self-bench 0.3.5 → 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 +38 -21
- 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 -369
- 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 -242
- package/dist/contracts.d.ts.map +1 -1
- package/dist/contracts.js +5 -127
- 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/discovery.d.ts.map +1 -1
- package/dist/extensions/discovery.js +12 -5
- package/dist/extensions/discovery.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 -461
- 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/project-paths.d.ts +2 -0
- package/dist/project-paths.d.ts.map +1 -0
- package/dist/project-paths.js +15 -0
- package/dist/project-paths.js.map +1 -0
- 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 +22 -0
- package/dist/provenance-associations.d.ts.map +1 -0
- package/dist/provenance-associations.js +121 -0
- package/dist/provenance-associations.js.map +1 -0
- package/dist/provenance.d.ts +7 -20
- package/dist/provenance.d.ts.map +1 -1
- package/dist/provenance.js +6 -360
- 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 +76 -0
- package/dist/sandbox/contracts.d.ts.map +1 -0
- package/dist/sandbox/contracts.js +12 -0
- package/dist/sandbox/contracts.js.map +1 -0
- package/dist/sandbox/index.d.ts +5 -0
- package/dist/sandbox/index.d.ts.map +1 -0
- package/dist/sandbox/index.js +27 -0
- package/dist/sandbox/index.js.map +1 -0
- 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.d.ts +3 -0
- package/dist/sandbox/programs/author.d.ts.map +1 -0
- package/dist/sandbox/programs/author.js +27 -0
- package/dist/sandbox/programs/author.js.map +1 -0
- 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-task.js +32 -0
- 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 +14 -0
- package/dist/sandbox/providers/docker/executor.d.ts.map +1 -0
- package/dist/sandbox/providers/docker/executor.js +153 -0
- package/dist/sandbox/providers/docker/executor.js.map +1 -0
- 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/sandbox/providers/modal/auth.d.ts +2 -0
- package/dist/sandbox/providers/modal/auth.d.ts.map +1 -0
- package/dist/sandbox/providers/modal/auth.js +9 -0
- package/dist/sandbox/providers/modal/auth.js.map +1 -0
- package/dist/sandbox/providers/modal/executor.d.ts +15 -0
- package/dist/sandbox/providers/modal/executor.d.ts.map +1 -0
- package/dist/sandbox/providers/modal/executor.js +207 -0
- package/dist/sandbox/providers/modal/executor.js.map +1 -0
- 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 +20 -0
- package/dist/sandbox/providers/vercel/command.d.ts.map +1 -0
- package/dist/sandbox/providers/vercel/command.js +126 -0
- package/dist/sandbox/providers/vercel/command.js.map +1 -0
- package/dist/sandbox/providers/vercel/executor.d.ts +13 -0
- package/dist/sandbox/providers/vercel/executor.d.ts.map +1 -0
- package/dist/sandbox/providers/vercel/executor.js +190 -0
- package/dist/sandbox/providers/vercel/executor.js.map +1 -0
- package/dist/sandbox/providers/vercel/fetch.d.ts +6 -0
- package/dist/sandbox/providers/vercel/fetch.d.ts.map +1 -0
- package/dist/sandbox/providers/vercel/fetch.js +39 -0
- package/dist/sandbox/providers/vercel/fetch.js.map +1 -0
- 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 +16 -0
- package/dist/sandbox/timeout.d.ts.map +1 -0
- package/dist/sandbox/timeout.js +53 -0
- package/dist/sandbox/timeout.js.map +1 -0
- package/dist/sandbox-author.bundle.js +48 -14877
- package/dist/sandbox-check.bundle.js +20155 -0
- 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 +38 -0
- package/dist/setup/vercel/cli.d.ts.map +1 -0
- package/dist/setup/vercel/cli.js +193 -0
- package/dist/setup/vercel/cli.js.map +1 -0
- package/dist/setup/vercel/index.d.ts +4 -0
- package/dist/setup/vercel/index.d.ts.map +1 -0
- package/dist/setup/vercel/index.js +3 -0
- package/dist/setup/vercel/index.js.map +1 -0
- package/dist/setup/vercel/probe.d.ts +49 -0
- package/dist/setup/vercel/probe.d.ts.map +1 -0
- package/dist/setup/vercel/probe.js +151 -0
- package/dist/setup/vercel/probe.js.map +1 -0
- 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 +18 -0
- package/dist/setup/vercel/profile.d.ts.map +1 -0
- package/dist/setup/vercel/profile.js +118 -0
- package/dist/setup/vercel/profile.js.map +1 -0
- package/dist/setup/vercel/runtime-image.d.ts +51 -0
- package/dist/setup/vercel/runtime-image.d.ts.map +1 -0
- package/dist/setup/vercel/runtime-image.js +123 -0
- package/dist/setup/vercel/runtime-image.js.map +1 -0
- 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 +17 -0
- package/dist/setup/vercel/setup.d.ts.map +1 -0
- package/dist/setup/vercel/setup.js +172 -0
- package/dist/setup/vercel/setup.js.map +1 -0
- 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 -39
- package/dist/temporal/activities.d.ts.map +1 -1
- package/dist/temporal/activities.js +2 -839
- 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 +13 -5
- package/dist/temporal/workflow.d.ts.map +1 -1
- package/dist/temporal/workflow.js +38 -420
- 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 +292 -30
- package/docs/solver-evaluations.md +63 -0
- package/docs/task-construction.md +24 -12
- 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 +43 -29
- package/src/extensions/authoring.ts +83 -72
- package/src/extensions/discovery.ts +14 -5
- 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 -18
- 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/docker-executor.d.ts +0 -11
- package/dist/docker-executor.d.ts.map +0 -1
- package/dist/docker-executor.js +0 -103
- package/dist/docker-executor.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 +0 -2
- package/dist/modal-auth.d.ts.map +0 -1
- package/dist/modal-auth.js +0 -9
- package/dist/modal-auth.js.map +0 -1
- package/dist/modal-executor.d.ts +0 -12
- package/dist/modal-executor.d.ts.map +0 -1
- package/dist/modal-executor.js +0 -152
- package/dist/modal-executor.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-author.d.ts +0 -3
- package/dist/sandbox-author.d.ts.map +0 -1
- package/dist/sandbox-author.js +0 -17
- package/dist/sandbox-author.js.map +0 -1
- package/dist/sandbox-repair.bundle.js +0 -315
- package/dist/sandbox-repair.d.ts +0 -3
- package/dist/sandbox-repair.d.ts.map +0 -1
- package/dist/sandbox-repair.js +0 -121
- package/dist/sandbox-repair.js.map +0 -1
- package/dist/sandbox-review.bundle.js +0 -14462
- package/dist/sandbox-review.d.ts +0 -2
- package/dist/sandbox-review.d.ts.map +0 -1
- package/dist/sandbox-review.js +0 -18
- package/dist/sandbox-review.js.map +0 -1
- package/dist/sandbox-timeout.d.ts +0 -11
- package/dist/sandbox-timeout.d.ts.map +0 -1
- package/dist/sandbox-timeout.js +0 -41
- package/dist/sandbox-timeout.js.map +0 -1
- package/dist/sandbox-validation-repair.bundle.js +0 -14778
- package/dist/sandbox-validation-repair.d.ts +0 -3
- package/dist/sandbox-validation-repair.d.ts.map +0 -1
- package/dist/sandbox-validation-repair.js +0 -136
- package/dist/sandbox-validation-repair.js.map +0 -1
- package/dist/sandbox.d.ts +0 -39
- package/dist/sandbox.d.ts.map +0 -1
- package/dist/sandbox.js +0 -15
- package/dist/sandbox.js.map +0 -1
- 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/dist/vercel-cli.d.ts +0 -64
- package/dist/vercel-cli.d.ts.map +0 -1
- package/dist/vercel-cli.js +0 -303
- package/dist/vercel-cli.js.map +0 -1
- package/dist/vercel-command.d.ts +0 -14
- package/dist/vercel-command.d.ts.map +0 -1
- package/dist/vercel-command.js +0 -93
- package/dist/vercel-command.js.map +0 -1
