setting forceImportRoot to false

.github/workflows/fix_eval_warnings.yml

@@ -1,30 +0,0 @@
-name: fix_eval_warnings
-on:
-  workflow_run:
-    workflows: ["build_systems"]
-    types: [completed]
-
-jobs:
-  check-warnings:
-    if: >-
-      github.event.workflow_run.conclusion != 'cancelled' &&
-      github.event.workflow_run.head_branch == 'main' &&
-      (github.event.workflow_run.event == 'push' || github.event.workflow_run.event == 'schedule')
-    runs-on: self-hosted
-    permissions:
-      contents: write
-      pull-requests: write
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Fix eval warnings
-        env:
-          GH_TOKEN: ${{ secrets.GH_TOKEN_FOR_UPDATES }}
-        run: >-
-          nix develop .#devShells.x86_64-linux.default -c
-          python -m python.eval_warnings.main
-          --run-id "${{ github.event.workflow_run.id }}"
-          --repo "${{ github.repository }}"
-          --ollama-url "${{ secrets.OLLAMA_URL }}"
-          --run-url "${{ github.event.workflow_run.html_url }}"

.github/workflows/merge_flake_lock_update.yml

@@ -6,24 +6,18 @@ on:
 
 jobs:
   merge:
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
 
     permissions:
       contents: write
       pull-requests: write
 
     steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-
       - name: merge_flake_lock_update
-        run: |
+        run: >-
-          pr_number=$(gh pr list --state open --author RichieCahill --label flake_lock_update --json number --jq '.[0].number')
+          nix develop .#devShells.x86_64-linux.default -c
-          echo "pr_number=$pr_number" >> $GITHUB_ENV
+          python -m python.gitea_flake_lock merge
-          if [ -n "$pr_number" ]; then
+          --repo "${{ github.repository }}"
-            gh pr merge "$pr_number" --rebase
-          else
-            echo "No open PR found with label flake_lock_update"
-          fi
         env:
-          GITHUB_TOKEN: ${{ secrets.GH_TOKEN_FOR_UPDATES }}
+          GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
+          GITEA_URL: https://gitea.tmmworkshop.com

.github/workflows/pytest.yml

@@ -7,7 +7,6 @@ on:
   pull_request:
     branches:
       - main
-  merge_group:
 
 jobs:
   pytest:

.github/workflows/update-flake-lock.yml

@@ -6,18 +6,20 @@ on:
 
 jobs:
   lockfile:
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
+    permissions:
+      contents: write
+      pull-requests: write
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
-      - name: Install Nix
-        uses: DeterminateSystems/nix-installer-action@main
       - name: Update flake.lock
-        uses: DeterminateSystems/update-flake-lock@main
+        run: nix flake update
-        with:
+      - name: Create or update flake.lock PR
-          token: ${{ secrets.GH_TOKEN_FOR_UPDATES }}
+        env:
-          pr-title: "Update flake.lock"
+          GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
-          pr-labels: |
+          GITEA_URL: https://gitea.tmmworkshop.com
-            dependencies
+        run: >-
-            automated
+          nix develop .#devShells.x86_64-linux.default -c
-            flake_lock_update
+          python -m python.gitea_flake_lock update
+          --repo "${{ github.repository }}"

common/global/default.nix

@@ -23,7 +23,10 @@
   boot = {
     tmp.useTmpfs = true;
     kernelPackages = lib.mkDefault pkgs.linuxPackages_6_12;
-    zfs.package = lib.mkDefault pkgs.zfs_2_4;
+    zfs = {
+      package = lib.mkDefault pkgs.zfs_2_4;
+      forceImportRoot = lib.mkDefault false;
+    };
   };
 
   hardware.enableRedistributableFirmware = true;
@@ -37,10 +40,17 @@
 
   nixpkgs = {
     overlays = builtins.attrValues outputs.overlays;
-    config.allowUnfree = true;
+    config = {
+      allowUnfree = true;
+      permittedInsecurePackages = [
+        "openssl-1.1.1w" # This is for discord-canary
+      ];
+    };
   };
 
   services = {
+    dbus.implementation = "dbus";
+
     # firmware update
     fwupd.enable = true;
 

