LibrePortal/containers/stalwart/scripts/stalwart_install_hooks.sh
librelad 65167463f9 fix(chat apps): tag every service so its IP actually substitutes
Installing rocketchat failed with

    invalid IPv4 address: ParseAddr("IP_DATA_2"): unable to parse IP

ipUpdateComposeTags allocates one IP per SERVICE_TAG_N annotation and fills
IP_TAG_i only where SERVICE_TAG_i exists. The four new apps tagged only their
primary service, so every sidecar — matrix's postgres, mattermost's postgres,
rocketchat's mongo, and fifteen of stoat's sixteen — kept a literal IP_DATA_n
in the deployed compose and docker refused to create the container.

Tag every service that carries an ipv4_address, index-aligned with its IP_TAG.
For stoat that also meant moving caddy from SERVICE_TAG_1 to _6 so the indices
line up with the IPs rather than the reading order.

mastodon had the same latent break (IP_TAG_2 and _3 untagged) and is fixed the
same way — it would have failed on first install for the same reason.

SERVICE_TAG carries the compose *key*, not container_name: 'libreportal app
restart <app> <service>' passes it to 'docker compose restart', which only
understands keys.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-18 19:48:09 +01:00

325 lines
17 KiB
Bash

#!/bin/bash
# Stalwart install hooks.
#
# Installing a mail server is not like installing any other app: the container
# starting successfully means almost nothing. Mail only works once DNS, reverse
# DNS and outbound port 25 are right, and every one of those lives OUTSIDE the
# box — at the registrar and the VPS provider. So the job of these hooks is to
# say plainly what still has to be done, with the actual values to enter, rather
# than reporting "installed" and leaving the admin to discover weeks later that
# their mail is landing in spam.
# Echo the admin credentials for the standard final-message block (word-split
# by the caller into positional args: user pass).
stalwart_install_message_data()
{
printf '%s %s' "${CFG_STALWART_ADMIN_USER:-admin}" "${CFG_STALWART_ADMIN_PASSWORD_1:-}"
}
# Run the Stalwart CLI against our own container.
#
# The CLI is deliberately NOT in the server image — upstream split it into its
# own repository so it ships and versions separately. It does publish a
# multi-arch container, which suits us better than a host binary: nothing to
# install, nothing to clean up on uninstall, and arm64 works for Pi installs.
#
# `--network container:stalwart-service` borrows the server's network namespace,
# so the CLI reaches it on localhost:8080 without us having to resolve the
# LibrePortal network name or expose the admin port to get at it.
stalwart_cli()
{
runFileOp docker run --rm -i --network "container:stalwart-service" \
-e STALWART_URL="http://localhost:8080" \
-e STALWART_USER="${CFG_STALWART_ADMIN_USER:-admin}" \
-e STALWART_PASSWORD="${CFG_STALWART_ADMIN_PASSWORD_1:-}" \
"ghcr.io/stalwartlabs/cli:${CFG_STALWART_CLI_VERSION:-1.0.12}" --no-color "$@"
}
# Wait for the admin HTTP listener. Used twice: once for the bootstrap listener
# before we configure anything, once for the real one after the restart.
stalwart_wait_http()
{
local probe="$1" tries="${2:-40}" i code
for ((i = 0; i < tries; i++)); do
code=$(runFileOp docker exec stalwart-service curl -fsS -o /dev/null -w '%{http_code}' \
--max-time 3 "http://localhost:8080/healthz/$probe" 2>/dev/null | tr -d '\r')
[[ "$code" == "200" ]] && return 0
sleep 2
done
return 1
}
# Fill in the first-run setup wizard instead of making the user do it.
#
# Out of the box Stalwart boots into "bootstrap mode" and waits for a human to
# answer five screens of questions in the WebUI: hostname, domain, which storage
# backend, which directory, where to log, how to handle DNS. LibrePortal already
# knows the answers to the ones that matter and the rest have sane defaults, so
# making the user answer them is asking a question we can answer ourselves.
#
# `Bootstrap` is a singleton object holding exactly those wizard fields, so the
# whole wizard is one `update`. Once it is set the server writes its config.json,
# provisions the domain, generates DKIM keys and leaves bootstrap mode — and the
# user's first sight of Stalwart is a configured mail server, not a form.
stalwart_install_provision()