- package/dist/vercel-executor.d.ts +0 -14
- package/dist/vercel-executor.d.ts.map +0 -1
- package/dist/vercel-executor.js +0 -356
- package/dist/vercel-executor.js.map +0 -1
- package/dist/vercel-fetch.d.ts +0 -6
- package/dist/vercel-fetch.d.ts.map +0 -1
- package/dist/vercel-fetch.js +0 -39
- package/dist/vercel-fetch.js.map +0 -1
- package/dist/vercel-profile.d.ts +0 -34
- package/dist/vercel-profile.d.ts.map +0 -1
- package/dist/vercel-profile.js +0 -244
- package/dist/vercel-profile.js.map +0 -1
- package/dist/vercel-runtime-image.d.ts +0 -51
- package/dist/vercel-runtime-image.d.ts.map +0 -1
- package/dist/vercel-runtime-image.js +0 -123
- package/dist/vercel-runtime-image.js.map +0 -1
- package/dist/vercel-setup-probe.d.ts +0 -49
- package/dist/vercel-setup-probe.d.ts.map +0 -1
- package/dist/vercel-setup-probe.js +0 -151
- package/dist/vercel-setup-probe.js.map +0 -1
- package/dist/vercel-setup.d.ts +0 -42
- package/dist/vercel-setup.d.ts.map +0 -1
- package/dist/vercel-setup.js +0 -280
- package/dist/vercel-setup.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/verify-package.ts +0 -81
- 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 -290
- package/src/artifacts.ts +0 -357
- package/src/audit.ts +0 -106
- package/src/build-metadata.ts +0 -3
- package/src/cli.ts +0 -420
- package/src/codex-review.ts +0 -229
- package/src/config.ts +0 -239
- package/src/contracts.ts +0 -231
- package/src/coupling.ts +0 -259
- package/src/docker-executor.ts +0 -115
- 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 -528
- package/src/hash.ts +0 -5
- package/src/modal-auth.ts +0 -11
- package/src/modal-executor.ts +0 -176
- package/src/parallel.ts +0 -24
- package/src/process.ts +0 -167
- package/src/provenance.ts +0 -457
- 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-author.ts +0 -19
- package/src/sandbox-repair.ts +0 -156
- package/src/sandbox-review.ts +0 -19
- package/src/sandbox-timeout.ts +0 -56
- package/src/sandbox-validation-repair.ts +0 -177
- package/src/sandbox.ts +0 -61
- package/src/subscription-auth.ts +0 -80
- package/src/temporal/activities.ts +0 -1247
- package/src/temporal/connection.ts +0 -23
- package/src/temporal/worker-main.ts +0 -28
- package/src/temporal/workflow.ts +0 -519
- 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/src/vercel-cli.ts +0 -403
- package/src/vercel-command.ts +0 -127
- package/src/vercel-executor.ts +0 -448
- package/src/vercel-fetch.ts +0 -45
- package/src/vercel-profile.ts +0 -319
- package/src/vercel-runtime-image.ts +0 -204
- package/src/vercel-setup-probe.ts +0 -229
- package/src/vercel-setup.ts +0 -419
- package/tsconfig.build.json +0 -13
- package/tsconfig.json +0 -21
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
// src/extensions/verifier.ts
|
|
2
|
+
import { existsSync, mkdirSync, writeFileSync } from "node:fs";
|
|
3
|
+
import { join } from "node:path";
|
|
4
|
+
import { Type } from "@sinclair/typebox";
|
|
5
|
+
function writeVerdict(verdict) {
|
|
6
|
+
const root = requiredEnvironment("SELFBENCH_VERDICT_OUTPUT");
|
|
7
|
+
mkdirSync(root, { recursive: true });
|
|
8
|
+
const path = join(root, "verdict.json");
|
|
9
|
+
if (existsSync(path))
|
|
10
|
+
throw new Error("a verdict was already submitted this round");
|
|
11
|
+
writeFileSync(path, `${JSON.stringify(verdict, null, 2)}
|
|
12
|
+
`, { flag: "wx" });
|
|
13
|
+
}
|
|
14
|
+
function requiredEnvironment(name) {
|
|
15
|
+
const value = process.env[name];
|
|
16
|
+
if (!value)
|
|
17
|
+
throw new Error(`${name} is required`);
|
|
18
|
+
return value;
|
|
19
|
+
}
|
|
20
|
+
function verifierExtension(pi) {
|
|
21
|
+
pi.registerTool({
|
|
22
|
+
name: "accept_task",
|
|
23
|
+
label: "Accept SelfBench task",
|
|
24
|
+
description: "Accept a fair task after the latest report is GREEN.",
|
|
25
|
+
parameters: Type.Object({
|
|
26
|
+
reason: Type.String({ minLength: 1 }),
|
|
27
|
+
findings: Type.Array(Type.Object({
|
|
28
|
+
artifact: Type.String({ minLength: 1 }),
|
|
29
|
+
disposition: Type.Union([
|
|
30
|
+
Type.Literal("base_contract"),
|
|
31
|
+
Type.Literal("prompt_contract"),
|
|
32
|
+
Type.Literal("external_contract"),
|
|
33
|
+
Type.Literal("not_contract")
|
|
34
|
+
]),
|
|
35
|
+
evidence: Type.String({ minLength: 1 })
|
|
36
|
+
}, { additionalProperties: false })),
|
|
37
|
+
counterexample: Type.String({ minLength: 1 })
|
|
38
|
+
}, { additionalProperties: false }),
|
|
39
|
+
async execute(_toolCallId, input) {
|
|
40
|
+
writeVerdict({ kind: "accepted", ...input });
|
|
41
|
+
return { content: [{ type: "text", text: "Recorded the acceptance verdict." }], details: {} };
|
|
42
|
+
}
|
|
43
|
+
});
|
|
44
|
+
pi.registerTool({
|
|
45
|
+
name: "submit_suggestions",
|
|
46
|
+
label: "Submit authoring suggestions",
|
|
47
|
+
description: "Submit concise, actionable suggestions for the next authoring agent. This verifier is read-only and must not edit task files.",
|
|
48
|
+
parameters: Type.Object({
|
|
49
|
+
summary: Type.String({ minLength: 1 }),
|
|
50
|
+
suggestions: Type.String({ minLength: 1 })
|
|
51
|
+
}, { additionalProperties: false }),
|
|
52
|
+
async execute(_toolCallId, input) {
|
|
53
|
+
writeVerdict({ kind: "suggestions", ...input });
|
|
54
|
+
return {
|
|
55
|
+
content: [{ type: "text", text: "Recorded suggestions for the next authoring round." }],
|
|
56
|
+
details: {}
|
|
57
|
+
};
|
|
58
|
+
}
|
|
59
|
+
});
|
|
60
|
+
pi.registerTool({
|
|
61
|
+
name: "reject_task",
|
|
62
|
+
label: "Reject SelfBench task",
|
|
63
|
+
description: "Reject a task that cannot be made fair within the authoring workflow.",
|
|
64
|
+
parameters: Type.Object({ reason: Type.String({ minLength: 1 }) }, { additionalProperties: false }),
|
|
65
|
+
async execute(_toolCallId, input) {
|
|
66
|
+
writeVerdict({ kind: "rejected", ...input });
|
|
67
|
+
return { content: [{ type: "text", text: "Recorded the rejection verdict." }], details: {} };
|
|
68
|
+
}
|
|
69
|
+
});
|
|
70
|
+
}
|
|
71
|
+
export {
|
|
72
|
+
verifierExtension as default
|
|
73
|
+
};
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"authoring.d.ts","sourceRoot":"","sources":["../../src/extensions/authoring.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,iCAAiC,CAAC;
|
|
1
|
+
{"version":3,"file":"authoring.d.ts","sourceRoot":"","sources":["../../src/extensions/authoring.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,iCAAiC,CAAC;AAkBpE,MAAM,CAAC,OAAO,UAAU,kBAAkB,CAAC,EAAE,EAAE,YAAY,GAAG,IAAI,CA4EjE"}
|
|
@@ -1,71 +1,82 @@
|
|
|
1
|
-
import {
|
|
1
|
+
import { cpSync, mkdirSync } from "node:fs";
|
|
2
2
|
import { join } from "node:path";
|
|
3
3
|
import { Type } from "@sinclair/typebox";
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
testCommand: Type.String({ minLength: 1 }),
|
|
13
|
-
failToPass: Type.Array(Type.String({ minLength: 1 }), { minItems: 1 }),
|
|
14
|
-
passToPass: Type.Array(Type.String({ minLength: 1 })),
|
|
15
|
-
testPaths: Type.Array(Type.String({ minLength: 1 }), { minItems: 1 }),
|
|
16
|
-
toolchains: Type.Array(Type.Union([
|
|
17
|
-
Type.Literal("uv"),
|
|
18
|
-
Type.Literal("bun"),
|
|
19
|
-
Type.Literal("go"),
|
|
20
|
-
Type.Literal("node"),
|
|
21
|
-
Type.Literal("python"),
|
|
22
|
-
Type.Literal("rust"),
|
|
23
|
-
]), { minItems: 1 }),
|
|
24
|
-
sourcePr: Type.Integer({ minimum: 1 }),
|
|
25
|
-
sourceUrl: Type.String({ minLength: 1 }),
|
|
26
|
-
prompt: Type.String({ minLength: 1 }),
|
|
27
|
-
timeouts: Type.Object({
|
|
