@rpamis/comet 0.4.0-beta.3 → 0.4.0-beta.5
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/LICENSE +21 -21
- package/README.md +15 -1
- package/assets/manifest.json +2 -1
- package/assets/skills/comet/SKILL.md +54 -28
- package/assets/skills/comet/reference/auto-transition.md +1 -1
- package/assets/skills/comet/reference/comet-yaml-fields.md +11 -6
- package/assets/skills/comet/reference/context-recovery.md +12 -2
- package/assets/skills/comet/reference/decision-point.md +11 -0
- package/assets/skills/comet/reference/scripts.md +47 -15
- package/assets/skills/comet/reference/subagent-dispatch.md +6 -5
- package/assets/skills/comet/rules/comet-phase-guard.en.md +31 -28
- package/assets/skills/comet/rules/comet-phase-guard.md +31 -29
- package/assets/skills/comet/scripts/comet-resume-probe.mjs +3 -0
- package/assets/skills/comet/scripts/comet-runtime.mjs +1568 -476
- package/assets/skills/comet-any/SKILL.md +1 -1
- package/assets/skills/comet-any/reference/authored-zone-example.md +10 -5
- package/assets/skills/comet-any/reference/subagents/pause-points-author.md +14 -11
- package/assets/skills/comet-any/reference/subagents/skill-reviewer.md +2 -0
- package/assets/skills/comet-any/reference/subagents/workflow-entry-author.md +5 -4
- package/assets/skills/comet-archive/SKILL.md +52 -18
- package/assets/skills/comet-build/SKILL.md +64 -45
- package/assets/skills/comet-design/SKILL.md +24 -22
- package/assets/skills/comet-hotfix/SKILL.md +37 -34
- package/assets/skills/comet-open/SKILL.md +106 -57
- package/assets/skills/comet-tweak/SKILL.md +23 -18
- package/assets/skills/comet-verify/SKILL.md +57 -72
- package/assets/skills-zh/comet/SKILL.md +54 -28
- package/assets/skills-zh/comet/reference/auto-transition.md +1 -1
- package/assets/skills-zh/comet/reference/comet-yaml-fields.md +11 -6
- package/assets/skills-zh/comet/reference/context-recovery.md +12 -2
- package/assets/skills-zh/comet/reference/decision-point.md +11 -0
- package/assets/skills-zh/comet/reference/scripts.md +47 -15
- package/assets/skills-zh/comet/reference/subagent-dispatch.md +6 -5
- package/assets/skills-zh/comet-any/SKILL.md +1 -1
- package/assets/skills-zh/comet-any/reference/authored-zone-example.md +10 -5
- package/assets/skills-zh/comet-any/reference/subagents/pause-points-author.md +14 -12
- package/assets/skills-zh/comet-any/reference/subagents/skill-reviewer.md +2 -0
- package/assets/skills-zh/comet-any/reference/subagents/workflow-entry-author.md +5 -4
- package/assets/skills-zh/comet-archive/SKILL.md +52 -18
- package/assets/skills-zh/comet-build/SKILL.md +64 -45
- package/assets/skills-zh/comet-design/SKILL.md +24 -22
- package/assets/skills-zh/comet-hotfix/SKILL.md +36 -33
- package/assets/skills-zh/comet-open/SKILL.md +105 -56
- package/assets/skills-zh/comet-tweak/SKILL.md +22 -17
- package/assets/skills-zh/comet-verify/SKILL.md +57 -72
- package/dist/app/cli/comet-banner.d.ts +25 -0
- package/dist/app/cli/comet-banner.d.ts.map +1 -0
- package/dist/app/cli/comet-banner.js +265 -0
- package/dist/app/cli/comet-banner.js.map +1 -0
- package/dist/app/cli/index.js +36 -2
- package/dist/app/cli/index.js.map +1 -1
- package/dist/app/commands/classic.d.ts +4 -0
- package/dist/app/commands/classic.d.ts.map +1 -0
- package/dist/app/commands/classic.js +11 -0
- package/dist/app/commands/classic.js.map +1 -0
- package/dist/app/commands/doctor.d.ts.map +1 -1
- package/dist/app/commands/doctor.js +99 -37
- package/dist/app/commands/doctor.js.map +1 -1
- package/dist/app/commands/eval.d.ts.map +1 -1
- package/dist/app/commands/eval.js +57 -20
- package/dist/app/commands/eval.js.map +1 -1
- package/dist/app/commands/i18n.d.ts +1 -1
- package/dist/app/commands/i18n.d.ts.map +1 -1
- package/dist/app/commands/i18n.js +12 -4
- package/dist/app/commands/i18n.js.map +1 -1
- package/dist/app/commands/init.d.ts +1 -1
- package/dist/app/commands/init.d.ts.map +1 -1
- package/dist/app/commands/init.js +72 -25
- package/dist/app/commands/init.js.map +1 -1
- package/dist/app/commands/project-scope-selection.d.ts +13 -0
- package/dist/app/commands/project-scope-selection.d.ts.map +1 -0
- package/dist/app/commands/project-scope-selection.js +33 -0
- package/dist/app/commands/project-scope-selection.js.map +1 -0
- package/dist/app/commands/resume-probe.d.ts +11 -0
- package/dist/app/commands/resume-probe.d.ts.map +1 -0
- package/dist/app/commands/resume-probe.js +63 -0
- package/dist/app/commands/resume-probe.js.map +1 -0
- package/dist/app/commands/status.d.ts +31 -0
- package/dist/app/commands/status.d.ts.map +1 -1
- package/dist/app/commands/status.js +109 -20
- package/dist/app/commands/status.js.map +1 -1
- package/dist/app/commands/uninstall.d.ts +5 -0
- package/dist/app/commands/uninstall.d.ts.map +1 -1
- package/dist/app/commands/uninstall.js +264 -53
- package/dist/app/commands/uninstall.js.map +1 -1
- package/dist/app/commands/update.d.ts +6 -0
- package/dist/app/commands/update.d.ts.map +1 -1
- package/dist/app/commands/update.js +558 -86
- package/dist/app/commands/update.js.map +1 -1
- package/dist/config/repository-layout.json +4 -2
- package/dist/domains/bundle/bundle-platform.d.ts +1 -0
- package/dist/domains/bundle/bundle-platform.d.ts.map +1 -1
- package/dist/domains/bundle/bundle-platform.js +9 -3
- package/dist/domains/bundle/bundle-platform.js.map +1 -1
- package/dist/domains/bundle/eval-manifest-runtime.d.ts +6 -0
- package/dist/domains/bundle/eval-manifest-runtime.d.ts.map +1 -0
- package/dist/domains/bundle/eval-manifest-runtime.js +58 -0
- package/dist/domains/bundle/eval-manifest-runtime.js.map +1 -0
- package/dist/domains/bundle/types.d.ts +1 -1
- package/dist/domains/bundle/types.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-archive.d.ts +1 -0
- package/dist/domains/comet-classic/classic-archive.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-archive.js +35 -38
- package/dist/domains/comet-classic/classic-archive.js.map +1 -1
- package/dist/domains/comet-classic/classic-cli.d.ts +1 -1
- package/dist/domains/comet-classic/classic-cli.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-cli.js +3 -0
- package/dist/domains/comet-classic/classic-cli.js.map +1 -1
- package/dist/domains/comet-classic/classic-command-checks.d.ts +20 -0
- package/dist/domains/comet-classic/classic-command-checks.d.ts.map +1 -0
- package/dist/domains/comet-classic/classic-command-checks.js +97 -0
- package/dist/domains/comet-classic/classic-command-checks.js.map +1 -0
- package/dist/domains/comet-classic/classic-current-change.d.ts +19 -0
- package/dist/domains/comet-classic/classic-current-change.d.ts.map +1 -0
- package/dist/domains/comet-classic/classic-current-change.js +132 -0
- package/dist/domains/comet-classic/classic-current-change.js.map +1 -0
- package/dist/domains/comet-classic/classic-diagnostics.d.ts +2 -1
- package/dist/domains/comet-classic/classic-diagnostics.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-diagnostics.js +54 -1
- package/dist/domains/comet-classic/classic-diagnostics.js.map +1 -1
- package/dist/domains/comet-classic/classic-evidence.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-evidence.js +4 -0
- package/dist/domains/comet-classic/classic-evidence.js.map +1 -1
- package/dist/domains/comet-classic/classic-guard.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-guard.js +83 -80
- package/dist/domains/comet-classic/classic-guard.js.map +1 -1
- package/dist/domains/comet-classic/classic-hook-guard.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-hook-guard.js +179 -42
- package/dist/domains/comet-classic/classic-hook-guard.js.map +1 -1
- package/dist/domains/comet-classic/classic-project-config.d.ts +16 -0
- package/dist/domains/comet-classic/classic-project-config.d.ts.map +1 -0
- package/dist/domains/comet-classic/classic-project-config.js +40 -0
- package/dist/domains/comet-classic/classic-project-config.js.map +1 -0
- package/dist/domains/comet-classic/classic-resolver.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-resolver.js +4 -4
- package/dist/domains/comet-classic/classic-resolver.js.map +1 -1
- package/dist/domains/comet-classic/classic-resume-probe-command.d.ts +3 -0
- package/dist/domains/comet-classic/classic-resume-probe-command.d.ts.map +1 -0
- package/dist/domains/comet-classic/classic-resume-probe-command.js +58 -0
- package/dist/domains/comet-classic/classic-resume-probe-command.js.map +1 -0
- package/dist/domains/comet-classic/classic-resume-probe-entry.d.ts +2 -0
- package/dist/domains/comet-classic/classic-resume-probe-entry.d.ts.map +1 -0
- package/dist/domains/comet-classic/classic-resume-probe-entry.js +4 -0
- package/dist/domains/comet-classic/classic-resume-probe-entry.js.map +1 -0
- package/dist/domains/comet-classic/classic-resume-probe.d.ts +29 -0
- package/dist/domains/comet-classic/classic-resume-probe.d.ts.map +1 -0
- package/dist/domains/comet-classic/classic-resume-probe.js +386 -0
- package/dist/domains/comet-classic/classic-resume-probe.js.map +1 -0
- package/dist/domains/comet-classic/classic-runtime-run.d.ts +2 -1
- package/dist/domains/comet-classic/classic-runtime-run.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-runtime-run.js +38 -0
- package/dist/domains/comet-classic/classic-runtime-run.js.map +1 -1
- package/dist/domains/comet-classic/classic-state-command.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-state-command.js +150 -25
- package/dist/domains/comet-classic/classic-state-command.js.map +1 -1
- package/dist/domains/comet-classic/classic-state.d.ts +5 -2
- package/dist/domains/comet-classic/classic-state.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-state.js +17 -1
- package/dist/domains/comet-classic/classic-state.js.map +1 -1
- package/dist/domains/comet-classic/classic-store.d.ts +4 -1
- package/dist/domains/comet-classic/classic-store.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-store.js +4 -3
- package/dist/domains/comet-classic/classic-store.js.map +1 -1
- package/dist/domains/comet-classic/classic-transitions.d.ts +1 -1
- package/dist/domains/comet-classic/classic-transitions.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-transitions.js +36 -3
- package/dist/domains/comet-classic/classic-transitions.js.map +1 -1
- package/dist/domains/comet-classic/classic-validate-command.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-validate-command.js +8 -1
- package/dist/domains/comet-classic/classic-validate-command.js.map +1 -1
- package/dist/domains/comet-classic/index.d.ts +3 -0
- package/dist/domains/comet-classic/index.d.ts.map +1 -1
- package/dist/domains/comet-classic/index.js +3 -0
- package/dist/domains/comet-classic/index.js.map +1 -1
- package/dist/domains/dashboard/collector.js +10 -2
- package/dist/domains/dashboard/collector.js.map +1 -1
- package/dist/domains/dashboard/web/assets/_commonjsHelpers-CqkleIqs.js +1 -0
- package/dist/domains/dashboard/web/assets/arc-TGVUG2WN.js +1 -0
- package/dist/domains/dashboard/web/assets/architectureDiagram-3BPJPVTR-ASHmiHoP.js +36 -0
- package/dist/domains/dashboard/web/assets/blockDiagram-GPEHLZMM-CwASxBKe.js +132 -0
- package/dist/domains/dashboard/web/assets/c4Diagram-AAUBKEIU-BU8z_WNk.js +10 -0
- package/dist/domains/dashboard/web/assets/channel-kp6Ng2JJ.js +1 -0
- package/dist/domains/dashboard/web/assets/chunk-2J33WTMH-CBGlUx4_.js +1 -0
- package/dist/domains/dashboard/web/assets/chunk-4BX2VUAB-CS-iGcFz.js +1 -0
- package/dist/domains/dashboard/web/assets/chunk-55IACEB6-BUtCVJat.js +1 -0
- package/dist/domains/dashboard/web/assets/chunk-727SXJPM-C94tj_pf.js +206 -0
- package/dist/domains/dashboard/web/assets/chunk-AQP2D5EJ-BFOKcpdG.js +231 -0
- package/dist/domains/dashboard/web/assets/chunk-FMBD7UC4-Dmx8B-st.js +15 -0
- package/dist/domains/dashboard/web/assets/chunk-ND2GUHAM-DYV00CNn.js +1 -0
- package/dist/domains/dashboard/web/assets/chunk-QZHKN3VN-DMJJyQnw.js +1 -0
- package/dist/domains/dashboard/web/assets/classDiagram-4FO5ZUOK-yBDjgMY_.js +1 -0
- package/dist/domains/dashboard/web/assets/classDiagram-v2-Q7XG4LA2-yBDjgMY_.js +1 -0
- package/dist/domains/dashboard/web/assets/cose-bilkent-S5V4N54A-P4nE2rea.js +1 -0
- package/dist/domains/dashboard/web/assets/cynefin-VYW2F7L2-C-R1HXDv.js +166 -0
- package/dist/domains/dashboard/web/assets/cytoscape.esm-D3_iZ_3b.js +321 -0
- package/dist/domains/dashboard/web/assets/dagre-BM42HDAG-BH8d-C9z.js +4 -0
- package/dist/domains/dashboard/web/assets/defaultLocale-DX6XiGOO.js +1 -0
- package/dist/domains/dashboard/web/assets/diagram-2AECGRRQ-DpXTgQIH.js +43 -0
- package/dist/domains/dashboard/web/assets/diagram-5GNKFQAL-DSiFJzSw.js +10 -0
- package/dist/domains/dashboard/web/assets/diagram-KO2AKTUF-DULMkben.js +3 -0
- package/dist/domains/dashboard/web/assets/diagram-LMA3HP47-Pi8m_NO9.js +24 -0
- package/dist/domains/dashboard/web/assets/diagram-OG6HWLK6-BSe6bCWm.js +24 -0
- package/dist/domains/dashboard/web/assets/erDiagram-TEJ5UH35-zb-FEcbq.js +85 -0
- package/dist/domains/dashboard/web/assets/flowDiagram-I6XJVG4X-Dr-Gk0z2.js +162 -0
- package/dist/domains/dashboard/web/assets/ganttDiagram-6RSMTGT7-qs6Zb2A6.js +292 -0
- package/dist/domains/dashboard/web/assets/gitGraphDiagram-PVQCEYII-BQ314orT.js +106 -0
- package/dist/domains/dashboard/web/assets/graph--OzhPTMs.js +1 -0
- package/dist/domains/dashboard/web/assets/index-BLAfkNTu.css +1 -0
- package/dist/domains/dashboard/web/assets/index-DlSYK56b.js +139 -0
- package/dist/domains/dashboard/web/assets/index-DtLUOcAW.js +24 -0
- package/dist/domains/dashboard/web/assets/index-QO0z6F4w.js +10 -0
- package/dist/domains/dashboard/web/assets/infoDiagram-5YYISTIA-O0bQp98A.js +2 -0
- package/dist/domains/dashboard/web/assets/init-Gi6I4Gst.js +1 -0
- package/dist/domains/dashboard/web/assets/ishikawaDiagram-YF4QCWOH-BPC7wbKh.js +70 -0
- package/dist/domains/dashboard/web/assets/journeyDiagram-JHISSGLW-ohViOd4b.js +139 -0
- package/dist/domains/dashboard/web/assets/kanban-definition-UN3LZRKU-CHleNdbG.js +89 -0
- package/dist/domains/dashboard/web/assets/katex-HP8lGamR.js +257 -0
- package/dist/domains/dashboard/web/assets/layout-SsrduOYp.js +1 -0
- package/dist/domains/dashboard/web/assets/linear-CyqiW--Q.js +1 -0
- package/dist/domains/dashboard/web/assets/marked.esm-DECB3bxB.js +64 -0
- package/dist/domains/dashboard/web/assets/mermaid.core-qS9XvtaK.js +301 -0
- package/dist/domains/dashboard/web/assets/mindmap-definition-RKZ34NQL-oaGkqO9l.js +96 -0
- package/dist/domains/dashboard/web/assets/ordinal-Cboi1Yqb.js +1 -0
- package/dist/domains/dashboard/web/assets/pieDiagram-4H26LBE5-CPcB-AFh.js +30 -0
- package/dist/domains/dashboard/web/assets/purify.es-VaSPOPhr.js +3 -0
- package/dist/domains/dashboard/web/assets/quadrantDiagram-W4KKPZXB-LFy52Qtj.js +7 -0
- package/dist/domains/dashboard/web/assets/requirementDiagram-4Y6WPE33-BdjeaYP_.js +84 -0
- package/dist/domains/dashboard/web/assets/sankeyDiagram-5OEKKPKP-DDJ4styL.js +40 -0
- package/dist/domains/dashboard/web/assets/sequenceDiagram-3UESZ5HK-BL5bFNoz.js +162 -0
- package/dist/domains/dashboard/web/assets/stateDiagram-AJRCARHV-BNUfikui.js +1 -0
- package/dist/domains/dashboard/web/assets/stateDiagram-v2-BHNVJYJU-DGrsmWts.js +1 -0
- package/dist/domains/dashboard/web/assets/timeline-definition-PNZ67QCA--ps2uu6L.js +120 -0
- package/dist/domains/dashboard/web/assets/vennDiagram-CIIHVFJN-C2q8q26c.js +34 -0
- package/dist/domains/dashboard/web/assets/wardleyDiagram-YWT4CUSO-BUH9gXqd.js +78 -0
- package/dist/domains/dashboard/web/assets/xychartDiagram-2RQKCTM6-B-DielEy.js +7 -0
- package/dist/domains/dashboard/web/index.html +16 -16
- package/dist/domains/engine/types.d.ts +1 -1
- package/dist/domains/engine/types.d.ts.map +1 -1
- package/dist/domains/factory/package.d.ts.map +1 -1
- package/dist/domains/factory/package.js +20 -6
- package/dist/domains/factory/package.js.map +1 -1
- package/dist/domains/integrations/openspec.d.ts +4 -1
- package/dist/domains/integrations/openspec.d.ts.map +1 -1
- package/dist/domains/integrations/openspec.js +62 -10
- package/dist/domains/integrations/openspec.js.map +1 -1
- package/dist/domains/skill/find.d.ts.map +1 -1
- package/dist/domains/skill/find.js +1 -6
- package/dist/domains/skill/find.js.map +1 -1
- package/dist/domains/skill/json-object.d.ts +13 -0
- package/dist/domains/skill/json-object.d.ts.map +1 -0
- package/dist/domains/skill/json-object.js +24 -0
- package/dist/domains/skill/json-object.js.map +1 -0
- package/dist/domains/skill/managed-markdown.d.ts +14 -0
- package/dist/domains/skill/managed-markdown.d.ts.map +1 -0
- package/dist/domains/skill/managed-markdown.js +126 -0
- package/dist/domains/skill/managed-markdown.js.map +1 -0
- package/dist/domains/skill/platform-inspect.d.ts +9 -0
- package/dist/domains/skill/platform-inspect.d.ts.map +1 -0
- package/dist/domains/skill/platform-inspect.js +149 -0
- package/dist/domains/skill/platform-inspect.js.map +1 -0
- package/dist/domains/skill/platform-install.d.ts +20 -9
- package/dist/domains/skill/platform-install.d.ts.map +1 -1
- package/dist/domains/skill/platform-install.js +356 -153
- package/dist/domains/skill/platform-install.js.map +1 -1
- package/dist/domains/skill/project-instructions.d.ts +22 -0
- package/dist/domains/skill/project-instructions.d.ts.map +1 -0
- package/dist/domains/skill/project-instructions.js +61 -0
- package/dist/domains/skill/project-instructions.js.map +1 -0
- package/dist/domains/skill/uninstall.d.ts +3 -1
- package/dist/domains/skill/uninstall.d.ts.map +1 -1
- package/dist/domains/skill/uninstall.js +259 -149
- package/dist/domains/skill/uninstall.js.map +1 -1
- package/dist/platform/fs/file-system.d.ts +3 -3
- package/dist/platform/fs/file-system.d.ts.map +1 -1
- package/dist/platform/fs/file-system.js +21 -11
- package/dist/platform/fs/file-system.js.map +1 -1
- package/dist/platform/install/detect.d.ts +2 -1
- package/dist/platform/install/detect.d.ts.map +1 -1
- package/dist/platform/install/detect.js +10 -1
- package/dist/platform/install/detect.js.map +1 -1
- package/dist/platform/install/platforms.d.ts +9 -1
- package/dist/platform/install/platforms.d.ts.map +1 -1
- package/dist/platform/install/platforms.js +23 -4
- package/dist/platform/install/platforms.js.map +1 -1
- package/dist/platform/install/project-registry.d.ts +38 -0
- package/dist/platform/install/project-registry.d.ts.map +1 -0
- package/dist/platform/install/project-registry.js +213 -0
- package/dist/platform/install/project-registry.js.map +1 -0
- package/dist/platform/install/skill-root-owner.d.ts +15 -0
- package/dist/platform/install/skill-root-owner.d.ts.map +1 -0
- package/dist/platform/install/skill-root-owner.js +68 -0
- package/dist/platform/install/skill-root-owner.js.map +1 -0
- package/eval/.env.example +52 -0
- package/eval/CLAUDE.md +43 -0
- package/eval/README.md +538 -0
- package/eval/langsmith/.env.example +16 -0
- package/eval/langsmith/README.md +93 -0
- package/eval/langsmith/skills/README.md +5 -0
- package/eval/langsmith/tasks/README.md +5 -0
- package/eval/langsmith/tests/conftest.py +187 -0
- package/eval/langsmith/tests/tasks/test_tasks.py +287 -0
- package/eval/langsmith/treatments/README.md +5 -0
- package/eval/local/README.md +80 -0
- package/eval/local/regression_baseline.json +13 -0
- package/eval/local/report-style-demo-assets/quality_cost.en.svg +41 -0
- package/eval/local/report-style-demo-assets/quality_cost.zh.svg +41 -0
- package/eval/local/report-style-demo-assets/rubric_delta.en.svg +56 -0
- package/eval/local/report-style-demo-assets/rubric_delta.zh.svg +56 -0
- package/eval/local/report-style-demo-assets/task_outcomes.en.svg +46 -0
- package/eval/local/report-style-demo-assets/task_outcomes.zh.svg +46 -0
- package/eval/local/report-style-demo.html +867 -0
- package/eval/local/scripts/compare_baselines.py +1018 -0
- package/eval/local/scripts/generate_report_style_demo_charts.py +322 -0
- package/eval/local/scripts/regression_check.py +171 -0
- package/eval/local/scripts/render_readme_benchmark_figures.py +416 -0
- package/eval/local/scripts/rescore_rubric.py +120 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/SKILL.md +282 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/auto-transition.md +27 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/comet-yaml-fields.md +68 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/context-recovery.md +35 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/debug-gate.md +17 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/decision-point.md +20 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/dirty-worktree.md +59 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/file-structure.md +28 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/reference/subagent-dispatch.md +113 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/rules/comet-phase-guard.md +125 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-archive.sh +311 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-env.sh +110 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-guard.sh +778 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-handoff.sh +390 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-hook-guard.sh +336 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-state.sh +1338 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039/scripts/comet-yaml-validate.sh +225 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039-archive/SKILL.md +100 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039-build/SKILL.md +304 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039-design/SKILL.md +263 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039-hotfix/SKILL.md +204 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039-open/SKILL.md +220 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039-tweak/SKILL.md +180 -0
