homelab-deploy: enable prometheus metrics

- Update homelab-deploy input to get metrics support
- Enable metrics endpoint on port 9972
- Add scrape target for prometheus auto-discovery

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

.mcp.json

@@ -22,6 +22,17 @@
         "ALERTMANAGER_URL": "https://alertmanager.home.2rjus.net",
         "LOKI_URL": "http://monitoring01.home.2rjus.net:3100"
       }
+    },
+    "homelab-deploy": {
+      "command": "nix",
+      "args": [
+        "run",
+        "git+https://git.t-juice.club/torjus/homelab-deploy",
+        "--",
+        "mcp",
+        "--nats-url", "nats://nats1.home.2rjus.net:4222",
+        "--nkey-file", "/home/torjus/.config/homelab-deploy/test-deployer.nkey"
+      ]
     }
   }
 }

CLAUDE.md

@@ -194,6 +194,51 @@ node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes
 node_filesystem_avail_bytes{mountpoint="/"}
 ```
 
+### Deploying to Test Hosts
+
+The **homelab-deploy** MCP server enables remote deployments to test-tier hosts via NATS messaging.
+
+**Available Tools:**
+
+- `deploy` - Deploy NixOS configuration to test-tier hosts
+- `list_hosts` - List available deployment targets
+
+**Deploy Parameters:**
+
+- `hostname` - Target a specific host (e.g., `vaulttest01`)
+- `role` - Deploy to all hosts with a specific role (e.g., `vault`)
+- `all` - Deploy to all test-tier hosts
+- `action` - nixos-rebuild action: `switch` (default), `boot`, `test`, `dry-activate`
+- `branch` - Git branch or commit to deploy (default: `master`)
+
+**Examples:**
+
+```
+# List available hosts
+list_hosts()
+
+# Deploy to a specific host
+deploy(hostname="vaulttest01", action="switch")
+
+# Dry-run deployment
+deploy(hostname="vaulttest01", action="dry-activate")
+
+# Deploy to all hosts with a role
+deploy(role="vault", action="switch")
+```
+
+**Note:** Only test-tier hosts with `homelab.deploy.enable = true` and the listener service running will respond to deployments.
+
+**Verifying Deployments:**
+
+After deploying, use the `nixos_flake_info` metric from nixos-exporter to verify the host is running the expected revision:
+
+```promql
+nixos_flake_info{instance=~"vaulttest01.*"}
+```
+
+The `current_rev` label contains the git commit hash of the deployed flake configuration.
+
 ## Architecture
 
 ### Directory Structure

docs/plans/long-term-metrics-storage.md

@@ -0,0 +1,122 @@
+# Long-Term Metrics Storage Options
+
+## Problem Statement
+
+Current Prometheus configuration retains metrics for 30 days (`retentionTime = "30d"`). Extending retention further raises disk usage concerns on the homelab hypervisor with limited local storage.
+
+Prometheus does not support downsampling - it stores all data at full resolution until the retention period expires, then deletes it entirely.
+
+## Current Configuration
+
+Location: `services/monitoring/prometheus.nix`
+
+- **Retention**: 30 days
+- **Scrape interval**: 15s
+- **Features**: Alertmanager, Pushgateway, auto-generated scrape configs from flake hosts
+- **Storage**: Local disk on monitoring01
+
+## Options Evaluated
+
+### Option 1: VictoriaMetrics
+
+VictoriaMetrics is a Prometheus-compatible TSDB with significantly better compression (5-10x smaller storage footprint).
