fix(cicd): isolate pull request runner jobs

.gitea/actionlint.yaml

@@ -7,4 +7,5 @@ self-hosted-runner:
   labels:
     - arch
     - homelab
+    - homelab-pr
     - prod

.gitea/runner/README.md

@@ -1,17 +1,18 @@
 # Homelab CI/CD
 
-The native Gitea runner runs on **vps**; production runs on **workstation**.
+The native Gitea runners run on **vps**; production runs on **workstation**.
-Compose, workflow, shell, Python, formatting, YAML, Dockerfile and Kubernetes
+Main-branch checks and image builds use `homelab:host`. Pull request and
-checks appear as separate jobs. Jobs run on `homelab:host`, one at a time; the
+non-main checks use `homelab-pr:host` under a separate account without Docker
-build waits for every check to pass. CI and deploy runs also show a summary with
+access. Each runner accepts one job at a time; the build waits for every check
+to pass. CI and deploy runs also show a summary with
 the release SHA, image build or reuse results, deploy mode, selected services,
 and image digests. Failed runs keep a summary of completed image builds, stage
 results, apply results, and recorded Kubernetes recovery. The final deploy
 summary is in the smoke job; earlier jobs show the state observed at that time.
 Apply success is separate from health and recovery. Update the installed
 workstation controller with `setup-workstation.sh` when no deploy is running.
-No job images or Kubernetes credentials
+No job images or Kubernetes credentials are needed on the VPS. Builds use one
-are needed on the VPS. Builds use one pinned BuildKit helper container. CI and deploy are separate workflows.
+pinned BuildKit helper container. CI and deploy are separate workflows.
 
 ## Runner installation
 
@@ -37,6 +38,32 @@ pushes directly to the registry, and caps retained local cache at 1 GiB with a
 2 GiB free-space target. This is not a hard limit on peak build disk usage.
 Nothing runs `docker system prune`, removes unrelated images, or deletes volumes.
 
+### Pull request runner
+
+Install the unprivileged host runner on the VPS:
+
+```sh
+sudo bash .gitea/runner/setup-pr-runner.sh
+```
+
+Get a registration token from the repository Actions runner settings. Run the
+installer in a terminal. It asks for the token without echoing it, registers the
+runner as `homelab-pr` with label `homelab-pr:host`, then enables the service.
+The work directory is `/var/lib/gitea-pr-runner`. Confirm that Gitea lists
+`homelab-pr:host` before merging the workflow change. An unmatched label can
+fall back to the default job image.
+
+Renovate PR validation uses `pull_request_target`, which reads the workflow from
+the base branch. It checks out the PR head only after runner selection and runs
+that code on `homelab-pr`. Keep this workflow read-only and do not add secrets.
+
+The PR runner has a separate home and tool cache. Do not add it to the `docker`
+group or give it access to `/var/run/docker.sock`. It runs repository code from
+pull requests, so keep its registration and permissions separate from the
+trusted `homelab` runner. This separates users and host permissions, but both
+runners still share the VPS kernel and network. Use a disposable VM if PRs from
+untrusted external authors must be fully isolated.
+
 ## Workstation setup
 
 As the existing SSH deploy user on workstation:

.gitea/runner/pr-config.yaml

@@ -0,0 +1,8 @@
+runner:
+  file: /var/lib/gitea-pr-runner/.runner
+  capacity: 1
+  timeout: 5h
+  labels:
+    - homelab-pr:host
+cache:
+  enabled: false

.gitea/runner/pr-runner.service

@@ -0,0 +1,27 @@
+[Unit]
+Description=Gitea Actions untrusted pull request runner
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+User=gitea-pr-runner
+Group=gitea-pr-runner
+WorkingDirectory=/var/lib/gitea-pr-runner
+Environment=HOME=/var/lib/gitea-pr-runner
+Environment=PATH=/var/lib/gitea-pr-runner/.cache/homelab-ci/bin:/usr/local/bin:/usr/bin:/bin
+ExecStart=/usr/local/bin/gitea-runner daemon --config /etc/gitea-pr-runner/config.yaml
+Restart=on-failure
+RestartSec=5
+NoNewPrivileges=yes
+PrivateTmp=yes
+ProtectSystem=full
+ProtectHome=yes
+ProtectKernelTunables=yes
+ProtectKernelModules=yes
+ProtectControlGroups=yes
+RestrictSUIDSGID=yes
+LockPersonality=yes
+UMask=0077
+
+[Install]
+WantedBy=multi-user.target

