homelab-codex-ws/hosts/solaria
oskar 38cb204a64 fix(ollama): declare service on SOLARIA, restrict bind, add cutover runbook
Ollama's service.yaml/docker-compose.yml declared owner_node: solaria but
was never added to hosts/solaria/services.yaml, the manifest deploy-node.sh
actually reads — so it stayed running manually/natively instead of via the
declarative pipeline. Add the missing entry.

Also switch the port publish from 0.0.0.0 to loopback + TAILSCALE_BIND_IP
(same convention as llm-gateway@PIHA), since this is a private service and
llm-gateway@PIHA is the only consumer beyond the host itself.

Live cutover (relocating the existing native model store, disabling the
systemd unit, bringing up the container, verifying bge-m3 embeddings +
GPU use) is documented in docs/infra/ollama-solaria-cutover-2026-07-15.md
but not executed here — no SSH access to SOLARIA from this worktree.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
2026-07-15 16:09:08 +02:00
..
runtime refactor(kb-postgres): relokacja SOLARIA→PIHA — arm64, mem_limit 1g, tuning pod małą maszynę 2026-06-22 19:59:58 +02:00
capabilities.yaml fix(capabilities): saturn RAM/storage + solaria CPU/storage — reconcile with real hardware (audit 2026-06-30) 2026-07-03 14:45:53 +02:00
host.yaml feat(hosts): add os_hostname field to all host.yaml files 2026-06-24 22:24:34 +02:00
README.md Add infrastructure standards and deployment conventions 2026-05-07 21:16:03 +02:00
services.yaml fix(ollama): declare service on SOLARIA, restrict bind, add cutover runbook 2026-07-15 16:09:08 +02:00

SOLARIA - Compute / GPU / Inference Node

Role

  • High-performance compute tasks.
  • GPU-accelerated workloads (LLM inference, transcoding).

Configured Services

  • Ollama
  • Open WebUI

Runtime Data

  • /opt/homelab/data/ollama