diff --git a/ai-hub/integration_tests/test_browser_llm.py b/ai-hub/integration_tests/test_browser_llm.py
index 56c920b..173f788 100644
--- a/ai-hub/integration_tests/test_browser_llm.py
+++ b/ai-hub/integration_tests/test_browser_llm.py
@@ -77,12 +77,22 @@
         # Step 3: Verify the browser agent physically saved the screenshot and metadata to the file sync system.
         # Since the session_id is either used directly or via sync_workspace_id wrapper, we search the mirrors directory.
         import subprocess
-        cmd = [
-            "docker", "exec", "ai_hub_service", "bash", "-c", 
-            "find /app/data/mirrors/ -name '.browser_data' -type d"
-        ]
-        res = subprocess.run(cmd, capture_output=True, text=True)
-        assert res.returncode == 0, f"Failed to search for .browser_data inside Docker: {res.stderr}"
+        import time
+        
+        # Give the mesh file-sync engine up to 15 seconds to sync the .browser_data from the Node back into the Hub's mirrors.
+        print("\\n[test] Waiting up to 15s for file-sync mesh propagation of browser artifacts...")
+        res = None
+        for _ in range(15):
+            cmd = [
+                "docker", "exec", "ai_hub_service", "bash", "-c", 
+                "find /app/data/mirrors/ -name '.browser_data' -type d"
+            ]
+            res = subprocess.run(cmd, capture_output=True, text=True)
+            if res.stdout.strip():
+                break
+            time.sleep(1)
+        
+        assert res and res.returncode == 0, f"Failed to search for .browser_data inside Docker: {res.stderr}"
         
         # We expect at least one .browser_data directory corresponding to our session
         found_dirs = res.stdout.strip().split('\n')