@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
|
@@ -0,0 +1,181 @@
|
|
|
1
|
+
#!/usr/bin/env bash
|
|
2
|
+
# Multi-turn claude driver for interactive workflow eval.
|
|
3
|
+
#
|
|
4
|
+
# Runs the primary (subject) claude with the task prompt, then when it pauses
|
|
5
|
+
# at a decision point (asks the user a question), drives a lightweight
|
|
6
|
+
# "user-simulator" turn to answer, feeding the answer back via --resume.
|
|
7
|
+
# Both calls share the same container HOME so session state persists.
|
|
8
|
+
#
|
|
9
|
+
# Usage: run-claude-loop.sh <prompt|@prompt-file> [--max-turns N] [--model MODEL]
|
|
10
|
+
# --max-turns N Maximum number of subject<->simulator round trips (default 12)
|
|
11
|
+
# --model MODEL Model for both subject and simulator
|
|
12
|
+
# --simulator-prompt-file File containing the simulator system prompt
|
|
13
|
+
# --continue-prompt TEXT Nudge used when the workflow should continue
|
|
14
|
+
# --decision-pattern TEXT Extra case-insensitive substring to treat as a decision point
|
|
15
|
+
#
|
|
16
|
+
# Env: ANTHROPIC_AUTH_TOKEN / ANTHROPIC_BASE_URL / ANTHROPIC_MODEL for the proxy.
|
|
17
|
+
# Stdout: concatenated stream-json from every subject turn (for event extraction).
|
|
18
|
+
# Stderr: driver progress log.
|
|
19
|
+
|
|
20
|
+
set -uo pipefail
|
|
21
|
+
|
|
22
|
+
PROMPT_ARG="${1:?usage: run-claude-loop.sh <prompt|@prompt-file> [--max-turns N]}"
|
|
23
|
+
shift || true
|
|
24
|
+
|
|
25
|
+
if [[ "$PROMPT_ARG" == @* ]]; then
|
|
26
|
+
PROMPT="$(cat "${PROMPT_ARG#@}")"
|
|
27
|
+
else
|
|
28
|
+
PROMPT="$PROMPT_ARG"
|
|
29
|
+
fi
|
|
30
|
+
|
|
31
|
+
MAX_TURNS=12
|
|
32
|
+
MODEL="${ANTHROPIC_MODEL:-}"
|
|
33
|
+
SIMULATOR_PROMPT=""
|
|
34
|
+
CONTINUE_PROMPT="Please continue with the next phase of the comet workflow."
|
|
35
|
+
DECISION_PATTERNS=()
|
|
36
|
+
PLUGIN_ARGS=()
|
|
37
|
+
while [[ $# -gt 0 ]]; do
|
|
38
|
+
case "$1" in
|
|
39
|
+
--max-turns) MAX_TURNS="$2"; shift 2 ;;
|
|
40
|
+
--model) MODEL="$2"; shift 2 ;;
|
|
41
|
+
--plugin-dir)
|
|
42
|
+
PLUGIN_ARGS+=(--plugin-dir "$2")
|
|
43
|
+
shift 2
|
|
44
|
+
;;
|
|
45
|
+
--simulator-prompt-file)
|
|
46
|
+
SIMULATOR_PROMPT="$(cat "$2")"
|
|
47
|
+
shift 2
|
|
48
|
+
;;
|
|
49
|
+
--continue-prompt) CONTINUE_PROMPT="$2"; shift 2 ;;
|
|
50
|
+
--decision-pattern)
|
|
51
|
+
DECISION_PATTERNS+=("$2")
|
|
52
|
+
shift 2
|
|
53
|
+
;;
|
|
54
|
+
*) shift ;;
|
|
55
|
+
esac
|
|
56
|
+
done
|
|
57
|
+
|
|
58
|
+
MODEL_FLAG=()
|
|
59
|
+
[[ -n "$MODEL" ]] && MODEL_FLAG=(--model "$MODEL")
|
|
60
|
+
|
|
61
|
+
# Detect whether the last subject turn is waiting on the user. comet decision
|
|
62
|
+
# points present as a question / confirmation request with no pending tool call.
|
|
63
|
+
is_decision_point() {
|
|
64
|
+
local text="$1"
|
|
65
|
+
local pattern
|
|
66
|
+
for pattern in "${DECISION_PATTERNS[@]}"; do
|
|
67
|
+
if [[ -n "$pattern" ]] && echo "$text" | grep -qiF -- "$pattern"; then
|
|
68
|
+
return 0
|
|
69
|
+
fi
|
|
70
|
+
done
|
|
71
|
+
# Heuristics: question marks, explicit "confirm/choose/proceed/continue" asks.
|
|
72
|
+
if echo "$text" | grep -qiE '\?|confirm|choose|proceed|continue|approve|select an option|which (option|approach|name)|enter the|provide|would you|shall we|do you want|preferred'; then
|
|
73
|
+
return 0
|
|
74
|
+
fi
|
|
75
|
+
return 1
|
|
76
|
+
}
|
|
77
|
+
|
|
78
|
+
# Drive the user-simulator: given the subject's last message, produce a concise
|
|
79
|
+
# affirmative/clarifying reply that lets the workflow proceed.
|
|
80
|
+
simulate_user() {
|
|
81
|
+
local subject_text="$1"
|
|
82
|
+
local sim_prompt
|
|
83
|
+
if [[ -n "$SIMULATOR_PROMPT" ]]; then
|
|
84
|
+
sim_prompt=$(cat <<EOF
|
|
85
|
+
${SIMULATOR_PROMPT}
|
|
86
|
+
|
|
87
|
+
Assistant's message:
|
|
88
|
+
"""
|
|
89
|
+
${subject_text:0:3000}
|
|
90
|
+
"""
|
|
91
|
+
EOF
|
|
92
|
+
)
|
|
93
|
+
else
|
|
94
|
+
sim_prompt=$(cat <<EOF
|
|
95
|
+
You are simulating a developer user in an automated eval. The AI assistant below is running the Comet development workflow and has paused to ask you something. Read its message and reply with a SHORT (1-3 sentences) response that:
|
|
96
|
+
- Approves the proposed approach / name / plan when asked to confirm
|
|
97
|
+
- Picks the most reasonable default option when asked to choose
|
|
98
|
+
- Asks for clarification only if the question is truly ambiguous about WHAT to build
|
|
99
|
+
Never refuse; always let the workflow move forward. Do not write code or files.
|
|
100
|
+
|
|
101
|
+
Assistant's message:
|
|
102
|
+
"""
|
|
103
|
+
${subject_text:0:3000}
|
|
104
|
+
"""
|
|
105
|
+
EOF
|
|
106
|
+
)
|
|
107
|
+
fi
|
|
108
|
+
# Run the simulator as a one-shot print call (separate session).
|
|
109
|
+
claude -p "$sim_prompt" "${MODEL_FLAG[@]}" --dangerously-skip-permissions 2>/dev/null
|
|
110
|
+
}
|
|
111
|
+
|
|
112
|
+
SESSION_ID=""
|
|
113
|
+
COMBINED_OUT=""
|
|
114
|
+
TURN=0
|
|
115
|
+
|
|
116
|
+
while [[ $TURN -lt $MAX_TURNS ]]; do
|
|
117
|
+
TURN=$((TURN + 1))
|
|
118
|
+
echo "[loop] turn $TURN/$MAX_TURNS" >&2
|
|
119
|
+
|
|
120
|
+
if [[ -z "$SESSION_ID" ]]; then
|
|
121
|
+
# First turn: start fresh with the task prompt.
|
|
122
|
+
RAW=$(claude -p "$PROMPT" "${PLUGIN_ARGS[@]}" "${MODEL_FLAG[@]}" \
|
|
123
|
+
--output-format stream-json --verbose \
|
|
124
|
+
--dangerously-skip-permissions 2>/dev/null) || RAW=""
