feat(dns): fleet .internal naming — git-sourced, agent-managed, three resolvers

Names for fleet hosts so addresses stop needing to be memorised. Built because
IPv6 makes that hopeless — and, more to the point, because v6 addresses are
derived rather than assigned, so they cannot reliably be written down once and
trusted either.

  dns/internal.yaml     source of truth: 38 hosts + 4 service aliases
  scripts/dns-sync.py   reconciles AdGuard resolvers against it
  stacks/adguard-ana/   the colo's resolver, which did not exist

Naming is <host>.<site>.internal with sites ana/esh/nh3 (operator's call).
.internal is ICANN-reserved for this; .local is reserved for mDNS, which is
why searxng.pfi.local was a collision that merely happened to work.

Same posture as deploy-stack.sh: file is intent, resolvers are derived state,
you see a diff before anything changes. Every name is published to every
resolver, so the site label says where a host IS, not who knows about it.

Two properties that matter:
- Authority is scoped to the ZONE, not the resolver. ESH carries hand-made
  esteban.net rewrites predating this; they are read, ignored and preserved.
  Resolver-wide authority would have silently deleted them.
- Within .internal it IS authoritative, so UI-added names get removed. That is
  the point — one place to look.

Colo gap closed: ana-docker had no resolver at all (hosts went straight to
1.1.1.1). Its AdGuard runs API on 8053 because 8080/3000 were taken, so the
port is carried per-site in the yaml rather than assumed by the script. It
ships with no blocklists — a false positive on a server network breaks
service-to-service calls for no upside.

Auth is a dedicated infra-ops AdGuard user, not the operator's account,
password vaulted at nh3-dev/adguard-infra-ops-password. Pre-change configs
backed up on each resolver. Both resolvers stayed answering across the restart.

searxng.pfi.local -> searxng.ana.internal, with the old Host() kept alongside
so nothing breaks mid-migration. matrix.pfi.local deliberately NOT migrated: a
Matrix server_name is baked into every user id, room id and signing key, so
renaming it rebuilds the homeserver's identity rather than changing a DNS name.

The v6 column is empty and correct — no fleet host has a global v6 address
yet. The file documents why addresses must be pinned statically before they go
in, since a record that silently stops matching is worse than no record.
This commit is contained in:
2026-08-19 01:10:55 -07:00
parent 8189076daf
commit b8003c73ae
7 changed files with 559 additions and 2 deletions
+21
View File
@@ -241,10 +241,31 @@ eshpfi-management/
│ └── README.md # what this stack does, how to deploy
├── stacks-mirror/ # gitignored snapshot of live host state (drift detection)
│ └── <host>/<stack>/ # populated by sync-stacks.sh, NOT a deploy source
├── dns/ # fleet internal DNS — *.internal names
│ ├── internal.yaml # source of truth (hosts, sites, aliases)
│ └── README.md # workflow, naming, IPv6 caveat
└── docs/
└── pfi/ # general PFI infrastructure reference
```
## Internal DNS (`*.internal`)
Fleet hosts have names: `<host>.<site>.internal`, sites `ana` / `esh` / `nh3`.
`dns/internal.yaml` is the source of truth; the AdGuard resolvers are derived
state.
```bash
$EDITOR dns/internal.yaml
scripts/dns-sync.py --dry-run # diff
scripts/dns-sync.py # apply
```
The sync is authoritative **within `.internal` only** — names added by hand in
the AdGuard UI get deleted, but rewrites in other zones (ESH's `esteban.net`
entries) are left alone. See `dns/README.md`, especially the IPv6 note: v6
addresses only go in the file once they are pinned statically on the host,
because SLAAC addresses rotate and a stale record is worse than none.
## Working rules
- **Copies, not symlinks.** Files here reflect what's on the server at the time of the last sync. When you edit here, the server doesn't change until you deploy.
+125
View File
@@ -0,0 +1,125 @@
# Fleet internal DNS — `*.internal`
Names for fleet hosts so nobody has to remember addresses. Built 2026-08-19
because IPv6 makes memorising them hopeless — and, more to the point, because
v6 addresses are *derived* rather than assigned, so they cannot be reliably
memorised **or** written down once and trusted.
