cairnobs/docker-compose.yml

# Phase 0+1 stack: Redpanda -> ingest -> ClickHouse -> api -> web, plus
# search (Tantivy full-text indexing, reads the same Redpanda topic
# ingest's consumer does).
#
# Does NOT include the Rust agent — see /agent/README.md: journald
# sourcing needs the host's journal, which isn't something a container
# gets for free. Run the agent natively on the host per
# /docs/phase-0-runbook.md, pointed at ingest's mapped port (localhost:4317).
# Windows Event Log/ETW sourcing needs a real Windows host regardless —
# see /docs/phase-1-runbook.md.
#
# Before first run: generate dev mTLS certs (hack/dev-certs/generate.sh).
# See /docs/phase-0-runbook.md (Linux pipeline) and
# /docs/phase-1-runbook.md (Windows + full-text search) for the full
# sequences.
services:
  redpanda:
    image: docker.redpanda.com/redpandadata/redpanda:v24.2.7
    container_name: sentry-redpanda
    command:
      - redpanda
      - start
      - --smp=1
      - --memory=1G
      - --reserve-memory=0M
      - --overprovisioned
      - --node-id=0
      - --check=false
      - --kafka-addr=PLAINTEXT://0.0.0.0:9092
      - --advertise-kafka-addr=PLAINTEXT://redpanda:9092
    ports:
      - "9092:9092"
    volumes:
      - redpanda-data:/var/lib/redpanda/data
    healthcheck:
      test: ["CMD", "rpk", "cluster", "health", "--exit-when-healthy"]
      interval: 5s
      timeout: 5s
      retries: 30

  # One-shot: creates the sentry.logs.raw topic, then exits 0. ingest
  # waits on this completing successfully before it starts.
  redpanda-provision:
    build:
      context: ./transport
    container_name: sentry-redpanda-provision
    depends_on:
      redpanda:
        condition: service_healthy
    environment:
      REDPANDA_BROKERS: "redpanda:9092"
      REDPANDA_ADMIN_HOSTS: "redpanda:9644"
      # Explicit rather than relying on both this script's and /search's
      # defaults happening to agree — search consumes this same topic and
      # needs to know the partition count up front (see /search/README.md).
      REDPANDA_TOPIC_PARTITIONS: "6"

  clickhouse:
    image: clickhouse/clickhouse-server:24.8
    container_name: sentry-clickhouse
    ports:
      - "8123:8123" # HTTP interface, used by the migrate step
      - "9000:9000" # native protocol, used by ingest and api
    environment:
      # The official image disables *network* access entirely for the
      # default user (even from sibling containers) unless
      # CLICKHOUSE_USER or CLICKHOUSE_PASSWORD is set to a genuinely
      # non-empty value — confirmed by testing, not just reading docs: an
      # explicitly-empty CLICKHOUSE_PASSWORD="" still triggers the
      # lockdown, silently returning 403 to every other container. This
      # password isn't a real secret (mTLS between agent and ingest is
      # the actual security boundary here) — it exists purely to satisfy
      # this image's login gate for local/homelab use.
      CLICKHOUSE_PASSWORD: "sentry-dev-only"
    volumes:
      - clickhouse-data:/var/lib/clickhouse
    ulimits:
      nofile:
        soft: 262144
        hard: 262144
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8123/ping"]
      interval: 5s
      timeout: 5s
      retries: 30

  # One-shot: applies /storage/migrations/*.sql, then exits 0. ingest and
  # api both wait on this completing successfully.
  clickhouse-migrate:
    build:
      context: ./storage
    container_name: sentry-clickhouse-migrate
    depends_on:
      clickhouse:
        condition: service_healthy
    environment:
      CLICKHOUSE_HTTP: "http://clickhouse:8123"
      CLICKHOUSE_PASSWORD: "sentry-dev-only"

  # Control-plane metadata store (dashboards, alert rules -- see
  # /docs/phase-3-dashboard-design.md for why this is Postgres rather
  # than new ClickHouse tables). Log data stays on ClickHouse/Tantivy
  # only, unaffected.
  metadata-postgres:
    image: postgres:16-alpine
    container_name: sentry-metadata-postgres
    environment:
      POSTGRES_DB: sentry_metadata
      POSTGRES_USER: sentry
      POSTGRES_PASSWORD: "sentry-dev-only" # not a real secret, same framing as CLICKHOUSE_PASSWORD above
    volumes:
      - metadata-postgres-data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U sentry -d sentry_metadata"]
      interval: 5s
      timeout: 5s
      retries: 30

