FabledCurator/.forgejo/workflows/ci.yml

name: CI

# CI lanes per FabledRulebook/forgejo.md "CI philosophy":
#   - lint: ruff only, no dep install — fast-fail for the common lint bounce.
#   - backend-lint-and-test: `pytest -m "not integration"`, no service containers.
#   - frontend-build: vitest unit + vite build.
#   - integration: pgvector + redis service containers; alembic + `pytest -m integration`.

on:
  push:
    branches: [dev, main]
  # pull_request trigger intentionally absent — with branches: [dev, main]
  # above, every PR commit already fires CI via the push event on dev. Adding
  # pull_request would duplicate runs on dev→main PRs. FC has no fork PRs
  # (single-operator Forgejo repo) so push coverage is complete.

jobs:
  # Fast-fail lint lane. ruff is pre-installed in the ci-python image, so
  # this runs with NO dependency install and surfaces the most common bounce
  # class (lint: I001 / UP037 / ASYNC109 / W293 …) in seconds — instead of
  # after the backend job's ~30-60s wheel install. ruff is static analysis,
  # so no DB/secret env is needed.
  lint:
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    steps:
      - uses: actions/checkout@v4
      - name: Ruff lint
        run: ruff check backend/ tests/ alembic/

  backend-lint-and-test:
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    env:
      # DB_PASSWORD and SECRET_KEY are required by config.py at import time
      # even though unit tests don't actually touch the DB or use the secret.
      DB_PASSWORD: ci_unit_test_placeholder
      SECRET_KEY: ci_unit_test_placeholder
    steps:
      - uses: actions/checkout@v4

      # Cache step removed 2026-05-26: act_runner's cache backend has been
      # broken on this homelab runner since 2026-05-15 (first as request-
      # timeout warnings, then as hard "Cannot find module .../dist/restore/
      # index.js" failures that tank the whole job). The cache step targeted
      # ~/.cache/pip but the install below uses `uv pip install` primarily,
      # whose own cache lives at ~/.cache/uv — so the cache step's real
      # benefit was marginal even when working. Cost of removal: ~30s of
      # wheel downloads per job. Future re-enable: mount ~/.cache/uv as a
      # docker volume at the runner level (skips actions/cache entirely),
      # or fix the runner-side cache backend (clear /var/run/act/actions/*,
      # pin act_runner version, etc.).

      - name: Install Python deps
        # ruff is pre-installed in the ci-python image (see CI-Runner/CI-python/
        # Dockerfile's RUFF_VERSION). Per FabledRulebook ci-runners.md, toolchain
        # versions live on the runner image, not here.
        # uv: 5-10x faster wheel resolve than pip for cold caches.
        # Falls back to pip install on uv-missing runners (older images).
        run: |
          if command -v uv >/dev/null 2>&1; then
            uv pip install --system -r requirements.txt pytest pytest-asyncio
          else
            pip install -r requirements.txt pytest pytest-asyncio
          fi

      # Ruff moved to the dedicated fast `lint` job above (fails in seconds,
      # no dep install). This job is now unit tests only.
      - name: Pytest (unit only — integration runs in the integration job)
        run: pytest tests/ -v -m "not integration"

  frontend-build:
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    defaults:
      run:
        working-directory: frontend
    steps:
      - uses: actions/checkout@v4
      # No package-lock.json is tracked yet (we don't run npm locally per
      # feedback-no-local-runs). Using `npm install` instead of `npm ci`.
      # If we want strict lockfile-based reproducibility later, commit a
      # package-lock.json and flip this back to `npm ci`.
      - run: npm install --no-audit --no-fund
      # `npm run check` (vue-tsc --noEmit) skipped: the frontend is pure JS
      # with no .ts files and no JSDoc annotations, so vue-tsc has nothing
      # to type-check. Re-enable once we add a tsconfig.json and either
      # convert to TS or add JSDoc.
      - run: npm run test:unit
      - run: npm run build

  # Single integration job — collapsed from a 3-way shard split on 2026-06-04.
  # The shards existed to parallelize ~8.5min of integration tests; once the
  # throwaway Postgres runs with fsync OFF (the durability step below) the whole
  # suite runs in ~45s, so the split only triplicated the ~2min fixed overhead
  # (container + `uv pip install` + `alembic upgrade head`) and burned 3 of 6
  # runner slots for no wall-clock gain. One job now: spin up once, install
  # once, migrate once, run every integration test.
  #
  # The docker-ps filter scopes to THIS job's own Postgres/Redis service
  # containers by job name. act_runner strips underscores from job names when
  # labelling containers (`int_api` matched nothing on 2026-05-25), so the name
  # stays separator-free (`integration`). The step prints `docker ps -a` first
  # so a future naming-convention shift surfaces in the log without a
  # guess-and-push cycle.
  #
  # Pre-baking requirements.txt into ci-python:3.14 is intentionally NOT done —
  # per ci-requirements.md, FC is the only Python consumer of that image and the
  # CI-Runner "add deps to image when used by >1 project" rule keeps it per-job.
  integration:
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    env:
      DB_USER: fabledcurator
      DB_PASSWORD: ci_integration
      DB_PORT: "5432"
      DB_NAME: fabledcurator_test
      SECRET_KEY: ci_integration_placeholder
    services:
      postgres:
        image: pgvector/pgvector:pg16
        env:
          POSTGRES_USER: fabledcurator
          POSTGRES_PASSWORD: ci_integration
          POSTGRES_DB: fabledcurator_test
        options: >-
          --health-cmd "pg_isready -U fabledcurator"
          --health-interval 10s
          --health-timeout 5s
          --health-retries 10
      redis:
        image: redis:7-alpine
        options: >-
          --health-cmd "redis-cli ping"
          --health-interval 10s
          --health-timeout 5s
          --health-retries 10
    steps:
      - uses: actions/checkout@v4
      - name: Integration suite (resolve service IPs, migrate, test)
        run: |
          set -eux
          echo "=== container landscape (diagnostic for filter scoping) ==="
          docker ps -a --format '{{.ID}} {{.Image}} -> {{.Names}}'
          echo "=== end landscape ==="
          PG=$(docker ps --filter "name=integration" --filter "ancestor=pgvector/pgvector:pg16" -q | head -n1)
          RD=$(docker ps --filter "name=integration" --filter "ancestor=redis:7-alpine" -q | head -n1)
          test -n "$PG" && test -n "$RD"
          PG_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$PG")
          RD_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$RD")
          test -n "$PG_IP" && test -n "$RD_IP"
          export DB_HOST="$PG_IP"
          export CELERY_BROKER_URL="redis://$RD_IP:6379/0"
          export CELERY_RESULT_BACKEND="redis://$RD_IP:6379/0"
          for i in $(seq 1 60); do
            (echo > "/dev/tcp/$PG_IP/5432") >/dev/null 2>&1 && break
            sleep 2
          done
          if command -v uv >/dev/null 2>&1; then
            uv pip install --system -r requirements.txt pytest pytest-asyncio
          else
            pip install -r requirements.txt pytest pytest-asyncio
          fi
          # Relax durability on the throwaway CI Postgres so the per-test
          # TRUNCATE's commit-fsync — the integration teardown's dominant cost
          # (~1.5-2s/test, which collapsed the suite from ~13min to ~45s) — is
          # skipped. fsync/full_page_writes are sighup GUCs and synchronous_commit
          # is user-context, so ALTER SYSTEM + pg_reload_conf() applies them with
          # NO restart. Ephemeral DB ⇒ fsync-off is safe. Non-fatal so a perms
          # surprise can't red the job; fabledcurator is the postgres image's
          # bootstrap superuser.
          python -c "import os,psycopg; c=psycopg.connect(host=os.environ['DB_HOST'],port=5432,user=os.environ['DB_USER'],password=os.environ['DB_PASSWORD'],dbname=os.environ['DB_NAME'],autocommit=True); [c.execute(q) for q in ('ALTER SYSTEM SET fsync=off','ALTER SYSTEM SET synchronous_commit=off','ALTER SYSTEM SET full_page_writes=off','SELECT pg_reload_conf()')]; c.close()" || echo 'WARN: durability GUC relax failed (continuing)'
          alembic upgrade head
          pytest tests/ -v -m integration --durations=15