```
dns/internal.yaml the source of truth — hosts, sites, aliases
scripts/dns-sync.py reconciles the resolvers against it
```
## Adding a name
Edit `dns/internal.yaml`, then:
```bash
scripts/dns-sync.py --dry-run # see the diff
scripts/dns-sync.py # apply, with a prompt
```
That is the whole workflow. It is deliberately the same shape as
`deploy-stack.sh`: a file in git is the intent, the running system is derived
state, and you see a diff before anything changes.
## Naming
`<host>.<site>.internal`, sites **`ana`** (Anaheim colo), **`esh`** (home lab),
**`nh3`** (office).
`.internal` is ICANN-reserved for private use, which is why it is used here
rather than `.local` (reserved for mDNS — the old `searxng.pfi.local` was a
standards collision that happened to work) or an invented TLD that could later
collide with a real one.
**Every name is published to every resolver.** The site label says where a host
*is*, not which resolver knows about it — `ana-docker.ana.internal` resolves
from ESH and NH3 too.
Irvine is not a fourth zone: `irv-ml1` is reachable only through NH3's
WireGuard tunnel and numbered out of NH3's `10.100.79.0/24`, so it lives under
`nh3`. Worth revisiting if Irvine ever becomes a site in its own right.
## The resolvers
| site | resolver | API port |
|---|---|---|
| ana | ana-docker `10.250.50.70` | **8053** |
| esh | esh-docker-vm `10.0.50.45` | 8080 |
| nh3 | nh3-docker `10.100.50.40` | 8080 |
ana is the odd one out — `:8080` and `:3000` were already taken on that host —
so the port is carried per-site in `internal.yaml` rather than assumed by the
script.
The colo resolver (`stacks/adguard-ana/`) was stood up as part of this work;
before it, colo hosts resolved straight against `1.1.1.1` and the site had no
way to answer for internal names. ESH and NH3 run older, unmanaged compose
files, left alone on purpose — adopting three live resolvers into this repo
while also introducing a new naming system is two risky changes at once.
## Two properties worth not breaking
**Authority is scoped to the zone, not the resolver.** Only rewrites ending in
`.internal` are managed. The ESH resolver carries hand-made `esteban.net`
entries that predate this system; the sync reads them, ignores them, and leaves
them alone. If this ever grows to manage another zone, that scoping is the
thing to be careful with — resolver-wide authority would silently delete
somebody else's work.
**Within the zone it is authoritative.** Names added by hand in the AdGuard UI
*will* be deleted by the next sync. That is the point: one place to look.
## Credential
`scripts/dns-sync.py` authenticates as a dedicated **`infra-ops`** AdGuard user,
not as the operator's account, and pulls the password from the vault:
```bash
secret get nh3-dev/adguard-infra-ops-password
```
⚠️ The vault appends a trailing newline on read. The script strips it, because
a password carrying a stray `\n` fails auth in a way that looks exactly like a
wrong password.
The existing `lkraven` AdGuard user was left untouched. Config backups from
before the user was added are on each resolver as
`AdGuardHome.yaml.bak-preinfraops-*`.
## ⚠️ IPv6 — the reason this exists, and still the unfinished half
The `v6:` column is empty and that is correct as of 2026-08-19: **no fleet host
has a global IPv6 address yet.** ESH's `/56` is live only on `esh-cameras`,
NH3's LANs are back to `ipv6_interface_type: none`, the colo has no v6 at all.
When v6 arrives, **do not paste in whatever `ip -6 addr` shows.** SLAAC gives
hosts either EUI-64 addresses (MAC-coupled) or privacy-extension ones (which
rotate), and UniFi has no v6 equivalent of a DHCP reservation. An address only
belongs in this file once it has been pinned **statically on the host itself**.
A record that silently stops matching reality is worse than no record — the
name keeps resolving and starts lying.
The suggested convention when that happens: give each server a static address
out of its site's `/64` whose low-order bits echo the v4 host octet
(`esh-docker-vm` at `…::45`), so the addresses are both declarable and
semi-memorable.
## Not migrated: `matrix.pfi.local`
`searxng.pfi.local` moved to `searxng.ana.internal` (both names still route,
so nothing breaks mid-migration; drop the fallback `Host()` in
`stacks/searxng/compose.yaml` once the Traefik log shows the old one unused).
