Python: [BREAKING] Types API Review improvements (#3647)

* Replace Role and FinishReason classes with NewType + Literal - Remove EnumLike metaclass from _types.py - Replace Role class with NewType('Role', str) + RoleLiteral - Replace FinishReason class with NewType('FinishReason', str) + FinishReasonLiteral - Update all usages across codebase to use string literals - Remove .value access patterns (direct string comparison now works) - Add backward compatibility for legacy dict serialization format - Update tests to reflect new string-based types Addresses #3591, #3615 * Simplify ChatResponse and AgentResponse type hints (#3592) - Remove overloads from ChatResponse.__init__ - Remove text parameter from ChatResponse.__init__ - Remove | dict[str, Any] from finish_reason and usage_details params - Remove **kwargs from AgentResponse.__init__ - Both now accept ChatMessage | Sequence[ChatMessage] | None for messages - Update docstrings and examples to reflect changes - Fix tests that were using removed kwargs - Fix Role type hint usage in ag-ui utils * Remove text parameter from ChatResponseUpdate and AgentResponseUpdate (#3597) - Remove text parameter from ChatResponseUpdate.__init__ - Remove text parameter from AgentResponseUpdate.__init__ - Remove **kwargs from both update classes - Simplify contents parameter type to Sequence[Content] | None - Update all usages to use contents=[Content.from_text(...)] pattern - Fix imports in test files - Update docstrings and examples * Rename from_chat_response_updates to from_updates (#3593) - ChatResponse.from_chat_response_updates → ChatResponse.from_updates - ChatResponse.from_chat_response_generator → ChatResponse.from_update_generator - AgentResponse.from_agent_run_response_updates → AgentResponse.from_updates * Remove try_parse_value method from ChatResponse and AgentResponse (#3595) - Remove try_parse_value method from ChatResponse - Remove try_parse_value method from AgentResponse - Remove try_parse_value calls from from_updates and from_update_generator methods - Update samples to use try/except with response.value instead - Update tests to use response.value pattern - Users should now use response.value with try/except for safe parsing * Add agent_id to AgentResponse and clarify author_name documentation (#3596) - Add agent_id parameter to AgentResponse class - Document that author_name is on ChatMessage objects, not responses - Update ChatResponse docstring with author_name note - Update AgentResponse docstring with author_name note * Simplify ChatMessage.__init__ signature (#3618) - Make contents a positional argument accepting Sequence[Content | str] - Auto-convert strings in contents to TextContent - Remove overloads, keep text kwarg for backward compatibility with serialization - Update _parse_content_list to handle string items - Update all usages across codebase to use new format: ChatMessage("role", ["text"]) * Allow Content as input on run and get_response - Update prepare_messages and normalize_messages to accept Content - Update type signatures in _agents.py and _clients.py - Add tests for Content input handling * Fix ChatMessage usage across packages and samples Update all remaining ChatMessage(role=..., text=...) to use new ChatMessage('role', ['text']) signature. * Fix Role string usage and response format parsing - Fix redis provider: remove .value access on string literals - Fix durabletask ensure_response_format: set _response_format before accessing .value * Fix ollama .value and ai_model_id issues, handle None in content list - Fix ollama _chat_client: remove .value on string literals - Fix ollama _chat_client: rename ai_model_id to model_id - Fix _parse_content_list: skip None values gracefully * Fix A2AAgent type signature to include Content * Fix Role/FinishReason NewType dict annotations and improve test coverage to 95% * Fix mypy errors for Role/FinishReason NewType usage * Fix Role.TOOL and Role.ASSISTANT usage in _orchestrator_helpers.py * Fix Role NewType usage in durabletask _models.py
2026-06-16 21:04:09 +08:00 · 2026-02-04 11:13:23 +01:00
parent ef798629e5
commit 838a7fd61d
341 changed files with 3766 additions and 3228 deletions
@@ -8,7 +8,6 @@ from agent_framework import (
    WorkflowContext,
    executor,
    handler,
-    tool,
 )
 from typing_extensions import Never

@@ -13,7 +13,6 @@ from agent_framework import (
    WorkflowRunState,
    WorkflowStatusEvent,
    handler,
-    tool,
 )
 from agent_framework._workflows._events import WorkflowOutputEvent
 from agent_framework.azure import AzureOpenAIChatClient
@@ -123,7 +122,7 @@ async def main():
    # Run the workflow with the user's initial message and stream events as they occur.
    # This surfaces executor events, workflow outputs, run-state changes, and errors.
    async for event in workflow.run_stream(
-        ChatMessage(role="user", text="Create a slogan for a new electric SUV that is affordable and fun to drive.")
+        ChatMessage("user", ["Create a slogan for a new electric SUV that is affordable and fun to drive."])
    ):
        if isinstance(event, WorkflowStatusEvent):
            prefix = f"State ({event.origin.value}): "
@@ -11,7 +11,6 @@ from agent_framework import (
    WorkflowOutputEvent,
    executor,
    handler,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -9,12 +9,10 @@ from agent_framework import (
    AgentResponse,
    AgentRunUpdateEvent,
    ChatMessage,
-    Role,
    WorkflowBuilder,
    WorkflowContext,
    WorkflowOutputEvent,
    executor,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -72,7 +70,7 @@ async def enrich_with_references(
 ) -> None:
    """Inject a follow-up user instruction that adds an external note for the next agent."""
    conversation = list(draft.full_conversation or draft.agent_response.messages)
-    original_prompt = next((message.text for message in conversation if message.role == Role.USER), "")
+    original_prompt = next((message.text for message in conversation if message.role == "user"), "")
    external_note = _lookup_external_note(original_prompt) or (
        "No additional references were found. Please refine the previous assistant response for clarity."
    )
@@ -82,7 +80,7 @@ async def enrich_with_references(
        f"{external_note}\n\n"
        "Please update the prior assistant answer so it weaves this note into the guidance."
    )
-    conversation.append(ChatMessage(role=Role.USER, text=follow_up))
+    conversation.append(ChatMessage("user", [follow_up]))

    await ctx.send_message(AgentExecutorRequest(messages=conversation))

@@ -16,7 +16,6 @@ from agent_framework import (
    FunctionCallContent,
    FunctionResultContent,
    RequestInfoEvent,
-    Role,
    WorkflowBuilder,
    WorkflowContext,
    WorkflowOutputEvent,
@@ -50,9 +49,9 @@ Prerequisites:
 - Authentication via azure-identity. Run `az login` before executing.
 """

+
 # NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
@tool(approval_mode="never_require")
-
 def fetch_product_brief(
    product_name: Annotated[str, Field(description="Product name to look up.")],
 ) -> str:
@@ -68,8 +67,8 @@ def fetch_product_brief(
    }
    return briefs.get(product_name.lower(), f"No stored brief for '{product_name}'.")

