pad/.github/workflows/ci.yml

name: CI

on:
  push:
    branches: [main]
  pull_request:
    branches: [main]

concurrency:
  group: ci-${{ github.ref }}
  cancel-in-progress: true

permissions:
  contents: read

# All third-party Actions are pinned to a 40-char commit SHA with a trailing
# '# vX.Y.Z' comment so a compromised maintainer or moved tag cannot silently
# execute attacker code in CI. Bump the SHA + comment together when updating.

jobs:
  go:
    name: Go
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

      - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
        with:
          go-version: "1.26"

      - name: Allow Go to fetch the toolchain go.mod pins
        # actions/setup-go unconditionally exports GOTOOLCHAIN=local, which
        # forbids Go from fetching the toolchain go.mod requires. go.mod pins
        # `go 1.26.5`, but setup-go's "1.26" resolves to the newest patch in
        # its manifest (1.26.4 here), so every `go` command fails with
        # "go.mod requires go >= 1.26.5 (running go 1.26.4)". Written AFTER
        # setup-go so it wins the $GITHUB_ENV last-write; `auto` lets Go pull
        # 1.26.5 on demand. Added after #896 raised the go.mod floor.
        run: echo "GOTOOLCHAIN=auto" >> "$GITHUB_ENV"

      - name: Create web build placeholder for embed
        run: mkdir -p web/build && echo "placeholder" > web/build/.gitkeep

      - name: Run go vet
        run: go vet ./...

      - name: Run golangci-lint
        # only-new-issues: false means CI fails on ANY linter finding,
        # not just findings on PR-changed lines. The IDEA-732 cleanup
        # (PRs #247/#249/#251/#252) cleared the existing findings under
        # the configured linter set in .golangci.yml — staticcheck SA*,
        # govet, ineffassign, gofmt, and the standalone `unused` linter
        # (which reports U1000). Flipping the gate now prevents
        # regression drift going forward.
        # v2 of golangci-lint is required because v1 is capped at older
        # Go releases that we no longer support.
        uses: golangci/golangci-lint-action@ba0d7d2ec06a0ea1cb5fa41b2e4a3ab91d21278a # v9.3.0
        with:
          version: v2.11.4
          args: --timeout=5m
          only-new-issues: false
          # Cap the blast radius of a stale-cache event to ~24h. The action's
          # cache stores the resolved issue list from a prior pass; if any
          # one pass writes degenerate results (analyzer upgrade, plugin
          # reset, sub-package version drift), every downstream restore
          # replays that list verbatim until the cache key rotates. PR #635
          # hit exactly this — 30+ SA5011/SA4023 false positives against
          # unchanged code while local (cold-cache) runs reported 0 issues.
          # Default is 7 days; 1 day still keeps most runs cache-hot while
          # guaranteeing daily refresh. See BUG-1624.
          cache-invalidation-interval: "1"

      - name: Run govulncheck
        # Fails the build on any known vulnerability in a package we
        # actually reach via the call graph. Net-positive: catches CVEs
        # in indirect deps early, without the noise of hitting every
        # stale entry in our dependency tree.
        #
        # Runs in BINARY mode against a freshly-built pad binary rather than
        # source mode (`govulncheck ./...`). Source mode builds an SSA call-
        # graph over the whole dependency tree and can balloon to multiple GB
        # of RAM (BUG-2084); binary mode reads the binary's symbol table — a
        # fraction of the memory, still call-graph-precise, and detects stdlib
        # vulns from the Go version stamped in the binary. The "Create web
        # build placeholder for embed" step above satisfies the //go:embed so
        # the scan build succeeds. Mirrors the Makefile `vuln` target — keep
        # the two in sync.
        #
        # Pinned to a specific govulncheck release. Track upstream in
        # Pad's workspace; bump intentionally so an upstream behavior
        # change can't break unrelated PRs. Update via:
        #   go install golang.org/x/vuln/cmd/govulncheck@<new-tag>
        run: |
          go install golang.org/x/vuln/cmd/govulncheck@v1.2.0
          go build -o pad-vulnscan ./cmd/pad
          "$(go env GOPATH)/bin/govulncheck" -mode binary pad-vulnscan

      - name: Run tests
        run: go test ./...

      - name: Run tests with race detector
        # Runs on both push-to-main AND pull_request. Previously gated to
        # main only because GitHub Actions minutes were billed on private
        # repos; the repo is public now, so PR minutes are free and we'd
        # rather catch race regressions on the contributing branch than
        # after merge. See BUG-1371 (also dropped test-only bcrypt cost
        # via TestMain so this step stays well under the 30m budget).
        #
        # Default 10m is tight: the full server-package suite under -race
        # measures ~13m locally on a developer laptop after BUG-851 (the
        # ipRateLimiter goroutine drain). The PLAN-866 attachment work
        # (image decode/encode/resize across thumbnail + transform tests)
        # pushes total race-step runtime past 20m on the GitHub-hosted
        # runner. BUG-1913: the suite organically grew past the old 30m
        # budget (734 server-package tests, ~30.3m under -race even on a
        # fast local machine; no single test exceeds 14s — aggregate
        # weight, not a hang), turning most main runs red. 45m restores
        # headroom; genuine deadlocks still hit this and produce the
        # goroutine-dump panic, just up to 15m later. The real fix
        # (cheaper suite: shared fixtures / sharding) is tracked on
        # BUG-1913.
        run: go test -race -timeout=45m ./...

