niceeval 0.13.2 → 0.13.3
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/dist/agents/bub.cjs +4 -4
- package/dist/agents/bub.cjs.map +1 -1
- package/dist/agents/bub.d.cts +2 -2
- package/dist/agents/bub.d.mts +2 -2
- package/dist/agents/bub.d.ts +2 -2
- package/dist/agents/claude-code-native.cjs +213 -0
- package/dist/agents/claude-code-native.cjs.map +1 -0
- package/dist/agents/claude-code-native.d.cts +5 -0
- package/dist/agents/claude-code-native.d.mts +5 -0
- package/dist/agents/claude-code-native.d.ts +5 -0
- package/dist/agents/claude-code-native.js +6 -0
- package/dist/agents/claude-code-native.js.map +1 -0
- package/dist/agents/claude-code.cjs +26 -80
- package/dist/agents/claude-code.cjs.map +1 -1
- package/dist/agents/codex-app-server.cjs +314 -0
- package/dist/agents/codex-app-server.cjs.map +1 -0
- package/dist/agents/codex-app-server.d.cts +9 -0
- package/dist/agents/codex-app-server.d.mts +9 -0
- package/dist/agents/codex-app-server.d.ts +9 -0
- package/dist/agents/codex-app-server.js +6 -0
- package/dist/agents/codex-app-server.js.map +1 -0
- package/dist/agents/codex.cjs +19 -68
- package/dist/agents/codex.cjs.map +1 -1
- package/dist/agents/codex.d.cts +3 -3
- package/dist/agents/codex.d.mts +3 -3
- package/dist/agents/codex.d.ts +3 -3
- package/dist/agents/index.cjs +3 -1
- package/dist/agents/index.cjs.map +1 -1
- package/dist/agents/index.d.cts +1 -0
- package/dist/agents/index.d.mts +1 -0
- package/dist/agents/index.d.ts +1 -0
- package/dist/agents/index.js +84 -82
- package/dist/agents/index.mjs +84 -82
- package/dist/agents/managed-jsonl.cjs +207 -0
- package/dist/agents/managed-jsonl.cjs.map +1 -0
- package/dist/agents/managed-jsonl.d.cts +39 -0
- package/dist/agents/managed-jsonl.d.mts +39 -0
- package/dist/agents/managed-jsonl.d.ts +39 -0
- package/dist/agents/managed-jsonl.js +6 -0
- package/dist/agents/managed-jsonl.js.map +1 -0
- package/dist/agents/managed-process.cjs +31 -0
- package/dist/agents/managed-process.cjs.map +1 -0
- package/dist/agents/managed-process.d.cts +3 -0
- package/dist/agents/managed-process.d.mts +3 -0
- package/dist/agents/managed-process.d.ts +3 -0
- package/dist/agents/managed-process.js +6 -0
- package/dist/agents/managed-process.js.map +1 -0
- package/dist/agents/omp.cjs +18 -1
- package/dist/agents/omp.cjs.map +1 -1
- package/dist/agents/sdk-streams.cjs +11 -4
- package/dist/agents/sdk-streams.cjs.map +1 -1
- package/dist/agents/types.cjs.map +1 -1
- package/dist/agents/types.d.cts +8 -0
- package/dist/agents/types.d.mts +8 -0
- package/dist/agents/types.d.ts +8 -0
- package/dist/analysis/bindings.cjs +74 -19
- package/dist/analysis/bindings.cjs.map +1 -1
- package/dist/analysis/bindings.d.cts +534 -156
- package/dist/analysis/bindings.d.mts +534 -156
- package/dist/analysis/bindings.d.ts +534 -156
- package/dist/analysis/domain-view.cjs.map +1 -1
- package/dist/analysis/domain-view.d.cts +137 -8
- package/dist/analysis/domain-view.d.mts +137 -8
- package/dist/analysis/domain-view.d.ts +137 -8
- package/dist/analysis/index.cjs.map +1 -1
- package/dist/analysis/index.d.cts +1 -1
- package/dist/analysis/index.d.mts +1 -1
- package/dist/analysis/index.d.ts +1 -1
- package/dist/assertions/api.cjs.map +1 -1
- package/dist/assertions/api.d.cts +62 -0
- package/dist/assertions/api.d.mts +62 -0
- package/dist/assertions/api.d.ts +62 -0
- package/dist/assertions/judge.cjs +56 -5
- package/dist/assertions/judge.cjs.map +1 -1
- package/dist/assertions/match.cjs +66 -42
- package/dist/assertions/match.cjs.map +1 -1
- package/dist/assertions/match.d.cts +13 -0
- package/dist/assertions/match.d.mts +13 -0
- package/dist/assertions/match.d.ts +13 -0
- package/dist/assertions/record/attachment.cjs +104 -33
- package/dist/assertions/record/attachment.cjs.map +1 -1
- package/dist/assertions/record/attachment.d.cts +294 -57
