Expand GCP infra: accounts + API services, Cloud SQL, Artifact Registry

Architecture: intelligence stays on Legion; only compiled artifacts cross
to GCP. Source code and Neuron's knowledge base never leave the system.

Artifact Registry:
- neuron-marketing, neuron-accounts, neuron-api repos in us-central1
- Keep-last-10 cleanup policy; ci-pusher SA with writer access
- Legion CI runners authenticate via GCP_SA_KEY Gitea secret

Cloud SQL (cloud-sql.tf):
- postgres-15 on db-g1-small, us-central1 (scale up to REGIONAL HA at 1k users)
- Point-in-time recovery, 14-day backup retention
- Accounts DB + user; password generated and stored in Secret Manager
- JWT signing key in Secret Manager (shared by accounts + api)
- Cloud Run connects via built-in Auth Proxy (Unix socket volume mount)

Accounts Cloud Run (cloud-run-accounts.tf):
- 3 regions (us-central1, europe-west1, asia-northeast1), min:1 max:50
- Cloud SQL proxy volume mount; secrets via Secret Manager
- Stripe + JWT env vars; health probe on /health

API Cloud Run (cloud-run-api.tf):
- 3 regions, min:1 max:100, cpu_idle=false (always-hot)
- Validates JWTs from accounts service; no direct DB connection
- License admin token from Secret Manager

Load balancer (host-based routing):
- Same global anycast IP for all three services
- URL map routes by Host: neurontechnologies.ai→marketing,
  api.neurontechnologies.ai→api, accounts.neurontechnologies.ai→accounts
- New managed SSL certs for api.* and accounts.* added to HTTPS proxy
- Cloud Armor (WAF + rate limit) applied to all backends

Service accounts + IAM:
- neuron-accounts-sa: secretmanager.secretAccessor + cloudsql.client
- neuron-api-sa: secretmanager.secretAccessor
- allUsers invoker on all prod Cloud Run services (LB health checks)

