@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 +1,723 @@
|
|
|
1
|
+
const crypto = require('crypto');
|
|
2
|
+
const http = require('http');
|
|
3
|
+
const fs = require('fs');
|
|
4
|
+
const path = require('path');
|
|
5
|
+
|
|
6
|
+
// ========== WebSocket Protocol (RFC 6455) ==========
|
|
7
|
+
|
|
8
|
+
const OPCODES = { TEXT: 0x01, CLOSE: 0x08, PING: 0x09, PONG: 0x0A };
|
|
9
|
+
const WS_MAGIC = '258EAFA5-E914-47DA-95CA-C5AB0DC85B11';
|
|
10
|
+
const MAX_FRAME_PAYLOAD_BYTES = 10 * 1024 * 1024;
|
|
11
|
+
|
|
12
|
+
function computeAcceptKey(clientKey) {
|
|
13
|
+
return crypto.createHash('sha1').update(clientKey + WS_MAGIC).digest('base64');
|
|
14
|
+
}
|
|
15
|
+
|
|
16
|
+
function encodeFrame(opcode, payload) {
|
|
17
|
+
const fin = 0x80;
|
|
18
|
+
const len = payload.length;
|
|
19
|
+
let header;
|
|
20
|
+
|
|
21
|
+
if (len < 126) {
|
|
22
|
+
header = Buffer.alloc(2);
|
|
23
|
+
header[0] = fin | opcode;
|
|
24
|
+
header[1] = len;
|
|
25
|
+
} else if (len < 65536) {
|
|
26
|
+
header = Buffer.alloc(4);
|
|
27
|
+
header[0] = fin | opcode;
|
|
28
|
+
header[1] = 126;
|
|
29
|
+
header.writeUInt16BE(len, 2);
|
|
30
|
+
} else {
|
|
31
|
+
header = Buffer.alloc(10);
|
|
32
|
+
header[0] = fin | opcode;
|
|
33
|
+
header[1] = 127;
|
|
34
|
+
header.writeBigUInt64BE(BigInt(len), 2);
|
|
35
|
+
}
|
|
36
|
+
|
|
37
|
+
return Buffer.concat([header, payload]);
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
function decodeFrame(buffer) {
|
|
41
|
+
if (buffer.length < 2) return null;
|
|
42
|
+
|
|
43
|
+
const secondByte = buffer[1];
|
|
44
|
+
const opcode = buffer[0] & 0x0F;
|
|
45
|
+
const masked = (secondByte & 0x80) !== 0;
|
|
46
|
+
let payloadLen = secondByte & 0x7F;
|
|
47
|
+
let offset = 2;
|
|
48
|
+
|
|
49
|
+
if (!masked) throw new Error('Client frames must be masked');
|
|
50
|
+
|
|
51
|
+
if (payloadLen === 126) {
|
|
52
|
+
if (buffer.length < 4) return null;
|
|
53
|
+
payloadLen = buffer.readUInt16BE(2);
|
|
54
|
+
offset = 4;
|
|
55
|
+
} else if (payloadLen === 127) {
|
|
56
|
+
if (buffer.length < 10) return null;
|
|
57
|
+
const extendedLen = buffer.readBigUInt64BE(2);
|
|
58
|
+
if (extendedLen > BigInt(MAX_FRAME_PAYLOAD_BYTES)) {
|
|
59
|
+
throw new Error('WebSocket frame payload exceeds maximum allowed size');
|
|
60
|
+
}
|
|
61
|
+
payloadLen = Number(extendedLen);
|
|
62
|
+
offset = 10;
|
|
63
|
+
}
|
|
64
|
+
|
|
65
|
+
if (payloadLen > MAX_FRAME_PAYLOAD_BYTES) {
|
|
66
|
+
throw new Error('WebSocket frame payload exceeds maximum allowed size');
|
|
67
|
+
}
|
|
68
|
+
|
|
69
|
+
const maskOffset = offset;
|
|
70
|
+
const dataOffset = offset + 4;
|
|
71
|
+
const totalLen = dataOffset + payloadLen;
|
|
72
|
+
if (buffer.length < totalLen) return null;
|
|
73
|
+
|
|
74
|
+
const mask = buffer.slice(maskOffset, dataOffset);
|
|
75
|
+
const data = Buffer.alloc(payloadLen);
|
|
76
|
+
for (let i = 0; i < payloadLen; i++) {
|
|
77
|
+
data[i] = buffer[dataOffset + i] ^ mask[i % 4];
|
|
78
|
+
}
|
|
79
|
+
|
|
80
|
+
return { opcode, payload: data, bytesConsumed: totalLen };
|
|
81
|
+
}
|
|
82
|
+
|
|
83
|
+
// ========== Configuration ==========
|
|
84
|
+
|
|
85
|
+
const PORT_FILE = process.env.BRAINSTORM_PORT_FILE || null;
|
|
86
|
+
const randomPort = () => 49152 + Math.floor(Math.random() * 16383);
|
|
87
|
+
// Prefer an explicit port, else the port this session last bound (so a restart
|
|
88
|
+
// reuses it and an already-open browser tab reconnects), else a random high port.
