self-bench 0.3.6 → 0.3.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.dockerignore +11 -1
- package/Dockerfile +9 -9
- package/Dockerfile.sandbox +5 -4
- package/README.md +27 -12
- package/bun.lock +462 -95
- package/compose.yaml +64 -20
- package/dist/agent-feed.d.ts +8 -0
- package/dist/agent-feed.d.ts.map +1 -0
- package/dist/agent-feed.js +56 -0
- package/dist/agent-feed.js.map +1 -0
- package/dist/api/http.d.ts +18 -0
- package/dist/api/http.d.ts.map +1 -0
- package/dist/api/http.js +111 -0
- package/dist/api/http.js.map +1 -0
- package/dist/api/run-request.d.ts +37 -0
- package/dist/api/run-request.d.ts.map +1 -0
- package/dist/api/run-request.js +59 -0
- package/dist/api/run-request.js.map +1 -0
- package/dist/api/status.d.ts +4 -0
- package/dist/api/status.d.ts.map +1 -0
- package/dist/api/status.js +36 -0
- package/dist/api/status.js.map +1 -0
- package/dist/api/viewer-routes.d.ts +9 -0
- package/dist/api/viewer-routes.d.ts.map +1 -0
- package/dist/api/viewer-routes.js +98 -0
- package/dist/api/viewer-routes.js.map +1 -0
- package/dist/api-main.js +5 -1
- package/dist/api-main.js.map +1 -1
- package/dist/api.d.ts +7 -25
- package/dist/api.d.ts.map +1 -1
- package/dist/api.js +80 -148
- package/dist/api.js.map +1 -1
- package/dist/archive.d.ts +14 -0
- package/dist/archive.d.ts.map +1 -0
- package/dist/archive.js +114 -0
- package/dist/archive.js.map +1 -0
- package/dist/artifacts/common.d.ts +15 -0
- package/dist/artifacts/common.d.ts.map +1 -0
- package/dist/artifacts/common.js +58 -0
- package/dist/artifacts/common.js.map +1 -0
- package/dist/artifacts/gcs.d.ts +18 -0
- package/dist/artifacts/gcs.d.ts.map +1 -0
- package/dist/artifacts/gcs.js +178 -0
- package/dist/artifacts/gcs.js.map +1 -0
- package/dist/artifacts/local.d.ts +17 -0
- package/dist/artifacts/local.d.ts.map +1 -0
- package/dist/artifacts/local.js +205 -0
- package/dist/artifacts/local.js.map +1 -0
- package/dist/artifacts/types.d.ts +18 -0
- package/dist/artifacts/types.d.ts.map +1 -0
- package/dist/artifacts/types.js +2 -0
- package/dist/artifacts/types.js.map +1 -0
- package/dist/artifacts.d.ts +5 -28
- package/dist/artifacts.d.ts.map +1 -1
- package/dist/artifacts.js +5 -302
- package/dist/artifacts.js.map +1 -1
- package/dist/audit.d.ts.map +1 -1
- package/dist/audit.js +8 -2
- package/dist/audit.js.map +1 -1
- package/dist/auth/api-key-routes.d.ts +17 -0
- package/dist/auth/api-key-routes.d.ts.map +1 -0
- package/dist/auth/api-key-routes.js +57 -0
- package/dist/auth/api-key-routes.js.map +1 -0
- package/dist/auth/api-keys.d.ts +47 -0
- package/dist/auth/api-keys.d.ts.map +1 -0
- package/dist/auth/api-keys.js +102 -0
- package/dist/auth/api-keys.js.map +1 -0
- package/dist/auth/config.d.ts +17 -0
- package/dist/auth/config.d.ts.map +1 -0
- package/dist/auth/config.js +38 -0
- package/dist/auth/config.js.map +1 -0
- package/dist/auth/cookies.d.ts +12 -0
- package/dist/auth/cookies.d.ts.map +1 -0
- package/dist/auth/cookies.js +45 -0
- package/dist/auth/cookies.js.map +1 -0
- package/dist/auth/crypto.d.ts +19 -0
- package/dist/auth/crypto.d.ts.map +1 -0
- package/dist/auth/crypto.js +48 -0
- package/dist/auth/crypto.js.map +1 -0
- package/dist/auth/github.d.ts +37 -0
- package/dist/auth/github.d.ts.map +1 -0
- package/dist/auth/github.js +127 -0
- package/dist/auth/github.js.map +1 -0
- package/dist/auth/routes.d.ts +41 -0
- package/dist/auth/routes.d.ts.map +1 -0
- package/dist/auth/routes.js +153 -0
- package/dist/auth/routes.js.map +1 -0
- package/dist/auth/session-expired.d.ts +4 -0
- package/dist/auth/session-expired.d.ts.map +1 -0
- package/dist/auth/session-expired.js +17 -0
- package/dist/auth/session-expired.js.map +1 -0
- package/dist/auth/session.d.ts +23 -0
- package/dist/auth/session.d.ts.map +1 -0
- package/dist/auth/session.js +56 -0
- package/dist/auth/session.js.map +1 -0
- package/dist/auth/users.d.ts +49 -0
- package/dist/auth/users.d.ts.map +1 -0
- package/dist/auth/users.js +125 -0
- package/dist/auth/users.js.map +1 -0
- package/dist/build-metadata.js +1 -1
- package/dist/cli/api-client.d.ts +8 -0
- package/dist/cli/api-client.d.ts.map +1 -0
- package/dist/cli/api-client.js +71 -0
- package/dist/cli/api-client.js.map +1 -0
- package/dist/cli/associate.d.ts +2 -0
- package/dist/cli/associate.d.ts.map +1 -0
- package/dist/cli/associate.js +51 -0
- package/dist/cli/associate.js.map +1 -0
- package/dist/cli/help.d.ts +2 -0
- package/dist/cli/help.d.ts.map +1 -0
- package/dist/cli/help.js +52 -0
- package/dist/cli/help.js.map +1 -0
- package/dist/cli/main.d.ts +2 -0
- package/dist/cli/main.d.ts.map +1 -0
- package/dist/cli/main.js +55 -0
- package/dist/cli/main.js.map +1 -0
- package/dist/cli/replay.d.ts +3 -0
- package/dist/cli/replay.d.ts.map +1 -0
- package/dist/cli/replay.js +59 -0
- package/dist/cli/replay.js.map +1 -0
- package/dist/cli/repository.d.ts +6 -0
- package/dist/cli/repository.d.ts.map +1 -0
- package/dist/cli/repository.js +36 -0
- package/dist/cli/repository.js.map +1 -0
- package/dist/cli/run.d.ts +2 -0
- package/dist/cli/run.d.ts.map +1 -0
- package/dist/cli/run.js +93 -0
- package/dist/cli/run.js.map +1 -0
- package/dist/cli/stack-environment.d.ts +26 -0
- package/dist/cli/stack-environment.d.ts.map +1 -0
- package/dist/cli/stack-environment.js +86 -0
- package/dist/cli/stack-environment.js.map +1 -0
- package/dist/cli/stack.d.ts +6 -0
- package/dist/cli/stack.d.ts.map +1 -0
- package/dist/cli/stack.js +131 -0
- package/dist/cli/stack.js.map +1 -0
- package/dist/cli/values.d.ts +8 -0
- package/dist/cli/values.d.ts.map +1 -0
- package/dist/cli/values.js +30 -0
- package/dist/cli/values.js.map +1 -0
- package/dist/cli/view.d.ts +2 -0
- package/dist/cli/view.d.ts.map +1 -0
- package/dist/cli/view.js +40 -0
- package/dist/cli/view.js.map +1 -0
- package/dist/cli.js +2 -429
- package/dist/cli.js.map +1 -1
- package/dist/config.d.ts +16 -2
- package/dist/config.d.ts.map +1 -1
- package/dist/config.js +60 -22
- package/dist/config.js.map +1 -1
- package/dist/contracts/common.d.ts +22 -0
- package/dist/contracts/common.d.ts.map +1 -0
- package/dist/contracts/common.js +29 -0
- package/dist/contracts/common.js.map +1 -0
- package/dist/contracts/results.d.ts +66 -0
- package/dist/contracts/results.d.ts.map +1 -0
- package/dist/contracts/results.js +2 -0
- package/dist/contracts/results.js.map +1 -0
- package/dist/contracts/run.d.ts +145 -0
- package/dist/contracts/run.d.ts.map +1 -0
- package/dist/contracts/run.js +74 -0
- package/dist/contracts/run.js.map +1 -0
- package/dist/contracts/task.d.ts +232 -0
- package/dist/contracts/task.d.ts.map +1 -0
- package/dist/contracts/task.js +198 -0
- package/dist/contracts/task.js.map +1 -0
- package/dist/contracts/verify.d.ts +331 -0
- package/dist/contracts/verify.d.ts.map +1 -0
- package/dist/contracts/verify.js +84 -0
- package/dist/contracts/verify.js.map +1 -0
- package/dist/contracts.d.ts +5 -243
- package/dist/contracts.d.ts.map +1 -1
- package/dist/contracts.js +5 -128
- package/dist/contracts.js.map +1 -1
- package/dist/db/client.d.ts +12 -0
- package/dist/db/client.d.ts.map +1 -0
- package/dist/db/client.js +16 -0
- package/dist/db/client.js.map +1 -0
- package/dist/db/schema.d.ts +1256 -0
- package/dist/db/schema.d.ts.map +1 -0
- package/dist/db/schema.js +128 -0
- package/dist/db/schema.js.map +1 -0
- package/dist/environment.d.ts +9 -0
- package/dist/environment.d.ts.map +1 -0
- package/dist/environment.js +101 -0
- package/dist/environment.js.map +1 -0
- package/dist/evaluation/account.d.ts +30 -0
- package/dist/evaluation/account.d.ts.map +1 -0
- package/dist/evaluation/account.js +34 -0
- package/dist/evaluation/account.js.map +1 -0
- package/dist/evaluation/activities.d.ts +9 -0
- package/dist/evaluation/activities.d.ts.map +1 -0
- package/dist/evaluation/activities.js +40 -0
- package/dist/evaluation/activities.js.map +1 -0
- package/dist/evaluation/catalog-pricing.d.ts +3 -0
- package/dist/evaluation/catalog-pricing.d.ts.map +1 -0
- package/dist/evaluation/catalog-pricing.js +37 -0
- package/dist/evaluation/catalog-pricing.js.map +1 -0
- package/dist/evaluation/catalog.d.ts +17 -0
- package/dist/evaluation/catalog.d.ts.map +1 -0
- package/dist/evaluation/catalog.js +126 -0
- package/dist/evaluation/catalog.js.map +1 -0
- package/dist/evaluation/codex-login-process.d.ts +12 -0
- package/dist/evaluation/codex-login-process.d.ts.map +1 -0
- package/dist/evaluation/codex-login-process.js +121 -0
- package/dist/evaluation/codex-login-process.js.map +1 -0
- package/dist/evaluation/codex-login-routes.d.ts +5 -0
- package/dist/evaluation/codex-login-routes.d.ts.map +1 -0
- package/dist/evaluation/codex-login-routes.js +55 -0
- package/dist/evaluation/codex-login-routes.js.map +1 -0
- package/dist/evaluation/codex-login.d.ts +42 -0
- package/dist/evaluation/codex-login.d.ts.map +1 -0
- package/dist/evaluation/codex-login.js +143 -0
- package/dist/evaluation/codex-login.js.map +1 -0
- package/dist/evaluation/comparisons.d.ts +65 -0
- package/dist/evaluation/comparisons.d.ts.map +1 -0
- package/dist/evaluation/comparisons.js +161 -0
- package/dist/evaluation/comparisons.js.map +1 -0
- package/dist/evaluation/config.d.ts +43 -0
- package/dist/evaluation/config.d.ts.map +1 -0
- package/dist/evaluation/config.js +116 -0
- package/dist/evaluation/config.js.map +1 -0
- package/dist/evaluation/cost.d.ts +3 -0
- package/dist/evaluation/cost.d.ts.map +1 -0
- package/dist/evaluation/cost.js +95 -0
- package/dist/evaluation/cost.js.map +1 -0
- package/dist/evaluation/credential-execution.d.ts +10 -0
- package/dist/evaluation/credential-execution.d.ts.map +1 -0
- package/dist/evaluation/credential-execution.js +65 -0
- package/dist/evaluation/credential-execution.js.map +1 -0
- package/dist/evaluation/credentials.d.ts +40 -0
- package/dist/evaluation/credentials.d.ts.map +1 -0
- package/dist/evaluation/credentials.js +146 -0
- package/dist/evaluation/credentials.js.map +1 -0
- package/dist/evaluation/encrypted-records.d.ts +15 -0
- package/dist/evaluation/encrypted-records.d.ts.map +1 -0
- package/dist/evaluation/encrypted-records.js +57 -0
- package/dist/evaluation/encrypted-records.js.map +1 -0
- package/dist/evaluation/gateway-execution.d.ts +18 -0
- package/dist/evaluation/gateway-execution.d.ts.map +1 -0
- package/dist/evaluation/gateway-execution.js +38 -0
- package/dist/evaluation/gateway-execution.js.map +1 -0
- package/dist/evaluation/harbor-cost.d.ts +3 -0
- package/dist/evaluation/harbor-cost.d.ts.map +1 -0
- package/dist/evaluation/harbor-cost.js +39 -0
- package/dist/evaluation/harbor-cost.js.map +1 -0
- package/dist/evaluation/harbor_e2b.py +20 -0
- package/dist/evaluation/harbor_gateway.py +22 -0
- package/dist/evaluation/harnesses.d.ts +8 -0
- package/dist/evaluation/harnesses.d.ts.map +1 -0
- package/dist/evaluation/harnesses.js +10 -0
- package/dist/evaluation/harnesses.js.map +1 -0
- package/dist/evaluation/model-options.d.ts +9 -0
- package/dist/evaluation/model-options.d.ts.map +1 -0
- package/dist/evaluation/model-options.js +81 -0
- package/dist/evaluation/model-options.js.map +1 -0
- package/dist/evaluation/org-credential-routes.d.ts +5 -0
- package/dist/evaluation/org-credential-routes.d.ts.map +1 -0
- package/dist/evaluation/org-credential-routes.js +56 -0
- package/dist/evaluation/org-credential-routes.js.map +1 -0
- package/dist/evaluation/org-records.d.ts +4 -0
- package/dist/evaluation/org-records.d.ts.map +1 -0
- package/dist/evaluation/org-records.js +14 -0
- package/dist/evaluation/org-records.js.map +1 -0
- package/dist/evaluation/output.d.ts +9 -0
- package/dist/evaluation/output.d.ts.map +1 -0
- package/dist/evaluation/output.js +171 -0
- package/dist/evaluation/output.js.map +1 -0
