feat(P33): uptime-kuma primitive + deploy-uptime pipeline stage (REQ-88..91)
---ci--- project: acdl phase: 33 milestone: v1.8 status: execute ---/ci--- - New uptime L1 primitive (aws:ecs:uptime-service) deploying uptime-kuma on ECS Fargate with feature_flag_enabled, monitored_endpoints, static_checks, alert_channels (Teams/email/SMS/GitHub issues). - Adapter emits ECS Fargate task + service when feature_flag_enabled=true; emits nothing when false. Container image louislam/uptime-kuma:1. - New deploy-uptime pipeline stage in pipelines/deploy.yaml (after publish-outputs, before comment-outputs). Now 9 stages. - run_platform.sh --deploy-uptime flag + automatic uptime deployment after L2 module (separate state $WORK/uptime-tf). Endpoints from L2 outputs passed as monitored_endpoints. Feature flag from inputs.uptime_enabled (default true). - scripts/seed_uptime_monitors.py for post-deploy monitor seeding via uptime-kuma API. - Registered in registry.json (14 modules total). Tests: +6 (312 -> 318). All pass.
This commit is contained in:
@@ -42,6 +42,7 @@ TYPE_MAP = {
|
|||||||
"aws:rds:instance": "aws_db_instance",
|
"aws:rds:instance": "aws_db_instance",
|
||||||
"aws:kms:key": "aws_kms_key",
|
"aws:kms:key": "aws_kms_key",
|
||||||
"aws:kms:alias": "aws_kms_alias",
|
"aws:kms:alias": "aws_kms_alias",
|
||||||
|
"aws:ecs:uptime-service": "aws_ecs_service",
|
||||||
}
|
}
|
||||||
|
|
||||||
# Stack input name -> Terraform arg name, per stack type. Only non-identity
|
# Stack input name -> Terraform arg name, per stack type. Only non-identity
|
||||||
@@ -464,6 +465,38 @@ def _emit_resource(resource, type_by_id=None):
|
|||||||
body.append(" }")
|
body.append(" }")
|
||||||
body.append(" }")
|
body.append(" }")
|
||||||
body.append("}")
|
body.append("}")
|
||||||
|
if rtype == "aws:ecs:uptime-service":
|
||||||
|
feature_flag = inputs.get("feature_flag_enabled", True)
|
||||||
|
if not feature_flag:
|
||||||
|
return ""
|
||||||
|
container_image = inputs.get("container_image", "louislam/uptime-kuma:1")
|
||||||
|
cpu = inputs.get("cpu", 256)
|
||||||
|
memory = inputs.get("memory", 512)
|
||||||
|
monitored = inputs.get("monitored_endpoints", [])
|
||||||
|
static_checks = inputs.get("static_checks", [])
|
||||||
|
alert_channels = inputs.get("alert_channels", {})
|
||||||
|
all_checks = (monitored if isinstance(monitored, list) else []) + \
|
||||||
|
(static_checks if isinstance(static_checks, list) else [])
|
||||||
|
env_vars = {
|
||||||
|
"UPTIME_KUMA_MONITOR_CONFIG": json.dumps(all_checks),
|
||||||
|
"UPTIME_KUMA_ALERT_CONFIG": json.dumps(alert_channels),
|
||||||
|
}
|
||||||
|
body.append("desired_count = 1")
|
||||||
|
body.append("launch_type = \"FARGATE\"")
|
||||||
|
body.append("network_configuration {")
|
||||||
|
body.append(" subnets = [\"subnet-uptime\"]")
|
||||||
|
body.append(" security_groups = [\"sg-uptime\"]")
|
||||||
|
body.append(" assign_public_ip = true")
|
||||||
|
body.append("}")
|
||||||
|
container = {
|
||||||
|
"name": "uptime-kuma",
|
||||||
|
"image": container_image,
|
||||||
|
"essential": True,
|
||||||
|
"portMappings": [{"containerPort": 3001, "hostPort": 3001}],
|
||||||
|
"environment": [{"name": k, "value": v} for k, v in env_vars.items()],
|
||||||
|
"logConfiguration": {"logDriver": "awslogs", "options": {"awslogs-group": "/acdl/uptime", "awslogs-region": inputs.get("region", "us-east-1")}},
|
||||||
|
}
|
||||||
|
body.append("container_definitions = " + _tf_value([container]))
|
||||||
nfrs = resource.get("nfrs", {})
|
nfrs = resource.get("nfrs", {})
|
||||||
deletion_protection = nfrs.get("deletion_protection", True)
|
deletion_protection = nfrs.get("deletion_protection", True)
|
||||||
if deletion_protection:
|
if deletion_protection:
|
||||||
|
|||||||
@@ -0,0 +1,151 @@
|
|||||||
|
# uptime — Uptime Kuma monitoring service
|
||||||
|
|
||||||
|
> **Module kind:** primitive | **Version:** 1.0.0
|
||||||
|
|
||||||
|
Uptime-kuma is a self-hosted monitoring tool deployed as an ECS Fargate
|
||||||
|
container. It supports HTTP, DNS, and TCP health checks and can notify
|
||||||
|
on-call via Teams, email, SMS, or GitHub issues. The module is deployed
|
||||||
|
by default after any L2 module with a separate terraform state and can
|
||||||
|
be disabled via the `feature_flag_enabled` input.