  # One-shot: applies /metadata/migrations/*.sql, then exits 0. api waits
  # on this completing successfully, same shape as clickhouse-migrate.
  metadata-migrate:
    build:
      context: ./metadata
    container_name: sentry-metadata-migrate
    depends_on:
      metadata-postgres:
        condition: service_healthy
    environment:
      POSTGRES_HOST: "metadata-postgres"
      POSTGRES_PORT: "5432"
      POSTGRES_USER: "sentry"
      POSTGRES_PASSWORD: "sentry-dev-only"
      POSTGRES_DATABASE: "sentry_metadata"
      # Password for the restricted audit_writer Postgres role (Phase 4
      # task 4) -- INSERT+SELECT only on audit_log, never UPDATE/DELETE,
      # via its own connection pool distinct from the shared "sentry"
      # role every other store uses. See /docs/phase-4-isolation-design.md.
      AUDIT_WRITER_PASSWORD: "audit-writer-dev-only"

  ingest:
    build:
      context: . # needs both ingest/ and proto/
      dockerfile: ingest/Dockerfile
    container_name: sentry-ingest
    depends_on:
      redpanda-provision:
        condition: service_completed_successfully
      clickhouse-migrate:
        condition: service_completed_successfully
    ports:
      - "4317:4317" # gRPC, mTLS — this is what the host-run agent connects to
    environment:
      REDPANDA_BROKERS: "redpanda:9092"
      CLICKHOUSE_ADDR: "clickhouse:9000"
      CLICKHOUSE_PASSWORD: "sentry-dev-only"
      # TLS_*_FILE env vars are left at their defaults
      # (/etc/sentry-ingest/{server,server-key,ca}.pem) — matches where
      # the volume below mounts the generated dev certs.
    volumes:
      - ./hack/dev-certs/out:/etc/sentry-ingest:ro

  # Reads the same sentry.logs.raw topic ingest's consumer does (own
  # offset tracking, own failure domain — see /search/README.md) and
  # builds a Tantivy full-text index over the message field.
  search:
    build:
      context: . # needs both search/ and proto/
      dockerfile: search/Dockerfile
    container_name: sentry-search
    depends_on:
      redpanda-provision:
        condition: service_completed_successfully
    environment:
      REDPANDA_BROKERS: "redpanda:9092"
      REDPANDA_TOPIC_PARTITIONS: "6" # must match redpanda-provision's above
      # tracing-subscriber's default filter suppresses INFO without this
      # -- found by actually checking `docker compose logs search` and
      # seeing nothing, same silent-logging gap the agent had in Phase 0.
      RUST_LOG: "info"
    volumes:
      - search-index-data:/var/lib/sentry-search

  api:
    build:
      context: . # needs both api/ and proto/ (gRPC client to search)
      dockerfile: api/Dockerfile
    container_name: sentry-api
    depends_on:
      clickhouse-migrate:
        condition: service_completed_successfully
      metadata-migrate:
        condition: service_completed_successfully
    ports:
      - "8080:8080"
    environment:
      CLICKHOUSE_ADDR: "clickhouse:9000"
      CLICKHOUSE_PASSWORD: "sentry-dev-only"
      SEARCH_GRPC_ADDR: "search:50052"
      POSTGRES_ADDR: "metadata-postgres:5432"
      POSTGRES_DATABASE: "sentry_metadata"
      POSTGRES_USERNAME: "sentry"
      POSTGRES_PASSWORD: "sentry-dev-only"
    healthcheck:
      # alerting (Phase 3 task 5) depends_on api -- without this, that
      # dependency can only mean "container started," not "actually
      # listening," and would hammer a not-yet-ready api with errors on
      # every evaluator tick during stack startup. api's image is
      # distroless (no shell, no wget) so this execs the api binary's own
      # -healthcheck self-check mode instead of an external tool.
      test: ["CMD", "/api", "-healthcheck"]
      interval: 5s
      timeout: 5s
      retries: 30

  alerting:
    build:
      context: alerting # self-contained, no /proto needed -- see alerting/Dockerfile
      dockerfile: Dockerfile
    container_name: sentry-alerting
    depends_on:
      metadata-migrate:
        condition: service_completed_successfully
      api:
        condition: service_healthy
    ports:
      - "8081:8081"
    environment:
      POSTGRES_ADDR: "metadata-postgres:5432"
      POSTGRES_DATABASE: "sentry_metadata"
      POSTGRES_USERNAME: "sentry"
      POSTGRES_PASSWORD: "sentry-dev-only"
      API_QUERY_URL: "http://api:8080"
    healthcheck:
      test: ["CMD", "/alerting", "-healthcheck"]
      interval: 5s
      timeout: 5s
      retries: 30

