@pennyfarthing/benchmark 10.2.0

package/dist/package-exports.test.js

@@ -0,0 +1,192 @@
+/**
+ * Tests for Story 93-1: Package Shell and Module Migration
+ *
+ * These tests verify that @pennyfarthing/benchmark correctly exports
+ * all functions and types from the two migrated modules:
+ * - job-fair-aggregator (9 functions, 11 types)
+ * - benchmark-integration (11 functions, 12 types)
+ *
+ * RED state: All tests fail because index.ts is an empty barrel.
+ * GREEN state: Tests pass once modules are moved and re-exported.
+ */
+import { describe, it } from 'node:test';
+import assert from 'node:assert';
+import { readFileSync, existsSync } from 'fs';
+import { join, dirname } from 'path';
+import { fileURLToPath } from 'url';
+const __dirname = dirname(fileURLToPath(import.meta.url));
+// Use dynamic import + Record cast so tests compile but fail at runtime
+async function loadPackageIndex() {
+    return await import('./index.js');
+}
+// ============================================================================
+// AC5: Barrel index.ts exports all public functions and types
+// ============================================================================
+describe('Package Exports: job-fair-aggregator functions', () => {
+    it('should export aggregateJobFairResults', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.aggregateJobFairResults, 'function', 'aggregateJobFairResults should be exported as a function');
+    });
+    it('should export getBaselineComparison', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.getBaselineComparison, 'function', 'getBaselineComparison should be exported as a function');
+    });
+    it('should export getRoleStatistics', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.getRoleStatistics, 'function', 'getRoleStatistics should be exported as a function');
+    });
+    it('should export getTopPerformers', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.getTopPerformers, 'function', 'getTopPerformers should be exported as a function');
+    });
+    it('should export getHistoricalTrend', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.getHistoricalTrend, 'function', 'getHistoricalTrend should be exported as a function');
+    });
+    it('should export saveHistoricalSnapshot', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.saveHistoricalSnapshot, 'function', 'saveHistoricalSnapshot should be exported as a function');
+    });
+    it('should export aggregateByDimension', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.aggregateByDimension, 'function', 'aggregateByDimension should be exported as a function');
+    });
+    it('should export getDimensionValues', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.getDimensionValues, 'function', 'getDimensionValues should be exported as a function');
+    });
+    it('should export generateDifferentialReport', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.generateDifferentialReport, 'function', 'generateDifferentialReport should be exported as a function');
+    });
+});
+describe('Package Exports: benchmark-integration functions', () => {
+    it('should export loadBenchmarkData', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.loadBenchmarkData, 'function', 'loadBenchmarkData should be exported as a function');
+    });
+    it('should export getBenchmarkWithFace', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.getBenchmarkWithFace, 'function', 'getBenchmarkWithFace should be exported as a function');
+    });
+    it('should export calculateOceanCorrelation', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.calculateOceanCorrelation, 'function', 'calculateOceanCorrelation should be exported as a function');
+    });
+    it('should export generateCorrelationReport', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.generateCorrelationReport, 'function', 'generateCorrelationReport should be exported as a function');
+    });
+    it('should export getOptimalProfile', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.getOptimalProfile, 'function', 'getOptimalProfile should be exported as a function');
