.mcp.json

@@ -31,7 +31,8 @@
         "--",
         "mcp",
         "--nats-url", "nats://nats1.home.2rjus.net:4222",
-        "--nkey-file", "/home/torjus/.config/homelab-deploy/test-deployer.nkey"
+        "--nkey-file", "/home/torjus/.config/homelab-deploy/test-deployer.nkey",
+        "--enable-builds"
       ]
     },
     "git-explorer": {

docs/plans/nix-cache-reprovision.md

@@ -6,207 +6,144 @@ Reprovision `nix-cache01` using the OpenTofu workflow, and improve the build/cac
 1. NATS-based remote build triggering (replacing the current bash script)
 2. Safer flake update workflow that validates builds before pushing to master
 
+## Status
+
+**Phase 1: New Build Host** - COMPLETE
+**Phase 2: NATS Build Triggering** - COMPLETE
+**Phase 3: Safe Flake Update Workflow** - NOT STARTED
+**Phase 4: Decommission Old System** - NOT STARTED
+
+## Completed Work
+
+### New Build Host (nix-cache02)
+
+Instead of reprovisioning nix-cache01 in-place, we created a new host `nix-cache02` at 10.69.13.25:
+
+- **Specs**: 8 CPU cores, 16GB RAM (temporarily, will increase to 24GB after nix-cache01 decommissioned), 200GB disk
+- **Provisioned via OpenTofu** with automatic Vault credential bootstrapping
+- **Builder service** configured with two repos:
+  - `nixos-servers` → `git+https://git.t-juice.club/torjus/nixos-servers.git`
+  - `nixos` (gunter) → `git+https://git.t-juice.club/torjus/nixos.git`
+
+### NATS-Based Build Triggering
+
+The `homelab-deploy` tool was extended with a builder mode:
+
+**NATS Subjects:**
+- `build.<repo>.<target>` - e.g., `build.nixos-servers.all` or `build.nixos-servers.ns1`
+
+**NATS Permissions (in DEPLOY account):**
+| User | Publish | Subscribe |
+|------|---------|-----------|
+| Builder | `build.responses.>` | `build.>` |
+| Test deployer | `deploy.test.>`, `deploy.discover`, `build.>` | `deploy.responses.>`, `deploy.discover`, `build.responses.>` |
+| Admin deployer | `deploy.>`, `build.>` | `deploy.>`, `build.responses.>` |
+
+**Vault Secrets:**
+- `shared/homelab-deploy/builder-nkey` - NKey seed for builder authentication
+
+**NixOS Configuration:**
+- `hosts/nix-cache02/builder.nix` - Builder service configuration
+- `services/nats/default.nix` - Updated with builder NATS user
+
+**MCP Integration:**
+- `.mcp.json` updated with `--enable-builds` flag
+- Build tool available via MCP for Claude Code
+
+**Tested:**
+- Single host build: `build nixos-servers testvm01` (~30s)
+- All hosts build: `build nixos-servers all` (16 hosts in ~226s)
+
 ## Current State
 
-### Host Configuration
+### Old System (nix-cache01)
-- `nix-cache01` at 10.69.13.15 serves the binary cache via Harmonia
+- Still running at 10.69.13.15
-- Runs Gitea Actions runner for CI workflows
+- Serves binary cache via Harmonia
-- Has `homelab.deploy.enable = true` (already supports NATS-based deployment)
+- Runs Gitea Actions runner
-- Uses a dedicated XFS volume at `/nix` for cache storage
+- Has the old `build-flakes.sh` timer (every 30 min)
+- Will be decommissioned after nix-cache02 is fully validated
 
-### Current Build System (`services/nix-cache/build-flakes.sh`)
+### New System (nix-cache02)
-- Runs every 30 minutes via systemd timer
+- Running at 10.69.13.25
-- Clones/pulls two repos: `nixos-servers` and `nixos` (gunter)
+- Builder service active, responding to NATS build requests
-- Builds all hosts with `nixos-rebuild build` (no blacklist despite docs mentioning it)
+- Metrics exposed on port 9973 (`homelab-deploy-builder` job)
-- Pushes success/failure metrics to pushgateway
+- Does NOT yet have:
-- Simple but has no filtering, no parallelism, no remote triggering
+  - Harmonia (binary cache server)
+  - Actions runner
+  - Cache signing key
 
-### Current Flake Update Workflow (`.github/workflows/flake-update.yaml`)
+## Remaining Work
-- Runs daily at midnight via cron
-- Runs `nix flake update --commit-lock-file`
-- Pushes directly to master
-- No build validation — can push broken inputs
 
-## Improvement 1: NATS-Based Remote Build Triggering
+### Phase 3: Safe Flake Update Workflow
-
-### Design
-
-Extend the existing `homelab-deploy` tool to support a "build" command that triggers builds on the cache host. This reuses the NATS infrastructure already in place.
-
-| Approach | Pros | Cons |
-|----------|------|------|
-| Extend homelab-deploy | Reuses existing NATS auth, NKey handling, CLI | Adds scope to existing tool |
-| New nix-cache-tool | Clean separation | Duplicate NATS boilerplate, new credentials |
-| Gitea Actions webhook | No custom tooling | Less flexible, tied to Gitea |
-
-**Recommendation:** Extend `homelab-deploy` with a build subcommand. The tool already has NATS client code, authentication handling, and a listener module in NixOS.
-
-### Implementation
-
-1. Add new message type to homelab-deploy: `build.<host>` subject
-2. Listener on nix-cache01 subscribes to `build.>` wildcard
-3. On message receipt, builds the specified host and returns success/failure
-4. CLI command: `homelab-deploy build <hostname>` or `homelab-deploy build --all`
-
-### Benefits
-- Trigger rebuild for specific host to ensure it's cached
-- Could be called from CI after merging PRs
-- Reuses existing NATS infrastructure and auth
-- Progress/status could stream back via NATS reply
-
-## Improvement 2: Smarter Flake Update Workflow
-
-### Current Problems
-1. Updates can push breaking changes to master
-2. No visibility into what broke when it does
-3. Hosts that auto-update can pull broken configs
-
-### Proposed Workflow
-
-```
-┌─────────────────────────────────────────────────────────────────┐
-│                    Flake Update Workflow                         │
-├─────────────────────────────────────────────────────────────────┤
-│  1. nix flake update (on feature branch)                        │
-│  2. Build ALL hosts locally                                      │
-│  3. If all pass → fast-forward merge to master                  │
-│  4. If any fail → create PR with failure logs attached          │
-└─────────────────────────────────────────────────────────────────┘
-```
-
-### Implementation Options
-
-| Option | Description | Pros | Cons |
-|--------|-------------|------|------|
-| **A: Self-hosted runner** | Build on nix-cache01 | Fast (local cache), simple | Ties up cache host during build |
-| **B: Gitea Actions only** | Use container runner | Clean separation | Slow (no cache), resource limits |