28
|
-
setupSeconds: Type.Integer({ minimum: 1 }),
|
|
29
|
-
agentSeconds: Type.Integer({ minimum: 1 }),
|
|
30
|
-
testsSeconds: Type.Integer({ minimum: 1 }),
|
|
31
|
-
}),
|
|
32
|
-
resources: Type.Object({
|
|
33
|
-
cpus: Type.Number({ exclusiveMinimum: 0 }),
|
|
34
|
-
memoryMb: Type.Integer({ minimum: 1 }),
|
|
35
|
-
storageMb: Type.Integer({ minimum: 1 }),
|
|
36
|
-
}),
|
|
37
|
-
}, { additionalProperties: false });
|
|
4
|
+
import { loadTaskDeliverable } from "./shared/deliverable.js";
|
|
5
|
+
import { VerifyClient, verifyOutcomeText } from "./shared/mailbox.js";
|
|
6
|
+
import { requiredEnvironment, runStaticCheck, stageSubmission, staticCheckFailure, } from "./shared/static-check.js";
|
|
7
|
+
const noArguments = Type.Object({}, { additionalProperties: false });
|
|
8
|
+
/** The clean base tree the patches must apply to: /work/repo at the definition's base commit. */
|
|
9
|
+
function applyTarget(definition) {
|
|
10
|
+
return { base: typeof definition.baseCommit === "string" ? definition.baseCommit : "HEAD" };
|
|
11
|
+
}
|
|
38
12
|
export default function authoringExtension(pi) {
|
|
13
|
+
const client = new VerifyClient();
|
|
14
|
+
const deliverable = () => process.env.SELFBENCH_DELIVERABLE ?? "/work/task";
|
|
39
15
|
pi.registerTool({
|
|
40
|
-
name: "
|
|
41
|
-
label: "
|
|
42
|
-
description: "
|
|
43
|
-
parameters:
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
async execute(_toolCallId, input) {
|
|
49
|
-
const root = process.env.SELFBENCH_TASK_OUTPUT;
|
|
50
|
-
if (!root) {
|
|
51
|
-
throw new Error("SELFBENCH_TASK_OUTPUT is not configured");
|
|
16
|
+
name: "verify",
|
|
17
|
+
label: "Verify SelfBench task",
|
|
18
|
+
description: "Takes no arguments. Reads the deliverable in /work/task (definition.json, instruction.md, test.patch, gold.patch), runs the static check, then the harness's real verification: trusted compile, audit, image build, smoke, nop, and oracle. Blocks until the report is back (can take up to an hour). Budget-limited per session; the result says how many calls remain.",
|
|
19
|
+
parameters: noArguments,
|
|
20
|
+
async execute() {
|
|
21
|
+
const loaded = loadTaskDeliverable(deliverable());
|
|
22
|
+
if ("isError" in loaded) {
|
|
23
|
+
return loaded;
|
|
52
24
|
}
|
|
53
|
-
const
|
|
54
|
-
|
|
55
|
-
|
|
25
|
+
const staging = stageSubmission(loaded.definition, loaded.testPatch, loaded.goldPatch, "selfbench-verify-");
|
|
26
|
+
try {
|
|
27
|
+
const verdict = runStaticCheck(staging.directory, [], applyTarget(loaded.definition));
|
|
28
|
+
if (!verdict.ok) {
|
|
29
|
+
return staticCheckFailure(verdict, "task");
|
|
30
|
+
}
|
|
56
31
|
}
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
});
|
|
62
|
-
writeFileSync(join(directory, "test.patch"), testPatch, { flag: "wx" });
|
|
63
|
-
writeFileSync(join(directory, "gold.patch"), goldPatch, { flag: "wx" });
|
|
32
|
+
finally {
|
|
33
|
+
staging.dispose();
|
|
34
|
+
}
|
|
35
|
+
const outcome = await client.verify("task", loaded);
|
|
64
36
|
return {
|
|
65
|
-
content: [{ type: "text", text:
|
|
66
|
-
details: {
|
|
37
|
+
content: [{ type: "text", text: verifyOutcomeText(outcome, "submit_task") }],
|
|
38
|
+
details: { kind: outcome.kind, remaining: client.remaining },
|
|
39
|
+
...(outcome.kind === "exhausted" ? { isError: true } : {}),
|
|
67
40
|
};
|
|
68
41
|
},
|
|
69
42
|
});
|
|
43
|
+
pi.registerTool({
|
|
44
|
+
name: "submit_task",
|
|
45
|
+
label: "Submit SelfBench task",
|
|
46
|
+
description: "Takes no arguments. Reads the deliverable in /work/task, runs the static check, and records the task; a passing submission ends the session. Run verify first and submit only what verify reported green.",
|
|
47
|
+
parameters: noArguments,
|
|
48
|
+
async execute() {
|
|
49
|
+
const root = requiredEnvironment("SELFBENCH_TASK_OUTPUT");
|
|
50
|
+
const loaded = loadTaskDeliverable(deliverable());
|
|
51
|
+
if ("isError" in loaded) {
|
|
52
|
+
return loaded;
|
|
53
|
+
}
|
|
54
|
+
const taskId = String(loaded.definition.taskId ?? "");
|
|
55
|
+
const staging = stageSubmission(loaded.definition, loaded.testPatch, loaded.goldPatch);
|
|
56
|
+
try {
|
|
57
|
+
const verdict = runStaticCheck(staging.directory, [], applyTarget(loaded.definition));
|
|
58
|
+
if (!verdict.ok) {
|
|
59
|
+
return staticCheckFailure(verdict, "submission");
|
|
60
|
+
}
|
|
61
|
+
const directory = join(root, taskId);
|
|
62
|
+
mkdirSync(root, { recursive: true });
|
|
63
|
+
mkdirSync(directory, { recursive: false });
|
|
64
|
+
cpSync(staging.directory, directory, { recursive: true });
|
|
65
|
+
const verified = client.verifiedGreen(loaded);
|
|
66
|
+
return {
|
|
67
|
+
content: [
|
|
68
|
+
{
|
|
69
|
+
type: "text",
|
|
70
|
+
text: `Submitted ${taskId}; the static check passed and the Harbor tree is dry-rendered under ${verdict.renderedDirectory ?? "/work/rendered"}. ${verified ? "This deliverable matches your last green verify, so the worker reuses that report." : "This deliverable was not verified green in this session, so the worker verifies it now and a round is spent if it fails."} Stop here and wait.`,
|
|
71
|
+
},
|
|
72
|
+
],
|
|
73
|
+
details: { taskId, verified },
|
|
74
|
+
};
|
|
75
|
+
}
|
|
76
|
+
finally {
|
|
77
|
+
staging.dispose();
|
|
78
|
+
}
|
|
79
|
+
},
|
|
80
|
+
});
|
|
70
81
|
}
|
|
71
82
|
//# sourceMappingURL=authoring.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"authoring.js","sourceRoot":"","sources":["../../src/extensions/authoring.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,
|
|
1
|
+
{"version":3,"file":"authoring.js","sourceRoot":"","sources":["../../src/extensions/authoring.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,SAAS,CAAC;AAC5C,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAEjC,OAAO,EAAE,IAAI,EAAE,MAAM,mBAAmB,CAAC;AACzC,OAAO,EAAE,mBAAmB,EAAE,MAAM,yBAAyB,CAAC;AAC9D,OAAO,EAAE,YAAY,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAC;AACtE,OAAO,EACL,mBAAmB,EACnB,cAAc,EACd,eAAe,EACf,kBAAkB,GACnB,MAAM,0BAA0B,CAAC;AAElC,MAAM,WAAW,GAAG,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,EAAE,oBAAoB,EAAE,KAAK,EAAE,CAAC,CAAC;AAErE,iGAAiG;AACjG,SAAS,WAAW,CAAC,UAAmC;IACtD,OAAO,EAAE,IAAI,EAAE,OAAO,UAAU,CAAC,UAAU,KAAK,QAAQ,CAAC,CAAC,CAAC,UAAU,CAAC,UAAU,CAAC,CAAC,CAAC,MAAM,EAAE,CAAC;AAC9F,CAAC;AAED,MAAM,CAAC,OAAO,UAAU,kBAAkB,CAAC,EAAgB;IACzD,MAAM,MAAM,GAAG,IAAI,YAAY,EAAE,CAAC;IAClC,MAAM,WAAW,GAAG,GAAW,EAAE,CAAC,OAAO,CAAC,GAAG,CAAC,qBAAqB,IAAI,YAAY,CAAC;IAEpF,EAAE,CAAC,YAAY,CAAC;QACd,IAAI,EAAE,QAAQ;QACd,KAAK,EAAE,uBAAuB;QAC9B,WAAW,EACT,2WAA2W;QAC7W,UAAU,EAAE,WAAW;QACvB,KAAK,CAAC,OAAO;YACX,MAAM,MAAM,GAAG,mBAAmB,CAAC,WAAW,EAAE,CAAC,CAAC;YAClD,IAAI,SAAS,IAAI,MAAM,EAAE,CAAC;gBACxB,OAAO,MAAM,CAAC;YAChB,CAAC;YACD,MAAM,OAAO,GAAG,eAAe,CAC7B,MAAM,CAAC,UAAU,EACjB,MAAM,CAAC,SAAS,EAChB,MAAM,CAAC,SAAS,EAChB,mBAAmB,CACpB,CAAC;YACF,IAAI,CAAC;gBACH,MAAM,OAAO,GAAG,cAAc,CAAC,OAAO,CAAC,SAAS,EAAE,EAAE,EAAE,WAAW,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC,CAAC;gBACtF,IAAI,CAAC,OAAO,CAAC,EAAE,EAAE,CAAC;oBAChB,OAAO,kBAAkB,CAAC,OAAO,EAAE,MAAM,CAAC,CAAC;gBAC7C,CAAC;YACH,CAAC;oBAAS,CAAC;gBACT,OAAO,CAAC,OAAO,EAAE,CAAC;YACpB,CAAC;YACD,MAAM,OAAO,GAAG,MAAM,MAAM,CAAC,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;YACpD,OAAO;gBACL,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,iBAAiB,CAAC,OAAO,EAAE,aAAa,CAAC,EAAE,CAAC;gBAC5E,OAAO,EAAE,EAAE,IAAI,EAAE,OAAO,CAAC,IAAI,EAAE,SAAS,EAAE,MAAM,CAAC,SAAS,EAAE;gBAC5D,GAAG,CAAC,OAAO,CAAC,IAAI,KAAK,WAAW,CAAC,CAAC,CAAC,EAAE,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;aAC3D,CAAC;QACJ,CAAC;KACF,CAAC,CAAC;IAEH,EAAE,CAAC,YAAY,CAAC;QACd,IAAI,EAAE,aAAa;QACnB,KAAK,EAAE,uBAAuB;QAC9B,WAAW,EACT,2MAA2M;QAC7M,UAAU,EAAE,WAAW;QACvB,KAAK,CAAC,OAAO;YACX,MAAM,IAAI,GAAG,mBAAmB,CAAC,uBAAuB,CAAC,CAAC;YAC1D,MAAM,MAAM,GAAG,mBAAmB,CAAC,WAAW,EAAE,CAAC,CAAC;YAClD,IAAI,SAAS,IAAI,MAAM,EAAE,CAAC;gBACxB,OAAO,MAAM,CAAC;YAChB,CAAC;YACD,MAAM,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC,UAAU,CAAC,MAAM,IAAI,EAAE,CAAC,CAAC;YACtD,MAAM,OAAO,GAAG,eAAe,CAAC,MAAM,CAAC,UAAU,EAAE,MAAM,CAAC,SAAS,EAAE,MAAM,CAAC,SAAS,CAAC,CAAC;YACvF,IAAI,CAAC;gBACH,MAAM,OAAO,GAAG,cAAc,CAAC,OAAO,CAAC,SAAS,EAAE,EAAE,EAAE,WAAW,CAAC,MAAM,CAAC,UAAU,CAAC,CAAC,CAAC;gBACtF,IAAI,CAAC,OAAO,CAAC,EAAE,EAAE,CAAC;oBAChB,OAAO,kBAAkB,CAAC,OAAO,EAAE,YAAY,CAAC,CAAC;gBACnD,CAAC;gBACD,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,EAAE,MAAM,CAAC,CAAC;gBACrC,SAAS,CAAC,IAAI,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;gBACrC,SAAS,CAAC,SAAS,EAAE,EAAE,SAAS,EAAE,KAAK,EAAE,CAAC,CAAC;gBAC3C,MAAM,CAAC,OAAO,CAAC,SAAS,EAAE,SAAS,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;gBAC1D,MAAM,QAAQ,GAAG,MAAM,CAAC,aAAa,CAAC,MAAM,CAAC,CAAC;gBAC9C,OAAO;oBACL,OAAO,EAAE;wBACP;4BACE,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE,aAAa,MAAM,uEAAuE,OAAO,CAAC,iBAAiB,IAAI,gBAAgB,KAAK,QAAQ,CAAC,CAAC,CAAC,oFAAoF,CAAC,CAAC,CAAC,0HAA0H,sBAAsB;yBACrY;qBACF;oBACD,OAAO,EAAE,EAAE,MAAM,EAAE,QAAQ,EAAE;iBAC9B,CAAC;YACJ,CAAC;oBAAS,CAAC;gBACT,OAAO,CAAC,OAAO,EAAE,CAAC;YACpB,CAAC;QACH,CAAC;KACF,CAAC,CAAC;AACL,CAAC"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"discovery.d.ts","sourceRoot":"","sources":["../../src/extensions/discovery.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,iCAAiC,CAAC;AAGpE,MAAM,CAAC,OAAO,UAAU,kBAAkB,CAAC,EAAE,EAAE,YAAY,GAAG,IAAI,
|
|
1
|
+
{"version":3,"file":"discovery.d.ts","sourceRoot":"","sources":["../../src/extensions/discovery.ts"],"names":[],"mappings":"AACA,OAAO,KAAK,EAAE,YAAY,EAAE,MAAM,iCAAiC,CAAC;AAGpE,MAAM,CAAC,OAAO,UAAU,kBAAkB,CAAC,EAAE,EAAE,YAAY,GAAG,IAAI,CAiEjE"}
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
import { writeFileSync } from "node:fs";
|
|
1
|
+
import { readFileSync, writeFileSync } from "node:fs";
|
|
2
2
|
import { Type } from "@sinclair/typebox";
|
|
3
3
|
export default function discoveryExtension(pi) {
|
|
4
4
|
pi.registerTool({
|
|
@@ -17,7 +17,6 @@ export default function discoveryExtension(pi) {
|
|
|
17
17
|
sourceUrl: Type.String({ minLength: 1 }),
|
|
18
18
|
baseCommit: Type.String({ pattern: "^[0-9a-fA-F]{40}$" }),
|
|
19
19
|
completedCommit: Type.String({ pattern: "^[0-9a-fA-F]{40}$" }),
|
|
20
|
-
request: Type.String({ minLength: 1 }),
|
|
21
20
|
provenance: Type.Object({
|
|
22
21
|
sourceType: Type.Union([
|
|
23
22
|
Type.Literal("pi"),
|
|
@@ -40,10 +39,18 @@ export default function discoveryExtension(pi) {
|
|
|
40
39
|
if (!candidates) {
|
|
41
40
|
throw new Error("submit_discovery received no candidates");
|
|
42
41
|
}
|
|
43
|
-
|
|
42
|
+
const exclusionsPath = process.env.SELFBENCH_DISCOVERY_EXCLUSIONS;
|
|
43
|
+
if (!exclusionsPath) {
|
|
44
|
+
throw new Error("SELFBENCH_DISCOVERY_EXCLUSIONS is not configured");
|
|
45
|
+
}
|
|
46
|
+
const excluded = new Set(JSON.parse(readFileSync(exclusionsPath, "utf8")));
|
|
47
|
+
const accepted = candidates.filter(({ sourcePr }) => sourcePr !== undefined && !excluded.has(sourcePr));
|
|
48
|
+
writeFileSync(output, `${JSON.stringify({ candidates: accepted }, null, 2)}\n`, {
|
|
49
|
+
flag: "wx",
|
|
50
|
+
});
|
|
44
51
|
return {
|
|
45
|
-
content: [{ type: "text", text: `Submitted ${
|
|
46
|
-
details: { candidates },
|
|
52
|
+
content: [{ type: "text", text: `Submitted ${accepted.length} new candidates.` }],
|
|
53
|
+
details: { candidates: accepted },
|
|
47
54
|
};
|
|
48
55
|
},
|
|
49
56
|
});
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"discovery.js","sourceRoot":"","sources":["../../src/extensions/discovery.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,MAAM,SAAS,CAAC;
|
|
1
|
+
{"version":3,"file":"discovery.js","sourceRoot":"","sources":["../../src/extensions/discovery.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,aAAa,EAAE,MAAM,SAAS,CAAC;AAEtD,OAAO,EAAE,IAAI,EAAE,MAAM,mBAAmB,CAAC;AAEzC,MAAM,CAAC,OAAO,UAAU,kBAAkB,CAAC,EAAgB;IACzD,EAAE,CAAC,YAAY,CAAC;QACd,IAAI,EAAE,kBAAkB;QACxB,KAAK,EAAE,4BAA4B;QACnC,WAAW,EAAE,6DAA6D;QAC1E,UAAU,EAAE,IAAI,CAAC,MAAM,CACrB;YACE,UAAU,EAAE,IAAI,CAAC,KAAK,CACpB,IAAI,CAAC,MAAM,CACT;gBACE,WAAW,EAAE,IAAI,CAAC,MAAM,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,CAAC;gBAC1C,UAAU,EAAE,IAAI,CAAC,KAAK,CAAC;oBACrB,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC;oBACpB,IAAI,CAAC,OAAO,CAAC,QAAQ,CAAC;oBACtB,IAAI,CAAC,OAAO,CAAC,MAAM,CAAC;iBACrB,CAAC;gBACF,QAAQ,EAAE,IAAI,CAAC,OAAO,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,CAAC;gBACtC,SAAS,EAAE,IAAI,CAAC,MAAM,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,CAAC;gBACxC,UAAU,EAAE,IAAI,CAAC,MAAM,CAAC,EAAE,OAAO,EAAE,mBAAmB,EAAE,CAAC;gBACzD,eAAe,EAAE,IAAI,CAAC,MAAM,CAAC,EAAE,OAAO,EAAE,mBAAmB,EAAE,CAAC;gBAC9D,UAAU,EAAE,IAAI,CAAC,MAAM,CAAC;oBACtB,UAAU,EAAE,IAAI,CAAC,KAAK,CAAC;wBACrB,IAAI,CAAC,OAAO,CAAC,IAAI,CAAC;wBAClB,IAAI,CAAC,OAAO,CAAC,aAAa,CAAC;wBAC3B,IAAI,CAAC,OAAO,CAAC,OAAO,CAAC;wBACrB,IAAI,CAAC,OAAO,CAAC,SAAS,CAAC;wBACvB,IAAI,CAAC,OAAO,CAAC,qBAAqB,CAAC;qBACpC,CAAC;oBACF,SAAS,EAAE,IAAI,CAAC,MAAM,CAAC,EAAE,SAAS,EAAE,CAAC,EAAE,CAAC;oBACxC,YAAY,EAAE,IAAI,CAAC,OAAO,CAAC,EAAE,OAAO,EAAE,CAAC,EAAE,CAAC;iBAC3C,CAAC;aACH,EACD,EAAE,oBAAoB,EAAE,KAAK,EAAE,CAChC,EACD,EAAE,QAAQ,EAAE,GAAG,EAAE,CAClB;SACF,EACD,EAAE,oBAAoB,EAAE,KAAK,EAAE,CAChC;QACD,KAAK,CAAC,OAAO,CAAC,WAAW,EAAE,KAAK;YAC9B,MAAM,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,0BAA0B,CAAC;YACtD,IAAI,CAAC,MAAM,EAAE,CAAC;gBACZ,MAAM,IAAI,KAAK,CAAC,8CAA8C,CAAC,CAAC;YAClE,CAAC;YACD,MAAM,UAAU,GAAG,KAAK,CAAC,UAAU,CAAC;YACpC,IAAI,CAAC,UAAU,EAAE,CAAC;gBAChB,MAAM,IAAI,KAAK,CAAC,yCAAyC,CAAC,CAAC;YAC7D,CAAC;YACD,MAAM,cAAc,GAAG,OAAO,CAAC,GAAG,CAAC,8BAA8B,CAAC;YAClE,IAAI,CAAC,cAAc,EAAE,CAAC;gBACpB,MAAM,IAAI,KAAK,CAAC,kDAAkD,CAAC,CAAC;YACtE,CAAC;YACD,MAAM,QAAQ,GAAG,IAAI,GAAG,CAAS,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,cAAc,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC;YACnF,MAAM,QAAQ,GAAG,UAAU,CAAC,MAAM,CAChC,CAAC,EAAE,QAAQ,EAAE,EAAE,EAAE,CAAC,QAAQ,KAAK,SAAS,IAAI,CAAC,QAAQ,CAAC,GAAG,CAAC,QAAQ,CAAC,CACpE,CAAC;YACF,aAAa,CAAC,MAAM,EAAE,GAAG,IAAI,CAAC,SAAS,CAAC,EAAE,UAAU,EAAE,QAAQ,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC,IAAI,EAAE;gBAC9E,IAAI,EAAE,IAAI;aACX,CAAC,CAAC;YACH,OAAO;gBACL,OAAO,EAAE,CAAC,EAAE,IAAI,EAAE,MAAM,EAAE,IAAI,EAAE,aAAa,QAAQ,CAAC,MAAM,kBAAkB,EAAE,CAAC;gBACjF,OAAO,EAAE,EAAE,UAAU,EAAE,QAAQ,EAAE;aAClC,CAAC;QACJ,CAAC;KACF,CAAC,CAAC;AACL,CAAC"}
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
import { type ToolFailure } from "./static-check.js";
|
|
2
|
+
export interface TaskDeliverable {
|
|
3
|
+
readonly definition: Record<string, unknown>;
|
|
4
|
+
readonly testPatch: string;
|
|
5
|
+
readonly goldPatch: string;
|
|
6
|
+
}
|
|
7
|
+
export declare const TASK_DELIVERABLE_FILES: readonly ["definition.json", "instruction.md", "test.patch", "gold.patch"];
|
|
8
|
+
/**
|
|
9
|
+
* Authoring deliverable: `<root>/definition.json` (schema 2 with the environment contract),
|
|
10
|
+
* `instruction.md`, `test.patch`, `gold.patch`. instruction.md is authoritative for the prompt:
|
|
11
|
+
* `definition.prompt` is derived from it and must match when present.
