diff --git a/.github/workflows/test-terraform-modules.yml b/.github/workflows/test-terraform-modules.yml index 0e3e5330453..52006d9b578 100644 --- a/.github/workflows/test-terraform-modules.yml +++ b/.github/workflows/test-terraform-modules.yml @@ -4,6 +4,7 @@ on: push: paths: - "terraform/litellm/aws/**" + - "terraform/litellm/gcp/**" - ".github/workflows/test-terraform-modules.yml" pull_request: branches: @@ -13,6 +14,7 @@ on: - "litellm_**" paths: - "terraform/litellm/aws/**" + - "terraform/litellm/gcp/**" - ".github/workflows/test-terraform-modules.yml" permissions: @@ -52,3 +54,32 @@ jobs: # Plan-only, mock_provider-backed: no AWS credentials, no API calls. - name: test run: terraform test + + gcp-module: + name: fmt, validate, test (gcp) + runs-on: ubuntu-latest + timeout-minutes: 15 + defaults: + run: + working-directory: terraform/litellm/gcp + steps: + - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0 + with: + persist-credentials: false + + - uses: hashicorp/setup-terraform@b9cd54a3c349d3f38e8881555d616ced269862dd # v3.1.2 + with: + terraform_version: 1.13.3 + terraform_wrapper: false + + - name: fmt + run: terraform fmt -recursive -check -diff + + - name: init + run: terraform init -backend=false -input=false + + - name: validate + run: terraform validate + + - name: test + run: terraform test diff --git a/terraform/litellm/gcp/README.md b/terraform/litellm/gcp/README.md index 88e9979148f..c93e5f6b303 100644 --- a/terraform/litellm/gcp/README.md +++ b/terraform/litellm/gcp/README.md @@ -392,6 +392,63 @@ with its own provider config (one `examples/default`-style root per project), or fork the module to add `configuration_aliases` and pass per-instance `providers = { ... }`. +## Dependencies only (run LiteLLM on GKE) + +Set `create_runtime = false` to provision Cloud SQL, Memorystore, GCS, +Secret Manager, and the runtime service account without Cloud Run or the +load balancer. For a Shared VPC, set the full host-project network ID and +skip PSA creation after the host project has configured it: + +```hcl +create_runtime = false +network_id = "projects//global/networks/" +create_psa_connection = false +``` + +The host project must already have Private Services Access configured on +that network and the Service Networking API enabled; the module cannot set +PSA up from a service project. GKE nodes must sit on the same Shared VPC so +the Cloud SQL and Memorystore private IPs are routable from the pods. Run +the root with its provider pointed at the project that should own the +dependencies. `create_runtime = true` with `network_id` set is also allowed, +but the Serverless VPC Access connector has to live in the same project as +the network, so that combination only works when the VPC is in the +deployment project + +Map the outputs into the Helm values as follows: + +```yaml +database: + writer: + host: + dbname: + passwordSecret: + name: + reader: + host: + dbname: + passwordSecret: + name: +redis: + host: + port: +masterKey: + secretName: +``` + +Create the database Secret with keys `username` (the `db_username` output) +and `password` (read it with `gcloud secrets versions access latest +--secret=`), and the master key Secret from +`master_key_secret_id` the same way. Memorystore only accepts TLS by +default, so store the `redis_server_ca_pem` output in a third Secret, +mount it into the gateway and backend pods via `volumes` / `volumeMounts`, +and add `REDIS_SSL=true` and `REDIS_SSL_CA_CERTS=` to each +component's `extraEnv`. Setting `redis_transit_encryption = false` removes +the CA plumbing at the cost of plaintext Redis traffic inside the VPC + +The chart's pre-install/pre-upgrade migration hook runs the Prisma +migration, so nothing replaces the Cloud Run migrations Job in this mode + ## Storage and database retention Two opt-in tripwires guard against accidental data loss on @@ -409,14 +466,15 @@ Flip `cloudsql_deletion_protection` to `false` or `gcs_force_destroy` to ## Redis encryption -Memorystore runs with `transit_encryption_mode = "SERVER_AUTHENTICATION"`, -so the proxy connects via `rediss://`. The instance's self-signed CA cert -(`server_ca_certs[0].cert`) is shipped to gateway + backend as -`REDIS_CA_PEM_B64`; their entrypoint shell decodes it to `/tmp/redis-ca.pem` -before uvicorn starts and points `REDIS_SSL_CA_CERTS` at that path. No -extra config needed — but if you ever swap Memorystore for an external -Redis, override `REDIS_HOST`/`REDIS_PORT` and either drop these env vars -or point them at your own CA. +By default, Memorystore runs with +`transit_encryption_mode = "SERVER_AUTHENTICATION"`, so Cloud Run connects +via `rediss://`. The instance's self-signed CA cert +(`server_ca_certs[0].cert`) is shipped to gateway and backend as +`REDIS_CA_PEM_B64`; their entrypoint shell decodes it to +`/tmp/redis-ca.pem` before uvicorn starts and points `REDIS_SSL_CA_CERTS` at +that path. Set `redis_transit_encryption = false` to use plaintext Redis. +For GKE, use `redis_server_ca_pem` as described in the dependencies-only +section, or accept the security tradeoff of disabling transit encryption ## Files @@ -434,4 +492,5 @@ or point them at your own CA. | `iam.tf` | Runtime SA + Cloud SQL client + Secret Manager accessor | | `cloudrun.tf` | 3 Cloud Run services + Cloud Run Job for migrations | | `load_balancer.tf`| External HTTPS LB, serverless NEGs, URL map for path routing | -| `outputs.tf` | LB IP, service URLs, secret IDs, migration `execute` command | +| `outputs.tf` | LB IP, service URLs, dependency endpoints, secret IDs, migration command | +| `tests/` | Plan-only mock-provider coverage for deployment modes and Redis encryption | diff --git a/terraform/litellm/gcp/bootstrap.tf b/terraform/litellm/gcp/bootstrap.tf index b929c4d76f3..dead5c41f6b 100644 --- a/terraform/litellm/gcp/bootstrap.tf +++ b/terraform/litellm/gcp/bootstrap.tf @@ -15,15 +15,17 @@ # enough to invoke Cloud Run admin APIs (`gcloud auth login`). resource "terraform_data" "migration" { + count = var.create_runtime ? 