Files
triggerdotdev--trigger.dev/docker/docker-compose.yml
T
Eric Allam a04cdffda6 fix(webapp): stop replica lag from double-triggering session runs and 404ing fresh sessions (#3914)
## Summary

Two read-replica races on the session APIs could break chats whose first
activity lands inside the replication window (or any time the replica
lags):

1. A session's first `.in` append or `.out` subscribe could fail with a
404 for a session that exists on the writer, because the route resolved
the Session row on the replica only.
2. `ensureRunForSession` probed run liveness on the replica, so a probe
miss on a run triggered moments earlier was judged "run is dead" and a
second live run was spawned for the same session. Both runs then
consumed the same input stream, producing duplicated turns and doubled
responses (and doubled LLM cost).

## Fix

Liveness now re-probes the writer before declaring the current run dead
(the old code already fell back to the writer, but only to recover the
friendlyId, after the wrong verdict was made). Session resolution on the
append and subscribe/init routes goes through a new
`resolveSessionWithWriterFallback`, which stays replica-first on the hot
path and only touches the writer on a miss.

Reproduced and verified against a local streaming replica with an
artificial apply delay: pre-fix, a send immediately after session
creation reliably produced either the 404 or two executing runs with a
doubled response; post-fix, the same flow produces exactly one run and
one response.

Also rides along: the local docker replica's default apply delay drops
from 150ms to a realistic 20ms (override via `REPLICA_APPLY_DELAY` when
you want to deliberately widen the race window).
2026-06-12 14:07:36 +01:00

