renamed all (#3207)

python/samples/getting_started/workflows/_start-here/step4_using_factories.py

@@ -3,7 +3,7 @@
 import asyncio
 
 from agent_framework import (
-    AgentRunResponse,
+    AgentResponse,
     ChatAgent,
     Executor,
     WorkflowBuilder,
@@ -83,9 +83,9 @@ async def main():
         .build()
     )
 
-    output: AgentRunResponse | None = None
+    output: AgentResponse | None = None
     async for event in workflow.run_stream("hello world"):
-        if isinstance(event, WorkflowOutputEvent) and isinstance(event.data, AgentRunResponse):
+        if isinstance(event, WorkflowOutputEvent) and isinstance(event.data, AgentResponse):
             output = event.data
 
     if output:

python/samples/getting_started/workflows/agents/azure_chat_agents_function_bridge.py

@@ -6,7 +6,7 @@ from typing import Final
 from agent_framework import (
     AgentExecutorRequest,
     AgentExecutorResponse,
-    AgentRunResponse,
+    AgentResponse,
     AgentRunUpdateEvent,
     ChatMessage,
     Role,
@@ -70,7 +70,7 @@ async def enrich_with_references(
     ctx: WorkflowContext[AgentExecutorRequest],
 ) -> None:
     """Inject a follow-up user instruction that adds an external note for the next agent."""
-    conversation = list(draft.full_conversation or draft.agent_run_response.messages)
+    conversation = list(draft.full_conversation or draft.agent_response.messages)
     original_prompt = next((message.text for message in conversation if message.role == Role.USER), "")
     external_note = _lookup_external_note(original_prompt) or (
         "No additional references were found. Please refine the previous assistant response for clarity."
@@ -134,7 +134,7 @@ async def main() -> None:
         elif isinstance(event, WorkflowOutputEvent):
             print("\n\n===== Final Output =====")
             response = event.data
-            if isinstance(response, AgentRunResponse):
+            if isinstance(response, AgentResponse):
                 print(response.text or "(empty response)")
             else:
                 print(response if response is not None else "No response generated.")

python/samples/getting_started/workflows/agents/azure_chat_agents_tool_calls_with_feedback.py

@@ -8,7 +8,7 @@ from typing import Annotated
 from agent_framework import (
     AgentExecutorRequest,
     AgentExecutorResponse,
-    AgentRunResponse,
+    AgentResponse,
     AgentRunUpdateEvent,
     ChatAgent,
     ChatMessage,
@@ -102,12 +102,12 @@ class Coordinator(Executor):
     async def on_writer_response(
         self,
         draft: AgentExecutorResponse,
-        ctx: WorkflowContext[Never, AgentRunResponse],
+        ctx: WorkflowContext[Never, AgentResponse],
     ) -> None:
         """Handle responses from the other two agents in the workflow."""
         if draft.executor_id == self.final_editor_id:
             # Final editor response; yield output directly.
-            await ctx.yield_output(draft.agent_run_response)
+            await ctx.yield_output(draft.agent_response)
             return
 
         # Writer agent response; request human feedback.
@@ -117,8 +117,8 @@ class Coordinator(Executor):
         if draft.full_conversation is not None:
             conversation = list(draft.full_conversation)
         else:
-            conversation = list(draft.agent_run_response.messages)
-        draft_text = draft.agent_run_response.text.strip()
+            conversation = list(draft.agent_response.messages)
+        draft_text = draft.agent_response.text.strip()
         if not draft_text:
             draft_text = "No draft text was produced."
 

python/samples/getting_started/workflows/agents/handoff_workflow_as_agent.py

@@ -4,7 +4,7 @@ import asyncio
 from typing import Annotated
 
 from agent_framework import (
-    AgentRunResponse,
+    AgentResponse,
     ChatAgent,
     ChatMessage,
     FunctionCallContent,
@@ -101,7 +101,7 @@ def create_agents(chat_client: AzureOpenAIChatClient) -> tuple[ChatAgent, ChatAg
     return triage_agent, refund_agent, order_agent, return_agent
 
 
-def handle_response_and_requests(response: AgentRunResponse) -> dict[str, HandoffAgentUserRequest]:
+def handle_response_and_requests(response: AgentResponse) -> dict[str, HandoffAgentUserRequest]:
     """Process agent response messages and extract any user requests.
 