|
|
125
|
+
else
|
|
126
|
+
# Subsequent turns: resume the session with the simulated user reply.
|
|
127
|
+
RAW=$(claude -p "$USER_REPLY" "${PLUGIN_ARGS[@]}" "${MODEL_FLAG[@]}" \
|
|
128
|
+
--resume "$SESSION_ID" \
|
|
129
|
+
--output-format stream-json --verbose \
|
|
130
|
+
--dangerously-skip-permissions 2>/dev/null) || RAW=""
|
|
131
|
+
fi
|
|
132
|
+
|
|
133
|
+
COMBINED_OUT="${COMBINED_OUT}${RAW}"$'\n'
|
|
134
|
+
|
|
135
|
+
# Extract session id and the final assistant text from this turn.
|
|
136
|
+
SESSION_ID=$(echo "$RAW" | grep -oE '"session_id":\s*"[^"]+"' | head -1 | sed -E 's/.*"session_id":\s*"([^"]+)".*/\1/') || true
|
|
137
|
+
|
|
138
|
+
# Pull the result text (type=result) for decision-point detection.
|
|
139
|
+
RESULT_TEXT=$(echo "$RAW" | grep '"type": *"result"' | tail -1 | python3 -c "import json,sys; print(json.loads(sys.stdin.read()).get('result',''))" 2>/dev/null || echo "")
|
|
140
|
+
# Fallback: last assistant text block.
|
|
141
|
+
if [[ -z "$RESULT_TEXT" ]]; then
|
|
142
|
+
RESULT_TEXT=$(echo "$RAW" | grep '"type": *"assistant"' | tail -1 | python3 -c "
|
|
143
|
+
import json,sys
|
|
144
|
+
try:
|
|
145
|
+
d=json.loads(sys.stdin.read())
|
|
146
|
+
c=d.get('message',{}).get('content',[])
|
|
147
|
+
print(' '.join(i.get('text','') for i in c if isinstance(i,dict) and i.get('type')=='text'))
|
|
148
|
+
except: print('')
|
|
149
|
+
" 2>/dev/null || echo "")
|
|
150
|
+
fi
|
|
151
|
+
|
|
152
|
+
if [[ -z "$RESULT_TEXT" ]]; then
|
|
153
|
+
echo "[loop] no result text; ending" >&2
|
|
154
|
+
break
|
|
155
|
+
fi
|
|
156
|
+
|
|
157
|
+
if is_decision_point "$RESULT_TEXT"; then
|
|
158
|
+
echo "[loop] decision point detected; simulating user reply" >&2
|
|
159
|
+
USER_REPLY=$(simulate_user "$RESULT_TEXT")
|
|
160
|
+
if [[ -z "$USER_REPLY" ]]; then
|
|
161
|
+
USER_REPLY="Yes, please proceed with the recommended option."
|
|
162
|
+
fi
|
|
163
|
+
echo "[loop] simulated reply (${#USER_REPLY} chars)" >&2
|
|
164
|
+
continue
|
|
165
|
+
fi
|
|
166
|
+
|
|
167
|
+
# Not a decision point: check if workflow looks complete.
|
|
168
|
+
if echo "$RESULT_TEXT" | grep -qiE 'archive(d)? complete|workflow complete|change archived|all (5|five) phases|finished|done'; then
|
|
169
|
+
echo "[loop] workflow appears complete; ending" >&2
|
|
170
|
+
break
|
|
171
|
+
fi
|
|
172
|
+
|
|
173
|
+
# If the result has no question and isn't complete, the subject likely finished
|
|
174
|
+
# its turn naturally — try one more nudge to keep going, then stop.
|
|
175
|
+
echo "[loop] no decision point and not complete; nudging to continue" >&2
|
|
176
|
+
USER_REPLY="$CONTINUE_PROMPT"
|
|
177
|
+
done
|
|
178
|
+
|
|
179
|
+
echo "[loop] finished after $TURN turns" >&2
|
|
180
|
+
# Emit the combined stream-json on stdout for the harness to parse.
|
|
181
|
+
printf '%s' "$COMBINED_OUT"
|
|
@@ -0,0 +1,259 @@
|
|
|
1
|
+
#!/usr/bin/env bash
|
|
2
|
+
# Test environment setup utilities
|
|
3
|
+
# Source this file or run directly
|
|
4
|
+
#
|
|
5
|
+
# Commands:
|
|
6
|
+
# ./setup.sh verify <env_dir> [required_files...]
|
|
7
|
+
# ./setup.sh create-temp [prefix]
|
|
8
|
+
# ./setup.sh cleanup <temp_dir>
|
|
9
|
+
# ./setup.sh write-skill <test_dir> <skill_name> <content_file> [scripts_dir] [source_dir]
|
|
10
|
+
# ./setup.sh write-claude-md <test_dir> <content_file>
|
|
11
|
+
# ./setup.sh copy-env <test_dir> <env_dir>
|
|
12
|
+
|
|
13
|
+
set -eo pipefail
|
|
14
|
+
|
|
15
|
+
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
16
|
+
source "$SCRIPT_DIR/common.sh"
|
|
17
|
+
source "$SCRIPT_DIR/docker.sh"
|
|
18
|
+
|
|
19
|
+
# =============================================================================
|
|
20
|
+
# VERIFICATION
|
|
21
|
+
# =============================================================================
|
|
22
|
+
|
|
23
|
+
verify_environment() {
|
|
24
|
+
local env_dir="$1"
|
|
25
|
+
shift
|
|
26
|
+
local required_files=("$@")
|
|
27
|
+
local errors=()
|
|
28
|
+
|
|
29
|
+
# Default required files
|
|
30
|
+
if [[ ${#required_files[@]} -eq 0 ]]; then
|
|
31
|
+
required_files=("Dockerfile" "requirements.txt")
|
|
32
|
+
fi
|
|
33
|
+
|
|
34
|
+
# Check Claude CLI
|
|
35
|
+
if ! command -v claude &> /dev/null; then
|
|
36
|
+
errors+=("Claude Code CLI not found. Install from: https://claude.ai/code")
|
|
37
|
+
fi
|
|
38
|
+
|
|
39
|
+
# Check Docker
|
|
40
|
+
if ! check_docker; then
|
|
41
|
+
errors+=("Docker not available")
|
|
42
|
+
fi
|
|
43
|
+
|
|
44
|
+
# Check API keys
|
|
45
|
+
if [[ -z "${ANTHROPIC_API_KEY:-}" ]]; then
|
|
46
|
+
errors+=("ANTHROPIC_API_KEY not set")
|
|
47
|
+
fi
|
|
48
|
+
if [[ -z "${OPENAI_API_KEY:-}" ]]; then
|
|
49
|
+
errors+=("OPENAI_API_KEY not set")
|
|
50
|
+
fi
|
|
51
|
+
|
|
52
|
+
# Check environment directory
|
|
53
|
+
if [[ ! -d "$env_dir" ]]; then
|
|
54
|
+
errors+=("Environment directory not found: $env_dir")
|
|
55
|
+
else
|
|
56
|
+
for file in "${required_files[@]}"; do
|
|
57
|
+
if [[ ! -f "$env_dir/$file" ]]; then
|
|
58
|
+
errors+=("Missing: $env_dir/$file")
|
|
59
|
+
fi
|
|
60
|
+
done
|
|
61
|
+
fi
|
|
62
|
+
|
|
63
|
+
# Report errors
|
|
64
|
+
if [[ ${#errors[@]} -gt 0 ]]; then
|
|
65
|
+
log_error "Environment verification failed:"
|
|
66
|
+
for error in "${errors[@]}"; do
|
|
67
|
+
echo " - $error" >&2
|
|
68
|
+
done
|
|
69
|
+
return 1
|
|
70
|
+
fi
|
|
71
|
+
|
|
72
|
+
log_success "Environment verified (Docker, Claude CLI, API keys)"
|
|
73
|
+
return 0
|
|
74
|
+
}
|
|
75
|
+
|
|
76
|
+
# =============================================================================
|
|
77
|
+
# TEMP DIRECTORY MANAGEMENT
|
|
78
|
+
# =============================================================================
|
|
79
|
+
|
|
80
|
+
create_temp_dir() {
|
|
81
|
+
local prefix="${1:-claude_test_}"
|
|
82
|
+
mktemp -d -t "${prefix}XXXXXXXX"
|
|
83
|
+
}
|
|
84
|
+
|
|
85
|
+
cleanup_temp_dir() {
|
|
86
|
+
local dir="$1"
|
|
87
|
+
|
|
88
|
+
# Safety check: only remove if it looks like our temp dir
|
|
89
|
+
if [[ "$dir" != *"claude_test_"* && "$dir" != */tmp/* && "$dir" != */var/folders/* ]]; then
|
|
90
|
+
log_warn "Refusing to clean up $dir (not a temp directory)"
|
|
91
|
+
return 1
|
|
92
|
+
fi
|
|
93
|
+
|
|
94
|
+
if [[ -d "$dir" ]]; then
|
|
95
|
+
log_info "Cleaning up $dir..."
