agent/agent-framework
2
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

[BREAKING] Python: Standardize orchestration outputs as list of ChatMessage. Allow agent as group chat manager. (#2291)

Browse Source 
* Standardize orchestration outputs as list of chatmessage. Add chat options to group chat prompt manager

* refactor group chat

* Improve group chat manager

* README Update

* Cleanup

* Add comment

* More cleanup

* Standardize termination condition for group chat

* Improvements on termination logic

* Fix tests

* Fix new line

* PR feedback

* Update ChatKit based on OpenAI type change

* Raise error if response format is not expected type

* Only one starting executor required. Add tests.

* Add magentic start executor test
This commit is contained in:
Evan Mattson
2025-11-26 16:51:04 +09:00
committed by GitHub
Unverified
parent ed53ba158b
commit 907d79ab3c
19 changed files with 1724 additions and 573 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/README.md
+1 -91
View File
@@ -268,97 +268,7 @@ This directory contains samples demonstrating the capabilities of Microsoft Agen
## Workflows
### Start Here
| File | Description |
|------|-------------|
| [`getting_started/workflows/_start-here/step1_executors_and_edges.py`](./getting_started/workflows/_start-here/step1_executors_and_edges.py) | Step 1: Foundational patterns: Executors and edges |
| [`getting_started/workflows/_start-here/step2_agents_in_a_workflow.py`](./getting_started/workflows/_start-here/step2_agents_in_a_workflow.py) | Step 2: Agents in a Workflow non-streaming |
| [`getting_started/workflows/_start-here/step3_streaming.py`](./getting_started/workflows/_start-here/step3_streaming.py) | Step 3: Agents in a workflow with streaming |
### Agents in Workflows
| File | Description |
|------|-------------|
| [`getting_started/workflows/agents/azure_ai_agents_streaming.py`](./getting_started/workflows/agents/azure_ai_agents_streaming.py) | Sample: Agents in a workflow with streaming |
| [`getting_started/workflows/agents/azure_chat_agents_function_bridge.py`](./getting_started/workflows/agents/azure_chat_agents_function_bridge.py) | Sample: Two agents connected by a function executor bridge |
| [`getting_started/workflows/agents/azure_chat_agents_streaming.py`](./getting_started/workflows/agents/azure_chat_agents_streaming.py) | Sample: Agents in a workflow with streaming |
| [`getting_started/workflows/agents/azure_chat_agents_tool_calls_with_feedback.py`](./getting_started/workflows/agents/azure_chat_agents_tool_calls_with_feedback.py) | Sample: Tool-enabled agents with human feedback |
| [`getting_started/workflows/agents/custom_agent_executors.py`](./getting_started/workflows/agents/custom_agent_executors.py) | Step 2: Agents in a Workflow non-streaming |
| [`getting_started/workflows/agents/workflow_as_agent_human_in_the_loop.py`](./getting_started/workflows/agents/workflow_as_agent_human_in_the_loop.py) | Sample: Workflow Agent with Human-in-the-Loop |
| [`getting_started/workflows/agents/workflow_as_agent_reflection_pattern.py`](./getting_started/workflows/agents/workflow_as_agent_reflection_pattern.py) | Sample: Workflow as Agent with Reflection and Retry Pattern |
### Checkpoint
| File | Description |
|------|-------------|
| [`getting_started/workflows/checkpoint/checkpoint_with_human_in_the_loop.py`](./getting_started/workflows/checkpoint/checkpoint_with_human_in_the_loop.py) | Sample: Checkpoint + human-in-the-loop quickstart |
| [`getting_started/workflows/checkpoint/checkpoint_with_resume.py`](./getting_started/workflows/checkpoint/checkpoint_with_resume.py) | Sample: Checkpointing and Resuming a Workflow (with an Agent stage) |
| [`getting_started/workflows/checkpoint/sub_workflow_checkpoint.py`](./getting_started/workflows/checkpoint/sub_workflow_checkpoint.py) | Sample: Checkpointing for workflows that embed sub-workflows |
### Composition
| File | Description |
|------|-------------|
| [`getting_started/workflows/composition/sub_workflow_basics.py`](./getting_started/workflows/composition/sub_workflow_basics.py) | Sample: Sub-Workflows (Basics) |
| [`getting_started/workflows/composition/sub_workflow_parallel_requests.py`](./getting_started/workflows/composition/sub_workflow_parallel_requests.py) | Sample: Sub-workflow with parallel request handling by specialized interceptors |
| [`getting_started/workflows/composition/sub_workflow_request_interception.py`](./getting_started/workflows/composition/sub_workflow_request_interception.py) | Sample: Sub-Workflows with Request Interception |
### Control Flow
| File | Description |
|------|-------------|
| [`getting_started/workflows/control-flow/edge_condition.py`](./getting_started/workflows/control-flow/edge_condition.py) | Sample: Conditional routing with structured outputs |
| [`getting_started/workflows/control-flow/multi_selection_edge_group.py`](./getting_started/workflows/control-flow/multi_selection_edge_group.py) | Step 06b — Multi-Selection Edge Group sample |
| [`getting_started/workflows/control-flow/sequential_executors.py`](./getting_started/workflows/control-flow/sequential_executors.py) | Sample: Sequential workflow with streaming |
| [`getting_started/workflows/control-flow/sequential_streaming.py`](./getting_started/workflows/control-flow/sequential_streaming.py) | Sample: Foundational sequential workflow with streaming using function-style executors |
