@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 +1,110 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: comet-archive
|
|
3
|
+
description: "Use when Comet change 验证已通过,需要用户确认归档、合并 delta spec,或恢复 archive 阶段。"
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Comet 阶段 5:归档(Archive)
|
|
7
|
+
|
|
8
|
+
## 前置条件
|
|
9
|
+
|
|
10
|
+
- 验证已通过(阶段 4 完成)
|
|
11
|
+
- 分支已处理
|
|
12
|
+
- `openspec/changes/<name>/.comet.yaml` 中 `verify_result: pass`
|
|
13
|
+
|
|
14
|
+
## 步骤
|
|
15
|
+
|
|
16
|
+
### 0. 输出语言约束
|
|
17
|
+
|
|
18
|
+
归档摘要和生命周期闭环说明必须使用触发本次工作流的用户请求语言。
|
|
19
|
+
|
|
20
|
+
### 0b. 入口状态验证(Entry Check)
|
|
21
|
+
|
|
22
|
+
按 `comet/reference/scripts.md` 定位脚本(定位 `comet-env.mjs`),然后执行入口验证;从任意入口恢复时先按 `comet/reference/context-recovery.md` 运行恢复检查:
|
|
23
|
+
|
|
24
|
+
```bash
|
|
25
|
+
node "$COMET_STATE" check <name> archive
|
|
26
|
+
```
|
|
27
|
+
|
|
28
|
+
验证通过后继续 Step 1。验证失败时脚本会输出具体失败原因。
|
|
29
|
+
|
|
30
|
+
### 1. 归档前最终确认(阻塞点)
|
|
31
|
+
|
|
32
|
+
入口验证通过后,**必须按 `comet/reference/decision-point.md` 的协议暂停并等待用户确认是否立即归档**。不得在用户确认前运行 `node "$COMET_ARCHIVE" "<change-name>"`。
|
|
33
|
+
|
|
34
|
+
确认前必须向用户展示简短摘要:
|
|
35
|
+
- change 名称
|
|
36
|
+
- 验证报告路径和结论
|
|
37
|
+
- 分支处理状态
|
|
38
|
+
- 本次归档将执行的不可逆动作:按 OpenSpec delta 语义合并主 spec、标注 design doc / plan、移动 change 到 archive 目录
|
|
39
|
+
|
|
40
|
+
用户确认问题必须以单选题形式呈现,包含以下选项:
|
|
41
|
+
- 「确认归档」— 立即执行归档脚本,完成 spec 合并和 change 移动
|
|
42
|
+
- 「需要调整或重新验证」— 不执行归档;运行 `node "$COMET_STATE" transition <change-name> archive-reopen` 回到 `phase: verify`,再调用 `/comet-verify`。若验证阶段确认需要修复,再按 `/comet-verify` 的验证失败决策回到 `/comet-build`
|
|
43
|
+
- 「暂不归档」— 不执行归档,保留当前 `phase: archive` 状态,等待用户稍后再次调用 `/comet-archive`
|
|
44
|
+
|
|
45
|
+
只有用户选择「确认归档」后,才允许继续 Step 2。用户选择「需要调整或重新验证」后,必须先执行 `archive-reopen` 状态回退,不得手动编辑 `.comet.yaml`。
|
|
46
|
+
|
|
47
|
+
### 2. 执行归档
|
|
48
|
+
|
|
49
|
+
运行归档脚本,自动完成以下全部步骤:
|
|
50
|
+
|
|
51
|
+
```bash
|
|
52
|
+
node "$COMET_ARCHIVE" "<change-name>"
|
|
53
|
+
```
|
|
54
|
+
|
|
55
|
+
脚本自动执行:
|
|
56
|
+
1. 入口状态验证(phase=archive, verify_result=pass, archived=false)
|
|
57
|
+
2. Design doc 前置元数据标注(archived-with, status)
|
|
58
|
+
3. Plan 前置元数据标注(archived-with)
|
|
59
|
+
4. 调用 OpenSpec archive 按 delta 语义合并主 spec 并移动 change 到归档目录
|
|
60
|
+
5. 校验主 spec 未残留 delta-only section 标题
|
|
61
|
+
6. 在 OpenSpec 实际归档目录中更新 archived 状态,并协调 pending recovery 元数据
|
|
62
|
+
|
|
63
|
+
如脚本返回非零退出码,报告错误并停止。
|
|
64
|
+
如脚本返回零退出码,归档完成。
|
|
65
|
+
脚本摘要中的 `X/Y steps succeeded` 以真实执行步骤计数,不会因 delta spec 同步或文档标注重复累计。
|
|
66
|
+
|
|
67
|
+
脚本会调用 OpenSpec 归档能力按 `ADDED/MODIFIED/REMOVED/RENAMED` 语义合并主 spec,并在归档后校验主 spec 中没有残留 delta-only section 标题。
|
|
68
|
+
|
|
69
|
+
如需预览而不实际执行,使用 `--dry-run` 参数。
|
|
70
|
+
|
|
71
|
+
### 3. 生命周期闭环
|
|
72
|
+
|
|
73
|
+
Spec 生命周期在此完成:
|
|
74
|
+
```
|
|
75
|
+
brainstorming → delta spec → 实施 → 验证 → 主 spec 合并 → design doc 标注 → 归档
|
|
76
|
+
```
|
|
77
|
+
|
|
78
|
+
### 4. 提交归档改动
|
|
79
|
+
|
|
80
|
+
归档脚本只移动文件和合并 spec,不会自动提交。归档完成后工作区会有以下未提交改动:
|
|
81
|
+
- change 目录从 `openspec/changes/<name>/` 移动到 `openspec/changes/archive/YYYY-MM-DD-<name>/`
|
|
82
|
+
- 主 spec 按 delta 语义合并的内容
|
|
83
|
+
- design doc / plan 的归档元数据标注
|
|
84
|
+
|
|
85
|
+
**必须提示用户提交这些归档改动**,否则归档成果会停留在工作区。展示待提交文件后建议执行:
|
|
86
|
+
|
|
87
|
+
```bash
|
|
88
|
+
git add -A
|
|
89
|
+
git commit -m "chore: archive <change-name>"
|
|
90
|
+
```
|
|
91
|
+
|
|
92
|
+
如分支处理(阶段 4)选择尚未合并到主分支,提交后按所选方式(合并 / PR / 保持分支)一并收尾。
|
|
93
|
+
|
|
94
|
+
## 退出条件
|
|
95
|
+
|
|
96
|
+
- 归档脚本执行成功(退出码 0)
|
|
97
|
+
- 归档目录 `openspec/changes/archive/YYYY-MM-DD-<change-name>/` 存在
|
|
98
|
+
- 归档后的 `.comet.yaml` 中 `archived: true`
|
|
99
|
+
|
|
100
|
+
归档脚本会把 `openspec/changes/<name>/` 移动到 `openspec/changes/archive/YYYY-MM-DD-<name>/`。
|
|
101
|
+
|
|
102
|
+
> **WARNING**: 归档成功后**不要再对原 change 名运行** `node "$COMET_GUARD" <change-name> archive`,因为原活跃目录已经不存在。误调会导致 guard 报错"change directory not found"。归档完整性以脚本退出码和归档目录状态为准。
|
|
103
|
+
|
|
104
|
+
## 完成
|
|
105
|
+
|
|
106
|
+
Comet 流程全部完成。如需开始新工作,调用 `/comet` 或 `/comet-open`。
|
|
107
|
+
|
|
108
|
+
## 上下文压缩恢复
|
|
109
|
+
|
|
110
|
+
按 `comet/reference/context-recovery.md` 执行,phase 参数为 `archive`。若 `archived: true` 且归档目录存在,归档已完成,无需再次执行归档操作。
|
|
@@ -0,0 +1,315 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: comet-build
|
|
3
|
+
description: "Use when full Comet change 已完成 design 阶段,需要创建/恢复实施计划、选择执行方式或继续 build 阶段任务。"
|
|
4
|
+
---
|
|
5
|
+
|
|
6
|
+
# Comet 阶段 3:计划与构建(Build)
|
|
7
|
+
|
|
8
|
+
## 前置条件
|
|
9
|
+
|
|
10
|
+
- Design Doc 已创建(阶段 2 完成)
|
|
11
|
+
- 活跃 change 存在
|
|
12
|
+
|
|
13
|
+
## 步骤
|
|
14
|
+
|
|
15
|
+
### 0. 入口状态验证(Entry Check)
|
|
16
|
+
|
|
17
|
+
按 `comet/reference/scripts.md` 定位脚本(定位 `comet-env.mjs`),然后执行入口验证;从任意入口恢复时先按 `comet/reference/context-recovery.md` 运行恢复检查:
|
|
18
|
+
|
|
19
|
+
```bash
|
|
20
|
+
node "$COMET_STATE" check <name> build
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
验证通过后继续 Step 1。验证失败时脚本会输出具体失败原因。
|
|
24
|
+
|
