// Shared native Grafana Alloy configuration for Docker guests.
// Metrics and logs use the endpoints and credentials supplied through
// APEX_PROM_PUSH_URL, APEX_LOKI_PUSH_URL, and APEX_OBS_BASIC_AUTH_USER/PASS.

// ----------------------------------------------------------------------------
// METRICS
// ----------------------------------------------------------------------------

// Native filesystem views; physical capacity is collected on the Proxmox host.


// Container metrics (cadvisor-equivalent) via the docker socket.
prometheus.exporter.cadvisor "containers" {
  docker_host                  = "unix:///var/run/docker.sock"
  store_container_labels       = false
  allowlisted_container_labels = [
    "com.docker.compose.project",
    "com.docker.compose.service",
  ]
  docker_only                  = true
  enabled_metrics              = [
    "cpu",
    "cpuLoad",
    "diskIO",
    "memory",
    "network",
    "oom_event",
  ]
}

// Stamp a static `node` label onto each exporter's targets.

discovery.relabel "container_metrics" {
  targets = prometheus.exporter.cadvisor.containers.targets
  rule {
    action       = "replace"
    target_label = "node"
    replacement  = sys.env("APEX_NODE_HOST")
  }
  rule {
    action       = "replace"
    target_label = "instance"
    replacement  = sys.env("APEX_NODE_HOST")
  }
}


prometheus.scrape "containers" {
  targets         = discovery.relabel.container_metrics.output
  forward_to      = [prometheus.remote_write.default.receiver]
  scrape_interval = "30s"
}

// The configured Prometheus-compatible endpoint must accept remote writes.
prometheus.remote_write "default" {
  endpoint {
    url = sys.env("APEX_PROM_PUSH_URL")
    basic_auth {
      username = sys.env("APEX_OBS_BASIC_AUTH_USER")
      password = sys.env("APEX_OBS_BASIC_AUTH_PASS")
    }
    queue_config {
      capacity             = 5000
      max_shards           = 10
      min_shards           = 1
      max_samples_per_send = 1000
      batch_send_deadline  = "5s"
      min_backoff          = "100ms"
      max_backoff          = "10s"
    }
  }
  wal {
    truncate_frequency = "30m"
    min_keepalive_time = "5m"
    max_keepalive_time = "30m"
  }
}

// ----------------------------------------------------------------------------
// LOGS
// ----------------------------------------------------------------------------

// systemd journal (host services, ufw, sshd, crowdsec, etc.).
loki.source.journal "systemd" {
  path    = "/var/log/journal"
  max_age = "12h"
  labels  = {
    node = sys.env("APEX_NODE_HOST"),
    job  = "systemd-journal",
  }
  forward_to = [loki.write.default.receiver]
}

// All docker containers' stdout/stderr.
discovery.docker "containers" {
  host = "unix:///var/run/docker.sock"
}
discovery.relabel "container_logs" {
  targets = discovery.docker.containers.targets
  rule {
    action        = "replace"
    source_labels = ["__meta_docker_container_name"]
    regex         = "/?(.*)"
    target_label  = "container"
  }
  rule {
    action       = "replace"
    target_label = "node"
    replacement  = sys.env("APEX_NODE_HOST")
  }
}
loki.source.docker "containers" {
  host          = "unix:///var/run/docker.sock"
  targets       = discovery.relabel.container_logs.output
  relabel_rules = discovery.relabel.container_logs.rules
  forward_to    = [loki.write.default.receiver]
}

// Push logs to the central Loki.
loki.write "default" {
  endpoint {
    url = sys.env("APEX_LOKI_PUSH_URL")
    basic_auth {
      username = sys.env("APEX_OBS_BASIC_AUTH_USER")
      password = sys.env("APEX_OBS_BASIC_AUTH_PASS")
    }
  }
}