@langfuse/client 4.1.0-alpha.1 → 4.1.0

package/dist/index.d.cts

@@ -120,6 +120,14 @@ type ExperimentParams<Input = any, ExpectedOutput = any, Metadata extends Record
      * Choose a descriptive name that identifies the experiment's purpose.
      */
     name: string;
+    /**
+     * Optional exact name for the experiment run.
+     *
+     * If provided, this will be used as the exact dataset run name if the data
+     * contains Langfuse dataset items. If not provided, this will default to
+     * the experiment name appended with an ISO timestamp.
+     */
+    runName?: string;
     /**
      * Optional description explaining the experiment's purpose.
      *
@@ -227,10 +235,10 @@ type ExperimentItemResult<Input = any, ExpectedOutput = any, Metadata extends Re
  * console.log(`Average score: ${avgScore?.value}`);
  *
  * // Print formatted results
- * console.log(await result.prettyPrint());
+ * console.log(await result.format());
  *
  * // Print summary with individual item results
- * console.log(await result.prettyPrint({ includeItemResults: true }));
+ * console.log(await result.format({ includeItemResults: true }));
  *
  * // Link to dataset run (if available)
  * if (result.datasetRunUrl) {
@@ -241,6 +249,13 @@ type ExperimentItemResult<Input = any, ExpectedOutput = any, Metadata extends Re
  * @public
  */
 type ExperimentResult<Input = any, ExpectedOutput = any, Metadata extends Record<string, any> = Record<string, any>> = {
+    /**
+     * The experiment run name.
+     *
+     * This is equal to the dataset run name if experiment was on Langfuse dataset.
+     * Either the provided runName parameter or generated name (experiment name + timestamp).
+     */
+    runName: string;
     /**
      * ID of the dataset run in Langfuse (only for experiments on Langfuse datasets).
      *
@@ -273,7 +288,7 @@ type ExperimentResult<Input = any, ExpectedOutput = any, Metadata extends Record
      */
     runEvaluations: Evaluation[];
     /**
-     * Function to format and display experiment results in a human-readable format.
+     * Function to format experiment results in a human-readable format.
      *
      * Generates a comprehensive, nicely formatted summary including individual results,
      * aggregate statistics, evaluation scores, and links to traces and dataset runs.
@@ -282,7 +297,7 @@ type ExperimentResult<Input = any, ExpectedOutput = any, Metadata extends Record
      * @param options.includeItemResults - Whether to include individual item details (default: false)
      * @returns Promise resolving to formatted string representation
      */
-    prettyPrint: (options?: {
+    format: (options?: {
         includeItemResults?: boolean;
     }) => Promise<string>;
 };
@@ -301,6 +316,7 @@ type ExperimentResult<Input = any, ExpectedOutput = any, Metadata extends Record
  * const dataset = await langfuse.dataset.get("my-dataset");
  * const result = await dataset.runExperiment({
  *   name: "Model Evaluation",
+ *   runName: "Model Evaluation Run 1", // optional
  *   task: myTask,
  *   evaluators: [myEvaluator]
  * });
@@ -469,6 +485,7 @@ declare class DatasetManager {
      *
      * const result = await dataset.runExperiment({
      *   name: "GPT-4 Benchmark",
+     *   runName: "GPT-4 Benchmark v1.2", // optional exact run name
      *   description: "Evaluating GPT-4 on our benchmark tasks",
      *   task: async ({ input }) => {
      *     const response = await openai.chat.completions.create({
@@ -485,7 +502,7 @@ declare class DatasetManager {
      *   ]
      * });
      *
-     * console.log(await result.prettyPrint());
+     * console.log(await result.format());
      * ```
      *
      * @example Handling large datasets
@@ -549,7 +566,7 @@ declare class DatasetManager {
  *   ]
  * });
  *
- * console.log(await result.prettyPrint());
+ * console.log(await result.format());
  * ```
  *
  * @example Using with Langfuse datasets
@@ -597,6 +614,7 @@ declare class ExperimentManager {
      *
      * @param config - The experiment configuration
