Factory

Affected: api.factory.ai, Web App, Desktop

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. identified 2026-09-18 22:57 UTC

   User logins are currently unavailable due to a critical incident with our authentication provider, WorkOS. Users will be unable to log in or create new sessions at this time. Our engineering team is closely tracking the situation with the vendor to ensure fast recovery once...

2. identified 2026-09-18 22:58 UTC

   For live updates on the incident, check the official WorkOS Status Page at https://status.workos.com

3. resolved 2026-09-18 23:10 UTC

   The incident affecting our authentication provider, WorkOS, has been resolved. For full details regarding the resolution, please visit the WorkOS Status Page at https://status.workos.com/incidents/phs2prf38d75

Excerpts are shortened. Read the full incident on Factory's status page.

Affected: GLM

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. monitoring 2026-08-25 16:06 UTC

   We're having issues with our inference provider for GLM 5.2 in the EU. We'll update here until the model is back up.

2. resolved 2026-08-25 16:11 UTC

   GLM 5.2 is available again in EU.

Excerpts are shortened. Read the full incident on Factory's status page.

Affected: DeepSeek

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2026-08-19 07:37 UTC

   We're monitoring an issue with our DeepSeek V4 Flash deployment that is causing slow response times. We will provide an update once this has been resolved.

2. resolved 2026-08-19 08:05 UTC

   Response times have recovered to baseline levels.

Excerpts are shortened. Read the full incident on Factory's status page.

Affected: MiniMax

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. identified 2026-08-11 19:24 UTC

   We have identified an issue with our Minimax M3 serving. We are in communication with our providers and awaiting resolution. We advise temporarily switching to other models in the meantime for uninterrupted workflow.

2. monitoring 2026-08-11 20:36 UTC

   We are observing improved Minimax M3 serving. We will keep monitoring the service quality to make sure it is fully recovered.

3. resolved 2026-08-11 21:22 UTC

   Minimax M3 serving is fully restored.

Excerpts are shortened. Read the full incident on Factory's status page.

Affected: OpenAI

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

Names an upstream provider: OpenAI.

1. monitoring 2026-08-07 16:12 UTC

   OpenAI models may return 'Error: 431 status code (no body)'. We are in communication with OpenAI and awaiting resolution.

2. monitoring 2026-08-07 18:32 UTC

   We continue to investigate 431 errors from OpenAI models. We advise temporarily switching to non-OpenAI models for uninterrupted workflow.

3. monitoring 2026-08-07 18:49 UTC

   To mitigate the issue, users encountering 431 errors should update to Factory CLI `0.188.0` or newer, or Desktop `0.145.0` or newer

4. resolved 2026-08-07 21:14 UTC

   We deployed a backend fix for the errors affecting OpenAI models and have confirmed that error rates returned to normal. Users can resume normal usage; no Factory CLI or Desktop update or other action is required.

Excerpts are shortened. Read the full incident on Factory's status page.

Affected: Web App, CLI, Desktop

Failure mode: A configuration change caused the failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-08-01 00:43 UTC

   Enterprise accounts are being prompted for billing info when this should be isolated to self-serve

2. investigating 2026-08-01 00:58 UTC

   Enterprise accounts are being prompted for billing info when this should be isolated to self-serve

3. identified 2026-08-01 00:59 UTC

   Enterprise accounts are being prompted for billing info when this should be isolated to self-serve

4. resolved 2026-08-01 01:35 UTC

   Fix has been deployed in production.

Excerpts are shortened. Read the full incident on Factory's status page.

Failure mode: Login, tokens, certificates or credentials failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. resolved 2026-07-26 07:00 UTC

   Windows users faced an issue blocking login on the latest version of the Desktop App.

Excerpts are shortened. Read the full incident on Factory's status page.

Affected: api.factory.ai, Web App

Failure mode: A code release introduced the failure. Root cause: A bug in the vendor's own code. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. monitoring 2026-07-23 01:21 UTC

   Actions to subscriptions like creation and cancellation have been failing.

2. monitoring 2026-07-23 01:31 UTC

   A new release is being hotfixed.

3. monitoring 2026-07-23 01:43 UTC

   The fix has been deployed. Seeing signs of recovery.

4. resolved 2026-07-23 01:52 UTC

   All actions have fully recovered.

Excerpts are shortened. Read the full incident on Factory's status page.