- package/eval/local/skills/benchmarks/039-release/comet-classic-039-verify/SKILL.md +234 -0
- package/eval/local/skills/benchmarks/040-beta/comet/SKILL.md +261 -0
- package/eval/local/skills/benchmarks/040-beta/comet/reference/auto-transition.md +27 -0
- package/eval/local/skills/benchmarks/040-beta/comet/reference/comet-yaml-fields.md +73 -0
- package/eval/local/skills/benchmarks/040-beta/comet/reference/context-recovery.md +45 -0
- package/eval/local/skills/benchmarks/040-beta/comet/reference/debug-gate.md +33 -0
- package/eval/local/skills/benchmarks/040-beta/comet/reference/decision-point.md +31 -0
- package/eval/local/skills/benchmarks/040-beta/comet/reference/dirty-worktree.md +59 -0
- package/eval/local/skills/benchmarks/040-beta/comet/reference/file-structure.md +28 -0
- package/eval/local/skills/benchmarks/040-beta/comet/reference/intent-frame.md +74 -0
- package/eval/local/skills/benchmarks/040-beta/comet/reference/scripts.md +69 -0
- package/eval/local/skills/benchmarks/040-beta/comet/reference/subagent-dispatch.md +169 -0
- package/eval/local/skills/benchmarks/040-beta/comet/rules/comet-phase-guard.md +130 -0
- package/eval/local/skills/benchmarks/040-beta/comet/runtime/classic/checks.yaml +6 -0
- package/eval/local/skills/benchmarks/040-beta/comet/runtime/classic/guardrails.yaml +13 -0
- package/eval/local/skills/benchmarks/040-beta/comet/runtime/classic/skill.yaml +122 -0
- package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-archive.mjs +9515 -0
- package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-env.mjs +15 -0
- package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-guard.mjs +10173 -0
- package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-handoff.mjs +9491 -0
- package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-hook-guard.mjs +9175 -0
- package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-intent.mjs +404 -0
- package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-state.mjs +9273 -0
- package/eval/local/skills/benchmarks/040-beta/comet/scripts/comet-yaml-validate.mjs +7627 -0
- package/eval/local/skills/benchmarks/040-beta/comet-archive/SKILL.md +110 -0
- package/eval/local/skills/benchmarks/040-beta/comet-build/SKILL.md +315 -0
- package/eval/local/skills/benchmarks/040-beta/comet-design/SKILL.md +260 -0
- package/eval/local/skills/benchmarks/040-beta/comet-hotfix/SKILL.md +190 -0
- package/eval/local/skills/benchmarks/040-beta/comet-open/SKILL.md +210 -0
- package/eval/local/skills/benchmarks/040-beta/comet-tweak/SKILL.md +183 -0
- package/eval/local/skills/benchmarks/040-beta/comet-verify/SKILL.md +230 -0
- package/eval/local/skills/benchmarks/dependency/claude-md/comet-workflow/CLAUDE.md +12 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-apply-change/SKILL.md +156 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-archive-change/SKILL.md +114 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-bulk-archive-change/SKILL.md +246 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-continue-change/SKILL.md +118 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-explore/SKILL.md +288 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-ff-change/SKILL.md +101 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-new-change/SKILL.md +74 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-onboard/SKILL.md +554 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-propose/SKILL.md +110 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-sync-specs/SKILL.md +138 -0
- package/eval/local/skills/benchmarks/dependency/openspec/openspec-verify-change/SKILL.md +168 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/SKILL.md +159 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/scripts/frame-template.html +213 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/scripts/helper.js +167 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/scripts/server.cjs +723 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/scripts/start-server.sh +209 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/scripts/stop-server.sh +120 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/spec-document-reviewer-prompt.md +49 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/brainstorming/visual-companion.md +291 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/dispatching-parallel-agents/SKILL.md +185 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/executing-plans/SKILL.md +70 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/finishing-a-development-branch/SKILL.md +241 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/receiving-code-review/SKILL.md +213 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/requesting-code-review/SKILL.md +103 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/requesting-code-review/code-reviewer.md +172 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/SKILL.md +418 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/implementer-prompt.md +139 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/scripts/review-package +44 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/scripts/sdd-workspace +22 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/scripts/task-brief +40 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/subagent-driven-development/task-reviewer-prompt.md +188 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/CREATION-LOG.md +119 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/SKILL.md +296 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/condition-based-waiting-example.ts +158 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/condition-based-waiting.md +115 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/defense-in-depth.md +122 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/find-polluter.sh +63 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/root-cause-tracing.md +169 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/test-academic.md +14 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/test-pressure-1.md +58 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/test-pressure-2.md +68 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/systematic-debugging/test-pressure-3.md +69 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/test-driven-development/SKILL.md +371 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/test-driven-development/testing-anti-patterns.md +299 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/using-git-worktrees/SKILL.md +202 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/verification-before-completion/SKILL.md +139 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/writing-plans/SKILL.md +174 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/writing-plans/plan-document-reviewer-prompt.md +49 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/SKILL.md +689 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/anthropic-best-practices.md +1150 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/examples/CLAUDE_MD_TESTING.md +189 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/graphviz-conventions.dot +172 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/persuasion-principles.md +187 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/render-graphs.js +168 -0