|
|
89
|
+
function preferredPort() {
|
|
90
|
+
if (process.env.BRAINSTORM_PORT) return Number(process.env.BRAINSTORM_PORT);
|
|
91
|
+
if (PORT_FILE) {
|
|
92
|
+
try {
|
|
93
|
+
const p = Number(fs.readFileSync(PORT_FILE, 'utf-8').trim());
|
|
94
|
+
if (Number.isInteger(p) && p > 1023 && p < 65536) return p;
|
|
95
|
+
} catch (e) { /* no prior port recorded */ }
|
|
96
|
+
}
|
|
97
|
+
return randomPort();
|
|
98
|
+
}
|
|
99
|
+
let PORT = preferredPort();
|
|
100
|
+
const HOST = process.env.BRAINSTORM_HOST || '127.0.0.1';
|
|
101
|
+
const URL_HOST = process.env.BRAINSTORM_URL_HOST || (HOST === '127.0.0.1' ? 'localhost' : HOST);
|
|
102
|
+
const SESSION_DIR = process.env.BRAINSTORM_DIR || '/tmp/brainstorm';
|
|
103
|
+
const CONTENT_DIR = path.join(SESSION_DIR, 'content');
|
|
104
|
+
const STATE_DIR = path.join(SESSION_DIR, 'state');
|
|
105
|
+
const SUPERPOWERS_VERSION = readSuperpowersVersion();
|
|
106
|
+
const SUPERPOWERS_BRAND_IMAGE_URL = 'https://primeradiant.com/brand/superpowers-visual-brainstorming-logo.png';
|
|
107
|
+
const TELEMETRY_DISABLE_ENV_VARS = [
|
|
108
|
+
'SUPERPOWERS_DISABLE_TELEMETRY',
|
|
109
|
+
'DISABLE_TELEMETRY',
|
|
110
|
+
'CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC'
|
|
111
|
+
];
|
|
112
|
+
const SUPERPOWERS_TELEMETRY_DISABLED = TELEMETRY_DISABLE_ENV_VARS.some(name => isTruthyEnv(process.env[name]));
|
|
113
|
+
let ownerPid = process.env.BRAINSTORM_OWNER_PID ? Number(process.env.BRAINSTORM_OWNER_PID) : null;
|
|
114
|
+
|
|
115
|
+
// Per-session secret key. The companion is reachable by any local browser tab
|
|
116
|
+
// and, when bound to a non-loopback host, by any host that can route to it.
|
|
117
|
+
// The key authenticates the real client uniformly across loopback, tunnel, and
|
|
118
|
+
// remote binds — and defeats DNS rebinding — where a Host/Origin allowlist
|
|
119
|
+
// cannot. It rides the served URL as ?key= and is mirrored into a cookie on
|
|
120
|
+
// first load so same-origin subresources and the WebSocket carry it for free.
|
|
121
|
+
// Persisted alongside the port (BRAINSTORM_TOKEN_FILE) so a restart keeps the
|
|
122
|
+
// same key and an already-open tab's cookie still validates.
|
|
123
|
+
const TOKEN_FILE = process.env.BRAINSTORM_TOKEN_FILE || null;
|
|
124
|
+
function generateToken() {
|
|
125
|
+
return crypto.randomBytes(32).toString('hex');
|
|
126
|
+
}
|
|
127
|
+
|
|
128
|
+
function chmodOwnerOnly(file) {
|
|
129
|
+
try { fs.chmodSync(file, 0o600); } catch (e) { /* best effort */ }
|
|
130
|
+
}
|
|
131
|
+
|
|
132
|
+
function initialToken() {
|
|
133
|
+
if (process.env.BRAINSTORM_TOKEN) {
|
|
134
|
+
return { value: process.env.BRAINSTORM_TOKEN, source: 'env' };
|
|
135
|
+
}
|
|
136
|
+
if (TOKEN_FILE) {
|
|
137
|
+
try {
|
|
138
|
+
const t = fs.readFileSync(TOKEN_FILE, 'utf-8').trim();
|
|
139
|
+
if (/^[0-9a-f]{32,}$/i.test(t)) {
|
|
140
|
+
chmodOwnerOnly(TOKEN_FILE);
|
|
141
|
+
return { value: t, source: 'file' };
|
|
142
|
+
}
|
|
143
|
+
} catch (e) { /* no prior token recorded */ }
|
|
144
|
+
}
|
|
145
|
+
return { value: generateToken(), source: 'generated' };
|
|
146
|
+
}
|
|
147
|
+
|
|
148
|
+
const tokenInfo = initialToken();
|
|
149
|
+
let TOKEN = tokenInfo.value;
|
|
150
|
+
let tokenSource = tokenInfo.source;
|
|
151
|
+
let COOKIE_NAME = 'brainstorm-key-' + PORT; // refined to the actual bound port in onListen
|
|
152
|
+
|
|
153
|
+
const MIME_TYPES = {
|
|
154
|
+
'.html': 'text/html', '.css': 'text/css', '.js': 'application/javascript',
|
|
155
|
+
'.json': 'application/json', '.png': 'image/png', '.jpg': 'image/jpeg',
|
|
156
|
+
'.jpeg': 'image/jpeg', '.gif': 'image/gif', '.svg': 'image/svg+xml'
|
|
157
|
+
};
|
|
158
|
+
|
|
159
|
+
// ========== Templates and Constants ==========
|
|
160
|
+
|
|
161
|
+
function waitingPage() {
|
|
162
|
+
return renderBranding(`<!DOCTYPE html>
|
|
163
|
+
<html>
|
|
164
|
+
<head><meta charset="utf-8"><title>Brainstorm Companion</title>
