From 5be38c3a271cb4402bb83a6c758a56cc0b0aafef Mon Sep 17 00:00:00 2001
From: Christian Gunderman <gundermanc@google.com>
Date: Mon, 26 Jan 2026 15:25:37 -0800
Subject: [PATCH] Add slash command for diagnosing test failures.

---
 evals/README.md | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/evals/README.md b/evals/README.md
index eb3cf2be70..cdcbcff124 100644
--- a/evals/README.md
+++ b/evals/README.md
@@ -160,8 +160,7 @@ failing evaluations. It will:
     `evals/logs`.
 2.  **Fix**: Suggest and apply targeted fixes to the prompt or tool definitions.
     It prioritizes minimal changes to `prompt.ts`, tool instructions, and
-    modules that contribute to the prompt. It generally tries to avoid changing
-    the test itself.
+    modules that contribute to the prompt.
 3.  **Verify**: Re-run the test 3 times across multiple models (e.g., Gemini
     3.0, Gemini 3 Flash, Gemini 2.5 Pro) to ensure stability and calculate a
     success rate.