[job-hunter] Add infra stack + Grafana dashboard + n8n digest workflow

New service stack at stacks/job-hunter/ mirroring the payslip-ingest
pattern: per-service CNPG database + role (via dbaas null_resource),
Vault static role pg-job-hunter (7d rotation), ExternalSecrets for app
secrets and DB creds, Deployment with alembic-migrate init container,
ClusterIP Service, Grafana datasource ConfigMap.

Grafana dashboard job-hunter.json in Finance folder: new roles per
day, source breakdown, top companies, GBP salary distribution, recent
roles table (sorted by parse confidence then salary).

n8n weekly-digest workflow calls POST /digest/generate with bearer
auth every Monday 07:00 London; digest_runs table provides
idempotency.

Refs: code-snp

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Viktor Barzin 2026-04-19 17:09:29 +00:00
parent 7cb44d7264
commit e7ce545da2
7 changed files with 655 additions and 17 deletions

View file

@ -1185,6 +1185,30 @@ resource "null_resource" "pg_payslip_ingest_db" {
} }
} }
# Create job_hunter database for the job-hunter scraper service.
# Role password is managed by Vault Database Secrets Engine (static role `pg-job-hunter`, 7d rotation).
resource "null_resource" "pg_job_hunter_db" {
depends_on = [null_resource.pg_cluster]
triggers = {
db_name = "job_hunter"
username = "job_hunter"
}
provisioner "local-exec" {
command = <<-EOT
kubectl --kubeconfig ${var.kube_config_path} exec -n dbaas pg-cluster-1 -c postgres -- \
bash -c '
psql -U postgres -tc "SELECT 1 FROM pg_catalog.pg_roles WHERE rolname = '"'"'job_hunter'"'"'" | grep -q 1 || \
psql -U postgres -c "CREATE ROLE job_hunter WITH LOGIN PASSWORD '"'"'changeme-vault-will-rotate'"'"'"
psql -U postgres -tc "SELECT 1 FROM pg_catalog.pg_database WHERE datname = '"'"'job_hunter'"'"'" | grep -q 1 || \
psql -U postgres -c "CREATE DATABASE job_hunter OWNER job_hunter"
psql -U postgres -c "GRANT ALL PRIVILEGES ON DATABASE job_hunter TO job_hunter"
'
EOT
}
}
# Old PostgreSQL deployment kept commented for rollback reference # Old PostgreSQL deployment kept commented for rollback reference
# resource "kubernetes_deployment" "postgres" { # resource "kubernetes_deployment" "postgres" {
# metadata { # metadata {

320
stacks/job-hunter/main.tf Normal file
View file

@ -0,0 +1,320 @@
variable "image_tag" {
type = string
default = "latest"
description = "job-hunter image tag. Use 8-char git SHA in CI; :latest only for local trials."
}
variable "postgresql_host" { type = string }
locals {
namespace = "job-hunter"
image = "registry.viktorbarzin.me/job-hunter:${var.image_tag}"
labels = {
app = "job-hunter"
}
}
resource "kubernetes_namespace" "job_hunter" {
metadata {
name = local.namespace
labels = {
tier = local.tiers.aux
"istio-injection" = "disabled"
}
}
lifecycle {
# KYVERNO_LIFECYCLE_V1: goldilocks-vpa-auto-mode ClusterPolicy stamps this label on every namespace
ignore_changes = [metadata[0].labels["goldilocks.fairwinds.com/vpa-update-mode"]]
}
}
# App secrets seed these in Vault before applying:
# secret/job-hunter
# webhook_bearer_token bearer for /webhook/cdio, /digest/generate, /refresh
# cdio_api_key changedetection.io x-api-key (copy from
# `jsondecode(secret/changedetection.homepage_credentials).changedetection.api_key`)
# smtp_username SMTP sender account (mailserver)
# smtp_password SMTP password (mailserver)
# digest_to_address where the weekly digest goes
# digest_from_address From: header for the digest
resource "kubernetes_manifest" "external_secret" {
manifest = {
apiVersion = "external-secrets.io/v1beta1"
kind = "ExternalSecret"
metadata = {
name = "job-hunter-secrets"
namespace = local.namespace
}
spec = {
refreshInterval = "15m"
secretStoreRef = {
name = "vault-kv"
kind = "ClusterSecretStore"
}
target = {
name = "job-hunter-secrets"
template = {
metadata = {
annotations = {
"reloader.stakater.com/match" = "true"
}
}
}
}
dataFrom = [{
extract = {
key = "job-hunter"
}
}]
}
}
depends_on = [kubernetes_namespace.job_hunter]
}
# DB credentials from Vault database engine (7-day rotation).
# Template builds the asyncpg DSN consumed by the FastAPI app as DB_CONNECTION_STRING.
resource "kubernetes_manifest" "db_external_secret" {
manifest = {
apiVersion = "external-secrets.io/v1beta1"
kind = "ExternalSecret"
metadata = {
name = "job-hunter-db-creds"
namespace = local.namespace
}
spec = {
refreshInterval = "15m"
secretStoreRef = {
name = "vault-database"
kind = "ClusterSecretStore"
}
target = {
name = "job-hunter-db-creds"
template = {
metadata = {
annotations = {
"reloader.stakater.com/match" = "true"
}
}
data = {
DB_CONNECTION_STRING = "postgresql+asyncpg://job_hunter:{{ .password }}@${var.postgresql_host}:5432/job_hunter"
DB_PASSWORD = "{{ .password }}"
}
}
}
data = [{
secretKey = "password"
remoteRef = {
key = "static-creds/pg-job-hunter"
property = "password"
}
}]
}
}
depends_on = [kubernetes_namespace.job_hunter]
}
resource "kubernetes_deployment" "job_hunter" {
metadata {
name = "job-hunter"
namespace = kubernetes_namespace.job_hunter.metadata[0].name
labels = merge(local.labels, {
tier = local.tiers.aux
})
annotations = {
"reloader.stakater.com/search" = "true"
}
}
spec {
replicas = 1
strategy {
type = "Recreate"
}
selector {
match_labels = local.labels
}
template {
metadata {
labels = local.labels
}
spec {
image_pull_secrets {
name = "registry-credentials"
