self-bench 0.3.6 → 0.3.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.dockerignore +11 -1
- package/Dockerfile +9 -9
- package/Dockerfile.sandbox +5 -4
- package/README.md +27 -12
- package/bun.lock +462 -95
- package/compose.yaml +64 -20
- package/dist/agent-feed.d.ts +8 -0
- package/dist/agent-feed.d.ts.map +1 -0
- package/dist/agent-feed.js +56 -0
- package/dist/agent-feed.js.map +1 -0
- package/dist/api/http.d.ts +18 -0
- package/dist/api/http.d.ts.map +1 -0
- package/dist/api/http.js +111 -0
- package/dist/api/http.js.map +1 -0
- package/dist/api/run-request.d.ts +37 -0
- package/dist/api/run-request.d.ts.map +1 -0
- package/dist/api/run-request.js +59 -0
- package/dist/api/run-request.js.map +1 -0
- package/dist/api/status.d.ts +4 -0
- package/dist/api/status.d.ts.map +1 -0
- package/dist/api/status.js +36 -0
- package/dist/api/status.js.map +1 -0
- package/dist/api/viewer-routes.d.ts +9 -0
- package/dist/api/viewer-routes.d.ts.map +1 -0
- package/dist/api/viewer-routes.js +98 -0
- package/dist/api/viewer-routes.js.map +1 -0
- package/dist/api-main.js +5 -1
- package/dist/api-main.js.map +1 -1
- package/dist/api.d.ts +7 -25
- package/dist/api.d.ts.map +1 -1
- package/dist/api.js +80 -148
- package/dist/api.js.map +1 -1
- package/dist/archive.d.ts +14 -0
- package/dist/archive.d.ts.map +1 -0
- package/dist/archive.js +114 -0
- package/dist/archive.js.map +1 -0
- package/dist/artifacts/common.d.ts +15 -0
- package/dist/artifacts/common.d.ts.map +1 -0
- package/dist/artifacts/common.js +58 -0
- package/dist/artifacts/common.js.map +1 -0
- package/dist/artifacts/gcs.d.ts +18 -0
- package/dist/artifacts/gcs.d.ts.map +1 -0
- package/dist/artifacts/gcs.js +178 -0
- package/dist/artifacts/gcs.js.map +1 -0
- package/dist/artifacts/local.d.ts +17 -0
- package/dist/artifacts/local.d.ts.map +1 -0
- package/dist/artifacts/local.js +205 -0
- package/dist/artifacts/local.js.map +1 -0
- package/dist/artifacts/types.d.ts +18 -0
- package/dist/artifacts/types.d.ts.map +1 -0
- package/dist/artifacts/types.js +2 -0
- package/dist/artifacts/types.js.map +1 -0
- package/dist/artifacts.d.ts +5 -28
- package/dist/artifacts.d.ts.map +1 -1
- package/dist/artifacts.js +5 -302
- package/dist/artifacts.js.map +1 -1
- package/dist/audit.d.ts.map +1 -1
- package/dist/audit.js +8 -2
- package/dist/audit.js.map +1 -1
- package/dist/auth/api-key-routes.d.ts +17 -0
- package/dist/auth/api-key-routes.d.ts.map +1 -0
- package/dist/auth/api-key-routes.js +57 -0
- package/dist/auth/api-key-routes.js.map +1 -0
- package/dist/auth/api-keys.d.ts +47 -0
- package/dist/auth/api-keys.d.ts.map +1 -0
- package/dist/auth/api-keys.js +102 -0
- package/dist/auth/api-keys.js.map +1 -0
- package/dist/auth/config.d.ts +17 -0
- package/dist/auth/config.d.ts.map +1 -0
- package/dist/auth/config.js +38 -0
- package/dist/auth/config.js.map +1 -0
- package/dist/auth/cookies.d.ts +12 -0
- package/dist/auth/cookies.d.ts.map +1 -0
- package/dist/auth/cookies.js +45 -0
- package/dist/auth/cookies.js.map +1 -0
- package/dist/auth/crypto.d.ts +19 -0
- package/dist/auth/crypto.d.ts.map +1 -0
- package/dist/auth/crypto.js +48 -0
- package/dist/auth/crypto.js.map +1 -0
- package/dist/auth/github.d.ts +37 -0
- package/dist/auth/github.d.ts.map +1 -0
- package/dist/auth/github.js +127 -0
- package/dist/auth/github.js.map +1 -0
- package/dist/auth/routes.d.ts +41 -0
- package/dist/auth/routes.d.ts.map +1 -0
- package/dist/auth/routes.js +153 -0
- package/dist/auth/routes.js.map +1 -0
- package/dist/auth/session-expired.d.ts +4 -0
- package/dist/auth/session-expired.d.ts.map +1 -0
- package/dist/auth/session-expired.js +17 -0
- package/dist/auth/session-expired.js.map +1 -0
- package/dist/auth/session.d.ts +23 -0
- package/dist/auth/session.d.ts.map +1 -0
- package/dist/auth/session.js +56 -0
- package/dist/auth/session.js.map +1 -0
- package/dist/auth/users.d.ts +49 -0
- package/dist/auth/users.d.ts.map +1 -0
- package/dist/auth/users.js +125 -0
- package/dist/auth/users.js.map +1 -0
- package/dist/build-metadata.js +1 -1
- package/dist/cli/api-client.d.ts +8 -0
- package/dist/cli/api-client.d.ts.map +1 -0
- package/dist/cli/api-client.js +71 -0
- package/dist/cli/api-client.js.map +1 -0
- package/dist/cli/associate.d.ts +2 -0
- package/dist/cli/associate.d.ts.map +1 -0
- package/dist/cli/associate.js +51 -0
- package/dist/cli/associate.js.map +1 -0
- package/dist/cli/help.d.ts +2 -0
- package/dist/cli/help.d.ts.map +1 -0
- package/dist/cli/help.js +52 -0
- package/dist/cli/help.js.map +1 -0
- package/dist/cli/main.d.ts +2 -0
- package/dist/cli/main.d.ts.map +1 -0
- package/dist/cli/main.js +55 -0
- package/dist/cli/main.js.map +1 -0
- package/dist/cli/replay.d.ts +3 -0
- package/dist/cli/replay.d.ts.map +1 -0
- package/dist/cli/replay.js +59 -0
- package/dist/cli/replay.js.map +1 -0
- package/dist/cli/repository.d.ts +6 -0
- package/dist/cli/repository.d.ts.map +1 -0
- package/dist/cli/repository.js +36 -0
- package/dist/cli/repository.js.map +1 -0
- package/dist/cli/run.d.ts +2 -0
- package/dist/cli/run.d.ts.map +1 -0
- package/dist/cli/run.js +93 -0
- package/dist/cli/run.js.map +1 -0
- package/dist/cli/stack-environment.d.ts +26 -0
- package/dist/cli/stack-environment.d.ts.map +1 -0
- package/dist/cli/stack-environment.js +86 -0
- package/dist/cli/stack-environment.js.map +1 -0
- package/dist/cli/stack.d.ts +6 -0
- package/dist/cli/stack.d.ts.map +1 -0
- package/dist/cli/stack.js +131 -0
- package/dist/cli/stack.js.map +1 -0
- package/dist/cli/values.d.ts +8 -0
- package/dist/cli/values.d.ts.map +1 -0
- package/dist/cli/values.js +30 -0
- package/dist/cli/values.js.map +1 -0
- package/dist/cli/view.d.ts +2 -0
- package/dist/cli/view.d.ts.map +1 -0
- package/dist/cli/view.js +40 -0
- package/dist/cli/view.js.map +1 -0
- package/dist/cli.js +2 -429
- package/dist/cli.js.map +1 -1
- package/dist/config.d.ts +16 -2
- package/dist/config.d.ts.map +1 -1
- package/dist/config.js +60 -22
- package/dist/config.js.map +1 -1
- package/dist/contracts/common.d.ts +22 -0
- package/dist/contracts/common.d.ts.map +1 -0
- package/dist/contracts/common.js +29 -0
- package/dist/contracts/common.js.map +1 -0
- package/dist/contracts/results.d.ts +66 -0
- package/dist/contracts/results.d.ts.map +1 -0
- package/dist/contracts/results.js +2 -0
- package/dist/contracts/results.js.map +1 -0
- package/dist/contracts/run.d.ts +145 -0
- package/dist/contracts/run.d.ts.map +1 -0
- package/dist/contracts/run.js +74 -0
- package/dist/contracts/run.js.map +1 -0
- package/dist/contracts/task.d.ts +232 -0
- package/dist/contracts/task.d.ts.map +1 -0
- package/dist/contracts/task.js +198 -0
- package/dist/contracts/task.js.map +1 -0
- package/dist/contracts/verify.d.ts +331 -0
- package/dist/contracts/verify.d.ts.map +1 -0
- package/dist/contracts/verify.js +84 -0
- package/dist/contracts/verify.js.map +1 -0
- package/dist/contracts.d.ts +5 -243
- package/dist/contracts.d.ts.map +1 -1
- package/dist/contracts.js +5 -128
- package/dist/contracts.js.map +1 -1
- package/dist/db/client.d.ts +12 -0
- package/dist/db/client.d.ts.map +1 -0
- package/dist/db/client.js +16 -0
- package/dist/db/client.js.map +1 -0
- package/dist/db/schema.d.ts +1256 -0
- package/dist/db/schema.d.ts.map +1 -0
- package/dist/db/schema.js +128 -0
- package/dist/db/schema.js.map +1 -0
- package/dist/environment.d.ts +9 -0
- package/dist/environment.d.ts.map +1 -0
- package/dist/environment.js +101 -0
- package/dist/environment.js.map +1 -0
- package/dist/evaluation/account.d.ts +30 -0
- package/dist/evaluation/account.d.ts.map +1 -0
- package/dist/evaluation/account.js +34 -0
- package/dist/evaluation/account.js.map +1 -0
- package/dist/evaluation/activities.d.ts +9 -0
- package/dist/evaluation/activities.d.ts.map +1 -0
- package/dist/evaluation/activities.js +40 -0
- package/dist/evaluation/activities.js.map +1 -0
- package/dist/evaluation/catalog-pricing.d.ts +3 -0
- package/dist/evaluation/catalog-pricing.d.ts.map +1 -0
- package/dist/evaluation/catalog-pricing.js +37 -0
- package/dist/evaluation/catalog-pricing.js.map +1 -0
- package/dist/evaluation/catalog.d.ts +17 -0
- package/dist/evaluation/catalog.d.ts.map +1 -0
- package/dist/evaluation/catalog.js +126 -0
- package/dist/evaluation/catalog.js.map +1 -0
- package/dist/evaluation/codex-login-process.d.ts +12 -0
- package/dist/evaluation/codex-login-process.d.ts.map +1 -0
- package/dist/evaluation/codex-login-process.js +121 -0
- package/dist/evaluation/codex-login-process.js.map +1 -0
- package/dist/evaluation/codex-login-routes.d.ts +5 -0
- package/dist/evaluation/codex-login-routes.d.ts.map +1 -0
- package/dist/evaluation/codex-login-routes.js +55 -0
- package/dist/evaluation/codex-login-routes.js.map +1 -0
- package/dist/evaluation/codex-login.d.ts +42 -0
- package/dist/evaluation/codex-login.d.ts.map +1 -0
- package/dist/evaluation/codex-login.js +143 -0
- package/dist/evaluation/codex-login.js.map +1 -0
- package/dist/evaluation/comparisons.d.ts +65 -0
- package/dist/evaluation/comparisons.d.ts.map +1 -0
- package/dist/evaluation/comparisons.js +161 -0
- package/dist/evaluation/comparisons.js.map +1 -0
- package/dist/evaluation/config.d.ts +43 -0
- package/dist/evaluation/config.d.ts.map +1 -0
- package/dist/evaluation/config.js +116 -0
- package/dist/evaluation/config.js.map +1 -0
- package/dist/evaluation/cost.d.ts +3 -0
- package/dist/evaluation/cost.d.ts.map +1 -0
- package/dist/evaluation/cost.js +95 -0
- package/dist/evaluation/cost.js.map +1 -0
- package/dist/evaluation/credential-execution.d.ts +10 -0
- package/dist/evaluation/credential-execution.d.ts.map +1 -0
- package/dist/evaluation/credential-execution.js +65 -0
- package/dist/evaluation/credential-execution.js.map +1 -0
- package/dist/evaluation/credentials.d.ts +40 -0
- package/dist/evaluation/credentials.d.ts.map +1 -0
- package/dist/evaluation/credentials.js +146 -0
- package/dist/evaluation/credentials.js.map +1 -0
- package/dist/evaluation/encrypted-records.d.ts +15 -0
- package/dist/evaluation/encrypted-records.d.ts.map +1 -0
- package/dist/evaluation/encrypted-records.js +57 -0
- package/dist/evaluation/encrypted-records.js.map +1 -0
- package/dist/evaluation/gateway-execution.d.ts +18 -0
- package/dist/evaluation/gateway-execution.d.ts.map +1 -0
- package/dist/evaluation/gateway-execution.js +38 -0
- package/dist/evaluation/gateway-execution.js.map +1 -0
- package/dist/evaluation/harbor-cost.d.ts +3 -0
- package/dist/evaluation/harbor-cost.d.ts.map +1 -0
- package/dist/evaluation/harbor-cost.js +39 -0
- package/dist/evaluation/harbor-cost.js.map +1 -0
- package/dist/evaluation/harbor_e2b.py +20 -0
- package/dist/evaluation/harbor_gateway.py +22 -0
- package/dist/evaluation/harnesses.d.ts +8 -0
- package/dist/evaluation/harnesses.d.ts.map +1 -0
- package/dist/evaluation/harnesses.js +10 -0
- package/dist/evaluation/harnesses.js.map +1 -0
- package/dist/evaluation/model-options.d.ts +9 -0
- package/dist/evaluation/model-options.d.ts.map +1 -0
- package/dist/evaluation/model-options.js +81 -0
- package/dist/evaluation/model-options.js.map +1 -0
- package/dist/evaluation/org-credential-routes.d.ts +5 -0
- package/dist/evaluation/org-credential-routes.d.ts.map +1 -0
- package/dist/evaluation/org-credential-routes.js +56 -0
- package/dist/evaluation/org-credential-routes.js.map +1 -0
- package/dist/evaluation/org-records.d.ts +4 -0
- package/dist/evaluation/org-records.d.ts.map +1 -0