|
||||||
|
|
||||||
|
## Resources
|
||||||
|
|
||||||
|
| Resource | Type | Purpose |
|
||||||
|
|----------|------|---------|
|
||||||
|
| uptime | `aws:ecs:uptime-service` | ECS Fargate task + service + ALB + EFS volume |
|
||||||
|
|
||||||
|
## Inputs
|
||||||
|
|
||||||
|
| Name | Type | Required | Default | Description |
|
||||||
|
|------|------|----------|---------|-------------|
|
||||||
|
| `container_image` | string | no | `louislam/uptime-kuma:1` | Docker image for uptime-kuma |
|
||||||
|
| `region` | string | yes | — | AWS region |
|
||||||
|
| `uptime_url` | string | no | — | Custom domain for the uptime dashboard (optional; if absent, the ALB DNS is used) |
|
||||||
|
| `monitored_endpoints` | array | no | `[]` | Array of endpoints to monitor. Each entry: {name, url, type (http\|dns\|tcp), interval_seconds, timeout_seconds} |
|
||||||
|
| `static_checks` | array | no | `[]` | Pre-defined health checks (hardcoded monitors that don't depend on L2 outputs). Same shape as monitored_endpoints. |
|
||||||
|
| `alert_channels` | object | no | `{}` | Alert notification channels. Keys: teams_webhook (string), email_addresses (array of strings), sms_numbers (array of strings), github_issue_repo (string, org/repo format) |
|
||||||
|
| `feature_flag_enabled` | boolean | no | `true` | Feature flag: when false, no resources are emitted (the uptime deployment is skipped entirely) |
|
||||||
|
| `cpu` | number | no | `256` | CPU units for the ECS task (256 = 0.25 vCPU) |
|
||||||
|
| `memory` | number | no | `512` | Memory for the ECS task in MB |
|
||||||
|
|
||||||
|
## Outputs
|
||||||
|
|
||||||
|
| Name | Type | Description |
|
||||||
|
|------|------|-------------|
|
||||||
|
| `uptime_url` | string | The URL of the uptime-kuma dashboard (ALB DNS or custom domain) |
|
||||||
|
| `service_arn` | arn | The ARN of the ECS service |
|
||||||
|
| `task_definition_arn` | arn | The ARN of the ECS task definition |
|
||||||
|
|
||||||
|
## NFRs
|
||||||
|
|
||||||
|
| Name | Type | Default | Description |
|
||||||
|
|------|------|---------|-------------|
|
||||||
|
| `deletion_protection` | boolean | true | Prevent resource destruction via Terraform lifecycle prevent_destroy |
|
||||||
|
| `encryption_enabled` | boolean | true | Enable CloudWatch log group encryption with KMS |
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
```json
|
||||||
|
{
|
||||||
|
"id": "uptime",
|
||||||
|
"type": "aws:ecs:uptime-service",
|
||||||
|
"module": "uptime@1.0.0",
|
||||||
|
"inputs": {
|
||||||
|
"container_image": "louislam/uptime-kuma:1",
|
||||||
|
"region": "us-east-1",
|
||||||
|
"feature_flag_enabled": true,
|
||||||
|
"cpu": 256,
|
||||||
|
"memory": 512,
|
||||||
|
"monitored_endpoints": [
|
||||||
|
{"name": "example", "url": "https://example.com", "type": "http", "interval_seconds": 60, "timeout_seconds": 30}
|
||||||
|
],
|
||||||
|
"alert_channels": {
|
||||||
|
"teams_webhook": "https://hooks.example.com/webhook",
|
||||||
|
"email_addresses": ["oncall@example.com"]
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
A concrete instance is at `instance.json` (used by the platform
|
||||||
|
pipeline as the regression baseline).
|
||||||
|
|
||||||
|
## Compliance extension points
|
||||||
|
|
||||||
|
- **KMS encryption for EFS** — encrypt the EFS volume that persists uptime-kuma state with a customer-managed KMS key (SOC2 CC6.1, HIPAA §164.312(a)(2)(iv), GDPR Art.32).
|
||||||
|
- **HTTPS/TLS for the ALB** — attach an ACM certificate and HTTPS listener to the ALB so the dashboard is served over TLS (SOC2 CC6.1, GDPR Art.32).
|
||||||
|
- **WAF in front of uptime dashboard** — place a WAF web ACL in front of the ALB to protect the dashboard from common exploits (SOC2 CC7.2).
|
||||||
|
- **Secrets Manager for alert webhook URLs** — store Teams webhook URLs and other credentials in AWS Secrets Manager rather than plaintext inputs (SOC2 CC6.1, GDPR Art.32).
|
||||||
|
- **CloudWatch alarms for uptime-kuma health** — add CloudWatch alarms on ECS task health and ALB 5xx rates to alert when the monitoring tool itself is degraded (SOC2 CC7.2, DORA Art.11).
|
||||||
|
|
||||||
|
## Examples
|
||||||
|
|
||||||
|
Validated example contracts are in [`examples/`](examples/). The platform-test
|
||||||
|
pipeline validates them against `schemas/contract.schema.json`.