- package/eval/local/skills/benchmarks/dependency/superpowers/writing-skills/testing-skills-with-subagents.md +384 -0
- package/eval/local/tasks/authoring-skill-smoke/environment/Dockerfile +2 -0
- package/eval/local/tasks/authoring-skill-smoke/instruction.md +4 -0
- package/eval/local/tasks/authoring-skill-smoke/task.toml +21 -0
- package/eval/local/tasks/authoring-skill-smoke/validation/test_authoring_skill_smoke.py +54 -0
- package/eval/local/tasks/comet-agent-memory-routing/environment/Dockerfile +28 -0
- package/eval/local/tasks/comet-agent-memory-routing/environment/agent_system.py +40 -0
- package/eval/local/tasks/comet-agent-memory-routing/environment/test_agent_system.py +29 -0
- package/eval/local/tasks/comet-agent-memory-routing/instruction.md +20 -0
- package/eval/local/tasks/comet-agent-memory-routing/task.toml +24 -0
- package/eval/local/tasks/comet-agent-memory-routing/validation/test_agent_memory_routing.py +24 -0
- package/eval/local/tasks/comet-api-cache-ttl/environment/Dockerfile +39 -0
- package/eval/local/tasks/comet-api-cache-ttl/environment/cache.py +39 -0
- package/eval/local/tasks/comet-api-cache-ttl/environment/test_cache.py +81 -0
- package/eval/local/tasks/comet-api-cache-ttl/instruction.md +33 -0
- package/eval/local/tasks/comet-api-cache-ttl/task.toml +24 -0
- package/eval/local/tasks/comet-api-cache-ttl/validation/test_api_cache_ttl.py +58 -0
- package/eval/local/tasks/comet-cross-file-refactor/environment/Dockerfile +15 -0
- package/eval/local/tasks/comet-cross-file-refactor/environment/cli.py +13 -0
- package/eval/local/tasks/comet-cross-file-refactor/environment/counting.py +13 -0
- package/eval/local/tasks/comet-cross-file-refactor/environment/test_textkit.py +21 -0
- package/eval/local/tasks/comet-cross-file-refactor/instruction.md +16 -0
- package/eval/local/tasks/comet-cross-file-refactor/task.toml +20 -0
- package/eval/local/tasks/comet-cross-file-refactor/validation/test_cross_file_refactor.py +20 -0
- package/eval/local/tasks/comet-dependency-confusion/environment/Dockerfile +28 -0
- package/eval/local/tasks/comet-dependency-confusion/environment/app.py +8 -0
- package/eval/local/tasks/comet-dependency-confusion/environment/settings_loader.py +14 -0
- package/eval/local/tasks/comet-dependency-confusion/environment/test_settings_service.py +19 -0
- package/eval/local/tasks/comet-dependency-confusion/instruction.md +18 -0
- package/eval/local/tasks/comet-dependency-confusion/task.toml +24 -0
- package/eval/local/tasks/comet-dependency-confusion/validation/test_dependency_confusion.py +24 -0
- package/eval/local/tasks/comet-fix-median/environment/Dockerfile +50 -0
- package/eval/local/tasks/comet-fix-median/environment/stats.py +54 -0
- package/eval/local/tasks/comet-fix-median/environment/test_stats.py +68 -0
- package/eval/local/tasks/comet-fix-median/instruction.md +25 -0
- package/eval/local/tasks/comet-fix-median/task.toml +24 -0
- package/eval/local/tasks/comet-fix-median/validation/test_fix_median.py +60 -0
- package/eval/local/tasks/comet-framework-selection/environment/Dockerfile +28 -0
- package/eval/local/tasks/comet-framework-selection/environment/architecture.py +12 -0
- package/eval/local/tasks/comet-framework-selection/environment/test_architecture.py +30 -0
- package/eval/local/tasks/comet-framework-selection/instruction.md +22 -0
- package/eval/local/tasks/comet-framework-selection/task.toml +24 -0
- package/eval/local/tasks/comet-framework-selection/validation/test_framework_selection.py +24 -0
- package/eval/local/tasks/comet-full-workflow/environment/Dockerfile +53 -0
- package/eval/local/tasks/comet-full-workflow/environment/test_wordcount.py +29 -0
- package/eval/local/tasks/comet-full-workflow/environment/wordcount.py +40 -0
- package/eval/local/tasks/comet-full-workflow/instruction.md +18 -0
- package/eval/local/tasks/comet-full-workflow/task.toml +24 -0
- package/eval/local/tasks/comet-full-workflow/validation/test_full_workflow.py +171 -0
- package/eval/local/tasks/comet-graph-execution-review/environment/Dockerfile +28 -0
- package/eval/local/tasks/comet-graph-execution-review/environment/pipeline.py +19 -0
- package/eval/local/tasks/comet-graph-execution-review/environment/test_pipeline.py +53 -0
- package/eval/local/tasks/comet-graph-execution-review/instruction.md +21 -0
- package/eval/local/tasks/comet-graph-execution-review/task.toml +24 -0
- package/eval/local/tasks/comet-graph-execution-review/validation/test_graph_execution_review.py +24 -0
- package/eval/local/tasks/comet-human-approval-flow/environment/Dockerfile +15 -0
- package/eval/local/tasks/comet-human-approval-flow/environment/approvals.py +17 -0
- package/eval/local/tasks/comet-human-approval-flow/environment/test_approvals.py +30 -0
- package/eval/local/tasks/comet-human-approval-flow/instruction.md +15 -0
- package/eval/local/tasks/comet-human-approval-flow/task.toml +20 -0
- package/eval/local/tasks/comet-human-approval-flow/validation/test_human_approval_flow.py +20 -0
- package/eval/local/tasks/comet-layered-streaming-fix/environment/Dockerfile +20 -0
- package/eval/local/tasks/comet-layered-streaming-fix/environment/chat_app.py +19 -0
- package/eval/local/tasks/comet-layered-streaming-fix/environment/test_chat_app.py +15 -0
- package/eval/local/tasks/comet-layered-streaming-fix/instruction.md +14 -0
- package/eval/local/tasks/comet-layered-streaming-fix/task.toml +20 -0
- package/eval/local/tasks/comet-layered-streaming-fix/validation/test_layered_streaming_fix.py +20 -0
- package/eval/local/tasks/comet-noise-distractor/environment/Dockerfile +15 -0
- package/eval/local/tasks/comet-noise-distractor/environment/distractor.md +4 -0
- package/eval/local/tasks/comet-noise-distractor/environment/invoice.py +5 -0
- package/eval/local/tasks/comet-noise-distractor/environment/test_invoice.py +18 -0
- package/eval/local/tasks/comet-noise-distractor/instruction.md +17 -0
- package/eval/local/tasks/comet-noise-distractor/task.toml +20 -0
- package/eval/local/tasks/comet-noise-distractor/validation/test_noise_distractor.py +20 -0
- package/eval/local/tasks/comet-observability-env-template/environment/Dockerfile +15 -0
- package/eval/local/tasks/comet-observability-env-template/environment/env_writer.py +17 -0
- package/eval/local/tasks/comet-observability-env-template/environment/test_env_writer.py +17 -0
- package/eval/local/tasks/comet-observability-env-template/instruction.md +20 -0
- package/eval/local/tasks/comet-observability-env-template/task.toml +20 -0
- package/eval/local/tasks/comet-observability-env-template/validation/test_observability_env_template.py +46 -0