-@tool(approval_mode="never_require")

+@tool(approval_mode="never_require")
 def get_brand_voice_profile(
    voice_name: Annotated[str, Field(description="Brand or campaign voice to emulate.")],
 ) -> str:
@@ -149,7 +148,7 @@ class Coordinator(Executor):
            await ctx.send_message(
                AgentExecutorRequest(
                    messages=original_request.conversation
-                    + [ChatMessage(Role.USER, text="The draft is approved as-is.")],
+                    + [ChatMessage("user", text="The draft is approved as-is.")],
                    should_respond=True,
                ),
                target_id=self.final_editor_id,
@@ -164,7 +163,7 @@ class Coordinator(Executor):
            "Rewrite the draft from the previous assistant message into a polished final version. "
            "Keep the response under 120 words and reflect any requested tone adjustments."
        )
-        conversation.append(ChatMessage(Role.USER, text=instruction))
+        conversation.append(ChatMessage("user", text=instruction))
        await ctx.send_message(
            AgentExecutorRequest(messages=conversation, should_respond=True), target_id=self.writer_id
        )
@@ -9,7 +9,6 @@ from agent_framework import (
    WorkflowBuilder,
    WorkflowContext,
    handler,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -121,7 +120,7 @@ async def main():
    # Run the workflow with the user's initial message.
    # For foundational clarity, use run (non streaming) and print the workflow output.
    events = await workflow.run(
-        ChatMessage(role="user", text="Create a slogan for a new electric SUV that is affordable and fun to drive.")
+        ChatMessage("user", ["Create a slogan for a new electric SUV that is affordable and fun to drive."])
    )
    # The terminal node yields output; print its contents.
    outputs = events.get_outputs()
@@ -11,7 +11,6 @@ from agent_framework import (
    FunctionResultContent,
    HandoffAgentUserRequest,
    HandoffBuilder,
-    Role,
    WorkflowAgent,
    tool,
 )
@@ -118,7 +117,7 @@ def handle_response_and_requests(response: AgentResponse) -> dict[str, HandoffAg
    pending_requests: dict[str, HandoffAgentUserRequest] = {}
    for message in response.messages:
        if message.text:
-            print(f"- {message.author_name or message.role.value}: {message.text}")
+            print(f"- {message.author_name or message.role}: {message.text}")
        for content in message.contents:
            if isinstance(content, FunctionCallContent):
                if isinstance(content.arguments, dict):
@@ -200,7 +199,7 @@ async def main() -> None:
        for request in pending_requests.values():
            for message in request.agent_response.messages:
                if message.text:
-                    print(f"- {message.author_name or message.role.value}: {message.text}")
+                    print(f"- {message.author_name or message.role}: {message.text}")

        if not scripted_responses:
            # No more scripted responses; terminate the workflow
@@ -217,7 +216,7 @@ async def main() -> None:
        function_results = [
            FunctionResultContent(call_id=req_id, result=response) for req_id, response in responses.items()
        ]
-        response = await agent.run(ChatMessage(role=Role.TOOL, contents=function_results))
+        response = await agent.run(ChatMessage("tool", function_results))
        pending_requests = handle_response_and_requests(response)


@@ -6,7 +6,6 @@ from agent_framework import (
    ChatAgent,
    HostedCodeInterpreterTool,
    MagenticBuilder,
-    tool,
 )
 from agent_framework.openai import OpenAIChatClient, OpenAIResponsesClient

@@ -11,7 +11,6 @@ from agent_framework import (
    WorkflowBuilder,
    WorkflowContext,
    handler,
-    tool,
 )
 from agent_framework.azure import AzureAIAgentClient
 from azure.identity.aio import AzureCliCredential
@@ -2,7 +2,7 @@

 import asyncio

-from agent_framework import Role, SequentialBuilder
+from agent_framework import SequentialBuilder
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential

@@ -52,7 +52,7 @@ async def main() -> None:
        for i, msg in enumerate(agent_response.messages, start=1):
            role_value = getattr(msg.role, "value", msg.role)
            normalized_role = str(role_value).lower() if role_value is not None else "assistant"
-            name = msg.author_name or ("assistant" if normalized_role == Role.ASSISTANT.value else "user")
+            name = msg.author_name or ("assistant" if normalized_role == "assistant".value else "user")
            print(f"{'-' * 60}\n{i:02d} [{name}]\n{msg.text}")

    """
@@ -20,13 +20,11 @@ from agent_framework import (  # noqa: E402
    Executor,
    FunctionCallContent,
    FunctionResultContent,
-    Role,
    WorkflowAgent,
    WorkflowBuilder,
    WorkflowContext,
    handler,
    response_handler,
-    tool,
 )
 from getting_started.workflows.agents.workflow_as_agent_reflection_pattern import (  # noqa: E402
    ReviewRequest,
@@ -168,7 +166,7 @@ async def main() -> None:
            result=human_response,
        )
        # Send the human review result back to the agent.
-        response = await agent.run(ChatMessage(role=Role.TOOL, contents=[human_review_function_result]))
+        response = await agent.run(ChatMessage("tool", [human_review_function_result]))
        print(f"📤 Agent Response: {response.messages[-1].text}")

    print("=" * 50)
@@ -11,11 +11,9 @@ from agent_framework import (
    ChatMessage,
    Content,
    Executor,
-    Role,
    WorkflowBuilder,
    WorkflowContext,
    handler,
-    tool,
 )
 from agent_framework.openai import OpenAIChatClient
 from pydantic import BaseModel
@@ -81,7 +79,7 @@ class Reviewer(Executor):
        # Construct review instructions and context.
        messages = [
            ChatMessage(
-                role=Role.SYSTEM,
+                role="system",
                text=(
                    "You are a reviewer for an AI agent. Provide feedback on the "
                    "exchange between a user and the agent. Indicate approval only if:\n"
@@ -98,7 +96,7 @@ class Reviewer(Executor):
        messages.extend(request.agent_messages)

        # Add explicit review instruction.
-        messages.append(ChatMessage(role=Role.USER, text="Please review the agent's responses."))
+        messages.append(ChatMessage("user", ["Please review the agent's responses."]))

        print("Reviewer: Sending review request to LLM...")
        response = await self._chat_client.get_response(messages=messages, options={"response_format": _Response})
@@ -127,7 +125,7 @@ class Worker(Executor):
        print("Worker: Received user messages, generating response...")

        # Initialize chat with system prompt.
-        messages = [ChatMessage(role=Role.SYSTEM, text="You are a helpful assistant.")]
+        messages = [ChatMessage("system", ["You are a helpful assistant."])]
        messages.extend(user_messages)

        print("Worker: Calling LLM to generate response...")
@@ -162,7 +160,7 @@ class Worker(Executor):

            # Emit approved result to external consumer via AgentRunUpdateEvent.
            await ctx.add_event(
-                AgentRunUpdateEvent(self.id, data=AgentResponseUpdate(contents=contents, role=Role.ASSISTANT))
+                AgentRunUpdateEvent(self.id, data=AgentResponseUpdate(contents=contents, role="assistant"))
            )
            return

@@ -170,9 +168,9 @@ class Worker(Executor):
        print("Worker: Regenerating response with feedback...")

        # Incorporate review feedback.
-        messages.append(ChatMessage(role=Role.SYSTEM, text=review.feedback))
+        messages.append(ChatMessage("system", [review.feedback]))
        messages.append(
-            ChatMessage(role=Role.SYSTEM, text="Please incorporate the feedback and regenerate the response.")
+            ChatMessage("system", ["Please incorporate the feedback and regenerate the response."])
        )
        messages.extend(request.user_messages)

@@ -78,7 +78,7 @@ async def main() -> None:
    response1 = await agent.run(query1, thread=thread)
    if response1.messages:
        for msg in response1.messages:
-            speaker = msg.author_name or msg.role.value
+            speaker = msg.author_name or msg.role
            print(f"[{speaker}]: {msg.text}")

    # Second turn: Reference the previous topic
@@ -88,7 +88,7 @@ async def main() -> None:
    response2 = await agent.run(query2, thread=thread)
    if response2.messages:
        for msg in response2.messages:
-            speaker = msg.author_name or msg.role.value
+            speaker = msg.author_name or msg.role
            print(f"[{speaker}]: {msg.text}")

    # Third turn: Ask a follow-up question
@@ -98,7 +98,7 @@ async def main() -> None:
    response3 = await agent.run(query3, thread=thread)
    if response3.messages:
        for msg in response3.messages:
-            speaker = msg.author_name or msg.role.value
+            speaker = msg.author_name or msg.role
            print(f"[{speaker}]: {msg.text}")

    # Show the accumulated conversation history
@@ -108,7 +108,7 @@ async def main() -> None:
    if thread.message_store:
        history = await thread.message_store.list_messages()
        for i, msg in enumerate(history, start=1):
-            role = msg.role.value if hasattr(msg.role, "value") else str(msg.role)
+            role = msg.role if hasattr(msg.role, "value") else str(msg.role)
            speaker = msg.author_name or role
            text_preview = msg.text[:80] + "..." if len(msg.text) > 80 else msg.text
            print(f"{i:02d}. [{speaker}]: {text_preview}")
@@ -16,7 +16,6 @@ from agent_framework import (
    Executor,
    FileCheckpointStorage,
    RequestInfoEvent,
-    Role,
    Workflow,
    WorkflowBuilder,
    WorkflowCheckpoint,
@@ -26,7 +25,6 @@ from agent_framework import (
    get_checkpoint_summary,
    handler,
    response_handler,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -94,7 +92,7 @@ class BriefPreparer(Executor):
        # Hand the prompt to the writer agent. We always route through the
        # workflow context so the runtime can capture messages for checkpointing.
        await ctx.send_message(
-            AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=prompt)], should_respond=True),
+            AgentExecutorRequest(messages=[ChatMessage("user", text=prompt)], should_respond=True),
            target_id=self._agent_id,
        )

@@ -156,7 +154,7 @@ class ReviewGateway(Executor):
            f"Human guidance: {reply}"
        )
        await ctx.send_message(
-            AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=prompt)], should_respond=True),
+            AgentExecutorRequest(messages=[ChatMessage("user", text=prompt)], should_respond=True),
            target_id=self._writer_id,
        )

@@ -37,7 +37,6 @@ from agent_framework import (
    WorkflowContext,
    WorkflowOutputEvent,
    handler,
-    tool,
 )


@@ -106,7 +106,7 @@ def create_workflow(checkpoint_storage: FileCheckpointStorage) -> tuple[Workflow
        .with_checkpointing(checkpoint_storage)
        .with_termination_condition(
            # Terminate after 5 user messages for this demo
-            lambda conv: sum(1 for msg in conv if msg.role.value == "user") >= 5
+            lambda conv: sum(1 for msg in conv if msg.role == "user") >= 5
        )
        .build()
    )
@@ -285,7 +285,7 @@ async def resume_with_responses(
                # Now safe to cast event.data to list[ChatMessage]
                conversation = cast(list[ChatMessage], event.data)
                for msg in conversation[-3:]:  # Show last 3 messages
-                    author = msg.author_name or msg.role.value
+                    author = msg.author_name or msg.role
                    text = msg.text[:100] + "..." if len(msg.text) > 100 else msg.text
                    print(f"  {author}: {text}")