**`matrix.pfi.local` was deliberately left alone.** A Matrix `server_name` is
baked into every user ID, room ID and signing key, and federation identity is
derived from it — renaming it is not a DNS change, it is rebuilding the
homeserver's identity and invalidating its history. It stays on `.local`.
## Still open
Colo hosts still point at `1.1.1.1`, so they do not yet *use* the new resolver
— they only get answers if something asks it directly. Repointing a whole
site's DNS is a bigger change than standing the service up, so it is a separate
operator-approved step.
+110
View File
@@ -0,0 +1,110 @@
# Fleet internal DNS — the source of truth for *.internal names.
#
# THIS FILE IS AUTHORITATIVE. `scripts/dns-sync.sh` reconciles every resolver
# against it: names here are created, names removed here are deleted, and
# names edited here are updated. Do NOT add .internal names in the AdGuard UI
# — the next sync will delete them.
#
# WHAT THE SYNC WILL NOT TOUCH: any rewrite outside the `.internal` zone. The
# ESH resolver carries hand-made `esteban.net` entries that predate this file
# and are deliberately left alone. Authority is scoped to the zone, not to the
# resolver's whole table.
#
# NAMING: <host>.<site>.internal, sites `ana` / `esh` / `nh3` (operator,
# 2026-08-19). `.internal` is ICANN-reserved for exactly this use since 2024,
# which is why it is used here rather than `.local` (reserved for mDNS) or a
# made-up TLD that could later collide with a real one.
#
# EVERY name is published to EVERY resolver, so `ana-docker.ana.internal`
# resolves from ESH and NH3 too. The site label says where a host IS, not
# which resolver knows about it.
#
# ⚠️ THE v6 COLUMN IS EMPTY ON PURPOSE, AND MUST STAY DECLARATIVE.
# No fleet host has a global IPv6 address today (verified 2026-08-19: ESH's
# /56 is live only on esh-cameras, NH3's LANs are back to ipv6_interface_type
# none, the colo has no v6 at all). When v6 lands, do NOT paste in whatever
# `ip -6 addr` happens to show: SLAAC addresses are either EUI-64 (MAC-coupled)
# or privacy-extension (they rotate), and UniFi has no v6 equivalent of a DHCP
# reservation. A v6 address only belongs in this file once it has been pinned
# STATICALLY on the host itself — otherwise the record rots silently and the
# name starts lying, which is worse than having no record.
zone: internal
sites:
ana:
subnet: 10.250.0.0/16
resolver: 10.250.50.70 # ana-docker — AdGuard #3, stood up for this
# ⚠️ NOT 8080. ana-docker already has :8080 and :3000 taken, so this
# AdGuard's API is on 8053. The port lives here rather than in the script
# precisely so the odd one out cannot be forgotten.
api_port: 8053
description: Anaheim colo
esh:
subnet: 10.0.0.0/16
resolver: 10.0.50.45 # esh-docker-vm
api_port: 8080
description: ESH home lab (esteban.net)
nh3:
subnet: 10.100.0.0/16
resolver: 10.100.50.40 # nh3-docker
api_port: 8080
description: NH3 office
hosts:
# ---- ana: Anaheim colo ----
- {name: ana-docker, site: ana, v4: 10.250.50.70, note: general-purpose docker host}
- {name: ana-ml2, site: ana, v4: 10.250.50.54, note: GPU inference, dual RTX PRO 6000}
- {name: ana-nas, site: ana, v4: 10.250.50.50, note: CT109 on pfi-pve — NFS/SMB}
- {name: ana-filebot, site: ana, v4: 10.250.50.53, note: file-task automation}
- {name: ana-wg, site: ana, v4: 10.250.50.252, note: WireGuard host}
- {name: corviduo-dev, site: ana, v4: 10.250.50.152, note: Worldtree-team dev VM (PFI-hosted)}
- {name: pbs-ana, site: ana, v4: 10.250.50.90, note: Proxmox Backup Server — fleet primary}
- {name: pfi-ana-webhost, site: ana, v4: 10.250.50.52, note: web workload}
- {name: pfi-postgres, site: ana, v4: 10.250.50.80, note: shared Postgres}
- {name: pfi-pteradactyl, site: ana, v4: 10.250.50.55, note: game panel}
- {name: pfi-tacticalrmm, site: ana, v4: 10.250.50.57, note: TacticalRMM}
- {name: pfi-pve, site: ana, v4: 10.250.250.31, note: Proxmox hypervisor}
- {name: ana-gw, site: ana, v4: 10.250.0.1, note: FortiGate-80F edge}
- {name: pfi-pve-idrac, site: ana, v4: 10.250.250.30, note: iDRAC — OOB for pfi-pve}
