forust/homelab
0
0 Fork 0
Code Issues 1 Pull Requests 3 Actions Packages Wiki Activity
Files
f54589a05c2234a70753b1871ed1aa6868761d92
homelab/.gitea/workflows/ci.yaml
T
forust 4f74fe1778 ci: stop inheriting the runner's python and node 
The runner executes jobs on the host rather than in a container, so a
workflow that says 'python3' or 'npm' is really saying 'whatever this
machine happens to have today'. Both of the test jobs added in c00a472
were red on the first run for exactly that reason.

uv venv with no --python takes the first interpreter it finds, which is
the host's 3.14 here. pyrogram's sync.py calls the bare
asyncio.get_event_loop() that 3.14 no longer auto-creates, so three
tests died at collection. Pinned to 3.13, which is both what uv will
fetch when the host has none and what python:3.13-slim actually builds.

npm was missing outright, and turned up an hour later as npm 12 on node
26 - the same push, minutes apart. Neither is the panel image's
node:22-alpine, so node is now installed from the official tarball the
way the other tools are, at the image's major. npm is checked by running
it rather than by looking it up, so a name that resolves to something
broken reads as not installed.

Renovate keeps NODE_VERSION in step with the Dockerfile's node: tag, and
the two are one grouped dependency: CI that tests on a different major
than it builds on is a gate that can pass over a real break.
2026-09-27 11:42:56 +02:00

699 lines
27 KiB
YAML
Raw Blame History

name: ci
on:
push:
branches:
- "**"
pull_request:
workflow_dispatch:
# Every job here is checkout plus local tools. The token needs to read the tree
# and nothing else, and saying so keeps a future step that reaches for the API
# from quietly holding a token that can write to the repository.
permissions:
contents: read
concurrency:
group: ci-${{ github.ref }}
cancel-in-progress: ${{ github.ref != 'refs/heads/main' }}
env:
REGISTRY: gcr.forust.xyz
jobs:
lint-compose:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
# Structure check for every committed Compose file, active or not.
# Interpolation, env-file and bind-mount resolution are all switched off,
# because inactive stacks have no .env here and would only fail on their
# ${VAR:?} guards. Active stacks get the full check with interpolation in
# the deploy workflow, where the real .env files live.
- name: Validate Compose files
shell: bash
run: |
set -euo pipefail
source .gitea/workflows/compose-lint.sh
mapfile -t safe_flags < <(compose_safe_flags)
echo "docker compose config ${safe_flags[*]-}"
mapfile -t files < <(compose_files)
if [ "${#files[@]}" -eq 0 ]; then
echo "No Compose files found."
exit 0
fi
failed=0
for f in "${files[@]}"; do
if ! out="$(validate_compose_file "$f" ${safe_flags[@]+"${safe_flags[@]}"} 2>&1)"; then
failed=1
echo "::error file=${f}::$(printf '%s' "$out" | head -1)"
fi
done
if [ "$failed" -ne 0 ]; then
echo "Compose validation failed."
exit 1
fi
echo "checked ${#files[@]} Compose file(s)"
lint-actionlint:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Lint Gitea Actions workflows with actionlint
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh actionlint)"
export PATH="$tools_dir:$PATH"
actionlint -config-file .gitea/actionlint.yaml -color .gitea/workflows/*.yaml
lint-shellcheck:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Lint shell scripts with ShellCheck
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh shellcheck)"
export PATH="$tools_dir:$PATH"
# userbot/ is a git subtree synced from forust/userbot, so its shell
# scripts are upstream's to maintain, not ours. Linting them would let a
# routine subtree pull turn the deploy gate red on code we do not own.
mapfile -t scripts < <(
git ls-files '*.sh' ':(glob)**/*.bash' ':!userbot/**'
)
if [ "${#scripts[@]}" -eq 0 ]; then
echo "No shell scripts found."
exit 0
fi
shellcheck --external-sources --source-path=SCRIPTDIR --severity=style "${scripts[@]}"
lint-prettier:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Check formatting with Prettier
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh prettier)"
export PATH="$tools_dir:$PATH"
mapfile -t prettier_files < <(
git ls-files \
| grep -E '\.(md|json|ya?ml|html|css)$' \
| grep -Ev '^(\.docs/|\.zed/|errorpages/html/|homepages/(forust_files|xdfnx_files)/)'
)
if [ "${#prettier_files[@]}" -eq 0 ]; then
echo "No Prettier-managed files found."
