mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Stephen Toub
03ef7f054f
* Add AgentWorkflowBuilder group chat
And fix a variety of issues along the way:
- Use DateTime{Offset}.UtcNow rather than Now
- AIAgentHostExecutor shouldn't be publishing empty messages
- Sequential workflows should be flowing all history and not just the output from the previous agent as the input into the next agent
- Renamed some of the new agent workflow methods... still not super happy with the shape, though
- Simplified handoffs builder, e.g. using a hashset with a custom comparer instead of a dictionary
- Improved multi-service use by trying to change assistant->user role for messages created by other agents
- Changed MessageMerger to rely on M.E.AI's coalescing more and to avoid empty contents / text
- Ensured that messages from ChatClientAgent include MessageId and CreatedAt timestamps
- Avoided including instructions for agents in a handoff workflow that don't have any handoffs
- Removed the unnecessary end function in handoffs
- Improved naming of executors to include agent name for debuggability
- Use "N" formatting with Guid.ToString everywhere, to avoid the unnecessary extra dash character which is also not valid in various places (like function tool names)
- Replace `params T[]` with `params IEnumerable<T>` to make public APIs more flexible in what they consume
* Address feedback
- Fix unintentional provider change in sample
03ef7f054f
ยท
2025-09-24 16:38:34 +00:00
History
Workflow Getting Started Samples
The getting started with workflow samples demonstrate the fundamental concepts and functionalities of workflows in Agent Framework.
Samples Overview
Foundational Concepts - Start Here
Please begin with the Foundational samples in order. These three samples introduce the core concepts of executors, edges, agents in workflows, streaming, and workflow construction.
The folder name starts with an underscore (
_Foundational) to ensure it appears first in the explorer view.
| Sample | Concepts |
|---|---|
| Executors and Edges | Minimal workflow with basic executors and edges |
| Streaming | Extends workflows with event streaming |
| Agents | Use agents in workflows |
| Agentic Workflow Patterns | Demonstrates common agentic workflow patterns |
| Multi-Service Workflows | Shows using multiple AI services in the same workflow |
Once completed, please proceed to other samples listed below.
Note that you don't need to follow a strict order after the foundational samples. However, some samples build upon concepts from previous ones, so it's beneficial to be aware of the dependencies.
Agents
| Sample | Concepts |
|---|---|
| Foundry Agents in Workflows | Demonstrates using Azure Foundry Agents within a workflow |
| Custom Agent Executors | Shows how to create a custom agent executor for more complex scenarios |
| Workflow as an Agent | Illustrates how to encapsulate a workflow as an agent |
Concurrent Execution
| Sample | Concepts |
|---|---|
| Fan-Out and Fan-In | Introduces parallel processing with fan-out and fan-in patterns |
Loop
| Sample | Concepts |
|---|---|
| Looping | Shows how to create a loop within a workflow |
Workflow Shared States
| Sample | Concepts |
|---|---|
| Shared States | Demonstrates shared states between executors for data sharing and coordination |
Conditional Edges
| Sample | Concepts |
|---|---|
| Edge Conditions | Introduces conditional edges for dynamic routing based on executor outputs |
| Switch-Case Routing | Extends conditional edges with switch-case routing for multiple paths |
| Multi-Selection Routing | Demonstrates multi-selection routing where one executor can trigger multiple downstream executors |
These 3 samples build upon each other. It's recommended to explore them in sequence to fully grasp the concepts.
Declarative Workflows
| Sample | Concepts |
|---|---|
| DeclarativeWorkflow | Demonstrates execution of declartive workflows. |
Checkpointing
| Sample | Concepts |
|---|---|
| Checkpoint and Resume | Introduces checkpoints for saving and restoring workflow state for time travel purposes |
| Checkpoint and Rehydrate | Demonstrates hydrating a new workflow instance from a saved checkpoint |
| Checkpoint with Human-in-the-Loop | Combines checkpointing with human-in-the-loop interactions |
Human-in-the-Loop
| Sample | Concepts |
|---|---|
| Basic Human-in-the-Loop | Introduces human-in-the-loop interaction using input ports and external requests |