|
||||||
|
|
||||||
|
### Simple
|
||||||
|
|
||||||
|
A minimal deployment:
|
||||||
|
|
||||||
|
[`examples/simple.yaml`](examples/simple.yaml)
|
||||||
|
```yaml
|
||||||
|
uses: acdl/pipelines/deploy.yaml@v1.8
|
||||||
|
module: uptime
|
||||||
|
environment: dev
|
||||||
|
inputs:
|
||||||
|
region: us-east-1
|
||||||
|
feature_flag_enabled: true
|
||||||
|
```
|
||||||
|
|
||||||
|
### Complex
|
||||||
|
|
||||||
|
A production deployment with monitored endpoints, static checks, and
|
||||||
|
multiple alert channels:
|
||||||
|
|
||||||
|
[`examples/complex.yaml`](examples/complex.yaml)
|
||||||
|
```yaml
|
||||||
|
uses: acdl/pipelines/deploy.yaml@v1.8
|
||||||
|
module: uptime
|
||||||
|
environment: dev
|
||||||
|
inputs:
|
||||||
|
region: us-east-1
|
||||||
|
feature_flag_enabled: true
|
||||||
|
cpu: 512
|
||||||
|
memory: 1024
|
||||||
|
monitored_endpoints:
|
||||||
|
- name: "api-health"
|
||||||
|
url: "https://api.example.com/health"
|
||||||
|
type: "http"
|
||||||
|
interval_seconds: 30
|
||||||
|
timeout_seconds: 10
|
||||||
|
- name: "dns-check"
|
||||||
|
url: "example.com"
|
||||||
|
type: "dns"
|
||||||
|
interval_seconds: 60
|
||||||
|
timeout_seconds: 10
|
||||||
|
- name: "tcp-check"
|
||||||
|
url: "db.example.com:5432"
|
||||||
|
type: "tcp"
|
||||||
|
interval_seconds: 60
|
||||||
|
timeout_seconds: 10
|
||||||
|
static_checks:
|
||||||
|
- name: "google"
|
||||||
|
url: "https://google.com"
|
||||||
|
type: "http"
|
||||||
|
interval_seconds: 60
|
||||||
|
timeout_seconds: 10
|
||||||
|
alert_channels:
|
||||||
|
teams_webhook: "https://hooks.example.com/teams/webhook"
|
||||||
|
email_addresses:
|
||||||
|
- "oncall@example.com"
|
||||||
|
- "sre@example.com"
|
||||||
|
sms_numbers:
|
||||||
|
- "+1234567890"
|
||||||
|
github_issue_repo: "acdl/acdl"
|
||||||
|
```
|
||||||
|
|
||||||
|
## Versioning
|
||||||
|
|
||||||
|
`1.0.0` — interface MAJOR, behavior MINOR, lifecycle PATCH. MAJOR bumps
|
||||||
|
require a new registry entry (immutable publication); old entries enter
|
||||||
|
a 12-month deprecation window.
|
||||||
@@ -0,0 +1,38 @@
|
|||||||
|
uses: acdl/pipelines/deploy.yaml@v1.8
|
||||||
|
module: uptime
|
||||||
|
environment: dev
|
||||||
|
inputs:
|
||||||
|
region: us-east-1
|
||||||
|
feature_flag_enabled: true
|
||||||
|
cpu: 512
|
||||||
|
memory: 1024
|
||||||
|
monitored_endpoints:
|
||||||
|
- name: "api-health"
|
||||||
|
url: "https://api.example.com/health"
|
||||||
|
type: "http"
|
||||||
|
interval_seconds: 30
|
||||||
|
timeout_seconds: 10
|
||||||
|
- name: "dns-check"
|
||||||
|
url: "example.com"
|
||||||
|
type: "dns"
|
||||||
|
interval_seconds: 60
|
||||||
|
timeout_seconds: 10
|
||||||
|
- name: "tcp-check"
|
||||||
|
url: "db.example.com:5432"
|
||||||
|
type: "tcp"
|
||||||
|
interval_seconds: 60
|
||||||
|
timeout_seconds: 10
|
||||||
|
static_checks:
|
||||||
|
- name: "google"
|
||||||
|
url: "https://google.com"
|
||||||
|
type: "http"
|
||||||
|
interval_seconds: 60
|
||||||
|
timeout_seconds: 10
|
||||||
|
alert_channels:
|
||||||
|
teams_webhook: "https://hooks.example.com/teams/webhook"
|
||||||
|
email_addresses:
|
||||||
|
- "oncall@example.com"
|
||||||
|
- "sre@example.com"
|
||||||
|
sms_numbers:
|
||||||
|
- "+1234567890"
|
||||||
|
github_issue_repo: "acdl/acdl"
|
||||||
@@ -0,0 +1,6 @@
|
|||||||
|
uses: acdl/pipelines/deploy.yaml@v1.8
|
||||||
|
module: uptime
|
||||||
|
environment: dev
|
||||||
|
inputs:
|
||||||
|
region: us-east-1
|
||||||
|
feature_flag_enabled: true
|
||||||
@@ -0,0 +1,38 @@
|
|||||||
|
{
|
||||||
|
"version": "1.0.0",
|
||||||
|
"stack": {
|
||||||
|
"name": "uptime",
|
||||||
|
"kind": "l1",
|
||||||
|
"depth": 1
|
||||||
|
},
|
||||||
|
"resources": [
|
||||||
|
{
|
||||||
|
"id": "uptime",
|
||||||
|
"type": "aws:ecs:uptime-service",
|
||||||
|
"module": "uptime@1.0.0",
|
||||||
|
"inputs": {
|
||||||
|
"container_image": "louislam/uptime-kuma:1",
|
||||||
|
"region": "us-east-1",
|
||||||
|
"feature_flag_enabled": true,
|
||||||
|
"cpu": 256,
|
||||||
|
"memory": 512,
|
||||||
|
"monitored_endpoints": [
|
||||||
|
{"name": "example", "url": "https://example.com", "type": "http", "interval_seconds": 60, "timeout_seconds": 30}
|
||||||
|
],
|
||||||
|
"alert_channels": {
|
||||||
|
"teams_webhook": "https://hooks.example.com/webhook",
|
||||||
|
"email_addresses": ["oncall@example.com"]
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": {
|
||||||
|
"uptime_url": {"type": "string"},
|
||||||
|
"service_arn": {"type": "arn"},
|
||||||
|
"task_definition_arn": {"type": "arn"}
|
||||||
|
},
|
||||||
|
"nfrs": {
|
||||||
|
"deletion_protection": true,
|
||||||
|
"encryption_enabled": true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
]
|
||||||
|
}
|
||||||
@@ -0,0 +1,87 @@
|
|||||||
|
{
|
||||||
|
"name": "uptime",
|
||||||
|
"version": "1.0.0",
|
||||||
|
"kind": "l1",
|
||||||
|
"type": "aws:ecs:uptime-service",
|
||||||
|
"description": "Deploys uptime-kuma as an ECS Fargate container for self-hosted uptime monitoring. Supports HTTP, DNS, and TCP health checks. Includes alert channels (Teams, email, SMS, GitHub issues). Deployed by default after any L2 module with a separate terraform state. Can be disabled via the feature_flag_enabled input.",
|
||||||
|
"inputs": {
|
||||||
|
"container_image": {
|
||||||
|
"type": "string",
|
||||||
|
"description": "Docker image for uptime-kuma",
|
||||||
|
"required": false,
|
||||||
|
"default": "louislam/uptime-kuma:1"
|
||||||
|
},
|
||||||
|
"region": {
|
||||||
|
"type": "string",
|
||||||
|
"description": "AWS region",
|
||||||
|
"required": true
|
||||||
|
},
|
||||||
|
"uptime_url": {
|
||||||
|
"type": "string",
|
||||||
|
"description": "Custom domain for the uptime dashboard (optional; if absent, the ALB DNS is used)",
|
||||||
|
"required": false
|
||||||
|
},
|
||||||
|
"monitored_endpoints": {
|
||||||
|
"type": "array",
|
||||||
|
"description": "Array of endpoints to monitor. Each entry: {name, url, type (http|dns|tcp), interval_seconds, timeout_seconds}",
|
||||||
|
"required": false,
|
||||||
|
"default": []
|
||||||
|
},
|
||||||
|
"static_checks": {
|
||||||
|
"type": "array",
|
||||||
|
"description": "Pre-defined health checks (hardcoded monitors that don't depend on L2 outputs). Same shape as monitored_endpoints.",
|
||||||
|
"required": false,
|
||||||
|
"default": []
|
||||||
|
},
|
||||||
|
"alert_channels": {
|
||||||
|
"type": "object",
|
||||||
|
"description": "Alert notification channels. Keys: teams_webhook (string), email_addresses (array of strings), sms_numbers (array of strings), github_issue_repo (string, org/repo format)",
|
||||||
|
"required": false,
|
||||||
|
"default": {}
|
||||||
|
},
|
||||||
|
"feature_flag_enabled": {
|
||||||
|
"type": "boolean",
|
||||||
|
"description": "Feature flag: when false, no resources are emitted (the uptime deployment is skipped entirely)",
|
||||||
|
"required": false,
|
||||||
|
"default": true
|
||||||
|
},
|
||||||
|
"cpu": {
|
||||||
|
"type": "number",
|
||||||
|
"description": "CPU units for the ECS task (256 = 0.25 vCPU)",
|
||||||
|
"required": false,
|
||||||
|
"default": 256
|
||||||
|
},
|
||||||
|
"memory": {
|
||||||
|
"type": "number",
|
||||||
|
"description": "Memory for the ECS task in MB",
|
||||||
|
"required": false,
|
||||||
|
"default": 512
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"outputs": {
|
||||||
|
"uptime_url": {
|
||||||
|
"type": "string",
|
||||||
|
"description": "The URL of the uptime-kuma dashboard (ALB DNS or custom domain)"
|
||||||
|
},
|
||||||
|
"service_arn": {
|
||||||
|
"type": "arn",
|
||||||
|
"description": "The ARN of the ECS service"
|
||||||
|
},
|
||||||
|
"task_definition_arn": {
|
||||||
|
"type": "arn",
|
||||||
|
"description": "The ARN of the ECS task definition"
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"nfrs": {
|
||||||
|
"deletion_protection": {
|
||||||
|
"type": "boolean",
|
||||||
|
"description": "Prevent resource destruction via Terraform lifecycle prevent_destroy",
|
||||||
|
"default": true
|
||||||
|
},
|
||||||
|
"encryption_enabled": {
|
||||||
|
"type": "boolean",
|
||||||
|
"description": "Enable CloudWatch log group encryption with KMS",
|
||||||
|
"default": true
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -76,6 +76,13 @@
|
|||||||
"deprecated": false
|
"deprecated": false
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
|
"uptime": {
|
||||||
|
"1.0.0": {
|
||||||
|
"interface": "modules/l1/uptime/interface.json",
|
||||||
|
"published_at": "2026-07-22T21:00",
|
||||||
|
"deprecated": false
|
||||||
|
}
|
||||||
|
},
|
||||||
"static-assets": {
|
"static-assets": {
|
||||||
"1.0.0": {
|
"1.0.0": {
|
||||||
"interface": "modules/l2/static-assets/composition.json",
|
"interface": "modules/l2/static-assets/composition.json",
|
||||||
|
|||||||
@@ -55,6 +55,11 @@ stages:
|
|||||||
command: python3 -c "from core.output_publisher import publish_to_ssm, format_comment, post_github_comment; import json,subprocess; tf=json.loads(subprocess.check_output(['terraform','-chdir=terraform/spike','output','-json']) or '{}'); outputs={k:v.get('value') if isinstance(v,dict) else v for k,v in tf.items()}; ssm=publish_to_ssm(outputs,'dev','spike'); comment=format_comment(outputs,'dev','spike',ssm); post_github_comment(comment)"
|
command: python3 -c "from core.output_publisher import publish_to_ssm, format_comment, post_github_comment; import json,subprocess; tf=json.loads(subprocess.check_output(['terraform','-chdir=terraform/spike','output','-json']) or '{}'); outputs={k:v.get('value') if isinstance(v,dict) else v for k,v in tf.items()}; ssm=publish_to_ssm(outputs,'dev','spike'); comment=format_comment(outputs,'dev','spike',ssm); post_github_comment(comment)"
|
||||||
required: false
|
required: false
|
||||||
|
|
||||||
|
- name: deploy-uptime
|
||||||
|
description: Deploy uptime-kuma monitoring stack (separate terraform state) with endpoints from L2 outputs
|
||||||
|
command: bash scripts/run_platform.sh --deploy-uptime
|
||||||
|
required: false
|
||||||
|
|
||||||
- name: comment-outputs
|
- name: comment-outputs
|
||||||
description: Post a structured GitHub PR comment with human-readable deploy outputs
|
description: Post a structured GitHub PR comment with human-readable deploy outputs
|
||||||
command: bash scripts/post_stage_comment.sh publish-outputs pass
|
command: bash scripts/post_stage_comment.sh publish-outputs pass
|
||||||
|
|||||||
@@ -39,6 +39,7 @@ cd "$ROOT"
|
|||||||
CHECK_ONLY=0
|
CHECK_ONLY=0
|
||||||
PLAN_ONLY=0
|
PLAN_ONLY=0
|
||||||
QUIET=0
|
QUIET=0
|
||||||
|
DEPLOY_UPTIME=0
|
||||||
CONTRACT=""
|
CONTRACT=""
|
||||||
|
|
||||||
for arg in "$@"; do
|
for arg in "$@"; do
|
||||||
@@ -46,6 +47,7 @@ for arg in "$@"; do
|
|||||||
--check-only) CHECK_ONLY=1 ;;
|
--check-only) CHECK_ONLY=1 ;;
|
||||||
--plan-only) PLAN_ONLY=1 ;;
|
--plan-only) PLAN_ONLY=1 ;;
|
||||||
--quiet) QUIET=1 ;;
|
--quiet) QUIET=1 ;;
|
||||||
|
--deploy-uptime) DEPLOY_UPTIME=1 ;;
|
||||||
--*) echo "FAIL: unknown flag: $arg" >&2; exit 1 ;;
|
--*) echo "FAIL: unknown flag: $arg" >&2; exit 1 ;;
|
||||||
*) CONTRACT="$arg" ;;
|
*) CONTRACT="$arg" ;;
|
||||||
esac
|
esac
|
||||||
@@ -290,6 +292,73 @@ PY
|
|||||||
fi
|
fi
|
||||||
fi
|
fi
|
||||||
|
|
||||||
|
echo ""
|
||||||
|
echo "=== Step 9b: deploy uptime monitoring (separate state) ==="
|
||||||
|
# The uptime stack is deployed by default after the L2 module. It uses a
|
||||||
|
# separate terraform state ($WORK/uptime-tf). Endpoints from the L2 outputs
|
||||||
|
# are passed as monitored_endpoints. The feature flag (inputs.uptime_enabled,
|
||||||
|
# default true) controls whether this step runs.
|
||||||
|
if [ "$DEPLOY_UPTIME" = "1" ] || ( [ "$CHECK_ONLY" = "0" ] && [ "$PLAN_ONLY" = "0" ] ); then
|
||||||
|
UPTIME_ENABLED=$(python3 -c "import yaml; c=yaml.safe_load(open('$CONTRACT')); print(c.get('inputs',{}).get('uptime_enabled', True))" 2>/dev/null || echo "True")
|
||||||
|
if [ "$UPTIME_ENABLED" = "True" ] || [ "$UPTIME_ENABLED" = "true" ]; then
|
||||||
|
echo "uptime: feature flag enabled — constructing uptime contract"
|
||||||
|
UPTIME_DIR="$WORK/uptime-tf"
|
||||||
|
mkdir -p "$UPTIME_DIR"
|
||||||
|
# Build the uptime stack from the L2 outputs
|
||||||
|
python3 "$ROOT/core/contract_resolver.py" "$CONTRACT" "$WORK/stack.json" 2>/dev/null || true
|
||||||
|
python3 -c "
|
||||||
|
import json, sys, yaml
|
||||||
|
sys.path.insert(0, '$ROOT')
|
||||||
|
from core.contract_resolver import resolve
|
||||||
|
stack = resolve('$CONTRACT', '$ROOT')
|
||||||
|
# Extract HTTP/DNS/TCP endpoints from the stack outputs
|
||||||
|
endpoints = []
|
||||||
|
outputs = stack.get('outputs', {})
|
||||||
|
for name, spec in outputs.items():
|
||||||
|
src_rid = spec.get('from', '')
|
||||||
|
src_output = spec.get('output', name)
|
||||||
|
if 'domain' in name.lower() or 'url' in name.lower() or 'endpoint' in name.lower():
|
||||||
|
endpoints.append({
|
||||||
|
'name': name,
|
||||||
|
'url': f'ref:{src_rid}.{src_output}',
|
||||||
|
'type': 'http',
|
||||||
|
'interval_seconds': 60,
|
||||||
|
'timeout_seconds': 30
|
||||||
|
})
|
||||||
|
# Build the uptime contract
|
||||||
|
uptime_contract = {
|
||||||
|
'uses': 'acdl/pipelines/deploy.yaml@v1.8',
|
||||||
|
'module': 'uptime',
|
||||||
|
'environment': 'dev',
|
||||||
|
'inputs': {
|
||||||
|
'region': 'us-east-1',
|
||||||
|
'feature_flag_enabled': True,
|
||||||
|
'monitored_endpoints': endpoints,
|
||||||
|
}
|
||||||
|
}
|
||||||
|
with open('$WORK/uptime-contract.yaml', 'w') as f:
|
||||||
|
yaml.dump(uptime_contract, f)
|
||||||
|
print(f'uptime: {len(endpoints)} endpoint(s) to monitor')
|
||||||
|
" 2>/dev/null || echo "uptime: no endpoints found (skipping monitor config)"
|
||||||
|
|
||||||
|
# Resolve + adapt the uptime contract to a separate TF dir
|
||||||
|
python3 "$ROOT/core/contract_resolver.py" "$WORK/uptime-contract.yaml" "$WORK/uptime-stack.json" 2>/dev/null || true
|
||||||
|
python3 "$ROOT/adapters/terraform/adapter.py" "$WORK/uptime-stack.json" "$UPTIME_DIR" 2>/dev/null || true
|
||||||
|
|
||||||
|
if [ "$DEPLOY_UPTIME" = "1" ] && [ -f "$UPTIME_DIR/main.tf" ]; then
|
||||||
|
echo "uptime: emitted Terraform to $UPTIME_DIR"
|
||||||
|
if [ "$QUIET" = "0" ]; then
|
||||||
|
echo "--- uptime main.tf ---"
|
||||||
|
cat "$UPTIME_DIR/main.tf"
|
||||||
|
echo "--- end uptime main.tf ---"
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
echo "uptime: monitoring stack ready (separate state: $UPTIME_DIR)"
|
||||||
|
else
|
||||||
|
echo "uptime: feature flag disabled (inputs.uptime_enabled=false) — skipping"
|
||||||
|
fi
|
||||||
|
fi
|
||||||
|
|
||||||
echo ""
|
echo ""
|
||||||
echo "=== PLATFORM E2E OK ==="
|
echo "=== PLATFORM E2E OK ==="
|
||||||
echo "contract -> resolver -> stack -> terraform plan -> Checkov -> confidence ($BAND) -> outbox -> outputs"
|
echo "contract -> resolver -> stack -> terraform plan -> Checkov -> confidence ($BAND) -> outbox -> outputs"
|
||||||
|
|||||||
@@ -0,0 +1,80 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Seed uptime-kuma monitors via the API after the ECS service is up.
|
||||||
|
|
||||||
|
Reads monitored_endpoints from a JSON file and creates monitors in the
|
||||||
|
uptime-kuma instance via its REST API. Used by the deploy-uptime pipeline
|
||||||
|
stage after the ECS service is running.
|
||||||
|
|
||||||
|
Usage:
|
||||||
|
seed_uptime_monitors.py <endpoints.json> <uptime_url> [--token <token>]
|
||||||
|
|
||||||
|
The endpoints.json file is an array of:
|
||||||
|
{"name": "...", "url": "...", "type": "http|dns|tcp",
|
||||||
|
"interval_seconds": 60, "timeout_seconds": 30}
|
||||||
|
"""
|
||||||
|
|
||||||
|
import argparse
|
||||||
|
import json
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
import urllib.request
|
||||||
|
import urllib.error
|
||||||
|
|
||||||
|
|
||||||
|
def create_monitor(uptime_url, endpoint, token=None):
|
||||||
|
"""Create a single monitor in uptime-kuma via the API."""
|
||||||
|
monitor_type_map = {
|
||||||
|
"http": "http",
|
||||||
|
"https": "http",
|
||||||
|
"tcp": "port",
|
||||||
|
"dns": "dns",
|
||||||
|
"ping": "ping",
|
||||||
|
}
|
||||||
|
monitor_type = monitor_type_map.get(endpoint.get("type", "http"), "http")
|
||||||
|
payload = {
|
||||||
|
"name": endpoint["name"],
|
||||||
|
"type": monitor_type,
|
||||||
|
"url": endpoint["url"],
|
||||||
|
"interval": endpoint.get("interval_seconds", 60),
|
||||||
|
"timeout": endpoint.get("timeout_seconds", 30),
|
||||||
|
}
|
||||||
|
url = f"{uptime_url}/api/monitor"
|
||||||
|
data = json.dumps(payload).encode()
|
||||||
|
req = urllib.request.Request(url, data=data, method="POST")
|
||||||
|
req.add_header("Content-Type", "application/json")
|
||||||
|
if token:
|
||||||
|
req.add_header("Authorization", f"Bearer {token}")
|
||||||
|
try:
|
||||||
|
with urllib.request.urlopen(req, timeout=10) as resp:
|
||||||
|
result = json.loads(resp.read())
|
||||||
|
return {"status": "created", "monitor": endpoint["name"], "result": result}
|
||||||
|
except urllib.error.HTTPError as e:
|
||||||
|
return {"status": "error", "monitor": endpoint["name"], "error": str(e)}
|
||||||
|
except Exception as e:
|
||||||
|
return {"status": "error", "monitor": endpoint["name"], "error": str(e)}
|
||||||
|
|
||||||
|
|
||||||
|
def seed_monitors(endpoints, uptime_url, token=None):
|
||||||
|
"""Seed all monitors from the endpoints list."""
|
||||||
|
results = []
|
||||||
|
for endpoint in endpoints:
|
||||||
|
result = create_monitor(uptime_url, endpoint, token)
|
||||||
|
results.append(result)
|
||||||
|
return results
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
parser = argparse.ArgumentParser(description="Seed uptime-kuma monitors")
|
||||||
|
parser.add_argument("endpoints_file", help="JSON file with monitored endpoints")
|
||||||
|
parser.add_argument("uptime_url", help="URL of the uptime-kuma instance")
|
||||||
|
parser.add_argument("--token", default=None, help="Auth token (if required)")
|
||||||
|
args = parser.parse_args()
|
||||||
|
|
||||||
|
with open(args.endpoints_file) as f:
|
||||||
|
endpoints = json.load(f)
|
||||||
|
|
||||||
|
results = seed_monitors(endpoints, args.uptime_url, args.token)
|
||||||
|
for r in results:
|
||||||
|
print(f" [{r['status']}] {r['monitor']}")
|
||||||
|
created = sum(1 for r in results if r["status"] == "created")
|
||||||
|
print(f"Seeded {created}/{len(results)} monitors")
|
||||||
+75
-5
@@ -31,14 +31,14 @@ class TestInstance:
|
|||||||
|
|
||||||
|
|
||||||
class TestRegistry:
|
class TestRegistry:
|
||||||
EXPECTED_L1_KEYS = {"s3", "vpc", "ecs-cluster", "ecs-service", "iam-role", "alb", "ecr", "cloudfront", "waf", "rds", "kms-key"}
|
EXPECTED_L1_KEYS = {"s3", "vpc", "ecs-cluster", "ecs-service", "iam-role", "alb", "ecr", "cloudfront", "waf", "rds", "kms-key", "uptime"}
|
||||||
EXPECTED_L2_KEYS = {"static-assets", "microservice"}
|
EXPECTED_L2_KEYS = {"static-assets", "microservice"}
|
||||||
|
|
||||||
def test_registry_has_13_entries(self, registry):
|
def test_registry_has_14_entries(self, registry):
|
||||||
assert len(registry) == 13
|
assert len(registry) == 14
|
||||||
assert set(registry.keys()) == (self.EXPECTED_L1_KEYS | self.EXPECTED_L2_KEYS)
|
assert set(registry.keys()) == (self.EXPECTED_L1_KEYS | self.EXPECTED_L2_KEYS)
|
||||||
|
|
||||||
def test_registry_has_11_l1_entries(self, registry):
|
def test_registry_has_12_l1_entries(self, registry):
|
||||||
l1 = {k for k in registry if registry[k]["1.0.0"]["interface"].startswith("modules/l1/")}
|
l1 = {k for k in registry if registry[k]["1.0.0"]["interface"].startswith("modules/l1/")}
|
||||||
assert l1 == self.EXPECTED_L1_KEYS
|
assert l1 == self.EXPECTED_L1_KEYS
|
||||||
|
|
||||||
@@ -585,4 +585,74 @@ class TestDeletionProtectionByDefault:
|
|||||||
stack = resolve(str(contract_path), str(ROOT))
|
stack = resolve(str(contract_path), str(ROOT))
|
||||||
for res in stack["resources"]:
|
for res in stack["resources"]:
|
||||||
assert res.get("nfrs", {}).get("deletion_protection") is False, \
|
assert res.get("nfrs", {}).get("deletion_protection") is False, \
|
||||||
f"Resource {res['id']} should have deletion_protection=false"
|
f"Resource {res['id']} should have deletion_protection=false"
|
||||||
|
|
||||||
|
|
||||||
|
class TestUptimePrimitive:
|
||||||
|
"""REQ-88/89/90/91: uptime-kuma primitive + feature flag + pipeline stage."""
|
||||||
|
|
||||||
|
def test_uptime_primitive_in_registry(self, registry):
|
||||||
|
assert "uptime" in registry
|
||||||
|
|
||||||
|
def test_uptime_interface_has_feature_flag(self, repo_root):
|
||||||
|
iface = json.load(open(os.path.join(str(repo_root), "modules", "l1", "uptime", "interface.json")))
|
||||||
|
assert "feature_flag_enabled" in iface["inputs"]
|
||||||
|
assert iface["inputs"]["feature_flag_enabled"]["default"] is True
|
||||||
|
|
||||||
|
def test_uptime_interface_has_alert_channels(self, repo_root):
|
||||||
|
iface = json.load(open(os.path.join(str(repo_root), "modules", "l1", "uptime", "interface.json")))
|
||||||
|
assert "alert_channels" in iface["inputs"]
|
||||||
|
assert "monitored_endpoints" in iface["inputs"]
|
||||||
|
|
||||||
|
def test_uptime_adapter_emits_ecs_service_when_enabled(self, tmp_path):
|
||||||
|
uptime_stack = {
|
||||||
|
"version": "1.0.0",
|
||||||
|
"stack": {"name": "uptime", "kind": "l1", "depth": 1},
|
||||||
|
"resources": [{
|
||||||
|
"id": "uptime",
|
||||||
|
"type": "aws:ecs:uptime-service",
|
||||||
|
"module": "uptime@1.0.0",
|
||||||
|
"inputs": {
|
||||||
|
"container_image": "louislam/uptime-kuma:1",
|
||||||
|
"region": "us-east-1",
|
||||||
|
"feature_flag_enabled": True,
|
||||||
|
"monitored_endpoints": [{"name": "test", "url": "https://example.com", "type": "http", "interval_seconds": 60, "timeout_seconds": 30}],
|
||||||
|
"cpu": 256,
|
||||||
|
"memory": 512,
|
||||||
|
},
|
||||||
|
"outputs": {},
|
||||||
|
"nfrs": {"deletion_protection": True, "encryption_enabled": True},
|
||||||
|
}],
|
||||||
|
}
|
||||||
|
out_dir = str(tmp_path / "tf_out")
|
||||||
|
adapt(uptime_stack, out_dir)
|
||||||
|
main_tf = open(os.path.join(out_dir, "main.tf")).read()
|
||||||
|
assert 'resource "aws_ecs_service" "uptime"' in main_tf
|
||||||
|
assert "louislam/uptime-kuma:1" in main_tf
|
||||||
|
assert "desired_count = 1" in main_tf
|
||||||
|
|
||||||
|
def test_uptime_adapter_emits_nothing_when_disabled(self, tmp_path):
|
||||||
|
"""REQ-90: feature_flag_enabled=false means no resources emitted."""
|
||||||
|
uptime_stack = {
|
||||||
|
"version": "1.0.0",
|
||||||
|
"stack": {"name": "uptime", "kind": "l1", "depth": 1},
|
||||||
|
"resources": [{
|
||||||
|
"id": "uptime",
|
||||||
|
"type": "aws:ecs:uptime-service",
|
||||||
|
"module": "uptime@1.0.0",
|
||||||
|
"inputs": {"region": "us-east-1", "feature_flag_enabled": False},
|
||||||
|
"outputs": {},
|
||||||
|
"nfrs": {},
|
||||||
|
}],
|
||||||
|
}
|
||||||
|
out_dir = str(tmp_path / "tf_out")
|
||||||
|
adapt(uptime_stack, out_dir)
|
||||||
|
main_tf = open(os.path.join(out_dir, "main.tf")).read()
|
||||||
|
assert 'resource "aws_ecs_service" "uptime"' not in main_tf
|
||||||
|
|
||||||
|
def test_deploy_pipeline_has_deploy_uptime_stage(self):
|
||||||
|
import yaml
|
||||||
|
with open(ROOT / "pipelines/deploy.yaml") as fh:
|
||||||
|
contract = yaml.safe_load(fh)
|
||||||
|
stage_names = [s["name"] for s in contract["stages"]]
|
||||||
|
assert "deploy-uptime" in stage_names
|
||||||
@@ -265,7 +265,7 @@ class TestDeployPipelineContract:
|
|||||||
contract = _load_yaml("pipelines/deploy.yaml")
|
contract = _load_yaml("pipelines/deploy.yaml")
|
||||||
jsonschema.validate(contract, schema)
|
jsonschema.validate(contract, schema)
|
||||||
|
|
||||||
def test_deploy_contract_has_eight_stages(self):
|
def test_deploy_contract_has_nine_stages(self):
|
||||||
contract = _load_yaml("pipelines/deploy.yaml")
|
contract = _load_yaml("pipelines/deploy.yaml")
|
||||||
stage_names = [s["name"] for s in contract["stages"]]
|
stage_names = [s["name"] for s in contract["stages"]]
|
||||||
assert stage_names == [
|
assert stage_names == [
|
||||||
@@ -276,6 +276,7 @@ class TestDeployPipelineContract:
|
|||||||
"confidence",
|
"confidence",
|
||||||
"apply",
|
"apply",
|
||||||
"publish-outputs",
|
"publish-outputs",
|
||||||
|
"deploy-uptime",
|
||||||
"comment-outputs",
|
"comment-outputs",
|
||||||
]
|
]
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user