Incident with Copilot

What to do

• Check whether you use GitHub Copilot. Check your stack

  Paste a package.json, lockfile, Terraform or a list of domains at down.guide/stack to see every provider you depend on.

• Confirm your retries, queues and scheduled jobs caught up after the 1h 32m it lasted.

  Anything that failed between 2026-08-03 09:53 UTC and 2026-08-03 11:25 UTC may need a replay.

• Subscribe to GitHub's feed to hear about the next one first. RSS feed

  https://down.guide/feed?provider=github works in Slack (/feed subscribe), Discord feed bots and any RSS reader.

Updates from GitHub 5

1. investigatingAug 3, 2026, 9:53 AM UTC

   We are investigating reports of degraded performance for Copilot

   provider

2. investigatingAug 3, 2026, 9:54 AM UTC

   We are experiencing degraded availability for chat & agent models in Copilot. Multiple models are impacted and customers may experience requests failing. We are investigating and will provide an update as soon as possible.

   provider

3. investigatingAug 3, 2026, 10:35 AM UTC

   We are still seeing intermittent errors with Copilot, and are continuing to investigate and consider mitigations.

   provider

4. monitoringAug 3, 2026, 11:19 AM UTC

   The degradation affecting Copilot has been mitigated. We are monitoring to ensure stability.

   provider

5. resolvedAug 3, 2026, 11:25 AM UTC

   On 2026-08-03, between 06:52 and 11:25 UTC, some GitHub Copilot users experienced errors when using chat and agent features. Requests to list the available models failed, and because every chat or agent interaction begins by retrieving the list of models, affected users saw their requests fail. On average about 3% of these model-listing requests failed during the incident (roughly 97% succeeded), but failures were significantly higher during peak-traffic periods, at times approaching 100% for the affected internal lookups. Approximately 4,066 users were affected in a single 60-minute window, concentrated among IDE-based clients. The underlying AI models themselves remained healthy throughout. The incident was caused by an increase in how often clients requested the model list, which pushed an internal user-authorization lookup past a rate limit; the rate-limited responses were surfaced to users as errors. We mitigated the impact by increasing how long Copilot caches that authorization lookup, which reduced load on the internal service, and we have additional capacity and rate-limit changes in progress. To prevent recurrence we are improving monitoring for this class of failure, adjusting cache and rate-limit settings, and coordinating with client teams on request patterns.

   provider

Corrections

None so far.

Something wrong on this page? Report an error or send us a note. Every fix is listed here.