exit 0
fi
prettier --check --ignore-unknown "${prettier_files[@]}"
lint-ruff:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Lint and format-check Python with Ruff
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh ruff)"
export PATH="$tools_dir:$PATH"
ruff check .
ruff format --check .
lint-yaml:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Lint YAML syntax
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh yamllint)"
export PATH="$tools_dir:$PATH"
mapfile -t yaml_files < <(
git ls-files '*.yaml' '*.yml' \
':!node_modules/**' \
':!**/.venv/**'
)
if [ "${#yaml_files[@]}" -eq 0 ]; then
echo "No YAML files found."
exit 0
fi
yamllint -c .yamllint "${yaml_files[@]}"
lint-dockerfiles:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 10
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Lint Dockerfiles
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh hadolint)"
export PATH="$tools_dir:$PATH"
mapfile -t dockerfiles < <(
git ls-files ':(glob)**/Dockerfile' ':(glob)**/Dockerfile.*'
)
if [ "${#dockerfiles[@]}" -eq 0 ]; then
echo "No Dockerfiles found."
exit 0
fi
hadolint -c .hadolint.yaml "${dockerfiles[@]}"
# Known, accepted, and recorded. Each line is a real advisory against a
# package we build into the panel image, kept in this workflow rather than in
# the package manifest so that a subtree sync from forust/userbot cannot
# silently widen the exemption.
#
# starlette is the reason this job is not simply "fail on everything":
# fastapi 0.115.12 pins `starlette<0.47.0`, and the fixes for the last four
# below need 0.49.1 through 1.3.1, so clearing them means a jump from fastapi
# 0.115.12 to 0.141.x. That is upstream's call, not a drive-by in a lint
# commit. Of the seven, four are reachable here in principle: 1942 is a
# crafted Range header hitting FileResponse, and the panel serves its built
# SPA through exactly that; 249 is request.form() ignoring max_fields for
# x-www-form-urlencoded, which is the login form; 1941 is a large multipart
# body blocking the event loop; 161 and 248 are unvalidated Host and request
# path reaching request.url. 2280 needs HTTPEndpoint, which the panel does
# not use, and 2281 is Windows-only, and this deploys on Linux.
#
# The panel answers on userbot.workstation.internal and has no public
# forust.xyz route, which is what keeps the four reachable ones from being
# an internet-facing DoS. It still manages Telegram credentials.
#
# Deleting an entry here is how you accept a new advisory, so the diff says
# so out loud.
scan-deps:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 15
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Audit the Python dependencies that ship in the image
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh pip-audit)"
export PATH="$tools_dir:$PATH"
# requirements.txt, not requirements-dev.txt: this is what the image
# installs, and the test tooling is not a shipped attack surface.
pip-audit -r userbot/panel/backend/requirements.txt --strict \
--ignore-vuln CVE-2025-67720 \
--ignore-vuln PYSEC-2026-161 \
--ignore-vuln PYSEC-2026-1941 \
--ignore-vuln PYSEC-2026-1942 \
--ignore-vuln PYSEC-2026-2280 \
--ignore-vuln PYSEC-2026-2281 \
--ignore-vuln PYSEC-2026-248 \
--ignore-vuln PYSEC-2026-249
# devDependencies are excluded on purpose. `npm audit` on the full tree
# reports 7 findings, and every one of them is a build- or test-time
# package: the esbuild CORS advisory needs a vite dev server serving to
# the internet, and nanoid's infinite loop needs a custom generator
# called with size 0, which postcss does not do. None of them are in the
# 91 kB bundle the panel serves. The one production finding, devalue
# via svelte, is moderate, which is where --audit-level draws the line;
# this fails on the next high or critical one.
- name: Audit the production npm dependencies
shell: bash
run: |
set -euo pipefail
# The pinned node, not whatever the runner has. Its system node is a
# rolling Arch package: during this very push its npm was missing
# entirely, and an hour later it was npm 12 on node 26. Both are the
# wrong major anyway — the panel image is node:22-alpine.
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh node)"
export PATH="$tools_dir:$PATH"
