Index

NexusLabs.Foundry.Langfuse Namespace

Classes
LangfuseDataset	Describes one hosted Langfuse dataset.
LangfuseDatasetCaseSource<TCase>	Materializes one hosted Langfuse dataset as a finite provider-neutral experiment case source.
LangfuseDatasetItem	A single Langfuse dataset item — one eval case. Upserted via UpsertItemAsync(LangfuseDatasetItem) and later referenced by an experiment run.
LangfuseDatasetItemSnapshot	Captures one active hosted Langfuse dataset item at the selected dataset version.
LangfuseDatasetSelection	Selects the latest state or an explicit timestamped version of a hosted Langfuse dataset.
LangfuseDatasetSnapshot	Contains one hosted dataset and its complete ordered active-item selection.
LangfuseDrainHealth	Describes the latest local flush or shutdown drain.
LangfuseEvaluateAndRecordOptions	Configures evaluator execution and Langfuse score projection for one LangfuseEvaluationScoreExtensions evaluate-and-record operation.
LangfuseEvaluationScoreExtensions	Convenience extensions for projecting Microsoft.Extensions.AI.Evaluation results onto a Langfuse scenario trace as scores.
LangfuseEvaluationScoreOptions	Configures score identities when projecting an Microsoft.Extensions.AI.Evaluation.EvaluationResult to Langfuse.
LangfuseException	The exception thrown when a request to the Langfuse API fails.
LangfuseExperimentDecisionScoreOptions	Configures optional categorical publication of the canonical experiment decision.
LangfuseExperimentItemLinkCounts	Contains immutable counts of experiment item-link outcomes.
LangfuseExperimentItemLinkResult	Describes the direct REST publication outcome for one dataset-run-item link.
LangfuseExperimentItemOptions	Configures the scenario and dataset-link behavior for one experiment item execution.
LangfuseExperimentItemResult<T>	Contains the callback value and Langfuse publication status for one experiment item.
LangfuseExperimentItemScopeExtensions	Creates provider-neutral experiment item scopes from the built-in Langfuse client or session.
LangfuseExperimentItemScopeOptions<TCase>	Configures Langfuse scenario traces and publication behavior for provider-neutral experiment trials.
LangfuseExperimentItemScopeProvider<TCase,TOutput>	Creates one Langfuse scenario trace for each statistical trial and reactivates it around every retry attempt and item evaluation.
LangfuseExperimentItemScoreResult	Describes one canonical item metric projected to a Langfuse trace score.
LangfuseExperimentResultSink<TCase,TOutput>	Projects completed canonical experiment measurements to Langfuse trace and dataset-run scores without changing the canonical quality decision.
LangfuseExperimentResultSinkExtensions	Creates provider-neutral result sinks from the built-in Langfuse client or session.
LangfuseExperimentResultSinkOptions<TCase,TOutput>	Configures canonical item, run-evaluation, and decision score projection to Langfuse.
LangfuseExperimentResultSinkSnapshot	Captures the latest detailed score projection performed by a Langfuse experiment result sink.
LangfuseExperimentRunEvaluationScoreResult	Describes one successful canonical run-evaluation metric projected to a dataset-run score.
LangfuseExperimentRunOptions	Configures the Langfuse dataset run created implicitly by experiment item links.
LangfuseExperimentRunPublicationSnapshot	Provides an immutable snapshot of direct REST publication observed by one experiment run.
LangfuseExperimentRunScoreResult	Describes the publication outcome for one score against a Langfuse dataset run.
LangfuseExperimentScoreCounts	Contains immutable counts of experiment score outcomes.
LangfuseHttpOptions	Configures bounded timeout and retry behavior for Langfuse REST API requests.
LangfuseInProcessResourceLockProvider	Coordinates Langfuse resource creation within one process.
LangfuseMetric	One metric in a LangfuseMetricsQuery: a measure plus an aggregation. The result column is named {Aggregation}_{Measure} (for example avg_value, sum_totalCost).
LangfuseMetricsFilter	One filter in a LangfuseMetricsQuery.
LangfuseMetricsQuery	A query against the Langfuse Metrics API (GET /api/public/metrics). Use it to read aggregates back from Langfuse — for example to drive a CI quality gate from recorded eval scores.
LangfuseMetricsResult	The result of a LangfuseMetricsQuery. Each row is a dictionary of column name to value; aggregated columns are named {Aggregation}_{Measure} and dimension columns keep their field name.
LangfuseModelPrice	A model price definition registered with Langfuse so it can compute cost for generations whose model it does not price out of the box (for example mock or internal model names). Langfuse derives cost from token usage and these prices when a generation carries no explicit cost.
LangfuseOptions	Configuration for exporting Foundry agent telemetry and evaluation scores to Langfuse.
LangfusePage<T>	Contains one validated page returned by a Langfuse list endpoint.
LangfusePrompt	A prompt fetched from Langfuse prompt management. Use Text for a text prompt's content, and pass the prompt to SetPrompt(LangfusePrompt) to link generations to the exact version that was used.
LangfusePublicationFailure	Describes why a Langfuse publication operation did not complete.
LangfusePublicationHealth	Collects thread-safe Langfuse publication-health counters.
LangfusePublicationHealthSnapshot	Provides an immutable point-in-time view of Langfuse publication health.
LangfusePublicationOperationHealth	Describes direct REST publication outcomes for one operation category.
LangfuseResourceLockKey	Represents a stable opaque key for a project-scoped Langfuse resource lock.
LangfuseRetryHealth	Describes bounded Langfuse REST retry attempts by cause.
LangfuseScoreConfig	Declares the shape of a named Langfuse score so the dashboard renders consistent ranges, colors, and category sets and validates incoming values. Created via EnsureScoreConfigAsync(LangfuseScoreConfig, CancellationToken).
LangfuseScoreConfigCategory	One allowed category for a Categorical score config.
LangfuseScoreError	Describes a single failed attempt to upload an evaluation score to Langfuse. Passed to ScoreErrorCallback when NonFatal is in effect, so callers can log the loss with their own logger.
LangfuseScoreOptions	Configures one score publication to Langfuse.
LangfuseServiceCollectionExtensions	Registers Langfuse OTLP export and a complete non-owning ILangfuseClient facade on an Microsoft.Extensions.DependencyInjection.IServiceCollection for dependency-injection-based applications.
LangfuseShutdownOutcome	Reports whether local OpenTelemetry trace and metric provider shutdown completed.
LangfuseTelemetry	Entry point for exporting Foundry agent telemetry to Langfuse without requiring a generic host. Designed for evals, console apps, and test fixtures that build telemetry by hand.
LangfuseTraceExportHealth	Describes local trace queue and exporter outcomes.
LangfuseTraceExportOptions	Configures bounded local batching for Langfuse trace export.

Interfaces
ILangfuseClient	Provides the complete non-owning Langfuse client surface for scenarios, experiments, datasets, score configuration, metrics, model pricing, prompts, comments, and known-trace scoring.
ILangfuseDatasetClient	Reads, creates, and populates Langfuse datasets — the named collections of evaluation cases that experiment runs are scored against.
ILangfuseExperimentRun	Represents an in-progress Langfuse experiment (dataset run). Each call to RunItemAsync<T>(string, Func<ILangfuseScenario,CancellationToken,Task<T>>, LangfuseExperimentItemOptions, CancellationToken) executes one dataset item inside an active scenario trace and links it to this run, so scores recorded on that trace roll up into the experiment-comparison view.
ILangfuseMetricsClient	Reads aggregates back from Langfuse via the Metrics API, so recorded eval scores (and observation metrics) can drive CI quality gates and dashboards from Langfuse as the source of truth.
ILangfuseModelClient	Registers model price definitions with Langfuse so it can compute cost for generations whose model it does not price by default.
ILangfusePromptClient	Fetches and creates prompts in Langfuse prompt management, so the prompt an eval runs against lives in Langfuse and the generations link to the exact version that was used.
ILangfuseResourceLockProvider	Coordinates project-resource creation across Langfuse client instances.
ILangfuseScenario	Represents a single Langfuse trace scoped to one eval scenario or agent run. Created via BeginScenario(string, string, string, IEnumerable<string>, IReadOnlyDictionary<string,string>).
ILangfuseScoreClient	Records Langfuse scores against a known trace id. Registered in dependency injection by AddFoundryLangfuse(this IServiceCollection) for ASP.NET Core and generic-host applications that score their own request traces.
ILangfuseScoreConfigClient	Idempotently registers Langfuse score configs so eval scores appear on the dashboard with defined data types, ranges, and category sets.
ILangfuseSession	Represents a standalone Langfuse export owner. Extends the non-owning ILangfuseClient facade with explicit flush, shutdown, and disposal lifecycle.

Enums
LangfuseDatasetRunIdentityStatus	Describes whether a Langfuse experiment run has one authoritative dataset-run id.
LangfuseDrainStatus	Describes the most recent local telemetry drain attempt.
LangfuseExperimentApiPublicationStatus	Summarizes direct Langfuse REST publication observed by one experiment run instance.
LangfuseExperimentItemLinkFailureMode	Controls whether a Langfuse dataset-run-item link failure prevents experiment item execution.
LangfuseExperimentItemLinkStatus	Describes whether an experiment item trace was linked to its Langfuse dataset run.
LangfuseExperimentScoreStatus	Describes the direct API outcome for one experiment score.
LangfuseMetricsView	The Langfuse Metrics API view to query. Determines which measures and dimensions are available.
LangfuseProviderShutdownStatus	Describes the local OpenTelemetry shutdown state for one telemetry provider.
LangfusePublicationFailureCode	Identifies a machine-actionable Langfuse publication failure category.
LangfuseRegion	Identifies the Langfuse deployment that traces and scores are sent to. Used to derive the base URL of the OTLP ingestion endpoint when Host is not set explicitly.
LangfuseScoreDataType	The data type of a Langfuse score, controlling how the score value is interpreted and displayed.
LangfuseScoreFailureMode	Controls how a Langfuse scenario reacts when uploading an evaluation score to the Langfuse Scores API fails.

Delegates
LangfuseDatasetItemMapper<TCase>(LangfuseDatasetItemSnapshot)	Maps one hosted Langfuse dataset item to a provider-neutral experiment case.