@prismatic-io/lux 0.0.2-preview.4 → 0.0.2-preview.41
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/lib/answerers/claude-code/index.d.ts +15 -3
- package/lib/answerers/claude-code/index.d.ts.map +1 -1
- package/lib/answerers/claude-code/index.js +6 -5
- package/lib/answerers/claude-code/index.js.map +1 -1
- package/lib/answerers/persona/index.d.ts +44 -5
- package/lib/answerers/persona/index.d.ts.map +1 -1
- package/lib/answerers/persona/index.js +65 -34
- package/lib/answerers/persona/index.js.map +1 -1
- package/lib/answerers/terminal/index.d.ts +9 -3
- package/lib/answerers/terminal/index.d.ts.map +1 -1
- package/lib/answerers/terminal/index.js +6 -4
- package/lib/answerers/terminal/index.js.map +1 -1
- package/lib/assertions/authoring.d.ts +2 -2
- package/lib/assertions/authoring.d.ts.map +1 -1
- package/lib/assertions/authoring.js.map +1 -1
- package/lib/assertions/core/command-exits-zero.d.ts +5 -2
- package/lib/assertions/core/command-exits-zero.d.ts.map +1 -1
- package/lib/assertions/core/command-exits-zero.js +59 -14
- package/lib/assertions/core/command-exits-zero.js.map +1 -1
- package/lib/assertions/core/event-checks.d.ts +3 -0
- package/lib/assertions/core/event-checks.d.ts.map +1 -1
- package/lib/assertions/core/event-checks.js +49 -3
- package/lib/assertions/core/event-checks.js.map +1 -1
- package/lib/assertions/core/file-checks.d.ts +6 -0
- package/lib/assertions/core/file-checks.d.ts.map +1 -1
- package/lib/assertions/core/index.d.ts.map +1 -1
- package/lib/assertions/core/index.js +2 -1
- package/lib/assertions/core/index.js.map +1 -1
- package/lib/assertions/core/json-pointer-equals.d.ts +1 -0
- package/lib/assertions/core/json-pointer-equals.d.ts.map +1 -1
- package/lib/assertions/core/output-checks.d.ts +3 -0
- package/lib/assertions/core/output-checks.d.ts.map +1 -1
- package/lib/assertions/core/predicate.d.ts +1 -0
- package/lib/assertions/core/predicate.d.ts.map +1 -1
- package/lib/assertions/core/resource-checks.d.ts +25 -0
- package/lib/assertions/core/resource-checks.d.ts.map +1 -1
- package/lib/assertions/core/resource-checks.js +35 -5
- package/lib/assertions/core/resource-checks.js.map +1 -1
- package/lib/assertions/core/safe-regex.d.ts.map +1 -1
- package/lib/assertions/core/safe-regex.js +7 -1
- package/lib/assertions/core/safe-regex.js.map +1 -1
- package/lib/assertions/rubric/evidence.d.ts +88 -0
- package/lib/assertions/rubric/evidence.d.ts.map +1 -0
- package/lib/assertions/rubric/evidence.js +75 -0
- package/lib/assertions/rubric/evidence.js.map +1 -0
- package/lib/assertions/rubric/index.d.ts +88 -34
- package/lib/assertions/rubric/index.d.ts.map +1 -1
- package/lib/assertions/rubric/index.js +67 -43
- package/lib/assertions/rubric/index.js.map +1 -1
- package/lib/assertions/rubric/internal.d.ts +30 -5
- package/lib/assertions/rubric/internal.d.ts.map +1 -1
- package/lib/assertions/rubric/internal.js +211 -46
- package/lib/assertions/rubric/internal.js.map +1 -1
- package/lib/authoring.d.ts +37 -2
- package/lib/authoring.d.ts.map +1 -1
- package/lib/authoring.js +36 -1
- package/lib/authoring.js.map +1 -1
- package/lib/cli/bin.js +2 -13
- package/lib/cli/bin.js.map +1 -1
- package/lib/cli/command-runtime.d.ts +3 -3
- package/lib/cli/command-runtime.d.ts.map +1 -1
- package/lib/cli/command-runtime.js +17 -6
- package/lib/cli/command-runtime.js.map +1 -1
- package/lib/cli/doctor.d.ts +55 -0
- package/lib/cli/doctor.d.ts.map +1 -0
- package/lib/cli/doctor.js +14 -0
- package/lib/cli/doctor.js.map +1 -0
- package/lib/cli/harness-plan.d.ts +27 -0
- package/lib/cli/harness-plan.d.ts.map +1 -0
- package/lib/cli/harness-plan.js +75 -0
- package/lib/cli/harness-plan.js.map +1 -0
- package/lib/cli/init-templates.d.ts +11 -0
- package/lib/cli/init-templates.d.ts.map +1 -0
- package/lib/cli/init-templates.js +153 -0
- package/lib/cli/init-templates.js.map +1 -0
- package/lib/cli/init.d.ts +10 -0
- package/lib/cli/init.d.ts.map +1 -1
- package/lib/cli/init.js +34 -173
- package/lib/cli/init.js.map +1 -1
- package/lib/cli/output-schemas.d.ts +1412 -0
- package/lib/cli/output-schemas.d.ts.map +1 -0
- package/lib/cli/output-schemas.js +94 -0
- package/lib/cli/output-schemas.js.map +1 -0
- package/lib/cli/program.d.ts +140 -12
- package/lib/cli/program.d.ts.map +1 -1
- package/lib/cli/program.js +783 -650
- package/lib/cli/program.js.map +1 -1
- package/lib/cli/render/format.d.ts.map +1 -1
- package/lib/cli/render/format.js +1 -1
- package/lib/cli/render/format.js.map +1 -1
- package/lib/cli/render/reporter.d.ts.map +1 -1
- package/lib/cli/render/reporter.js +35 -8
- package/lib/cli/render/reporter.js.map +1 -1
- package/lib/cli/run-options.d.ts +19 -4
- package/lib/cli/run-options.d.ts.map +1 -1
- package/lib/cli/run-options.js +100 -19
- package/lib/cli/run-options.js.map +1 -1
- package/lib/cli/view.d.ts +15 -0
- package/lib/cli/view.d.ts.map +1 -0
- package/lib/cli/view.js +168 -0
- package/lib/cli/view.js.map +1 -0
- package/lib/container/driver.d.ts +27 -0
- package/lib/container/driver.d.ts.map +1 -0
- package/lib/container/driver.js +199 -0
- package/lib/container/driver.js.map +1 -0
- package/lib/container/paths.d.ts +3 -0
- package/lib/container/paths.d.ts.map +1 -0
- package/lib/container/paths.js +27 -0
- package/lib/container/paths.js.map +1 -0
- package/lib/container/protocol.d.ts +12 -0
- package/lib/container/protocol.d.ts.map +1 -0
- package/lib/container/protocol.js +38 -0
- package/lib/container/protocol.js.map +1 -0
- package/lib/container/resources.d.ts +14 -0
- package/lib/container/resources.d.ts.map +1 -0
- package/lib/container/resources.js +141 -0
- package/lib/container/resources.js.map +1 -0
- package/lib/container/worker.d.ts +2 -0
- package/lib/container/worker.d.ts.map +1 -0
- package/lib/container/worker.js +85 -0
- package/lib/container/worker.js.map +1 -0
- package/lib/core/action-events.d.ts +29 -0
- package/lib/core/action-events.d.ts.map +1 -0
- package/lib/core/action-events.js +51 -0
- package/lib/core/action-events.js.map +1 -0
- package/lib/core/agent-activity.d.ts +49 -0
- package/lib/core/agent-activity.d.ts.map +1 -0
- package/lib/core/agent-activity.js +206 -0
- package/lib/core/agent-activity.js.map +1 -0
- package/lib/core/agent-environment.d.ts +5 -0
- package/lib/core/agent-environment.d.ts.map +1 -0
- package/lib/core/agent-environment.js +47 -0
- package/lib/core/agent-environment.js.map +1 -0
- package/lib/core/agent-events.d.ts +26 -0
- package/lib/core/agent-events.d.ts.map +1 -0
- package/lib/core/agent-events.js +13 -0
- package/lib/core/agent-events.js.map +1 -0
- package/lib/core/annotation.d.ts +6 -2
- package/lib/core/annotation.d.ts.map +1 -1
- package/lib/core/annotation.js +2 -1
- package/lib/core/annotation.js.map +1 -1
- package/lib/core/answerer.d.ts +12 -0
- package/lib/core/answerer.d.ts.map +1 -1
- package/lib/core/answerer.js +2 -0
- package/lib/core/answerer.js.map +1 -1
- package/lib/core/artifact-evidence.d.ts +6 -1
- package/lib/core/artifact-evidence.d.ts.map +1 -1
- package/lib/core/artifact-evidence.js +27 -6
- package/lib/core/artifact-evidence.js.map +1 -1
- package/lib/core/assertion.d.ts +10 -4
- package/lib/core/assertion.d.ts.map +1 -1
- package/lib/core/assertion.js +8 -2
- package/lib/core/assertion.js.map +1 -1
- package/lib/core/case-defaults.d.ts +16 -0
- package/lib/core/case-defaults.d.ts.map +1 -0
- package/lib/core/case-defaults.js +42 -0
- package/lib/core/case-defaults.js.map +1 -0
- package/lib/core/case.d.ts +120 -6
- package/lib/core/case.d.ts.map +1 -1
- package/lib/core/case.js +51 -5
- package/lib/core/case.js.map +1 -1
- package/lib/core/command-verification.d.ts +10 -0
- package/lib/core/command-verification.d.ts.map +1 -0
- package/lib/core/command-verification.js +66 -0
- package/lib/core/command-verification.js.map +1 -0
- package/lib/core/driver-execution.d.ts +83 -0
- package/lib/core/driver-execution.d.ts.map +1 -0
- package/lib/core/driver-execution.js +72 -0
- package/lib/core/driver-execution.js.map +1 -0
- package/lib/core/driver-metrics.d.ts +98 -0
- package/lib/core/driver-metrics.d.ts.map +1 -0
- package/lib/core/driver-metrics.js +36 -0
- package/lib/core/driver-metrics.js.map +1 -0
- package/lib/core/driver.d.ts +64 -0
- package/lib/core/driver.d.ts.map +1 -1
- package/lib/core/driver.js +28 -0
- package/lib/core/driver.js.map +1 -1
- package/lib/core/duration.d.ts +5 -0
- package/lib/core/duration.d.ts.map +1 -0
- package/lib/core/duration.js +49 -0
- package/lib/core/duration.js.map +1 -0
- package/lib/core/environment.d.ts +18 -0
- package/lib/core/environment.d.ts.map +1 -0
- package/lib/core/environment.js +21 -0
- package/lib/core/environment.js.map +1 -0
- package/lib/core/evaluation-clusters.d.ts +17 -0
- package/lib/core/evaluation-clusters.d.ts.map +1 -0
- package/lib/core/evaluation-clusters.js +23 -0
- package/lib/core/evaluation-clusters.js.map +1 -0
- package/lib/core/events.d.ts +34 -0
- package/lib/core/events.d.ts.map +1 -1
- package/lib/core/events.js +11 -2
- package/lib/core/events.js.map +1 -1
- package/lib/core/experiment.d.ts +33 -2
- package/lib/core/experiment.d.ts.map +1 -1
- package/lib/core/experiment.js +40 -19
- package/lib/core/experiment.js.map +1 -1
- package/lib/core/file-tree.d.ts +7 -0
- package/lib/core/file-tree.d.ts.map +1 -0
- package/lib/core/file-tree.js +35 -0
- package/lib/core/file-tree.js.map +1 -0
- package/lib/core/global-id.d.ts +6 -0
- package/lib/core/global-id.d.ts.map +1 -0
- package/lib/core/global-id.js +17 -0
- package/lib/core/global-id.js.map +1 -0
- package/lib/core/harness-catalog.d.ts +35 -0
- package/lib/core/harness-catalog.d.ts.map +1 -0
- package/lib/core/harness-catalog.js +45 -0
- package/lib/core/harness-catalog.js.map +1 -0
- package/lib/core/harness-catalogs/antigravity.d.ts +11 -0
- package/lib/core/harness-catalogs/antigravity.d.ts.map +1 -0
- package/lib/core/harness-catalogs/antigravity.js +23 -0
- package/lib/core/harness-catalogs/antigravity.js.map +1 -0
- package/lib/core/harness-catalogs/claude-code.d.ts +12 -0
- package/lib/core/harness-catalogs/claude-code.d.ts.map +1 -0
- package/lib/core/harness-catalogs/claude-code.js +24 -0
- package/lib/core/harness-catalogs/claude-code.js.map +1 -0
- package/lib/core/harness-catalogs/codex.d.ts +11 -0
- package/lib/core/harness-catalogs/codex.d.ts.map +1 -0
- package/lib/core/harness-catalogs/codex.js +26 -0
- package/lib/core/harness-catalogs/codex.js.map +1 -0
- package/lib/core/harness-catalogs/copilot.d.ts +29 -0
- package/lib/core/harness-catalogs/copilot.d.ts.map +1 -0
- package/lib/core/harness-catalogs/copilot.js +45 -0
- package/lib/core/harness-catalogs/copilot.js.map +1 -0
- package/lib/core/harness-catalogs/cursor.d.ts +2 -0
- package/lib/core/harness-catalogs/cursor.d.ts.map +1 -0
- package/lib/core/harness-catalogs/cursor.js +13 -0
- package/lib/core/harness-catalogs/cursor.js.map +1 -0
- package/lib/core/harness-catalogs/grok-build.d.ts +7 -0
- package/lib/core/harness-catalogs/grok-build.d.ts.map +1 -0
- package/lib/core/harness-catalogs/grok-build.js +18 -0
- package/lib/core/harness-catalogs/grok-build.js.map +1 -0
- package/lib/core/harness-catalogs/index.d.ts +73 -0
- package/lib/core/harness-catalogs/index.d.ts.map +1 -0
- package/lib/core/harness-catalogs/index.js +17 -0
- package/lib/core/harness-catalogs/index.js.map +1 -0
- package/lib/core/harness-matrix.d.ts +154 -0
- package/lib/core/harness-matrix.d.ts.map +1 -0
- package/lib/core/harness-matrix.js +204 -0
- package/lib/core/harness-matrix.js.map +1 -0
- package/lib/core/index.d.ts +12 -0
- package/lib/core/index.d.ts.map +1 -1
- package/lib/core/index.js +12 -0
- package/lib/core/index.js.map +1 -1
- package/lib/core/lifecycle-fixtures.d.ts.map +1 -1
- package/lib/core/lifecycle-fixtures.js +4 -2
- package/lib/core/lifecycle-fixtures.js.map +1 -1
- package/lib/core/model-cli.d.ts +31 -15
- package/lib/core/model-cli.d.ts.map +1 -1
- package/lib/core/model-cli.js +53 -23
- package/lib/core/model-cli.js.map +1 -1
- package/lib/core/platform-process.d.ts +7 -2
- package/lib/core/platform-process.d.ts.map +1 -1
- package/lib/core/platform-process.js +54 -16
- package/lib/core/platform-process.js.map +1 -1
- package/lib/core/reference-defaults.d.ts +5 -0
- package/lib/core/reference-defaults.d.ts.map +1 -0
- package/lib/core/reference-defaults.js +42 -0
- package/lib/core/reference-defaults.js.map +1 -0
- package/lib/core/rubric.d.ts +1 -0
- package/lib/core/rubric.d.ts.map +1 -1
- package/lib/core/run.d.ts +292 -1
- package/lib/core/run.d.ts.map +1 -1
- package/lib/core/run.js +27 -0
- package/lib/core/run.js.map +1 -1
- package/lib/core/secure-copy.d.ts.map +1 -0
- package/lib/core/secure-copy.js.map +1 -0
- package/lib/core/usage.d.ts +5 -0
- package/lib/core/usage.d.ts.map +1 -1
- package/lib/core/usage.js +3 -0
- package/lib/core/usage.js.map +1 -1
- package/lib/core/wire.d.ts +11 -0
- package/lib/core/wire.d.ts.map +1 -1
- package/lib/drivers/antigravity/artifacts.d.ts +2 -0
- package/lib/drivers/antigravity/artifacts.d.ts.map +1 -0
- package/lib/drivers/antigravity/artifacts.js +33 -0
- package/lib/drivers/antigravity/artifacts.js.map +1 -0
- package/lib/drivers/antigravity/config.d.ts +88 -0
- package/lib/drivers/antigravity/config.d.ts.map +1 -0
- package/lib/drivers/antigravity/config.js +87 -0
- package/lib/drivers/antigravity/config.js.map +1 -0
- package/lib/drivers/antigravity/events.d.ts +4 -0
- package/lib/drivers/antigravity/events.d.ts.map +1 -0
- package/lib/drivers/antigravity/events.js +241 -0
- package/lib/drivers/antigravity/events.js.map +1 -0
- package/lib/drivers/antigravity/index.d.ts +114 -0
- package/lib/drivers/antigravity/index.d.ts.map +1 -0
- package/lib/drivers/antigravity/index.js +113 -0
- package/lib/drivers/antigravity/index.js.map +1 -0
- package/lib/drivers/antigravity/runtime.d.ts +7 -0
- package/lib/drivers/antigravity/runtime.d.ts.map +1 -0
- package/lib/drivers/antigravity/runtime.js +83 -0
- package/lib/drivers/antigravity/runtime.js.map +1 -0
- package/lib/drivers/claude-code/deferred-process.d.ts +17 -0
- package/lib/drivers/claude-code/deferred-process.d.ts.map +1 -0
- package/lib/drivers/claude-code/deferred-process.js +108 -0
- package/lib/drivers/claude-code/deferred-process.js.map +1 -0
- package/lib/drivers/claude-code/index.d.ts +187 -10
- package/lib/drivers/claude-code/index.d.ts.map +1 -1
- package/lib/drivers/claude-code/index.js +198 -253
- package/lib/drivers/claude-code/index.js.map +1 -1
- package/lib/drivers/claude-code/isolation.d.ts +8 -0
- package/lib/drivers/claude-code/isolation.d.ts.map +1 -0
- package/lib/drivers/claude-code/isolation.js +199 -0
- package/lib/drivers/claude-code/isolation.js.map +1 -0
- package/lib/drivers/claude-code/parse-events.d.ts.map +1 -1
- package/lib/drivers/claude-code/parse-events.js +73 -8
- package/lib/drivers/claude-code/parse-events.js.map +1 -1
- package/lib/drivers/codex/app-events.d.ts +9 -2
- package/lib/drivers/codex/app-events.d.ts.map +1 -1
- package/lib/drivers/codex/app-events.js +104 -12
- package/lib/drivers/codex/app-events.js.map +1 -1
- package/lib/drivers/codex/config.d.ts +69 -5
- package/lib/drivers/codex/config.d.ts.map +1 -1
- package/lib/drivers/codex/config.js +48 -8
- package/lib/drivers/codex/config.js.map +1 -1
- package/lib/drivers/codex/exec-events.d.ts +4 -0
- package/lib/drivers/codex/exec-events.d.ts.map +1 -0
- package/lib/drivers/codex/exec-events.js +230 -0
- package/lib/drivers/codex/exec-events.js.map +1 -0
- package/lib/drivers/codex/index.d.ts +142 -4
- package/lib/drivers/codex/index.d.ts.map +1 -1
- package/lib/drivers/codex/index.js +114 -276
- package/lib/drivers/codex/index.js.map +1 -1
- package/lib/drivers/copilot/config.d.ts +84 -0
- package/lib/drivers/copilot/config.d.ts.map +1 -0
- package/lib/drivers/copilot/config.js +57 -0
- package/lib/drivers/copilot/config.js.map +1 -0
- package/lib/drivers/copilot/index.d.ts +107 -0
- package/lib/drivers/copilot/index.d.ts.map +1 -0
- package/lib/drivers/copilot/index.js +268 -0
- package/lib/drivers/copilot/index.js.map +1 -0
- package/lib/drivers/cursor/config.d.ts +28 -0
- package/lib/drivers/cursor/config.d.ts.map +1 -0
- package/lib/drivers/cursor/config.js +28 -0
- package/lib/drivers/cursor/config.js.map +1 -0
- package/lib/drivers/cursor/index.d.ts +44 -0
- package/lib/drivers/cursor/index.d.ts.map +1 -0
- package/lib/drivers/cursor/index.js +286 -0
- package/lib/drivers/cursor/index.js.map +1 -0
- package/lib/drivers/cursor/interaction.d.ts +6 -0
- package/lib/drivers/cursor/interaction.d.ts.map +1 -0
- package/lib/drivers/cursor/interaction.js +55 -0
- package/lib/drivers/cursor/interaction.js.map +1 -0
- package/lib/drivers/grok-build/config.d.ts +68 -0
- package/lib/drivers/grok-build/config.d.ts.map +1 -0
- package/lib/drivers/grok-build/config.js +40 -0
- package/lib/drivers/grok-build/config.js.map +1 -0
- package/lib/drivers/grok-build/index.d.ts +87 -0
- package/lib/drivers/grok-build/index.d.ts.map +1 -0
- package/lib/drivers/grok-build/index.js +293 -0
- package/lib/drivers/grok-build/index.js.map +1 -0
- package/lib/drivers/mcp/index.d.ts +37 -4
- package/lib/drivers/mcp/index.d.ts.map +1 -1
- package/lib/drivers/mcp/index.js +25 -11
- package/lib/drivers/mcp/index.js.map +1 -1
- package/lib/drivers/shared/acp-events.d.ts +15 -0
- package/lib/drivers/shared/acp-events.d.ts.map +1 -0
- package/lib/drivers/shared/acp-events.js +83 -0
- package/lib/drivers/shared/acp-events.js.map +1 -0
- package/lib/drivers/shared/acp-interaction.d.ts +7 -0
- package/lib/drivers/shared/acp-interaction.d.ts.map +1 -0
- package/lib/drivers/shared/acp-interaction.js +20 -0
- package/lib/drivers/shared/acp-interaction.js.map +1 -0
- package/lib/drivers/shared/acp-session.d.ts +4 -0
- package/lib/drivers/shared/acp-session.d.ts.map +1 -0
- package/lib/drivers/shared/acp-session.js +23 -0
- package/lib/drivers/shared/acp-session.js.map +1 -0
- package/lib/drivers/shared/acp-transport.d.ts +40 -0
- package/lib/drivers/shared/acp-transport.d.ts.map +1 -0
- package/lib/drivers/shared/acp-transport.js +152 -0
- package/lib/drivers/shared/acp-transport.js.map +1 -0
- package/lib/drivers/shared/artifacts.d.ts.map +1 -1
- package/lib/drivers/shared/artifacts.js +3 -2
- package/lib/drivers/shared/artifacts.js.map +1 -1
- package/lib/drivers/shared/experiment-behavior.d.ts +13 -0
- package/lib/drivers/shared/experiment-behavior.d.ts.map +1 -0
- package/lib/drivers/shared/experiment-behavior.js +200 -0
- package/lib/drivers/shared/experiment-behavior.js.map +1 -0
- package/lib/drivers/shared/experiment-policy.d.ts +4 -0
- package/lib/drivers/shared/experiment-policy.d.ts.map +1 -0
- package/lib/drivers/shared/experiment-policy.js +149 -0
- package/lib/drivers/shared/experiment-policy.js.map +1 -0
- package/lib/drivers/shared/skills.d.ts +3 -0
- package/lib/drivers/shared/skills.d.ts.map +1 -0
- package/lib/drivers/shared/skills.js +73 -0
- package/lib/drivers/shared/skills.js.map +1 -0
- package/lib/drivers/subprocess/index.d.ts +39 -4
- package/lib/drivers/subprocess/index.d.ts.map +1 -1
- package/lib/drivers/subprocess/index.js +56 -12
- package/lib/drivers/subprocess/index.js.map +1 -1
- package/lib/index.d.ts +24 -8
- package/lib/index.d.ts.map +1 -1
- package/lib/index.js +20 -5
- package/lib/index.js.map +1 -1
- package/lib/optimization/reflective.d.ts +3 -1
- package/lib/optimization/reflective.d.ts.map +1 -1
- package/lib/optimization/reflective.js +3 -2
- package/lib/optimization/reflective.js.map +1 -1
- package/lib/orchestrator/annotation-loader.d.ts +6 -2
- package/lib/orchestrator/annotation-loader.d.ts.map +1 -1
- package/lib/orchestrator/annotation-loader.js +8 -0
- package/lib/orchestrator/annotation-loader.js.map +1 -1
- package/lib/orchestrator/annotation-store.d.ts.map +1 -1
- package/lib/orchestrator/annotation-store.js +16 -2
- package/lib/orchestrator/annotation-store.js.map +1 -1
- package/lib/orchestrator/artifact-origin.d.ts +3 -0