- package/dist/evaluation/org-records.js +14 -0
- package/dist/evaluation/org-records.js.map +1 -0
- package/dist/evaluation/output.d.ts +9 -0
- package/dist/evaluation/output.d.ts.map +1 -0
- package/dist/evaluation/output.js +171 -0
- package/dist/evaluation/output.js.map +1 -0
- package/dist/evaluation/platform-routes.d.ts +5 -0
- package/dist/evaluation/platform-routes.d.ts.map +1 -0
- package/dist/evaluation/platform-routes.js +123 -0
- package/dist/evaluation/platform-routes.js.map +1 -0
- package/dist/evaluation/profile-routes.d.ts +16 -0
- package/dist/evaluation/profile-routes.d.ts.map +1 -0
- package/dist/evaluation/profile-routes.js +47 -0
- package/dist/evaluation/profile-routes.js.map +1 -0
- package/dist/evaluation/profiles.d.ts +48 -0
- package/dist/evaluation/profiles.d.ts.map +1 -0
- package/dist/evaluation/profiles.js +134 -0
- package/dist/evaluation/profiles.js.map +1 -0
- package/dist/evaluation/providers.d.ts +11 -0
- package/dist/evaluation/providers.d.ts.map +1 -0
- package/dist/evaluation/providers.js +30 -0
- package/dist/evaluation/providers.js.map +1 -0
- package/dist/evaluation/routes.d.ts +23 -0
- package/dist/evaluation/routes.d.ts.map +1 -0
- package/dist/evaluation/routes.js +212 -0
- package/dist/evaluation/routes.js.map +1 -0
- package/dist/evaluation/runner.d.ts +16 -0
- package/dist/evaluation/runner.d.ts.map +1 -0
- package/dist/evaluation/runner.js +241 -0
- package/dist/evaluation/runner.js.map +1 -0
- package/dist/evaluation/store.d.ts +8 -0
- package/dist/evaluation/store.d.ts.map +1 -0
- package/dist/evaluation/store.js +60 -0
- package/dist/evaluation/store.js.map +1 -0
- package/dist/evaluation/types.d.ts +98 -0
- package/dist/evaluation/types.d.ts.map +1 -0
- package/dist/evaluation/types.js +2 -0
- package/dist/evaluation/types.js.map +1 -0
- package/dist/evaluation/worker-main.d.ts +2 -0
- package/dist/evaluation/worker-main.d.ts.map +1 -0
- package/dist/evaluation/worker-main.js +26 -0
- package/dist/evaluation/worker-main.js.map +1 -0
- package/dist/evaluation/worker-records.d.ts +5 -0
- package/dist/evaluation/worker-records.d.ts.map +1 -0
- package/dist/evaluation/worker-records.js +11 -0
- package/dist/evaluation/worker-records.js.map +1 -0
- package/dist/evaluation/workflow.d.ts +3 -0
- package/dist/evaluation/workflow.d.ts.map +1 -0
- package/dist/evaluation/workflow.js +20 -0
- package/dist/evaluation/workflow.js.map +1 -0
- package/dist/execution-environment.d.ts +3 -0
- package/dist/execution-environment.d.ts.map +1 -0
- package/dist/execution-environment.js +9 -0
- package/dist/execution-environment.js.map +1 -0
- package/dist/extension-authoring.bundle.js +347 -0
- package/dist/extension-verifier.bundle.js +73 -0
- package/dist/extensions/authoring.d.ts.map +1 -1
- package/dist/extensions/authoring.js +70 -59
- package/dist/extensions/authoring.js.map +1 -1
- package/dist/extensions/shared/deliverable.d.ts +33 -0
- package/dist/extensions/shared/deliverable.d.ts.map +1 -0
- package/dist/extensions/shared/deliverable.js +123 -0
- package/dist/extensions/shared/deliverable.js.map +1 -0
- package/dist/extensions/shared/mailbox.d.ts +33 -0
- package/dist/extensions/shared/mailbox.d.ts.map +1 -0
- package/dist/extensions/shared/mailbox.js +102 -0
- package/dist/extensions/shared/mailbox.js.map +1 -0
- package/dist/extensions/shared/schemas.d.ts +90 -0
- package/dist/extensions/shared/schemas.d.ts.map +1 -0
- package/dist/extensions/shared/schemas.js +71 -0
- package/dist/extensions/shared/schemas.js.map +1 -0
- package/dist/extensions/shared/static-check.d.ts +38 -0
- package/dist/extensions/shared/static-check.d.ts.map +1 -0
- package/dist/extensions/shared/static-check.js +52 -0
- package/dist/extensions/shared/static-check.js.map +1 -0
- package/dist/extensions/verifier.d.ts +4 -0
- package/dist/extensions/verifier.d.ts.map +1 -0
- package/dist/extensions/verifier.js +70 -0
- package/dist/extensions/verifier.js.map +1 -0
- package/dist/github.d.ts +1 -1
- package/dist/github.d.ts.map +1 -1
- package/dist/github.js +3 -3
- package/dist/github.js.map +1 -1
- package/dist/harbor-environment.d.ts +13 -1
- package/dist/harbor-environment.d.ts.map +1 -1
- package/dist/harbor-environment.js +37 -4
- package/dist/harbor-environment.js.map +1 -1
- package/dist/harbor-results.d.ts +2 -0
- package/dist/harbor-results.d.ts.map +1 -1
- package/dist/harbor-results.js +2 -0
- package/dist/harbor-results.js.map +1 -1
- package/dist/harbor-task/compiler.d.ts +10 -0
- package/dist/harbor-task/compiler.d.ts.map +1 -0
- package/dist/harbor-task/compiler.js +174 -0
- package/dist/harbor-task/compiler.js.map +1 -0
- package/dist/harbor-task/constants.d.ts +3 -0
- package/dist/harbor-task/constants.d.ts.map +1 -0
- package/dist/harbor-task/constants.js +3 -0
- package/dist/harbor-task/constants.js.map +1 -0
- package/dist/harbor-task/dependencies.d.ts +3 -0
- package/dist/harbor-task/dependencies.d.ts.map +1 -0
- package/dist/harbor-task/dependencies.js +20 -0
- package/dist/harbor-task/dependencies.js.map +1 -0
- package/dist/harbor-task/paths.d.ts +6 -0
- package/dist/harbor-task/paths.d.ts.map +1 -0
- package/dist/harbor-task/paths.js +37 -0
- package/dist/harbor-task/paths.js.map +1 -0
- package/dist/harbor-task/render.d.ts +11 -0
- package/dist/harbor-task/render.d.ts.map +1 -0
- package/dist/harbor-task/render.js +194 -0
- package/dist/harbor-task/render.js.map +1 -0
- package/dist/harbor-task/runtime/command.sh +26 -0
- package/dist/harbor-task/runtime/junit.py +69 -0
- package/dist/harbor-task/runtime-assets.d.ts +2 -0
- package/dist/harbor-task/runtime-assets.d.ts.map +1 -0
- package/dist/harbor-task/runtime-assets.js +8 -0
- package/dist/harbor-task/runtime-assets.js.map +1 -0
- package/dist/harbor-task/test-patch.d.ts +4 -0
- package/dist/harbor-task/test-patch.d.ts.map +1 -0
- package/dist/harbor-task/test-patch.js +15 -0
- package/dist/harbor-task/test-patch.js.map +1 -0
- package/dist/harbor-task/verifier.d.ts +4 -0
- package/dist/harbor-task/verifier.d.ts.map +1 -0
- package/dist/harbor-task/verifier.js +105 -0
- package/dist/harbor-task/verifier.js.map +1 -0
- package/dist/harbor-task.d.ts +3 -11
- package/dist/harbor-task.d.ts.map +1 -1
- package/dist/harbor-task.js +2 -463
- package/dist/harbor-task.js.map +1 -1
- package/dist/log-excerpt.d.ts +15 -0
- package/dist/log-excerpt.d.ts.map +1 -0
- package/dist/log-excerpt.js +104 -0
- package/dist/log-excerpt.js.map +1 -0
- package/dist/patch-check.d.ts +26 -0
- package/dist/patch-check.d.ts.map +1 -0
- package/dist/patch-check.js +137 -0
- package/dist/patch-check.js.map +1 -0
- package/dist/pi-event-feed.d.ts +16 -0
- package/dist/pi-event-feed.d.ts.map +1 -0
- package/dist/pi-event-feed.js +86 -0
- package/dist/pi-event-feed.js.map +1 -0
- package/dist/pi-session.d.ts +32 -0
- package/dist/pi-session.d.ts.map +1 -0
- package/dist/pi-session.js +175 -0
- package/dist/pi-session.js.map +1 -0
- package/dist/process.d.ts +5 -0
- package/dist/process.d.ts.map +1 -1
- package/dist/process.js +31 -9
- package/dist/process.js.map +1 -1
- package/dist/provenance/github.d.ts +4 -0
- package/dist/provenance/github.d.ts.map +1 -0
- package/dist/provenance/github.js +65 -0
- package/dist/provenance/github.js.map +1 -0
- package/dist/provenance/local.d.ts +4 -0
- package/dist/provenance/local.d.ts.map +1 -0
- package/dist/provenance/local.js +82 -0
- package/dist/provenance/local.js.map +1 -0
- package/dist/provenance/redact.d.ts +2 -0
- package/dist/provenance/redact.d.ts.map +1 -0
- package/dist/provenance/redact.js +28 -0
- package/dist/provenance/redact.js.map +1 -0
- package/dist/provenance/selection.d.ts +4 -0
- package/dist/provenance/selection.d.ts.map +1 -0
- package/dist/provenance/selection.js +29 -0
- package/dist/provenance/selection.js.map +1 -0
- package/dist/provenance/session.d.ts +3 -0
- package/dist/provenance/session.d.ts.map +1 -0
- package/dist/provenance/session.js +214 -0
- package/dist/provenance/session.js.map +1 -0
- package/dist/provenance/shared.d.ts +7 -0
- package/dist/provenance/shared.d.ts.map +1 -0
- package/dist/provenance/shared.js +10 -0
- package/dist/provenance/shared.js.map +1 -0
- package/dist/provenance/types.d.ts +34 -0
- package/dist/provenance/types.d.ts.map +1 -0
- package/dist/provenance/types.js +22 -0
- package/dist/provenance/types.js.map +1 -0
- package/dist/provenance-associations/apply.d.ts +3 -0
- package/dist/provenance-associations/apply.d.ts.map +1 -0
- package/dist/provenance-associations/apply.js +66 -0
- package/dist/provenance-associations/apply.js.map +1 -0
- package/dist/provenance-associations/shared.d.ts +45 -0
- package/dist/provenance-associations/shared.d.ts.map +1 -0
- package/dist/provenance-associations/shared.js +42 -0
- package/dist/provenance-associations/shared.js.map +1 -0
- package/dist/provenance-associations.d.ts +3 -30
- package/dist/provenance-associations.d.ts.map +1 -1
- package/dist/provenance-associations.js +4 -103
- package/dist/provenance-associations.js.map +1 -1
- package/dist/provenance.d.ts +7 -41
- package/dist/provenance.d.ts.map +1 -1
- package/dist/provenance.js +6 -432
- package/dist/provenance.js.map +1 -1
- package/dist/providers.d.ts +25 -2
- package/dist/providers.d.ts.map +1 -1
- package/dist/providers.js +23 -2
- package/dist/providers.js.map +1 -1
- package/dist/repair.d.ts +1 -6
- package/dist/repair.d.ts.map +1 -1
- package/dist/repair.js +17 -27
- package/dist/repair.js.map +1 -1
- package/dist/review/assets/index-BHHztQ9x.js +1679 -0
- package/dist/review/assets/index-KQ1eFQ0t.css +1 -0
- package/dist/review/index.html +11 -8
- package/dist/runtime/command.sh +26 -0
- package/dist/runtime/junit.py +69 -0
- package/dist/sandbox/contracts.d.ts +36 -1
- package/dist/sandbox/contracts.d.ts.map +1 -1
- package/dist/sandbox/contracts.js +3 -0
- package/dist/sandbox/contracts.js.map +1 -1
- package/dist/sandbox/index.d.ts +1 -1
- package/dist/sandbox/index.d.ts.map +1 -1
- package/dist/sandbox/index.js +13 -2
- package/dist/sandbox/index.js.map +1 -1
- package/dist/sandbox/live.d.ts +18 -0
- package/dist/sandbox/live.d.ts.map +1 -0
- package/dist/sandbox/live.js +55 -0
- package/dist/sandbox/live.js.map +1 -0
- package/dist/sandbox/output-retry.d.ts +16 -0
- package/dist/sandbox/output-retry.d.ts.map +1 -0
- package/dist/sandbox/output-retry.js +36 -0
- package/dist/sandbox/output-retry.js.map +1 -0
- package/dist/sandbox/programs/author.js +16 -6
- package/dist/sandbox/programs/author.js.map +1 -1
- package/dist/sandbox/programs/check.d.ts +3 -0
- package/dist/sandbox/programs/check.d.ts.map +1 -0
- package/dist/sandbox/programs/check.js +76 -0
- package/dist/sandbox/programs/check.js.map +1 -0
- package/dist/sandbox/programs/prepare-task.d.ts +12 -0
- package/dist/sandbox/programs/prepare-task.d.ts.map +1 -0
- package/dist/sandbox/programs/{prepare-repair.js → prepare-task.js} +11 -9
- package/dist/sandbox/programs/prepare-task.js.map +1 -0
- package/dist/sandbox/programs/verifier.d.ts +3 -0
- package/dist/sandbox/programs/verifier.d.ts.map +1 -0
- package/dist/sandbox/programs/verifier.js +9 -0
- package/dist/sandbox/programs/verifier.js.map +1 -0
- package/dist/sandbox/providers/docker/executor.d.ts +4 -1
- package/dist/sandbox/providers/docker/executor.d.ts.map +1 -1
- package/dist/sandbox/providers/docker/executor.js +75 -25
- package/dist/sandbox/providers/docker/executor.js.map +1 -1
