chore: update example baselines and remove eval_set compat shims

apps/cli/src/commands/eval/artifact-writer.ts

@@ -463,8 +463,7 @@ function safeTargetId(target: string | undefined): string {
 }
 
 function getDataset(result: EvaluationResult): string | undefined {
-  const record = result as EvaluationResult & { eval_set?: string; evalSet?: string };
-  return result.dataset ?? record.eval_set ?? record.evalSet;
+  return result.dataset;
 }
 
 function buildArtifactSubdir(result: EvaluationResult): string {

apps/cli/src/commands/pipeline/bench.ts

@@ -45,7 +45,7 @@ export const evalBenchCommand = command({
     const manifest = JSON.parse(await readFile(join(exportDir, 'manifest.json'), 'utf8'));
     const testIds: string[] = manifest.test_ids;
     const targetName: string = manifest.target?.name ?? 'unknown';
-    const evalSet: string = manifest.dataset ?? manifest.eval_set ?? '';
+    const evalSet: string = manifest.dataset ?? '';
     const experiment: string | undefined = manifest.experiment;
     const safeEvalSet = evalSet ? evalSet.replace(/[\/\\:*?"<>|]/g, '_') : '';
 

apps/cli/src/commands/pipeline/grade.ts

@@ -40,7 +40,7 @@ export const evalGradeCommand = command({
     const manifestPath = join(exportDir, 'manifest.json');
     const manifest = JSON.parse(await readFile(manifestPath, 'utf8'));
     const testIds: string[] = manifest.test_ids;
-    const evalSet: string = manifest.dataset ?? manifest.eval_set ?? '';
+    const evalSet: string = manifest.dataset ?? '';
     const safeEvalSet = evalSet ? evalSet.replace(/[\/\\:*?"<>|]/g, '_') : '';
 
     let totalGraders = 0;

apps/cli/src/commands/results/manifest.ts

@@ -12,7 +12,6 @@ export interface ResultManifestRecord {
   readonly test_id?: string;
   readonly eval_id?: string;
   readonly dataset?: string;
-  readonly eval_set?: string; // deprecated alias for dataset
   readonly experiment?: string;
   readonly target?: string;
   readonly score: number;
@@ -125,7 +124,7 @@ function hydrateManifestRecord(baseDir: string, record: ResultManifestRecord): E
   return {
     timestamp: record.timestamp,
     testId,
-    dataset: record.dataset ?? record.eval_set,
+    dataset: record.dataset,
     target: record.target,
     score: record.score,
     executionStatus: record.execution_status,

apps/cli/src/commands/trace/stats.ts

@@ -110,7 +110,6 @@ function groupResults(results: RawResult[], groupBy?: string): GroupedResults[]
         key = result.target ?? 'unknown';
         break;
       case 'dataset':
-      case 'eval-set':
         key = result.dataset ?? 'unknown';
         break;
       case 'test-id':

examples/showcase/offline-grader-benchmark/scripts/score-grader-benchmark.ts

@@ -17,7 +17,6 @@ type EvalResult = {
   timestamp?: string;
   test_id?: string;
   dataset?: string;
-  eval_set?: string; // backward compat
   target?: string;
   input?: string;
   output_text?: string;
@@ -222,7 +221,7 @@ for (const line of rawResults) {
   const output = {
     timestamp: result.timestamp,
     test_id: result.test_id,
-    dataset: result.dataset ?? result.eval_set,
+    dataset: result.dataset,
     target: labelOverride ?? result.target ?? labelFromPath(resultsPath),
     input: result.input,
     output_text: result.output_text,

packages/core/src/evaluation/validation/eval-file.schema.ts

@@ -350,7 +350,6 @@ const EvalTestSchema = z.object({
   metadata: z.record(z.unknown()).optional(),
   conversation_id: z.string().optional(),
   dataset: z.string().optional(),
-  eval_set: z.string().optional(), // deprecated alias for dataset
   note: z.string().optional(),
 });
 

plugins/agentv-dev/skills/agentv-eval-writer/references/eval-schema.json

@@ -6390,9 +6390,6 @@
                   "dataset": {
                     "type": "string"
                   },
-                  "eval_set": {
-                    "type": "string"
-                  },
                   "note": {
                     "type": "string"
                   }
@@ -12704,9 +12701,6 @@
                   "dataset": {
                     "type": "string"
                   },
-                  "eval_set": {
-                    "type": "string"
-                  },
                   "note": {
                     "type": "string"
                   }