391a7f2f1f
Now that both the agent image (a68d1c4d, via the kustomize images: override) and the hux sidecar (build-39) are multi-arch with amd64 leaves, move the worker onto the amd64 accelerator titan-22: - Add an OR'd nodeSelectorTerm for amd64 + node-role.kubernetes.io/accelerator + hostname titan-22, with NO worker=true requirement. Keep the arm64 pi-fleet term as an OR'd fallback so the worker is never stranded. - Strong primary preference: hostname=titan-22 at weight 100 (scheduler max), pi-fleet rpi5 nudge lowered to 50, so hermes actually lives on titan-22. - Tolerate node-role.kubernetes.io/accelerator=true:NoSchedule (harmless where absent) and the soft atlas.bstein.dev/media-primary:PreferNoSchedule that titan-22 currently carries, so the weight-100 preference is not offset and placement is deterministic. Completes the titan-22 effort the flip branches missed; the earlier branches never repointed to multi-arch images, which is why the worker never landed here. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01BvMSXH8VH2tMWXanb8SJdf
titan-iac
Flux-managed Kubernetes desired-state config for bstein.dev.
Canonical source URL:
ssh://git@scm.bstein.dev:2242/atlas/titan-iac.git
Scope
This repo contains cluster configuration consumed by Flux:
- platform/infrastructure manifests
- service manifests and kustomizations
- operational scripts for render/reconcile workflows
Apply model
I use Git + Flux as the source of truth and avoid manual in-cluster edits for durable changes.