A full audit of the installer and first-run experience found the mandatory
first-run wizard (is_initial_setup gate + InitialSetup.tsx) already works
correctly end-to-end — the real gap was discoverability and drift between
the installer and current app, not the wizard itself:
- nginx's static welcome page (served on the default HTTP/HTTPS ports, the
first place any new admin looks) never mentioned the admin panel lives on
a separate port, still shipped a Korean-language switcher despite Korean
being fully removed from the product, and linked to the retired
"Argus-appliance" identity. Now surfaces a live, dynamically-derived
admin panel link and drops the dead i18n/branding.
- users.language defaulted to 'ko' at the schema level (both the column
DEFAULT and the seed admin row) — a leftover from before Korean removal,
silently affecting every new user, not just the seed account.
- Three independently-drifting install paths existed (public distribution
installer, private-repo SSH-ship installer, and a fully manual README/docs
flow). README/docs now lead with the public alleyviper/argus installer
(verified to actually exist and mirror distribution/); the manual path is
kept only as an explicit private/pre-release fallback.
- Both scripted installers auto-rotated admin/admin via the API as their
last step, silently warning (not failing) if it didn't work — inconsistent
with the manual path and capable of leaving defaults active undetected.
Removed; every install path now consistently lands on admin/admin + the
in-app wizard.
- ANIS_ADMIN_KEY was documented as required ("ARGUS fails closed without
it") but is never read anywhere in src/api — confirmed dead, not just
vestigial. Retired from env templates, compose files, and docs; ROADMAP's
existing "wire it up or retire it" item resolved for this variable.
- Proxy host creation returned an opaque 500 when given an unresolvable
forward_host (e.g. a Docker container name typed into the free-text
field — ARGUS's nginx runs in host-network mode with no embedded DNS).
nginx -t's real "host not found in upstream" failure now surfaces as an
actionable 400 instead of a generic internal error; placeholder text
fixed to stop inviting the failure. Live-verified both the failure path
(with NGINX_SKIP_TEST temporarily disabled in the sandbox to exercise the
real validation) and the no-regression path (valid IP still succeeds).
- LOG_COLLECTION silently disables the entire access-log/analytics/live-event
pipeline when set to anything but the exact string "true", with zero log
output anywhere. Added a boot-time WARN matching the existing
IsInitialSetupRequired nudge pattern.
Every fix live-verified against a genuinely fresh sandbox install
(docker/docker-compose.local-sandbox.yml, zero pre-existing volumes),
not just read from source.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
230 lines
6.8 KiB
YAML
230 lines
6.8 KiB
YAML
services:
|
|
# TimescaleDB (PostgreSQL with time-series optimization)
|
|
db:
|
|
image: timescale/timescaledb:latest-pg17
|
|
container_name: argus-db
|
|
restart: unless-stopped
|
|
logging:
|
|
driver: "json-file"
|
|
options:
|
|
max-size: "50m"
|
|
max-file: "3"
|
|
environment:
|
|
TZ: ${TZ:-UTC}
|
|
POSTGRES_USER: ${DB_USER:-postgres}
|
|
POSTGRES_PASSWORD: ${DB_PASSWORD:-postgres}
|
|
POSTGRES_DB: ${DB_NAME:-argus}
|
|
command: postgres -c timezone=${TZ:-UTC} -c log_timezone=${TZ:-UTC} -c shared_preload_libraries=timescaledb -c timescaledb.telemetry_level=off -c max_locks_per_transaction=512
|
|
volumes:
|
|
- postgres_data:/var/lib/postgresql/data
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U ${DB_USER:-postgres}"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 10
|
|
start_period: 30s
|
|
|
|
# Valkey (Redis-compatible) for caching
|
|
valkey:
|
|
image: valkey/valkey:9-alpine
|
|
container_name: argus-valkey
|
|
restart: unless-stopped
|
|
logging:
|
|
driver: "json-file"
|
|
options:
|
|
max-size: "10m"
|
|
max-file: "3"
|
|
environment:
|
|
TZ: ${TZ:-UTC}
|
|
command: >
|
|
valkey-server
|
|
--maxmemory 256mb
|
|
--maxmemory-policy allkeys-lru
|
|
--appendonly yes
|
|
--appendfsync everysec
|
|
volumes:
|
|
- valkey_data:/data
|
|
healthcheck:
|
|
test: ["CMD", "valkey-cli", "ping"]
