workflow-ai 1.0.63 → 1.0.65
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 +239 -145
- package/configs/agent-health-rules.yaml +64 -0
- package/configs/config.yaml +134 -0
- package/configs/pipeline.yaml +901 -0
- package/configs/ticket-movement-rules.yaml +80 -0
- package/package.json +1 -1
- package/src/global-dir.mjs +25 -1
- package/src/init.mjs +20 -3
- package/src/lib/agent-health-registry.mjs +245 -0
- package/src/lib/artifact-snapshot.mjs +233 -0
- package/src/lib/error-classifier.mjs +274 -0
- package/src/lib/test-error-classifier.mjs +60 -0
- package/src/lib/test-extends.mjs +58 -0
- package/src/lib/test-version.mjs +21 -0
- package/src/scripts/move-to-review.js +5 -7
- package/src/scripts/reset-agent-health.js +62 -0
- package/src/scripts/run-skill-tests.js +348 -136
- package/src/skills/analyze-report/README.md +44 -0
- package/src/skills/analyze-report/SKILL.md +121 -0
- package/src/skills/analyze-report/algorithms/progress-assessment.md +108 -0
- package/src/skills/analyze-report/knowledge/analysis-frameworks.md +66 -0
- package/src/skills/analyze-report/knowledge/report-structure.md +61 -0
- package/src/skills/analyze-report/scripts/calc-plan-metrics.js +234 -0
- package/src/skills/analyze-report/templates/analysis-report.md +80 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/claude-sonnet/trial-1.md +69 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/claude-sonnet/trial-2.md +103 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/claude-sonnet/trial-3.md +99 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/judge.json +163 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-deepseek/trial-1.md +89 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-deepseek/trial-2.md +88 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-deepseek/trial-3.md +100 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-glm/trial-1.md +77 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-glm/trial-2.md +64 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-glm/trial-3.md +110 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-minimax/trial-1.md +74 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-minimax/trial-2.md +38 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/kilo-minimax/trial-3.md +61 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001/current/meta.json +115 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-001-evidence-from-log.yaml +60 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/claude-sonnet/trial-1.md +90 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/claude-sonnet/trial-2.md +89 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/claude-sonnet/trial-3.md +77 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/judge.json +163 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-deepseek/trial-1.md +84 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-deepseek/trial-2.md +77 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-deepseek/trial-3.md +89 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-glm/trial-1.md +103 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-glm/trial-2.md +103 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-glm/trial-3.md +103 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-minimax/trial-1.md +93 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-minimax/trial-2.md +93 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/kilo-minimax/trial-3.md +86 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002/current/meta.json +115 -0
- package/src/skills/analyze-report/tests/cases/TC-ANALYZE-REPORT-002-result-block-format.yaml +44 -0
- package/src/skills/analyze-report/tests/fixtures/REPORT-002-incorrect-attribution.md +27 -0
- package/src/skills/analyze-report/tests/fixtures/pipeline-2026-04-06_qa-001-skip.log +32 -0
- package/src/skills/analyze-report/tests/index.yaml +25 -0
- package/src/skills/analyze-report/tests/rubrics/evidence-from-log.md +22 -0
- package/src/skills/analyze-report/tests/rubrics/result-block-format.md +22 -0
- package/src/skills/analyze-report/workflows/progress.md +158 -0
- package/src/skills/analyze-report/workflows/retrospective.md +143 -0
- package/src/skills/coach/README.md +43 -0
- package/src/skills/coach/SKILL.md +167 -0
- package/src/skills/coach/SKILL.md.legacy +157 -0
- package/src/skills/coach/algorithms/gap-analysis.md +69 -0
- package/src/skills/coach/algorithms/improvement-prioritization.md +62 -0
- package/src/skills/coach/algorithms/skill-scoring.md +80 -0
- package/src/skills/coach/knowledge/audit-applied-changes-clean.txt +11 -0
- package/src/skills/coach/knowledge/backlog-management.md +67 -0
- package/src/skills/coach/knowledge/backlog-management.md.legacy +90 -0
- package/src/skills/coach/knowledge/common-antipatterns.md +76 -0
- package/src/skills/coach/knowledge/prompt-engineering.md +45 -0
- package/src/skills/coach/knowledge/shared-knowledge-guide.md +44 -0
- package/src/skills/coach/knowledge/skill-anatomy.md +49 -0
- package/src/skills/coach/knowledge/test-authorship.md +141 -0
- package/src/skills/coach/templates/audit-report.md +39 -0
- package/src/skills/coach/templates/coach-backlog-init.yaml +14 -0
- package/src/skills/coach/templates/coach-backlog-init.yaml.legacy +10 -0
- package/src/skills/coach/templates/improvement-plan.md +42 -0
- package/src/skills/coach/templates/new-skill.md +95 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/claude-sonnet/trial-1.md +58 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/claude-sonnet/trial-2.md +65 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/claude-sonnet/trial-3.md +58 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/judge.json +151 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-deepseek/trial-1.md +46 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-deepseek/trial-2.md +0 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-deepseek/trial-3.md +75 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-glm/trial-1.md +81 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-glm/trial-2.md +101 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-glm/trial-3.md +91 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-minimax/trial-1.md +48 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-minimax/trial-2.md +30 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/kilo-minimax/trial-3.md +55 -0
- package/src/skills/coach/tests/cases/TC-COACH-001/current/meta.json +94 -0
- package/src/skills/coach/tests/cases/TC-COACH-001-evidence-based-temporal-diagram.yaml +53 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/claude-sonnet/trial-1.md +46 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/claude-sonnet/trial-2.md +50 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/claude-sonnet/trial-3.md +48 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/judge.json +151 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-deepseek/trial-1.md +0 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-deepseek/trial-2.md +37 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-deepseek/trial-3.md +30 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-glm/trial-1.md +23 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-glm/trial-2.md +29 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-glm/trial-3.md +35 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-minimax/trial-1.md +13 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-minimax/trial-2.md +19 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/kilo-minimax/trial-3.md +33 -0
- package/src/skills/coach/tests/cases/TC-COACH-002/current/meta.json +94 -0
- package/src/skills/coach/tests/cases/TC-COACH-002-root-cause-first.yaml +57 -0
- package/src/skills/coach/tests/fixtures/pipeline-2026-04-06_id-collision.log +77 -0
