agent/agent-framework
1
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Python: Remove deprecated add_agent() calls from workflow samples (#1508)

Browse Source 
* Initial plan

* Remove add_agent calls from workflow samples

Co-authored-by: moonbox3 <35585003+moonbox3@users.noreply.github.com>

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: moonbox3 <35585003+moonbox3@users.noreply.github.com>
This commit is contained in:
Copilot
2025-10-16 19:25:31 -07:00
committed by GitHub
Unverified
parent 2046f16cdb
commit 151efd2e80
4 changed files with 5 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/getting_started/workflows/agents/azure_ai_agents_streaming.py
+2 -7
View File
@@ -16,12 +16,10 @@ A Writer agent generates content, then a Reviewer agent critiques it.
The workflow uses streaming so you can observe incremental AgentRunUpdateEvent chunks as each agent produces tokens.
Purpose:
Show how to wire chat agents into a WorkflowBuilder pipeline using add_agent
with settings for streaming and workflow outputs.
Show how to wire chat agents into a WorkflowBuilder pipeline by adding agents directly as edges.
Demonstrate:
- Automatic streaming of agent deltas via AgentRunUpdateEvent when using run_stream().
- Add an agent via WorkflowBuilder.add_agent() with output_response=True to emit final AgentRunResponse.
- Agents adapt to workflow mode: run_stream() emits incremental updates, run() emits complete responses.
Prerequisites:
@@ -67,13 +65,10 @@ async def main() -> None:
"Provide the feedback in the most concise manner possible."
),
)
# Add agents to workflow with custom settings using add_agent.
# Build the workflow by adding agents directly as edges.
# Agents adapt to workflow mode: run_stream() for incremental updates, run() for complete responses.
# Reviewer agent emits final AgentRunResponse as a workflow output.
workflow = (
WorkflowBuilder()
.add_agent(writer, id="Writer")
.add_agent(reviewer, id="Reviewer", output_response=True)
.set_start_executor(writer)
.add_edge(writer, reviewer)
.build()
python/samples/getting_started/workflows/agents/azure_chat_agents_function_bridge.py
+1 -3
View File
@@ -107,11 +107,9 @@ async def main() -> None:
workflow = (
WorkflowBuilder()
.add_agent(research_agent, id="research_agent")
.add_agent(final_editor_agent, id="final_editor_agent", output_response=True)
.set_start_executor(research_agent)
.add_edge(research_agent, enrich_with_references)
.add_edge(enrich_with_references, final_editor_agent)
.set_start_executor(research_agent)
.build()
)
python/samples/getting_started/workflows/agents/azure_chat_agents_streaming.py
+2 -8
View File
@@ -13,12 +13,10 @@ A Writer agent generates content, then a Reviewer agent critiques it.
The workflow uses streaming so you can observe incremental AgentRunUpdateEvent chunks as each agent produces tokens.
Purpose:
Show how to wire chat agents into a WorkflowBuilder pipeline using add_agent
with settings for streaming and workflow outputs.
Show how to wire chat agents into a WorkflowBuilder pipeline by adding agents directly as edges.
Demonstrate:
- Automatic streaming of agent deltas via AgentRunUpdateEvent when using run_stream().
- Add an agent via WorkflowBuilder.add_agent() with output_response=True to emit final AgentRunResponse.
- Agents adapt to workflow mode: run_stream() emits incremental updates, run() emits complete responses.
Prerequisites:
@@ -51,14 +49,10 @@ async def main():
)
# Build the workflow using the fluent builder.
# Add agents to workflow with custom settings using add_agent.
# Agents adapt to workflow mode: run_stream() for incremental updates, run() for complete responses.
# Reviewer agent emits final AgentRunResponse as a workflow output.
# Set the start node and connect an edge from writer to reviewer.
# Agents adapt to workflow mode: run_stream() for incremental updates, run() for complete responses.
workflow = (
WorkflowBuilder()
.add_agent(writer_agent, id="Writer")
.add_agent(reviewer_agent, id="Reviewer", output_response=True)
.set_start_executor(writer_agent)
.add_edge(writer_agent, reviewer_agent)
.build()
python/samples/getting_started/workflows/agents/azure_chat_agents_tool_calls_with_feedback.py
-2
View File
@@ -167,8 +167,6 @@ async def main() -> None:
workflow = (
WorkflowBuilder()
.add_agent(writer_agent, id="Writer")
.add_agent(final_editor_agent, id="FinalEditor", output_response=True)
.set_start_executor(writer_agent)
.add_edge(writer_agent, feedback_coordinator)
.add_edge(feedback_coordinator, request_info_executor)