- package/dist/assertions/record/attachment.d.mts +294 -57
- package/dist/assertions/record/attachment.d.ts +294 -57
- package/dist/assertions/record/codec.cjs +91 -17
- package/dist/assertions/record/codec.cjs.map +1 -1
- package/dist/assertions/record/codec.d.cts +280 -52
- package/dist/assertions/record/codec.d.mts +280 -52
- package/dist/assertions/record/codec.d.ts +280 -52
- package/dist/assertions/record/index.js +2 -0
- package/dist/assertions/record/model.cjs +16 -0
- package/dist/assertions/record/model.cjs.map +1 -1
- package/dist/assertions/record/model.d.cts +120 -13
- package/dist/assertions/record/model.d.mts +120 -13
- package/dist/assertions/record/model.d.ts +120 -13
- package/dist/assertions/record/model.js +2 -0
- package/dist/assertions/record/producer.cjs +70 -50
- package/dist/assertions/record/producer.cjs.map +1 -1
- package/dist/assertions/record/producer.d.cts +8 -7
- package/dist/assertions/record/producer.d.mts +8 -7
- package/dist/assertions/record/producer.d.ts +8 -7
- package/dist/assertions/runtime.cjs +49 -7
- package/dist/assertions/runtime.cjs.map +1 -1
- package/dist/cli/application.cjs +40 -0
- package/dist/cli/application.cjs.map +1 -0
- package/dist/cli/application.d.cts +129 -0
- package/dist/cli/application.d.mts +129 -0
- package/dist/cli/application.d.ts +129 -0
- package/dist/cli/application.js +24 -0
- package/dist/cli/application.js.map +1 -0
- package/dist/cli/bootstrap.cjs +10 -4
- package/dist/cli/bootstrap.cjs.map +1 -1
- package/dist/cli/node-application.cjs +123 -0
- package/dist/cli/node-application.cjs.map +1 -0
- package/dist/cli/node-application.d.cts +14 -0
- package/dist/cli/node-application.d.mts +14 -0
- package/dist/cli/node-application.d.ts +14 -0
- package/dist/cli/node-application.js +26 -0
- package/dist/cli/node-application.js.map +1 -0
- package/dist/cli/program.cjs +2807 -0
- package/dist/cli/program.cjs.map +1 -0
- package/dist/cli/program.d.cts +352 -0
- package/dist/cli/program.d.mts +352 -0
- package/dist/cli/program.d.ts +352 -0
- package/dist/cli/program.js +36 -0
- package/dist/cli/program.js.map +1 -0
- package/dist/cli/project-configuration.cjs +134 -0
- package/dist/cli/project-configuration.cjs.map +1 -0
- package/dist/cli/project-configuration.d.cts +64 -0
- package/dist/cli/project-configuration.d.mts +64 -0
- package/dist/cli/project-configuration.d.ts +64 -0
- package/dist/cli/project-configuration.js +22 -0
- package/dist/cli/project-configuration.js.map +1 -0
- package/dist/cli/record.cjs +20 -4
- package/dist/cli/record.cjs.map +1 -1
- package/dist/cli/record.d.cts +3 -3
- package/dist/cli/record.d.mts +3 -3
- package/dist/cli/record.d.ts +3 -3
- package/dist/cli.cjs +19 -3130
- package/dist/cli.cjs.map +1 -1
- package/dist/cli.d.cts +2 -148
- package/dist/cli.d.mts +2 -148
- package/dist/cli.d.ts +2 -148
- package/dist/cli.js +22 -30
- package/dist/context/assert-first.cjs +21 -15
- package/dist/context/assert-first.cjs.map +1 -1
- package/dist/context/assert-first.d.cts +1 -0
- package/dist/context/assert-first.d.mts +1 -0
- package/dist/context/assert-first.d.ts +1 -0
- package/dist/context/attempt-resources.cjs +13 -0
- package/dist/context/attempt-resources.cjs.map +1 -0
- package/dist/context/attempt-resources.d.cts +3 -0
- package/dist/context/attempt-resources.d.mts +3 -0
- package/dist/context/attempt-resources.d.ts +3 -0
- package/dist/context/attempt-resources.js +8 -0
- package/dist/context/attempt-resources.js.map +1 -0
- package/dist/context/session.cjs +4 -3
- package/dist/context/session.cjs.map +1 -1
- package/dist/context/session.d.cts +1 -0
- package/dist/context/session.d.mts +1 -0
- package/dist/context/session.d.ts +1 -0
- package/dist/eval/record/verdict.cjs +3 -2
- package/dist/eval/record/verdict.cjs.map +1 -1
- package/dist/experiment/host/index.cjs +1 -6
- package/dist/experiment/host/index.cjs.map +1 -1
- package/dist/experiment/host/index.d.cts +1 -0
- package/dist/experiment/host/index.d.mts +1 -0
- package/dist/experiment/host/index.d.ts +1 -0
- package/dist/load-config.cjs +13 -4
- package/dist/load-config.cjs.map +1 -1
- package/dist/load-config.d.cts +4 -3
- package/dist/load-config.d.mts +4 -3
- package/dist/load-config.d.ts +4 -3
- package/dist/load-config.js +4 -2
- package/dist/o11y/parsers/codex.cjs +29 -7
- package/dist/o11y/parsers/codex.cjs.map +1 -1
- package/dist/record/codec/core.d.cts +0 -2
- package/dist/record/codec/core.d.mts +0 -2
- package/dist/record/codec/core.d.ts +0 -2
- package/dist/record/codec/identifiers.cjs +2 -3
- package/dist/record/codec/identifiers.cjs.map +1 -1
- package/dist/record/codec/identifiers.d.cts +1 -2
- package/dist/record/codec/identifiers.d.mts +1 -2
- package/dist/record/codec/identifiers.d.ts +1 -2
- package/dist/record/codec/identifiers.js +10 -12
- package/dist/record/codec/index.js +42 -44
- package/dist/record/definition/attachment.cjs +1 -0
- package/dist/record/definition/attachment.cjs.map +1 -1
- package/dist/record/definition/attachment.d.cts +14 -0
- package/dist/record/definition/attachment.d.mts +14 -0
- package/dist/record/definition/attachment.d.ts +14 -0
- package/dist/record/family/assertions-v1.cjs +104 -0
- package/dist/record/family/assertions-v1.cjs.map +1 -0
- package/dist/record/family/assertions-v1.d.cts +2 -0
- package/dist/record/family/assertions-v1.d.mts +2 -0
- package/dist/record/family/assertions-v1.d.ts +2 -0
- package/dist/record/family/assertions-v1.js +6 -0
- package/dist/record/family/assertions-v1.js.map +1 -0
- package/dist/record/family/assertions.cjs +16 -5
- package/dist/record/family/assertions.cjs.map +1 -1
- package/dist/record/family/assertions.d.cts +510 -56
- package/dist/record/family/assertions.d.mts +510 -56
- package/dist/record/family/assertions.d.ts +510 -56
- package/dist/record/family/assertions.js +14 -10
- package/dist/record/family/catalog.cjs +17 -1
- package/dist/record/family/catalog.cjs.map +1 -1
- package/dist/record/family/catalog.d.cts +1292 -104
- package/dist/record/family/catalog.d.mts +1292 -104
- package/dist/record/family/catalog.d.ts +1292 -104
- package/dist/record/family/catalog.js +22 -20
- package/dist/record/family/index.js +144 -138
- package/dist/record/family/observability-v1.cjs +5 -0
- package/dist/record/family/observability-v1.cjs.map +1 -1
- package/dist/record/family/observability.cjs +1 -1
- package/dist/record/family/observability.cjs.map +1 -1
- package/dist/record/host/runtime.cjs +323 -173
- package/dist/record/host/runtime.cjs.map +1 -1
- package/dist/record/host/types.cjs.map +1 -1
- package/dist/record/host/types.d.cts +9 -7
- package/dist/record/host/types.d.mts +9 -7
- package/dist/record/host/types.d.ts +9 -7
- package/dist/record/model/core.cjs.map +1 -1
- package/dist/record/model/core.d.cts +1 -2
- package/dist/record/model/core.d.mts +1 -2
- package/dist/record/model/core.d.ts +1 -2
- package/dist/record/model/definition.cjs +1 -2
- package/dist/record/model/definition.cjs.map +1 -1
- package/dist/record/model/definition.d.cts +1 -7
- package/dist/record/model/definition.d.mts +1 -7
- package/dist/record/model/definition.d.ts +1 -7
- package/dist/record/model/identifiers.cjs +2 -3
- package/dist/record/model/identifiers.cjs.map +1 -1
- package/dist/record/model/identifiers.d.cts +1 -3
- package/dist/record/model/identifiers.d.mts +1 -3
- package/dist/record/model/identifiers.d.ts +1 -3
- package/dist/record/model/identifiers.js +36 -38
- package/dist/record/model/index.js +60 -62
- package/dist/record/platform/node.cjs +17 -7
- package/dist/record/platform/node.cjs.map +1 -1
- package/dist/record/platform/services.cjs.map +1 -1
- package/dist/record/platform/services.d.cts +8 -3
- package/dist/record/platform/services.d.mts +8 -3