1 : 0 + triggers_replace = { - job_id = google_cloud_run_v2_job.migrations.id + job_id = google_cloud_run_v2_job.migrations[0].id job_image = local.migrations_image } provisioner "local-exec" { interpreter = ["bash", "-c"] environment = { - JOB = google_cloud_run_v2_job.migrations.name + JOB = google_cloud_run_v2_job.migrations[0].name REGION = var.region PROJECT = var.project_id } diff --git a/terraform/litellm/gcp/cloudrun.tf b/terraform/litellm/gcp/cloudrun.tf index 5a5c361b832..84ae8b9247f 100644 --- a/terraform/litellm/gcp/cloudrun.tf +++ b/terraform/litellm/gcp/cloudrun.tf @@ -6,25 +6,28 @@ locals { # Memorystore exposes a self-signed CA cert per instance; we ship it as # a base64 env var and decode it to a file at container startup so the # rediss:// connection can validate. Public cert, not sensitive. - redis_ca_pem_b64 = base64encode(google_redis_instance.this.server_ca_certs[0].cert) + redis_ca_pem_b64 = var.redis_transit_encryption ? base64encode(google_redis_instance.this.server_ca_certs[0].cert) : "" - shared_env_kv = [ - { name = "DATABASE_HOST", value = google_sql_database_instance.writer.private_ip_address }, - { name = "DATABASE_PORT", value = "5432" }, - { name = "DATABASE_USER", value = var.db_username }, - { name = "DATABASE_NAME", value = var.db_name }, - { name = "DATABASE_HOST_READ_REPLICA", value = google_sql_database_instance.reader.private_ip_address }, - { name = "DATABASE_PORT_READ_REPLICA", value = "5432" }, - { name = "REDIS_HOST", value = google_redis_instance.this.host }, - { name = "REDIS_PORT", value = tostring(google_redis_instance.this.port) }, - # _redis.get_redis_url_from_environment honors REDIS_SSL to flip the - # scheme to rediss://; REDIS_SSL_CA_CERTS is mapped via - # _get_redis_env_kwarg_mapping → ssl_ca_certs on the redis-py client. - { name = "REDIS_SSL", value = "true" }, - { name = "REDIS_SSL_CA_CERTS", value = "/tmp/redis-ca.pem" }, - { name = "REDIS_CA_PEM_B64", value = local.redis_ca_pem_b64 }, - { name = "GCS_BUCKET_NAME", value = google_storage_bucket.this.name }, - ] + shared_env_kv = concat( + [ + { name = "DATABASE_HOST", value = google_sql_database_instance.writer.private_ip_address }, + { name = "DATABASE_PORT", value = "5432" }, + { name = "DATABASE_USER", value = var.db_username }, + { name = "DATABASE_NAME", value = var.db_name }, + { name = "DATABASE_HOST_READ_REPLICA", value = google_sql_database_instance.reader.private_ip_address }, + { name = "DATABASE_PORT_READ_REPLICA", value = "5432" }, + { name = "REDIS_HOST", value = google_redis_instance.this.host }, + { name = "REDIS_PORT", value = tostring(google_redis_instance.this.port) }, + ], + var.redis_transit_encryption ? [ + { name = "REDIS_SSL", value = "true" }, + { name = "REDIS_SSL_CA_CERTS", value = "/tmp/redis-ca.pem" }, + { name = "REDIS_CA_PEM_B64", value = local.redis_ca_pem_b64 }, + ] : [], + [ + { name = "GCS_BUCKET_NAME", value = google_storage_bucket.this.name }, + ], + ) # OTel v2 is opt-in and gated on otel_endpoint, matching the AWS stack — # nothing OTel-related is added to the container env until an endpoint is @@ -126,9 +129,9 @@ locals { # Decode the Memorystore CA cert (passed as REDIS_CA_PEM_B64) to the # path REDIS_SSL_CA_CERTS points at, so the redis-py client can validate # the rediss:// handshake. - redis_ca_fragment = [ + redis_ca_fragment = var.redis_transit_encryption ? [ "python -c \"import os, base64, pathlib; pathlib.Path(os.environ['REDIS_SSL_CA_CERTS']).write_bytes(base64.b64decode(os.environ['REDIS_CA_PEM_B64']))\"" - ] + ] : [] database_url_fragment = [ "export DATABASE_URL=\"postgresql://$${DATABASE_USER}:$${DATABASE_PASSWORD}@$${DATABASE_HOST}:$${DATABASE_PORT}/$${DATABASE_NAME}\"", @@ -171,29 +174,7 @@ locals { # ---------- Gateway ---------- resource "google_cloud_run_v2_service" "gateway" { - # Metering needs a client certificate AND its key. Each secret is created only - # when its own PEM is supplied, so an endpoint set with a missing key would - # otherwise apply cleanly and leave the proxy logging "missing config" and - # never exporting. ca_cert_pem stays optional: empty means fall back to the - # system trust store. - # - # The guard lives here, on an unconditional resource, rather than on the cert - # secret: that secret is count-gated on the cert itself, so it has zero - # instances in exactly the case this must catch. Adding count or for_each to - # this resource would silently stop the guard from evaluating. - # - # endpoint cert key -> result - # "" any any -> metering off, no secrets created - # set set set -> metering on - # set any-missing -> plan fails here - lifecycle { - precondition { - condition = var.billing_metrics_endpoint == "" || ( - var.billing_metrics_client_cert_pem != "" && var.billing_metrics_client_key_pem != "" - ) - error_message = "billing_metrics_client_cert_pem and billing_metrics_client_key_pem are both required when billing_metrics_endpoint is set." - } - } + count = var.create_runtime ? 