- {name: ana-ml2-bmc, site: ana, v4: 10.250.250.50, note: BMC for ana-ml2}
# SureFire tenant hardware — PFI-managed under the hosting agreement.
- {name: sfsrv-ana, site: ana, v4: 10.250.250.115, note: SureFire tenant hypervisor}
- {name: sf-ana-container, site: ana, v4: 10.250.150.100, note: SureFire tenant container host}
- {name: sf-r630-idrac, site: ana, v4: 10.250.250.110, note: SureFire tenant R630 iDRAC}
# ---- nh3: NH3 office ----
- {name: nh3-docker, site: nh3, v4: 10.100.50.40, note: general-purpose docker host + AdGuard}
- {name: nh3-dev, site: nh3, v4: 10.100.10.50, note: dev box, fleet sidecars, Claude sessions}
- {name: nh3-extdev, site: nh3, v4: 10.100.50.42, note: manager / external-dev box}
- {name: nh3-nas, site: nh3, v4: 10.100.50.50, note: Synology RS2418+}
- {name: nh3-pve, site: nh3, v4: 10.100.250.60, note: Proxmox hypervisor}
- {name: pbs-nh3, site: nh3, v4: 10.100.50.90, note: Proxmox Backup Server — DR mirror}
- {name: nh3-gw, site: nh3, v4: 10.100.0.1, note: UniFi UDM Pro SE — gateway + controller}
# Irvine is not its own zone: irv-ml1 is reachable only through NH3's
# WireGuard tunnel and is numbered out of NH3's 10.100.79.0/24, so it is
# named under nh3. Revisit if Irvine ever becomes a site in its own right.
- {name: irv-ml1, site: nh3, v4: 10.100.79.3, note: GPU host (Irvine, via WG) — 3090 + A6000}
# ---- esh: ESH home lab ----
- {name: esh-docker-vm, site: esh, v4: 10.0.50.45, note: general-purpose docker host + AdGuard}
- {name: esh-nas, site: esh, v4: 10.0.50.50, note: NAS}
- {name: esh-pve, site: esh, v4: 10.0.250.35, note: Proxmox hypervisor}
- {name: esh-pve-nas, site: esh, v4: 10.0.50.55, note: Proxmox hypervisor — storage/media}
- {name: esh-vm-db, site: esh, v4: 10.0.50.60, note: PostgreSQL + MongoDB}
- {name: vm-esh-nas, site: esh, v4: 10.0.50.154, note: NAS-adjacent docker host}
- {name: esh-filebot, site: esh, v4: 10.0.50.70, note: restic / file-sync VM}
- {name: esh-gw, site: esh, v4: 10.0.250.1, note: esh-gw}
- {name: esh-udm, site: esh, v4: 10.0.0.1, note: UniFi UDM Pro Max — gateway + controller}
- {name: plex, site: esh, v4: 10.0.50.56, note: media server}
- {name: jellyfin, site: esh, v4: 10.0.50.57, note: media server}
- {name: brother, site: esh, v4: 10.0.90.125, note: Brother printer}
# Service aliases — a name that points at whatever host currently runs it, so
# consumers reference the SERVICE rather than the box. Changing where something
# runs becomes a one-line edit here instead of a hunt through configs.
aliases:
- {name: searxng, site: ana, target: ana-docker, note: replaces searxng.pfi.local (.local is mDNS-reserved)}
- {name: gateway, site: ana, target: ana-docker, note: LiteLLM gateway :4000}
- {name: booth, site: nh3, target: nh3-dev, note: The Booth :8090}
- {name: homepage, site: esh, target: esh-docker-vm, note: fleet dashboard :5100}
+193
View File
@@ -0,0 +1,193 @@
#!/usr/bin/env python3
"""dns-sync.py — reconcile the fleet's AdGuard resolvers against dns/internal.yaml.