- package/src/skills/coach/tests/index.yaml +29 -0
- package/src/skills/coach/tests/rubrics/calibration/evidence-based-bad.md +13 -0
- package/src/skills/coach/tests/rubrics/calibration/evidence-based-good.md +29 -0
- package/src/skills/coach/tests/rubrics/evidence-based.md +26 -0
- package/src/skills/coach/tests/rubrics/root-cause-first.md +21 -0
- package/src/skills/coach/workflows/analyze.md +79 -0
- package/src/skills/coach/workflows/analyze.md.legacy +64 -0
- package/src/skills/coach/workflows/audit.md +74 -0
- package/src/skills/coach/workflows/audit.md.legacy +59 -0
- package/src/skills/coach/workflows/create.md +80 -0
- package/src/skills/coach/workflows/create.md.legacy +67 -0
- package/src/skills/coach/workflows/improve.md +71 -0
- package/src/skills/coach/workflows/improve.md.legacy +60 -0
- package/src/skills/coach/workflows/research.md +55 -0
- package/src/skills/coach/workflows/review.md +52 -0
- package/src/skills/coach/workflows/review.md.legacy +48 -0
- package/src/skills/coach/workflows/test.md +97 -0
- package/src/skills/create-plan/README.md +39 -0
- package/src/skills/create-plan/SKILL.md +104 -0
- package/src/skills/create-plan/algorithms/risk-assessment.md +73 -0
- package/src/skills/create-plan/knowledge/plan-completeness.md +67 -0
- package/src/skills/create-plan/knowledge/plan-lifecycle.md +33 -0
- package/src/skills/create-plan/knowledge/task-verification-pairs.md +151 -0
- package/src/skills/create-plan/scripts/validate-completeness.js +182 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/claude-sonnet/trial-1.md +5 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/claude-sonnet/trial-2.md +39 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/claude-sonnet/trial-3.md +35 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/judge.json +167 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-deepseek/trial-1.md +5 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-deepseek/trial-2.md +10 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-deepseek/trial-3.md +5 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-glm/trial-1.md +26 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-glm/trial-2.md +86 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-glm/trial-3.md +5 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-minimax/trial-1.md +11 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-minimax/trial-2.md +15 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/kilo-minimax/trial-3.md +14 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001/current/meta.json +119 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-001-validate-completeness.yaml +41 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/claude-sonnet/trial-1.md +25 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/claude-sonnet/trial-2.md +30 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/claude-sonnet/trial-3.md +37 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/judge.json +164 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-deepseek/trial-1.md +3 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-deepseek/trial-2.md +11 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-deepseek/trial-3.md +13 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-glm/trial-1.md +44 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-glm/trial-2.md +5 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-glm/trial-3.md +49 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-minimax/trial-1.md +6 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-minimax/trial-2.md +11 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/kilo-minimax/trial-3.md +16 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002/current/meta.json +116 -0
- package/src/skills/create-plan/tests/cases/TC-CREATE-PLAN-002-task-granularity.yaml +39 -0
- package/src/skills/create-plan/tests/index.yaml +25 -0
- package/src/skills/create-plan/tests/rubrics/task-granularity.md +21 -0
- package/src/skills/create-plan/tests/rubrics/validate-completeness.md +21 -0
- package/src/skills/create-plan/workflows/create.md +136 -0
- package/src/skills/create-report/README.md +40 -0
- package/src/skills/create-report/SKILL.md +73 -0
- package/src/skills/create-report/algorithms/metric-calculation.md +93 -0
- package/src/skills/create-report/knowledge/report-metrics.md +82 -0
- package/src/skills/create-report/scripts/calc-metrics.js +383 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/claude-sonnet/trial-1.md +25 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/claude-sonnet/trial-2.md +26 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/claude-sonnet/trial-3.md +28 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/judge.json +163 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-deepseek/trial-1.md +4 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-deepseek/trial-2.md +3 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-deepseek/trial-3.md +6 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-glm/trial-1.md +8 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-glm/trial-2.md +12 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-glm/trial-3.md +7 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-minimax/trial-1.md +12 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-minimax/trial-2.md +22 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/kilo-minimax/trial-3.md +13 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001/current/meta.json +115 -0
- package/src/skills/create-report/tests/cases/TC-CREATE-REPORT-001-root-cause-attribution.yaml +57 -0
- package/src/skills/create-report/tests/index.yaml +20 -0
- package/src/skills/create-report/tests/rubrics/root-cause-attribution.md +21 -0
- package/src/skills/create-report/workflows/standard.md +175 -0
- package/src/skills/decompose-gaps/README.md +39 -0
- package/src/skills/decompose-gaps/SKILL.md +78 -0
- package/src/skills/decompose-gaps/algorithms/scope-check.md +110 -0
- package/src/skills/decompose-gaps/knowledge/scope-validation.md +65 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/claude-sonnet/trial-1.md +41 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/claude-sonnet/trial-2.md +41 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/claude-sonnet/trial-3.md +56 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/judge.json +164 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-deepseek/trial-1.md +25 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-deepseek/trial-2.md +17 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-deepseek/trial-3.md +22 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-glm/trial-1.md +25 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-glm/trial-2.md +5 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-glm/trial-3.md +29 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-minimax/trial-1.md +27 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-minimax/trial-2.md +35 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/kilo-minimax/trial-3.md +18 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001/current/meta.json +116 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-001-scope-exclusion.yaml +46 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/claude-sonnet/trial-1.md +27 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/claude-sonnet/trial-2.md +30 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/claude-sonnet/trial-3.md +27 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/judge.json +163 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-deepseek/trial-1.md +0 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-deepseek/trial-2.md +15 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-deepseek/trial-3.md +7 