@@ -24,7 +24,6 @@ from agent_framework import (
    WorkflowStatusEvent,
    handler,
    response_handler,
-    tool,
 )

 CHECKPOINT_DIR = Path(__file__).with_suffix("").parent / "tmp" / "sub_workflow_checkpoints"
@@ -31,7 +31,6 @@ from agent_framework import (
    ChatMessageStore,
    InMemoryCheckpointStorage,
    SequentialBuilder,
-    tool,
 )
 from agent_framework.openai import OpenAIChatClient

@@ -70,7 +69,7 @@ async def basic_checkpointing() -> None:
    response = await agent.run(query, checkpoint_storage=checkpoint_storage)

    for msg in response.messages:
-        speaker = msg.author_name or msg.role.value
+        speaker = msg.author_name or msg.role
        print(f"[{speaker}]: {msg.text}")

    # Show checkpoints that were created
@@ -10,10 +10,9 @@ from agent_framework import (
    WorkflowContext,
    WorkflowExecutor,
    handler,
-    tool,
 )
 from typing_extensions import Never
- 
+
 """
 Sample: Sub-Workflows (Basics)

@@ -16,7 +16,6 @@ from agent_framework import (
    WorkflowExecutor,
    handler,
    response_handler,
-    tool,
 )
 from typing_extensions import Never

@@ -14,7 +14,6 @@ from agent_framework import (
    WorkflowOutputEvent,
    handler,
    response_handler,
-    tool,
 )
 from typing_extensions import Never

@@ -9,12 +9,10 @@ from agent_framework import (  # Core chat primitives used to build requests
    AgentExecutorResponse,
    ChatAgent,  # Output from an AgentExecutor
    ChatMessage,
-    Role,
    WorkflowBuilder,  # Fluent builder for wiring executors and edges
    WorkflowContext,  # Per-run context and event bus
    executor,  # Decorator to declare a Python function as a workflow executor
-    tool,
-)
+    )
 from agent_framework.azure import AzureOpenAIChatClient  # Thin client wrapper for Azure OpenAI chat models
 from azure.identity import AzureCliCredential  # Uses your az CLI login for credentials
 from pydantic import BaseModel  # Structured outputs for safer parsing
@@ -125,7 +123,7 @@ async def to_email_assistant_request(
    """
    # Bridge executor. Converts a structured DetectionResult into a ChatMessage and forwards it as a new request.
    detection = DetectionResult.model_validate_json(response.agent_response.text)
-    user_msg = ChatMessage(Role.USER, text=detection.email_content)
+    user_msg = ChatMessage("user", text=detection.email_content)
    await ctx.send_message(AgentExecutorRequest(messages=[user_msg], should_respond=True))


@@ -189,7 +187,7 @@ async def main() -> None:

    # Execute the workflow. Since the start is an AgentExecutor, pass an AgentExecutorRequest.
    # The workflow completes when it becomes idle (no more work to do).
-    request = AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=email)], should_respond=True)
+    request = AgentExecutorRequest(messages=[ChatMessage("user", text=email)], should_respond=True)
    events = await workflow.run(request)
    outputs = events.get_outputs()
    if outputs:
@@ -13,13 +13,11 @@ from agent_framework import (
    AgentExecutorResponse,
    ChatAgent,
    ChatMessage,
-    Role,
    WorkflowBuilder,
    WorkflowContext,
    WorkflowEvent,
    WorkflowOutputEvent,
    executor,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -93,7 +91,7 @@ async def store_email(email_text: str, ctx: WorkflowContext[AgentExecutorRequest
    await ctx.set_shared_state(CURRENT_EMAIL_ID_KEY, new_email.email_id)

    await ctx.send_message(
-        AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=new_email.email_content)], should_respond=True)
+        AgentExecutorRequest(messages=[ChatMessage("user", text=new_email.email_content)], should_respond=True)
    )


@@ -120,7 +118,7 @@ async def submit_to_email_assistant(analysis: AnalysisResult, ctx: WorkflowConte

    email: Email = await ctx.get_shared_state(f"{EMAIL_STATE_PREFIX}{analysis.email_id}")
    await ctx.send_message(
-        AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=email.email_content)], should_respond=True)
+        AgentExecutorRequest(messages=[ChatMessage("user", text=email.email_content)], should_respond=True)
    )


@@ -135,7 +133,7 @@ async def summarize_email(analysis: AnalysisResult, ctx: WorkflowContext[AgentEx
    # Only called for long NotSpam emails by selection_func
    email: Email = await ctx.get_shared_state(f"{EMAIL_STATE_PREFIX}{analysis.email_id}")
    await ctx.send_message(
-        AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=email.email_content)], should_respond=True)
+        AgentExecutorRequest(messages=[ChatMessage("user", text=email.email_content)], should_respond=True)
    )


@@ -9,7 +9,6 @@ from agent_framework import (
    WorkflowContext,
    WorkflowOutputEvent,
    handler,
-    tool,
 )
 from typing_extensions import Never

@@ -10,11 +10,9 @@ from agent_framework import (
    ChatMessage,
    Executor,
    ExecutorCompletedEvent,
-    Role,
    WorkflowBuilder,
    WorkflowContext,
    handler,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -97,7 +95,7 @@ class SubmitToJudgeAgent(Executor):
            f"Target: {self._target}\nGuess: {guess}\nResponse:"
        )
        await ctx.send_message(
-            AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=prompt)], should_respond=True),
+            AgentExecutorRequest(messages=[ChatMessage("user", text=prompt)], should_respond=True),
            target_id=self._judge_agent_id,
        )