common/optional/monitoring-agent.nix

@@ -0,0 +1,256 @@
+{
+  config,
+  lib,
+  pkgs,
+  ...
+}:
+let
+  monitoringInterface = "ztwfunumly";
+  nodeTextfileDir = "/var/lib/prometheus-node-exporter-textfile";
+
+  mkProcessNameTemplate =
+    perPid: template: if perPid then "${template}:{{.PID}}:{{.StartTime}}" else template;
+
+  mkProcessMatchers = perPid: [
+    {
+      name = mkProcessNameTemplate perPid "{{.Username}}:{{.Matches.Module}}";
+      cmdline = [ "^/nix/store[^ ]*/bin/python[^ ]* -m (?P<Module>[^ ]+)" ];
+    }
+    {
+      name = mkProcessNameTemplate perPid "{{.Username}}:{{.Matches.Wrapped}}";
+      cmdline = [
+        "^/nix/store[^ ]*/bin/python[^ ]* /nix/store[^ ]*/bin/\\.?(?P<Wrapped>[^ /]+?)(?:-wrapped)?(?:\\s|$)"
+      ];
+    }
+    {
+      name = mkProcessNameTemplate perPid "{{.Username}}:{{.Matches.Wrapped}}";
+      cmdline = [
+        "^/nix/store[^ ]*/bin/node /nix/store[^ ]*-(?P<Wrapped>[A-Za-z0-9._+-]+)-[0-9][^ /]*/"
+      ];
+    }
+    {
+      name = mkProcessNameTemplate perPid "{{.Username}}:{{.Matches.Wrapped}}";
+      cmdline = [ "^/nix/store[^ ]*/(?:bin/|lib/[^ ]*/)?\\.?(?P<Wrapped>[^ /]+?)(?:-wrapped)?(?:\\s|$)" ];
+    }
+    {
+      name = mkProcessNameTemplate perPid "{{.Username}}:{{.ExeBase}}";
+      cmdline = [ ".+" ];
+    }
+  ];
+
+  perPidConfig = pkgs.writeText "process-exporter-per-pid.yaml" (
+    builtins.toJSON {
+      process_names = mkProcessMatchers true;
+    }
+  );
+
+  zpoolLatencyScript = pkgs.writeShellScript "zpool-latency-exporter" ''
+        set -euo pipefail
+
+        out_dir=${lib.escapeShellArg nodeTextfileDir}
+        host=${lib.escapeShellArg config.networking.hostName}
+        tmp_file="$(mktemp "$out_dir/zpool.prom.XXXXXX")"
+        trap 'rm -f "$tmp_file"' EXIT
+
+        pools="$(zpool list -H -o name | paste -sd, -)"
+
+        cat >"$tmp_file" <<'EOF'
+    # HELP zpool_iostat_total_wait_read_ns Average total read wait time reported by zpool iostat.
+    # TYPE zpool_iostat_total_wait_read_ns gauge
+    # HELP zpool_iostat_total_wait_write_ns Average total write wait time reported by zpool iostat.
+    # TYPE zpool_iostat_total_wait_write_ns gauge
+    # HELP zpool_iostat_disk_wait_read_ns Average disk read wait time reported by zpool iostat.
+    # TYPE zpool_iostat_disk_wait_read_ns gauge
+    # HELP zpool_iostat_disk_wait_write_ns Average disk write wait time reported by zpool iostat.
+    # TYPE zpool_iostat_disk_wait_write_ns gauge
+    # HELP zpool_iostat_syncq_wait_read_ns Average synchronous queue read wait time reported by zpool iostat.
+    # TYPE zpool_iostat_syncq_wait_read_ns gauge
+    # HELP zpool_iostat_syncq_wait_write_ns Average synchronous queue write wait time reported by zpool iostat.
+    # TYPE zpool_iostat_syncq_wait_write_ns gauge
+    # HELP zpool_iostat_asyncq_wait_read_ns Average asynchronous queue read wait time reported by zpool iostat.
+    # TYPE zpool_iostat_asyncq_wait_read_ns gauge
+    # HELP zpool_iostat_asyncq_wait_write_ns Average asynchronous queue write wait time reported by zpool iostat.
+    # TYPE zpool_iostat_asyncq_wait_write_ns gauge
+    EOF
+
+        zpool iostat -Hplvy -y 1 1 | awk -F '\t' -v host="$host" -v pools="$pools" '
+          function esc(str, out) {
+            out = str
+            gsub(/\\/, "\\\\", out)
+            gsub(/"/, "\\\"", out)
+            return out
+          }
+
+          function emit(metric, pool, vdev, value) {
+            if (value == "" || value == "-") {
+              return
+            }
+
+            printf "%s{host=\"%s\",pool=\"%s\",vdev=\"%s\"} %s\n",
+              metric,
+              esc(host),
+              esc(pool),
+              esc(vdev),
+              value
+          }
+
+          BEGIN {
+            split(pools, pool_names, ",")
+            for (idx in pool_names) {
+              if (pool_names[idx] != "") {
+                known_pools[pool_names[idx]] = 1
+              }
+            }
+          }
+
+          NF == 0 {
+            next
+          }
+
+          {
+            row_name = $1
+
+            if (row_name in known_pools) {
+              current_pool = row_name
+              current_vdev = "_pool"
+            } else if (current_pool == "") {
+              next
+            } else {
+              current_vdev = row_name
+            }
+
+            emit("zpool_iostat_total_wait_read_ns", current_pool, current_vdev, $8)
+            emit("zpool_iostat_total_wait_write_ns", current_pool, current_vdev, $9)
+            emit("zpool_iostat_disk_wait_read_ns", current_pool, current_vdev, $10)
+            emit("zpool_iostat_disk_wait_write_ns", current_pool, current_vdev, $11)
+            emit("zpool_iostat_syncq_wait_read_ns", current_pool, current_vdev, $12)
+            emit("zpool_iostat_syncq_wait_write_ns", current_pool, current_vdev, $13)
+            emit("zpool_iostat_asyncq_wait_read_ns", current_pool, current_vdev, $14)
+            emit("zpool_iostat_asyncq_wait_write_ns", current_pool, current_vdev, $15)
+          }
+        ' >>"$tmp_file"
+
+        mv "$tmp_file" "$out_dir/zpool.prom"
+        trap - EXIT
+  '';
+in
+{
+  networking.firewall.interfaces.${monitoringInterface}.allowedTCPPorts = [
+    9100
+    9134
+    9256
+    9257
+    9633
+  ];
+
+  services.prometheus.exporters = {
+    node = {
+      enable = true;
+      enabledCollectors = [
+        "pressure"
+        "processes"
+        "systemd"
+      ];
+      extraFlags = [ "--collector.textfile.directory=${nodeTextfileDir}" ];
+    };
+
+    process = {
+      enable = true;
+      user = "root";
+      group = "root";
+      settings.process_names = mkProcessMatchers false;
+      extraFlags = [
+        "-gather-smaps=false"
+        "-remove-empty-groups=true"
+        "-threads=false"
+      ];
+    };
+
+    smartctl.enable = true;
+    zfs.enable = true;
+  };
+
+  programs.atop = {
+    enable = true;
+    atopService.enable = true;
+    atopRotateTimer.enable = true;
+    atopacctService.enable = true;
+    settings.interval = 30;
+  };
+
+  systemd = {
+    services = {
+      prometheus-process-pid-exporter = {
+        description = "Prometheus process exporter with per-PID naming";
+        wantedBy = [ "multi-user.target" ];
+        after = [ "network.target" ];
+        serviceConfig = {
+          ExecStart = ''
+            ${pkgs.prometheus-process-exporter}/bin/process-exporter \
+              --web.listen-address 0.0.0.0:9257 \
+              --config.path ${perPidConfig} \
+              -children=false \
+              -gather-smaps=false \
+              -remove-empty-groups=true \
+              -threads=false
+          '';
+          User = "root";
+          Group = "root";
+          Restart = "always";
+          WorkingDirectory = "/tmp";
+          CapabilityBoundingSet = [ "" ];
+          DeviceAllow = [ "" ];
+          LockPersonality = true;
+          MemoryDenyWriteExecute = true;
+          NoNewPrivileges = true;
+          PrivateDevices = true;
+          PrivateTmp = true;
+          ProtectClock = true;
+          ProtectControlGroups = true;
+          ProtectHome = true;
+          ProtectHostname = true;
+          ProtectKernelLogs = true;
+          ProtectKernelModules = true;
+          ProtectKernelTunables = true;
+          ProtectSystem = "strict";
+          RemoveIPC = true;
+          RestrictAddressFamilies = [
+            "AF_INET"
+            "AF_INET6"
+          ];
+          RestrictNamespaces = true;
+          RestrictRealtime = true;
+          RestrictSUIDSGID = true;
+          SystemCallArchitectures = "native";
+          UMask = "0077";
+        };
+      };
+
+      zpool-latency-exporter = {
+        description = "Exports ZFS latency metrics for node_exporter textfile collection";
+        after = [ "zfs-import.target" ];
+        requires = [ "zfs-import.target" ];
+        path = [
+          config.boot.zfs.package
+          pkgs.coreutils
+          pkgs.gawk
+        ];
+        serviceConfig = {
+          Type = "oneshot";
+          ExecStart = zpoolLatencyScript;
+        };
+      };
+    };
+
+    timers.zpool-latency-exporter = {
+      wantedBy = [ "timers.target" ];
+      timerConfig = {
+        OnBootSec = "2m";
+        OnUnitActiveSec = "60s";
+        Unit = "zpool-latency-exporter.service";
+      };
+    };
+
+    tmpfiles.rules = [ "d ${nodeTextfileDir} 0755 root root - -" ];
+  };
+}

common/optional/update.nix

@@ -4,7 +4,7 @@
     flags = [ "--accept-flake-config" ];
     randomizedDelaySec = "1h";
     persistent = true;
-    flake = "github:RichieCahill/dotfiles";
+    flake = "git+https://gitea.tmmworkshop.com/richie/dotfiles?ref=main";
     allowReboot = true;
     dates = "Sat *-*-* 06:00:00";
   };

docs/zfs_failed_root_import_recovry.md

@@ -0,0 +1,76 @@
+# ZFS failed root import recovery
+
+## Fast path
+
+If the machine fails to boot because ZFS refuses to import `root_pool`:
+
+### GRUB
+
+1. At the bootloader menu, select the normal NixOS entry.
+2. Press `e`.
+3. Find the line that starts with `linux`.
+4. Append this to the end of that line:
+
+```text
+zfs_force=1
+```
+
+5. Boot once with `Ctrl+x` or `F10`.
+
+### systemd-boot
+
+1. At the bootloader menu, highlight the normal NixOS entry.
+2. Press `e`.
+3. Append this to the end of the options line:
+
+```text
+zfs_force=1
+```
+
+4. Press `Enter` to boot once.
+
+## After boot
+
+Run:
+
+```bash
+sudo zpool status
+sudo zpool import
+journalctl -b | rg "ZFS|zfs|import|root_pool"
+```
+
+## Expected result
+
+`sudo zpool status` should show `root_pool` as `ONLINE`.
+
+## Reboot test
+
+Run:
+
+```bash
+sudo reboot
+```
+
+Do not add `zfs_force=1` the second time.
+
+## If it still fails
+
+Boot once more with:
+
+```text
+zfs_force=1
+```
+
+Then run:
+
+```bash
+sudo zpool status -v
+sudo zpool history | tail -n 50
+journalctl -b | rg "ZFS|zfs|import|root_pool"
+```
+
+## Notes
+
+- Root pool name is `root_pool`.
+- This is a one-time recovery path after disk moves, controller changes, dirty exports, or interrupted imports.
+- Some hosts also need the LUKS unlock USB key inserted before boot.