-| **C: Hybrid** | Trigger builds on nix-cache01 via NATS from Actions | Best of both | More complex |
-
-**Recommendation:** Option A with nix-cache01 as the runner. The host is already running Gitea Actions runner and has the cache. Building all ~16 hosts is disk I/O heavy but feasible on dedicated hardware.
-
-### Workflow Steps
-
-1. Workflow runs on schedule (daily or weekly)
-2. Creates branch `flake-update/YYYY-MM-DD`
-3. Runs `nix flake update --commit-lock-file`
-4. Builds each host: `nix build .#nixosConfigurations.<host>.config.system.build.toplevel`
-5. If all succeed:
-   - Fast-forward merge to master
-   - Delete feature branch
-6. If any fail:
-   - Create PR from the update branch
-   - Attach build logs as PR comment
-   - Label PR with `needs-review` or `build-failure`
-   - Do NOT merge automatically
-
-### Workflow File Changes
-
-```yaml
-# New: .github/workflows/flake-update-safe.yaml
-name: Safe flake update
-on:
-  schedule:
-    - cron: "0 2 * * 0"  # Weekly on Sunday at 2 AM
-  workflow_dispatch:  # Manual trigger
-
-jobs:
-  update-and-validate:
-    runs-on: homelab  # Use self-hosted runner on nix-cache01
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: master
-          fetch-depth: 0  # Need full history for merge
-
-      - name: Create update branch
-        run: |
-          BRANCH="flake-update/$(date +%Y-%m-%d)"
-          git checkout -b "$BRANCH"
-
-      - name: Update flake
-        run: nix flake update --commit-lock-file
-
-      - name: Build all hosts
-        id: build
-        run: |
-          FAILED=""
-          for host in $(nix flake show --json | jq -r '.nixosConfigurations | keys[]'); do
-            echo "Building $host..."
-            if ! nix build ".#nixosConfigurations.$host.config.system.build.toplevel" 2>&1 | tee "build-$host.log"; then
-              FAILED="$FAILED $host"
-            fi
-          done
-          echo "failed=$FAILED" >> $GITHUB_OUTPUT
-
-      - name: Merge to master (if all pass)
-        if: steps.build.outputs.failed == ''
-        run: |
-          git checkout master
-          git merge --ff-only "$BRANCH"
-          git push origin master
-          git push origin --delete "$BRANCH"
-
-      - name: Create PR (if any fail)
-        if: steps.build.outputs.failed != ''
-        run: |
-          git push origin "$BRANCH"
-          # Create PR via Gitea API with build logs
-          # ... (PR creation with log attachment)
-```
-
-## Migration Steps
-
-### Phase 1: Reprovision Host via OpenTofu
-
-1. Add `nix-cache01` to `terraform/vms.tf`:
-   ```hcl
-   "nix-cache01" = {
-     ip        = "10.69.13.15/24"
-     cpu_cores = 4
-     memory    = 8192
-     disk_size = "100G"  # Larger for nix store
-   }
-   ```
-
-2. Shut down existing nix-cache01 VM
-3. Run `tofu apply` to provision new VM
-4. Verify bootstrap completes and cache is serving
-
-**Note:** The cache will be cold after reprovision. Run initial builds to populate.
-
-### Phase 2: Add Build Triggering to homelab-deploy
-
-1. Add `build` command to homelab-deploy CLI
-2. Add listener handler in NixOS module for `build.*` subjects
-3. Update nix-cache01 config to enable build listener
-4. Test with `homelab-deploy build testvm01`
-
-### Phase 3: Implement Safe Flake Update Workflow
 