|
25
|
+
**幂等性**:build 阶段所有操作可安全重复执行。读取 `.comet.yaml` 的 `phase` 字段确认仍在 build 阶段,读取 plan 文件头的 `base-ref`,再用 `grep -n '\- \[ \]' tasks.md | head -1` 找到第一个未勾选任务继续执行。已提交的任务不得重复提交。
|
|
26
|
+
|
|
27
|
+
### 1. 制定计划(Subagent Offload)
|
|
28
|
+
|
|
29
|
+
通过 subagent 创建实施计划,避免 planning skill 占用主 session 上下文。计划文件和执行反馈必须使用触发本次工作流的用户请求语言。
|
|
30
|
+
|
|
31
|
+
**Subagent 指令**:
|
|
32
|
+
|
|
33
|
+
你是实施计划专家。基于以下输入创建实施计划:
|
|
34
|
+
|
|
35
|
+
1. **立即执行:** 使用 Skill 工具加载 Superpowers `writing-plans` 技能。禁止跳过此步骤。技能加载后,ARGUMENTS 必须包含:`Language: 使用触发本次工作流的用户请求语言输出`
|
|
36
|
+
2. 读取 Design Doc(`docs/superpowers/specs/` 下的技术设计文档)
|
|
37
|
+
3. 读取 `openspec/changes/<name>/tasks.md`(任务边界)
|
|
38
|
+
4. 按技能指引创建计划
|
|
39
|
+
|
|
40
|
+
计划要求:
|
|
41
|
+
- 保存至 `docs/superpowers/plans/YYYY-MM-DD-<feature>.md`
|
|
42
|
+
- 引用设计文档,拆分为可执行任务
|
|
43
|
+
- **Plan 文件头必须包含关联元数据**:
|
|
44
|
+
|
|
45
|
+
```yaml
|
|
46
|
+
---
|
|
47
|
+
change: <openspec-change-name>
|
|
48
|
+
design-doc: docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md
|
|
49
|
+
base-ref: <git rev-parse HEAD before implementation>
|
|
50
|
+
---
|
|
51
|
+
```
|
|
52
|
+
|
|
53
|
+
`base-ref` 用于验证阶段跨提交统计改动规模。创建计划时先记录当前提交:
|
|
54
|
+
|
|
55
|
+
```bash
|
|
56
|
+
git rev-parse HEAD
|
|
57
|
+
```
|
|
58
|
+
|
|
59
|
+
将计划写入文件后,返回文件路径。
|
|
60
|
+
|
|
61
|
+
**执行 subagent**:使用当前平台的 subagent 调度机制派发上述任务。
|
|
62
|
+
|
|
63
|
+
Subagent 完成后:
|
|
64
|
+
- 若返回有效文件路径且文件存在,记录为 plan
|
|
65
|
+
- 若 subagent 失败或返回路径无效,在主 session 内联加载 Superpowers `writing-plans` 技能创建计划(降级回退)
|
|
66
|
+
|
|
67
|
+
### 2. 更新计划状态并提供 plan-ready 暂停点
|
|
68
|
+
|
|
69
|
+
先记录 plan 路径:
|
|
70
|
+
|
|
71
|
+
```bash
|
|
72
|
+
node "$COMET_STATE" set <name> plan docs/superpowers/plans/YYYY-MM-DD-feature.md
|
|
73
|
+
```
|
|
74
|
+
|
|
75
|
+
无需手动更新 phase,阶段守卫(guard `--apply`)会在退出条件满足后推进 `phase` 字段。
|
|
76
|
+
|
|
77
|
+
计划写入后,立即提供一个新的用户决策点:
|
|
78
|
+
|
|
79
|
+
| 选项 | 行为 | 说明 |
|
|
80
|
+
|------|------|------|
|
|
81
|
+
| A | 继续执行 | 保持在当前模型中,进入 Step 3 选择工作区隔离、执行方式、TDD 模式和代码审查模式 |
|
|
82
|
+
| B | 暂停切换模型 | 记录 `build_pause: plan-ready`,本次 `/comet-build` 停止,用户稍后可从 `/comet` 或 `/comet-build` 恢复 |
|
|
83
|
+
|
|
84
|
+
这是用户决策点。**必须按 `comet/reference/decision-point.md` 的协议暂停并等待用户明确选择**,不得自动继续,也不得把暂停写入 `build_mode`。
|
|
85
|
+
|
|
86
|
+
用户选择继续时:
|
|
87
|
+
|
|
88
|
+
```bash
|
|
89
|
+
node "$COMET_STATE" set <name> build_pause null
|
|
90
|
+
```
|
|
91
|
+
|
|
92
|
+
用户选择暂停时:
|
|
93
|
+
|
|
94
|
+
```bash
|
|
95
|
+
node "$COMET_STATE" set <name> build_pause plan-ready
|
|
96
|
+
```
|
|
97
|
+
|
|
98
|
+
设置 `build_pause: plan-ready` 后,当前调用停止。不要选择 `isolation` 或 `build_mode`,不要加载执行技能。
|
|
99
|
+
|
|
100
|
+
### 3. 选择工作方式
|
|
101
|
+
|
|
102
|
+
如果恢复时检测到 `build_pause: plan-ready` 且 `plan` 文件存在,不要重新运行 `writing-plans`。先告知用户当前停在 plan-ready 暂停点;用户确认继续后,设置:
|
|
103
|
+
|
|
104
|
+
```bash
|
|
105
|
+
node "$COMET_STATE" set <name> build_pause null
|
|
106
|
+
```
|
|
107
|
+
|
|
108
|
+
然后继续本步骤选择工作区隔离、执行方式、TDD 模式和代码审查模式。
|
|
109
|
+
|
|
110
|
+
计划已写入当前分支。在开始执行前,**一次性询问用户**选择工作区隔离方式、执行方式、TDD 模式和代码审查模式:
|
|
111
|
+
|
|
112
|
+
**工作区隔离**:
|
|
113
|
+
|
|
114
|
+
| 选项 | 方式 | 说明 |
|
|
115
|
+
|------|------|------|
|
|
116
|
+
| A | 创建分支 | 在当前仓库创建新分支,简单快速 |
|
|
117
|
+
| B | 创建 Worktree | 隔离工作区,完全独立,适合并行开发 |
|
|
118
|
+
|
|
119
|
+
**推荐规则**:
|
|
120
|
+
- 变更涉及 ≤ 3 个文件 → 推荐 A
|
|
121
|
+
- 需要并行开发、当前分支有未提交工作 → 推荐 B
|
|
122
|
+
|
|
123
|
+
**执行方式**:
|
|
124
|
+
|
|
125
|
+
| 选项 | 技能 | 适用场景 |
|
|
126
|
+
|------|------|---------|
|
|
127
|
+
| A | Superpowers `subagent-driven-development` | 任务独立、复杂度高;每个任务在隔离的 implementer subagent 中执行,审查由 `review_mode` 驱动 |
|
|
128
|
+
| B | Superpowers `executing-plans` | 任务简单、无子agent环境、轻量快速 |
|
|
129
|
+
|
|
130
|
+
**执行方式推荐规则**:
|
|
131
|
+
- 任务数 ≥ 3 → 推荐 A
|
|
132
|
+
- 任务数 ≤ 2 且无跨模块依赖 → 推荐 B
|
|
133
|
+
- 来自 hotfix 路径 → 推荐 B
|
|
134
|
+
|
|
135
|
+
这是用户决策点。**必须按 `comet/reference/decision-point.md` 的协议暂停并等待用户明确选择隔离方式、执行方式、TDD 模式和代码审查模式**,不得根据推荐规则自行选择 `branch` 或 `worktree`,也不得根据推荐规则自行选择执行方式、TDD 模式或代码审查模式。推荐规则只能用于说明建议,不能替代用户确认。
|
|
136
|
+
|
|
137
|
+
用户选择后,更新 `isolation`、执行方式、TDD 模式和代码审查模式相关字段:
|
|
138
|
+
|
|
139
|
+
```bash
|
|
140
|
+
node "$COMET_STATE" set <name> isolation <branch|worktree>
|
|
141
|
+
```
|
|
142
|
+
|
|
143
|
+
- 若用户选择 `executing-plans`:运行 `node "$COMET_STATE" set <name> subagent_dispatch null`,再运行 `node "$COMET_STATE" set <name> build_mode executing-plans`
|
|
144
|
+
- 若用户选择 `subagent-driven-development`:先确认当前平台存在可调用的真实后台 subagent / Task / multi-agent 调度能力;确认后先运行 `node "$COMET_STATE" set <name> subagent_dispatch confirmed`,再运行 `node "$COMET_STATE" set <name> build_mode subagent-driven-development`
|
|
145
|
+
- 若无法确认真实后台调度能力,不得写入 `build_mode: subagent-driven-development`;必须暂停等待用户改选 `executing-plans`
|
|
146
|
+
|
|
147
|
+
**TDD 模式**:
|
|
148
|
+
|
|
149
|
+
| 选项 | 含义 | 适用场景 |
|
|
150
|
+
|------|------|---------|
|
|
151
|
+
| `tdd` | 每个任务先写失败测试再写实现 | 推荐。变更涉及业务逻辑、新功能、API |
|
|
152
|
+
| `direct` | 直接实现,不强制 TDD 流程 | 变更不需要测试覆盖,或用户选择跳过测试直接写代码。hotfix/tweak 预设默认使用 `direct` |
|
|
153
|
+
|
|
154
|
+
运行 `node "$COMET_STATE" set <name> tdd_mode <tdd|direct>`
|
|
155
|
+
|
|
156
|
+
**代码审查模式**:
|
|
157
|
+
|
|
158
|
+
| 选项 | 含义 | 适用场景 |
|
|
159
|
+
|------|------|---------|
|
|
160
|
+
| `off` | 不自动派发代码审查 | 文档、配置、文案、小范围低风险任务 |
|
|
161
|
+
| `standard` | 默认不为每任务派发 reviewer,仅当任务命中风险信号时派发每任务 reviewer,外加一次最终轻量代码审查 | 默认推荐,适合大多数普通改动 |
|
|
162
|
+
| `thorough` | 为每个任务派发每任务 reviewer(spec + quality),外加一次最终完整审查 | 高风险、多模块、架构或安全相关改动 |
|
|
163
|
+
|
|
164
|
+
运行 `node "$COMET_STATE" set <name> review_mode <off|standard|thorough>`
|
|
165
|
+
|
|
166
|
+
`isolation` 是脚本级硬约束。full workflow 初始化时可以为 `null`,但只允许存在到本步骤之前。若保持 `null`,`build → verify` 的 guard 和 `comet-state transition build-complete` 都会失败。
|
|
167
|
+
|
|
168
|
+
`subagent_dispatch` 是脚本级硬约束。`build_mode: subagent-driven-development` 离开 build 阶段前必须同时满足 `subagent_dispatch: confirmed`,否则 `comet-guard.mjs build --apply` 和 `comet-state transition build-complete` 都会失败。
|
|
169
|
+
|
|
170
|
+
`tdd_mode` 是脚本级硬约束。full workflow 离开 build 阶段前 `tdd_mode` 必须已选择为 `tdd` 或 `direct`,否则 `comet-guard.mjs build --apply` 和 `comet-state transition build-complete` 都会失败。
|
|
171
|
+
|
|
172
|
+
`review_mode` 是脚本级硬约束。新建 full workflow 离开 build 阶段前 `review_mode` 必须已选择为 `off`、`standard` 或 `thorough`,否则 `comet-guard.mjs build --apply` 和 `comet-state transition build-complete` 都会失败。旧状态文件若没有该字段,按兼容路径继续,但恢复时应补写该字段。
|
|
173
|
+
|
|
174
|
+
`build_mode` 默认仅 hotfix/tweak 预设使用 `direct`。full workflow 不得默认使用 `direct`。只有用户明确要求跳过计划执行技能,且你已记录显式 override 时,才允许:
|
|
175
|
+
|
|
176
|
+
```bash
|
|
177
|
+
node "$COMET_STATE" set <name> direct_override true
|
|
178
|
+
node "$COMET_STATE" set <name> build_mode direct
|
|
179
|
+
```
|
|
180
|
+
|
|
181
|
+
没有 `direct_override: true` 时,full workflow 的 `build_mode=direct` 会被 guard 和状态转换同时拦截。
|
|
182
|
+
|
|
183
|
+
**执行隔离**:
|
|
184
|
+
|
|
185
|
+
- **branch**:根据 workflow 类型和当前日期推荐分支名,然后让用户确认或输入自定义名称。这是用户决策点——**必须使用当前平台可用的用户输入/确认机制暂停并等待用户明确确认或覆盖分支名**,不得跳过此步骤直接创建分支。
|
|
186
|
+
|
|
187
|
+
分支命名规范:
|
|
188
|
+
- 读取 `.comet.yaml` 的 `workflow` 字段确定前缀
|
|
189
|
+
- `workflow: full` → 推荐 `feature/YYYYMMDD/<change-name>`
|
|
190
|
+
- `workflow: hotfix` → 推荐 `hotfix/YYYYMMDD/<change-name>`
|
|
191
|
+
- `workflow: tweak` → 推荐 `tweak/YYYYMMDD/<change-name>`
|
|
192
|
+
- 日期取运行时 `date +%Y%m%d` 的结果
|
|
193
|
+
|
|
194
|
+
示例:如果 change 名称为 `fix-login-bug`,今天是 2026-06-09,则推荐 `feature/20260609/fix-login-bug`
|
|
195
|
+
|
|
196
|
+
用户确认或提供自定义分支名后,执行 `git checkout -b <branch-name>`,后续工作在新分支上进行。
|
|
197
|
+
|
|
198
|
+
- **worktree**:必须使用 Skill 工具加载 Superpowers `using-git-worktrees` 技能创建隔离工作区。禁止用普通 shell 命令或原生工具绕过该技能;如该技能不可用,停止流程并提示安装或启用 Superpowers 技能。
|
|
199
|
+
|
|
200
|
+
创建隔离后,确认计划文件可访问(分支方式天然可访问;worktree 方式需确认计划已提交)。若 worktree 模式下计划文件尚未提交,先提交计划文件再创建 worktree:
|
|
201
|
+
|
|
202
|
+
```bash
|
|
203
|
+
git add docs/superpowers/plans/YYYY-MM-DD-feature.md
|
|
204
|
+
git commit -m "chore: add implementation plan"
|
|
205
|
+
```
|
|
206
|
+
|
|
207
|
+
**执行计划**:必须按 `build_mode` 的真实运行位置处理。
|
|
208
|
+
|
|
209
|
+
- `build_mode: executing-plans`:**立即执行:** 使用 Skill 工具加载 Superpowers `executing-plans` 技能。禁止跳过此步骤。若该技能不可用,停止流程并提示安装或启用对应技能,不要用普通对话替代该步骤。技能加载后,ARGUMENTS 必须包含与 Step 1 相同的 Language 约束:`Language: 使用触发本次工作流的用户请求语言输出`。按计划执行。
|
|
210
|
+
- `build_mode: subagent-driven-development`:主会话只负责协调,禁止直接编写实现代码。**立即执行:** 使用 Skill 工具加载 Superpowers `subagent-driven-development` 技能。技能加载后,读取 `comet/reference/subagent-dispatch.md` 获取 Comet 专属扩展(真实后台调度、任务隔离、勾选验证、TDD 约束、连续执行、上下文恢复),与技能工作流配合应用。若两者发生冲突,以更具体的 Comet 扩展为准。
|
|
211
|
+
- 如果当前平台没有真实后台 agent 调度能力,必须暂停并等待用户选择改用主窗口执行。用户选择改用主窗口执行后,必须先运行 `node "$COMET_STATE" set <name> build_mode executing-plans`,再按 `build_mode: executing-plans` 分支加载 Superpowers `executing-plans` 技能。用户未明确选择前,不得继续执行任务。
|
|
212
|
+
|
|
213
|
+
**TDD 模式执行约束**:
|
|
214
|
+
|
|
215
|
+
若 `tdd_mode: tdd`:
|
|
216
|
+
- `build_mode: executing-plans`:加载执行技能后、执行第一个任务前,**立即执行:** 使用 Skill 工具加载 Superpowers `test-driven-development` 技能一次。禁止跳过此步骤。技能加载后,从第一个未勾选任务开始,对每个任务遵循已加载的 TDD Red-Green-Refactor 循环执行。不得跳过失败测试验证阶段。后续任务不再重新加载该技能,直接遵循已加载流程。若上下文压缩后恢复,重新运行本步骤加载 TDD 技能一次,然后从第一个未勾选任务继续。
|
|
217
|
+
- `build_mode: subagent-driven-development`:主会话不加载 TDD skill;TDD 约束和证据门槛已在 `comet/reference/subagent-dispatch.md` 中定义,每个后台 implementer 和修复 agent 必须自行使用 Skill 工具加载 Superpowers `test-driven-development` 技能,并遵循 Comet 注入的 TDD 硬约束。
|
|
218
|
+
|
|
219
|
+
若 `tdd_mode: direct`:按正常流程执行,不强制 TDD。
|
|
220
|
+
|
|
221
|
+
**`executing-plans` review gate**:
|
|
222
|
+
|
|
223
|
+
在 `executing-plans` 下,主会话直接执行任务(没有隔离的 implementer subagent),因此不存在 `subagent-driven-development` 那样的每任务 reviewer。代码审查针对已完成的 diff 进行,并按 `review_mode` 分级:
|
|
224
|
+
|
|
225
|
+
- **`review_mode: off`**:不自动代码审查。不加载 `requesting-code-review`。在验证报告草稿或 tasks.md 中记录跳过原因。
|
|
226
|
+
