x-api: &api build: context: . environment: APP_HOST: 0.0.0.0 APP_PORT: 8080 APP_ENV: lab OTEL_ENABLED: "1" OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318 DATABASE_URL_FILE: /run/secrets/database_url SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS:-3600} IDEMPOTENCY_TTL_SECONDS: ${IDEMPOTENCY_TTL_SECONDS:-86400} CURSOR_SECRET_FILE: /run/secrets/cursor_secret S3_ENDPOINT: http://s3:8333 S3_BUCKET: messenger-attachments S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_access_key_id S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_secret_access_key BROKER_URL_FILE: /run/secrets/broker_url MAX_UPLOAD_BYTES: "10485760" MAX_IMAGE_PIXELS: "40000000" UPLOAD_CONCURRENCY: "1" UPLOAD_TIMEOUT_SECONDS: "30" UPLOAD_FAULT_AFTER_S3_PUT: ${UPLOAD_FAULT_AFTER_S3_PUT:-0} OUTBOX_FAULT_AFTER_COMMIT: ${OUTBOX_FAULT_AFTER_COMMIT:-0} MAX_PENDING_JOBS: ${MAX_PENDING_JOBS:-100} secrets: - database_url - cursor_secret - s3_access_key_id - s3_secret_access_key - broker_url depends_on: s3-init: condition: service_completed_successfully migrate: condition: service_completed_successfully broker: condition: service_healthy expose: - "8080" stop_grace_period: 10s healthcheck: test: ["CMD", "/app/.venv/bin/python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8080/health/ready', timeout=2).read()"] interval: 5s timeout: 3s retries: 12 start_period: 10s deploy: resources: limits: cpus: "0.50" memory: 512M services: broker: image: rabbitmq:4.1.2-alpine environment: RABBITMQ_DEFAULT_USER: messenger entrypoint: ["/bin/sh", "/usr/local/bin/rabbitmq-secret-entrypoint.sh"] command: ["rabbitmq-server"] secrets: - rabbitmq_password volumes: - rabbitmq_data:/var/lib/rabbitmq - ./infra/rabbitmq-secret-entrypoint.sh:/usr/local/bin/rabbitmq-secret-entrypoint.sh:ro healthcheck: test: ["CMD", "rabbitmq-diagnostics", "-q", "ping"] interval: 5s timeout: 3s retries: 20 start_period: 10s deploy: resources: limits: cpus: "0.50" memory: 256M s3: image: chrislusf/seaweedfs:4.17@sha256:186de7ef977a20343ee9a5544073f081976a29e2d29ecf8379891e7bf177fbe9 command: ["server", "-dir=/data", "-ip=s3", "-ip.bind=0.0.0.0", "-s3", "-s3.config=/run/secrets/s3_config", "-master.volumeSizeLimitMB=128", "-volume.max=64", "-s3.port.iceberg=0", "-filer.exposeDirectoryData=false"] secrets: - s3_config volumes: - s3_data:/data - ./infra/filer.toml:/etc/seaweedfs/filer.toml:ro healthcheck: test: ["CMD", "wget", "-q", "-O", "/dev/null", "http://localhost:9333/cluster/status"] interval: 5s timeout: 3s retries: 20 start_period: 15s deploy: resources: limits: cpus: "1.0" memory: 512M s3-init: build: context: . command: ["/app/.venv/bin/python", "-m", "src.bootstrap_s3"] environment: S3_ENDPOINT: http://s3:8333 S3_BUCKET: messenger-attachments S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_admin_key S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_admin_secret secrets: - s3_admin_key - s3_admin_secret depends_on: s3: condition: service_healthy restart: "no" postgres: image: postgres:17.6-alpine command: ["postgres", "-c", "track_commit_timestamp=on"] environment: POSTGRES_DB: messenger POSTGRES_USER: messenger POSTGRES_PASSWORD_FILE: /run/secrets/postgres_password secrets: - postgres_password volumes: - postgres_data:/var/lib/postgresql/data healthcheck: test: ["CMD-SHELL", "pg_isready -U messenger -d messenger"] interval: 5s timeout: 3s retries: 12 start_period: 5s deploy: resources: limits: cpus: "0.75" memory: 512M migrate: build: context: . command: ["/app/.venv/bin/python", "-m", "src.migrate"] environment: DATABASE_URL_FILE: /run/secrets/database_url CURSOR_SECRET_FILE: /run/secrets/cursor_secret secrets: - database_url - cursor_secret depends_on: postgres: condition: service_healthy restart: "no" deploy: resources: limits: cpus: "0.25" memory: 128M reconcile: healthcheck: disable: true build: context: . entrypoint: ["/app/.venv/bin/python", "-m", "src.reconcile"] command: ["--apply", "--loop"] restart: unless-stopped environment: DATABASE_URL_FILE: /run/secrets/database_url CURSOR_SECRET_FILE: /run/secrets/cursor_secret S3_ENDPOINT: http://s3:8333 S3_BUCKET: messenger-attachments S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_admin_key S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_admin_secret STAGING_RETENTION_SECONDS: ${STAGING_RETENTION_SECONDS:-86400} secrets: - database_url - cursor_secret - s3_admin_key - s3_admin_secret depends_on: postgres: condition: service_healthy s3: condition: service_healthy deploy: resources: limits: cpus: "0.25" memory: 128M api-a: <<: *api api-b: <<: *api worker: restart: unless-stopped healthcheck: test: ["CMD", "/app/.venv/bin/python", "-c", "import time,pathlib; assert time.time()-float(pathlib.Path('/tmp/worker-heartbeat').read_text()) < 15"] interval: 5s timeout: 3s retries: 3 deploy: resources: limits: cpus: "2.0" memory: 4G build: context: . command: ["/app/.venv/bin/python", "-m", "src.worker"] environment: APP_ENV: lab OTEL_ENABLED: "1" OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318 DATABASE_URL_FILE: /run/secrets/database_url CURSOR_SECRET_FILE: /run/secrets/cursor_secret S3_ENDPOINT: http://s3:8333 S3_BUCKET: messenger-attachments S3_ACCESS_KEY_ID_FILE: /run/secrets/s3_access_key_id S3_SECRET_ACCESS_KEY_FILE: /run/secrets/s3_secret_access_key BROKER_URL_FILE: /run/secrets/broker_url WORKER_CONCURRENCY: ${WORKER_CONCURRENCY:-2} WORKER_FAULT_AFTER_S3_PUT: ${WORKER_FAULT_AFTER_S3_PUT:-0} RENDER_MEMORY_MB: ${RENDER_MEMORY_MB:-768} WORKER_PREFETCH: ${WORKER_PREFETCH:-2} JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5} JOB_TIMEOUT_SECONDS: ${JOB_TIMEOUT_SECONDS:-60} STAGING_RETENTION_SECONDS: ${STAGING_RETENTION_SECONDS:-86400} secrets: - database_url - cursor_secret - s3_access_key_id - s3_secret_access_key - broker_url depends_on: s3-init: condition: service_completed_successfully migrate: condition: service_completed_successfully broker: condition: service_healthy stop_grace_period: 30s outbox: healthcheck: disable: true build: context: . command: ["/app/.venv/bin/python", "-m", "src.outbox"] environment: APP_ENV: lab OTEL_ENABLED: "1" OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318 DATABASE_URL_FILE: /run/secrets/database_url CURSOR_SECRET_FILE: /run/secrets/cursor_secret BROKER_URL_FILE: /run/secrets/broker_url OUTBOX_DISPATCH_INTERVAL_SECONDS: "1" JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5} secrets: - database_url - cursor_secret - broker_url depends_on: migrate: condition: service_completed_successfully broker: condition: service_healthy restart: unless-stopped load_balancer: image: haproxy:3.0.11-alpine ports: - "127.0.0.1:8080:8080" volumes: - ./infra/haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro depends_on: api-a: condition: service_healthy api-b: condition: service_healthy healthcheck: test: ["CMD-SHELL", "wget -q -O /dev/null http://127.0.0.1:8080/health/ready"] interval: 5s timeout: 3s retries: 12 start_period: 5s deploy: resources: limits: cpus: "0.25" memory: 128M otel-collector: image: otel/opentelemetry-collector-contrib:0.120.0 command: ["--config=/etc/otelcol/config.yaml"] volumes: - ./infra/otel/collector.yaml:/etc/otelcol/config.yaml:ro mem_limit: 256m restart: unless-stopped prometheus: image: prom/prometheus:v3.2.1 command: ["--config.file=/etc/prometheus/prometheus.yaml", "--storage.tsdb.path=/prometheus", "--storage.tsdb.retention.time=7d"] volumes: - ./infra/prometheus/prometheus.yaml:/etc/prometheus/prometheus.yaml:ro - ./infra/prometheus/alerts.yaml:/etc/prometheus/alerts.yaml:ro - prometheus_data:/prometheus restart: unless-stopped loki: image: grafana/loki:3.4.2 command: ["-config.file=/etc/loki/loki.yaml"] volumes: - ./infra/loki/loki.yaml:/etc/loki/loki.yaml:ro - loki_data:/loki restart: unless-stopped tempo: image: grafana/tempo:2.7.1 command: ["-config.file=/etc/tempo/tempo.yaml"] volumes: - ./infra/tempo/tempo.yaml:/etc/tempo/tempo.yaml:ro - tempo_data:/var/tempo restart: unless-stopped grafana: image: grafana/grafana:11.5.2 ports: ["127.0.0.1:3000:3000"] environment: GF_SECURITY_ADMIN_USER: admin GF_SECURITY_ADMIN_PASSWORD__FILE: /run/secrets/grafana_password GF_USERS_ALLOW_SIGN_UP: "false" secrets: [grafana_password] volumes: - grafana_data:/var/lib/grafana - ./infra/grafana/provisioning:/etc/grafana/provisioning:ro - ./infra/grafana/dashboards:/var/lib/grafana/dashboards:ro restart: unless-stopped secrets: grafana_password: file: ./secrets/grafana_password s3_config: file: ./secrets/s3.json s3_admin_key: file: ./secrets/s3_admin_key s3_admin_secret: file: ./secrets/s3_admin_secret s3_access_key_id: file: ./secrets/s3_access_key_id s3_secret_access_key: file: ./secrets/s3_secret_access_key postgres_password: file: ./secrets/postgres_password database_url: file: ./secrets/database_url cursor_secret: file: ./secrets/cursor_secret rabbitmq_password: file: ./secrets/rabbitmq_password broker_url: file: ./secrets/broker_url volumes: prometheus_data: loki_data: tempo_data: grafana_data: s3_data: postgres_data: rabbitmq_data: