co-op/ops-docs
2
0 Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity
70 Commits 6 Branches 0 Tags
main
Commit Graph
5 Commits
Author SHA1 Message Date
inference-bot fcd4ac6943 incident: portal's copied LiteLLM DB credential rotted after the 2026-11-05 gateway restore; all-time spend silently read $0 — timeline, fix, the digest spend-consistency guard, and the two-copies-of-one-secret dependency flagged for the next rotation 2026-11-05 19:10:26 +00:00
inference-bot bb10d93412 incident: 2026-11-05 gateway addon loss during multi-app deploy — wiped LiteLLM DB, restored from the pre-deploy snapshot the same hour 
Full mechanics, impact, detection and prevention in the file. Portal
member data was never at risk.
 2026-11-05 16:36:05 +00:00
inference-bot b1a1c70e8a ops: record the allowance-shortfall manual-remediation ledger 
The portal's SHORTFALL_REMEDIATED constant now carries only the OC charge
reference (de-PII'd from the public member-portal repo); the member
identity and the timeline of the manual reset live here, keyed on the
charge, plus the rationale for charging-keyed exclusion.
 2026-11-05 15:59:13 +00:00
solo.istandClaude Fable 5.1 891490d0d7 incidents: fix the 2026-10-02 byline date and the outage duration (review) 
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
 2026-10-27 01:34:15 -04:00
solo.ist 317af55621 incidents: add the 2026-10-02 gateway outage write-up (from the unmerged incident branch) 
The write-up has sat on incident/2026-10-02-gateway-cve-upgrade since the
outage and that branch is now far behind main. This lifts just the incident
text and the CVE note into incidents/, attributed to InferenceBot with the
substance unchanged, and links it from infrastructure.md under a new
Incident log section.
 2026-10-26 02:11:33 -04:00