{
# config.json only exists once setup has completed, which makes it the
# honest "is this already configured?" test. Re-running the installer over a
# working server must not re-answer its setup questions.
if runFileOp docker exec stalwart-service test -f /etc/stalwart/config.json 2>/dev/null; then
isNotice "Stalwart is already configured — leaving its existing settings alone."
return 0
fi
local mail_host="${host_setup:-}"
local mail_domain="${mail_host#*.}"
if [[ -z "$mail_host" || "$mail_host" != *.* ]]; then
isError "No mail hostname is configured, so Stalwart cannot be set up automatically."
isNotice " Set a domain in the general config, then open the admin console to"
isNotice " complete setup by hand."
return 1
fi
isNotice "Waiting for Stalwart's setup listener…"
if ! stalwart_wait_http live; then
isError "Stalwart did not open its setup listener — skipping automatic setup."
return 1
fi
# requestTlsCertificate matters more than it looks. Traefik only fronts the
# admin port; SMTP and IMAP (25/465/587/993) bypass it entirely, so Traefik's
# certificate never reaches a mail client. Without this Stalwart serves a
# self-signed cert on 993 and every mail client throws a warning.
#
# generateDkimKeys makes the server own DKIM: it creates an Ed25519 and an
# RSA key, publishes both, and rotates them on a schedule. Hand-managed DKIM
# keys are, in practice, keys that never get rotated.
isNotice "Configuring Stalwart for ${mail_domain}"
local plan
plan=$(printf '{"@type":"update","object":"Bootstrap","value":{"serverHostname":"%s","defaultDomain":"%s","generateDkimKeys":true,"requestTlsCertificate":true}}' \
"$mail_host" "$mail_domain")
# Keep the server's own error rather than swallowing it. The two that
# actually happen say exactly what is wrong — a hostname under a TLD that
# does not exist, or a data directory the server cannot write — and both are
# unfixable guesswork without the message.
local apply_out
if ! apply_out=$(printf '%s\n' "$plan" | stalwart_cli apply --stdin 2>&1); then
isError "Automatic setup failed — open the admin console to finish it by hand."
local reason
reason=$(printf '%s\n' "$apply_out" | grep -oE '(Invalid|Failed|Permission)[^|]*' | head -1)
[[ -n "$reason" ]] && isNotice " Stalwart said: ${reason% }"
return 1
fi
# Leaving bootstrap mode needs a restart: the server swaps its temporary
# setup listener for the real ones (SMTP, IMAP, submission) on the way back up.
isNotice "Restarting Stalwart to bring up the mail services…"
runFileOp docker restart stalwart-service >/dev/null 2>&1
if ! stalwart_wait_http ready 60; then
isError "Stalwart did not come back up after setup — check: docker logs stalwart-service"
return 1
fi
isSuccessful "Stalwart configured: ${mail_domain} added, DKIM keys generated."
stalwart_install_dns_provider
stalwart_install_first_mailbox
return 0
}
# Optionally hand DNS to the provider's API.
#
# This is the part that turns a page of records-to-paste into nothing at all:
# Stalwart writes MX, SPF, DKIM, DMARC, MTA-STS, TLS-RPT, SRV and CAA into the
# zone itself and keeps them in sync — including republishing DKIM records when
# it rotates the keys, which is the whole reason rotation is safe to automate.
#
# Off by default. It needs an API token with write access to the zone, stored in
# the mail server's database, which widens what a compromise of this box costs.
# Scope the token to the single zone if your provider supports it.
stalwart_install_dns_provider()
{
local provider="${CFG_STALWART_DNS_PROVIDER:-manual}"
[[ "$provider" == "manual" || -z "$provider" ]] && return 0
if [[ -z "${CFG_STALWART_DNS_API_TOKEN:-}" ]]; then
isError "CFG_STALWART_DNS_PROVIDER is set to '$provider' but no API token was given."
isNotice " Falling back to manual DNS — the records are printed below."
return 0
fi
local mail_domain="${host_setup#*.}"
# Verified against Cloudflare; DigitalOcean and DeSEC take the same
# description+secret shape. Providers needing more than a token (Route 53,
# Google Cloud DNS) are not wired up here — add them in the admin console.
local plan