      - name: Build binary
        run: go build -o pad ./cmd/pad

      - name: Verify binary runs
        run: ./pad --help

  native-smoke:
    name: Smoke (${{ matrix.os }})
    runs-on: ${{ matrix.os }}
    timeout-minutes: 10
    defaults:
      run:
        shell: pwsh
    strategy:
      fail-fast: false
      matrix:
        include:
          - os: macos-latest
            binary: pad
            path: ./pad
          - os: windows-latest
            binary: pad.exe
            path: .\pad.exe
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

      - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
        with:
          go-version-file: go.mod

      - name: Create web build placeholder
        run: |
          New-Item -ItemType Directory -Force web/build | Out-Null
          Set-Content web/build/index.html '<!doctype html>'

      - name: Build binary
        run: go build -o "${{ matrix.binary }}" ./cmd/pad

      - name: Verify help output
        run: '& "${{ matrix.path }}" --help'

      - name: Run CLI smoke test
        run: |
          $ErrorActionPreference = 'Stop'
          $PSNativeCommandUseErrorActionPreference = $true
          $binary = '${{ matrix.path }}'
          $env:PAD_DATA_DIR = Join-Path $env:RUNNER_TEMP 'pad-smoke'
          $env:PAD_BYPASS_SETUP_TOKEN = 'true'
          $stdout = Join-Path $env:RUNNER_TEMP 'pad-server.out.log'
          $stderr = Join-Path $env:RUNNER_TEMP 'pad-server.err.log'
          $server = Start-Process -FilePath $binary -ArgumentList 'server','start','--port','17777' -PassThru -RedirectStandardOutput $stdout -RedirectStandardError $stderr

          try {
            $ready = $false
            for ($attempt = 0; $attempt -lt 60; $attempt++) {
              try {
                Invoke-WebRequest -UseBasicParsing http://127.0.0.1:17777/api/v1/health | Out-Null
                $ready = $true
                break
              } catch {
                Start-Sleep -Seconds 1
              }
            }
            if (-not $ready) {
              Get-Content $stdout, $stderr -ErrorAction SilentlyContinue
              throw 'Pad server did not become ready'
            }

            & $binary auth configure --mode local --port 17777
            & $binary auth setup --email smoke@example.com --name Smoke --password 'SmokePass123!'
            & $binary workspace create Smoke --slug smoke --template startup

            $item = (& $binary --workspace smoke --format json item create task 'Native smoke item') | ConvertFrom-Json
            $shown = (& $binary --workspace smoke --format json item show $item.ref) | ConvertFrom-Json
            if ($shown.title -ne 'Native smoke item') {
              throw "Unexpected item title: $($shown.title)"
            }
          } finally {
            Stop-Process -Id $server.Id -ErrorAction SilentlyContinue
          }

  go-postgres:
    name: Go (PostgreSQL)
    runs-on: ubuntu-latest
    services:
      postgres:
        image: postgres:17-alpine
        env:
          POSTGRES_USER: pad
          POSTGRES_PASSWORD: pad
          POSTGRES_DB: pad
        ports:
          - 5432:5432
        options: >-
          --health-cmd "pg_isready -U pad"
          --health-interval 5s
          --health-timeout 3s
          --health-retries 10
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

      - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
        with:
          go-version: "1.26"

      - name: Allow Go to fetch the toolchain go.mod pins
        # See the identical step in the `go` job — setup-go pins
        # GOTOOLCHAIN=local, blocking the 1.26.5 fetch go.mod requires.
        run: echo "GOTOOLCHAIN=auto" >> "$GITHUB_ENV"

      - name: Create web build placeholder for embed
        run: mkdir -p web/build && echo "placeholder" > web/build/.gitkeep

      - name: Run tests against PostgreSQL
        env:
          PAD_TEST_POSTGRES_URL: "postgres://pad:pad@localhost:5432/pad?sslmode=disable"
        run: go test ./... -count=1

      - name: Run tests with race detector against PostgreSQL
        env:
          PAD_TEST_POSTGRES_URL: "postgres://pad:pad@localhost:5432/pad?sslmode=disable"
        # Runs on both push-to-main AND pull_request — see SQLite race-step
        # comment for the public-repo / BUG-1371 reasoning.
        #
        # Headroom over the default 10m. PostgreSQL adds latency on
        # every CREATE/DROP, and the PLAN-866 attachment work pushed the
        # cumulative wall over 20m. The bootstrap-user bcrypt cost that
        # blew past 30m on main (BUG-1371) is now handled by TestMain
        # dropping the cost to bcrypt.MinCost for test binaries.
        # BUG-1913: raised 30m → 45m alongside the SQLite step — the
        # suite's aggregate runtime crossed the old budget (this job
        # variant failed main at f235a04 with the same timeout panic).
        run: go test -race -timeout=45m ./... -count=1

  web:
    name: Web
    runs-on: ubuntu-latest
    defaults:
      run:
        working-directory: web
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
        with:
          node-version: "24"
          cache: "npm"
          cache-dependency-path: web/package-lock.json

      - name: Install dependencies
        run: npm ci

      - name: Check coordinated Tiptap pins
        # The Y.Doc/ProseMirror schema is shared across @tiptap/core,
        # @tiptap/extension-collaboration, @tiptap/y-tiptap and @tiptap/pm.
        # A stray `npm update` that slides one of them can silently change
        # the persisted Y.Doc shape, producing divergent collab ops the
        # relay can't reconcile (see CLAUDE.md "Tiptap multi-package
        # coordinated bumps" and BUG-2009). This guard fails if any of them
        # loses its exact pin in package.json or resolves to more than one
        # version in the lockfile.
        run: npm run check:tiptap-pins

      - name: Audit npm dependencies (production, high+)
        # Fail the build on any HIGH or CRITICAL advisory in production deps.
        # Dev-only advisories are treated as informational — they don't ship
        # and fixing them can require waiting on upstream maintainers.
        run: npm audit --audit-level=high --omit=dev

      - name: Build
        run: npm run build

      - name: Type check (svelte-check)
        run: npm run check

      - name: Run web unit tests (vitest)
        run: npm run test

  e2e:
    name: E2E (Playwright)
    runs-on: ubuntu-latest
    # Build the binary + UI once and reuse across Playwright projects.
    # The suite is small (<10s at the time of writing — see TASK-733 for
    # follow-up coverage); the `timeout-minutes` cap is a sanity check.
    timeout-minutes: 10
    steps:
      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

      - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
        with:
          go-version: "1.26"

      - name: Allow Go to fetch the toolchain go.mod pins
        # See the identical step in the `go` job — setup-go pins
        # GOTOOLCHAIN=local, blocking the 1.26.5 fetch go.mod requires
        # (the "Build pad binary" step below fails without this).
        run: echo "GOTOOLCHAIN=auto" >> "$GITHUB_ENV"

      - uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
        with:
          node-version: "24"
          cache: "npm"
          cache-dependency-path: web/package-lock.json

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

      - name: Build web UI
        working-directory: web
        run: npm run build

      - name: Build pad binary
        # Web build output is embedded via //go:embed; it must exist before
        # the Go build. The CI `go` job above builds against a placeholder,
        # which is fine for tests — for e2e we need the real embedded UI.
        run: go build -o pad ./cmd/pad

      # Playwright browser binaries are downloaded from cdn.playwright.dev,
      # which occasionally hangs (PR #635 hit two consecutive 10-minute
      # timeouts during a CDN slow patch — see BUG-1625). Cache them per
      # @playwright/test version so warm-cache runs skip the ~150 MB
      # Chromium download entirely; only the apt system libraries
      # (libatk, libnss, libcups, …) need a fresh install, which is
      # ~10s on a healthy runner. Cache key is the resolved version from
      # package-lock.json so a Playwright bump auto-invalidates.
      - name: Get Playwright version
        id: playwright-version
        working-directory: web
        run: echo "version=$(node -p "require('@playwright/test/package.json').version")" >> $GITHUB_OUTPUT

      - name: Cache Playwright browsers
        id: playwright-cache
        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
        with:
          path: ~/.cache/ms-playwright
          key: playwright-${{ runner.os }}-${{ steps.playwright-version.outputs.version }}-chromium

      - name: Install Playwright browsers (cache miss)
        if: steps.playwright-cache.outputs.cache-hit != 'true'
        working-directory: web
        # --with-deps pulls in the Ubuntu libraries Playwright needs
        # (libatk, libnss, libcups, …). Scoped to chromium to cut download
        # time — the suite's mobile project uses Pixel 7, which defaults to
        # Chromium, so we don't need WebKit.
        run: npx playwright install --with-deps chromium

      - name: Install Playwright system deps (cache hit)
        if: steps.playwright-cache.outputs.cache-hit == 'true'
        working-directory: web
        # When the browser binary cache hits, we still need the apt-level
        # system libraries on the fresh runner — `install-deps` does just
        # that without re-downloading the browser binary itself.
        run: npx playwright install-deps chromium

      - name: Run Playwright
        working-directory: web
        env:
          CI: "1"
        run: npx playwright test

      - name: Upload Playwright report on failure
        if: failure()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
        with:
          name: playwright-report
          path: web/playwright-report/
          retention-days: 14