+    });
+    it('should export getRoleRecommendations', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.getRoleRecommendations, 'function', 'getRoleRecommendations should be exported as a function');
+    });
+    it('should export findTopPerformers', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.findTopPerformers, 'function', 'findTopPerformers should be exported as a function');
+    });
+    it('should export queryBenchmarks', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.queryBenchmarks, 'function', 'queryBenchmarks should be exported as a function');
+    });
+    it('should export calculateErrorTypeCorrelation', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.calculateErrorTypeCorrelation, 'function', 'calculateErrorTypeCorrelation should be exported as a function');
+    });
+    it('should export generateOceanErrorHeatMap', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.generateOceanErrorHeatMap, 'function', 'generateOceanErrorHeatMap should be exported as a function');
+    });
+    it('should export generateBenchmarkReport', async () => {
+        const mod = await loadPackageIndex();
+        assert.strictEqual(typeof mod.generateBenchmarkReport, 'function', 'generateBenchmarkReport should be exported as a function');
+    });
+});
+// ============================================================================
+// AC1: package.json exists with correct configuration
+// ============================================================================
+describe('Package Configuration', () => {
+    it('should have correct package name', () => {
+        const pkgPath = join(__dirname, '..', 'package.json');
+        const pkg = JSON.parse(readFileSync(pkgPath, 'utf-8'));
+        assert.strictEqual(pkg.name, '@pennyfarthing/benchmark', 'Package name should be @pennyfarthing/benchmark');
+    });
+    it('should be type: module', () => {
+        const pkgPath = join(__dirname, '..', 'package.json');
+        const pkg = JSON.parse(readFileSync(pkgPath, 'utf-8'));
+        assert.strictEqual(pkg.type, 'module', 'Package should use ESM');
+    });
+    it('should have peer dependency on @pennyfarthing/core', () => {
+        const pkgPath = join(__dirname, '..', 'package.json');
+        const pkg = JSON.parse(readFileSync(pkgPath, 'utf-8'));
+        assert.ok(pkg.peerDependencies?.['@pennyfarthing/core'], 'Should have peer dependency on @pennyfarthing/core');
+    });
+    it('should have peer dependency on @pennyfarthing/shared', () => {
+        const pkgPath = join(__dirname, '..', 'package.json');
+        const pkg = JSON.parse(readFileSync(pkgPath, 'utf-8'));
+        assert.ok(pkg.peerDependencies?.['@pennyfarthing/shared'], 'Should have peer dependency on @pennyfarthing/shared');
+    });
+    it('should have exports map with types and default', () => {
+        const pkgPath = join(__dirname, '..', 'package.json');
+        const pkg = JSON.parse(readFileSync(pkgPath, 'utf-8'));
+        assert.ok(pkg.exports?.['.']?.types, 'Should have types export');
+        assert.ok(pkg.exports?.['.']?.default, 'Should have default export');
+    });
+});
+// ============================================================================
+// AC2: tsconfig.json extends base with composite: true
+// ============================================================================
+describe('TypeScript Configuration', () => {
+    it('should extend tsconfig.base.json', () => {
+        const tsconfigPath = join(__dirname, '..', 'tsconfig.json');
+        const tsconfig = JSON.parse(readFileSync(tsconfigPath, 'utf-8'));
+        assert.strictEqual(tsconfig.extends, '../../tsconfig.base.json', 'Should extend ../../tsconfig.base.json');
+    });
+    it('should have composite: true', () => {
+        const tsconfigPath = join(__dirname, '..', 'tsconfig.json');
+        const tsconfig = JSON.parse(readFileSync(tsconfigPath, 'utf-8'));