@@ -13,12 +13,10 @@ from agent_framework import (  # Core chat primitives used to form LLM requests
    ChatAgent,  # Case entry for a switch-case edge group
    ChatMessage,
    Default,  # Default branch when no cases match
-    Role,
    WorkflowBuilder,  # Fluent builder for assembling the graph
    WorkflowContext,  # Per-run context and event bus
    executor,  # Decorator to turn a function into a workflow executor
-    tool,
-)
+    )
 from agent_framework.azure import AzureOpenAIChatClient  # Thin client for Azure OpenAI chat models
 from azure.identity import AzureCliCredential  # Uses your az CLI login for credentials
 from pydantic import BaseModel  # Structured outputs with validation
@@ -100,7 +98,7 @@ async def store_email(email_text: str, ctx: WorkflowContext[AgentExecutorRequest

    # Kick off the detector by forwarding the email as a user message to the spam_detection_agent.
    await ctx.send_message(
-        AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=new_email.email_content)], should_respond=True)
+        AgentExecutorRequest(messages=[ChatMessage("user", text=new_email.email_content)], should_respond=True)
    )


@@ -121,7 +119,7 @@ async def submit_to_email_assistant(detection: DetectionResult, ctx: WorkflowCon
    # Load the original content from shared state using the id carried in DetectionResult.
    email: Email = await ctx.get_shared_state(f"{EMAIL_STATE_PREFIX}{detection.email_id}")
    await ctx.send_message(
-        AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=email.email_content)], should_respond=True)
+        AgentExecutorRequest(messages=[ChatMessage("user", text=email.email_content)], should_respond=True)
    )


@@ -3,9 +3,9 @@
 """Ticketing plugin for CustomerSupport workflow."""

 import uuid
+from collections.abc import Callable
 from dataclasses import dataclass
 from enum import Enum
-from collections.abc import Callable

 # ANSI color codes
 MAGENTA = "\033[35m"
@@ -10,8 +10,7 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Annotated, Any

-from agent_framework import FileCheckpointStorage, RequestInfoEvent, WorkflowOutputEvent
-from agent_framework import tool
+from agent_framework import FileCheckpointStorage, RequestInfoEvent, WorkflowOutputEvent, tool
 from agent_framework.azure import AzureOpenAIChatClient
 from agent_framework_declarative import ExternalInputRequest, ExternalInputResponse, WorkflowFactory
 from azure.identity import AzureCliCredential
@@ -38,17 +37,20 @@ MENU_ITEMS = [
    MenuItem(category="Drink", name="Soda", price=1.95, is_special=False),
 ]

+
 # NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
@tool(approval_mode="never_require")
 def get_menu() -> list[dict[str, Any]]:
    """Get all menu items."""
    return [{"category": i.category, "name": i.name, "price": i.price} for i in MENU_ITEMS]

+
@tool(approval_mode="never_require")
 def get_specials() -> list[dict[str, Any]]:
    """Get today's specials."""
    return [{"category": i.category, "name": i.name, "price": i.price} for i in MENU_ITEMS if i.is_special]

+
@tool(approval_mode="never_require")
 def get_item_price(name: Annotated[str, Field(description="Menu item name")]) -> str:
    """Get price of a menu item."""
@@ -13,9 +13,9 @@ from agent_framework import (
    Executor,
    WorkflowBuilder,
    WorkflowContext,
-    tool,
    executor,
    handler,
+    tool,
 )
 from agent_framework.openai import OpenAIChatClient

@@ -29,11 +29,9 @@ from agent_framework import (
    ChatMessage,
    ConcurrentBuilder,
    RequestInfoEvent,
-    Role,
    WorkflowOutputEvent,
    WorkflowRunState,
    WorkflowStatusEvent,
-    tool,
 )
 from agent_framework._workflows._agent_executor import AgentExecutorResponse
 from agent_framework.azure import AzureOpenAIChatClient
@@ -72,7 +70,7 @@ async def aggregate_with_synthesis(results: list[AgentExecutorResponse]) -> Any:
            # Check for human feedback in the conversation (will be last user message if present)
            if r.full_conversation:
                for msg in reversed(r.full_conversation):
-                    if msg.role == Role.USER and msg.text and "perspectives" not in msg.text.lower():
+                    if msg.role == "user" and msg.text and "perspectives" not in msg.text.lower():
                        human_guidance = msg.text
                        break
        except Exception:
@@ -82,14 +80,14 @@ async def aggregate_with_synthesis(results: list[AgentExecutorResponse]) -> Any:
    guidance_text = f"\n\nHuman guidance: {human_guidance}" if human_guidance else ""

    system_msg = ChatMessage(
-        Role.SYSTEM,
+        "system",
        text=(
            "You are a synthesis expert. Consolidate the following analyst perspectives "
            "into one cohesive, balanced summary (3-4 sentences). If human guidance is provided, "
            "prioritize aspects as directed."
        ),
    )
-    user_msg = ChatMessage(Role.USER, text="\n\n".join(expert_sections) + guidance_text)
+    user_msg = ChatMessage("user", text="\n\n".join(expert_sections) + guidance_text)