- package/lib/orchestrator/artifact-origin.d.ts.map +1 -0
- package/lib/orchestrator/artifact-origin.js +40 -0
- package/lib/orchestrator/artifact-origin.js.map +1 -0
- package/lib/orchestrator/campaign-lifecycle.d.ts +1 -0
- package/lib/orchestrator/campaign-lifecycle.d.ts.map +1 -1
- package/lib/orchestrator/campaign-lifecycle.js +4 -1
- package/lib/orchestrator/campaign-lifecycle.js.map +1 -1
- package/lib/orchestrator/candidates.d.ts.map +1 -1
- package/lib/orchestrator/candidates.js +3 -2
- package/lib/orchestrator/candidates.js.map +1 -1
- package/lib/orchestrator/compare.d.ts +23 -6
- package/lib/orchestrator/compare.d.ts.map +1 -1
- package/lib/orchestrator/compare.js +45 -12
- package/lib/orchestrator/compare.js.map +1 -1
- package/lib/orchestrator/comparison-identity.d.ts.map +1 -1
- package/lib/orchestrator/comparison-identity.js +2 -0
- package/lib/orchestrator/comparison-identity.js.map +1 -1
- package/lib/orchestrator/config.d.ts +231 -10
- package/lib/orchestrator/config.d.ts.map +1 -1
- package/lib/orchestrator/config.js +21 -2
- package/lib/orchestrator/config.js.map +1 -1
- package/lib/orchestrator/discover.d.ts +1 -0
- package/lib/orchestrator/discover.d.ts.map +1 -1
- package/lib/orchestrator/discover.js +7 -1
- package/lib/orchestrator/discover.js.map +1 -1
- package/lib/orchestrator/doctor.d.ts +1 -0
- package/lib/orchestrator/doctor.d.ts.map +1 -1
- package/lib/orchestrator/doctor.js +163 -78
- package/lib/orchestrator/doctor.js.map +1 -1
- package/lib/orchestrator/driver-capabilities.d.ts +4 -0
- package/lib/orchestrator/driver-capabilities.d.ts.map +1 -0
- package/lib/orchestrator/driver-capabilities.js +13 -0
- package/lib/orchestrator/driver-capabilities.js.map +1 -0
- package/lib/orchestrator/driver-identity.d.ts +5 -0
- package/lib/orchestrator/driver-identity.d.ts.map +1 -0
- package/lib/orchestrator/driver-identity.js +51 -0
- package/lib/orchestrator/driver-identity.js.map +1 -0
- package/lib/orchestrator/experiment-context.d.ts +52 -4
- package/lib/orchestrator/experiment-context.d.ts.map +1 -1
- package/lib/orchestrator/experiment-context.js +2 -1
- package/lib/orchestrator/experiment-context.js.map +1 -1
- package/lib/orchestrator/experiment-contracts.d.ts +31 -1
- package/lib/orchestrator/experiment-contracts.d.ts.map +1 -1
- package/lib/orchestrator/experiment-corpus.d.ts +2 -1
- package/lib/orchestrator/experiment-corpus.d.ts.map +1 -1
- package/lib/orchestrator/experiment-corpus.js +32 -24
- package/lib/orchestrator/experiment-corpus.js.map +1 -1
- package/lib/orchestrator/experiment-effects.d.ts +33 -0
- package/lib/orchestrator/experiment-effects.d.ts.map +1 -0
- package/lib/orchestrator/experiment-effects.js +46 -0
- package/lib/orchestrator/experiment-effects.js.map +1 -0
- package/lib/orchestrator/experiment-evaluation.d.ts.map +1 -1
- package/lib/orchestrator/experiment-evaluation.js +70 -5
- package/lib/orchestrator/experiment-evaluation.js.map +1 -1
- package/lib/orchestrator/experiment-identity.d.ts +3 -0
- package/lib/orchestrator/experiment-identity.d.ts.map +1 -1
- package/lib/orchestrator/experiment-identity.js +50 -42
- package/lib/orchestrator/experiment-identity.js.map +1 -1
- package/lib/orchestrator/experiment-loader.d.ts +8 -3
- package/lib/orchestrator/experiment-loader.d.ts.map +1 -1
- package/lib/orchestrator/experiment-preflight.d.ts +3 -0
- package/lib/orchestrator/experiment-preflight.d.ts.map +1 -0
- package/lib/orchestrator/experiment-preflight.js +21 -0
- package/lib/orchestrator/experiment-preflight.js.map +1 -0
- package/lib/orchestrator/experiment-report.d.ts +91 -1
- package/lib/orchestrator/experiment-report.d.ts.map +1 -1
- package/lib/orchestrator/experiment-report.js +9 -1
- package/lib/orchestrator/experiment-report.js.map +1 -1
- package/lib/orchestrator/experiment-runs.d.ts +63 -2
- package/lib/orchestrator/experiment-runs.d.ts.map +1 -1
- package/lib/orchestrator/experiment-runs.js +13 -5
- package/lib/orchestrator/experiment-runs.js.map +1 -1
- package/lib/orchestrator/experiment-runtime-identity.d.ts +0 -16
- package/lib/orchestrator/experiment-runtime-identity.d.ts.map +1 -1
- package/lib/orchestrator/experiment-runtime-identity.js +5 -220
- package/lib/orchestrator/experiment-runtime-identity.js.map +1 -1
- package/lib/orchestrator/experiment-selection.d.ts.map +1 -1
- package/lib/orchestrator/experiment-selection.js +151 -43
- package/lib/orchestrator/experiment-selection.js.map +1 -1
- package/lib/orchestrator/experiment.d.ts +3 -3
- package/lib/orchestrator/experiment.d.ts.map +1 -1
- package/lib/orchestrator/experiment.js +26 -21
- package/lib/orchestrator/experiment.js.map +1 -1
- package/lib/orchestrator/fixture-identity.d.ts +1 -0
- package/lib/orchestrator/fixture-identity.d.ts.map +1 -1
- package/lib/orchestrator/fixture-identity.js +6 -1
- package/lib/orchestrator/fixture-identity.js.map +1 -1
- package/lib/orchestrator/fs-read.d.ts +1 -6
- package/lib/orchestrator/fs-read.d.ts.map +1 -1
- package/lib/orchestrator/fs-read.js +2 -32
- package/lib/orchestrator/fs-read.js.map +1 -1
- package/lib/orchestrator/grader-experiment.d.ts +23 -5
- package/lib/orchestrator/grader-experiment.d.ts.map +1 -1
- package/lib/orchestrator/grader-experiment.js +54 -9
- package/lib/orchestrator/grader-experiment.js.map +1 -1
- package/lib/orchestrator/grading.d.ts +1 -0
- package/lib/orchestrator/grading.d.ts.map +1 -1
- package/lib/orchestrator/grading.js +41 -33
- package/lib/orchestrator/grading.js.map +1 -1
- package/lib/orchestrator/harness-catalog-drift.d.ts +22 -0
- package/lib/orchestrator/harness-catalog-drift.d.ts.map +1 -0
- package/lib/orchestrator/harness-catalog-drift.js +90 -0
- package/lib/orchestrator/harness-catalog-drift.js.map +1 -0
- package/lib/orchestrator/harness-registry.d.ts +4 -0
- package/lib/orchestrator/harness-registry.d.ts.map +1 -0
- package/lib/orchestrator/harness-registry.js +5 -0
- package/lib/orchestrator/harness-registry.js.map +1 -0
- package/lib/orchestrator/index.d.ts +1 -1
- package/lib/orchestrator/index.d.ts.map +1 -1
- package/lib/orchestrator/index.js +1 -1
- package/lib/orchestrator/index.js.map +1 -1
- package/lib/orchestrator/list-runs.d.ts +8 -1
- package/lib/orchestrator/list-runs.d.ts.map +1 -1
- package/lib/orchestrator/list-runs.js +83 -18
- package/lib/orchestrator/list-runs.js.map +1 -1
- package/lib/orchestrator/optimization-lifecycle.d.ts.map +1 -1
- package/lib/orchestrator/optimization-lifecycle.js +3 -1
- package/lib/orchestrator/optimization-lifecycle.js.map +1 -1
- package/lib/orchestrator/orchestrator.d.ts +17 -2
- package/lib/orchestrator/orchestrator.d.ts.map +1 -1
- package/lib/orchestrator/orchestrator.js +59 -179
