatMessage, ChatRole
+from agent_framework import ChatMessage, Role
 from agent_framework.azure import AzureChatClient
 from agent_framework.workflow import (
     AgentExecutor,
@@ -36,7 +36,7 @@ class RoundRobinGroupChatManager(Executor):
     @handler
     async def start(self, task: str, ctx: WorkflowContext[AgentExecutorRequest]) -> None:
         """Execute the task by sending messages to the next executor in the round-robin sequence."""
-        initial_message = ChatMessage(ChatRole.USER, text=task)
+        initial_message = ChatMessage(Role.USER, text=task)
 
         # Send the initial message to the members
         await asyncio.gather(*[
@@ -132,7 +132,7 @@ async def main():
 
     # Step 3: Run the workflow with an initial message.
     completion_event = None
-    async for event in workflow.run_streaming(
+    async for event in workflow.run_stream(
         "Create a slogan for a new electric SUV that is affordable and fun to drive."
     ):
         if isinstance(event, AgentRunEvent):

python/samples/getting_started/workflow/step_05_basic_group_chat_with_hil.py

@@ -2,7 +2,7 @@
 
 import asyncio
 
-from agent_framework import ChatMessage, ChatRole
+from agent_framework import ChatMessage, Role
 from agent_framework.azure import AzureChatClient
 from agent_framework.workflow import (
     AgentExecutor,
@@ -39,7 +39,7 @@ class CriticGroupChatManager(Executor):
     @handler
     async def start(self, task: str, ctx: WorkflowContext[AgentExecutorRequest]) -> None:
         """Handler that starts the group chat with an initial task."""
-        initial_message = ChatMessage(ChatRole.USER, text=task)
+        initial_message = ChatMessage(Role.USER, text=task)
 
         # Send the initial message to the members
         await asyncio.gather(*[
@@ -129,7 +129,7 @@ class CriticGroupChatManager(Executor):
             return False
 
         last_message = self._chat_history[-1]
-        return bool(last_message.role == ChatRole.USER and "approve" in last_message.text.lower())
+        return bool(last_message.role == Role.USER and "approve" in last_message.text.lower())
 
     def _should_request_info(self) -> bool:
         """Determine if the group chat should request HIL based on the last message."""
@@ -137,7 +137,7 @@ class CriticGroupChatManager(Executor):
             return True
 
         last_message = self._chat_history[-1]
-        return last_message.role == ChatRole.ASSISTANT
+        return last_message.role == Role.ASSISTANT
 
     def _get_next_member(self) -> str:
         """Get the next member in the round-robin sequence."""
@@ -200,12 +200,12 @@ async def main():
         # Depending on whether we have a RequestInfoEvent event, we either
         # run the workflow normally or send the message to the HIL executor.
         if not request_info_event:
-            response_stream = workflow.run_streaming(
+            response_stream = workflow.run_stream(
                 "Create a slogan for a new electric SUV that is affordable and fun to drive."
             )
         else:
             response_stream = workflow.send_responses_streaming({
-                request_info_event.request_id: [ChatMessage(ChatRole.USER, text=user_input)]
+                request_info_event.request_id: [ChatMessage(Role.USER, text=user_input)]
             })
             request_info_event = None
 

python/samples/getting_started/workflow/step_06_map_reduce_and_visualization.py

@@ -314,7 +314,7 @@ async def main():
 
     # Step 4: Run the workflow with the raw text as input.
     completion_event = None
-    async for event in workflow.run_streaming(raw_text):
+    async for event in workflow.run_stream(raw_text):
         print(f"Event: {event}")
         if isinstance(event, WorkflowCompletedEvent):
             completion_event = event

python/samples/getting_started/workflow/step_07_checkpoint_resume.py

@@ -135,7 +135,7 @@ async def main():
     )
 
     print("Running workflow with initial message...")
-    async for event in workflow.run_streaming(message="hello world"):
+    async for event in workflow.run_stream(message="hello world"):
         print(f"Event: {event}")
 
     # Inspect checkpoints
@@ -179,7 +179,7 @@ async def main():
     )
 
     print(f"\nResuming from checkpoint: {checkpoint_id}")
-    async for event in new_workflow.run_streaming_from_checkpoint(checkpoint_id, checkpoint_storage=checkpoint_storage):
+    async for event in new_workflow.run_stream_from_checkpoint(checkpoint_id, checkpoint_storage=checkpoint_storage):
         print(f"Resumed Event: {event}")
 
     """

python/samples/getting_started/workflow/step_08a_magentic_workflow.py

@@ -3,7 +3,7 @@
 import asyncio
 import logging
 
-from agent_framework import ChatClientAgent, HostedCodeInterpreterTool
+from agent_framework import ChatAgent, HostedCodeInterpreterTool
 from agent_framework.openai import OpenAIChatClient, OpenAIResponsesClient
 from agent_framework_workflow import (
     MagenticAgentDeltaEvent,
@@ -25,9 +25,9 @@ Magentic Workflow (multi-agent) sample.
 This sample shows how to orchestrate multiple agents using the
 MagenticBuilder:
 
-- ResearcherAgent (ChatClientAgent backed by an OpenAI chat client) for
+- ResearcherAgent (ChatAgent backed by an OpenAI chat client) for
     finding information.
-- CoderAgent (ChatClientAgent backed by OpenAI Assistants with the hosted
+- CoderAgent (ChatAgent backed by OpenAI Assistants with the hosted
     code interpreter tool) for analysis and computation.
 