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-glm/trial-1.md +21 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-glm/trial-2.md +38 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-glm/trial-3.md +16 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-minimax/trial-1.md +5 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-minimax/trial-2.md +10 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/kilo-minimax/trial-3.md +9 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002/current/meta.json +115 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-002-glob-before-write.yaml +36 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/claude-sonnet/trial-1.md +30 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/claude-sonnet/trial-2.md +30 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/claude-sonnet/trial-3.md +30 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/judge.json +165 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/kilo-deepseek/trial-1.md +5 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/kilo-deepseek/trial-2.md +26 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/kilo-deepseek/trial-3.md +5 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/kilo-glm/trial-1.md +39 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/kilo-glm/trial-2.md +37 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/kilo-glm/trial-3.md +45 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/kilo-minimax/trial-1.md +26 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/kilo-minimax/trial-2.md +27 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/kilo-minimax/trial-3.md +7 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003/current/meta.json +117 -0
- package/src/skills/decompose-gaps/tests/cases/TC-DECOMPOSE-GAPS-003-parent-plan-mandatory.yaml +41 -0
- package/src/skills/decompose-gaps/tests/index.yaml +30 -0
- package/src/skills/decompose-gaps/tests/rubrics/glob-before-write.md +21 -0
- package/src/skills/decompose-gaps/tests/rubrics/parent-plan-mandatory.md +22 -0
- package/src/skills/decompose-gaps/tests/rubrics/scope-exclusion.md +21 -0
- package/src/skills/decompose-gaps/workflows/decompose.md +123 -0
- package/src/skills/decompose-plan/README.md +43 -0
- package/src/skills/decompose-plan/SKILL.md +87 -0
- package/src/skills/decompose-plan/algorithms/deduplication.md +101 -0
- package/src/skills/decompose-plan/knowledge/atomicity-checklist.md +139 -0
- package/src/skills/decompose-plan/knowledge/capabilities.md +68 -0
- package/src/skills/decompose-plan/knowledge/human-task-rules.md +82 -0
- package/src/skills/decompose-plan/knowledge/scope-guard-checklist.md +73 -0
- package/src/skills/decompose-plan/scripts/check-atomicity-limit.js +47 -0
- package/src/skills/decompose-plan/scripts/check-duplicates.js +323 -0
- package/src/skills/decompose-plan/scripts/verify-atomicity.js +408 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/claude-sonnet/trial-1.md +30 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/claude-sonnet/trial-2.md +36 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/claude-sonnet/trial-3.md +37 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/judge.json +163 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-deepseek/trial-1.md +20 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-deepseek/trial-2.md +17 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-deepseek/trial-3.md +28 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-glm/trial-1.md +114 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-glm/trial-2.md +137 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-glm/trial-3.md +188 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-minimax/trial-1.md +0 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-minimax/trial-2.md +32 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/kilo-minimax/trial-3.md +110 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001/current/meta.json +115 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-001-atomicity-no-1to1.yaml +56 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/claude-sonnet/trial-1.md +47 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/claude-sonnet/trial-2.md +54 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/claude-sonnet/trial-3.md +43 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/judge.json +163 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-deepseek/trial-1.md +15 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-deepseek/trial-2.md +5 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-deepseek/trial-3.md +12 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-glm/trial-1.md +34 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-glm/trial-2.md +30 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-glm/trial-3.md +35 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-minimax/trial-1.md +0 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-minimax/trial-2.md +31 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/kilo-minimax/trial-3.md +0 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002/current/meta.json +115 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-002-get-next-id-mandatory.yaml +44 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/claude-sonnet/trial-1.md +21 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/claude-sonnet/trial-2.md +38 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/claude-sonnet/trial-3.md +30 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/judge.json +163 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-deepseek/trial-1.md +31 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-deepseek/trial-2.md +35 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-deepseek/trial-3.md +48 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-glm/trial-1.md +167 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-glm/trial-2.md +62 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-glm/trial-3.md +174 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-minimax/trial-1.md +0 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-minimax/trial-2.md +0 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/kilo-minimax/trial-3.md +0 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003/current/meta.json +115 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-003-verbatim-dod-transfer.yaml +42 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/claude-sonnet/trial-1.md +55 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/claude-sonnet/trial-2.md +49 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/claude-sonnet/trial-3.md +49 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/judge.json +163 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/kilo-deepseek/trial-1.md +104 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/kilo-deepseek/trial-2.md +45 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/kilo-deepseek/trial-3.md +58 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/kilo-glm/trial-1.md +193 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/kilo-glm/trial-2.md +202 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/kilo-glm/trial-3.md +155 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/kilo-minimax/trial-1.md +52 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/kilo-minimax/trial-2.md +17 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/kilo-minimax/trial-3.md +0 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004/current/meta.json +115 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-004-executor-atomicity.yaml +64 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/claude-sonnet/trial-1.md +59 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/claude-sonnet/trial-2.md +204 