     This function inspects the agent response and:
@@ -109,7 +109,7 @@ def handle_response_and_requests(response: AgentRunResponse) -> dict[str, Handof
     - Collects HandoffAgentUserRequest instances for response handling
 
     Args:
-        response: The AgentRunResponse from the agent run call.
+        response: The AgentResponse from the agent run call.
 
     Returns:
         A dictionary mapping request IDs to HandoffAgentUserRequest instances.

python/samples/getting_started/workflows/agents/mixed_agents_and_executors.py

@@ -66,8 +66,8 @@ class Evaluator(Executor):
             ctx: Workflow context for yielding the final output string
         """
         target_text = "1, 1, 2, 3, 5, 8, 13, 21, 34, 55, 89"
-        correctness = target_text in message.agent_run_response.text
-        consumption = message.agent_run_response.usage_details
+        correctness = target_text in message.agent_response.text
+        consumption = message.agent_response.usage_details
         await ctx.yield_output(f"Correctness: {correctness}, Consumption: {consumption}")
 
 

python/samples/getting_started/workflows/agents/workflow_as_agent_reflection_pattern.py

@@ -5,7 +5,7 @@ from dataclasses import dataclass
 from uuid import uuid4
 
 from agent_framework import (
-    AgentRunResponseUpdate,
+    AgentResponseUpdate,
     AgentRunUpdateEvent,
     ChatClientProtocol,
     ChatMessage,
@@ -161,7 +161,7 @@ class Worker(Executor):
 
             # Emit approved result to external consumer via AgentRunUpdateEvent.
             await ctx.add_event(
-                AgentRunUpdateEvent(self.id, data=AgentRunResponseUpdate(contents=contents, role=Role.ASSISTANT))
+                AgentRunUpdateEvent(self.id, data=AgentResponseUpdate(contents=contents, role=Role.ASSISTANT))
             )
             return
 

python/samples/getting_started/workflows/checkpoint/checkpoint_with_human_in_the_loop.py

@@ -127,7 +127,7 @@ class ReviewGateway(Executor):
         await ctx.request_info(
             request_data=HumanApprovalRequest(
                 prompt="Review the draft. Reply 'approve' or provide edit instructions.",
-                draft=response.agent_run_response.text,
+                draft=response.agent_response.text,
                 iteration=self._iteration,
             ),
             response_type=str,

python/samples/getting_started/workflows/control-flow/edge_condition.py

@@ -85,7 +85,7 @@ def get_condition(expected_result: bool):
         try:
             # Prefer parsing a structured DetectionResult from the agent JSON text.
             # Using model_validate_json ensures type safety and raises if the shape is wrong.
-            detection = DetectionResult.model_validate_json(message.agent_run_response.text)
+            detection = DetectionResult.model_validate_json(message.agent_response.text)
             # Route only when the spam flag matches the expected path.
             return detection.is_spam == expected_result
         except Exception:
@@ -99,14 +99,14 @@ def get_condition(expected_result: bool):
 @executor(id="send_email")
 async def handle_email_response(response: AgentExecutorResponse, ctx: WorkflowContext[Never, str]) -> None:
     # Downstream of the email assistant. Parse a validated EmailResponse and yield the workflow output.
-    email_response = EmailResponse.model_validate_json(response.agent_run_response.text)
+    email_response = EmailResponse.model_validate_json(response.agent_response.text)
     await ctx.yield_output(f"Email sent:\n{email_response.response}")
 
 
 @executor(id="handle_spam")
 async def handle_spam_classifier_response(response: AgentExecutorResponse, ctx: WorkflowContext[Never, str]) -> None:
     # Spam path. Confirm the DetectionResult and yield the workflow output. Guard against accidental non spam input.
-    detection = DetectionResult.model_validate_json(response.agent_run_response.text)
+    detection = DetectionResult.model_validate_json(response.agent_response.text)
     if detection.is_spam:
         await ctx.yield_output(f"Email marked as spam: {detection.reason}")
     else:
@@ -123,7 +123,7 @@ async def to_email_assistant_request(
     Extracts DetectionResult.email_content and forwards it as a user message.
     """
     # Bridge executor. Converts a structured DetectionResult into a ChatMessage and forwards it as a new request.
-    detection = DetectionResult.model_validate_json(response.agent_run_response.text)
+    detection = DetectionResult.model_validate_json(response.agent_response.text)
     user_msg = ChatMessage(Role.USER, text=detection.email_content)
     await ctx.send_message(AgentExecutorRequest(messages=[user_msg], should_respond=True))
 

python/samples/getting_started/workflows/control-flow/multi_selection_edge_group.py

@@ -98,7 +98,7 @@ async def store_email(email_text: str, ctx: WorkflowContext[AgentExecutorRequest
 
 @executor(id="to_analysis_result")
 async def to_analysis_result(response: AgentExecutorResponse, ctx: WorkflowContext[AnalysisResult]) -> None:
-    parsed = AnalysisResultAgent.model_validate_json(response.agent_run_response.text)
+    parsed = AnalysisResultAgent.model_validate_json(response.agent_response.text)
     email_id: str = await ctx.get_shared_state(CURRENT_EMAIL_ID_KEY)
     email: Email = await ctx.get_shared_state(f"{EMAIL_STATE_PREFIX}{email_id}")
     await ctx.send_message(
@@ -125,7 +125,7 @@ async def submit_to_email_assistant(analysis: AnalysisResult, ctx: WorkflowConte
 
 @executor(id="finalize_and_send")
 async def finalize_and_send(response: AgentExecutorResponse, ctx: WorkflowContext[Never, str]) -> None:
-    parsed = EmailResponse.model_validate_json(response.agent_run_response.text)
+    parsed = EmailResponse.model_validate_json(response.agent_response.text)
     await ctx.yield_output(f"Email sent: {parsed.response}")
 
 
@@ -140,7 +140,7 @@ async def summarize_email(analysis: AnalysisResult, ctx: WorkflowContext[AgentEx
 
 @executor(id="merge_summary")
 async def merge_summary(response: AgentExecutorResponse, ctx: WorkflowContext[AnalysisResult]) -> None:
-    summary = EmailSummaryModel.model_validate_json(response.agent_run_response.text)
+    summary = EmailSummaryModel.model_validate_json(response.agent_response.text)
     email_id: str = await ctx.get_shared_state(CURRENT_EMAIL_ID_KEY)
     email: Email = await ctx.get_shared_state(f"{EMAIL_STATE_PREFIX}{email_id}")
     # Build an AnalysisResult mirroring to_analysis_result but with summary

python/samples/getting_started/workflows/control-flow/simple_loop.py

@@ -106,7 +106,7 @@ class ParseJudgeResponse(Executor):
 
     @handler
     async def parse(self, response: AgentExecutorResponse, ctx: WorkflowContext[NumberSignal]) -> None:
-        text = response.agent_run_response.text.strip().upper()
+        text = response.agent_response.text.strip().upper()
         if "MATCHED" in text:
             await ctx.send_message(NumberSignal.MATCHED)
         elif "ABOVE" in text and "BELOW" not in text:

python/samples/getting_started/workflows/control-flow/switch_case_edge_group.py

@@ -106,7 +106,7 @@ async def store_email(email_text: str, ctx: WorkflowContext[AgentExecutorRequest
 @executor(id="to_detection_result")
 async def to_detection_result(response: AgentExecutorResponse, ctx: WorkflowContext[DetectionResult]) -> None:
     # Parse the detector JSON into a typed model. Attach the current email id for downstream lookups.
-    parsed = DetectionResultAgent.model_validate_json(response.agent_run_response.text)
+    parsed = DetectionResultAgent.model_validate_json(response.agent_response.text)
     email_id: str = await ctx.get_shared_state(CURRENT_EMAIL_ID_KEY)
     await ctx.send_message(DetectionResult(spam_decision=parsed.spam_decision, reason=parsed.reason, email_id=email_id))
 
@@ -127,7 +127,7 @@ async def submit_to_email_assistant(detection: DetectionResult, ctx: WorkflowCon
 @executor(id="finalize_and_send")
 async def finalize_and_send(response: AgentExecutorResponse, ctx: WorkflowContext[Never, str]) -> None:
     # Terminal step for the drafting branch. Yield the email response as output.
-    parsed = EmailResponse.model_validate_json(response.agent_run_response.text)
+    parsed = EmailResponse.model_validate_json(response.agent_response.text)
     await ctx.yield_output(f"Email sent: {parsed.response}")
 
 

python/samples/getting_started/workflows/human-in-the-loop/agents_with_approval_requests.py

@@ -208,7 +208,7 @@ async def conclude_workflow(
     ctx: WorkflowContext[Never, str],
 ) -> None:
     """Conclude the workflow by yielding the final email response."""
-    await ctx.yield_output(email_response.agent_run_response.text)
+    await ctx.yield_output(email_response.agent_response.text)
 
 
 def create_email_writer_agent() -> ChatAgent:

python/samples/getting_started/workflows/human-in-the-loop/concurrent_request_info.py

@@ -64,7 +64,7 @@ async def aggregate_with_synthesis(results: list[AgentExecutorResponse]) -> Any:
 
     for r in results:
         try:
-            messages = getattr(r.agent_run_response, "messages", [])
+            messages = getattr(r.agent_response, "messages", [])
             final_text = messages[-1].text if messages and hasattr(messages[-1], "text") else "(no content)"
             expert_sections.append(f"{getattr(r, 'executor_id', 'analyst')}:\n{final_text}")
 
@@ -161,7 +161,7 @@ async def main() -> None:
                     print("\n" + "-" * 40)
                     print("INPUT REQUESTED")
                     print(
-                        f"Agent {event.source_executor_id} just responded with: '{event.data.agent_run_response.text}'. "
+                        f"Agent {event.source_executor_id} just responded with: '{event.data.agent_response.text}'. "
                         "Please provide your feedback."
                     )
                     print("-" * 40)

python/samples/getting_started/workflows/human-in-the-loop/group_chat_request_info.py

@@ -27,7 +27,7 @@ import asyncio
 from agent_framework import (
     AgentExecutorResponse,
     AgentRequestInfoResponse,
-    AgentRunResponse,
+    AgentResponse,
     AgentRunUpdateEvent,
     ChatMessage,
     GroupChatBuilder,
@@ -138,8 +138,8 @@ async def main() -> None:
                     print(f"About to call agent: {event.source_executor_id}")
                     print("-" * 40)
                     print("Conversation context:")
-                    agent_run_response: AgentRunResponse = event.data.agent_run_response
-                    messages: list[ChatMessage] = agent_run_response.messages
+                    agent_response: AgentResponse = event.data.agent_response
+                    messages: list[ChatMessage] = agent_response.messages
                     recent: list[ChatMessage] = messages[-3:] if len(messages) > 3 else messages  # type: ignore
                     for msg in recent:
                         name = msg.author_name or "unknown"

python/samples/getting_started/workflows/human-in-the-loop/guessing_game_with_human_input.py

@@ -103,7 +103,7 @@ class TurnManager(Executor):
         2) Request info with a HumanFeedbackRequest as the payload.
         """
         # Parse structured model output
-        text = result.agent_run_response.text
+        text = result.agent_response.text
         last_guess = GuessOutput.model_validate_json(text).guess
 