1 : 0 name = "${local.name}-gateway" location = var.region @@ -206,7 +187,7 @@ resource "google_cloud_run_v2_service" "gateway" { max_instance_request_concurrency = var.gateway_max_instance_request_concurrency vpc_access { - connector = google_vpc_access_connector.this.id + connector = google_vpc_access_connector.this[0].id egress = "PRIVATE_RANGES_ONLY" } @@ -312,17 +293,7 @@ resource "google_cloud_run_v2_service" "gateway" { # ---------- Backend ---------- resource "google_cloud_run_v2_service" "backend" { - # Same guard as the gateway: the backend meters too (it serves the named-server - # MCP transport), and a targeted apply of just this resource must not slip a - # billing endpoint through without the credentials to use it. - lifecycle { - precondition { - condition = var.billing_metrics_endpoint == "" || ( - var.billing_metrics_client_cert_pem != "" && var.billing_metrics_client_key_pem != "" - ) - error_message = "billing_metrics_client_cert_pem and billing_metrics_client_key_pem are both required when billing_metrics_endpoint is set." - } - } + count = var.create_runtime ? 1 : 0 name = "${local.name}-backend" location = var.region @@ -335,7 +306,7 @@ resource "google_cloud_run_v2_service" "backend" { max_instance_request_concurrency = var.backend_max_instance_request_concurrency vpc_access { - connector = google_vpc_access_connector.this.id + connector = google_vpc_access_connector.this[0].id egress = "PRIVATE_RANGES_ONLY" } @@ -443,6 +414,8 @@ resource "google_cloud_run_v2_service" "backend" { # with zero IAM bindings, so a compromised UI container can't pivot to # Secret Manager / Cloud SQL via the metadata service. resource "google_cloud_run_v2_service" "ui" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-ui" location = var.region ingress = "INGRESS_TRAFFIC_INTERNAL_LOAD_BALANCER" @@ -450,7 +423,7 @@ resource "google_cloud_run_v2_service" "ui" { deletion_protection = false template { - service_account = google_service_account.ui_runtime.email + service_account = google_service_account.ui_runtime[0].email max_instance_request_concurrency = var.ui_max_instance_request_concurrency scaling { @@ -491,25 +464,31 @@ resource "google_cloud_run_v2_service" "ui" { # (LITELLM_MASTER_KEY); these IAM bindings just open up Cloud Run's invoker # gate so the LB request makes it to the container. resource "google_cloud_run_v2_service_iam_member" "gateway_allusers" { + count = var.create_runtime ? 1 : 0 + project = var.project_id - location = google_cloud_run_v2_service.gateway.location - name = google_cloud_run_v2_service.gateway.name + location = google_cloud_run_v2_service.gateway[0].location + name = google_cloud_run_v2_service.gateway[0].name role = "roles/run.invoker" member = "allUsers" } resource "google_cloud_run_v2_service_iam_member" "backend_allusers" { + count = var.create_runtime ? 1 : 0 + project = var.project_id - location = google_cloud_run_v2_service.backend.location - name = google_cloud_run_v2_service.backend.name + location = google_cloud_run_v2_service.backend[0].location + name = google_cloud_run_v2_service.backend[0].name role = "roles/run.invoker" member = "allUsers" } resource "google_cloud_run_v2_service_iam_member" "ui_allusers" { + count = var.create_runtime ? 1 : 0 + project = var.project_id - location = google_cloud_run_v2_service.ui.location - name = google_cloud_run_v2_service.ui.name + location = google_cloud_run_v2_service.ui[0].location + name = google_cloud_run_v2_service.ui[0].name role = "roles/run.invoker" member = "allUsers" } @@ -519,6 +498,8 @@ resource "google_cloud_run_v2_service_iam_member" "ui_allusers" { # assembles DATABASE_URL from the DATABASE_* env vars and runs `prisma # migrate deploy`. No proxy_config, no master key, no shell wrapper. resource "google_cloud_run_v2_job" "migrations" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-migrations" location = var.region labels = local.labels @@ -529,7 +510,7 @@ resource "google_cloud_run_v2_job" "migrations" { service_account = google_service_account.runtime.email vpc_access { - connector = google_vpc_access_connector.this.id + connector = google_vpc_access_connector.this[0].id egress = "PRIVATE_RANGES_ONLY" } diff --git a/terraform/litellm/gcp/cloudsql.tf b/terraform/litellm/gcp/cloudsql.tf index c9c2d03b2de..777434b4727 100644 --- a/terraform/litellm/gcp/cloudsql.tf +++ b/terraform/litellm/gcp/cloudsql.tf @@ -36,7 +36,7 @@ resource "google_sql_database_instance" "writer" { ip_configuration { ipv4_enabled = false - private_network = google_compute_network.this.id + private_network = local.network_id } insights_config { @@ -55,6 +55,11 @@ resource "google_sql_database_instance" "writer" { # (full data loss). Set the initial size only; let Cloud SQL own it # thereafter. ignore_changes = [settings[0].disk_size] + + precondition { + condition = var.create_psa_connection || var.network_id != "" + error_message = "create_psa_connection must be true unless network_id references an existing VPC with Private Services Access configured." + } } } @@ -76,7 +81,7 @@ resource "google_sql_database_instance" "reader" { ip_configuration { ipv4_enabled = false - private_network = google_compute_network.this.id + private_network = local.network_id } } diff --git