Find a file
oskar 1cd6401adb mitigation(solaria): M1 — NODE_TYPE=lte_node wyłącza prune node-agenta
Mitygacja tymczasowa z incydentu 2026-07-30-ollama-solaria-vanish (§7, M1),
na czas backfillu embed (faza mailowa KB). Na SOLARII node-agent robił
niefiltrowany `docker container prune` co cykl (60 s), kasując również
kontenery z `restart: unless-stopped` zatrzymane świadomie przez operatora.

Zweryfikowane w kodzie (services/node-agent/src/node_agent.py, linie zgodne
z incydentem): `self.node_type` jest czytane wyłącznie w run_safe_cleanup()
(648, 654) i w dwóch liniach logu (250, 1103). `lte_node` daje wczesny return
w run_safe_cleanup — monitoring, eventy, dispatch akcji bez zmian.
_cleanup_control_plane_fs jest bramkowane node_name == VPS, nie node_type.
stability-agent nie prune'uje — node-agent był jedynym źródłem.

Ścieżka deployu zweryfikowana: deploy-service.sh:100 składa
${HOST_DIR}/runtime/${SERVICE}/docker-compose.override.yml, a HOST_DIR to
hosts/<node> w obu wywołaniach (deploy-node.sh:102 operatorskie,
deploy-runner.sh:170 agentowe). Dowód, że plik nie jest martwy: działający
kontener na SOLARII ma NODE_TYPE=ai_node, co występuje wyłącznie w tym pliku.
`docker compose config` na złożeniu daje NODE_TYPE=lte_node, group_add 999+996
zachowane, projekt "node-agent" (bez zmiany nazwy projektu).

Skutek uboczny: lte_node pomija CAŁY cleanup, więc dangling images i build
cache też nie są sprzątane — pilnować miejsca na dysku SOLARII.

Zdjąć po wdrożeniu R1 na nodzie → przywrócić NODE_TYPE=ai_node.
Nie zdeployowane — deploy po stronie operatora.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-04 14:49:22 +02:00
.claude/skills docs: session 2026-06-11 — lustro ssh shipping fix + ha-diag-agent piha + backlog/flota-bomba 2026-06-11 14:18:00 +02:00
backups/zigbee Add Zigbee coordinator backup 2026-05-14 18:24:26 +02:00
docs mitigation(solaria): M1 — NODE_TYPE=lte_node wyłącza prune node-agenta 2026-08-04 14:49:22 +02:00
dotfiles add shared zshrc 2026-05-10 20:52:44 +02:00
hardware/esp/ir-ac-ha-integration feat(gree-ir): wlasny komponent ESPHome dla klimy Gree 2026-07-22 16:46:03 +02:00
hosts mitigation(solaria): M1 — NODE_TYPE=lte_node wyłącza prune node-agenta 2026-08-04 14:49:22 +02:00
inventory docs(topology): lustro daily duty cycle — nightly power-off, expected liveness cycles 2026-07-30 15:36:13 +02:00
jobs fix(control-plane): redeploy wykonywalny — dispatch do host-side deploy-runnera 2026-08-03 18:26:30 +02:00
packages feat(kb-retrieval,kb-query): add hybrid retrieval mode (faza mailowa Krok 3) 2026-07-23 17:06:49 +02:00
scripts fix(control-plane): redeploy wykonywalny — dispatch do host-side deploy-runnera 2026-08-03 18:26:30 +02:00
services fix(control-plane): redeploy wykonywalny — dispatch do host-side deploy-runnera 2026-08-03 18:26:30 +02:00
.codex Document current homelab state 2026-04-15 17:37:25 +02:00
.gitignore feat(hardware): ESPHome Gree IR blaster (Wemos D1 Mini + Grove IR) 2026-07-22 16:46:03 +02:00
.mcp.json feat(ha-mcp): read-only MCP server (faza 2a) 2026-07-30 16:47:27 +02:00
CLAUDE.md fix(control-plane): redeploy wykonywalny — dispatch do host-side deploy-runnera 2026-08-03 18:26:30 +02:00
codex_context Add session context state 2026-04-20 22:10:39 +02:00
codex_context.yaml add shared context lock 2026-05-05 17:25:50 +02:00
deploy_agent.py Add deploy escalation output 2026-04-22 22:08:26 +02:00
ollama_client.py Initial shared homelab agent workspace 2026-05-03 19:37:40 +02:00
README.md docs: add link to maintenance plan in README.md 2026-08-03 13:03:58 +02:00
start-aider.sh Initial shared homelab agent workspace 2026-05-03 19:37:40 +02:00
start-codex.sh Initial shared homelab agent workspace 2026-05-03 19:37:40 +02:00
sync-context.sh add shared context lock 2026-05-05 17:25:50 +02:00
tech-debt.md docs(tech-debt): cleanup artefaktow paste-error w ~oskar (SOLARIA, niski prio) 2026-06-24 17:13:51 +02:00
update-context.md Initial shared homelab agent workspace 2026-05-03 19:37:40 +02:00

Homelab Codex

GitOps-lite orchestration for a distributed homelab environment.

Architecture

The homelab consists of several nodes connected via a Tailscale internal mesh.

Host Role Description
SATURN Primary Node Development, orchestration, and git source of truth (commit node).
SOLARIA Compute Node GPU, inference, and heavy compute workloads.
PIHA Infra Node Core infrastructure services, automation, and monitoring.
VPS Edge Node Public ingress, reverse proxy, and edge services.

Agent System

The homelab uses a multi-agent orchestration model with human-in-the-loop for destructive actions:

Agent Node Role
stability-agent all nodes Per-node watchdog — monitors Docker, disk, Tailscale, MQTT; emits events
node-agent all nodes Publishes container health events to Redis pub/sub
observer VPS Synthesizes world state from events into /opt/homelab/world/*.json
supervisor VPS Detects drift between desired and actual state; writes pending actions
planner-agent SOLARIA LLM-powered diagnosis — listens to Redis, proposes remediation actions
executor VPS Executes actions only after operator approval
operator-ui + telegram-bot VPS / PIHA Operator reviews and approves/rejects pending actions

Action approval flow: pending/ → operator approves → approved/ → executor runs.

Repository Structure

Getting Started

  1. Standardization: Follow the Infrastructure Standards.
  2. Deployment: See Deployment Conventions for how to roll out changes.
  3. SATURN: Remember that SATURN is the only node where commits should be made.

Documentation Index


Note: This repository documents the state of the homelab. Runtime state lives outside the repository in /opt/homelab.