flake.lock

@@ -8,11 +8,11 @@
       },
       "locked": {
         "dir": "pkgs/firefox-addons",
-        "lastModified": 1777435375,
+        "lastModified": 1777521781,
-        "narHash": "sha256-2WRfJbipnTz+EY3rHRnCoG4kWkzPczb/cLcWwhy/0QA=",
+        "narHash": "sha256-bQ9oIcNyHsiagt7yptfe7OmfUDEyuXFUb7ajkrWNzSo=",
         "owner": "rycee",
         "repo": "nur-expressions",
-        "rev": "4d89e8e2c50711ee3fea3a25e662cfa5c6628e07",
+        "rev": "8a444a5c02840666c9c2f92042bfbb7a10c68200",
         "type": "gitlab"
       },
       "original": {
@@ -29,11 +29,11 @@
         ]
       },
       "locked": {
-        "lastModified": 1777434174,
+        "lastModified": 1777518431,
-        "narHash": "sha256-KwTyQ5g2qDhWIs/O6vH8HeF8n4JCzZIT/VYE7nYnukQ=",
+        "narHash": "sha256-SwgiG2T5pbyo33Vz7/vUCAhEMgwCK8Pa2nDSx5a6/WE=",
         "owner": "nix-community",
         "repo": "home-manager",
-        "rev": "d3b4e4b1bd59aedd3d4eb0a8df7162edb6da4607",
+        "rev": "2e54a938cdd4c8e414b2518edc3d82308027c670",
         "type": "github"
       },
       "original": {
@@ -76,11 +76,11 @@
     },
     "nixpkgs-master": {
       "locked": {
-        "lastModified": 1777437048,
+        "lastModified": 1777553282,
-        "narHash": "sha256-Ca4jKXJuYp1D+DqiuQ/vGHRYKPlAZTn1vq7XDU9t18w=",
+        "narHash": "sha256-GCJkEogieqOYJ1BBhG0w9fqezul1cGdEcmBbJ+34F4U=",
         "owner": "nixos",
         "repo": "nixpkgs",
-        "rev": "1e1459dda883651ef85e23c7c6e2224cba195065",
+        "rev": "0d93cb69a4fd4449088c69859e1836fda6eb9f6a",
         "type": "github"
       },
       "original": {

python/gitea.py

@@ -0,0 +1,335 @@
+"""Small Gitea API client for repository automation."""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Self
+
+import httpx
+
+DEFAULT_PAGE_SIZE = 100
+EXPECTED_CREATED = 201
+EXPECTED_OK = 200
+
+
+@dataclass(frozen=True)
+class CreatedIssue:
+    """Issue data returned by Gitea."""
+
+    number: int | None
+    html_url: str | None
+    title: str
+
+
+@dataclass(frozen=True)
+class PullRequest:
+    """Pull request data returned by Gitea."""
+
+    number: int
+    title: str
+    html_url: str | None
+    labels: tuple[str, ...]
+    head_branch: str | None
+    base_branch: str | None
+
+
+@dataclass(frozen=True)
+class WorkflowJob:
+    """Workflow job data returned by Gitea Actions."""
+
+    id: int
+    name: str
+    run_id: int | None
+    status: str | None
+    conclusion: str | None
+
+
+class GiteaError(RuntimeError):
+    """Raised when Gitea rejects an API request."""
+
+
+def split_repo_name(repo: str) -> tuple[str, str]:
+    """Split an owner/repo string into its parts."""
+    owner, separator, repo_name = repo.partition("/")
+    if not separator or not owner or not repo_name:
+        msg = f"Invalid repository name: {repo}"
+        raise ValueError(msg)
+    return owner, repo_name
+
+
+class GiteaClient:
+    """HTTP client for the subset of Gitea APIs used in this repository."""
+
+    def __init__(
+        self,
+        *,
+        base_url: str,
+        token: str,
+        timeout: int = 30,
+        transport: httpx.BaseTransport | None = None,
+    ) -> None:
+        """Initialize the Gitea client."""
+        self._client = httpx.Client(
+            base_url=base_url.rstrip("/"),
+            timeout=timeout,
+            headers={"Authorization": f"token {token}"},
+            transport=transport,
+        )
+
+    def create_issue(
+        self,
+        *,
+        owner: str,
+        repo: str,
+        title: str,
+        body: str,
+        labels: list[int] | None = None,
+    ) -> CreatedIssue:
+        """Create a Gitea issue."""
+        payload: dict[str, object] = {"title": title, "body": body, "labels": labels or []}
+        response = self._request(
+            "POST",
+            f"/api/v1/repos/{owner}/{repo}/issues",
+            expected_statuses={EXPECTED_CREATED},
+            json=payload,
+        )
+        data = response.json()
+        return CreatedIssue(
+            number=_optional_int(data.get("number")),
+            html_url=_optional_str(data.get("html_url")),
+            title=str(data.get("title", title)),
+        )
+
+    def resolve_label_ids(self, *, owner: str, repo: str, labels: list[str]) -> list[int]:
+        """Resolve label names to Gitea label IDs."""
+        if not labels:
+            return []
+
+        available_labels: dict[str, int] = {}
+        page = 1
+        while True:
+            response = self._request(
+                "GET",
+                f"/api/v1/repos/{owner}/{repo}/labels",
+                params={"page": page, "limit": DEFAULT_PAGE_SIZE},
+            )
+            batch = response.json()
+            if not batch:
+                break
+            for label in batch:
+                label_name = str(label.get("name", ""))
+                label_id = _optional_int(label.get("id"))
+                if label_name and label_id is not None:
+                    available_labels[label_name] = label_id
+            if len(batch) < DEFAULT_PAGE_SIZE:
+                break
+            page += 1
+
+        missing = [label for label in labels if label not in available_labels]
+        if missing:
+            missing_names = ", ".join(sorted(missing))
+            msg = f"Missing Gitea labels: {missing_names}"
+            raise GiteaError(msg)
+
+        return [available_labels[label] for label in labels]
+
+    def list_open_pull_requests(
+        self,
+        *,
+        owner: str,
+        repo: str,
+        labels: list[str] | None = None,
+        head: str | None = None,
+    ) -> list[PullRequest]:
+        """List open pull requests for a repository."""
+        expected_labels = set(labels or [])
+        pull_requests: list[PullRequest] = []
+        page = 1
+        while True:
+            response = self._request(
+                "GET",
+                f"/api/v1/repos/{owner}/{repo}/pulls",
+                params={"state": "open", "page": page, "limit": DEFAULT_PAGE_SIZE},
+            )
+            batch = response.json()
+            if not batch:
+                break
+
+            for item in batch:
+                pull_request = _pull_request_from_api(item)
+                if head and pull_request.head_branch != head:
+                    continue
+                if expected_labels and not expected_labels.issubset(set(pull_request.labels)):
+                    continue
+                pull_requests.append(pull_request)
+
+            if len(batch) < DEFAULT_PAGE_SIZE:
+                break
+            page += 1
+
+        return pull_requests
+
+    def create_pull_request(
+        self,
+        *,
+        owner: str,
+        repo: str,
+        title: str,
+        body: str,
+        head: str,
+        base: str,
+        labels: list[str] | None = None,
+    ) -> PullRequest:
+        """Create a pull request."""
+        payload: dict[str, object] = {
+            "title": title,
+            "body": body,
+            "head": head,
+            "base": base,
+        }
+        if labels:
+            payload["labels"] = self.resolve_label_ids(owner=owner, repo=repo, labels=labels)
+
+        response = self._request(
+            "POST",
+            f"/api/v1/repos/{owner}/{repo}/pulls",
+            expected_statuses={EXPECTED_CREATED},
+            json=payload,
+        )
+        return _pull_request_from_api(response.json())
+
+    def merge_pull_request(
+        self,
+        *,
+        owner: str,
+        repo: str,
+        number: int,
+        merge_method: str = "rebase",
+        head_commit_id: str | None = None,
+        delete_branch_after_merge: bool = False,
+    ) -> None:
+        """Merge a pull request."""
+        payload: dict[str, object] = {
+            "Do": merge_method,
+            "delete_branch_after_merge": delete_branch_after_merge,
+        }
+        if head_commit_id:
+            payload["head_commit_id"] = head_commit_id
+
+        self._request(
+            "POST",
+            f"/api/v1/repos/{owner}/{repo}/pulls/{number}/merge",
+            json=payload,
+        )
+
+    def list_run_jobs(self, *, owner: str, repo: str, run_id: str | int) -> list[WorkflowJob]:
+        """List workflow jobs for a specific run."""
+        jobs: list[WorkflowJob] = []
+        page = 1
+        while True:
+            response = self._request(
+                "GET",
+                f"/api/v1/repos/{owner}/{repo}/actions/jobs",
+                params={"page": page, "limit": DEFAULT_PAGE_SIZE},
+            )
+            payload = response.json()
+            batch = payload.get("jobs", [])
+            if not batch:
+                break
+
+            for item in batch:
+                if str(item.get("run_id")) != str(run_id):
+                    continue
+                jobs.append(_workflow_job_from_api(item))
+
+            if len(batch) < DEFAULT_PAGE_SIZE:
+                break
+            page += 1
+
+        return jobs
+
+    def download_job_logs(self, *, owner: str, repo: str, job_id: int) -> str:
+        """Download logs for a workflow job."""
+        response = self._request(
+            "GET",
+            f"/api/v1/repos/{owner}/{repo}/actions/jobs/{job_id}/logs",
+        )
+        return response.text
+
+    def close(self) -> None:
+        """Close the underlying HTTP client."""
+        self._client.close()
+
+    def __enter__(self) -> Self:
+        """Enter the context manager."""
+        return self
+
+    def __exit__(self, *args: object) -> None:
+        """Close the HTTP client."""
+        self.close()
+
+    def _request(
+        self,
+        method: str,
+        path: str,
+        *,
+        expected_statuses: set[int] | None = None,
+        **kwargs: object,
+    ) -> httpx.Response:
+        """Send an HTTP request and validate the response status."""
+        response = self._client.request(method, path, **kwargs)
+        statuses = expected_statuses or {EXPECTED_OK}
+        if response.status_code not in statuses:
+            msg = f"Gitea request failed ({response.status_code}): {response.text}"
+            raise GiteaError(msg)
+        return response
+
+
+def _pull_request_from_api(data: dict[str, object]) -> PullRequest:
+    """Convert Gitea API pull-request data into a dataclass."""
+    number = _optional_int(data.get("number")) or _optional_int(data.get("index"))
+    if number is None:
+        msg = "Gitea pull request payload is missing a number"
+        raise GiteaError(msg)
+
+    labels = tuple(str(label.get("name", "")) for label in data.get("labels", []))
+    head = data.get("head", {})
+    base = data.get("base", {})
+    return PullRequest(
+        number=number,
+        title=str(data.get("title", "")),
+        html_url=_optional_str(data.get("html_url")),
+        labels=tuple(label for label in labels if label),
+        head_branch=_optional_str(head.get("ref")) or _optional_str(data.get("head_branch")),
+        base_branch=_optional_str(base.get("ref")) or _optional_str(data.get("base_branch")),
+    )
+
+
+def _workflow_job_from_api(data: dict[str, object]) -> WorkflowJob:
+    """Convert Gitea API workflow-job data into a dataclass."""
+    job_id = _optional_int(data.get("id"))
+    if job_id is None:
+        msg = "Gitea workflow job payload is missing an ID"
+        raise GiteaError(msg)
+
+    return WorkflowJob(
+        id=job_id,
+        name=str(data.get("name", "")),
+        run_id=_optional_int(data.get("run_id")),
+        status=_optional_str(data.get("status")),
+        conclusion=_optional_str(data.get("conclusion")),
+    )
+
+
+def _optional_int(value: object) -> int | None:
+    """Convert an API value to an integer when present."""
+    if value is None:
+        return None
+    return int(value)
+
+
+def _optional_str(value: object) -> str | None:
+    """Convert an API value to a string when present."""
+    if value is None:
+        return None
+    return str(value)

python/gitea_flake_lock.py

@@ -0,0 +1,138 @@
+"""Automation helpers for flake.lock pull requests on Gitea."""
+
+from __future__ import annotations
+
+import subprocess
+from os import getenv
+from typing import Annotated
+
+import typer
+
+from python.gitea import GiteaClient, PullRequest, split_repo_name
+
+DEFAULT_BASE_BRANCH = "main"
+DEFAULT_BRANCH = "automation/update-flake-lock"
+DEFAULT_GITEA_URL = "https://gitea.tmmworkshop.com"
+PR_LABELS = ["dependencies", "automated", "flake_lock_update"]
+PR_TITLE = "Update flake.lock"
+PR_BODY = "Automated flake.lock update."
+
+app = typer.Typer(add_completion=False)
+
+
+def run_cmd(cmd: list[str], *, check: bool = True) -> subprocess.CompletedProcess[str]:
+    """Run a subprocess command."""
+    return subprocess.run(cmd, capture_output=True, text=True, check=check)
+
+
+def ensure_flake_lock_pull_request(
+    client: GiteaClient,
+    *,
+    owner: str,
+    repo: str,
+    branch: str,
+    base: str,
+) -> PullRequest:
+    """Return an existing flake.lock PR for the branch or create one."""
+    pull_requests = client.list_open_pull_requests(owner=owner, repo=repo, head=branch)
+    if pull_requests:
+        return pull_requests[0]
+
+    return client.create_pull_request(
+        owner=owner,
+        repo=repo,
+        title=PR_TITLE,
+        body=PR_BODY,
+        head=branch,
+        base=base,
+        labels=PR_LABELS,
+    )
+
+
+def find_flake_lock_pull_request(client: GiteaClient, *, owner: str, repo: str) -> PullRequest | None:
+    """Find the first open flake.lock pull request."""
+    pull_requests = client.list_open_pull_requests(owner=owner, repo=repo, labels=["flake_lock_update"])
+    if not pull_requests:
+        return None
+    return pull_requests[0]
+
+
+def has_worktree_changes() -> bool:
+    """Return whether `flake.lock` has worktree changes."""
+    result = run_cmd(["git", "diff", "--quiet", "--", "flake.lock"], check=False)
+    return result.returncode != 0
+
+
+def commit_flake_lock_update(*, branch: str) -> None:
+    """Commit the updated lock file to the automation branch."""
+    run_cmd(["git", "config", "user.name", "gitea-actions[bot]"])
+    run_cmd(["git", "config", "user.email", "gitea-actions@tmmworkshop.com"])
+    run_cmd(["git", "checkout", "-B", branch])
+    run_cmd(["git", "add", "flake.lock"])
+    run_cmd(["git", "commit", "-m", "chore: update flake.lock"])
+
+
+def push_branch(*, branch: str) -> None:
+    """Push the automation branch to origin."""
+    run_cmd(["git", "push", "origin", f"HEAD:{branch}", "--force"])
+
+
+def _required_gitea_token() -> str:
+    """Read the required Gitea token from the environment."""
+    token = getenv("GITEA_TOKEN")
+    if token:
+        return token
+
+    msg = "GITEA_TOKEN environment variable is required"
+    raise RuntimeError(msg)
+
+
+@app.command()
+def update(
+    repo: Annotated[str, typer.Option("--repo", help="Gitea repository in owner/repo form")],
+    base: Annotated[str, typer.Option("--base", help="Base branch")] = DEFAULT_BASE_BRANCH,
+    branch: Annotated[str, typer.Option("--branch", help="Automation branch")] = DEFAULT_BRANCH,
+) -> None:
+    """Commit flake.lock changes and ensure a pull request exists."""
+    if not has_worktree_changes():
+        typer.echo("No flake.lock changes detected")
+        return
+
+    commit_flake_lock_update(branch=branch)
+    push_branch(branch=branch)
+
+    owner, repo_name = split_repo_name(repo)
+    with GiteaClient(
+        base_url=getenv("GITEA_URL", DEFAULT_GITEA_URL),
+        token=_required_gitea_token(),
+    ) as client:
+        pull_request = ensure_flake_lock_pull_request(
+            client,
+            owner=owner,
+            repo=repo_name,
+            branch=branch,
+            base=base,
+        )
+    typer.echo(pull_request.html_url or f"Pull request #{pull_request.number}")
+
+
+@app.command()
+def merge(
+    repo: Annotated[str, typer.Option("--repo", help="Gitea repository in owner/repo form")],
+) -> None:
+    """Merge the first open flake.lock pull request."""
+    owner, repo_name = split_repo_name(repo)
+    with GiteaClient(
+        base_url=getenv("GITEA_URL", DEFAULT_GITEA_URL),
+        token=_required_gitea_token(),
+    ) as client:
+        pull_request = find_flake_lock_pull_request(client, owner=owner, repo=repo_name)
+        if not pull_request:
+            typer.echo("No open PR found with label flake_lock_update")
+            return
+        client.merge_pull_request(owner=owner, repo=repo_name, number=pull_request.number, merge_method="rebase")
+    typer.echo(f"Merged PR #{pull_request.number}")
+
+
+if __name__ == "__main__":
+    app()

