From 9f99201e799d5f57288237a1965cfe896ae5a4e2 Mon Sep 17 00:00:00 2001
From: Christopher <christso@gmail.com>
Date: Thu, 9 Apr 2026 04:11:12 +0000
Subject: [PATCH] fix(stats): include execution errors in pass/total
 denominator

Previously the summary showed passedCount/gradedCount where gradedCount
excluded execution errors, making results appear better than they were.
Now shows passedCount/total to match the Convex Evals convention that
inspired this design: the denominator is all tests actually attempted,
not just those that reached the grading stage.

Execution errors are still reported separately in the detail section.

Closes #998
---
 apps/cli/src/commands/eval/statistics.ts | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/apps/cli/src/commands/eval/statistics.ts b/apps/cli/src/commands/eval/statistics.ts
index 553d14878..98abf987a 100644
--- a/apps/cli/src/commands/eval/statistics.ts
+++ b/apps/cli/src/commands/eval/statistics.ts
@@ -226,7 +226,7 @@ export function formatEvaluationSummary(
   } else {
     overallVerdict = overallPassed ? 'PASS' : 'FAIL';
     verdictColor = overallPassed ? '\x1b[32m' : '\x1b[31m';
-    verdictText = `RESULT: ${overallVerdict}  (${summary.passedCount}/${gradedCount} scored >= ${threshold}, mean: ${formatScore(summary.mean)})`;
+    verdictText = `RESULT: ${overallVerdict}  (${summary.passedCount}/${summary.total} scored >= ${threshold}, mean: ${formatScore(summary.mean)})`;
   }
 
   lines.push('\n==================================================');