| AgentRunDiagnosticsContext |
Carries an NexusLabs.Needlr.AgentFramework.Diagnostics.IAgentRunDiagnostics snapshot through the Microsoft.Extensions.AI.Evaluation evaluator pipeline so that Needlr-native deterministic evaluators can score execution-mode, tool-call trajectory, and termination behaviour without being re-invoked against the LLM. |
| AgentRunDiagnosticsEvaluationExtensions |
Extensions that convert NexusLabs.Needlr.AgentFramework.Diagnostics.IAgentRunDiagnostics into the input shape expected by Microsoft.Extensions.AI.Evaluation evaluators. |
| EfficiencyEvaluator |
Deterministic evaluator that scores the token efficiency and cost profile of an agent run from the captured NexusLabs.Needlr.AgentFramework.Diagnostics.IAgentRunDiagnostics snapshot carried in an AgentRunDiagnosticsContext. |
| EvaluationCaptureChatClient |
Microsoft.Extensions.AI.DelegatingChatClient that persists every LLM request/response pair to an IEvaluationCaptureStore and replays cached responses on subsequent calls with an identical request. Intended to make evaluator runs deterministic and cheap to re-execute. |
| EvaluationCaptureChatClientExtensions |
Extension methods for opting in to EvaluationCaptureChatClient capture/replay behavior. |
| EvaluationQualityGate |
Configurable quality gate that asserts evaluation metrics meet defined thresholds. Designed for CI pipelines — call Assert(EvaluationResult[]) after running evaluators to fail the build when metrics regress. |
| FileEvaluationCaptureStore |
Disk-backed IEvaluationCaptureStore that persists each response as a single JSON file under a caller-supplied directory. File names are the request hash plus a .json extension. |
| IterationCoherenceEvaluator |
Deterministic evaluator that scores the iteration coherence of an iterative-loop agent run from the captured NexusLabs.Needlr.AgentFramework.Diagnostics.IAgentRunDiagnostics snapshot carried in an AgentRunDiagnosticsContext. |
| PipelineCostEvaluator |
Deterministic evaluator that scores token usage and cost breakdown per stage of a pipeline run from the captured NexusLabs.Needlr.AgentFramework.Diagnostics.IPipelineRunResult snapshot carried in a PipelineEvaluationContext. |
| PipelineEvaluationContext |
Carries an NexusLabs.Needlr.AgentFramework.Diagnostics.IPipelineRunResult through the Microsoft.Extensions.AI.Evaluation evaluator pipeline so that pipeline-aware evaluators can score per-stage and aggregate metrics without re-invoking the model. |
| PipelineEvaluationExtensions |
Extensions that convert NexusLabs.Needlr.AgentFramework.Diagnostics.IPipelineRunResult into the input shape expected by Microsoft.Extensions.AI.Evaluation evaluators. |
| PipelineStageEvaluator |
Deterministic evaluator that scores per-stage success/failure and overall pipeline health from the captured NexusLabs.Needlr.AgentFramework.Diagnostics.IPipelineRunResult snapshot carried in a PipelineEvaluationContext. |
| QualityGateFailedException |
Thrown by Assert(EvaluationResult[]) when one or more evaluation metrics violate their configured thresholds. |
| TaskCompletionEvaluator |
LLM-judged evaluator that assesses whether an agent actually accomplished the task it was given. Unlike MEAI's TaskAdherenceEvaluator (which checks instruction following), this evaluator checks \<em>task success\</em>: did the agent produce output that satisfies the original request? |
| TerminationAppropriatenessEvaluator |
Deterministic evaluator that scores whether an agent run terminated appropriately, using the captured NexusLabs.Needlr.AgentFramework.Diagnostics.IAgentRunDiagnostics snapshot carried in an AgentRunDiagnosticsContext. |
| ToolCallTrajectoryEvaluator |
Deterministic evaluator that scores the tool-call trajectory of an agent run from the captured NexusLabs.Needlr.AgentFramework.Diagnostics.IAgentRunDiagnostics snapshot carried in an AgentRunDiagnosticsContext. |