}
init_container {
name = "alembic-migrate"
image = local.image
command = ["python", "-m", "job_hunter", "migrate"]
env_from {
secret_ref {
name = "job-hunter-secrets"
}
}
env_from {
secret_ref {
name = "job-hunter-db-creds"
}
}
resources {
requests = {
cpu = "50m"
memory = "256Mi"
}
limits = {
memory = "512Mi"
}
}
}
container {
name = "job-hunter"
image = local.image
port {
container_port = 8080
}
env_from {
secret_ref {
name = "job-hunter-secrets"
}
}
env_from {
secret_ref {
name = "job-hunter-db-creds"
}
}
env {
name = "CDIO_BASE_URL"
value = "http://changedetection.changedetection.svc.cluster.local"
}
env {
name = "SMTP_HOST"
value = "mailserver.mailserver.svc.cluster.local"
}
env {
name = "SMTP_PORT"
value = "587"
}
env {
name = "JOB_HUNTER_WEBHOOK_URL"
value = "http://job-hunter.job-hunter.svc.cluster.local:8080/webhook/cdio"
}
readiness_probe {
http_get {
path = "/healthz"
port = 8080
}
initial_delay_seconds = 5
period_seconds = 10
}
liveness_probe {
http_get {
path = "/healthz"
port = 8080
}
initial_delay_seconds = 5
period_seconds = 10
}
resources {
requests = {
cpu = "100m"
memory = "512Mi"
}
# Chromium baseline ~1Gi matches broker-sync precedent.
limits = {
memory = "1280Mi"
}
}
}
}
}
}
lifecycle {
ignore_changes = [spec[0].template[0].spec[0].dns_config] # KYVERNO_LIFECYCLE_V1
}
depends_on = [
kubernetes_manifest.external_secret,
kubernetes_manifest.db_external_secret,
]
}
# ClusterIP-only job-hunter has no public UI. Webhook, digest, and refresh
# endpoints are cluster-internal (n8n / CDIO / CronJob triggers).
resource "kubernetes_service" "job_hunter" {
metadata {
name = "job-hunter"
namespace = kubernetes_namespace.job_hunter.metadata[0].name
labels = local.labels
}
spec {
type = "ClusterIP"
selector = local.labels
port {
name = "http"
port = 8080
target_port = 8080
}
}
}
# Plan-time read of the ESO-created DB creds Secret for Grafana datasource.
# First apply: -target=kubernetes_manifest.db_external_secret first so the Secret exists.
data "kubernetes_secret" "job_hunter_db_creds" {
metadata {
name = "job-hunter-db-creds"
namespace = kubernetes_namespace.job_hunter.metadata[0].name
}
depends_on = [kubernetes_manifest.db_external_secret]
}
# Grafana datasource for the job_hunter Postgres DB. Lives in the monitoring
# namespace so the grafana sidecar (label grafana_datasource=1) picks it up.
resource "kubernetes_config_map" "grafana_job_hunter_datasource" {
metadata {
name = "grafana-job-hunter-datasource"
namespace = "monitoring"
labels = {
grafana_datasource = "1"
}
}
data = {
"job-hunter-datasource.yaml" = yamlencode({
apiVersion = 1
datasources = [{
name = "Job Hunter"
type = "postgres"
access = "proxy"
url = "${var.postgresql_host}:5432"
user = "job_hunter"
uid = "job-hunter-pg"
# Grafana 11.2+ Postgres plugin reads the DB name from jsonData.database;
# the top-level `database` field is silently ignored by the frontend.
jsonData = {
database = "job_hunter"
sslmode = "disable"
postgresVersion = 1600
timescaledb = false
}
secureJsonData = {
password = data.kubernetes_secret.job_hunter_db_creds.data["DB_PASSWORD"]
}
editable = true
}]
})
}
}