|
|
165
|
+
<style>
|
|
166
|
+
body { font-family: system-ui, sans-serif; padding: 2rem; max-width: 800px; margin: 0 auto; }
|
|
167
|
+
h1 { color: #333; } p { color: #666; }
|
|
168
|
+
.brand { display: flex; align-items: center; min-width: 0; overflow: hidden; margin-bottom: 1.5rem; color: #666; font-size: 0.9rem; line-height: 1; }
|
|
169
|
+
.brand a { color: inherit; text-decoration: none; display: flex; align-items: center; gap: 0.5rem; min-width: 0; max-width: 100%; line-height: 1; }
|
|
170
|
+
.brand-copy { display: block; min-width: 0; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; line-height: 1; transform: translateY(-1px); }
|
|
171
|
+
.brand-logo { display: block; height: 1em; width: auto; max-width: 180px; filter: invert(1); }
|
|
172
|
+
</style>
|
|
173
|
+
</head>
|
|
174
|
+
<body><!-- BRANDING --><h1>Brainstorm Companion</h1>
|
|
175
|
+
<p>Waiting for the agent to push a screen...</p></body></html>`);
|
|
176
|
+
}
|
|
177
|
+
|
|
178
|
+
const FORBIDDEN_PAGE = `<!DOCTYPE html>
|
|
179
|
+
<html>
|
|
180
|
+
<head><meta charset="utf-8"><title>Session key required</title>
|
|
181
|
+
<style>body { font-family: system-ui, sans-serif; padding: 2rem; max-width: 800px; margin: 0 auto; }
|
|
182
|
+
h1 { color: #333; } p { color: #666; } code { background: #f0f0f0; padding: 0.1em 0.3em; border-radius: 4px; }</style>
|
|
183
|
+
</head>
|
|
184
|
+
<body><h1>Session key required</h1>
|
|
185
|
+
<p>This page needs the full URL your coding agent gave you, including the
|
|
186
|
+
<code>?key=…</code> part. Copy the complete URL and open it again.</p></body></html>`;
|
|
187
|
+
|
|
188
|
+
function bootstrapPage(key) {
|
|
189
|
+
const jsonKey = JSON.stringify(String(key));
|
|
190
|
+
return `<!DOCTYPE html>
|
|
191
|
+
<html>
|
|
192
|
+
<head><meta charset="utf-8"><title>Opening Brainstorm Companion</title></head>
|
|
193
|
+
<body>
|
|
194
|
+
<script>
|
|
195
|
+
try { sessionStorage.setItem('brainstorm-session-key', ${jsonKey}); } catch (e) {}
|
|
196
|
+
location.replace('/');
|
|
197
|
+
</script>
|
|
198
|
+
</body>
|
|
199
|
+
</html>`;
|
|
200
|
+
}
|
|
201
|
+
|
|
202
|
+
const frameTemplate = fs.readFileSync(path.join(__dirname, 'frame-template.html'), 'utf-8');
|
|
203
|
+
const helperScript = fs.readFileSync(path.join(__dirname, 'helper.js'), 'utf-8');
|
|
204
|
+
const helperInjection = '<script>\n' + helperScript + '\n</script>';
|
|
205
|
+
|
|
206
|
+
// ========== Helper Functions ==========
|
|
207
|
+
|
|
208
|
+
function readSuperpowersVersion() {
|
|
209
|
+
const root = path.join(__dirname, '../../..');
|
|
210
|
+
const manifests = [
|
|
211
|
+
path.join(root, 'package.json'),
|
|
212
|
+
path.join(root, '.codex-plugin/plugin.json')
|
|
213
|
+
];
|
|
214
|
+
|
|
215
|
+
for (const manifest of manifests) {
|
|
216
|
+
try {
|
|
217
|
+
const data = JSON.parse(fs.readFileSync(manifest, 'utf-8'));
|
|
218
|
+
if (data.version) return String(data.version);
|
|
219
|
+
} catch (e) {
|
|
220
|
+
// Packaged Codex plugins omit package.json; try the next manifest.
|
|
221
|
+
}
|
|
222
|
+
}
|
|
223
|
+
|
|
224
|
+
return 'unknown';
|
|
225
|
+
}
|
|
226
|
+
|
|
227
|
+
function isTruthyEnv(value) {
|
|
228
|
+
if (!value) return false;
|
|
229
|
+
const normalized = String(value).trim().toLowerCase();
|
|
230
|
+
if (!normalized) return false;
|
|
231
|
+
return !['0', 'false', 'no', 'off'].includes(normalized);
|
|
232
|
+
}
|
|
233
|
+
|
|
234
|
+
function escapeHtmlText(value) {
|
|
235
|
+
return String(value)
|
|
236
|
+
.replace(/&/g, '&')
|
|
237
|
+
.replace(/</g, '<')
|
|
238
|
+
.replace(/>/g, '>')
|
|
239
|
+
.replace(/"/g, '"');
|
|
240
|
+
}
|
|
241
|
+
|
|
242
|
+
function brandMarkup() {
|
|
243
|
+
const version = escapeHtmlText(SUPERPOWERS_VERSION);
|
|
244
|
+
const text = SUPERPOWERS_TELEMETRY_DISABLED
|
|
245
|
+
? 'Prime Radiant Superpowers v' + version
|
|
246
|
+
: 'Superpowers v' + version;
|
|
247
|
+
const logo = SUPERPOWERS_TELEMETRY_DISABLED
