Langfuse

Import from @anvia/langfuse.

LangfuseTracingOptions

type LangfuseTracingOptions = {
  publicKey?: string;
  secretKey?: string;
  baseUrl?: string;
  environment?: string;
  release?: string;
};

Purpose: configure Langfuse tracing and scoring.

Return behavior: consumed by langfuse.create(...).

Notable errors: scoring requires both publicKey and secretKey.

LangfuseTracing

type LangfuseTracing = AgentObserver & {
  flush(): Promise<void>;
  shutdown(): Promise<void>;
  score(args: LangfuseScoreArgs): Promise<void>;
};

Purpose: Agent observer with Langfuse lifecycle and scoring methods.

Return behavior: can be passed to AgentBuilder.observe(...).

Notable errors: score(...) throws without a trace id or credentials and rejects on Langfuse API failures.

LangfuseScoreArgs

type LangfuseScoreArgs = {
  traceId?: string;
  observationId?: string;
  name: string;
  value: number;
  comment?: string;
  metadata?: Record<string, JsonValue | undefined>;
};

Purpose: submit Langfuse scores for a trace or observation.

Return behavior: consumed by LangfuseTracing.score(...).

Notable errors: score submission requires a trace id and Langfuse credentials.

langfuse

const langfuse: {
  create(options?: LangfuseTracingOptions): LangfuseTracing;
};

Purpose: factory for Langfuse tracing observers.

Return behavior: starts an OpenTelemetry SDK with a Langfuse span processor and returns an observer.

Notable errors: construction or later flush/shutdown can fail through OpenTelemetry or Langfuse dependencies.

Eval Reporter

type LangfuseEvalReporterOptions = {
  publishInvalid?: boolean;
  strict?: boolean;
};

function createLangfuseEvalReporter<Input = unknown, Output = unknown, Expected = unknown>(
  tracing: Pick<LangfuseTracing, "score">,
  options?: LangfuseEvalReporterOptions,
): EvalReporter<Input, Output, Expected>;

Purpose: bridge core eval metric results to Langfuse scores.

Return behavior: returns an EvalReporter for runEvalSuite(...). Invalid outcomes are skipped unless publishInvalid is true.

Notable errors: with strict: true, missing trace ids reject the reporter call; scoring errors reject through the supplied tracing object.