teqo-backup/.forgejo/workflows/ci.yml
Francisco Solla 6a3f61f968 ops(OPS53): etapa de deploy no CI para o homeserver (teqo-1313)
Job deploy em ci.yml (runs-on host na workstation) streama
scripts/deploy-homeserver.sh para o homeserver via SSH: build dos stages
runner+migrator com secrets do teqo-1313.env, push no registry local,
migrate pelo serviço de maintenance antes do rollout, up + smoke. Zero
secrets novos no Forgejo; HEAD guard + flock; rollback automático com
backup do compose; runbook docs/ops/teqo-1313-deploy.md; invariantes
unit do script (bash -n + estrutura).
2026-08-18 00:50:41 +00:00

228 lines
8.7 KiB
YAML
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Post-merge verifier on `main`: always the FULL suite (no affected skips).
# When the suite is green, the `deploy` job publishes teqo-1313 on the
# homeserver (OPS53): it streams scripts/deploy-homeserver.sh to the homeserver
# over SSH; the remote script builds the standalone image at the pushed SHA,
# pushes it to the local registry (localhost:5000), applies pending migrations
# through the compose maintenance service and rolls the container out.
#
# Forgejo port (OPS50): Postgres services publish to per-job HOST ports on the
# runner machine (act/forgejo runner semantics — the canonical 5432 is the
# workstation's own dev database), and jobs reach them through the bridge
# gateway: DB_HOST = gateway IP from /proc/net/route. No `permissions:`
# (Forgejo issues one native GITHUB_TOKEN) and no `concurrency:` (unsupported).
# `gh workflow run` requeues became `node scripts/forgejo-dispatch.mjs`.
# The GitHub fail-fast action was dropped (Forgejo has no cancel-run plumbing);
# job timeouts cover that role.
name: CI
on:
push:
branches: [main]
workflow_dispatch:
env:
PAYLOAD_SECRET: test-only-secret-not-used-in-production
NEXT_PUBLIC_SITE_URL: http://localhost:3000
jobs:
static:
runs-on: ubuntu-latest
timeout-minutes: 20
steps:
- uses: actions/checkout@v5
- uses: pnpm/action-setup@v6
- uses: actions/setup-node@v5
with:
node-version: 24
cache: pnpm
- run: pnpm install --frozen-lockfile
- run: node scripts/check-test-locations.mjs
- run: pnpm lint
- run: pnpm format:check
- run: pnpm typecheck
- run: pnpm knip
- run: pnpm check:cycles
- run: pnpm test:unit
int:
runs-on: ubuntu-latest
timeout-minutes: 25
env:
# Self-hosted runner has 8 CPUs; vitest forks ≈ CPUs and each fork holds
# a Payload pool (max 10) → overflows the service Postgres' 100 clients
# ("too many clients already"). 4 forks stay well under. GitHub's 2–4
# vCPU runners keep the CPU-relative default (no env).
VITEST_MAX_WORKERS: 4
services:
postgres:
image: postgres:17-alpine
env:
POSTGRES_USER: teqo
POSTGRES_PASSWORD: teqo
POSTGRES_DB: teqo_test
ports:
- 5433:5432
options: >-
--health-cmd "pg_isready -U teqo"
--health-interval 5s
--health-timeout 5s
--health-retries 12
steps:
- uses: actions/checkout@v5
- uses: pnpm/action-setup@v6
- uses: actions/setup-node@v5
with:
node-version: 24
cache: pnpm
- run: pnpm install --frozen-lockfile
- name: Prepare database URL (service via bridge gateway)
run: |
set -euo pipefail
DB_HOST=$(awk '$2 == "00000000" {a=$3; print strtonum("0x" substr(a,7,2)) "." strtonum("0x" substr(a,5,2)) "." strtonum("0x" substr(a,3,2)) "." strtonum("0x" substr(a,1,2)); exit}' /proc/net/route)
echo "DATABASE_URL=postgresql://teqo:teqo@${DB_HOST}:5433/teqo_test" >> "$GITHUB_ENV"