|
|
248
|
+
? ''
|
|
249
|
+
: '<img class="brand-logo" src="' + SUPERPOWERS_BRAND_IMAGE_URL + '?v=' + encodeURIComponent(SUPERPOWERS_VERSION) + '" alt="Prime Radiant" referrerpolicy="no-referrer" decoding="async">';
|
|
250
|
+
|
|
251
|
+
return '<div class="brand"><a href="https://github.com/obra/superpowers">' + logo + '<span class="brand-copy">' + text + '</span></a></div>';
|
|
252
|
+
}
|
|
253
|
+
|
|
254
|
+
function renderBranding(html) {
|
|
255
|
+
return html.split('<!-- BRANDING -->').join(brandMarkup());
|
|
256
|
+
}
|
|
257
|
+
|
|
258
|
+
function isFullDocument(html) {
|
|
259
|
+
const trimmed = html.trimStart().toLowerCase();
|
|
260
|
+
return trimmed.startsWith('<!doctype') || trimmed.startsWith('<html');
|
|
261
|
+
}
|
|
262
|
+
|
|
263
|
+
function wrapInFrame(content) {
|
|
264
|
+
return renderBranding(frameTemplate).replace('<!-- CONTENT -->', content);
|
|
265
|
+
}
|
|
266
|
+
|
|
267
|
+
function getNewestScreen() {
|
|
268
|
+
const files = fs.readdirSync(CONTENT_DIR)
|
|
269
|
+
.filter(f => !f.startsWith('.') && f.endsWith('.html'))
|
|
270
|
+
.map(f => {
|
|
271
|
+
const fp = path.join(CONTENT_DIR, f);
|
|
272
|
+
if (!isRegularFileInsideContentDir(fp)) return null;
|
|
273
|
+
return { path: fp, mtime: fs.statSync(fp).mtime.getTime() };
|
|
274
|
+
})
|
|
275
|
+
.filter(Boolean)
|
|
276
|
+
.sort((a, b) => b.mtime - a.mtime);
|
|
277
|
+
return files.length > 0 ? files[0].path : null;
|
|
278
|
+
}
|
|
279
|
+
|
|
280
|
+
function urlHostForHttp(host) {
|
|
281
|
+
const h = String(host);
|
|
282
|
+
if (h.startsWith('[') && h.endsWith(']')) return h;
|
|
283
|
+
return h.includes(':') ? '[' + h + ']' : h;
|
|
284
|
+
}
|
|
285
|
+
|
|
286
|
+
function companionUrl() {
|
|
287
|
+
return 'http://' + urlHostForHttp(URL_HOST) + ':' + PORT + '/?key=' + TOKEN;
|
|
288
|
+
}
|
|
289
|
+
|
|
290
|
+
function browserLauncherForPlatform(url, {
|
|
291
|
+
platform = process.platform,
|
|
292
|
+
osRelease = require('os').release(),
|
|
293
|
+
env = process.env
|
|
294
|
+
} = {}) {
|
|
295
|
+
const isWSL = platform === 'linux' && /microsoft/i.test(osRelease);
|
|
296
|
+
if (platform === 'darwin') return { bin: 'open', args: [url] };
|
|
297
|
+
if (platform === 'win32' || isWSL) {
|
|
298
|
+
return { bin: 'rundll32.exe', args: ['url.dll,FileProtocolHandler', url] };
|
|
299
|
+
}
|
|
300
|
+
if (env.DISPLAY || env.WAYLAND_DISPLAY) return { bin: 'xdg-open', args: [url] };
|
|
301
|
+
return null;
|
|
302
|
+
}
|
|
303
|
+
|
|
304
|
+
function isRegularFileInsideContentDir(filePath) {
|
|
305
|
+
let stat, realContentDir, realFilePath;
|
|
306
|
+
try {
|
|
307
|
+
stat = fs.lstatSync(filePath);
|
|
308
|
+
if (stat.isSymbolicLink()) return false;
|
|
309
|
+
if (!stat.isFile()) return false;
|
|
310
|
+
if (stat.nlink !== 1) return false;
|
|
311
|
+
realContentDir = fs.realpathSync(CONTENT_DIR);
|
|
312
|
+
realFilePath = fs.realpathSync(filePath);
|
|
313
|
+
} catch (e) {
|
|
314
|
+
return false;
|
|
315
|
+
}
|
|
316
|
+
return realFilePath.startsWith(realContentDir + path.sep);
|
|
317
|
+
}
|
|
318
|
+
|
|
319
|
+
// ========== Authentication ==========
|
|
320
|
+
|
|
321
|
+
function timingSafeEqualStr(a, b) {
|
|
322
|
+
const ab = Buffer.from(String(a));
|
|
323
|
+
const bb = Buffer.from(String(b));
|
|
324
|
+
if (ab.length !== bb.length) return false;
|
|
325
|
+
return crypto.timingSafeEqual(ab, bb);
|
|
326
|
+
}
|
|
327
|
+
|
|
328
|
+
function parseCookies(header) {
|
|
329
|
+
const out = {};
|
|
330
|
+
if (!header) return out;
|
|
331
|
+
for (const part of header.split(';')) {
|
|
332
|
+
const eq = part.indexOf('=');
|
|
333
|
+
if (eq < 0) continue;
|
|
334
|
+
out[part.slice(0, eq).trim()] = part.slice(eq + 1).trim();
|
|
335
|
+
}
|
|
336
|
+
return out;
|
|
337
|
+
}
|
|
338
|
+
|
|
339
|
+
// A request is authorized if it carries the session key as ?key= or as the
|
|
340
|
+
// session cookie. Both are compared in constant time.
