test(benchmark): report each scenario as it finishes

Print the report header before the measured runs and each scenario's rows
as soon as its repetitions complete, so a timed-out job still shows the
finished scenarios. The final report, scenarios, warm-ups, repetitions,
assertions, heap limit and timeout are unchanged.

Refs #281

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/app/benchmark/leave-planner-benchmark.spec.ts

@@ -1,7 +1,9 @@
 import { vi } from 'vitest';
 import { createPlanningCalculation } from '../services/leave-planner.service';
 import {
+	BENCHMARK_REPORT_HEADER,
 	benchmarkReport,
+	benchmarkReportRows,
 	benchmarkScenarios,
 	runLeavePlannerBenchmark,
 } from './leave-planner-benchmark';
@@ -64,7 +66,10 @@ describe('leave planner benchmark protocol', () => {
 					),
 				).toHaveLength(2);
 			}
-			const measurements = await runLeavePlannerBenchmark(2);
+			console.info(BENCHMARK_REPORT_HEADER);
+			const measurements = await runLeavePlannerBenchmark(2, (rows) =>
+				console.info(benchmarkReportRows(rows)),
+			);
 			for (const [name, placements] of [
 				['two years', 60],
 				['three years', 90],

src/app/benchmark/leave-planner-benchmark.ts

@@ -193,18 +193,24 @@ function resultSummary(outcome: PlanningOutcome): {
 	return { outcome: outcome.kind, placements: 0 };
 }
 
-export async function runLeavePlannerBenchmark(repetitions = 1): Promise<BenchmarkMeasurement[]> {
+export async function runLeavePlannerBenchmark(
+	repetitions = 1,
+	onScenario?: (measurements: BenchmarkMeasurement[]) => void,
+): Promise<BenchmarkMeasurement[]> {
 	const scenarios = benchmarkScenarios();
 	for (const scenario of scenarios) await warmUpScenario(scenario);
 
 	const measurements: BenchmarkMeasurement[] = [];
 	for (const scenario of scenarios) {
+		const scenarioMeasurements: BenchmarkMeasurement[] = [];
 		let baseline: string | undefined;
 		for (let repetition = 1; repetition <= repetitions; repetition++) {
 			const result = await measureRepetition(scenario, repetition, baseline);
-			measurements.push(result.measurement);
+			scenarioMeasurements.push(result.measurement);
 			baseline ??= result.stable;
 		}
+		measurements.push(...scenarioMeasurements);
+		onScenario?.(scenarioMeasurements);
 	}
 	return measurements;
 }
@@ -271,12 +277,12 @@ async function measureRepetition(
 	}
 }
 
-export function benchmarkReport(measurements: BenchmarkMeasurement[]): string {
-	const header =
-		'scenario\trepetition\tpreparation_ms\tplanning_ms\twall_ms\toutcome\tlast_stage\tplacements\tdeterministic\tmax_ui_delay_ms\tplanning_work_ms\tpeak_main_thread_heap_bytes';
-	return [
-		header,
-		...measurements.map((item) =>
+export const BENCHMARK_REPORT_HEADER =
+	'scenario\trepetition\tpreparation_ms\tplanning_ms\twall_ms\toutcome\tlast_stage\tplacements\tdeterministic\tmax_ui_delay_ms\tplanning_work_ms\tpeak_main_thread_heap_bytes';
+
+export function benchmarkReportRows(measurements: BenchmarkMeasurement[]): string {
+	return measurements
+		.map((item) =>
 			[
 				item.scenario,
 				item.repetition,
@@ -291,6 +297,13 @@ export function benchmarkReport(measurements: BenchmarkMeasurement[]): string {
 				item.planningWorkMs?.toFixed(1) ?? '',
 				item.peakMainThreadHeapBytes ?? '',
 			].join('\t'),
-		),
-	].join('\n');
+		)
+		.join('\n');
+}
+
+export function benchmarkReport(measurements: BenchmarkMeasurement[]): string {
+	// Empty input yields the header alone, with no trailing newline.
+	return measurements.length
+		? [BENCHMARK_REPORT_HEADER, benchmarkReportRows(measurements)].join('\n')
+		: BENCHMARK_REPORT_HEADER;
 }