      * @param config.name - Human-readable name for the experiment
+     * @param config.runName - Optional exact name for the experiment run (defaults to name + timestamp)
      * @param config.description - Optional description of the experiment's purpose
      * @param config.metadata - Optional metadata to attach to the experiment run
      * @param config.data - Array of data items to process (ExperimentItem[] or DatasetItem[])
@@ -606,10 +624,11 @@ declare class ExperimentManager {
      * @param config.maxConcurrency - Maximum number of concurrent task executions (default: Infinity)
      *
      * @returns Promise that resolves to experiment results including:
+     *   - runName: The experiment run name (either provided or generated)
      *   - itemResults: Results for each processed data item
      *   - runEvaluations: Results from run-level evaluators
      *   - datasetRunId: ID of the dataset run (if using Langfuse datasets)
-     *   - prettyPrint: Function to format and display results
+     *   - format: Function to format results for display
      *
      * @throws {Error} When task execution fails and cannot be handled gracefully
      * @throws {Error} When required evaluators fail critically
@@ -669,6 +688,7 @@ declare class ExperimentManager {
      *
      * @param params - Parameters for item execution
      * @param params.experimentName - Name of the parent experiment
+     * @param params.experimentRunName - Run name for the parent experiment
      * @param params.experimentDescription - Description of the parent experiment
      * @param params.experimentMetadata - Metadata for the parent experiment
      * @param params.item - The data item to process
@@ -758,6 +778,20 @@ declare class ExperimentManager {
      */
     private formatValue;
     private isOtelRegistered;
+    /**
+     * Creates an experiment run name based on provided parameters.
+     *
+     * If runName is provided, returns it directly. Otherwise, generates
+     * a name by combining the experiment name with an ISO timestamp.
+     *
+     * @param params - Parameters for run name creation
+     * @param params.name - The experiment name
+     * @param params.runName - Optional provided run name
+     * @returns The final run name to use
+     *
+     * @internal
+     */
+    private createExperimentRunName;
 }
 
 /**
@@ -1501,7 +1535,7 @@ declare class LangfuseClient {
      *   ]
      * });
      *
-     * console.log(await result.prettyPrint());
+     * console.log(await result.format());
      * ```
      *
      * @example Using with datasets
@@ -1674,10 +1708,10 @@ declare class LangfuseClient {
  * @example Basic usage with AutoEvals
  * ```typescript
  * import { Factuality, Levenshtein } from 'autoevals';
- * import { autoevalsToLangfuseEvaluator } from '@langfuse/client';
+ * import { createEvaluatorFromAutoevals } from '@langfuse/client';
  *
- * const factualityEvaluator = autoevalsToLangfuseEvaluator(Factuality);
- * const levenshteinEvaluator = autoevalsToLangfuseEvaluator(Levenshtein);
+ * const factualityEvaluator = createEvaluatorFromAutoevals(Factuality);
+ * const levenshteinEvaluator = createEvaluatorFromAutoevals(Levenshtein);
  *
  * await langfuse.experiment.run({
  *   name: "AutoEvals Integration Test",
@@ -1691,7 +1725,7 @@ declare class LangfuseClient {
  * ```typescript
  * import { Factuality } from 'autoevals';
  *
- * const factualityEvaluator = autoevalsToLangfuseEvaluator(
+ * const factualityEvaluator = createEvaluatorFromAutoevals(
  *   Factuality,
  *   { model: 'gpt-4o' } // Additional params for AutoEvals
  * );
@@ -1710,7 +1744,7 @@ declare class LangfuseClient {
  * @public
  * @since 4.0.0
  */
-declare function autoevalsToLangfuseEvaluator<E extends CallableFunction>(autoevalEvaluator: E, params?: Params<E>): Evaluator;
+declare function createEvaluatorFromAutoevals<E extends CallableFunction>(autoevalEvaluator: E, params?: Params<E>): Evaluator;
 /**
  * Utility type to extract parameter types from AutoEvals evaluator functions.