         # Craft a precise human prompt that defines higher and lower relative to the agent's guess.

python/samples/getting_started/workflows/human-in-the-loop/sequential_request_info.py

@@ -96,7 +96,7 @@ async def main() -> None:
                     print("\n" + "-" * 40)
                     print("REQUEST INFO: INPUT REQUESTED")
                     print(
-                        f"Agent {event.source_executor_id} just responded with: '{event.data.agent_run_response.text}'. "
+                        f"Agent {event.source_executor_id} just responded with: '{event.data.agent_response.text}'. "
                         "Please provide your feedback."
                     )
                     print("-" * 40)

python/samples/getting_started/workflows/orchestration/concurrent_custom_aggregator.py

@@ -58,7 +58,7 @@ async def main() -> None:
         expert_sections: list[str] = []
         for r in results:
             try:
-                messages = getattr(r.agent_run_response, "messages", [])
+                messages = getattr(r.agent_response, "messages", [])
                 final_text = messages[-1].text if messages and hasattr(messages[-1], "text") else "(no content)"
                 expert_sections.append(f"{getattr(r, 'executor_id', 'expert')}:\n{final_text}")
             except Exception as e:

python/samples/getting_started/workflows/orchestration/concurrent_participant_factory.py

@@ -89,7 +89,7 @@ class SummarizationExecutor(Executor):
         expert_sections: list[str] = []
         for r in results:
             try:
-                messages = getattr(r.agent_run_response, "messages", [])
+                messages = getattr(r.agent_response, "messages", [])
                 final_text = messages[-1].text if messages and hasattr(messages[-1], "text") else "(no content)"
                 expert_sections.append(f"{getattr(r, 'executor_id', 'expert')}:\n{final_text}")
             except Exception as e:

python/samples/getting_started/workflows/orchestration/handoff_autonomous.py

@@ -5,7 +5,7 @@ import logging
 from typing import cast
 
 from agent_framework import (
-    AgentRunResponseUpdate,
+    AgentResponseUpdate,
     AgentRunUpdateEvent,
     ChatAgent,
     ChatMessage,
@@ -82,7 +82,7 @@ last_response_id: str | None = None
 def _display_event(event: WorkflowEvent) -> None:
     """Print the final conversation snapshot from workflow output events."""
     if isinstance(event, AgentRunUpdateEvent) and event.data:
-        update: AgentRunResponseUpdate = event.data
+        update: AgentResponseUpdate = event.data
         if not update.text:
             return
         global last_response_id

python/samples/getting_started/workflows/orchestration/handoff_participant_factory.py

@@ -5,8 +5,8 @@ import logging
 from typing import Annotated, cast
 
 from agent_framework import (
+    AgentResponse,
     AgentRunEvent,
-    AgentRunResponse,
     ChatAgent,
     ChatMessage,
     HandoffAgentUserRequest,
@@ -163,14 +163,14 @@ def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
     return requests
 
 
-def _print_handoff_agent_user_request(response: AgentRunResponse) -> None:
+def _print_handoff_agent_user_request(response: AgentResponse) -> None:
     """Display the agent's response messages when requesting user input.
 
     This will happen when an agent generates a response that doesn't trigger
     a handoff, i.e., the agent is asking the user for more information.
 
     Args:
-        response: The AgentRunResponse from the agent requesting user input
+        response: The AgentResponse from the agent requesting user input
     """
     if not response.messages:
         raise RuntimeError("Cannot print agent responses: response has no messages.")

python/samples/getting_started/workflows/orchestration/handoff_simple.py

@@ -4,8 +4,8 @@ import asyncio
 from typing import Annotated, cast
 
 from agent_framework import (
+    AgentResponse,
     AgentRunEvent,
-    AgentRunResponse,
     ChatAgent,
     ChatMessage,
     HandoffAgentUserRequest,
@@ -158,14 +158,14 @@ def _handle_events(events: list[WorkflowEvent]) -> list[RequestInfoEvent]:
     return requests
 
 
-def _print_handoff_agent_user_request(response: AgentRunResponse) -> None:
+def _print_handoff_agent_user_request(response: AgentResponse) -> None:
     """Display the agent's response messages when requesting user input.
 
