Add WebVoyager agent-eval optimization loop #271
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Tier2 Staging Gate | |
| on: | |
| push: | |
| branches: [main] | |
| pull_request: | |
| branches: [main] | |
| workflow_dispatch: | |
| jobs: | |
| tier2-gate: | |
| if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: pnpm/action-setup@v4 | |
| with: | |
| version: 10 | |
| - uses: actions/setup-node@v4 | |
| with: | |
| node-version: 20 | |
| cache: pnpm | |
| - run: pnpm install --frozen-lockfile | |
| - run: pnpm build | |
| - name: Install Playwright browsers | |
| run: pnpm exec playwright install --with-deps chromium | |
| - name: Verify secrets | |
| env: | |
| OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} | |
| AI_TANGLE_STORAGE_STATE: ${{ secrets.AI_TANGLE_STORAGE_STATE }} | |
| run: | | |
| if [ -z "${OPENAI_API_KEY}" ] || [ -z "${AI_TANGLE_STORAGE_STATE}" ]; then | |
| echo "::warning::Required secrets not available — skipping Tier2 gate" | |
| echo "SKIP_GATE=true" >> "$GITHUB_ENV" | |
| fi | |
| - name: Materialize storage state | |
| if: env.SKIP_GATE != 'true' | |
| env: | |
| AI_TANGLE_STORAGE_STATE: ${{ secrets.AI_TANGLE_STORAGE_STATE }} | |
| run: | | |
| mkdir -p ./.auth | |
| printf '%s' "${AI_TANGLE_STORAGE_STATE}" > ./.auth/ai-tangle-tools.json | |
| node -e "JSON.parse(require('node:fs').readFileSync('./.auth/ai-tangle-tools.json','utf8'))" | |
| - name: Run repeated staging gate | |
| if: env.SKIP_GATE != 'true' | |
| run: | | |
| pnpm bench:tier2:repeat -- \ | |
| --out ./agent-results/tier2-staging \ | |
| --model gpt-5.2 \ | |
| --storage-state ./.auth/ai-tangle-tools.json \ | |
| --repetitions 2 \ | |
| --min-full-pass-rate 1 \ | |
| --min-fast-pass-rate 1 \ | |
| --max-avg-turns 45 \ | |
| --max-avg-duration-ms 300000 | |
| env: | |
| OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }} | |
| - name: Upload gate artifacts | |
| if: always() && env.SKIP_GATE != 'true' | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: tier2-staging-results | |
| path: ./agent-results/tier2-staging |