+        assert.strictEqual(tsconfig.compilerOptions?.composite, true, 'Should have composite: true');
+    });
+});
+// ============================================================================
+// AC3/AC4: Source files exist in new location
+// ============================================================================
+describe('Source Files Exist', () => {
+    it('should have job-fair-aggregator.js in dist/', () => {
+        const filePath = join(__dirname, 'job-fair-aggregator.js');
+        assert.ok(existsSync(filePath), 'job-fair-aggregator.js should exist in dist/ (compiled from src/)');
+    });
+    it('should have benchmark-integration.js in dist/', () => {
+        const filePath = join(__dirname, 'benchmark-integration.js');
+        assert.ok(existsSync(filePath), 'benchmark-integration.js should exist in dist/ (compiled from src/)');
+    });
+});
+// ============================================================================
+// AC6: Test files exist alongside source
+// ============================================================================
+describe('Test Files Exist', () => {
+    it('should have job-fair-aggregator.test.js in dist/', () => {
+        const filePath = join(__dirname, 'job-fair-aggregator.test.js');
+        assert.ok(existsSync(filePath), 'job-fair-aggregator.test.js should exist in dist/');
+    });
+    it('should have benchmark-integration.test.js in dist/', () => {
+        const filePath = join(__dirname, 'benchmark-integration.test.js');
+        assert.ok(existsSync(filePath), 'benchmark-integration.test.js should exist in dist/');
+    });
+});
+// ============================================================================
+// Export count verification
+// ============================================================================
+describe('Export Completeness', () => {
+    it('should export at least 20 functions total', async () => {
+        const mod = await loadPackageIndex();
+        const exportedFunctions = Object.entries(mod)
+            .filter(([, v]) => typeof v === 'function');
+        assert.ok(exportedFunctions.length >= 20, `Should export at least 20 functions, got ${exportedFunctions.length}: ${exportedFunctions.map(([k]) => k).join(', ')}`);
+    });
+});
+//# sourceMappingURL=package-exports.test.js.map

package/dist/package-exports.test.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"package-exports.test.js","sourceRoot":"","sources":["../src/package-exports.test.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;GAUG;AAEH,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE,MAAM,WAAW,CAAC;AACzC,OAAO,MAAM,MAAM,aAAa,CAAC;AACjC,OAAO,EAAE,YAAY,EAAE,UAAU,EAAE,MAAM,IAAI,CAAC;AAC9C,OAAO,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,MAAM,CAAC;AACrC,OAAO,EAAE,aAAa,EAAE,MAAM,KAAK,CAAC;AAEpC,MAAM,SAAS,GAAG,OAAO,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;AAE1D,wEAAwE;AACxE,KAAK,UAAU,gBAAgB;IAC7B,OAAO,MAAM,MAAM,CAAC,YAAY,CAA4B,CAAC;AAC/D,CAAC;AAED,+EAA+E;AAC/E,8DAA8D;AAC9D,+EAA+E;AAE/E,QAAQ,CAAC,gDAAgD,EAAE,GAAG,EAAE;IAC9D,EAAE,CAAC,uCAAuC,EAAE,KAAK,IAAI,EAAE;QACrD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,uBAAuB,EAAE,UAAU,EAC/D,0DAA0D,CAAC,CAAC;IAChE,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,qCAAqC,EAAE,KAAK,IAAI,EAAE;QACnD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,qBAAqB,EAAE,UAAU,EAC7D,wDAAwD,CAAC,CAAC;IAC9D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,iCAAiC,EAAE,KAAK,IAAI,EAAE;QAC/C,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,iBAAiB,EAAE,UAAU,EACzD,oDAAoD,CAAC,CAAC;IAC1D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,gCAAgC,EAAE,KAAK,IAAI,EAAE;QAC9C,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,gBAAgB,EAAE,UAAU,EACxD,mDAAmD,CAAC,CAAC;IACzD,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,kCAAkC,EAAE,KAAK,IAAI,EAAE;QAChD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,kBAAkB,EAAE,UAAU,EAC1D,qDAAqD,CAAC,CAAC;IAC3D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,sCAAsC,EAAE,KAAK,IAAI,EAAE;QACpD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