mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Tao Chen
e3b4b6662b
* feat(workflows): Make telemetry opt-in via WithOpenTelemetry() - Add WorkflowTelemetryOptions class with EnableSensitiveData property - Add WorkflowTelemetryContext to manage ActivitySource lifecycle - Add WithOpenTelemetry() extension method on WorkflowBuilder - Update all workflow components to use telemetry context: - WorkflowBuilder, Workflow, Executor - InProcessRunnerContext, InProcessRunner - LockstepRunEventStream, StreamingRunEventStream - All edge runners (Direct, FanIn, FanOut, Response) - Telemetry is now disabled by default - Users must call WithOpenTelemetry() to enable spans/activities BREAKING CHANGE: Workflow telemetry is now opt-in. Users who relied on automatic telemetry must add .WithOpenTelemetry() to their workflow builder. * refactor: Pass telemetry context as parameter instead of via interface - Remove IWorkflowContextWithTelemetry interface - Add internal ExecuteAsync overload that accepts WorkflowTelemetryContext - Public ExecuteAsync delegates with WorkflowTelemetryContext.Disabled - InProcessRunner passes TelemetryContext when calling ExecuteAsync - BoundContext now implements IWorkflowContext (not the removed interface) * Add optional ActivitySource parameter to WithOpenTelemetry Allow users to provide their own ActivitySource when enabling telemetry, giving them better control over the ActivitySource lifecycle. When not provided, the framework creates one internally (existing behavior). Changes: - Add optional activitySource parameter to WithOpenTelemetry() extension - Update WorkflowTelemetryContext to accept external ActivitySource - Add unit test for user-provided ActivitySource scenario * Add component-level telemetry control with disable flags Allow users to selectively disable specific activity types via WorkflowTelemetryOptions. All activities are enabled by default. New disable flags: - DisableWorkflowBuild: Disables workflow.build activities - DisableWorkflowRun: Disables workflow_invoke activities - DisableExecutorProcess: Disables executor.process activities - DisableEdgeGroupProcess: Disables edge_group.process activities - DisableMessageSend: Disables message.send activities Added helper methods to WorkflowTelemetryContext for each activity type and updated all activity creation sites to use them. * Implement EnableSensitiveData to log executor input/output When EnableSensitiveData is true in WorkflowTelemetryOptions, executor input and output are logged as JSON-serialized attributes in the executor.process activity. New activity tags: - executor.input: JSON serialized input message - executor.output: JSON serialized output result (non-void only) Added suppression attributes for AOT/trimming warnings since this is an opt-in feature for debugging/diagnostics. * Refactor activity start methods to centralize tagging logic Move tagging logic into WorkflowTelemetryContext methods: - StartExecutorProcessActivity now accepts executorId, executorType, messageType, and message; sets all tags including executor.input when EnableSensitiveData is true - Added SetExecutorOutput method to set executor.output after execution - StartMessageSendActivity now accepts sourceId, targetId, and message; sets all tags including message.content when EnableSensitiveData is true Simplified Executor.cs and InProcessRunnerContext.cs by removing inline tagging code. Added message.content tag constant. * Revert Python changes * Update samples and code cleanup * Fix file formatting * Add comment * Add telemetry configuration to declarative workflow * Remove delays in tests * Address comments
e3b4b6662b
ยท
2026-02-09 23:10:50 +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 |
| Sub-Workflows | Demonstrates composing workflows hierarchically by embedding workflows as executors |
| Mixed Workflow with Agents and Executors | Shows how to mix agents and executors with adapter pattern for type conversion and protocol handling |
| Writer-Critic Workflow | Demonstrates iterative refinement with quality gates, max iteration safety, multiple message handlers, and conditional routing for feedback loops |
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 |
| Group Chat with Tool Approval | Shows multi-agent group chat with tool approval requests and human-in-the-loop interaction |
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 |
|---|---|
| Declarative | 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 |