- package/lib/orchestrator/orchestrator.js.map +1 -1
- package/lib/orchestrator/paired-effects.d.ts +34 -0
- package/lib/orchestrator/paired-effects.d.ts.map +1 -0
- package/lib/orchestrator/paired-effects.js +164 -0
- package/lib/orchestrator/paired-effects.js.map +1 -0
- package/lib/orchestrator/profile.d.ts +4 -0
- package/lib/orchestrator/profile.d.ts.map +1 -0
- package/lib/orchestrator/profile.js +10 -0
- package/lib/orchestrator/profile.js.map +1 -0
- package/lib/orchestrator/provenance.d.ts +5 -1
- package/lib/orchestrator/provenance.d.ts.map +1 -1
- package/lib/orchestrator/provenance.js +16 -3
- package/lib/orchestrator/provenance.js.map +1 -1
- package/lib/orchestrator/regrade.d.ts +4 -2
- package/lib/orchestrator/regrade.d.ts.map +1 -1
- package/lib/orchestrator/regrade.js +5 -1
- package/lib/orchestrator/regrade.js.map +1 -1
- package/lib/orchestrator/rubric-loader.js +1 -1
- package/lib/orchestrator/rubric-loader.js.map +1 -1
- package/lib/orchestrator/run-dir.d.ts +2 -0
- package/lib/orchestrator/run-dir.d.ts.map +1 -1
- package/lib/orchestrator/run-dir.js +1 -1
- package/lib/orchestrator/run-dir.js.map +1 -1
- package/lib/orchestrator/run-execution.d.ts +3 -0
- package/lib/orchestrator/run-execution.d.ts.map +1 -1
- package/lib/orchestrator/run-execution.js +64 -10
- package/lib/orchestrator/run-execution.js.map +1 -1
- package/lib/orchestrator/run-lifecycle.d.ts +1 -0
- package/lib/orchestrator/run-lifecycle.d.ts.map +1 -1
- package/lib/orchestrator/run-lifecycle.js +3 -2
- package/lib/orchestrator/run-lifecycle.js.map +1 -1
- package/lib/orchestrator/run-workspace.d.ts +10 -0
- package/lib/orchestrator/run-workspace.d.ts.map +1 -0
- package/lib/orchestrator/run-workspace.js +58 -0
- package/lib/orchestrator/run-workspace.js.map +1 -0
- package/lib/orchestrator/suite-compare.d.ts +37 -0
- package/lib/orchestrator/suite-compare.d.ts.map +1 -1
- package/lib/orchestrator/suite-compare.js +44 -22
- package/lib/orchestrator/suite-compare.js.map +1 -1
- package/lib/orchestrator/suite-runs.d.ts +6 -1
- package/lib/orchestrator/suite-runs.d.ts.map +1 -1
- package/lib/orchestrator/suite-runs.js +14 -2
- package/lib/orchestrator/suite-runs.js.map +1 -1
- package/lib/orchestrator/suite-summary.d.ts +79 -0
- package/lib/orchestrator/suite-summary.d.ts.map +1 -1
- package/lib/orchestrator/suite-summary.js +67 -14
- package/lib/orchestrator/suite-summary.js.map +1 -1
- package/lib/previewer/artifacts.d.ts +25 -0
- package/lib/previewer/artifacts.d.ts.map +1 -0
- package/lib/previewer/artifacts.js +180 -0
- package/lib/previewer/artifacts.js.map +1 -0
- package/lib/previewer/server.d.ts +111 -0
- package/lib/previewer/server.d.ts.map +1 -0
- package/lib/previewer/server.js +559 -0
- package/lib/previewer/server.js.map +1 -0
- package/package.json +4 -2
- package/skills/lux-answerer/SKILL.md +2 -2
- package/src/answerers/claude-code/index.ts +6 -5
- package/src/answerers/persona/index.ts +80 -34
- package/src/answerers/terminal/index.ts +7 -11
- package/src/assertions/authoring.ts +2 -0
- package/src/assertions/core/command-exits-zero.ts +82 -17
- package/src/assertions/core/event-checks.ts +64 -3
- package/src/assertions/core/index.ts +2 -0
- package/src/assertions/core/resource-checks.ts +38 -5
- package/src/assertions/core/safe-regex.ts +16 -6
- package/src/assertions/rubric/evidence.ts +85 -0
- package/src/assertions/rubric/index.ts +76 -46
- package/src/assertions/rubric/internal.ts +264 -46
- package/src/authoring.ts +346 -2
- package/src/cli/bin.ts +2 -12
- package/src/cli/command-runtime.ts +20 -9
- package/src/cli/doctor.ts +17 -0
- package/src/cli/harness-plan.ts +123 -0
- package/src/cli/init-templates.ts +176 -0
- package/src/cli/init.ts +53 -184
- package/src/cli/output-schemas.ts +109 -0
- package/src/cli/program.ts +697 -730
- package/src/cli/render/format.ts +1 -1
- package/src/cli/render/reporter.ts +36 -8
- package/src/cli/run-options.ts +131 -25
- package/src/cli/view.ts +129 -0
- package/src/container/driver.ts +213 -0
- package/src/container/paths.ts +29 -0
- package/src/container/protocol.ts +48 -0
- package/src/container/resources.ts +165 -0
- package/src/container/worker.ts +107 -0
- package/src/core/action-events.ts +59 -0
- package/src/core/agent-activity.ts +236 -0
- package/src/core/agent-environment.ts +64 -0
- package/src/core/agent-events.ts +17 -0
- package/src/core/annotation.ts +2 -1
- package/src/core/answerer.ts +9 -0
- package/src/core/artifact-evidence.ts +40 -5
- package/src/core/assertion.ts +8 -2
- package/src/core/case-defaults.ts +65 -0
- package/src/core/case.ts +79 -8
- package/src/core/command-verification.ts +74 -0
- package/src/core/driver-execution.ts +84 -0
- package/src/core/driver-metrics.ts +51 -0
- package/src/core/driver.ts +76 -0
- package/src/core/duration.ts +52 -0
- package/src/core/environment.ts +22 -0
- package/src/core/evaluation-clusters.ts +35 -0
- package/src/core/events.ts +13 -2
- package/src/core/experiment.ts +71 -25
- package/src/core/file-tree.ts +35 -0
- package/src/core/global-id.ts +26 -0
- package/src/core/harness-catalog.ts +100 -0
- package/src/core/harness-catalogs/antigravity.ts +24 -0
- package/src/core/harness-catalogs/claude-code.ts +25 -0
- package/src/core/harness-catalogs/codex.ts +27 -0
- package/src/core/harness-catalogs/copilot.ts +46 -0
- package/src/core/harness-catalogs/cursor.ts +13 -0
- package/src/core/harness-catalogs/grok-build.ts +19 -0
- package/src/core/harness-catalogs/index.ts +31 -0
- package/src/core/harness-matrix.ts +316 -0
- package/src/core/index.ts +12 -0
- package/src/core/lifecycle-fixtures.ts +4 -2
- package/src/core/model-cli.ts +78 -28
- package/src/core/platform-process.ts +65 -16
- package/src/core/reference-defaults.ts +47 -0
- package/src/core/run.ts +31 -0
- package/src/core/usage.ts +8 -0
- package/src/drivers/antigravity/README.md +171 -0
- package/src/drivers/antigravity/artifacts.ts +37 -0
- package/src/drivers/antigravity/config.ts +92 -0
- package/src/drivers/antigravity/events.ts +290 -0
- package/src/drivers/antigravity/index.ts +132 -0
- package/src/drivers/antigravity/runtime.ts +94 -0
- package/src/drivers/claude-code/deferred-process.ts +118 -0
- package/src/drivers/claude-code/index.ts +228 -282
- package/src/drivers/claude-code/isolation.ts +228 -0
- package/src/drivers/claude-code/parse-events.ts +98 -12
- package/src/drivers/codex/app-events.ts +126 -16
- package/src/drivers/codex/config.ts +59 -8
- package/src/drivers/codex/exec-events.ts +258 -0
- package/src/drivers/codex/index.ts +146 -312
- package/src/drivers/copilot/README.md +60 -0
- package/src/drivers/copilot/config.ts +61 -0