|
|
96
|
+
rm -rf "$dir"
|
|
97
|
+
log_success "Cleaned up"
|
|
98
|
+
fi
|
|
99
|
+
}
|
|
100
|
+
|
|
101
|
+
# =============================================================================
|
|
102
|
+
# SKILL SETUP
|
|
103
|
+
# =============================================================================
|
|
104
|
+
|
|
105
|
+
write_skill() {
|
|
106
|
+
local test_dir="$1"
|
|
107
|
+
local skill_name="$2"
|
|
108
|
+
local content_file="$3"
|
|
109
|
+
local scripts_dir="${4:-}"
|
|
110
|
+
local source_dir="${5:-}"
|
|
111
|
+
|
|
112
|
+
local skill_dir="$test_dir/.claude/skills/$skill_name"
|
|
113
|
+
mkdir -p "$skill_dir"
|
|
114
|
+
|
|
115
|
+
if [[ -n "$source_dir" && -d "$source_dir" ]]; then
|
|
116
|
+
cp -r "$source_dir"/. "$skill_dir"/
|
|
117
|
+
log_info "Copied skill package to $skill_name/"
|
|
118
|
+
fi
|
|
119
|
+
|
|
120
|
+
# Write SKILL.md
|
|
121
|
+
if [[ -f "$content_file" ]]; then
|
|
122
|
+
cp "$content_file" "$skill_dir/SKILL.md"
|
|
123
|
+
else
|
|
124
|
+
# Content passed as string (for piping)
|
|
125
|
+
echo "$content_file" > "$skill_dir/SKILL.md"
|
|
126
|
+
fi
|
|
127
|
+
|
|
128
|
+
# Copy scripts if provided
|
|
129
|
+
if [[ -n "$scripts_dir" && -d "$scripts_dir" ]]; then
|
|
130
|
+
rm -rf "$skill_dir/scripts"
|
|
131
|
+
cp -r "$scripts_dir" "$skill_dir/scripts"
|
|
132
|
+
chmod -R u+x "$skill_dir/scripts" 2>/dev/null || true
|
|
133
|
+
log_info "Copied scripts to $skill_name/scripts/"
|
|
134
|
+
fi
|
|
135
|
+
|
|
136
|
+
echo "$skill_dir/SKILL.md"
|
|
137
|
+
}
|
|
138
|
+
|
|
139
|
+
write_claude_md() {
|
|
140
|
+
local test_dir="$1"
|
|
141
|
+
local content_file="$2"
|
|
142
|
+
|
|
143
|
+
local claude_dir="$test_dir/.claude"
|
|
144
|
+
mkdir -p "$claude_dir"
|
|
145
|
+
|
|
146
|
+
if [[ -f "$content_file" ]]; then
|
|
147
|
+
cp "$content_file" "$claude_dir/CLAUDE.md"
|
|
148
|
+
cp "$content_file" "$test_dir/CLAUDE.md"
|
|
149
|
+
else
|
|
150
|
+
# Content passed as string
|
|
151
|
+
echo "$content_file" > "$claude_dir/CLAUDE.md"
|
|
152
|
+
echo "$content_file" > "$test_dir/CLAUDE.md"
|
|
153
|
+
fi
|
|
154
|
+
|
|
155
|
+
local size
|
|
156
|
+
size=$(wc -c < "$claude_dir/CLAUDE.md" | tr -d ' ')
|
|
157
|
+
log_success "Created CLAUDE.md ($size chars)"
|
|
158
|
+
}
|
|
159
|
+
|
|
160
|
+
# =============================================================================
|
|
161
|
+
# ENVIRONMENT COPY
|
|
162
|
+
# =============================================================================
|
|
163
|
+
|
|
164
|
+
copy_environment() {
|
|
165
|
+
local test_dir="$1"
|
|
166
|
+
local env_dir="$2"
|
|
167
|
+
|
|
168
|
+
if [[ ! -d "$env_dir" ]]; then
|
|
169
|
+
log_error "Environment directory not found: $env_dir"
|
|
170
|
+
return 1
|
|
171
|
+
fi
|
|
172
|
+
|
|
173
|
+
# Merge (rsync-like) instead of clobber: copy each top-level item, and for
|
|
174
|
+
# directories that already exist in test_dir (e.g. .claude/, openspec/),
|
|
175
|
+
# merge contents recursively so injected skills/commands are preserved.
|
|
176
|
+
for item in "$env_dir"/*; do
|
|
177
|
+
[[ -e "$item" ]] || continue
|
|
178
|
+
local name
|
|
179
|
+
name=$(basename "$item")
|
|
180
|
+
local dest="$test_dir/$name"
|
|
181
|
+
if [[ -d "$item" && -d "$dest" ]]; then
|
|
182
|
+
# Both dirs: copy contents into existing dest (merge).
|
|
183
|
+
cp -r "$item"/. "$dest"/ 2>/dev/null || cp -r "$item"/* "$dest"/ 2>/dev/null || true
|
|
184
|
+
else
|
|
185
|
+
cp -r "$item" "$dest"
|
|
186
|
+
fi
|
|
187
|
+
done
|
|
188
|
+
|
|
189
|
+
log_success "Copied environment from $(basename "$env_dir")/ (merged)"
|
|
190
|
+
}
|
|
191
|
+
|
|
192
|
+
# =============================================================================
|
|
193
|
+
# CLI MODE
|
|
194
|
+
# =============================================================================
|
|
195
|
+
|
|
196
|
+
if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
|
|
197
|
+
cmd="${1:-help}"
|
|
198
|
+
shift || true
|
|
199
|
+
|
|
200
|
+
case "$cmd" in
|
|
201
|
+
verify)
|
|
202
|
+
env_dir="${1:-}"
|
|
203
|
+
if [[ -z "$env_dir" ]]; then
|
|
204
|
+
die "Usage: $0 verify <env_dir> [required_files...]"
|
|
205
|
+
fi
|
|
206
|
+
shift
|
|
207
|
+
verify_environment "$env_dir" "$@"
|
|
208
|
+
;;
|
|
209
|
+
create-temp)
|
|
210
|
+
prefix="${1:-claude_test_}"
|
|
211
|
+
create_temp_dir "$prefix"
|
|
212
|
+
;;
|
|
213
|
+
cleanup)
|
|
214
|
+
dir="${1:-}"
|
|
215
|
+
if [[ -z "$dir" ]]; then
|
|
216
|
+
die "Usage: $0 cleanup <temp_dir>"
|
|
217
|
+
fi
|
|
218
|
+
cleanup_temp_dir "$dir"
|
|
219
|
+
;;
|
|
220
|
+
write-skill)
|
|
221
|
+
test_dir="${1:-}"
|
|
222
|
+
skill_name="${2:-}"
|
|
223
|
+
content="${3:-}"
|
|
224
|
+
scripts_dir="${4:-}"
|
|
225
|
+
source_dir="${5:-}"
|
|
226
|
+
if [[ -z "$test_dir" || -z "$skill_name" || -z "$content" ]]; then
|
|
227
|
+
die "Usage: $0 write-skill <test_dir> <skill_name> <content_file> [scripts_dir] [source_dir]"
|
|
228
|
+
fi
|
|
229
|
+
write_skill "$test_dir" "$skill_name" "$content" "$scripts_dir" "$source_dir"
|
|
230
|
+
;;
|
|
231
|
+
write-claude-md)
|
|
232
|
+
test_dir="${1:-}"
|
|
233
|
+
content="${2:-}"
|
|
234
|
+
if [[ -z "$test_dir" || -z "$content" ]]; then
|
|
235
|
+
die "Usage: $0 write-claude-md <test_dir> <content_file>"
|
|
236
|
+
fi
|
|
237
|
+
write_claude_md "$test_dir" "$content"
|
|
238
|
+
;;
|
|
239
|
+
copy-env)
|
|
240
|
+
test_dir="${1:-}"
|
|
241
|
+
env_dir="${2:-}"
|
|
242
|
+
if [[ -z "$test_dir" || -z "$env_dir" ]]; then
|
|
243
|
+
die "Usage: $0 copy-env <test_dir> <env_dir>"
|
|
244
|
+
fi
|
|
245
|
+
copy_environment "$test_dir" "$env_dir"
|
|
246
|
+
;;
|
|
247
|
+
help|*)
|
|
248
|
+
echo "Usage: $0 <command> [args...]"