- package/dist/sandbox/providers/e2b/bytes.d.ts +3 -0
- package/dist/sandbox/providers/e2b/bytes.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/bytes.js +8 -0
- package/dist/sandbox/providers/e2b/bytes.js.map +1 -0
- package/dist/sandbox/providers/e2b/cleanup.d.ts +8 -0
- package/dist/sandbox/providers/e2b/cleanup.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/cleanup.js +124 -0
- package/dist/sandbox/providers/e2b/cleanup.js.map +1 -0
- package/dist/sandbox/providers/e2b/command.d.ts +23 -0
- package/dist/sandbox/providers/e2b/command.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/command.js +160 -0
- package/dist/sandbox/providers/e2b/command.js.map +1 -0
- package/dist/sandbox/providers/e2b/config.d.ts +13 -0
- package/dist/sandbox/providers/e2b/config.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/config.js +2 -0
- package/dist/sandbox/providers/e2b/config.js.map +1 -0
- package/dist/sandbox/providers/e2b/executor.d.ts +15 -0
- package/dist/sandbox/providers/e2b/executor.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/executor.js +207 -0
- package/dist/sandbox/providers/e2b/executor.js.map +1 -0
- package/dist/sandbox/providers/e2b/lifecycle.d.ts +8 -0
- package/dist/sandbox/providers/e2b/lifecycle.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/lifecycle.js +37 -0
- package/dist/sandbox/providers/e2b/lifecycle.js.map +1 -0
- package/dist/sandbox/providers/e2b/outcome.d.ts +11 -0
- package/dist/sandbox/providers/e2b/outcome.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/outcome.js +72 -0
- package/dist/sandbox/providers/e2b/outcome.js.map +1 -0
- package/dist/sandbox/providers/e2b/stage-files.d.ts +10 -0
- package/dist/sandbox/providers/e2b/stage-files.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/stage-files.js +45 -0
- package/dist/sandbox/providers/e2b/stage-files.js.map +1 -0
- package/dist/sandbox/providers/e2b/startup.d.ts +10 -0
- package/dist/sandbox/providers/e2b/startup.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/startup.js +26 -0
- package/dist/sandbox/providers/e2b/startup.js.map +1 -0
- package/dist/sandbox/providers/e2b/types.d.ts +9 -0
- package/dist/sandbox/providers/e2b/types.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/types.js +2 -0
- package/dist/sandbox/providers/e2b/types.js.map +1 -0
- package/dist/sandbox/providers/e2b/validation.d.ts +14 -0
- package/dist/sandbox/providers/e2b/validation.d.ts.map +1 -0
- package/dist/sandbox/providers/e2b/validation.js +60 -0
- package/dist/sandbox/providers/e2b/validation.js.map +1 -0
- package/dist/{modal-auth.d.ts → sandbox/providers/modal/auth.d.ts} +1 -1
- package/dist/sandbox/providers/modal/auth.d.ts.map +1 -0
- package/dist/{modal-auth.js → sandbox/providers/modal/auth.js} +1 -1
- package/dist/sandbox/providers/modal/auth.js.map +1 -0
- package/dist/sandbox/providers/modal/executor.d.ts +4 -1
- package/dist/sandbox/providers/modal/executor.d.ts.map +1 -1
- package/dist/sandbox/providers/modal/executor.js +33 -9
- package/dist/sandbox/providers/modal/executor.js.map +1 -1
- package/dist/sandbox/providers/modal/live.d.ts +7 -0
- package/dist/sandbox/providers/modal/live.d.ts.map +1 -0
- package/dist/sandbox/providers/modal/live.js +50 -0
- package/dist/sandbox/providers/modal/live.js.map +1 -0
- package/dist/sandbox/providers/vercel/command.d.ts +6 -0
- package/dist/sandbox/providers/vercel/command.d.ts.map +1 -1
- package/dist/sandbox/providers/vercel/command.js +44 -11
- package/dist/sandbox/providers/vercel/command.js.map +1 -1
- package/dist/sandbox/providers/vercel/executor.d.ts +6 -7
- package/dist/sandbox/providers/vercel/executor.d.ts.map +1 -1
- package/dist/sandbox/providers/vercel/executor.js +21 -187
- package/dist/sandbox/providers/vercel/executor.js.map +1 -1
- package/dist/sandbox/providers/vercel/lifecycle.d.ts +13 -0
- package/dist/sandbox/providers/vercel/lifecycle.d.ts.map +1 -0
- package/dist/sandbox/providers/vercel/lifecycle.js +140 -0
- package/dist/sandbox/providers/vercel/lifecycle.js.map +1 -0
- package/dist/sandbox/providers/vercel/validation.d.ts +11 -0
- package/dist/sandbox/providers/vercel/validation.d.ts.map +1 -0
- package/dist/sandbox/providers/vercel/validation.js +30 -0
- package/dist/sandbox/providers/vercel/validation.js.map +1 -0
- package/dist/sandbox/remote-files.d.ts +11 -0
- package/dist/sandbox/remote-files.d.ts.map +1 -0
- package/dist/sandbox/remote-files.js +41 -0
- package/dist/sandbox/remote-files.js.map +1 -0
- package/dist/sandbox/request-validation.d.ts +5 -0
- package/dist/sandbox/request-validation.d.ts.map +1 -0
- package/dist/sandbox/request-validation.js +43 -0
- package/dist/sandbox/request-validation.js.map +1 -0
- package/dist/sandbox/supervisor.d.ts +42 -0
- package/dist/sandbox/supervisor.d.ts.map +1 -0
- package/dist/sandbox/supervisor.js +126 -0
- package/dist/sandbox/supervisor.js.map +1 -0
- package/dist/sandbox/timeout.d.ts +6 -1
- package/dist/sandbox/timeout.d.ts.map +1 -1
- package/dist/sandbox/timeout.js +12 -0
- package/dist/sandbox/timeout.js.map +1 -1
- package/dist/sandbox-author.bundle.js +47 -14879
- package/dist/{sandbox-validation-repair.bundle.js → sandbox-check.bundle.js} +7261 -1893
- package/dist/sandbox-verifier.bundle.js +307 -0
- package/dist/setup/e2b/build.d.ts +24 -0
- package/dist/setup/e2b/build.d.ts.map +1 -0
- package/dist/setup/e2b/build.js +46 -0
- package/dist/setup/e2b/build.js.map +1 -0
- package/dist/setup/e2b/cli.d.ts +2 -0
- package/dist/setup/e2b/cli.d.ts.map +1 -0
- package/dist/setup/e2b/cli.js +51 -0
- package/dist/setup/e2b/cli.js.map +1 -0
- package/dist/setup/e2b/index.d.ts +5 -0
- package/dist/setup/e2b/index.d.ts.map +1 -0
- package/dist/setup/e2b/index.js +4 -0
- package/dist/setup/e2b/index.js.map +1 -0
- package/dist/setup/e2b/template.d.ts +4 -0
- package/dist/setup/e2b/template.d.ts.map +1 -0
- package/dist/setup/e2b/template.js +53 -0
- package/dist/setup/e2b/template.js.map +1 -0
- package/dist/setup/vercel/cli-helpers.d.ts +22 -0
- package/dist/setup/vercel/cli-helpers.d.ts.map +1 -0
- package/dist/setup/vercel/cli-helpers.js +87 -0
- package/dist/setup/vercel/cli-helpers.js.map +1 -0
- package/dist/setup/vercel/cli-runner.d.ts +14 -0
- package/dist/setup/vercel/cli-runner.d.ts.map +1 -0
- package/dist/setup/vercel/cli-runner.js +24 -0
- package/dist/setup/vercel/cli-runner.js.map +1 -0
- package/dist/setup/vercel/cli-types.d.ts +24 -0
- package/dist/setup/vercel/cli-types.d.ts.map +1 -0
- package/dist/setup/vercel/cli-types.js +18 -0
- package/dist/setup/vercel/cli-types.js.map +1 -0
- package/dist/setup/vercel/cli.d.ts +5 -31
- package/dist/setup/vercel/cli.d.ts.map +1 -1
- package/dist/setup/vercel/cli.js +15 -125
- package/dist/setup/vercel/cli.js.map +1 -1
- package/dist/setup/vercel/profile-files.d.ts +6 -0
- package/dist/setup/vercel/profile-files.d.ts.map +1 -0
- package/dist/setup/vercel/profile-files.js +100 -0
- package/dist/setup/vercel/profile-files.js.map +1 -0
- package/dist/setup/vercel/profile-schema.d.ts +48 -0
- package/dist/setup/vercel/profile-schema.d.ts.map +1 -0
- package/dist/setup/vercel/profile-schema.js +39 -0
- package/dist/setup/vercel/profile-schema.js.map +1 -0
- package/dist/setup/vercel/profile.d.ts +3 -19
- package/dist/setup/vercel/profile.d.ts.map +1 -1
- package/dist/setup/vercel/profile.js +4 -130
- package/dist/setup/vercel/profile.js.map +1 -1
- package/dist/setup/vercel/selection.d.ts +18 -0
- package/dist/setup/vercel/selection.d.ts.map +1 -0
- package/dist/setup/vercel/selection.js +113 -0
- package/dist/setup/vercel/selection.js.map +1 -0
- package/dist/setup/vercel/setup-types.d.ts +34 -0
- package/dist/setup/vercel/setup-types.d.ts.map +1 -0
- package/dist/setup/vercel/setup-types.js +2 -0
- package/dist/setup/vercel/setup-types.js.map +1 -0
- package/dist/setup/vercel/setup.d.ts +3 -28
- package/dist/setup/vercel/setup.d.ts.map +1 -1
- package/dist/setup/vercel/setup.js +3 -111
- package/dist/setup/vercel/setup.js.map +1 -1
- package/dist/site/batch-activity.d.ts +5 -0
- package/dist/site/batch-activity.d.ts.map +1 -0
- package/dist/site/batch-activity.js +31 -0
- package/dist/site/batch-activity.js.map +1 -0
- package/dist/site/batch-progress.d.ts +16 -0
- package/dist/site/batch-progress.d.ts.map +1 -0
- package/dist/site/batch-progress.js +52 -0
- package/dist/site/batch-progress.js.map +1 -0
- package/dist/site/batch-routes.d.ts +30 -0
- package/dist/site/batch-routes.d.ts.map +1 -0
- package/dist/site/batch-routes.js +117 -0
- package/dist/site/batch-routes.js.map +1 -0
- package/dist/site/batch-start.d.ts +60 -0
- package/dist/site/batch-start.d.ts.map +1 -0
- package/dist/site/batch-start.js +39 -0
- package/dist/site/batch-start.js.map +1 -0
- package/dist/site/connected-repos.d.ts +25 -0
- package/dist/site/connected-repos.d.ts.map +1 -0
- package/dist/site/connected-repos.js +109 -0
- package/dist/site/connected-repos.js.map +1 -0
- package/dist/site/evaluation-start.d.ts +4 -0
- package/dist/site/evaluation-start.d.ts.map +1 -0
- package/dist/site/evaluation-start.js +19 -0
- package/dist/site/evaluation-start.js.map +1 -0
- package/dist/site/generation-config.d.ts +4 -0
- package/dist/site/generation-config.d.ts.map +1 -0
- package/dist/site/generation-config.js +16 -0
- package/dist/site/generation-config.js.map +1 -0
- package/dist/site/generation-credentials.d.ts +6 -0
- package/dist/site/generation-credentials.d.ts.map +1 -0
- package/dist/site/generation-credentials.js +101 -0
- package/dist/site/generation-credentials.js.map +1 -0
- package/dist/site/generation-run.d.ts +6 -0
- package/dist/site/generation-run.d.ts.map +1 -0
- package/dist/site/generation-run.js +22 -0
- package/dist/site/generation-run.js.map +1 -0
- package/dist/site/generation-settings.d.ts +80 -0
- package/dist/site/generation-settings.d.ts.map +1 -0
- package/dist/site/generation-settings.js +84 -0
- package/dist/site/generation-settings.js.map +1 -0
- package/dist/site/generation-subscription.d.ts +3 -0
- package/dist/site/generation-subscription.d.ts.map +1 -0
- package/dist/site/generation-subscription.js +38 -0
- package/dist/site/generation-subscription.js.map +1 -0
- package/dist/site/github-repos.d.ts +35 -0
- package/dist/site/github-repos.d.ts.map +1 -0
- package/dist/site/github-repos.js +121 -0
- package/dist/site/github-repos.js.map +1 -0
- package/dist/site/pr-candidate.d.ts +26 -0
- package/dist/site/pr-candidate.d.ts.map +1 -0
- package/dist/site/pr-candidate.js +101 -0
- package/dist/site/pr-candidate.js.map +1 -0
- package/dist/site/pr-list.d.ts +13 -0
- package/dist/site/pr-list.d.ts.map +1 -0
- package/dist/site/pr-list.js +24 -0
- package/dist/site/pr-list.js.map +1 -0
- package/dist/site/pr-routes.d.ts +26 -0
- package/dist/site/pr-routes.d.ts.map +1 -0
- package/dist/site/pr-routes.js +139 -0
- package/dist/site/pr-routes.js.map +1 -0
- package/dist/site/repo-store.d.ts +40 -0
- package/dist/site/repo-store.d.ts.map +1 -0
- package/dist/site/repo-store.js +74 -0
- package/dist/site/repo-store.js.map +1 -0
- package/dist/site/run-store.d.ts +17 -0
- package/dist/site/run-store.d.ts.map +1 -0
- package/dist/site/run-store.js +42 -0
- package/dist/site/run-store.js.map +1 -0
- package/dist/site/runtime.d.ts +27 -0
- package/dist/site/runtime.d.ts.map +1 -0
- package/dist/site/runtime.js +97 -0
- package/dist/site/runtime.js.map +1 -0