- **`review_mode: standard`**:在所有计划任务完成后、运行 build → verify 阶段守卫前,使用 Skill 工具加载 Superpowers `requesting-code-review` 技能一次,请求一次轻量代码审查(正确性、安全、边界),范围覆盖整个 change。
|
|
227
|
+
- **`review_mode: thorough`**:除最终那次审查外,按任务分段每 3 个任务请求一次分段代码审查(范围限于该段的 diff)。若总任务数 ≤ 3,跳过执行中分段,只做最终审查。每次分段审查用 `requesting-code-review` 针对该段的提交区间进行。这是 `executing-plans` 下最接近 `subagent-driven-development` 每任务审查的等价物,因为它没有隔离的 implementer 可供逐任务审查。
|
|
228
|
+
|
|
229
|
+
要求(适用于 `standard` 和 `thorough`):
|
|
230
|
+
- `requesting-code-review` 技能必须在 `node "$COMET_GUARD" <change-name> build --apply` 之前加载
|
|
231
|
+
- 若 `requesting-code-review` 技能不可用,跳过 review gate 但必须在 tasks.md 中记录 `<!-- review skipped: skill unavailable -->`,并继续 guard 流转
|
|
232
|
+
- CRITICAL review 发现(安全漏洞、数据丢失风险、构建/测试失败)必须先修复,不得带入 verify
|
|
233
|
+
- 非 CRITICAL review 发现如选择接受,必须在 tasks.md、commit body、验证报告草稿或其他持久产物中记录接受原因和影响范围
|
|
234
|
+
|
|
235
|
+
### 3b. 执行中异常调试(异常调试协议)
|
|
236
|
+
|
|
237
|
+
执行任务期间,只要运行程序、测试、构建或手动验证时出现崩溃、异常行为、测试失败或构建失败,必须使用 Skill 工具加载 Superpowers `systematic-debugging` 技能。在完成根因调查前,不得提出或实施源码修复。
|
|
238
|
+
|
|
239
|
+
具体调查、最小失败测试、修复验证和保持当前 change 验证闭环的要求,按 `comet/reference/debug-gate.md` 执行。
|
|
240
|
+
|
|
241
|
+
### 4. Spec 增量更新
|
|
242
|
+
|
|
243
|
+
实施过程中发现初版 spec 不完整时,按变更规模分级处理:
|
|
244
|
+
|
|
245
|
+
| 规模 | 触发条件 | 做法 |
|
|
246
|
+
|------|---------|------|
|
|
247
|
+
| 小 | 遗漏验收场景、边界条件 | 直接编辑 delta spec + design.md,追加 tasks.md 任务 |
|
|
248
|
+
| 中 | 接口变更、新增组件、数据流变化 | **使用当前平台可用的用户输入/确认机制暂停并等待用户确认后**,必须使用 Skill 工具加载 Superpowers `brainstorming` 更新 Design Doc + delta spec |
|
|
249
|
+
| 大 | 全新 capability 需求 | **必须使用当前平台可用的用户输入/确认机制暂停并等待用户确认拆分**;用户确认后,通过 `/comet-open` 创建独立 change |
|
|
250
|
+
|
|
251
|
+
**50% 阈值判定**:以 tasks.md 初始任务总数为基准,若新增任务数超过该总数的一半,视为超出原计划范围,**必须按 `comet/reference/decision-point.md` 的协议暂停并等待用户决定是否拆分为新 change**。
|
|
252
|
+
|
|
253
|
+
创建独立 change 时必须调用 `/comet-open`,不得直接调用 `/opsx:new`。`/comet-open` 会同时创建 OpenSpec 产物和 `.comet.yaml`,避免新 change 脱离 Comet 状态机。
|
|
254
|
+
|
|
255
|
+
**用户选择必须包含**:
|
|
256
|
+
- 「拆分为新 change」— 通过 `/comet-open` 创建独立 change
|
|
257
|
+
- 「继续在当前 change 内完成」— 记录范围扩展决策,更新 tasks.md 和 delta spec 后继续
|
|
258
|
+
|
|
259
|
+
**原则**:
|
|
260
|
+
- delta spec 是活文档,本阶段期间随时可修改
|
|
261
|
+
- 每次更新应提交,commit message 说明变更原因
|
|
262
|
+
- 不提前同步到 main spec,归档时统一同步
|
|
263
|
+
- 小规模增量直接改 delta spec 时,应在 commit message 中注明,便于归档时判断 design doc 漂移
|
|
264
|
+
|
|
265
|
+
### 5. 上下文管理
|
|
266
|
+
|
|
267
|
+
Build 是最长阶段,可能跨越大量任务。为支持上下文压缩后断点恢复:
|
|
268
|
+
|
|
269
|
+