cd userbot/panel/frontend
npm ci
npm audit --omit=dev --audit-level=high
test-backend:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 15
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
# 25 tests over the panel's pydantic models, its auth flow, the SPA
# fallback and the Kubernetes client it shells out with. They existed and
# had never been executed by anything.
#
# Note that userbot/ is a subtree synced from forust/userbot, so a routine
# sync can turn this red on upstream's code. Unlike the shellcheck job,
# which skips that tree because style disagreements there are ours to
# lose, a failing test here is a real defect in a service we deploy.
- name: Run the panel backend test suite
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh uv)"
export PATH="$tools_dir:$PATH"
# A venv in a temp dir rather than a checked-out one: the runner is
# shared, and a leftover .venv would let a dependency the
# requirements no longer pin still satisfy an import.
#
# --python is not optional. uv otherwise takes whatever interpreter it
# finds first, and which one that is depends on the machine: this
# runner runs jobs on the host, where the only interpreter is 3.14,
# and pyrogram's sync.py calls the bare asyncio.get_event_loop() that
# 3.14 no longer auto-creates, so three tests fail at collection. The
# image is python:3.13-slim, so 3.13 is also the version worth
# testing: uv fetches a managed build of it when the host has none,
# which is what makes this job independent of the runner.
venv="$(mktemp -d)/venv"
uv venv --python 3.13 --quiet "$venv"
uv pip install --quiet --python "$venv/bin/python" \
-r userbot/panel/backend/requirements-dev.txt
# `python -m`, not bare `pytest`: the tests import `app.*` relative to
# the backend directory, which only works if the cwd is on sys.path,
# and only `python -m` puts it there.
cd userbot/panel/backend
"$venv/bin/python" -m pytest tests/ -q
test-frontend:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 15
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
# One `npm ci` for both checks below: it is by far the slowest part of
# this job, and a second one would learn nothing the first did not.
#
# `npm ci`, not `npm install`, for the same reason the Dockerfile uses it:
# the lockfile is what makes the tree that gets checked the tree that
# gets shipped.
- name: Type-check and test the panel frontend
shell: bash
run: |
set -euo pipefail
# The pinned node, not whatever the runner has. Its system node is a
# rolling Arch package: during this very push its npm was missing
# entirely, and an hour later it was npm 12 on node 26. Both are the
# wrong major anyway — the panel image is node:22-alpine.
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh node)"
export PATH="$tools_dir:$PATH"
cd userbot/panel/frontend
npm ci
# svelte-check has been a devDependency all along with no script
# pointing at it, so the type errors it reports had nowhere to
# surface. It is clean today, which is the only reason it can be a
# gate: it stops at whatever upstream introduces rather than
# reporting a backlog we inherited.
npm run check
npm test
validate:
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 20
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
- name: Validate Kubernetes manifests against JSON schemas
shell: bash
run: |
set -euo pipefail
tools_dir="$(bash .gitea/workflows/install-ci-tools.sh kubeconform)"
export PATH="$tools_dir:$PATH"
mapfile -t manifests < <(
git ls-files ':(glob)**/k8s/**/*.yaml' ':(glob)**/k8s/**/*.yml' \
| grep -Ev '(^|/)(kustomization\.ya?ml|.*\.example\.ya?ml|.*values\.ya?ml|patch-.*\.ya?ml)$'
)
if [ "${#manifests[@]}" -eq 0 ]; then
echo "No Kubernetes manifests found."
exit 0
fi
kubeconform \
-strict \
-ignore-missing-schemas \
-summary \
"${manifests[@]}"
# kubeconform has no schemas for CRDs, so every IngressRoute, Certificate,
# PrometheusRule, Middleware, ServersTransport and ServiceMonitor is silently
# skipped above. The live API server knows the real CRD schemas (and runs the
# cert-manager / Traefik admission webhooks), so validate there too.
#
# Only services marked with a k8s/active marker are checked: server-side
# dry-run needs the target namespace to exist, and inactive services are not
# deployed. Services being enabled for the first time are still covered by
# the JSON-schema pass above.
#
# Main pushes only. `--dry-run=server` persists nothing, but it does execute
# the admission webhooks of the production API server, so anyone able to open
# a pull request would be able to run arbitrary manifest content through
# cert-manager and Traefik. A pull request has nothing to gain from it either:
# only main is ever deployed, and this job runs to completion before the
# deploy workflow is allowed to start, so a bad CRD is still caught before
# anything reaches the cluster -- just on the push rather than on the PR.
- name: Note the server-side check is not running here
if: github.event_name == 'pull_request' || github.ref != 'refs/heads/main'
shell: bash
run: |
echo "::notice::Skipping the server-side dry-run. It executes the cert-manager and" \
"Traefik admission webhooks against the production API server, so it is limited" \
"to pushes to main. CRDs are still schema-checked by kubeconform above, and the" \
"server-side pass still runs on main before the deploy."
- name: Validate active manifests against the live API server
if: github.event_name != 'pull_request' && github.ref == 'refs/heads/main'
shell: bash
run: |
set -euo pipefail
if ! kubectl get --raw='/readyz' --request-timeout=10s >/dev/null 2>&1; then
echo "::warning::Cluster unreachable — skipped server-side validation of CRDs (IngressRoute, Certificate, PrometheusRule). Review manifest changes manually."
exit 0
fi
mapfile -t k8s_dirs < <(
git ls-files '*.yaml' '*.yml' \
| grep -E '(^|/)k8s/' \
| sed -E 's#((^|.*/)k8s)/.*#\1#' \
| sort -u
)
manifests=()
kustomize_apps=()
for dir in "${k8s_dirs[@]}"; do
if [ ! -f "${dir}/active" ]; then
echo "skip (no k8s/active): ${dir}"
continue
fi
if [ -f "${dir}/overlays/prod/kustomization.yaml" ]; then
kustomize_apps+=("${dir}/overlays/prod")
elif [ -f "${dir}/base/kustomization.yaml" ]; then
kustomize_apps+=("${dir}/base")
else
while IFS= read -r f; do
[ -n "$f" ] && manifests+=("$f")
done < <(
git ls-files "${dir}/*.yaml" "${dir}/*.yml" \
| grep -Ev '(^|/)(kustomization\.ya?ml|.*\.example\.ya?ml|.*values\.ya?ml|patch-.*\.ya?ml)$'
)
fi
done
echo "server-side dry-run: ${#manifests[@]} manifests, ${#kustomize_apps[@]} kustomize apps"
failed=0
for m in ${manifests[@]+"${manifests[@]}"}; do
if ! out="$(kubectl apply --dry-run=server -f "$m" 2>&1)"; then
failed=1
echo "::error file=${m}::$(printf '%s' "$out" | head -1)"
fi
done
for k in ${kustomize_apps[@]+"${kustomize_apps[@]}"}; do
if ! out="$(kubectl apply -k "$k" --dry-run=server 2>&1)"; then
failed=1
echo "::error file=${k}::$(printf '%s' "$out" | head -1)"
fi
done
if [ "$failed" -ne 0 ]; then
echo "Server-side validation failed. The API server (or an admission webhook) rejected these manifests."
exit 1
fi
echo "server-side dry-run: all active manifests accepted by the API server"
build:
needs:
[lint-actionlint, lint-shellcheck, lint-compose, lint-prettier, lint-ruff, lint-yaml, lint-dockerfiles, validate]
if: github.event_name != 'pull_request' && (github.ref_name == 'main' || github.ref_name == 'dev')
runs-on: [self-hosted, linux, arch, homelab]
timeout-minutes: 60
outputs:
services: ${{ steps.services.outputs.services }}
steps:
- name: Checkout repository
uses: actions/checkout@11d5960a326750d5838078e36cf38b85af677262 # v4
with:
fetch-depth: 0
- name: Detect changed docker-built services
id: services
shell: bash
run: |
base="${{ github.event.before }}"
if [ -z "$base" ] || [ "$base" = "0000000000000000000000000000000000000000" ]; then
base="$(git rev-list --max-parents=0 HEAD)"
fi
mapfile -t changed_files < <(git diff --name-only "$base" "${GITHUB_SHA}")
services=()
add_service() {
local name="$1"
local seen=0
for existing in "${services[@]}"; do
if [ "$existing" = "$name" ]; then
seen=1
break
fi
done
if [ "$seen" -eq 0 ]; then
services+=("$name")
fi
}
for file in "${changed_files[@]}"; do
case "$file" in
dtek_notif/*)
add_service dtek_notif
;;
errorpages/*)
add_service errorpages
;;
userbot/*)
add_service userbot
;;
homepages/*)
add_service homepages
;;
edu_master/phpsessid-bot/*|edu_master/webinar-checker/*|edu_master/compose.yaml)
add_service edu_master
;;
esac
done
if [ "${#services[@]}" -eq 0 ]; then
echo "No docker-built services changed."
