Wiki audit 2026-09-30: managed-runtime dependency incident, cron fleet reconciliation, provider/model refresh
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
# Anthony's Systems Wiki
|
||||
> Operational knowledge for Anthony's agents, infrastructure,
|
||||
> model routing and automation. Last updated: 2026-09-20
|
||||
> model routing and automation. Last updated: 2026-09-30
|
||||
|
||||
## Start here
|
||||
- [[current-state]] — Current systems status
|
||||
@@ -28,10 +28,11 @@
|
||||
|
||||
### Integrations
|
||||
- [[systems/messaging-integrations]] — Telegram, Discord, email, Slack, etc.
|
||||
- [[systems/scheduled-tasks]] — 27 active cron jobs
|
||||
- [[systems/scheduled-tasks]] — 30 cron jobs (27 enabled, 3 disabled)
|
||||
- [[systems/skills-index]] — Installed skills inventory (auto-regenerated daily)
|
||||
|
||||
## Incidents
|
||||
- [[incidents/2026-09-28-hermes-managed-runtime-deps]] — Managed-runtime venvs missing `dotenv`/`mnemosyne` broke every cron worker (resolved 2026-09-30); dependency guard now runs every 15 min
|
||||
- [[incidents/2026-08-18-mnemosyne-capture-pipeline]] — Mnemosyne capture pipeline broken (active); ~48h of turns not captured
|
||||
- [[incidents/2026-08-15-skills-index-drift]] — Skills index 4x undercount (66 vs 330 installed); fixed via auto-regeneration
|
||||
|
||||
|
||||
Reference in New Issue
Block a user