LocalAI/.github/workflows/tests-e2e-distributed.yml

---
name: 'E2E Distributed Tests'

on:
  pull_request:
    # The suite's dependency graph is 99 packages, so an allowlist of paths
    # silently stops guarding the moment code moves. At ~75s the job is cheap
    # enough to run unless the diff is confined to paths it provably cannot
    # reach. See .agents/ci-caching.md.
    paths-ignore:
      - 'gallery/**'
      - 'docs/**'
      - 'examples/**'
      - '**/*.md'
  push:
    branches:
      - master

concurrency:
  group: ci-tests-e2e-distributed-${{ github.event.pull_request.number || github.sha }}-${{ github.repository }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' }}

jobs:
  tests-e2e-distributed:
    runs-on: ubuntu-latest
    # Advisory because it is deliberately not in branch protection, so a failure
    # is a visible red X rather than a blocked merge. Promoting it to a required
    # check is a repository-settings change, to be made once it has a track
    # record; a heavy suite made required on day one gets disabled instead of
    # fixed.
    timeout-minutes: 45
    steps:
      - name: Clone
        uses: actions/checkout@v7
        with:
          submodules: true
      - name: Configure apt mirror on runner
        uses: ./.github/actions/configure-apt-mirror
      - name: Setup Go
        uses: actions/setup-go@v5
        with:
          go-version: '1.26.0'
          cache: false
      - name: Dependencies
        run: |
          sudo apt-get update
          sudo apt-get install -y build-essential libopus-dev
      - name: Proto Dependencies
        run: |
          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
          rm protoc.zip
          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
          PATH="$PATH:$HOME/go/bin" make protogen-go
      - name: Pre-pull test images
        # Pulling here rather than inside the suite keeps container-start timing
        # out of the spec timeouts and makes a registry outage read as a
        # setup failure instead of a test failure. These two are the only images
        # the suite needs once the testcontainers reaper is disabled below.
        run: |
          docker pull postgres:16-alpine
          docker pull nats:2-alpine
      - name: Distributed E2E
        # TESTCONTAINERS_RYUK_DISABLED keeps the pre-pull above meaningful. The
        # reaper exists to clean up leaked containers on a long-lived host, but
        # this runner is ephemeral and every container dies with the VM. Leaving
        # it enabled would pull a third, unpinned image (testcontainers/ryuk)
        # from Docker Hub mid-suite: exactly the registry dependency the
        # pre-pull step exists to remove.
        env:
          TESTCONTAINERS_RYUK_DISABLED: "true"
        run: |
          PATH="$PATH:$HOME/go/bin" make test-e2e-distributed
      - name: Setup tmate session if tests fail
        if: ${{ failure() }}
        uses: mxschmitt/action-tmate@v3.23
        with:
          detached: true
          connect-timeout-seconds: 180
          limit-access-to-actor: true

  tests-e2e-cluster:
    runs-on: ubuntu-latest
    # Advisory for the same reason as the job above: master has no branch
    # protection, so a failure here is a visible red X rather than a blocked
    # merge. That is a repository-settings property, not a YAML key. The key
    # that looks like it says "advisory" instead flips the run's conclusion to
    # success, which hides the failure rather than flagging it, so it appears in
    # none of this repo's workflows and must not be added here.
    #
    # Separate job from tests-e2e-distributed so the fast in-process suite is
    # not held behind a Go build of local-ai. Serial on purpose: each Ginkgo
    # process would get its own PostgreSQL and NATS container and each spec
    # spawns two or three local-ai children, so --procs on an unmeasured runner
    # is a change to make with numbers, not by default.
    #
    # The two timeouts bound different things and are not alternatives. Ginkgo's
    # --timeout=20m bounds the SUITE only; this job timeout must additionally
    # cover setup, which here is the larger and more variable half: submodule
    # checkout, apt, protoc plus two go installs plus protogen-go, a cold-cache
    # module download (cache: false), a full go build of ./cmd/local-ai, and a
    # separate ginkgo test compile. That build alone is ~316s of CPU, so on a
    # 4-vCPU runner setup is realistically 8-12 minutes.
    #
    # 45 minutes therefore, matching the sibling job. A tighter number does not
    # make a hang fail faster, it just moves the kill from Ginkgo, which prints
    # which spec hung, to the runner, which prints nothing: a red job with no
    # evidence, which is how a suite gets disabled rather than fixed.
    #
    # The suite itself is about 8m30s over three consecutive runs (509.1s /
    # 509.8s / 512.3s, so 8m29s to 8m32s) on a developer box, and will be slower
    # here. Three specs sit at ~167s each because they wait out a 60s staleness
    # threshold plus a 15s health-check tick (HealthCheckInterval, in
    # core/services/nodes/health.go, not one of the reconcilers). Do not shorten those windows to make this job faster: the
    # wait is what stops the assertions from passing before the system could
    # have reacted, which was a real false green earlier on.
    timeout-minutes: 45
    steps:
      - name: Clone
        uses: actions/checkout@v7
        with:
          submodules: true
      - name: Configure apt mirror on runner
        uses: ./.github/actions/configure-apt-mirror
      - name: Setup Go
        uses: actions/setup-go@v5
        with:
          go-version: '1.26.0'
          cache: false
      - name: Dependencies
        run: |
          sudo apt-get update
          sudo apt-get install -y build-essential libopus-dev
      - name: Proto Dependencies
        run: |
          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
          rm protoc.zip
          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
          PATH="$PATH:$HOME/go/bin" make protogen-go
      - name: Stub the embedded React UI
        # core/http/react-ui/dist is gitignored and built by Node, but this
        # suite drives the HTTP API and never the UI, which has its own e2e
        # suite. A single index.html satisfies the //go:embed react-ui/dist/*
        # in core/http/app.go, so the job skips a full Node and Vite install.
        # If a cluster spec ever asserts on a UI asset, this step must go and
        # the real build come back: a developer box has a real dist/, so such a
        # spec would pass locally and fail only here, or worse be served the
        # stub and pass in both places.
        run: |
          mkdir -p core/http/react-ui/dist
          printf '<!doctype html><title>stub</title>\n' > core/http/react-ui/dist/index.html
      - name: Build local-ai
        # Not `make build`: that target pulls in the React UI build. The specs
        # exec this binary directly via LOCALAI_E2E_BINARY.
        run: |
          PATH="$PATH:$HOME/go/bin" go build -o local-ai ./cmd/local-ai
      - name: Pre-pull test images
        # Same reasoning as the job above: pulling here keeps container-start
        # timing out of the spec timeouts and makes a registry outage read as a
        # setup failure rather than a test failure.
        run: |
          docker pull postgres:16-alpine
          docker pull nats:2-alpine
      - name: Cluster E2E
        env:
          LOCALAI_E2E_BINARY: ${{ github.workspace }}/local-ai
          # Must live under the workspace so the upload step below can reach it.
          # The harness defaults to GinkgoT().TempDir(), which lands under
          # TMPDIR and would leave the artifact glob matching nothing.
          LOCALAI_E2E_LOG_DIR: ${{ github.workspace }}/cluster-logs
          # Belt and braces: the harness already fails rather than skips when CI
          # is set, and GitHub Actions always sets CI. Stating it here means a
          # future edit to that default cannot silently turn this job into one
          # that passes without ever starting a cluster, since a skipped cluster
          # spec is indistinguishable from a passing one.
          LOCALAI_E2E_REQUIRE_BINARIES: "true"
          # See the job above: the runner is ephemeral, so the reaper buys
          # nothing and would pull a third, unpinned Docker Hub image mid-suite.
          TESTCONTAINERS_RYUK_DISABLED: "true"
        run: |
          PATH="$PATH:$HOME/go/bin" make test-e2e-cluster
      - name: Upload process logs
        # The per-process logs are the only way to read a cluster failure: the
        # Ginkgo output says which assertion failed, not what the four child
        # processes were doing. Without this a red job is undebuggable.
        if: ${{ failure() }}
        uses: actions/upload-artifact@v7
        with:
          name: cluster-process-logs
          path: cluster-logs/**/*.log
          if-no-files-found: ignore
          retention-days: 7
      - name: Setup tmate session if tests fail
        if: ${{ failure() }}
        uses: mxschmitt/action-tmate@v3.23
        with:
          detached: true
          connect-timeout-seconds: 180
          limit-access-to-actor: true