    response = await _chat_client.get_response([system_msg, user_msg])
    return response.messages[-1].text if response.messages else ""
@@ -174,7 +172,7 @@ async def main() -> None:
                            else event.data.full_conversation
                        )
                        for msg in recent:
-                            name = msg.author_name or msg.role.value
+                            name = msg.author_name or msg.role
                            text = (msg.text or "")[:150]
                            print(f"  [{name}]: {text}...")
                        print("-" * 40)
@@ -35,7 +35,6 @@ from agent_framework import (
    WorkflowOutputEvent,
    WorkflowRunState,
    WorkflowStatusEvent,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -164,7 +163,7 @@ async def main() -> None:
                if event.data:
                    messages: list[ChatMessage] = event.data
                    for msg in messages:
-                        role = msg.role.value.capitalize()
+                        role = msg.role.capitalize()
                        name = msg.author_name or "unknown"
                        text = (msg.text or "")[:200]
                        print(f"[{role}][{name}]: {text}...")
@@ -10,7 +10,6 @@ from agent_framework import (
    ChatMessage,  # Chat message structure
    Executor,  # Base class for workflow executors
    RequestInfoEvent,  # Event emitted when human input is requested
-    Role,  # Enum of chat roles (user, assistant, system)
    WorkflowBuilder,  # Fluent builder for assembling the graph
    WorkflowContext,  # Per run context and event bus
    WorkflowOutputEvent,  # Event emitted when workflow yields output
@@ -18,8 +17,7 @@ from agent_framework import (
    WorkflowStatusEvent,  # Event emitted on run state changes
    handler,
    response_handler,  # Decorator to expose an Executor method as a step
-    tool,
-)
+    )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
 from pydantic import BaseModel
@@ -88,7 +86,7 @@ class TurnManager(Executor):
        - Input is a simple starter token (ignored here).
        - Output is an AgentExecutorRequest that triggers the agent to produce a guess.
        """
-        user = ChatMessage(Role.USER, text="Start by making your first guess.")
+        user = ChatMessage("user", text="Start by making your first guess.")
        await ctx.send_message(AgentExecutorRequest(messages=[user], should_respond=True))

    @handler
@@ -138,7 +136,7 @@ class TurnManager(Executor):
        # Provide feedback to the agent to try again.
        # We keep the agent's output strictly JSON to ensure stable parsing on the next turn.
        user_msg = ChatMessage(
-            Role.USER,
+            "user",
            text=(f'Feedback: {reply}. Return ONLY a JSON object matching the schema {{"guess": <int 1..10>}}.'),
        )
        await ctx.send_message(AgentExecutorRequest(messages=[user_msg], should_respond=True))
@@ -32,7 +32,6 @@ from agent_framework import (
    WorkflowOutputEvent,
    WorkflowRunState,
    WorkflowStatusEvent,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -109,7 +108,7 @@ async def main() -> None:
                            else event.data.full_conversation
                        )
                        for msg in recent:
-                            name = msg.author_name or msg.role.value
+                            name = msg.author_name or msg.role
                            text = (msg.text or "")[:150]
                            print(f"  [{name}]: {text}...")
                        print("-" * 40)
@@ -132,7 +131,7 @@ async def main() -> None:
                if event.data:
                    messages: list[ChatMessage] = event.data[-3:]
                    for msg in messages:
-                        role = msg.role.value if msg.role else "unknown"
+                        role = msg.role if msg.role else "unknown"
                        print(f"[{role}]: {msg.text}")
                workflow_complete = True

@@ -11,7 +11,6 @@ from agent_framework import (
    WorkflowContext,
    WorkflowOutputEvent,
    handler,
-    tool,
 )
 from typing_extensions import Never

@@ -12,7 +12,6 @@ from agent_framework import (
    Executor,
    WorkflowContext,
    handler,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -3,7 +3,7 @@
 import asyncio
 from typing import Any

-from agent_framework import ChatMessage, ConcurrentBuilder, Role
+from agent_framework import ChatMessage, ConcurrentBuilder
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential

@@ -66,13 +66,13 @@ async def main() -> None:

        # Ask the model to synthesize a concise summary of the experts' outputs
        system_msg = ChatMessage(
-            Role.SYSTEM,
+            "system",
            text=(
                "You are a helpful assistant that consolidates multiple domain expert outputs "
                "into one cohesive, concise summary with clear takeaways. Keep it under 200 words."
            ),
        )
-        user_msg = ChatMessage(Role.USER, text="\n\n".join(expert_sections))
+        user_msg = ChatMessage("user", text="\n\n".join(expert_sections))

        response = await chat_client.get_response([system_msg, user_msg])
        # Return the model's final assistant text as the completion result
@@ -8,11 +8,9 @@ from agent_framework import (
    ChatMessage,
    ConcurrentBuilder,
    Executor,
-    Role,
    Workflow,
    WorkflowContext,
    handler,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -98,13 +96,13 @@ class SummarizationExecutor(Executor):

        # Ask the model to synthesize a concise summary of the experts' outputs
        system_msg = ChatMessage(
-            Role.SYSTEM,
+            "system",
            text=(
                "You are a helpful assistant that consolidates multiple domain expert outputs "
                "into one cohesive, concise summary with clear takeaways. Keep it under 200 words."
            ),
        )
-        user_msg = ChatMessage(Role.USER, text="\n\n".join(expert_sections))
+        user_msg = ChatMessage("user", text="\n\n".join(expert_sections))

        response = await self.chat_client.get_response([system_msg, user_msg])

@@ -7,9 +7,7 @@ from agent_framework import (
    ChatAgent,
    ChatMessage,
    GroupChatBuilder,
-    Role,
    WorkflowOutputEvent,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -73,7 +71,7 @@ async def main() -> None:
        .participants([researcher, writer])
        # Set a hard termination condition: stop after 4 assistant messages
        # 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 == Role.ASSISTANT) >= 4)
+        .with_termination_condition(lambda messages: sum(1 for msg in messages if msg.role == "assistant") >= 4)
        .build()
    )

@@ -9,9 +9,7 @@ from agent_framework import (
    ChatAgent,
    ChatMessage,
    GroupChatBuilder,
-    Role,
    WorkflowOutputEvent,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -214,7 +212,7 @@ Share your perspective authentically. Feel free to:
        GroupChatBuilder()
        .with_orchestrator(agent=moderator)
        .participants([farmer, developer, teacher, activist, spiritual_leader, artist, immigrant, doctor])
-        .with_termination_condition(lambda messages: sum(1 for msg in messages if msg.role == Role.ASSISTANT) >= 10)
+        .with_termination_condition(lambda messages: sum(1 for msg in messages if msg.role == "assistant") >= 10)
        .build()
    )

