Incident with Copilot AI Model Providers
This summary is created by Generative AI and may differ from the actual content.
Overview
On August 1, 2026, between 17:47 UTC and 18:20 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 0.007%, while failures for Fable 5 peaked at 5.6%. Other models remained available. The incident was caused by degradation of an upstream model provider. The affected endpoint recovered, and the service was monitored until error rates and latency returned to normal levels.
Impact
Fable 5 model experienced peak failure rate of 5.6% while average failure rate across all Copilot requests was 0.007%. Other models remained available and unaffected. The incident lasted 33 minutes.
Trigger
Degradation of an upstream model provider caused increased request failures and latency for the Fable 5 model.
Detection
Degraded performance for Copilot AI Model Providers was detected at 18:03 UTC. Increased error rates from specific upstream AI Model Providers were identified, prompting investigation.
Resolution
The affected endpoint recovered. Users were advised to choose another model or select 'Auto' to continue using Copilot. The service was monitored until error rates and latency returned to normal levels. The upstream model provider issue was resolved by 18:20 UTC. Future mitigation includes adding endpoint redundancy to mitigate similar provider issues.
Root Cause
Degradation of an upstream model provider caused the incident. The root cause analysis indicates a dependency on a single upstream provider without sufficient redundancy.