thermograph/infra/deploy/forgejo/docker-stack.yml
emi dcf15ea572
Some checks failed
Sync infra to hosts / sync-beta (push) Successful in 7s
Sync infra to hosts / sync-prod (push) Failing after 8s
secrets-guard / encrypted (push) Successful in 7s
shell-lint / shellcheck (push) Successful in 8s
infra/forgejo: add resource limits and a leaner CI job image (#38)
2026-07-24 18:56:46 +00:00

156 lines
7.2 KiB
YAML

# Forgejo (self-hosted Git + CI/CD) as a Docker Swarm stack — the only workload
# this Swarm cluster runs (see deploy/swarm/README.md). Deliberately separate
# from the Terraform-managed docker-compose.yml that runs the Thermograph app
# itself: this stack's only job is Forgejo and its container registry.
#
# The Actions RUNNER is deliberately NOT a service in this stack. Per
# thermograph-docs/runbooks/implementation-handoff.md (Track B step 5), the canonical
# design registers the runner on the desktop node as a plain systemd service
# (deploy/forgejo/register-lan-runner.sh) — the same place the pre-Forgejo
# GitHub self-hosted runner already lived, not a Swarm-scheduled container.
#
# No Traefik here. Forgejo is pinned to beta (node.labels.role == forge)
# because that's what was chosen, but beta is ALSO today's live thermograph.org
# host — Caddy already owns its ports 80/443 (see /etc/caddy/Caddyfile on that
# box). A second reverse proxy binding those same ports would either fail to
# start or fight Caddy. Instead: forgejo's web port publishes to
# 127.0.0.1:3080 only (host-local, mode: host), and beta's existing Caddy gets
# a new site block reverse-proxying git.thermograph.org -> 127.0.0.1:3080,
# same pattern as its thermograph.org block. TLS is Caddy's existing
# automatic-HTTPS (HTTP-01), not a second ACME flow.
#
# Deploy from the manager node (prod), after all three nodes (prod, beta,
# desktop) have joined the swarm and beta is labeled role=forge:
#
# docker stack deploy -c deploy/forgejo/docker-stack.yml forgejo
#
# Requires this Swarm secret to exist first (see deploy/forgejo/README.md):
# forgejo_db_password
#
# Registry exposure (hazard #15 in thermograph-docs/runbooks/hop1-forgejo-registry-cutover.md):
# resolved as the runbook's first listed option — serve Git/UI publicly but
# firewall the /v2/ registry API paths so only WireGuard-mesh clients can
# reach them. That's implemented in the Caddy site block (see
# deploy/forgejo/README.md), not here — nothing in this stack file is
# registry-specific, the restriction lives entirely in Caddy's config on beta.
services:
db:
image: postgres:16-alpine
environment:
POSTGRES_USER: forgejo
POSTGRES_DB: forgejo
POSTGRES_PASSWORD_FILE: /run/secrets/forgejo_db_password
secrets: [forgejo_db_password]
volumes:
- forgejo_db:/var/lib/postgresql/data
networks: [forgejo_net]
deploy:
placement:
constraints: [node.labels.role == forge]
resources:
limits:
cpus: "${FORGEJO_DB_CPUS:-1}"
memory: ${FORGEJO_DB_MEMORY:-1g}
restart_policy:
condition: on-failure
forgejo:
image: codeberg.org/forgejo/forgejo:9-rootless
depends_on: [db]
environment:
FORGEJO__database__DB_TYPE: postgres
FORGEJO__database__HOST: db:5432
FORGEJO__database__NAME: forgejo
FORGEJO__database__USER: forgejo
FORGEJO__server__DOMAIN: "${FORGEJO_DOMAIN:-git.thermograph.org}"
FORGEJO__server__ROOT_URL: "https://${FORGEJO_DOMAIN:-git.thermograph.org}/"
FORGEJO__server__SSH_PORT: "2222"
# Without this, Forgejo starts no SSH server at all despite SSH_PORT
# being set — git@ clones get "connection refused", not a slow failure.
FORGEJO__server__START_SSH_SERVER: "true"
