Ship production optimization M1-M12.5A: queues, metrics, HTTP observability, and vector search reliability.

Keep similar-ai from tripping the global circuit on a lone URL 502, clamp Qdrant search to 100, and add Server-Timing plus slow-request logging. Studio shared props, Academy S3 exists caching, heat chunking, and Redis/scheduler hygiene stay in this rollout.

app/Http/Middleware/AddServerTiming.php

@@ -0,0 +1,43 @@
+<?php
+
+declare(strict_types=1);
+
+namespace App\Http\Middleware;
+
+use Closure;
+use Illuminate\Http\Request;
+use Symfony\Component\HttpFoundation\Response;
+
+/**
+ * Negligible-overhead request duration header for production HTTP profiling.
+ * Does not log queries or payloads.
+ */
+final class AddServerTiming
+{
+    public function handle(Request $request, Closure $next): Response
+    {
+        $started = hrtime(true);
+        $response = $next($request);
+        $durationMs = (hrtime(true) - $started) / 1_000_000;
+
+        if (headers_sent()) {
+            return $response;
+        }
+
+        $metrics = ['app;desc="Laravel";dur='.number_format($durationMs, 1, '.', '')];
+        $ssrMs = $request->attributes->get('http.ssr_ms');
+        if (is_numeric($ssrMs) && (float) $ssrMs >= 0) {
+            $metrics[] = 'ssr;desc="Inertia SSR";dur='.number_format((float) $ssrMs, 1, '.', '');
+        }
+
+        $metric = implode(', ', $metrics);
+        $existing = $response->headers->get('Server-Timing');
+
+        $response->headers->set(
+            'Server-Timing',
+            $existing ? $existing.', '.$metric : $metric,
+        );
+
+        return $response;
+    }
+}