plan=$(printf '{"@type":"upsert","object":"DnsServer","matchOn":["description"],"value":{"dns":{"@type":"%s","description":"LibrePortal managed DNS","secret":{"@type":"Value","secret":"%s"}}}}\n{"@type":"upsert","object":"Domain","matchOn":["name"],"value":{"dom":{"name":"%s","dnsManagement":{"@type":"Automatic","dnsServerId":"#dns"}}}}' \
"$provider" "$CFG_STALWART_DNS_API_TOKEN" "$mail_domain")
if printf '%s\n' "$plan" | stalwart_cli apply --stdin >/dev/null 2>&1; then
isSuccessful "DNS records will be published and kept in sync via $provider."
else
isError "Could not enable automatic DNS via $provider — check the API token."
isNotice " Manual DNS is still in effect; the records are printed below."
fi
}
# Create one real mailbox.
#
# Setup leaves you with admin@<domain>, which is an administrator account — using
# it as a day-to-day mailbox is the wrong habit to start someone on. More
# concretely: the generated zone file points DMARC and TLS-RPT reports at
# postmaster@<domain>, and nothing creates that address, so those reports would
# bounce. Creating it fixes a real gap and gives the user a mailbox to log into.
stalwart_install_first_mailbox()
{
local mailbox="${CFG_STALWART_FIRST_MAILBOX:-postmaster}"
[[ -z "$mailbox" ]] && return 0
local mail_domain="${host_setup#*.}"
local plan
# The domain is upserted by name purely to get a reference to it — it already
# exists, so this matches rather than creates. Credentials are a map keyed by
# slot, not a list. Stalwart enforces password strength, so the password has
# to be a generated one, not a short hand-picked string.
plan=$(printf '{"@type":"upsert","object":"Domain","matchOn":["name"],"value":{"dom":{"name":"%s"}}}\n{"@type":"upsert","object":"Account","matchOn":["name"],"value":{"acc":{"@type":"User","name":"%s","domainId":"#dom","description":"First mailbox","credentials":{"0":{"@type":"Password","secret":"%s"}}}}}' \
"$mail_domain" "$mailbox" "${CFG_STALWART_FIRST_MAILBOX_PASSWORD_1:-}")
if printf '%s\n' "$plan" | stalwart_cli apply --stdin >/dev/null 2>&1; then
isSuccessful "Created the first mailbox: ${mailbox}@${mail_domain}"
else
isError "Could not create ${mailbox}@${mail_domain} — add it in the admin console."
fi
}
stalwart_install_post_start()
{
local app_name="$1"
((menu_number++))
echo ""
echo "---- $menu_number. Mail server checks + the DNS records you still need"
echo ""
# Resolved admin port comes from the compose tag (format `external:internal`),
# the same source adguard's hook reads — the legacy $usedport1 isn't populated
# by the current install pipeline.
local compose_file="$containers_dir$app_name/docker-compose.yml"
local admin_pair admin_port
admin_pair=$(tagsManagerGetTagContent "$compose_file" "PORTS_TAG_1" 2>/dev/null)
admin_port="${admin_pair%%:*}"
# ---- 1. Answer the setup wizard on the user's behalf ------------------
stalwart_install_provision
# ---- 2. Can this host even send mail? --------------------------------
# Most cheap VPS providers block outbound 25 by default (and several only
# unblock on request). A blocked port 25 means no mail EVER leaves the box,
# and nothing in the WebUI would otherwise reveal it.
isNotice "Checking outbound port 25 (required to deliver mail to other servers)…"
if command -v timeout >/dev/null 2>&1 \
&& timeout 8 bash -c 'exec 3<>/dev/tcp/gmail-smtp-in.l.google.com/25' 2>/dev/null; then
isSuccessful "Outbound port 25 is open."
else
isError "Outbound port 25 appears BLOCKED or filtered on this host."
isNotice " Most VPS providers block it by default. Ask your provider to unblock"
isNotice " outbound 25, or mail will queue and never deliver."
fi
# ---- 3. Reverse DNS --------------------------------------------------
# Receiving servers check that the sending IP resolves back to a name. A
# generic provider PTR (e.g. static.1.2.3.4.provider.net) is a common reason
# for mail being junked, and it can only be fixed in the provider's panel.
if [[ -n "$public_ip_v4" ]] && command -v dig >/dev/null 2>&1; then
local ptr; ptr=$(dig +short -x "$public_ip_v4" 2>/dev/null | head -1)
if [[ -n "$ptr" ]]; then
isNotice "Reverse DNS (PTR) for $public_ip_v4 is: ${ptr%.}"
isNotice " It should match your mail hostname. Set it in your VPS provider's panel."
