Monitoring has been completed following the deployment of the fix for the Firebase database connection issue. The service is operating normally, and database access has been fully restored.
All impacted services have now fully recovered.The Google Calendar sync issue affecting some users has been fully resolved. Monitoring confirmed that all services are now functioning correctly.
The Neon database and API are fully operational. Tests confirm that the deployed fix has resolved the issue, and normal service has resumed.
The fix has been deployed, and tests indicate that the credit system and Neon database are functioning normally.
The fix has been applied, and after thorough testing, all systems are functioning normally. Users should no longer experience errors.
The issue affecting the mixerno.space API has been resolved by their team, and all services are now functioning normally.
Fixed
The previously deployed patch has been successfully applied and is functioning as expected. The issue affecting AI responses has been resolved. Services are operating normally, and monitoring will continue to ensure stability.
We are currently experiencing a high error rate affecting the Z-Image Turbo model on DockyAI. All other models on the platform are functioning normally and are not impacted. The issue appears to be isolated to this specific model, and we are actively investigating to restore normal service.
After conducting multiple tests, we have confirmed that the previously observed errors have been resolved. The service is operating normally at this time. We will continue to monitor the system to ensure ongoing stability.
All impacted services have now fully recovered.
All impacted services have now fully recovered.
All impacted services have now fully recovered.
After several tests, the issue appears to be fully resolved. No further unjustified blocking of legitimate content has been observed, and the service is operating normally at this time. Continued monitoring remains in place to ensure stability.
All impacted services have now fully recovered.
The previously observed abnormally high error rate affecting the tools of all DockyAI AI models, including operations such as </tool_call> and create_document, has now been resolved. The tools are functioning normally again, and related features should operate as expected. The incident is considered closed.
After verification, the Qwen 3 Coder 30B model is now responding correctly to users on DockyAI. The service has been restored and the incident is considered resolved.