- package/src/drivers/copilot/index.ts +310 -0
- package/src/drivers/cursor/README.md +66 -0
- package/src/drivers/cursor/config.ts +31 -0
- package/src/drivers/cursor/index.ts +326 -0
- package/src/drivers/cursor/interaction.ts +74 -0
- package/src/drivers/grok-build/README.md +112 -0
- package/src/drivers/grok-build/config.ts +43 -0
- package/src/drivers/grok-build/index.ts +331 -0
- package/src/drivers/mcp/index.ts +25 -11
- package/src/drivers/shared/acp-events.ts +94 -0
- package/src/drivers/shared/acp-interaction.ts +27 -0
- package/src/drivers/shared/acp-session.ts +40 -0
- package/src/drivers/shared/acp-transport.ts +187 -0
- package/src/drivers/shared/artifacts.ts +6 -2
- package/src/drivers/shared/experiment-behavior.ts +217 -0
- package/src/drivers/shared/experiment-policy.ts +201 -0
- package/src/drivers/shared/skills.ts +74 -0
- package/src/drivers/subprocess/index.ts +55 -12
- package/src/index.ts +117 -6
- package/src/optimization/reflective.ts +3 -2
- package/src/orchestrator/annotation-loader.ts +10 -0
- package/src/orchestrator/annotation-store.ts +24 -3
- package/src/orchestrator/artifact-origin.ts +50 -0
- package/src/orchestrator/campaign-lifecycle.ts +5 -1
- package/src/orchestrator/candidates.ts +3 -2
- package/src/orchestrator/compare.ts +62 -13
- package/src/orchestrator/comparison-identity.ts +2 -0
- package/src/orchestrator/config.ts +23 -1
- package/src/orchestrator/discover.ts +8 -1
- package/src/orchestrator/doctor.ts +281 -74
- package/src/orchestrator/driver-capabilities.ts +21 -0
- package/src/orchestrator/driver-identity.ts +69 -0
- package/src/orchestrator/experiment-context.ts +5 -3
- package/src/orchestrator/experiment-corpus.ts +68 -39
- package/src/orchestrator/experiment-effects.ts +63 -0
- package/src/orchestrator/experiment-evaluation.ts +88 -10
- package/src/orchestrator/experiment-identity.ts +98 -61
- package/src/orchestrator/experiment-preflight.ts +27 -0
- package/src/orchestrator/experiment-report.ts +21 -1
- package/src/orchestrator/experiment-runs.ts +11 -4
- package/src/orchestrator/experiment-runtime-identity.ts +5 -243
- package/src/orchestrator/experiment-selection.ts +178 -18
- package/src/orchestrator/experiment.ts +29 -29
- package/src/orchestrator/fixture-identity.ts +9 -1
- package/src/orchestrator/fs-read.ts +2 -32
- package/src/orchestrator/grader-experiment.ts +74 -13
- package/src/orchestrator/grading.ts +60 -31
- package/src/orchestrator/harness-catalog-drift.ts +132 -0
- package/src/orchestrator/harness-registry.ts +12 -0
- package/src/orchestrator/index.ts +1 -0
- package/src/orchestrator/list-runs.ts +102 -18
- package/src/orchestrator/optimization-lifecycle.ts +4 -1
- package/src/orchestrator/orchestrator.ts +104 -226
- package/src/orchestrator/paired-effects.ts +214 -0
- package/src/orchestrator/profile.ts +24 -0
- package/src/orchestrator/provenance.ts +23 -3
- package/src/orchestrator/regrade.ts +5 -1
- package/src/orchestrator/rubric-loader.ts +1 -1
- package/src/orchestrator/run-dir.ts +8 -1
- package/src/orchestrator/run-execution.ts +75 -10
- package/src/orchestrator/run-lifecycle.ts +4 -2
- package/src/orchestrator/run-workspace.ts +62 -0
- package/src/orchestrator/suite-compare.ts +47 -23
- package/src/orchestrator/suite-runs.ts +13 -2
- package/src/orchestrator/suite-summary.ts +129 -15
- package/src/previewer/artifacts.ts +221 -0
- package/src/previewer/server.ts +789 -0
- package/viewer/app.css +2111 -0
- package/viewer/app.js +627 -0
- package/viewer/artifact-view.js +48 -0
- package/viewer/charts.js +98 -0
- package/viewer/detail.js +1266 -0
- package/viewer/format.js +129 -0
- package/viewer/index.html +151 -0
- package/lib/cli/skills.d.ts +0 -38
- package/lib/cli/skills.d.ts.map +0 -1
- package/lib/cli/skills.js +0 -84
- package/lib/cli/skills.js.map +0 -1
- package/lib/drivers/shared/secure-copy.d.ts.map +0 -1
- package/lib/drivers/shared/secure-copy.js.map +0 -1
- package/skills/lux/SKILL.md +0 -89
- package/skills/lux/references/cli.md +0 -125
- package/skills/lux/references/eval-authoring.md +0 -257
- package/src/cli/skills.ts +0 -129
- /package/lib/{drivers/shared → core}/secure-copy.d.ts +0 -0
- /package/lib/{drivers/shared → core}/secure-copy.js +0 -0
- /package/src/{drivers/shared → core}/secure-copy.ts +0 -0
|
@@ -2,6 +2,11 @@ import { existsSync } from "node:fs";
|
|
|
2
2
|
import { constants, lstat, open, readdir } from "node:fs/promises";
|
|
3
3
|
import { basename, join, relative, sep } from "node:path";
|
|
4
4
|
import {
|
|
5
|
+
ActionProgressPayloadSchema,
|
|
6
|
+
AgentCompletedPayloadSchema,
|
|
7
|
+
AgentSpawnPayloadSchema,
|
|
8
|
+
type Artifact,
|
|
9
|
+
ArtifactSchema,
|
|
5
10
|
type GradingReport,
|
|
6
11
|
GradingReportSchema,
|
|
7
12
|
harnessUsage,
|
|
@@ -15,6 +20,7 @@ import {
|
|
|
15
20
|
ToolResultPayloadSchema,
|
|
16
21
|
totalTokens,
|
|
17
22
|
} from "../core/index.js";
|
|
23
|
+
import { hasAgentUsage } from "../core/usage.js";
|
|
18
24
|
import { readBoundedHandle, safeReadJson, walkFiles } from "./fs-read.js";
|
|
19
25
|
import { MAX_RUN_TRACE_BYTES, MAX_RUN_TRACE_EVENTS } from "./trace-limits.js";
|
|
20
26
|
|
|
@@ -31,10 +37,16 @@ export type ListedRun = {
|
|
|
31
37
|
startedAt: string | null;
|
|
32
38
|
endedAt: string | null;
|
|
33
39
|
durationMs: number | null;
|
|
40
|
+
timeToFirstActionMs: number | null;
|
|
41
|
+
timeToFirstMutationMs: number | null;
|
|
42
|
+
timeToFirstDurableMutationMs: number | null;
|
|
43
|
+
driverMetrics: NonNullable<RunMetadata["driverMetrics"]>;
|
|
44
|
+
subagentCount: number;
|
|
34
45
|
casePassed: boolean | null;
|
|
35
46
|
caseScore: number | null;
|
|
36
47
|
assertionPassed: number;
|
|
37
48
|
assertionTotal: number;
|
|
49
|
+
readErrors?: string[];
|
|
38
50
|
};
|
|
39
51
|
|
|
40
52
|
const summarizeRun = async (
|
|
@@ -43,10 +55,19 @@ const summarizeRun = async (
|
|
|
43
55
|
ts: string,
|
|
44
56
|
runDir: string,
|
|
45
57
|
): Promise<ListedRun> => {
|
|
46
|
-
const [
|
|
58
|
+
const [metadataResult, gradingResult] = await Promise.allSettled([
|
|
47
59
|
safeReadJson(join(runDir, "run.json"), RunMetadataSchema),
|
|
48
60
|
safeReadJson(join(runDir, "grading.json"), GradingReportSchema),
|
|
49
61
|
]);
|
|
62
|
+
const readErrors = [metadataResult, gradingResult].flatMap((result) =>
|
|
63
|
+
result.status === "rejected"
|
|
64
|
+
? [result.reason instanceof Error ? result.reason.message : String(result.reason)]
|
|
65
|
+
: [],
|
|
66
|
+
);
|
|
67
|
+
const meta = metadataResult.status === "fulfilled" ? metadataResult.value : null;
|
|
68
|
+
// A valid grading file cannot establish a result when its run metadata is damaged.