- package/dist/site/task-deletion.d.ts +7 -0
- package/dist/site/task-deletion.d.ts.map +1 -0
- package/dist/site/task-deletion.js +29 -0
- package/dist/site/task-deletion.js.map +1 -0
- package/dist/site/task-start-reservation.d.ts +4 -0
- package/dist/site/task-start-reservation.d.ts.map +1 -0
- package/dist/site/task-start-reservation.js +18 -0
- package/dist/site/task-start-reservation.js.map +1 -0
- package/dist/site/task-start.d.ts +33 -0
- package/dist/site/task-start.d.ts.map +1 -0
- package/dist/site/task-start.js +50 -0
- package/dist/site/task-start.js.map +1 -0
- package/dist/site/task-status.d.ts +36 -0
- package/dist/site/task-status.d.ts.map +1 -0
- package/dist/site/task-status.js +113 -0
- package/dist/site/task-status.js.map +1 -0
- package/dist/site/task-store.d.ts +78 -0
- package/dist/site/task-store.d.ts.map +1 -0
- package/dist/site/task-store.js +186 -0
- package/dist/site/task-store.js.map +1 -0
- package/dist/site/task-sync.d.ts +30 -0
- package/dist/site/task-sync.d.ts.map +1 -0
- package/dist/site/task-sync.js +121 -0
- package/dist/site/task-sync.js.map +1 -0
- package/dist/site/tasks.d.ts +47 -0
- package/dist/site/tasks.d.ts.map +1 -0
- package/dist/site/tasks.js +164 -0
- package/dist/site/tasks.js.map +1 -0
- package/dist/site/temporal-status.d.ts +8 -0
- package/dist/site/temporal-status.d.ts.map +1 -0
- package/dist/site/temporal-status.js +41 -0
- package/dist/site/temporal-status.js.map +1 -0
- package/dist/site/tenant.d.ts +4 -0
- package/dist/site/tenant.d.ts.map +1 -0
- package/dist/site/tenant.js +6 -0
- package/dist/site/tenant.js.map +1 -0
- package/dist/static-check.d.ts +38 -0
- package/dist/static-check.d.ts.map +1 -0
- package/dist/static-check.js +131 -0
- package/dist/static-check.js.map +1 -0
- package/dist/submission-hash.d.ts +18 -0
- package/dist/submission-hash.d.ts.map +1 -0
- package/dist/submission-hash.js +16 -0
- package/dist/submission-hash.js.map +1 -0
- package/dist/subscription-auth.d.ts +0 -7
- package/dist/subscription-auth.d.ts.map +1 -1
- package/dist/subscription-auth.js +3 -23
- package/dist/subscription-auth.js.map +1 -1
- package/dist/temporal/activities/agent-feed.d.ts +5 -0
- package/dist/temporal/activities/agent-feed.d.ts.map +1 -0
- package/dist/temporal/activities/agent-feed.js +41 -0
- package/dist/temporal/activities/agent-feed.js.map +1 -0
- package/dist/temporal/activities/agent-scripts.d.ts +16 -0
- package/dist/temporal/activities/agent-scripts.d.ts.map +1 -0
- package/dist/temporal/activities/agent-scripts.js +162 -0
- package/dist/temporal/activities/agent-scripts.js.map +1 -0
- package/dist/temporal/activities/authoring-round.d.ts +13 -0
- package/dist/temporal/activities/authoring-round.d.ts.map +1 -0
- package/dist/temporal/activities/authoring-round.js +160 -0
- package/dist/temporal/activities/authoring-round.js.map +1 -0
- package/dist/temporal/activities/constants.d.ts +5 -0
- package/dist/temporal/activities/constants.d.ts.map +1 -0
- package/dist/temporal/activities/constants.js +5 -0
- package/dist/temporal/activities/constants.js.map +1 -0
- package/dist/temporal/activities/discovery.d.ts +17 -0
- package/dist/temporal/activities/discovery.d.ts.map +1 -0
- package/dist/temporal/activities/discovery.js +153 -0
- package/dist/temporal/activities/discovery.js.map +1 -0
- package/dist/temporal/activities/drafts.d.ts +15 -0
- package/dist/temporal/activities/drafts.d.ts.map +1 -0
- package/dist/temporal/activities/drafts.js +51 -0
- package/dist/temporal/activities/drafts.js.map +1 -0
- package/dist/temporal/activities/excluded-source-prs.d.ts +9 -0
- package/dist/temporal/activities/excluded-source-prs.d.ts.map +1 -0
- package/dist/temporal/activities/excluded-source-prs.js +132 -0
- package/dist/temporal/activities/excluded-source-prs.js.map +1 -0
- package/dist/temporal/activities/export.d.ts +38 -0
- package/dist/temporal/activities/export.d.ts.map +1 -0
- package/dist/temporal/activities/export.js +79 -0
- package/dist/temporal/activities/export.js.map +1 -0
- package/dist/temporal/activities/factory.d.ts +5 -0
- package/dist/temporal/activities/factory.d.ts.map +1 -0
- package/dist/temporal/activities/factory.js +26 -0
- package/dist/temporal/activities/factory.js.map +1 -0
- package/dist/temporal/activities/gate-logs.d.ts +20 -0
- package/dist/temporal/activities/gate-logs.d.ts.map +1 -0
- package/dist/temporal/activities/gate-logs.js +62 -0
- package/dist/temporal/activities/gate-logs.js.map +1 -0
- package/dist/temporal/activities/generation-runtime.d.ts +6 -0
- package/dist/temporal/activities/generation-runtime.d.ts.map +1 -0
- package/dist/temporal/activities/generation-runtime.js +56 -0
- package/dist/temporal/activities/generation-runtime.js.map +1 -0
- package/dist/temporal/activities/harbor.d.ts +11 -0
- package/dist/temporal/activities/harbor.d.ts.map +1 -0
- package/dist/temporal/activities/harbor.js +112 -0
- package/dist/temporal/activities/harbor.js.map +1 -0
- package/dist/temporal/activities/modal-build-log.d.ts +12 -0
- package/dist/temporal/activities/modal-build-log.d.ts.map +1 -0
- package/dist/temporal/activities/modal-build-log.js +57 -0
- package/dist/temporal/activities/modal-build-log.js.map +1 -0
- package/dist/temporal/activities/prompts-authoring.d.ts +6 -0
- package/dist/temporal/activities/prompts-authoring.d.ts.map +1 -0
- package/dist/temporal/activities/prompts-authoring.js +87 -0
- package/dist/temporal/activities/prompts-authoring.js.map +1 -0
- package/dist/temporal/activities/prompts-verifier.d.ts +17 -0
- package/dist/temporal/activities/prompts-verifier.d.ts.map +1 -0
- package/dist/temporal/activities/prompts-verifier.js +66 -0
- package/dist/temporal/activities/prompts-verifier.js.map +1 -0
- package/dist/temporal/activities/provenance.d.ts +4 -0
- package/dist/temporal/activities/provenance.d.ts.map +1 -0
- package/dist/temporal/activities/provenance.js +18 -0
- package/dist/temporal/activities/provenance.js.map +1 -0
- package/dist/temporal/activities/replay.d.ts +20 -0
- package/dist/temporal/activities/replay.d.ts.map +1 -0
- package/dist/temporal/activities/replay.js +135 -0
- package/dist/temporal/activities/replay.js.map +1 -0
- package/dist/temporal/activities/round-outcome.d.ts +63 -0
- package/dist/temporal/activities/round-outcome.d.ts.map +1 -0
- package/dist/temporal/activities/round-outcome.js +127 -0
- package/dist/temporal/activities/round-outcome.js.map +1 -0
- package/dist/temporal/activities/runtime.d.ts +38 -0
- package/dist/temporal/activities/runtime.d.ts.map +1 -0
- package/dist/temporal/activities/runtime.js +146 -0
- package/dist/temporal/activities/runtime.js.map +1 -0
- package/dist/temporal/activities/session-verify.d.ts +45 -0
- package/dist/temporal/activities/session-verify.d.ts.map +1 -0
- package/dist/temporal/activities/session-verify.js +91 -0
- package/dist/temporal/activities/session-verify.js.map +1 -0
- package/dist/temporal/activities/submissions.d.ts +9 -0
- package/dist/temporal/activities/submissions.d.ts.map +1 -0
- package/dist/temporal/activities/submissions.js +28 -0
- package/dist/temporal/activities/submissions.js.map +1 -0
- package/dist/temporal/activities/task-compiler.d.ts +21 -0
- package/dist/temporal/activities/task-compiler.d.ts.map +1 -0
- package/dist/temporal/activities/task-compiler.js +63 -0
- package/dist/temporal/activities/task-compiler.js.map +1 -0
- package/dist/temporal/activities/types.d.ts +57 -0
- package/dist/temporal/activities/types.d.ts.map +1 -0
- package/dist/temporal/activities/types.js +2 -0
- package/dist/temporal/activities/types.js.map +1 -0
- package/dist/temporal/activities/verifier-material.d.ts +18 -0
- package/dist/temporal/activities/verifier-material.d.ts.map +1 -0
- package/dist/temporal/activities/verifier-material.js +49 -0
- package/dist/temporal/activities/verifier-material.js.map +1 -0
- package/dist/temporal/activities/verifier-outcome.d.ts +19 -0
- package/dist/temporal/activities/verifier-outcome.d.ts.map +1 -0
- package/dist/temporal/activities/verifier-outcome.js +70 -0
- package/dist/temporal/activities/verifier-outcome.js.map +1 -0
- package/dist/temporal/activities/verifier-round.d.ts +8 -0
- package/dist/temporal/activities/verifier-round.d.ts.map +1 -0
- package/dist/temporal/activities/verifier-round.js +110 -0
- package/dist/temporal/activities/verifier-round.js.map +1 -0
- package/dist/temporal/activities/verify-harbor.d.ts +15 -0
- package/dist/temporal/activities/verify-harbor.d.ts.map +1 -0
- package/dist/temporal/activities/verify-harbor.js +193 -0
- package/dist/temporal/activities/verify-harbor.js.map +1 -0
- package/dist/temporal/activities/verify.d.ts +11 -0
- package/dist/temporal/activities/verify.d.ts.map +1 -0
- package/dist/temporal/activities/verify.js +151 -0
- package/dist/temporal/activities/verify.js.map +1 -0
- package/dist/temporal/activities.d.ts +3 -51
- package/dist/temporal/activities.d.ts.map +1 -1
- package/dist/temporal/activities.js +2 -886
- package/dist/temporal/activities.js.map +1 -1
- package/dist/temporal/connection.d.ts.map +1 -1
- package/dist/temporal/connection.js +3 -2
- package/dist/temporal/connection.js.map +1 -1
- package/dist/temporal/worker-main.js +19 -3
- package/dist/temporal/worker-main.js.map +1 -1
- package/dist/temporal/workflow/activity-proxies.d.ts +3 -0
- package/dist/temporal/workflow/activity-proxies.d.ts.map +1 -0
- package/dist/temporal/workflow/activity-proxies.js +45 -0
- package/dist/temporal/workflow/activity-proxies.js.map +1 -0
- package/dist/temporal/workflow/authoring-stage.d.ts +5 -0
- package/dist/temporal/workflow/authoring-stage.d.ts.map +1 -0
- package/dist/temporal/workflow/authoring-stage.js +64 -0
- package/dist/temporal/workflow/authoring-stage.js.map +1 -0
- package/dist/temporal/workflow/candidate-tracker.d.ts +28 -0
- package/dist/temporal/workflow/candidate-tracker.d.ts.map +1 -0
- package/dist/temporal/workflow/candidate-tracker.js +85 -0
- package/dist/temporal/workflow/candidate-tracker.js.map +1 -0
- package/dist/temporal/workflow/candidate.d.ts +6 -0
- package/dist/temporal/workflow/candidate.d.ts.map +1 -0
- package/dist/temporal/workflow/candidate.js +54 -0
- package/dist/temporal/workflow/candidate.js.map +1 -0
- package/dist/temporal/workflow/discovery.d.ts +19 -0
- package/dist/temporal/workflow/discovery.d.ts.map +1 -0
- package/dist/temporal/workflow/discovery.js +137 -0
- package/dist/temporal/workflow/discovery.js.map +1 -0
- package/dist/temporal/workflow/failures.d.ts +5 -0
- package/dist/temporal/workflow/failures.d.ts.map +1 -0
- package/dist/temporal/workflow/failures.js +28 -0
- package/dist/temporal/workflow/failures.js.map +1 -0
- package/dist/temporal/workflow/run.d.ts +5 -0
- package/dist/temporal/workflow/run.d.ts.map +1 -0
- package/dist/temporal/workflow/run.js +154 -0
- package/dist/temporal/workflow/run.js.map +1 -0
- package/dist/temporal/workflow/stage.d.ts +26 -0
- package/dist/temporal/workflow/stage.d.ts.map +1 -0
- package/dist/temporal/workflow/stage.js +16 -0
- package/dist/temporal/workflow/stage.js.map +1 -0
- package/dist/temporal/workflow/verification-stage.d.ts +11 -0
- package/dist/temporal/workflow/verification-stage.d.ts.map +1 -0
- package/dist/temporal/workflow/verification-stage.js +20 -0
- package/dist/temporal/workflow/verification-stage.js.map +1 -0
- package/dist/temporal/workflow.d.ts +12 -4
- package/dist/temporal/workflow.d.ts.map +1 -1