|
|
341
|
+
function isAuthorized(req) {
|
|
342
|
+
const q = req.url.indexOf('?');
|
|
343
|
+
if (q >= 0) {
|
|
344
|
+
const params = new URLSearchParams(req.url.slice(q + 1));
|
|
345
|
+
if (params.has('key')) {
|
|
346
|
+
const key = params.get('key');
|
|
347
|
+
return Boolean(key && timingSafeEqualStr(key, TOKEN));
|
|
348
|
+
}
|
|
349
|
+
}
|
|
350
|
+
const cookie = parseCookies(req.headers['cookie'])[COOKIE_NAME];
|
|
351
|
+
if (cookie && timingSafeEqualStr(cookie, TOKEN)) return true;
|
|
352
|
+
return false;
|
|
353
|
+
}
|
|
354
|
+
|
|
355
|
+
function pathnameOf(url) {
|
|
356
|
+
const q = url.indexOf('?');
|
|
357
|
+
return q >= 0 ? url.slice(0, q) : url;
|
|
358
|
+
}
|
|
359
|
+
|
|
360
|
+
function queryKey(url) {
|
|
361
|
+
const q = url.indexOf('?');
|
|
362
|
+
if (q < 0) return null;
|
|
363
|
+
return new URLSearchParams(url.slice(q + 1)).get('key');
|
|
364
|
+
}
|
|
365
|
+
|
|
366
|
+
function securityHeaders(headers = {}) {
|
|
367
|
+
return {
|
|
368
|
+
'Referrer-Policy': 'no-referrer',
|
|
369
|
+
'Cache-Control': 'no-store',
|
|
370
|
+
'X-Frame-Options': 'DENY',
|
|
371
|
+
'Content-Security-Policy': "frame-ancestors 'none'",
|
|
372
|
+
'Cross-Origin-Resource-Policy': 'same-origin',
|
|
373
|
+
...headers
|
|
374
|
+
};
|
|
375
|
+
}
|
|
376
|
+
|
|
377
|
+
function isAllowedWebSocketOrigin(req) {
|
|
378
|
+
const origin = req.headers.origin;
|
|
379
|
+
if (!origin) return true;
|
|
380
|
+
const host = req.headers.host;
|
|
381
|
+
if (!host) return false;
|
|
382
|
+
return origin === 'http://' + host;
|
|
383
|
+
}
|
|
384
|
+
|
|
385
|
+
// ========== HTTP Request Handler ==========
|
|
386
|
+
|
|
387
|
+
function handleRequest(req, res) {
|
|
388
|
+
if (!isAuthorized(req)) {
|
|
389
|
+
res.writeHead(403, securityHeaders({ 'Content-Type': 'text/html; charset=utf-8' }));
|
|
390
|
+
res.end(FORBIDDEN_PAGE);
|
|
391
|
+
return;
|
|
392
|
+
}
|
|
393
|
+
touchActivity(); // only authorized requests count as activity
|
|
394
|
+
|
|
395
|
+
// Mirror the key into a cookie so same-origin subresources (/files/*) can
|
|
396
|
+
// authenticate after bootstrap. HttpOnly keeps it away from page scripts; the
|
|
397
|
+
// WebSocket Origin check below is what blocks cross-origin localhost injection.
|
|
398
|
+
res.setHeader('Set-Cookie',
|
|
399
|
+
COOKIE_NAME + '=' + TOKEN + '; HttpOnly; SameSite=Strict; Path=/');
|
|
400
|
+
|
|
401
|
+
const pathname = pathnameOf(req.url);
|
|
402
|
+
const keyFromQuery = queryKey(req.url);
|
|
403
|
+
if (req.method === 'GET' && pathname === '/' && keyFromQuery && timingSafeEqualStr(keyFromQuery, TOKEN)) {
|
|
404
|
+
res.writeHead(200, securityHeaders({ 'Content-Type': 'text/html; charset=utf-8' }));
|
|
405
|
+
res.end(bootstrapPage(keyFromQuery));
|
|
406
|
+
} else if (req.method === 'GET' && pathname === '/') {
|
|
407
|
+
const screenFile = getNewestScreen();
|
|
408
|
+
let html = screenFile
|
|
409
|
+
? (raw => isFullDocument(raw) ? raw : wrapInFrame(raw))(fs.readFileSync(screenFile, 'utf-8'))
|
|
410
|
+
: waitingPage();
|
|
411
|
+
|
|
412
|
+
if (html.includes('</body>')) {
|
|
413
|
+
html = html.replace('</body>', helperInjection + '\n</body>');
|
|
414
|
+
} else {
|
|
415
|
+
html += helperInjection;
|
|
416
|
+
}
|
|
417
|
+
|
|
418
|
+
res.writeHead(200, securityHeaders({ 'Content-Type': 'text/html; charset=utf-8' }));
|
|
419
|
+
res.end(html);
|
|
420
|
+
} else if (req.method === 'GET' && pathname.startsWith('/files/')) {
|
|
421
|
+
const fileName = path.basename(pathname.slice(7));
|
|
422
|
+
const filePath = path.join(CONTENT_DIR, fileName);
|
|
423
|
+
// Reject empty/dotfile names and anything that isn't a regular file —
|
|
424
|
+
// `/files/` would otherwise resolve to CONTENT_DIR and crash readFileSync (EISDIR).