|
|
12
|
+
*/
|
|
13
|
+
export declare function loadTaskDeliverable(root: string): TaskDeliverable | ToolFailure;
|
|
14
|
+
export interface FixDeliverable {
|
|
15
|
+
readonly definition: Record<string, unknown>;
|
|
16
|
+
readonly testPatch: string;
|
|
17
|
+
readonly goldPatch: string;
|
|
18
|
+
readonly testPatchSource: "file" | "working-tree";
|
|
19
|
+
readonly original: {
|
|
20
|
+
definition: string;
|
|
21
|
+
testPatch: string;
|
|
22
|
+
goldPatch: string;
|
|
23
|
+
};
|
|
24
|
+
}
|
|
25
|
+
/**
|
|
26
|
+
* Verifier deliverable: `<fixRoot>/definition.json` (optional; only environment, testCommand,
|
|
27
|
+
* failToPass, passToPass, testPaths, timeouts, resources are read and merged onto the compiled
|
|
28
|
+
* task's definition) and `<fixRoot>/test.patch` (optional; regenerated with `git diff` from the
|
|
29
|
+
* repository working tree when absent).
|
|
30
|
+
*/
|
|
31
|
+
export declare function loadFixDeliverable(fixRoot: string, taskDirectory: string, repository: string): FixDeliverable | ToolFailure;
|
|
32
|
+
export declare function workingTreePatch(repository: string): string;
|
|
33
|
+
//# sourceMappingURL=deliverable.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"deliverable.d.ts","sourceRoot":"","sources":["../../../src/extensions/shared/deliverable.ts"],"names":[],"mappings":"AAIA,OAAO,EAAW,KAAK,WAAW,EAAE,MAAM,mBAAmB,CAAC;AAE9D,MAAM,WAAW,eAAe;IAC9B,QAAQ,CAAC,UAAU,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IAC7C,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;IAC3B,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;CAC5B;AAED,eAAO,MAAM,sBAAsB,4EAKzB,CAAC;AAEX;;;;GAIG;AACH,wBAAgB,mBAAmB,CAAC,IAAI,EAAE,MAAM,GAAG,eAAe,GAAG,WAAW,CA0C/E;AAED,MAAM,WAAW,cAAc;IAC7B,QAAQ,CAAC,UAAU,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IAC7C,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;IAC3B,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;IAC3B,QAAQ,CAAC,eAAe,EAAE,MAAM,GAAG,cAAc,CAAC;IAClD,QAAQ,CAAC,QAAQ,EAAE;QAAE,UAAU,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAC;QAAC,SAAS,EAAE,MAAM,CAAA;KAAE,CAAC;CACjF;AAED;;;;;GAKG;AACH,wBAAgB,kBAAkB,CAChC,OAAO,EAAE,MAAM,EACf,aAAa,EAAE,MAAM,EACrB,UAAU,EAAE,MAAM,GACjB,cAAc,GAAG,WAAW,CAyC9B;AAED,wBAAgB,gBAAgB,CAAC,UAAU,EAAE,MAAM,GAAG,MAAM,CAiB3D"}
|
|
@@ -0,0 +1,123 @@
|
|
|
1
|
+
import { spawnSync } from "node:child_process";
|
|
2
|
+
import { existsSync, readFileSync } from "node:fs";
|
|
3
|
+
import { join } from "node:path";
|
|
4
|
+
import { FIX_FIELDS } from "./schemas.js";
|
|
5
|
+
import { failure } from "./static-check.js";
|
|
6
|
+
export const TASK_DELIVERABLE_FILES = [
|
|
7
|
+
"definition.json",
|
|
8
|
+
"instruction.md",
|
|
9
|
+
"test.patch",
|
|
10
|
+
"gold.patch",
|
|
11
|
+
];
|
|
12
|
+
/**
|
|
13
|
+
* Authoring deliverable: `<root>/definition.json` (schema 2 with the environment contract),
|
|
14
|
+
* `instruction.md`, `test.patch`, `gold.patch`. instruction.md is authoritative for the prompt:
|
|
15
|
+
* `definition.prompt` is derived from it and must match when present.
|
|
16
|
+
*/
|
|
17
|
+
export function loadTaskDeliverable(root) {
|
|
18
|
+
const missing = TASK_DELIVERABLE_FILES.filter((name) => !existsSync(join(root, name)));
|
|
19
|
+
if (missing.length > 0) {
|
|
20
|
+
return deliverableFailure(root, missing.map((name) => `${name} is missing`));
|
|
21
|
+
}
|
|
22
|
+
let definition;
|
|
23
|
+
try {
|
|
24
|
+
const parsed = JSON.parse(readFileSync(join(root, "definition.json"), "utf8"));
|
|
25
|
+
if (typeof parsed !== "object" || parsed === null || Array.isArray(parsed)) {
|
|
26
|
+
throw new Error("must be a JSON object");
|
|
27
|
+
}
|
|
28
|
+
definition = parsed;
|
|
29
|
+
}
|
|
30
|
+
catch (error) {
|
|
31
|
+
return deliverableFailure(root, [
|
|
32
|
+
`definition.json is not valid JSON: ${error instanceof Error ? error.message : String(error)}`,
|
|
33
|
+
]);
|
|
34
|
+
}
|
|
35
|
+
const instruction = readFileSync(join(root, "instruction.md"), "utf8").trim();
|
|
36
|
+
const testPatch = readFileSync(join(root, "test.patch"), "utf8");
|
|
37
|
+
const goldPatch = readFileSync(join(root, "gold.patch"), "utf8");
|
|
38
|
+
const problems = [];
|
|
39
|
+
if (!instruction) {
|
|
40
|
+
problems.push("instruction.md is empty");
|
|
41
|
+
}
|
|
42
|
+
if (typeof definition.prompt === "string" && definition.prompt.trim() !== instruction) {
|
|
43
|
+
problems.push("definition.json prompt differs from instruction.md; remove prompt or make them identical");
|
|
44
|
+
}
|
|
45
|
+
if (!testPatch.trim()) {
|
|
46
|
+
problems.push("test.patch is empty");
|
|
47
|
+
}
|
|
48
|
+
if (!goldPatch.trim()) {
|
|
49
|
+
problems.push("gold.patch is empty");
|
|
50
|
+
}
|
|
51
|
+
if (problems.length > 0) {
|
|
52
|
+
return deliverableFailure(root, problems);
|
|
53
|
+
}
|
|
54
|
+
return { definition: { ...definition, prompt: instruction }, testPatch, goldPatch };
|
|
55
|
+
}
|
|
56
|
+
/**
|
|
57
|
+
* Verifier deliverable: `<fixRoot>/definition.json` (optional; only environment, testCommand,
|
|
58
|
+
* failToPass, passToPass, testPaths, timeouts, resources are read and merged onto the compiled
|
|
59
|
+
* task's definition) and `<fixRoot>/test.patch` (optional; regenerated with `git diff` from the
|
|
60
|
+
* repository working tree when absent).
