services: node-agent: environment: - NODE_NAME=vps - CHECK_INTERVAL=60 # TEMPORARY mitigation (M1) for the unfiltered-prune incident # (docs/incidents/2026-07-30-ollama-solaria-vanish.md §7). node-agent runs # `docker container prune()` with NO filters every CHECK_INTERVAL, and the # Docker API removes EVERY non-running container regardless of restart # policy or compose labels — this already destroyed ollama@solaria. On VPS # the loss is worse: humanai-mailer and humanai-landing have no compose # definition in this repo, so a pruned container cannot be recreated. # node_type is read ONLY by run_safe_cleanup() (plus two log lines), so # lte_node disables cleanup and nothing else — monitoring, event shipping # and action dispatch keep working. # REMOVE once R1 (explicit-enumeration prune) is deployed to VPS. - NODE_TYPE=lte_node # host network mode: node-agent on VPS shares the host's network namespace # so that localhost:18180 resolves to the control-plane's exposed port. # Without this, localhost inside the container is the container's own loopback # and the _check_control_plane_health() probe would always fail. network_mode: host # HARD memory ceiling: node-agent mounts /opt/homelab/events/ (page cache) # and may accumulate Python RSS over hours; 640m cap ensures it is killed and # auto-restarted by Docker before consuming host memory. oom_score_adj -900 # prevents the host kernel OOM-killer from picking it as a global victim. mem_limit: 640m oom_score_adj: -900