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 5
|
|
start_period: 10s
|
|
|
|
# Restricts the api service's Docker Engine API access to exactly what it
|
|
# needs (list/inspect/exec/restart existing containers for log collection
|
|
# and nginx reload) — it cannot create new containers or touch the host
|
|
# beyond that. See docker-socket-proxy/README.md for the exact allowed set.
|
|
docker-socket-proxy:
|
|
image: tecnativa/docker-socket-proxy:latest
|
|
container_name: argus-docker-socket-proxy
|
|
restart: unless-stopped
|
|
security_opt:
|
|
- "no-new-privileges:true"
|
|
environment:
|
|
CONTAINERS: 1
|
|
IMAGES: 1
|
|
VOLUMES: 1
|
|
SYSTEM: 1
|
|
EXEC: 1
|
|
VERSION: 1
|
|
POST: 1
|
|
volumes:
|
|
- /var/run/docker.sock:/var/run/docker.sock:ro
|
|
- ./docker-socket-proxy/haproxy.cfg.template:/usr/local/etc/haproxy/haproxy.cfg.template:ro
|
|
logging:
|
|
driver: "json-file"
|
|
options:
|
|
max-size: "10m"
|
|
max-file: "3"
|
|
|
|
# Go API Server
|
|
api:
|
|
image: ghcr.io/alleyviper/argus-secure-api:latest
|
|
container_name: argus-api
|
|
restart: unless-stopped
|
|
# Container hardening: no-new-privileges blocks setuid privilege
|
|
# escalation; cap_drop ALL removes every Linux capability, re-adding only
|
|
# what's needed (DAC_OVERRIDE for the shared /etc/nginx volume owned by
|
|
# the nginx user, NET_BIND_SERVICE for the DNS Security Engine's :53).
|
|
security_opt:
|
|
- "no-new-privileges:true"
|
|
cap_drop:
|
|
- ALL
|
|
cap_add:
|
|
- DAC_OVERRIDE
|
|
- NET_BIND_SERVICE
|
|
logging:
|
|
driver: "json-file"
|
|
options:
|
|
max-size: "100m"
|
|
max-file: "5"
|
|
extra_hosts:
|
|
- "host.docker.internal:host-gateway"
|
|
environment:
|
|
TZ: ${TZ:-UTC}
|
|
PORT: "8080"
|
|
DATABASE_URL: postgres://${DB_USER:-postgres}:${DB_PASSWORD:-postgres}@db:5432/${DB_NAME:-argus}?sslmode=disable
|
|
REDIS_URL: redis://valkey:6379/0
|
|
ENVIRONMENT: ${ENVIRONMENT:-production}
|
|
NGINX_CONTAINER: argus-proxy
|
|
NGINX_SKIP_TEST: "false"
|
|
NGINX_STATUS_URL: "http://host.docker.internal:${NGINX_HTTP_PORT:-80}/nginx_status"
|
|
NGINX_ACCESS_LOG: "/etc/nginx/logs/access_raw.log"
