INCIDENT OFICIAL ARCHIVADO

Disruption with some GitHub services

GitHub · Último estado guardado del proveedor: resolved

Informe actual del servicio →

El texto de la fuente oficial se muestra en su idioma original.

Es evidencia histórica.

El último estado guardado de un evento no es el estado actual del servicio. Las listas de fuentes pueden ser incompletas, y desaparecer de una fuente no confirma recuperación. Abre el informe actual o la fuente oficial para obtener evidencia más reciente.

Detalles de evento guardados

Estado del proveedor
resolved
Impacto del proveedor
minor
Registro del proveedor creado
15 Sep 2026, 09:47:15 UTC
Registro del proveedor actualizado
22 Sep 2026, 12:41:35 UTC
Inicio explícito del proveedor
15 Sep 2026, 09:47:15 UTC
Fin explícito del proveedor
15 Sep 2026, 11:17:22 UTC

Componentes afectados reportados por el proveedor

  • Copilot AI Model Providers cnnb39dkkk82

Estas asociaciones describen el alcance reportado del evento. No establecen disponibilidad actual de componentes ni dependencias verificadas.

La hora de creación de un registro no es necesariamente el inicio de una interrupción. Las horas no reportadas siguen sin estar disponibles. No calculamos el tiempo de inactividad a partir de las horas de recopilación.

Actualizaciones del proveedor en revisiones guardadas

Más recientes primero. Mostramos hasta 100 actualizaciones distintas de las últimas 20 revisiones de contenido guardadas. Las modificaciones de redacción a la misma hora del proveedor se conservan por separado.

  1. resolved

    On September 15, 2026, between 05:45 and 09:50 UTC, the Claude Fable 5.1 model in GitHub Copilot experienced intermittently degraded availability, with an average error rate of 2.8%. During brief recurring 15 minute periods that recurred every ~45 minutes, availability for Claude Fable 5.1 dropped to a maximum of ~40% before recovering completely. Other Copilot models were not affected. Users could continue to work with a different model or with 'Auto'.<br /><br />The cause was an issue with an upstream model provider that intermittently rejected requests while overloaded. GitHub worked with the provider, who acknowledged and then resolved the underlying issue at 9:50 UTC, after which the model returned to constant normal availability. Once recovery was guaranteed, we resolved the incident at 11:17 UTC.<br /><br />To reduce the chance of recurrence and customer impact, GitHub is reviewing per-model availability alerting and automatic in-product fallback so that requests to a degraded model can shift to a healthy alternative more quickly.

    Visto en una revisión guardada a las 06 Oct 2026, 13:58:39 UTC
  2. investigating

    The issues with our upstream model provider have been resolved, and Claude Fable 5.1 is once again available in Copilot products and IDE surfaces.<br /><br />We will continue monitoring to ensure stability, but mitigation is complete.

    Visto en una revisión guardada a las 06 Oct 2026, 13:58:39 UTC
  3. investigating

    We continue to monitor intermittent errors affecting Claude Fable 5.1 in some Copilot products and integrated development environments. Customer-facing metrics have recovered, and we are awaiting confirmation from our upstream provider that the issue will not recur. Customers can select another model or Auto in the meantime.

    Visto en una revisión guardada a las 06 Oct 2026, 13:58:39 UTC
  4. investigating

    We continue to investigate intermittent errors affecting Claude Fable 5.1 in some Copilot products and integrated development environments. Customers can use another model or select Auto while we monitor the situation.

    Visto en una revisión guardada a las 06 Oct 2026, 13:58:39 UTC
  5. investigating

    Copilot AI Model Providers is experiencing degraded performance. We are continuing to investigate.

    Visto en una revisión guardada a las 06 Oct 2026, 13:58:39 UTC
  6. monitoring

    We are investigating degraded availability for Claude Fable 5.1, affecting some Copilot products and integrated development environments. The issue is caused by a problem with our upstream model provider. Customers can use another model or select Auto while we investigate.

    Visto en una revisión guardada a las 06 Oct 2026, 13:58:39 UTC
  7. investigating

    We are investigating reports of impacted performance for some GitHub services.

    Visto en una revisión guardada a las 06 Oct 2026, 13:58:39 UTC