  *
@@ -1723,4 +1757,4 @@ declare function autoevalsToLangfuseEvaluator<E extends CallableFunction>(autoev
  */
 type Params<E> = Parameters<E extends (...args: any[]) => any ? E : never>[0] extends infer P ? Omit<P, "input" | "output" | "expected"> : never;
 
-export { type ChatMessageOrPlaceholder, ChatMessageType, ChatPromptClient, type CreateChatPromptBodyWithPlaceholders, DatasetManager, type Evaluation, type Evaluator, type EvaluatorParams, type ExperimentItem, type ExperimentItemResult, ExperimentManager, type ExperimentParams, type ExperimentResult, type ExperimentTask, type ExperimentTaskParams, type FetchedDataset, type LangchainMessagesPlaceholder, LangfuseClient, type LangfuseClientParams, type LangfuseMediaResolveMediaReferencesParams, type LinkDatasetItemFunction, MediaManager, PromptManager, type RunEvaluator, type RunEvaluatorParams, type RunExperimentOnDataset, ScoreManager, TextPromptClient, autoevalsToLangfuseEvaluator };
+export { type ChatMessageOrPlaceholder, ChatMessageType, ChatPromptClient, type CreateChatPromptBodyWithPlaceholders, DatasetManager, type Evaluation, type Evaluator, type EvaluatorParams, type ExperimentItem, type ExperimentItemResult, ExperimentManager, type ExperimentParams, type ExperimentResult, type ExperimentTask, type ExperimentTaskParams, type FetchedDataset, type LangchainMessagesPlaceholder, LangfuseClient, type LangfuseClientParams, type LangfuseMediaResolveMediaReferencesParams, type LinkDatasetItemFunction, MediaManager, PromptManager, type RunEvaluator, type RunEvaluatorParams, type RunExperimentOnDataset, ScoreManager, TextPromptClient, createEvaluatorFromAutoevals };

package/dist/index.d.ts

@@ -120,6 +120,14 @@ type ExperimentParams<Input = any, ExpectedOutput = any, Metadata extends Record
      * Choose a descriptive name that identifies the experiment's purpose.
      */
     name: string;
+    /**
+     * Optional exact name for the experiment run.
+     *
+     * If provided, this will be used as the exact dataset run name if the data
+     * contains Langfuse dataset items. If not provided, this will default to
+     * the experiment name appended with an ISO timestamp.
+     */
+    runName?: string;
     /**
      * Optional description explaining the experiment's purpose.
      *
@@ -227,10 +235,10 @@ type ExperimentItemResult<Input = any, ExpectedOutput = any, Metadata extends Re
  * console.log(`Average score: ${avgScore?.value}`);
  *
  * // Print formatted results
- * console.log(await result.prettyPrint());
+ * console.log(await result.format());
  *
  * // Print summary with individual item results
- * console.log(await result.prettyPrint({ includeItemResults: true }));
+ * console.log(await result.format({ includeItemResults: true }));
  *
  * // Link to dataset run (if available)
  * if (result.datasetRunUrl) {
@@ -241,6 +249,13 @@ type ExperimentItemResult<Input = any, ExpectedOutput = any, Metadata extends Re
  * @public
  */
 type ExperimentResult<Input = any, ExpectedOutput = any, Metadata extends Record<string, any> = Record<string, any>> = {
+    /**
+     * The experiment run name.
+     *
+     * This is equal to the dataset run name if experiment was on Langfuse dataset.
+     * Either the provided runName parameter or generated name (experiment name + timestamp).
+     */
+    runName: string;
     /**
      * ID of the dataset run in Langfuse (only for experiments on Langfuse datasets).
      *
@@ -273,7 +288,7 @@ type ExperimentResult<Input = any, ExpectedOutput = any, Metadata extends Record
      */
     runEvaluations: Evaluation[];
     /**
-     * Function to format and display experiment results in a human-readable format.
+     * Function to format experiment results in a human-readable format.
      *
      * Generates a comprehensive, nicely formatted summary including individual results,
      * aggregate statistics, evaluation scores, and links to traces and dataset runs.
