feat(test): add large conversation scenario for performance test

packages/core/src/telemetry/memory-monitor.test.ts

@@ -17,13 +17,18 @@ import {
   _resetGlobalMemoryMonitorForTests,
 } from './memory-monitor.js';
 import type { Config } from '../config/config.js';
-import { recordMemoryUsage, isPerformanceMonitoringActive } from './metrics.js';
+import {
+  recordMemoryUsage,
+  recordCpuUsage,
+  isPerformanceMonitoringActive,
+} from './metrics.js';
 import { HighWaterMarkTracker } from './high-water-mark-tracker.js';
 import { RateLimiter } from './rate-limiter.js';
 
 // Mock dependencies
 vi.mock('./metrics.js', () => ({
   recordMemoryUsage: vi.fn(),
+  recordCpuUsage: vi.fn(),
   isPerformanceMonitoringActive: vi.fn(),
   MemoryMetricType: {
     HEAP_USED: 'heap_used',
@@ -50,6 +55,7 @@ vi.mock('node:process', () => ({
 }));
 
 const mockRecordMemoryUsage = vi.mocked(recordMemoryUsage);
+const mockRecordCpuUsage = vi.mocked(recordCpuUsage);
 const mockIsPerformanceMonitoringActive = vi.mocked(
   isPerformanceMonitoringActive,
 );
@@ -192,6 +198,13 @@ describe('MemoryMonitor', () => {
             component: 'test_context',
           },
         );
+        expect(mockRecordCpuUsage).toHaveBeenCalledWith(
+          mockConfig,
+          expect.any(Number),
+          {
+            component: 'test_context',
+          },
+        );
       });
 
       it('should not record metrics when performance monitoring is inactive', () => {

packages/core/src/telemetry/memory-monitor.ts

@@ -12,6 +12,7 @@ import { isUserActive } from './activity-detector.js';
 import { HighWaterMarkTracker } from './high-water-mark-tracker.js';
 import {
   recordMemoryUsage,
+  recordCpuUsage,
   MemoryMetricType,
   isPerformanceMonitoringActive,
 } from './metrics.js';
@@ -37,6 +38,7 @@ export class MemoryMonitor {
   private intervalId: NodeJS.Timeout | null = null;
   private isRunning = false;
   private lastSnapshot: MemorySnapshot | null = null;
+  private lastCpuUsage: NodeJS.CpuUsage | null = null;
   private monitoringInterval: number = 10000;
   private highWaterMarkTracker: HighWaterMarkTracker;
   private rateLimiter: RateLimiter;
@@ -191,6 +193,13 @@ export class MemoryMonitor {
         memory_type: MemoryMetricType.RSS,
         component: context,
       });
+
+      // Record delta CPU usage (in microseconds)
+      const cpuUsage = process.cpuUsage(this.lastCpuUsage ?? undefined);
+      this.lastCpuUsage = process.cpuUsage();
+      recordCpuUsage(config, cpuUsage.user + cpuUsage.system, {
+        component: context,
+      });
     }
 
     this.lastSnapshot = snapshot;

packages/test-utils/src/perf-test-harness.ts

@@ -147,7 +147,9 @@ export class PerfTestHarness {
       throw new Error(`No active timer found for label "${label}"`);
     }
 
-    const wallClockMs = performance.now() - timer.startTime;
+    // Round wall-clock time to nearest 0.1 ms
+    const wallClockMs =
+      Math.round((performance.now() - timer.startTime) * 10) / 10;
     const cpuDelta = process.cpuUsage(timer.startCpuUsage);
     this.activeTimers.delete(label);
 

packages/test-utils/src/test-rig.ts

@@ -193,6 +193,28 @@ export function checkModelOutputContent(
   return isValid;
 }
 
+export interface MetricDataPoint {
+  attributes?: Record<string, unknown>;
+  value?: {
+    sum?: number;
+    min?: number;
+    max?: number;
+    count?: number;
+  };
+  startTime?: [number, number];
+  endTime?: string;
+}
+
+export interface TelemetryMetric {
+  descriptor: {
+    name: string;
+    type?: string;
+    description?: string;
+    unit?: string;
+  };
+  dataPoints: MetricDataPoint[];
+}
+
 export interface ParsedLog {
   attributes?: {
     'event.name'?: string;
@@ -213,11 +235,7 @@ export interface ParsedLog {
     prompt_id?: string;
   };
   scopeMetrics?: {
-    metrics: {
-      descriptor: {
-        name: string;
-      };
-    }[];
+    metrics: TelemetryMetric[];
   }[];
 }
 
@@ -1297,6 +1315,10 @@ export class TestRig {
     return logs;
   }
 
+  readTelemetryLogs(): ParsedLog[] {
+    return this._readAndParseTelemetryLog();
+  }
+
   private _readAndParseTelemetryLog(): ParsedLog[] {
     // Telemetry is always written to the test directory
     const logFilePath = join(this.homeDir!, 'telemetry.log');
@@ -1450,7 +1472,7 @@ export class TestRig {
     );
   }
 
-  readMetric(metricName: string): Record<string, unknown> | null {
+  readMetric(metricName: string): TelemetryMetric | null {
     const logs = this._readAndParseTelemetryLog();
     for (const logData of logs) {
       if (logData.scopeMetrics) {

perf-tests/baselines.json

@@ -1,14 +1,14 @@
 {
   "version": 1,
-  "updatedAt": "2026-04-09T02:30:22.000Z",
+  "updatedAt": "2026-04-14T14:04:02.662Z",
   "scenarios": {
     "cold-startup-time": {
-      "wallClockMs": 927.553249999999,
+      "wallClockMs": 927.6,
       "cpuTotalUs": 1470,
       "timestamp": "2026-04-08T22:27:54.871Z"
     },
     "idle-cpu-usage": {
-      "wallClockMs": 5000.460750000002,
+      "wallClockMs": 5000.5,
       "cpuTotalUs": 12157,
       "timestamp": "2026-04-08T22:28:19.098Z"
     },
@@ -18,14 +18,39 @@
       "timestamp": "2026-04-14T15:22:56.133Z"
     },
     "skill-loading-time": {
-      "wallClockMs": 930.0920409999962,
+      "wallClockMs": 930.1,
       "cpuTotalUs": 1323,
       "timestamp": "2026-04-08T22:28:23.290Z"
     },
     "high-volume-shell-output": {
       "wallClockMs": 1119.9,
       "cpuTotalUs": 2100,
       "timestamp": "2026-04-09T02:30:22.000Z"
+    },
+    "long-conversation-resume": {
+      "wallClockMs": 4212.5,
+      "cpuTotalUs": 351393,
+      "timestamp": "2026-04-14T14:02:53.268Z"
+    },
+    "long-conversation-typing": {
+      "wallClockMs": 113.7,
+      "cpuTotalUs": 3304,
+      "timestamp": "2026-04-14T14:03:12.525Z"
+    },
+    "long-conversation-execution": {
+      "wallClockMs": 248.7,
+      "cpuTotalUs": 3825,
+      "timestamp": "2026-04-14T14:03:28.575Z"
+    },
+    "long-conversation-terminal-scrolling": {
+      "wallClockMs": 362.4,
+      "cpuTotalUs": 12755860,
+      "timestamp": "2026-04-14T14:03:45.687Z"
+    },
+    "long-conversation-alternate-scrolling": {
+      "wallClockMs": 362.4,
+      "cpuTotalUs": 12755860,
+      "timestamp": "2026-04-14T14:04:02.662Z"
     }
   }
 }