systems/bob/default.nix

@@ -7,6 +7,7 @@
     "${inputs.self}/common/global"
     "${inputs.self}/common/optional/docker.nix"
     "${inputs.self}/common/optional/scanner.nix"
+    "${inputs.self}/common/optional/monitoring-agent.nix"
     "${inputs.self}/common/optional/steam.nix"
     "${inputs.self}/common/optional/syncthing_base.nix"
     "${inputs.self}/common/optional/systemd-boot.nix"

systems/jeeves/default.nix

@@ -10,10 +10,12 @@ in
     "${inputs.self}/users/steve"
     "${inputs.self}/common/global"
     "${inputs.self}/common/optional/docker.nix"
+    "${inputs.self}/common/optional/monitoring-agent.nix"
     "${inputs.self}/common/optional/ssh_decrypt.nix"
     "${inputs.self}/common/optional/syncthing_base.nix"
     "${inputs.self}/common/optional/update.nix"
     "${inputs.self}/common/optional/zerotier.nix"
+    ./monitoring
     ./docker
     ./services
     ./web_services

systems/jeeves/monitoring/dashboards/overview.json

@@ -0,0 +1,426 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 6,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "100 * (1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])))",
+          "legendFormat": "{{instance}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "CPU Used",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 6,
+        "x": 6,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "100 * (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes))",
+          "legendFormat": "{{instance}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "RAM Used",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 6,
+        "x": 12,
+        "y": 0
+      },
+      "id": 3,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "100 * (1 - (node_memory_SwapFree_bytes / node_memory_SwapTotal_bytes))",
+          "legendFormat": "{{instance}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Swap Used",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 6,
+        "x": 18,
+        "y": 0
+      },
+      "id": 4,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "node_load1",
+          "legendFormat": "{{instance}} load1",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "node_load5",
+          "legendFormat": "{{instance}} load5",
+          "range": true,
+          "refId": "B"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "node_load15",
+          "legendFormat": "{{instance}} load15",
+          "range": true,
+          "refId": "C"
+        }
+      ],
+      "title": "Load",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "id": 5,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "sum by (instance) (rate(node_disk_read_bytes_total[5m]))",
+          "legendFormat": "{{instance}} read",
+          "range": true,
+          "refId": "A"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "sum by (instance) (rate(node_disk_written_bytes_total[5m]))",
+          "legendFormat": "{{instance}} write",
+          "range": true,
+          "refId": "B"
+        }
+      ],
+      "title": "Disk Throughput",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "id": 6,
+      "options": {
+        "cellHeight": "sm",
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Value"
+          }
+        ]
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "100 * (1 - (node_filesystem_avail_bytes{mountpoint=~\"(/|/home|/var|/zfs.*)\",fstype!=\"\"} / node_filesystem_size_bytes{mountpoint=~\"(/|/home|/var|/zfs.*)\",fstype!=\"\"}))",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{instance}} {{mountpoint}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Filesystem Usage",
+      "type": "table"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percentunit"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 10,
+        "w": 12,
+        "x": 0,
+        "y": 17
+      },
+      "id": 7,
+      "options": {
+        "cellHeight": "sm",
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Value"
+          }
+        ]
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "topk(10, rate(namedprocess_namegroup_cpu_seconds_total[5m]))",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{instance}} {{groupname}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Top Grouped CPU",
+      "type": "table"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "bytes"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 10,
+        "w": 12,
+        "x": 12,
+        "y": 17
+      },
+      "id": 8,
+      "options": {
+        "cellHeight": "sm",
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Value"
+          }
+        ]
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "topk(10, namedprocess_namegroup_memory_bytes{memtype=\"resident\"})",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{instance}} {{groupname}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Top Grouped Memory",
+      "type": "table"
+    }
+  ],
+  "refresh": "30s",
+  "schemaVersion": 39,
+  "style": "dark",
+  "tags": [
+    "monitoring"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-24h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Overview",
+  "uid": "monitor-overview",
+  "version": 1,
+  "weekStart": ""
+}

systems/jeeves/monitoring/dashboards/process-history-grouped.json

@@ -0,0 +1,216 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percentunit"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 10,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "topk(10, rate(namedprocess_namegroup_cpu_seconds_total[5m]))",
+          "legendFormat": "{{instance}} {{groupname}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Grouped CPU",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "bytes"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 10,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "topk(10, namedprocess_namegroup_memory_bytes{memtype=\"resident\"})",
+          "legendFormat": "{{instance}} {{groupname}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Grouped Resident Memory",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 10,
+        "w": 12,
+        "x": 0,
+        "y": 10
+      },
+      "id": 3,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "topk(10, rate(namedprocess_namegroup_read_bytes_total[5m]))",
+          "legendFormat": "{{instance}} {{groupname}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Grouped Read I/O",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 10,
+        "w": 12,
+        "x": 12,
+        "y": 10
+      },
+      "id": 4,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "topk(10, rate(namedprocess_namegroup_write_bytes_total[5m]))",
+          "legendFormat": "{{instance}} {{groupname}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Grouped Write I/O",
+      "type": "timeseries"
+    }
+  ],
+  "refresh": "30s",
+  "schemaVersion": 39,
+  "style": "dark",
+  "tags": [
+    "monitoring",
+    "process"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-7d",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Process History Grouped",
+  "uid": "monitor-process-history",
+  "version": 1,
+  "weekStart": ""
+}

systems/jeeves/monitoring/dashboards/process-live-pid.json

@@ -0,0 +1,224 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-pid-short"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percentunit"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 10,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "cellHeight": "sm",
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Value"
+          }
+        ]
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-pid-short"
+          },
+          "editorMode": "code",
+          "expr": "topk(20, rate(namedprocess_namegroup_cpu_seconds_total[2m]))",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{instance}} {{groupname}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Top PID CPU",
+      "type": "table"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-pid-short"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "bytes"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 10,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "cellHeight": "sm",
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Value"
+          }
+        ]
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-pid-short"
+          },
+          "editorMode": "code",
+          "expr": "topk(20, namedprocess_namegroup_memory_bytes{memtype=\"resident\"})",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{instance}} {{groupname}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Top PID RSS",
+      "type": "table"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-pid-short"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 10,
+        "w": 12,
+        "x": 0,
+        "y": 10
+      },
+      "id": 3,
+      "options": {
+        "cellHeight": "sm",
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Value"
+          }
+        ]
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-pid-short"
+          },
+          "editorMode": "code",
+          "expr": "topk(20, rate(namedprocess_namegroup_read_bytes_total[2m]))",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{instance}} {{groupname}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Top PID Read I/O",
+      "type": "table"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-pid-short"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 10,
+        "w": 12,
+        "x": 12,
+        "y": 10
+      },
+      "id": 4,
+      "options": {
+        "cellHeight": "sm",
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Value"
+          }
+        ]
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-pid-short"
+          },
+          "editorMode": "code",
+          "expr": "topk(20, rate(namedprocess_namegroup_write_bytes_total[2m]))",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{instance}} {{groupname}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Top PID Write I/O",
+      "type": "table"
+    }
+  ],
+  "refresh": "15s",
+  "schemaVersion": 39,
+  "style": "dark",
+  "tags": [
+    "monitoring",
+    "process"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-10m",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Process Live PID",
+  "uid": "monitor-process-pid",
+  "version": 1,
+  "weekStart": ""
+}