232 lines
7.7 KiB
YAML

# Core local-dev stack: the minimum a contributor needs to boot the webapp.
# For optional services (object store, observability, HTTP/2 proxy, chaos
# tooling, ClickHouse UI, extra electric shard) see ./docker-compose.extras.yml
# and the `pnpm run docker:full` script.
#
# Every host port is overridable via env vars from the root `.env` so multiple
# instances (worktrees, branch experiments) can run side by side. See the
# "Multiple instances" block in `.env.example` for the full set of knobs.
name: triggerdotdev-docker
volumes:
database-data:
database-data-alt:
database-replica-data:
redis-data:
minio-data:
clickhouse-data:
clickhouse-logs:
networks:
app_network:
external: false
services:
database:
container_name: ${CONTAINER_PREFIX:-}database
build:
context: .
dockerfile: Dockerfile.postgres
restart: always
volumes:
- ${DB_VOLUME:-database-data}:/var/lib/postgresql/data/
environment:
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
POSTGRES_DB: postgres
networks:
- app_network
ports:
- "${POSTGRES_HOST_PORT:-5432}:5432"
command:
- -c
- listen_addresses=*
- -c
- wal_level=logical
- -c
- shared_preload_libraries=pg_partman_bgw
# The webapp opens ~50 pooled connections per instance and Electric another
# ~40, so the default 100 is exhausted by one webapp + Electric alone. Raise
# it so multiple instances / load tests have headroom.
- -c
- max_connections=500
# Opt-in streaming read replica with configurable apply lag — a dial-a-lag rig for
# testing replica-race behavior (e.g. the realtime read-your-writes gate) locally.
# Start with: COMPOSE_PROFILES=replica pnpm run docker
# One-time primary prep (allows replication connections; additive, survives restarts):
# docker exec database bash -c 'grep -q "host replication" "$PGDATA/pg_hba.conf" || echo "host replication all all md5" >> "$PGDATA/pg_hba.conf"'
# docker exec database psql -U postgres -c "SELECT pg_reload_conf()"
# Then point the webapp at it: DATABASE_READ_REPLICA_URL=postgresql://postgres:postgres@localhost:5433/postgres
# Tune the lag via REPLICA_APPLY_DELAY (default 20ms ~ realistic prod lag; crank to 150ms/2s to
# shake out replica races). Wipe database-replica-data to re-init.
database-replica:
container_name: ${CONTAINER_PREFIX:-}database-replica
profiles: ["replica"]
build:
context: .
dockerfile: Dockerfile.postgres
restart: always
depends_on:
- database
volumes:
- ${DB_REPLICA_VOLUME:-database-replica-data}:/var/lib/postgresql/data/
environment:
PGPASSWORD: postgres
REPLICA_APPLY_DELAY: ${REPLICA_APPLY_DELAY:-20ms}
networks:
- app_network
ports:
- "${POSTGRES_REPLICA_HOST_PORT:-5433}:5432"
entrypoint: ["bash", "-c"]
command:
- |
set -e
if [ ! -s "$$PGDATA/PG_VERSION" ]; then
echo "initializing streaming replica from 'database'..."
mkdir -p "$$PGDATA"
chown postgres:postgres "$$PGDATA"
chmod 0700 "$$PGDATA"
until gosu postgres pg_basebackup -h database -U postgres -D "$$PGDATA" -Fp -Xs -R; do
echo "primary not ready for replication (did you run the one-time pg_hba prep above?); retrying..."
rm -rf "$$PGDATA"/* 2>/dev/null || true
sleep 2
done
fi
# max_connections must be >= the primary's (hot-standby requirement).
exec docker-entrypoint.sh postgres -c hot_standby=on -c max_connections=500 -c "recovery_min_apply_delay=$$REPLICA_APPLY_DELAY"
redis:
container_name: ${CONTAINER_PREFIX:-}redis
image: redis:7@sha256:3e1b24a1a8f24ff926b15e5ace8c38a03e5657fb66e1fc7e5188e315aa5fa094
restart: always
volumes:
- redis-data:/data
networks:
- app_network
ports:
- "${REDIS_HOST_PORT:-6379}:6379"
# S3-compatible API for the local object store (large payloads / packet
# offload). Host :${MINIO_API_HOST_PORT:-9005} = S3 API,
# host :${MINIO_CONSOLE_HOST_PORT:-9006} = web console. The webapp only
# routes to it when the OBJECT_STORE_* env vars are set (see .env.example).
minio:
container_name: ${CONTAINER_PREFIX:-}minio
image: minio/minio:latest@sha256:14cea493d9a34af32f524e538b8346cf79f3321eff8e708c1e2960462bd8936e
restart: always
command: server /data --console-address ":9001"
environment:
MINIO_ROOT_USER: minioadmin
MINIO_ROOT_PASSWORD: minioadmin
volumes:
- minio-data:/data
ports:
- "${MINIO_API_HOST_PORT:-9005}:9000"
- "${MINIO_CONSOLE_HOST_PORT:-9006}:9001"
networks:
- app_network
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
interval: 5s
timeout: 5s
retries: 5
start_period: 5s
minio-init:
image: minio/mc:latest@sha256:a7fe349ef4bd8521fb8497f55c6042871b2ae640607cf99d9bede5e9bdf11727
depends_on:
minio:
condition: service_healthy
networks:
- app_network
entrypoint: /bin/sh
command:
- -c
- |
mc alias set local http://minio:9000 minioadmin minioadmin
mc mb -p local/packets || true
restart: "no"
electric:
container_name: ${CONTAINER_PREFIX:-}electric
image: electricsql/electric:1.2.4@sha256:20da3d0b0e74926c5623392db67fd56698b9e374c4aeb6cb5cadeb8fea171c36
restart: always
environment:
DATABASE_URL: postgresql://postgres:postgres@database:5432/postgres?sslmode=disable
ELECTRIC_INSECURE: true
ELECTRIC_ENABLE_INTEGRATION_TESTING: true
networks:
- app_network
ports:
- "${ELECTRIC_HOST_PORT:-3060}:3000"
depends_on:
- database
clickhouse:
image: clickhouse/clickhouse-server:25.6.2@sha256:97f0fe0f8729569e8c9d11069acee23abadeade4889f56ca3dc3df069f28cb85
restart: always
container_name: ${CONTAINER_PREFIX:-}clickhouse
ulimits:
nofile:
soft: 262144
hard: 262144
environment:
CLICKHOUSE_USER: default
CLICKHOUSE_PASSWORD: password
CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT: 1
ports:
- "${CLICKHOUSE_HTTP_HOST_PORT:-8123}:8123"
- "${CLICKHOUSE_TCP_HOST_PORT:-9000}:9000"
volumes:
- clickhouse-data:/var/lib/clickhouse
- clickhouse-logs:/var/log/clickhouse-server
- ./config/clickhouse-disable-system-logs.xml:/etc/clickhouse-server/config.d/disable-system-logs.xml:ro
networks:
- app_network
healthcheck:
test:
[
"CMD",
"clickhouse-client",
"--host",
"localhost",
"--port",
"9000",
"--user",
"default",
"--password",
"password",
"--query",
"SELECT 1",
]
interval: "3s"
timeout: "5s"
retries: "5"
start_period: "10s"
clickhouse_migrator:
build:
context: ../internal-packages/clickhouse
dockerfile: ./Dockerfile
depends_on:
clickhouse:
condition: service_healthy
networks:
- app_network
command: ["goose", "${GOOSE_COMMAND:-up}"]
# s2-lite: open-source S2 (https://s2.dev) for local realtime streams v2.
# The image is distroless (no shell), so a `wget` / `curl` healthcheck
# always reports unhealthy even when the API is responding. No other
# service depends on this one, so the healthcheck is omitted.
s2:
image: ghcr.io/s2-streamstore/s2:latest@sha256:d6ded5ca7dd619fa7c946f06e39a98f9c95c6883c8bb884e5eaa129f232c920c
command: ["lite", "--init-file", "/s2-spec.json"]
volumes:
- ./config/s2-spec.json:/s2-spec.json:ro
ports:
- "${S2_HOST_PORT:-4566}:80"
networks:
- app_network