@@ -282,7 +297,7 @@ type ExperimentResult<Input = any, ExpectedOutput = any, Metadata extends Record
      * @param options.includeItemResults - Whether to include individual item details (default: false)
      * @returns Promise resolving to formatted string representation
      */
-    prettyPrint: (options?: {
+    format: (options?: {
         includeItemResults?: boolean;
     }) => Promise<string>;
 };
@@ -301,6 +316,7 @@ type ExperimentResult<Input = any, ExpectedOutput = any, Metadata extends Record
  * const dataset = await langfuse.dataset.get("my-dataset");
  * const result = await dataset.runExperiment({
  *   name: "Model Evaluation",
+ *   runName: "Model Evaluation Run 1", // optional
  *   task: myTask,
  *   evaluators: [myEvaluator]
  * });
@@ -469,6 +485,7 @@ declare class DatasetManager {
      *
      * const result = await dataset.runExperiment({
      *   name: "GPT-4 Benchmark",
+     *   runName: "GPT-4 Benchmark v1.2", // optional exact run name
      *   description: "Evaluating GPT-4 on our benchmark tasks",
      *   task: async ({ input }) => {
      *     const response = await openai.chat.completions.create({
@@ -485,7 +502,7 @@ declare class DatasetManager {
      *   ]
      * });
      *
-     * console.log(await result.prettyPrint());
+     * console.log(await result.format());
      * ```
      *
      * @example Handling large datasets
@@ -549,7 +566,7 @@ declare class DatasetManager {
  *   ]
  * });
  *
- * console.log(await result.prettyPrint());
+ * console.log(await result.format());
  * ```
  *
  * @example Using with Langfuse datasets
@@ -597,6 +614,7 @@ declare class ExperimentManager {
      *
      * @param config - The experiment configuration
      * @param config.name - Human-readable name for the experiment
+     * @param config.runName - Optional exact name for the experiment run (defaults to name + timestamp)
      * @param config.description - Optional description of the experiment's purpose
      * @param config.metadata - Optional metadata to attach to the experiment run
      * @param config.data - Array of data items to process (ExperimentItem[] or DatasetItem[])
@@ -606,10 +624,11 @@ declare class ExperimentManager {
      * @param config.maxConcurrency - Maximum number of concurrent task executions (default: Infinity)
      *
      * @returns Promise that resolves to experiment results including:
+     *   - runName: The experiment run name (either provided or generated)
      *   - itemResults: Results for each processed data item
      *   - runEvaluations: Results from run-level evaluators
      *   - datasetRunId: ID of the dataset run (if using Langfuse datasets)
-     *   - prettyPrint: Function to format and display results
+     *   - format: Function to format results for display
      *
      * @throws {Error} When task execution fails and cannot be handled gracefully
      * @throws {Error} When required evaluators fail critically
@@ -669,6 +688,7 @@ declare class ExperimentManager {
      *
      * @param params - Parameters for item execution
      * @param params.experimentName - Name of the parent experiment
+     * @param params.experimentRunName - Run name for the parent experiment
      * @param params.experimentDescription - Description of the parent experiment
      * @param params.experimentMetadata - Metadata for the parent experiment
      * @param params.item - The data item to process
@@ -758,6 +778,20 @@ declare class ExperimentManager {
      */
     private formatValue;
     private isOtelRegistered;
+    /**
+     * Creates an experiment run name based on provided parameters.
+     *
+     * If runName is provided, returns it directly. Otherwise, generates
+     * a name by combining the experiment name with an ISO timestamp.