View file

@ -0,0 +1,23 @@
include "root" {
path = find_in_parent_folders()
}
dependency "platform" {
config_path = "../platform"
skip_outputs = true
}
dependency "vault" {
config_path = "../vault"
skip_outputs = true
}
dependency "external-secrets" {
config_path = "../external-secrets"
skip_outputs = true
}
inputs = {
# Bump on every deploy 8-char git SHA from the CI build.
image_tag = "latest"
}

View file

@ -0,0 +1,213 @@
{
"annotations": {"list": []},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": null,
"links": [],
"liveNow": false,
"panels": [
{
"datasource": {"type": "grafana-postgresql-datasource", "uid": "job-hunter-pg"},
"description": "Newly-ingested roles (by fetched_at).",
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {
"drawStyle": "bars",
"fillOpacity": 60,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"showPoints": "auto",
"spanNulls": false,
"stacking": {"mode": "none"}
},
"thresholds": {"mode": "absolute", "steps": []}
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 0},
"id": 1,
"options": {
"legend": {"displayMode": "list", "placement": "bottom", "showLegend": true},
"tooltip": {"mode": "single", "sort": "none"}
},
"targets": [
{
"datasource": {"type": "grafana-postgresql-datasource", "uid": "job-hunter-pg"},
"format": "time_series",
"rawQuery": true,
"rawSql": "SELECT date_trunc('day', fetched_at) AT TIME ZONE 'UTC' AS time, source, COUNT(*) AS value FROM job_hunter.roles WHERE $__timeFilter(fetched_at) GROUP BY 1, 2 ORDER BY 1",
"refId": "A"
}
],
"title": "New roles per day by source",
"type": "timeseries"
},
{
"datasource": {"type": "grafana-postgresql-datasource", "uid": "job-hunter-pg"},
"description": "Distinct open roles by source over the time window.",
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {"hideFrom": {"legend": false, "tooltip": false, "viz": false}},
"mappings": []
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 0},
"id": 2,
"options": {
"legend": {"displayMode": "table", "placement": "right", "showLegend": true, "values": ["value"]},
"pieType": "donut",
"reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false},
"tooltip": {"mode": "single", "sort": "none"}
},
"targets": [
{
"datasource": {"type": "grafana-postgresql-datasource", "uid": "job-hunter-pg"},
"format": "table",
"rawQuery": true,
"rawSql": "SELECT source AS metric, COUNT(DISTINCT dedup_key) AS value FROM job_hunter.roles WHERE $__timeFilter(fetched_at) GROUP BY source ORDER BY value DESC",
"refId": "A"
}
],
"title": "Roles by source (deduplicated)",
"type": "piechart"
},
{
"datasource": {"type": "grafana-postgresql-datasource", "uid": "job-hunter-pg"},
"description": "Top 20 companies by recent role volume.",
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {
"axisPlacement": "auto",
"fillOpacity": 80,
"gradientMode": "none",
"lineWidth": 1
},
"mappings": [],
"thresholds": {"mode": "absolute", "steps": []}
},
"overrides": []
},
"gridPos": {"h": 9, "w": 12, "x": 0, "y": 8},
"id": 3,
"options": {
"barRadius": 0,
"barWidth": 0.85,
"fullHighlight": false,
"groupWidth": 0.7,
"legend": {"displayMode": "hidden", "placement": "bottom", "showLegend": false},
"orientation": "horizontal",
"showValue": "auto",
"stacking": "none",
"tooltip": {"mode": "single", "sort": "none"},
"xTickLabelRotation": 0,
"xTickLabelSpacing": 0
},
"targets": [
{
"datasource": {"type": "grafana-postgresql-datasource", "uid": "job-hunter-pg"},
"format": "table",
"rawQuery": true,
"rawSql": "SELECT c.display_name, COUNT(*) AS roles FROM job_hunter.roles r JOIN job_hunter.companies c ON r.company_id = c.id WHERE $__timeFilter(r.fetched_at) GROUP BY c.display_name ORDER BY roles DESC LIMIT 20",
"refId": "A"
}
],
"title": "Top companies by role volume",
"type": "barchart"
},
{
"datasource": {"type": "grafana-postgresql-datasource", "uid": "job-hunter-pg"},
"description": "Normalised base salary distribution (£) for roles with explicit comp.",
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {"fillOpacity": 80, "lineWidth": 1},
"mappings": []
},
"overrides": []
},
"gridPos": {"h": 9, "w": 12, "x": 12, "y": 8},
"id": 4,
"options": {
"bucketOffset": 0,
"combine": false,
"legend": {"displayMode": "list", "placement": "bottom", "showLegend": true}
},
"targets": [
{
"datasource": {"type": "grafana-postgresql-datasource", "uid": "job-hunter-pg"},
"format": "table",
"rawQuery": true,
"rawSql": "SELECT parsed_base_gbp::float AS base_gbp FROM job_hunter.roles WHERE parsed_base_gbp IS NOT NULL AND $__timeFilter(fetched_at)",
"refId": "A"
}
],
"title": "Salary distribution (GBP)",
"type": "histogram"
},
{
"datasource": {"type": "grafana-postgresql-datasource", "uid": "job-hunter-pg"},
"description": "Recent roles, ranked by salary-parse confidence then parsed base.",
"fieldConfig": {
"defaults": {
"color": {"mode": "thresholds"},
"custom": {
"align": "auto",
"cellOptions": {"type": "auto"},
"filterable": true,
"inspect": false
},
"mappings": [],
"thresholds": {"mode": "absolute", "steps": []}
},
"overrides": [
{
"matcher": {"id": "byName", "options": "apply_url"},
"properties": [
{"id": "custom.cellOptions", "value": {"type": "auto"}},
{"id": "links", "value": [{"targetBlank": true, "title": "Open", "url": "${__value.raw}"}]}
]
},
{
"matcher": {"id": "byName", "options": "base_gbp"},
"properties": [{"id": "unit", "value": "currencyGBP"}]
}
]
},
"gridPos": {"h": 12, "w": 24, "x": 0, "y": 17},
"id": 5,
"options": {
"cellHeight": "sm",
"footer": {"countRows": false, "fields": "", "reducer": ["sum"], "show": false},
"showHeader": true
},
"targets": [
{
"datasource": {"type": "grafana-postgresql-datasource", "uid": "job-hunter-pg"},
"format": "table",
"rawQuery": true,
"rawSql": "SELECT r.posted_at, c.display_name AS company, r.title, r.location, r.remote_policy, r.parsed_base_gbp::float AS base_gbp, r.salary_parse_confidence, r.source, r.apply_url FROM job_hunter.roles r JOIN job_hunter.companies c ON r.company_id = c.id WHERE $__timeFilter(r.fetched_at) ORDER BY r.salary_parse_confidence DESC NULLS LAST, r.parsed_base_gbp DESC NULLS LAST, r.posted_at DESC NULLS LAST LIMIT 100",
"refId": "A"
}
],
"title": "Top roles",
"type": "table"
}
],
"refresh": "",
"schemaVersion": 39,
"tags": ["job-hunter", "jobs", "careers"],
"templating": {"list": []},
"time": {"from": "now-30d", "to": "now"},
"timepicker": {},
"timezone": "browser",
"title": "Job Hunter",
"uid": "job-hunter",
"version": 1,
"weekStart": ""
}

