GitHub Copilot problems on 9 November 2026
| Status | Resolved |
|---|---|
| Worst verdict | Some users report problems |
| Started | |
| Ended | |
| Duration | 49 min |
| Official incident | Degraded availability for GPT-5.3 Codex and GPT-5.6 models in Copilot |
| Affected | Copilot, Copilot AI Model Providers |
Timeline
-
We started seeing problems. Our verdict: Some users report problems.
- · official updateDegraded availability for GPT-5.3 Codex and GPT-5.6 models in Copilot (investigating): “We are investigating reports of degraded availability for Copilot” Source
- · official updateDegraded availability for GPT-5.3 Codex and GPT-5.6 models in Copilot (investigating): “We are experiencing degraded availability for GPT-5.3 Codex, GPT-5.6 Luna, and GPT-5.6 Sol in Copilot products and IDE surfaces due to an issue with an upstream model provider. We recommend choosing another model or selecting Auto to continue using Copilot until the issue is resolved.” Source
- · official updateDegraded availability for GPT-5.3 Codex and GPT-5.6 models in Copilot (investigating): “Copilot is operating normally.” Source
- · official updateDegraded availability for GPT-5.3 Codex and GPT-5.6 models in Copilot (monitoring): “The degradation affecting Copilot AI Model Providers has been mitigated. We are monitoring to ensure stability.” Source
- · official updateDegraded availability for GPT-5.3 Codex and GPT-5.6 models in Copilot (monitoring): “The issue affecting GPT-5.3 Codex, GPT-5.6 Luna, and GPT-5.6 Sol in Copilot products and IDE surfaces has been mitigated. We are monitoring the service to ensure stability.” Source
-
Looking normal again. We'll keep watching for 15 minutes before closing this.
-
Everything has looked normal for 15 minutes, so we marked this incident as resolved.
Times are shown in your local time zone. “Official update” entries quote GitHub's status page; follow the source link for the full text.
How we track incidents
We open an incident when GitHub Copilot stops looking normal or GitHub posts an official incident, and close it after 15 minutes with everything back to normal. More about our method.