systems/jeeves/monitoring/dashboards/storage-zfs.json

@@ -0,0 +1,351 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "100 * (zfs_pool_allocated_bytes / zfs_pool_size_bytes)",
+          "legendFormat": "{{instance}} {{pool}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Pool Usage",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "bytes"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 8,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "zfs_pool_free_bytes",
+          "legendFormat": "{{instance}} {{pool}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "Pool Free Bytes",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "bytes"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 16,
+        "y": 0
+      },
+      "id": 3,
+      "options": {
+        "cellHeight": "sm",
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Value"
+          }
+        ]
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "topk(20, zfs_dataset_used_bytes{type=\"filesystem\"})",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{instance}} {{name}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Top Filesystems by Used Bytes",
+      "type": "table"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ns"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "id": 4,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "topk(20, zpool_iostat_total_wait_read_ns{vdev!=\"_pool\"})",
+          "legendFormat": "{{host}} {{pool}} {{vdev}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "ZFS Read Wait",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ns"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "id": 5,
+      "options": {
+        "legend": {
+          "displayMode": "list",
+          "placement": "bottom"
+        },
+        "tooltip": {
+          "mode": "multi"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "topk(20, zpool_iostat_total_wait_write_ns{vdev!=\"_pool\"})",
+          "legendFormat": "{{host}} {{pool}} {{vdev}}",
+          "range": true,
+          "refId": "A"
+        }
+      ],
+      "title": "ZFS Write Wait",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "celsius"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 0,
+        "y": 17
+      },
+      "id": 6,
+      "options": {
+        "cellHeight": "sm",
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "Value"
+          }
+        ]
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "smartctl_device_temperature{temperature_type=\"current\"}",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{instance}} {{device}}",
+          "refId": "A"
+        }
+      ],
+      "title": "Disk Temperature",
+      "type": "table"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prom-main"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 9,
+        "w": 12,
+        "x": 12,
+        "y": 17
+      },
+      "id": 7,
+      "options": {
+        "cellHeight": "sm",
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": false,
+            "displayName": "Value"
+          }
+        ]
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prom-main"
+          },
+          "editorMode": "code",
+          "expr": "smartctl_device_smart_status",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "{{instance}} {{device}}",
+          "refId": "A"
+        }
+      ],
+      "title": "SMART Health",
+      "type": "table"
+    }
+  ],
+  "refresh": "30s",
+  "schemaVersion": 39,
+  "style": "dark",
+  "tags": [
+    "monitoring",
+    "zfs"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-24h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Storage and ZFS",
+  "uid": "monitor-storage",
+  "version": 1,
+  "weekStart": ""
+}

systems/jeeves/monitoring/default.nix

@@ -0,0 +1,186 @@
+{
+  lib,
+  pkgs,
+  ...
+}:
+let
+  vars = import ../vars.nix;
+
+  prometheusDataRoot = "${vars.database}/prometheus";
+  mainPrometheusDataDir = "${prometheusDataRoot}/main";
+  pidPrometheusDataDir = "${prometheusDataRoot}/pid-short";
+
+  prometheusYaml = pkgs.formats.yaml { };
+
+  mkPrometheusConfig =
+    name: cfg:
+    let
+      configFile = prometheusYaml.generate "${name}.yaml" cfg;
+    in
+    pkgs.runCommand "${name}-checked.yaml"
+      {
+        nativeBuildInputs = [ pkgs.prometheus.cli ];
+      }
+      ''
+        promtool check config ${configFile}
+        cp ${configFile} $out
+      '';
+
+  mkTarget = host: address: {
+    targets = [ address ];
+    labels.instance = host;
+  };
+
+  mainPrometheusConfig = mkPrometheusConfig "prometheus-main" {
+    global = {
+      scrape_interval = "30s";
+      scrape_timeout = "10s";
+      evaluation_interval = "30s";
+    };
+    scrape_configs = [
+      {
+        job_name = "node";
+        static_configs = [
+          (mkTarget "jeeves" "192.168.90.40:9100")
+          (mkTarget "bob" "192.168.90.25:9100")
+        ];
+      }
+      {
+        job_name = "process_grouped";
+        static_configs = [
+          (mkTarget "jeeves" "192.168.90.40:9256")
+          (mkTarget "bob" "192.168.90.25:9256")
+        ];
+      }
+      {
+        job_name = "smartctl";
+        static_configs = [
+          (mkTarget "jeeves" "192.168.90.40:9633")
+          (mkTarget "bob" "192.168.90.25:9633")
+        ];
+      }
+      {
+        job_name = "zfs";
+        static_configs = [
+          (mkTarget "jeeves" "192.168.90.40:9134")
+          (mkTarget "bob" "192.168.90.25:9134")
+        ];
+      }
+    ];
+  };
+
+  pidPrometheusConfig = mkPrometheusConfig "prometheus-pid-short" {
+    global = {
+      scrape_interval = "15s";
+      scrape_timeout = "10s";
+      evaluation_interval = "15s";
+    };
+    scrape_configs = [
+      {
+        job_name = "process_pid";
+        static_configs = [
+          (mkTarget "jeeves" "192.168.90.40:9257")
+          (mkTarget "bob" "192.168.90.25:9257")
+        ];
+      }
+    ];
+  };
+
+  mkPrometheusService =
+    {
+      dataDir,
+      configFile,
+      port,
+      retention,
+    }:
+    {
+      after = [
+        "zfs-media-database-prometheus.mount"
+        "network.target"
+      ];
+      requires = [ "zfs-media-database-prometheus.mount" ];
+      wantedBy = [ "multi-user.target" ];
+      unitConfig.RequiresMountsFor = [ dataDir ];
+      serviceConfig = {
+        ExecStart = "${lib.getExe pkgs.prometheus} ${
+          lib.escapeShellArgs [
+            "--config.file=${configFile}"
+            "--storage.tsdb.path=${dataDir}"
+            "--storage.tsdb.retention.time=${retention}"
+            "--web.listen-address=127.0.0.1:${toString port}"
+          ]
+        }";
+        User = "prometheus";
+        Group = "prometheus";
+        Restart = "always";
+        RestartSec = "5s";
+        WorkingDirectory = dataDir;
+        ReadWritePaths = [ dataDir ];
+        CapabilityBoundingSet = [ "" ];
+        DeviceAllow = [ "/dev/null rw" ];
+        DevicePolicy = "strict";
+        LockPersonality = true;
+        MemoryDenyWriteExecute = true;
+        NoNewPrivileges = true;
+        PrivateDevices = true;
+        PrivateTmp = true;
+        ProtectClock = true;
+        ProtectControlGroups = true;
+        ProtectHome = true;
+        ProtectHostname = true;
+        ProtectKernelLogs = true;
+        ProtectKernelModules = true;
+        ProtectKernelTunables = true;
+        ProtectProc = "invisible";
+        ProtectSystem = "strict";
+        RemoveIPC = true;
+        RestrictAddressFamilies = [
+          "AF_INET"
+          "AF_INET6"
+          "AF_UNIX"
+        ];
+        RestrictNamespaces = true;
+        RestrictRealtime = true;
+        RestrictSUIDSGID = true;
+        SystemCallArchitectures = "native";
+        SystemCallFilter = [
+          "@system-service"
+          "~@privileged"
+        ];
+      };
+    };
+in
+{
+  users = {
+    groups.prometheus = { };
+    users.prometheus = {
+      isSystemUser = true;
+      group = "prometheus";
+      description = "Prometheus daemon user";
+    };
+  };
+
+  systemd = {
+    services = {
+      prometheus-main = mkPrometheusService {
+        configFile = mainPrometheusConfig;
+        dataDir = mainPrometheusDataDir;
+        port = 9090;
+        retention = "90d";
+      };
+
+      prometheus-pid-short = mkPrometheusService {
+        configFile = pidPrometheusConfig;
+        dataDir = pidPrometheusDataDir;
+        port = 9092;
+        retention = "10m";
+      };
+    };
+
+    tmpfiles.rules = [
+      "d ${prometheusDataRoot} 0755 root root - -"
+      "d ${mainPrometheusDataDir} 0750 prometheus prometheus - -"
+      "d ${pidPrometheusDataDir} 0750 prometheus prometheus - -"
+    ];
+  };
+}