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/claude-sonnet/trial-3.md +213 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/judge.json +163 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/kilo-deepseek/trial-1.md +0 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/kilo-deepseek/trial-2.md +57 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/kilo-deepseek/trial-3.md +54 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/kilo-glm/trial-1.md +147 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/kilo-glm/trial-2.md +165 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/kilo-glm/trial-3.md +133 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/kilo-minimax/trial-1.md +81 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/kilo-minimax/trial-2.md +108 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/kilo-minimax/trial-3.md +3 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005/current/meta.json +114 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-005-capabilities-registry.yaml +78 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/claude-sonnet/trial-1.md +225 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/claude-sonnet/trial-2.md +66 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/claude-sonnet/trial-3.md +36 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/judge.json +163 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/kilo-deepseek/trial-1.md +42 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/kilo-deepseek/trial-2.md +67 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/kilo-deepseek/trial-3.md +40 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/kilo-glm/trial-1.md +122 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/kilo-glm/trial-2.md +131 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/kilo-glm/trial-3.md +138 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/kilo-minimax/trial-1.md +41 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/kilo-minimax/trial-2.md +88 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/kilo-minimax/trial-3.md +0 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006/current/meta.json +115 -0
- package/src/skills/decompose-plan/tests/cases/TC-DECOMPOSE-PLAN-006-dod-threshold.yaml +72 -0
- package/src/skills/decompose-plan/tests/index.yaml +45 -0
- package/src/skills/decompose-plan/tests/rubrics/atomicity-no-1to1.md +21 -0
- package/src/skills/decompose-plan/tests/rubrics/capabilities-registry.md +21 -0
- package/src/skills/decompose-plan/tests/rubrics/dod-threshold.md +21 -0
- package/src/skills/decompose-plan/tests/rubrics/executor-atomicity.md +21 -0
- package/src/skills/decompose-plan/tests/rubrics/get-next-id-mandatory.md +21 -0
- package/src/skills/decompose-plan/tests/rubrics/verbatim-dod-transfer.md +21 -0
- package/src/skills/decompose-plan/workflows/decompose.md +305 -0
- package/src/skills/deep-research/README.md +36 -0
- package/src/skills/deep-research/SKILL.md +106 -0
- package/src/skills/deep-research/algorithms/source-scoring.md +63 -0
- package/src/skills/deep-research/algorithms/synthesis.md +67 -0
- package/src/skills/deep-research/knowledge/data-validation.md +44 -0
- package/src/skills/deep-research/knowledge/perplexity-config.md +30 -0
- package/src/skills/deep-research/knowledge/research-methodology.md +54 -0
- package/src/skills/deep-research/knowledge/source-evaluation.md +33 -0
- package/src/skills/deep-research/scripts/perplexity-research.js +315 -0
- package/src/skills/deep-research/templates/brief-summary.md +25 -0
- package/src/skills/deep-research/templates/research-report.md +76 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/claude-haiku/trial-1.md +48 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/claude-haiku/trial-2.md +88 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/claude-haiku/trial-3.md +56 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/judge.json +163 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-free/trial-1.md +58 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-free/trial-2.md +249 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-free/trial-3.md +44 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm/trial-1.md +96 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm/trial-2.md +56 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm/trial-3.md +94 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm-air/trial-1.md +11 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm-air/trial-2.md +1 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/kilo-glm-air/trial-3.md +1 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001/current/meta.json +115 -0
- package/src/skills/deep-research/tests/cases/TC-DEEP-RESEARCH-001-self-check-url.yaml +58 -0
- package/src/skills/deep-research/tests/index.yaml +20 -0
- package/src/skills/deep-research/tests/rubrics/self-check-url.md +34 -0
- package/src/skills/deep-research/workflows/base-checklist.md +19 -0
- package/src/skills/deep-research/workflows/benchmark.md +38 -0
- package/src/skills/deep-research/workflows/competitor.md +44 -0
- package/src/skills/deep-research/workflows/custom.md +32 -0
- package/src/skills/deep-research/workflows/market.md +44 -0
- package/src/skills/deep-research/workflows/technology.md +40 -0
- package/src/skills/deep-research/workflows/trend.md +40 -0
- package/src/skills/execute-task/README.md +44 -0
- package/src/skills/execute-task/SKILL.md +292 -0
- package/src/skills/execute-task/algorithms/execution-strategy.md +136 -0
- package/src/skills/execute-task/knowledge/context-checkpoints.md +75 -0
- package/src/skills/execute-task/knowledge/ticket-structure.md +70 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/claude-haiku/trial-1.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/claude-haiku/trial-2.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/claude-haiku/trial-3.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/judge.json +124 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-free/trial-1.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-free/trial-2.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-free/trial-3.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-glm-air/trial-1.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-glm-air/trial-2.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/kilo-glm-air/trial-3.md +11 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001/current/meta.json +88 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-001-no-ticket-creation.yaml +48 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/claude-haiku/trial-1.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/claude-haiku/trial-2.md +6 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/claude-haiku/trial-3.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/judge.json +124 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-free/trial-1.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-free/trial-2.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-free/trial-3.md +8 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-glm-air/trial-1.md +9 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-glm-air/trial-2.md +26 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/kilo-glm-air/trial-3.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002/current/meta.json +89 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-002-no-duplicate-dod.yaml +44 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003/current/claude-haiku/trial-1.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003/current/claude-haiku/trial-2.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003/current/claude-haiku/trial-3.