History/.gitea/workflows/ci.yml

# CI for the History simulator. Mirrors the local verification list in AGENTS.md
# (typecheck → lint → unit → build) and then runs the deterministic Playwright e2e
# suite (LLM_STUB=1) against the app's OWN dev webServer (npm run dev) on the runner.
# No dind / docker-compose / static IP / NO_PROXY needed: history's e2e targets the dev
# webServer, not a Docker image (unlike flight/orb's image-based e2e). CI never deploys:
# production is updated manually on the host after a tag.
name: CI

on:
  push:
    branches: [master]
  pull_request:
    branches: [master]
  workflow_dispatch:

jobs:
  ci:
    name: build + unit + e2e
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v4

      - name: Setup Node
        uses: actions/setup-node@v4
        with:
          node-version: 22

      # Job-level dep cache via the runner's built-in cache server. continue-on-error:
      # an unreachable/broken cache server must never break the run (sibling convention).
      # Caches node_modules and npm's tarball store ($HOME/.npm); npm ci wipes
      # node_modules, so the $HOME/.npm store is what actually makes a cache hit fast.
      - name: Restore deps cache
        uses: actions/cache@v4
        continue-on-error: true
        with:
          path: |
            node_modules
            $HOME/.npm
          key: ${{ runner.os }}-deps-npm-${{ hashFiles('package-lock.json') }}

      # Retried: the runner's outbound network/DNS is flaky (transient EAI_AGAIN seen in CI).
      # npm ci is fully reproducible from the committed package-lock.json.
      - name: Install dependencies
        run: |
          set -u
          ok=0
          for i in 1 2 3; do
            if npm ci; then ok=1; break; fi
            echo "::warning::dependency install attempt $i/3 failed (likely transient network) — retrying in 5s" >&2
            sleep 5
          done
          [ "$ok" = "1" ] || { echo "::error::dependency install failed after 3 attempts" >&2; exit 1; }

      - name: Typecheck
        run: npm run typecheck

      - name: Lint
        run: npm run lint

      # Deterministic: the LLM client uses the stub transport (LLM_STUB=1), so no model
      # or network is needed. vitest auto-appends its summary to $GITHUB_STEP_SUMMARY.
      - name: Unit tests
        run: npm test

      # Vite client build → dist/ + tsup server bundle → server/dist/. Verifies the
      # production build path (docker build does the same thing inside the image).
      - name: Build
        run: npm run build

      # Browsers run locally in CI (no remote browser server, no dind). Binaries
      # (~187 MiB) are cached across runs — the runner's uplink is flaky and
      # cdn.playwright.dev downloads time out mid-transfer; once seeded, installs skip.
      - name: Restore browser cache
        uses: actions/cache@v4
        continue-on-error: true
        with:
          path: $HOME/.cache/ms-playwright
          key: ${{ runner.os }}-pw-browsers-${{ hashFiles('package.json') }}

      # Retried: cdn.playwright.dev is flaky from this runner — Playwright's internal
      # retry window is often not enough, but runs get through with a longer one.
      # Progress accumulates across attempts: playwright skips already-installed browsers.
      - name: Install browsers (local)
        run: |
          set -u
          ok=0
          for i in 1 2 3 4 5 6; do
            if npx playwright install --with-deps chromium; then ok=1; break; fi
            echo "::warning::browser install attempt $i/6 failed (flaky cdn.playwright.dev) — retrying in 5s" >&2
            sleep 5
          done
          [ "$ok" = "1" ] || { echo "::error::browser install failed after 6 attempts" >&2; exit 1; }

      # E2E: fully deterministic. The Playwright config boots its own dev webServer
      # (npm run dev) with LLM_STUB=1 and DATA_DIR=data/e2e. VITE_PORT / HISTORY_API_PORT
      # are set to free ports so that webServer won't collide with anything else on the
      # runner (history's normal dev ports are 5173/4321). The config emits an HTML report
      # (playwright-report/) and a JSON report (test-results/e2e.json) used below.
      - name: E2E
        env:
          VITE_PORT: "5199"
          HISTORY_API_PORT: "4399"
        run: npm run e2e

      # Short machine-readable summary appended to the PR/job. Runs even on failure
      # (always()) and never breaks the job (|| true). Parses Playwright's JSON report:
      # stats.expected = passed, stats.unexpected = failed, stats.skipped = skipped.
      - name: E2E results summary
        if: always()
        run: |
          {
            echo "## E2E results"
            echo
            if [ -f test-results/e2e.json ]; then
              node -e '
                const fs = require("fs");
                const r = JSON.parse(fs.readFileSync("test-results/e2e.json", "utf8"));
                const s = r.stats || {};
                console.log(`- **Passed:** ${s.expected ?? 0}`);
                console.log(`- **Failed:** ${s.unexpected ?? 0}` + (s.flaky ? ` (flaky: ${s.flaky})` : ""));
                console.log(`- **Skipped:** ${s.skipped ?? 0}`);
                console.log(`- **Duration:** ${((s.duration ?? 0) / 1000).toFixed(1)}s`);
              ' || echo "- could not parse test-results/e2e.json"
            else
              echo "- no test-results/e2e.json produced (e2e did not run)"
            fi
          } >> "$GITHUB_STEP_SUMMARY" || true

      # On failure, keep the HTML report + raw results for debugging.
      - name: Upload Playwright report
        if: failure()
        uses: actions/upload-artifact@v4
        continue-on-error: true
        with:
          name: playwright-report
          path: |
            playwright-report/
            test-results/
          retention-days: 7