     This will happen when an agent generates a response that doesn't trigger
     a handoff, i.e., the agent is asking the user for more information.
 
     Args:
-        response: The AgentRunResponse from the agent requesting user input
+        response: The AgentResponse from the agent requesting user input
     """
     if not response.messages:
         raise RuntimeError("Cannot print agent responses: response has no messages.")

python/samples/getting_started/workflows/parallelism/fan_out_fan_in_edges.py

@@ -36,7 +36,7 @@ Show how to construct a parallel branch pattern in workflows. Demonstrate:
 Prerequisites:
 - Familiarity with WorkflowBuilder, executors, edges, events, and streaming runs.
 - Azure OpenAI access configured for AzureOpenAIChatClient. Log in with Azure CLI and set any required environment variables.
-- Comfort reading AgentExecutorResponse.agent_run_response.text for assistant output aggregation.
+- Comfort reading AgentExecutorResponse.agent_response.text for assistant output aggregation.
 """
 
 
@@ -67,8 +67,8 @@ class AggregateInsights(Executor):
         # Map responses to text by executor id for a simple, predictable demo.
         by_id: dict[str, str] = {}
         for r in results:
-            # AgentExecutorResponse.agent_run_response.text is the assistant text produced by the agent.
-            by_id[r.executor_id] = r.agent_run_response.text
+            # AgentExecutorResponse.agent_response.text is the assistant text produced by the agent.
+            by_id[r.executor_id] = r.agent_response.text
 
         research_text = by_id.get("researcher", "")
         marketing_text = by_id.get("marketer", "")

python/samples/getting_started/workflows/state-management/shared_states_with_agents.py

@@ -117,7 +117,7 @@ async def to_detection_result(response: AgentExecutorResponse, ctx: WorkflowCont
     2) Retrieve the current email_id from shared state.
     3) Send a typed DetectionResult for conditional routing.
     """
-    parsed = DetectionResultAgent.model_validate_json(response.agent_run_response.text)
+    parsed = DetectionResultAgent.model_validate_json(response.agent_response.text)
     email_id: str = await ctx.get_shared_state(CURRENT_EMAIL_ID_KEY)
     await ctx.send_message(DetectionResult(is_spam=parsed.is_spam, reason=parsed.reason, email_id=email_id))
 
@@ -142,7 +142,7 @@ async def submit_to_email_assistant(detection: DetectionResult, ctx: WorkflowCon
 @executor(id="finalize_and_send")
 async def finalize_and_send(response: AgentExecutorResponse, ctx: WorkflowContext[Never, str]) -> None:
     """Validate the drafted reply and yield the final output."""
-    parsed = EmailResponse.model_validate_json(response.agent_run_response.text)
+    parsed = EmailResponse.model_validate_json(response.agent_response.text)
     await ctx.yield_output(f"Email sent: {parsed.response}")
 
 

python/samples/getting_started/workflows/visualization/concurrent_with_visualization.py

@@ -61,8 +61,8 @@ class AggregateInsights(Executor):
         # Map responses to text by executor id for a simple, predictable demo.
         by_id: dict[str, str] = {}
         for r in results:
-            # AgentExecutorResponse.agent_run_response.text contains concatenated assistant text
-            by_id[r.executor_id] = r.agent_run_response.text
+            # AgentExecutorResponse.agent_response.text contains concatenated assistant text
+            by_id[r.executor_id] = r.agent_response.text
 
         research_text = by_id.get("researcher", "")
         marketing_text = by_id.get("marketer", "")