|
|
249
|
+
echo ""
|
|
250
|
+
echo "Commands:"
|
|
251
|
+
echo " verify <env_dir> [files...] Verify environment (Docker, Claude, keys)"
|
|
252
|
+
echo " create-temp [prefix] Create temp directory"
|
|
253
|
+
echo " cleanup <temp_dir> Remove temp directory"
|
|
254
|
+
echo " write-skill <dir> <name> <file> [scripts] [source] Write skill to .claude/skills/"
|
|
255
|
+
echo " write-claude-md <dir> <file> Write CLAUDE.md"
|
|
256
|
+
echo " copy-env <dir> <env_dir> Copy environment files"
|
|
257
|
+
;;
|
|
258
|
+
esac
|
|
259
|
+
fi
|
|
@@ -0,0 +1,9 @@
|
|
|
1
|
+
You are simulating a developer user in an automated eval. The AI assistant is
|
|
2
|
+
running the Comet development workflow and has paused to ask you something. Read
|
|
3
|
+
its message and reply with a SHORT (1-3 sentences) response that:
|
|
4
|
+
|
|
5
|
+
- Approves the proposed approach / name / plan when asked to confirm
|
|
6
|
+
- Picks the most reasonable default option when asked to choose
|
|
7
|
+
- Asks for clarification only if the question is truly ambiguous about WHAT to build
|
|
8
|
+
|
|
9
|
+
Never refuse; always let the workflow move forward. Do not write code or files.
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@rpamis/comet",
|
|
3
|
-
"version": "0.4.0-beta.
|
|
4
|
-
"description": "Agent Skill Harness
|
|
3
|
+
"version": "0.4.0-beta.5",
|
|
4
|
+
"description": "Agent Skill Harness For Turning Ideas Into Evaluated Workflows",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"comet",
|
|
7
7
|
"openspec",
|
|
@@ -22,6 +22,28 @@
|
|
|
22
22
|
"dist",
|
|
23
23
|
"bin",
|
|
24
24
|
"assets",
|
|
25
|
+
"eval",
|
|
26
|
+
"!eval/.venv",
|
|
27
|
+
"!eval/.uv-cache",
|
|
28
|
+
"!eval/.cache",
|
|
29
|
+
"!eval/.tmp",
|
|
30
|
+
"!eval/.ruff_cache",
|
|
31
|
+
"!eval/uv.lock",
|
|
32
|
+
"!eval/**/__pycache__",
|
|
33
|
+
"!eval/.pytest_cache",
|
|
34
|
+
"!eval/.pytest_cache*",
|
|
35
|
+
"!eval/.pytest-basetemp-*",
|
|
36
|
+
"!eval/.pytest-tmp-*",
|
|
37
|
+
"!eval/local/logs",
|
|
38
|
+
"!eval/local/.pytest_docker_build.lock",
|
|
39
|
+
"!eval/**/logs",
|
|
40
|
+
"!eval/**/.cache",
|
|
41
|
+
"!eval/**/.ruff_cache",
|
|
42
|
+
"!eval/**/.tmp",
|
|
43
|
+
"!eval/**/.pytest_cache",
|
|
44
|
+
"!eval/**/.pytest_cache*",
|
|
45
|
+
"!eval/**/.pytest-basetemp-*",
|
|
46
|
+
"!eval/**/.pytest-tmp-*",
|
|
25
47
|
"scripts/install/postinstall.js",
|
|
26
48
|
"!dist/**/*.test.js",
|
|
27
49
|
"!dist/**/__tests__"
|
|
@@ -72,6 +94,7 @@
|
|
|
72
94
|
"esbuild": "0.28.1",
|
|
73
95
|
"eslint": "^10.4.0",
|
|
74
96
|
"husky": "^9.1.7",
|
|
97
|
+
"jsdom": "^29.1.1",
|
|
75
98
|
"lint-staged": "^17.0.7",
|
|
76
99
|
"prettier": "^3.8.3",
|
|
77
100
|
"react": "^19.2.7",
|
|
@@ -90,6 +113,10 @@
|
|
|
90
113
|
"@inquirer/prompts": "^8.4.3",
|
|
91
114
|
"@inquirer/type": "^4.0.5",
|
|
92
115
|
"commander": "^14.0.0",
|
|
116
|
+
"dompurify": "^3.4.12",
|
|
117
|
+
"highlight.js": "^11.11.1",
|
|
118
|
+
"marked": "^18.0.4",
|
|
119
|
+
"mermaid": "11.15.0",
|
|
93
120
|
"yaml": "^2.9.0"
|
|
94
121
|
}
|
|
95
122
|
}
|
|
@@ -1 +0,0 @@
|
|
|
1
|
-
@layer properties{@supports (((-webkit-hyphens:none)) and (not (margin-trim:inline))) or ((-moz-orient:inline) and (not (color:rgb(from red r g b)))){*,:before,:after,::backdrop{--tw-translate-x:0;--tw-translate-y:0;--tw-translate-z:0;--tw-space-y-reverse:0;--tw-border-style:solid;--tw-leading:initial;--tw-font-weight:initial;--tw-tracking:initial;--tw-ordinal:initial;--tw-slashed-zero:initial;--tw-numeric-figure:initial;--tw-numeric-spacing:initial;--tw-numeric-fraction:initial;--tw-shadow:0 0 #0000;--tw-shadow-color:initial;--tw-shadow-alpha:100%;--tw-inset-shadow:0 0 #0000;--tw-inset-shadow-color:initial;--tw-inset-shadow-alpha:100%;--tw-ring-color:initial;--tw-ring-shadow:0 0 #0000;--tw-inset-ring-color:initial;--tw-inset-ring-shadow:0 0 #0000;--tw-ring-inset:initial;--tw-ring-offset-width:0px;--tw-ring-offset-color:#fff;--tw-ring-offset-shadow:0 0 #0000;--tw-backdrop-blur:initial;--tw-backdrop-brightness:initial;--tw-backdrop-contrast:initial;--tw-backdrop-grayscale:initial;--tw-backdrop-hue-rotate:initial;--tw-backdrop-invert:initial;--tw-backdrop-opacity:initial;--tw-backdrop-saturate:initial;--tw-backdrop-sepia:initial;--tw-duration:initial}}}@layer theme{:root,:host{--font-sans:ui-sans-serif, system-ui, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji";--font-mono:ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace;--color-black:#000;--color-white:#fff;--spacing:.25rem;--text-xs:.75rem;--text-xs--line-height:calc(1 / .75);--text-sm:.875rem;--text-sm--line-height:calc(1.25 / .875);--text-base:1rem;--text-base--line-height: 1.5 ;--text-lg:1.125rem;--text-lg--line-height:calc(1.75 / 1.125);--text-xl:1.25rem;--text-xl--line-height:calc(1.75 / 1.25);--font-weight-medium:500;--font-weight-semibold:600;--font-weight-bold:700;--tracking-tight:-.025em;--tracking-wider:.05em;--leading-tight:1.25;--leading-relaxed:1.625;--radius-md:.375rem;--radius-lg:.5rem;--radius-xl:.75rem;--blur-xl:24px;--default-transition-duration:.15s;--default-transition-timing-function:cubic-bezier(.4, 0, .2, 1);--default-font-family:var(--font-sans);--default-mono-font-family:var(--font-mono);--color-bg:#fff;--color-surface:#f5f5f7;--color-surface-warm:#fbfbfd;--color-fg:#1d1d1f;--color-fg-2:#424245;--color-muted:#6e6e73;--color-meta:#6e6e73;--color-border:#d2d2d7;--color-border-soft:#e8e8ed;--color-accent:#0063f8;--color-accent-active:#0052e0;--color-accent-soft:oklab(95.5173% -.00376316 -.0232734);--color-accent-softer:oklab(97.3104% -.00225789 -.013964);--color-success:#16a34a;--color-warn:#c47a06;--color-danger:#dc2626;--color-info:#0063f8;--color-ok-soft:oklab(95.5246% -.0175162 .0104361);--color-warn-soft:oklab(95.7223% .00634364 .0155582);--color-danger-soft:oklab(95.771% .0191149 .00987657);--color-info-soft:oklab(95.5173% -.00376316 -.0232734);--spacing-dashboard:1620px}}@layer base{*,:after,:before,::backdrop{box-sizing:border-box;border:0 solid;margin:0;padding:0}::file-selector-button{box-sizing:border-box;border:0 solid;margin:0;padding:0}html,:host{-webkit-text-size-adjust:100%;tab-size:4;line-height:1.5;font-family:var(--default-font-family,ui-sans-serif, system-ui, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol", "Noto Color