From 2c194eb0768fe64c6de579105f21de856c2dc96a Mon Sep 17 00:00:00 2001
From: Liang-Chi Hsieh <viirya@gmail.com>
Date: Fri, 29 May 2026 13:20:25 -0700
Subject: [PATCH] [SPARK-57155][INFRA] Fix `update_build_status` check-run
 pagination and output parsing

### What changes were proposed in this pull request?

Two robustness fixes to the scheduled `update_build_status.yml` workflow:

1. List a commit's check-runs with `github.paginate(..., per_page: 100)` instead
   of a single un-paginated `github.request`, matching `notify_test_workflow.yml`.
   The default page size is 30, so the target `Build` check could fall off the
   first page on a SHA that accumulates more check-runs than that (CI matrix,
   external checks, duplicate `Build` checks from reopened PRs).

2. Wrap `JSON.parse(cr.output.text)` in try/catch and `continue` on failure. A
   `Build` check created by something other than this mechanism (an older
   version, a manual run, or another app), or one with empty output text, would
   otherwise throw inside the loop and abort the whole scheduled run.

### Why are the changes needed?

Both issues silently block status updates. If the `Build` check is paginated off
the first page, the PR stays stuck in `queued` forever because the updater never
sees it. If an unparseable `Build` check is encountered, the uncaught exception
aborts the run and blocks updates for every PR queued behind it that cycle.

### Does this PR introduce _any_ user-facing change?

No. CI infrastructure only.

### How was this patch tested?

Static verification: the embedded `actions/github-script` body passes
`node --check`, and the workflow YAML parses. Note `github.paginate` returns a
flat array, so the iteration was updated from `checkRuns.data.check_runs` to
`checkRuns`.

### Was this patch authored or co-authored using generative AI tooling?

Generated-by: Claude Code (Claude Opus 4.8)

Co-authored-by: Claude Code
---
 .github/workflows/update_build_status.yml | 36 ++++++++++++++++++-----
 1 file changed, 28 insertions(+), 8 deletions(-)

diff --git a/.github/workflows/update_build_status.yml b/.github/workflows/update_build_status.yml
index 26ab78fbee1a..6b16c59ce6ac 100644
--- a/.github/workflows/update_build_status.yml
+++ b/.github/workflows/update_build_status.yml
@@ -53,17 +53,37 @@ jobs:
                 console.log('SHA: ' + pr.head.sha)
                 console.log('  Mergeable status: ' + pr.mergeable_state)
                 if (pr.mergeable_state == null || maybeReady.includes(pr.mergeable_state)) {
-                  const checkRuns = await github.request('GET /repos/{owner}/{repo}/commits/{ref}/check-runs', {
-                    owner: context.repo.owner,
-                    repo: context.repo.repo,
-                    ref: pr.head.sha
-                  })
+                  // Paginate with per_page=100 to match notify_test_workflow.yml. The default
+                  // page size is 30, and a SHA can accumulate more check-runs than that (CI
+                  // matrix, external checks, duplicate Build checks from reopened PRs), which
+                  // could push the target Build check off the first page and leave the PR
+                  // stuck in 'queued' forever.
+                  const checkRuns = await github.paginate(
+                    'GET /repos/{owner}/{repo}/commits/{ref}/check-runs',
+                    {
+                      owner: context.repo.owner,
+                      repo: context.repo.repo,
+                      ref: pr.head.sha,
+                      per_page: 100
+                    }
+                  )
 
                   // Iterator GitHub Checks in the PR
-                  for await (const cr of checkRuns.data.check_runs) {
+                  for await (const cr of checkRuns) {
                     if (cr.name == 'Build' && cr.conclusion != "action_required") {
-                      // text contains parameters to make request in JSON.
-                      const params = JSON.parse(cr.output.text)
+                      // text contains parameters to make request in JSON. A Build check
+                      // created by something other than notify_test_workflow.yml (an older
+                      // version, a manual run, or another app) may have empty or malformed
+                      // output text; skip it instead of aborting the whole scheduled run,
+                      // which would block updates for every PR queued behind it.
+                      let params
+                      try {
+                        params = JSON.parse(cr.output.text)
+                      } catch (error) {
+                        console.error('Skipping Build check ' + cr.id + ' with unparseable output text')
+                        console.error(error)
+                        continue
+                      }
 
                       // Get the workflow run in the forked repository
                       let run