- package/dist/evaluation/platform-routes.d.ts +5 -0
- package/dist/evaluation/platform-routes.d.ts.map +1 -0
- package/dist/evaluation/platform-routes.js +123 -0
- package/dist/evaluation/platform-routes.js.map +1 -0
- package/dist/evaluation/profile-routes.d.ts +16 -0
- package/dist/evaluation/profile-routes.d.ts.map +1 -0
- package/dist/evaluation/profile-routes.js +47 -0
- package/dist/evaluation/profile-routes.js.map +1 -0
- package/dist/evaluation/profiles.d.ts +48 -0
- package/dist/evaluation/profiles.d.ts.map +1 -0
- package/dist/evaluation/profiles.js +134 -0
- package/dist/evaluation/profiles.js.map +1 -0
- package/dist/evaluation/providers.d.ts +11 -0
- package/dist/evaluation/providers.d.ts.map +1 -0
- package/dist/evaluation/providers.js +30 -0
- package/dist/evaluation/providers.js.map +1 -0
- package/dist/evaluation/routes.d.ts +23 -0
- package/dist/evaluation/routes.d.ts.map +1 -0
- package/dist/evaluation/routes.js +212 -0
- package/dist/evaluation/routes.js.map +1 -0
- package/dist/evaluation/runner.d.ts +16 -0
- package/dist/evaluation/runner.d.ts.map +1 -0
- package/dist/evaluation/runner.js +241 -0
- package/dist/evaluation/runner.js.map +1 -0
- package/dist/evaluation/store.d.ts +8 -0
- package/dist/evaluation/store.d.ts.map +1 -0
- package/dist/evaluation/store.js +60 -0
- package/dist/evaluation/store.js.map +1 -0
- package/dist/evaluation/types.d.ts +98 -0
- package/dist/evaluation/types.d.ts.map +1 -0
- package/dist/evaluation/types.js +2 -0
- package/dist/evaluation/types.js.map +1 -0
- package/dist/evaluation/worker-main.d.ts +2 -0
- package/dist/evaluation/worker-main.d.ts.map +1 -0
- package/dist/evaluation/worker-main.js +26 -0
- package/dist/evaluation/worker-main.js.map +1 -0
- package/dist/evaluation/worker-records.d.ts +5 -0
- package/dist/evaluation/worker-records.d.ts.map +1 -0
- package/dist/evaluation/worker-records.js +11 -0
- package/dist/evaluation/worker-records.js.map +1 -0
- package/dist/evaluation/workflow.d.ts +3 -0
- package/dist/evaluation/workflow.d.ts.map +1 -0
- package/dist/evaluation/workflow.js +20 -0
- package/dist/evaluation/workflow.js.map +1 -0
- package/dist/execution-environment.d.ts +3 -0
- package/dist/execution-environment.d.ts.map +1 -0
- package/dist/execution-environment.js +9 -0
- package/dist/execution-environment.js.map +1 -0
- package/dist/extension-authoring.bundle.js +347 -0
- package/dist/extension-verifier.bundle.js +73 -0
- package/dist/extensions/authoring.d.ts.map +1 -1
- package/dist/extensions/authoring.js +70 -59
- package/dist/extensions/authoring.js.map +1 -1
- package/dist/extensions/shared/deliverable.d.ts +33 -0
- package/dist/extensions/shared/deliverable.d.ts.map +1 -0
- package/dist/extensions/shared/deliverable.js +123 -0
- package/dist/extensions/shared/deliverable.js.map +1 -0
- package/dist/extensions/shared/mailbox.d.ts +33 -0
- package/dist/extensions/shared/mailbox.d.ts.map +1 -0
- package/dist/extensions/shared/mailbox.js +102 -0
- package/dist/extensions/shared/mailbox.js.map +1 -0
- package/dist/extensions/shared/schemas.d.ts +90 -0
- package/dist/extensions/shared/schemas.d.ts.map +1 -0
- package/dist/extensions/shared/schemas.js +71 -0
- package/dist/extensions/shared/schemas.js.map +1 -0
- package/dist/extensions/shared/static-check.d.ts +38 -0
- package/dist/extensions/shared/static-check.d.ts.map +1 -0
- package/dist/extensions/shared/static-check.js +52 -0
- package/dist/extensions/shared/static-check.js.map +1 -0
- package/dist/extensions/verifier.d.ts +4 -0
- package/dist/extensions/verifier.d.ts.map +1 -0
- package/dist/extensions/verifier.js +70 -0
- package/dist/extensions/verifier.js.map +1 -0
- package/dist/github.d.ts +1 -1
- package/dist/github.d.ts.map +1 -1
- package/dist/github.js +3 -3
- package/dist/github.js.map +1 -1
- package/dist/harbor-environment.d.ts +13 -1
- package/dist/harbor-environment.d.ts.map +1 -1
- package/dist/harbor-environment.js +37 -4
- package/dist/harbor-environment.js.map +1 -1
- package/dist/harbor-results.d.ts +2 -0
- package/dist/harbor-results.d.ts.map +1 -1
- package/dist/harbor-results.js +2 -0
- package/dist/harbor-results.js.map +1 -1
- package/dist/harbor-task/compiler.d.ts +10 -0
- package/dist/harbor-task/compiler.d.ts.map +1 -0
- package/dist/harbor-task/compiler.js +174 -0
- package/dist/harbor-task/compiler.js.map +1 -0
- package/dist/harbor-task/constants.d.ts +3 -0
- package/dist/harbor-task/constants.d.ts.map +1 -0
- package/dist/harbor-task/constants.js +3 -0
- package/dist/harbor-task/constants.js.map +1 -0
- package/dist/harbor-task/dependencies.d.ts +3 -0
- package/dist/harbor-task/dependencies.d.ts.map +1 -0
- package/dist/harbor-task/dependencies.js +20 -0
- package/dist/harbor-task/dependencies.js.map +1 -0
- package/dist/harbor-task/paths.d.ts +6 -0
- package/dist/harbor-task/paths.d.ts.map +1 -0
- package/dist/harbor-task/paths.js +37 -0
- package/dist/harbor-task/paths.js.map +1 -0
- package/dist/harbor-task/render.d.ts +11 -0
- package/dist/harbor-task/render.d.ts.map +1 -0
- package/dist/harbor-task/render.js +194 -0
- package/dist/harbor-task/render.js.map +1 -0
- package/dist/harbor-task/runtime/command.sh +26 -0
- package/dist/harbor-task/runtime/junit.py +69 -0
- package/dist/harbor-task/runtime-assets.d.ts +2 -0
- package/dist/harbor-task/runtime-assets.d.ts.map +1 -0
- package/dist/harbor-task/runtime-assets.js +8 -0
- package/dist/harbor-task/runtime-assets.js.map +1 -0
- package/dist/harbor-task/test-patch.d.ts +4 -0
- package/dist/harbor-task/test-patch.d.ts.map +1 -0
- package/dist/harbor-task/test-patch.js +15 -0
- package/dist/harbor-task/test-patch.js.map +1 -0
- package/dist/harbor-task/verifier.d.ts +4 -0
- package/dist/harbor-task/verifier.d.ts.map +1 -0
- package/dist/harbor-task/verifier.js +105 -0
- package/dist/harbor-task/verifier.js.map +1 -0
- package/dist/harbor-task.d.ts +3 -11
- package/dist/harbor-task.d.ts.map +1 -1
- package/dist/harbor-task.js +2 -463
- package/dist/harbor-task.js.map +1 -1
- package/dist/log-excerpt.d.ts +15 -0
- package/dist/log-excerpt.d.ts.map +1 -0
- package/dist/log-excerpt.js +104 -0
- package/dist/log-excerpt.js.map +1 -0
- package/dist/patch-check.d.ts +26 -0
- package/dist/patch-check.d.ts.map +1 -0
- package/dist/patch-check.js +137 -0
- package/dist/patch-check.js.map +1 -0
- package/dist/pi-event-feed.d.ts +16 -0
- package/dist/pi-event-feed.d.ts.map +1 -0
- package/dist/pi-event-feed.js +86 -0
- package/dist/pi-event-feed.js.map +1 -0
- package/dist/pi-session.d.ts +32 -0
- package/dist/pi-session.d.ts.map +1 -0
- package/dist/pi-session.js +175 -0
- package/dist/pi-session.js.map +1 -0
- package/dist/process.d.ts +5 -0
- package/dist/process.d.ts.map +1 -1
- package/dist/process.js +31 -9
- package/dist/process.js.map +1 -1
- package/dist/provenance/github.d.ts +4 -0
- package/dist/provenance/github.d.ts.map +1 -0
- package/dist/provenance/github.js +65 -0
- package/dist/provenance/github.js.map +1 -0
- package/dist/provenance/local.d.ts +4 -0
- package/dist/provenance/local.d.ts.map +1 -0
- package/dist/provenance/local.js +82 -0
- package/dist/provenance/local.js.map +1 -0
- package/dist/provenance/redact.d.ts +2 -0
- package/dist/provenance/redact.d.ts.map +1 -0
- package/dist/provenance/redact.js +28 -0
- package/dist/provenance/redact.js.map +1 -0
- package/dist/provenance/selection.d.ts +4 -0
- package/dist/provenance/selection.d.ts.map +1 -0
- package/dist/provenance/selection.js +29 -0
- package/dist/provenance/selection.js.map +1 -0
- package/dist/provenance/session.d.ts +3 -0
- package/dist/provenance/session.d.ts.map +1 -0
- package/dist/provenance/session.js +214 -0
- package/dist/provenance/session.js.map +1 -0
- package/dist/provenance/shared.d.ts +7 -0
- package/dist/provenance/shared.d.ts.map +1 -0
- package/dist/provenance/shared.js +10 -0
- package/dist/provenance/shared.js.map +1 -0
- package/dist/provenance/types.d.ts +34 -0
- package/dist/provenance/types.d.ts.map +1 -0
- package/dist/provenance/types.js +22 -0
- package/dist/provenance/types.js.map +1 -0
- package/dist/provenance-associations/apply.d.ts +3 -0
- package/dist/provenance-associations/apply.d.ts.map +1 -0
- package/dist/provenance-associations/apply.js +66 -0
- package/dist/provenance-associations/apply.js.map +1 -0
- package/dist/provenance-associations/shared.d.ts +45 -0
- package/dist/provenance-associations/shared.d.ts.map +1 -0
- package/dist/provenance-associations/shared.js +42 -0
- package/dist/provenance-associations/shared.js.map +1 -0
- package/dist/provenance-associations.d.ts +3 -30
- package/dist/provenance-associations.d.ts.map +1 -1
- package/dist/provenance-associations.js +4 -103
- package/dist/provenance-associations.js.map +1 -1
- package/dist/provenance.d.ts +7 -41
- package/dist/provenance.d.ts.map +1 -1
- package/dist/provenance.js +6 -432
- package/dist/provenance.js.map +1 -1
- package/dist/providers.d.ts +25 -2
- package/dist/providers.d.ts.map +1 -1
- package/dist/providers.js +23 -2
- package/dist/providers.js.map +1 -1
- package/dist/repair.d.ts +1 -6
- package/dist/repair.d.ts.map +1 -1
- package/dist/repair.js +17 -27
- package/dist/repair.js.map +1 -1
- package/dist/review/assets/index-BHHztQ9x.js +1679 -0
- package/dist/review/assets/index-KQ1eFQ0t.css +1 -0
- package/dist/review/index.html +11 -8
- package/dist/runtime/command.sh +26 -0
- package/dist/runtime/junit.py +69 -0
- package/dist/sandbox/contracts.d.ts +36 -1
- package/dist/sandbox/contracts.d.ts.map +1 -1
- package/dist/sandbox/contracts.js +3 -0
- package/dist/sandbox/contracts.js.map +1 -1
- package/dist/sandbox/index.d.ts +1 -1
- package/dist/sandbox/index.d.ts.map +1 -1
- package/dist/sandbox/index.js +13 -2
- package/dist/sandbox/index.js.map +1 -1
- package/dist/sandbox/live.d.ts +18 -0
- package/dist/sandbox/live.d.ts.map +1 -0
- package/dist/sandbox/live.js +55 -0
- package/dist/sandbox/live.js.map +1 -0
- package/dist/sandbox/output-retry.d.ts +16 -0
- package/dist/sandbox/output-retry.d.ts.map +1 -0
- package/dist/sandbox/output-retry.js +36 -0
- package/dist/sandbox/output-retry.js.map +1 -0
- package/dist/sandbox/programs/author.js +16 -6
- package/dist/sandbox/programs/author.js.map +1 -1
- package/dist/sandbox/programs/check.d.ts +3 -0
- package/dist/sandbox/programs/check.d.ts.map +1 -0
- package/dist/sandbox/programs/check.js +76 -0
- package/dist/sandbox/programs/check.js.map +1 -0
- package/dist/sandbox/programs/prepare-task.d.ts +12 -0
- package/dist/sandbox/programs/prepare-task.d.ts.map +1 -0
- package/dist/sandbox/programs/{prepare-repair.js → prepare-task.js} +11 -9
- package/dist/sandbox/programs/prepare-task.js.map +1 -0
- package/dist/sandbox/programs/verifier.d.ts +3 -0
- package/dist/sandbox/programs/verifier.d.ts.map +1 -0
- package/dist/sandbox/programs/verifier.js +9 -0
- package/dist/sandbox/programs/verifier.js.map +1 -0
- package/dist/sandbox/providers/docker/executor.d.ts +4 -1
- package/dist/sandbox/providers/docker/executor.d.ts.map +1 -1
- package/dist/sandbox/providers/docker/executor.js +75 -25
- package/dist/sandbox/providers/docker/executor.js.map +1 -1
- package/dist/sandbox/providers/e2b/bytes.d.ts +3 -0
- package/dist/sandbox/providers/e2b/bytes.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/bytes.js +8 -0
- package/dist/sandbox/providers/e2b/bytes.js.map +1 -0
- package/dist/sandbox/providers/e2b/cleanup.d.ts +8 -0
- package/dist/sandbox/providers/e2b/cleanup.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/cleanup.js +124 -0
- package/dist/sandbox/providers/e2b/cleanup.js.map +1 -0
- package/dist/sandbox/providers/e2b/command.d.ts +23 -0
- package/dist/sandbox/providers/e2b/command.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/command.js +160 -0
- package/dist/sandbox/providers/e2b/command.js.map +1 -0
- package/dist/sandbox/providers/e2b/config.d.ts +13 -0
- package/dist/sandbox/providers/e2b/config.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/config.js +2 -0
- package/dist/sandbox/providers/e2b/config.js.map +1 -0
- package/dist/sandbox/providers/e2b/executor.d.ts +15 -0
- package/dist/sandbox/providers/e2b/executor.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/executor.js +207 -0
- package/dist/sandbox/providers/e2b/executor.js.map +1 -0
- package/dist/sandbox/providers/e2b/lifecycle.d.ts +8 -0
- package/dist/sandbox/providers/e2b/lifecycle.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/lifecycle.js +37 -0
- package/dist/sandbox/providers/e2b/lifecycle.js.map +1 -0
- package/dist/sandbox/providers/e2b/outcome.d.ts +11 -0
- package/dist/sandbox/providers/e2b/outcome.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/outcome.js +72 -0
- package/dist/sandbox/providers/e2b/outcome.js.map +1 -0
- package/dist/sandbox/providers/e2b/stage-files.d.ts +10 -0
- package/dist/sandbox/providers/e2b/stage-files.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/stage-files.js +45 -0
- package/dist/sandbox/providers/e2b/stage-files.js.map +1 -0
- package/dist/sandbox/providers/e2b/startup.d.ts +10 -0
- package/dist/sandbox/providers/e2b/startup.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/startup.js +26 -0
- package/dist/sandbox/providers/e2b/startup.js.map +1 -0
- package/dist/sandbox/providers/e2b/types.d.ts +9 -0
- package/dist/sandbox/providers/e2b/types.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/types.js +2 -0
- package/dist/sandbox/providers/e2b/types.js.map +1 -0
- package/dist/sandbox/providers/e2b/validation.d.ts +14 -0
- package/dist/sandbox/providers/e2b/validation.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/validation.js +60 -0
- package/dist/sandbox/providers/e2b/validation.js.map +1 -0
- package/dist/{modal-auth.d.ts → sandbox/providers/modal/auth.d.ts} +1 -1
- package/dist/sandbox/providers/modal/auth.d.ts.map +1 -0
- package/dist/{modal-auth.js → sandbox/providers/modal/auth.js} +1 -1
- package/dist/sandbox/providers/modal/auth.js.map +1 -0
- package/dist/sandbox/providers/modal/executor.d.ts +4 -1
- package/dist/sandbox/providers/modal/executor.d.ts.map +1 -1
- package/dist/sandbox/providers/modal/executor.js +33 -9
- package/dist/sandbox/providers/modal/executor.js.map +1 -1
- package/dist/sandbox/providers/modal/live.d.ts +7 -0
- package/dist/sandbox/providers/modal/live.d.ts.map +1 -0
- package/dist/sandbox/providers/modal/live.js +50 -0
- package/dist/sandbox/providers/modal/live.js.map +1 -0
- package/dist/sandbox/providers/vercel/command.d.ts +6 -0
- package/dist/sandbox/providers/vercel/command.d.ts.map +1 -1
- package/dist/sandbox/providers/vercel/command.js +44 -11
- package/dist/sandbox/providers/vercel/command.js.map +1 -1
- package/dist/sandbox/providers/vercel/executor.d.ts +6 -7
- package/dist/sandbox/providers/vercel/executor.d.ts.map +1 -1
- package/dist/sandbox/providers/vercel/executor.js +21 -187
- package/dist/sandbox/providers/vercel/executor.js.map +1 -1
- package/dist/sandbox/providers/vercel/lifecycle.d.ts +13 -0
- package/dist/sandbox/providers/vercel/lifecycle.d.ts.map +1 -0
- package/dist/sandbox/providers/vercel/lifecycle.js +140 -0
- package/dist/sandbox/providers/vercel/lifecycle.js.map +1 -0
- package/dist/sandbox/providers/vercel/validation.d.ts +11 -0
- package/dist/sandbox/providers/vercel/validation.d.ts.map +1 -0
- package/dist/sandbox/providers/vercel/validation.js +30 -0
- package/dist/sandbox/providers/vercel/validation.js.map +1 -0
- package/dist/sandbox/remote-files.d.ts +11 -0
- package/dist/sandbox/remote-files.d.ts.map +1 -0
- package/dist/sandbox/remote-files.js +41 -0
- package/dist/sandbox/remote-files.js.map +1 -0
- package/dist/sandbox/request-validation.d.ts +5 -0
- package/dist/sandbox/request-validation.d.ts.map +1 -0
- package/dist/sandbox/request-validation.js +43 -0
- package/dist/sandbox/request-validation.js.map +1 -0
- package/dist/sandbox/supervisor.d.ts +42 -0
- package/dist/sandbox/supervisor.d.ts.map +1 -0
- package/dist/sandbox/supervisor.js +126 -0
- package/dist/sandbox/supervisor.js.map +1 -0
- package/dist/sandbox/timeout.d.ts +6 -1
- package/dist/sandbox/timeout.d.ts.map +1 -1
- package/dist/sandbox/timeout.js +12 -0
- package/dist/sandbox/timeout.js.map +1 -1
- package/dist/sandbox-author.bundle.js +47 -14879
- package/dist/{sandbox-validation-repair.bundle.js → sandbox-check.bundle.js} +7261 -1893
- package/dist/sandbox-verifier.bundle.js +307 -0
- package/dist/setup/e2b/build.d.ts +24 -0
- package/dist/setup/e2b/build.d.ts.map +1 -0
- package/dist/setup/e2b/build.js +46 -0
- package/dist/setup/e2b/build.js.map +1 -0
- package/dist/setup/e2b/cli.d.ts +2 -0
- package/dist/setup/e2b/cli.d.ts.map +1 -0
- package/dist/setup/e2b/cli.js +51 -0
- package/dist/setup/e2b/cli.js.map +1 -0
- package/dist/setup/e2b/index.d.ts +5 -0
- package/dist/setup/e2b/index.d.ts.map +1 -0
- package/dist/setup/e2b/index.js +4 -0
- package/dist/setup/e2b/index.js.map +1 -0
- package/dist/setup/e2b/template.d.ts +4 -0
- package/dist/setup/e2b/template.d.ts.map +1 -0
- package/dist/setup/e2b/template.js +53 -0
- package/dist/setup/e2b/template.js.map +1 -0
- package/dist/setup/vercel/cli-helpers.d.ts +22 -0
- package/dist/setup/vercel/cli-helpers.d.ts.map +1 -0
- package/dist/setup/vercel/cli-helpers.js +87 -0
- package/dist/setup/vercel/cli-helpers.js.map +1 -0
- package/dist/setup/vercel/cli-runner.d.ts +14 -0
- package/dist/setup/vercel/cli-runner.d.ts.map +1 -0
- package/dist/setup/vercel/cli-runner.js +24 -0
- package/dist/setup/vercel/cli-runner.js.map +1 -0
- package/dist/setup/vercel/cli-types.d.ts +24 -0
- package/dist/setup/vercel/cli-types.d.ts.map +1 -0
- package/dist/setup/vercel/cli-types.js +18 -0
- package/dist/setup/vercel/cli-types.js.map +1 -0
- package/dist/setup/vercel/cli.d.ts +5 -31
- package/dist/setup/vercel/cli.d.ts.map +1 -1
- package/dist/setup/vercel/cli.js +15 -125
- package/dist/setup/vercel/cli.js.map +1 -1
- package/dist/setup/vercel/profile-files.d.ts +6 -0
- package/dist/setup/vercel/profile-files.d.ts.map +1 -0
- package/dist/setup/vercel/profile-files.js +100 -0
- package/dist/setup/vercel/profile-files.js.map +1 -0
- package/dist/setup/vercel/profile-schema.d.ts +48 -0
- package/dist/setup/vercel/profile-schema.d.ts.map +1 -0
- package/dist/setup/vercel/profile-schema.js +39 -0
- package/dist/setup/vercel/profile-schema.js.map +1 -0
- package/dist/setup/vercel/profile.d.ts +3 -19
- package/dist/setup/vercel/profile.d.ts.map +1 -1
- package/dist/setup/vercel/profile.js +4 -130
- package/dist/setup/vercel/profile.js.map +1 -1
- package/dist/setup/vercel/selection.d.ts +18 -0
- package/dist/setup/vercel/selection.d.ts.map +1 -0
- package/dist/setup/vercel/selection.js +113 -0
- package/dist/setup/vercel/selection.js.map +1 -0
- package/dist/setup/vercel/setup-types.d.ts +34 -0
- package/dist/setup/vercel/setup-types.d.ts.map +1 -0
- package/dist/setup/vercel/setup-types.js +2 -0
- package/dist/setup/vercel/setup-types.js.map +1 -0
- package/dist/setup/vercel/setup.d.ts +3 -28
- package/dist/setup/vercel/setup.d.ts.map +1 -1
- package/dist/setup/vercel/setup.js +3 -111
- package/dist/setup/vercel/setup.js.map +1 -1
- package/dist/site/batch-activity.d.ts +5 -0
- package/dist/site/batch-activity.d.ts.map +1 -0
- package/dist/site/batch-activity.js +31 -0
- package/dist/site/batch-activity.js.map +1 -0
- package/dist/site/batch-progress.d.ts +16 -0
- package/dist/site/batch-progress.d.ts.map +1 -0
- package/dist/site/batch-progress.js +52 -0
- package/dist/site/batch-progress.js.map +1 -0
- package/dist/site/batch-routes.d.ts +30 -0
- package/dist/site/batch-routes.d.ts.map +1 -0
- package/dist/site/batch-routes.js +117 -0
- package/dist/site/batch-routes.js.map +1 -0
- package/dist/site/batch-start.d.ts +60 -0
- package/dist/site/batch-start.d.ts.map +1 -0
- package/dist/site/batch-start.js +39 -0
- package/dist/site/batch-start.js.map +1 -0
- package/dist/site/connected-repos.d.ts +25 -0
- package/dist/site/connected-repos.d.ts.map +1 -0
- package/dist/site/connected-repos.js +109 -0
- package/dist/site/connected-repos.js.map +1 -0
- package/dist/site/evaluation-start.d.ts +4 -0
- package/dist/site/evaluation-start.d.ts.map +1 -0
- package/dist/site/evaluation-start.js +19 -0
- package/dist/site/evaluation-start.js.map +1 -0
- package/dist/site/generation-config.d.ts +4 -0
- package/dist/site/generation-config.d.ts.map +1 -0
- package/dist/site/generation-config.js +16 -0
- package/dist/site/generation-config.js.map +1 -0
- package/dist/site/generation-credentials.d.ts +6 -0
- package/dist/site/generation-credentials.d.ts.map +1 -0
- package/dist/site/generation-credentials.js +101 -0
- package/dist/site/generation-credentials.js.map +1 -0
- package/dist/site/generation-run.d.ts +6 -0
- package/dist/site/generation-run.d.ts.map +1 -0
- package/dist/site/generation-run.js +22 -0
- package/dist/site/generation-run.js.map +1 -0
- package/dist/site/generation-settings.d.ts +80 -0
- package/dist/site/generation-settings.d.ts.map +1 -0
- package/dist/site/generation-settings.js +84 -0
- package/dist/site/generation-settings.js.map +1 -0
- package/dist/site/generation-subscription.d.ts +3 -0
- package/dist/site/generation-subscription.d.ts.map +1 -0
- package/dist/site/generation-subscription.js +38 -0
- package/dist/site/generation-subscription.js.map +1 -0
- package/dist/site/github-repos.d.ts +35 -0
- package/dist/site/github-repos.d.ts.map +1 -0
- package/dist/site/github-repos.js +121 -0
- package/dist/site/github-repos.js.map +1 -0
- package/dist/site/pr-candidate.d.ts +26 -0
- package/dist/site/pr-candidate.d.ts.map +1 -0
- package/dist/site/pr-candidate.js +101 -0
- package/dist/site/pr-candidate.js.map +1 -0
- package/dist/site/pr-list.d.ts +13 -0
- package/dist/site/pr-list.d.ts.map +1 -0
- package/dist/site/pr-list.js +24 -0
- package/dist/site/pr-list.js.map +1 -0
- package/dist/site/pr-routes.d.ts +26 -0
- package/dist/site/pr-routes.d.ts.map +1 -0
- package/dist/site/pr-routes.js +139 -0
- package/dist/site/pr-routes.js.map +1 -0
- package/dist/site/repo-store.d.ts +40 -0
- package/dist/site/repo-store.d.ts.map +1 -0
- package/dist/site/repo-store.js +74 -0
- package/dist/site/repo-store.js.map +1 -0
- package/dist/site/run-store.d.ts +17 -0
- package/dist/site/run-store.d.ts.map +1 -0
- package/dist/site/run-store.js +42 -0
- package/dist/site/run-store.js.map +1 -0
- package/dist/site/runtime.d.ts +27 -0
- package/dist/site/runtime.d.ts.map +1 -0
- package/dist/site/runtime.js +97 -0
- package/dist/site/runtime.js.map +1 -0
- package/dist/site/task-deletion.d.ts +7 -0
- package/dist/site/task-deletion.d.ts.map +1 -0
- package/dist/site/task-deletion.js +29 -0
- package/dist/site/task-deletion.js.map +1 -0
- package/dist/site/task-start-reservation.d.ts +4 -0
- package/dist/site/task-start-reservation.d.ts.map +1 -0
- package/dist/site/task-start-reservation.js +18 -0
- package/dist/site/task-start-reservation.js.map +1 -0
- package/dist/site/task-start.d.ts +33 -0
- package/dist/site/task-start.d.ts.map +1 -0
- package/dist/site/task-start.js +50 -0
- package/dist/site/task-start.js.map +1 -0
- package/dist/site/task-status.d.ts +36 -0
- package/dist/site/task-status.d.ts.map +1 -0
- package/dist/site/task-status.js +113 -0
- package/dist/site/task-status.js.map +1 -0
- package/dist/site/task-store.d.ts +78 -0
- package/dist/site/task-store.d.ts.map +1 -0
- package/dist/site/task-store.js +186 -0