+     *
+     * @param params - Parameters for run name creation
+     * @param params.name - The experiment name
+     * @param params.runName - Optional provided run name
+     * @returns The final run name to use
+     *
+     * @internal
+     */
+    private createExperimentRunName;
 }
 
 /**
@@ -1501,7 +1535,7 @@ declare class LangfuseClient {
      *   ]
      * });
      *
-     * console.log(await result.prettyPrint());
+     * console.log(await result.format());
      * ```
      *
      * @example Using with datasets
@@ -1674,10 +1708,10 @@ declare class LangfuseClient {
  * @example Basic usage with AutoEvals
  * ```typescript
  * import { Factuality, Levenshtein } from 'autoevals';
- * import { autoevalsToLangfuseEvaluator } from '@langfuse/client';
+ * import { createEvaluatorFromAutoevals } from '@langfuse/client';
  *
- * const factualityEvaluator = autoevalsToLangfuseEvaluator(Factuality);
- * const levenshteinEvaluator = autoevalsToLangfuseEvaluator(Levenshtein);
+ * const factualityEvaluator = createEvaluatorFromAutoevals(Factuality);
+ * const levenshteinEvaluator = createEvaluatorFromAutoevals(Levenshtein);
  *
  * await langfuse.experiment.run({
  *   name: "AutoEvals Integration Test",
@@ -1691,7 +1725,7 @@ declare class LangfuseClient {
  * ```typescript
  * import { Factuality } from 'autoevals';
  *
- * const factualityEvaluator = autoevalsToLangfuseEvaluator(
+ * const factualityEvaluator = createEvaluatorFromAutoevals(
  *   Factuality,
  *   { model: 'gpt-4o' } // Additional params for AutoEvals
  * );
@@ -1710,7 +1744,7 @@ declare class LangfuseClient {
  * @public
  * @since 4.0.0
  */
-declare function autoevalsToLangfuseEvaluator<E extends CallableFunction>(autoevalEvaluator: E, params?: Params<E>): Evaluator;
+declare function createEvaluatorFromAutoevals<E extends CallableFunction>(autoevalEvaluator: E, params?: Params<E>): Evaluator;
 /**
  * Utility type to extract parameter types from AutoEvals evaluator functions.
  *
@@ -1723,4 +1757,4 @@ declare function autoevalsToLangfuseEvaluator<E extends CallableFunction>(autoev
  */
 type Params<E> = Parameters<E extends (...args: any[]) => any ? E : never>[0] extends infer P ? Omit<P, "input" | "output" | "expected"> : never;
 
-export { type ChatMessageOrPlaceholder, ChatMessageType, ChatPromptClient, type CreateChatPromptBodyWithPlaceholders, DatasetManager, type Evaluation, type Evaluator, type EvaluatorParams, type ExperimentItem, type ExperimentItemResult, ExperimentManager, type ExperimentParams, type ExperimentResult, type ExperimentTask, type ExperimentTaskParams, type FetchedDataset, type LangchainMessagesPlaceholder, LangfuseClient, type LangfuseClientParams, type LangfuseMediaResolveMediaReferencesParams, type LinkDatasetItemFunction, MediaManager, PromptManager, type RunEvaluator, type RunEvaluatorParams, type RunExperimentOnDataset, ScoreManager, TextPromptClient, autoevalsToLangfuseEvaluator };
+export { type ChatMessageOrPlaceholder, ChatMessageType, ChatPromptClient, type CreateChatPromptBodyWithPlaceholders, DatasetManager, type Evaluation, type Evaluator, type EvaluatorParams, type ExperimentItem, type ExperimentItemResult, ExperimentManager, type ExperimentParams, type ExperimentResult, type ExperimentTask, type ExperimentTaskParams, type FetchedDataset, type LangchainMessagesPlaceholder, LangfuseClient, type LangfuseClientParams, type LangfuseMediaResolveMediaReferencesParams, type LinkDatasetItemFunction, MediaManager, PromptManager, type RunEvaluator, type RunEvaluatorParams, type RunExperimentOnDataset, ScoreManager, TextPromptClient, createEvaluatorFromAutoevals };

package/dist/index.mjs

@@ -59,6 +59,7 @@ var DatasetManager = class {
    *
    * const result = await dataset.runExperiment({
    *   name: "GPT-4 Benchmark",
+   *   runName: "GPT-4 Benchmark v1.2", // optional exact run name
    *   description: "Evaluating GPT-4 on our benchmark tasks",
    *   task: async ({ input }) => {
    *     const response = await openai.chat.completions.create({
@@ -75,7 +76,7 @@ var DatasetManager = class {
    *   ]
    * });
    *
-   * console.log(await result.prettyPrint());
+   * console.log(await result.format());
    * ```
    *
    * @example Handling large datasets
@@ -184,6 +185,7 @@ var ExperimentManager = class {
    *
    * @param config - The experiment configuration
    * @param config.name - Human-readable name for the experiment
+   * @param config.runName - Optional exact name for the experiment run (defaults to name + timestamp)
    * @param config.description - Optional description of the experiment's purpose
    * @param config.metadata - Optional metadata to attach to the experiment run
    * @param config.data - Array of data items to process (ExperimentItem[] or DatasetItem[])
@@ -193,10 +195,11 @@ var ExperimentManager = class {
    * @param config.maxConcurrency - Maximum number of concurrent task executions (default: Infinity)
    *
    * @returns Promise that resolves to experiment results including:
+   *   - runName: The experiment run name (either provided or generated)
    *   - itemResults: Results for each processed data item
    *   - runEvaluations: Results from run-level evaluators
    *   - datasetRunId: ID of the dataset run (if using Langfuse datasets)
-   *   - prettyPrint: Function to format and display results
+   *   - format: Function to format results for display
    *
    * @throws {Error} When task execution fails and cannot be handled gracefully
    * @throws {Error} When required evaluators fail critically
@@ -249,11 +252,16 @@ var ExperimentManager = class {
       evaluators,
       task,
       name,
+      runName: providedRunName,
       description,
       metadata,
       maxConcurrency: batchSize = Infinity,
       runEvaluators
     } = config;
+    const runName = this.createExperimentRunName({
+      name,
+      runName: providedRunName
+    });
     if (!this.isOtelRegistered()) {
       this.logger.warn(
         "OpenTelemetry has not been set up. Traces will not be sent to Langfuse.See our docs on how to set up OpenTelemetry: https://langfuse.com/docs/observability/sdk/typescript/setup#tracing-setup"
@@ -268,11 +276,26 @@ var ExperimentManager = class {
           evaluators,
           task,
           experimentName: name,
+          experimentRunName: runName,
           experimentDescription: description,
           experimentMetadata: metadata
         });
       });
-      const results = await Promise.all(promises);
+      const settledResults = await Promise.allSettled(promises);
+      const results = settledResults.reduce(
+        (acc, settledResult) => {
+          if (settledResult.status === "fulfilled") {
+            acc.push(settledResult.value);
+          } else {
+            const errorMessage = settledResult.reason instanceof Error ? settledResult.reason.message : String(settledResult.reason);
+            this.logger.error(
+              `Task failed with error: ${errorMessage}. Skipping item.`
+            );
+          }
+          return acc;
+        },
+        []
+      );
       itemResults.push(...results);
     }
     const datasetRunId = itemResults.length > 0 ? itemResults[0].datasetRunId : void 0;
@@ -311,11 +334,12 @@ var ExperimentManager = class {
     }
     await this.langfuseClient.score.flush();
     return {
+      runName,
       itemResults,
       datasetRunId,
       datasetRunUrl,
       runEvaluations,
-      prettyPrint: async (options) => {
+      format: async (options) => {
         var _a;
         return await this.prettyPrintResults({
           datasetRunUrl,
@@ -323,6 +347,7 @@ var ExperimentManager = class {
           originalData: data,
           runEvaluations,
           name: config.name,
+          runName,
           description: config.description,
           includeItemResults: (_a = options == null ? void 0 : options.includeItemResults) != null ? _a : false
         });
@@ -341,6 +366,7 @@ var ExperimentManager = class {
    *
    * @param params - Parameters for item execution
    * @param params.experimentName - Name of the parent experiment
+   * @param params.experimentRunName - Run name for the parent experiment
    * @param params.experimentDescription - Description of the parent experiment
    * @param params.experimentMetadata - Metadata for the parent experiment
    * @param params.item - The data item to process
@@ -355,7 +381,7 @@ var ExperimentManager = class {
    */
   async runItem(params) {
     const { item, evaluators = [], task, experimentMetadata = {} } = params;
-    const { output, traceId } = await startActiveObservation(
+    const { output, traceId, observationId } = await startActiveObservation(
       "experiment-item-run",
       async (span) => {
         var _a;
@@ -364,26 +390,28 @@ var ExperimentManager = class {
           input: item.input,
           output: output2,
           metadata: {
-            experimentName: params.experimentName,
+            experiment_name: params.experimentName,
+            experiment_run_name: params.experimentRunName,
             ...experimentMetadata,
             ...(_a = item.metadata) != null ? _a : {},
             ..."id" in item && "datasetId" in item ? {
-              datasetId: item["datasetId"],
-              datasetItemId: item["id"]
+              dataset_id: item["datasetId"],
+              dataset_item_id: item["id"]
             } : {}
           }
         });
-        return { output: output2, traceId: span.traceId };
+        return { output: output2, traceId: span.traceId, observationId: span.id };
       }
     );
     let datasetRunId = void 0;
     if ("id" in item) {
       await this.langfuseClient.api.datasetRunItems.create({
-        runName: params.experimentName,
+        runName: params.experimentRunName,
         runDescription: params.experimentDescription,
         metadata: params.experimentMetadata,
         datasetItemId: item.id,
-        traceId
+        traceId,
+        observationId
       }).then((result) => {
         datasetRunId = result.datasetRunId;
       }).catch(
@@ -505,6 +533,7 @@ ${JSON.stringify(params2)}
       originalData,
       runEvaluations,
       name,
+      runName,
       description,
       includeItemResults = false
     } = params;
@@ -562,7 +591,7 @@ ${index + 1}. Item ${index + 1}:
     } else {
       output += `Individual Results: Hidden (${itemResults.length} items)
 `;
-      output += "\u{1F4A1} Call prettyPrint({ includeItemResults: true }) to view them\n";
+      output += "\u{1F4A1} Call format({ includeItemResults: true }) to view them\n";
     }
     const totalItems = itemResults.length;
     const evaluationNames = new Set(
@@ -571,7 +600,9 @@ ${index + 1}. Item ${index + 1}:
     output += `
 ${"\u2500".repeat(50)}
 `;
-    output += `\u{1F4CA} ${name}`;
+    output += `\u{1F9EA} Experiment: ${name}`;
+    output += `
+\u{1F4CB} Run name: ${runName}`;
     if (description) {
       output += ` - ${description}`;
     }
@@ -646,6 +677,26 @@ Run Evaluations:`;
     }
     return tracerProvider.constructor.name !== "NoopTracerProvider";
   }
+  /**
+   * Creates an experiment run name based on provided parameters.
+   *
+   * If runName is provided, returns it directly. Otherwise, generates
+   * a name by combining the experiment name with an ISO timestamp.
+   *
+   * @param params - Parameters for run name creation
+   * @param params.name - The experiment name
+   * @param params.runName - Optional provided run name
+   * @returns The final run name to use
+   *
+   * @internal
+   */
+  createExperimentRunName(params) {
+    if (params.runName) {
+      return params.runName;
+    }
+    const isoTimestamp = (/* @__PURE__ */ new Date()).toISOString();
+    return `${params.name} - ${isoTimestamp}`;
+  }
 };
 
 // src/media/index.ts
@@ -1850,7 +1901,7 @@ var LangfuseClient = class {
 };
 
 // src/experiment/adapters.ts
-function autoevalsToLangfuseEvaluator(autoevalEvaluator, params) {
+function createEvaluatorFromAutoevals(autoevalEvaluator, params) {
   const langfuseEvaluator = async (langfuseEvaluatorParams) => {
     var _a;
     const score = await autoevalEvaluator({
@@ -1877,6 +1928,6 @@ export {
   PromptManager,
   ScoreManager,
   TextPromptClient,
-  autoevalsToLangfuseEvaluator
+  createEvaluatorFromAutoevals
 };
 //# sourceMappingURL=index.mjs.map