.gitea/runner/setup-pr-runner.sh

@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+# Install a native runner for untrusted PR jobs without Docker access.
+set -euo pipefail
+here="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+[ "$(id -u)" -eq 0 ] || { echo 'Run with sudo on the runner host' >&2; exit 1; }
+for tool in cp cut date getent id install runuser systemctl useradd; do
+  command -v "$tool" >/dev/null || { echo "Install missing prerequisite: $tool" >&2; exit 1; }
+done
+command -v /usr/local/bin/gitea-runner >/dev/null || {
+  echo 'Install gitea-runner 3.0.2 at /usr/local/bin/gitea-runner first' >&2
+  exit 1
+}
+
+id gitea-pr-runner >/dev/null 2>&1 || \
+  useradd --system --create-home --home-dir /var/lib/gitea-pr-runner --shell /usr/bin/bash gitea-pr-runner
+runner_home="$(getent passwd gitea-pr-runner | cut -d: -f6)"
+[ "$runner_home" = /var/lib/gitea-pr-runner ] || {
+  echo 'Unexpected PR runner home; inspect the existing service first' >&2
+  exit 1
+}
+case " $(id -nG gitea-pr-runner) " in
+  *' docker '*)
+    echo 'The PR runner account must not belong to the docker group' >&2
+    exit 1
+    ;;
+esac
+
+install -d -m 0755 /etc/gitea-pr-runner
+stamp="$(date -u +%Y%m%dT%H%M%SZ)"
+for existing in /etc/gitea-pr-runner/config.yaml /etc/systemd/system/gitea-pr-runner.service; do
+  [ ! -f "$existing" ] || cp -p "$existing" "$existing.before-$stamp"
+done
+install -m 0644 "$here/pr-config.yaml" /etc/gitea-pr-runner/config.yaml
+install -m 0644 "$here/pr-runner.service" /etc/systemd/system/gitea-pr-runner.service
+
+if [ ! -f /var/lib/gitea-pr-runner/.runner ]; then
+  read -r -s -p 'Enter the Gitea repository runner registration token: ' runner_token
+  printf '\n'
+  [ -n "$runner_token" ] || { echo 'Runner token is required' >&2; exit 1; }
+  export GITEA_RUNNER_REGISTRATION_TOKEN="$runner_token"
+  unset runner_token
+  runuser --preserve-environment -u gitea-pr-runner -- \
+    /usr/local/bin/gitea-runner register \
+    --config /etc/gitea-pr-runner/config.yaml \
+    --instance https://gitea.forust.xyz \
+    --name homelab-pr \
+    --labels homelab-pr:host \
+    --no-interactive
+  unset GITEA_RUNNER_REGISTRATION_TOKEN
+fi
+
+systemctl daemon-reload
+systemctl enable --now gitea-pr-runner.service
+systemctl restart gitea-pr-runner.service
+echo "PR runner ready. Configuration backups: *.before-$stamp"