- package/dist/site/task-store.js.map +1 -0
- package/dist/site/task-sync.d.ts +30 -0
- package/dist/site/task-sync.d.ts.map +1 -0
- package/dist/site/task-sync.js +121 -0
- package/dist/site/task-sync.js.map +1 -0
- package/dist/site/tasks.d.ts +47 -0
- package/dist/site/tasks.d.ts.map +1 -0
- package/dist/site/tasks.js +164 -0
- package/dist/site/tasks.js.map +1 -0
- package/dist/site/temporal-status.d.ts +8 -0
- package/dist/site/temporal-status.d.ts.map +1 -0
- package/dist/site/temporal-status.js +41 -0
- package/dist/site/temporal-status.js.map +1 -0
- package/dist/site/tenant.d.ts +4 -0
- package/dist/site/tenant.d.ts.map +1 -0
- package/dist/site/tenant.js +6 -0
- package/dist/site/tenant.js.map +1 -0
- package/dist/static-check.d.ts +38 -0
- package/dist/static-check.d.ts.map +1 -0
- package/dist/static-check.js +131 -0
- package/dist/static-check.js.map +1 -0
- package/dist/submission-hash.d.ts +18 -0
- package/dist/submission-hash.d.ts.map +1 -0
- package/dist/submission-hash.js +16 -0
- package/dist/submission-hash.js.map +1 -0
- package/dist/subscription-auth.d.ts +0 -7
- package/dist/subscription-auth.d.ts.map +1 -1
- package/dist/subscription-auth.js +3 -23
- package/dist/subscription-auth.js.map +1 -1
- package/dist/temporal/activities/agent-feed.d.ts +5 -0
- package/dist/temporal/activities/agent-feed.d.ts.map +1 -0
- package/dist/temporal/activities/agent-feed.js +41 -0
- package/dist/temporal/activities/agent-feed.js.map +1 -0
- package/dist/temporal/activities/agent-scripts.d.ts +16 -0
- package/dist/temporal/activities/agent-scripts.d.ts.map +1 -0
- package/dist/temporal/activities/agent-scripts.js +162 -0
- package/dist/temporal/activities/agent-scripts.js.map +1 -0
- package/dist/temporal/activities/authoring-round.d.ts +13 -0
- package/dist/temporal/activities/authoring-round.d.ts.map +1 -0
- package/dist/temporal/activities/authoring-round.js +160 -0
- package/dist/temporal/activities/authoring-round.js.map +1 -0
- package/dist/temporal/activities/constants.d.ts +5 -0
- package/dist/temporal/activities/constants.d.ts.map +1 -0
- package/dist/temporal/activities/constants.js +5 -0
- package/dist/temporal/activities/constants.js.map +1 -0
- package/dist/temporal/activities/discovery.d.ts +17 -0
- package/dist/temporal/activities/discovery.d.ts.map +1 -0
- package/dist/temporal/activities/discovery.js +153 -0
- package/dist/temporal/activities/discovery.js.map +1 -0
- package/dist/temporal/activities/drafts.d.ts +15 -0
- package/dist/temporal/activities/drafts.d.ts.map +1 -0
- package/dist/temporal/activities/drafts.js +51 -0
- package/dist/temporal/activities/drafts.js.map +1 -0
- package/dist/temporal/activities/excluded-source-prs.d.ts +9 -0
- package/dist/temporal/activities/excluded-source-prs.d.ts.map +1 -0
- package/dist/temporal/activities/excluded-source-prs.js +132 -0
- package/dist/temporal/activities/excluded-source-prs.js.map +1 -0
- package/dist/temporal/activities/export.d.ts +38 -0
- package/dist/temporal/activities/export.d.ts.map +1 -0
- package/dist/temporal/activities/export.js +79 -0
- package/dist/temporal/activities/export.js.map +1 -0
- package/dist/temporal/activities/factory.d.ts +5 -0
- package/dist/temporal/activities/factory.d.ts.map +1 -0
- package/dist/temporal/activities/factory.js +26 -0
- package/dist/temporal/activities/factory.js.map +1 -0
- package/dist/temporal/activities/gate-logs.d.ts +20 -0
- package/dist/temporal/activities/gate-logs.d.ts.map +1 -0
- package/dist/temporal/activities/gate-logs.js +62 -0
- package/dist/temporal/activities/gate-logs.js.map +1 -0
- package/dist/temporal/activities/generation-runtime.d.ts +6 -0
- package/dist/temporal/activities/generation-runtime.d.ts.map +1 -0
- package/dist/temporal/activities/generation-runtime.js +56 -0
- package/dist/temporal/activities/generation-runtime.js.map +1 -0
- package/dist/temporal/activities/harbor.d.ts +11 -0
- package/dist/temporal/activities/harbor.d.ts.map +1 -0
- package/dist/temporal/activities/harbor.js +112 -0
- package/dist/temporal/activities/harbor.js.map +1 -0
- package/dist/temporal/activities/modal-build-log.d.ts +12 -0
- package/dist/temporal/activities/modal-build-log.d.ts.map +1 -0
- package/dist/temporal/activities/modal-build-log.js +57 -0
- package/dist/temporal/activities/modal-build-log.js.map +1 -0
- package/dist/temporal/activities/prompts-authoring.d.ts +6 -0
- package/dist/temporal/activities/prompts-authoring.d.ts.map +1 -0
- package/dist/temporal/activities/prompts-authoring.js +87 -0
- package/dist/temporal/activities/prompts-authoring.js.map +1 -0
- package/dist/temporal/activities/prompts-verifier.d.ts +17 -0
- package/dist/temporal/activities/prompts-verifier.d.ts.map +1 -0
- package/dist/temporal/activities/prompts-verifier.js +66 -0
- package/dist/temporal/activities/prompts-verifier.js.map +1 -0
- package/dist/temporal/activities/provenance.d.ts +4 -0
- package/dist/temporal/activities/provenance.d.ts.map +1 -0
- package/dist/temporal/activities/provenance.js +18 -0
- package/dist/temporal/activities/provenance.js.map +1 -0
- package/dist/temporal/activities/replay.d.ts +20 -0
- package/dist/temporal/activities/replay.d.ts.map +1 -0
- package/dist/temporal/activities/replay.js +135 -0
- package/dist/temporal/activities/replay.js.map +1 -0
- package/dist/temporal/activities/round-outcome.d.ts +63 -0
- package/dist/temporal/activities/round-outcome.d.ts.map +1 -0
- package/dist/temporal/activities/round-outcome.js +127 -0
- package/dist/temporal/activities/round-outcome.js.map +1 -0
- package/dist/temporal/activities/runtime.d.ts +38 -0
- package/dist/temporal/activities/runtime.d.ts.map +1 -0
- package/dist/temporal/activities/runtime.js +146 -0
- package/dist/temporal/activities/runtime.js.map +1 -0
- package/dist/temporal/activities/session-verify.d.ts +45 -0
- package/dist/temporal/activities/session-verify.d.ts.map +1 -0
- package/dist/temporal/activities/session-verify.js +91 -0
- package/dist/temporal/activities/session-verify.js.map +1 -0
- package/dist/temporal/activities/submissions.d.ts +9 -0
- package/dist/temporal/activities/submissions.d.ts.map +1 -0
- package/dist/temporal/activities/submissions.js +28 -0
- package/dist/temporal/activities/submissions.js.map +1 -0
- package/dist/temporal/activities/task-compiler.d.ts +21 -0
- package/dist/temporal/activities/task-compiler.d.ts.map +1 -0
- package/dist/temporal/activities/task-compiler.js +63 -0
- package/dist/temporal/activities/task-compiler.js.map +1 -0
- package/dist/temporal/activities/types.d.ts +57 -0
- package/dist/temporal/activities/types.d.ts.map +1 -0
- package/dist/temporal/activities/types.js +2 -0
- package/dist/temporal/activities/types.js.map +1 -0
- package/dist/temporal/activities/verifier-material.d.ts +18 -0
- package/dist/temporal/activities/verifier-material.d.ts.map +1 -0
- package/dist/temporal/activities/verifier-material.js +49 -0
- package/dist/temporal/activities/verifier-material.js.map +1 -0
- package/dist/temporal/activities/verifier-outcome.d.ts +19 -0
- package/dist/temporal/activities/verifier-outcome.d.ts.map +1 -0
- package/dist/temporal/activities/verifier-outcome.js +70 -0
- package/dist/temporal/activities/verifier-outcome.js.map +1 -0
- package/dist/temporal/activities/verifier-round.d.ts +8 -0
- package/dist/temporal/activities/verifier-round.d.ts.map +1 -0
- package/dist/temporal/activities/verifier-round.js +110 -0
- package/dist/temporal/activities/verifier-round.js.map +1 -0
- package/dist/temporal/activities/verify-harbor.d.ts +15 -0
- package/dist/temporal/activities/verify-harbor.d.ts.map +1 -0
- package/dist/temporal/activities/verify-harbor.js +193 -0
- package/dist/temporal/activities/verify-harbor.js.map +1 -0
- package/dist/temporal/activities/verify.d.ts +11 -0
- package/dist/temporal/activities/verify.d.ts.map +1 -0
- package/dist/temporal/activities/verify.js +151 -0
- package/dist/temporal/activities/verify.js.map +1 -0
- package/dist/temporal/activities.d.ts +3 -51
- package/dist/temporal/activities.d.ts.map +1 -1
- package/dist/temporal/activities.js +2 -886
- package/dist/temporal/activities.js.map +1 -1
- package/dist/temporal/connection.d.ts.map +1 -1
- package/dist/temporal/connection.js +3 -2
- package/dist/temporal/connection.js.map +1 -1
- package/dist/temporal/worker-main.js +19 -3
- package/dist/temporal/worker-main.js.map +1 -1
- package/dist/temporal/workflow/activity-proxies.d.ts +3 -0
- package/dist/temporal/workflow/activity-proxies.d.ts.map +1 -0
- package/dist/temporal/workflow/activity-proxies.js +45 -0
- package/dist/temporal/workflow/activity-proxies.js.map +1 -0
- package/dist/temporal/workflow/authoring-stage.d.ts +5 -0
- package/dist/temporal/workflow/authoring-stage.d.ts.map +1 -0
- package/dist/temporal/workflow/authoring-stage.js +64 -0
- package/dist/temporal/workflow/authoring-stage.js.map +1 -0
- package/dist/temporal/workflow/candidate-tracker.d.ts +28 -0
- package/dist/temporal/workflow/candidate-tracker.d.ts.map +1 -0
- package/dist/temporal/workflow/candidate-tracker.js +85 -0
- package/dist/temporal/workflow/candidate-tracker.js.map +1 -0
- package/dist/temporal/workflow/candidate.d.ts +6 -0
- package/dist/temporal/workflow/candidate.d.ts.map +1 -0
- package/dist/temporal/workflow/candidate.js +54 -0
- package/dist/temporal/workflow/candidate.js.map +1 -0
- package/dist/temporal/workflow/discovery.d.ts +19 -0
- package/dist/temporal/workflow/discovery.d.ts.map +1 -0
- package/dist/temporal/workflow/discovery.js +137 -0
- package/dist/temporal/workflow/discovery.js.map +1 -0
- package/dist/temporal/workflow/failures.d.ts +5 -0
- package/dist/temporal/workflow/failures.d.ts.map +1 -0
- package/dist/temporal/workflow/failures.js +28 -0
- package/dist/temporal/workflow/failures.js.map +1 -0
- package/dist/temporal/workflow/run.d.ts +5 -0
- package/dist/temporal/workflow/run.d.ts.map +1 -0
- package/dist/temporal/workflow/run.js +154 -0
- package/dist/temporal/workflow/run.js.map +1 -0
- package/dist/temporal/workflow/stage.d.ts +26 -0
- package/dist/temporal/workflow/stage.d.ts.map +1 -0
- package/dist/temporal/workflow/stage.js +16 -0
- package/dist/temporal/workflow/stage.js.map +1 -0
- package/dist/temporal/workflow/verification-stage.d.ts +11 -0
- package/dist/temporal/workflow/verification-stage.d.ts.map +1 -0
- package/dist/temporal/workflow/verification-stage.js +20 -0
- package/dist/temporal/workflow/verification-stage.js.map +1 -0
- package/dist/temporal/workflow.d.ts +12 -4
- package/dist/temporal/workflow.d.ts.map +1 -1
- package/dist/temporal/workflow.js +38 -445
- package/dist/temporal/workflow.js.map +1 -1
- package/dist/verifier-fix.d.ts +20 -0
- package/dist/verifier-fix.d.ts.map +1 -0
- package/dist/verifier-fix.js +62 -0
- package/dist/verifier-fix.js.map +1 -0
- package/dist/verify-report.d.ts +9 -0
- package/dist/verify-report.d.ts.map +1 -0
- package/dist/verify-report.js +135 -0
- package/dist/verify-report.js.map +1 -0
- package/dist/viewer/archived-keys.d.ts +9 -0
- package/dist/viewer/archived-keys.d.ts.map +1 -0
- package/dist/viewer/archived-keys.js +36 -0
- package/dist/viewer/archived-keys.js.map +1 -0
- package/dist/viewer/archived.d.ts +20 -0
- package/dist/viewer/archived.d.ts.map +1 -0
- package/dist/viewer/archived.js +238 -0
- package/dist/viewer/archived.js.map +1 -0
- package/dist/viewer/artifacts.d.ts +8 -0
- package/dist/viewer/artifacts.d.ts.map +1 -0
- package/dist/viewer/artifacts.js +96 -0
- package/dist/viewer/artifacts.js.map +1 -0
- package/dist/viewer/bundle.d.ts +9 -0
- package/dist/viewer/bundle.d.ts.map +1 -0
- package/dist/viewer/bundle.js +79 -0
- package/dist/viewer/bundle.js.map +1 -0
