Comio/docker-compose.yml at main · DivineAvi/Comio · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
# Comio — Local Development Environment
# Start:  docker compose up -d
# Stop:   docker compose down
# Reset:  docker compose down -v  (wipes all data)
# Logs:   docker compose logs -f postgres

services:
  # ─── PostgreSQL Database ─────────────────────────────────────
  # Stores all application data: projects, incidents, users, deployments,
  # chat history, AI diagnoses, etc.
  # Uses pgvector extension for storing AI embeddings (needed for RAG search).
  postgres:
    image: pgvector/pgvector:pg16
    container_name: comio-postgres
    restart: unless-stopped
    environment:
      POSTGRES_USER: comio
      POSTGRES_PASSWORD: comio
      POSTGRES_DB: comio
    ports:
      - "5432:5432"
    volumes:
      - postgres_data:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U comio"]
      interval: 10s
      timeout: 5s
      retries: 5

  # ─── Redis ───────────────────────────────────────────────────
  # In-memory data store used for:
  # - Caching LLM responses (save money by not re-calling for same queries)
  # - Rate limiting API requests
  # - Pub/Sub events (real-time incident notifications, deploy status)
  # - Storing anomaly detection model state
  # - Session data
  redis:
    image: redis:7-alpine
    container_name: comio-redis
    restart: unless-stopped
    ports:
      - "6379:6379"
    volumes:
      - redis_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5

  # ─── Demo Order API ──────────────────────────────────────────
  # Simulated e-commerce service for testing monitoring/alerting.
  # Includes chaos endpoints to trigger failures on demand.
  demo-app:
    build:
      context: .
      dockerfile: docker/Dockerfile.demo-app
    container_name: comio-demo-app
    restart: unless-stopped
    ports:
      - "8001:8000"
    environment:
      - LOG_LEVEL=INFO
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 15s
      timeout: 5s
      retries: 3
    depends_on:
      - prometheus

  # ─── Prometheus ──────────────────────────────────────────────
  # Metrics collection and storage. Scrapes /metrics endpoints
  # from demo-app and Comio API. Evaluates alerting rules.
  prometheus:
    image: prom/prometheus:v2.51.0
    container_name: comio-prometheus
    restart: unless-stopped
    ports:
      - "9090:9090"
    volumes:
      - ./infra/observability/prometheus.yml:/etc/prometheus/prometheus.yml
      - ./infra/observability/alert_rules.yml:/etc/prometheus/alert_rules.yml
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
    healthcheck:
      test: ["CMD", "wget", "-q", "--spider", "http://localhost:9090/-/healthy"]
      interval: 15s
      timeout: 5s
      retries: 3

  # ─── Alertmanager ────────────────────────────────────────────
  # Handles alerts from Prometheus. Routes them to webhooks,
  # Slack, PagerDuty, etc. We configure it to send to Comio API.
  alertmanager:
    image: prom/alertmanager:v0.27.0
    container_name: comio-alertmanager
    restart: unless-stopped
    ports:
      - "9093:9093"
    volumes:
      - ./infra/observability/alertmanager.yml:/etc/alertmanager/alertmanager.yml
      - alertmanager_data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
    healthcheck:
      test: ["CMD", "wget", "-q", "--spider", "http://localhost:9093/-/healthy"]
      interval: 15s
      timeout: 5s
      retries: 3
    depends_on:
      - prometheus

# Named volumes — Docker manages the storage location.
# Data persists across container restarts.
# Run `docker compose down -v` to wipe everything and start fresh.
volumes:
  postgres_data:
  redis_data:
  prometheus_data:
  alertmanager_data: