Incident with Copilot AI Model Providers

Update timeline

1. investigating Jul 29, 2026, 08:07 PM UTC

   We are investigating reports of degraded performance for Copilot AI Model Providers

2. investigating Jul 29, 2026, 08:07 PM UTC

   We are seeing increased error rates with requests to specific model providers.

3. investigating Jul 29, 2026, 08:18 PM UTC

   We are investigating increased error rates affecting GitHub Copilot requests to external AI model providers. Some users may experience failures or degraded performance when using Copilot features.

4. investigating Jul 29, 2026, 08:38 PM UTC

   The external AI model provider has identified the issue and is working to resolve.

5. investigating Jul 29, 2026, 09:08 PM UTC

   The external AI model provider is continuing to investigate.

6. investigating Jul 29, 2026, 09:51 PM UTC

   The external ai model provider has resolved the issues, and we have verified Copilot's traffic is fully recovered.

7. resolved Jul 29, 2026, 09:51 PM UTC

   This incident has been resolved. Thank you for your patience and understanding as we addressed this issue. A detailed root cause analysis will be shared as soon as it is available.

8. postmortem Aug 12, 2026, 05:25 PM UTC

   On July 29, 2026, between 19:45 UTC and 21:51 UTC, users of the Fable 5 model in GitHub Copilot experienced increased request failures and latency. The average failure rate across all Copilot requests was 0.006%, while failures for Fable 5 peaked at 21%. Other models remained available. This was caused by degradation of an upstream model provider. The affected endpoint recovered, and we monitored the service until error rates and latency returned to normal levels. We are working to add endpoint redundancy to mitigate similar provider issues in the future.