else
isError "No reverse DNS (PTR) record for $public_ip_v4 — set one at your VPS provider."
fi
fi
# ---- 4. Is the admin console actually there? -------------------------
# Stalwart v0.16 does not ship the WebUI inside the Docker image: the admin
# console is a single-page app the server fetches from GitHub on first
# start. If this host had no outbound HTTPS at that moment the download
# silently fails, the server still comes up healthy, and /admin and
# /account answer 404 forever with nothing to explain why. Checking it here
# turns "the panel is broken" into a one-line, fixable cause.
isNotice "Checking the admin console (WebUI) responds…"
local admin_code
admin_code=$(runFileOp docker exec stalwart-service curl -fsS -o /dev/null -w '%{http_code}' \
--max-time 5 http://localhost:8080/admin 2>/dev/null | tr -d '\r')
if [[ "$admin_code" == "404" ]]; then
isError "The admin console is missing (/admin returns 404)."
isNotice " Stalwart does not bundle the WebUI — it downloads it from"
isNotice " https://github.com/stalwartlabs/webui/releases/latest on first start."
isNotice " That download failed, so /admin and /account will 404 until it succeeds."
isNotice " Allow outbound HTTPS to github.com from this host, then restart the"
isNotice " container: docker restart stalwart-service"
isNotice " The mail server itself is unaffected — only the web interface is."
elif [[ -z "$admin_code" ]]; then
isError "Could not probe the admin console (no response from the container)."
else
isSuccessful "Admin console is being served (HTTP $admin_code)."
fi
# ---- 5. The records that still have to be published -------------------
# Read back from the server rather than composed here. Stalwart keeps the
# domain's full record set in `dnsZoneFile`, so this prints what it actually
# expects — MX, SPF, DMARC, MTA-STS, TLS-RPT, the SRV records clients use to
# autoconfigure, and crucially the real DKIM public keys. The old version of
# this hook had to tell the user to go and fetch DKIM themselves; by this
# point the keys exist, so there is nothing left to look up.
local mail_host="${host_setup:-your-mail-hostname}"
local mail_domain="${mail_host#*.}"
if [[ "${CFG_STALWART_DNS_PROVIDER:-manual}" != "manual" && -n "${CFG_STALWART_DNS_API_TOKEN:-}" ]]; then
isNotice "DNS is managed automatically — no records to add by hand."
isNotice " Still set at your provider, because they are not in the zone:"
echo " A ${mail_host} ${public_ip_v4:-<the IP of this server>}"
echo " PTR ${public_ip_v4:-<the IP of this server>} ${mail_host}"
else
local domain_id zone
domain_id=$(stalwart_cli query Domain 2>/dev/null | awk 'NR==2{print $1}')
if [[ -n "$domain_id" ]]; then
zone=$(stalwart_cli get Domain "$domain_id" 2>/dev/null \
| sed -n '/DNS Zone File:/,$p' | sed 's/^ *DNS Zone File: *//')
fi
echo ""
if [[ -n "$zone" ]]; then
isNotice "DNS records to add at your domain registrar:"
echo " A ${mail_host} ${public_ip_v4:-<the IP of this server>}"
echo ""
printf '%s\n' "$zone" | sed 's/^/ /'
else
# Setup did not complete, so there is no zone to read. Say what is
# needed rather than printing nothing.
isNotice "DNS records to add at your domain registrar:"
echo " MX @ 10 ${mail_host}"
echo " A ${mail_host} ${public_ip_v4:-<the IP of this server>}"
echo " TXT @ \"v=spf1 mx -all\""
echo " TXT _dmarc \"v=DMARC1; p=quarantine; rua=mailto:postmaster@${mail_domain}\""
isNotice " DKIM records are shown in the admin console under your domain."
fi
echo ""
fi
# ---- 6. Where to go next ---------------------------------------------
if [[ -n "$admin_port" ]]; then
isNotice "Admin console (server settings, domains, queue, reports):"
[[ -n "$public_ip_v4" ]] && echo " http://$public_ip_v4:$admin_port/admin"
isNotice "Mailbox settings for everyday users (password, filters, autoresponder):"
[[ -n "$public_ip_v4" ]] && echo " http://$public_ip_v4:$admin_port/account"
echo ""
isNotice "Sign in as '${CFG_STALWART_ADMIN_USER:-admin}' with the password shown below."
fi
isNotice "Until MX, PTR, SPF, DKIM and DMARC are all in place, expect delivery"
isNotice "problems — that is normal for a new mail server, not a fault in the app."
}