@rpamis/comet 0.4.0-beta.2 → 0.4.0-beta.4
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/README.md +27 -18
- package/assets/manifest.json +2 -1
- package/assets/skills/comet/SKILL.md +25 -1
- package/assets/skills/comet/reference/comet-yaml-fields.md +6 -4
- package/assets/skills/comet/reference/context-recovery.md +10 -0
- package/assets/skills/comet/reference/scripts.md +47 -15
- package/assets/skills/comet/rules/comet-phase-guard.en.md +8 -0
- package/assets/skills/comet/rules/comet-phase-guard.md +9 -1
- package/assets/skills/comet/scripts/comet-resume-probe.mjs +3 -0
- package/assets/skills/comet/scripts/comet-runtime.mjs +1664 -512
- package/assets/skills/comet-archive/SKILL.md +24 -11
- package/assets/skills/comet-build/SKILL.md +40 -31
- package/assets/skills/comet-design/SKILL.md +1 -0
- package/assets/skills/comet-hotfix/SKILL.md +3 -1
- package/assets/skills/comet-open/SKILL.md +11 -1
- package/assets/skills/comet-tweak/SKILL.md +3 -1
- package/assets/skills/comet-verify/SKILL.md +29 -20
- package/assets/skills-zh/comet/SKILL.md +25 -1
- package/assets/skills-zh/comet/reference/comet-yaml-fields.md +5 -4
- package/assets/skills-zh/comet/reference/context-recovery.md +10 -0
- package/assets/skills-zh/comet/reference/scripts.md +47 -15
- package/assets/skills-zh/comet-archive/SKILL.md +24 -11
- package/assets/skills-zh/comet-build/SKILL.md +40 -31
- package/assets/skills-zh/comet-design/SKILL.md +1 -0
- package/assets/skills-zh/comet-hotfix/SKILL.md +3 -1
- package/assets/skills-zh/comet-open/SKILL.md +11 -1
- package/assets/skills-zh/comet-tweak/SKILL.md +3 -1
- package/assets/skills-zh/comet-verify/SKILL.md +30 -21
- 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 +37 -3
- 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 +1 -0
- package/dist/app/commands/doctor.d.ts.map +1 -1
- package/dist/app/commands/doctor.js +100 -35
- 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.map +1 -1
- package/dist/app/commands/init.js +16 -13
- 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 +2 -0
- package/dist/app/commands/uninstall.d.ts.map +1 -1
- package/dist/app/commands/uninstall.js +217 -40
- 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 +361 -68
- 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.map +1 -1
- package/dist/domains/bundle/bundle-platform.js +3 -1
- 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 +101 -141
- 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 +67 -29
- 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 +3 -3
- 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 +269 -4
- 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 +129 -15
- package/dist/domains/comet-classic/classic-state-command.js.map +1 -1
- package/dist/domains/comet-classic/classic-state.d.ts +3 -3
- package/dist/domains/comet-classic/classic-state.d.ts.map +1 -1
- package/dist/domains/comet-classic/classic-state.js +4 -6
- 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 +27 -9
- 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 +20 -1
- 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 +1 -0
- 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/{index-CjU3VXVu.js → index-CIvN-PL8.js} +11 -11
- package/dist/domains/dashboard/web/assets/{index-BcO3_QlT.css → index-DcyRPBnT.css} +1 -1
- 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/integrations/openspec.d.ts.map +1 -1
- package/dist/domains/integrations/openspec.js +6 -6
- 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/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-install.d.ts +4 -3
- package/dist/domains/skill/platform-install.d.ts.map +1 -1
- package/dist/domains/skill/platform-install.js +96 -26
- 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 +86 -39
- package/dist/domains/skill/uninstall.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 +5 -1
- package/dist/platform/install/platforms.d.ts.map +1 -1
- package/dist/platform/install/platforms.js +21 -4
- package/dist/platform/install/platforms.js.map +1 -1
- package/dist/platform/install/project-registry.d.ts +37 -0
- package/dist/platform/install/project-registry.d.ts.map +1 -0
- package/dist/platform/install/project-registry.js +205 -0
- package/dist/platform/install/project-registry.js.map +1 -0
- package/eval/.env +28 -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 +24 -2
|
@@ -0,0 +1,48 @@
|
|
|
1
|
+
from scaffold.python.attribution import classify_failures
|
|
2
|
+
|
|
3
|
+
|
|
4
|
+
def test_classify_failures_marks_missing_skill_without_invocation_as_harness():
|
|
5
|
+
failures = classify_failures(
|
|
6
|
+
["Required skill not invoked: comet"],
|
|
7
|
+
{"skills_invoked": []},
|
|
8
|
+
"generic",
|
|
9
|
+
)
|
|
10
|
+
|
|
11
|
+
assert failures == [
|
|
12
|
+
{
|
|
13
|
+
"bucket": "harness",
|
|
14
|
+
"check": "Required skill not invoked: comet",
|
|
15
|
+
"reason": "target Skill was never invoked, so workflow quality is not observable",
|
|
16
|
+
}
|
|
17
|
+
]
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
def test_classify_failures_marks_state_failures_as_workflow():
|
|
21
|
+
failures = classify_failures(
|
|
22
|
+
["Expected .comet.yaml state transition to advance"],
|
|
23
|
+
{"skills_invoked": ["comet"]},
|
|
24
|
+
"comet-workflow",
|
|
25
|
+
)
|
|
26
|
+
|
|
27
|
+
assert failures[0]["bucket"] == "workflow"
|
|
28
|
+
assert "state or guard" in failures[0]["reason"]
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
def test_classify_failures_marks_validator_path_issues_as_task():
|
|
32
|
+
failures = classify_failures(
|
|
33
|
+
["validator artifact path not found in archive"],
|
|
34
|
+
{"skills_invoked": ["comet"]},
|
|
35
|
+
"authoring-skill",
|
|
36
|
+
)
|
|
37
|
+
|
|
38
|
+
assert failures[0]["bucket"] == "task"
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
def test_classify_failures_defaults_to_model_when_workflow_observable():
|
|
42
|
+
failures = classify_failures(
|
|
43
|
+
["Expected package to contain summary section"],
|
|
44
|
+
{"skills_invoked": ["comet-any"]},
|
|
45
|
+
"authoring-skill",
|
|
46
|
+
)
|
|
47
|
+
|
|
48
|
+
assert failures[0]["bucket"] == "model"
|