- **每完成一个 task**:按当前执行分支和 `review_mode` 完成验收后再勾选对应任务并提交。`subagent-driven-development` 在 `off` 时不派发每任务 reviewer;`standard` 下仅当任务命中风险信号时派发;`thorough` 下每个任务都派发每任务 reviewer。所有模式都必须按任务唯一文本完成定向检查。可用 `grep -c '\- \[ \]' tasks.md` 检查剩余未勾选数,无需重新读取整个文件
|
|
270
|
+
- **上下文压缩后恢复**:按 `comet/reference/context-recovery.md` 执行,phase 参数为 `build`。
|
|
271
|
+
- **用户手动修改恢复**:按 `comet/reference/dirty-worktree.md` 协议处理未提交改动。该协议定义了检查步骤、归因分类和禁令。build 阶段的特殊处理:
|
|
272
|
+
1. 归因后,若 diff 暗示计划或 spec 已变化,按 Step 4「Spec 增量更新」分级处理
|
|
273
|
+
- **长任务拆分**:单任务超过 200 行代码变更时,考虑拆分为多个子任务分别提交
|
|
274
|
+
|
|
275
|
+
## 退出条件
|
|
276
|
+
|
|
277
|
+
- tasks.md 全部勾选
|
|
278
|
+
- 代码已提交
|
|
279
|
+
- 已显式运行项目对应的构建/测试命令并通过(不要只依赖 guard 自动猜测)
|
|
280
|
+
- `isolation` 已写为 `branch` 或 `worktree`
|
|
281
|
+
- `build_mode` 已写为 `subagent-driven-development`、`executing-plans` 或带显式 override 的 `direct`;若为 `subagent-driven-development`,`subagent_dispatch` 必须为 `confirmed`
|
|
282
|
+
- `tdd_mode` 已写为 `tdd` 或 `direct`
|
|
283
|
+
- `review_mode` 已写为 `off`、`standard` 或 `thorough`
|
|
284
|
+
- 已按所选 `review_mode` 完成"执行计划"章节中 executing-plans review gate 规定的代码审查:`standard` 或 `thorough` 下已请求代码审查且 CRITICAL review 发现已修复、非 CRITICAL review 发现已记录接受理由;`review_mode: off` 下已在持久产物中记录跳过自动代码审查的原因
|
|
285
|
+
- **阶段守卫**:运行 `node "$COMET_GUARD" <change-name> build --apply`,全部 PASS 后由守卫推进到 `phase: verify`(此步骤更新 `phase` 字段,与 `auto_transition` 无关)
|
|
286
|
+
|
|
287
|
+
Guard 会优先读取项目配置中的命令:
|
|
288
|
+
|
|
289
|
+
```yaml
|
|
290
|
+
build_command: <build command>
|
|
291
|
+
verify_command: <verify command>
|
|
292
|
+
```
|
|
293
|
+
|
|
294
|
+
配置位置可为 change 的 `.comet.yaml`,也可为仓库根目录的 `.comet.yaml` / `comet.yaml` / `.comet.yml` / `comet.yml`。
|
|
295
|
+
配置命令使用受限 shell 语法:允许命令词、引号、路径和用 `&&` 串联的顺序步骤;拒绝 `;`、管道、裸 `&`、`$` 和反引号。未配置时才回退到 `npm run build`、Maven 或 Cargo 的默认探测。构建失败时 guard 会打印失败命令输出,作为排查证据。
|
|
296
|
+
|
|
297
|
+
退出前运行阶段守卫推进 phase(此步骤与 `auto_transition` 无关):
|
|
298
|
+
|
|
299
|
+
```bash
|
|
300
|
+
node "$COMET_GUARD" <change-name> build --apply
|
|
301
|
+
```
|
|
302
|
+
|
|
303
|
+
状态文件自动更新为 `phase: verify`、`verify_result: pending`。
|
|
304
|
+
|
|
305
|
+
## 自动衔接下一阶段
|
|
306
|
+
|
|
307
|
+
按 `comet/reference/auto-transition.md` 执行。关键命令:
|
|
308
|
+
|
|
309
|
+
```bash
|
|
310
|
+
node "$COMET_STATE" next <change-name>
|
|
311
|
+
```
|
|
312
|
+
|
|
313
|
+
- `NEXT: auto` → 调用 `SKILL` 指向的 skill 进入下一阶段
|
|
314
|
+
- `NEXT: manual` → 不要调用下一 skill,按 `HINT` 提示用户手动运行 `/<SKILL>`
|
|
315
|
+
- `NEXT: done` → 流程已完成,无需继续
|