 The workflow is configured with:
@@ -42,7 +42,7 @@ events to the console, and prints the final aggregated answer at completion.
 
 
 async def main() -> None:
-    researcher_agent = ChatClientAgent(
+    researcher_agent = ChatAgent(
         name="ResearcherAgent",
         description="Specialist in research and information gathering",
         instructions=(
@@ -50,11 +50,11 @@ async def main() -> None:
         ),
         # This agent requires the gpt-4o-search-preview model to perform web searches.
         # Feel free to explore with other agents that support web search, for example,
-        # the `OpenAIResponseAgent` or `AzureAIAgent` with bing grounding.
+        # the `OpenAIResponseAgent` or `AzureAgentProtocol` with bing grounding.
         chat_client=OpenAIChatClient(ai_model_id="gpt-4o-search-preview"),
     )
 
-    coder_agent = ChatClientAgent(
+    coder_agent = ChatAgent(
         name="CoderAgent",
         description="A helpful assistant that writes and executes code to process and analyze data.",
         instructions="You solve questions using code. Please provide detailed analysis and computation process.",
@@ -129,7 +129,7 @@ async def main() -> None:
 
     try:
         completion_event = None
-        async for event in workflow.run_streaming(task):
+        async for event in workflow.run_stream(task):
             print(f"Event: {event}")
 
             if isinstance(event, WorkflowCompletedEvent):

python/samples/getting_started/workflow/step_08b_magentic_human_plan_update.py

@@ -4,7 +4,7 @@ import asyncio
 import logging
 from typing import cast
 
-from agent_framework import ChatClientAgent, HostedCodeInterpreterTool
+from agent_framework import ChatAgent, HostedCodeInterpreterTool
 from agent_framework.openai import OpenAIChatClient, OpenAIResponsesClient
 from agent_framework_workflow import (
     MagenticAgentDeltaEvent,
@@ -30,8 +30,8 @@ Magentic workflow with human-in-the-loop plan review and update.
 This sample builds a Magentic workflow with two cooperating agents and enables
 plan review so a human can approve or revise the plan before execution:
 
-- researcher: ChatClientAgent backed by OpenAIChatClient (web/search-capable model)
-- coder: ChatClientAgent backed by OpenAIAssistantsClient with the Hosted Code Interpreter tool
+- researcher: ChatAgent backed by OpenAIChatClient (web/search-capable model)
+- coder: ChatAgent backed by OpenAIAssistantsClient with the Hosted Code Interpreter tool
 
 Key behaviors demonstrated:
 - with_plan_review(): requests a PlanReviewRequest before coordination begins
@@ -46,7 +46,7 @@ clients can run. You can swap clients/models as needed.
 
 
 async def main() -> None:
-    researcher_agent = ChatClientAgent(
+    researcher_agent = ChatAgent(
         name="ResearcherAgent",
         description="Specialist in research and information gathering",
         instructions=(
@@ -54,11 +54,11 @@ async def main() -> None:
         ),
         # This agent requires the gpt-4o-search-preview model to perform web searches.
         # Feel free to explore with other agents that support web search, for example,
-        # the `OpenAIResponseAgent` or `AzureAIAgent` with bing grounding.
+        # the `OpenAIResponseAgent` or `AzureAgentProtocol` with bing grounding.
         chat_client=OpenAIChatClient(ai_model_id="gpt-4o-search-preview"),
     )
 
-    coder_agent = ChatClientAgent(
+    coder_agent = ChatAgent(
         name="CoderAgent",
         description="A helpful assistant that writes and executes code to process and analyze data.",
         instructions="You solve questions using code. Please provide detailed analysis and computation process.",
@@ -140,7 +140,7 @@ async def main() -> None:
         while True:
             # Phase 1: run until either completion or a HIL request
             if pending_request is None:
-                async for event in workflow.run_streaming(task):
+                async for event in workflow.run_stream(task):
                     print(f"Event: {event}")
 
                     if isinstance(event, WorkflowCompletedEvent):

python/samples/getting_started/workflow/step_10a_workflow_agent_reflection_pattern.py

@@ -4,7 +4,7 @@ import asyncio
 from dataclasses import dataclass
 from uuid import uuid4
 
-from agent_framework import AgentRunResponseUpdate, AIContents, ChatClient, ChatMessage, ChatRole
+from agent_framework import AgentRunResponseUpdate, ChatClientProtocol, ChatMessage, Contents, Role
 from agent_framework.openai import OpenAIChatClient
 from agent_framework.workflow import AgentRunUpdateEvent, Executor, WorkflowBuilder, WorkflowContext, handler
 from pydantic import BaseModel
@@ -51,7 +51,7 @@ class ReviewResponse:
 class Reviewer(Executor):
     """An executor that reviews messages and provides feedback."""
 
