Behavioral evals framework. (#16047)

This commit is contained in:
Christian Gunderman
2026-01-14 04:49:17 +00:00
committed by GitHub
parent 933bc5774f
commit 8030404b08
15 changed files with 1577 additions and 1413 deletions

View File

@@ -41,6 +41,8 @@
"test": "npm run test --workspaces --if-present",
"test:ci": "npm run test:ci --workspaces --if-present && npm run test:scripts",
"test:scripts": "vitest run --config ./scripts/tests/vitest.config.ts",
"test:always_passing_evals": "vitest run --config evals/vitest.config.ts",
"test:all_evals": "cross-env RUN_EVALS=1 vitest run --config evals/vitest.config.ts",
"test:e2e": "cross-env VERBOSE=true KEEP_OUTPUT=true npm run test:integration:sandbox:none",
"test:integration:all": "npm run test:integration:sandbox:none && npm run test:integration:sandbox:docker && npm run test:integration:sandbox:podman",
"test:integration:sandbox:none": "cross-env GEMINI_SANDBOX=false vitest run --root ./integration-tests",