e2e.yml

name: E2E Integration

# Validates that the plugin works end-to-end against the latest published
# OpenClaw release. Installs OpenClaw fresh, builds and installs the plugin
# from source, starts the gateway with a mock LLM + mock Opik server, runs
# a real agent turn, and asserts that traces and spans were exported.
#
# This catches regressions caused by OpenClaw plugin lifecycle changes that
# unit tests cannot detect.

permissions:
  contents: read

on:
  push:
    branches: [main]
    paths:
      - ".github/workflows/e2e.yml"
      - "index.ts"
      - "openclaw.plugin.json"
      - "src/**"
      - ".scripts/**"
      - "package.json"
      - "package-lock.json"
      - "tsconfig.json"
      - "tsconfig.build.json"
  pull_request:
    branches: [main]
    paths:
      - ".github/workflows/e2e.yml"
      - "index.ts"
      - "openclaw.plugin.json"
      - "src/**"
      - ".scripts/**"
      - "package.json"
      - "package-lock.json"
      - "tsconfig.json"
      - "tsconfig.build.json"
  schedule:
    - cron: '0 6 * * *'  # daily at 6am UTC — catches new OpenClaw releases breaking the plugin
  workflow_dispatch:

jobs:
  e2e:
    name: E2E against OpenClaw ${{ matrix.openclaw-version }}
    runs-on: ubuntu-latest
    timeout-minutes: 15

    strategy:
      fail-fast: false
      matrix:
        openclaw-version:
          - latest

    env:
      E2E_RESULT_FILE: e2e-result.json
      E2E_LLM_RESULT_FILE: e2e-llm-result.json
      E2E_OPIK_JOURNAL_FILE: e2e-opik-journal.json
      E2E_LLM_JOURNAL_FILE: e2e-llm-journal.json
      E2E_EXPECTED_OPIK_PROJECT: e2e-test
      OPENCLAW_GATEWAY_TOKEN: e2e-test-token

    steps:
      - name: Checkout plugin source
        uses: actions/checkout@v6

      - name: Setup Node.js
        uses: actions/setup-node@v6
        with:
          node-version: "22.x"
          cache: "npm"

      - name: Setup npm
        run: npm install -g npm@11.6.2

      - name: Setup npm global prefix for caching
        run: |
          npm config set prefix ~/.npm-global
          echo "$HOME/.npm-global/bin" >> $GITHUB_PATH

      - name: Resolve OpenClaw version
        id: openclaw-version
        run: |
          if [ "${{ matrix.openclaw-version }}" = "latest" ]; then
            version="$(npm view openclaw version)"
          else
            version="${{ matrix.openclaw-version }}"
          fi
          echo "value=$version" >> "$GITHUB_OUTPUT"
          echo "Resolved OpenClaw version: $version"

      - name: Cache OpenClaw install
        id: cache-openclaw
        uses: actions/cache@v5
        with:
          path: ~/.npm-global
          key: openclaw-${{ steps.openclaw-version.outputs.value }}-${{ runner.os }}-${{ runner.arch }}

      - name: Install OpenClaw (${{ steps.openclaw-version.outputs.value }})
        if: steps.cache-openclaw.outputs.cache-hit != 'true'
        run: npm install -g openclaw@${{ steps.openclaw-version.outputs.value }}

      - name: Print OpenClaw version
        run: openclaw --version

      - name: Cache plugin dependencies
        id: cache-node-modules
        uses: actions/cache@v5
        with:
          path: node_modules
          key: node-modules-${{ runner.os }}-node22-${{ hashFiles('package-lock.json') }}

      - name: Install plugin dependencies
        if: steps.cache-node-modules.outputs.cache-hit != 'true'
        run: npm ci

      - name: Build plugin tarball
        run: npm pack

      - name: Write OpenClaw config
        run: |
          mkdir -p ~/.openclaw/agents/main/sessions
          cat > ~/.openclaw/openclaw.json << 'EOF'
          {
            "gateway": {
              "mode": "local",
              "bind": "loopback",
              "auth": { "mode": "token", "token": "e2e-test-token" },
              "port": 18789
            },
            "agents": {
              "defaults": {
                "model": {
                  "primary": "mock-openai/gpt-4o-mini"
                }
              }
            },
            "models": {
              "mode": "merge",
              "providers": {
                "mock-openai": {
                  "baseUrl": "http://127.0.0.1:18790/v1",
                  "apiKey": "mock-key",
                  "authHeader": true,
                  "api": "openai-responses",
                  "models": [
                    {
                      "id": "gpt-4o-mini",
                      "name": "Mock GPT-4o Mini",
                      "reasoning": false,
                      "input": ["text"],
                      "cost": {
                        "input": 0,
                        "output": 0,
                        "cacheRead": 0,
                        "cacheWrite": 0
                      },
                      "contextWindow": 128000,
                      "maxTokens": 16384
                    }
                  ]
                }
              }
            },
            "plugins": {
              "allow": ["opik-openclaw"],
              "entries": {
                "opik-openclaw": {
                  "enabled": true,
                  "hooks": {
                    "allowConversationAccess": true
                  },
                  "config": {
                    "enabled": true,
                    "apiUrl": "http://127.0.0.1:18791",
                    "apiKey": "mock-key",
                    "projectName": "e2e-test",
                    "workspaceName": "default"
                  }
                }
              }
            }
          }
          EOF

      - name: Install plugin from tarball
        run: openclaw plugins install ./opik-opik-openclaw-*.tgz

      - name: Start mock Opik server
        run: |
          node .scripts/mock-opik-server.mjs > mock-opik.log 2>&1 &
          echo $! > mock-opik.pid
        env:
          MOCK_OPIK_PORT: "18791"

      - name: Start mock LLM server
        run: |
          node .scripts/mock-llm-server.mjs > mock-llm.log 2>&1 &
          echo $! > mock-llm.pid
        env:
          MOCK_LLM_PORT: "18790"

      - name: Wait for mock servers to be ready
        run: |
          for i in $(seq 1 10); do
            curl -sf http://127.0.0.1:18791/health > /dev/null 2>&1 && \
            curl -sf http://127.0.0.1:18790/v1/models > /dev/null 2>&1 && break
            sleep 1
          done

      - name: Start OpenClaw gateway
        run: |
          openclaw gateway run > gateway.log 2>&1 &
          echo $! > gateway.pid

      - name: Wait for gateway to be ready
        run: |
          for i in $(seq 1 15); do
            openclaw health > /dev/null 2>&1 && break
            sleep 1
          done
          openclaw health

      - name: Run agent turn
        run: |
          set -o pipefail
          openclaw agent --agent main --message "ping" --deliver 2>&1 | tee agent-output.log
          if grep -q "falling back to embedded" agent-output.log; then
            echo "[e2e] FAIL: gateway turn fell back to embedded mode"
            exit 1
          fi
        timeout-minutes: 2

      - name: Stop gateway and flush traces
        run: |
          openclaw gateway stop || true
          if [ -f gateway.pid ]; then
            kill "$(cat gateway.pid)" > /dev/null 2>&1 || true
          fi
          sleep 2

      - name: Stop mock servers and collect results
        run: |
          if [ -f mock-opik.pid ]; then
            kill "$(cat mock-opik.pid)" > /dev/null 2>&1 || true
          fi
          if [ -f mock-llm.pid ]; then
            kill "$(cat mock-llm.pid)" > /dev/null 2>&1 || true
          fi
          sleep 1

      - name: Assert E2E results
        run: node .scripts/check-e2e-result.mjs

      - name: Upload E2E result on failure
        if: failure()
        uses: actions/upload-artifact@v7
        with:
          name: e2e-debug
          path: |
            e2e-result.json
            e2e-llm-result.json
            e2e-opik-journal.json
            e2e-llm-journal.json
            agent-output.log
            gateway.log
            mock-opik.log
            mock-llm.log
          if-no-files-found: ignore