CompletionMarkerLoopEvaluator Class
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
A LoopEvaluator that stops the loop once a configured marker string appears in the agent's latest response, and otherwise continues with feedback asking the agent to keep working and to emit the marker when done.
public sealed class CompletionMarkerLoopEvaluator : Microsoft.Agents.AI.LoopEvaluatortype CompletionMarkerLoopEvaluator = class
inherit LoopEvaluatorPublic NotInheritable Class CompletionMarkerLoopEvaluator
Inherits LoopEvaluator- Inheritance
Remarks
The feedback produced while the marker is absent is built from a template (see FeedbackMessageTemplate) with the configured marker substituted for CompletionMarkerPlaceholder, and the agent's latest response text substituted for LastResponsePlaceholder. How that feedback is delivered to the agent (and whether the session is reset) is decided by the LoopAgent that consumes this evaluator.
Constructors
| Name | Description |
|---|---|
| CompletionMarkerLoopEvaluator(String, CompletionMarkerLoopEvaluatorOptions) |
Initializes a new instance of the CompletionMarkerLoopEvaluator class. |
Fields
| Name | Description |
|---|---|
| CompletionMarkerPlaceholder |
The placeholder token within DefaultFeedbackMessageTemplate (or a custom FeedbackMessageTemplate) that is replaced with the configured completion marker. |
| DefaultFeedbackMessageTemplate |
The default template used to build the feedback produced while the completion marker is absent. |
| LastResponsePlaceholder |
The placeholder token within a custom FeedbackMessageTemplate that is replaced with the text of the agent's latest response. This is substituted on each evaluation, so it lets the feedback echo back what the agent previously produced — useful when the consuming LoopAgent uses FreshContextPerIteration, where the agent would otherwise have no record of its prior output. |
Methods
| Name | Description |
|---|---|
| EvaluateAsync(LoopContext, CancellationToken) |
Evaluates the loop state after an iteration and decides whether to re-invoke the wrapped agent and what feedback to provide. |