 1. Create `.github/workflows/flake-update-safe.yaml`
 2. Disable or remove old `flake-update.yaml`
 3. Test manually with `workflow_dispatch`
 4. Monitor first automated run
 
-### Phase 4: Remove Old Build Script
+### Phase 4: Complete Migration
 
-1. After new workflow is stable, remove:
+1. **Add Harmonia to nix-cache02** - Copy cache signing key, configure service
-   - `services/nix-cache/build-flakes.nix`
+2. **Add Actions runner to nix-cache02** - Configure with Vault token
-   - `services/nix-cache/build-flakes.sh`
+3. **Update DNS** - Point `nix-cache.home.2rjus.net` to nix-cache02
-2. The new workflow handles scheduled builds
+4. **Increase RAM** - Bump to 24GB after nix-cache01 is gone
+5. **Decommission nix-cache01**:
+   - Remove from `terraform/vms.tf`
+   - Remove old build script (`services/nix-cache/build-flakes.nix`, `build-flakes.sh`)
+   - Archive or delete host config
+
+### Phase 5: Scheduled Builds (Optional)
+
+Add a systemd timer on nix-cache02 to trigger periodic builds via NATS:
+
+```nix
+systemd.services.scheduled-build = {
+  script = ''
+    homelab-deploy build nixos-servers --all
+    homelab-deploy build nixos --all
+  '';
+};
+systemd.timers.scheduled-build = {
+  wantedBy = [ "timers.target" ];
+  timerConfig.OnCalendar = "*-*-* *:30:00";
+};
+```
+
+Or trigger builds from CI after merges to master.
+
+## Resolved Questions
+
+- **Parallel vs sequential builds?** Sequential - hosts share packages, subsequent builds are fast after first
+- **What about gunter?** Configured as `nixos` repo in builder settings
+- **Disk size?** 200GB for new host
+- **Build host specs?** 8 cores, 16-24GB RAM matches current nix-cache01
+
+### Phase 6: Observability
+
+1. **Alerting rules** for build failures:
+   ```promql
+   # Alert if any build fails
+   increase(homelab_deploy_build_host_total{status="failure"}[1h]) > 0
+
+   # Alert if no successful builds in 24h (scheduled builds stopped)
+   time() - homelab_deploy_build_last_success_timestamp > 86400
+   ```
+
+2. **Grafana dashboard** for build metrics:
+   - Build success/failure rate over time
+   - Average build duration per host (histogram)
+   - Build frequency (builds per hour/day)
+   - Last successful build timestamp per repo
+
+Available metrics:
+- `homelab_deploy_builds_total{repo, status}` - total builds by repo and status
+- `homelab_deploy_build_host_total{repo, host, status}` - per-host build counts
+- `homelab_deploy_build_duration_seconds_{bucket,sum,count}` - build duration histogram
+- `homelab_deploy_build_last_timestamp{repo}` - last build attempt
+- `homelab_deploy_build_last_success_timestamp{repo}` - last successful build
 
 ## Open Questions
 
-- [ ] What runner labels should the self-hosted runner use for the update workflow?
+- [ ] When to cut over DNS from nix-cache01 to nix-cache02?
-- [ ] Should we build hosts in parallel (faster) or sequentially (easier to debug)?
+- [ ] Keep Actions runner on nix-cache02 or separate host?
-- [ ] How long to keep flake-update PRs open before auto-closing stale ones?
+- [ ] Implement safe flake update workflow before or after full migration?
-- [ ] Should successful updates trigger a NATS notification to rebuild all hosts?
-- [ ] What to do about `gunter` (external nixos repo) - include in validation?
-- [ ] Disk size for new nix-cache01 - is 100G enough for cache + builds?
-
-## Notes
-
-- The existing `homelab.deploy.enable = true` on nix-cache01 means it already has NATS connectivity
-- The Harmonia service and cache signing key will work the same after reprovision
-- Actions runner token is in Vault, will be provisioned automatically
-- Consider adding a `homelab.host.role = "build-host"` label for monitoring/filtering

flake.lock

@@ -28,11 +28,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1770648258,
+        "lastModified": 1770758165,
-        "narHash": "sha256-sExxD8N9Q0RrHIoppOV6qp4jcJirLVjpQd20C72V78I=",
+        "narHash": "sha256-jjCcxhZavm2r7gjZ2+FNOMvTYQsRlIa9ijPICK0HVk4=",
         "ref": "master",
-        "rev": "277a49a666347e2e2ae67128cf732956a9c3be56",
+        "rev": "a8aab16d0e7400aaa00500d08c12734da3b638e0",
-        "revCount": 27,
+        "revCount": 32,
         "type": "git",
         "url": "https://git.t-juice.club/torjus/homelab-deploy"
       },