  # Commercial-license SSO/RBAC service (Phase 4) -- see
  # /docs/phase-4-isolation-design.md and enterprise/README.md. Included
  # here so it can be built/run/curled like every other service, but
  # deliberately NOT wired into api's ENTERPRISE_AUTH_URL or alerting's
  # API_SERVICE_TOKEN below: turning that on makes every /query and
  # /dashboards request require a valid session/service token, and there
  # is no OIDC/SAML login flow built yet to issue a human one (see
  # enterprise/cmd/enterprise-auth/main.go's doc comment) -- flipping it
  # on by default would break the web UI and sentryctl with no way to
  # log in. See enterprise/README.md for how to turn enforcement on for
  # manual testing (mint a service token, set the two env vars, restart).
  enterprise-auth:
    build:
      context: enterprise
      dockerfile: Dockerfile
    container_name: sentry-enterprise-auth
    ports:
      - "8082:8082"
    environment:
      # Dev-only, same framing as CLICKHOUSE_PASSWORD above -- not a real
      # secret. Must be at least 32 bytes (see internal/config.Load).
      ENTERPRISE_SESSION_SIGNING_KEY: "sentry-dev-only-session-signing-key-32bytes+"
    healthcheck:
      test: ["CMD", "/enterprise-auth", "-healthcheck"]
      interval: 5s
      timeout: 5s
      retries: 30

  # Multi-tenant-aware alternative to `api` (Phase 4) -- see
  # enterprise/cmd/enterprise-api/main.go's doc comment for why this is
  # a second binary rather than a flag on `api`. NOT part of the default
  # traffic path: `web`'s VITE_API_BASE_URL still points at `api`
  # (localhost:8080), and nothing here provisions any tenants (see that
  # binary's -provision-tenant flag) -- included so it can be
  # built/run/curled directly, same "available, not defaulted in" shape
  # as enterprise-auth above. CLICKHOUSE_ADMIN_USERNAME/PASSWORD reuse
  # the same admin credential `clickhouse-migrate` uses, since
  # tenantprovision needs access_management, not a tenant-scoped grant.
  enterprise-api:
    build:
      context: .
      dockerfile: enterprise/cmd/enterprise-api/Dockerfile
    container_name: sentry-enterprise-api
    depends_on:
      clickhouse-migrate:
        condition: service_completed_successfully
      metadata-migrate:
        condition: service_completed_successfully
    ports:
      - "8083:8083"
    environment:
      CLICKHOUSE_ADDR: "clickhouse:9000"
      CLICKHOUSE_ADMIN_USERNAME: "default"
      CLICKHOUSE_ADMIN_PASSWORD: "sentry-dev-only"
      SEARCH_GRPC_ADDR: "search:50052"
      POSTGRES_ADDR: "metadata-postgres:5432"
      POSTGRES_DATABASE: "sentry_metadata"
      POSTGRES_USERNAME: "sentry"
      POSTGRES_PASSWORD: "sentry-dev-only"
      AUDIT_WRITER_USERNAME: "audit_writer"
      AUDIT_WRITER_PASSWORD: "audit-writer-dev-only"
      ENTERPRISE_AUTH_URL: "http://enterprise-auth:8082"
    healthcheck:
      test: ["CMD", "/enterprise-api", "-healthcheck"]
      interval: 5s
      timeout: 5s
      retries: 30

  web:
    build:
      context: web
      args:
        # Baked in at build time (static site, not a server) as
        # localhost:8080/8081 -- fetched from the *browser*, which
        # resolves against the host's mapped ports, not the compose
        # network's service DNS names.
        VITE_API_BASE_URL: "http://localhost:8080"
        VITE_ALERTING_API_BASE_URL: "http://localhost:8081"
        VITE_ENTERPRISE_AUTH_BASE_URL: "http://localhost:8082"
    container_name: sentry-web
    depends_on:
      - api
      - alerting
      - enterprise-auth
    ports:
      - "3000:3000"

volumes:
  redpanda-data:
  clickhouse-data:
  search-index-data:
  metadata-postgres-data: