name: Build & Deploy (Nix)

on:
  push:
    branches: [main]
  workflow_dispatch:

concurrency:
  group: gmw-deploy
  cancel-in-progress: false

permissions:
  contents: read
  id-token: write

env:
  VPS_HOST: ${{ secrets.VPS_HOST }}
  VPS_USER: ${{ secrets.VPS_USER }}

jobs:
  test:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@v7
        with:
          fetch-depth: 0
          submodules: false

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

      - name: Install pnpm
        run: corepack enable && corepack prepare pnpm@11 --activate

      - name: Install deps (backend)
        working-directory: services/backend
        run: pnpm install --ignore-scripts --no-frozen-lockfile

      - name: Typecheck + test (backend)
        working-directory: services/backend
        run: |
          ./node_modules/.bin/tsc --noEmit
          # e2e.test.ts requires a live backend (API_BASE) — run unit tests only
          ./node_modules/.bin/vitest run --exclude "src/e2e.test.ts"

      - name: Install deps (discord-gateway)
        working-directory: services/discord-gateway
        run: pnpm install --ignore-scripts --no-frozen-lockfile

      - name: Typecheck + test (discord-gateway)
        working-directory: services/discord-gateway
        run: |
          ./node_modules/.bin/tsc --noEmit
          ./node_modules/.bin/vitest run

      - name: Biome check (all services)
        run: |
          cd services/backend && ./node_modules/.bin/biome check src/ tests/
          cd ../discord-gateway && ./node_modules/.bin/biome check src/

  build-and-deploy:
    needs: test
    runs-on: ubuntu-latest
    strategy:
      fail-fast: false
      matrix:
        service: [backend, discord-gateway, proxy, frontend]
    steps:
      - name: Checkout
        uses: actions/checkout@v7
        with:
          fetch-depth: 0
          submodules: false

      - name: Install Nix
        uses: DeterminateSystems/nix-installer-action@v22
        with:
          determinate: false
          extra-conf: |
            sandbox = false
            accept-flake-config = true
            # Attic binary cache as substituter on the runner: lets CI pull the
            # prebuilt attic client (and any cached deps/builds) over HTTPS,
            # no SSH round-trip needed. extra-substituters (NOT
            # extra-trusted-substituters) is required — Determinate Nix never
            # merges trusted-* substituters for nix-store CLI clients.
            extra-substituters = https://attic.asepharyana.my.id/gmw
            extra-trusted-public-keys = gmw:Fq2Anzuhkb+T/hftWnPcveHSi21/RzIgIOeG8pCJa88=
            # NOTE: nix-installer-action unconditionally injects
            # 'build-provenance-tags' into /etc/nix/nix.conf (a Determinate
            # Nix-only setting). With determinate:false the runner's upstream
            # nix warns 'unknown setting build-provenance-tags' on every
            # invocation — benign, cosmetic. Switching determinate:true would
            # silence it but changes the runner's nix flavor.

      - name: Cache Nix
        uses: DeterminateSystems/magic-nix-cache-action@v14
        with:
          use-flakehub: false

      - name: Build ${{ matrix.service }}
        id: build
        run: |
          nix build .#${{ matrix.service }} --impure --option sandbox false --print-build-logs
          STORE_PATH=$(readlink result)
          echo "store-path=$STORE_PATH" >> "$GITHUB_OUTPUT"
          echo "Build OK ${{ matrix.service }}: $STORE_PATH"

      - name: Setup SSH key
        env:
          SSH_KEY: ${{ secrets.SSH_PRIVATE_KEY }}
        run: |
          mkdir -p ~/.ssh
          echo "$SSH_KEY" > ~/.ssh/id_ed25519
          chmod 600 ~/.ssh/id_ed25519
          sed -i 's/\r$//' ~/.ssh/id_ed25519
          ssh-keygen -y -f ~/.ssh/id_ed25519 >/dev/null 2>&1 || { echo "SSH key invalid"; exit 1; }
          ssh-keyscan -H "$VPS_HOST" >> ~/.ssh/known_hosts 2>/dev/null

      # Push build result to Attic binary cache (attic.asepharyana.my.id) so
      # the VPS can substitute it instead of a single-stream `nix copy ssh://`.
      #
      # Fast path: push DIRECTLY from the runner to the public attic endpoint
      # (validated 2026-08-10: token auth over public HTTPS works without
      # Tailscale). This skips the ~794MB closure SSH copy to the VPS that
      # used to take 25+ minutes per new store path.
      #
      # The attic client is NOT in nixpkgs anymore and has no prebuilt
      # releases, so we pull the same prebuilt closure the VPS uses
      # (/nix/store/fygyy3yk4rqdknxkiwkqambpnhyax0k4-attic-0.1.0, ~52MB).
      # The closure itself lives in the attic cache (pushed once from the
      # VPS), so the runner bootstraps it over HTTPS via the configured
      # extra-substituters — no SSH round-trip. If that fails we fall back
      # to `nix copy --from ssh://`, then the old VPS-hop flow (SSH copy to
      # VPS, then attic push from the VPS over Tailscale) so the deploy step
      # always has a working closure path.
      - name: Push to Attic cache
        env:
          ATTIC_TOKEN: ${{ secrets.ATTIC_TOKEN }}
        run: |
          if [ -z "$ATTIC_TOKEN" ]; then
            echo "ATTIC_TOKEN not set; skipping attic push"
            exit 0
          fi
          STORE_PATH="${{ steps.build.outputs.store-path }}"
          ATTIC_DIR="/nix/store/fygyy3yk4rqdknxkiwkqambpnhyax0k4-attic-0.1.0"
          ATTIC_BIN="$ATTIC_DIR/bin/attic"

          attic_push_vps_hop() {
            echo "Fallback: VPS-hop attic push"
            # Copy closure to VPS (fast if attic already has it via substitute)
            ssh "$VPS_USER@$VPS_HOST" "sudo /nix/var/nix/profiles/default/bin/nix-store --realise '$STORE_PATH'" 2>/dev/null \
              || nix copy --to "ssh://$VPS_USER@$VPS_HOST" "$STORE_PATH"
            # Push from VPS → Attic over Tailscale.
            # --ignore-upstream-cache-filter is REQUIRED: without it, attic skips
            # writing the narinfo to gmw when chunks exist in the upstream
            # cache.nixos.org — leaving the path 404 on gmw so the VPS deploy's
            # nix-store --realise can't find it and falls back to ssh copy.
            # sudo: attic must read root's config (~/.config/attic), which has
            # the imrnes-ts server → Tailscale. Non-root users' configs only
            # have the public `pub` server → "Server imrnes-ts does not exist".
            ssh "$VPS_USER@$VPS_HOST" "sudo $ATTIC_BIN push imrnes-ts:gmw '$STORE_PATH' --jobs 4 --ignore-upstream-cache-filter" \
              || echo "attic push failed (non-fatal; ssh copy fallback below)"
          }

          # ── Get an attic client on the runner ────────────────────────────
          # Order: PATH → pull the prebuilt closure from the attic cache
          # itself (extra-substituters configured in Install Nix step, HTTPS
          # only, no SSH) → pull over ssh from the VPS → VPS-hop.
          # The attic client closure is stored in the attic cache (pushed
          # once from the VPS), so the fast path never depends on SSH.
          ATTIC_BIN=""
          if command -v attic >/dev/null 2>&1; then
            ATTIC_BIN="$(command -v attic)"
          elif nix-store --realise "$ATTIC_DIR" 2>/tmp/attic-bootstrap.err; then
            echo "✅ Pulled attic client from attic cache (HTTPS substituter)"
            ATTIC_BIN="$ATTIC_DIR/bin/attic"
          elif nix copy --from "ssh://$VPS_USER@$VPS_HOST" "$ATTIC_DIR" 2>>/tmp/attic-bootstrap.err; then
            echo "✅ Pulled attic client from VPS over ssh"
            ATTIC_BIN="$ATTIC_DIR/bin/attic"
          else
            echo "attic client unavailable on runner; using VPS-hop flow"
            echo "--- bootstrap errors (stderr) ---"
            tail -5 /tmp/attic-bootstrap.err 2>/dev/null || true
            attic_push_vps_hop
            exit 0
          fi

          # ── Direct push: runner → attic public endpoint ──────────────────
          # --ignore-upstream-cache-filter forces the narinfo write even when
          # the path's chunks already exist in upstream cache.nixos.org (which
          # attic would otherwise skip, leaving the path 404 on the gmw cache).
          mkdir -p "$HOME/.config/attic"
          cat > "$HOME/.config/attic/config.toml" <<EOF
          default-server = "pub"

          [servers.pub]
          endpoint = "https://attic.asepharyana.my.id"
          token = "$ATTIC_TOKEN"
          EOF
          # Retry the direct push — a transient 502 (e.g. atticd restart,
          # Traefik blip) must not abort the whole closure upload. attic push
          # is idempotent, so re-running only uploads what's still missing.
          push_ok=""
          for attempt in 1 2 3; do
            if "$ATTIC_BIN" push pub:gmw "$STORE_PATH" --jobs 4 --ignore-upstream-cache-filter; then
              echo "✅ Pushed $STORE_PATH to attic directly from runner"
              push_ok=1
              break
            fi
            echo "⚠️ Direct attic push attempt $attempt/3 failed; retrying in 10s..."
            sleep 10
          done
          if [ -z "$push_ok" ]; then
            echo "Direct attic push failed after 3 attempts; using VPS-hop flow"
            attic_push_vps_hop
          fi

      # NOTE: env files /etc/gmw/backend.env & /etc/gmw/discord-gateway.env are
      # managed MANUALLY on the VPS (source of truth). CI only builds & deploys.
      - name: Deploy ${{ matrix.service }} to VPS
        run: |
          STORE_PATH="${{ steps.build.outputs.store-path }}"
          echo "=== Copying ${{ matrix.service }}: $STORE_PATH ==="
          if [ -n "${{ secrets.ATTIC_TOKEN }}" ] && ssh "$VPS_USER@$VPS_HOST" "sudo /nix/var/nix/profiles/default/bin/nix-store --realise '$STORE_PATH'" 2>/dev/null; then
            echo "Substituted ${{ matrix.service }} from Attic cache"
          else
            echo "Attic substitute failed; falling back to ssh copy"
            nix copy --to "ssh://$VPS_USER@$VPS_HOST" "$STORE_PATH"
          fi

          echo "=== Updating profile ==="
          ssh "$VPS_USER@$VPS_HOST" "sudo /nix/var/nix/profiles/default/bin/nix-env --profile /nix/var/nix/profiles/gmw-${{ matrix.service }} --set '$STORE_PATH'"

          echo "=== Restarting service ===\n"
                    ssh "$VPS_USER@$VPS_HOST" \
                      "sudo systemctl daemon-reload && sudo systemctl restart gmw-${{ matrix.service }} && for i in \$(seq 1 15); do state=\$(sudo systemctl is-active gmw-${{ matrix.service }} 2>/dev/null || echo inactive); [ \"\$state\" = \"active\" ] && break; sleep 2; done; echo \"final-state=\$state\"; [ \"\$state\" = \"active\" ]" 
                    echo "✅ gmw-${{ matrix.service }} deployed"

  cleanup:
    # Bersihkan sampah Nix di VPS SETELAH semua deploy selesai: hapus generasi
    # profile lama + nix store gc. Profil yang sedang dipakai tidak disentuh.
    needs: build-and-deploy
    if: always()
    runs-on: ubuntu-latest
    steps:
      - name: Nix GC on VPS
        env:
          VPS_HOST: ${{ secrets.VPS_HOST }}
          VPS_USER: ${{ secrets.VPS_USER }}
          SSH_KEY: ${{ secrets.SSH_PRIVATE_KEY }}
        run: |
          mkdir -p ~/.ssh
          echo "$SSH_KEY" > ~/.ssh/id_ed25519
          chmod 600 ~/.ssh/id_ed25519
          ssh-keyscan -H "$VPS_HOST" >> ~/.ssh/known_hosts 2>/dev/null
          ssh "$VPS_USER@$VPS_HOST" "sudo /usr/local/bin/nix-gc-vps.sh" || echo "⚠️ Nix GC gagal (non-fatal)"