|
|
425
|
+
if (!fileName || fileName.startsWith('.') || !isRegularFileInsideContentDir(filePath)) {
|
|
426
|
+
res.writeHead(404, securityHeaders());
|
|
427
|
+
res.end('Not found');
|
|
428
|
+
return;
|
|
429
|
+
}
|
|
430
|
+
const ext = path.extname(filePath).toLowerCase();
|
|
431
|
+
const contentType = MIME_TYPES[ext] || 'application/octet-stream';
|
|
432
|
+
res.writeHead(200, securityHeaders({ 'Content-Type': contentType }));
|
|
433
|
+
res.end(fs.readFileSync(filePath));
|
|
434
|
+
} else {
|
|
435
|
+
res.writeHead(404, securityHeaders());
|
|
436
|
+
res.end('Not found');
|
|
437
|
+
}
|
|
438
|
+
}
|
|
439
|
+
|
|
440
|
+
// ========== WebSocket Connection Handling ==========
|
|
441
|
+
|
|
442
|
+
const clients = new Set();
|
|
443
|
+
|
|
444
|
+
function handleUpgrade(req, socket) {
|
|
445
|
+
if (!isAuthorized(req) || !isAllowedWebSocketOrigin(req)) { socket.destroy(); return; }
|
|
446
|
+
|
|
447
|
+
const key = req.headers['sec-websocket-key'];
|
|
448
|
+
if (!key) { socket.destroy(); return; }
|
|
449
|
+
|
|
450
|
+
const accept = computeAcceptKey(key);
|
|
451
|
+
socket.write(
|
|
452
|
+
'HTTP/1.1 101 Switching Protocols\r\n' +
|
|
453
|
+
'Upgrade: websocket\r\n' +
|
|
454
|
+
'Connection: Upgrade\r\n' +
|
|
455
|
+
'Sec-WebSocket-Accept: ' + accept + '\r\n\r\n'
|
|
456
|
+
);
|
|
457
|
+
|
|
458
|
+
let buffer = Buffer.alloc(0);
|
|
459
|
+
clients.add(socket);
|
|
460
|
+
|
|
461
|
+
socket.on('data', (chunk) => {
|
|
462
|
+
buffer = Buffer.concat([buffer, chunk]);
|
|
463
|
+
while (buffer.length > 0) {
|
|
464
|
+
let result;
|
|
465
|
+
try {
|
|
466
|
+
result = decodeFrame(buffer);
|
|
467
|
+
} catch (e) {
|
|
468
|
+
socket.end(encodeFrame(OPCODES.CLOSE, Buffer.alloc(0)));
|
|
469
|
+
clients.delete(socket);
|
|
470
|
+
return;
|
|
471
|
+
}
|
|
472
|
+
if (!result) break;
|
|
473
|
+
buffer = buffer.slice(result.bytesConsumed);
|
|
474
|
+
|
|
475
|
+
switch (result.opcode) {
|
|
476
|
+
case OPCODES.TEXT:
|
|
477
|
+
handleMessage(result.payload.toString());
|
|
478
|
+
break;
|
|
479
|
+
case OPCODES.CLOSE:
|
|
480
|
+
socket.end(encodeFrame(OPCODES.CLOSE, Buffer.alloc(0)));
|
|
481
|
+
clients.delete(socket);
|
|
482
|
+
return;
|
|
483
|
+
case OPCODES.PING:
|
|
484
|
+
socket.write(encodeFrame(OPCODES.PONG, result.payload));
|
|
485
|
+
break;
|
|
486
|
+
case OPCODES.PONG:
|
|
487
|
+
break;
|
|
488
|
+
default: {
|
|
489
|
+
const closeBuf = Buffer.alloc(2);
|
|
490
|
+
closeBuf.writeUInt16BE(1003);
|
|
491
|
+
socket.end(encodeFrame(OPCODES.CLOSE, closeBuf));
|
|
492
|
+
clients.delete(socket);
|
|
493
|
+
return;
|
|
494
|
+
}
|
|
495
|
+
}
|
|
496
|
+
}
|
|
497
|
+
});
|
|
498
|
+
|
|
499
|
+
socket.on('close', () => clients.delete(socket));
|
|
500
|
+
socket.on('error', () => clients.delete(socket));
|
|
501
|
+
}
|
|
502
|
+
|
|
503
|
+
function handleMessage(text) {
|
|
504
|
+
let event;
|
|
505
|
+
try {
|
|
506
|
+
event = JSON.parse(text);
|
|
507
|
+
} catch (e) {
|
|
508
|
+
console.error('Failed to parse WebSocket message:', e.message);
|
|
509
|
+
return;
|
|
510
|
+
}
|
|
511
|
+
touchActivity();
|
|
512
|
+
console.log(JSON.stringify({ source: 'user-event', ...event }));
|
|
513
|
+
if (event && event.choice) {
|
|
514
|
+
const eventsFile = path.join(STATE_DIR, 'events');
|
|
515
|
+
fs.appendFileSync(eventsFile, JSON.stringify(event) + '\n');
|
|
516
|
+
}
|
|
517
|
+
}
|
|
518
|
+
|
|
519
|
+
function broadcast(msg) {
|
|
520
|
+
const frame = encodeFrame(OPCODES.TEXT, Buffer.from(JSON.stringify(msg)));
|
|
521
|
+
for (const socket of clients) {
|
|
522
|
+
try { socket.write(frame); } catch (e) { clients.delete(socket); }
|
|
523
|
+
}
|
|
524
|
+
}
|
|
525
|
+
|
|
526
|
+
// Best-effort: open the user's browser the first time a screen is actually ready
|
|
527
|
+
// to show. Skips when disabled, on a non-loopback (remote) bind, or when a
|
|
528
|
+
// browser is already connected. Override the launcher with BRAINSTORM_OPEN_CMD.
|
|
529
|
+
let browserOpened = false;
|
|
530
|
+
function maybeOpenBrowser() {
|
|
531
|
+
if (browserOpened) return;
|
|
532
|
+
browserOpened = true;
|
|
533
|
+
if (!process.env.BRAINSTORM_OPEN) return; // opt-in: only after the user approves the companion
|
|
534
|
+
if (HOST !== '127.0.0.1' && HOST !== 'localhost') return;
|
|
535
|
+
if (clients.size > 0) return; // the user already opened it
|
|
536
|
+
const url = companionUrl(); // must carry the key or the gate 403s it
|
|
537
|
+
const cp = require('child_process');
|
|
538
|
+
// Operator-provided launcher: run as given (this env var is trusted operator input).
|
|
539
|
+
if (process.env.BRAINSTORM_OPEN_CMD) {
|
|
540
|
+
try { cp.exec(process.env.BRAINSTORM_OPEN_CMD + ' ' + JSON.stringify(url), () => {}); } catch (e) { /* best effort */ }
|
|
541
|
+
return;
|
|
542
|
+
}
|
|
543
|
+
// Platform launchers: pass the URL as an argv element via execFile (no shell),
|
|
544
|
+
// so a url-host containing shell metacharacters can't inject a command.