- package/dist/temporal/workflow.js +38 -445
- package/dist/temporal/workflow.js.map +1 -1
- package/dist/verifier-fix.d.ts +20 -0
- package/dist/verifier-fix.d.ts.map +1 -0
- package/dist/verifier-fix.js +62 -0
- package/dist/verifier-fix.js.map +1 -0
- package/dist/verify-report.d.ts +9 -0
- package/dist/verify-report.d.ts.map +1 -0
- package/dist/verify-report.js +135 -0
- package/dist/verify-report.js.map +1 -0
- package/dist/viewer/archived-keys.d.ts +9 -0
- package/dist/viewer/archived-keys.d.ts.map +1 -0
- package/dist/viewer/archived-keys.js +36 -0
- package/dist/viewer/archived-keys.js.map +1 -0
- package/dist/viewer/archived.d.ts +20 -0
- package/dist/viewer/archived.d.ts.map +1 -0
- package/dist/viewer/archived.js +238 -0
- package/dist/viewer/archived.js.map +1 -0
- package/dist/viewer/artifacts.d.ts +8 -0
- package/dist/viewer/artifacts.d.ts.map +1 -0
- package/dist/viewer/artifacts.js +96 -0
- package/dist/viewer/artifacts.js.map +1 -0
- package/dist/viewer/bundle.d.ts +9 -0
- package/dist/viewer/bundle.d.ts.map +1 -0
- package/dist/viewer/bundle.js +79 -0
- package/dist/viewer/bundle.js.map +1 -0
- package/dist/viewer/candidates.d.ts +9 -0
- package/dist/viewer/candidates.d.ts.map +1 -0
- package/dist/viewer/candidates.js +137 -0
- package/dist/viewer/candidates.js.map +1 -0
- package/dist/viewer/local-server.d.ts +11 -0
- package/dist/viewer/local-server.d.ts.map +1 -0
- package/dist/viewer/local-server.js +64 -0
- package/dist/viewer/local-server.js.map +1 -0
- package/dist/viewer/task-files.d.ts +10 -0
- package/dist/viewer/task-files.d.ts.map +1 -0
- package/dist/viewer/task-files.js +120 -0
- package/dist/viewer/task-files.js.map +1 -0
- package/dist/viewer/types.d.ts +78 -0
- package/dist/viewer/types.d.ts.map +1 -0
- package/dist/viewer/types.js +36 -0
- package/dist/viewer/types.js.map +1 -0
- package/docs/api.md +168 -0
- package/docs/evaluations.md +42 -15
- package/docs/operations.md +254 -26
- package/docs/solver-evaluations.md +63 -0
- package/docs/task-construction.md +21 -11
- package/drizzle/0000_glossy_johnny_blaze.sql +97 -0
- package/drizzle/0001_evaluation_records.sql +5 -0
- package/drizzle/0002_task_deletion.sql +1 -0
- package/drizzle/0003_drop_repo_runs.sql +3 -0
- package/drizzle/0004_preserve_batch_runs.sql +8 -0
- package/drizzle/0005_api_keys.sql +15 -0
- package/drizzle/meta/0000_snapshot.json +776 -0
- package/drizzle/meta/0001_snapshot.json +807 -0
- package/drizzle/meta/0002_snapshot.json +813 -0
- package/drizzle/meta/0003_snapshot.json +726 -0
- package/drizzle/meta/0004_snapshot.json +813 -0
- package/drizzle/meta/0005_snapshot.json +919 -0
- package/drizzle/meta/_journal.json +48 -0
- package/package.json +39 -25
- package/src/extensions/authoring.ts +83 -72
- package/src/extensions/shared/deliverable.ts +153 -0
- package/src/extensions/shared/mailbox.ts +128 -0
- package/src/extensions/shared/schemas.ts +101 -0
- package/src/extensions/shared/static-check.ts +103 -0
- package/src/extensions/verifier.ts +88 -0
- package/src/skills/selfbench/SKILL.md +71 -13
- package/biome.json +0 -24
- package/dist/agent-smoke-main.d.ts +0 -3
- package/dist/agent-smoke-main.d.ts.map +0 -1
- package/dist/agent-smoke-main.js +0 -55
- package/dist/agent-smoke-main.js.map +0 -1
- package/dist/agent-smoke.d.ts +0 -18
- package/dist/agent-smoke.d.ts.map +0 -1
- package/dist/agent-smoke.js +0 -103
- package/dist/agent-smoke.js.map +0 -1
- package/dist/codex-review.d.ts +0 -41
- package/dist/codex-review.d.ts.map +0 -1
- package/dist/codex-review.js +0 -193
- package/dist/codex-review.js.map +0 -1
- package/dist/eval-main.d.ts +0 -3
- package/dist/eval-main.d.ts.map +0 -1
- package/dist/eval-main.js +0 -81
- package/dist/eval-main.js.map +0 -1
- package/dist/evaluate.d.ts +0 -25
- package/dist/evaluate.d.ts.map +0 -1
- package/dist/evaluate.js +0 -214
- package/dist/evaluate.js.map +0 -1
- package/dist/modal-auth.d.ts.map +0 -1
- package/dist/modal-auth.js.map +0 -1
- package/dist/reaudit-main.d.ts +0 -3
- package/dist/reaudit-main.d.ts.map +0 -1
- package/dist/reaudit-main.js +0 -158
- package/dist/reaudit-main.js.map +0 -1
- package/dist/repair-main.d.ts +0 -3
- package/dist/repair-main.d.ts.map +0 -1
- package/dist/repair-main.js +0 -171
- package/dist/repair-main.js.map +0 -1
- package/dist/review/assets/index-CZ3G759O.js +0 -1568
- package/dist/review/assets/index-DgSLzX8l.css +0 -1
- package/dist/sandbox/programs/prepare-repair.d.ts +0 -7
- package/dist/sandbox/programs/prepare-repair.d.ts.map +0 -1
- package/dist/sandbox/programs/prepare-repair.js.map +0 -1
- package/dist/sandbox/programs/repair.d.ts +0 -3
- package/dist/sandbox/programs/repair.d.ts.map +0 -1
- package/dist/sandbox/programs/repair.js +0 -100
- package/dist/sandbox/programs/repair.js.map +0 -1
- package/dist/sandbox/programs/review.d.ts +0 -2
- package/dist/sandbox/programs/review.d.ts.map +0 -1
- package/dist/sandbox/programs/review.js +0 -18
- package/dist/sandbox/programs/review.js.map +0 -1
- package/dist/sandbox/programs/validation-repair.d.ts +0 -3
- package/dist/sandbox/programs/validation-repair.d.ts.map +0 -1
- package/dist/sandbox/programs/validation-repair.js +0 -115
- package/dist/sandbox/programs/validation-repair.js.map +0 -1
- package/dist/sandbox-repair.bundle.js +0 -323
- package/dist/sandbox-review.bundle.js +0 -14462
- package/dist/validate-main.d.ts +0 -3
- package/dist/validate-main.d.ts.map +0 -1
- package/dist/validate-main.js +0 -143
- package/dist/validate-main.js.map +0 -1
- package/dist/validation-repair.d.ts +0 -10
- package/dist/validation-repair.d.ts.map +0 -1
- package/dist/validation-repair.js +0 -72
- package/dist/validation-repair.js.map +0 -1
- package/review/index.html +0 -14
- package/review/src/App.tsx +0 -338
- package/review/src/export-loader.test.ts +0 -57
- package/review/src/export-loader.ts +0 -151
- package/review/src/main.tsx +0 -15
- package/review/src/styles.css +0 -162
- package/review/src/types.ts +0 -47
- package/review/tsconfig.json +0 -16
- package/review/vite.config.ts +0 -20
- package/scripts/build-sandbox-programs.ts +0 -22
- package/scripts/verify-package.ts +0 -102
- package/scripts/write-build-metadata.ts +0 -27
- package/src/agent-smoke-main.ts +0 -64
- package/src/agent-smoke.ts +0 -138
- package/src/api-main.ts +0 -12
- package/src/api.ts +0 -291
- package/src/artifacts.ts +0 -357
- package/src/audit.ts +0 -106
- package/src/build-metadata.ts +0 -3
- package/src/cli.ts +0 -504
- package/src/codex-review.ts +0 -229
- package/src/config.ts +0 -239
- package/src/contracts.ts +0 -233
- package/src/coupling.ts +0 -259
- package/src/eval-main.ts +0 -93
- package/src/evaluate.ts +0 -300
- package/src/github.ts +0 -26
- package/src/harbor-environment.ts +0 -17
- package/src/harbor-results.ts +0 -144
- package/src/harbor-task.ts +0 -533
- package/src/hash.ts +0 -5
- package/src/modal-auth.ts +0 -11
- package/src/parallel.ts +0 -24
- package/src/process.ts +0 -167
- package/src/project-paths.ts +0 -15
- package/src/provenance-associations.ts +0 -311
- package/src/provenance.ts +0 -561
- package/src/providers.ts +0 -22
- package/src/reaudit-main.ts +0 -198
- package/src/repair-main.ts +0 -209
- package/src/repair.ts +0 -55
- package/src/run-wait.ts +0 -40
- package/src/sandbox/contracts.ts +0 -52
- package/src/sandbox/index.ts +0 -23
- package/src/sandbox/programs/author.ts +0 -19
- package/src/sandbox/programs/prepare-repair.ts +0 -44
- package/src/sandbox/programs/repair.ts +0 -132
- package/src/sandbox/programs/review.ts +0 -19
- package/src/sandbox/programs/validation-repair.ts +0 -153
- package/src/sandbox/providers/docker/executor.ts +0 -115
- package/src/sandbox/providers/modal/executor.ts +0 -217
- package/src/sandbox/providers/vercel/command.ts +0 -127
- package/src/sandbox/providers/vercel/executor.ts +0 -448
- package/src/sandbox/providers/vercel/fetch.ts +0 -45
- package/src/sandbox/timeout.ts +0 -56
- package/src/setup/vercel/cli.ts +0 -403
- package/src/setup/vercel/index.ts +0 -3
- package/src/setup/vercel/probe.ts +0 -232
- package/src/setup/vercel/profile.ts +0 -322
- package/src/setup/vercel/runtime-image.ts +0 -204
- package/src/setup/vercel/setup.ts +0 -419
- package/src/subscription-auth.ts +0 -80
- package/src/temporal/activities.ts +0 -1348
- package/src/temporal/connection.ts +0 -23
- package/src/temporal/worker-main.ts +0 -28
- package/src/temporal/workflow.ts +0 -568
- package/src/terminal-prompts.ts +0 -197
- package/src/terminal-reporter.ts +0 -126
- package/src/validate-main.ts +0 -177
- package/src/validation-repair.ts +0 -94
- package/tsconfig.build.json +0 -13
- package/tsconfig.json +0 -21
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
import { createHash } from "node:crypto";
|
|
2
|
+
export function evaluationPrefix(repoId, id = "") {
|
|
3
|
+
if (!Number.isSafeInteger(repoId) || repoId < 1 || (id && !/^[a-f0-9-]{36}$/.test(id)))
|
|
4
|
+
throw new Error("Invalid evaluation identity");
|
|
5
|
+
return `evaluations/repos/${repoId}/${id ? `${id}/` : ""}`;
|
|
6
|
+
}
|
|
7
|
+
export function initialEvaluation(input, modelLabel) {
|
|
8
|
+
const { tasks, ...metadata } = input;
|
|
9
|
+
return {
|
|
10
|
+
...metadata,
|
|
11
|
+
revision: 0,
|
|
12
|
+
datasetKey: createHash("sha256")
|
|
13
|
+
.update(JSON.stringify(tasks
|
|
14
|
+
.map(({ runId, taskId, bundleKey }) => [runId, taskId, bundleKey])
|
|
15
|
+
.sort((left, right) => JSON.stringify(left).localeCompare(JSON.stringify(right)))))
|
|
16
|
+
.digest("hex"),
|
|
17
|
+
modelLabel,
|
|
18
|
+
status: "queued",
|
|
19
|
+
trials: tasks.flatMap((task) => input.harnesses.map((harness) => ({
|
|
20
|
+
taskId: task.taskId,
|
|
21
|
+
runId: task.runId,
|
|
22
|
+
harness,
|
|
23
|
+
status: "queued",
|
|
24
|
+
rewards: {},
|
|
25
|
+
log: "",
|
|
26
|
+
steps: [],
|
|
27
|
+
artifacts: [],
|
|
28
|
+
}))),
|
|
29
|
+
};
|
|
30
|
+
}
|
|
31
|
+
export async function saveEvaluation(store, run) {
|
|
32
|
+
run.revision += 1;
|
|
33
|
+
await store.put(`${evaluationPrefix(run.repoId, run.id)}snapshots/${String(run.revision).padStart(10, "0")}.json`, Buffer.from(JSON.stringify(run)), "application/json");
|
|
34
|
+
}
|
|
35
|
+
export async function getEvaluation(store, repoId, id) {
|
|
36
|
+
const entries = await store.list(`${evaluationPrefix(repoId, id)}snapshots`);
|
|
37
|
+
const latest = entries.sort((left, right) => right.key.localeCompare(left.key))[0];
|
|
38
|
+
const bytes = latest ? await store.getByKey(latest.key) : undefined;
|
|
39
|
+
return bytes ? JSON.parse(Buffer.from(bytes).toString("utf8")) : undefined;
|
|
40
|
+
}
|
|
41
|
+
export async function listEvaluations(store, repoId) {
|
|
42
|
+
const prefix = evaluationPrefix(repoId);
|
|
43
|
+
const entries = (await store.list(prefix.slice(0, -1))).filter((entry) => entry.key.startsWith(prefix));
|
|
44
|
+
const latest = new Map();
|
|
45
|
+
for (const entry of entries) {
|
|
46
|
+
if (!/\/snapshots\/\d{10}\.json$/.test(entry.key))
|
|
47
|
+
continue;
|
|
48
|
+
const id = entry.key.slice(prefix.length).split("/")[0];
|
|
49
|
+
if (id && entry.key > (latest.get(id) ?? ""))
|
|
50
|
+
latest.set(id, entry.key);
|
|
51
|
+
}
|
|
52
|
+
const runs = await Promise.all([...latest.values()].map(async (key) => {
|
|
53
|
+
const bytes = await store.getByKey(key);
|
|
54
|
+
return bytes ? JSON.parse(Buffer.from(bytes).toString("utf8")) : undefined;