systems/jeeves/networking.nix

@@ -1,4 +1,13 @@
 {
+  # Docker loads br_netfilter on jeeves. Disable bridge netfilter so
+  # br-nix-builder behaves like a pure L2 bridge and bridged traffic
+  # does not hit the host firewall/rpfilter path.
+  boot.kernel.sysctl = {
+    "net.bridge.bridge-nf-call-arptables" = 0;
+    "net.bridge.bridge-nf-call-ip6tables" = 0;
+    "net.bridge.bridge-nf-call-iptables" = 0;
+  };
+
   networking = {
     hostName = "jeeves";
     hostId = "0e15ce35";
@@ -49,23 +58,10 @@
       "60-br-nix-builder" = {
         matchConfig.Name = "br-nix-builder";
         bridgeConfig = { };
-        address = [ "192.168.3.10/24" ];
+        networkConfig = {
-        routingPolicyRules = [
+          IPv6AcceptRA = false;
-          {
+          LinkLocalAddressing = "no";
-            From = "192.168.3.0/24";
+        };
-            Table = 100;
-            Priority = 100;
-          }
-        ];
-        routes = [
-          {
-            Gateway = "192.168.3.1";
-            Table = 100;
-            GatewayOnLink = false;
-            Metric = 2048;
-            PreferredSource = "192.168.3.10";
-          }
-        ];
         linkConfig.RequiredForOnline = "no";
       };
     };

systems/jeeves/runners/default.nix

@@ -1,20 +1,7 @@
-{ pkgs, ... }:
+{ ... }:
 {
   imports = [ ./nix_builder.nix ];
 
-  users = {
-    users.github-runners = {
-      shell = pkgs.bash;
-      isSystemUser = true;
-      group = "github-runners";
-      uid = 601;
-      openssh.authorizedKeys.keys = [
-        "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIA/S8i+BNX/12JNKg+5EKGX7Aqimt5KM+ve3wt/SyWuO github-runners" # cspell:disable-line
-      ];
-    };
-    groups.github-runners.gid = 601;
-  };
-
   services.nix_builder.containers = {
     nix-builder-00.enable = true;
     nix-builder-01.enable = true;

systems/jeeves/runners/nix_builder.nix

@@ -2,6 +2,7 @@
   config,
   lib,
   outputs,
+  utils,
   ...
 }:
 
@@ -9,6 +10,8 @@ with lib;
 let
   vars = import ../vars.nix;
   cfg = config.services.nix_builder;
+  runnerUsername = "gitea-runner";
+  runnerUserid = 601;
 in
 {
   options.services.nix_builder = {
@@ -23,37 +26,40 @@ in
         types.submodule (
           { name, ... }:
           {
-            options.enable = mkEnableOption "GitHub runner container";
+            options.enable = mkEnableOption "Gitea runner container";
           }
         )
       );
       default = { };
-      description = "GitHub runner container configurations";
+      description = "Gitea runner container configurations";
     };
   };
 
   config = {
+    users = {
+      users.${runnerUsername} = {
+        isSystemUser = true;
+        group = runnerUsername;
+        uid = runnerUserid;
+      };
+      groups.${runnerUsername}.gid = runnerUserid;
+    };
+
     containers = mapAttrs (
       name: containerCfg:
       mkIf containerCfg.enable {
         autoStart = true;
         privateNetwork = true;
         hostBridge = cfg.bridgeName;
-        ephemeral = true;
         bindMounts = {
-          storage = {
-            hostPath = "/zfs/media/github-runners/${name}";
-            mountPoint = "/zfs/media/github-runners/${name}";
-            isReadOnly = false;
-          };
           host-nix = {
             mountPoint = "/host-nix/var/nix/daemon-socket";
             hostPath = "/nix/var/nix/daemon-socket";
             isReadOnly = false;
           };
-          pat = {
+          token = {
-            hostPath = "${vars.secrets}/services/github-runners/runner_pat";
+            hostPath = "${vars.secrets}/services/gitea-runners";
-            mountPoint = "${vars.secrets}/services/github-runners/runner_pat";
+            mountPoint = "/run/secrets/gitea-runners";
             isReadOnly = true;
           };
         };
@@ -92,46 +98,69 @@ in
                 "nix-command"
               ];
               sandbox = true;
-              allowed-users = [ "github-runners" ];
+              allowed-users = [ "gitea-runner" ];
               trusted-users = [
                 "root"
-                "github-runners"
+                "gitea-runner"
               ];
             };
             nixpkgs = {
               overlays = builtins.attrValues outputs.overlays;
               config.allowUnfree = true;
             };
-            services.github-runners.${name} = {
+            users = {
+              users.${runnerUsername} = {
+                isSystemUser = true;
+                group = runnerUsername;
+                uid = runnerUserid;
+              };
+              groups.${runnerUsername}.gid = runnerUserid;
+            };
+            services.gitea-actions-runner.instances.${name} = {
               enable = true;
-              replace = true;
+              name = "jeeves-${name}";
-              workDir = "/zfs/media/github-runners/${name}";
+              url = "http://192.168.99.14:6443/";
-              url = "https://github.com/RichieCahill/dotfiles";
+              labels = [
-              extraLabels = [ "nixos" ];
+                "self-hosted:host"
-              tokenFile = "${vars.secrets}/services/github-runners/runner_pat";
+                "nixos:host"
-              user = "github-runners";
+              ];
-              group = "github-runners";
+              tokenFile = "/run/secrets/gitea-runners/registration-token";
-              extraPackages = with pkgs; [
+              hostPackages = with pkgs; [
+                bash
+                coreutils
+                curl
+                gawk
                 gitMinimal
-                gh
+                gnused
+                my_python
+                nix
                 nixfmt
                 nixos-rebuild
+                nodejs
                 treefmt
-                my_python
+                wget
               ];
             };
-            users = {
+            systemd.services."gitea-runner-${utils.escapeSystemdPath name}" = {
-              users.github-runners = {
+              serviceConfig = {
-                shell = pkgs.bash;
+                DynamicUser = mkForce false;
-                isSystemUser = true;
+                User = mkForce runnerUsername;
-                group = "github-runners";
+                Group = mkForce runnerUsername;
-                uid = 601;
               };
-              groups.github-runners.gid = 601;
             };
             system.stateVersion = "24.05";
           };
       }
     ) cfg.containers;
+
+    systemd.services = builtins.listToAttrs (
+      map (name: {
+        name = "container@${name}";
+        value = {
+          requires = [ "gitea.service" ];
+          after = [ "gitea.service" ];
+        };
+      }) (builtins.attrNames (filterAttrs (_: c: c.enable) cfg.containers))
+    );
   };
 }

systems/jeeves/scripts/zfs.sh

@@ -23,6 +23,7 @@ sudo zfs create media/secure/home_assistant -o compression=zstd-19
 sudo zfs create media/secure/notes -o copies=2
 sudo zfs create media/secure/postgres -o mountpoint=/zfs/media/database/postgres -o recordsize=16k -o primarycache=metadata
 sudo zfs create media/secure/postgres-wal -o mountpoint=/zfs/media/database/postgres-wal -o recordsize=32k -o primarycache=metadata -o special_small_blocks=32K -o compression=lz4 -o secondarycache=none -o logbias=latency
+sudo zfs create media/secure/prometheus -o mountpoint=/zfs/media/database/prometheus -o compression=lz4
 sudo zfs create media/secure/services -o compression=zstd-9
 sudo zfs create media/secure/share -o mountpoint=/zfs/media/share -o exec=off
 