Emoji");font-feature-settings:var(--default-font-feature-settings,normal);font-variation-settings:var(--default-font-variation-settings,normal);-webkit-tap-highlight-color:transparent}hr{height:0;color:inherit;border-top-width:1px}abbr:where([title]){-webkit-text-decoration:underline dotted;text-decoration:underline dotted}h1,h2,h3,h4,h5,h6{font-size:inherit;font-weight:inherit}a{color:inherit;-webkit-text-decoration:inherit;text-decoration:inherit}b,strong{font-weight:bolder}code,kbd,samp,pre{font-family:var(--default-mono-font-family,ui-monospace, SFMono-Regular, Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace);font-feature-settings:var(--default-mono-font-feature-settings,normal);font-variation-settings:var(--default-mono-font-variation-settings,normal);font-size:1em}small{font-size:80%}sub,sup{vertical-align:baseline;font-size:75%;line-height:0;position:relative}sub{bottom:-.25em}sup{top:-.5em}table{text-indent:0;border-color:inherit;border-collapse:collapse}:-moz-focusring{outline:auto}progress{vertical-align:baseline}summary{display:list-item}ol,ul,menu{list-style:none}img,svg,video,canvas,audio,iframe,embed,object{vertical-align:middle;display:block}img,video{max-width:100%;height:auto}button,input,select,optgroup,textarea{font:inherit;font-feature-settings:inherit;font-variation-settings:inherit;letter-spacing:inherit;color:inherit;opacity:1;background-color:#0000;border-radius:0}::file-selector-button{font:inherit;font-feature-settings:inherit;font-variation-settings:inherit;letter-spacing:inherit;color:inherit;opacity:1;background-color:#0000;border-radius:0}:where(select:is([multiple],[size])) optgroup{font-weight:bolder}:where(select:is([multiple],[size])) optgroup option{padding-inline-start:20px}::file-selector-button{margin-inline-end:4px}::placeholder{opacity:1}@supports (not ((-webkit-appearance:-apple-pay-button))) or (contain-intrinsic-size:1px){::placeholder{color:currentColor}@supports (color:color-mix(in lab,red,red)){::placeholder{color:color-mix(in oklab,currentcolor 50%,transparent)}}}textarea{resize:vertical}::-webkit-search-decoration{-webkit-appearance:none}::-webkit-date-and-time-value{min-height:1lh;text-align:inherit}::-webkit-datetime-edit{display:inline-flex}::-webkit-datetime-edit-fields-wrapper{padding:0}::-webkit-datetime-edit{padding-block:0}::-webkit-datetime-edit-year-field{padding-block:0}::-webkit-datetime-edit-month-field{padding-block:0}::-webkit-datetime-edit-day-field{padding-block:0}::-webkit-datetime-edit-hour-field{padding-block:0}::-webkit-datetime-edit-minute-field{padding-block:0}::-webkit-datetime-edit-second-field{padding-block:0}::-webkit-datetime-edit-millisecond-field{padding-block:0}::-webkit-datetime-edit-meridiem-field{padding-block:0}::-webkit-calendar-picker-indicator{line-height:1}:-moz-ui-invalid{box-shadow:none}button,input:where([type=button],[type=reset],[type=submit]){appearance:button}::file-selector-button{appearance:button}::-webkit-inner-spin-button{height:auto}::-webkit-outer-spin-button{height:auto}[hidden]:where(:not([hidden=until-found])){display:none!important}}@layer components;@layer utilities{.visible{visibility:visible}.absolute{position:absolute}.fixed{position:fixed}.relative{position:relative}.sticky{position:sticky}.inset-0{inset:0}.inset-y-0{inset-block:0}.top-0{top:0}.top-1\/2{top:50%}.top-4{top:calc(var(--spacing) * 4)}.top-5{top:calc(var(--spacing) * 5)}.right-0{right:0}.right-1\/2{right:50%}.right-5{right:calc(var(--spacing) * 5)}.left-0{left:0}.left-1\/2{left:50%}.left-3{left:calc(var(--spacing) * 3)}.z-10{z-index:10}.z-30{z-index:30}.z-40{z-index:40}.z-50{z-index:50}.z-\[90\]{z-index:90}.mx-auto{margin-inline:auto}.mt-0\.5{margin-top:calc(var(--spacing) * .5)}.mt-1{margin-top:var(--spacing)}.mt-1\.5{margin-top:calc(var(--spacing) * 1.5)}.mt-2{margin-top:calc(var(--spacing) * 2)}.mt-4{margin-top:calc(var(--spacing) * 4)}.mt-6{margin-top:calc(var(--spacing) * 6)}.mt-auto{margin-top:auto}.mb-1{margin-bottom:var(--spacing)}.mb-1\.5{margin-bottom:calc(var(--spacing) * 1.5)}.mb-2{margin-bottom:calc(var(--spacing) * 2)}.mb-4{margin-bottom:calc(var(--spacing) * 4)}.ml-auto{margin-left:auto}.block{display:block}.flex{display:flex}.grid{display:grid}.hidden{display:none}.inline-flex{display:inline-flex}.size-5{width:calc(var(--spacing) * 5);height:calc(var(--spacing) * 5)}.size-7{width:calc(var(--spacing) * 7);height:calc(var(--spacing) * 7)}.size-8{width:calc(var(--spacing) * 8);height:calc(var(--spacing) * 8)}.size-10{width:calc(var(--spacing) * 10);height:calc(var(--spacing) * 10)}.size-full{width:100%;height:100%}.h-1\.5{height:calc(var(--spacing) * 1.5)}.h-2{height:calc(var(--spacing) * 2)}.h-4{height:calc(var(--spacing) * 4)}.h-6{height:calc(var(--spacing) * 6)}.h-10{height:calc(var(--spacing) * 10)}.h-\[110px\]{height:110px}.h-full{height:100%}.h-px{height:1px}.min-h-0{min-height:0}.min-h-\[480px\]{min-height:480px}.min-h-screen{min-height:100vh}.w-1\.5{width:calc(var(--spacing) * 1.5)}.w-2{width:calc(var(--spacing) * 2)}.w-4{width:calc(var(--spacing) * 4)}.w-16{width:calc(var(--spacing) * 16)}.w-\[110px\]{width:110px}.w-\[clamp\(180px\,24vw\,300px\)\]{width:clamp(180px,24vw,300px)}.w-\[var\(--rail-w\)\]{width:var(--rail-w)}.w-full{width:100%}.w-px{width:1px}.max-w-dashboard{max-width:var(--spacing-dashboard)}.min-w-0{min-width:0}.flex-1{flex:1}.shrink-0{flex-shrink:0}.-translate-x-full{--tw-translate-x:-100%;translate:var(--tw-translate-x) var(--tw-translate-y)}.translate-x-0{--tw-translate-x:0;translate:var(--tw-translate-x) var(--tw-translate-y)}.-translate-y-1\/2{--tw-translate-y: -50% ;translate:var(--tw-translate-x) var(--tw-translate-y)}.