|
|
55
|
+
}));
|
|
56
|
+
return runs
|
|
57
|
+
.filter((run) => !!run)
|
|
58
|
+
.sort((left, right) => right.createdAt.localeCompare(left.createdAt));
|
|
59
|
+
}
|
|
60
|
+
//# sourceMappingURL=store.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"store.js","sourceRoot":"","sources":["../../src/evaluation/store.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AAIzC,MAAM,UAAU,gBAAgB,CAAC,MAAc,EAAE,EAAE,GAAG,EAAE;IACtD,IAAI,CAAC,MAAM,CAAC,aAAa,CAAC,MAAM,CAAC,IAAI,MAAM,GAAG,CAAC,IAAI,CAAC,EAAE,IAAI,CAAC,iBAAiB,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACpF,MAAM,IAAI,KAAK,CAAC,6BAA6B,CAAC,CAAC;IACjD,OAAO,qBAAqB,MAAM,IAAI,EAAE,CAAC,CAAC,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC;AAC7D,CAAC;AACD,MAAM,UAAU,iBAAiB,CAAC,KAAsB,EAAE,UAAkB;IAC1E,MAAM,EAAE,KAAK,EAAE,GAAG,QAAQ,EAAE,GAAG,KAAK,CAAC;IACrC,OAAO;QACL,GAAG,QAAQ;QACX,QAAQ,EAAE,CAAC;QACX,UAAU,EAAE,UAAU,CAAC,QAAQ,CAAC;aAC7B,MAAM,CACL,IAAI,CAAC,SAAS,CACZ,KAAK;aACF,GAAG,CAAC,CAAC,EAAE,KAAK,EAAE,MAAM,EAAE,SAAS,EAAE,EAAE,EAAE,CAAC,CAAC,KAAK,EAAE,MAAM,EAAE,SAAS,CAAC,CAAC;aACjE,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,IAAI,CAAC,SAAS,CAAC,IAAI,CAAC,CAAC,aAAa,CAAC,IAAI,CAAC,SAAS,CAAC,KAAK,CAAC,CAAC,CAAC,CACpF,CACF;aACA,MAAM,CAAC,KAAK,CAAC;QAChB,UAAU;QACV,MAAM,EAAE,QAAQ;QAChB,MAAM,EAAE,KAAK,CAAC,OAAO,CAAC,CAAC,IAAI,EAAE,EAAE,CAC7B,KAAK,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,OAAO,EAAE,EAAE,CAAC,CAAC;YAChC,MAAM,EAAE,IAAI,CAAC,MAAM;YACnB,KAAK,EAAE,IAAI,CAAC,KAAK;YACjB,OAAO;YACP,MAAM,EAAE,QAAQ;YAChB,OAAO,EAAE,EAAE;YACX,GAAG,EAAE,EAAE;YACP,KAAK,EAAE,EAAE;YACT,SAAS,EAAE,EAAE;SACd,CAAC,CAAC,CACJ;KACF,CAAC;AACJ,CAAC;AACD,MAAM,CAAC,KAAK,UAAU,cAAc,CAAC,KAAoB,EAAE,GAAkB;IAC3E,GAAG,CAAC,QAAQ,IAAI,CAAC,CAAC;IAClB,MAAM,KAAK,CAAC,GAAG,CACb,GAAG,gBAAgB,CAAC,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,EAAE,CAAC,aAAa,MAAM,CAAC,GAAG,CAAC,QAAQ,CAAC,CAAC,QAAQ,CAAC,EAAE,EAAE,GAAG,CAAC,OAAO,EACjG,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,CAAC,EAChC,kBAAkB,CACnB,CAAC;AACJ,CAAC;AACD,MAAM,CAAC,KAAK,UAAU,aAAa,CACjC,KAAoB,EACpB,MAAc,EACd,EAAU;IAEV,MAAM,OAAO,GAAG,MAAM,KAAK,CAAC,IAAI,CAAC,GAAG,gBAAgB,CAAC,MAAM,EAAE,EAAE,CAAC,WAAW,CAAC,CAAC;IAC7E,MAAM,MAAM,GAAG,OAAO,CAAC,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,aAAa,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC;IACnF,MAAM,KAAK,GAAG,MAAM,CAAC,CAAC,CAAC,MAAM,KAAK,CAAC,QAAQ,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,SAAS,CAAC;IACpE,OAAO,KAAK,CAAC,CAAC,CAAE,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAmB,CAAC,CAAC,CAAC,SAAS,CAAC;AAChG,CAAC;AACD,MAAM,CAAC,KAAK,UAAU,eAAe,CACnC,KAAoB,EACpB,MAAc;IAEd,MAAM,MAAM,GAAG,gBAAgB,CAAC,MAAM,CAAC,CAAC;IACxC,MAAM,OAAO,GAAG,CAAC,MAAM,KAAK,CAAC,IAAI,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,KAAK,EAAE,EAAE,CACvE,KAAK,CAAC,GAAG,CAAC,UAAU,CAAC,MAAM,CAAC,CAC7B,CAAC;IACF,MAAM,MAAM,GAAG,IAAI,GAAG,EAAkB,CAAC;IACzC,KAAK,MAAM,KAAK,IAAI,OAAO,EAAE,CAAC;QAC5B,IAAI,CAAC,4BAA4B,CAAC,IAAI,CAAC,KAAK,CAAC,GAAG,CAAC;YAAE,SAAS;QAC5D,MAAM,EAAE,GAAG,KAAK,CAAC,GAAG,CAAC,KAAK,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;QACxD,IAAI,EAAE,IAAI,KAAK,CAAC,GAAG,GAAG,CAAC,MAAM,CAAC,GAAG,CAAC,EAAE,CAAC,IAAI,EAAE,CAAC;YAAE,MAAM,CAAC,GAAG,CAAC,EAAE,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC;IAC1E,CAAC;IACD,MAAM,IAAI,GAAG,MAAM,OAAO,CAAC,GAAG,CAC5B,CAAC,GAAG,MAAM,CAAC,MAAM,EAAE,CAAC,CAAC,GAAG,CAAC,KAAK,EAAE,GAAG,EAAE,EAAE;QACrC,MAAM,KAAK,GAAG,MAAM,KAAK,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC;QACxC,OAAO,KAAK,CAAC,CAAC,CAAE,IAAI,CAAC,KAAK,CAAC,MAAM,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAmB,CAAC,CAAC,CAAC,SAAS,CAAC;IAChG,CAAC,CAAC,CACH,CAAC;IACF,OAAO,IAAI;SACR,MAAM,CAAC,CAAC,GAAG,EAAwB,EAAE,CAAC,CAAC,CAAC,GAAG,CAAC;SAC5C,IAAI,CAAC,CAAC,IAAI,EAAE,KAAK,EAAE,EAAE,CAAC,KAAK,CAAC,SAAS,CAAC,aAAa,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC,CAAC;AAC1E,CAAC"}
|
|
@@ -0,0 +1,98 @@
|
|
|
1
|
+
import type { Harness } from "./harnesses.js";
|
|
2
|
+
import type { ThinkingLevel } from "./model-options.js";
|
|
3
|
+
export type { Harness } from "./harnesses.js";
|
|
4
|
+
export type EvaluationSandbox = "docker" | "modal" | "e2b" | "daytona";
|
|
5
|
+
export interface EvaluationPricing {
|
|
6
|
+
maxInputTokens?: number;
|
|
7
|
+
input: number;
|
|
8
|
+
output: number;
|
|
9
|
+
cacheRead: number;
|
|
10
|
+
cacheWrite: number;
|
|
11
|
+
source: string;
|
|
12
|
+
asOf: string;
|
|
13
|
+
}
|
|
14
|
+
export interface EvaluationTask {
|
|
15
|
+
runId: string;
|
|
16
|
+
taskId: string;
|
|
17
|
+
bundleKey: string;
|
|
18
|
+
}
|
|
19
|
+
export interface EvaluationInput {
|
|
20
|
+
id: string;
|
|
21
|
+
repoId: number;
|
|
22
|
+
tenant: string;
|
|
23
|
+
startedBy: string;
|
|
24
|
+
createdAt: string;
|
|
25
|
+
model: string;
|
|
26
|
+
modelName: string;
|
|
27
|
+
thinking?: ThinkingLevel;
|
|
28
|
+
harnesses: Harness[];
|
|
29
|
+
sandbox: EvaluationSandbox;
|
|
30
|
+
tasks: EvaluationTask[];
|
|
31
|
+
pricing?: EvaluationPricing;
|
|
32
|
+
credentialOwnerId?: number;
|
|
33
|
+
credentialOrgId?: number;
|
|
34
|
+
comparisonId?: string;
|
|
35
|
+
credentials?: {
|
|
36
|
+
modelCredentialId: string;
|
|
37
|
+
sandboxCredentialId: string;
|
|
38
|
+
provider: "openai" | "anthropic" | "openrouter" | "custom";
|
|
39
|
+
};
|
|
40
|
+
}
|
|
41
|
+
export interface SolverStep {
|
|
42
|
+
id: string;
|
|
43
|
+
role: string;
|
|
44
|
+
text: string;
|
|
45
|
+
tools: {
|
|
46
|
+
id: string;
|
|
47
|
+
name: string;
|
|
48
|
+
input: string;
|
|
49
|
+
output: string;
|
|
50
|
+
}[];
|
|
51
|
+
}
|
|
52
|
+
export interface TokenUsage {
|
|
53
|
+
input: number;
|
|
54
|
+
output: number;
|
|
55
|
+
cacheRead: number;
|
|
56
|
+
cacheWrite: number;
|
|
57
|
+
}
|
|
58
|
+
export interface EvaluationTrial {
|
|
59
|
+
taskId: string;
|
|
60
|
+
runId: string;
|
|
61
|
+
harness: Harness;
|
|
62
|
+
status: "queued" | "running" | "completed" | "failed";
|
|
63
|
+
rewards: Record<string, number>;
|
|
64
|
+
error?: string;
|
|
65
|
+
log: string;
|
|
66
|
+
steps: SolverStep[];
|
|
67
|
+
artifacts: string[];
|
|
68
|
+
startedAt?: string;
|
|
69
|
+
finishedAt?: string;
|
|
70
|
+
modelVerified?: boolean;
|
|
71
|
+
apiCostUsd?: number;
|
|
72
|
+
tokenUsage?: TokenUsage;
|
|
73
|
+
costSource?: "harbor" | "reference-rates";
|
|
74
|
+
}
|
|
75
|
+
export interface EvaluationRun extends Omit<EvaluationInput, "tasks"> {
|
|
76
|
+
revision: number;
|
|
77
|
+
datasetKey?: string;
|
|
78
|
+
modelLabel: string;
|
|
79
|
+
status: "queued" | "running" | "completed" | "failed";
|
|
80
|
+
trials: EvaluationTrial[];
|
|
81
|
+
finishedAt?: string;
|
|
82
|
+
error?: string;
|
|
83
|
+
}
|
|
84
|
+
export interface EvaluationModel {
|
|
85
|
+
id: string;
|
|
86
|
+
label: string;
|
|
87
|
+
model: string;
|
|
88
|
+
harnesses: Harness[];
|
|
89
|
+
pricing?: EvaluationPricing;
|
|
90
|
+
sandbox?: EvaluationSandbox;
|
|
91
|
+
}
|
|
92
|
+
export interface EvaluationChoices {
|
|
93
|
+
models: EvaluationModel[];
|
|
94
|
+
sandboxes: EvaluationSandbox[];
|
|
95
|
+
harborVersion: string;
|
|
96
|
+
configurable?: boolean;
|
|
97
|
+
}
|
|
98
|
+
//# sourceMappingURL=types.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"types.d.ts","sourceRoot":"","sources":["../../src/evaluation/types.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,OAAO,EAAE,MAAM,gBAAgB,CAAC;AAC9C,OAAO,KAAK,EAAE,aAAa,EAAE,MAAM,oBAAoB,CAAC;AAExD,YAAY,EAAE,OAAO,EAAE,MAAM,gBAAgB,CAAC;AAC9C,MAAM,MAAM,iBAAiB,GAAG,QAAQ,GAAG,OAAO,GAAG,KAAK,GAAG,SAAS,CAAC;AACvE,MAAM,WAAW,iBAAiB;IAChC,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,EAAE,MAAM,CAAC;IACnB,MAAM,EAAE,MAAM,CAAC;IACf,IAAI,EAAE,MAAM,CAAC;CACd;AACD,MAAM,WAAW,cAAc;IAC7B,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;CACnB;AACD,MAAM,WAAW,eAAe;IAC9B,EAAE,EAAE,MAAM,CAAC;IACX,MAAM,EAAE,MAAM,CAAC;IACf,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;IAClB,SAAS,EAAE,MAAM,CAAC;IAClB,KAAK,EAAE,MAAM,CAAC;IACd,SAAS,EAAE,MAAM,CAAC;IAClB,QAAQ,CAAC,EAAE,aAAa,CAAC;IACzB,SAAS,EAAE,OAAO,EAAE,CAAC;IACrB,OAAO,EAAE,iBAAiB,CAAC;IAC3B,KAAK,EAAE,cAAc,EAAE,CAAC;IACxB,OAAO,CAAC,EAAE,iBAAiB,CAAC;IAC5B,iBAAiB,CAAC,EAAE,MAAM,CAAC;IAC3B,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,YAAY,CAAC,EAAE,MAAM,CAAC;IACtB,WAAW,CAAC,EAAE;QACZ,iBAAiB,EAAE,MAAM,CAAC;QAC1B,mBAAmB,EAAE,MAAM,CAAC;QAC5B,QAAQ,EAAE,QAAQ,GAAG,WAAW,GAAG,YAAY,GAAG,QAAQ,CAAC;KAC5D,CAAC;CACH;AACD,MAAM,WAAW,UAAU;IACzB,EAAE,EAAE,MAAM,CAAC;IACX,IAAI,EAAE,MAAM,CAAC;IACb,IAAI,EAAE,MAAM,CAAC;IACb,KAAK,EAAE;QAAE,EAAE,EAAE,MAAM,CAAC;QAAC,IAAI,EAAE,MAAM,CAAC;QAAC,KAAK,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,MAAM,CAAA;KAAE,EAAE,CAAC;CACtE;AACD,MAAM,WAAW,UAAU;IACzB,KAAK,EAAE,MAAM,CAAC;IACd,MAAM,EAAE,MAAM,CAAC;IACf,SAAS,EAAE,MAAM,CAAC;IAClB,UAAU,EAAE,MAAM,CAAC;CACpB;AACD,MAAM,WAAW,eAAe;IAC9B,MAAM,EAAE,MAAM,CAAC;IACf,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,OAAO,CAAC;IACjB,MAAM,EAAE,QAAQ,GAAG,SAAS,GAAG,WAAW,GAAG,QAAQ,CAAC;IACtD,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IAChC,KAAK,CAAC,EAAE,MAAM,CAAC;IACf,GAAG,EAAE,MAAM,CAAC;IACZ,KAAK,EAAE,UAAU,EAAE,CAAC;IACpB,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,aAAa,CAAC,EAAE,OAAO,CAAC;IACxB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,UAAU,CAAC,EAAE,UAAU,CAAC;IACxB,UAAU,CAAC,EAAE,QAAQ,GAAG,iBAAiB,CAAC;CAC3C;AACD,MAAM,WAAW,aAAc,SAAQ,IAAI,CAAC,eAAe,EAAE,OAAO,CAAC;IACnE,QAAQ,EAAE,MAAM,CAAC;IACjB,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,UAAU,EAAE,MAAM,CAAC;IACnB,MAAM,EAAE,QAAQ,GAAG,SAAS,GAAG,WAAW,GAAG,QAAQ,CAAC;IACtD,MAAM,EAAE,eAAe,EAAE,CAAC;IAC1B,UAAU,CAAC,EAAE,MAAM,CAAC;IACpB,KAAK,CAAC,EAAE,MAAM,CAAC;CAChB;AACD,MAAM,WAAW,eAAe;IAC9B,EAAE,EAAE,MAAM,CAAC;IACX,KAAK,EAAE,MAAM,CAAC;IACd,KAAK,EAAE,MAAM,CAAC;IACd,SAAS,EAAE,OAAO,EAAE,CAAC;IACrB,OAAO,CAAC,EAAE,iBAAiB,CAAC;IAC5B,OAAO,CAAC,EAAE,iBAAiB,CAAC;CAC7B;AACD,MAAM,WAAW,iBAAiB;IAChC,MAAM,EAAE,eAAe,EAAE,CAAC;IAC1B,SAAS,EAAE,iBAAiB,EAAE,CAAC;IAC/B,aAAa,EAAE,MAAM,CAAC;IACtB,YAAY,CAAC,EAAE,OAAO,CAAC;CACxB"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"types.js","sourceRoot":"","sources":["../../src/evaluation/types.ts"],"names":[],"mappings":""}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"worker-main.d.ts","sourceRoot":"","sources":["../../src/evaluation/worker-main.ts"],"names":[],"mappings":""}
|
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
import { fileURLToPath } from "node:url";
|
|
2
|
+
import { Worker } from "@temporalio/worker";
|
|
3
|
+
import { createArtifactStore } from "../artifacts.js";
|
|
4
|
+
import { loadConfig } from "../config.js";
|
|
5
|
+
import { connectTemporalWorker } from "../temporal/connection.js";
|
|
6
|
+
import { createEvaluationActivities } from "./activities.js";
|
|
7
|
+
import { openWorkerRecords } from "./worker-records.js";
|
|
8
|
+
const config = loadConfig();
|
|
9
|
+
const connection = await connectTemporalWorker(config.temporal);
|
|
10
|
+
const credentials = await openWorkerRecords();
|
|
11
|
+
const worker = await Worker.create({
|
|
12
|
+
connection,
|
|
13
|
+
namespace: config.temporal.namespace,
|
|
14
|
+
taskQueue: process.env.SELFBENCH_EVAL_TASK_QUEUE ?? "selfbench-evaluations",
|
|
15
|
+
workflowsPath: fileURLToPath(new URL("./workflow.js", import.meta.url)),
|
|
16
|
+
activities: createEvaluationActivities(createArtifactStore(config.artifact), credentials?.records),
|
|
17
|
+
maxConcurrentActivityTaskExecutions: 1,
