Degraded Gemini 2.5 Pro experience in Copilot
Final update
Between October 1st, 2025 at 1 AM UTC and October 2nd, 2025 at 10:33 PM UTC, the Copilot service experienced a degradation of the Gemini 2.5 Pro model due to an issue with our upstream provider. Before 15:53 UTC on October 1st, users experienced higher error rates with large context requests while using Gemini 2.5 Pro. After 15:53 UTC and until 10:33 PM UTC on October 2nd, requests were restricted to smaller context windows when using Gemini 2.5. Pro. No other models were impacted. The issue was resolved by a mitigation put in place by our provider. GitHub is collaborating with our provider to enhance communication and improve the ability to reproduce issues with the aim to reduce resolution time.
Timeline
- Resolved · Oct 2, 22:33 UTC
Between October 1st, 2025 at 1 AM UTC and October 2nd, 2025 at 10:33 PM UTC, the Copilot service experienced a degradation of the Gemini 2.5 Pro model due to an issue with our upstream provider. Before 15:53 UTC on October 1st, users experienced higher error rates with large context requests while using Gemini 2.5 Pro. After 15:53 UTC and until 10:33 PM UTC on October 2nd, requests were restricted to smaller context windows when using Gemini 2.5. Pro. No other models were impacted. The issue was resolved by a mitigation put in place by our provider. GitHub is collaborating with our provider to enhance communication and improve the ability to reproduce issues with the aim to reduce resolution time.
More from GitHub
Full history| Started | Incident | Impact | Duration |
|---|---|---|---|
| Sep 2416:51 UTC | Disruption with billing information updates | minor | 3h 50m |
| Sep 2310:11 UTC | Incident across several services | minor | 18h 44m |
| Sep 2022:13 UTC | Incident with Pull Requests | minor | 1h 9m |
| Sep 1720:59 UTC | Elevated rate of errors for OpenAI models provided by Copilot | minor | 50m |
| Sep 1607:20 UTC | Degradation with Gemini 3.8 Flash | major | 10h 28m |
| Sep 1519:11 UTC | Disruption with some GitHub services | minor | 49m |
Also caused by third-party dependency
All| Started | Vendor | Incident | Impact | Duration |
|---|---|---|---|---|
| Sep 1609:48 UTC |  DigitalOcean | Support Portal Service DisruptionDigitalOcean | minor | 11h 21m |
| Sep 1608:31 UTC |  Cloudflare | Support Helpdesk Availability IssuesCloudflare | minor | 6h 27m |
| Sep 417:03 UTC |  Grafana Labs | Degradation of Hosted Grafana in US Central RegionGrafana Labs | major | 3h 39m |
| Sep 416:05 UTC |  Expo | Elevated Linux worker queue timesExpo | major | 15h 4m |
| Sep 115:25 UTC | Grafana Labs | Investigating issues in US Central (prod-us-central-0, prod-us-central-5)Grafana Labs | minor | 4h 54m |
| Aug 3106:26 UTC |  Fly.io | Packet loss in ORDFly.io | minor | 1h 44m |
Sources: vendors' own status pages, published postmortems and SEC 8-K Item 1.05 filings, read daily. Times as reported. Logos via logo.dev; trademarks belong to their owners.