|
|
BACKUP_PATH: ${BACKUP_PATH:-/app/data/backups}
|
|
DOCKER_API_VERSION: ${DOCKER_API_VERSION:-}
|
|
DOCKER_HOST: tcp://docker-socket-proxy:2375
|
|
NGINX_HTTP_PORT: ${NGINX_HTTP_PORT:-}
|
|
NGINX_HTTPS_PORT: ${NGINX_HTTPS_PORT:-}
|
|
API_HOST_PORT: ${API_HOST_PORT:-9080}
|
|
API_HOST: ${API_HOST:-}
|
|
# ANIS community intelligence — optional, off by default. Set these to
|
|
# connect this instance to an already-running ANIS hub.
|
|
ANIS_ENABLED: ${ANIS_ENABLED:-false}
|
|
ANIS_URL: ${ANIS_URL:-}
|
|
ANIS_LICENSE_KEY: ${ANIS_LICENSE_KEY:-}
|
|
ANIS_SHARE_ATTACKERS: ${ANIS_SHARE_ATTACKERS:-false}
|
|
DNS_SECURITY_LISTEN_ADDR: ":53"
|
|
ports:
|
|
- "127.0.0.1:${API_HOST_PORT:-9080}:8080"
|
|
# DNS Security Engine. Host-only by default — a bare forwarding
|
|
# resolver reachable from the network is exactly the profile abused
|
|
# for DNS amplification attacks against third parties. Set
|
|
# DNS_LISTEN_HOST to an internal interface IP to route real client
|
|
# DNS traffic through it (never 0.0.0.0 on an untrusted network).
|
|
- "${DNS_LISTEN_HOST:-127.0.0.1}:53:53/udp"
|
|
- "${DNS_LISTEN_HOST:-127.0.0.1}:53:53/tcp"
|
|
volumes:
|
|
- nginx_data:/etc/nginx:rw
|
|
- api_data:/app/data:rw
|
|
depends_on:
|
|
db:
|
|
condition: service_healthy
|
|
valkey:
|
|
condition: service_started
|
|
docker-socket-proxy:
|
|
condition: service_started
|
|
healthcheck:
|
|
test: ["CMD", "wget", "-q", "--spider", "http://localhost:8080/health"]
|
|
interval: 30s
|
|
timeout: 5s
|
|
retries: 3
|
|
start_period: 360s
|
|
|
|
# React UI (Admin Panel), served over HTTPS
|
|
ui:
|
|
image: ghcr.io/alleyviper/argus-secure-ui:latest
|
|
container_name: argus-ui
|
|
restart: unless-stopped
|
|
security_opt:
|
|
- "no-new-privileges:true"
|
|
cap_drop:
|
|
- ALL
|
|
cap_add:
|
|
- NET_BIND_SERVICE
|
|
logging:
|
|
driver: "json-file"
|
|
options:
|
|
max-size: "10m"
|
|
max-file: "3"
|
|
environment:
|
|
TZ: ${TZ:-UTC}
|
|
ports:
|
|
- "${UI_PORT:-81}:443"
|
|
volumes:
|
|
- ui_data:/app/ssl:rw
|
|
depends_on:
|
|
- api
|
|
|
|
# Nginx reverse proxy — host network mode, so real client IPs are visible
|
|
# directly without needing PROXY protocol.
|
|
nginx:
|
|
image: ghcr.io/alleyviper/argus-secure-nginx:latest
|
|
container_name: argus-proxy
|
|
restart: always
|
|
network_mode: host
|
|
# Not cap_drop'd: runs nginx in host-network mode with a root master that
|
|
# drops workers to the nginx user, needing CHOWN/SETUID/SETGID plus binds
|
|
# on privileged 80/443.
|
|
security_opt:
|
|
- "no-new-privileges:true"
|
|
logging:
|
|
driver: "json-file"
|
|
options:
|
|
max-size: "100m"
|
|
max-file: "5"
|
|
environment:
|
|
TZ: ${TZ:-UTC}
|
|
UI_PORT: ${UI_PORT:-81}
|
|
ulimits:
|
|
nofile:
|
|
soft: 65535
|
|
hard: 65535
|
|
volumes:
|
|
- nginx_data:/etc/nginx:rw
|
|
depends_on:
|
|
- api
|
|
healthcheck:
|
|
test: ["CMD", "curl", "-f", "http://127.0.0.1:${NGINX_HTTP_PORT:-80}/health"]
|
|
interval: 15s
|
|
timeout: 5s
|
|
retries: 3
|
|
start_period: 10s
|
|
|
|
volumes:
|
|
postgres_data:
|
|
name: argus_postgres_data
|
|
valkey_data:
|
|
name: argus_valkey_data
|
|
nginx_data:
|
|
name: argus_nginx_data
|
|
api_data:
|
|
name: argus_api_data
|
|
ui_data:
|
|
name: argus_ui_data
|
|
|
|
networks:
|
|
default:
|
|
name: argus-network
|
|
external: true
|