- package/dist/viewer/candidates.d.ts +9 -0
- package/dist/viewer/candidates.d.ts.map +1 -0
- package/dist/viewer/candidates.js +137 -0
- package/dist/viewer/candidates.js.map +1 -0
- package/dist/viewer/local-server.d.ts +11 -0
- package/dist/viewer/local-server.d.ts.map +1 -0
- package/dist/viewer/local-server.js +64 -0
- package/dist/viewer/local-server.js.map +1 -0
- package/dist/viewer/task-files.d.ts +10 -0
- package/dist/viewer/task-files.d.ts.map +1 -0
- package/dist/viewer/task-files.js +120 -0
- package/dist/viewer/task-files.js.map +1 -0
- package/dist/viewer/types.d.ts +78 -0
- package/dist/viewer/types.d.ts.map +1 -0
- package/dist/viewer/types.js +36 -0
- package/dist/viewer/types.js.map +1 -0
- package/docs/api.md +168 -0
- package/docs/evaluations.md +42 -15
- package/docs/operations.md +254 -26
- package/docs/solver-evaluations.md +63 -0
- package/docs/task-construction.md +21 -11
- package/drizzle/0000_glossy_johnny_blaze.sql +97 -0
- package/drizzle/0001_evaluation_records.sql +5 -0
- package/drizzle/0002_task_deletion.sql +1 -0
- package/drizzle/0003_drop_repo_runs.sql +3 -0
- package/drizzle/0004_preserve_batch_runs.sql +8 -0
- package/drizzle/0005_api_keys.sql +15 -0
- package/drizzle/meta/0000_snapshot.json +776 -0
- package/drizzle/meta/0001_snapshot.json +807 -0
- package/drizzle/meta/0002_snapshot.json +813 -0
- package/drizzle/meta/0003_snapshot.json +726 -0
- package/drizzle/meta/0004_snapshot.json +813 -0
- package/drizzle/meta/0005_snapshot.json +919 -0
- package/drizzle/meta/_journal.json +48 -0
- package/package.json +39 -25
- package/src/extensions/authoring.ts +83 -72
- package/src/extensions/shared/deliverable.ts +153 -0
- package/src/extensions/shared/mailbox.ts +128 -0
- package/src/extensions/shared/schemas.ts +101 -0
- package/src/extensions/shared/static-check.ts +103 -0
- package/src/extensions/verifier.ts +88 -0
- package/src/skills/selfbench/SKILL.md +71 -13
- package/biome.json +0 -24
- package/dist/agent-smoke-main.d.ts +0 -3
- package/dist/agent-smoke-main.d.ts.map +0 -1
- package/dist/agent-smoke-main.js +0 -55
- package/dist/agent-smoke-main.js.map +0 -1
- package/dist/agent-smoke.d.ts +0 -18
- package/dist/agent-smoke.d.ts.map +0 -1
- package/dist/agent-smoke.js +0 -103
- package/dist/agent-smoke.js.map +0 -1
- package/dist/codex-review.d.ts +0 -41
- package/dist/codex-review.d.ts.map +0 -1
- package/dist/codex-review.js +0 -193
- package/dist/codex-review.js.map +0 -1
- package/dist/eval-main.d.ts +0 -3
- package/dist/eval-main.d.ts.map +0 -1
- package/dist/eval-main.js +0 -81
- package/dist/eval-main.js.map +0 -1
- package/dist/evaluate.d.ts +0 -25
- package/dist/evaluate.d.ts.map +0 -1
- package/dist/evaluate.js +0 -214
- package/dist/evaluate.js.map +0 -1
- package/dist/modal-auth.d.ts.map +0 -1
- package/dist/modal-auth.js.map +0 -1
- package/dist/reaudit-main.d.ts +0 -3
- package/dist/reaudit-main.d.ts.map +0 -1
- package/dist/reaudit-main.js +0 -158
- package/dist/reaudit-main.js.map +0 -1
- package/dist/repair-main.d.ts +0 -3
- package/dist/repair-main.d.ts.map +0 -1
- package/dist/repair-main.js +0 -171
- package/dist/repair-main.js.map +0 -1
- package/dist/review/assets/index-CZ3G759O.js +0 -1568
- package/dist/review/assets/index-DgSLzX8l.css +0 -1
- package/dist/sandbox/programs/prepare-repair.d.ts +0 -7
- package/dist/sandbox/programs/prepare-repair.d.ts.map +0 -1
- package/dist/sandbox/programs/prepare-repair.js.map +0 -1
- package/dist/sandbox/programs/repair.d.ts +0 -3
- package/dist/sandbox/programs/repair.d.ts.map +0 -1
- package/dist/sandbox/programs/repair.js +0 -100
- package/dist/sandbox/programs/repair.js.map +0 -1
- package/dist/sandbox/programs/review.d.ts +0 -2
- package/dist/sandbox/programs/review.d.ts.map +0 -1
- package/dist/sandbox/programs/review.js +0 -18
- package/dist/sandbox/programs/review.js.map +0 -1
- package/dist/sandbox/programs/validation-repair.d.ts +0 -3
- package/dist/sandbox/programs/validation-repair.d.ts.map +0 -1
- package/dist/sandbox/programs/validation-repair.js +0 -115
- package/dist/sandbox/programs/validation-repair.js.map +0 -1
- package/dist/sandbox-repair.bundle.js +0 -323
- package/dist/sandbox-review.bundle.js +0 -14462
- package/dist/validate-main.d.ts +0 -3
- package/dist/validate-main.d.ts.map +0 -1
- package/dist/validate-main.js +0 -143
- package/dist/validate-main.js.map +0 -1
- package/dist/validation-repair.d.ts +0 -10
- package/dist/validation-repair.d.ts.map +0 -1
- package/dist/validation-repair.js +0 -72
- package/dist/validation-repair.js.map +0 -1
- package/review/index.html +0 -14
- package/review/src/App.tsx +0 -338
- package/review/src/export-loader.test.ts +0 -57
- package/review/src/export-loader.ts +0 -151
- package/review/src/main.tsx +0 -15
- package/review/src/styles.css +0 -162
- package/review/src/types.ts +0 -47
- package/review/tsconfig.json +0 -16
- package/review/vite.config.ts +0 -20
- package/scripts/build-sandbox-programs.ts +0 -22
- package/scripts/verify-package.ts +0 -102
- package/scripts/write-build-metadata.ts +0 -27
- package/src/agent-smoke-main.ts +0 -64
- package/src/agent-smoke.ts +0 -138
- package/src/api-main.ts +0 -12
- package/src/api.ts +0 -291
- package/src/artifacts.ts +0 -357
- package/src/audit.ts +0 -106
- package/src/build-metadata.ts +0 -3
- package/src/cli.ts +0 -504
- package/src/codex-review.ts +0 -229
- package/src/config.ts +0 -239
- package/src/contracts.ts +0 -233
- package/src/coupling.ts +0 -259
- package/src/eval-main.ts +0 -93
- package/src/evaluate.ts +0 -300
- package/src/github.ts +0 -26
- package/src/harbor-environment.ts +0 -17
- package/src/harbor-results.ts +0 -144
- package/src/harbor-task.ts +0 -533
- package/src/hash.ts +0 -5
- package/src/modal-auth.ts +0 -11
- package/src/parallel.ts +0 -24
- package/src/process.ts +0 -167
- package/src/project-paths.ts +0 -15
- package/src/provenance-associations.ts +0 -311
- package/src/provenance.ts +0 -561
- package/src/providers.ts +0 -22
- package/src/reaudit-main.ts +0 -198
- package/src/repair-main.ts +0 -209
- package/src/repair.ts +0 -55
- package/src/run-wait.ts +0 -40
- package/src/sandbox/contracts.ts +0 -52
- package/src/sandbox/index.ts +0 -23
- package/src/sandbox/programs/author.ts +0 -19
- package/src/sandbox/programs/prepare-repair.ts +0 -44
- package/src/sandbox/programs/repair.ts +0 -132
- package/src/sandbox/programs/review.ts +0 -19
- package/src/sandbox/programs/validation-repair.ts +0 -153
- package/src/sandbox/providers/docker/executor.ts +0 -115
- package/src/sandbox/providers/modal/executor.ts +0 -217
- package/src/sandbox/providers/vercel/command.ts +0 -127
- package/src/sandbox/providers/vercel/executor.ts +0 -448
- package/src/sandbox/providers/vercel/fetch.ts +0 -45
- package/src/sandbox/timeout.ts +0 -56
- package/src/setup/vercel/cli.ts +0 -403
- package/src/setup/vercel/index.ts +0 -3
- package/src/setup/vercel/probe.ts +0 -232
- package/src/setup/vercel/profile.ts +0 -322
- package/src/setup/vercel/runtime-image.ts +0 -204
- package/src/setup/vercel/setup.ts +0 -419
- package/src/subscription-auth.ts +0 -80
- package/src/temporal/activities.ts +0 -1348
- package/src/temporal/connection.ts +0 -23
- package/src/temporal/worker-main.ts +0 -28
- package/src/temporal/workflow.ts +0 -568
- package/src/terminal-prompts.ts +0 -197
- package/src/terminal-reporter.ts +0 -126
- package/src/validate-main.ts +0 -177
- package/src/validation-repair.ts +0 -94
- package/tsconfig.build.json +0 -13
- package/tsconfig.json +0 -21
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"runtime-assets.js","sourceRoot":"","sources":["../../src/harbor-task/runtime-assets.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,SAAS,CAAC;AAEvC,MAAM,UAAU,oBAAoB;IAClC,OAAO;QACL,oBAAoB,EAAE,YAAY,CAAC,IAAI,GAAG,CAAC,sBAAsB,EAAE,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,MAAM,CAAC;QAC5F,kBAAkB,EAAE,YAAY,CAAC,IAAI,GAAG,CAAC,oBAAoB,EAAE,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,MAAM,CAAC;KACzF,CAAC;AACJ,CAAC"}
|
|
@@ -0,0 +1,4 @@
|
|
|
1
|
+
import type { TaskDefinition } from "../contracts.js";
|
|
2
|
+
export declare function isBaseOnlyTestPatch(definition: TaskDefinition, patch: string): boolean;
|
|
3
|
+
export declare function assertTestPatch(definition: TaskDefinition, patch: string): void;
|
|
4
|
+
//# sourceMappingURL=test-patch.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"test-patch.d.ts","sourceRoot":"","sources":["../../src/harbor-task/test-patch.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAC;AAGtD,wBAAgB,mBAAmB,CAAC,UAAU,EAAE,cAAc,EAAE,KAAK,EAAE,MAAM,GAAG,OAAO,CAEtF;AAED,wBAAgB,eAAe,CAAC,UAAU,EAAE,cAAc,EAAE,KAAK,EAAE,MAAM,GAAG,IAAI,CAO/E"}
|
|
@@ -0,0 +1,15 @@
|
|
|
1
|
+
import { assertSafePatchPaths } from "./paths.js";
|
|
2
|
+
export function isBaseOnlyTestPatch(definition, patch) {
|
|
3
|
+
return definition.testSelection?.mode === "base-only" && patch === "";
|
|
4
|
+
}
|
|
5
|
+
export function assertTestPatch(definition, patch) {
|
|
6
|
+
if (isBaseOnlyTestPatch(definition, patch))
|
|
7
|
+
return;
|
|
8
|
+
if (definition.testSelection?.mode === "base-only") {
|
|
9
|
+
throw new Error("base-only requires an empty test.patch");
|
|
10
|
+
}
|
|
11
|
+
if (!patch.startsWith("diff --git "))
|
|
12
|
+
throw new Error("test.patch is not a Git patch");
|
|
13
|
+
assertSafePatchPaths(patch, "test patch");
|
|
14
|
+
}
|
|
15
|
+
//# sourceMappingURL=test-patch.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"test-patch.js","sourceRoot":"","sources":["../../src/harbor-task/test-patch.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,oBAAoB,EAAE,MAAM,YAAY,CAAC;AAElD,MAAM,UAAU,mBAAmB,CAAC,UAA0B,EAAE,KAAa;IAC3E,OAAO,UAAU,CAAC,aAAa,EAAE,IAAI,KAAK,WAAW,IAAI,KAAK,KAAK,EAAE,CAAC;AACxE,CAAC;AAED,MAAM,UAAU,eAAe,CAAC,UAA0B,EAAE,KAAa;IACvE,IAAI,mBAAmB,CAAC,UAAU,EAAE,KAAK,CAAC;QAAE,OAAO;IACnD,IAAI,UAAU,CAAC,aAAa,EAAE,IAAI,KAAK,WAAW,EAAE,CAAC;QACnD,MAAM,IAAI,KAAK,CAAC,wCAAwC,CAAC,CAAC;IAC5D,CAAC;IACD,IAAI,CAAC,KAAK,CAAC,UAAU,CAAC,aAAa,CAAC;QAAE,MAAM,IAAI,KAAK,CAAC,+BAA+B,CAAC,CAAC;IACvF,oBAAoB,CAAC,KAAK,EAAE,YAAY,CAAC,CAAC;AAC5C,CAAC"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"verifier.d.ts","sourceRoot":"","sources":["../../src/harbor-task/verifier.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAC;AAItD,wBAAgB,cAAc,IAAI,MAAM,CAKvC;AAED,wBAAgB,UAAU,CAAC,IAAI,EAAE,cAAc,EAAE,SAAS,EAAE,MAAM,GAAG,MAAM,CA4F1E"}
|
|
@@ -0,0 +1,105 @@
|
|
|
1
|
+
import { patchPaths } from "../repair.js";
|
|
2
|
+
import { repositoryRelativePath, shellQuote } from "./paths.js";
|
|
3
|
+
export function solutionScript() {
|
|
4
|
+
return `#!/bin/bash
|
|
5
|
+
set -euo pipefail
|
|
6
|
+
git -C /app apply --binary --whitespace=nowarn /solution/gold.patch
|
|
7
|
+
`;
|
|
8
|
+
}
|
|
9
|
+
export function testScript(task, testPatch) {
|
|
10
|
+
const repositoryTestPaths = [
|
|
11
|
+
...new Set([
|
|
12
|
+
...task.testPaths.map((path) => repositoryRelativePath(task, path)),
|
|
13
|
+
...patchPaths(testPatch),
|
|
14
|
+
]),
|
|
15
|
+
].sort();
|
|
16
|
+
const exclusions = repositoryTestPaths
|
|
17
|
+
.flatMap((path) => [
|
|
18
|
+
`--exclude=${shellQuote(path.replace(/\/$/, ""))}`,
|
|
19
|
+
`--exclude=${shellQuote(`${path.replace(/\/$/, "")}/*`)}`,
|
|
20
|
+
])
|
|
21
|
+
.join(" ");
|
|
22
|
+
const protectedPaths = repositoryTestPaths.map(shellQuote).join(" ");
|
|
23
|
+
const protectedAbsolute = repositoryTestPaths.map((path) => shellQuote(`/app/${path}`)).join(" ");
|
|
24
|
+
const structured = task.testResults;
|
|
25
|
+
const f2p = taskCommand(task, task.failToPass);
|
|
26
|
+
const p2p = task.passToPass.length > 0 ? taskCommand(task, task.passToPass) : "true";