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003/current/judge.json +46 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003/current/meta.json +37 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-003-verification-proportionality.yaml +46 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/claude-haiku/trial-1.md +18 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/claude-haiku/trial-2.md +16 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/claude-haiku/trial-3.md +14 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/judge.json +124 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-free/trial-1.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-free/trial-2.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-free/trial-3.md +1 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-glm-air/trial-1.md +8 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-glm-air/trial-2.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/kilo-glm-air/trial-3.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004/current/meta.json +89 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-004-no-foreign-ticket-edit.yaml +50 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/claude-haiku/trial-1.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/claude-haiku/trial-2.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/claude-haiku/trial-3.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/judge.json +124 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-free/trial-1.md +15 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-free/trial-2.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-free/trial-3.md +5 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-glm-air/trial-1.md +11 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-glm-air/trial-2.md +11 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/kilo-glm-air/trial-3.md +4 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005/current/meta.json +88 -0
- package/src/skills/execute-task/tests/cases/TC-EXECUTE-TASK-005-ticket-fields-updated.yaml +39 -0
- package/src/skills/execute-task/tests/fixtures/IMPL-902-create-file.md +41 -0
- package/src/skills/execute-task/tests/fixtures/IMPL-904-current-task.md +40 -0
- package/src/skills/execute-task/tests/fixtures/IMPL-906-fill-ticket.md +42 -0
- package/src/skills/execute-task/tests/fixtures/QA-901-button-click.md +41 -0
- package/src/skills/execute-task/tests/fixtures/QA-903-visual-figma.md +40 -0
- package/src/skills/execute-task/tests/fixtures/TASK-905-done-with-typo.md +36 -0
- package/src/skills/execute-task/tests/index.yaml +39 -0
- package/src/skills/execute-task/tests/rubrics/no-duplicate-dod.md +22 -0
- package/src/skills/execute-task/tests/rubrics/no-foreign-ticket-edit.md +20 -0
- package/src/skills/execute-task/tests/rubrics/no-ticket-creation.md +21 -0
- package/src/skills/execute-task/tests/rubrics/ticket-fields-updated.md +23 -0
- package/src/skills/execute-task/tests/rubrics/verification-proportionality.md +22 -0
- package/src/skills/execute-task/workflows/execute.md +104 -0
- package/src/skills/manual-testing/README.md +63 -0
- package/src/skills/manual-testing/SKILL.md +176 -0
- package/src/skills/manual-testing/algorithms/blocked-tool-strategy.md +74 -0
- package/src/skills/manual-testing/algorithms/bug-severity.md +73 -0
- package/src/skills/manual-testing/algorithms/mcp-budget.md +97 -0
- package/src/skills/manual-testing/algorithms/test-prioritization.md +69 -0
- package/src/skills/manual-testing/knowledge/browser-extension-testing.md +102 -0
- package/src/skills/manual-testing/knowledge/browser-tools.md +114 -0
- package/src/skills/manual-testing/knowledge/desktop-tools-advanced.md +92 -0
- package/src/skills/manual-testing/knowledge/desktop-tools-core.md +76 -0
- package/src/skills/manual-testing/knowledge/sandbox-advanced.md +83 -0
- package/src/skills/manual-testing/knowledge/sandbox-core.md +67 -0
- package/src/skills/manual-testing/knowledge/stateful-edge-cases.md +69 -0
- package/src/skills/manual-testing/knowledge/test-case-design.md +107 -0
- package/src/skills/manual-testing/knowledge/testing-types.md +45 -0
- package/src/skills/manual-testing/templates/bug-report.md +52 -0
- package/src/skills/manual-testing/templates/test-case.md +34 -0
- package/src/skills/manual-testing/templates/test-plan.md +97 -0
- package/src/skills/manual-testing/templates/test-session-report.md +56 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/claude-sonnet/trial-1.md +34 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/claude-sonnet/trial-2.md +32 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/claude-sonnet/trial-3.md +30 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/judge.json +163 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-deepseek/trial-1.md +0 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-deepseek/trial-2.md +7 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-deepseek/trial-3.md +0 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-glm/trial-1.md +4 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-glm/trial-2.md +15 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-glm/trial-3.md +8 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-minimax/trial-1.md +5 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-minimax/trial-2.md +7 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/kilo-minimax/trial-3.md +7 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001/current/meta.json +114 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-001-sandbox-mandatory.yaml +38 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/claude-sonnet/trial-1.md +44 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/claude-sonnet/trial-2.md +32 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/claude-sonnet/trial-3.md +47 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/judge.json +163 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-deepseek/trial-1.md +19 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-deepseek/trial-2.md +15 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-deepseek/trial-3.md +24 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-glm/trial-1.md +19 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-glm/trial-2.md +13 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-glm/trial-3.md +18 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-minimax/trial-1.md +21 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-minimax/trial-2.md +15 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/kilo-minimax/trial-3.md +14 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002/current/meta.json +114 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-002-visual-tc-screenshot.yaml +37 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-003/current/claude-sonnet/trial-1.md +76 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-003/current/claude-sonnet/trial-2.md +71 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-003/current/claude-sonnet/trial-3.md +85 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-003/current/judge.json +46 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-003/current/meta.json +36 -0
- package/src/skills/manual-testing/tests/cases/TC-MANUAL-TESTING-003-qa-non-ui-assertion.yaml +65 -0
- package/src/skills/manual-testing/tests/index.yaml +30 -0
- package/src/skills/manual-testing/tests/last-run-tc001-sonnet.log +140 -0
- package/src/skills/manual-testing/tests/last-run-tc002.log +1 -0
- package/src/skills/manual-testing/tests/last-run.log +1469 -0
- package/src/skills/manual-testing/tests/rubrics/qa-non-ui-assertion.md +31 -0
- package/src/skills/manual-testing/tests/rubrics/sandbox-mandatory.md +20 -0
- package/src/skills/manual-testing/tests/rubrics/visual-tc-screenshot.md +21 -0
- package/src/skills/manual-testing/workflows/acceptance.md +80 -0
- package/src/skills/manual-testing/workflows/exploratory.md +84 -0
