From 46231a1755e8e03bc8c026b98c7e3a962b318a2c Mon Sep 17 00:00:00 2001
From: Christian Gunderman <gundermanc@gmail.com>
Date: Tue, 3 Mar 2026 00:29:31 +0000
Subject: [PATCH] ci(evals): only run evals in CI if prompts or tools changed
 (#20898)

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
---
 .github/workflows/chained_e2e.yml | 15 ++++++++--
 scripts/changed_prompt.js         | 49 +++++++++++++++++++++++++++++++
 2 files changed, 62 insertions(+), 2 deletions(-)
 create mode 100644 scripts/changed_prompt.js

diff --git a/.github/workflows/chained_e2e.yml b/.github/workflows/chained_e2e.yml
index 2e1586bcd4..3633c5027b 100644
--- a/.github/workflows/chained_e2e.yml
+++ b/.github/workflows/chained_e2e.yml
@@ -290,6 +290,7 @@ jobs:
         with:
           ref: '${{ needs.parse_run_context.outputs.sha }}'
           repository: '${{ needs.parse_run_context.outputs.repository }}'
+          fetch-depth: 0
 
       - name: 'Set up Node.js 20.x'
         uses: 'actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020' # ratchet:actions-node@v4
@@ -302,7 +303,14 @@ jobs:
       - name: 'Build project'
         run: 'npm run build'
 
-      - name: 'Run Evals (ALWAYS_PASSING)'
+      - name: 'Check if evals should run'
+        id: 'check_evals'
+        run: |
+          SHOULD_RUN=$(node scripts/changed_prompt.js)
+          echo "should_run=$SHOULD_RUN" >> "$GITHUB_OUTPUT"
+
+      - name: 'Run Evals (Required to pass)'
+        if: "${{ steps.check_evals.outputs.should_run == 'true' }}"
         env:
           GEMINI_API_KEY: '${{ secrets.GEMINI_API_KEY }}'
         run: 'npm run test:always_passing_evals'
@@ -315,6 +323,7 @@ jobs:
       - 'e2e_linux'
       - 'e2e_mac'
       - 'e2e_windows'
+      - 'evals'
       - 'merge_queue_skipper'
     runs-on: 'gemini-cli-ubuntu-16-core'
     steps:
@@ -322,7 +331,8 @@ jobs:
         run: |
           if [[ ${NEEDS_E2E_LINUX_RESULT} != 'success' || \
                ${NEEDS_E2E_MAC_RESULT} != 'success' || \
-               ${NEEDS_E2E_WINDOWS_RESULT} != 'success' ]]; then
+               ${NEEDS_E2E_WINDOWS_RESULT} != 'success' || \
+               ${NEEDS_EVALS_RESULT} != 'success' ]]; then
             echo "One or more E2E jobs failed."
             exit 1
           fi
@@ -331,6 +341,7 @@ jobs:
           NEEDS_E2E_LINUX_RESULT: '${{ needs.e2e_linux.result }}'
           NEEDS_E2E_MAC_RESULT: '${{ needs.e2e_mac.result }}'
           NEEDS_E2E_WINDOWS_RESULT: '${{ needs.e2e_windows.result }}'
+          NEEDS_EVALS_RESULT: '${{ needs.evals.result }}'
 
   set_workflow_status:
     runs-on: 'gemini-cli-ubuntu-16-core'
diff --git a/scripts/changed_prompt.js b/scripts/changed_prompt.js
new file mode 100644
index 0000000000..9cf7c1a261
--- /dev/null
+++ b/scripts/changed_prompt.js
@@ -0,0 +1,49 @@
+/**
+ * @license
+ * Copyright 2026 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+import { execSync } from 'node:child_process';
+
+const EVALS_FILE_PREFIXES = [
+  'packages/core/src/prompts/',
+  'packages/core/src/tools/',
+  'evals/',
+];
+
+function main() {
+  const targetBranch = process.env.GITHUB_BASE_REF || 'main';
+  try {
+    // Fetch target branch from origin.
+    execSync(`git fetch origin ${targetBranch}`, {
+      stdio: 'ignore',
+    });
+
+    // Find the merge base with the target branch.
+    const mergeBase = execSync('git merge-base HEAD FETCH_HEAD', {
+      encoding: 'utf-8',
+    }).trim();
+
+    // Get changed files
+    const changedFiles = execSync(`git diff --name-only ${mergeBase} HEAD`, {
+      encoding: 'utf-8',
+    })
+      .split('\n')
+      .filter(Boolean);
+
+    const shouldRun = changedFiles.some((file) =>
+      EVALS_FILE_PREFIXES.some((prefix) => file.startsWith(prefix)),
+    );
+
+    console.log(shouldRun ? 'true' : 'false');
+  } catch (error) {
+    // If anything fails (e.g., no git history), run evals to be safe
+    console.warn(
+      'Warning: Failed to determine if evals should run. Defaulting to true.',
+    );
+    console.error(error);
+    console.log('true');
+  }
+}
+
+main();