ci(benchmark): gate scenario speed relative to the runner

Before the protocol, time the frozen engine on the two-year scenario, best
of three, and fail any scenario whose mean planning time exceeds its
multiplier times that calibration. Multipliers come from development-machine
ratios with about 1.5x headroom until #286 tightens them. The 300-second
timeout stays only as a hang guard. The benchmark keeps running on push and
pull_request events because the push run gates image publication.

This replaces the absolute 300-second acceptance protocol named in #78.

Refs #285

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

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

@@ -1,10 +1,13 @@
 import { vi } from 'vitest';
+import { calculatePlanningAsyncInternal } from '../services/frozen-engine/leave-planner.core.frozen.mjs';
 import { createPlanningCalculation } from '../services/leave-planner.service';
 import {
+	BENCHMARK_BUDGET_MULTIPLIERS,
 	BENCHMARK_REPORT_HEADER,
 	benchmarkReport,
 	benchmarkReportRows,
 	benchmarkScenarios,
+	budgetViolations,
 	runLeavePlannerBenchmark,
 } from './leave-planner-benchmark';
 
@@ -66,6 +69,16 @@ describe('leave planner benchmark protocol', () => {
 					),
 				).toHaveLength(2);
 			}
+			// Frozen engine (a871f8f) on 'two years', best of three: the runner-speed yardstick.
+			const calibrationRequest = scenarios.find((item) => item.name === 'two years')!.request;
+			let calibrationMs = Infinity;
+			for (let run = 0; run < 3; run++) {
+				const request = structuredClone(calibrationRequest);
+				const start = performance.now();
+				await calculatePlanningAsyncInternal({ ...request, calculationDate: '2024-01-01' });
+				calibrationMs = Math.min(calibrationMs, performance.now() - start);
+			}
+			console.info(`calibration\tfrozen two years best of 3\t${calibrationMs.toFixed(1)}`);
 			console.info(BENCHMARK_REPORT_HEADER);
 			const measurements = await runLeavePlannerBenchmark(2, (rows) =>
 				console.info(benchmarkReportRows(rows)),
@@ -106,6 +119,13 @@ describe('leave planner benchmark protocol', () => {
 			expect(report).toContain('planning_ms\twall_ms');
 			expect(report).toContain('planning_work_ms\tpeak_main_thread_heap_bytes');
 			expect(report).toContain('\tbaseline\t');
+			const violations = budgetViolations(
+				measurements,
+				calibrationMs,
+				BENCHMARK_BUDGET_MULTIPLIERS,
+			);
+			if (violations.length)
+				throw new Error(`Benchmark over budget:\n${violations.join('\n')}`);
 		} finally {
 			vi.stubGlobal('window', browserWindow);
 		}