bootstrap.sh:
- One-shot setup: pulls Stripe secrets from Vault → Secret Manager,
  creates CI SA JSON key, prints DNS + next-step instructions
This commit is contained in:
Will Anderson
2026-04-25 22:43:19 -05:00
parent 93358505fc
commit d4c65d5857
11 changed files with 1245 additions and 45 deletions
+226
View File
@@ -0,0 +1,226 @@
# ── REST API (neuron-rest) — Cloud Run ────────────────────────────────────────
# Stateless API layer. Validates JWTs issued by the accounts service.
# Does NOT connect to Cloud SQL directly — reads from accounts service for
# user context; maintains its own in-process state only.
# No Cloud SQL volume needed here.
locals {
api_labels = {
"managed-by" = "terraform"
"service" = "neuron-api"
}
}
# ── Prod — us-central1 ────────────────────────────────────────────────────────
resource "google_cloud_run_v2_service" "api_us" {
name = "api-prod-us"
location = "us-central1"
project = var.project_id
ingress = "INGRESS_TRAFFIC_ALL"
labels = local.api_labels
template {
service_account = google_service_account.api.email
scaling {
min_instance_count = 1
max_instance_count = 100
}
containers {
image = local.api_image
resources {
limits = {
cpu = "2"
memory = "1Gi"
}
cpu_idle = false # API needs to be always-hot; no cold starts
}
env { name = "ENV"; value = "production" }
env { name = "PORT"; value = "8080" }
# JWT key — shared with accounts service for token validation
env {
name = "JWT_SECRET"
value_source {
secret_key_ref {
secret = google_secret_manager_secret.jwt_secret.secret_id
version = "latest"
}
}
}
# License admin token — for neuron-mcp license checks
env {
name = "LICENSE_ADMIN_TOKEN"
value_source {
secret_key_ref {
secret = google_secret_manager_secret.license_admin_token.secret_id
version = "latest"
}
}
}
# Accounts service URL — for JWT validation and user lookups
env {
name = "ACCOUNTS_SERVICE_URL"
value = "https://accounts.neurontechnologies.ai"
}
ports {
container_port = 8080
name = "http1"
}
startup_probe {
http_get {
path = "/health"
port = 8080
}
initial_delay_seconds = 2
timeout_seconds = 5
period_seconds = 5
failure_threshold = 6
}
liveness_probe {
http_get {
path = "/health"
port = 8080
}
timeout_seconds = 5
period_seconds = 30
failure_threshold = 3
}
}
max_instance_request_concurrency = 1000
}
traffic {
type = "TRAFFIC_TARGET_ALLOCATION_TYPE_LATEST"
percent = 100
}
depends_on = [
google_project_iam_member.api_secret_accessor,
google_secret_manager_secret_version.jwt_secret,
]
}
# ── Prod — europe-west1 ───────────────────────────────────────────────────────
resource "google_cloud_run_v2_service" "api_eu" {
name = "api-prod-eu"
location = "europe-west1"
project = var.project_id
ingress = "INGRESS_TRAFFIC_ALL"
labels = local.api_labels
template {
service_account = google_service_account.api.email
scaling {
min_instance_count = 1
max_instance_count = 100
}
containers {
image = local.api_image
resources {
limits = { cpu = "2"; memory = "1Gi" }
cpu_idle = false
}
env { name = "ENV"; value = "production" }
env { name = "PORT"; value = "8080" }
env {
name = "JWT_SECRET"
value_source { secret_key_ref { secret = google_secret_manager_secret.jwt_secret.secret_id; version = "latest" } }
}
env {
name = "LICENSE_ADMIN_TOKEN"
value_source { secret_key_ref { secret = google_secret_manager_secret.license_admin_token.secret_id; version = "latest" } }
}
env { name = "ACCOUNTS_SERVICE_URL"; value = "https://accounts.neurontechnologies.ai" }
ports { container_port = 8080; name = "http1" }
startup_probe {
http_get { path = "/health"; port = 8080 }
initial_delay_seconds = 2; timeout_seconds = 5; period_seconds = 5; failure_threshold = 6
}
liveness_probe {
http_get { path = "/health"; port = 8080 }
timeout_seconds = 5; period_seconds = 30; failure_threshold = 3
}
}
max_instance_request_concurrency = 1000
}
traffic { type = "TRAFFIC_TARGET_ALLOCATION_TYPE_LATEST"; percent = 100 }
depends_on = [google_project_iam_member.api_secret_accessor]
}
# ── Prod — asia-northeast1 ────────────────────────────────────────────────────
resource "google_cloud_run_v2_service" "api_apac" {
name = "api-prod-apac"
location = "asia-northeast1"
project = var.project_id
ingress = "INGRESS_TRAFFIC_ALL"
labels = local.api_labels
template {
service_account = google_service_account.api.email
scaling {
min_instance_count = 1
max_instance_count = 100
}
containers {
image = local.api_image
resources {
limits = { cpu = "2"; memory = "1Gi" }
cpu_idle = false
}
env { name = "ENV"; value = "production" }
env { name = "PORT"; value = "8080" }
env {
name = "JWT_SECRET"
value_source { secret_key_ref { secret = google_secret_manager_secret.jwt_secret.secret_id; version = "latest" } }
}
env {
name = "LICENSE_ADMIN_TOKEN"
value_source { secret_key_ref { secret = google_secret_manager_secret.license_admin_token.secret_id; version = "latest" } }
}
env { name = "ACCOUNTS_SERVICE_URL"; value = "https://accounts.neurontechnologies.ai" }
ports { container_port = 8080; name = "http1" }
startup_probe {
http_get { path = "/health"; port = 8080 }
initial_delay_seconds = 2; timeout_seconds = 5; period_seconds = 5; failure_threshold = 6
}
liveness_probe {
http_get { path = "/health"; port = 8080 }
timeout_seconds = 5; period_seconds = 30; failure_threshold = 3
}
}
max_instance_request_concurrency = 1000
}
traffic { type = "TRAFFIC_TARGET_ALLOCATION_TYPE_LATEST"; percent = 100 }
depends_on = [google_project_iam_member.api_secret_accessor]
}