|
|
27
|
+
return `#!/bin/bash
|
|
28
|
+
set -uo pipefail
|
|
29
|
+
mkdir -p /logs/verifier
|
|
30
|
+
source /opt/selfbench-runtime/command.sh
|
|
31
|
+
# Root steps after our Dockerfile can leave root-owned files in the verifier's caches.
|
|
32
|
+
chown -R verifier:verifier /home/verifier 2>/dev/null || true
|
|
33
|
+
patch_applied=1
|
|
34
|
+
fail_to_pass=0
|
|
35
|
+
pass_to_pass=0
|
|
36
|
+
deterministic=0
|
|
37
|
+
setup_completed=0
|
|
38
|
+
fail_to_pass_exit_code=-1
|
|
39
|
+
fail_to_pass_repeat_exit_code=-1
|
|
40
|
+
pass_to_pass_exit_code=-1
|
|
41
|
+
kill_verifier_processes() { pkill -KILL -u "$(id -u verifier)" 2>/dev/null || true; }
|
|
42
|
+
protect_held_out_path() {
|
|
43
|
+
local path="$1"
|
|
44
|
+
chown -R root:root -- "$path"
|
|
45
|
+
chmod -R a-w,go+rX -- "$path"
|
|
46
|
+
}
|
|
47
|
+
|
|
48
|
+
if [ ! -f /opt/selfbench/agent.patch ]; then
|
|
49
|
+
patch_applied=0
|
|
50
|
+
elif [ -s /opt/selfbench/agent.patch ]; then
|
|
51
|
+
git -C /app apply --binary --whitespace=nowarn ${exclusions} /opt/selfbench/agent.patch || patch_applied=0
|
|
52
|
+
fi
|
|
53
|
+
|
|
54
|
+
if [ "$patch_applied" -eq 1 ]; then setup_completed=1; fi
|
|
55
|
+
|
|
56
|
+
if [ "$patch_applied" -eq 1 ] && [ "$setup_completed" -eq 1 ]; then
|
|
57
|
+
kill_verifier_processes
|
|
58
|
+
for protected_path in ${protectedPaths}; do
|
|
59
|
+
git -C /app restore --source=HEAD --staged --worktree -- "$protected_path" 2>/dev/null || true
|
|
60
|
+
git -C /app clean -fd -- "$protected_path" >/dev/null 2>&1 || true
|
|
61
|
+
done
|
|
62
|
+
git -C /app apply --allow-empty --binary --whitespace=nowarn /tests/test.patch || patch_applied=0
|
|
63
|
+
if [ "$patch_applied" -eq 1 ]; then
|
|
64
|
+
for protected_path in ${protectedAbsolute}; do protect_held_out_path "$protected_path"; done
|
|
65
|
+
fi
|
|
66
|
+
rm -f /tests/test.patch
|
|
67
|
+
fi
|
|
68
|
+
|
|
69
|
+
if [ "$patch_applied" -eq 1 ] && [ "$setup_completed" -eq 1 ]; then
|
|
70
|
+
cd ${shellQuote(`/app/${task.workdir}`)}
|
|
71
|
+
if run_verifier_command ${shellQuote(f2p)} ${structured ? "junit" : "command"} ${shellQuote(JSON.stringify(structured?.failToPass ?? []))}; then
|
|
72
|
+
fail_to_pass_exit_code=0
|
|
73
|
+
fail_to_pass=1
|
|
74
|
+
if run_verifier_command ${shellQuote(f2p)} ${structured ? "junit" : "command"} ${shellQuote(JSON.stringify(structured?.failToPass ?? []))}; then
|
|
75
|
+
fail_to_pass_repeat_exit_code=0
|
|
76
|
+
deterministic=1
|
|
77
|
+
else
|
|
78
|
+
fail_to_pass_repeat_exit_code=$?
|
|
79
|
+
fi
|
|
80
|
+
else
|
|
81
|
+
fail_to_pass_exit_code=$?
|
|
82
|
+
fi
|
|
83
|
+
if [ "${task.passToPass.length}" -eq 0 ]; then
|
|
84
|
+
pass_to_pass_exit_code=0
|
|
85
|
+
pass_to_pass=1
|
|
86
|
+
elif run_verifier_command ${shellQuote(p2p)} ${structured ? "junit" : "command"} ${shellQuote(JSON.stringify(structured?.passToPass ?? []))}; then
|
|
87
|
+
pass_to_pass_exit_code=0
|
|
88
|
+
pass_to_pass=1
|
|
89
|
+
else
|
|
90
|
+
pass_to_pass_exit_code=$?
|
|
91
|
+
fi
|
|
92
|
+
fi
|
|
93
|
+
|
|
94
|
+
reward=0
|
|
95
|
+
if [ "$patch_applied" -eq 1 ] && [ "$fail_to_pass" -eq 1 ] && [ "$pass_to_pass" -eq 1 ] && [ "$deterministic" -eq 1 ]; then reward=1; fi
|
|
96
|
+
cat > /logs/verifier/reward.json <<EOF
|
|
97
|
+
{"structured_results": ${structured ? 1 : 0}, "reward": $reward, "patch_applied": $patch_applied, "fail_to_pass": $fail_to_pass, "pass_to_pass": $pass_to_pass, "deterministic": $deterministic, "setup_completed": $setup_completed, "fail_to_pass_exit_code": $fail_to_pass_exit_code, "fail_to_pass_repeat_exit_code": $fail_to_pass_repeat_exit_code, "pass_to_pass_exit_code": $pass_to_pass_exit_code}
|
|
98
|
+
EOF
|
|
99
|
+
exit 0
|
|
100
|
+
`;
|
|
101
|
+
}
|
|
102
|
+
function taskCommand(task, tests) {
|
|
103
|
+
return task.testCommand.replaceAll("{tests}", tests.map(shellQuote).join(" "));
|
|
104
|
+
}
|
|
105
|
+
//# sourceMappingURL=verifier.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"verifier.js","sourceRoot":"","sources":["../../src/harbor-task/verifier.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,UAAU,EAAE,MAAM,cAAc,CAAC;AAC1C,OAAO,EAAE,sBAAsB,EAAE,UAAU,EAAE,MAAM,YAAY,CAAC;AAEhE,MAAM,UAAU,cAAc;IAC5B,OAAO;;;CAGR,CAAC;AACF,CAAC;AAED,MAAM,UAAU,UAAU,CAAC,IAAoB,EAAE,SAAiB;IAChE,MAAM,mBAAmB,GAAG;QAC1B,GAAG,IAAI,GAAG,CAAC;YACT,GAAG,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,sBAAsB,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC;YACnE,GAAG,UAAU,CAAC,SAAS,CAAC;SACzB,CAAC;KACH,CAAC,IAAI,EAAE,CAAC;IACT,MAAM,UAAU,GAAG,mBAAmB;SACnC,OAAO,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC;QACjB,aAAa,UAAU,CAAC,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC,EAAE;QAClD,aAAa,UAAU,CAAC,GAAG,IAAI,CAAC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,EAAE;KAC1D,CAAC;SACD,IAAI,CAAC,GAAG,CAAC,CAAC;IACb,MAAM,cAAc,GAAG,mBAAmB,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;IACrE,MAAM,iBAAiB,GAAG,mBAAmB,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,UAAU,CAAC,QAAQ,IAAI,EAAE,CAAC,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;IAClG,MAAM,UAAU,GAAG,IAAI,CAAC,WAAW,CAAC;IACpC,MAAM,GAAG,GAAG,WAAW,CAAC,IAAI,EAAE,IAAI,CAAC,UAAU,CAAC,CAAC;IAC/C,MAAM,GAAG,GAAG,IAAI,CAAC,UAAU,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,WAAW,CAAC,IAAI,EAAE,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC;IACrF,OAAO;;;;;;;;;;;;;;;;;;;;;;;;mDAwB0C,UAAU;;;;;;;0BAOnC,cAAc;;;;;;4BAMZ,iBAAiB;;;;;;OAMtC,UAAU,CAAC,QAAQ,IAAI,CAAC,OAAO,EAAE,CAAC;4BACb,UAAU,CAAC,GAAG,CAAC,IAAI,UAAU,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,IAAI,UAAU,CAAC,IAAI,CAAC,SAAS,CAAC,UAAU,EAAE,UAAU,IAAI,EAAE,CAAC,CAAC;;;8BAG7G,UAAU,CAAC,GAAG,CAAC,IAAI,UAAU,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,IAAI,UAAU,CAAC,IAAI,CAAC,SAAS,CAAC,UAAU,EAAE,UAAU,IAAI,EAAE,CAAC,CAAC;;;;;;;;;UASnI,IAAI,CAAC,UAAU,CAAC,MAAM;;;8BAGF,UAAU,CAAC,GAAG,CAAC,IAAI,UAAU,CAAC,CAAC,CAAC,OAAO,CAAC,CAAC,CAAC,SAAS,IAAI,UAAU,CAAC,IAAI,CAAC,SAAS,CAAC,UAAU,EAAE,UAAU,IAAI,EAAE,CAAC,CAAC;;;;;;;;;;;yBAWpH,UAAU,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;;;CAG1C,CAAC;AACF,CAAC;AAED,SAAS,WAAW,CAAC,IAAoB,EAAE,KAAwB;IACjE,OAAO,IAAI,CAAC,WAAW,CAAC,UAAU,CAAC,SAAS,EAAE,KAAK,CAAC,GAAG,CAAC,UAAU,CAAC,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC;AACjF,CAAC"}
|
package/dist/harbor-task.d.ts
CHANGED
|
@@ -1,12 +1,4 @@
|
|
|
1
|
-
|
|
2
|
-
export
|
|
3
|
-
|
|
4
|
-
readonly testPatch: string;
|
|
5
|
-
readonly goldPatch: string;
|
|
6
|
-
}
|
|
7
|
-
export declare function loadAuthoredTask(directory: string): Promise<AuthoredTaskFiles>;
|
|
8
|
-
export declare function compileHarborTask(authoredDirectory: string, repositoryDirectory: string, outputDirectory: string): Promise<void>;
|
|
9
|
-
export declare function refreshHarborTask(outputDirectory: string, definition: TaskDefinition): Promise<void>;
|
|
10
|
-
export declare function goldPatchChangesDependencyManifests(patch: string): boolean;
|
|
11
|
-
export declare function dependencyManifestPatch(patch: string): string;
|
|
1
|
+
export type { AuthoredTaskFiles } from "./harbor-task/compiler.js";
|
|
2
|
+
export { compileHarborTask, loadAuthoredTask, refreshHarborTask } from "./harbor-task/compiler.js";
|
|
3
|
+
export { dependencyManifestPatch, goldPatchChangesDependencyManifests, } from "./harbor-task/dependencies.js";
|
|
12
4
|
//# sourceMappingURL=harbor-task.d.ts.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"harbor-task.d.ts","sourceRoot":"","sources":["../src/harbor-task.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"harbor-task.d.ts","sourceRoot":"","sources":["../src/harbor-task.ts"],"names":[],"mappings":"AAAA,YAAY,EAAE,iBAAiB,EAAE,MAAM,2BAA2B,CAAC;AACnE,OAAO,EAAE,iBAAiB,EAAE,gBAAgB,EAAE,iBAAiB,EAAE,MAAM,2BAA2B,CAAC;AACnG,OAAO,EACL,uBAAuB,EACvB,mCAAmC,GACpC,MAAM,+BAA+B,CAAC"}
|
package/dist/harbor-task.js
CHANGED
|
@@ -1,464 +1,3 @@
|
|
|
1
|
-
|
|
2
|
-
|
|
3
|
-
import { taskDefinitionSchema } from "./contracts.js";
|
|
4
|
-
import { sha256 } from "./hash.js";
|
|
5
|
-
import { runCommand } from "./process.js";
|
|
6
|
-
import { patchPaths } from "./repair.js";
|
|
7
|
-
const HARBOR_SCHEMA_VERSION = "1.4";
|
|
8
|
-
const COMPILER_REVISION = 24;
|
|
9
|
-
export async function loadAuthoredTask(directory) {
|
|
10
|
-
const definition = taskDefinitionSchema.parse(JSON.parse(await readFile(join(directory, "definition.json"), "utf8")));
|
|
11
|
-
assertSafeTaskPaths(definition);
|
|
12
|
-
const [testPatch, goldPatch] = await Promise.all([
|
|
13
|
-
readFile(join(directory, "test.patch"), "utf8"),
|
|
14
|
-
readFile(join(directory, "gold.patch"), "utf8"),
|
|
15
|
-
]);
|
|
16
|
-
if (!testPatch.startsWith("diff --git ")) {
|
|
17
|
-
throw new Error("test.patch is not a Git patch");
|
|
18
|
-
}
|
|
19
|
-
assertSafePatchPaths(testPatch);
|
|
20
|
-
if (!goldPatch.startsWith("diff --git ")) {
|
|
21
|
-
throw new Error("gold.patch is not a Git patch");
|
|
22
|
-
}
|
|
23
|
-
return { definition, testPatch, goldPatch };
|
|
24
|
-
}
|
|
25
|
-
export async function compileHarborTask(authoredDirectory, repositoryDirectory, outputDirectory) {
|
|
26
|
-
const task = await loadAuthoredTask(authoredDirectory);
|
|
27
|
-
const dependencySetupPatch = dependencyManifestPatch(task.goldPatch);
|
|
28
|
-
const preinstallGoldDependencies = dependencySetupPatch.length > 0;
|
|
29
|
-
await runCommand("git", [
|
|
30
|
-
"-C",
|
|
31
|
-
repositoryDirectory,
|
|
32
|
-
"cat-file",
|
|
33
|
-
"-e",
|
|
34
|
-
`${task.definition.baseCommit}^{commit}`,
|
|
35
|
-
]);
|
|
36
|
-
await rm(outputDirectory, { recursive: true, force: true });
|
|
37
|
-
const environment = join(outputDirectory, "environment");
|
|
38
|
-
const solution = join(outputDirectory, "solution");
|
|
39
|
-
const tests = join(outputDirectory, "tests");
|
|
40
|
-
await Promise.all([
|
|
41
|
-
mkdir(environment, { recursive: true }),
|
|
42
|
-
mkdir(solution, { recursive: true }),
|
|
43
|
-
mkdir(tests, { recursive: true }),
|
|
44
|
-
]);
|
|
45
|
-
const snapshot = join(outputDirectory, ".repo.tar.gz");
|
|
46
|
-
await runCommand("git", [
|
|
47
|
-
"-C",
|
|
48
|
-
repositoryDirectory,
|
|
49
|
-
"archive",
|
|
50
|
-
"--format=tar.gz",
|
|
51
|
-
`--output=${snapshot}`,
|
|
52
|
-
task.definition.baseCommit,
|
|
53
|
-
]);
|
|
54
|
-
await Promise.all([
|
|
55
|
-
cp(snapshot, join(environment, "repo.tar.gz")),
|
|
56
|
-
cp(snapshot, join(tests, "repo.tar.gz")),
|
|
57
|
-
writeFile(join(outputDirectory, "definition.json"), `${JSON.stringify(task.definition, null, 2)}\n`),
|
|
58
|
-
writeFile(join(outputDirectory, "instruction.md"), `${task.definition.prompt.trim()}\n`),