-    def __init__(self, chat_client: ChatClient) -> None:
+    def __init__(self, chat_client: ChatClientProtocol) -> None:
         super().__init__()
         self._chat_client = chat_client
 
@@ -69,7 +69,7 @@ class Reviewer(Executor):
         # Define the system prompt.
         messages = [
             ChatMessage(
-                role=ChatRole.SYSTEM,
+                role=Role.SYSTEM,
                 text="You are a reviewer for an AI agent, please provide feedback on the "
                 "following exchange between a user and the AI agent, "
                 "and indicate if the agent's responses are approved or not.\n"
@@ -91,7 +91,7 @@ class Reviewer(Executor):
 
         # Add add one more instruction for the assistant to follow.
         messages.append(
-            ChatMessage(role=ChatRole.USER, text="Please provide a review of the agent's responses to the user.")
+            ChatMessage(role=Role.USER, text="Please provide a review of the agent's responses to the user.")
         )
 
         print("🔍 Reviewer: Sending review request to LLM...")
@@ -113,7 +113,7 @@ class Reviewer(Executor):
 class Worker(Executor):
     """An executor that performs tasks for the user."""
 
-    def __init__(self, chat_client: ChatClient) -> None:
+    def __init__(self, chat_client: ChatClientProtocol) -> None:
         super().__init__()
         self._chat_client = chat_client
         self._pending_requests: dict[str, tuple[ReviewRequest, list[ChatMessage]]] = {}
@@ -124,7 +124,7 @@ class Worker(Executor):
 
         # Handle user messages and prepare a review request for the reviewer.
         # Define the system prompt.
-        messages = [ChatMessage(role=ChatRole.SYSTEM, text="You are a helpful assistant.")]
+        messages = [ChatMessage(role=Role.SYSTEM, text="You are a helpful assistant.")]
 
         # Add user messages.
         messages.extend(user_messages)
@@ -163,14 +163,14 @@ class Worker(Executor):
             print("✅ Worker: Response approved! Emitting to external consumer...")
             # If approved, emit the agent run response update to the workflow's
             # external consumer.
-            contents: list[AIContents] = []
+            contents: list[Contents] = []
             for message in request.agent_messages:
                 contents.extend(message.contents)
             # Emitting an AgentRunUpdateEvent in a workflow wrapped by a WorkflowAgent
             # will send the AgentRunResponseUpdate to the WorkflowAgent's
             # event stream.
             await ctx.add_event(
-                AgentRunUpdateEvent(self.id, data=AgentRunResponseUpdate(contents=contents, role=ChatRole.ASSISTANT))
+                AgentRunUpdateEvent(self.id, data=AgentRunResponseUpdate(contents=contents, role=Role.ASSISTANT))
             )
             return
 
@@ -178,12 +178,12 @@ class Worker(Executor):
         print("🔧 Worker: Incorporating feedback and regenerating response...")
 
         # Construct new messages with feedback.
-        messages.append(ChatMessage(role=ChatRole.SYSTEM, text=review.feedback))
+        messages.append(ChatMessage(role=Role.SYSTEM, text=review.feedback))
 
         # Add additional instruction to address the feedback.
         messages.append(
             ChatMessage(
-                role=ChatRole.SYSTEM,
+                role=Role.SYSTEM,
                 text="Please incorporate the feedback above, and provide a response to user's next message.",
             )
         )
@@ -234,7 +234,7 @@ async def main() -> None:
     print("-" * 50)
 
     # Run the agent and stream events.
-    async for event in agent.run_streaming(
+    async for event in agent.run_stream(
         "Write code for parallel reading 1 million files on disk and write to a sorted output file."
     ):
         print(f"📤 Agent Response: {event}")

python/samples/getting_started/workflow/step_10b_workflow_agent_human_in_the_loop.py

@@ -5,9 +5,9 @@ from dataclasses import dataclass
 
 from agent_framework import (
     ChatMessage,
-    ChatRole,
     FunctionCallContent,
     FunctionResultContent,
+    Role,
 )
 from agent_framework.openai import OpenAIChatClient
 from agent_framework.workflow import (
@@ -133,7 +133,7 @@ async def main() -> None:
             result=human_response,
         )
         # Send the human review result back to the agent.
-        response = await agent.run(ChatMessage(role=ChatRole.TOOL, contents=[human_review_function_result]))
+        response = await agent.run(ChatMessage(role=Role.TOOL, contents=[human_review_function_result]))
         print(f"📤 Agent Response: {response.messages[-1].text}")
 
     print("=" * 50)