|
|
61
|
+
*/
|
|
62
|
+
export function loadFixDeliverable(fixRoot, taskDirectory, repository) {
|
|
63
|
+
const originalDefinition = join(taskDirectory, "definition.json");
|
|
64
|
+
const definition = JSON.parse(readFileSync(originalDefinition, "utf8"));
|
|
65
|
+
const fixDefinitionPath = join(fixRoot, "definition.json");
|
|
66
|
+
if (existsSync(fixDefinitionPath)) {
|
|
67
|
+
let fix;
|
|
68
|
+
try {
|
|
69
|
+
fix = JSON.parse(readFileSync(fixDefinitionPath, "utf8"));
|
|
70
|
+
}
|
|
71
|
+
catch (error) {
|
|
72
|
+
return deliverableFailure(fixRoot, [
|
|
73
|
+
`definition.json is not valid JSON: ${error instanceof Error ? error.message : String(error)}`,
|
|
74
|
+
]);
|
|
75
|
+
}
|
|
76
|
+
for (const field of FIX_FIELDS) {
|
|
77
|
+
if (fix[field] !== undefined) {
|
|
78
|
+
definition[field] = fix[field];
|
|
79
|
+
}
|
|
80
|
+
}
|
|
81
|
+
}
|
|
82
|
+
const testPatchPath = join(fixRoot, "test.patch");
|
|
83
|
+
const fromFile = existsSync(testPatchPath);
|
|
84
|
+
const testPatch = fromFile ? readFileSync(testPatchPath, "utf8") : workingTreePatch(repository);
|
|
85
|
+
if (!testPatch.trim()) {
|
|
86
|
+
return deliverableFailure(fixRoot, [
|
|
87
|
+
fromFile ? "test.patch is empty" : "test.patch is absent and /work/repo has no changes",
|
|
88
|
+
]);
|
|
89
|
+
}
|
|
90
|
+
return {
|
|
91
|
+
definition,
|
|
92
|
+
testPatch,
|
|
93
|
+
goldPatch: readFileSync(join(taskDirectory, "solution/gold.patch"), "utf8"),
|
|
94
|
+
testPatchSource: fromFile ? "file" : "working-tree",
|
|
95
|
+
original: {
|
|
96
|
+
definition: originalDefinition,
|
|
97
|
+
testPatch: join(taskDirectory, "tests/test.patch"),
|
|
98
|
+
goldPatch: join(taskDirectory, "solution/gold.patch"),
|
|
99
|
+
},
|
|
100
|
+
};
|
|
101
|
+
}
|
|
102
|
+
export function workingTreePatch(repository) {
|
|
103
|
+
for (const args of [
|
|
104
|
+
["add", "-N", "--all"],
|
|
105
|
+
["diff", "--binary", "HEAD"],
|
|
106
|
+
]) {
|
|
107
|
+
const result = spawnSync("git", ["-C", repository, ...args], {
|
|
108
|
+
encoding: "utf8",
|
|
109
|
+
maxBuffer: 256 * 1024 * 1024,
|
|
110
|
+
});
|
|
111
|
+
if (result.status !== 0) {
|
|
112
|
+
throw new Error(`git ${args[0]} failed: ${result.stderr.slice(-2_000)}`);
|
|
113
|
+
}
|
|
114
|
+
if (args[0] === "diff") {
|
|
115
|
+
return result.stdout;
|
|
116
|
+
}
|
|
117
|
+
}
|
|
118
|
+
return "";
|
|
119
|
+
}
|
|
120
|
+
function deliverableFailure(root, problems) {
|
|
121
|
+
return failure(`The deliverable in ${root} is incomplete; nothing was recorded. Fix every item and call the tool again:\n${problems.map((problem) => `- [files] ${problem}`).join("\n")}`);
|
|
122
|
+
}
|
|
123
|
+
//# sourceMappingURL=deliverable.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"deliverable.js","sourceRoot":"","sources":["../../../src/extensions/shared/deliverable.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,SAAS,EAAE,MAAM,oBAAoB,CAAC;AAC/C,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,MAAM,SAAS,CAAC;AACnD,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AACjC,OAAO,EAAE,UAAU,EAAE,MAAM,cAAc,CAAC;AAC1C,OAAO,EAAE,OAAO,EAAoB,MAAM,mBAAmB,CAAC;AAQ9D,MAAM,CAAC,MAAM,sBAAsB,GAAG;IACpC,iBAAiB;IACjB,gBAAgB;IAChB,YAAY;IACZ,YAAY;CACJ,CAAC;AAEX;;;;GAIG;AACH,MAAM,UAAU,mBAAmB,CAAC,IAAY;IAC9C,MAAM,OAAO,GAAG,sBAAsB,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,EAAE,IAAI,CAAC,CAAC,CAAC,CAAC;IACvF,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACvB,OAAO,kBAAkB,CACvB,IAAI,EACJ,OAAO,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,GAAG,IAAI,aAAa,CAAC,CAC5C,CAAC;IACJ,CAAC;IACD,IAAI,UAAmC,CAAC;IACxC,IAAI,CAAC;QACH,MAAM,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,IAAI,CAAC,IAAI,EAAE,iBAAiB,CAAC,EAAE,MAAM,CAAC,CAAY,CAAC;QAC1F,IAAI,OAAO,MAAM,KAAK,QAAQ,IAAI,MAAM,KAAK,IAAI,IAAI,KAAK,CAAC,OAAO,CAAC,MAAM,CAAC,EAAE,CAAC;YAC3E,MAAM,IAAI,KAAK,CAAC,uBAAuB,CAAC,CAAC;QAC3C,CAAC;QACD,UAAU,GAAG,MAAiC,CAAC;IACjD,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,OAAO,kBAAkB,CAAC,IAAI,EAAE;YAC9B,sCAAsC,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE;SAC/F,CAAC,CAAC;IACL,CAAC;IACD,MAAM,WAAW,GAAG,YAAY,CAAC,IAAI,CAAC,IAAI,EAAE,gBAAgB,CAAC,EAAE,MAAM,CAAC,CAAC,IAAI,EAAE,CAAC;IAC9E,MAAM,SAAS,GAAG,YAAY,CAAC,IAAI,CAAC,IAAI,EAAE,YAAY,CAAC,EAAE,MAAM,CAAC,CAAC;IACjE,MAAM,SAAS,GAAG,YAAY,CAAC,IAAI,CAAC,IAAI,EAAE,YAAY,CAAC,EAAE,MAAM,CAAC,CAAC;IACjE,MAAM,QAAQ,GAAa,EAAE,CAAC;IAC9B,IAAI,CAAC,WAAW,EAAE,CAAC;QACjB,QAAQ,CAAC,IAAI,CAAC,yBAAyB,CAAC,CAAC;IAC3C,CAAC;IACD,IAAI,OAAO,UAAU,CAAC,MAAM,KAAK,QAAQ,IAAI,UAAU,CAAC,MAAM,CAAC,IAAI,EAAE,KAAK,WAAW,EAAE,CAAC;QACtF,QAAQ,CAAC,IAAI,CACX,0FAA0F,CAC3F,CAAC;IACJ,CAAC;IACD,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,EAAE,CAAC;QACtB,QAAQ,CAAC,IAAI,CAAC,qBAAqB,CAAC,CAAC;IACvC,CAAC;IACD,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,EAAE,CAAC;QACtB,QAAQ,CAAC,IAAI,CAAC,qBAAqB,CAAC,CAAC;IACvC,CAAC;IACD,IAAI,QAAQ,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACxB,OAAO,kBAAkB,CAAC,IAAI,EAAE,QAAQ,CAAC,CAAC;IAC5C,CAAC;IACD,OAAO,EAAE,UAAU,EAAE,EAAE,GAAG,UAAU,EAAE,MAAM,EAAE,WAAW,EAAE,EAAE,SAAS,EAAE,SAAS,EAAE,CAAC;AACtF,CAAC;AAUD;;;;;GAKG;AACH,MAAM,UAAU,kBAAkB,CAChC,OAAe,EACf,aAAqB,EACrB,UAAkB;IAElB,MAAM,kBAAkB,GAAG,IAAI,CAAC,aAAa,EAAE,iBAAiB,CAAC,CAAC;IAClE,MAAM,UAAU,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,kBAAkB,EAAE,MAAM,CAAC,CAGrE,CAAC;IACF,MAAM,iBAAiB,GAAG,IAAI,CAAC,OAAO,EAAE,iBAAiB,CAAC,CAAC;IAC3D,IAAI,UAAU,CAAC,iBAAiB,CAAC,EAAE,CAAC;QAClC,IAAI,GAA4B,CAAC;QACjC,IAAI,CAAC;YACH,GAAG,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,iBAAiB,EAAE,MAAM,CAAC,CAA4B,CAAC;QACvF,CAAC;QAAC,OAAO,KAAK,EAAE,CAAC;YACf,OAAO,kBAAkB,CAAC,OAAO,EAAE;gBACjC,sCAAsC,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,EAAE;aAC/F,CAAC,CAAC;QACL,CAAC;QACD,KAAK,MAAM,KAAK,IAAI,UAAU,EAAE,CAAC;YAC/B,IAAI,GAAG,CAAC,KAAK,CAAC,KAAK,SAAS,EAAE,CAAC;gBAC7B,UAAU,CAAC,KAAK,CAAC,GAAG,GAAG,CAAC,KAAK,CAAC,CAAC;YACjC,CAAC;QACH,CAAC;IACH,CAAC;IACD,MAAM,aAAa,GAAG,IAAI,CAAC,OAAO,EAAE,YAAY,CAAC,CAAC;IAClD,MAAM,QAAQ,GAAG,UAAU,CAAC,aAAa,CAAC,CAAC;IAC3C,MAAM,SAAS,GAAG,QAAQ,CAAC,CAAC,CAAC,YAAY,CAAC,aAAa,EAAE,MAAM,CAAC,CAAC,CAAC,CAAC,gBAAgB,CAAC,UAAU,CAAC,CAAC;IAChG,IAAI,CAAC,SAAS,CAAC,IAAI,EAAE,EAAE,CAAC;QACtB,OAAO,kBAAkB,CAAC,OAAO,EAAE;YACjC,QAAQ,CAAC,CAAC,CAAC,qBAAqB,CAAC,CAAC,CAAC,oDAAoD;SACxF,CAAC,CAAC;IACL,CAAC;IACD,OAAO;QACL,UAAU;QACV,SAAS;QACT,SAAS,EAAE,YAAY,CAAC,IAAI,CAAC,aAAa,EAAE,qBAAqB,CAAC,EAAE,MAAM,CAAC;QAC3E,eAAe,EAAE,QAAQ,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,cAAc;QACnD,QAAQ,EAAE;YACR,UAAU,EAAE,kBAAkB;YAC9B,SAAS,EAAE,IAAI,CAAC,aAAa,EAAE,kBAAkB,CAAC;YAClD,SAAS,EAAE,IAAI,CAAC,aAAa,EAAE,qBAAqB,CAAC;SACtD;KACF,CAAC;AACJ,CAAC;AAED,MAAM,UAAU,gBAAgB,CAAC,UAAkB;IACjD,KAAK,MAAM,IAAI,IAAI;QACjB,CAAC,KAAK,EAAE,IAAI,EAAE,OAAO,CAAC;QACtB,CAAC,MAAM,EAAE,UAAU,EAAE,MAAM,CAAC;KAC7B,EAAE,CAAC;QACF,MAAM,MAAM,GAAG,SAAS,CAAC,KAAK,EAAE,CAAC,IAAI,EAAE,UAAU,EAAE,GAAG,IAAI,CAAC,EAAE;YAC3D,QAAQ,EAAE,MAAM;YAChB,SAAS,EAAE,GAAG,GAAG,IAAI,GAAG,IAAI;SAC7B,CAAC,CAAC;QACH,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;YACxB,MAAM,IAAI,KAAK,CAAC,OAAO,IAAI,CAAC,CAAC,CAAC,YAAY,MAAM,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;QAC3E,CAAC;QACD,IAAI,IAAI,CAAC,CAAC,CAAC,KAAK,MAAM,EAAE,CAAC;YACvB,OAAO,MAAM,CAAC,MAAM,CAAC;QACvB,CAAC;IACH,CAAC;IACD,OAAO,EAAE,CAAC;AACZ,CAAC;AAED,SAAS,kBAAkB,CAAC,IAAY,EAAE,QAA2B;IACnE,OAAO,OAAO,CACZ,sBAAsB,IAAI,kFAAkF,QAAQ,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,aAAa,OAAO,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAC3K,CAAC;AACJ,CAAC"}
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
export interface VerifyPayload {
|
|
2
|
+
readonly definition: unknown;
|
|
3
|
+
readonly testPatch: string;
|
|
4
|
+
readonly goldPatch: string;
|
|
5
|
+
}
|
|
6
|
+
export type VerifyOutcome = {
|
|
7
|
+
readonly kind: "report";
|
|
8
|
+
readonly green: boolean;
|
|
9
|
+
readonly summary: string;
|
|
10
|
+
readonly rendered: string;
|
|
11
|
+
readonly remaining: number;
|
|
12
|
+
} | {
|
|
13
|
+
readonly kind: "error";
|
|
14
|
+
readonly message: string;
|
|
15
|
+
} | {
|
|
16
|
+
readonly kind: "exhausted";
|
|
17
|
+
};
|
|
18
|
+
/** Same formula as src/submission-hash.ts on the worker. */
|
|
19
|
+
export declare function payloadHash(payload: VerifyPayload): string;
|
|
20
|
+
/**
|
|
21
|
+
* Sandbox side of the worker mailbox: writes a verify request the supervising activity picks up,
|
|
22
|
+
* then blocks until the response arrives. Reports consume the per-session budget; worker errors
|
|
23
|
+
* and budget exhaustion do not.
