feat(evals): add automated usage metrics reporting for behavioral evals

packages/cli/src/test-utils/AppRig.tsx

@@ -36,6 +36,10 @@ import {
   CoreToolCallStatus,
   IntegrityDataStatus,
 } from '@google/gemini-cli-core';
+import {
+  getUsageMetrics,
+  type UsageMetrics,
+} from '@google/gemini-cli-test-utils';
 import {
   type MockShellCommand,
   MockShellExecutionService,
@@ -477,6 +481,14 @@ export class AppRig {
     return this.testDir;
   }
 
+  /**
+   * Scans the session recordings and extracts aggregate token usage and turn counts.
+   * This provides an empirical measure of the agent's efficiency and cost.
+   */
+  getUsageMetrics(): UsageMetrics {
+    return getUsageMetrics(this.testDir);
+  }
+
   getPendingConfirmations() {
     return Array.from(this.pendingConfirmations.values());
   }