|
|
59
|
-
writeFile(join(solution, "gold.patch"), task.goldPatch),
|
|
60
|
-
writeFile(join(solution, "solve.sh"), solutionScript()),
|
|
61
|
-
writeFile(join(tests, "test.patch"), task.testPatch),
|
|
62
|
-
writeFile(join(tests, "test.sh"), testScript(task.definition, task.testPatch)),
|
|
63
|
-
writeFile(join(environment, "Dockerfile"), agentDockerfile(task.definition)),
|
|
64
|
-
writeFile(join(tests, "Dockerfile"), verifierDockerfile(task.definition, preinstallGoldDependencies)),
|
|
65
|
-
writeFile(join(outputDirectory, "task.toml"), taskToml(task.definition)),
|
|
66
|
-
...(preinstallGoldDependencies
|
|
67
|
-
? [writeFile(join(tests, "dependency-setup.patch"), dependencySetupPatch)]
|
|
68
|
-
: []),
|
|
69
|
-
]);
|
|
70
|
-
await rm(snapshot);
|
|
71
|
-
await Promise.all([
|
|
72
|
-
chmod(join(solution, "solve.sh"), 0o755),
|
|
73
|
-
chmod(join(tests, "test.sh"), 0o755),
|
|
74
|
-
]);
|
|
75
|
-
await writeFile(join(outputDirectory, ".selfbench-manifest.json"), `${JSON.stringify({
|
|
76
|
-
generator: "selfbench",
|
|
77
|
-
harborSchemaVersion: HARBOR_SCHEMA_VERSION,
|
|
78
|
-
compilerRevision: COMPILER_REVISION,
|
|
79
|
-
taskId: task.definition.taskId,
|
|
80
|
-
difficulty: task.definition.difficulty,
|
|
81
|
-
definitionSha256: sha256(JSON.stringify(task.definition)),
|
|
82
|
-
testPatchSha256: sha256(task.testPatch),
|
|
83
|
-
goldPatchSha256: sha256(task.goldPatch),
|
|
84
|
-
}, null, 2)}\n`);
|
|
85
|
-
}
|
|
86
|
-
export async function refreshHarborTask(outputDirectory, definition) {
|
|
87
|
-
const manifestPath = join(outputDirectory, ".selfbench-manifest.json");
|
|
88
|
-
const manifest = JSON.parse(await readFile(manifestPath, "utf8"));
|
|
89
|
-
if (manifest.taskId !== definition.taskId) {
|
|
90
|
-
throw new Error(`bundle task ${String(manifest.taskId)} does not match ${definition.taskId}`);
|
|
91
|
-
}
|
|
92
|
-
const [goldPatch, testPatch] = await Promise.all([
|
|
93
|
-
readFile(join(outputDirectory, "solution/gold.patch"), "utf8"),
|
|
94
|
-
readFile(join(outputDirectory, "tests/test.patch"), "utf8"),
|
|
95
|
-
]);
|
|
96
|
-
assertSafePatchPaths(testPatch);
|
|
97
|
-
const dependencySetupPatch = dependencyManifestPatch(goldPatch);
|
|
98
|
-
const preinstallGoldDependencies = dependencySetupPatch.length > 0;
|
|
99
|
-
await writeFile(join(outputDirectory, "tests/test.sh"), testScript(definition, testPatch));
|
|
100
|
-
await Promise.all([
|
|
101
|
-
writeFile(join(outputDirectory, "definition.json"), `${JSON.stringify(definition, null, 2)}\n`),
|
|
102
|
-
writeFile(join(outputDirectory, "task.toml"), taskToml(definition)),
|
|
103
|
-
writeFile(join(outputDirectory, "environment/Dockerfile"), agentDockerfile(definition)),
|
|
104
|
-
writeFile(join(outputDirectory, "tests/Dockerfile"), verifierDockerfile(definition, preinstallGoldDependencies)),
|
|
105
|
-
preinstallGoldDependencies
|
|
106
|
-
? writeFile(join(outputDirectory, "tests/dependency-setup.patch"), dependencySetupPatch)
|
|
107
|
-
: rm(join(outputDirectory, "tests/dependency-setup.patch"), { force: true }),
|
|
108
|
-
chmod(join(outputDirectory, "tests/test.sh"), 0o755),
|
|
109
|
-
]);
|
|
110
|
-
await writeFile(manifestPath, `${JSON.stringify({
|
|
111
|
-
...manifest,
|
|
112
|
-
compilerRevision: COMPILER_REVISION,
|
|
113
|
-
difficulty: definition.difficulty,
|
|
114
|
-
definitionSha256: sha256(JSON.stringify(definition)),
|
|
115
|
-
testPatchSha256: sha256(testPatch),
|
|
116
|
-
goldPatchSha256: sha256(goldPatch),
|
|
117
|
-
}, null, 2)}\n`);
|
|
118
|
-
}
|
|
119
|
-
function taskToml(task) {
|
|
120
|
-
const metadata = {
|
|
121
|
-
selfbench_task_id: task.taskId,
|
|
122
|
-
difficulty: task.difficulty,
|
|
123
|
-
repo: task.repo,
|
|
124
|
-
base_commit: task.baseCommit,
|
|
125
|
-
workdir: task.workdir,
|
|
126
|
-
source_pr: task.sourcePr,
|
|
127
|
-
compiler_revision: COMPILER_REVISION,
|
|
128
|
-
};
|
|
129
|
-
return `${[
|
|
130
|
-
`schema_version = ${tomlString(HARBOR_SCHEMA_VERSION)}`,
|
|
131
|
-
'artifacts = ["/opt/selfbench/agent.patch"]',
|
|
132
|
-
"",
|
|
133
|
-
"[task]",
|
|
134
|
-
`name = ${tomlString(`selfbench/${task.taskId}`)}`,
|
|
135
|
-
'version = "1.0.0"',
|
|
136
|
-
`description = ${tomlString(`Reproduce ${task.taskId} from its authentic engineer request.`)}`,
|
|
137
|
-
`keywords = ["software-engineering", "private-swe", "selfbench", ${tomlString(task.difficulty)}]`,
|
|
138
|
-
"",
|
|
139
|
-
"[metadata]",
|
|
140
|
-
...Object.entries(metadata).map(([key, value]) => `${key} = ${tomlValue(value)}`),
|
|
141
|
-
"",
|
|
142
|
-
"[agent]",
|
|
143
|
-
`timeout_sec = ${task.timeouts.agentSeconds}.0`,
|
|
144
|
-
'user = "agent"',
|
|
145
|
-
'network_mode = "allowlist"',
|
|
146
|
-
'allowed_hosts = ["chatgpt.com", "*.chatgpt.com", "openai.com", "*.openai.com"]',
|
|
147
|
-
"",
|
|
148
|
-
"[verifier]",
|
|
149
|
-
`timeout_sec = ${task.timeouts.setupSeconds + task.timeouts.testsSeconds}.0`,
|
|
150
|
-
'user = "root"',
|
|
151
|
-
'environment_mode = "separate"',
|
|
152
|
-
'network_mode = "public"',
|
|
153
|
-
"",
|
|
154
|
-
"[[verifier.collect]]",
|
|
155
|
-
'service = "main"',
|
|
156
|
-
'user = "root"',
|
|
157
|
-
`timeout_sec = ${Math.min(task.timeouts.testsSeconds, 300)}.0`,
|
|
158
|
-
'command = "git --git-dir=/opt/selfbench/base.git --work-tree=/app add -A && git --git-dir=/opt/selfbench/base.git --work-tree=/app diff --cached --binary HEAD > /opt/selfbench/agent.patch"',
|
|
159
|
-
"",
|
|
160
|
-
"[environment]",
|
|
161
|
-
'network_mode = "public"',
|
|
162
|
-
`build_timeout_sec = ${task.timeouts.setupSeconds + 600}.0`,
|
|
163
|
-
`cpus = ${task.resources.cpus}`,
|
|
164
|
-
`memory_mb = ${task.resources.memoryMb}`,
|
|
165
|
-
`storage_mb = ${task.resources.storageMb}`,
|
|
166
|
-
"",
|
|
167
|
-
"[verifier.environment]",
|
|
168
|
-
'network_mode = "public"',
|
|
169
|
-
`build_timeout_sec = ${task.timeouts.setupSeconds + 600}.0`,
|
|
170
|
-
`cpus = ${task.resources.cpus}`,
|
|
171
|
-
`memory_mb = ${task.resources.memoryMb}`,
|
|
172
|
-
`storage_mb = ${task.resources.storageMb}`,
|
|
173
|
-
].join("\n")}\n`;
|
|
174
|
-
}
|
|
175
|
-
function agentDockerfile(task) {
|
|
176
|
-
return `${toolchainDockerfile(task.toolchains)}
|
|
177
|
-
RUN useradd --create-home --shell /bin/bash agent
|
|
178
|
-
${repositoryDockerfile(task)}
|
|
179
|
-
RUN git -C /app reset --hard -q HEAD \\
|
|
180
|
-
&& git -C /app clean -fdq \\
|
|
181
|
-
&& mkdir -p /opt/selfbench \\
|
|
182
|
-
&& cp -a /app/.git /opt/selfbench/base.git \\
|
|
183
|
-
&& chown -R agent:agent /app /home/agent /opt/uv-cache \\
|
|
184
|
-
&& chown -R root:root /opt/selfbench \\
|
|
185
|
-
&& chmod 700 /opt/selfbench \\
|
|
186
|
-
&& mkdir -p /home/agent/.cache/uv \\
|
|
187
|
-
&& chown -R agent:agent /home/agent/.cache
|
|
188
|
-
ENV UV_CACHE_DIR=/home/agent/.cache/uv \\
|
|
189
|
-
UV_NO_BUILD_ISOLATION=1
|
|
190
|
-
USER agent
|
|
191
|
-
WORKDIR /app
|
|
192
|
-
`;
|
|
193
|
-
}
|
|
194
|
-
function verifierDockerfile(task, preinstallGoldDependencies) {
|
|
195
|
-
return `${toolchainDockerfile(task.toolchains)}
|
|
196
|
-
${repositoryDockerfile(task)}
|
|
197
|
-
${preinstallGoldDependencies ? goldDependencySetupLayer(task) : ""}
|
|
198
|
-
RUN useradd --create-home --shell /bin/bash verifier \\
|
|
199
|
-
&& chown -R verifier:verifier /app /opt/uv-cache \\
|
|
200
|
-
&& mkdir -p /opt/selfbench \\
|
|
201
|
-
&& chmod 700 /opt/selfbench \\
|
|
202
|
-
&& mkdir -p /home/verifier/.cache/uv \\
|
|
203
|
-
&& chown -R verifier:verifier /home/verifier/.cache
|
|
204
|
-
ENV UV_CACHE_DIR=/home/verifier/.cache/uv \\
|
|
205
|
-
UV_NO_BUILD_ISOLATION=1
|
|
206
|
-
COPY test.patch test.sh /tests/
|
|
207
|
-
RUN chmod 700 /tests && chmod 600 /tests/test.patch && chmod +x /tests/test.sh
|
|
208
|
-
WORKDIR /app
|
|
209
|
-
`;
|
|
210
|
-
}
|
|
211
|
-
function goldDependencySetupLayer(task) {
|
|
212
|
-
return `COPY dependency-setup.patch /tmp/selfbench-dependency-setup.patch
|
|
213
|
-
RUN git -C /app apply --binary --whitespace=nowarn /tmp/selfbench-dependency-setup.patch \\
|
|
214
|
-
&& cd ${shellQuote(`/app/${task.workdir}`)} \\
|
|
215
|
-
&& bash -lc ${shellQuote(task.setupCommand)} \\
|
|
216
|
-
&& git -C /app reset --hard -q HEAD \\
|
|
217
|
-
&& git -C /app clean -fdq \\
|
|
218
|
-
&& rm /tmp/selfbench-dependency-setup.patch
|
|
219
|
-
`;
|
|
220
|
-
}
|
|
221
|
-
export function goldPatchChangesDependencyManifests(patch) {
|
|
222
|
-
return dependencyManifestPatch(patch).length > 0;
|
|
223
|
-
}
|
|
224
|
-
export function dependencyManifestPatch(patch) {
|
|
225
|
-
const sections = patch.split(/(?=^diff --git )/m);
|
|
226
|
-
const selected = sections.filter((section) => {
|
|
227
|
-
const header = section.split("\n", 1)[0] ?? "";
|
|
228
|
-
const match = /^diff --git a\/(.+) b\/(.+)$/.exec(header);
|
|
229
|
-
return match?.[2] ? isDependencyManifest(match[2]) : false;
|
|
230
|
-
});
|
|
231
|
-
return selected.length > 0 ? `${selected.join("").trimEnd()}\n` : "";
|
|
232
|
-
}
|
|
233
|
-
function isDependencyManifest(path) {
|
|
234
|
-
const name = posix.basename(path);
|
|
235
|
-
return (/^(?:package(?:-lock)?\.json|npm-shrinkwrap\.json|yarn\.lock|pnpm-lock\.yaml|bun\.lockb?|deno\.lock)$/.test(name) ||
|
|
236
|
-
/^(?:pyproject\.toml|uv\.lock|poetry\.lock|Pipfile(?:\.lock)?|requirements[^/]*\.txt)$/.test(name) ||
|
|
237
|
-
/^(?:go\.(?:mod|sum)|Cargo\.(?:toml|lock))$/.test(name));
|
|
238
|
-
}
|
|
239
|
-
function toolchainDockerfile(toolchains) {
|
|
240
|
-
const layers = {
|
|
241
|
-
uv: "RUN curl -LsSf https://astral.sh/uv/install.sh | env UV_INSTALL_DIR=/usr/local/bin UV_NO_MODIFY_PATH=1 sh",
|
|
242
|
-
python: "RUN uv python install 3.11 3.12 3.13 && ln -sf /usr/local/bin/python3.12 /usr/local/bin/python3 && ln -sf /usr/local/bin/python3.12 /usr/local/bin/python",
|
|
243
|
-
node: `ENV PLAYWRIGHT_BROWSERS_PATH=/opt/playwright
|
|
244
|
-
RUN mkdir -p "$PLAYWRIGHT_BROWSERS_PATH" && chmod 755 "$PLAYWRIGHT_BROWSERS_PATH" \\
|
|
245
|
-
&& arch="$(dpkg --print-architecture)" && case "$arch" in arm64) node_arch=arm64 ;; amd64) node_arch=x64 ;; *) exit 1 ;; esac \\
|
|
246
|
-
&& curl -fsSL "https://nodejs.org/dist/v22.14.0/node-v22.14.0-linux-\${node_arch}.tar.xz" | tar -C /usr/local --strip-components=1 -xJ \\
|
|
247
|
-
&& mkdir -p /opt/corepack && chmod 755 /opt/corepack \\
|
|
248
|
-
&& corepack enable`,
|
|
249
|
-
bun: "RUN npm install --global bun@1.3.14",
|
|
250
|
-
// biome-ignore lint/suspicious/noTemplateCurlyInString: the output is a shell variable.
