tinker_tickets/cron/retry_failed_notifications.php

#!/usr/bin/env php
<?php

/**
 * Failed Matrix Notification Retry Cron Job
 *
 * NotificationHelper::fire() queues a failed webhook post to
 * notification_retry_queue instead of just logging and losing it. This
 * script retries due rows with exponential backoff, up to each row's
 * max_attempts, then leaves an exhausted row in place (not deleted) so it
 * remains visible for manual investigation.
 *
 * Run this via cron every 5-10 minutes (see README.md's Cron Jobs section
 * for the exact crontab line — the "every 5 minutes" syntax isn't repeated
 * here since it would terminate this comment block early).
 */

// Prevent web access
if (php_sapi_name() !== 'cli') {
    http_response_code(403);
    exit('CLI access only');
}

chdir(dirname(__DIR__));

require_once 'config/config.php';
require_once 'helpers/Database.php';
require_once 'helpers/NotificationHelper.php';

function logMessage($message)
{
    echo '[' . date('Y-m-d H:i:s') . '] ' . $message . "\n";
}

/** Exponential backoff in minutes: 2, 4, 8, 16, 32, capped at 60. */
function nextAttemptDelayMinutes(int $attemptNumber): int
{
    return min(60, 2 ** $attemptNumber);
}

$webhookUrl = $GLOBALS['config']['MATRIX_WEBHOOK_URL'] ?? null;
if (empty($webhookUrl)) {
    logMessage('MATRIX_WEBHOOK_URL not configured — nothing to retry, exiting.');
    exit(0);
}

try {
    $conn = Database::getConnection();
} catch (Exception $e) {
    logMessage('FATAL ERROR: could not connect to database: ' . $e->getMessage());
    exit(1);
}

// Process a bounded batch per run so one cron tick can't run indefinitely if
// the queue has backed up.
$batchLimit = 50;

$stmt = $conn->prepare(
    "SELECT retry_id, payload, attempts, max_attempts
       FROM notification_retry_queue
      WHERE next_attempt_at <= NOW() AND attempts < max_attempts
      ORDER BY retry_id ASC
      LIMIT ?"
);
$stmt->bind_param('i', $batchLimit);
$stmt->execute();
$dueRows = $stmt->get_result()->fetch_all(MYSQLI_ASSOC);
$stmt->close();

if (empty($dueRows)) {
    logMessage('No notifications due for retry.');
    exit(0);
}

$succeeded = 0;
$failed = 0;
$exhausted = 0;

foreach ($dueRows as $row) {
    $payload = json_decode($row['payload'], true);
    if (!is_array($payload)) {
        // Corrupt row — can't retry something unparseable. Remove it rather
        // than retrying forever against a row that will never succeed.
        $del = $conn->prepare("DELETE FROM notification_retry_queue WHERE retry_id = ?");
        $del->bind_param('i', $row['retry_id']);
        $del->execute();
        $del->close();
        logMessage("Discarded retry #{$row['retry_id']}: payload is not valid JSON");
        continue;
    }

    $result = NotificationHelper::attemptDelivery($webhookUrl, $payload);

    if ($result['success']) {
        $del = $conn->prepare("DELETE FROM notification_retry_queue WHERE retry_id = ?");
        $del->bind_param('i', $row['retry_id']);
        $del->execute();
        $del->close();
        $succeeded++;
        logMessage("Retry #{$row['retry_id']} succeeded (attempt " . ((int)$row['attempts'] + 1) . ')');
        continue;
    }

    $newAttempts = (int)$row['attempts'] + 1;
    if ($newAttempts >= (int)$row['max_attempts']) {
        // Exhausted: leave the row (attempts is now == max_attempts, so the
        // WHERE clause above naturally excludes it from future runs) rather
        // than deleting it, so it stays visible for manual investigation.
        $upd = $conn->prepare(
            "UPDATE notification_retry_queue SET attempts = ?, last_error = ? WHERE retry_id = ?"
        );
        $upd->bind_param('isi', $newAttempts, $result['error'], $row['retry_id']);
        $upd->execute();
        $upd->close();
        $exhausted++;
        logMessage("Retry #{$row['retry_id']} exhausted after {$newAttempts} attempts: {$result['error']}");
        continue;
    }

    $delayMinutes = nextAttemptDelayMinutes($newAttempts);
    $upd = $conn->prepare(
        "UPDATE notification_retry_queue
            SET attempts = ?, last_error = ?, next_attempt_at = DATE_ADD(NOW(), INTERVAL ? MINUTE)
          WHERE retry_id = ?"
    );
    $upd->bind_param('isii', $newAttempts, $result['error'], $delayMinutes, $row['retry_id']);
    $upd->execute();
    $upd->close();
    $failed++;
    logMessage("Retry #{$row['retry_id']} failed (attempt {$newAttempts}), next attempt in {$delayMinutes}m: {$result['error']}");
}

logMessage("Done: {$succeeded} succeeded, {$failed} rescheduled, {$exhausted} exhausted (of " . count($dueRows) . ' processed)');