|
|
18
|
+
});
|
|
19
|
+
console.log("Evaluation worker ready; waiting for explicit Run submissions");
|
|
20
|
+
try {
|
|
21
|
+
await worker.run();
|
|
22
|
+
}
|
|
23
|
+
finally {
|
|
24
|
+
await credentials?.close();
|
|
25
|
+
}
|
|
26
|
+
//# sourceMappingURL=worker-main.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"worker-main.js","sourceRoot":"","sources":["../../src/evaluation/worker-main.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,aAAa,EAAE,MAAM,UAAU,CAAC;AACzC,OAAO,EAAE,MAAM,EAAE,MAAM,oBAAoB,CAAC;AAC5C,OAAO,EAAE,mBAAmB,EAAE,MAAM,iBAAiB,CAAC;AACtD,OAAO,EAAE,UAAU,EAAE,MAAM,cAAc,CAAC;AAC1C,OAAO,EAAE,qBAAqB,EAAE,MAAM,2BAA2B,CAAC;AAClE,OAAO,EAAE,0BAA0B,EAAE,MAAM,iBAAiB,CAAC;AAC7D,OAAO,EAAE,iBAAiB,EAAE,MAAM,qBAAqB,CAAC;AAExD,MAAM,MAAM,GAAG,UAAU,EAAE,CAAC;AAC5B,MAAM,UAAU,GAAG,MAAM,qBAAqB,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC;AAChE,MAAM,WAAW,GAAG,MAAM,iBAAiB,EAAE,CAAC;AAC9C,MAAM,MAAM,GAAG,MAAM,MAAM,CAAC,MAAM,CAAC;IACjC,UAAU;IACV,SAAS,EAAE,MAAM,CAAC,QAAQ,CAAC,SAAS;IACpC,SAAS,EAAE,OAAO,CAAC,GAAG,CAAC,yBAAyB,IAAI,uBAAuB;IAC3E,aAAa,EAAE,aAAa,CAAC,IAAI,GAAG,CAAC,eAAe,EAAE,MAAM,CAAC,IAAI,CAAC,GAAG,CAAC,CAAC;IACvE,UAAU,EAAE,0BAA0B,CACpC,mBAAmB,CAAC,MAAM,CAAC,QAAQ,CAAC,EACpC,WAAW,EAAE,OAAO,CACrB;IACD,mCAAmC,EAAE,CAAC;CACvC,CAAC,CAAC;AACH,OAAO,CAAC,GAAG,CAAC,+DAA+D,CAAC,CAAC;AAC7E,IAAI,CAAC;IACH,MAAM,MAAM,CAAC,GAAG,EAAE,CAAC;AACrB,CAAC;QAAS,CAAC;IACT,MAAM,WAAW,EAAE,KAAK,EAAE,CAAC;AAC7B,CAAC"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"worker-records.d.ts","sourceRoot":"","sources":["../../src/evaluation/worker-records.ts"],"names":[],"mappings":"AAGA,wBAAsB,iBAAiB,CAAC,GAAG,GAAE,MAAM,CAAC,UAAwB;;;eAM3E"}
|
|
@@ -0,0 +1,11 @@
|
|
|
1
|
+
import { openDatabase } from "../db/client.js";
|
|
2
|
+
import { createEncryptedRecords } from "./encrypted-records.js";
|
|
3
|
+
export async function openWorkerRecords(env = process.env) {
|
|
4
|
+
const key = env.SELFBENCH_EVAL_CREDENTIAL_KEY;
|
|
5
|
+
const url = env.SELFBENCH_DATABASE_URL;
|
|
6
|
+
if (!key || !url)
|
|
7
|
+
return undefined;
|
|
8
|
+
const connection = await openDatabase(url);
|
|
9
|
+
return { records: createEncryptedRecords(connection.db, key), close: () => connection.close() };
|
|
10
|
+
}
|
|
11
|
+
//# sourceMappingURL=worker-records.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"worker-records.js","sourceRoot":"","sources":["../../src/evaluation/worker-records.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,YAAY,EAAE,MAAM,iBAAiB,CAAC;AAC/C,OAAO,EAAE,sBAAsB,EAAE,MAAM,wBAAwB,CAAC;AAEhE,MAAM,CAAC,KAAK,UAAU,iBAAiB,CAAC,MAAyB,OAAO,CAAC,GAAG;IAC1E,MAAM,GAAG,GAAG,GAAG,CAAC,6BAA6B,CAAC;IAC9C,MAAM,GAAG,GAAG,GAAG,CAAC,sBAAsB,CAAC;IACvC,IAAI,CAAC,GAAG,IAAI,CAAC,GAAG;QAAE,OAAO,SAAS,CAAC;IACnC,MAAM,UAAU,GAAG,MAAM,YAAY,CAAC,GAAG,CAAC,CAAC;IAC3C,OAAO,EAAE,OAAO,EAAE,sBAAsB,CAAC,UAAU,CAAC,EAAE,EAAE,GAAG,CAAC,EAAE,KAAK,EAAE,GAAG,EAAE,CAAC,UAAU,CAAC,KAAK,EAAE,EAAE,CAAC;AAClG,CAAC"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"workflow.d.ts","sourceRoot":"","sources":["../../src/evaluation/workflow.ts"],"names":[],"mappings":"AAEA,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,YAAY,CAAC;AAYlD,wBAAsB,2BAA2B,CAAC,KAAK,EAAE,eAAe,GAAG,OAAO,CAAC,IAAI,CAAC,CAMvF"}
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
import { ActivityCancellationType, CancellationScope, proxyActivities } from "@temporalio/workflow";
|
|
2
|
+
const solver = proxyActivities({
|
|
3
|
+
startToCloseTimeout: "72 hours",
|
|
4
|
+
heartbeatTimeout: "2 minutes",
|
|
5
|
+
cancellationType: ActivityCancellationType.WAIT_CANCELLATION_COMPLETED,
|
|
6
|
+
retry: { maximumAttempts: 1 },
|
|
7
|
+
});
|
|
8
|
+
const finalizer = proxyActivities({
|
|
9
|
+
startToCloseTimeout: "1 minute",
|
|
10
|
+
retry: { maximumAttempts: 5 },
|
|
11
|
+
});
|
|
12
|
+
export async function selfBenchEvaluationWorkflow(input) {
|
|
13
|
+
try {
|
|
14
|
+
await solver.executeSolverEvaluation(input);
|
|
15
|
+
}
|
|
16
|
+
catch {
|
|
17
|
+
await CancellationScope.nonCancellable(() => finalizer.failSolverEvaluation(input));
|
|
18
|
+
}
|
|
19
|
+
}
|
|
20
|
+
//# sourceMappingURL=workflow.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"workflow.js","sourceRoot":"","sources":["../../src/evaluation/workflow.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,wBAAwB,EAAE,iBAAiB,EAAE,eAAe,EAAE,MAAM,sBAAsB,CAAC;AAIpG,MAAM,MAAM,GAAG,eAAe,CAAuB;IACnD,mBAAmB,EAAE,UAAU;IAC/B,gBAAgB,EAAE,WAAW;IAC7B,gBAAgB,EAAE,wBAAwB,CAAC,2BAA2B;IACtE,KAAK,EAAE,EAAE,eAAe,EAAE,CAAC,EAAE;CAC9B,CAAC,CAAC;AACH,MAAM,SAAS,GAAG,eAAe,CAAuB;IACtD,mBAAmB,EAAE,UAAU;IAC/B,KAAK,EAAE,EAAE,eAAe,EAAE,CAAC,EAAE;CAC9B,CAAC,CAAC;AACH,MAAM,CAAC,KAAK,UAAU,2BAA2B,CAAC,KAAsB;IACtE,IAAI,CAAC;QACH,MAAM,MAAM,CAAC,uBAAuB,CAAC,KAAK,CAAC,CAAC;IAC9C,CAAC;IAAC,MAAM,CAAC;QACP,MAAM,iBAAiB,CAAC,cAAc,CAAC,GAAG,EAAE,CAAC,SAAS,CAAC,oBAAoB,CAAC,KAAK,CAAC,CAAC,CAAC;IACtF,CAAC;AACH,CAAC"}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"execution-environment.d.ts","sourceRoot":"","sources":["../src/execution-environment.ts"],"names":[],"mappings":"AAGA,wBAAgB,oBAAoB,IAAI,MAAM,CAAC,UAAU,CAExD;AACD,wBAAgB,wBAAwB,CAAC,CAAC,EACxC,WAAW,EAAE,MAAM,CAAC,UAAU,EAC9B,MAAM,EAAE,MAAM,OAAO,CAAC,CAAC,CAAC,cAGzB"}
|
|
@@ -0,0 +1,9 @@
|
|
|
1
|
+
import { AsyncLocalStorage } from "node:async_hooks";
|
|
2
|
+
const environments = new AsyncLocalStorage();
|
|
3
|
+
export function executionEnvironment() {
|
|
4
|
+
return environments.getStore() ?? process.env;
|
|
5
|
+
}
|
|
6
|
+
export function withExecutionEnvironment(environment, action) {
|
|
7
|
+
return environments.run(environment, action);
|
|
8
|
+
}
|
|
9
|
+
//# sourceMappingURL=execution-environment.js.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"execution-environment.js","sourceRoot":"","sources":["../src/execution-environment.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,iBAAiB,EAAE,MAAM,kBAAkB,CAAC;AAErD,MAAM,YAAY,GAAG,IAAI,iBAAiB,EAAqB,CAAC;AAChE,MAAM,UAAU,oBAAoB;IAClC,OAAO,YAAY,CAAC,QAAQ,EAAE,IAAI,OAAO,CAAC,GAAG,CAAC;AAChD,CAAC;AACD,MAAM,UAAU,wBAAwB,CACtC,WAA8B,EAC9B,MAAwB;IAExB,OAAO,YAAY,CAAC,GAAG,CAAC,WAAW,EAAE,MAAM,CAAC,CAAC;AAC/C,CAAC"}
|
|
@@ -0,0 +1,347 @@
|
|
|
1
|
+
// src/extensions/authoring.ts
|
|
2
|
+
import { cpSync, mkdirSync as mkdirSync2 } from "node:fs";
|
|
3
|
+
import { join as join4 } from "node:path";
|
|
4
|
+
import { Type as Type2 } from "@sinclair/typebox";
|
|
5
|
+
|
|
6
|
+
// src/extensions/shared/deliverable.ts
|
|
7
|
+
import { existsSync, readFileSync } from "node:fs";
|
|
8
|
+
import { join as join2 } from "node:path";
|
|
9
|
+
|
|
10
|
+
// src/extensions/shared/schemas.ts
|
|
11
|
+
import { Type } from "@sinclair/typebox";
|
|
12
|
+
var environmentVariableName = Type.String({ pattern: "^[A-Za-z_][A-Za-z0-9_]*$" });
|
|
13
|
+
var environmentVariables = Type.Record(environmentVariableName, Type.String());
|
|
14
|
+
var service = Type.Object({
|
|
15
|
+
name: Type.String({ pattern: "^[a-z][a-z0-9_-]*$" }),
|
|
16
|
+
image: Type.String({ minLength: 1 }),
|
|
17
|
+
environmentVariables,
|
|
18
|
+
command: Type.Optional(Type.Array(Type.String())),
|
|
19
|
+
healthcheck: Type.Object({
|
|
20
|
+
test: Type.Array(Type.String({ minLength: 1 }), { minItems: 1 }),
|
|
21
|
+
intervalSeconds: Type.Integer({ minimum: 1 }),
|
|
22
|
+
timeoutSeconds: Type.Integer({ minimum: 1 }),
|
|
23
|
+
retries: Type.Integer({ minimum: 1 }),
|
|
24
|
+
startPeriodSeconds: Type.Integer({ minimum: 0 })
|
|
25
|
+
}, { additionalProperties: false })
|
|
26
|
+
}, { additionalProperties: false });
|
|
27
|
+
var environmentContract = Type.Object({
|
|
28
|
+
schemaVersion: Type.Literal(1),
|
|
29
|
+
baseImage: Type.String({ minLength: 1 }),
|
|
30
|
+
rootSetupCommand: Type.String({ minLength: 1 }),
|
|
31
|
+
setupCommand: Type.String({ minLength: 1 }),
|
|
32
|
+
smokeCommand: Type.String({ minLength: 1 }),
|
|
33
|
+
environmentVariables,
|
|
34
|
+
services: Type.Array(service),
|
|
35
|
+
source: Type.Union([
|
|
36
|
+
Type.Literal("repository-dockerfile"),
|
|
37
|
+
Type.Literal("devcontainer"),
|
|
38
|
+
Type.Literal("ci-adapted"),
|
|
39
|
+
Type.Literal("generated")
|
|
40
|
+
]),
|
|
41
|
+
evidence: Type.Array(Type.Object({ path: Type.String({ minLength: 1 }), reason: Type.String({ minLength: 1 }) }, { additionalProperties: false }), { minItems: 1 })
|
|
42
|
+
}, { additionalProperties: false });
|
|
43
|
+
var taskTimeouts = Type.Object({
|
|
44
|
+
setupSeconds: Type.Integer({ minimum: 1 }),
|
|
45
|
+
agentSeconds: Type.Integer({ minimum: 1 }),
|
|
46
|
+
testsSeconds: Type.Integer({ minimum: 1 })
|
|
47
|
+
}, { additionalProperties: false });
|
|
48
|
+
var taskResources = Type.Object({
|
|
49
|
+
cpus: Type.Number({ exclusiveMinimum: 0 }),
|
|
50
|
+
memoryMb: Type.Integer({ minimum: 1 }),
|
|
51
|
+
storageMb: Type.Integer({ minimum: 1 })
|
|
52
|
+
}, { additionalProperties: false });
|
|
53
|
+
var taskDefinition = Type.Object({
|
|
54
|
+
schemaVersion: Type.Literal(2),
|
|
55
|
+
difficulty: Type.Union([Type.Literal("easy"), Type.Literal("medium"), Type.Literal("hard")]),
|
|
56
|
+
taskId: Type.String({ pattern: "^[A-Za-z0-9][A-Za-z0-9._-]*$" }),
|
|
57
|
+
repo: Type.String({ minLength: 1 }),
|
|
58
|
+
baseCommit: Type.String({ pattern: "^[0-9a-fA-F]{40}$" }),
|
|
59
|
+
workdir: Type.String({ minLength: 1 }),
|
|
60
|
+
testCommand: Type.String({ minLength: 1 }),
|
|
61
|
+
failToPass: Type.Array(Type.String({ minLength: 1 }), { minItems: 1 }),
|
|
62
|
+
passToPass: Type.Array(Type.String({ minLength: 1 })),
|
|
63
|
+
testPaths: Type.Array(Type.String({ minLength: 1 }), { minItems: 1 }),
|
|
64
|
+
sourcePr: Type.Integer({ minimum: 1 }),
|
|
65
|
+
sourceUrl: Type.String({ minLength: 1 }),
|
|
66
|
+
prompt: Type.String({ minLength: 1 }),
|
|
67
|
+
timeouts: taskTimeouts,
|
|
68
|
+
resources: taskResources,
|
|
69
|
+
environment: environmentContract
|
|
70
|
+
}, { additionalProperties: false });
|
|
71
|
+
|
|
72
|
+
// src/extensions/shared/static-check.ts
|
|
73
|
+
import { spawnSync } from "node:child_process";
|
|
74
|
+
import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
|
|
75
|
+
import { tmpdir } from "node:os";
|
|
76
|
+
import { join } from "node:path";
|
|
77
|
+
function requiredEnvironment(name) {
|
|
78
|
+
const value = process.env[name];
|
|
79
|
+
if (!value) {
|
|
80
|
+
throw new Error(`${name} is not configured`);
|
|
81
|
+
}
|
|
82
|
+
return value;
|
|
83
|
+
}
|
|
84
|
+
function stageSubmission(definition, testPatch, goldPatch, prefix = "selfbench-submit-") {
|
|
85
|
+
const directory = mkdtempSync(join(tmpdir(), prefix));
|
|
86
|
+
const definitionJson = `${JSON.stringify(definition, null, 2)}
|
|
87
|
+
`;
|
|
88
|
+
writeFileSync(join(directory, "definition.json"), definitionJson);
|
|
89
|
+
writeFileSync(join(directory, "test.patch"), testPatch);
|
|
90
|
+
writeFileSync(join(directory, "gold.patch"), goldPatch);
|
|
91
|
+
return {
|
|
92
|
+
directory,
|
|
93
|
+
definitionJson,
|
|
94
|
+
dispose: () => rmSync(directory, { recursive: true, force: true })
|
|
95
|
+
};
|
|
96
|
+
}
|
|
97
|
+
function runStaticCheck(staging, extra = [], applyAgainst) {
|
|
98
|
+
const program = requiredEnvironment("SELFBENCH_CHECK_PROGRAM");
|
|
99
|
+
const repository = applyAgainst?.repository ?? process.env.SELFBENCH_REPO_DIRECTORY ?? "/work/repo";
|
|
100
|
+
const result = spawnSync(process.execPath, [