systems/jeeves/services/gitea.nix

@@ -21,6 +21,10 @@ in
       createDatabase = false;
     };
     settings = {
+      actions = {
+        ENABLED = true;
+        DEFAULT_ACTIONS_URL = "github";
+      };
       service.DISABLE_REGISTRATION = true;
       server = {
         DOMAIN = "tmmworkshop.com";

systems/jeeves/services/grafana.nix

@@ -0,0 +1,80 @@
+{
+  ...
+}:
+let
+  vars = import ../vars.nix;
+  grafanaDataDir = "${vars.services}/grafana";
+in
+{
+  networking.firewall.allowedTCPPorts = [ 3000 ];
+
+  services.grafana = {
+    enable = true;
+    dataDir = grafanaDataDir;
+    settings = {
+      database.type = "sqlite3";
+      security = {
+        admin_password = "$__file{${vars.secrets}/services/grafana/admin_password}";
+        admin_user = "admin";
+        secret_key = "$__file{${vars.secrets}/services/grafana/secret_key}";
+      };
+      server = {
+        http_addr = "192.168.90.40";
+        http_port = 3000;
+        root_url = "http://192.168.90.40:3000/";
+      };
+    };
+    provision = {
+      enable = true;
+      dashboards.settings = {
+        apiVersion = 1;
+        providers = [
+          {
+            name = "monitoring";
+            folder = "Monitoring";
+            type = "file";
+            disableDeletion = false;
+            editable = false;
+            allowUiUpdates = false;
+            updateIntervalSeconds = 30;
+            options.path = ../monitoring/dashboards;
+          }
+        ];
+      };
+      datasources.settings = {
+        apiVersion = 1;
+        prune = true;
+        datasources = [
+          {
+            access = "proxy";
+            editable = false;
+            isDefault = true;
+            name = "prom-main";
+            type = "prometheus";
+            uid = "prom-main";
+            url = "http://127.0.0.1:9090";
+          }
+          {
+            access = "proxy";
+            editable = false;
+            name = "prom-pid-short";
+            type = "prometheus";
+            uid = "prom-pid-short";
+            url = "http://127.0.0.1:9092";
+          }
+        ];
+      };
+    };
+  };
+
+  systemd = {
+    services.grafana.after = [
+      "prometheus-main.service"
+      "prometheus-pid-short.service"
+    ];
+
+    tmpfiles.rules = [
+      "d ${grafanaDataDir} 0750 grafana grafana - -"
+    ];
+  };
+}

systems/jeeves/services/hedgedoc.nix

@@ -1,24 +0,0 @@
-{
-  services.hedgedoc = {
-    enable = true;
-    settings = {
-      host = "0.0.0.0";
-      port = 3000;
-      domain = "192.168.90.40";
-      urlAddPort = true;
-      protocolUseSSL = false;
-      db = {
-        dialect = "postgres";
-        database = "hedgedoc";
-        username = "hedgedoc";
-        host = "/run/postgresql";
-      };
-    };
-  };
-  networking.firewall.allowedTCPPorts = [ 3000 ];
-
-  systemd.services.hedgedoc = {
-    after = [ "postgresql.service" ];
-    requires = [ "postgresql.service" ];
-  };
-}

systems/jeeves/services/signal_bot.nix

@@ -1,57 +0,0 @@
-{
-  pkgs,
-  inputs,
-  ...
-}:
-let
-  vars = import ../vars.nix;
-in
-{
-  users = {
-    users.signalbot = {
-      isSystemUser = true;
-      group = "signalbot";
-    };
-    groups.signalbot = { };
-  };
-
-  systemd.services.signal-bot = {
-    description = "Signal command and control bot";
-    after = [
-      "network.target"
-      "podman-signal_cli_rest_api.service"
-    ];
-    wants = [ "podman-signal_cli_rest_api.service" ];
-    wantedBy = [ "multi-user.target" ];
-
-    environment = {
-      PYTHONPATH = "${inputs.self}";
-      SIGNALBOT_DB = "signalbot";
-      SIGNALBOT_USER = "signalbot";
-      SIGNALBOT_HOST = "/run/postgresql";
-      SIGNALBOT_PORT = "5432";
-    };
-
-    serviceConfig = {
-      Type = "simple";
-      WorkingDirectory = "${inputs.self}";
-      User = "signalbot";
-      Group = "signalbot";
-      EnvironmentFile = "${vars.secrets}/services/signal-bot";
-      ExecStart = "${pkgs.my_python}/bin/python -m python.signal_bot.main";
-      StateDirectory = "signal-bot";
-      Restart = "on-failure";
-      RestartSec = "10s";
-      StandardOutput = "journal";
-      StandardError = "journal";
-      NoNewPrivileges = true;
-      ProtectSystem = "strict";
-      ProtectHome = "read-only";
-      PrivateTmp = true;
-      ReadWritePaths = [ "/var/lib/signal-bot" ];
-      ReadOnlyPaths = [
-        "${inputs.self}"
-      ];
-    };
-  };
-}

systems/jeeves/web_services/acme.nix

@@ -5,7 +5,6 @@ let
     "gitea"
     "jellyfin"
     "share"
-    "verilux"
   ];
   extraDomains = [ "www.norn-sight.com" ];
 

systems/jeeves/web_services/haproxy.cfg

@@ -28,7 +28,6 @@ frontend ContentSwitching
 
   # ACME challenge routing (must be first)
   acl is_acme path_beg /.well-known/acme-challenge/
-  use_backend acme_challenge if is_acme
 
   # tmmworkshop.com
   acl host_audiobookshelf  hdr(host) -i audiobookshelf.tmmworkshop.com
@@ -45,6 +44,7 @@ frontend ContentSwitching
   # Redirect all HTTP to HTTPS unless on the allow list or ACME challenge
   http-request redirect scheme https code 301 if !{ ssl_fc } !allow_http !is_acme
 
+  use_backend acme_challenge if is_acme
   use_backend audiobookshelf_nodes if host_audiobookshelf
   use_backend cache_nodes  if host_cache
   use_backend jellyfin if host_jellyfin

users/richie/home/gui/vscode/keybindings.json

@@ -2,28 +2,32 @@
   {
     "key": "shift+alt+f",
     "command": "editor.action.formatDocument",
-    "when": "editorHasDocumentFormattingProvider && editorTextFocus && !editorReadonly && !inCompositeEditor"
+    "when": "editorHasDocumentFormattingProvider && editorTextFocus && !editorReadonly && !inCompositeEditor",
   },
   {
     "key": "alt+a d",
-    "command": "cSpell.addWordToWorkspaceSettings"
+    "command": "cSpell.addWordToWorkspaceSettings",
   },
   {
     "key": "ctrl+shift+`",
-    "command": "workbench.action.createTerminalEditor"
+    "command": "workbench.action.createTerminalEditor",
   },
   {
     "key": "ctrl+shift+`",
     "command": "-workbench.action.terminal.new",
-    "when": "terminalProcessSupported || terminalWebExtensionContributedProfile"
+    "when": "terminalProcessSupported || terminalWebExtensionContributedProfile",
   },
   {
     "key": "ctrl+shift+g r",
-    "command": "gitlens.git.rebase"
+    "command": "gitlens.git.rebase",
   },
   {
     "key": "ctrl+shift+g c",
     "command": "-gitlens.showQuickCommitFileDetails",
-    "when": "editorTextFocus && !gitlens:disabled && config.gitlens.keymap == 'chorded'"
+    "when": "editorTextFocus && !gitlens:disabled && config.gitlens.keymap == 'chorded'",
-  }
+  },
+  {
+    "key": "ctrl+shift+g p",
+    "command": "gitlens.pushRepositories",
+  },
 ]

users/richie/home/gui/vscode/settings.json

@@ -78,6 +78,8 @@
     "Corvidae",
     "drivername",
     "fastapi",
+    "Michal",
+    "Nornsight",
     "sandboxing",
     "syncthing",
   ],