@@ -9,7 +9,6 @@ from agent_framework import (
    GroupChatBuilder,
    GroupChatState,
    WorkflowOutputEvent,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -14,7 +14,6 @@ from agent_framework import (
    WorkflowEvent,
    WorkflowOutputEvent,
    resolve_agent_id,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -95,7 +94,7 @@ def _display_event(event: WorkflowEvent) -> None:
        conversation = cast(list[ChatMessage], event.data)
        print("\n=== Final Conversation (Autonomous with Iteration) ===")
        for message in conversation:
-            speaker = message.author_name or message.role.value
+            speaker = message.author_name or message.role
            text_preview = message.text[:200] + "..." if len(message.text) > 200 else message.text
            print(f"- {speaker}: {text_preview}")
        print(f"\nTotal messages: {len(conversation)}")
@@ -131,7 +130,7 @@ async def main() -> None:
        )
        .with_termination_condition(
            # Terminate after coordinator provides 5 assistant responses
-            lambda conv: sum(1 for msg in conv if msg.author_name == "coordinator" and msg.role.value == "assistant")
+            lambda conv: sum(1 for msg in conv if msg.author_name == "coordinator" and msg.role == "assistant")
            >= 5
        )
        .build()
@@ -131,7 +131,7 @@ def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
                if not message.text:
                    # Skip messages without text (e.g., tool calls)
                    continue
-                speaker = message.author_name or message.role.value
+                speaker = message.author_name or message.role
                print(f"- {speaker}: {message.text}")

        # HandoffSentEvent: Indicates a handoff has been initiated
@@ -151,7 +151,7 @@ def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
            if isinstance(conversation, list):
                print("\n=== Final Conversation Snapshot ===")
                for message in conversation:
-                    speaker = message.author_name or message.role.value
+                    speaker = message.author_name or message.role
                    print(f"- {speaker}: {message.text or [content.type for content in message.contents]}")
                print("===================================")

@@ -183,7 +183,7 @@ def _print_handoff_agent_user_request(response: AgentResponse) -> None:
        if not message.text:
            # Skip messages without text (e.g., tool calls)
            continue
-        speaker = message.author_name or message.role.value
+        speaker = message.author_name or message.role
        print(f"- {speaker}: {message.text}")


@@ -126,7 +126,7 @@ def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
                if not message.text:
                    # Skip messages without text (e.g., tool calls)
                    continue
-                speaker = message.author_name or message.role.value
+                speaker = message.author_name or message.role
                print(f"- {speaker}: {message.text}")

        # HandoffSentEvent: Indicates a handoff has been initiated
@@ -146,7 +146,7 @@ def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
            if isinstance(conversation, list):
                print("\n=== Final Conversation Snapshot ===")
                for message in conversation:
-                    speaker = message.author_name or message.role.value
+                    speaker = message.author_name or message.role
                    print(f"- {speaker}: {message.text or [content.type for content in message.contents]}")
                print("===================================")

@@ -178,7 +178,7 @@ def _print_handoff_agent_user_request(response: AgentResponse) -> None:
        if not message.text:
            # Skip messages without text (e.g., tool calls)
            continue
-        speaker = message.author_name or message.role.value
+        speaker = message.author_name or message.role
        print(f"- {speaker}: {message.text}")


@@ -41,7 +41,6 @@ from agent_framework import (
    WorkflowEvent,
    WorkflowRunState,
    WorkflowStatusEvent,
-    tool,
 )
 from azure.identity.aio import AzureCliCredential

@@ -157,7 +156,7 @@ async def main() -> None:
                HandoffBuilder()
                .participants([triage, code_specialist])
                .with_start_agent(triage)
-                .with_termination_condition(lambda conv: sum(1 for msg in conv if msg.role.value == "user") >= 2)
+                .with_termination_condition(lambda conv: sum(1 for msg in conv if msg.role == "user") >= 2)
                .build()
            )

@@ -15,7 +15,6 @@ from agent_framework import (
    MagenticOrchestratorEvent,
    MagenticProgressLedger,
    WorkflowOutputEvent,
-    tool,
 )
 from agent_framework.openai import OpenAIChatClient, OpenAIResponsesClient

@@ -16,7 +16,6 @@ from agent_framework import (
    WorkflowOutputEvent,
    WorkflowRunState,
    WorkflowStatusEvent,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity._credentials import AzureCliCredential
@@ -12,7 +12,6 @@ from agent_framework import (
    MagenticPlanReviewRequest,
    RequestInfoEvent,
    WorkflowOutputEvent,
-    tool,
 )
 from agent_framework.openai import OpenAIChatClient

@@ -3,7 +3,7 @@
 import asyncio
 from typing import cast

-from agent_framework import ChatMessage, Role, SequentialBuilder, WorkflowOutputEvent
+from agent_framework import ChatMessage, SequentialBuilder, WorkflowOutputEvent
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential

@@ -53,7 +53,7 @@ async def main() -> None:
    if outputs:
        print("===== Final Conversation =====")
        for i, msg in enumerate(outputs[-1], start=1):
-            name = msg.author_name or ("assistant" if msg.role == Role.ASSISTANT else "user")
+            name = msg.author_name or ("assistant" if msg.role == "assistant" else "user")
            print(f"{'-' * 60}\n{i:02d} [{name}]\n{msg.text}")

    """
@@ -7,11 +7,9 @@ from agent_framework import (
    AgentExecutorResponse,
    ChatMessage,
    Executor,
-    Role,
    SequentialBuilder,
    WorkflowContext,
    handler,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -48,12 +46,12 @@ class Summarizer(Executor):
        the output must be `list[ChatMessage]`.
        """
        if not agent_response.full_conversation:
-            await ctx.send_message([ChatMessage(role=Role.ASSISTANT, text="No conversation to summarize.")])
+            await ctx.send_message([ChatMessage("assistant", ["No conversation to summarize."])])
            return