Source of truth is the file; the resolvers are derived state. Same posture as
deploy-stack.sh: show a diff, ask, then apply.
scripts/dns-sync.py # diff every resolver, prompt before applying
scripts/dns-sync.py --dry-run # diff only, never write
scripts/dns-sync.py --yes # skip the prompt
scripts/dns-sync.py --site esh # one resolver
AUTHORITY IS SCOPED TO THE ZONE, NOT THE RESOLVER. Only rewrites ending in
`.internal` are considered. The ESH resolver carries hand-made `esteban.net`
entries that predate this system; they are read, ignored, and left alone. If
this ever grows to manage other zones, that scoping is the thing to be careful
with — a resolver-wide authority would silently delete a colleague's work.
CREDENTIAL: pulled from the vault, never hardcoded.
secret get nh3-dev/adguard-infra-ops-password
The vault appends a trailing newline on read; it is stripped here, because a
password with a stray \\n fails auth in a way that looks like a wrong password.
"""
from __future__ import annotations
import argparse
import base64
import json
import pathlib
import subprocess
import sys
import urllib.error
import urllib.request
REPO = pathlib.Path(__file__).resolve().parent.parent
SPEC = REPO / "dns" / "internal.yaml"
SECRET_CLI = REPO / "services" / "secrets-broker" / "secret"
SECRET_NAME = "nh3-dev/adguard-infra-ops-password"
DEFAULT_API_PORT = 8080
USER = "infra-ops"
TIMEOUT = 10
def load_spec() -> dict:
import yaml # local import so --help works without the dep
return yaml.safe_load(SPEC.read_text())
def get_password() -> str:
try:
out = subprocess.run([str(SECRET_CLI), "get", SECRET_NAME],
capture_output=True, text=True, timeout=60)
except FileNotFoundError:
sys.exit(f"secret CLI not found at {SECRET_CLI}")
if out.returncode != 0:
sys.exit(f"could not read {SECRET_NAME} from the vault:\n{out.stderr.strip()}")
pw = out.stdout.strip("\n")
if not pw:
sys.exit(f"{SECRET_NAME} came back empty")
return pw
def desired_pairs(spec: dict) -> set[tuple[str, str]]:
"""The (domain, answer) pairs the zone should contain.
A pair IS AdGuard's identity for a rewrite, which is why this is a set of
tuples rather than a name->address map: a dual-stack host is two rewrites
that share one name, and a map would silently drop one of them.
Every name is published to every resolver — the site label says where a
host IS, not which resolver knows about it.
"""
zone = spec["zone"]
hosts = spec.get("hosts") or []
by_name = {h["name"]: h for h in hosts}
pairs: set[tuple[str, str]] = set()
def emit(fqdn: str, host: dict) -> None:
for key in ("v4", "v6"):
if host.get(key):
pairs.add((fqdn, str(host[key])))
seen: set[str] = set()
for h in hosts:
fqdn = f"{h['name']}.{h['site']}.{zone}"
if fqdn in seen:
sys.exit(f"duplicate name in dns/internal.yaml: {fqdn}")
seen.add(fqdn)
emit(fqdn, h)
for a in spec.get("aliases") or []:
target = by_name.get(a["target"])
if target is None:
sys.exit(f"alias {a['name']} points at unknown host {a['target']!r}")
fqdn = f"{a['name']}.{a['site']}.{zone}"
if fqdn in seen:
sys.exit(f"alias {fqdn} collides with a host of the same name")
seen.add(fqdn)
emit(fqdn, target)
return pairs
def api(host: str, path: str, pw: str, payload: dict | None = None,
port: int = DEFAULT_API_PORT):
url = f"http://{host}:{port}/control/{path}"
data = json.dumps(payload).encode() if payload is not None else None
req = urllib.request.Request(url, data=data, method="POST" if data else "GET")
token = base64.b64encode(f"{USER}:{pw}".encode()).decode()
req.add_header("Authorization", f"Basic {token}")
if data:
req.add_header("Content-Type", "application/json")
try:
with urllib.request.urlopen(req, timeout=TIMEOUT) as r:
body = r.read().decode().strip()
return json.loads(body) if body else None
except urllib.error.HTTPError as e:
sys.exit(f"{host}: {path} -> HTTP {e.code} {e.reason}\n{e.read().decode()[:200]}")
except urllib.error.URLError as e:
sys.exit(f"{host}: unreachable ({e.reason}). Tried port {port}; "
f"run this from a host that can reach it.")
