outages.live
Live
SourcegraphIncident · 2026-10-01 19:20 UTC

Code completion for Cody is unavailable

ResolvedOfficial update

The issue has been resolved

The latest update from Sourcegraph.

State

Resolved

Started

31 d ago

2026-10-01 19:20 UTC

Lasted

26 h 33 min

until 2026-10-02 21:53 UTC

Worst impact

Notice

Timeline

2 updates
19:2001:5908:3715:1521:53
NoticeUpdate postedTimes in UTC

Investigating

26 h 33 min 100%

Updates

Times in UTC

As posted by Sourcegraph

Resolved2026-10-02 21:53 UTC

The issue has been resolved

Investigating2026-10-01 19:20 UTC

We noticed our default code completion model is down and we are investigating

Sourcegraph in the last 90 days

Full history
90 days agoToday

Incidents in 90 days

9

Days with an incident

17

Median duration

18 h 6 min

This incident

1.5× the median

How long each incident lasted, on the day it started. The outlined bar is this incident.

5 days
median 18 h 6 min
90 days agoToday

Other Sourcegraph incidents

All incidents

Sourcegraph·Sourcegraph.com public code search issues

The issue has been resolved

Resolvedresolved 12 d ago

Sourcegraph·Sourcegraph Cloud is degraded in Europe region

The issue has been resolved

Resolvedresolved 12 d ago

Sourcegraph·Sourcegraph Cloud is degraded in US Central region

The issue has been resolved

Resolvedresolved 53 d ago

Sourcegraph·Sign-in and authentication errors

The issue has been resolved

Resolvedresolved 60 d ago

Sourcegraph·Cloud customers might see degraded performance because of underling Google Platform issues

The issue has been resolved

Resolvedresolved 61 d ago

Follow Sourcegraph

Your coding agent knows when Sourcegraph is down, and tells you when a failure is theirs, not yours. You can also get Sourcegraph incidents in a feed reader or in Slack.

Prompt
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.

Add it as a remote MCP server named "outages" at https://outages.cc/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.

Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "sourcegraph" and tell me if Sourcegraph has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.

Paste this into any coding agent. It adds the server with its own MCP setup.

RSS
https://outages.cc/feed.xml?providers=sourcegraph
Slack
/feed subscribe https://outages.cc/feed.xml?providers=sourcegraph

FAQ

Go from tracking outages to fixing production issues with Polylane.

Try Polylane