# Config is fully supplied via env, so lock the install wizard rather
# than leave it open on the public internet waiting for someone to
# complete it first (DB config alone does NOT imply this).
FORGEJO__security__INSTALL_LOCK: "true"
# Actions on: repo/org/user-level runners register against this instance.
FORGEJO__actions__ENABLED: "true"
# --- Access model: OAuth-only login, multi-user via an approval gate ---
# Login is Google SSO only. Forgejo 9.0.3 has no setting to hide the
# password sign-in form, so "OAuth-only" is enforced operationally: every
# account is given an unusable (random) password and no NEW local account
# can be created (ALLOW_ONLY_EXTERNAL_REGISTRATION). ENABLE_PASSWORD_SIGNIN_FORM
# is set anyway — ignored on 9.0.3, effective if the instance is upgraded.
# Auto-registration stays ON so a Google login auto-links (by verified email)
# to a PRE-CREATED account (`forgejo admin user create --username X --email
# X@gmail.com --random-password`). A single required-claim-value can't
# allowlist more than one email, so instead of pinning one address the
# required-claim-value is CLEARED (a DB change on the auth source, persisted
# in the forgejo_data volume — not re-applied from here) and every NEW signup
# is gated: a stranger who signs in with Google lands INACTIVE
# (REGISTER_MANUAL_CONFIRM) and RESTRICTED (DEFAULT_USER_IS_RESTRICTED)
# pending admin approval, so an un-provisioned Google user gets zero access.
FORGEJO__oauth2_client__ACCOUNT_LINKING: "auto"
FORGEJO__oauth2_client__ENABLE_AUTO_REGISTRATION: "true"
FORGEJO__service__ALLOW_ONLY_EXTERNAL_REGISTRATION: "true"
FORGEJO__service__ENABLE_PASSWORD_SIGNIN_FORM: "false"
FORGEJO__service__REGISTER_MANUAL_CONFIRM: "true"
FORGEJO__service__DEFAULT_USER_IS_RESTRICTED: "true"
# Outbound mail via prod's Postfix null client over the WireGuard mesh
# (10.10.0.1:25 — mynetworks permits beta); self-signed cert on :25, so
# trust it. Send-only; used for admin/approval and notification mail.
FORGEJO__mailer__ENABLED: "true"
FORGEJO__mailer__PROTOCOL: "smtp"
FORGEJO__mailer__SMTP_ADDR: "10.10.0.1"
FORGEJO__mailer__SMTP_PORT: "25"
FORGEJO__mailer__FORCE_TRUST_SERVER_CERT: "true"
FORGEJO__mailer__FROM: "Thermograph Git <no-reply@thermograph.org>"
# Gitea/Forgejo's app.ini env-mapping honors a __FILE suffix to read a
# value from a file instead of the literal env var — same convention as
# the official Postgres image's POSTGRES_PASSWORD_FILE above.
FORGEJO__database__PASSWD__FILE: /run/secrets/forgejo_db_password
secrets:
- source: forgejo_db_password
target: forgejo_db_password
volumes:
- forgejo_data:/var/lib/gitea
networks: [forgejo_net]
ports:
# SSH for git@ clones — published on whichever node the task lands on
# (pinned to beta by the placement constraint below, so effectively
# always beta's public IP, port 2222).
- target: 2222
published: 2222
protocol: tcp
mode: host
# Web UI/API. Swarm's port schema has no host_ip scoping, so this binds
# 0.0.0.0:3080 on beta — NOT actually localhost-only by itself. A
# DOCKER-USER iptables rule (see deploy/forgejo/README.md) is what
# actually restricts it, since Docker's own iptables rules bypass ufw
# for published ports. beta's Caddy reverse-proxies to 127.0.0.1:3080.
- target: 3000
published: 3080
protocol: tcp
mode: host
deploy:
placement:
constraints: [node.labels.role == forge]
resources:
limits:
cpus: "${FORGEJO_CPUS:-2}"
memory: ${FORGEJO_MEMORY:-2g}
restart_policy:
condition: on-failure
networks:
forgejo_net:
driver: overlay
attachable: false
volumes:
forgejo_db:
forgejo_data:
secrets:
forgejo_db_password:
external: true