diff --git a/.github/workflows/ai-eval.yml b/.github/workflows/ai-eval.yml index 5f9aa67..b87b3cb 100644 --- a/.github/workflows/ai-eval.yml +++ b/.github/workflows/ai-eval.yml @@ -43,7 +43,7 @@ jobs: uses: actions/upload-artifact@v4 with: name: ai-eval-responses - path: ai-evals/*.responses.md + path: ai-evals/**/*.responses.md retention-days: 14 - name: Notify Slack on failure diff --git a/package.json b/package.json index 5dca1a9..b4b279c 100644 --- a/package.json +++ b/package.json @@ -106,8 +106,7 @@ "prepare": "husky", "release": "node release.js", "test": "vitest run && echo 'Test complete.' && npm run -s lint && npm run -s typecheck", - "test:ai-eval": "riteway ai ai-evals/aidd-review/review-skill-test.sudo --runs 1 --threshold 75 --timeout 600000 --agent claude --color --save-responses", - "test:ai-eval:upskill": "riteway ai ai-evals/aidd-upskill/*.sudo --runs 1 --threshold 75 --timeout 600000 --agent claude --color --save-responses", + "test:ai-eval": "riteway ai 'ai-evals/**/*.sudo' --runs 1 --threshold 75 --timeout 600000 --agent claude --color --save-responses", "test:e2e": "vitest run **/*-e2e.test.js && echo 'E2E tests complete.'", "test:unit": "vitest run --exclude '**/*-e2e.test.js' && echo 'Unit tests complete.' && npm run -s lint && npm run -s typecheck", "toc": "doctoc README.md",