Files
coder/coderd/templatebuilder/testdata/gcp-linux.tf.golden
T
Jeremy Ruppel 581f906947 fix(coderd): declare project_id variable in GCP template builder bases (#27015)
## Summary

GCP base templates (`gcp-linux`, `gcp-windows`) in the Template Builder
had a Terraform `variable "project_id"` with no default, but their
`base.json` manifests didn't declare it. The UI never prompted for it,
so the provisioner import always failed with:

```
required template variables need values: project_id
```

## Changes

- Add `project_id` as a required variable in both GCP `base.json`
manifests
- Convert templates from raw Terraform variable blocks to Go template
injection (`{{ .Variables.project_id }}`), matching the existing
kubernetes pattern
- Fix `DefaultBaseRenderContext` to supply a `"REQUIRED"` placeholder
for required variables without defaults (previously rendered as `<no
value>`)
- Replace duplicate test subtests with proper GCP coverage including a
missing-variable error case

<details>
<summary>Implementation plan</summary>

### Root cause

The GCP base templates contained `variable "project_id" {}` (no default
= required) in their `.tf.tmpl` files, but the `base.json` manifests had
an empty `variables` array. The Template Builder UI
(`BaseTemplateParametersStep`) is data-driven from `base.json`, so it
never showed a field for `project_id`. The composed Terraform output
still contained the required variable, causing the provisioner import to
fail.

### Fix approach

Follow the pattern established by the kubernetes base template:
1. Declare variables in `base.json` so the UI prompts for them
2. Use Go template syntax (`{{ .Variables.project_id }}`) to inject
values at compose time
3. Remove raw Terraform `variable` blocks from the template since the
value is now baked in

### Files changed

| File | Change |
|---|---|
| `bases/gcp-linux/base.json` | Added `project_id` as a required
variable |
| `bases/gcp-windows/base.json` | Added `project_id` as a required
variable |
| `bases/gcp-linux/main.tf.tmpl` | Removed Terraform variable block, use
Go template injection |
| `bases/gcp-windows/main.tf.tmpl` | Same |
| `bases.go` | `DefaultBaseRenderContext` supplies placeholder for
required vars without defaults |
| `compose_test.go` | Replaced duplicate subtests with proper GCP tests
|
| `templatebuilder_handler_test.go` | Updated `gcp-windows` spec to
expect `project_id` variable |
| Golden files | Regenerated |

</details>

> 🤖 Generated by Coder Agents on behalf of @jeremyruppel
2026-07-06 16:48:00 -04:00

154 lines
3.9 KiB
Plaintext

terraform {
required_providers {
coder = {
source = "coder/coder"
}
google = {
source = "hashicorp/google"
}
}
}
provider "coder" {}
variable "project_id" {
description = "Which Google Compute Project should your workspace live in?"
default = "test-project_id"
}
# See https://registry.coder.com/modules/coder/gcp-region
module "gcp_region" {
source = "registry.coder.com/coder/gcp-region/coder"
# This ensures that the latest non-breaking version of the module gets downloaded, you can also pin the module version to prevent breaking changes in production.
version = "~> 1.0"
regions = ["us", "europe"]
default = "us-central1-a"
}
provider "google" {
zone = module.gcp_region.value
project = var.project_id
}
data "google_compute_default_service_account" "default" {}
data "coder_workspace" "me" {}
data "coder_workspace_owner" "me" {}
resource "google_compute_disk" "root" {
name = "coder-${data.coder_workspace.me.id}-root"
type = "pd-ssd"
zone = module.gcp_region.value
image = "debian-cloud/debian-11"
lifecycle {
ignore_changes = [name, image]
}
}
resource "coder_agent" "main" {
auth = "google-instance-identity"
arch = "amd64"
os = "linux"
startup_script = <<-EOT
set -e
# Add any commands that should be executed at workspace startup (e.g install requirements, start a program, etc) here
EOT
metadata {
key = "cpu"
display_name = "CPU Usage"
interval = 5
timeout = 5
script = <<-EOT
#!/bin/bash
set -e
top -bn1 | grep "Cpu(s)" | awk '{print $2 + $4 "%"}'
EOT
}
metadata {
key = "memory"
display_name = "Memory Usage"
interval = 5
timeout = 5
script = <<-EOT
#!/bin/bash
set -e
free -m | awk 'NR==2{printf "%.2f%%\t", $3*100/$2 }'
EOT
}
metadata {
key = "disk"
display_name = "Disk Usage"
interval = 600 # every 10 minutes
timeout = 30 # df can take a while on large filesystems
script = <<-EOT
#!/bin/bash
set -e
df /home/coder | awk '$NF=="/"{printf "%s", $5}'
EOT
}
}
resource "google_compute_instance" "dev" {
zone = module.gcp_region.value
count = data.coder_workspace.me.start_count
name = "coder-${lower(data.coder_workspace_owner.me.name)}-${lower(data.coder_workspace.me.name)}-root"
machine_type = "e2-medium"
network_interface {
network = "default"
access_config {
// Ephemeral public IP
}
}
boot_disk {
auto_delete = false
source = google_compute_disk.root.name
}
service_account {
email = data.google_compute_default_service_account.default.email
scopes = ["cloud-platform"]
}
# The startup script runs as root with no $HOME environment set up, so instead of directly
# running the agent init script, create a user (with a homedir, default shell and sudo
# permissions) and execute the init script as that user.
metadata_startup_script = <<EOMETA
#!/usr/bin/env sh
set -eux
# If user does not exist, create it and set up passwordless sudo
if ! id -u "${local.linux_user}" >/dev/null 2>&1; then
useradd -m -s /bin/bash "${local.linux_user}"
echo "${local.linux_user} ALL=(ALL) NOPASSWD:ALL" > /etc/sudoers.d/coder-user
fi
exec sudo -u "${local.linux_user}" sh -c '${coder_agent.main.init_script}'
EOMETA
}
locals {
# Ensure Coder username is a valid Linux username
linux_user = lower(substr(data.coder_workspace_owner.me.name, 0, 32))
}
resource "coder_metadata" "workspace_info" {
count = data.coder_workspace.me.start_count
resource_id = google_compute_instance.dev[0].id
item {
key = "type"
value = google_compute_instance.dev[0].machine_type
}
}
resource "coder_metadata" "home_info" {
resource_id = google_compute_disk.root.id
item {
key = "size"
value = "${google_compute_disk.root.size} GiB"
}
}