[BREAKING] Python: Merge send_responses into run method (#3720)

* Streamline workflow run api with send responses in one method

* Fixes

* Address copilot feedback

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

@@ -199,7 +199,7 @@ async def main() -> None:
     )
 
     # Initiate the first run of the workflow.
-    # Runs are not isolated; state is preserved across multiple calls to run or send_responses_streaming.
+    # Runs are not isolated; state is preserved across multiple calls to run.
     stream = workflow.run(
         "Create a short launch blurb for the LumenX desk lamp. Emphasize adjustability and warm lighting.",
         stream=True,
@@ -209,7 +209,7 @@ async def main() -> None:
     while pending_responses is not None:
         # Run the workflow until there is no more human feedback to provide,
         # in which case this workflow completes.
-        stream = workflow.send_responses_streaming(pending_responses)
+        stream = workflow.run(stream=True, responses=pending_responses)
         pending_responses = await process_event_stream(stream)
 
     print("\nWorkflow complete.")

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

@@ -249,7 +249,7 @@ async def main() -> None:
     )
 
     # Initiate the first run of the workflow.
-    # Runs are not isolated; state is preserved across multiple calls to run or send_responses_streaming.
+    # Runs are not isolated; state is preserved across multiple calls to run.
     events = await workflow.run(incoming_email)
     request_info_events = events.get_request_info_events()
 
@@ -276,7 +276,7 @@ async def main() -> None:
             print("Performing automatic approval for demo purposes...")
             responses[request_info_event.request_id] = data.to_function_approval_response(approved=True)
 
-        events = await workflow.send_responses(responses)
+        events = await workflow.run(responses=responses)
         request_info_events = events.get_request_info_events()
 
     # The output should only come from conclude_workflow executor and it's a single string

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

@@ -183,14 +183,14 @@ async def main() -> None:
     )
 
     # Initiate the first run of the workflow.
-    # Runs are not isolated; state is preserved across multiple calls to run or send_responses_streaming.
+    # Runs are not isolated; state is preserved across multiple calls to run.
     stream = workflow.run("Analyze the impact of large language models on software development.", stream=True)
 
     pending_responses = await process_event_stream(stream)
     while pending_responses is not None:
         # Run the workflow until there is no more human feedback to provide,
         # in which case this workflow completes.
-        stream = workflow.send_responses_streaming(pending_responses)
+        stream = workflow.run(stream=True, responses=pending_responses)
         pending_responses = await process_event_stream(stream)
 
 

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

@@ -147,7 +147,7 @@ async def main() -> None:
     )
 
     # Initiate the first run of the workflow.
-    # Runs are not isolated; state is preserved across multiple calls to run or send_responses_streaming.
+    # Runs are not isolated; state is preserved across multiple calls to run.
     stream = workflow.run(
         "Discuss how our team should approach adopting AI tools for productivity. "
         "Consider benefits, risks, and implementation strategies.",
@@ -158,7 +158,7 @@ async def main() -> None:
     while pending_responses is not None:
         # Run the workflow until there is no more human feedback to provide,
         # in which case this workflow completes.
-        stream = workflow.send_responses_streaming(pending_responses)
+        stream = workflow.run(stream=True, responses=pending_responses)
         pending_responses = await process_event_stream(stream)
 
 

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

@@ -29,7 +29,7 @@ the workflow completes when idle with no pending work.
 
 Purpose:
 Show how to integrate a human step in the middle of an LLM workflow by using
-`request_info` and `send_responses_streaming`.
+`request_info` and `run(responses=..., stream=True)`.
 
 Demonstrate:
 - Alternating turns between an AgentExecutor and a human, driven by events.
@@ -42,11 +42,11 @@ Prerequisites:
 - Basic familiarity with WorkflowBuilder, executors, edges, events, and streaming runs.
 """
 
-# How human-in-the-loop is achieved via `request_info` and `send_responses_streaming`:
+# How human-in-the-loop is achieved via `request_info` and `run(responses=..., stream=True)`:
 # - An executor (TurnManager) calls `ctx.request_info` with a payload (HumanFeedbackRequest).
 # - The workflow run pauses and emits a  with the payload and the request_id.
 # - The application captures the event, prompts the user, and collects replies.
-# - The application calls `send_responses_streaming` with a map of request_ids to replies.
+# - The application calls `run(stream=True, responses=...)` with a map of request_ids to replies.
 # - The workflow resumes, and the response is delivered to the executor method decorated with @response_handler.
 # - The executor can then continue the workflow, e.g., by sending a new message to the agent.
 
@@ -205,14 +205,14 @@ async def main() -> None:
     ).build()
 
     # Initiate the first run of the workflow.
-    # Runs are not isolated; state is preserved across multiple calls to run or send_responses_streaming.
+    # Runs are not isolated; state is preserved across multiple calls to run.
     stream = workflow.run("start", stream=True)
 
     pending_responses = await process_event_stream(stream)
     while pending_responses is not None:
         # Run the workflow until there is no more human feedback to provide,
         # in which case this workflow completes.
-        stream = workflow.send_responses_streaming(pending_responses)
+        stream = workflow.run(stream=True, responses=pending_responses)
         pending_responses = await process_event_stream(stream)
 
     """

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

@@ -13,8 +13,8 @@ using the standard request_info pattern for consistency.
 
 Demonstrate:
 - Configuring request info with `.with_request_info()`
-- Handling  with AgentInputRequest data
-- Injecting responses back into the workflow via send_responses_streaming
+- Handling request_info events with AgentInputRequest data
+- Injecting responses back into the workflow via run(responses=..., stream=True)
 
 Prerequisites:
 - Azure OpenAI configured for AzureOpenAIChatClient with required environment variables
@@ -122,14 +122,14 @@ async def main() -> None:
     )
 
     # Initiate the first run of the workflow.
-    # Runs are not isolated; state is preserved across multiple calls to run or send_responses_streaming.
+    # Runs are not isolated; state is preserved across multiple calls to run.
     stream = workflow.run("Write a brief introduction to artificial intelligence.", stream=True)
 
     pending_responses = await process_event_stream(stream)
     while pending_responses is not None:
         # Run the workflow until there is no more human feedback to provide,
         # in which case this workflow completes.
-        stream = workflow.send_responses_streaming(pending_responses)
+        stream = workflow.run(stream=True, responses=pending_responses)
         pending_responses = await process_event_stream(stream)