- package/src/skills/manual-testing/workflows/regression.md +76 -0
- package/src/skills/manual-testing/workflows/smoke.md +109 -0
- package/src/skills/manual-testing/workflows/test-plan.md +75 -0
- package/src/skills/review-result/README.md +59 -0
- package/src/skills/review-result/SKILL.md +138 -0
- package/src/skills/review-result/algorithms/verification.md +112 -0
- package/src/skills/review-result/knowledge/dod-patterns.md +115 -0
- package/src/skills/review-result/scripts/verify-artifacts.js +384 -0
- package/src/skills/review-result/templates/verdict.md +153 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-haiku/trial-1.md +22 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-haiku/trial-2.md +7 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-haiku/trial-3.md +21 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-sonnet/trial-1.md +6 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-sonnet/trial-2.md +6 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/claude-sonnet/trial-3.md +18 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/judge.json +164 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-deepseek/trial-1.md +5 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-deepseek/trial-2.md +7 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-deepseek/trial-3.md +6 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-glm/trial-1.md +49 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-glm/trial-2.md +28 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-glm/trial-3.md +37 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-minimax/trial-1.md +22 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-minimax/trial-2.md +13 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/kilo-minimax/trial-3.md +21 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001/current/meta.json +116 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-001-visual-tc-trigger.yaml +51 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-haiku/trial-1.md +23 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-haiku/trial-2.md +22 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-haiku/trial-3.md +28 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-sonnet/trial-1.md +4 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-sonnet/trial-2.md +36 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/claude-sonnet/trial-3.md +4 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/judge.json +163 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-deepseek/trial-1.md +4 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-deepseek/trial-2.md +0 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-deepseek/trial-3.md +4 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-glm/trial-1.md +39 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-glm/trial-2.md +25 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-glm/trial-3.md +32 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-minimax/trial-1.md +34 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-minimax/trial-2.md +8 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/kilo-minimax/trial-3.md +23 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002/current/meta.json +115 -0
- package/src/skills/review-result/tests/cases/TC-REVIEW-RESULT-002-path-line-suffix.yaml +39 -0
- package/src/skills/review-result/tests/fixtures/IMPL-902-path-with-line.md +43 -0
- package/src/skills/review-result/tests/fixtures/QA-901-visual-button.md +46 -0
- package/src/skills/review-result/tests/index.yaml +25 -0
- package/src/skills/review-result/tests/rubrics/path-line-suffix.md +19 -0
- package/src/skills/review-result/tests/rubrics/visual-tc-trigger.md +19 -0
- package/src/skills/review-result/workflows/review.md +209 -0
|
@@ -0,0 +1,274 @@
|
|
|
1
|
+
import { load as loadYaml } from './js-yaml.mjs';
|
|
2
|
+
import { readFileSync, existsSync } from 'fs';
|
|
3
|
+
import { resolve, join } from 'path';
|
|
4
|
+
|
|
5
|
+
const STDERR_MATCH_LIMIT = 64 * 1024;
|
|
6
|
+
const MATCH_TIMEOUT_MS = 100;
|
|
7
|
+
const SUPPORTED_VERSION = '1.0';
|
|
8
|
+
const MIN_UTC_MIDNIGHT_DELAY_MS = 30 * 60 * 1000;
|
|
9
|
+
|
|
10
|
+
export class InvalidRulesConfigError extends Error {
|
|
11
|
+
constructor(message) {
|
|
12
|
+
super(message);
|
|
13
|
+
this.name = 'InvalidRulesConfigError';
|
|
14
|
+
if (Error.captureStackTrace) {
|
|
15
|
+
Error.captureStackTrace(this, this.constructor);
|
|
16
|
+
}
|
|
17
|
+
}
|
|
18
|
+
}
|
|
19
|
+
|
|
20
|
+
function parseConfigFile(configPath) {
|
|
21
|
+
if (!existsSync(configPath)) {
|
|
22
|
+
return { common: [], agents: {} };
|
|
23
|
+
}
|
|
24
|
+
const content = readFileSync(configPath, 'utf-8');
|
|
25
|
+
const config = loadYaml(content);
|
|
26
|
+
if (!config || typeof config !== 'object') {
|
|
27
|
+
return { common: [], agents: {} };
|
|
28
|
+
}
|
|
29
|
+
return config;
|
|
30
|
+
}
|
|
31
|
+
|
|
32
|
+
function validateVersion(version) {
|
|
33
|
+
if (version !== SUPPORTED_VERSION) {
|
|
34
|
+
throw new InvalidRulesConfigError(
|
|
35
|
+
`Unsupported rules version: ${version}. Update runner or downgrade rules file.`
|
|
36
|
+
);
|
|
37
|
+
}
|
|
38
|
+
}
|
|
39
|
+
|
|
40
|
+
function compilePattern(pattern) {
|
|
41
|
+
if (!pattern) {
|
|
42
|
+
return null;
|
|
43
|
+
}
|
|
44
|
+
try {
|
|
45
|
+
return new RegExp(pattern);
|
|
46
|
+
} catch (e) {
|
|
47
|
+
throw new InvalidRulesConfigError(`Invalid regex pattern: ${pattern}. ${e.message}`);
|
|
48
|
+
}
|
|
49
|
+
}
|
|
50
|
+
|
|
51
|
+
function resolveExtends(agentsConfig, agentId, visited = new Set()) {
|
|
52
|
+
if (!agentsConfig[agentId]) {
|
|
53
|
+
return null;
|
|
54
|
+
}
|
|
55
|
+
if (!agentsConfig[agentId].extends) {
|
|
56
|
+
return null;
|
|
57
|
+
}
|
|
58
|
+
const extendsTarget = agentsConfig[agentId].extends;
|
|
59
|
+
if (visited.has(agentId)) {
|
|
60
|
+
throw new InvalidRulesConfigError('chained extends not supported');
|
|
61
|
+
}
|
|
62
|
+
if (!agentsConfig[extendsTarget]) {
|
|
63
|
+
throw new InvalidRulesConfigError(`extends target '${extendsTarget}' not found`);
|
|
64
|
+
}
|
|
65
|
+
if (agentsConfig[extendsTarget].extends) {
|
|
66
|
+
throw new InvalidRulesConfigError('chained extends not supported');
|
|
67
|
+
}
|
|
68
|
+
visited.add(agentId);
|
|
69
|
+
return agentsConfig[extendsTarget].rules || [];
|
|
70
|
+
}
|
|
71
|
+
|
|
72
|
+
function buildRules(rulesData, compiledRules = []) {
|
|
73
|
+
if (!Array.isArray(rulesData)) {
|
|
74
|
+
return compiledRules;
|
|
75
|
+
}
|
|
76
|
+
for (const rule of rulesData) {
|
|
77
|
+
if (!rule || !rule.id || !rule.class || !rule.ttl) {
|
|
78
|
+
continue;
|
|
79
|
+
}
|
|
80
|
+
compiledRules.push({
|
|
81
|
+
id: rule.id,
|
|
82
|
+
class: rule.class,
|
|
83
|
+
ttl: rule.ttl,
|
|
84
|
+
pattern: compilePattern(rule.pattern),
|
|
85
|
+
exitCodes: rule.exit_codes === 'any' ? 'any' : (
|
|
86
|
+
Array.isArray(rule.exit_codes)
|
|
87
|
+
? rule.exit_codes.filter(c => typeof c === 'number')
|
|
88
|
+
: []
|
|
89
|
+
),
|
|
90
|
+
});
|
|
91
|
+
}
|
|
92
|
+
return compiledRules;
|
|
93
|
+
}
|
|
94
|
+
|
|
95
|
+
export function loadRules(projectRoot, configPath) {
|
|
96
|
+
const defaultPath = join(projectRoot, '.workflow/config/agent-health-rules.yaml');
|
|
97
|
+
const fullPath = configPath || defaultPath;
|
|
98
|
+
let config;
|
|
99
|
+
try {
|
|
100
|
+
config = parseConfigFile(fullPath);
|
|
101
|
+
} catch (e) {
|
|
102
|
+
if (e instanceof InvalidRulesConfigError) {
|
|
103
|
+
throw e;
|
|
104
|
+
}
|
|
105
|
+
return { common: [], agents: new Map() };
|
|
106
|
+
}
|
|
107
|
+
if (!config || typeof config !== 'object') {
|
|
108
|
+
return { common: [], agents: new Map() };
|
|
109
|
+
}
|
|
110
|
+
if (config.version) {
|
|
111
|
+
validateVersion(config.version);
|
|
112
|
+
}
|
|
113
|
+
const commonRules = buildRules(config.common || []);
|
|
114
|
+
const agents = new Map();
|
|
115
|
+
const agentsConfig = config.agents || {};
|
|
116
|
+
for (const agentId of Object.keys(agentsConfig)) {
|
|
117
|
+
const agentConfig = agentsConfig[agentId];
|
|
118
|
+
if (!agentConfig) {
|
|
119
|
+
continue;
|
|
120
|
+
}
|
|
121
|
+
const inheritedRules = resolveExtends(agentsConfig, agentId);
|
|
122
|
+
const ownRules = buildRules(agentConfig.rules || []);
|
|
123
|
+
const finalRules = [...ownRules];
|
|
124
|
+
if (inheritedRules && inheritedRules.length > 0) {
|
|
125
|
+
finalRules.push(...buildRules(inheritedRules));
|
|
126
|
+
}
|
|
127
|
+
agents.set(agentId, finalRules);
|
|
128
|
+
}
|
|
129
|
+
return { common: commonRules, agents };
|
|
130
|
+
}
|
|
131
|
+
|
|
132
|
+
function truncateStderr(stderr) {
|
|
133
|
+
if (!stderr || stderr.length <= STDERR_MATCH_LIMIT) {
|
|
134
|
+
return stderr;
|
|
135
|
+
}
|
|
136
|
+
const halfLimit = STDERR_MATCH_LIMIT / 2;
|
|
137
|
+
const head = stderr.slice(0, halfLimit);
|
|
138
|
+
const tail = stderr.slice(-halfLimit);
|
|
139
|
+
return head + '\n...[TRUNCATED]...\n' + tail;
|
|
140
|
+
}
|
|
141
|
+
|
|
142
|
+
function matchRule(rule, exitCode, truncatedStderr) {
|
|
143
|
+
const exitCodesMatch = rule.exitCodes === 'any' ||
|
|
144
|
+
rule.exitCodes.includes(exitCode);
|
|
145
|
+
if (!exitCodesMatch) {
|
|
146
|
+
return false;
|
|
147
|
+
}
|
|
148
|
+
if (!rule.pattern) {
|
|
149
|
+
return true;
|
|
150
|
+
}
|
|
151
|
+
try {
|
|
152
|
+
return rule.pattern.test(truncatedStderr);
|
|
153
|
+
} catch (e) {
|
|
154
|
+
return false;
|
|
155
|
+
}
|
|
156
|
+
}
|
|
157
|
+
|
|
158
|
+
function matchWithTimeout(regex, text) {
|
|
159
|
+
return new Promise((resolve) => {
|
|
160
|
+
const timeoutId = setTimeout(() => {
|
|
161
|
+
resolve(false);
|
|
162
|
+
}, MATCH_TIMEOUT_MS);
|
|
163
|
+
try {
|
|
164
|
+
const result = regex.test(text);
|
|
165
|
+
clearTimeout(timeoutId);
|
|
166
|
+
resolve(result);
|
|
167
|
+
} catch (e) {
|
|
168
|
+
clearTimeout(timeoutId);
|
|
169
|
+
resolve(false);
|
|
170
|
+
}
|
|
171
|
+
});
|
|
172
|
+
}
|
|
173
|
+
|
|
174
|
+
export async function classify(rules, agentId, { exitCode, stderr }) {
|
|
175
|
+
const truncatedStderr = truncateStderr(stderr);
|
|
176
|
+
const agentRules = rules.agents.get(agentId) || [];
|
|
177
|
+
for (const rule of agentRules) {
|
|
178
|
+
const matched = rule.pattern
|
|
179
|
+
? await matchWithTimeout(rule.pattern, truncatedStderr)
|
|
180
|
+
: matchRule(rule, exitCode, truncatedStderr);
|
|
181
|
+
if (matched) {
|
|
182
|
+
return {
|
|
183
|
+
class: rule.class,
|
|
184
|
+
rule_id: rule.id,
|
|
185
|
+
ttl: rule.ttl,
|
|
186
|
+
reason: truncatedStderr,
|
|
187
|
+
};
|
|
188
|
+
}
|
|
189
|
+
}
|
|
190
|
+
for (const rule of rules.common) {
|
|
191
|
+
const matched = rule.pattern
|
|
192
|
+
? await matchWithTimeout(rule.pattern, truncatedStderr)
|
|
193
|
+
: matchRule(rule, exitCode, truncatedStderr);
|
|
194
|
+
if (matched) {
|
|
195
|
+
return {
|
|
196
|
+
class: rule.class,
|
|
197
|
+
rule_id: rule.id,
|
|
198
|
+
ttl: rule.ttl,
|
|
199
|
+
reason: truncatedStderr,
|
|
200
|
+
};
|
|
201
|
+
}
|
|
202
|
+
}
|
|
203
|
+
return null;
|
|
204
|
+
}
|
|
205
|
+
|
|
206
|
+
export function parseTtl(ttl, now = Date.now()) {
|
|
207
|
+
if (ttl === 'infinite') {
|
|
208
|
+
return Number.MAX_SAFE_INTEGER;
|
|
209
|
+
}
|
|
210
|
+
const untilMatch = ttl.match(/^(\d+)d$/);
|
|
211
|
+
if (untilMatch) {
|
|
212
|
+
return now + parseInt(untilMatch[1], 10) * 24 * 60 * 60 * 1000;
|
|
213
|
+
}
|
|
214
|
+
const hourMatch = ttl.match(/^(\d+)h$/);
|
|
215
|
+
if (hourMatch) {
|
|
216
|
+
return now + parseInt(hourMatch[1], 10) * 60 * 60 * 1000;
|
|
217
|
+
}
|
|
218
|
+
const minMatch = ttl.match(/^(\d+)m$/);
|
|
219
|
+
if (minMatch) {
|
|
220
|
+
return now + parseInt(minMatch[1], 10) * 60 * 1000;
|
|
221
|
+
}
|
|
222
|
+
if (ttl === 'until_utc_midnight') {
|
|
223
|
+
const nextMidnight = new Date(now);
|
|
224
|
+
nextMidnight.setUTCHours(24, 0, 0, 0);
|
|
225
|
+
const minDelay = now + MIN_UTC_MIDNIGHT_DELAY_MS;
|
|
226
|
+
return Math.max(nextMidnight.getTime(), minDelay);
|
|
227
|
+
}
|
|
228
|
+
throw new Error(`Invalid TTL format: ${ttl}. Expected Nm, Nh, Nd, until_utc_midnight, or infinite.`);
|
|
229
|
+
}
|
|
230
|
+
|
|
231
|
+
export function classifySync(rules, agentId, { exitCode, stderr }) {
|
|
232
|
+
const truncatedStderr = truncateStderr(stderr);
|
|
233
|
+
const agentRules = rules.agents.get(agentId) || [];
|
|
234
|
+
for (const rule of agentRules) {
|
|
235
|
+
const matched = rule.pattern
|
|
236
|
+
? (() => {
|
|
237
|
+
try {
|
|
238
|
+
return rule.pattern.test(truncatedStderr);
|
|
239
|
+
} catch (e) {
|
|
240
|
+
return false;
|
|
241
|
+
}
|
|
242
|
+
})()
|
|
243
|
+
: matchRule(rule, exitCode, truncatedStderr);
|
|
244
|
+
if (matched) {
|
|
245
|
+
return {
|
|
246
|
+
class: rule.class,
|
|
247
|
+
rule_id: rule.id,
|
|
248
|
+
ttl: rule.ttl,
|
|
249
|
+
reason: truncatedStderr,
|
|
250
|
+
};
|
|
251
|
+
}
|
|
252
|
+
}
|
|
253
|
+
for (const rule of rules.common) {
|
|
254
|
+
const matched = rule.pattern
|
|
255
|
+
? (() => {
|
|
256
|
+
try {
|
|
257
|
+
return rule.pattern.test(truncatedStderr);
|
|
258
|
+
} catch (e) {
|
|
259
|
+
return false;
|
|
260
|
+
}
|
|
261
|
+
})()
|
|
262
|
+
: matchRule(rule, exitCode, truncatedStderr);
|
|
263
|
+
if (matched) {
|
|
264
|
+
return {
|
|
265
|
+
class: rule.class,
|
|
266
|
+
rule_id: rule.id,
|
|
267
|
+
ttl: rule.ttl,
|
|
268
|
+
reason: truncatedStderr,
|
|
269
|
+
};
|
|
270
|
+
}
|
|
271
|
+
}
|
|
272
|
+
return null;
|
|
273
|
+
}
|
|
274
|
+
|
|
@@ -0,0 +1,60 @@
|
|
|
1
|
+
import { loadRules, classify, parseTtl, classifySync, InvalidRulesConfigError } from './error-classifier.mjs';
|
|
2
|
+
import { mkdtempSync, writeFileSync, rmSync, mkdirSync } from 'fs';
|
|
3
|
+
import path from 'path';
|
|
4
|
+
import os from 'os';
|
|
5
|
+
|
|
6
|
+
const tmp = mkdtempSync(path.join(os.tmpdir(), 'ec-test-'));
|
|
7
|
+
const configDir = path.join(tmp, '.workflow/config');
|
|
8
|
+
mkdirSync(configDir, { recursive: true });
|
|
9
|
+
const configPath = path.join(configDir, 'agent-health-rules.yaml');
|
|
10
|
+
|
|
11
|
+
writeFileSync(configPath, `version: "1.0"
|
|
12
|
+
common:
|
|
13
|
+
- id: "net-econnreset"
|
|
14
|
+
class: "transient"
|
|
15
|
+
ttl: "5m"
|
|
16
|
+
pattern: "ECONNRESET|ETIMEDOUT"
|
|
17
|
+
exit_codes: "any"
|
|
18
|
+
agents:
|
|
19
|
+
qwen-code:
|
|
20
|
+
rules:
|
|
21
|
+
- id: "qwen-quota"
|
|
22
|
+
class: "unavailable"
|
|
23
|
+
ttl: "until_utc_midnight"
|
|
24
|
+
pattern: "Qwen OAuth quota exceeded"
|
|
25
|
+
exit_codes: "any"
|
|
26
|
+
`);
|
|
27
|
+
|
|
28
|
+
const rules = loadRules(tmp);
|
|
29
|
+
console.log('loadRules result:', { commonLen: rules.common.length, agentsSize: rules.agents.size });
|
|
30
|
+
|
|
31
|
+
const result1 = await classify(rules, 'qwen-code', { exitCode: 1, stderr: 'Qwen OAuth quota exceeded' });
|
|
32
|
+
console.log('classify qwen-quota:', result1?.class, result1?.rule_id);
|
|
33
|
+
|
|
34
|
+
const result2 = await classify(rules, 'qwen-code', { exitCode: 1, stderr: 'Some other error' });
|
|
35
|
+
console.log('classify no match:', result2);
|
|
36
|
+
|
|
37
|
+
const result3 = await classify(rules, 'claude-sonnet', { exitCode: 1, stderr: 'ECONNRESET' });
|
|
38
|
+
console.log('classify common:', result3?.class, result3?.rule_id);
|
|
39
|
+
|
|
40
|
+
const result4 = classifySync(rules, 'qwen-code', { exitCode: 1, stderr: 'Qwen OAuth quota exceeded' });
|
|
41
|
+
console.log('classifySync qwen-quota:', result4?.class, result4?.rule_id);
|
|
42
|
+
|
|
43
|
+
const ttl1 = parseTtl('5m');
|
|
44
|
+