# vitest re-loads .env.test over the process env, so the service URL
# must win through the .env.test.local layer (same mechanism
# `pnpm worktree next` uses). OPS50.
echo "DATABASE_URL=postgresql://teqo:teqo@${DB_HOST}:5433/teqo_test" > .env.test.local
- run: pnpm migrate
- run: pnpm db:seed:minimal
- run: pnpm test:int
build:
runs-on: ubuntu-latest
timeout-minutes: 25
services:
postgres:
image: postgres:17-alpine
env:
POSTGRES_USER: teqo
POSTGRES_PASSWORD: teqo
POSTGRES_DB: teqo_test
ports:
- 5434:5432
options: >-
--health-cmd "pg_isready -U teqo"
--health-interval 5s
--health-timeout 5s
--health-retries 12
steps:
- uses: actions/checkout@v5
- uses: pnpm/action-setup@v6
- uses: actions/setup-node@v5
with:
node-version: 24
cache: pnpm
- run: pnpm install --frozen-lockfile
- name: Prepare database URL (service via bridge gateway)
run: |
set -euo pipefail
DB_HOST=$(awk '$2 == "00000000" {a=$3; print strtonum("0x" substr(a,7,2)) "." strtonum("0x" substr(a,5,2)) "." strtonum("0x" substr(a,3,2)) "." strtonum("0x" substr(a,1,2)); exit}' /proc/net/route)
echo "DATABASE_URL=postgresql://teqo:teqo@${DB_HOST}:5434/teqo_test" >> "$GITHUB_ENV"
- name: Build (against the service database)
run: pnpm build
e2e:
runs-on: ubuntu-latest
timeout-minutes: 40
# Main always runs the full suite: split it across 2 jobs (OPS34), each
# building its own `.next-e2e` (measured 2026-08-10: build 172s + tests
# 196s + ~54s fixed → ≈ 5.5 min per shard vs 435s serial). `fail-fast:
# false` so one shard's failure keeps the other's diagnostics. Keep the
# [1, 2] / 2 literal in sync with `e2eShardConfig` in
# scripts/lib/test-affected-core.mjs (ci-pr pins the same literal).
strategy:
fail-fast: false
matrix:
shard: [1, 2]
env:
# Explicit CI workers; the local default stays 2 (playwright.config.ts).
PLAYWRIGHT_WORKERS: 2
services:
postgres:
image: postgres:17-alpine
env:
POSTGRES_USER: teqo
POSTGRES_PASSWORD: teqo
POSTGRES_DB: teqo_test
ports:
- ${{ matrix.shard == 1 && '5435' || '5436' }}:5432
options: >-
--health-cmd "pg_isready -U teqo"
--health-interval 5s
--health-timeout 5s
--health-retries 12
steps:
- uses: actions/checkout@v5
- uses: pnpm/action-setup@v6
- uses: actions/setup-node@v5
with:
node-version: 24
cache: pnpm
- run: pnpm install --frozen-lockfile
- name: Cache Playwright browsers
uses: actions/cache@v4
with:
path: ~/.cache/ms-playwright
key: playwright-${{ runner.os }}-${{ hashFiles('pnpm-lock.yaml') }}
restore-keys: |
playwright-${{ runner.os }}-
- name: Install Playwright chromium
run: pnpm exec playwright install --with-deps chromium
- name: Prepare database URL (service via bridge gateway)
run: |
set -euo pipefail
DB_HOST=$(awk '$2 == "00000000" {a=$3; print strtonum("0x" substr(a,7,2)) "." strtonum("0x" substr(a,5,2)) "." strtonum("0x" substr(a,3,2)) "." strtonum("0x" substr(a,1,2)); exit}' /proc/net/route)
DB_PORT=${{ matrix.shard == 1 && '5435' || '5436' }}
echo "DATABASE_URL=postgresql://teqo:teqo@${DB_HOST}:${DB_PORT}/teqo_test" >> "$GITHUB_ENV"
# playwright re-loads .env.test over the process env, so the service
# URL must win through the .env.test.local layer (same mechanism
# `pnpm worktree next` uses). OPS50.
echo "DATABASE_URL=postgresql://teqo:teqo@${DB_HOST}:${DB_PORT}/teqo_test" > .env.test.local
- run: pnpm migrate
- run: pnpm db:seed:minimal
- name: Build for e2e
run: pnpm build
env:
# Same dir the Playwright webServer serves (playwright.config.ts
# falls back to '.next-e2e'; gate-ci.mjs builds there too).
NEXT_DIST_DIR: .next-e2e
- name: E2E tests (full suite, shard ${{ matrix.shard }})
# No `--` separator: pnpm would forward it verbatim to playwright and
# the flag would be parsed as a file pattern ("No tests found").
run: pnpm test:e2e --shard=${{ matrix.shard }}/2
checks:
name: checks
runs-on: ubuntu-latest
needs: [static, int, build, e2e]
if: always()
steps:
- name: All main verifier checks green
env:
NEEDS: ${{ toJSON(needs) }}
run: |
set -euo pipefail
echo "$NEEDS" | jq -e '
to_entries
| all(.value.result == "success" or .value.result == "skipped")
'
deploy:
name: deploy homeserver (teqo-1313)
# OPS53. Runs directly on the runner HOST (not a job container): the
# deploy needs the workstation's SSH key to reach the homeserver
# (`ssh homeserver`) and streams the whole remote build/migrate/rollout
# to this job's logs. Deliberately wired ONLY here — push to main +
# workflow_dispatch — never in ci-pr.yml: a host job is code execution as
# `fsolla` on the workstation, and main only ever moves through a merged
# PR whose full suite was already green.
needs: [checks]
runs-on: host
timeout-minutes: 60
steps:
- uses: actions/checkout@v5
- name: Deploy teqo-1313 on the homeserver
run: |
set -euo pipefail
ssh homeserver "bash -s -- $GITHUB_SHA" < scripts/deploy-homeserver.sh