- package/dist/record/platform/services.d.ts +8 -3
- package/dist/record/reader/format.cjs +16 -65
- package/dist/record/reader/format.cjs.map +1 -1
- package/dist/record/reader/format.d.cts +5 -9
- package/dist/record/reader/format.d.mts +5 -9
- package/dist/record/reader/format.d.ts +5 -9
- package/dist/record/reader/index.js +10 -8
- package/dist/record/reader/runtime.cjs +63 -32
- package/dist/record/reader/runtime.cjs.map +1 -1
- package/dist/record/reader/runtime.d.cts +40 -4
- package/dist/record/reader/runtime.d.mts +40 -4
- package/dist/record/reader/runtime.d.ts +40 -4
- package/dist/record/reader/runtime.js +6 -4
- package/dist/report/assets/enhance.js +5 -5
- package/dist/report/assets/styles.css +190 -24
- package/dist/report/built-in/result-components.cjs +8 -5
- package/dist/report/built-in/result-components.cjs.map +1 -1
- package/dist/report/built-in/standard.cjs +3 -0
- package/dist/report/built-in/standard.cjs.map +1 -1
- package/dist/report/built-in/standard.d.cts +2 -0
- package/dist/report/built-in/standard.d.mts +2 -0
- package/dist/report/built-in/standard.d.ts +2 -0
- package/dist/report/client-dist/app.js +53 -0
- package/dist/report/components/attempt-detail/compute.cjs +108 -231
- package/dist/report/components/attempt-detail/compute.cjs.map +1 -1
- package/dist/report/components/attempt-detail/compute.d.cts +11 -45
- package/dist/report/components/attempt-detail/compute.d.mts +11 -45
- package/dist/report/components/attempt-detail/compute.d.ts +11 -45
- package/dist/report/components/attempt-detail/compute.js +2 -4
- package/dist/report/components/attempt-detail/content.cjs +4 -4
- package/dist/report/components/attempt-detail/content.cjs.map +1 -1
- package/dist/report/components/attempt-detail/validate.cjs +47 -4
- package/dist/report/components/attempt-detail/validate.cjs.map +1 -1
- package/dist/report/components/entity-lists/compute.cjs +9 -15
- package/dist/report/components/entity-lists/compute.cjs.map +1 -1
- package/dist/report/components/entity-lists/content.cjs +53 -40
- package/dist/report/components/entity-lists/content.cjs.map +1 -1
- package/dist/report/components/entity-lists/index.cjs +1 -3
- package/dist/report/components/entity-lists/index.cjs.map +1 -1
- package/dist/report/components/experiment-detail/compute.cjs +4 -6
- package/dist/report/components/experiment-detail/compute.cjs.map +1 -1
- package/dist/report/components/summaries/index.cjs +5 -1
- package/dist/report/components/summaries/index.cjs.map +1 -1
- package/dist/report/definition/cell.cjs +14 -7
- package/dist/report/definition/cell.cjs.map +1 -1
- package/dist/report/definition/cell.d.cts +4 -0
- package/dist/report/definition/cell.d.mts +4 -0
- package/dist/report/definition/cell.d.ts +4 -0
- package/dist/report/definition/primitives/assertion-evidence.cjs +96 -0
- package/dist/report/definition/primitives/assertion-evidence.cjs.map +1 -0
- package/dist/report/definition/primitives/assertion-evidence.d.cts +11 -0
- package/dist/report/definition/primitives/assertion-evidence.d.mts +11 -0
- package/dist/report/definition/primitives/assertion-evidence.d.ts +11 -0
- package/dist/report/definition/primitives/assertion-evidence.js +6 -0
- package/dist/report/definition/primitives/assertion-evidence.js.map +1 -0
- package/dist/report/definition/primitives/conversation.cjs +7 -0
- package/dist/report/definition/primitives/conversation.cjs.map +1 -1
- package/dist/report/definition/primitives/conversation.d.cts +2 -0
- package/dist/report/definition/primitives/conversation.d.mts +2 -0
- package/dist/report/definition/primitives/conversation.d.ts +2 -0
- package/dist/report/definition/primitives/turn-trace.cjs +53 -3
- package/dist/report/definition/primitives/turn-trace.cjs.map +1 -1
- package/dist/report/definition/primitives.cjs +14 -1
- package/dist/report/definition/primitives.cjs.map +1 -1
- package/dist/report/definition/report.cjs +16 -8
- package/dist/report/definition/report.cjs.map +1 -1
- package/dist/report/definition/report.d.cts +6 -0
- package/dist/report/definition/report.d.mts +6 -0
- package/dist/report/definition/report.d.ts +6 -0
- package/dist/report/definition/table-text.cjs +12 -3
- package/dist/report/definition/table-text.cjs.map +1 -1
- package/dist/report/definition/table-text.d.cts +6 -1
- package/dist/report/definition/table-text.d.mts +6 -1
- package/dist/report/definition/table-text.d.ts +6 -1
- package/dist/report/execution/model.cjs +6 -14
- package/dist/report/execution/model.cjs.map +1 -1
- package/dist/report/execution/model.d.cts +5 -10
- package/dist/report/execution/model.d.mts +5 -10
- package/dist/report/execution/model.d.ts +5 -10
- package/dist/report/execution/model.js +6 -6
- package/dist/report/execution/paths.cjs +0 -11
- package/dist/report/execution/paths.cjs.map +1 -1
- package/dist/report/execution/paths.d.cts +0 -1
- package/dist/report/execution/paths.d.mts +0 -1
- package/dist/report/execution/paths.d.ts +0 -1
- package/dist/report/execution/paths.js +6 -8
- package/dist/report/host/execute.cjs +13 -22
- package/dist/report/host/execute.cjs.map +1 -1
- package/dist/report/host/execute.d.cts +1 -4
- package/dist/report/host/execute.d.mts +1 -4
- package/dist/report/host/execute.d.ts +1 -4
- package/dist/report/host/from-record.cjs +3 -0
- package/dist/report/host/from-record.cjs.map +1 -1
- package/dist/report/host/from-record.d.cts +4 -1
- package/dist/report/host/from-record.d.mts +4 -1
- package/dist/report/host/from-record.d.ts +4 -1
- package/dist/report/host/site-assets.cjs +1 -2
- package/dist/report/host/site-assets.cjs.map +1 -1
- package/dist/report/host/site-assets.d.cts +0 -1
- package/dist/report/host/site-assets.d.mts +0 -1
- package/dist/report/host/site-assets.d.ts +0 -1
- package/dist/report/host/site-assets.js +2 -4
- package/dist/report/host/static.cjs +71 -346
- package/dist/report/host/static.cjs.map +1 -1
- package/dist/report/host/static.d.cts +1 -3
- package/dist/report/host/static.d.mts +1 -3
- package/dist/report/host/static.d.ts +1 -3
- package/dist/report/host/static.js +2 -2
- package/dist/report/host/view-session.cjs.map +1 -1
- package/dist/report/host/view-session.d.cts +1 -1
- package/dist/report/host/view-session.d.mts +1 -1
- package/dist/report/host/view-session.d.ts +1 -1
- package/dist/report/model/locale.cjs +1 -1
- package/dist/report/model/locale.cjs.map +1 -1
- package/dist/report/model/locale.d.cts +1 -1
- package/dist/report/model/locale.d.mts +1 -1
- package/dist/report/model/locale.d.ts +1 -1
- package/dist/report/model/pricing.cjs +2 -2
- package/dist/report/model/pricing.cjs.map +1 -1
- package/dist/report/react/enhance.js +5 -5
- package/dist/report/react/styles.css +190 -24
- package/dist/runner/adoption.cjs +4 -7
- package/dist/runner/adoption.cjs.map +1 -1
- package/dist/runner/attempt-resources.cjs +60 -0
- package/dist/runner/attempt-resources.cjs.map +1 -0
- package/dist/runner/attempt-resources.d.cts +13 -0
- package/dist/runner/attempt-resources.d.mts +13 -0
- package/dist/runner/attempt-resources.d.ts +13 -0
- package/dist/runner/attempt-resources.js +6 -0
- package/dist/runner/attempt-resources.js.map +1 -0
- package/dist/runner/attempt.cjs +37 -3
- package/dist/runner/attempt.cjs.map +1 -1
- package/dist/runner/feedback/failure.cjs +77 -2
- package/dist/runner/feedback/failure.cjs.map +1 -1
- package/dist/runner/feedback/failure.d.cts +2 -1
- package/dist/runner/feedback/failure.d.mts +2 -1
- package/dist/runner/feedback/failure.d.ts +2 -1
- package/dist/runner/project-current.cjs +2 -13
- package/dist/runner/project-current.cjs.map +1 -1
- package/dist/runner/project-current.d.cts +4 -2
- package/dist/runner/project-current.d.mts +4 -2