|
|
251
|
-
go: `RUN arch="$(dpkg --print-architecture)" && curl -fsSL "https://go.dev/dl/go1.25.0.linux-${"${arch}"}.tar.gz" | tar -C /usr/local -xz`,
|
|
252
|
-
rust: "RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | env RUSTUP_HOME=/usr/local/rustup CARGO_HOME=/usr/local/cargo sh -s -- -y --no-modify-path --profile minimal --default-toolchain 1.90.0",
|
|
253
|
-
};
|
|
254
|
-
const selected = new Set(toolchains);
|
|
255
|
-
if (selected.has("python")) {
|
|
256
|
-
selected.add("uv");
|
|
257
|
-
}
|
|
258
|
-
if (selected.has("bun")) {
|
|
259
|
-
selected.add("node");
|
|
260
|
-
}
|
|
261
|
-
const order = ["uv", "python", "node", "bun", "go", "rust"];
|
|
262
|
-
return `FROM ubuntu:24.04
|
|
263
|
-
ENV DEBIAN_FRONTEND=noninteractive \\
|
|
264
|
-
UV_LINK_MODE=copy \\
|
|
265
|
-
UV_CACHE_DIR=/opt/uv-cache \\
|
|
266
|
-
UV_PYTHON_INSTALL_DIR=/usr/local/share/uv/python \\
|
|
267
|
-
UV_PYTHON_BIN_DIR=/usr/local/bin \\
|
|
268
|
-
RUSTUP_HOME=/usr/local/rustup \\
|
|
269
|
-
CARGO_HOME=/usr/local/cargo \\
|
|
270
|
-
COREPACK_HOME=/opt/corepack \\
|
|
271
|
-
PATH=/usr/local/go/bin:/usr/local/cargo/bin:/usr/local/bin:/usr/local/sbin:/usr/bin:/usr/sbin:/bin:/sbin
|
|
272
|
-
RUN apt-get update && apt-get install -y --no-install-recommends \\
|
|
273
|
-
bash build-essential ca-certificates curl git jq passwd pkg-config procps unzip xz-utils \\
|
|
274
|
-
&& rm -rf /var/lib/apt/lists/*
|
|
275
|
-
${order
|
|
276
|
-
.filter((name) => selected.has(name))
|
|
277
|
-
.map((name) => layers[name])
|
|
278
|
-
.filter(Boolean)
|
|
279
|
-
.join("\n")}`;
|
|
280
|
-
}
|
|
281
|
-
function repositoryDockerfile(task) {
|
|
282
|
-
const pythonBuildDependencies = task.toolchains.includes("python")
|
|
283
|
-
? ` \\
|
|
284
|
-
&& find /app -path '*/.venv/bin/python' -exec uv pip install --python '{}' 'setuptools>=70' wheel ';'`
|
|
285
|
-
: "";
|
|
286
|
-
return `COPY repo.tar.gz /tmp/repo.tar.gz
|
|
287
|
-
RUN mkdir -p /app && tar -xzf /tmp/repo.tar.gz -C /app && rm /tmp/repo.tar.gz \\
|
|
288
|
-
&& git -C /app init -q \\
|
|
289
|
-
&& git -C /app config user.email selfbench@local \\
|
|
290
|
-
&& git -C /app config user.name selfbench \\
|
|
291
|
-
&& git -C /app add -A \\
|
|
292
|
-
&& git -C /app commit -qm base
|
|
293
|
-
RUN mkdir -p /opt/uv-cache && chmod 777 /opt/uv-cache \\
|
|
294
|
-
&& cd ${shellQuote(`/app/${task.workdir}`)} \\
|
|
295
|
-
&& bash -lc ${shellQuote(task.setupCommand)}${pythonBuildDependencies} \\
|
|
296
|
-
&& chmod -R a+rwX /opt/uv-cache`;
|
|
297
|
-
}
|
|
298
|
-
function solutionScript() {
|
|
299
|
-
return `#!/bin/bash
|
|
300
|
-
set -euo pipefail
|
|
301
|
-
git -C /app apply --binary --whitespace=nowarn /solution/gold.patch
|
|
302
|
-
`;
|
|
303
|
-
}
|
|
304
|
-
function testScript(task, testPatch) {
|
|
305
|
-
const repositoryTestPaths = [
|
|
306
|
-
...new Set([
|
|
307
|
-
...task.testPaths.map((path) => repositoryRelativePath(task, path)),
|
|
308
|
-
...patchPaths(testPatch),
|
|
309
|
-
]),
|
|
310
|
-
].sort();
|
|
311
|
-
const exclusions = repositoryTestPaths
|
|
312
|
-
.flatMap((path) => [
|
|
313
|
-
`--exclude=${shellQuote(path.replace(/\/$/, ""))}`,
|
|
314
|
-
`--exclude=${shellQuote(`${path.replace(/\/$/, "")}/*`)}`,
|
|
315
|
-
])
|
|
316
|
-
.join(" ");
|
|
317
|
-
const protectedPaths = repositoryTestPaths.map(shellQuote).join(" ");
|
|
318
|
-
const protectedAbsolute = repositoryTestPaths.map((path) => shellQuote(`/app/${path}`)).join(" ");
|
|
319
|
-
const f2p = taskCommand(task, task.failToPass);
|
|
320
|
-
const p2p = task.passToPass.length > 0 ? taskCommand(task, task.passToPass) : "true";
|
|
321
|
-
return `#!/bin/bash
|
|
322
|
-
set -uo pipefail
|
|
323
|
-
mkdir -p /logs/verifier
|
|
324
|
-
patch_applied=1
|
|
325
|
-
fail_to_pass=0
|
|
326
|
-
pass_to_pass=0
|
|
327
|
-
deterministic=0
|
|
328
|
-
setup_completed=0
|
|
329
|
-
fail_to_pass_exit_code=-1
|
|
330
|
-
fail_to_pass_repeat_exit_code=-1
|
|
331
|
-
pass_to_pass_exit_code=-1
|
|
332
|
-
verifier_cache=""
|
|
333
|
-
|
|
334
|
-
kill_verifier_processes() { pkill -KILL -u "$(id -u verifier)" 2>/dev/null || true; }
|
|
335
|
-
# Some toolchains fetch dependencies at test runtime (e.g. Next.js e2e installs),
|
|
336
|
-
# so a single registry connection reset must not be misread as a dead test. Retry
|
|
337
|
-
# only infrastructure-style failures with backoff; real assertion failures fail fast.
|
|
338
|
-
run_verifier_command() {
|
|
339
|
-
local logfile
|
|
340
|
-
logfile="$(mktemp /tmp/selfbench-verifier-command-XXXXXX.log)"
|
|
341
|
-
local attempt=1
|
|
342
|
-
local status=1
|
|
343
|
-
while [ "$attempt" -le 3 ]; do
|
|
344
|
-
: > "$logfile"
|
|
345
|
-
runuser -u verifier -- env PATH="/usr/local/go/bin:/usr/local/cargo/bin:/usr/local/bin:/usr/local/sbin:/usr/bin:/usr/sbin:/bin:/sbin" UV_CACHE_DIR="$verifier_cache" UV_NO_BUILD_ISOLATION=1 bash -lc "$1" >"$logfile" 2>&1
|
|
346
|
-
status=$?
|
|
347
|
-
if [ "$status" -eq 0 ]; then
|
|
348
|
-
break
|
|
349
|
-
fi
|
|
350
|
-
if [ "$attempt" -lt 3 ] && grep -qE 'ECONNRESET|ETIMEDOUT|ESOCKETTIMEDOUT|ENOTFOUND|EAI_AGAIN|META_FETCH_FAIL|FetchError|EPIPE|EPERM|registry\\.npmjs' "$logfile"; then
|
|
351
|
-
sleep "$((10 * attempt))"
|
|
352
|
-
attempt=$((attempt + 1))
|
|
353
|
-
continue
|
|
354
|
-
fi
|
|
355
|
-
break
|
|
356
|
-
done
|
|
357
|
-
cat "$logfile"
|
|
358
|
-
rm -f "$logfile"
|
|
359
|
-
kill_verifier_processes
|
|
360
|
-
return "$status"
|
|
361
|
-
}
|
|
362
|
-
protect_held_out_path() {
|
|
363
|
-
local path="$1"
|
|
364
|
-
chown -R root:root -- "$path"
|
|
365
|
-
chmod -R a-w,go+rX -- "$path"
|
|
366
|
-
}
|
|
367
|
-
|
|
368
|
-
if [ ! -f /opt/selfbench/agent.patch ]; then
|
|
369
|
-
patch_applied=0
|
|
370
|
-
elif [ -s /opt/selfbench/agent.patch ]; then
|
|
371
|
-
git -C /app apply --binary --whitespace=nowarn ${exclusions} /opt/selfbench/agent.patch || patch_applied=0
|
|
372
|
-
fi
|
|
373
|
-
|
|
374
|
-
if [ "$patch_applied" -eq 1 ]; then setup_completed=1; fi
|
|
375
|
-
|
|
376
|
-
if [ "$patch_applied" -eq 1 ] && [ "$setup_completed" -eq 1 ]; then
|
|
377
|
-
kill_verifier_processes
|
|
378
|
-
for protected_path in ${protectedPaths}; do
|
|
379
|
-
git -C /app restore --source=HEAD --staged --worktree -- "$protected_path" 2>/dev/null || true
|
|
380
|
-
git -C /app clean -fd -- "$protected_path" >/dev/null 2>&1 || true
|
|
381
|
-
done
|
|
382
|
-
git -C /app apply --binary --whitespace=nowarn /tests/test.patch || patch_applied=0
|
|
383
|
-
if [ "$patch_applied" -eq 1 ]; then
|
|
384
|
-
for protected_path in ${protectedAbsolute}; do protect_held_out_path "$protected_path"; done
|
|
385
|
-
fi
|
|
386
|
-
rm -f /tests/test.patch
|
|
387
|
-
fi
|
|
388
|
-
|
|
389
|
-
if [ "$patch_applied" -eq 1 ] && [ "$setup_completed" -eq 1 ]; then
|
|
390
|
-
cd ${shellQuote(`/app/${task.workdir}`)}
|
|
391
|
-
verifier_cache="$(mktemp -d /tmp/selfbench-verifier-uv-XXXXXX)"
|
|
392
|
-
cp -a /opt/uv-cache/. "$verifier_cache"/
|
|
393
|
-
chown -R verifier:verifier "$verifier_cache"
|
|
394
|
-
if run_verifier_command ${shellQuote(f2p)}; then
|
|
395
|
-
fail_to_pass_exit_code=0
|
|
396
|
-
fail_to_pass=1
|
|
397
|
-
if run_verifier_command ${shellQuote(f2p)}; then
|
|
398
|
-
fail_to_pass_repeat_exit_code=0
|
|
399
|
-
deterministic=1
|
|
400
|
-
else
|
|
401
|
-
fail_to_pass_repeat_exit_code=$?
|
|
402
|
-
fi
|
|
403
|
-
else
|
|
404
|
-
fail_to_pass_exit_code=$?
|
|
405
|
-
fi
|
|
406
|
-
if run_verifier_command ${shellQuote(p2p)}; then
|
|
407
|
-
pass_to_pass_exit_code=0
|
|
408
|
-
pass_to_pass=1
|
|
409
|
-
else
|
|
410
|
-
pass_to_pass_exit_code=$?
|
|
411
|
-
fi
|
|
412
|
-
rm -rf "$verifier_cache"
|
|
413
|
-
fi
|
|
414
|
-
|
|
415
|
-
reward=0
|
|
416
|
-
if [ "$patch_applied" -eq 1 ] && [ "$fail_to_pass" -eq 1 ] && [ "$pass_to_pass" -eq 1 ] && [ "$deterministic" -eq 1 ]; then reward=1; fi
|
|
417
|
-
cat > /logs/verifier/reward.json <<EOF
|
|
418
|
-
{"reward": $reward, "patch_applied": $patch_applied, "fail_to_pass": $fail_to_pass, "pass_to_pass": $pass_to_pass, "deterministic": $deterministic, "setup_completed": $setup_completed, "fail_to_pass_exit_code": $fail_to_pass_exit_code, "fail_to_pass_repeat_exit_code": $fail_to_pass_repeat_exit_code, "pass_to_pass_exit_code": $pass_to_pass_exit_code}
|
|
419
|
-
EOF
|
|
420
|
-
exit 0
|
|
421
|
-
`;
|
|
422
|
-
}
|
|
423
|
-
function taskCommand(task, tests) {
|
|
424
|
-
return task.testCommand.replaceAll("{tests}", tests.map(shellQuote).join(" "));
|
|
425
|
-
}
|
|
426
|
-
function assertSafeTaskPaths(task) {
|
|
427
|
-
for (const path of [
|
|
428
|
-
task.workdir,
|
|
429
|
-
...task.testPaths.map((value) => posix.join(task.workdir, value)),
|
|
430
|
-
]) {
|
|
431
|
-
const resolved = resolve("/repo", path);
|
|
432
|
-
if (resolved !== "/repo" && !resolved.startsWith(`/repo${sep}`)) {
|
|
433
|
-
throw new Error(`task path escapes repository: ${path}`);
|
|
434
|
-
}
|
|
435
|
-
}
|
|
436
|
-
}
|
|
437
|
-
function assertSafePatchPaths(patch) {
|
|
438
|
-
const paths = patchPaths(patch);
|
|
439
|
-
if (paths.length === 0) {
|
|
440
|
-
throw new Error("test.patch changes no files");
|
|
441
|
-
}
|
|
442
|
-
for (const path of paths) {
|
|
443
|
-
const resolved = resolve("/repo", path);
|
|
444
|
-
if (resolved === "/repo" ||
|
|
445
|
-
!resolved.startsWith(`/repo${sep}`) ||
|
|
446
|
-
resolved.startsWith(`/repo${sep}.git${sep}`) ||
|
|
447
|
-
resolved === `/repo${sep}.git`) {
|
|
448
|
-
throw new Error(`test patch path escapes repository: ${path}`);
|
|
449
|
-
}
|
|
450
|
-
}
|
|
451
|
-
}
|
|
452
|
-
function repositoryRelativePath(task, path) {
|
|
453
|
-
return posix.normalize(posix.join(task.workdir, path)).replace(/^\.\//, "");
|
|
454
|
-
}
|
|
455
|
-
function shellQuote(value) {
|
|
456
|
-
return `'${value.replaceAll("'", `'"'"'`)}'`;
|
|
457
|
-
}
|
|
458
|
-
function tomlString(value) {
|
|
459
|
-
return JSON.stringify(value);
|
|
460
|
-
}
|
|
461
|
-
function tomlValue(value) {
|
|
462
|
-
return typeof value === "string" ? tomlString(value) : String(value);
|
|
463
|
-
}
|
|
1
|
+
export { compileHarborTask, loadAuthoredTask, refreshHarborTask } from "./harbor-task/compiler.js";
|
|
2
|
+
export { dependencyManifestPatch, goldPatchChangesDependencyManifests, } from "./harbor-task/dependencies.js";
|
|
464
3
|
//# sourceMappingURL=harbor-task.js.map
|