a/terraform/litellm/gcp/examples/default/main.tf b/terraform/litellm/gcp/examples/default/main.tf index 8760d445f0c..f44b2a9a001 100644 --- a/terraform/litellm/gcp/examples/default/main.tf +++ b/terraform/litellm/gcp/examples/default/main.tf @@ -31,6 +31,11 @@ module "litellm" { tenant = var.tenant env = var.env + create_runtime = var.create_runtime + network_id = var.network_id + create_psa_connection = var.create_psa_connection + redis_transit_encryption = var.redis_transit_encryption + litellm_master_key = var.litellm_master_key litellm_license = var.litellm_license ui_password = var.ui_password diff --git a/terraform/litellm/gcp/examples/default/outputs.tf b/terraform/litellm/gcp/examples/default/outputs.tf index 3a9343c4850..48cdc1af66e 100644 --- a/terraform/litellm/gcp/examples/default/outputs.tf +++ b/terraform/litellm/gcp/examples/default/outputs.tf @@ -38,6 +38,31 @@ output "redis_endpoint" { value = module.litellm.redis_endpoint } +output "redis_host" { + description = "Memorystore Redis host." + value = module.litellm.redis_host +} + +output "redis_port" { + description = "Memorystore Redis port." + value = module.litellm.redis_port +} + +output "redis_server_ca_pem" { + description = "Memorystore server CA PEM." + value = module.litellm.redis_server_ca_pem +} + +output "db_username" { + description = "Cloud SQL application username." + value = module.litellm.db_username +} + +output "db_name" { + description = "Cloud SQL database name." + value = module.litellm.db_name +} + output "gcs_bucket" { description = "GCS bucket name." value = module.litellm.gcs_bucket @@ -53,6 +78,11 @@ output "db_password_secret_id" { value = module.litellm.db_password_secret_id } +output "runtime_service_account_email" { + description = "Runtime service account email." + value = module.litellm.runtime_service_account_email +} + output "migration_run_command" { description = "Break-glass command to re-run the one-off migration job." value = module.litellm.migration_run_command diff --git a/terraform/litellm/gcp/examples/default/terraform.tfvars.example b/terraform/litellm/gcp/examples/default/terraform.tfvars.example index 4416cf0ee5d..c35206503bb 100644 --- a/terraform/litellm/gcp/examples/default/terraform.tfvars.example +++ b/terraform/litellm/gcp/examples/default/terraform.tfvars.example @@ -8,6 +8,14 @@ region = "us-central1" tenant = "acme" env = "stage" +# Deployment mode. For dependencies only on a Shared VPC, set +# create_runtime = false, network_id to the full host-project network ID, and +# create_psa_connection = false after configuring PSA on that network. +# create_runtime = true +# network_id = "" +# create_psa_connection = true +# redis_transit_encryption = true + # Tenant-supplied secrets. Prefer TF_VAR_litellm_master_key / # TF_VAR_litellm_license / TF_VAR_ui_password env vars so the values don't # end up in a committed tfvars file. All three are optional — when diff --git a/terraform/litellm/gcp/examples/default/variables.tf b/terraform/litellm/gcp/examples/default/variables.tf index 56e5ec88ef8..88b57ce27eb 100644 --- a/terraform/litellm/gcp/examples/default/variables.tf +++ b/terraform/litellm/gcp/examples/default/variables.tf @@ -26,6 +26,30 @@ variable "env" { type = string } +variable "create_runtime" { + description = "Create Cloud Run and load balancer resources." + type = bool + default = true +} + +variable "network_id" { + description = "Existing VPC network resource ID. Empty creates a VPC." + type = string + default = "" +} + +variable "create_psa_connection" { + description = "Create Private Services Access resources." + type = bool + default = true +} + +variable "redis_transit_encryption" { + description = "Enable Memorystore transit encryption." + type = bool + default = true +} + # Sensitive — prefer TF_VAR_litellm_master_key / TF_VAR_litellm_license / # TF_VAR_ui_password so values stay out of any committed tfvars file. variable "litellm_master_key" { diff --git a/terraform/litellm/gcp/iam.tf b/terraform/litellm/gcp/iam.tf index 09df5e7dff0..509e6d48ffd 100644 --- a/terraform/litellm/gcp/iam.tf +++ b/terraform/litellm/gcp/iam.tf @@ -6,6 +6,15 @@ resource "google_service_account" "runtime" { account_id = "${local.name}-runtime" display_name = "LiteLLM Cloud Run runtime" + + lifecycle { + precondition { + condition = !var.create_runtime || var.billing_metrics_endpoint == "" || ( + var.billing_metrics_client_cert_pem != "" && var.billing_metrics_client_key_pem != "" + ) + error_message = "billing_metrics_client_cert_pem and billing_metrics_client_key_pem are both required when billing_metrics_endpoint is set and create_runtime is true." + } + } } # UI runtime SA — no role bindings. The UI is static nginx with no DB, @@ -14,6 +23,8 @@ resource "google_service_account" "runtime" { # project's serverless service agent (not this SA), so it doesn't need # artifactregistry.reader either. resource "google_service_account" "ui_runtime" { + count = var.create_runtime ? 