- package/dist/runner/project-current.d.ts +4 -2
- package/dist/runner/reporters/braintrust.cjs +7 -7
- package/dist/runner/reporters/braintrust.cjs.map +1 -1
- package/dist/runner/reuse-readback.cjs +3 -4
- package/dist/runner/reuse-readback.cjs.map +1 -1
- package/dist/runner/run.cjs +5 -2
- package/dist/runner/run.cjs.map +1 -1
- package/dist/sandbox/backend.cjs +32 -2
- package/dist/sandbox/backend.cjs.map +1 -1
- package/dist/sandbox/backend.d.cts +12 -1
- package/dist/sandbox/backend.d.mts +12 -1
- package/dist/sandbox/backend.d.ts +12 -1
- package/dist/sandbox/backend.js +28 -22
- package/dist/sandbox/docker.cjs +140 -0
- package/dist/sandbox/docker.cjs.map +1 -1
- package/dist/sandbox/docker.d.cts +3 -1
- package/dist/sandbox/docker.d.mts +3 -1
- package/dist/sandbox/docker.d.ts +3 -1
- package/dist/sandbox/e2b.cjs +42 -0
- package/dist/sandbox/e2b.cjs.map +1 -1
- package/dist/sandbox/e2b.d.cts +2 -0
- package/dist/sandbox/e2b.d.mts +2 -0
- package/dist/sandbox/e2b.d.ts +2 -0
- package/dist/sandbox/local.cjs +64 -0
- package/dist/sandbox/local.cjs.map +1 -1
- package/dist/sandbox/local.d.cts +3 -1
- package/dist/sandbox/local.d.mts +3 -1
- package/dist/sandbox/local.d.ts +3 -1
- package/dist/sandbox/managed-process.cjs +49 -0
- package/dist/sandbox/managed-process.cjs.map +1 -0
- package/dist/sandbox/managed-process.d.cts +11 -0
- package/dist/sandbox/managed-process.d.mts +11 -0
- package/dist/sandbox/managed-process.d.ts +11 -0
- package/dist/sandbox/managed-process.js +6 -0
- package/dist/sandbox/managed-process.js.map +1 -0
- package/dist/sandbox/types.cjs.map +1 -1
- package/dist/sandbox/types.d.cts +24 -0
- package/dist/sandbox/types.d.mts +24 -0
- package/dist/sandbox/types.d.ts +24 -0
- package/dist/sandbox/vercel.cjs +1 -0
- package/dist/sandbox/vercel.cjs.map +1 -1
- package/dist/sandbox/vercel.d.cts +1 -0
- package/dist/sandbox/vercel.d.mts +1 -0
- package/dist/sandbox/vercel.d.ts +1 -0
- package/dist/view/server.cjs +2 -37
- package/dist/view/server.cjs.map +1 -1
- package/dist/view/server.d.cts +0 -3
- package/dist/view/server.d.mts +0 -3
- package/dist/view/server.d.ts +0 -3
- package/docs-site/zh/reference/builtin-agents.mdx +7 -7
- package/docs-site/zh/reference/official-adapters.mdx +4 -4
- package/docs-site/zh/reference/report-components.mdx +2 -2
- package/docs-site/zh/tutorials/configuration.mdx +2 -2
- package/docs-site/zh/tutorials/deploy-report-site.mdx +24 -2
- package/docs-site/zh/tutorials/publish-report.mdx +4 -4
- package/docs-site/zh/tutorials/sandbox-agent.mdx +5 -5
- package/docs-site/zh/tutorials/theming.mdx +2 -2
- package/package.json +4 -6
- package/dist/record/migration/index.cjs +0 -5
- package/dist/record/migration/index.cjs.map +0 -1
- package/dist/record/migration/index.d.cts +0 -11
- package/dist/record/migration/index.d.mts +0 -11
- package/dist/record/migration/index.d.ts +0 -11
- package/dist/record/migration/index.js +0 -6
- package/dist/record/migration/index.js.map +0 -1
- package/dist/report/host/site-runtime.cjs +0 -92
- package/dist/report/host/site-runtime.cjs.map +0 -1
- package/dist/report/host/site-runtime.d.cts +0 -9
- package/dist/report/host/site-runtime.d.mts +0 -9
- package/dist/report/host/site-runtime.d.ts +0 -9
- package/dist/report/host/site-runtime.js +0 -10
- package/dist/report/host/site-runtime.js.map +0 -1
- package/dist/view/client-dist/app.css +0 -2
- package/dist/view/client-dist/app.js +0 -49
- package/dist/view/data.cjs +0 -3
- package/dist/view/data.cjs.map +0 -1
- package/dist/view/data.d.cts +0 -9
- package/dist/view/data.d.mts +0 -9
- package/dist/view/data.d.ts +0 -9
- package/dist/view/data.js +0 -4
- package/dist/view/data.js.map +0 -1
- package/dist/view/index.cjs +0 -24
- package/dist/view/index.cjs.map +0 -1
- package/dist/view/index.d.cts +0 -9
- package/dist/view/index.d.mts +0 -9