-        users = sum(1 for m in agent_response.full_conversation if m.role == Role.USER)
-        assistants = sum(1 for m in agent_response.full_conversation if m.role == Role.ASSISTANT)
-        summary = ChatMessage(role=Role.ASSISTANT, text=f"Summary -> users:{users} assistants:{assistants}")
+        users = sum(1 for m in agent_response.full_conversation if m.role == "user")
+        assistants = sum(1 for m in agent_response.full_conversation if m.role == "assistant")
+        summary = ChatMessage("assistant", [f"Summary -> users:{users} assistants:{assistants}"])
        final_conversation = list(agent_response.full_conversation) + [summary]
        await ctx.send_message(final_conversation)

@@ -78,7 +76,7 @@ async def main() -> None:
        print("===== Final Conversation =====")
        messages: list[ChatMessage] | Any = outputs[0]
        for i, msg in enumerate(messages, start=1):
-            name = msg.author_name or ("assistant" if msg.role == Role.ASSISTANT else "user")
+            name = msg.author_name or ("assistant" if msg.role == "assistant" else "user")
            print(f"{'-' * 60}\n{i:02d} [{name}]\n{msg.text}")

    """
@@ -6,12 +6,10 @@ from agent_framework import (
    ChatAgent,
    ChatMessage,
    Executor,
-    Role,
    SequentialBuilder,
    Workflow,
    WorkflowContext,
    handler,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -64,7 +62,7 @@ async def run_workflow(workflow: Workflow, query: str) -> None:
    if outputs:
        messages: list[ChatMessage] = outputs[0]
        for message in messages:
-            name = message.author_name or ("assistant" if message.role == Role.ASSISTANT else "user")
+            name = message.author_name or ("assistant" if message.role == "assistant" else "user")
            print(f"{name}: {message.text}")
    else:
        raise RuntimeError("No outputs received from the workflow.")
@@ -11,13 +11,11 @@ from agent_framework import (  # Core chat primitives to build LLM requests
    Executor,  # Base class for custom Python executors
    ExecutorCompletedEvent,
    ExecutorInvokedEvent,
-    Role,  # Enum of chat roles (user, assistant, system)
    WorkflowBuilder,  # Fluent builder for wiring the workflow graph
    WorkflowContext,  # Per run context and event bus
    WorkflowOutputEvent,  # Event emitted when workflow yields output
    handler,  # Decorator to mark an Executor method as invokable
-    tool,
-)
+    )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential  # Uses your az CLI login for credentials
 from typing_extensions import Never
@@ -47,7 +45,7 @@ class DispatchToExperts(Executor):
    @handler
    async def dispatch(self, prompt: str, ctx: WorkflowContext[AgentExecutorRequest]) -> None:
        # Wrap the incoming prompt as a user message for each expert and request a response.
-        initial_message = ChatMessage(Role.USER, text=prompt)
+        initial_message = ChatMessage("user", text=prompt)
        await ctx.send_message(AgentExecutorRequest(messages=[initial_message], should_respond=True))


@@ -14,8 +14,7 @@ from agent_framework import (
    WorkflowOutputEvent,  # Event emitted when workflow yields output
    WorkflowViz,  # Utility to visualize a workflow graph
    handler,  # Decorator to expose an Executor method as a step
-    tool,
-)
+    )
 from typing_extensions import Never

 """
@@ -11,11 +11,9 @@ from agent_framework import (
    AgentExecutorResponse,
    ChatAgent,
    ChatMessage,
-    Role,
    WorkflowBuilder,
    WorkflowContext,
    executor,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -105,7 +103,7 @@ async def store_email(email_text: str, ctx: WorkflowContext[AgentExecutorRequest
    await ctx.set_shared_state(CURRENT_EMAIL_ID_KEY, new_email.email_id)

    await ctx.send_message(
-        AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=new_email.email_content)], should_respond=True)
+        AgentExecutorRequest(messages=[ChatMessage("user", text=new_email.email_content)], should_respond=True)
    )


@@ -136,7 +134,7 @@ async def submit_to_email_assistant(detection: DetectionResult, ctx: WorkflowCon
    # Load the original content by id from shared state and forward it to the assistant.
    email: Email = await ctx.get_shared_state(f"{EMAIL_STATE_PREFIX}{detection.email_id}")
    await ctx.send_message(
-        AgentExecutorRequest(messages=[ChatMessage(Role.USER, text=email.email_content)], should_respond=True)
+        AgentExecutorRequest(messages=[ChatMessage("user", text=email.email_content)], should_respond=True)
    )


@@ -97,7 +97,7 @@ def _print_output(event: WorkflowOutputEvent) -> None:
    print("Workflow completed. Aggregated results from both agents:")
    for msg in messages:
        if msg.text:
-            print(f"- {msg.author_name or msg.role.value}: {msg.text}")
+            print(f"- {msg.author_name or msg.role}: {msg.text}")


 async def main() -> None:
@@ -116,7 +116,7 @@ async def main() -> None:
                    print("\n" + "-" * 60)
                    print("Workflow completed. Final conversation:")
                    for msg in output:
-                        role = msg.role.value if hasattr(msg.role, "value") else msg.role
+                        role = msg.role if hasattr(msg.role, "value") else msg.role
                        text = msg.text[:200] + "..." if len(msg.text) > 200 else msg.text
                        print(f"  [{role}]: {text}")
    else:
@@ -9,12 +9,10 @@ from agent_framework import (
    ChatAgent,
    ChatMessage,
    Executor,
-    Role,
    WorkflowBuilder,
    WorkflowContext,
    WorkflowViz,
    handler,
-    tool,
 )
 from agent_framework.azure import AzureOpenAIChatClient
 from azure.identity import AzureCliCredential
@@ -41,7 +39,7 @@ class DispatchToExperts(Executor):
    @handler
    async def dispatch(self, prompt: str, ctx: WorkflowContext[AgentExecutorRequest]) -> None:
        # Wrap the incoming prompt as a user message for each expert and request a response.
-        initial_message = ChatMessage(Role.USER, text=prompt)
+        initial_message = ChatMessage("user", text=prompt)
        await ctx.send_message(AgentExecutorRequest(messages=[initial_message], should_respond=True))