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/benchmark-budget.spec.ts

@@ -0,0 +1,30 @@
+import { BenchmarkMeasurement, budgetViolations } from './leave-planner-benchmark';
+
+const measure = (scenario: string, planningMs: number) =>
+	({ scenario, planningMs }) as BenchmarkMeasurement;
+
+describe('benchmark budget gate', () => {
+	const multipliers = { a: 2 };
+	it('accepts a mean within multiplier x calibration', () => {
+		expect(budgetViolations([measure('a', 150), measure('a', 250)], 100, multipliers)).toEqual(
+			[],
+		);
+	});
+	it('reports measured time, budget, multiplier and calibration when over budget', () => {
+		const [message] = budgetViolations(
+			[measure('a', 300), measure('a', 320)],
+			100,
+			multipliers,
+		);
+		expect(message).toContain('a:');
+		expect(message).toContain('measured 310.0 ms');
+		expect(message).toContain('budget 200.0 ms');
+		expect(message).toContain('multiplier 2');
+		expect(message).toContain('calibration 100.0 ms');
+	});
+	it('fails a scenario without a multiplier', () => {
+		expect(budgetViolations([measure('new', 1)], 100, multipliers)).toEqual([
+			'new: no budget multiplier defined',
+		]);
+	});
+});