|
|
545
|
+
const launcher = browserLauncherForPlatform(url);
|
|
546
|
+
if (!launcher) return; // headless: nothing to open
|
|
547
|
+
try { cp.execFile(launcher.bin, launcher.args, () => {}); } catch (e) { /* best effort */ }
|
|
548
|
+
}
|
|
549
|
+
|
|
550
|
+
// ========== Activity Tracking ==========
|
|
551
|
+
|
|
552
|
+
// Idle timeout: shut down after this long with no activity. Default 4 hours;
|
|
553
|
+
// override with BRAINSTORM_IDLE_TIMEOUT_MS (start-server.sh: --idle-timeout-minutes).
|
|
554
|
+
const IDLE_TIMEOUT_MS = (() => {
|
|
555
|
+
const ms = Number(process.env.BRAINSTORM_IDLE_TIMEOUT_MS);
|
|
556
|
+
return Number.isFinite(ms) && ms > 0 ? ms : 4 * 60 * 60 * 1000;
|
|
557
|
+
})();
|
|
558
|
+
// How often the watchdog checks for owner-death / idleness. Configurable mainly
|
|
559
|
+
// so tests can run fast; production default is 60s.
|
|
560
|
+
const LIFECYCLE_CHECK_MS = (() => {
|
|
561
|
+
const ms = Number(process.env.BRAINSTORM_LIFECYCLE_CHECK_MS);
|
|
562
|
+
return Number.isFinite(ms) && ms > 0 ? ms : 60 * 1000;
|
|
563
|
+
})();
|
|
564
|
+
let lastActivity = Date.now();
|
|
565
|
+
|
|
566
|
+
function touchActivity() {
|
|
567
|
+
lastActivity = Date.now();
|
|
568
|
+
}
|
|
569
|
+
|
|
570
|
+
// ========== File Watching ==========
|
|
571
|
+
|
|
572
|
+
const debounceTimers = new Map();
|
|
573
|
+
|
|
574
|
+
// ========== Server Startup ==========
|
|
575
|
+
|
|
576
|
+
function startServer() {
|
|
577
|
+
if (!fs.existsSync(CONTENT_DIR)) fs.mkdirSync(CONTENT_DIR, { recursive: true });
|
|
578
|
+
if (!fs.existsSync(STATE_DIR)) fs.mkdirSync(STATE_DIR, { recursive: true });
|
|
579
|
+
|
|
580
|
+
// Track known files to distinguish new screens from updates.
|
|
581
|
+
// macOS fs.watch reports 'rename' for both new files and overwrites,
|
|
582
|
+
// so we can't rely on eventType alone.
|
|
583
|
+
const knownFiles = new Set(
|
|
584
|
+
fs.readdirSync(CONTENT_DIR).filter(f => !f.startsWith('.') && f.endsWith('.html'))
|
|
585
|
+
);
|
|
586
|
+
|
|
587
|
+
const server = http.createServer(handleRequest);
|
|
588
|
+
server.on('upgrade', handleUpgrade);
|
|
589
|
+
|
|
590
|
+
const watcher = fs.watch(CONTENT_DIR, (eventType, filename) => {
|
|
591
|
+
if (!filename || filename.startsWith('.') || !filename.endsWith('.html')) return;
|
|
592
|
+
|
|
593
|
+
if (debounceTimers.has(filename)) clearTimeout(debounceTimers.get(filename));
|
|
594
|
+
debounceTimers.set(filename, setTimeout(() => {
|
|
595
|
+
debounceTimers.delete(filename);
|
|
596
|
+
const filePath = path.join(CONTENT_DIR, filename);
|
|
597
|
+
|
|
598
|
+
if (!fs.existsSync(filePath)) return; // file was deleted
|
|
599
|
+
touchActivity();
|
|
600
|
+
|
|
601
|
+
if (!knownFiles.has(filename)) {
|
|
602
|
+
knownFiles.add(filename);
|
|
603
|
+
const eventsFile = path.join(STATE_DIR, 'events');
|
|
604
|
+
if (fs.existsSync(eventsFile)) fs.unlinkSync(eventsFile);
|
|
605
|
+
console.log(JSON.stringify({ type: 'screen-added', file: filePath }));
|
|
606
|
+
maybeOpenBrowser();
|
|
607
|
+
} else {
|
|
608
|
+
console.log(JSON.stringify({ type: 'screen-updated', file: filePath }));
|
|
609
|
+
}
|
|
610
|
+
|
|
611
|
+
broadcast({ type: 'reload' });
|
|
612
|
+
}, 100));
|
|
613
|
+
});
|
|
614
|
+
watcher.on('error', (err) => console.error('fs.watch error:', err.message));
|
|
615
|
+
|
|
616
|
+
function shutdown(reason) {
|
|
617
|
+
console.log(JSON.stringify({ type: 'server-stopped', reason }));
|
|
618
|
+
const infoFile = path.join(STATE_DIR, 'server-info');
|
|
619
|
+
if (fs.existsSync(infoFile)) fs.unlinkSync(infoFile);
|
|
620
|
+
fs.writeFileSync(
|
|
621
|
+
path.join(STATE_DIR, 'server-stopped'),
|
|
622
|
+
JSON.stringify({ reason, timestamp: Date.now() }) + '\n'
|
|
623
|
+
);
|
|
624
|
+
watcher.close();
|
|
625
|
+
clearInterval(lifecycleCheck);
|
|
626
|
+
// Close any upgraded WebSocket sockets so server.close() can complete and
|
|
627
|
+
// the process actually exits instead of lingering on an open connection.