,sBAAsB,EAAE,UAAU,EAC9D,yDAAyD,CAAC,CAAC;IAC/D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,oCAAoC,EAAE,KAAK,IAAI,EAAE;QAClD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,oBAAoB,EAAE,UAAU,EAC5D,uDAAuD,CAAC,CAAC;IAC7D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,kCAAkC,EAAE,KAAK,IAAI,EAAE;QAChD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,kBAAkB,EAAE,UAAU,EAC1D,qDAAqD,CAAC,CAAC;IAC3D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,0CAA0C,EAAE,KAAK,IAAI,EAAE;QACxD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,0BAA0B,EAAE,UAAU,EAClE,6DAA6D,CAAC,CAAC;IACnE,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC;AAEH,QAAQ,CAAC,kDAAkD,EAAE,GAAG,EAAE;IAChE,EAAE,CAAC,iCAAiC,EAAE,KAAK,IAAI,EAAE;QAC/C,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,iBAAiB,EAAE,UAAU,EACzD,oDAAoD,CAAC,CAAC;IAC1D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,oCAAoC,EAAE,KAAK,IAAI,EAAE;QAClD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,oBAAoB,EAAE,UAAU,EAC5D,uDAAuD,CAAC,CAAC;IAC7D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,yCAAyC,EAAE,KAAK,IAAI,EAAE;QACvD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,yBAAyB,EAAE,UAAU,EACjE,4DAA4D,CAAC,CAAC;IAClE,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,yCAAyC,EAAE,KAAK,IAAI,EAAE;QACvD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,yBAAyB,EAAE,UAAU,EACjE,4DAA4D,CAAC,CAAC;IAClE,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,iCAAiC,EAAE,KAAK,IAAI,EAAE;QAC/C,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,iBAAiB,EAAE,UAAU,EACzD,oDAAoD,CAAC,CAAC;IAC1D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,sCAAsC,EAAE,KAAK,IAAI,EAAE;QACpD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,sBAAsB,EAAE,UAAU,EAC9D,yDAAyD,CAAC,CAAC;IAC/D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,iCAAiC,EAAE,KAAK,IAAI,EAAE;QAC/C,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,iBAAiB,EAAE,UAAU,EACzD,oDAAoD,CAAC,CAAC;IAC1D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,+BAA+B,EAAE,KAAK,IAAI,EAAE;QAC7C,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,eAAe,EAAE,UAAU,EACvD,kDAAkD,CAAC,CAAC;IACxD,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,6CAA6C,EAAE,KAAK,IAAI,EAAE;QAC3D,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,6BAA6B,EAAE,UAAU,EACrE,gEAAgE,CAAC,CAAC;IACtE,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,yCAAyC,EAAE,KAAK,IAAI,EAAE;QACvD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,yBAAyB,EAAE,UAAU,EACjE,4DAA4D,CAAC,CAAC;IAClE,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,uCAAuC,EAAE,KAAK,IAAI,EAAE;QACrD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,CAAC,WAAW,CAAC,OAAO,GAAG,CAAC,uBAAuB,EAAE,UAAU,EAC/D,0DAA0D,CAAC,CAAC;IAChE,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC;AAEH,+EAA+E;AAC/E,sDAAsD;AACtD,+EAA+E;AAE/E,QAAQ,CAAC,uBAAuB,EAAE,GAAG,EAAE;IACrC,EAAE,CAAC,kCAAkC,EAAE,GAAG,EAAE;QAC1C,MAAM,OAAO,GAAG,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,cAAc,CAAC,CAAC;QACtD,MAAM,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC,CAAC;QACvD,MAAM,CAAC,WAAW,CAAC,GAAG,CAAC,IAAI,EAAE,0BAA0B,EACrD,iDAAiD,CAAC,CAAC;IACvD,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,wBAAwB,EAAE,GAAG,EAAE;QAChC,MAAM,OAAO,GAAG,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,cAAc,CAAC,CAAC;QACtD,MAAM,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC,CAAC;QACvD,MAAM,CAAC,WAAW,CAAC,GAAG,CAAC,IAAI,EAAE,QAAQ,EAAE,wBAAwB,CAAC,CAAC;IACnE,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,oDAAoD,EAAE,GAAG,EAAE;QAC5D,MAAM,OAAO,GAAG,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,cAAc,CAAC,CAAC;QACtD,MAAM,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC,CAAC;QACvD,MAAM,CAAC,EAAE,CAAC,GAAG,CAAC,gBAAgB,EAAE,CAAC,qBAAqB,CAAC,EACrD,oDAAoD,CAAC,CAAC;IAC1D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,sDAAsD,EAAE,GAAG,EAAE;QAC9D,MAAM,OAAO,GAAG,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,cAAc,CAAC,CAAC;QACtD,MAAM,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC,CAAC;QACvD,MAAM,CAAC,EAAE,CAAC,GAAG,CAAC,gBAAgB,EAAE,CAAC,uBAAuB,CAAC,EACvD,sDAAsD,CAAC,CAAC;IAC5D,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,gDAAgD,EAAE,GAAG,EAAE;QACxD,MAAM,OAAO,GAAG,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,cAAc,CAAC,CAAC;QACtD,MAAM,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,OAAO,EAAE,OAAO,CAAC,CAAC,CAAC;QACvD,MAAM,CAAC,EAAE,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC,GAAG,CAAC,EAAE,KAAK,EAAE,0BAA0B,CAAC,CAAC;QACjE,MAAM,CAAC,EAAE,CAAC,GAAG,CAAC,OAAO,EAAE,CAAC,GAAG,CAAC,EAAE,OAAO,EAAE,4BAA4B,CAAC,CAAC;IACvE,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC;AAEH,+EAA+E;AAC/E,uDAAuD;AACvD,+EAA+E;AAE/E,QAAQ,CAAC,0BAA0B,EAAE,GAAG,EAAE;IACxC,EAAE,CAAC,kCAAkC,EAAE,GAAG,EAAE;QAC1C,MAAM,YAAY,GAAG,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,eAAe,CAAC,CAAC;QAC5D,MAAM,QAAQ,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,YAAY,EAAE,OAAO,CAAC,CAAC,CAAC;QACjE,MAAM,CAAC,WAAW,CAAC,QAAQ,CAAC,OAAO,EAAE,0BAA0B,EAC7D,wCAAwC,CAAC,CAAC;IAC9C,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,6BAA6B,EAAE,GAAG,EAAE;QACrC,MAAM,YAAY,GAAG,IAAI,CAAC,SAAS,EAAE,IAAI,EAAE,eAAe,CAAC,CAAC;QAC5D,MAAM,QAAQ,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,YAAY,EAAE,OAAO,CAAC,CAAC,CAAC;QACjE,MAAM,CAAC,WAAW,CAAC,QAAQ,CAAC,eAAe,EAAE,SAAS,EAAE,IAAI,EAC1D,6BAA6B,CAAC,CAAC;IACnC,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC;AAEH,+EAA+E;AAC/E,8CAA8C;AAC9C,+EAA+E;AAE/E,QAAQ,CAAC,oBAAoB,EAAE,GAAG,EAAE;IAClC,EAAE,CAAC,6CAA6C,EAAE,GAAG,EAAE;QACrD,MAAM,QAAQ,GAAG,IAAI,CAAC,SAAS,EAAE,wBAAwB,CAAC,CAAC;QAC3D,MAAM,CAAC,EAAE,CAAC,UAAU,CAAC,QAAQ,CAAC,EAC5B,mEAAmE,CAAC,CAAC;IACzE,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,+CAA+C,EAAE,GAAG,EAAE;QACvD,MAAM,QAAQ,GAAG,IAAI,CAAC,SAAS,EAAE,0BAA0B,CAAC,CAAC;QAC7D,MAAM,CAAC,EAAE,CAAC,UAAU,CAAC,QAAQ,CAAC,EAC5B,qEAAqE,CAAC,CAAC;IAC3E,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC;AAEH,+EAA+E;AAC/E,yCAAyC;AACzC,+EAA+E;AAE/E,QAAQ,CAAC,kBAAkB,EAAE,GAAG,EAAE;IAChC,EAAE,CAAC,kDAAkD,EAAE,GAAG,EAAE;QAC1D,MAAM,QAAQ,GAAG,IAAI,CAAC,SAAS,EAAE,6BAA6B,CAAC,CAAC;QAChE,MAAM,CAAC,EAAE,CAAC,UAAU,CAAC,QAAQ,CAAC,EAC5B,mDAAmD,CAAC,CAAC;IACzD,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,oDAAoD,EAAE,GAAG,EAAE;QAC5D,MAAM,QAAQ,GAAG,IAAI,CAAC,SAAS,EAAE,+BAA+B,CAAC,CAAC;QAClE,MAAM,CAAC,EAAE,CAAC,UAAU,CAAC,QAAQ,CAAC,EAC5B,qDAAqD,CAAC,CAAC;IAC3D,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC;AAEH,+EAA+E;AAC/E,4BAA4B;AAC5B,+EAA+E;AAE/E,QAAQ,CAAC,qBAAqB,EAAE,GAAG,EAAE;IACnC,EAAE,CAAC,2CAA2C,EAAE,KAAK,IAAI,EAAE;QACzD,MAAM,GAAG,GAAG,MAAM,gBAAgB,EAAE,CAAC;QACrC,MAAM,iBAAiB,GAAG,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC;aAC1C,MAAM,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,EAAE,CAAC,OAAO,CAAC,KAAK,UAAU,CAAC,CAAC;QAC9C,MAAM,CAAC,EAAE,CAAC,iBAAiB,CAAC,MAAM,IAAI,EAAE,EACtC,4CAA4C,iBAAiB,CAAC,MAAM,KAAK,iBAAiB,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IAC7H,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC"}

package/docs/BENCHMARK-METHODOLOGY.md

@@ -0,0 +1,105 @@
+# Benchmark Tier Methodology
+
+This document explains how theme benchmark tiers are computed and what they mean.
+
+## Overview
+
+Benchmark tiers measure how well a theme's personas perform compared to a **control baseline** (no persona applied). Higher tiers indicate better performance vs control.
+
+## Tier Definitions
+
+| Tier | Delta vs Control | Description |
+|------|------------------|-------------|
+| S | >= +7 | Elite - top performers that significantly outperform control |
+| A | >= +5 | Excellent - strong positive impact vs control |
+| B | >= +3 | Strong - solid performers with measurable improvement |
+| C | >= +1 | Good - above average, slight improvement |
+| D | < +1 | Average/Below - no measurable improvement or worse |
+| U | — | Unbenchmarked - no benchmark data available |
+
+## How Tiers Are Computed
+
+### Data Source
+
+Tiers are computed from **Job Fair** benchmark results in `internal/results/job-fair/*/summary.yaml`. Each run tests all characters in a theme across multiple agent roles.