|
|
69
|
+
const grading =
|
|
70
|
+
readErrors.length === 0 && gradingResult.status === "fulfilled" ? gradingResult.value : null;
|
|
50
71
|
const startedAt = meta?.startedAt ?? null;
|
|
51
72
|
const endedAt = meta?.endedAt ?? null;
|
|
52
73
|
const started = Date.parse(startedAt ?? "");
|
|
@@ -63,10 +84,17 @@ const summarizeRun = async (
|
|
|
63
84
|
startedAt,
|
|
64
85
|
endedAt,
|
|
65
86
|
durationMs,
|
|
87
|
+
timeToFirstActionMs: meta?.actionTiming?.timeToFirstActionMs ?? null,
|
|
88
|
+
timeToFirstMutationMs: meta?.actionTiming?.timeToFirstMutationMs ?? null,
|
|
89
|
+
timeToFirstDurableMutationMs: meta?.actionTiming?.timeToFirstDurableMutationMs ?? null,
|
|
90
|
+
driverMetrics: meta?.driverMetrics ?? {},
|
|
91
|
+
subagentCount:
|
|
92
|
+
meta?.agentActivity?.filter((activity) => activity.agent.role === "subagent").length ?? 0,
|
|
66
93
|
casePassed: grading?.casePassed ?? null,
|
|
67
94
|
caseScore: grading?.caseScore ?? null,
|
|
68
95
|
assertionPassed: passing,
|
|
69
|
-
assertionTotal: grading?.assertions.length ?? 0,
|
|
96
|
+
assertionTotal: grading?.assertions.filter((a) => a.passed !== null).length ?? 0,
|
|
97
|
+
...(readErrors.length > 0 ? { readErrors } : {}),
|
|
70
98
|
};
|
|
71
99
|
};
|
|
72
100
|
|
|
@@ -127,24 +155,26 @@ export const listRuns = async (runsRoot: string): Promise<ListedRun[]> => {
|
|
|
127
155
|
export const formatRunsTable = (runs: ListedRun[]): string => {
|
|
128
156
|
if (runs.length === 0) return "(no runs found)";
|
|
129
157
|
const rows: string[][] = [
|
|
130
|
-
["status", "case", "driver", "ts", "exit", "score", "duration"],
|
|
158
|
+
["status", "case", "driver", "agents", "ts", "exit", "score", "duration"],
|
|
131
159
|
...runs.map((r) => {
|
|
132
160
|
let status = "ungraded";
|
|
133
|
-
if (r.
|
|
161
|
+
if (r.readErrors?.length) status = "DAMAGED";
|
|
162
|
+
else if (r.casePassed === true) status = "PASS";
|
|
134
163
|
else if (r.casePassed === false) status = "FAIL";
|
|
135
164
|
const score =
|
|
136
|
-
r.caseScore !== null
|
|
137
|
-
? `${(r.caseScore * 100).toFixed(0)}% (${r.assertionPassed}/${r.assertionTotal})`
|
|
138
|
-
: "—";
|
|
165
|
+
r.caseScore !== null ? `${r.caseScore} (${r.assertionPassed}/${r.assertionTotal})` : "—";
|
|
139
166
|
const duration = r.durationMs !== null ? `${(r.durationMs / 1000).toFixed(1)}s` : "—";
|
|
140
|
-
|
|
167
|
+
const agents = r.subagentCount > 0 ? `1+${r.subagentCount}` : "1";
|
|
168
|
+
return [status, r.caseSlug, r.driverName, agents, r.ts, r.exitReason ?? "?", score, duration];
|
|
141
169
|
}),
|
|
142
170
|
];
|
|
143
171
|
const header = rows[0] ?? [];
|
|
144
172
|
const widths = header.map((_, col) => Math.max(...rows.map((r) => r[col]?.length ?? 0)));
|
|
145
|
-
|
|
173
|
+
const table = rows
|
|
146
174
|
.map((row) => row.map((cell, col) => cell.padEnd(widths[col] ?? 0)).join(" "))
|
|
147
175
|
.join("\n");
|
|
176
|
+
const diagnostics = runs.flatMap((run) => run.readErrors ?? []);
|
|
177
|
+
return diagnostics.length > 0 ? `${table}\n\n${diagnostics.join("\n")}` : table;
|
|
148
178
|
};
|
|
149
179
|
|
|
150
180
|
export type RunDetail = {
|
|
@@ -156,6 +186,9 @@ export type RunDetail = {
|
|
|
156
186
|
artifacts: string[];
|
|
157
187
|
};
|
|
158
188
|
|
|
189
|
+
export const loadRunArtifacts = async (runDir: string): Promise<Artifact[]> =>
|
|
190
|
+
(await safeReadJson(join(runDir, "artifacts.json"), ArtifactSchema.array())) ?? [];
|
|
191
|
+
|
|
159
192
|
const readEventsJsonl = async (path: string): Promise<RunEvent[]> => {
|
|
160
193
|
if (!existsSync(path)) return [];
|
|
161
194
|
if ((await lstat(path)).isSymbolicLink()) {
|
|
@@ -269,6 +302,12 @@ const appendMetadataDetail = (lines: string[], detail: RunDetail): void => {
|
|
|
269
302
|
}`,
|
|
270
303
|
);
|
|
271
304
|
}
|
|
305
|
+
const environment = provenance?.environment;
|
|
306
|
+
if (environment) {
|
|
307
|
+
lines.push(`concurrency: ${environment.concurrency}`);
|
|
308
|
+
if (environment.declared)
|
|
309
|
+
lines.push(`declared environment: ${JSON.stringify(environment.declared)}`);
|
|
310
|
+
}
|
|
272
311
|
const c = detail.metadata.interruptCounts;
|
|
273
312
|
lines.push(`interrupts: ask=${c.ask} approve=${c.approve} custom=${c.custom}`);
|
|
274
313
|
const tools = detail.metadata.toolOutcomes;
|
|
@@ -281,7 +320,7 @@ const appendMetadataDetail = (lines: string[], detail: RunDetail): void => {
|
|
|
281
320
|
}
|
|
282
321
|
const usage = detail.metadata.usage;
|
|
283
322
|
lines.push(
|
|
284
|
-
`tokens: agent=${totalTokens(usage.agent)} harness=${totalTokens(harnessUsage(usage))}` +
|
|
323
|
+
`tokens: agent=${hasAgentUsage(detail.metadata) ? totalTokens(usage.agent) : "unavailable"} harness=${totalTokens(harnessUsage(usage))}` +
|
|
285
324
|
` (answerer=${totalTokens(usage.answerer)} judge=${totalTokens(usage.grading)})`,
|
|
286
325
|
);
|
|
287
326
|
const phases = detail.metadata.phaseDurationMs;
|
|
@@ -291,6 +330,27 @@ const appendMetadataDetail = (lines: string[], detail: RunDetail): void => {
|
|
|
291
330
|
`phases: agent=${secs(phases.agent)} collect=${secs(phases.collect)} grading=${secs(phases.grading)}`,
|
|
292
331
|
);
|
|
293
332
|
}
|
|
333
|
+
const actions = detail.metadata.actionTiming;
|
|
334
|
+
if (actions) {
|
|
335
|
+
const value = (ms: number | undefined): string => (ms === undefined ? "—" : `${ms}ms`);
|
|
336
|
+
lines.push(
|
|
337
|
+
`first action: any=${value(actions.timeToFirstActionMs)} mutation=${value(actions.timeToFirstMutationMs)} durable-mutation=${value(actions.timeToFirstDurableMutationMs)}`,
|
|
338
|
+
);
|
|
339
|
+
}
|
|
340
|
+
const activities = detail.metadata.agentActivity ?? [];
|
|
341
|
+
const subagents = activities.filter((activity) => activity.agent.role === "subagent");
|
|
342
|
+
if (subagents.length > 0) {
|
|
343
|
+
lines.push(`subagents: ${subagents.length}`);
|
|
344
|
+
for (const activity of subagents) {
|
|
345
|
+
const label = activity.agent.name
|
|
346
|
+
? `${activity.agent.name} (${activity.agent.id})`
|
|
347
|
+
: activity.agent.id;
|
|
348
|
+
const agentActions = activity.actions;
|
|
349
|
+
lines.push(
|
|
350
|
+
` ${label}: ${activity.status}, ${(activity.durationMs / 1000).toFixed(1)}s, events=${activity.eventCount}, tokens=${totalTokens(activity.usage)}, tools=${activity.toolCalls.total} (${activity.toolCalls.succeeded} ok/${activity.toolCalls.failed} failed/${activity.toolCalls.unresolved} unresolved), actions=${agentActions.total}, mutations=${agentActions.mutations}`,
|
|
351
|
+
);
|
|
352
|
+
}
|
|
353
|
+
}
|
|
294
354
|
}
|
|
295
355
|
};
|
|
296
356
|
|
|
@@ -300,15 +360,19 @@ const appendGradingDetail = (lines: string[], detail: RunDetail): void => {
|
|
|
300
360
|
let status = "ungraded";
|
|
301
361
|
if (detail.grading.casePassed === true) status = "PASS";
|
|
302
362
|
else if (detail.grading.casePassed === false) status = "FAIL";
|
|
303
|
-
const score =
|
|
304
|
-
detail.grading.caseScore !== null ? `${(detail.grading.caseScore * 100).toFixed(0)}%` : "—";
|
|
363
|
+
const score = detail.grading.caseScore !== null ? String(detail.grading.caseScore) : "—";
|
|
305
364
|
lines.push(
|
|
306
|
-
`grading: ${status} (${score}, ${detail.grading.assertions.filter((a) => a.passed).length}/${detail.grading.assertions.length})`,
|
|
365
|
+
`grading: ${status} (${score}, ${detail.grading.assertions.filter((a) => a.passed).length}/${detail.grading.assertions.filter((a) => a.passed !== null).length})`,
|
|
307
366
|
);
|
|
308
367
|
for (const a of detail.grading.assertions) {
|
|
309
|
-
|
|
368
|
+
let mark = a.passed ? "✓" : "✗";
|
|
369
|
+
if (a.passed === null) mark = "ℹ informational";
|
|
370
|
+
if (a.abstention) mark = "?";
|
|
310
371
|
const took = ` (${(a.durationMs / 1000).toFixed(1)}s)`;
|
|
311
|
-
|
|
372
|
+
const abstention = a.abstention ? " — insufficient evidence" : "";
|
|
373
|
+
lines.push(
|
|
374
|
+
` ${mark} ${a.name} [score ${a.errorMessage !== undefined || a.abstention ? "unavailable" : a.score}]${took}${abstention}${a.comment ? ` — ${a.comment}` : ""}`,
|
|
375
|
+
);
|
|
312
376
|
}
|
|
313
377
|
}
|
|
314
378
|
};
|
|
@@ -361,17 +425,37 @@ const formatEventLine = (event: RunEvent): string => {
|
|
|
361
425
|
}`;
|
|
362
426
|
}
|
|
363
427
|
return `responded(custom): ${JSON.stringify(event.payload).slice(0, 80)}`;
|
|
364
|
-
case "progress":
|
|
428
|
+
case "progress": {
|
|
429
|
+
const agent = event.agent?.role === "subagent" ? ` [subagent ${event.agent.id}]` : "";
|
|
430
|
+
if (event.kind === "agent-spawn") {
|
|
431
|
+
const payload = AgentSpawnPayloadSchema.safeParse(event.payload).data;
|
|
432
|
+
return payload
|
|
433
|
+
? `agent-spawn: ${payload.agent.name ?? payload.agent.id} (${payload.agent.id})`
|
|
434
|
+
: "agent-spawn: malformed";
|
|
435
|
+
}
|
|
436
|
+
if (event.kind === "agent-completed") {
|
|
437
|
+
const payload = AgentCompletedPayloadSchema.safeParse(event.payload).data;
|
|
438
|
+
return payload
|
|
439
|
+
? `agent-completed: ${payload.agentId} (${payload.status})`
|
|
440
|
+
: "agent-completed: malformed";
|
|
441
|
+
}
|
|
442
|
+
if (event.kind === "action") {
|
|
443
|
+
const payload = ActionProgressPayloadSchema.safeParse(event.payload).data;
|
|
444
|
+
return payload
|
|
445
|
+
? `action${agent}: ${payload.name} (${payload.category})`
|
|
446
|
+
: "action: malformed";
|
|
447
|
+
}
|
|
365
448
|
if (event.kind === "tool-call") {
|
|
366
449
|
const payload = ToolCallPayloadSchema.safeParse(event.payload).data;
|
|
367
|
-
return payload ? `tool-call: ${payload.name}` : "tool-call: malformed";
|
|
450
|
+
return payload ? `tool-call${agent}: ${payload.name}` : "tool-call: malformed";
|
|
368
451
|
}
|
|
369
452
|
if (event.kind === "tool-result") {
|
|
370
453
|
const payload = ToolResultPayloadSchema.safeParse(event.payload).data;
|
|
371
454
|
if (!payload) return "tool-result: malformed";
|
|
372
|
-
return `tool-result: ${payload.name} (${payload.isError ? "failed" : "succeeded"})`;
|
|
455
|
+
return `tool-result${agent}: ${payload.name} (${payload.isError ? "failed" : "succeeded"})`;
|
|
373
456
|
}
|
|
374
457
|
return `progress(${event.kind})`;
|
|
458
|
+
}
|
|
375
459
|
case "lifecycle":
|
|
376
460
|
return `lifecycle: ${event.stage}`;
|
|
377
461
|
case "ready":
|
|
@@ -26,6 +26,7 @@ export const executeOptimizationLifecycle = async <Search, Deployment, Result>(
|
|
|
26
26
|
deployment: Deployment | undefined;
|
|
27
27
|
result: Result | undefined;
|
|
28
28
|
error: unknown;
|
|
29
|
+
failed: boolean;
|
|
29
30
|
};
|
|
30
31
|
|
|
31
32
|
const machine = setup({
|
|
@@ -59,6 +60,7 @@ export const executeOptimizationLifecycle = async <Search, Deployment, Result>(
|
|
|
59
60
|
result: ({ event }) => ("output" in event ? event.output : undefined),
|
|
60
61
|
}),
|
|
61
62
|
captureError: assign({
|
|
63
|
+
failed: true,
|
|
62
64
|
error: ({ event }) =>
|
|
63
65
|
"error" in event ? event.error : new Error("optimization lifecycle failed"),
|
|
64
66
|
}),
|
|
@@ -70,6 +72,7 @@ export const executeOptimizationLifecycle = async <Search, Deployment, Result>(
|
|
|
70
72
|
deployment: undefined,
|
|
71
73
|
result: undefined,
|
|
72
74
|
error: undefined,
|
|
75
|
+
failed: false,
|
|
73
76
|
},
|
|
74
77
|
initial: "evaluatingSearchSeeds",
|
|
75
78
|
states: {
|
|
@@ -112,7 +115,7 @@ export const executeOptimizationLifecycle = async <Search, Deployment, Result>(
|
|
|
112
115
|
failed: { type: "final" },
|
|
113
116
|
},
|
|
114
117
|
output: ({ context }) =>
|
|
115
|
-
context.
|
|
118
|
+
!context.failed
|
|
116
119
|
? { status: "succeeded", result: context.result }
|
|
117
120
|
: { status: "failed", error: context.error },
|
|
118
121
|
});
|