|
|
628
|
+
for (const socket of clients) {
|
|
629
|
+
try { socket.destroy(); } catch (e) { /* already gone */ }
|
|
630
|
+
}
|
|
631
|
+
server.close(() => process.exit(0));
|
|
632
|
+
}
|
|
633
|
+
|
|
634
|
+
function ownerAlive() {
|
|
635
|
+
if (!ownerPid) return true;
|
|
636
|
+
try { process.kill(ownerPid, 0); return true; } catch (e) { return e.code === 'EPERM'; }
|
|
637
|
+
}
|
|
638
|
+
|
|
639
|
+
// Periodically exit if the owner process died or we've been idle too long.
|
|
640
|
+
const lifecycleCheck = setInterval(() => {
|
|
641
|
+
if (!ownerAlive()) shutdown('owner process exited');
|
|
642
|
+
else if (Date.now() - lastActivity > IDLE_TIMEOUT_MS) shutdown('idle timeout');
|
|
643
|
+
}, LIFECYCLE_CHECK_MS);
|
|
644
|
+
lifecycleCheck.unref();
|
|
645
|
+
|
|
646
|
+
// Validate owner PID at startup. If it's already dead, the PID resolution
|
|
647
|
+
// was wrong (common on WSL, Tailscale SSH, and cross-user scenarios).
|
|
648
|
+
// Disable monitoring and rely on the idle timeout instead.
|
|
649
|
+
if (ownerPid) {
|
|
650
|
+
try { process.kill(ownerPid, 0); }
|
|
651
|
+
catch (e) {
|
|
652
|
+
if (e.code !== 'EPERM') {
|
|
653
|
+
console.log(JSON.stringify({ type: 'owner-pid-invalid', pid: ownerPid, reason: 'dead at startup' }));
|
|
654
|
+
ownerPid = null;
|
|
655
|
+
}
|
|
656
|
+
}
|
|
657
|
+
}
|
|
658
|
+
|
|
659
|
+
// If the preferred port is already taken (e.g. a previous server is still
|
|
660
|
+
// alive), fall back to a random port once instead of failing.
|
|
661
|
+
let triedFallback = false;
|
|
662
|
+
|
|
663
|
+
function onListen() {
|
|
664
|
+
// Cookie name keys on the ACTUAL bound port (may differ from the preferred
|
|
665
|
+
// one after an EADDRINUSE fallback) so it can't collide with another server's
|
|
666
|
+
// cookie in the shared localhost jar.
|
|
667
|
+
COOKIE_NAME = 'brainstorm-key-' + PORT;
|
|
668
|
+
// Record the bound port AND token so the next restart of this session reuses
|
|
669
|
+
// them — but ONLY when we got our preferred port. On a fallback we bound a
|
|
670
|
+
// *different* port because someone else holds the preferred one; persisting
|
|
671
|
+
// would overwrite the shared files and strand that other session's open tab.
|
|
672
|
+
if (PORT_FILE && !triedFallback) {
|
|
673
|
+
try { fs.writeFileSync(PORT_FILE, String(PORT)); } catch (e) { /* best effort */ }
|
|
674
|
+
if (TOKEN_FILE) {
|
|
675
|
+
try {
|
|
676
|
+
fs.writeFileSync(TOKEN_FILE, TOKEN, { mode: 0o600 });
|
|
677
|
+
chmodOwnerOnly(TOKEN_FILE);
|
|
678
|
+
} catch (e) { /* best effort */ }
|
|
679
|
+
}
|
|
680
|
+
}
|
|
681
|
+
const info = JSON.stringify({
|
|
682
|
+
type: 'server-started', port: Number(PORT), host: HOST,
|
|
683
|
+
url_host: URL_HOST, url: companionUrl(),
|
|
684
|
+
screen_dir: CONTENT_DIR, state_dir: STATE_DIR, idle_timeout_ms: IDLE_TIMEOUT_MS
|
|
685
|
+
});
|
|
686
|
+
console.log(info);
|
|
687
|
+
// server-info embeds the key — keep it owner-only.
|
|
688
|
+
fs.writeFileSync(path.join(STATE_DIR, 'server-info'), info + '\n', { mode: 0o600 });
|
|
689
|
+
}
|
|
690
|
+
|
|
691
|
+
server.on('error', (err) => {
|
|
692
|
+
if (err.code === 'EADDRINUSE' && !triedFallback) {
|
|
693
|
+
if (tokenSource === 'env') {
|
|
694
|
+
console.error('Server failed to bind: preferred port is in use and BRAINSTORM_TOKEN is set; refusing fallback with explicit token');
|
|
695
|
+
process.exit(1);
|
|
696
|
+
}
|
|
697
|
+
triedFallback = true;
|
|
698
|
+
PORT = randomPort();
|
|
699
|
+
if (tokenSource === 'file') {
|
|
700
|
+
TOKEN = generateToken();
|
|
701
|
+
tokenSource = 'generated-fallback';
|
|
702
|
+
}
|
|
703
|
+
server.listen(PORT, HOST, onListen);
|
|
704
|
+
} else {
|
|
705
|
+
console.error('Server failed to bind:', err.message);
|
|
706
|
+
process.exit(1);
|
|
707
|
+
}
|
|
708
|
+
});
|
|
709
|
+
server.listen(PORT, HOST, onListen);
|
|
710
|
+
}
|
|
711
|
+
|
|
712
|
+
if (require.main === module) {
|
|
713
|
+
startServer();
|
|
714
|
+
}
|
|
715
|
+
|
|
716
|
+
module.exports = {
|
|
717
|
+
computeAcceptKey,
|
|
718
|
+
encodeFrame,
|
|
719
|
+
decodeFrame,
|
|
720
|
+
browserLauncherForPlatform,
|
|
721
|
+
OPCODES,
|
|
722
|
+
MAX_FRAME_PAYLOAD_BYTES
|
|
723
|
+
};
|