1 : 0 + account_id = "${local.name}-ui-runtime" display_name = "LiteLLM Cloud Run UI runtime (no data-plane access)" } diff --git a/terraform/litellm/gcp/load_balancer.tf b/terraform/litellm/gcp/load_balancer.tf index 11f30d0f944..57e8af8210f 100644 --- a/terraform/litellm/gcp/load_balancer.tf +++ b/terraform/litellm/gcp/load_balancer.tf @@ -14,77 +14,93 @@ locals { } resource "google_compute_global_address" "lb" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-lb-ip" labels = local.labels } # Serverless NEGs — one per Cloud Run service. resource "google_compute_region_network_endpoint_group" "gateway" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-gateway-neg" region = var.region network_endpoint_type = "SERVERLESS" cloud_run { - service = google_cloud_run_v2_service.gateway.name + service = google_cloud_run_v2_service.gateway[0].name } } resource "google_compute_region_network_endpoint_group" "backend" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-backend-neg" region = var.region network_endpoint_type = "SERVERLESS" cloud_run { - service = google_cloud_run_v2_service.backend.name + service = google_cloud_run_v2_service.backend[0].name } } resource "google_compute_region_network_endpoint_group" "ui" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-ui-neg" region = var.region network_endpoint_type = "SERVERLESS" cloud_run { - service = google_cloud_run_v2_service.ui.name + service = google_cloud_run_v2_service.ui[0].name } } # Backend services wrap each NEG. resource "google_compute_backend_service" "gateway" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-gateway-bs" protocol = "HTTP" load_balancing_scheme = "EXTERNAL_MANAGED" backend { - group = google_compute_region_network_endpoint_group.gateway.id + group = google_compute_region_network_endpoint_group.gateway[0].id } } resource "google_compute_backend_service" "backend" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-backend-bs" protocol = "HTTP" load_balancing_scheme = "EXTERNAL_MANAGED" backend { - group = google_compute_region_network_endpoint_group.backend.id + group = google_compute_region_network_endpoint_group.backend[0].id } } resource "google_compute_backend_service" "ui" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-ui-bs" protocol = "HTTP" load_balancing_scheme = "EXTERNAL_MANAGED" backend { - group = google_compute_region_network_endpoint_group.ui.id + group = google_compute_region_network_endpoint_group.ui[0].id } } # URL map. Default → backend (management API). Path matchers route the # gateway and UI prefixes elsewhere. resource "google_compute_url_map" "this" { + count = var.create_runtime ? 1 : 0 + name = local.name - default_service = google_compute_backend_service.backend.id + default_service = google_compute_backend_service.backend[0].id host_rule { hosts = ["*"] @@ -93,13 +109,13 @@ resource "google_compute_url_map" "this" { path_matcher { name = "main" - default_service = google_compute_backend_service.backend.id + default_service = google_compute_backend_service.backend[0].id # UI paths (catch them before any /v1/* gateway rules so /favicon.ico # and / take precedence). path_rule { paths = local.ui_path_prefixes - service = google_compute_backend_service.ui.id + service = google_compute_backend_service.ui[0].id } # Gateway path prefixes. GCP URL maps cap a path_rule at 10 path globs, @@ -108,7 +124,7 @@ resource "google_compute_url_map" "this" { for_each = { for idx, chunk in chunklist(local.gateway_path_prefixes, 10) : idx => chunk } content { paths = path_rule.value - service = google_compute_backend_service.gateway.id + service = google_compute_backend_service.gateway[0].id } } } @@ -118,7 +134,7 @@ resource "google_compute_url_map" "this" { # target proxy when TLS is enabled; otherwise the regular path-routing # URL map is attached to the HTTP proxy and everything stays plaintext. resource "google_compute_url_map" "https_redirect" { - count = local.tls_enabled ? 1 : 0 + count = var.create_runtime && local.tls_enabled ? 1 : 0 name = "${local.name}-redirect" default_url_redirect { @@ -129,8 +145,10 @@ resource "google_compute_url_map" "https_redirect" { } resource "google_compute_target_http_proxy" "this" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-http" - url_map = local.tls_enabled ? google_compute_url_map.https_redirect[0].id : google_compute_url_map.this.id + url_map = local.tls_enabled ? google_compute_url_map.https_redirect[0].id : google_compute_url_map.this[0].id # Default-deny on the HTTP-only path: TLS is the supported posture. # Operators must either supply DNS names or explicitly opt in. @@ -143,12 +161,14 @@ resource "google_compute_target_http_proxy" "this" { } resource "google_compute_global_forwarding_rule" "http" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-http" ip_protocol = "TCP" port_range = "80" load_balancing_scheme = "EXTERNAL_MANAGED" - ip_address = google_compute_global_address.lb.address - target = google_compute_target_http_proxy.this.id + ip_address = google_compute_global_address.lb[0].address + target = google_compute_target_http_proxy.this[0].id labels = local.labels } @@ -161,7 +181,7 @@ resource "google_compute_global_forwarding_rule" "http" { # transitions to ACTIVE. resource "google_compute_managed_ssl_certificate" "this" { - count = local.tls_enabled ? 1 : 0 + count = var.create_runtime && local.tls_enabled ? 1 : 0 # A managed cert's `domains` is immutable, so changing var.lb_domains # forces replacement, and the cert is referenced by the HTTPS target @@ -181,19 +201,19 @@ resource "google_compute_managed_ssl_certificate" "this" { } resource "google_compute_target_https_proxy" "this" { - count = local.tls_enabled ? 1 : 0 + count = var.create_runtime && local.tls_enabled ? 1 : 0 name = "${local.name}-https" - url_map = google_compute_url_map.this.id + url_map = google_compute_url_map.this[0].id ssl_certificates = [google_compute_managed_ssl_certificate.this[0].id] } resource "google_compute_global_forwarding_rule" "https" { - count = local.tls_enabled ? 1 : 0 + count = var.create_runtime && local.tls_enabled ? 1 : 0 name = "${local.name}-https" ip_protocol = "TCP" port_range = "443" load_balancing_scheme = "EXTERNAL_MANAGED" - ip_address = google_compute_global_address.lb.address + ip_address = google_compute_global_address.lb[0].address target = google_compute_target_https_proxy.this[0].id labels = local.labels } diff --git a/terraform/litellm/gcp/locals.tf b/terraform/litellm/gcp/locals.tf index 9a817eba605..3861413d496 100644 --- a/terraform/litellm/gcp/locals.tf +++ b/terraform/litellm/gcp/locals.tf @@ -21,6 +21,9 @@ locals { var.labels, ) + create_network = var.network_id == "" + network_id = local.create_network ? google_compute_network.this[0].id : var.network_id + gateway_path_prefixes = [ "/v1/chat/*", "/chat/*", "/v1/completions*", "/completions*", @@ -74,7 +77,7 @@ locals { "/ui/*", ] - proxy_config_enabled = length(keys(var.proxy_config)) > 0 + proxy_config_enabled = var.create_runtime && length(keys(var.proxy_config)) > 0 proxy_config_yaml = local.proxy_config_enabled ? yamlencode(var.proxy_config) : "" proxy_config_mount_path = "/etc/litellm" diff --git a/terraform/litellm/gcp/network.tf b/terraform/litellm/gcp/network.tf index a1ccaed02f9..47c7bf94a2b 100644 --- a/terraform/litellm/gcp/network.tf +++ b/terraform/litellm/gcp/network.tf @@ -1,13 +1,17 @@ resource "google_compute_network" "this" { + count = local.create_network ? 1 : 0 + name = local.name auto_create_subnetworks = false routing_mode = "REGIONAL" } resource "google_compute_subnetwork" "this" { + count = local.create_network ? 1 : 0 + name = "${local.name}-${var.region}" region = var.region - network = google_compute_network.this.id + network = google_compute_network.this[0].id ip_cidr_range = var.subnet_cidr private_ip_google_access = true } @@ -16,17 +20,21 @@ resource "google_compute_subnetwork" "this" { # managed services peer with the VPC over the connection below using # addresses from this range. resource "google_compute_global_address" "psa" { + count = var.create_psa_connection ? 1 : 0 + name = "${local.name}-psa" purpose = "VPC_PEERING" address_type = "INTERNAL" prefix_length = 16 - network = google_compute_network.this.id + network = local.network_id } resource "google_service_networking_connection" "psa" { - network = google_compute_network.this.id + count = var.create_psa_connection ? 1 : 0 + + network = local.network_id service = "servicenetworking.googleapis.com" - reserved_peering_ranges = [google_compute_global_address.psa.name] + reserved_peering_ranges = [google_compute_global_address.psa[0].name] } # Serverless VPC Access connector — required so Cloud Run can reach @@ -37,9 +45,11 @@ resource "google_service_networking_connection" "psa" { # for low-to-moderate Cloud Run egress; bump max if your services push # heavy private-network traffic. resource "google_vpc_access_connector" "this" { + count = var.create_runtime ? 1 : 0 + name = "${local.name}-conn" region = var.region - network = google_compute_network.this.name + network = local.network_id ip_cidr_range = var.vpc_connector_cidr min_instances = 2 max_instances = 3 diff --git a/terraform/litellm/gcp/outputs.tf b/terraform/litellm/gcp/outputs.tf index 6f1f1d5ccf4..2a4742f42cf 100644 --- a/terraform/litellm/gcp/outputs.tf +++ b/terraform/litellm/gcp/outputs.tf @@ -1,26 +1,26 @@ output "lb_ip" { - description = "Global anycast IP of the external HTTPS load balancer." - value = google_compute_global_address.lb.address + description = "Global anycast IP of the external HTTPS load balancer. Null when create_runtime is false." + value = var.create_runtime ? one(google_compute_global_address.lb[*].address) : null } output "lb_url" { - description = "Proxy URL. Switches scheme based on whether lb_domains is set; when TLS is enabled the URL points at the first listed domain (since managed certs are tied to the hostname, not the anycast IP). The dashboard is served at /, the API at /v1/*." - value = local.tls_enabled ? "https://${var.lb_domains[0]}" : "http://${google_compute_global_address.lb.address}" + description = "Proxy URL, or null when create_runtime is false. Switches scheme based on whether lb_domains is set." + value = var.create_runtime ? (local.tls_enabled ? "https://${var.lb_domains[0]}" : "http://${one(google_compute_global_address.lb[*].address)}") : null } output "gateway_service_url" { - description = "Default Cloud Run URL for the gateway (bypasses the LB)." - value = google_cloud_run_v2_service.gateway.uri + description = "Default Cloud Run URL for the gateway, or null when create_runtime is false." + value = var.create_runtime ? one(google_cloud_run_v2_service.gateway[*].uri) : null } output "backend_service_url" { - description = "Default Cloud Run URL for the backend (bypasses the LB)." - value = google_cloud_run_v2_service.backend.uri + description = "Default Cloud Run URL for the backend, or null when create_runtime is false." + value = var.create_runtime ? one(google_cloud_run_v2_service.backend[*].uri) : null } output "ui_service_url" { - description = "Default Cloud Run URL for the UI (bypasses the LB)." - value = google_cloud_run_v2_service.ui.uri + description = "Default Cloud Run URL for the UI, or null when create_runtime is false." + value = var.create_runtime ? one(google_cloud_run_v2_service.ui[*].uri) : null } output "cloudsql_writer_ip" { @@ -38,6 +38,36 @@ output "redis_endpoint" { value = "${google_redis_instance.this.host}:${google_redis_instance.this.port}" } +output "runtime_service_account_email" { + description = "Runtime service account email for Cloud Run or GKE Workload Identity." + value = google_service_account.runtime.email +} + +output "redis_host" { + description = "Memorystore Redis host." + value = google_redis_instance.this.host +} + +output "redis_port" { + description = "Memorystore Redis port." + value = google_redis_instance.this.port +} + +output "redis_server_ca_pem" { + description = "Memorystore server CA PEM. Mount it in the pod and set REDIS_SSL=true and REDIS_SSL_CA_CERTS= via extraEnv when transit encryption is enabled." + value = var.redis_transit_encryption ? google_redis_instance.this.server_ca_certs[0].cert : null +} + +output "db_username" { + description = "Cloud SQL application username." + value = var.db_username +} + +output "db_name" { + description = "Cloud SQL database name." + value = var.db_name +} + output "gcs_bucket" { description = "GCS bucket name. Exposed to gateway + backend as GCS_BUCKET_NAME. Reference from proxy_config via `os.environ/GCS_BUCKET_NAME`." value = google_storage_bucket.this.name @@ -54,11 +84,11 @@ output "db_password_secret_id" { } output "migration_run_command" { - description = "Shell command that executes the one-off migration job against Cloud SQL. Run this once after the first apply." - value = format( + description = "Shell command that executes the one-off migration job against Cloud SQL, or null when create_runtime is false." + value = var.create_runtime ? format( "gcloud run jobs execute %s --region %s --project %s --wait", - google_cloud_run_v2_job.migrations.name, + one(google_cloud_run_v2_job.migrations[*].name), var.region, var.project_id, - ) + ) : null } diff --git a/terraform/litellm/gcp/redis.tf b/terraform/litellm/gcp/redis.tf index 0e07c416e85..0602758f090 100644 --- a/terraform/litellm/gcp/redis.tf +++ b/terraform/litellm/gcp/redis.tf @@ -4,7 +4,7 @@ resource "google_redis_instance" "this" { memory_size_gb = var.redis_memory_size_gb region = var.region - authorized_network = google_compute_network.this.id + authorized_network = local.network_id connect_mode = "PRIVATE_SERVICE_ACCESS" redis_version = "REDIS_7_0" @@ -16,7 +16,7 @@ resource "google_redis_instance" "this" { # and passed to the proxy as REDIS_CA_PEM_B64); the proxy decodes it to # /tmp/redis-ca.pem at startup and uses it to validate the rediss:// # handshake. Mirrors `transit_encryption_enabled = true` on AWS. - transit_encryption_mode = "SERVER_AUTHENTICATION" + transit_encryption_mode = var.redis_transit_encryption ? "SERVER_AUTHENTICATION" : "DISABLED" depends_on = [google_service_networking_connection.psa] } diff --git a/terraform/litellm/gcp/tests/deps_only.tftest.hcl b/terraform/litellm/gcp/tests/deps_only.tftest.hcl new file mode 100644 index 00000000000..610c49d5b52 --- /dev/null +++ b/terraform/litellm/gcp/tests/deps_only.tftest.hcl @@ -0,0 +1,175 @@ +mock_provider "google" { + mock_resource "google_redis_instance" { + defaults = { + host = "10.0.0.4" + port = 6379 + server_ca_certs = [{ + cert = "-----BEGIN CERTIFICATE-----\nmock\n-----END CERTIFICATE-----" + }] + } + } +} + +mock_provider "google-beta" {} +mock_provider "random" {} + +variables { + project_id = "test-project" + tenant = "tenant" + env = "test" + allow_plaintext_lb = true + image_registry = "us-central1-docker.pkg.dev/test-project/litellm" +} + +run "default_creates_everything" { + command = plan + + assert { + condition = alltrue([ + length(google_compute_network.this) == 1, + length(google_compute_subnetwork.this) == 1, + length(google_compute_global_address.psa) == 1, + length(google_service_networking_connection.psa) == 1, + length(google_vpc_access_connector.this) == 1, + length(google_cloud_run_v2_service.gateway) == 1, + length(google_cloud_run_v2_service.backend) == 1, + length(google_cloud_run_v2_service.ui) == 1, + length(google_cloud_run_v2_job.migrations) == 1, + length(google_compute_global_address.lb) == 1, + length(terraform_data.migration) == 1, + ]) + error_message = "The default mode must create networking, runtime services, the load balancer, and migrations." + } + + assert { + condition = google_redis_instance.this.transit_encryption_mode == "SERVER_AUTHENTICATION" + error_message = "Redis transit encryption must remain enabled by default." + } + + assert { + condition = length(local.shared_env_kv) == 12 + error_message = "The default runtime environment must include GCS and the three Redis TLS entries." + } +} + +run "deps_only_creates_no_runtime" { + command = plan + + variables { + create_runtime = false + proxy_config = { + model_list = [] + } + } + + assert { + condition = alltrue([ + length(google_cloud_run_v2_service.gateway) == 0, + length(google_cloud_run_v2_service.backend) == 0, + length(google_cloud_run_v2_service.ui) == 0, + length(google_cloud_run_v2_job.migrations) == 0, + length(google_cloud_run_v2_service_iam_member.gateway_allusers) == 0, + length(google_cloud_run_v2_service_iam_member.backend_allusers) == 0, + length(google_cloud_run_v2_service_iam_member.ui_allusers) == 0, + length(google_compute_global_address.lb) == 0, + length(google_compute_region_network_endpoint_group.gateway) == 0, + length(google_compute_region_network_endpoint_group.backend) == 0, + length(google_compute_region_network_endpoint_group.ui) == 0, + length(google_compute_backend_service.gateway) == 0, + length(google_compute_backend_service.backend) == 0, + length(google_compute_backend_service.ui) == 0, + length(google_compute_url_map.this) == 0, + length(google_compute_url_map.https_redirect) == 0, + length(google_compute_target_http_proxy.this) == 0, + length(google_compute_global_forwarding_rule.http) == 0, + length(google_compute_managed_ssl_certificate.this) == 0, + length(google_compute_target_https_proxy.this) == 0, + length(google_compute_global_forwarding_rule.https) == 0, + length(terraform_data.migration) == 0, + length(google_vpc_access_connector.this) == 0, + length(google_service_account.ui_runtime) == 0, + length(google_storage_bucket.proxy_config) == 0, + ]) + error_message = "Dependencies-only mode must omit all runtime, load balancer, connector, UI identity, and proxy config resources." + } + + assert { + condition = alltrue([ + google_sql_database_instance.writer.name == "tenant-litellm-test", + google_sql_database_instance.reader.name == "tenant-litellm-test-reader", + google_redis_instance.this.name == "tenant-litellm-test", + google_storage_bucket.this.force_destroy == false, + google_secret_manager_secret.master_key.secret_id == "tenant-litellm-test-master-key", + google_secret_manager_secret.db_password.secret_id == "tenant-litellm-test-db-password", + google_service_account.runtime.account_id == "tenant-litellm-test-runtime", + ]) + error_message = "Dependencies-only mode must retain data stores, secrets, and the runtime service account." + } + + assert { + condition = output.lb_url == null && output.migration_run_command == null + error_message = "Runtime outputs must be null while dependency outputs remain available." + } +} + +run "existing_network_attaches_data_stores" { + command = plan + + variables { + network_id = "projects/host-proj/global/networks/shared" + create_psa_connection = false + create_runtime = false + } + + assert { + condition = alltrue([ + length(google_compute_network.this) == 0, + length(google_compute_subnetwork.this) == 0, + length(google_compute_global_address.psa) == 0, + length(google_service_networking_connection.psa) == 0, + google_sql_database_instance.writer.settings[0].ip_configuration[0].private_network == var.network_id, + google_redis_instance.this.authorized_network == var.network_id, + ]) + error_message = "An existing VPC must receive the Cloud SQL and Memorystore private-network attachments." + } +} + +run "psa_required_without_existing_network" { + command = plan + + variables { + create_psa_connection = false + } + + expect_failures = [ + google_sql_database_instance.writer, + ] +} + +run "redis_plaintext_drops_tls_env" { + command = plan + + variables { + redis_transit_encryption = false + } + + assert { + condition = google_redis_instance.this.transit_encryption_mode == "DISABLED" + error_message = "Redis transit encryption must be disabled when requested." + } + + assert { + condition = length(local.shared_env_kv) == 9 + error_message = "Plaintext Redis mode must include GCS and omit the three Redis TLS entries." + } + + assert { + condition = length([for env in local.shared_env_kv : env if env.name == "REDIS_SSL"]) == 0 + error_message = "Plaintext Redis mode must not set REDIS_SSL." + } + + assert { + condition = length(local.redis_ca_fragment) == 0 + error_message = "Plaintext Redis mode must not decode a Redis CA at startup." + } +} diff --git a/terraform/litellm/gcp/variables.tf b/terraform/litellm/gcp/variables.tf index 1162e100bb2..9c68ed3db76 100644 --- a/terraform/litellm/gcp/variables.tf +++ b/terraform/litellm/gcp/variables.tf @@ -79,16 +79,42 @@ variable "ui_password" { sensitive = true } +# ---------- Deployment mode ---------- + +variable "create_runtime" { + description = "Create Cloud Run, load balancer, VPC connector, runtime support resources, and the migration job. Set false for GKE or another external runtime." + type = bool + default = true +} + +variable "network_id" { + description = "Existing VPC network resource ID (`projects//global/networks/`). When set, no VPC or subnet is created. A VPC connector requires this network to be in the deployment project when create_runtime is true." + type = string + default = "" +} + +variable "create_psa_connection" { + description = "Create the Private Services Access range and connection for Cloud SQL and Memorystore. Set false when the existing network already has PSA configured." + type = bool + default = true +} + +variable "redis_transit_encryption" { + description = "Enable Memorystore transit encryption and inject Redis TLS settings into Cloud Run. Set false to use plaintext Redis." + type = bool + default = true +} + # ---------- Networking ---------- variable "subnet_cidr" { - description = "Primary CIDR block for the LiteLLM subnet." + description = "Primary CIDR block for the LiteLLM subnet. Unused when network_id is set." type = string default = "10.40.0.0/16" } variable "vpc_connector_cidr" { - description = "CIDR for the Serverless VPC Access connector. /28 required." + description = "CIDR for the Serverless VPC Access connector. /28 required. Unused when create_runtime is false." type = string default = "10.41.0.0/28" }