- package/eval/local/tasks/comet-perf-dedupe/environment/Dockerfile +39 -0
- package/eval/local/tasks/comet-perf-dedupe/environment/dedupe.py +22 -0
- package/eval/local/tasks/comet-perf-dedupe/environment/test_dedupe.py +43 -0
- package/eval/local/tasks/comet-perf-dedupe/instruction.md +25 -0
- package/eval/local/tasks/comet-perf-dedupe/task.toml +24 -0
- package/eval/local/tasks/comet-perf-dedupe/validation/test_perf_dedupe.py +40 -0
- package/eval/local/tasks/comet-persistence-threading/environment/Dockerfile +15 -0
- package/eval/local/tasks/comet-persistence-threading/environment/session_store.py +15 -0
- package/eval/local/tasks/comet-persistence-threading/environment/test_session_store.py +21 -0
- package/eval/local/tasks/comet-persistence-threading/instruction.md +14 -0
- package/eval/local/tasks/comet-persistence-threading/task.toml +20 -0
- package/eval/local/tasks/comet-persistence-threading/validation/test_persistence_threading.py +20 -0
- package/eval/local/tasks/comet-refactor-counter/environment/Dockerfile +39 -0
- package/eval/local/tasks/comet-refactor-counter/environment/test_text_processor.py +57 -0
- package/eval/local/tasks/comet-refactor-counter/environment/text_processor.py +49 -0
- package/eval/local/tasks/comet-refactor-counter/instruction.md +31 -0
- package/eval/local/tasks/comet-refactor-counter/task.toml +24 -0
- package/eval/local/tasks/comet-refactor-counter/validation/test_refactor_counter.py +75 -0
- package/eval/local/tasks/comet-robust-config/environment/Dockerfile +39 -0
- package/eval/local/tasks/comet-robust-config/environment/config_loader.py +56 -0
- package/eval/local/tasks/comet-robust-config/environment/test_config_loader.py +72 -0
- package/eval/local/tasks/comet-robust-config/instruction.md +30 -0
- package/eval/local/tasks/comet-robust-config/task.toml +24 -0
- package/eval/local/tasks/comet-robust-config/validation/test_robust_config.py +37 -0
- package/eval/local/tasks/generic-skill-smoke/environment/Dockerfile +2 -0
- package/eval/local/tasks/generic-skill-smoke/instruction.md +7 -0
- package/eval/local/tasks/generic-skill-smoke/task.toml +21 -0
- package/eval/local/tasks/generic-skill-smoke/validation/test_generic_skill_smoke.py +36 -0
- package/eval/local/tasks/index.yaml +155 -0
- package/eval/local/tasks/workflow-overlay-contract/environment/Dockerfile +5 -0
- package/eval/local/tasks/workflow-overlay-contract/instruction.md +5 -0
- package/eval/local/tasks/workflow-overlay-contract/task.toml +21 -0
- package/eval/local/tasks/workflow-overlay-contract/validation/test_workflow_overlay_contract.py +235 -0
- package/eval/local/tasks/workflow-route-conformance/environment/Dockerfile +2 -0
- package/eval/local/tasks/workflow-route-conformance/instruction.md +5 -0
- package/eval/local/tasks/workflow-route-conformance/task.toml +21 -0
- package/eval/local/tasks/workflow-route-conformance/validation/test_workflow_route_conformance.py +84 -0
- package/eval/local/tests/conftest.py +1148 -0
- package/eval/local/tests/scaffold/test_attribution.py +48 -0
- package/eval/local/tests/scaffold/test_compare_baselines.py +999 -0
- package/eval/local/tests/scaffold/test_conftest_helpers.py +534 -0
- package/eval/local/tests/scaffold/test_evidence.py +15 -0
- package/eval/local/tests/scaffold/test_langsmith_conftest.py +244 -0
- package/eval/local/tests/scaffold/test_logging.py +243 -0
- package/eval/local/tests/scaffold/test_manifests.py +132 -0
- package/eval/local/tests/scaffold/test_profiles.py +866 -0
- package/eval/local/tests/scaffold/test_regression_check.py +19 -0
- package/eval/local/tests/scaffold/test_report_style_demo_charts.py +45 -0
- package/eval/local/tests/scaffold/test_sample_quality.py +211 -0
- package/eval/local/tests/scaffold/test_tasks.py +168 -0
- package/eval/local/tests/scaffold/test_treatments.py +244 -0
- package/eval/local/tests/scaffold/test_utils.py +139 -0
- package/eval/local/tests/tasks/test_tasks.py +445 -0
- package/eval/local/tests/tasks/test_validation_scripts.py +143 -0
- package/eval/local/treatments/comet/comet_full_039.yaml +141 -0
- package/eval/local/treatments/comet/comet_full_040_beta.yaml +140 -0
- package/eval/local/treatments/common/control.yaml +4 -0
- package/eval/pyproject.toml +41 -0
- package/eval/report-html-config.json +6 -0
- package/eval/scaffold/__init__.py +67 -0
- package/eval/scaffold/python/__init__.py +95 -0
- package/eval/scaffold/python/attribution.py +43 -0
- package/eval/scaffold/python/evidence.py +38 -0
- package/eval/scaffold/python/external_data_handler.py +18 -0
- package/eval/scaffold/python/generic_llm_judge.py +235 -0
- package/eval/scaffold/python/judge_config.py +168 -0
- package/eval/scaffold/python/llm_judge.py +191 -0
- package/eval/scaffold/python/logging.py +705 -0
- package/eval/scaffold/python/manifests.py +129 -0
- package/eval/scaffold/python/paper_charts.py +25 -0
- package/eval/scaffold/python/pass_at_k.py +107 -0
- package/eval/scaffold/python/paths.py +56 -0
- package/eval/scaffold/python/profiles.py +127 -0
- package/eval/scaffold/python/report_outputs.py +1391 -0
- package/eval/scaffold/python/sample_quality.py +339 -0
- package/eval/scaffold/python/schema.py +39 -0
- package/eval/scaffold/python/skill_parser.py +469 -0
- package/eval/scaffold/python/tasks.py +330 -0
- package/eval/scaffold/python/treatments.py +271 -0
- package/eval/scaffold/python/utils.py +366 -0
- package/eval/scaffold/python/validation/__init__.py +21 -0
- package/eval/scaffold/python/validation/authoring_rubric.py +326 -0
- package/eval/scaffold/python/validation/comet_workflow.py +187 -0
- package/eval/scaffold/python/validation/core.py +264 -0
- package/eval/scaffold/python/validation/dataset.py +337 -0
- package/eval/scaffold/python/validation/docker.py +106 -0
- package/eval/scaffold/python/validation/evaluator.py +549 -0
- package/eval/scaffold/python/validation/generic_rubric.py +169 -0
- package/eval/scaffold/python/validation/rubric.py +740 -0
- package/eval/scaffold/python/validation/runner.py +237 -0
- package/eval/scaffold/python/validation/scripts.py +58 -0
- package/eval/scaffold/python/validation/tracing.py +313 -0
- package/eval/scaffold/shell/common.sh +126 -0
- package/eval/scaffold/shell/docker.sh +482 -0
- package/eval/scaffold/shell/run-claude-loop.sh +181 -0
- package/eval/scaffold/shell/setup.sh +259 -0
- package/eval/simulator-instruction.md +9 -0
- package/package.json +29 -2
- package/dist/domains/dashboard/web/assets/index-BcO3_QlT.css +0 -1
- package/dist/domains/dashboard/web/assets/index-CjU3VXVu.js +0 -22
package/eval/local/tasks/workflow-overlay-contract/validation/test_workflow_overlay_contract.py
ADDED
|
@@ -0,0 +1,235 @@
|
|
|
1
|
+
import json
|
|
2
|
+
import re
|
|
3
|
+
from pathlib import Path
|
|
4
|
+
|
|
5
|
+
import yaml
|
|
6
|
+
|
|
7
|
+
from scaffold.python.validation.core import load_test_context, write_test_results
|
|
8
|
+
|
|
9
|
+
|
|
10
|
+
HASH_RE = re.compile(r"^[a-f0-9]{64}$")
|
|
11
|
+
|
|
12
|
+
|
|
13
|
+
def _package_root(context: dict) -> Path:
|
|
14
|
+
raw = context.get("skill_package_path")
|
|
15
|
+
if not raw:
|
|
16
|
+
return Path(".")
|
|
17
|
+
path = Path(raw)
|
|
18
|
+
return path if path.is_absolute() else Path(".") / path
|
|
19
|
+
|
|
20
|
+
|
|
21
|
+
def _contains_evidence(actual: list[dict], expected: dict) -> bool:
|
|
22
|
+
return any(
|
|
23
|
+
item.get("node") == expected.get("node")
|
|
24
|
+
and item.get("check") == expected.get("check")
|
|
25
|
+
and (
|
|
26
|
+
"enforcement" not in expected
|
|
27
|
+
or expected.get("enforcement") is None
|
|
28
|
+
or item.get("enforcement") == expected.get("enforcement")
|
|
29
|
+
)
|
|
30
|
+
for item in actual
|
|
31
|
+
if isinstance(item, dict)
|
|
32
|
+
)
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
def _read_required_text(
|
|
36
|
+
package: Path,
|
|
37
|
+
relative_path: str,
|
|
38
|
+
passed: list[str],
|
|
39
|
+
failed: list[str],
|
|
40
|
+
) -> str:
|
|
41
|
+
path = package / relative_path
|
|
42
|
+
if not path.exists():
|
|
43
|
+
failed.append(f"{relative_path} missing")
|
|
44
|
+
return ""
|
|
45
|
+
passed.append(f"{relative_path} present")
|
|
46
|
+
return path.read_text(encoding="utf-8")
|
|
47
|
+
|
|
48
|
+
|
|
49
|
+
def _require_markers(
|
|
50
|
+
text: str,
|
|
51
|
+
relative_path: str,
|
|
52
|
+
markers: list[tuple[str, str]],
|
|
53
|
+
passed: list[str],
|
|
54
|
+
failed: list[str],
|
|
55
|
+
) -> None:
|
|
56
|
+
if not text:
|
|
57
|
+
return
|
|
58
|
+
missing = [label for label, marker in markers if marker not in text]
|
|
59
|
+
if missing:
|
|
60
|
+
failed.append(f"{relative_path} missing contract markers: {', '.join(missing)}")
|
|
61
|
+
else:
|
|
62
|
+
passed.append(f"{relative_path} declares required contract markers")
|
|
63
|
+
|
|
64
|
+
|
|
65
|
+
def _check_workflow_protocol(package: Path, passed: list[str], failed: list[str]) -> None:
|
|
66
|
+
protocol_text = _read_required_text(package, "reference/workflow-protocol.json", passed, failed)
|
|
67
|
+
if not protocol_text:
|
|
68
|
+
return
|
|
69
|
+
try:
|
|
70
|
+
protocol = json.loads(protocol_text)
|
|
71
|
+
except json.JSONDecodeError as exc:
|
|
72
|
+
failed.append(f"reference/workflow-protocol.json invalid: {exc}")
|
|
73
|
+
return
|
|
74
|
+
|
|
75
|
+
if protocol.get("kind") == "comet-five-phase-overlay":
|
|
76
|
+
passed.append("workflow protocol kind is comet-five-phase-overlay")
|
|
77
|
+
else:
|
|
78
|
+
failed.append(
|
|
79
|
+
"workflow protocol kind mismatch: expected comet-five-phase-overlay, "
|
|
80
|
+
f"got {protocol.get('kind')}"
|
|
81
|
+
)
|
|
82
|
+
|
|
83
|
+
nodes = protocol.get("nodes")
|
|
84
|
+
if isinstance(nodes, list) and nodes:
|
|
85
|
+
passed.append(f"workflow protocol declares {len(nodes)} node(s)")
|
|
86
|
+
else:
|
|
87
|
+
failed.append("workflow protocol nodes missing or empty")
|
|
88
|
+
|
|
89
|
+
|
|
90
|
+
def _check_runtime_scripts(package: Path, passed: list[str], failed: list[str]) -> None:
|
|
91
|
+
state = _read_required_text(package, "scripts/workflow-state.mjs", passed, failed)
|
|
92
|
+
_require_markers(
|
|
93
|
+
state,
|
|
94
|
+
"scripts/workflow-state.mjs",
|
|
95
|
+
[
|
|
96
|
+
("activeCometChanges", "activeCometChanges"),
|
|
97
|
+
("resolveCometOverlayChange", "resolveCometOverlayChange"),
|
|
98
|
+
("sidecar workflow-evidence", "workflow-evidence"),
|
|
99
|
+
("overlay protocol branch", "isCometOverlay(protocol)"),
|
|
100
|
+
("init rejection branch", "command === 'init'"),
|
|
101
|
+
("/comet-open guidance", "/comet-open"),
|
|
102
|
+
],
|
|
103
|
+
passed,
|
|
104
|
+
failed,
|
|
105
|
+
)
|
|
106
|
+
|
|
107
|
+
guard = _read_required_text(package, "scripts/workflow-guard.mjs", passed, failed)
|
|
108
|
+
_require_markers(
|
|
109
|
+
guard,
|
|
110
|
+
"scripts/workflow-guard.mjs",
|
|
111
|
+
[
|
|
112
|
+
("overlay evidence reader", "readOverlayEvidence"),
|
|
113
|
+
("sidecar workflow-evidence", "workflow-evidence"),
|
|
114
|
+
("augmentation enforcement", "missing augmentation evidence"),
|
|
115
|
+
("unchanged Comet state message", "COMET STATE: unchanged"),
|
|
116
|
+
],
|
|
117
|
+
passed,
|
|
118
|
+
failed,
|
|
119
|
+
)
|
|
120
|
+
|
|
121
|
+
handoff = _read_required_text(package, "scripts/workflow-handoff.mjs", passed, failed)
|
|
122
|
+
_require_markers(
|
|
123
|
+
handoff,
|
|
124
|
+
"scripts/workflow-handoff.mjs",
|
|
125
|
+
[
|
|
126
|
+
("workflow protocol input", "workflow-protocol.json"),
|
|
127
|
+
("workflow output field", "workflow: protocol.name"),
|
|
128
|
+
("protocol nodes output", "protocol.nodes.map"),
|
|
129
|
+
("required skill calls", "requiredSkillCalls"),
|
|
130
|
+
("augmentations", "augmentations"),
|
|
131
|
+
("output schemas", "outputSchemas"),
|
|
132
|
+
],
|
|
133
|
+
passed,
|
|
134
|
+
failed,
|
|
135
|
+
)
|
|
136
|
+
|
|
137
|
+
|
|
138
|
+
def main():
|
|
139
|
+
context = load_test_context()
|
|
140
|
+
package = _package_root(context)
|
|
141
|
+
passed = []
|
|
142
|
+
failed = []
|
|
143
|
+
|
|
144
|
+
_check_workflow_protocol(package, passed, failed)
|
|
145
|
+
_check_runtime_scripts(package, passed, failed)
|
|
146
|
+
|
|
147
|
+
manifest_path = package / "comet" / "eval.yaml"
|
|
148
|
+
if not manifest_path.exists():
|
|
149
|
+
failed.append("comet/eval.yaml missing")
|
|
150
|
+
write_test_results({"passed": passed, "failed": failed})
|
|
151
|
+
return
|
|
152
|
+
|
|
153
|
+
try:
|
|
154
|
+
manifest = yaml.safe_load(manifest_path.read_text(encoding="utf-8")) or {}
|
|
155
|
+
passed.append("comet/eval.yaml parseable")
|
|
156
|
+
except yaml.YAMLError as exc:
|
|
157
|
+
failed.append(f"comet/eval.yaml invalid: {exc}")
|
|
158
|
+
write_test_results({"passed": passed, "failed": failed})
|
|
159
|
+
return
|
|
160
|
+
|
|
161
|
+
metadata = manifest.get("metadata") or {}
|
|
162
|
+
evaluation = manifest.get("evaluation") or {}
|
|
163
|
+
|
|
164
|
+
draft_hash = metadata.get("draftHash") or metadata.get("draft_hash")
|
|
165
|
+
expected_draft_hash = context.get("draft_hash")
|
|
166
|
+
if expected_draft_hash and draft_hash != expected_draft_hash:
|
|
167
|
+
failed.append("metadata.draftHash does not match manifest parser context")
|
|
168
|
+
elif isinstance(draft_hash, str) and HASH_RE.match(draft_hash):
|
|
169
|
+
passed.append("metadata.draftHash is stable sha256 hex")
|
|
170
|
+
else:
|
|
171
|
+
failed.append("metadata.draftHash missing or not 64 hex characters")
|
|
172
|
+
|
|
173
|
+
recommended = evaluation.get("recommendedTasks") or []
|
|
174
|
+
required_tasks = [
|
|
175
|
+
"workflow-overlay-contract",
|
|
176
|
+
"comet-full-workflow",
|
|
177
|
+
"comet-fix-median",
|
|
178
|
+
]
|
|
179
|
+
missing_tasks = [task for task in required_tasks if task not in recommended]
|
|
180
|
+
if missing_tasks:
|
|
181
|
+
failed.append(f"recommendedTasks missing: {', '.join(missing_tasks)}")
|
|
182
|
+
else:
|
|
183
|
+
passed.append("recommendedTasks includes overlay contract suite")
|
|
184
|
+
|
|
185
|
+
baseline_treatments = evaluation.get("baselineTreatments") or []
|
|
186
|
+
expected_baselines = context.get("baseline_treatments") or ["CONTROL", "COMET_FULL_040_BETA"]
|
|
187
|
+
if baseline_treatments == expected_baselines:
|
|
188
|
+
passed.append("baselineTreatments match expected overlay baselines")
|
|
189
|
+
else:
|
|
190
|
+
failed.append(
|
|
191
|
+
f"baselineTreatments mismatch: expected {expected_baselines}, got {baseline_treatments}"
|
|
192
|
+
)
|
|
193
|
+
|
|
194
|
+
gates = evaluation.get("qualityGates") or {}
|
|
195
|
+
expected_gates = context.get("quality_gates") or {
|
|
196
|
+
"minWeightedScore": 0.8,
|
|
197
|
+
"minPassAt1": 0.6,
|
|
198
|
+
"maxInstabilityGap": 0.4,
|
|
199
|
+
}
|
|
200
|
+
if all(gates.get(key) == value for key, value in expected_gates.items()):
|
|
201
|
+
passed.append("qualityGates declare required minimums")
|
|
202
|
+
else:
|
|
203
|
+
failed.append(f"qualityGates mismatch: expected {expected_gates}, got {gates}")
|
|
204
|
+
|
|
205
|
+
required_schemas = evaluation.get("requiredOutputSchemas") or []
|
|
206
|
+
expected_schemas = context.get("required_output_schemas") or []
|
|
207
|
+
missing_schemas = [schema for schema in expected_schemas if schema not in required_schemas]
|
|
208
|
+
if missing_schemas:
|
|
209
|
+
failed.append(f"requiredOutputSchemas missing: {', '.join(missing_schemas)}")
|
|
210
|
+
elif not required_schemas:
|
|
211
|
+
failed.append("requiredOutputSchemas empty")
|
|
212
|
+
elif isinstance(required_schemas, list):
|
|
213
|
+
passed.append("requiredOutputSchemas present")
|
|
214
|
+
else:
|
|
215
|
+
failed.append("requiredOutputSchemas is not a list")
|
|
216
|
+
|
|
217
|
+
expected_evidence = evaluation.get("expectedEvidence") or []
|
|
218
|
+
context_evidence = context.get("expected_evidence") or []
|
|
219
|
+
missing_evidence = [
|
|
220
|
+
item for item in context_evidence if not _contains_evidence(expected_evidence, item)
|
|
221
|
+
]
|
|
222
|
+
if missing_evidence:
|
|
223
|
+
failed.append(f"expectedEvidence missing checks: {missing_evidence}")
|
|
224
|
+
elif not expected_evidence:
|
|
225
|
+
failed.append("expectedEvidence empty")
|
|
226
|
+
elif isinstance(expected_evidence, list):
|
|
227
|
+
passed.append("expectedEvidence present")
|
|
228
|
+
else:
|
|
229
|
+
failed.append("expectedEvidence is not a list")
|
|
230
|
+
|
|
231
|
+
write_test_results({"passed": passed, "failed": failed})
|
|
232
|
+
|
|
233
|
+
|
|
234
|
+
if __name__ == "__main__":
|
|
235
|
+
main()
|
|
@@ -0,0 +1,5 @@
|
|
|
1
|
+
Inspect the generated Skill package available in this eval run.
|
|
2
|
+
|
|
3
|
+
Confirm that the generated workflow route recorded in `reference/workflow-protocol.json`
|
|
4
|
+
matches the route declared in `comet/eval.yaml`, and that every generated internal
|
|
5
|
+
Node Skill exists beside the entry Skill package.
|
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
[metadata]
|
|
2
|
+
name = "workflow-route-conformance"
|
|
3
|
+
description = "Validate generated Skill workflow route metadata."
|
|
4
|
+
difficulty = "easy"
|
|
5
|
+
category = "generic"
|
|
6
|
+
tags = ["authoring", "skill", "comet-any", "route"]
|
|
7
|
+
default_treatments = ["CONTROL"]
|
|
8
|
+
|
|
9
|
+
[environment]
|
|
10
|
+
description = "Workspace for generated Skill route inspection."
|
|
11
|
+
dockerfile = "environment/Dockerfile"
|
|
12
|
+
timeout_sec = 600
|
|
13
|
+
|
|
14
|
+
[validation]
|
|
15
|
+
test_scripts = ["test_workflow_route_conformance.py"]
|
|
16
|
+
target_artifacts = []
|
|
17
|
+
timeout = 60
|
|
18
|
+
|
|
19
|
+
[evaluation]
|
|
20
|
+
profile = "authoring-skill"
|
|
21
|
+
expected_artifacts = []
|
package/eval/local/tasks/workflow-route-conformance/validation/test_workflow_route_conformance.py
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
1
|
+
import json
|
|
2
|
+
from pathlib import Path
|
|
3
|
+
|
|
4
|
+
from scaffold.python.validation.core import load_test_context, write_test_results
|
|
5
|
+
|
|
6
|
+
|
|
7
|
+
def _package_root(context: dict) -> Path:
|
|
8
|
+
raw = context.get("skill_package_path")
|
|
9
|
+
if not raw:
|
|
10
|
+
return Path(".")
|
|
11
|
+
path = Path(raw)
|
|
12
|
+
return path if path.is_absolute() else Path(".") / path
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
def _protocol_route(protocol: dict) -> list[str]:
|
|
16
|
+
return [
|
|
17
|
+
str(node.get("id"))
|
|
18
|
+
for node in protocol.get("nodes") or []
|
|
19
|
+
if isinstance(node, dict) and node.get("id") and not node.get("disabled")
|
|
20
|
+
]
|
|
21
|
+
|
|
22
|
+
|
|
23
|
+
def main():
|
|
24
|
+
context = load_test_context()
|
|
25
|
+
package = _package_root(context)
|
|
26
|
+
expected_nodes = context.get("route_conformance_expected_node_order") or []
|
|
27
|
+
generated_node_skills = context.get("generated_node_skills") or []
|
|
28
|
+
passed = []
|
|
29
|
+
failed = []
|
|
30
|
+
|
|
31
|
+
if not expected_nodes:
|
|
32
|
+
failed.append("routeConformance expectedNodeOrder missing")
|
|
33
|
+
else:
|
|
34
|
+
passed.append(f"routeConformance declares {len(expected_nodes)} node(s)")
|
|
35
|
+
|
|
36
|
+
protocol_path = package / "reference" / "workflow-protocol.json"
|
|
37
|
+
if not protocol_path.exists():
|
|
38
|
+
failed.append("reference/workflow-protocol.json missing")
|
|
39
|
+
protocol_route = []
|
|
40
|
+
else:
|
|
41
|
+
try:
|
|
42
|
+
protocol_route = _protocol_route(json.loads(protocol_path.read_text(encoding="utf-8")))
|
|
43
|
+
passed.append("workflow-protocol.json parseable")
|
|
44
|
+
except json.JSONDecodeError as exc:
|
|
45
|
+
failed.append(f"workflow-protocol.json invalid: {exc}")
|
|
46
|
+
protocol_route = []
|
|
47
|
+
|
|
48
|
+
if expected_nodes and protocol_route == expected_nodes:
|
|
49
|
+
passed.append("workflow protocol route matches expectedNodeOrder")
|
|
50
|
+
elif expected_nodes:
|
|
51
|
+
failed.append(
|
|
52
|
+
f"workflow protocol route mismatch: expected {expected_nodes}, got {protocol_route}"
|
|
53
|
+
)
|
|
54
|
+
|
|
55
|
+
eval_manifest = package / "comet" / "eval.yaml"
|
|
56
|
+
if not eval_manifest.exists():
|
|
57
|
+
failed.append("comet/eval.yaml missing")
|
|
58
|
+
else:
|
|
59
|
+
text = eval_manifest.read_text(encoding="utf-8")
|
|
60
|
+
missing = [
|
|
61
|
+
item
|
|
62
|
+
for item in ["workflow-route-conformance", *expected_nodes, *generated_node_skills]
|
|
63
|
+
if item not in text
|
|
64
|
+
]
|
|
65
|
+
if missing:
|
|
66
|
+
failed.append(f"comet/eval.yaml missing route entries: {', '.join(missing)}")
|
|
67
|
+
else:
|
|
68
|
+
passed.append("comet/eval.yaml lists route conformance task and Nodes")
|
|
69
|
+
|
|
70
|
+
missing_node_skills = [
|
|
71
|
+
node_skill
|
|
72
|
+
for node_skill in generated_node_skills
|
|
73
|
+
if not (package.parent / node_skill / "SKILL.md").exists()
|
|
74
|
+
]
|
|
75
|
+
if missing_node_skills:
|
|
76
|
+
failed.append(f"internal Node Skill missing: {', '.join(missing_node_skills)}")
|
|
77
|
+
elif generated_node_skills:
|
|
78
|
+
passed.append("internal Node Skills present")
|
|
79
|
+
|
|
80
|
+
write_test_results({"passed": passed, "failed": failed})
|
|
81
|
+
|
|
82
|
+
|
|
83
|
+
if __name__ == "__main__":
|
|
84
|
+
main()
|