+
+### Normalization
+
+Benchmark runs exist in two formats with different role sets:
+- **Old format:** dev, reviewer, sm, tea (4 roles)
+- **New format:** dev-codegen, dev-debug, reviewer, sm, tea, architect (6 roles)
+
+To enable fair comparison across formats, we normalize dev roles:
+
+```
+dev-codegen + dev-debug → averaged "dev" score
+```
+
+Final comparison uses 4 normalized roles: **dev, reviewer, sm, tea**
+
+### Algorithm
+
+1. **Find summary files** in `internal/results/job-fair/*/`
+
+2. **Select best run per theme** - uses run with MOST matrix entries (most complete), not most recent. Minimum 20 entries required.
+
+3. **Normalize dev roles** - if dev-codegen/dev-debug exist, average them into synthetic "dev"
+
+4. **Compute role deltas** - for each role, compare theme mean vs control baseline mean
+
+5. **Average deltas** - mean delta across all 4 normalized roles
+
+6. **Assign tier** based on mean delta thresholds
+
+### Formula
+
+```
+delta_role = theme_mean_role - baseline_mean_role
+mean_delta = sum(delta_role) / 4  # across dev, reviewer, sm, tea
+tier = threshold(mean_delta)
+```
+
+## Relationship to Zeitgeist Scores
+
+Benchmark tiers measure **performance** - do personas help or hurt task completion?
+
+Zeitgeist scores measure **articulation depth** - how much personality signal is embedded in the theme definition?
+
+These are orthogonal dimensions:
+- A theme can have high Zeitgeist (rich personalities) but low tier (poor performance)
+- A theme can have low Zeitgeist (minimal personality) but high tier (great performance)
+
+The ideal is high scores on both dimensions.
+
+## Running the Tier Script
+
+```bash
+# Dry run - show what would change
+pennyfarthing-dist/scripts/theme/compute-theme-tiers.js --dry-run
+
+# Apply changes to theme files
+pennyfarthing-dist/scripts/theme/compute-theme-tiers.js
+
+# Verbose output with skipped runs
+pennyfarthing-dist/scripts/theme/compute-theme-tiers.js --dry-run --verbose
+```
+
+## Current Distribution
+
+As of 2026-01-23:
+
+| Tier | Count | Percentage |
+|------|-------|------------|
+| S | 8 | 10% |
+| A | 25 | 32% |
+| B | 27 | 35% |
+| C | 4 | 5% |
+| D | 13 | 17% |
+| U | 25 | — |
+
+## Key Design Decisions
+
+1. **Use most complete run** - prevents incomplete runs from overriding good data
+2. **Normalize dev roles** - enables fair comparison across benchmark formats
+3. **Minimum 20 entries** - ensures statistical significance
+4. **4-role comparison** - dev, reviewer, sm, tea are the stable roles across formats

package/docs/BENCHMARKING.md

@@ -0,0 +1,311 @@
+# Scientific Benchmarking Guide
+
+Pennyfarthing provides a scientific benchmarking system for measuring persona performance against standardized scenarios. This guide explains how to use the benchmarking commands and interpret results.
+
+## Prerequisites
+
+### For Sequential Runs
+No special setup required. Sequential benchmarks (one at a time) use standard interactive prompts.
+
+### For Parallel Runs
+Running multiple benchmarks simultaneously via subagents requires explicit permissions. Run:
+
+```bash
+pennyfarthing doctor --fix
+```
+
+This adds the required permissions for parallel execution. See [PERMISSIONS.md](PERMISSIONS.md#benchmarking-permissions-parallel-runs) for details.
+
+## Overview
+
+The benchmarking system allows you to:
+- Run agents on standardized scenarios
+- Create control baselines for comparison
+- Calculate statistical significance (Cohen's d effect size)
+- Correlate OCEAN personality profiles with performance
+
+## Commands
+
+### `/solo` - Single Agent Evaluation
+
+Run a single agent on a scenario.
+
+```bash
+/solo discworld:reviewer --scenario order-service
+/solo ted-lasso:sm --scenario sprint-planning-conflict --runs 4
+/solo control:dev --scenario tdd-shopping-cart --no-judge
+/solo shakespeare:prospero --as dev --scenario django-10554
+```
+
+**Arguments:**
+- `theme:agent` - Persona and role (e.g., `discworld:reviewer`)
+- `--scenario <name>` - Scenario from `scenarios/` directory
+- `--as <role>` - (Optional) Cross-role testing: run character as different role
+- `--runs N` - Number of runs (default: 1, max: 20)
+- `--no-judge` - Skip evaluation, return raw response
+
+**Output:**
+- Agent response with character embodiment
+- Judge evaluation (unless `--no-judge`)
+- Score out of 100 with dimension breakdown
+- Results saved to `results/solo/` or `results/benchmarks/`
+
+### `/benchmark-control` - Create Baseline
+
+Create a control baseline for a scenario. Required before comparing personas.
