bench/.gitea/workflows/ci.yml

# CI/CD — verify on every push, ship main when green.
#
# Runs on the act_runner registered on build-host (label `ubuntu-latest`, Docker-backed).
# Same shape as music.karti.ai: verify and deploy are two jobs in ONE workflow joined by
# `needs:`, because Gitea's cross-workflow triggers are less reliable than GitHub's. A red
# build cannot deploy.
#
# This repo is PUBLIC, so nothing here may name the deploy target. The host, the account,
# the checkout path and the service name all come from repo secrets; the workflow only
# describes the shape of the deploy.
#
# Requires these repo secrets:
#   DEPLOY_SSH_KEY  — private half of a deploy key whose public half is in the deploy
#                     account's authorized_keys on the web host
#   DEPLOY_HOST     — the web host to deploy to
#   DEPLOY_USER     — the account to ssh in as
#   DEPLOY_PATH     — the checkout on the web host that is reset to origin/main
#   DEPLOY_SERVICE  — the systemd unit restarted after the build

name: CI

on:
  push:
    branches: ["**"]
  pull_request:
    branches: [main]
  workflow_dispatch:

jobs:
  verify:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Harness imports and registry parses
        # Catches a malformed models.yaml or a broken target before it reaches
        # the site build, where the failure would be far less legible.
        run: |
          python3 -m pip install --quiet pyyaml
          python3 - <<'PY'
          import sys; sys.path.insert(0, '.')
          from kbench.registry import load_registry
          reg = load_registry()
          for t in reg.targets.values():
              t.inspect_model  # raises on an unserveable target
          print(f"registry ok: {len(reg.targets)} targets, {len(reg.hosts)} hosts")
          PY

      - name: Results files are valid and schema-consistent
        run: |
          python3 - <<'PY'
          import json, pathlib, sys
          bad = 0
          for p in sorted(pathlib.Path('results').glob('*.json')):
              d = json.loads(p.read_text())
              for field in ('run_id', 'timestamp', 'target_id', 'target', 'schema_version'):
                  if field not in d:
                      print(f"::error::{p.name} missing {field}"); bad += 1
          print(f"checked results files, {bad} problem(s)")
          sys.exit(1 if bad else 0)
          PY

      - name: Build site
        working-directory: site
        run: |
          npm install --no-audit --no-fund
          npm run build

  deploy:
    needs: verify
    # Gitea populates the **github** context, not a `gitea` one — `gitea.ref` silently
    # evaluates to nothing and the job is skipped with no error.
    if: github.ref == 'refs/heads/main' && github.event_name != 'pull_request'
    runs-on: ubuntu-latest
    steps:
      - name: Set up SSH
        env:
          DEPLOY_SSH_KEY: ${{ secrets.DEPLOY_SSH_KEY }}
          DEPLOY_HOST: ${{ secrets.DEPLOY_HOST }}
        run: |
          mkdir -p ~/.ssh
          printf '%s\n' "$DEPLOY_SSH_KEY" > ~/.ssh/deploy_key
          chmod 600 ~/.ssh/deploy_key
          ssh-keyscan -H "$DEPLOY_HOST" >> ~/.ssh/known_hosts 2>/dev/null

      - name: Deploy to the web host
        env:
          DEPLOY_HOST: ${{ secrets.DEPLOY_HOST }}
          DEPLOY_USER: ${{ secrets.DEPLOY_USER }}
          DEPLOY_PATH: ${{ secrets.DEPLOY_PATH }}
          DEPLOY_SERVICE: ${{ secrets.DEPLOY_SERVICE }}
        run: |
          # The path and unit name are passed as positional args, not interpolated:
          # the heredoc is quoted so the runner never expands them into the log.
          ssh -i ~/.ssh/deploy_key -o BatchMode=yes "$DEPLOY_USER@$DEPLOY_HOST" \
            bash -s -- "$DEPLOY_PATH" "$DEPLOY_SERVICE" <<'REMOTE'
          set -euo pipefail
          checkout="$1"
          service="$2"
          cd "$checkout"
          git fetch origin -q
          git reset --hard origin/main -q
          cd site
          npm install --no-audit --no-fund
          npm run build
          sudo systemctl restart "$service"
          REMOTE

      - name: Verify the deploy
        env:
          DEPLOY_HOST: ${{ secrets.DEPLOY_HOST }}
          DEPLOY_USER: ${{ secrets.DEPLOY_USER }}
          DEPLOY_SERVICE: ${{ secrets.DEPLOY_SERVICE }}
        run: |
          for i in $(seq 1 20); do
            if curl -sf https://bench.karti.ai/api/health | grep -q '"ok":true'; then
              echo "✓ bench.karti.ai is healthy"
              exit 0
            fi
            sleep 3
          done
          echo "::error::bench.karti.ai did not come back healthy after deploy"
          ssh -i ~/.ssh/deploy_key -o BatchMode=yes "$DEPLOY_USER@$DEPLOY_HOST" \
            bash -s -- "$DEPLOY_SERVICE" <<'REMOTE' || true
          sudo journalctl -u "$1" -n 40 --no-pager
          REMOTE
          exit 1