fix(email): show a queue nobody is working instead of reporting all-clear

Closes #1262.

"Gallery email queued" reads as a delivery confirmation, and System Health
agreed with it: "No stuck or failed emails -- all clear", while not one email
had gone out.

Both statements were true and neither was the one the admin needed. Queueing
writes an email_queue row at status='pending', retry_count 0 -- nothing more.
/failures matched only status='failed' or pending-with-retry_count>=3, so it
matched none of those rows, and there are two ordinary ways they never leave
that state:

- startEmailQueueProcessor() was never reached, so nothing polls the queue.
- Every pass returns early. processEmailQueue bails when the transporter will
  not initialise, before it touches a single row, so retry_count stays 0 and
  no error_message is ever written. A working SMTP test button does not
  contradict this: that path builds its own transport.

adminSystem.js made it worse by reporting `emailProcessor: { status: 'active' }`
as a literal, so the one place that named the worker always said it was fine.

- emailProcessor records what each pass did -- started, lastRunAt, lastResult,
  lastError -- and exports getQueueProcessorStatus(). The transporter bail and
  the queue-query failure, the two silent early returns, both write lastError.
- /failures gains `waitingEmails`: pending, under the retry cap, past any
  scheduled_at, and queued more than 10 minutes ago. The predicate mirrors the
  processor's own pickup query, so a row listed there is one it should already
  have taken; rows over the cap stay in `stuckEmails` and are not counted
  twice. A future scheduled_at is left alone -- split-payment invoices and the
  business-hours floor park rows deliberately.
- System Health leads with the processor's state (running / stopped /
  degraded) and lists waiting emails in their own table. The all-clear now
  needs both buckets empty.
- adminSystem reports the real processor state instead of the literal.
- The two "queued" toasts say the queue processor is what sends it and where
  to look if it doesn't arrive.

8 route tests, all 8 failing before the change.
This commit is contained in:
Paul Nothaft
2026-09-02 13:49:22 +02:00
parent f722bdaf4b
commit 73d867521a
10 changed files with 480 additions and 64 deletions
+34
View File
@@ -922,9 +922,32 @@ async function renderQueuedEmail(templateKey, variables = {}, to = '') {
// because ignoreSchedule also bypasses that cap.
//
// Returns { processed, sent, failed }.
// What the last pass actually did, so System Health can say whether the queue
// is being worked at all (#1262). "Queued" is not "delivered", and the two
// ways a queue silently stops -- the processor never started, or every pass
// returns early because the transport will not initialise -- both leave rows
// at status='pending' with retry_count 0, which no failure query matches.
const processorStatus = {
started: false,
lastRunAt: null,
lastResult: null,
lastError: null,
};
function getQueueProcessorStatus() {
return {
started: processorStatus.started,
lastRunAt: processorStatus.lastRunAt,
lastResult: processorStatus.lastResult,
lastError: processorStatus.lastError,
};
}
async function processEmailQueue({ ignoreSchedule = false, limit = 10, onlyId = null } = {}) {
logger.info('Email queue processor: Checking for pending emails...');
const result = { processed: 0, sent: 0, failed: 0 };
processorStatus.lastRunAt = new Date().toISOString();
processorStatus.lastError = null;
try {
// Try to initialize transporter if it's null (in case it failed at startup).
@@ -937,6 +960,10 @@ async function processEmailQueue({ ignoreSchedule = false, limit = 10, onlyId =
transporter = await initializeTransporter();
if (!transporter) {
logger.warn('Email transporter could not be initialized, skipping queue processing');
// #1262 — the row stays pending with retry_count 0, so nothing in the
// queue itself records that this pass did nothing. Say so here.
processorStatus.lastError = 'Email transporter could not be initialised — check the SMTP settings';
processorStatus.lastResult = result;
return result;
}
}
@@ -969,6 +996,8 @@ async function processEmailQueue({ ignoreSchedule = false, limit = 10, onlyId =
.limit(limit);
} catch (dbError) {
logger.error('Failed to query email queue:', dbError);
processorStatus.lastError = dbError.message;
processorStatus.lastResult = result;
return result;
}
@@ -1043,8 +1072,10 @@ async function processEmailQueue({ ignoreSchedule = false, limit = 10, onlyId =
}
} catch (error) {
logger.error('Error processing email queue:', error);
processorStatus.lastError = error.message;
}
processorStatus.lastResult = result;
return result;
}
@@ -1203,6 +1234,7 @@ function startEmailQueueProcessor() {
});
}, 60000);
processorStatus.started = true;
logger.info('Email queue processor started successfully');
} else {
logger.info('Email queue processor: Already running');
@@ -1213,6 +1245,7 @@ function stopEmailQueueProcessor() {
if (emailQueueInterval) {
clearInterval(emailQueueInterval);
emailQueueInterval = null;
processorStatus.started = false;
logger.info('Email queue processor stopped');
}
}
@@ -1231,6 +1264,7 @@ module.exports = {
sendRawEmail,
renderQueuedEmail,
processEmailQueue,
getQueueProcessorStatus,
queueEmail,
stopEmailQueueProcessor,
testEmailConnection,