|
|
101
|
+
program,
|
|
102
|
+
join(staging, "definition.json"),
|
|
103
|
+
join(staging, "test.patch"),
|
|
104
|
+
join(staging, "gold.patch"),
|
|
105
|
+
process.env.SELFBENCH_RENDER_OUTPUT ?? "/work",
|
|
106
|
+
...extra,
|
|
107
|
+
...applyAgainst ? ["--repository", repository, "--base", applyAgainst.base] : []
|
|
108
|
+
], { encoding: "utf8", maxBuffer: 64 * 1024 * 1024 });
|
|
109
|
+
if (result.status !== 0) {
|
|
110
|
+
throw new Error(`static check program failed: ${(result.stderr || result.stdout).slice(-4000)}`);
|
|
111
|
+
}
|
|
112
|
+
return JSON.parse(result.stdout);
|
|
113
|
+
}
|
|
114
|
+
function staticCheckFailure(verdict, subject) {
|
|
115
|
+
const lines = verdict.errors.map((error) => `- [${error.gate}] ${error.message}`).join(`
|
|
116
|
+
`);
|
|
117
|
+
const rendered = verdict.renderedDirectory ? `
|
|
118
|
+
The dry-rendered Harbor tree (as far as rendering succeeded) is under ${verdict.renderedDirectory}.` : "";
|
|
119
|
+
return failure(`The ${subject} failed the static check; nothing was recorded. Fix every item and try again:
|
|
120
|
+
${lines}${rendered}`);
|
|
121
|
+
}
|
|
122
|
+
function failure(text) {
|
|
123
|
+
return { content: [{ type: "text", text }], details: {}, isError: true };
|
|
124
|
+
}
|
|
125
|
+
|
|
126
|
+
// src/extensions/shared/deliverable.ts
|
|
127
|
+
var TASK_DELIVERABLE_FILES = [
|
|
128
|
+
"definition.json",
|
|
129
|
+
"instruction.md",
|
|
130
|
+
"test.patch",
|
|
131
|
+
"gold.patch"
|
|
132
|
+
];
|
|
133
|
+
function loadTaskDeliverable(root) {
|
|
134
|
+
const missing = TASK_DELIVERABLE_FILES.filter((name) => !existsSync(join2(root, name)));
|
|
135
|
+
if (missing.length > 0) {
|
|
136
|
+
return deliverableFailure(root, missing.map((name) => `${name} is missing`));
|
|
137
|
+
}
|
|
138
|
+
let definition;
|
|
139
|
+
try {
|
|
140
|
+
const parsed = JSON.parse(readFileSync(join2(root, "definition.json"), "utf8"));
|
|
141
|
+
if (typeof parsed !== "object" || parsed === null || Array.isArray(parsed)) {
|
|
142
|
+
throw new Error("must be a JSON object");
|
|
143
|
+
}
|
|
144
|
+
definition = parsed;
|
|
145
|
+
} catch (error) {
|
|
146
|
+
return deliverableFailure(root, [
|
|
147
|
+
`definition.json is not valid JSON: ${error instanceof Error ? error.message : String(error)}`
|
|
148
|
+
]);
|
|
149
|
+
}
|
|
150
|
+
const instruction = readFileSync(join2(root, "instruction.md"), "utf8").trim();
|
|
151
|
+
const testPatch = readFileSync(join2(root, "test.patch"), "utf8");
|
|
152
|
+
const goldPatch = readFileSync(join2(root, "gold.patch"), "utf8");
|
|
153
|
+
const problems = [];
|
|
154
|
+
if (!instruction) {
|
|
155
|
+
problems.push("instruction.md is empty");
|
|
156
|
+
}
|
|
157
|
+
if (typeof definition.prompt === "string" && definition.prompt.trim() !== instruction) {
|
|
158
|
+
problems.push("definition.json prompt differs from instruction.md; remove prompt or make them identical");
|
|
159
|
+
}
|
|
160
|
+
if (!testPatch.trim()) {
|
|
161
|
+
problems.push("test.patch is empty");
|
|
162
|
+
}
|
|
163
|
+
if (!goldPatch.trim()) {
|
|
164
|
+
problems.push("gold.patch is empty");
|
|
165
|
+
}
|
|
166
|
+
if (problems.length > 0) {
|
|
167
|
+
return deliverableFailure(root, problems);
|
|
168
|
+
}
|
|
169
|
+
return { definition: { ...definition, prompt: instruction }, testPatch, goldPatch };
|
|
170
|
+
}
|
|
171
|
+
function deliverableFailure(root, problems) {
|
|
172
|
+
return failure(`The deliverable in ${root} is incomplete; nothing was recorded. Fix every item and call the tool again:
|
|
173
|
+
${problems.map((problem) => `- [files] ${problem}`).join(`
|
|
174
|
+
`)}`);
|
|
175
|
+
}
|
|
176
|
+
|
|
177
|
+
// src/extensions/shared/mailbox.ts
|
|
178
|
+
import { createHash } from "node:crypto";
|
|
179
|
+
import { existsSync as existsSync2, mkdirSync, readFileSync as readFileSync2, renameSync, writeFileSync as writeFileSync2 } from "node:fs";
|
|
180
|
+
import { join as join3 } from "node:path";
|
|
181
|
+
var DEFAULT_MAILBOX = "/work/mailbox";
|
|
182
|
+
var DEFAULT_POLL_MS = 2000;
|
|
183
|
+
var DEFAULT_TIMEOUT_MS = 60 * 60 * 1000;
|
|
184
|
+
function payloadHash(payload) {
|
|
185
|
+
return createHash("sha256").update(`${JSON.stringify(payload.definition)}\x00${payload.testPatch}\x00${payload.goldPatch}`).digest("hex");
|
|
186
|
+
}
|
|
187
|
+
|
|
188
|
+
class VerifyClient {
|
|
189
|
+
#mailbox = process.env.SELFBENCH_MAILBOX ?? DEFAULT_MAILBOX;
|
|
190
|
+
#budget = Number(process.env.SELFBENCH_VERIFY_BUDGET ?? "0");
|
|
191
|
+
#pollMs = Number(process.env.SELFBENCH_VERIFY_POLL_MS ?? String(DEFAULT_POLL_MS));
|
|
192
|
+
#timeoutMs = Number(process.env.SELFBENCH_VERIFY_TIMEOUT_MS ?? String(DEFAULT_TIMEOUT_MS));
|
|
193
|
+
#used = 0;
|
|
194
|
+
#sequence = 0;
|
|
195
|
+
#lastGreenHash;
|
|
196
|
+
get remaining() {
|
|
197
|
+
return Math.max(0, this.#budget - this.#used);
|
|
198
|
+
}
|
|
199
|
+
verifiedGreen(payload) {
|
|
200
|
+
return this.#lastGreenHash !== undefined && this.#lastGreenHash === payloadHash(payload);
|
|
201
|
+
}
|
|
202
|
+
async verify(kind, payload) {
|
|
203
|
+
if (this.remaining === 0) {
|
|
204
|
+
return { kind: "exhausted" };
|
|
205
|
+
}
|
|
206
|
+
const requests = join3(this.#mailbox, "requests");
|
|
207
|
+
const responses = join3(this.#mailbox, "responses");
|
|
208
|
+
mkdirSync(requests, { recursive: true });
|
|
209
|
+
mkdirSync(responses, { recursive: true });
|
|
210
|
+
this.#sequence += 1;
|
|
211
|
+
const id = `${Date.now()}-${this.#sequence}`;
|
|
212
|
+
const request = join3(requests, `${id}.json`);
|
|
213
|
+
writeFileSync2(`${request}.tmp`, `${JSON.stringify({ id, kind, ...payload })}
|
|
214
|
+
`);
|
|
215
|
+
renameSync(`${request}.tmp`, request);
|
|
216
|
+
const response = join3(responses, `${id}.json`);
|
|
217
|
+
const deadline = Date.now() + this.#timeoutMs;
|
|
218
|
+
while (Date.now() < deadline) {
|
|
219
|
+
if (existsSync2(response)) {
|
|
220
|
+
let parsed;
|
|
221
|
+
try {
|
|
222
|
+
parsed = JSON.parse(readFileSync2(response, "utf8"));
|
|
223
|
+
} catch {
|
|
224
|
+
parsed = undefined;
|
|
225
|
+
}
|
|
226
|
+
if (parsed && typeof parsed === "object") {
|
|
227
|
+
return this.#record(parsed, payload);
|
|
228
|
+
}
|
|
229
|
+
}
|
|
230
|
+
await new Promise((resolve) => setTimeout(resolve, this.#pollMs));
|
|
231
|
+
}
|
|
232
|
+
this.#used += 1;
|
|
233
|
+
return {
|
|
234
|
+
kind: "error",
|
|
235
|
+
message: `verify timed out after ${Math.round(this.#timeoutMs / 60000)} minutes; the worker may still be building. ${this.remaining} verify call(s) remain.`
|
|
236
|
+
};
|
|
237
|
+
}
|
|
238
|
+
#record(response, payload) {
|
|
239
|
+
if (response.kind !== "report") {
|
|
240
|
+
return {
|
|
241
|
+
kind: "error",
|
|
242
|
+
message: typeof response.message === "string" ? response.message : "verify failed on the worker"
|
|
243
|
+
};
|
|
244
|
+
}
|
|
245
|
+
this.#used += 1;
|
|
246
|
+
const green = response.green === true;
|
|
247
|
+
if (green) {
|
|
248
|
+
this.#lastGreenHash = payloadHash(payload);
|
|
249
|
+
}
|
|
250
|
+
return {
|
|
251
|
+
kind: "report",
|
|
252
|
+
green,
|
|
253
|
+
summary: typeof response.summary === "string" ? response.summary : "",
|
|
254
|
+
rendered: typeof response.rendered === "string" ? response.rendered : "",
|
|
255
|
+
remaining: this.remaining
|
|
256
|
+
};
|
|
257
|
+
}
|
|
258
|
+
}
|
|
259
|
+
function verifyOutcomeText(outcome, submitTool) {
|
|
260
|
+
if (outcome.kind === "exhausted") {
|
|
261
|
+
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.`;
|
|
262
|
+
}
|
|
263
|
+
if (outcome.kind === "error") {
|
|
264
|
+
return `verify could not complete: ${outcome.message}`;
|
|
265
|
+
}
|
|
266
|
+
const next = outcome.green ? `Call ${submitTool} with exactly this payload to record it; the worker will reuse this report.` : `Fix the red gates and call verify again, or ${submitTool} if you must (the worker verifies again and a round is spent if it fails).`;
|
|
267
|
+
return `${outcome.rendered.trim()}
|
|
268
|
+
|
|
269
|
+
verify result: green=${outcome.green}. ${outcome.remaining} verify call(s) remain in this session. ${next}`;
|
|
270
|
+
}
|
|
271
|
+
|
|
272
|
+
// src/extensions/authoring.ts
|
|
273
|
+
var noArguments = Type2.Object({}, { additionalProperties: false });
|
|
274
|
+
function applyTarget(definition) {
|
|
275
|
+
return { base: typeof definition.baseCommit === "string" ? definition.baseCommit : "HEAD" };
|
|
276
|
+
}
|
|
277
|
+
function authoringExtension(pi) {
|
|
278
|
+
const client = new VerifyClient;
|
|
279
|
+
const deliverable = () => process.env.SELFBENCH_DELIVERABLE ?? "/work/task";
|
|
280
|
+
pi.registerTool({
|
|
281
|
+
name: "verify",
|
|
282
|
+
label: "Verify SelfBench task",
|
|
283
|
+
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.",
|
|
284
|
+
parameters: noArguments,
|
|
285
|
+
async execute() {
|
|
286
|
+
const loaded = loadTaskDeliverable(deliverable());
|
|
287
|
+
if ("isError" in loaded) {
|
|
288
|
+
return loaded;
|
|
289
|
+
}
|
|
290
|
+
const staging = stageSubmission(loaded.definition, loaded.testPatch, loaded.goldPatch, "selfbench-verify-");
|
|
291
|
+
try {
|
|
292
|
+
const verdict = runStaticCheck(staging.directory, [], applyTarget(loaded.definition));
|
|
293
|
+
if (!verdict.ok) {
|
|
294
|
+
return staticCheckFailure(verdict, "task");
|
|
295
|
+
}
|
|
296
|
+
} finally {
|
|
297
|
+
staging.dispose();
|
|
298
|
+
}
|
|
299
|
+
const outcome = await client.verify("task", loaded);
|
|
300
|
+
return {
|
|
301
|
+
content: [{ type: "text", text: verifyOutcomeText(outcome, "submit_task") }],
|
|
302
|
+
details: { kind: outcome.kind, remaining: client.remaining },
|
|
303
|
+
...outcome.kind === "exhausted" ? { isError: true } : {}
|
|
304
|
+
};
|
|
305
|
+
}
|
|
306
|
+
});
|
|
307
|
+
pi.registerTool({
|
|
308
|
+
name: "submit_task",
|
|
309
|
+
label: "Submit SelfBench task",
|
|
310
|
+
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.",
|
|
311
|
+
parameters: noArguments,
|
|
312
|
+
async execute() {
|
|
313
|
+
const root = requiredEnvironment("SELFBENCH_TASK_OUTPUT");
|
|
314
|
+
const loaded = loadTaskDeliverable(deliverable());
|
|
315
|
+
if ("isError" in loaded) {
|
|
316
|
+
return loaded;
|
|
317
|
+
}
|
|
318
|
+
const taskId = String(loaded.definition.taskId ?? "");
|
|
319
|
+
const staging = stageSubmission(loaded.definition, loaded.testPatch, loaded.goldPatch);
|
|
320
|
+
try {
|
|
321
|
+
const verdict = runStaticCheck(staging.directory, [], applyTarget(loaded.definition));
|
|
322
|
+
if (!verdict.ok) {
|
|
323
|
+
return staticCheckFailure(verdict, "submission");
|
|
324
|
+
}
|
|
325
|
+
const directory = join4(root, taskId);
|
|
326
|
+
mkdirSync2(root, { recursive: true });
|
|
327
|
+
mkdirSync2(directory, { recursive: false });
|
|
328
|
+
cpSync(staging.directory, directory, { recursive: true });
|
|
329
|
+
const verified = client.verifiedGreen(loaded);
|
|
330
|
+
return {
|
|
331
|
+
content: [
|
|
332
|
+
{
|
|
333
|
+
type: "text",
|
|
334
|
+
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.`
|
|
335
|
+
}
|
|
336
|
+
],
|
|
337
|
+
details: { taskId, verified }
|
|
338
|
+
};
|
|
339
|
+
} finally {
|
|
340
|
+
staging.dispose();
|
|
341
|
+
}
|
|
342
|
+
}
|
|
343
|
+
});
|
|
344
|
+
}
|
|
345
|
+
export {
|
|
346
|
+
authoringExtension as default
|
|
347
|
+
};
|