| [`getting_started/workflows/control-flow/simple_loop.py`](./getting_started/workflows/control-flow/simple_loop.py) | Sample: Simple Loop (with an Agent Judge) |
| [`getting_started/workflows/control-flow/switch_case_edge_group.py`](./getting_started/workflows/control-flow/switch_case_edge_group.py) | Sample: Switch-Case Edge Group with an explicit Uncertain branch |
### Human-in-the-Loop
| File | Description |
|------|-------------|
| [`getting_started/workflows/human-in-the-loop/guessing_game_with_human_input.py`](./getting_started/workflows/human-in-the-loop/guessing_game_with_human_input.py) | Sample: Human in the loop guessing game |
| [`getting_started/workflows/human-in-the-loop/agents_with_approval_requests.py`](./getting_started/workflows/human-in-the-loop/agents_with_approval_requests.py) | Sample: Agents with Approval Requests in Workflows |
### Orchestration
| File | Description |
|------|-------------|
| [`getting_started/workflows/orchestration/concurrent_agents.py`](./getting_started/workflows/orchestration/concurrent_agents.py) | Sample: Concurrent fan-out/fan-in (agent-only API) with default aggregator |
| [`getting_started/workflows/orchestration/concurrent_custom_agent_executors.py`](./getting_started/workflows/orchestration/concurrent_custom_agent_executors.py) | Sample: Concurrent Orchestration with Custom Agent Executors |
| [`getting_started/workflows/orchestration/concurrent_custom_aggregator.py`](./getting_started/workflows/orchestration/concurrent_custom_aggregator.py) | Sample: Concurrent Orchestration with Custom Aggregator |
| [`getting_started/workflows/orchestration/group_chat_prompt_based_manager.py`](./getting_started/workflows/orchestration/group_chat_prompt_based_manager.py) | Sample: Group Chat Orchestration with LLM-based manager |
| [`getting_started/workflows/orchestration/group_chat_simple_selector.py`](./getting_started/workflows/orchestration/group_chat_simple_selector.py) | Sample: Group Chat Orchestration with function-based speaker selector |
| [`getting_started/workflows/orchestration/handoff_simple.py`](./getting_started/workflows/orchestration/handoff_simple.py) | Sample: Handoff Orchestration with simple agent handoff pattern |
| [`getting_started/workflows/orchestration/handoff_specialist_to_specialist.py`](./getting_started/workflows/orchestration/handoff_specialist_to_specialist.py) | Sample: Handoff Orchestration with specialist-to-specialist routing |
| [`getting_started/workflows/orchestration/handoff_return_to_previous`](./getting_started/workflows/orchestration/handoff_return_to_previous.py) | Return-to-previous routing: after user input, routes back to the previous specialist instead of coordinator using `.enable_return_to_previous()` |
| [`getting_started/workflows/orchestration/magentic.py`](./getting_started/workflows/orchestration/magentic.py) | Sample: Magentic Orchestration (agentic task planning with multi-agent execution) |
| [`getting_started/workflows/orchestration/magentic_checkpoint.py`](./getting_started/workflows/orchestration/magentic_checkpoint.py) | Sample: Magentic Orchestration with Checkpointing |
| [`getting_started/workflows/orchestration/magentic_human_plan_update.py`](./getting_started/workflows/orchestration/magentic_human_plan_update.py) | Sample: Magentic Orchestration with Human Plan Review |
| [`getting_started/workflows/orchestration/sequential_agents.py`](./getting_started/workflows/orchestration/sequential_agents.py) | Sample: Sequential workflow (agent-focused API) with shared conversation context |
| [`getting_started/workflows/orchestration/sequential_custom_executors.py`](./getting_started/workflows/orchestration/sequential_custom_executors.py) | Sample: Sequential workflow mixing agents and a custom summarizer executor |
### Parallelism
| File | Description |
|------|-------------|
| [`getting_started/workflows/parallelism/aggregate_results_of_different_types.py`](./getting_started/workflows/parallelism/aggregate_results_of_different_types.py) | Sample: Concurrent fan out and fan in with two different tasks that output results of different types |
| [`getting_started/workflows/parallelism/fan_out_fan_in_edges.py`](./getting_started/workflows/parallelism/fan_out_fan_in_edges.py) | Sample: Concurrent fan out and fan in with three domain agents |
| [`getting_started/workflows/parallelism/map_reduce_and_visualization.py`](./getting_started/workflows/parallelism/map_reduce_and_visualization.py) | Sample: Map reduce word count with fan out and fan in over file backed intermediate results |
### State Management
| File | Description |
|------|-------------|
| [`getting_started/workflows/state-management/shared_states_with_agents.py`](./getting_started/workflows/state-management/shared_states_with_agents.py) | Sample: Shared state with agents and conditional routing |
### Visualization
| File | Description |
|------|-------------|
| [`getting_started/workflows/visualization/concurrent_with_visualization.py`](./getting_started/workflows/visualization/concurrent_with_visualization.py) | Sample: Concurrent (Fan-out/Fan-in) with Agents + Visualization |
View the list of Workflows samples [here](./getting_started/workflows/README.md).
## Sample Guidelines