- package/dist/view/index.d.ts +0 -9
- package/dist/view/index.js +0 -28
- package/dist/view/index.js.map +0 -1
- package/dist/view/report-view-cache.cjs +0 -200
- package/dist/view/report-view-cache.cjs.map +0 -1
- package/dist/view/report-view-cache.d.cts +0 -67
- package/dist/view/report-view-cache.d.mts +0 -67
- package/dist/view/report-view-cache.d.ts +0 -67
- package/dist/view/report-view-cache.js +0 -8
- package/dist/view/report-view-cache.js.map +0 -1
- package/dist/view/shared/types.cjs +0 -3
- package/dist/view/shared/types.cjs.map +0 -1
- package/dist/view/shared/types.d.cts +0 -51
- package/dist/view/shared/types.d.mts +0 -51
- package/dist/view/shared/types.d.ts +0 -51
- package/dist/view/shared/types.js +0 -4
- package/dist/view/shared/types.js.map +0 -1
- package/dist/view/site.cjs +0 -32
- package/dist/view/site.cjs.map +0 -1
- package/dist/view/site.d.cts +0 -24
- package/dist/view/site.d.mts +0 -24
- package/dist/view/site.d.ts +0 -24
- package/dist/view/site.js +0 -8
- package/dist/view/site.js.map +0 -1
- package/dist/view/styles.css +0 -170
- package/dist/view/template.html +0 -17
package/dist/runner/attempt.cjs
CHANGED
|
@@ -15,6 +15,8 @@ const registry_ts_1 = require("../sandbox/registry.cjs");
|
|
|
15
15
|
const paths_ts_1 = require("../sandbox/paths.cjs");
|
|
16
16
|
const request_executor_ts_1 = require("../sandbox/request-executor.cjs");
|
|
17
17
|
const cleanup_timeout_ts_1 = require("./cleanup-timeout.cjs");
|
|
18
|
+
const attempt_resources_ts_1 = require("./attempt-resources.cjs");
|
|
19
|
+
const attempt_resources_ts_2 = require("../context/attempt-resources.cjs");
|
|
18
20
|
const timeout_ts_1 = require("./timeout.cjs");
|
|
19
21
|
const deadline_ts_1 = require("../sandbox/deadline.cjs");
|
|
20
22
|
const failure_class_ts_1 = require("../shared/failure-class.cjs");
|
|
@@ -83,6 +85,15 @@ function runAttemptEffect(a, opts, sandboxSem, { buildLocators, runTiming, paren
|
|
|
83
85
|
// an internal capability until the Record producer seals its own Attachments.
|
|
84
86
|
const sourceRegistry = (0, source_loc_ts_1.createSourceRegistry)(process.cwd());
|
|
85
87
|
const sourceCapture = (0, source_producer_ts_1.createRunnerAttemptSourceCapture)(sourceRegistry);
|
|
88
|
+
const attemptResources = new attempt_resources_ts_1.ManagedAttemptResources();
|
|
89
|
+
let attemptResourceReleaseFailureReported = false;
|
|
90
|
+
const reportAttemptResourceReleaseFailure = (error) => {
|
|
91
|
+
if (attemptResourceReleaseFailureReported)
|
|
92
|
+
return;
|
|
93
|
+
attemptResourceReleaseFailureReported = true;
|
|
94
|
+
declareFailure("agent.teardown", error);
|
|
95
|
+
diagnostics.push(teardownDiagnostic("agent.teardown", error));
|
|
96
|
+
};
|
|
86
97
|
const base = {
|
|
87
98
|
id: evalDef.id,
|
|
88
99
|
description: evalDef.description,
|
|
@@ -767,6 +778,13 @@ function runAttemptEffect(a, opts, sandboxSem, { buildLocators, runTiming, paren
|
|
|
767
778
|
.catch(() => { });
|
|
768
779
|
}));
|
|
769
780
|
}
|
|
781
|
+
// Cross-send adapter processes belong to the Attempt Scope, not to the
|
|
782
|
+
// Promise-shaped body. On timeout the bridge is intentionally sealed
|
|
783
|
+
// before that Promise's finally continuation can submit more work, so a
|
|
784
|
+
// scope finalizer must remain the unconditional release owner.
|
|
785
|
+
yield* effect_1.Effect.addFinalizer(() => (0, cleanup_timeout_ts_1.cleanupCallback)((cleanupSignal) => attemptResources.releaseAll(cleanupSignal)).pipe(effect_1.Effect.catchAll((error) => effect_1.Effect.sync(() => {
|
|
786
|
+
reportAttemptResourceReleaseFailure(error);
|
|
787
|
+
}))));
|
|
770
788
|
// The legacy setup/diff body remains Promise-shaped, while OTLP waits,
|
|
771
789
|
// author execution, and sealing run in this Attempt's Effect scope. No
|
|
772
790
|
// nested runtime is introduced.
