The smoke test could not fail, and other people's eyes

Four fixes, two of them serious, three of them found by the session porting
this into subscriptions.

1. THE SMOKE TEST COULD NOT FAIL. `wp eval-file` runs the file through eval()
   INSIDE A METHOD, so the top level is function scope. `$wc_edm_failures = 0`
   at the top and `global $wc_edm_failures` in the helper were two different
   variables: the helpers incremented the real global, the verdict read the
   local, and the local was always zero.

   Measured rather than reasoned. A deliberately false assertion added to the
   unmodified file:

       FAIL  DELIBERATE FAILURE — this run must go red
       All assertions passed on WordPress 7.1 with WooCommerce 11.1.0.
       EXIT=0

   and with the fix, the same forced failure:

       FAIL  DELIBERATE FAILURE — this run must go red
       1 assertion(s) failed on WordPress 7.1.
       EXIT=1

   The FAIL lines always printed, so failures found by reading the output were
   real finds. What was broken is the CI gate: a regression on either forge
   would have gone green. Four lines at the top now prove the counter reaches
   the verdict before anything relies on it — this is the one file whose whole
   job is to be able to go red, so it checks that it can.

2. `git ls-files` QUOTES NON-ASCII PATHS. "TESTMILJØ.md" comes back as the
   literal string "TESTMILJ\303\230.md", which matches no pattern in
   .distignore, so the file is kept — an internal document walking into the
   release zip with nothing said. Fixed in ci/dist-files.sh and in
   ci/static.sh's trailing-?> check, which had the same bug and would have
   silently skipped the file it exists to check. Verified by adding such a
   filename and watching it be excluded. `done < <(...)` rather than a pipe, or
   the loop runs in a subshell and the failure counter stops incrementing.

3. THE FEED CACHE WAS SIX HOURS, and Kristian hit it: a release published and
   his shop shown nothing. The reasoning ("WordPress checks twice a day") was
   wrong. WordPress gates its own check by screen in wp_update_plugins() — one
   minute on Dashboard → Updates, one hour on Plugins, 2–12 hours in the
   background — so WordPress is already the rate limiter and a longer cache
   only hides releases underneath it. Fifteen minutes now, pinned by an
   assertion.

4. The wp_update_plugins() assertion made a real HTTP request, because the
   force-check tests had just deleted the transient. It passed only because
   this feed repo is public, which made it measure the environment rather than
   the code. Re-primed first.

ci_in_container() replaces the inline docker plumbing in ci_php(), taken from
the subscriptions port: the script goes in as a file rather than interpolated
into `sh -c`, and --entrypoint sh matters for images whose entrypoint swallows
its arguments.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
kristianwind
2026-09-16 13:18:22 +02:00
co-authored by Claude Opus 5
parent 48119f2034
commit a1f6e54f9d
7 changed files with 156 additions and 38 deletions
+53 -7
View File
@@ -14,7 +14,29 @@ if ( ! defined( 'ABSPATH' ) ) {
exit;
}
$wc_edm_failures = 0;
/*
* The counter lives in $GLOBALS on purpose, and the four lines below prove it
* reaches the verdict before anything relies on it.
*
* `wp eval-file` runs this file through eval() INSIDE A METHOD, so the top
* level here is function scope, not global scope. A plain `$failures = 0` at
* the top and a `global $failures` in a helper below are therefore two
* different variables: the helpers increment the real global, the verdict at
* the bottom reads the local, and the local is always zero. Every assertion
* fails, every FAIL line prints, the file ends with "All assertions passed"
* and exits 0 — and CI goes green. That is not reasoning, it is what this file
* did until it was measured.
*
* This is the one file whose entire job is to be able to go red, so it checks
* that it can.
*/
$GLOBALS['wc_edm_failures'] = 0;
( static function () { ++$GLOBALS['wc_edm_failures']; } )();
if ( 1 !== $GLOBALS['wc_edm_failures'] ) {
echo "The failure counter does not reach the verdict: this file cannot go red.\n";
exit( 1 );
}
$GLOBALS['wc_edm_failures'] = 0;
/**
* Assert a condition and keep going, so one run reports every failure.
@@ -24,14 +46,12 @@ $wc_edm_failures = 0;
* @param string $detail Shown when it fails.
*/
function wc_edm_ok( $what, $condition, $detail = '' ) {
global $wc_edm_failures;
if ( $condition ) {
printf( " ok %s\n", $what );
return;
}
++$wc_edm_failures;
++$GLOBALS['wc_edm_failures'];
printf( " FAIL %s%s\n", $what, '' !== $detail ? " — {$detail}" : '' );
}
@@ -345,7 +365,18 @@ wc_edm_is( 'the current version is answered too, not passed over', WC_EDM_VERSIO
* WordPress does with our answer, and a test that needs the internet fails for
* reasons that have nothing to do with it.
*/
// "Check again" must discard the six-hour cache, or the button lies: someone
// The cache must not outlive WordPress's own check cadence. It gates by screen
// — one minute on Dashboard → Updates, one hour on the Plugins screen — and
// this filter only runs when that check runs, so anything longer here hides a
// new release underneath a cache the shop owner cannot see. This was six hours
// and produced exactly that: a release published, and a shop shown nothing.
wc_edm_ok(
'the cache is shorter than the interval WordPress re-checks on',
WC_EDM_Updater::TTL <= 15 * MINUTE_IN_SECONDS,
'TTL is ' . WC_EDM_Updater::TTL . 's; WordPress re-checks every 60s on Dashboard → Updates'
);
// "Check again" must discard the cache, or the button lies: someone
// who has just published a release clicks it, sees nothing, and concludes the
// whole mechanism is broken.
set_transient( WC_EDM_Updater::TRANSIENT, array( 'version' => '1.0.0', 'package' => 'x', 'url' => 'x', 'tested' => '' ), 600 );
@@ -368,6 +399,21 @@ delete_transient( WC_EDM_Updater::TRANSIENT );
// strlen(null) deprecation from class-wp-plugins-list-table.php. It is
// WordPress's, not ours, which is why the deprecation check filters on this
// plugin's directory rather than failing on everything it sees.
// Primed again deliberately. The force-check assertions above deleted it, and
// without this offer_update() makes a real HTTP request — which passes only
// because this plugin's feed repo happens to be public. That would make the
// assertion measure the environment rather than the code under test.
set_transient(
WC_EDM_Updater::TRANSIENT,
array(
'version' => WC_EDM_VERSION,
'package' => 'https://gitea.nolimit.dk/kw/demo/releases/download/v1/demo.zip',
'url' => 'https://gitea.nolimit.dk/kw/demo',
'tested' => '7.1',
),
600
);
delete_site_transient( 'update_plugins' );
wp_update_plugins();
$transient = get_site_transient( 'update_plugins' );
@@ -407,8 +453,8 @@ delete_transient( WC_EDM_Updater::TRANSIENT );
/* --------------------------------------------------------------- verdict -- */
echo "\n";
if ( $wc_edm_failures > 0 ) {
printf( "%d assertion(s) failed on WordPress %s.\n", $wc_edm_failures, get_bloginfo( 'version' ) );
if ( $GLOBALS['wc_edm_failures'] > 0 ) {
printf( "%d assertion(s) failed on WordPress %s.\n", $GLOBALS['wc_edm_failures'], get_bloginfo( 'version' ) );
exit( 1 );
}
printf(