Incidents and maintenance reported on status page for Mira https://status.mira.day/ https://d1lppblt9t2x15.cloudfront.net/logos/9cd741e2689d13d0327887321ec70d97.png https://status.mira.day/ en https://status.mira.day/incident/1048095 Thu, 03 Sep 2026 05:39:24 -0000 https://status.mira.day/incident/1048095#abdec463f47e3d881a22d7edb9adbecd06f23dc2bf7f8e7e80eebf7cf45cce4a Incident Resolved. Our infrastructure provider has closed their incident and all regions are reported fully operational. Summary: tasks that run code, generate files, or execute shell commands failed to start between 01:44 and 02:01 UTC (approximately 17 minutes), with reduced reliability and slower start times continuing until 02:16 UTC. Since then we have recorded no failed sandbox provisioning attempts and no elevated latency across several hours of normal traffic. Everything is working normally. If a task of yours failed during the window above, simply run it again. Thank you for your patience. https://status.mira.day/incident/1048095 Thu, 03 Sep 2026 02:49:42 -0000 https://status.mira.day/incident/1048095#c1b77369ec5d17e1ef9d38189c3b04927c1cd5660f079607f165223e851f8b8e Incident Our error rates are back to baseline. No task has failed to start since 02:01 UTC, and we have recorded no failed sandbox provisioning attempts at all since 02:16 UTC. Sandbox start and suspend latency has returned to normal levels. Our infrastructure provider reports that their service has recovered and is holding their incident in a monitoring state to confirm stability. We are mirroring that posture: this component stays marked as degraded until they close their incident, at which point we will mark it operational. Tasks that run code or generate files are working normally. No action is needed on your side. https://status.mira.day/incident/1048095 Thu, 03 Sep 2026 02:19:47 -0000 https://status.mira.day/incident/1048095#ce5d0ad78342eb56e7f42f8acfa8bc3b6633dd9e3a3288c9e6f9f5113e42690d Incident Correction: this incident is not fully resolved. Our infrastructure provider's incident is still open. Task-starting failures stopped at 02:01 UTC and tasks have been completing since, but a portion of sandbox provisioning requests is still failing upstream and being absorbed by automatic retries. The practical effect for you is that tasks which run code or generate files may take longer than usual to start, and there is a risk of renewed failures until the provider completes their fix. We are keeping this component marked as degraded and monitoring continuously. We will mark it operational only once the upstream incident is closed and our error rate returns to baseline. https://status.mira.day/incident/1048095 Thu, 03 Sep 2026 02:01:00 -0000 https://status.mira.day/incident/1048095#dbc99be66e7c941dcf478d0a23758b9ba6315c7d820c8f44339f3d879542edd8 Incident Sandbox provisioning recovered at 02:01 UTC and tasks have been completing normally since. Total impact window was approximately 17 minutes. A small amount of elevated latency remains on an internal sandbox suspend operation. This is not user-visible and does not affect task execution; we are monitoring it. https://status.mira.day/incident/1048095 Thu, 03 Sep 2026 01:44:00 -0000 https://status.mira.day/incident/1048095#8f8c113857f9a5ec6dfaac5c1065b6dd95a82c60243bbf3c31179860bb1bbfa3 Incident Between 01:44 and 02:01 UTC on September 3, tasks that run code, generate files, or execute shell commands failed to start. Affected tasks returned an error in the conversation instead of completing, and some stalled before timing out. The cause was an outage at the third-party infrastructure provider that hosts our task sandboxes. Their gateway rejected sandbox provisioning requests for the duration of the window, so retries could not succeed either. Regular chat, search, and people and company lookups were not affected during this period. Service has recovered and new tasks are running normally. If a task of yours failed in this window, please run it again. We are following up with the provider. https://status.mira.day/incident/1020527 Wed, 19 Aug 2026 06:47:31 -0000 https://status.mira.day/incident/1020527#b66227e4fe7c808f98aaa1d448465ded6375f0a095d46bf5dc44a2927033aa4f Incident A fix has been deployed and image & PDF attachments are being processed normally again. Impact window: Aug 18, 10:00 UTC – Aug 19, 05:27 UTC (~19.5 hours). During this period, attachments uploaded to tasks were not visible to the assistant; approximately 60 tasks were affected. We have added regression tests and error-level monitoring for this code path to prevent recurrence. We apologize for the inconvenience. https://status.mira.day/incident/1020527 Tue, 18 Aug 2026 10:00:00 -0000 https://status.mira.day/incident/1020527#7264146e3081eb73c50fe60894d195f1130c7ab0c639e7cb90a166182c207b1d Incident Since Aug 18, ~10:00 UTC, image and PDF attachments uploaded to tasks may not be taken into account by the assistant — responses may appear as if the attachment was never received. Text input is unaffected. We have identified the root cause and a fix is in progress. Workaround: paste the text content of documents directly into the chat. We will post another update as soon as the fix is deployed.