-rotate-90{rotate:-90deg}.cursor-default{cursor:default}.cursor-pointer{cursor:pointer}.grid-cols-\[16px_1fr_auto\]{grid-template-columns:16px 1fr auto}.grid-cols-\[minmax\(0\,1fr\)_minmax\(360px\,760px\)\]{grid-template-columns:minmax(0,1fr) minmax(360px,760px)}.flex-col{flex-direction:column}.flex-wrap{flex-wrap:wrap}.place-items-center{place-items:center}.items-baseline{align-items:baseline}.items-center{align-items:center}.items-start{align-items:flex-start}.justify-between{justify-content:space-between}.justify-center{justify-content:center}.gap-2{gap:calc(var(--spacing) * 2)}.gap-3{gap:calc(var(--spacing) * 3)}.gap-4{gap:calc(var(--spacing) * 4)}.gap-5{gap:calc(var(--spacing) * 5)}.gap-6{gap:calc(var(--spacing) * 6)}:where(.space-y-1>:not(:last-child)){--tw-space-y-reverse:0;margin-block-start:calc(var(--spacing) * var(--tw-space-y-reverse));margin-block-end:calc(var(--spacing) * calc(1 - var(--tw-space-y-reverse)))}:where(.space-y-2>:not(:last-child)){--tw-space-y-reverse:0;margin-block-start:calc(calc(var(--spacing) * 2) * var(--tw-space-y-reverse));margin-block-end:calc(calc(var(--spacing) * 2) * calc(1 - var(--tw-space-y-reverse)))}:where(.space-y-2\.5>:not(:last-child)){--tw-space-y-reverse:0;margin-block-start:calc(calc(var(--spacing) * 2.5) * var(--tw-space-y-reverse));margin-block-end:calc(calc(var(--spacing) * 2.5) * calc(1 - var(--tw-space-y-reverse)))}:where(.space-y-3>:not(:last-child)){--tw-space-y-reverse:0;margin-block-start:calc(calc(var(--spacing) * 3) * var(--tw-space-y-reverse));margin-block-end:calc(calc(var(--spacing) * 3) * calc(1 - var(--tw-space-y-reverse)))}:where(.space-y-4>:not(:last-child)){--tw-space-y-reverse:0;margin-block-start:calc(calc(var(--spacing) * 4) * var(--tw-space-y-reverse));margin-block-end:calc(calc(var(--spacing) * 4) * calc(1 - var(--tw-space-y-reverse)))}:where(.space-y-5>:not(:last-child)){--tw-space-y-reverse:0;margin-block-start:calc(calc(var(--spacing) * 5) * var(--tw-space-y-reverse));margin-block-end:calc(calc(var(--spacing) * 5) * calc(1 - var(--tw-space-y-reverse)))}:where(.space-y-px>:not(:last-child)){--tw-space-y-reverse:0;margin-block-start:calc(1px * var(--tw-space-y-reverse));margin-block-end:calc(1px * calc(1 - var(--tw-space-y-reverse)))}.gap-x-2\.5{column-gap:calc(var(--spacing) * 2.5)}.truncate{text-overflow:ellipsis;white-space:nowrap;overflow:hidden}.overflow-hidden{overflow:hidden}.overflow-y-auto{overflow-y:auto}.overscroll-contain{overscroll-behavior:contain}.rounded-\[7px\]{border-radius:7px}.rounded-full{border-radius:3.40282e38px}.rounded-lg{border-radius:var(--radius-lg)}.rounded-md{border-radius:var(--radius-md)}.rounded-xl{border-radius:var(--radius-xl)}.border{border-style:var(--tw-border-style);border-width:1px}.border-t{border-top-style:var(--tw-border-style);border-top-width:1px}.border-r{border-right-style:var(--tw-border-style);border-right-width:1px}.border-b{border-bottom-style:var(--tw-border-style);border-bottom-width:1px}.border-l{border-left-style:var(--tw-border-style);border-left-width:1px}.border-accent{border-color:var(--color-accent)}.border-accent\/30{border-color:#0063f84d}@supports (color:color-mix(in lab,red,red)){.border-accent\/30{border-color:color-mix(in oklab,var(--color-accent) 30%,transparent)}}.border-border{border-color:var(--color-border)}.border-border-soft{border-color:var(--color-border-soft)}.border-transparent{border-color:#0000}.bg-accent{background-color:var(--color-accent)}.bg-accent-soft{background-color:var(--color-accent-soft)}.bg-accent-softer{background-color:var(--color-accent-softer)}.bg-bg{background-color:var(--color-bg)}.bg-black\/30{background-color:#0000004d}@supports (color:color-mix(in lab,red,red)){.bg-black\/30{background-color:color-mix(in oklab,var(--color-black) 30%,transparent)}}.bg-border{background-color:var(--color-border)}.bg-border-soft{background-color:var(--color-border-soft)}.bg-danger-soft{background-color:var(--color-danger-soft)}.bg-fg{background-color:var(--color-fg)}.bg-info-soft{background-color:var(--color-info-soft)}.bg-ok-soft{background-color:var(--color-ok-soft)}.bg-success{background-color:var(--color-success)}.bg-surface{background-color:var(--color-surface)}.bg-surface-warm{background-color:var(--color-surface-warm)}.bg-surface\/80{background-color:#f5f5f7cc}@supports (color:color-mix(in lab,red,red)){.bg-surface\/80{background-color:color-mix(in oklab,var(--color-surface) 80%,transparent)}}.bg-warn-soft{background-color:var(--color-warn-soft)}.p-1{padding:var(--spacing)}.p-3{padding:calc(var(--spacing) * 3)}.p-4{padding:calc(var(--spacing) * 4)}.p-5{padding:calc(var(--spacing) * 5)}.p-10{padding:calc(var(--spacing) * 10)}.px-2{padding-inline:calc(var(--spacing) * 2)}.px-2\.5{padding-inline:calc(var(--spacing) * 2.5)}.px-3{padding-inline:calc(var(--spacing) * 3)}.px-4{padding-inline:calc(var(--spacing) * 4)}.px-5{padding-inline:calc(var(--spacing) * 5)}.py-0\.5{padding-block:calc(var(--spacing) * .5)}.py-1{padding-block:var(--spacing)}.py-1\.5{padding-block:calc(var(--spacing) * 1.5)}.py-2{padding-block:calc(var(--spacing) * 2)}.py-3{padding-block:calc(var(--spacing) * 3)}.py-4{padding-block:calc(var(--spacing) * 4)}.py-5{padding-block:calc(var(--spacing) * 5)}.py-8{padding-block:calc(var(--spacing) * 8)}.pt-2{padding-top:calc(var(--spacing) * 2)}.pt-4{padding-top:calc(var(--spacing) * 4)}.pt-5{padding-top:calc(var(--spacing) * 5)}.pr-4{padding-right:calc(var(--spacing) * 4)}.pb-12{padding-bottom:calc(var(--spacing) * 12)}.pl-2{padding-left:calc(var(--spacing) * 2)}.pl-4{padding-left:calc(var(--spacing) * 4)}.pl-10{padding-left:calc(var(--spacing) * 10)}.text-center{text-align:center}.text-left{text-align:left}.text-right{text-align:right}.font-mono{font-family:var(--font-mono)}.text-base{font-size:var(--text-base);line-height:var(--tw-leading,var(--text-base--line-height))}.text-lg{font-size:var(--text-lg);line-height:var(--tw-leading,var(--text-lg--line-height))}.text-sm{font-size:var(--text-sm);line-height:var(--tw-leading,var(--text-sm--line-height))}.text-xl{font-size:var(--text-xl);line-height:var(--tw-leading,var(--text-xl--line-height))}.text-xs{font-size:var(--text-xs);line-height:var(--tw-leading,var(--text-xs--line-height))}.text-\[10px\]{font-size:10px}.text-\[11px\]{font-size:11px}.text-\[12px\]{font-size:12px}.text-\[13px\]{font-size:13px}.text-\[18px\]{font-size:18px}.text-\[26px\]{font-size:26px}.text-\[28px\]{font-size:28px}.text-\[40px\]{font-size:40px}.leading-none{--tw-leading:1;line-height:1}.leading-relaxed{--tw-leading:var(--leading-relaxed);line-height:var(--leading-relaxed)}.leading-tight{--tw-leading:var(--leading-tight);line-height:var(--leading-tight)}.font-bold{--tw-font-weight:var(--font-weight-bold);font-weight:var(--font-weight-bold)}.font-medium{--tw-font-weight:var(--font-weight-medium);font-weight:var(--font-weight-medium)}.font-semibold{--tw-font-weight:var(--font-weight-semibold);font-weight:var(--font-weight-semibold)}.tracking-tight{--tw-tracking:var(--tracking-tight);letter-spacing:var(--tracking-tight)}.tracking-wider{--tw-tracking:var(--tracking-wider);letter-spacing:var(--tracking-wider)}.break-words{overflow-wrap:break-word}.break-all{word-break:break-all}.whitespace-nowrap{white-space:nowrap}.text-accent{color:var(--color-accent)}.text-accent-active{color:var(--color-accent-active)}.text-bg{color:var(--color-bg)}.text-danger{color:var(--color-danger)}.text-fg{color:var(--color-fg)}.text-fg-2{color:var(--color-fg-2)}.text-info{color:var(--color-info)}.text-meta{color:var(--color-meta)}.text-muted{color:var(--color-muted)}.text-success{color:var(--color-success)}.text-warn{color:var(--color-warn)}.text-white{color:var(--color-white)}.uppercase{text-transform:uppercase}.tabular-nums{--tw-numeric-spacing:tabular-nums;font-variant-numeric:var(--tw-ordinal,) var(--tw-slashed-zero,) var(--tw-numeric-figure,) var(--tw-numeric-spacing,) var(--tw-numeric-fraction,)}.antialiased{-webkit-font-smoothing:antialiased;-moz-osx-font-smoothing:grayscale}.opacity-50{opacity:.5}.shadow-\[-20px_0_44px_rgba\(0\,0\,0\,0\.12\)\]{--tw-shadow:-20px 0 44px var(--tw-shadow-color,#0000001f);box-shadow:var(--tw-inset-shadow),var(--tw-inset-ring-shadow),var(--tw-ring-offset-shadow),var(--tw-ring-shadow),var(--tw-shadow)}.shadow-card{--tw-shadow:none;box-shadow:var(--tw-inset-shadow),var(--tw-inset-ring-shadow),var(--tw-ring-offset-shadow),var(--tw-ring-shadow),var(--tw-shadow)}.shadow-raised{--tw-shadow:0 12px 32px var(--tw-shadow-color,#00000014);box-shadow:var(--tw-inset-shadow),var(--tw-inset-ring-shadow),var(--tw-ring-offset-shadow),var(--tw-ring-shadow),var(--tw-shadow)}.shadow-sm{--tw-shadow:0 1px 3px 0 var(--tw-shadow-color,#0000001a), 0 1px 2px -1px var(--tw-shadow-color,#0000001a);box-shadow:var(--tw-inset-shadow),var(--tw-inset-ring-shadow),var(--tw-ring-offset-shadow),var(--tw-ring-shadow),var(--tw-shadow)}.backdrop-blur-xl{--tw-backdrop-blur:blur(var(--blur-xl));-webkit-backdrop-filter:var(--tw-backdrop-blur,) var(--tw-backdrop-brightness,) var(--tw-backdrop-contrast,) var(--tw-backdrop-grayscale,) var(--tw-backdrop-hue-rotate,) var(--tw-backdrop-invert,) var(--tw-backdrop-opacity,) var(--tw-backdrop-saturate,) var(--tw-backdrop-sepia,);backdrop-filter:var(--tw-backdrop-blur,) var(--tw-backdrop-brightness,) var(--tw-backdrop-contrast,) var(--tw-backdrop-grayscale,) var(--tw-backdrop-hue-rotate,) var(--tw-backdrop-invert,) var(--tw-backdrop-opacity,) var(--tw-backdrop-saturate,) var(--tw-backdrop-sepia,)}.transition-all{transition-property:all;transition-timing-function:var(--tw-ease,var(--default-transition-timing-function));transition-duration:var(--tw-duration,var(--default-transition-duration))}.transition-colors{transition-property:color,background-color,border-color,outline-color,text-decoration-color,fill,stroke,--tw-gradient-from,--tw-gradient-via,--tw-gradient-to;transition-timing-function:var(--tw-ease,var(--default-transition-timing-function));transition-duration:var(--tw-duration,var(--default-transition-duration))}.transition-shadow{transition-property:box-shadow;transition-timing-function:var(--tw-ease,var(--default-transition-timing-function));transition-duration:var(--tw-duration,var(--default-transition-duration))}.transition-transform{transition-property:transform,translate,scale,rotate;transition-timing-function:var(--tw-ease,var(--default-transition-timing-function));transition-duration:var(--tw-duration,var(--default-transition-duration))}.duration-100{--tw-duration:.1s;transition-duration:.1s}.duration-200{--tw-duration:.2s;transition-duration:.2s}.duration-500{--tw-duration:.5s;transition-duration:.5s}.outline-none{--tw-outline-style:none;outline-style:none}.first\:mt-2:first-child{margin-top:calc(var(--spacing) * 2)}@media(hover:hover){.hover\:border-border-soft:hover{border-color:var(--color-border-soft)}.hover\:bg-bg:hover{background-color:var(--color-bg)}.hover\:bg-surface:hover{background-color:var(--color-surface)}.hover\:text-fg:hover{color:var(--color-fg)}.hover\:shadow-lg:hover{--tw-shadow:0 10px 15px -3px var(--tw-shadow-color,#0000001a), 0 4px 6px -4px var(--tw-shadow-color,#0000001a);box-shadow:var(--tw-inset-shadow),var(--tw-inset-ring-shadow),var(--tw-ring-offset-shadow),var(--tw-ring-shadow),var(--tw-shadow)}}.focus\:border-accent:focus{border-color:var(--color-accent)}.focus\:ring-4:focus{--tw-ring-shadow:var(--tw-ring-inset,) 0 0 0 calc(4px + var(--tw-ring-offset-width)) var(--tw-ring-color,currentcolor);box-shadow:var(--tw-inset-shadow),var(--tw-inset-ring-shadow),var(--tw-ring-offset-shadow),var(--tw-ring-shadow),var(--tw-shadow)}.focus\:ring-accent\/20:focus{--tw-ring-color:#0063f833}@supports (color:color-mix(in lab,red,red)){.focus\:ring-accent\/20:focus{--tw-ring-color:color-mix(in oklab, var(--color-accent) 20%, transparent)}}@media not all and (min-width:40rem){.max-sm\:hidden{display:none}.max-sm\:grid-cols-1{grid-template-columns:repeat(1,minmax(0,1fr))}}@media(min-width:40rem){.sm\:px-6{padding-inline:calc(var(--spacing) * 6)}}@media(min-width:48rem){.md\:inline-flex{display:inline-flex}.md\:grid-cols-3{grid-template-columns:repeat(3,minmax(0,1fr))}.md\:grid-cols-\[1fr_340px\]{grid-template-columns:1fr 340px}}@media(min-width:64rem){.lg\:sticky{position:sticky}.lg\:top-0{top:0}.lg\:grid{display:grid}.lg\:hidden{display:none}.lg\:h-screen{height:100vh}.lg\:translate-x-0{--tw-translate-x:0;translate:var(--tw-translate-x) var(--tw-translate-y)}.lg\:grid-cols-5{grid-template-columns:repeat(5,minmax(0,1fr))}.lg\:grid-cols-\[var\(--rail-w\)_1fr\]{grid-template-columns:var(--rail-w) 1fr}.lg\:px-8{padding-inline:calc(var(--spacing) * 8)}}@media(min-width:80rem){.xl\:grid-cols-\[320px_minmax\(620px\,940px\)_320px\]{grid-template-columns:320px minmax(620px,940px) 320px}}}:root[data-theme=dark],:host[data-theme=dark]{--color-bg:#0b0e13;--color-surface:#181b1f;--color-surface-warm:#22252e;--color-fg:#d8dee9;--color-fg-2:#b0b8c4;--color-muted:#7b818a;--color-meta:#8e939e;--color-border:#343740;--color-border-soft:#282b33;--color-accent:#6e9fff;--color-accent-active:#8bb4ff;--color-accent-soft:oklab(26.1466% -.00500724 -.0363311);--color-accent-softer:oklab(22.8611% -.00397309 -.0280616);--color-success:#73bf69;--color-warn:#ff9830;--color-danger:#f2495c;--color-info:#6e9fff;--color-ok-soft:oklab(26.5788% -.0214788 .00639551);--color-warn-soft:oklab(27.2505% .0131415 .0162306);--color-danger-soft:oklab(23.6018% .0273997 .000079521);--color-info-soft:oklab(24.5038% -.00449016 -.0321963);--shadow-raised:0 8px 32px #00000080;--shadow-card:none}:root{--rail-w:248px;color:var(--color-fg);background:var(--color-surface);-webkit-font-smoothing:antialiased;text-rendering:optimizelegibility;font-family:Inter,Inter var,sans-serif}:root,:root *{transition-property:color,background-color,border-color,box-shadow;transition-duration:.15s;transition-timing-function:ease-out}:root button:active,:root input:active,:root .no-transition{transition:none!important}html{scrollbar-gutter:stable;overflow-y:scroll}::-webkit-scrollbar{width:8px;height:8px}::-webkit-scrollbar-track{background:0 0}::-webkit-scrollbar-thumb{background:var(--color-border);border-radius:4px}::-webkit-scrollbar-thumb:hover{background:var(--color-muted)}body{min-width:320px;margin:0}button,input{font:inherit}.max-w-dashboard{max-width:var(--spacing-dashboard)}.artifact-markdown{color:var(--color-fg-2);font-size:14px;line-height:1.65}.artifact-markdown h1,.artifact-markdown h2,.artifact-markdown h3,.artifact-markdown h4{color:var(--color-fg);margin:1.25rem 0 .5rem;font-weight:700;line-height:1.2}.artifact-markdown h1{font-size:1.75rem}.artifact-markdown h2{font-size:1.35rem}.artifact-markdown h3,.artifact-markdown h4{font-size:1rem}.artifact-markdown p{margin:.65rem 0}.artifact-markdown ul{margin:.65rem 0;padding-left:1.25rem;list-style:outside}.artifact-markdown li{margin:.35rem 0}.artifact-markdown code{background:var(--color-surface);border-radius:6px;padding:.12rem .35rem;font-family:Inter,Inter var,sans-serif;font-size:.92em}.artifact-markdown pre{color:#f5f5f7;background:#1d1d1f;border-radius:12px;margin:.9rem 0;padding:1rem;overflow:auto}:root[data-theme=dark] .artifact-markdown pre,:host[data-theme=dark] .artifact-markdown pre{color:#d8dee9;background:#14171c}:root[data-theme=dark] .artifact-markdown code,:host[data-theme=dark] .artifact-markdown code{background:#282b33}:root[data-theme=dark] .artifact-markdown h1,:root[data-theme=dark] .artifact-markdown h2,:root[data-theme=dark] .artifact-markdown h3,:root[data-theme=dark] .artifact-markdown h4,:host[data-theme=dark] .artifact-markdown h1,:host[data-theme=dark] .artifact-markdown h2,:host[data-theme=dark] .artifact-markdown h3,:host[data-theme=dark] .artifact-markdown h4{color:#e8ecf2}:root[data-theme=dark] .artifact-markdown a,:host[data-theme=dark] .artifact-markdown a{color:#6e9fff}:root[data-theme=dark] .artifact-markdown blockquote,:host[data-theme=dark] .artifact-markdown blockquote{color:#7b818a;border-left-color:#343740}:root[data-theme=dark] .artifact-markdown hr,:host[data-theme=dark] .artifact-markdown hr{border-color:#343740}:root[data-theme=dark] ::-webkit-scrollbar{width:8px;height:8px}:host[data-theme=dark] ::-webkit-scrollbar{width:8px;height:8px}:root[data-theme=dark] ::-webkit-scrollbar-track{background:#0b0e13}:host[data-theme=dark] ::-webkit-scrollbar-track{background:#0b0e13}:root[data-theme=dark] ::-webkit-scrollbar-thumb{background:#343740;border-radius:4px}:host[data-theme=dark] ::-webkit-scrollbar-thumb{background:#343740;border-radius:4px}:root[data-theme=dark] ::-webkit-scrollbar-thumb:hover{background:#4a4d56}:host[data-theme=dark] ::-webkit-scrollbar-thumb:hover{background:#4a4d56}:root[data-theme=dark] .summary-card-glow,:host[data-theme=dark] .summary-card-glow{box-shadow:0 0 0 1px #6cb6ff1a}:root[data-theme=dark] .accent-glow,:host[data-theme=dark] .accent-glow{box-shadow:0 0 12px #6cb6ff26}.artifact-markdown pre code{color:inherit;background:0 0;padding:0}.toast{z-index:100;opacity:0;pointer-events:none;background:var(--color-fg);color:var(--color-bg);border-radius:999px;padding:11px 20px;font-size:14px;transition:opacity .22s,transform .22s;position:fixed;bottom:28px;left:50%;transform:translate(-50%,20px)}.toast.show{opacity:1;transform:translate(-50%)}@property --tw-translate-x{syntax:"*";inherits:false;initial-value:0}@property --tw-translate-y{syntax:"*";inherits:false;initial-value:0}@property --tw-translate-z{syntax:"*";inherits:false;initial-value:0}@property --tw-space-y-reverse{syntax:"*";inherits:false;initial-value:0}@property --tw-border-style{syntax:"*";inherits:false;initial-value:solid}@property --tw-leading{syntax:"*";inherits:false}@property --tw-font-weight{syntax:"*";inherits:false}@property --tw-tracking{syntax:"*";inherits:false}@property --tw-ordinal{syntax:"*";inherits:false}@property --tw-slashed-zero{syntax:"*";inherits:false}@property --tw-numeric-figure{syntax:"*";inherits:false}@property --tw-numeric-spacing{syntax:"*";inherits:false}@property --tw-numeric-fraction{syntax:"*";inherits:false}@property --tw-shadow{syntax:"*";inherits:false;initial-value:0 0 #0000}@property --tw-shadow-color{syntax:"*";inherits:false}@property --tw-shadow-alpha{syntax:"<percentage>";inherits:false;initial-value:100%}@property --tw-inset-shadow{syntax:"*";inherits:false;initial-value:0 0 #0000}@property --tw-inset-shadow-color{syntax:"*";inherits:false}@property --tw-inset-shadow-alpha{syntax:"<percentage>";inherits:false;initial-value:100%}@property --tw-ring-color{syntax:"*";inherits:false}@property --tw-ring-shadow{syntax:"*";inherits:false;initial-value:0 0 #0000}@property --tw-inset-ring-color{syntax:"*";inherits:false}@property --tw-inset-ring-shadow{syntax:"*";inherits:false;initial-value:0 0 #0000}@property --tw-ring-inset{syntax:"*";inherits:false}@property --tw-ring-offset-width{syntax:"<length>";inherits:false;initial-value:0}@property --tw-ring-offset-color{syntax:"*";inherits:false;initial-value:#fff}@property --tw-ring-offset-shadow{syntax:"*";inherits:false;initial-value:0 0 #0000}@property --tw-backdrop-blur{syntax:"*";inherits:false}@property --tw-backdrop-brightness{syntax:"*";inherits:false}@property --tw-backdrop-contrast{syntax:"*";inherits:false}@property --tw-backdrop-grayscale{syntax:"*";inherits:false}@property --tw-backdrop-hue-rotate{syntax:"*";inherits:false}@property --tw-backdrop-invert{syntax:"*";inherits:false}@property --tw-backdrop-opacity{syntax:"*";inherits:false}@property --tw-backdrop-saturate{syntax:"*";inherits:false}@property --tw-backdrop-sepia{syntax:"*";inherits:false}@property --tw-duration{syntax:"*";inherits:false}
|