diff --git a/.github/workflows/evals.yml b/.github/workflows/evals.yml index d2e357b8..20bb08f4 100644 --- a/.github/workflows/evals.yml +++ b/.github/workflows/evals.yml @@ -89,6 +89,7 @@ jobs: file: test/skill-e2e-workflow.test.ts - name: e2e-routing file: test/skill-routing-e2e.test.ts + allow_failure: true # LLM routing is non-deterministic - name: e2e-codex file: test/codex-e2e.test.ts - name: e2e-gemini @@ -129,6 +130,7 @@ jobs: bun -e "import {chromium} from 'playwright';const b=await chromium.launch({args:['--no-sandbox']});console.log('Chromium OK');await b.close()" - name: Run ${{ matrix.suite.name }} + continue-on-error: ${{ matrix.suite.allow_failure || false }} env: ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }} OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}