+
+**NixOS Options Available:**
+- `services.victoriametrics.enable`
+- `services.victoriametrics.prometheusConfig` - accepts Prometheus scrape config format
+- `services.victoriametrics.retentionPeriod` - e.g., "6m" for 6 months
+- `services.vmagent` - dedicated scraping agent
+- `services.vmalert` - alerting rules evaluation
+
+**Pros:**
+- Simple migration - single service replacement
+- Same PromQL query language - Grafana dashboards work unchanged
+- Same scrape config format - existing auto-generated configs work as-is
+- 5-10x better compression means 30 days of Prometheus data could become 180+ days
+- Lightweight, single binary
+
+**Cons:**
+- No automatic downsampling (relies on compression alone)
+- Alerting requires switching to vmalert instead of Prometheus alertmanager integration
+- Would need to migrate existing data or start fresh
+
+**Migration Steps:**
+1. Replace `services.prometheus` with `services.victoriametrics`
+2. Move scrape configs to `prometheusConfig`
+3. Set up `services.vmalert` for alerting rules
+4. Update Grafana datasource to VictoriaMetrics port (8428)
+5. Keep Alertmanager for notification routing
+
+### Option 2: Thanos
+
+Thanos extends Prometheus with long-term storage and automatic downsampling by uploading data to object storage.
+
+**NixOS Options Available:**
+- `services.thanos.sidecar` - uploads Prometheus blocks to object storage
+- `services.thanos.compact` - compacts and downsamples data
+- `services.thanos.query` - unified query gateway
+- `services.thanos.query-frontend` - query caching and parallelization
+- `services.thanos.downsample` - dedicated downsampling service
+
+**Downsampling Behavior:**
+- Raw resolution kept for configurable period (default: indefinite)
+- 5-minute resolution created after 40 hours
+- 1-hour resolution created after 10 days
+
+**Retention Configuration (in compactor):**
+```nix
+services.thanos.compact = {
+  retention.resolution-raw = "30d";   # Keep raw for 30 days
+  retention.resolution-5m = "180d";   # Keep 5m samples for 6 months
+  retention.resolution-1h = "2y";     # Keep 1h samples for 2 years
+};
+```
+
+**Pros:**
+- True downsampling - older data uses progressively less storage
+- Keep metrics for years with minimal storage impact
+- Prometheus continues running unchanged
+- Existing Alertmanager integration preserved
+
+**Cons:**
+- Requires object storage (MinIO, S3, or local filesystem)
+- Multiple services to manage (sidecar, compactor, query)
+- More complex architecture
+- Additional infrastructure (MinIO) may be needed
+
+**Required Components:**
+1. Thanos Sidecar (runs alongside Prometheus)
+2. Object storage (MinIO or local filesystem)
+3. Thanos Compactor (handles downsampling)
+4. Thanos Query (provides unified query endpoint)
+
+**Migration Steps:**
+1. Deploy object storage (MinIO or configure filesystem backend)
+2. Add Thanos sidecar pointing to Prometheus data directory
+3. Add Thanos compactor with retention policies
+4. Add Thanos query gateway
+5. Update Grafana datasource to Thanos Query port (10902)
+
+## Comparison
+
+| Aspect | VictoriaMetrics | Thanos |
+|--------|-----------------|--------|
+| Complexity | Low (1 service) | Higher (3-4 services) |
+| Downsampling | No | Yes (automatic) |
+| Storage savings | 5-10x compression | Compression + downsampling |
+| Object storage required | No | Yes |
+| Migration effort | Minimal | Moderate |
+| Grafana changes | Change port only | Change port only |
+| Alerting changes | Need vmalert | Keep existing |
+
+## Recommendation
+
+**Start with VictoriaMetrics** for simplicity. The compression alone may provide 6+ months of retention in the same disk space currently used for 30 days.
+
+If multi-year retention with true downsampling becomes necessary, Thanos can be evaluated later. However, it requires deploying object storage infrastructure (MinIO) which adds operational complexity.
+
+## References
+
+- VictoriaMetrics docs: https://docs.victoriametrics.com/
+- Thanos docs: https://thanos.io/tip/thanos/getting-started.md/
+- NixOS options searched from nixpkgs revision e576e3c9 (NixOS 25.11)

flake.lock

@@ -21,6 +21,27 @@
         "url": "https://git.t-juice.club/torjus/alerttonotify"
       }
     },
+    "homelab-deploy": {
+      "inputs": {
+        "nixpkgs": [
+          "nixpkgs-unstable"
+        ]
+      },
+      "locked": {
+        "lastModified": 1770447502,
+        "narHash": "sha256-xH1PNyE3ydj4udhe1IpK8VQxBPZETGLuORZdSWYRmSU=",
+        "ref": "master",
+        "rev": "79db119d1ca6630023947ef0a65896cc3307c2ff",
+        "revCount": 22,
+        "type": "git",
+        "url": "https://git.t-juice.club/torjus/homelab-deploy"
+      },
+      "original": {
+        "ref": "master",
+        "type": "git",
+        "url": "https://git.t-juice.club/torjus/homelab-deploy"
+      }
+    },
     "labmon": {
       "inputs": {
         "nixpkgs": [
@@ -97,6 +118,7 @@
     "root": {
       "inputs": {
         "alerttonotify": "alerttonotify",
+        "homelab-deploy": "homelab-deploy",
         "labmon": "labmon",
         "nixos-exporter": "nixos-exporter",
         "nixpkgs": "nixpkgs",

flake.nix

@@ -21,6 +21,10 @@
       url = "git+https://git.t-juice.club/torjus/nixos-exporter";
       inputs.nixpkgs.follows = "nixpkgs-unstable";
     };
+    homelab-deploy = {
+      url = "git+https://git.t-juice.club/torjus/homelab-deploy?ref=master";
+      inputs.nixpkgs.follows = "nixpkgs-unstable";
+    };
   };
 
   outputs =
@@ -32,6 +36,7 @@
       alerttonotify,
       labmon,
       nixos-exporter,
+      homelab-deploy,
       ...
     }@inputs:
     let
@@ -58,6 +63,7 @@
         )
         sops-nix.nixosModules.sops
         nixos-exporter.nixosModules.default
+        homelab-deploy.nixosModules.default
         ./modules/homelab
       ];
       allSystems = [
@@ -219,11 +225,12 @@
         { pkgs }:
         {
           default = pkgs.mkShell {
-            packages = with pkgs; [
+            packages = [
-              ansible
+              pkgs.ansible
-              opentofu
+              pkgs.opentofu
-              openbao
+              pkgs.openbao
               (pkgs.callPackage ./scripts/create-host { })
+              homelab-deploy.packages.${pkgs.system}.default
             ];
           };
         }

hosts/ha1/configuration.nix

@@ -57,6 +57,7 @@
 
   # Vault secrets management
   vault.enable = true;
+  homelab.deploy.enable = true;
   vault.secrets.backup-helper = {
     secretPath = "shared/backup/password";
     extractKey = "password";

hosts/http-proxy/configuration.nix

@@ -61,6 +61,7 @@
     "flakes"
   ];
   vault.enable = true;
+  homelab.deploy.enable = true;
 
   nix.settings.tarball-ttl = 0;
   environment.systemPackages = with pkgs; [

hosts/monitoring01/configuration.nix

@@ -58,6 +58,7 @@
 
   # Vault secrets management
   vault.enable = true;
+  homelab.deploy.enable = true;
   vault.secrets.backup-helper = {
     secretPath = "shared/backup/password";
     extractKey = "password";

hosts/nix-cache01/configuration.nix

@@ -55,6 +55,7 @@
     "flakes"
   ];
   vault.enable = true;
+  homelab.deploy.enable = true;
 
   nix.settings.tarball-ttl = 0;
   environment.systemPackages = with pkgs; [

hosts/ns1/configuration.nix

@@ -48,6 +48,7 @@
     "flakes"
   ];
   vault.enable = true;
+  homelab.deploy.enable = true;
 
   homelab.host = {
     role = "dns";

hosts/ns2/configuration.nix

@@ -48,6 +48,7 @@
     "flakes"
   ];
   vault.enable = true;
+  homelab.deploy.enable = true;
 
   homelab.host = {
     role = "dns";

hosts/vaulttest01/configuration.nix

@@ -81,6 +81,7 @@ in
     vim
     wget
     git
+    htop # test deploy verification
   ];
 
   # Open ports in the firewall.
@@ -92,6 +93,7 @@ in
   # Testing config
   # Enable Vault secrets management
   vault.enable = true;
+  homelab.deploy.enable = true;
 
   # Define a test secret
   vault.secrets.test-service = {

modules/homelab/default.nix

@@ -1,6 +1,7 @@
 { ... }:
 {
   imports = [
+    ./deploy.nix
     ./dns.nix
     ./host.nix
     ./monitoring.nix

modules/homelab/deploy.nix

@@ -0,0 +1,16 @@
+{ config, lib, ... }:
+
+{
+  options.homelab.deploy = {
+    enable = lib.mkEnableOption "homelab-deploy listener for NATS-based deployments";
+  };
+
+  config = {
+    assertions = [
+      {
+        assertion = config.homelab.deploy.enable -> config.vault.enable;
+        message = "homelab.deploy.enable requires vault.enable to be true (needed for NKey secret)";
+      }
+    ];
+  };
+}

services/nats/default.nix

@@ -1,16 +1,18 @@
 { ... }:
 {
-  homelab.monitoring.scrapeTargets = [{
+  homelab.monitoring.scrapeTargets = [
-    job_name = "nats";
+    {
-    port = 7777;
+      job_name = "nats";
-  }];
+      port = 7777;
+    }
+  ];
 
   services.prometheus.exporters.nats = {
     enable = true;
     url = "http://localhost:8222";
     extraFlags = [
-      "-varz"    # General server info
+      "-varz" # General server info
-      "-connz"   # Connection info
+      "-connz" # Connection info
       "-jsz=all" # JetStream info
     ];
   };
@@ -38,6 +40,48 @@
             }
           ];
         };
+
+        DEPLOY = {
+          users = [
+            # Shared listener (all hosts use this)
+            {
+              nkey = "UCCZJSUGLCSLBBKHBPL4QA66TUMQUGIXGLIFTWDEH43MGWM3LDD232X4";
+              permissions = {
+                subscribe = [
+                  "deploy.test.>"
+                  "deploy.prod.>"
+                  "deploy.discover"
+                ];
+                publish = [
+                  "deploy.responses.>"
+                  "deploy.discover"
+                ];
+              };
+            }
+            # Test deployer (MCP without admin)
+            {
+              nkey = "UBR66CX2ZNY5XNVQF5VBG4WFAF54LSGUYCUNNCEYRILDQ4NXDAD2THZU";
+              permissions = {
+                publish = [
+                  "deploy.test.>"
+                  "deploy.discover"
+                ];
+                subscribe = [
+                  "deploy.responses.>"
+                  "deploy.discover"
+                ];
+              };
+            }
+            # Admin deployer (full access)
+            {
+              nkey = "UD2BFB7DLM67P5UUVCKBUJMCHADIZLGGVUNSRLZE2ZC66FW2XT44P73Y";
+              permissions = {
+                publish = [ "deploy.>" ];
+                subscribe = [ "deploy.>" ];
+              };
+            }
+          ];
+        };
       };
       system_account = "ADMIN";
       jetstream = {

system/default.nix

@@ -3,6 +3,7 @@
   imports = [
     ./acme.nix
     ./autoupgrade.nix
+    ./homelab-deploy.nix
     ./monitoring
     ./motd.nix
     ./packages.nix

system/homelab-deploy.nix

@@ -0,0 +1,37 @@
+{ config, lib, ... }:
+
+let
+  hostCfg = config.homelab.host;
+in
+{
+  config = lib.mkIf config.homelab.deploy.enable {
+    # Fetch listener NKey from Vault