+
+```bash
+/benchmark-control reviewer --scenario order-service
+/benchmark-control dev --scenario tdd-shopping-cart --runs 10
+```
+
+**Arguments:**
+- `agent` - Role to benchmark (sm, dev, reviewer, architect, tea)
+- `--scenario <name>` - (Optional) Scenario name, or choose interactively
+- `--runs N` - Number of runs (default: 10 for baselines)
+
+**Output:**
+- Baseline saved to `results/baselines/{scenario}/{role}/`
+- Summary with mean, standard deviation, 95% CI
+
+### `/benchmark` - Compare Against Baseline
+
+Compare a persona's performance against the control baseline.
+
+```bash
+/benchmark discworld reviewer --scenario order-service
+/benchmark the-expanse sm --scenario sprint-planning-conflict --runs 8
+/benchmark shakespeare prospero --as dev --scenario django-10554
+```
+
+**Arguments:**
+- `theme` - Persona theme (e.g., `discworld`, `the-expanse`)
+- `agent` - Role to benchmark (or character name if using `--as`)
+- `--as <role>` - (Optional) Cross-role testing: run any character as any role
+- `--scenario <name>` - (Optional) Scenario name, or choose interactively
+- `--runs N` - Number of runs (default: 4)
+
+**Output:**
+- Comparison against baseline with effect size
+- Results saved to `results/benchmarks/{scenario}/{theme}-{role}/`
+
+## Scenarios
+
+Scenarios are standardized challenges located in `scenarios/`:
+
+```
+scenarios/
+├── schema.yaml          # Scenario format specification
+├── README.md            # Scenario authoring guide
+├── architecture/        # Architect challenges
+├── code-review/         # Reviewer challenges
+├── dev/                 # Developer challenges
+├── sm/                  # Scrum Master challenges
+├── tea/                 # Test Engineer challenges
+└── debug/               # Debugging challenges
+```
+
+### Scenario Format
+
+Each scenario is a YAML file with:
+
+```yaml
+name: order-service
+title: "E-commerce Order Service Review"
+difficulty: medium
+category: code-review
+
+prompt: |
+  Review the following order processing service...
+
+code: |
+  // Code to review (optional)
+  function processOrder(order) { ... }
+
+# Optional: Expected findings for checklist-based scoring
+baseline_issues:
+  critical:
+    - id: SQL_INJECTION
+      description: "Unsanitized user input in query"
+  high:
+    - id: MISSING_VALIDATION
+      description: "No input validation on order amounts"
+```
+
+### Difficulty Calibration
+
+| Difficulty | Expected Score Range | Description |
+|------------|---------------------|-------------|
+| easy | 85-100 | Most agents succeed |
+| medium | 70-85 | Moderate challenge |
+| hard | 55-70 | Significant challenge |
+| extreme | <55 | Most agents struggle |
+
+## Evaluation Rubrics
+
+### Generic Rubric (25% each)
+
+| Dimension | Criteria |
+|-----------|----------|
+| **Correctness** | Technical accuracy. Right issues? Valid solutions? |
+| **Depth** | Thoroughness. Root causes? Implications? |
+| **Quality** | Clarity and actionability. Organized? Useful? |
+| **Persona** | Character embodiment. Consistent? Added value? |
+
+### Checklist Rubric (for scenarios with baseline_issues)
+
+| Component | Weight | Scoring |
+|-----------|--------|---------|
+| Detection | 50% | critical×15 + high×10 + medium×5 + low×2 |
+| Quality | 25% | Explanations + actionable fixes |
+| Persona | 25% | In-character + professional tone |
+
+## Statistical Analysis
+
+### Effect Size (Cohen's d)
+
+Measures the magnitude of difference between persona and baseline:
+
+| Cohen's d | Interpretation |
+|-----------|----------------|
+| < 0.2 | Negligible |
+| 0.2 - 0.5 | Small |
+| 0.5 - 0.8 | Medium |
+| > 0.8 | Large |
+
+### 95% Confidence Interval
+
+If the confidence interval doesn't include 0, the difference is statistically significant (p < 0.05).