echo "services=" >> "$GITHUB_OUTPUT"
exit 0
fi
printf '%s\n' "${services[@]}" | tee /tmp/services.txt
echo "services=$(paste -sd, /tmp/services.txt)" >> "$GITHUB_OUTPUT"
- name: Log in to registry
if: steps.services.outputs.services != ''
shell: bash
run: |
echo "${{ secrets.REGISTRY_PASSWORD }}" | docker login "${REGISTRY}" \
-u "${{ secrets.REGISTRY_USERNAME }}" \
--password-stdin
- name: Build and push changed images
if: steps.services.outputs.services != ''
shell: bash
run: |
IFS=, read -r -a services <<< "${{ steps.services.outputs.services }}"
for service in "${services[@]}"; do
case "$service" in
dtek_notif)
image="${REGISTRY}/forust/dtek-notif"
tags=()
case "${GITHUB_REF_NAME}" in
main)
tags+=("main" "prod")
;;
dev)
tags+=("dev")
;;
esac
build_args=()
for tag in "${tags[@]}"; do
build_args+=(-t "${image}:${tag}")
done
docker build \
--cache-from "type=registry,ref=${image}:buildcache" \
--cache-to "type=registry,ref=${image}:buildcache,mode=max" \
"${build_args[@]}" dtek_notif
for tag in "${tags[@]}"; do
docker push "${image}:${tag}"
done
;;
errorpages)
image="${REGISTRY}/forust/error-pages"
tags=()
case "${GITHUB_REF_NAME}" in
main)
tags+=("main" "prod")
;;
dev)
tags+=("dev")
;;
esac
build_args=()
for tag in "${tags[@]}"; do
build_args+=(-t "${image}:${tag}")
done
docker build \
--cache-from "type=registry,ref=${image}:buildcache" \
--cache-to "type=registry,ref=${image}:buildcache,mode=max" \
"${build_args[@]}" errorpages
for tag in "${tags[@]}"; do
docker push "${image}:${tag}"
done
;;
userbot)
tags=()
case "${GITHUB_REF_NAME}" in
main)
tags+=("main" "prod")
;;
dev)
tags+=("dev")
;;
esac
for target in runtime panel; do
case "$target" in
runtime)
context="userbot"
image="${REGISTRY}/forust/userbot"
;;
panel)
context="userbot/panel"
image="${REGISTRY}/forust/userbot-panel"
;;
esac
build_args=()
for tag in "${tags[@]}"; do
build_args+=(-t "${image}:${tag}")
done
docker build \
--cache-from "type=registry,ref=${image}:buildcache" \
--cache-to "type=registry,ref=${image}:buildcache,mode=max" \
"${build_args[@]}" "$context"
for tag in "${tags[@]}"; do
docker push "${image}:${tag}"
done
done
;;
homepages)
for variant in forust xdfnx; do
case "$variant" in
forust)
image="${REGISTRY}/forust/forust-homepage"
;;
xdfnx)
image="${REGISTRY}/forust/xdfnx-homepage"
;;
esac
tags=()
case "${GITHUB_REF_NAME}" in
main)
tags+=("main" "prod")
;;
dev)
tags+=("dev")
;;
esac
build_args=()
for tag in "${tags[@]}"; do
build_args+=(-t "${image}:${tag}")
done
docker build \
--cache-from "type=registry,ref=${image}:buildcache" \
--cache-to "type=registry,ref=${image}:buildcache,mode=max" \
"${build_args[@]}" -f "homepages/Dockerfile.${variant}" homepages
for tag in "${tags[@]}"; do
docker push "${image}:${tag}"
done
done
;;
edu_master)
for variant in session-keeper webinar-checker; do
case "$variant" in
session-keeper)
context="edu_master/phpsessid-bot"
image="${REGISTRY}/forust/session-keeper"
;;
webinar-checker)
context="edu_master/webinar-checker"
image="${REGISTRY}/forust/webinar-checker"
;;
esac
tags=()
case "${GITHUB_REF_NAME}" in
main)
tags+=("main" "prod")
;;
dev)
tags+=("dev")
;;
esac
build_args=()
for tag in "${tags[@]}"; do
build_args+=(-t "${image}:${tag}")
done
docker build \
--cache-from "type=registry,ref=${image}:buildcache" \
--cache-to "type=registry,ref=${image}:buildcache,mode=max" \
"${build_args[@]}" "$context"
for tag in "${tags[@]}"; do
docker push "${image}:${tag}"
done
done
;;
esac
done
Reference in new issue View Git Blame Copy Permalink