13e069d72c
Two production-readiness fixes called out in the scaling review for ~40 concurrent users + daily upstream webhook traffic: 1. Prisma connection pool DATABASE_URL now carries ?connection_limit=20&pool_timeout=10 both in docker-compose.yml (prod) and .env.example (local). Default is cpus*2+1 (~5-9 inside a container) which can exhaust at peak when mutations + TanStack Query polling coincide. Postgres max_connections is 100 so 20 × a couple of app replicas leaves headroom. 2. Webhook rate limiter New src/lib/webhooks/rate-limit.ts — in-memory sliding-window limiter keyed on "<scope>:<ip>". 100 req/min per IP per webhook (omg / deliverables / briefs). Applied to all three POST handlers; over the limit returns 429 with a Retry-After header. Dev-mode bypass honours the matching *_WEBHOOK_ALLOW_INSECURE env so stub testing isn't throttled. Single-process only — swap the Map for Redis if we scale to multiple Next.js instances. Single-instance dow-prod-tracker on optical-dev is the target today, so in-memory is sufficient. Also updated INTEGRATION.md with a rate-limiting section so the upstream integrator knows what to expect + how to handle 429s.
87 lines
3.8 KiB
YAML
87 lines
3.8 KiB
YAML
name: dow-prod-tracker
|
||
|
||
services:
|
||
# ─── PostgreSQL with pgvector ───────────────────────────
|
||
db:
|
||
image: pgvector/pgvector:pg17
|
||
restart: unless-stopped
|
||
environment:
|
||
POSTGRES_USER: postgres
|
||
POSTGRES_PASSWORD: ${DB_PASSWORD:-postgres}
|
||
POSTGRES_DB: dow_prod_tracker
|
||
# Host port is overridable via DB_HOST_PORT env var — deploy.sh auto-picks
|
||
# a free one if 5492 is taken on the host. The container-internal port
|
||
# (5432) never changes — the app connects to db:5432 over the Docker
|
||
# network and doesn't care what host port (if any) is mapped.
|
||
ports:
|
||
- "${DB_HOST_PORT:-5492}:5432"
|
||
volumes:
|
||
- pgdata:/var/lib/postgresql/data
|
||
- ./docker/db-init.sql:/docker-entrypoint-initdb.d/01-pgvector.sql:ro
|
||
healthcheck:
|
||
test: ["CMD-SHELL", "pg_isready -U postgres"]
|
||
interval: 5s
|
||
timeout: 5s
|
||
retries: 5
|
||
|
||
# ─── Next.js app ───────────────────────────────────────
|
||
app:
|
||
build:
|
||
context: .
|
||
dockerfile: Dockerfile
|
||
restart: unless-stopped
|
||
# Host port is overridable via APP_HOST_PORT env var — deploy.sh auto-picks
|
||
# a free one if 3002 is taken, and writes the chosen port into the Apache
|
||
# reverse-proxy config (apache/dow-prod-tracker.conf) at the same time.
|
||
ports:
|
||
- "${APP_HOST_PORT:-3002}:3000"
|
||
environment:
|
||
# DATABASE_URL tuning knobs matter at ~40 concurrent users:
|
||
# connection_limit — how many pooled connections Prisma will
|
||
# open per app instance. Default is cpus*2+1 (~5-9 inside a
|
||
# container), which can run out at peak when mutations + query
|
||
# polling coincide. 20 gives plenty of headroom for this scale.
|
||
# pool_timeout — seconds to wait for a free connection before
|
||
# failing the request (default 10). 10s matches the default
|
||
# and stays explicit.
|
||
# Postgres side: default max_connections is 100, so 20 × a few
|
||
# app replicas is well below the ceiling.
|
||
DATABASE_URL: postgresql://postgres:${DB_PASSWORD:-postgres}@db:5432/dow_prod_tracker?schema=public&connection_limit=20&pool_timeout=10
|
||
# Ollama — points to internal GPU server for embeddings + chat fallback
|
||
OLLAMA_HOST: ${OLLAMA_HOST:-http://10.24.42.219:11434}
|
||
OLLAMA_CHAT_HOST: ${OLLAMA_CHAT_HOST:-http://10.24.42.219:11434}
|
||
OLLAMA_CHAT_MODEL: ${OLLAMA_CHAT_MODEL:-gemma4:latest}
|
||
OLLAMA_EMBED_MODEL: ${OLLAMA_EMBED_MODEL:-nomic-embed-text}
|
||
NODE_ENV: production
|
||
AUTH_SECRET: ${AUTH_SECRET}
|
||
AUTH_TRUST_HOST: "true"
|
||
# Azure SPA registration — PKCE in browser, no client secret
|
||
AZURE_CLIENT_ID: ${AZURE_CLIENT_ID}
|
||
AZURE_TENANT_ID: ${AZURE_TENANT_ID}
|
||
AZURE_REDIRECT_URI: ${AZURE_REDIRECT_URI:-}
|
||
CRON_SECRET: ${CRON_SECRET:-change-me}
|
||
API_KEY: ${API_KEY:-}
|
||
ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-}
|
||
ANTHROPIC_MODEL: ${ANTHROPIC_MODEL:-}
|
||
DEV_BYPASS_AUTH: ${DEV_BYPASS_AUTH:-false}
|
||
DEV_USER_ID: ${DEV_USER_ID:-}
|
||
# OMG webhook (Shashank pending — stub until payload confirmed)
|
||
OMG_WEBHOOK_SECRET: ${OMG_WEBHOOK_SECRET:-}
|
||
OMG_WEBHOOK_ALLOW_INSECURE: ${OMG_WEBHOOK_ALLOW_INSECURE:-false}
|
||
# Auth: Entra SSO stays coded but gated. Flip to "true" post-MVP once redirect URI is live.
|
||
NEXT_PUBLIC_AUTH_ENTRA_ENABLED: ${NEXT_PUBLIC_AUTH_ENTRA_ENABLED:-false}
|
||
volumes:
|
||
- uploads_data:/data/uploads
|
||
depends_on:
|
||
db:
|
||
condition: service_healthy
|
||
healthcheck:
|
||
test: ["CMD-SHELL", "wget -q --spider http://localhost:3000/api/health || exit 1"]
|
||
interval: 15s
|
||
timeout: 5s
|
||
retries: 3
|
||
start_period: 30s
|
||
|
||
volumes:
|
||
pgdata:
|
||
uploads_data:
|