View file

@ -135,6 +135,7 @@ locals {
"qbittorrent.json" = "Applications" "qbittorrent.json" = "Applications"
"realestate-crawler.json" = "Applications" "realestate-crawler.json" = "Applications"
"uk-payslip.json" = "Finance" "uk-payslip.json" = "Finance"
"job-hunter.json" = "Finance"
} }
} }

View file

@ -0,0 +1,49 @@
{
"name": "Job Hunter Weekly Digest",
"active": false,
"nodes": [
{
"parameters": {
"rule": {
"interval": [{"field": "weeks", "triggerAtDay": [1], "triggerAtHour": 7, "triggerAtMinute": 0}]
}
},
"id": "cron-weekly",
"name": "Weekly Monday 07:00 London",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.1,
"position": [250, 300]
},
{
"parameters": {
"method": "POST",
"url": "http://job-hunter.job-hunter.svc.cluster.local:8080/digest/generate",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{"name": "Authorization", "value": "=Bearer {{ $env.JOB_HUNTER_WEBHOOK_TOKEN }}"},
{"name": "Content-Type", "value": "application/json"}
]
},
"sendBody": true,
"contentType": "json",
"jsonBody": "={\"window_days\":7,\"limit\":50,\"dry_run\":false}",
"options": {"timeout": 120000}
},
"id": "digest-generate",
"name": "Call /digest/generate",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [500, 300]
}
],
"connections": {
"Weekly Monday 07:00 London": {
"main": [[{"node": "Call /digest/generate", "type": "main", "index": 0}]]
}
},
"settings": {"executionOrder": "v1", "saveExecutionProgress": false, "saveManualExecutions": true},
"staticData": null,
"meta": {"templateCredsSetupCompleted": false},
"pinData": {}
}

View file

@ -536,7 +536,7 @@ resource "vault_database_secret_backend_connection" "postgresql" {
# "pg-trading", # Commented out 2026-04-06 - trading-bot disabled # "pg-trading", # Commented out 2026-04-06 - trading-bot disabled
"pg-health", "pg-linkwarden", "pg-health", "pg-linkwarden",
"pg-affine", "pg-woodpecker", "pg-claude-memory", "pg-affine", "pg-woodpecker", "pg-claude-memory",
"pg-terraform-state", "pg-payslip-ingest" "pg-terraform-state", "pg-payslip-ingest", "pg-job-hunter"
] ]
postgresql { postgresql {
@ -682,6 +682,14 @@ resource "vault_database_secret_backend_static_role" "pg_payslip_ingest" {
rotation_period = 604800 rotation_period = 604800
} }
resource "vault_database_secret_backend_static_role" "pg_job_hunter" {
backend = vault_mount.database.path
db_name = vault_database_secret_backend_connection.postgresql.name
name = "pg-job-hunter"
username = "job_hunter"
rotation_period = 604800
}
# ============================================================================= # =============================================================================
# Kubernetes Secrets Engine Dynamic K8s Credentials # Kubernetes Secrets Engine Dynamic K8s Credentials
# ============================================================================= # =============================================================================