def main() -> None:
ap = argparse.ArgumentParser(description=__doc__,
formatter_class=argparse.RawDescriptionHelpFormatter)
ap.add_argument("--site", help="only this site's resolver")
ap.add_argument("--dry-run", action="store_true", help="diff only, never write")
ap.add_argument("--yes", action="store_true", help="skip the confirmation prompt")
args = ap.parse_args()
spec = load_spec()
zone_suffix = "." + spec["zone"]
want = desired_pairs(spec)
sites = spec["sites"]
if args.site:
if args.site not in sites:
sys.exit(f"unknown site {args.site!r}; known: {', '.join(sites)}")
sites = {args.site: sites[args.site]}
pw = get_password()
plans = {}
for site, cfg in sites.items():
host = cfg["resolver"]
port = int(cfg.get("api_port", DEFAULT_API_PORT))
current_all = api(host, "rewrite/list", pw, port=port) or []
# SCOPE: only our zone. Everything else on this resolver is somebody
# else's and stays untouched.
current = {(r["domain"], r["answer"]) for r in current_all
if r["domain"].endswith(zone_suffix)}
foreign = len(current_all) - len(current)
add = sorted(want - current)
remove = sorted(current - want)
plans[site] = (host, port, add, remove, foreign)
print(f"\n=== {site} ({host}:{port}) ===")
print(f" in zone: {len(current)} outside zone (left alone): {foreign}")
for d, a in add:
print(f" + {d:<44} {a}")
for d, a in remove:
print(f" - {d:<44} {a}")
if not add and not remove:
print(" in sync")
total = sum(len(a) + len(r) for _, _, a, r, _ in plans.values())
if total == 0:
print("\nnothing to do.")
return
if args.dry_run:
print(f"\n--dry-run: {total} change(s) NOT applied.")
return
if not args.yes:
if input(f"\napply {total} change(s)? [y/N] ").strip().lower() not in ("y", "yes"):
sys.exit("aborted.")
for site, (host, port, add, remove, _) in plans.items():
# Delete first: AdGuard tolerates duplicate (domain, answer) pairs, so
# removing before adding keeps a re-pointed name from briefly resolving
# to BOTH its old and new address.
for d, a in remove:
api(host, "rewrite/delete", pw, {"domain": d, "answer": a}, port=port)
for d, a in add:
api(host, "rewrite/add", pw, {"domain": d, "answer": a}, port=port)
print(f"{site}: -{len(remove)} +{len(add)}")
print("done.")
if __name__ == "__main__":
main()