.gitea/workflows/ci.yaml

@@ -14,7 +14,7 @@ concurrency:
 jobs:
   compose:
     name: Compose
-    runs-on: homelab
+    runs-on: ${{ github.ref == 'refs/heads/main' && 'homelab' || 'homelab-pr' }}
     timeout-minutes: 15
     steps:
       - name: Checkout repository
@@ -66,7 +66,7 @@ jobs:
           fi
   workflows:
     name: Workflows
-    runs-on: homelab
+    runs-on: ${{ github.ref == 'refs/heads/main' && 'homelab' || 'homelab-pr' }}
     timeout-minutes: 15
     steps:
       - name: Checkout repository
@@ -102,7 +102,7 @@ jobs:
           fi
   shell:
     name: Shell
-    runs-on: homelab
+    runs-on: ${{ github.ref == 'refs/heads/main' && 'homelab' || 'homelab-pr' }}
     timeout-minutes: 15
     steps:
       - name: Checkout repository
@@ -146,7 +146,7 @@ jobs:
           fi
   formatting:
     name: Formatting
-    runs-on: homelab
+    runs-on: ${{ github.ref == 'refs/heads/main' && 'homelab' || 'homelab-pr' }}
     timeout-minutes: 15
     steps:
       - name: Checkout repository
@@ -194,7 +194,7 @@ jobs:
           fi
   python:
     name: Python and tests
-    runs-on: homelab
+    runs-on: ${{ github.ref == 'refs/heads/main' && 'homelab' || 'homelab-pr' }}
     timeout-minutes: 15
     steps:
       - name: Checkout repository
@@ -232,7 +232,7 @@ jobs:
           fi
   yaml:
     name: YAML
-    runs-on: homelab
+    runs-on: ${{ github.ref == 'refs/heads/main' && 'homelab' || 'homelab-pr' }}
     timeout-minutes: 15
     steps:
       - name: Checkout repository
@@ -280,7 +280,7 @@ jobs:
           fi
   dockerfiles:
     name: Dockerfiles
-    runs-on: homelab
+    runs-on: ${{ github.ref == 'refs/heads/main' && 'homelab' || 'homelab-pr' }}
     timeout-minutes: 15
     steps:
       - name: Checkout repository
@@ -326,7 +326,7 @@ jobs:
           fi
   kubernetes:
     name: Kubernetes
-    runs-on: homelab
+    runs-on: ${{ github.ref == 'refs/heads/main' && 'homelab' || 'homelab-pr' }}
     timeout-minutes: 15
     steps:
       - name: Checkout repository

.gitea/workflows/renovate-ci.yaml

@@ -1,7 +1,9 @@
 name: renovate-ci
 
 on:
-  pull_request:
+  # Read the workflow from the trusted base branch. PR code runs only on the
+  # unprivileged runner selected below.
+  pull_request_target:
     paths:
       - "renovate/**"
       - ".gitea/workflows/renovate-ci.yaml"
@@ -26,37 +28,47 @@ permissions:
 
 jobs:
   validate-renovate:
-    runs-on: homelab
+    runs-on: ${{ github.event_name == 'push' && github.ref == 'refs/heads/main' && 'homelab' || 'homelab-pr' }}
     timeout-minutes: 20
     steps:
       - name: Checkout repository
         uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
+        with:
+          ref: ${{ github.event_name == 'pull_request_target' && github.event.pull_request.head.sha || github.sha }}
 
-      # renovate/k8s/cronjob.yaml is the single source of truth for the image tag,
+      # renovate/k8s/cronjob.yaml is the single source of truth for the version.
-      # so the same version that runs in the cluster is the one validated here.
+      - name: Resolve the deployed Renovate version
-      - name: Resolve the deployed Renovate image
         id: image
         shell: bash
         run: |
           set -euo pipefail
           image="$(sed -n 's|.*image:[[:space:]]*\(renovate/renovate:[^[:space:]]*\).*|\1|p' \
             renovate/k8s/cronjob.yaml | head -1)"
-          if [ -z "$image" ]; then
+          if [[ ! "$image" =~ ^renovate/renovate:([0-9]+\.[0-9]+\.[0-9]+)$ ]]; then
-            echo "::error::no renovate/renovate image found in renovate/k8s/cronjob.yaml"
+            echo "::error::expected a pinned renovate/renovate semantic version in renovate/k8s/cronjob.yaml"
             exit 1
           fi
-          echo "using $image"
+          version="${BASH_REMATCH[1]}"
-          echo "image=$image" >> "$GITHUB_OUTPUT"
+          echo "using Renovate $version"
+          printf 'version=%s\n' "$version" >> "$GITHUB_OUTPUT"
 
