refactor: make engine domain-agnostic — identity from node.env, no hardcoded domain

Drop the hardcoded-domain FQDN regex and every hardcoded domain from commons.
Node identity is now explicit in node.env: APEX_NODE_FQDN (real FQDN,
traefik Host()), APEX_NODE_HOST (public host name — backup --host,
obs/notify instance), APEX_SUBNET. The short name (log prefix, sync/<node>
branch, messages) is derived as the first host label.

notify instance is just the host (no hardcoded prefix); the git bot identity
moves to APEX_GIT_AUTHOR_NAME/EMAIL (node.env) with generic defaults. Alloy
node+instance labels use APEX_NODE_HOST. Fallbacks keep a node working if it
omits a var (host<-fqdn<-hostname).

BREAKING CHANGE: removes APEX_NODE and APEX_CLUSTER env vars; node name is now derived from APEX_NODE_FQDN
This commit is contained in:
deytenit committed 2026-07-08 09:32:20 +03:00
1 parent 53d3bedca6
commit bd973d783d
13 files changed
+105 -107

No files matched your search

+7 -7
View File
@@ -16,7 +16,7 @@ TITLE = "Restic Host Backup"
def run(ctx, args):
log, node, url = ctx.log, ctx.node.name, args.telegram_bot_url
core = ctx.paths.core
host = f"{node}.apex.ermnvldmr.com" # restic --host: the per-node public name (matches the bucket)
host = ctx.node.host # restic --host: the node's public host name (APEX_NODE_HOST)
tag = "biweekly" # restic --tag: snapshot cadence (this cron fires on the 5th & 20th)
if not os.path.isfile(os.path.join(core, "docker-compose.yml")):
log.error(f"Core compose not found in {core}"); raise SystemExit(1)
@@ -47,12 +47,12 @@ def run(ctx, args):
if restic("snapshots", check=False).returncode == 0:
log.info("Restic repository reachable.")
elif restic("init", check=False).returncode != 0:
ctx.notify.error(TITLE, url, "restic init failed", node); raise SystemExit(1)
ctx.notify.error(TITLE, url, "restic init failed"); raise SystemExit(1)
before = host_snapshot_ids()
log.info("Backing up `restic.*`-labelled services (resticontainer discovers paths)...")
if restic("backup", "--host", host, "--tag", tag, "--compression", "max",
check=False).returncode != 0:
ctx.notify.error(TITLE, url, "restic backup failed", node); raise SystemExit(1)
ctx.notify.error(TITLE, url, "restic backup failed"); raise SystemExit(1)
# Guard: the label-driven backup is a silent no-op if no service carries the
# `restic.enable` label (resticontainer finds zero paths and skips restic).
# Prove a fresh snapshot for this host actually landed before we prune/notify.
@@ -60,18 +60,18 @@ def run(ctx, args):
if before is not None and after is not None and not (after - before):
log.error("No new snapshot produced — refusing to report success.")
ctx.notify.error(TITLE, url,
"backup produced no new snapshot (no restic.* labels discovered?)", node)
"backup produced no new snapshot (no restic.* labels discovered?)")
raise SystemExit(1)
log.info("Applying retention (forget --prune)...")
if restic("forget", "--prune", "--keep-daily", "7", "--keep-weekly", "4",
"--keep-monthly", "12", check=False).returncode != 0:
ctx.notify.error(TITLE, url, "restic forget/prune failed", node); raise SystemExit(1)
ctx.notify.error(TITLE, url, "restic forget/prune failed"); raise SystemExit(1)
log.success("Restic backup completed.")
if not ctx.notify.success(TITLE, url, f"Restic backup + retention succeeded for {node}", node):
if not ctx.notify.success(TITLE, url, f"Restic backup + retention succeeded for {node}"):
raise SystemExit(1) # bash exited 1 when the success telegram failed to send
except SystemExit:
raise
except Exception as e:
log.error(f"{type(e).__name__}: {e}")
ctx.notify.error(TITLE, url, f"backup failed: {e}", node)
ctx.notify.error(TITLE, url, f"backup failed: {e}")
raise SystemExit(1)