FabledScribe/.forgejo/workflows/ci.yml

# CI runs first; build only proceeds if all checks pass.
#
# Push to dev:        typecheck + lint + test + build :dev + :<sha>
# Push to main:       typecheck + lint + test + build :latest + :<sha>
# Tag v* (release):   typecheck + lint + test + build :latest + :<version> + :<sha>
#
# Both dev and main are gated AND built. dev pushes move :dev; main pushes move
# :latest — main IS the production line, so :latest tracks main's tip and there
# is no separate :main tag. Every push also gets an immutable :<sha> (the
# rollback point). A v* release tag additionally publishes the dated :<version>;
# since main already moved :latest, the release tag's distinct job is that
# :<version> marker (it refreshes :latest too, harmlessly).
#
# Successive pushes to the SAME ref supersede each other (see concurrency
# below), so rapid pushes don't stack identical work; dev and main runs are
# independent refs and never cancel one another.
#
# To cut a release:
#   Create a release via the Forgejo UI on main with a v* tag name.
#   The tag push triggers this workflow; build job pushes :latest + :<version>.
#
# PRs aren't triggered on purpose — this is a solo dev→main flow, so
# gating on branch push is already enough.
#
# NOTE on the `if:` guards below: Forgejo Actions does not consistently
# honor `on.push.branches` as a filter, so every job repeats the ref check
# explicitly — permitting dev, main, and v* tags, rejecting anything else.
#
# Required secrets (repo → Settings → Secrets → Actions):
#   REGISTRY_USER   — your Forgejo username
#   REGISTRY_TOKEN  — Forgejo PAT with write:packages scope
name: CI & Build

on:
  push:
    branches: [dev, main]
    tags: ["v*"]
    paths:
      - "src/**"
      - "frontend/**"
      - "tests/**"
      - "pyproject.toml"
      - "alembic/**"
      - "alembic.ini"
      - "Dockerfile"
      - "assets/**"
      - "fable-mcp/**"
      - ".forgejo/workflows/ci.yml"
  # Manual trigger from the Forgejo Actions UI. Useful when an image has
  # been built but the deployment didn't pick it up, or when re-running
  # against the same source produces different upstream behaviour
  # (e.g. a transient HF download flake during the voice-bundle step).
  workflow_dispatch: {}

# Cancel older runs on the same branch when a newer push lands. Tag runs
# get their own group implicitly (refs/tags/v1.2.3 ≠ refs/heads/dev) and
# are never cancelled, so a release build can't kill itself mid-flight.
concurrency:
  group: ci-${{ github.ref }}
  cancel-in-progress: ${{ !startsWith(github.ref, 'refs/tags/') }}

# Least-privilege default. Jobs that need more (build pushes to the
# registry) upgrade explicitly.
permissions:
  contents: read

env:
  REGISTRY: git.fabledsword.com
  IMAGE: git.fabledsword.com/bvandeusen/fabledscribe

jobs:
  typecheck:
    name: TypeScript typecheck
    # Gate dev, main, and v* tags; reject any other ref (see header note).
    if: github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    steps:
      - uses: actions/checkout@v6

      - name: Cache npm download cache
        uses: actions/cache@v4
        # Non-fatal: a transient cache-backend hiccup must NOT fail the whole
        # typecheck job (it was skipping install + type check and reporting red
        # on backend-only pushes — see issue task #828). On cache miss/error the
        # job just installs without the cache.
        continue-on-error: true
        with:
          path: ~/.npm
          key: npm-cache-${{ hashFiles('frontend/package-lock.json') }}
          restore-keys: npm-cache-

      - name: Install dependencies
        run: npm ci
        working-directory: frontend

      - name: Type check
        run: npx vue-tsc --noEmit
        working-directory: frontend

  lint:
    name: Python lint
    if: github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    steps:
      - uses: actions/checkout@v6

      # ruff is pre-installed in the ci-python image — no install
      # step needed, lint runs in ~2s.
      - name: Lint
        run: ruff check src/

  test:
    name: Python tests
    if: github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    steps:
      - uses: actions/checkout@v6

      - name: Cache uv packages
        uses: actions/cache@v4
        with:
          path: ~/.cache/uv
          # Keyed on the LOCK, not pyproject: the lock is what determines the
          # installed set now, and a pyproject edit that doesn't change
          # resolution shouldn't throw the cache away.
          key: uv-${{ hashFiles('uv.lock') }}
          restore-keys: uv-

      # Installs exactly what uv.lock pins. `--locked` additionally FAILS if the
      # lock is stale against pyproject, so a dependency change has to go through
      # a deliberate `uv lock` — it can't drift in silently.
      #
      # This replaced `uv pip install -e ".[dev]"`, which resolved from the
      # pyproject constraints and ignored the lock entirely. Every dependency
      # floated: on 2026-07-28 mcp 2.0.0 shipped mid-session and turned `main`
      # red with no repo change (issue #2194). Green CI has to mean "these exact
      # versions passed", or it isn't evidence of anything.
      - name: Install locked dependencies
        env:
          UV_PROJECT_ENVIRONMENT: /opt/venv
        run: uv sync --locked --extra dev

      - name: Run tests
        # Integration tests (real Postgres) run in the `integration` job below.
        run: /opt/venv/bin/python -m pytest tests/ -q -m "not integration"

  # Real-Postgres lane (family rule 6). Exercises the async SQLAlchemy connection
  # path the unit stubs can't reach — the un-awaited execution_options regression
  # that made every VACUUM report 0/6 lived here. Like `test`, it runs for
  # visibility and does NOT gate the build.
  #
  # Job key stays separator-free ("integration"): act_runner derives the service-
  # container name from the (truncated) job display name and the discovery step
  # filters `docker ps` by it. Service hostnames aren't routable on this runner,
  # so the step resolves the Postgres container's bridge IP. No `name:` on purpose.
  integration:
    if: github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    env:
      # Config + the module engine read these at import time. DATABASE_URL itself
      # is built from the discovered service IP in the run step.
      SECRET_KEY: ci_integration_placeholder
    services:
      postgres:
        # pgvector image so `alembic upgrade head` can run migration 0067
        # (CREATE EXTENSION vector). PG17 — matches the prod/quickstart image.
        image: pgvector/pgvector:pg17
        env:
          POSTGRES_USER: scribe
          POSTGRES_PASSWORD: ci_integration
          POSTGRES_DB: scribe_test
        options: >-
          --health-cmd "pg_isready -U scribe"
          --health-interval 10s
          --health-timeout 5s
          --health-retries 10
    steps:
      - uses: actions/checkout@v6
      # Same locked install as the unit lane — the two must agree on versions,
      # or "unit green, integration red" stops being a signal about the code.
      - name: Install locked dependencies
        env:
          UV_PROJECT_ENVIRONMENT: /opt/venv
        run: uv sync --locked --extra dev
      - name: Integration suite (resolve service IP, migrate, test)
        run: |
          set -eux
          echo "=== container landscape (diagnostic for the name filter) ==="
          docker ps -a --format '{{.ID}} {{.Image}} -> {{.Names}}'
          PG=$(docker ps --filter "name=integration" --filter "ancestor=pgvector/pgvector:pg17" -q | head -n1)
          test -n "$PG"
          PG_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$PG")
          test -n "$PG_IP"
          export DATABASE_URL="postgresql+asyncpg://scribe:ci_integration@${PG_IP}:5432/scribe_test"
          # Wait for Postgres to accept connections (busybox sh — the runner
          # default — has no bash /dev/tcp, so use Python).
          /opt/venv/bin/python - "$PG_IP" <<'PY'
          import socket, sys, time
          for _ in range(30):
              try:
                  socket.create_connection((sys.argv[1], 5432), timeout=2).close()
                  break
              except OSError:
                  time.sleep(1)
          else:
              sys.exit("postgres did not become reachable")
          PY
          # Real migrations build the schema; the maintenance tests then run
          # VACUUM (ANALYZE) and read pg_stat_user_tables against it.
          /opt/venv/bin/alembic upgrade head
          /opt/venv/bin/python -m pytest tests/ -v -m integration

  build:
    name: Build & push image
    needs: [typecheck, lint, test]
    # Build on dev, main, and v* tag pushes. dev → :dev, main → :latest,
    # tag → :latest + :<version>; every build also gets an immutable :<sha>.
    if: github.ref == 'refs/heads/dev' || github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/tags/v')
    runs-on: python-ci
    container:
      image: git.fabledsword.com/bvandeusen/ci-python:3.14
    permissions:
      contents: read
      packages: write
    steps:
      - uses: actions/checkout@v6

      - name: Generate image tags and version
        id: tags
        # POSIX `case` instead of bash `[[ ]]` because act_runner invokes
        # `sh -e` (dash on the ci-python:3.14 image, which has no bash on
        # the default PATH for /bin/sh). Previous `[[ ]]` form failed
        # silently — only the SHA tag got appended, so :dev / :latest
        # never updated in the registry and the deployed stack kept
        # pulling stale images. Verified via `[[: not found` lines in
        # the runner log on commit 2a374d9.
        run: |
          TAGS="${{ env.IMAGE }}:${{ github.sha }}"
          BUILD_VERSION="dev"
          case "${{ github.ref }}" in
            refs/heads/dev)
              TAGS="$TAGS,${{ env.IMAGE }}:dev"
              ;;
            refs/heads/main)
              # main IS the production line: publish :latest (plus the :<sha>
              # set above). No separate :main tag.
              TAGS="$TAGS,${{ env.IMAGE }}:latest"
              BUILD_VERSION="main"
              ;;
            refs/tags/*)
              TAGS="$TAGS,${{ env.IMAGE }}:latest,${{ env.IMAGE }}:${{ github.ref_name }}"
              BUILD_VERSION="${{ github.ref_name }}"
              ;;
          esac
          echo "value=$TAGS" >> $GITHUB_OUTPUT
          echo "build_version=$BUILD_VERSION" >> $GITHUB_OUTPUT

      - name: Free disk space
        # Self-hosted runner housekeeping. Two-step cleanup:
        # 1. Prune dangling containers/images globally (stops the runner
        #    from accumulating cruft from past failed builds).
        # 2. Trim the BuildKit layer cache to a 5GB ceiling so the pip
        #    mount cache survives but old intermediate layers don't
        #    accumulate indefinitely.
        run: |
          docker system prune -af || true
          docker builder prune --keep-storage 5g -f || true

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@v4

      - name: Log in to Forgejo registry
        uses: docker/login-action@v4
        with:
          registry: ${{ env.REGISTRY }}
          username: ${{ secrets.REGISTRY_USER }}
          password: ${{ secrets.REGISTRY_TOKEN }}

      - name: Build and push
        uses: docker/build-push-action@v7
        with:
          context: .
          push: true
          provenance: false
          tags: ${{ steps.tags.outputs.value }}
          build-args: BUILD_VERSION=${{ steps.tags.outputs.build_version }}
          # Registry-backed layer cache. Pull from :cache to prime
          # BuildKit, push updated layers back to :cache so the next
          # build starts warm even if the runner's local cache was
          # pruned. `mode=max` exports all intermediate layers, not
          # just the final image, which is what gives the ~80% speedup.
          cache-from: type=registry,ref=${{ env.IMAGE }}:cache
          cache-to: type=registry,ref=${{ env.IMAGE }}:cache,mode=max,ignore-error=true