-      - name: Validate Renovate repository config
+      - name: Prepare pinned validation tools
         shell: bash
         run: |
           set -euo pipefail
-          docker run --rm \
+          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh kubeconform node)"
-            -v "$PWD/renovate:/opt/renovate:ro" \
+          echo "$tools_dir" >> "$GITHUB_PATH"
-            -e RENOVATE_CONFIG_FILE=/opt/renovate/renovate.json \
+
-            "${{ steps.image.outputs.image }}" \
+      - name: Validate Renovate repository config
-            renovate-config-validator /opt/renovate/renovate.json
+        shell: bash
+        env:
+          RENOVATE_VERSION: ${{ steps.image.outputs.version }}
+        run: |
+          set -euo pipefail
+          npm_cache="$(mktemp -d "${RUNNER_TEMP:-/tmp}/renovate-npm-cache.XXXXXXXX")"
+          trap 'rm -rf "$npm_cache"' EXIT
+          NPM_CONFIG_CACHE="$npm_cache" RENOVATE_CONFIG_FILE="$PWD/renovate/renovate.json" \
+            npm exec --yes --package="renovate@${RENOVATE_VERSION}" -- renovate-config-validator
 
       # The CronJob cannot read the repository, so renovate/k8s/configmap.yaml
       # carries an inlined copy of the config. Fail if it no longer matches.
@@ -70,8 +82,6 @@ jobs:
         shell: bash
         run: |
           set -euo pipefail
-          tools_dir="$(bash .gitea/workflows/install-ci-tools.sh kubeconform)"
-          export PATH="$tools_dir:$PATH"
           kubeconform \
             -strict \
             -ignore-missing-schemas \

.gitea/workflows/renovate-run.yaml

@@ -32,11 +32,14 @@ concurrency:
 
 jobs:
   run-renovate:
+    if: github.ref == 'refs/heads/main'
     runs-on: homelab
     timeout-minutes: 60
     steps:
       - name: Checkout repository
         uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
+        with:
+          ref: refs/heads/main
 
       # renovate/k8s/cronjob.yaml is the single source of truth for the image tag.
       # Reading it here means this workflow validates and runs the exact version
@@ -48,21 +51,23 @@ jobs:
           set -euo pipefail
           image="$(sed -n 's|.*image:[[:space:]]*\(renovate/renovate:[^[:space:]]*\).*|\1|p' \
             renovate/k8s/cronjob.yaml | head -1)"
-          if [ -z "$image" ]; then
+          if [[ ! "$image" =~ ^renovate/renovate:[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
-            echo "::error::no renovate/renovate image found in renovate/k8s/cronjob.yaml"
+            echo "::error::expected a pinned renovate/renovate semantic version in renovate/k8s/cronjob.yaml"
             exit 1
           fi
           echo "using $image"
-          echo "image=$image" >> "$GITHUB_OUTPUT"
+          printf 'image=%s\n' "$image" >> "$GITHUB_OUTPUT"
 
       - name: Validate Renovate config
         shell: bash
+        env:
+          RENOVATE_IMAGE: ${{ steps.image.outputs.image }}
         run: |
           set -euo pipefail
           docker run --rm \
             -v "$PWD/renovate/renovate.json:/opt/renovate/renovate.json:ro" \
             -e RENOVATE_CONFIG_FILE=/opt/renovate/renovate.json \
-            "${{ steps.image.outputs.image }}" \
+            "$RENOVATE_IMAGE" \
             renovate-config-validator
 
       - name: Run Renovate
@@ -73,6 +78,7 @@ jobs:
           RENOVATE_REPOSITORIES: ${{ inputs.repositories }}
           RENOVATE_DRY_RUN: ${{ inputs.dry_run && 'full' || '' }}
           LOG_LEVEL: ${{ inputs.log_level }}
+          RENOVATE_IMAGE: ${{ steps.image.outputs.image }}
         run: |
           set -euo pipefail
 
@@ -89,4 +95,4 @@ jobs:
             -e RENOVATE_CONFIG_FILE=/opt/renovate/renovate.json \
             -e RENOVATE_BASE_DIR=/tmp/renovate \
             -e LOG_LEVEL="${LOG_LEVEL:-info}" \
-            "${{ steps.image.outputs.image }}"
+            "$RENOVATE_IMAGE"