|
|
24
|
+
*/
|
|
25
|
+
export declare class VerifyClient {
|
|
26
|
+
#private;
|
|
27
|
+
get remaining(): number;
|
|
28
|
+
/** Whether this exact payload was verified green in this session. */
|
|
29
|
+
verifiedGreen(payload: VerifyPayload): boolean;
|
|
30
|
+
verify(kind: "task" | "fix", payload: VerifyPayload): Promise<VerifyOutcome>;
|
|
31
|
+
}
|
|
32
|
+
export declare function verifyOutcomeText(outcome: VerifyOutcome, submitTool: string): string;
|
|
33
|
+
//# sourceMappingURL=mailbox.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"mailbox.d.ts","sourceRoot":"","sources":["../../../src/extensions/shared/mailbox.ts"],"names":[],"mappings":"AAQA,MAAM,WAAW,aAAa;IAC5B,QAAQ,CAAC,UAAU,EAAE,OAAO,CAAC;IAC7B,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;IAC3B,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;CAC5B;AAED,MAAM,MAAM,aAAa,GACrB;IACE,QAAQ,CAAC,IAAI,EAAE,QAAQ,CAAC;IACxB,QAAQ,CAAC,KAAK,EAAE,OAAO,CAAC;IACxB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;IACzB,QAAQ,CAAC,QAAQ,EAAE,MAAM,CAAC;IAC1B,QAAQ,CAAC,SAAS,EAAE,MAAM,CAAC;CAC5B,GACD;IAAE,QAAQ,CAAC,IAAI,EAAE,OAAO,CAAC;IAAC,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAA;CAAE,GACpD;IAAE,QAAQ,CAAC,IAAI,EAAE,WAAW,CAAA;CAAE,CAAC;AAEnC,4DAA4D;AAC5D,wBAAgB,WAAW,CAAC,OAAO,EAAE,aAAa,GAAG,MAAM,CAI1D;AAED;;;;GAIG;AACH,qBAAa,YAAY;;IAWvB,IAAI,SAAS,IAAI,MAAM,CAEtB;IAED,qEAAqE;IACrE,aAAa,CAAC,OAAO,EAAE,aAAa,GAAG,OAAO;IAIxC,MAAM,CAAC,IAAI,EAAE,MAAM,GAAG,KAAK,EAAE,OAAO,EAAE,aAAa,GAAG,OAAO,CAAC,aAAa,CAAC;CAyDnF;AAED,wBAAgB,iBAAiB,CAAC,OAAO,EAAE,aAAa,EAAE,UAAU,EAAE,MAAM,GAAG,MAAM,CAWpF"}
|
|
@@ -0,0 +1,102 @@
|
|
|
1
|
+
import { createHash } from "node:crypto";
|
|
2
|
+
import { existsSync, mkdirSync, readFileSync, renameSync, writeFileSync } from "node:fs";
|
|
3
|
+
import { join } from "node:path";
|
|
4
|
+
const DEFAULT_MAILBOX = "/work/mailbox";
|
|
5
|
+
const DEFAULT_POLL_MS = 2_000;
|
|
6
|
+
const DEFAULT_TIMEOUT_MS = 60 * 60 * 1_000;
|
|
7
|
+
/** Same formula as src/submission-hash.ts on the worker. */
|
|
8
|
+
export function payloadHash(payload) {
|
|
9
|
+
return createHash("sha256")
|
|
10
|
+
.update(`${JSON.stringify(payload.definition)}\0${payload.testPatch}\0${payload.goldPatch}`)
|
|
11
|
+
.digest("hex");
|
|
12
|
+
}
|
|
13
|
+
/**
|
|
14
|
+
* Sandbox side of the worker mailbox: writes a verify request the supervising activity picks up,
|
|
15
|
+
* then blocks until the response arrives. Reports consume the per-session budget; worker errors
|
|
16
|
+
* and budget exhaustion do not.
|
|
17
|
+
*/
|
|
18
|
+
export class VerifyClient {
|
|
19
|
+
#mailbox = process.env.SELFBENCH_MAILBOX ?? DEFAULT_MAILBOX;
|
|
20
|
+
#budget = Number(process.env.SELFBENCH_VERIFY_BUDGET ?? "0");
|
|
21
|
+
#pollMs = Number(process.env.SELFBENCH_VERIFY_POLL_MS ?? String(DEFAULT_POLL_MS));
|
|
22
|
+
#timeoutMs = Number(process.env.SELFBENCH_VERIFY_TIMEOUT_MS ?? String(DEFAULT_TIMEOUT_MS));
|
|
23
|
+
#used = 0;
|
|
24
|
+
#sequence = 0;
|
|
25
|
+
#lastGreenHash;
|
|
26
|
+
get remaining() {
|
|
27
|
+
return Math.max(0, this.#budget - this.#used);
|
|
28
|
+
}
|
|
29
|
+
/** Whether this exact payload was verified green in this session. */
|
|
30
|
+
verifiedGreen(payload) {
|
|
31
|
+
return this.#lastGreenHash !== undefined && this.#lastGreenHash === payloadHash(payload);
|
|
32
|
+
}
|
|
33
|
+
async verify(kind, payload) {
|
|
34
|
+
if (this.remaining === 0) {
|
|
35
|
+
return { kind: "exhausted" };
|
|
36
|
+
}
|
|
37
|
+
const requests = join(this.#mailbox, "requests");
|
|
38
|
+
const responses = join(this.#mailbox, "responses");
|
|
39
|
+
mkdirSync(requests, { recursive: true });
|
|
40
|
+
mkdirSync(responses, { recursive: true });
|
|
41
|
+
this.#sequence += 1;
|
|
42
|
+
const id = `${Date.now()}-${this.#sequence}`;
|
|
43
|
+
const request = join(requests, `${id}.json`);
|
|
44
|
+
writeFileSync(`${request}.tmp`, `${JSON.stringify({ id, kind, ...payload })}\n`);
|
|
45
|
+
renameSync(`${request}.tmp`, request);
|
|
46
|
+
const response = join(responses, `${id}.json`);
|
|
47
|
+
const deadline = Date.now() + this.#timeoutMs;
|
|
48
|
+
while (Date.now() < deadline) {
|
|
49
|
+
if (existsSync(response)) {
|
|
50
|
+
let parsed;
|
|
51
|
+
try {
|
|
52
|
+
parsed = JSON.parse(readFileSync(response, "utf8"));
|
|
53
|
+
}
|
|
54
|
+
catch {
|
|
55
|
+
parsed = undefined;
|
|
56
|
+
}
|
|
57
|
+
if (parsed && typeof parsed === "object") {
|
|
58
|
+
return this.#record(parsed, payload);
|
|
59
|
+
}
|
|
60
|
+
}
|
|
61
|
+
await new Promise((resolve) => setTimeout(resolve, this.#pollMs));
|
|
62
|
+
}
|
|
63
|
+
this.#used += 1;
|
|
64
|
+
return {
|
|
65
|
+
kind: "error",
|
|
66
|
+
message: `verify timed out after ${Math.round(this.#timeoutMs / 60_000)} minutes; the worker may still be building. ${this.remaining} verify call(s) remain.`,
|
|
67
|
+
};
|
|
68
|
+
}
|
|
69
|
+
#record(response, payload) {
|
|
70
|
+
if (response.kind !== "report") {
|
|
71
|
+
return {
|
|
72
|
+
kind: "error",
|
|
73
|
+
message: typeof response.message === "string" ? response.message : "verify failed on the worker",
|
|
74
|
+
};
|
|
75
|
+
}
|
|
76
|
+
this.#used += 1;
|
|
77
|
+
const green = response.green === true;
|
|
78
|
+
if (green) {
|
|
79
|
+
this.#lastGreenHash = payloadHash(payload);
|
|
80
|
+
}
|
|
81
|
+
return {
|
|
82
|
+
kind: "report",
|
|
83
|
+
green,
|
|
84
|
+
summary: typeof response.summary === "string" ? response.summary : "",