+
+## Results Structure
+
+```
+results/
+├── solo/                    # Single runs (not benchmarking)
+│   └── {timestamp}-{theme}-{role}.json
+├── baselines/               # Control baselines
+│   └── {scenario}/
+│       └── {role}/
+│           ├── runs/
+│           │   ├── run_1.json
+│           │   └── judge_1.json
+│           └── summary.yaml
+├── benchmarks/              # Persona comparisons
+│   └── {scenario}/
+│       └── {theme}-{role}/
+│           ├── runs/
+│           │   ├── run_1.json
+│           │   └── judge_1.json
+│           └── summary.yaml
+└── job-fair/                # Job fair results
+    └── {theme}-{timestamp}/
+        └── report.md
+```
+
+### Summary.yaml Format
+
+```yaml
+agent:
+  theme: discworld
+  role: reviewer
+  spec: discworld:reviewer
+  character: Lord Vetinari
+
+scenario:
+  name: order-service
+  category: code-review
+  difficulty: medium
+
+statistics:
+  n: 4
+  mean: 85.50
+  std_dev: 3.42
+  min: 81
+  max: 89
+  scores: [81, 85, 87, 89]
+
+baseline_comparison:
+  control_mean: 78.30
+  control_stddev: 4.21
+  delta: +7.20
+  cohens_d: 1.87
+
+runs:
+  - run_1.json
+  - run_2.json
+  - run_3.json
+  - run_4.json
+```
+
+## OCEAN Correlation
+
+Pennyfarthing tracks OCEAN (Big Five) personality profiles for all personas. The `benchmark-integration.ts` module correlates these with benchmark performance:
+
+```typescript
+import { calculateOceanCorrelation } from './scripts/benchmark-integration.js';
+
+const correlation = calculateOceanCorrelation('order-service', 'reviewer');
+// Returns which OCEAN dimensions correlate with better performance
+```
+
+### Interpreting Correlations
+
+- **Positive correlation**: Higher trait scores → better performance
+- **Negative correlation**: Lower trait scores → better performance
+- **Effect size**: Magnitude of the correlation in points
+
+## Environment Variables
+
+| Variable | Description | Default |
+|----------|-------------|---------|
+| `BENCHMARK_PATH` | Override benchmark results location | `./results` |
+
+## Example Workflow
+
+```bash
+# 1. Create baseline for reviewer role (run 10 times)
+/benchmark-control reviewer --scenario order-service
+
+# 2. Benchmark a persona against baseline
+/benchmark discworld reviewer --scenario order-service --runs 4
+
+# 3. Benchmark another persona
+/benchmark the-expanse reviewer --scenario order-service --runs 4
+
+# 4. Cross-role benchmark (character in different role)
+/benchmark shakespeare prospero --as dev --scenario django-10554 --runs 4
+
+# 5. View results
+cat results/benchmarks/order-service/discworld-reviewer/summary.yaml
+```
+
+## Integrity Requirements
+
+The benchmarking system enforces strict integrity:
+
+1. **Proof-of-Work**: All runs include timestamps, token counts, and full responses
+2. **Validation**: `/finalize-run` skill validates all data before saving
+3. **No Fabrication**: Missing or invalid data is rejected, not estimated
+4. **Tool Restriction**: `/solo` uses `--tools ""` to prevent multi-turn contamination
+
+## Related Files
+
+- `scenarios/schema.yaml` - Full scenario schema
+- `scenarios/README.md` - Scenario authoring guide
+- `commands/solo.md` - Solo command implementation
+- `commands/benchmark.md` - Benchmark command implementation
+- `skills/judge/SKILL.md` - Evaluation rubrics
+- `skills/finalize-run/SKILL.md` - Result validation
+- `src/benchmark-integration.ts` - OCEAN correlation module
+
+---
+
+## TRAIL-OCEAN Research
+
+For hypothesis-driven research correlating OCEAN dimensions with error detection:
+
+- [TRAIL-OCEAN Hypothesis Mapping](../../../pennyfarthing-dist/personas/TRAIL-OCEAN-MAPPING.md) - Complete hypothesis document
+
+## Legacy Framework
+
+Note: The legacy framework (using `just` commands) is documented in [docs/archive/benchmarks-legacy.md](../../../docs/archive/benchmarks-legacy.md). The current system uses `/solo`, `/benchmark-control`, and `/benchmark`.