+    vault.secrets.homelab-deploy-nkey = {
+      secretPath = "shared/homelab-deploy/listener-nkey";
+      extractKey = "nkey";
+    };
+
+    # Enable homelab-deploy listener
+    services.homelab-deploy.listener = {
+      enable = true;
+      tier = hostCfg.tier;
+      role = hostCfg.role;
+      natsUrl = "nats://nats1.home.2rjus.net:4222";
+      nkeyFile = "/run/secrets/homelab-deploy-nkey";
+      flakeUrl = "git+https://git.t-juice.club/torjus/nixos-servers.git";
+      metrics.enable = true;
+    };
+
+    # Expose metrics for Prometheus scraping
+    homelab.monitoring.scrapeTargets = [{
+      job_name = "homelab-deploy";
+      port = 9972;
+    }];
+
+    # Ensure listener starts after vault secret is available
+    systemd.services.homelab-deploy-listener = {
+      after = [ "vault-secret-homelab-deploy-nkey.service" ];
+      requires = [ "vault-secret-homelab-deploy-nkey.service" ];
+    };
+  };
+}

terraform/vault/approle.tf

@@ -4,6 +4,17 @@ resource "vault_auth_backend" "approle" {
   path = "approle"
 }
 
+# Shared policy for homelab-deploy (all hosts need this for NATS-based deployments)
+resource "vault_policy" "homelab_deploy" {
+  name = "homelab-deploy"
+
+  policy = <<EOT
+path "secret/data/shared/homelab-deploy/*" {
+  capabilities = ["read", "list"]
+}
+EOT
+}
+
 # Define host access policies
 locals {
   host_policies = {
@@ -89,6 +100,12 @@ locals {
         "secret/data/hosts/nix-cache01/*",
       ]
     }
+
+    "vaulttest01" = {
+      paths = [
+        "secret/data/hosts/vaulttest01/*",
+      ]
+    }
   }
 }
 
@@ -114,7 +131,7 @@ resource "vault_approle_auth_backend_role" "hosts" {
   backend   = vault_auth_backend.approle.path
   role_name = each.key
   token_policies = concat(
-    ["${each.key}-policy"],
+    ["${each.key}-policy", "homelab-deploy"],
     lookup(each.value, "extra_policies", [])
   )
 

terraform/vault/secrets.tf

@@ -92,6 +92,22 @@ locals {
       auto_generate = false
       data          = { token = var.actions_token_1 }
     }
+
+    # Homelab-deploy NKeys
+    "shared/homelab-deploy/listener-nkey" = {
+      auto_generate = false
+      data          = { nkey = var.homelab_deploy_listener_nkey }
+    }
+
+    "shared/homelab-deploy/test-deployer-nkey" = {
+      auto_generate = false
+      data          = { nkey = var.homelab_deploy_test_deployer_nkey }
+    }
+
+    "shared/homelab-deploy/admin-deployer-nkey" = {
+      auto_generate = false
+      data          = { nkey = var.homelab_deploy_admin_deployer_nkey }
+    }
   }
 }
 

terraform/vault/variables.tf

@@ -52,3 +52,24 @@ variable "actions_token_1" {
   sensitive   = true
 }
 
+variable "homelab_deploy_listener_nkey" {
+  description = "NKey seed for homelab-deploy listeners"
+  type        = string
+  default     = "PLACEHOLDER"
+  sensitive   = true
+}
+
+variable "homelab_deploy_test_deployer_nkey" {
+  description = "NKey seed for test-tier deployer"
+  type        = string
+  default     = "PLACEHOLDER"
+  sensitive   = true
+}
+
+variable "homelab_deploy_admin_deployer_nkey" {
+  description = "NKey seed for admin deployer"
+  type        = string
+  default     = "PLACEHOLDER"
+  sensitive   = true
+}
+