+56
View File
@@ -0,0 +1,56 @@
# adguard-ana — the Anaheim colo's resolver.
#
# Stood up 2026-08-19 to close the gap found while designing the .internal
# naming scheme: ESH and NH3 each had an AdGuard, but colo hosts were
# resolving straight against 1.1.1.1, so the colo had no way to answer for
# internal names at all.
#
# ⚠️ PORTS DIFFER FROM THE OTHER TWO SITES. ana-docker is a busy host: :8080
# and :3000 are already taken (langfuse and friends), so AdGuard's web UI and
# API live on :8053 here, not :8080. Anything that talks to this API — notably
# scripts/dns-sync.py — reads the port from dns/internal.yaml rather than
# assuming the ESH/NH3 value.
#
# ⚠️ THIS IS NOT YET THE COLO'S RESOLVER-OF-RECORD. Standing the service up and
# repointing a whole site's DNS are two different changes with two different
# blast radii. Colo hosts still use 1.1.1.1; the cutover is a separate,
# operator-approved step. Until then this answers only what asks it directly.
#
# ESH and NH3 run their own, older, unmanaged compose files. They were left
# alone deliberately — adopting three live resolvers into this repo while also
# introducing a new naming system is two risky changes at once. Worth doing
# later, as its own piece of work.
name: adguard-ana
services:
adguardhome:
image: adguard/adguardhome:latest
container_name: ${AG_CONTAINER:-adguardhome}
restart: unless-stopped
ports:
- "${AG_DNS_PORT:-53}:53/tcp"
- "${AG_DNS_PORT:-53}:53/udp"
# Web UI + REST API. 8053, not 8080 — see the note above.
- "${AG_WEB_PORT:-8053}:80/tcp"
volumes:
- adguard_work:/opt/adguardhome/work
- adguard_conf:/opt/adguardhome/conf
networks:
- tnet
labels:
- homepage.group=Service Networking
- homepage.name=AdGuard (ANA)
- homepage.icon=mdi-dns
- homepage.description=DNS resolver + .internal zone (colo)
- homepage.href=http://10.250.50.70:${AG_WEB_PORT:-8053}
- homepage.siteMonitor=http://10.250.50.70:${AG_WEB_PORT:-8053}
volumes:
adguard_work: {}
adguard_conf: {}
networks:
tnet:
name: traefik-net
external: true
@@ -0,0 +1,42 @@
# FIRST-BOOT SEED ONLY — AdGuard rewrites this file at runtime.
#
# It exists so the container comes up already configured instead of sitting in
# the setup wizard waiting for a human. After first boot the live copy is in
# the adguard-ana_adguard_conf volume and diverges from this file; treat this
# as the bootstrap, not as ongoing config. Notably the `rewrites:` list stays
# EMPTY here — scripts/dns-sync.py owns it from dns/internal.yaml.
#
# ⚠️ NO BLOCKLISTS, DELIBERATELY. The other two AdGuards filter ads for human
# browsing; this one resolves for a rack of servers. A blocklist false-positive
# here breaks service-to-service calls at 3am for no upside, so filtering is
# off and this instance is a plain recursive resolver plus the .internal zone.
http:
address: 0.0.0.0:80
users:
- name: infra-ops
password: $2a$05$v7d1ASBg9qprZNx3Y50YqempdiL.Lo8.jMYxyVr6MroaGF0w5tQje
auth_attempts: 5
block_auth_min: 15
language: en
theme: auto
dns:
bind_hosts:
- 0.0.0.0
port: 53
upstream_dns:
- 1.1.1.1
- 1.0.0.1
bootstrap_dns:
- 1.1.1.1
- 8.8.8.8
protection_enabled: true
filtering_enabled: false
safebrowsing_enabled: false
parental_enabled: false
rewrites: []
filters: []
whitelist_filters: []
user_rules: []
log:
verbose: false
schema_version: 29
+12 -2
View File
@@ -23,7 +23,12 @@ services:
# ------------------------------------------------------------------
environment:
- SEARXNG_SECRET=${SEARXNG_SECRET}
- BASE_URL=https://searxng.pfi.local/
# searxng.ana.internal, not the old searxng.pfi.local (migrated
# 2026-08-19). `.local` is reserved for mDNS, so the old name was a
# standards collision that happened to work; `.internal` is ICANN-
# reserved for exactly this. The name is served by the fleet's AdGuard
# resolvers from dns/internal.yaml — see scripts/dns-sync.py.
- BASE_URL=https://searxng.ana.internal/
- INSTANCE_NAME=SearXNG
# ------------------------------------------------------------------
# Resource limits — tune for VM 102's available RAM/CPU
@@ -72,7 +77,12 @@ services:
labels:
# Traefik configuration — auto-discovery via Docker provider
- traefik.enable=true
- traefik.http.routers.searxng.rule=Host(`searxng.pfi.local`)
# Both names during the migration: `.internal` is the real one now, and
# the old `.pfi.local` is kept as a fallback so anything still pointing
# at it (a bookmark, a hardcoded config elsewhere) does not break the
# day the name changes. Drop the second Host() once nothing uses it —
# the Traefik access log will tell you when that is.
- traefik.http.routers.searxng.rule=Host(`searxng.ana.internal`) || Host(`searxng.pfi.local`)
- traefik.http.routers.searxng.entrypoints=websecure
- traefik.http.routers.searxng.tls=true
- traefik.http.routers.searxng.service=searxng