console.log('parseTtl 5m:', typeof ttl1, ttl1 > Date.now());
|
|
45
|
+
|
|
46
|
+
const ttl2 = parseTtl('infinite');
|
|
47
|
+
console.log('parseTtl infinite:', ttl2 === Number.MAX_SAFE_INTEGER);
|
|
48
|
+
|
|
49
|
+
const now = new Date('2026-04-21T12:00:00Z').getTime();
|
|
50
|
+
const ttl3 = parseTtl('until_utc_midnight', now);
|
|
51
|
+
console.log('parseTtl until_utc_midnight:', ttl3 >= now);
|
|
52
|
+
|
|
53
|
+
const ttl4 = parseTtl('1h');
|
|
54
|
+
console.log('parseTtl 1h:', ttl4 > now);
|
|
55
|
+
|
|
56
|
+
const ttl5 = parseTtl('1d');
|
|
57
|
+
console.log('parseTtl 1d:', ttl5 > now);
|
|
58
|
+
|
|
59
|
+
rmSync(tmp, { recursive: true, force: true });
|
|
60
|
+
console.log('All tests passed!');
|
|
@@ -0,0 +1,58 @@
|
|
|
1
|
+
import { loadRules, classify, classifySync } from './error-classifier.mjs';
|
|
2
|
+
import { mkdtempSync, writeFileSync, rmSync, mkdirSync } from 'fs';
|
|
3
|
+
import path from 'path';
|
|
4
|
+
import os from 'os';
|
|
5
|
+
|
|
6
|
+
const tmp = mkdtempSync(path.join(os.tmpdir(), 'ec-test-'));
|
|
7
|
+
const configDir = path.join(tmp, '.workflow/config');
|
|
8
|
+
mkdirSync(configDir, { recursive: true });
|
|
9
|
+
const configPath = path.join(configDir, 'agent-health-rules.yaml');
|
|
10
|
+
|
|
11
|
+
writeFileSync(configPath, `version: "1.0"
|
|
12
|
+
common:
|
|
13
|
+
- id: "common-test"
|
|
14
|
+
class: "transient"
|
|
15
|
+
ttl: "5m"
|
|
16
|
+
pattern: "common-error"
|
|
17
|
+
exit_codes: "any"
|
|
18
|
+
agents:
|
|
19
|
+
claude-sonnet:
|
|
20
|
+
rules:
|
|
21
|
+
- id: "claude-specific"
|
|
22
|
+
class: "unavailable"
|
|
23
|
+
ttl: "10m"
|
|
24
|
+
pattern: "claude-specific-error"
|
|
25
|
+
exit_codes: "any"
|
|
26
|
+
claude-opus:
|
|
27
|
+
extends: claude-sonnet
|
|
28
|
+
kilo-glm:
|
|
29
|
+
rules:
|
|
30
|
+
- id: "kilo-own"
|
|
31
|
+
class: "misconfigured"
|
|
32
|
+
ttl: "1h"
|
|
33
|
+
pattern: "kilo-error"
|
|
34
|
+
exit_codes: "any"
|
|
35
|
+
`);
|
|
36
|
+
|
|
37
|
+
const rules = loadRules(tmp);
|
|
38
|
+
console.log('loadRules with extends:');
|
|
39
|
+
|
|
40
|
+
const opusRules = rules.agents.get('claude-opus');
|
|
41
|
+
console.log('claude-opus rules (from extends):', opusRules?.length);
|
|
42
|
+
console.log('claude-opus first rule:', opusRules?.[0]?.id);
|
|
43
|
+
|
|
44
|
+
const glmRules = rules.agents.get('kilo-glm');
|
|
45
|
+
console.log('kilo-glm rules (own):', glmRules?.length);
|
|
46
|
+
console.log('kilo-glm first rule:', glmRules?.[0]?.id);
|
|
47
|
+
|
|
48
|
+
const test1 = classifySync(rules, 'claude-opus', { exitCode: 1, stderr: 'claude-specific-error' });
|
|
49
|
+
console.log('classify claude-opus with specific error:', test1?.class, test1?.rule_id);
|
|
50
|
+
|
|
51
|
+
const test2 = classifySync(rules, 'claude-opus', { exitCode: 1, stderr: 'common-error' });
|
|
52
|
+
console.log('classify claude-opus with common error:', test2?.class, test2?.rule_id);
|
|
53
|
+
|
|
54
|
+
const test3 = classifySync(rules, 'kilo-glm', { exitCode: 1, stderr: 'kilo-error' });
|
|
55
|
+
console.log('classify kilo-glm with own error:', test3?.class, test3?.rule_id);
|
|
56
|
+
|
|
57
|
+
rmSync(tmp, { recursive: true, force: true });
|
|
58
|
+
console.log('Extends tests passed!');
|
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
import { InvalidRulesConfigError } from './error-classifier.mjs';
|
|
2
|
+
import { mkdtempSync, writeFileSync, rmSync, mkdirSync } from 'fs';
|
|
3
|
+
import path from 'path';
|
|
4
|
+
import os from 'os';
|
|
5
|
+
|
|
6
|
+
const tmp = mkdtempSync(path.join(os.tmpdir(), 'ec-test-'));
|
|
7
|
+
const configDir = path.join(tmp, '.workflow/config');
|
|
8
|
+
mkdirSync(configDir, { recursive: true });
|
|
9
|
+
const configPath = path.join(configDir, 'agent-health-rules.yaml');
|
|
10
|
+
|
|
11
|
+
writeFileSync(configPath, 'version: "2.0"\ncommon: []');
|
|
12
|
+
|
|
13
|
+
try {
|
|
14
|
+
const { loadRules } = await import('./error-classifier.mjs');
|
|
15
|
+
loadRules(tmp);
|
|
16
|
+
console.log('ERROR: should have thrown');
|
|
17
|
+
} catch (e) {
|
|
18
|
+
console.log('Version error works:', e.name === 'InvalidRulesConfigError', e.message.includes('2.0'));
|
|
19
|
+
}
|
|
20
|
+
|
|
21
|
+
rmSync(tmp, { recursive: true, force: true });
|
|
@@ -16,8 +16,6 @@ import fs from "fs";
|
|
|
16
16
|
import path from "path";
|
|
17
17
|
import { findProjectRoot } from "workflow-ai/lib/find-root.mjs";
|
|
18
18
|
import {
|
|
19
|
-
parseFrontmatter,
|
|
20
|
-
serializeFrontmatter,
|
|
21
19
|
printResult,
|
|
22
20
|
getLastReviewStatus,
|
|
23
21
|
} from "workflow-ai/lib/utils.mjs";
|
|
@@ -98,18 +96,18 @@ function moveToReview(ticketId) {
|
|
|
98
96
|
}
|
|
99
97
|
|
|
100
98
|
const content = fs.readFileSync(sourcePath, "utf8");
|
|
101
|
-
const { frontmatter, body } = parseFrontmatter(content);
|
|
102
99
|
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
|
|
100
|
+
// updated_at не обновляем: verify-artifacts сравнивает mtime файлов с updated_at,
|
|
101
|
+
// чтобы убедиться, что они были изменены агентом. updated_at должен сохранять момент
|
|
102
|
+
// перемещения тикета в in-progress (до начала работы агента) — иначе любой
|
|
103
|
+
// легитимно изменённый файл будет ложно отклонён (mtime_edit < updated_at_review).
|
|
106
104
|
|
|
107
105
|
if (!fs.existsSync(REVIEW_DIR)) {
|
|
108
106
|
fs.mkdirSync(REVIEW_DIR, { recursive: true });
|
|
109
107
|
}
|
|
110
108
|
|
|
111
109
|
fs.renameSync(sourcePath, targetPath);
|
|
112
|
-
fs.writeFileSync(targetPath,
|
|
110
|
+
fs.writeFileSync(targetPath, content, "utf8");
|
|
113
111
|
|
|
114
112
|
return {
|
|
115
113
|
status: "moved",
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
#!/usr/bin/env node
|
|
2
|
+
|
|
3
|
+
import { loadHealth, markHealthy, unhealthy } from '../lib/agent-health-registry.mjs';
|
|
4
|
+
|
|
5
|
+
const projectRoot = process.cwd();
|
|
6
|
+
|
|
7
|
+
function getState() {
|
|
8
|
+
return loadHealth(projectRoot);
|
|
9
|
+
}
|
|
10
|
+
|
|
11
|
+
function showState() {
|
|
12
|
+
const state = getState();
|
|
13
|
+
console.log('---RESULT---');
|
|
14
|
+
console.log(JSON.stringify(state, null, 2));
|
|
15
|
+
console.log('---RESULT---');
|
|
16
|
+
}
|
|
17
|
+
|
|
18
|
+
function resetAgent(agentId) {
|
|
19
|
+
const state = getState();
|
|
20
|
+
const agent = state.agents[agentId];
|
|
21
|
+
|
|
22
|
+
if (!agent) {
|
|
23
|
+
console.log(`Agent "${agentId}" not found in health registry`);
|
|
24
|
+
return;
|
|
25
|
+
}
|
|
26
|
+
|
|
27
|
+
markHealthy(projectRoot, agentId);
|
|
28
|
+
console.log(`Reset health status for agent "${agentId}"`);
|
|
29
|
+
}
|
|
30
|
+
|
|
31
|
+
function resetAll() {
|
|
32
|
+
const unhealthyAgents = unhealthy(projectRoot);
|
|
33
|
+
|
|
34
|
+
if (unhealthyAgents.length === 0) {
|
|
35
|
+
console.log('No unhealthy agents to reset');
|
|
36
|
+
return;
|
|
37
|
+
}
|
|
38
|
+
|
|
39
|
+
const resetList = unhealthyAgents.map(a => a.agentId);
|
|
40
|
+
|
|
41
|
+
for (const agentId of resetList) {
|
|
42
|
+
markHealthy(projectRoot, agentId);
|
|
43
|
+
}
|
|
44
|
+
|
|
45
|
+
console.log(`Reset ${resetList.length} agent(s): ${resetList.join(', ')}`);
|
|
46
|
+
}
|
|
47
|
+
|
|
48
|
+
const args = process.argv.slice(2);
|
|
49
|
+
|
|
50
|
+
if (args.length === 0) {
|
|
51
|
+
showState();
|
|
52
|
+
} else if (args[0] === '--agent' && args[1]) {
|
|
53
|
+
resetAgent(args[1]);
|
|
54
|
+
} else if (args[0] === '--all') {
|
|
55
|
+
resetAll();
|
|
56
|
+
} else {
|
|
57
|
+
console.log('Usage:');
|
|
58
|
+
console.log(' node reset-agent-health.js # Show current state');
|
|
59
|
+
console.log(' node reset-agent-health.js --agent <id> # Reset single agent');
|
|
60
|
+
console.log(' node reset-agent-health.js --all # Reset all unhealthy');
|
|
61
|
+
process.exit(1);
|
|
62
|
+
}
|