hosts/nix-cache02/builder.nix

@@ -0,0 +1,44 @@
+{ config, ... }:
+{
+  # Fetch builder NKey from Vault
+  vault.secrets.builder-nkey = {
+    secretPath = "shared/homelab-deploy/builder-nkey";
+    extractKey = "nkey";
+    outputDir = "/run/secrets/builder-nkey";
+    services = [ "homelab-deploy-builder" ];
+  };
+
+  # Configure the builder service
+  services.homelab-deploy.builder = {
+    enable = true;
+    natsUrl = "nats://nats1.home.2rjus.net:4222";
+    nkeyFile = "/run/secrets/builder-nkey";
+
+    settings.repos = {
+      nixos-servers = {
+        url = "git+https://git.t-juice.club/torjus/nixos-servers.git";
+        defaultBranch = "master";
+      };
+      nixos = {
+        url = "git+https://git.t-juice.club/torjus/nixos.git";
+        defaultBranch = "master";
+      };
+    };
+
+    metrics.enable = true;
+  };
+
+  # Expose builder metrics for Prometheus scraping
+  homelab.monitoring.scrapeTargets = [
+    {
+      job_name = "homelab-deploy-builder";
+      port = 9973;
+    }
+  ];
+
+  # Ensure builder starts after vault secret is available
+  systemd.services.homelab-deploy-builder = {
+    after = [ "vault-secret-builder-nkey.service" ];
+    requires = [ "vault-secret-builder-nkey.service" ];
+  };
+}

hosts/nix-cache02/default.nix

@@ -1,5 +1,6 @@
 { ... }: {
   imports = [
     ./configuration.nix
+    ./builder.nix
   ];
 }

services/nats/default.nix

@@ -74,10 +74,12 @@
                 publish = [
                   "deploy.test.>"
                   "deploy.discover"
+                  "build.>"
                 ];
                 subscribe = [
                   "deploy.responses.>"
                   "deploy.discover"
+                  "build.responses.>"
                 ];
               };
             }
@@ -85,8 +87,22 @@
             {
               nkey = "UD2BFB7DLM67P5UUVCKBUJMCHADIZLGGVUNSRLZE2ZC66FW2XT44P73Y";
               permissions = {
-                publish = [ "deploy.>" ];
+                publish = [
-                subscribe = [ "deploy.>" ];
+                  "deploy.>"
+                  "build.>"
+                ];
+                subscribe = [
+                  "deploy.>"
+                  "build.responses.>"
+                ];
+              };
+            }
+            # Builder (subscribes to build requests, publishes responses)
+            {
+              nkey = "UB4PUHGKAWAK6OS62FX7DOQTPFFJTLZZBTKCOCAXDP75H3NSMWAEDJ7E";
+              permissions = {
+                subscribe = [ "build.>" ];
+                publish = [ "build.responses.>" ];
               };
             }
           ];

terraform/vault/hosts-generated.tf

@@ -36,6 +36,7 @@ locals {
     "nix-cache02" = {
       paths = [
         "secret/data/hosts/nix-cache02/*",
+        "secret/data/shared/homelab-deploy/*",
       ]
     }
   

terraform/vault/secrets.tf

@@ -103,6 +103,11 @@ locals {
       data          = { nkey = var.homelab_deploy_admin_deployer_nkey }
     }
 
+    "shared/homelab-deploy/builder-nkey" = {
+      auto_generate = false
+      data          = { nkey = var.homelab_deploy_builder_nkey }
+    }
+
     # Kanidm idm_admin password
     "kanidm/idm-admin-password" = {
       auto_generate   = true

terraform/vault/variables.tf

@@ -73,6 +73,13 @@ variable "homelab_deploy_admin_deployer_nkey" {
   sensitive   = true
 }
 
+variable "homelab_deploy_builder_nkey" {
+  description = "NKey seed for homelab-deploy builder"
+  type        = string
+  default     = "PLACEHOLDER"
+  sensitive   = true
+}
+
 variable "nixos_exporter_nkey" {
   description = "NKey seed for nixos-exporter NATS authentication"
   type        = string