|
|
85
|
+
rendered: typeof response.rendered === "string" ? response.rendered : "",
|
|
86
|
+
remaining: this.remaining,
|
|
87
|
+
};
|
|
88
|
+
}
|
|
89
|
+
}
|
|
90
|
+
export function verifyOutcomeText(outcome, submitTool) {
|
|
91
|
+
if (outcome.kind === "exhausted") {
|
|
92
|
+
return `No verify calls remain in this session. Call ${submitTool} with your best task or explain in your final message why it cannot be made fair.`;
|
|
93
|
+
}
|
|
94
|
+
if (outcome.kind === "error") {
|
|
95
|
+
return `verify could not complete: ${outcome.message}`;
|
|
96
|
+
}
|
|
97
|
+
const next = outcome.green
|
|
98
|
+
? `Call ${submitTool} with exactly this payload to record it; the worker will reuse this report.`
|
|
99
|
+
: `Fix the red gates and call verify again, or ${submitTool} if you must (the worker verifies again and a round is spent if it fails).`;
|
|
100
|
+
return `${outcome.rendered.trim()}\n\nverify result: green=${outcome.green}. ${outcome.remaining} verify call(s) remain in this session. ${next}`;
|
|
101
|
+
}
|
|
102
|
+
//# sourceMappingURL=mailbox.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"mailbox.js","sourceRoot":"","sources":["../../../src/extensions/shared/mailbox.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AACzC,OAAO,EAAE,UAAU,EAAE,SAAS,EAAE,YAAY,EAAE,UAAU,EAAE,aAAa,EAAE,MAAM,SAAS,CAAC;AACzF,OAAO,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAEjC,MAAM,eAAe,GAAG,eAAe,CAAC;AACxC,MAAM,eAAe,GAAG,KAAK,CAAC;AAC9B,MAAM,kBAAkB,GAAG,EAAE,GAAG,EAAE,GAAG,KAAK,CAAC;AAmB3C,4DAA4D;AAC5D,MAAM,UAAU,WAAW,CAAC,OAAsB;IAChD,OAAO,UAAU,CAAC,QAAQ,CAAC;SACxB,MAAM,CAAC,GAAG,IAAI,CAAC,SAAS,CAAC,OAAO,CAAC,UAAU,CAAC,KAAK,OAAO,CAAC,SAAS,KAAK,OAAO,CAAC,SAAS,EAAE,CAAC;SAC3F,MAAM,CAAC,KAAK,CAAC,CAAC;AACnB,CAAC;AAED;;;;GAIG;AACH,MAAM,OAAO,YAAY;IACd,QAAQ,GAAG,OAAO,CAAC,GAAG,CAAC,iBAAiB,IAAI,eAAe,CAAC;IAC5D,OAAO,GAAG,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,uBAAuB,IAAI,GAAG,CAAC,CAAC;IAC7D,OAAO,GAAG,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,wBAAwB,IAAI,MAAM,CAAC,eAAe,CAAC,CAAC,CAAC;IAClF,UAAU,GAAG,MAAM,CAC1B,OAAO,CAAC,GAAG,CAAC,2BAA2B,IAAI,MAAM,CAAC,kBAAkB,CAAC,CACtE,CAAC;IACF,KAAK,GAAG,CAAC,CAAC;IACV,SAAS,GAAG,CAAC,CAAC;IACd,cAAc,CAAqB;IAEnC,IAAI,SAAS;QACX,OAAO,IAAI,CAAC,GAAG,CAAC,CAAC,EAAE,IAAI,CAAC,OAAO,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC;IAChD,CAAC;IAED,qEAAqE;IACrE,aAAa,CAAC,OAAsB;QAClC,OAAO,IAAI,CAAC,cAAc,KAAK,SAAS,IAAI,IAAI,CAAC,cAAc,KAAK,WAAW,CAAC,OAAO,CAAC,CAAC;IAC3F,CAAC;IAED,KAAK,CAAC,MAAM,CAAC,IAAoB,EAAE,OAAsB;QACvD,IAAI,IAAI,CAAC,SAAS,KAAK,CAAC,EAAE,CAAC;YACzB,OAAO,EAAE,IAAI,EAAE,WAAW,EAAE,CAAC;QAC/B,CAAC;QACD,MAAM,QAAQ,GAAG,IAAI,CAAC,IAAI,CAAC,QAAQ,EAAE,UAAU,CAAC,CAAC;QACjD,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,QAAQ,EAAE,WAAW,CAAC,CAAC;QACnD,SAAS,CAAC,QAAQ,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;QACzC,SAAS,CAAC,SAAS,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;QAC1C,IAAI,CAAC,SAAS,IAAI,CAAC,CAAC;QACpB,MAAM,EAAE,GAAG,GAAG,IAAI,CAAC,GAAG,EAAE,IAAI,IAAI,CAAC,SAAS,EAAE,CAAC;QAC7C,MAAM,OAAO,GAAG,IAAI,CAAC,QAAQ,EAAE,GAAG,EAAE,OAAO,CAAC,CAAC;QAC7C,aAAa,CAAC,GAAG,OAAO,MAAM,EAAE,GAAG,IAAI,CAAC,SAAS,CAAC,EAAE,EAAE,EAAE,IAAI,EAAE,GAAG,OAAO,EAAE,CAAC,IAAI,CAAC,CAAC;QACjF,UAAU,CAAC,GAAG,OAAO,MAAM,EAAE,OAAO,CAAC,CAAC;QACtC,MAAM,QAAQ,GAAG,IAAI,CAAC,SAAS,EAAE,GAAG,EAAE,OAAO,CAAC,CAAC;QAC/C,MAAM,QAAQ,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,IAAI,CAAC,UAAU,CAAC;QAC9C,OAAO,IAAI,CAAC,GAAG,EAAE,GAAG,QAAQ,EAAE,CAAC;YAC7B,IAAI,UAAU,CAAC,QAAQ,CAAC,EAAE,CAAC;gBACzB,IAAI,MAAe,CAAC;gBACpB,IAAI,CAAC;oBACH,MAAM,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,QAAQ,EAAE,MAAM,CAAC,CAAC,CAAC;gBACtD,CAAC;gBAAC,MAAM,CAAC;oBACP,MAAM,GAAG,SAAS,CAAC;gBACrB,CAAC;gBACD,IAAI,MAAM,IAAI,OAAO,MAAM,KAAK,QAAQ,EAAE,CAAC;oBACzC,OAAO,IAAI,CAAC,OAAO,CAAC,MAAiC,EAAE,OAAO,CAAC,CAAC;gBAClE,CAAC;YACH,CAAC;YACD,MAAM,IAAI,OAAO,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,UAAU,CAAC,OAAO,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC,CAAC;QACpE,CAAC;QACD,IAAI,CAAC,KAAK,IAAI,CAAC,CAAC;QAChB,OAAO;YACL,IAAI,EAAE,OAAO;YACb,OAAO,EAAE,0BAA0B,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,UAAU,GAAG,MAAM,CAAC,+CAA+C,IAAI,CAAC,SAAS,yBAAyB;SAC9J,CAAC;IACJ,CAAC;IAED,OAAO,CAAC,QAAiC,EAAE,OAAsB;QAC/D,IAAI,QAAQ,CAAC,IAAI,KAAK,QAAQ,EAAE,CAAC;YAC/B,OAAO;gBACL,IAAI,EAAE,OAAO;gBACb,OAAO,EACL,OAAO,QAAQ,CAAC,OAAO,KAAK,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAC,6BAA6B;aAC1F,CAAC;QACJ,CAAC;QACD,IAAI,CAAC,KAAK,IAAI,CAAC,CAAC;QAChB,MAAM,KAAK,GAAG,QAAQ,CAAC,KAAK,KAAK,IAAI,CAAC;QACtC,IAAI,KAAK,EAAE,CAAC;YACV,IAAI,CAAC,cAAc,GAAG,WAAW,CAAC,OAAO,CAAC,CAAC;QAC7C,CAAC;QACD,OAAO;YACL,IAAI,EAAE,QAAQ;YACd,KAAK;YACL,OAAO,EAAE,OAAO,QAAQ,CAAC,OAAO,KAAK,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAC,CAAC,EAAE;YACrE,QAAQ,EAAE,OAAO,QAAQ,CAAC,QAAQ,KAAK,QAAQ,CAAC,CAAC,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC,EAAE;YACxE,SAAS,EAAE,IAAI,CAAC,SAAS;SAC1B,CAAC;IACJ,CAAC;CACF;AAED,MAAM,UAAU,iBAAiB,CAAC,OAAsB,EAAE,UAAkB;IAC1E,IAAI,OAAO,CAAC,IAAI,KAAK,WAAW,EAAE,CAAC;QACjC,OAAO,gDAAgD,UAAU,mFAAmF,CAAC;IACvJ,CAAC;IACD,IAAI,OAAO,CAAC,IAAI,KAAK,OAAO,EAAE,CAAC;QAC7B,OAAO,8BAA8B,OAAO,CAAC,OAAO,EAAE,CAAC;IACzD,CAAC;IACD,MAAM,IAAI,GAAG,OAAO,CAAC,KAAK;QACxB,CAAC,CAAC,QAAQ,UAAU,6EAA6E;QACjG,CAAC,CAAC,+CAA+C,UAAU,4EAA4E,CAAC;IAC1I,OAAO,GAAG,OAAO,CAAC,QAAQ,CAAC,IAAI,EAAE,4BAA4B,OAAO,CAAC,KAAK,KAAK,OAAO,CAAC,SAAS,2CAA2C,IAAI,EAAE,CAAC;AACpJ,CAAC"}
|