|
|
@@ -797,6 +815,8 @@ function runAttemptEffect(a, opts, sandboxSem, { buildLocators, runTiming, paren
|
|
|
797
815
|
declareFailure,
|
|
798
816
|
isDeadlineTimedOut: () => timedOut,
|
|
799
817
|
layerCleanups,
|
|
818
|
+
attemptResources,
|
|
819
|
+
reportAttemptResourceReleaseFailure,
|
|
800
820
|
registerEvidence: (getEvents, getUsage, getRetryAttempts) => {
|
|
801
821
|
liveEvents = getEvents;
|
|
802
822
|
liveUsage = getUsage;
|
|
@@ -1210,8 +1230,9 @@ async function runAttemptBody(a, config, t0, base, res, parentSignal) {
|
|
|
1210
1230
|
const sandbox = usesSandbox
|
|
1211
1231
|
? withCommandTiming(rawSandbox, recorder, getPhase, commands, sensitiveValues, res.deadlineAt, observabilityRuntime, signal)
|
|
1212
1232
|
: rawSandbox;
|
|
1233
|
+
const { attemptResources, reportAttemptResourceReleaseFailure } = res;
|
|
1213
1234
|
// Direct Agent 只拿基础 ctx;Sandbox Agent 才拿带真实 Sandbox 的扩展 ctx。
|
|
1214
|
-
const attemptCtx = {
|
|
1235
|
+
const attemptCtx = (0, attempt_resources_ts_2.bindAttemptResources)({
|
|
1215
1236
|
signal,
|
|
1216
1237
|
evalId: evalDef.id,
|
|
1217
1238
|
attempt: { id: evalDef.id, index: attempt },
|
|
@@ -1229,8 +1250,8 @@ async function runAttemptBody(a, config, t0, base, res, parentSignal) {
|
|
|
1229
1250
|
diagnostic: feedback.diagnostic,
|
|
1230
1251
|
// log 是 progress({ message }) 的别名,不是第二条通道(见 AgentContext.log 注释)。
|
|
1231
1252
|
log,
|
|
1232
|
-
};
|
|
1233
|
-
const sandboxAttemptCtx = { ...attemptCtx, sandbox };
|
|
1253
|
+
}, attemptResources);
|
|
1254
|
+
const sandboxAttemptCtx = (0, attempt_resources_ts_2.bindAttemptResources)({ ...attemptCtx, sandbox }, attemptResources);
|
|
1234
1255
|
const commandTarget = (0, operations_ts_1.createSandboxCommandTarget)(sandbox);
|
|
1235
1256
|
/** agent.setup 时点已走到(未声明 setup 也置位)——agent.teardown 的触发条件(成对触发规则)。 */
|
|
1236
1257
|
let agentSetupReached = false;
|
|
@@ -1428,6 +1449,7 @@ async function runAttemptBody(a, config, t0, base, res, parentSignal) {
|
|
|
1428
1449
|
// 走的生命周期链是同一个函数,两条链的决议序各自单源在 send-failures.ts / failure-class.ts。
|
|
1429
1450
|
experimentClassifier: run.classifyFailure,
|
|
1430
1451
|
sourceRegistry,
|
|
1452
|
+
resources: attemptResources,
|
|
1431
1453
|
nextSourceOrder: sourceCapture.nextSourceOrder,
|
|
1432
1454
|
// Pass / Score share the same Assert-first entry runtime. Their
|
|
1433
1455
|
// independent folds are both derived only after this Attempt seals.
|
|
@@ -1847,6 +1869,18 @@ async function runAttemptBody(a, config, t0, base, res, parentSignal) {
|
|
|
1847
1869
|
})
|
|
1848
1870
|
.catch(() => { });
|
|
1849
1871
|
}
|
|
1872
|
+
try {
|
|
1873
|
+
await assertFirst.requestEffect((0, cleanup_timeout_ts_1.cleanupCallback)((cleanupSignal) => attemptResources.releaseAll(cleanupSignal)));
|
|
1874
|
+
}
|
|
1875
|
+
catch (error) {
|
|
1876
|
+
// An interrupted body can resume its Promise finally only after the
|
|
1877
|
+
// Effect bridge has closed. The Scope finalizer above still performs the
|
|
1878
|
+
// release; this named closure is therefore lifecycle control, not a
|
|
1879
|
+
// second teardown failure.
|
|
1880
|
+
if (!(error instanceof api_ts_1.AssertionAuthoringClosedError && error.reason === "attempt-interrupted")) {
|
|
1881
|
+
reportAttemptResourceReleaseFailure(error);
|
|
1882
|
+
}
|
|
1883
|
+
}
|
|
1850
1884
|
for (const lifecycle of evalPluginLifecycles.slice(0, activatedEvalPlugins).reverse()) {
|
|
1851
1885
|
if (lifecycle.teardown === undefined)
|
|
1852
1886
|
continue;
|