# Operations

Procedures for operating the fleet. The LLM-specific pages live under
; infrastructure and architecture under the
`../Infrastructure/` and `../Architecture/` folders.

- [[Remote Job Runner]] — Detached long jobs with sentinel files: why tail-watchers fail structurally, the script, its invariants, verification.
- [[Payload and Disk Reclaim]] — Disk pressure procedure: measure every bucket, classify, prove nothing references the payload, stage, purge on approval.
- [[Container Host Reachability]] — Two reachability quirks: containers cannot dial unpublished host ports, and netns membership decides reachability.
- [[Fleet Ops Playbook]] — Incident-shaped procedures: endpoint down with a GPU holder, stop-first bench windows, service iteration, waking a host.
- [[Fleet Audit and Posture]] — Three standing audits: monitoring completeness, vhost proxy health, and behavioural security posture.
- [[SSH and Remote Access]] — Passwordless SSH bootstrap without sshpass, remote execution against fish login shells, and frozen-GUI triage.

## Related
- [Observability Provisioning](../Infrastructure/Observability%20Provisioning.md)
  — monitoring config as code
- [Deploy State Triage](../Architecture/Deploy%20State%20Triage.md) — the
  deploy plumbing
- [Quadlet Lifecycle](../Architecture/Quadlet%20Lifecycle.md) — the unit layer