Wizard agent conversations returning errors
dbt Cloud Wizard agent conversations can return an error on every new message. The problem affects conversations that use Anthropic models, and it is degraded. dbt Cloud identified the cause and a fix is in progress. As a workaround, switch to an OpenAI model, then start a new conversation or continue the affected conversation.
State
Identified
Started
Ongoing for
37 min
Worst impact
Degraded
Timeline
3 updatesIdentified
37 min 100%
Updates
Times in UTCAs posted by dbt Cloud
We have identified the cause of the current issue affecting Wizard agent conversations. Some conversations using Anthropic models may return an error on every new message. Our team is actively working on a fix. In the meantime, switching to an OpenAI model restores functionality. You can start a new conversation, or continue an affected conversation after switching the model.
We have identified the cause of the current issue affecting Wizard agent conversations. Some conversations using Anthropic models may return an error on every new message. Our team is actively working on a fix. In the meantime, selecting a non-Anthropic model for new conversations avoids this issue.
We have identified the cause of the current issue affecting Wizard agent conversations. Some conversations may return an error on every new message. Our team is actively working on a fix.
dbt Cloud in the last 90 days
Full historyIncidents in 90 days
28
Days with an incident
28
Median duration
2 h 17 min
This incident
73% shorter than the median
Other dbt Cloud incidents
All incidentsdbt Cloud·Cloud IDE sessions failed to load
The issue has been resolved, and all affected systems are now functioning normally as of 17:47 UTC. Between 11:24 UTC and 17:47 UTC an issue with a long running CLI worker node resulted in indefinite load times in the IDE. We have put measures in place to prevent a recurrence and IDE behavior has returned to normal. Please contact Support via email [support@getdbt.com](http://support@getdbt.com "support@getdbt.com") if you continue to experience delays and are unsure of the root cause.
dbt Cloud·Jobs list and Environment pages failing to load
dbt Cloud could not load the Jobs page, the Project and Environment pages, and run logs for some accounts on the US and EMEA instances. Scheduled jobs continued to run. dbt Cloud reports that the issue is resolved. The outage lasted about 3 hours and 25 minutes.
dbt Cloud·Git errors for projects connected to GitHub over SSH
Git operations failed for dbt Cloud projects that use a dbt-managed repository or connect to GitHub with a deploy key. The errors were "Permission denied (publickey)" in job runs and dbt Studio git actions. dbt Cloud reports that this incident is resolved. It lasted 1 minute and 43 seconds.
dbt Cloud·dbt Studio error loop with restarting dbt Studio
dbt Cloud reported an error loop in dbt Studio that asked users to restart dbt Studio. The issue affected dbt Project Environments on versions 1.6 and 1.7. dbt Cloud resolved the issue after 86 minutes.
dbt Cloud·Expired GitLab project access tokens not refreshing causing failures in posting commit statuses
dbt Cloud did not post GitLab CI job commit statuses for existing projects with expired GitLab project access tokens. This affected a small number of customers in the EU2 (Azure) region. dbt Cloud reports that the issue is resolved and that it lasted about 111 minutes.
Follow dbt Cloud
Your coding agent knows when dbt Cloud is down, and tells you when a failure is theirs, not yours. You can also get dbt Cloud incidents in a feed reader or in Slack.
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.live/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 "dbt" and tell me if dbt Cloud 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.
https://outages.live/feed.xml?providers=dbt/feed subscribe https://outages.live/feed.xml?providers=dbtFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane