agentic-qe 3.4.1 → 3.4.2
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/.claude/skills/.validation/README.md +111 -0
- package/.claude/skills/.validation/examples/chaos-engineering-output.example.json +530 -0
- package/.claude/skills/.validation/examples/performance-testing-output.example.json +252 -0
- package/.claude/skills/.validation/examples/security-testing-output.example.json +413 -0
- package/.claude/skills/.validation/examples/testability-scoring-output.example.json +350 -0
- package/.claude/skills/.validation/schemas/skill-eval.schema.json +452 -0
- package/.claude/skills/.validation/schemas/skill-frontmatter.schema.json +341 -0
- package/.claude/skills/.validation/schemas/skill-output-meta.schema.json +199 -0
- package/.claude/skills/.validation/schemas/skill-output.template.json +610 -0
- package/.claude/skills/.validation/skill-validation-mcp-integration.md +250 -0
- package/.claude/skills/.validation/templates/eval.template.yaml +366 -0
- package/.claude/skills/.validation/templates/schemas/output.json +145 -0
- package/.claude/skills/.validation/templates/security-testing-eval.template.yaml +725 -0
- package/.claude/skills/.validation/templates/skill-frontmatter.example.yaml +225 -0
- package/.claude/skills/.validation/templates/validate.template.sh +1060 -0
- package/.claude/skills/.validation/templates/validator-lib.sh +1031 -0
- package/.claude/skills/.validation/test-data/invalid-output.json +5 -0
- package/.claude/skills/.validation/test-data/minimal-output.json +9 -0
- package/.claude/skills/.validation/test-data/sample-output.json +73 -0
- package/.claude/skills/TRUST-TIERS.md +158 -0
- package/.claude/skills/a11y-ally/SKILL.md +1664 -1658
- package/.claude/skills/a11y-ally/evals/a11y-ally.yaml +376 -0
- package/.claude/skills/a11y-ally/schemas/output.json +549 -0
- package/.claude/skills/a11y-ally/scripts/validate.sh +690 -0
- package/.claude/skills/accessibility-testing/SKILL.md +8 -1
- package/.claude/skills/accessibility-testing/evals/accessibility-testing.yaml +719 -0
- package/.claude/skills/accessibility-testing/schemas/output.json +776 -0
- package/.claude/skills/accessibility-testing/scripts/validate.sh +943 -0
- package/.claude/skills/accessibility-testing/test-data/sample-output.json +191 -0
- package/.claude/skills/agentic-quality-engineering/SKILL.md +4 -0
- package/.claude/skills/agentic-quality-engineering/schemas/output.json +577 -0
- package/.claude/skills/api-testing-patterns/SKILL.md +5 -0
- package/.claude/skills/api-testing-patterns/evals/api-testing-patterns.yaml +696 -0
- package/.claude/skills/api-testing-patterns/schemas/output.json +845 -0
- package/.claude/skills/api-testing-patterns/scripts/validate.sh +931 -0
- package/.claude/skills/aqe-v2-v3-migration/schemas/output.json +513 -0
- package/.claude/skills/aqe-v2-v3-migration/skill.md +4 -0
- package/.claude/skills/brutal-honesty-review/SKILL.md +5 -0
- package/.claude/skills/brutal-honesty-review/schemas/output.json +291 -0
- package/.claude/skills/brutal-honesty-review/scripts/validate.sh +130 -0
- package/.claude/skills/bug-reporting-excellence/SKILL.md +5 -0
- package/.claude/skills/bug-reporting-excellence/schemas/output.json +288 -0
- package/.claude/skills/bug-reporting-excellence/scripts/validate.sh +108 -0
- package/.claude/skills/chaos-engineering-resilience/SKILL.md +5 -0
- package/.claude/skills/chaos-engineering-resilience/evals/chaos-engineering-resilience.yaml +761 -0
- package/.claude/skills/chaos-engineering-resilience/schemas/output.json +1205 -0
- package/.claude/skills/chaos-engineering-resilience/scripts/validate.sh +1107 -0
- package/.claude/skills/cicd-pipeline-qe-orchestrator/SKILL.md +6 -0
- package/.claude/skills/cicd-pipeline-qe-orchestrator/evals/cicd-pipeline-qe-orchestrator.yaml +157 -0
- package/.claude/skills/cicd-pipeline-qe-orchestrator/schemas/output.json +542 -0
- package/.claude/skills/cicd-pipeline-qe-orchestrator/scripts/validate.sh +310 -0
- package/.claude/skills/code-review-quality/SKILL.md +5 -0
- package/.claude/skills/code-review-quality/schemas/output.json +264 -0
- package/.claude/skills/code-review-quality/scripts/validate.sh +113 -0
- package/.claude/skills/compatibility-testing/evals/compatibility-testing.yaml +410 -0
- package/.claude/skills/compatibility-testing/schemas/output.json +551 -0
- package/.claude/skills/compatibility-testing/scripts/validate.sh +605 -0
- package/.claude/skills/compliance-testing/SKILL.md +7 -0
- package/.claude/skills/compliance-testing/evals/compliance-testing.yaml +1107 -0
- package/.claude/skills/compliance-testing/schemas/output.json +845 -0
- package/.claude/skills/compliance-testing/scripts/validate.sh +888 -0
- package/.claude/skills/consultancy-practices/SKILL.md +4 -0
- package/.claude/skills/consultancy-practices/schemas/output.json +282 -0
- package/.claude/skills/context-driven-testing/SKILL.md +3 -0
- package/.claude/skills/contract-testing/SKILL.md +5 -0
- package/.claude/skills/contract-testing/evals/contract-testing.yaml +748 -0
- package/.claude/skills/contract-testing/schemas/output.json +638 -0
- package/.claude/skills/contract-testing/scripts/validate.sh +1033 -0
- package/.claude/skills/database-testing/SKILL.md +5 -0
- package/.claude/skills/database-testing/evals/database-testing.yaml +968 -0
- package/.claude/skills/database-testing/schemas/output.json +1446 -0
- package/.claude/skills/database-testing/scripts/validate.sh +1099 -0
- package/.claude/skills/exploratory-testing-advanced/SKILL.md +3 -0
- package/.claude/skills/holistic-testing-pact/SKILL.md +3 -0
- package/.claude/skills/localization-testing/SKILL.md +6 -0
- package/.claude/skills/localization-testing/evals/localization-testing.yaml +544 -0
- package/.claude/skills/localization-testing/schemas/output.json +325 -0
- package/.claude/skills/localization-testing/scripts/validate.sh +131 -0
- package/.claude/skills/mobile-testing/SKILL.md +6 -0
- package/.claude/skills/mobile-testing/evals/mobile-testing.yaml +537 -0
- package/.claude/skills/mobile-testing/schemas/output.json +318 -0
- package/.claude/skills/mobile-testing/scripts/validate.sh +127 -0
- package/.claude/skills/mutation-testing/SKILL.md +8 -1
- package/.claude/skills/mutation-testing/evals/mutation-testing.yaml +652 -0
- package/.claude/skills/mutation-testing/schemas/output.json +707 -0
- package/.claude/skills/mutation-testing/scripts/validate.sh +992 -0
- package/.claude/skills/mutation-testing/test-data/sample-output.json +295 -0
- package/.claude/skills/n8n-expression-testing/SKILL.md +6 -0
- package/.claude/skills/n8n-expression-testing/evals/n8n-expression-testing.yaml +450 -0
- package/.claude/skills/n8n-expression-testing/schemas/output.json +369 -0
- package/.claude/skills/n8n-expression-testing/scripts/validate.sh +162 -0
- package/.claude/skills/n8n-integration-testing-patterns/SKILL.md +6 -0
- package/.claude/skills/n8n-integration-testing-patterns/evals/n8n-integration-testing-patterns.yaml +522 -0
- package/.claude/skills/n8n-integration-testing-patterns/schemas/output.json +291 -0
- package/.claude/skills/n8n-integration-testing-patterns/scripts/validate.sh +104 -0
- package/.claude/skills/n8n-security-testing/SKILL.md +6 -0
- package/.claude/skills/n8n-security-testing/evals/n8n-security-testing.yaml +493 -0
- package/.claude/skills/n8n-security-testing/schemas/output.json +293 -0
- package/.claude/skills/n8n-security-testing/scripts/validate.sh +120 -0
- package/.claude/skills/n8n-trigger-testing-strategies/SKILL.md +6 -0
- package/.claude/skills/n8n-trigger-testing-strategies/evals/n8n-trigger-testing-strategies.yaml +500 -0
- package/.claude/skills/n8n-trigger-testing-strategies/schemas/output.json +295 -0
- package/.claude/skills/n8n-trigger-testing-strategies/scripts/validate.sh +121 -0
- package/.claude/skills/n8n-workflow-testing-fundamentals/SKILL.md +6 -0
- package/.claude/skills/n8n-workflow-testing-fundamentals/evals/n8n-workflow-testing-fundamentals.yaml +497 -0
- package/.claude/skills/n8n-workflow-testing-fundamentals/schemas/output.json +254 -0
- package/.claude/skills/n8n-workflow-testing-fundamentals/scripts/validate.sh +126 -0
- package/.claude/skills/performance-analysis/SKILL.md +6 -0
- package/.claude/skills/performance-analysis/evals/performance-analysis.yaml +144 -0
- package/.claude/skills/performance-analysis/schemas/output.json +588 -0
- package/.claude/skills/performance-analysis/scripts/validate.sh +63 -0
- package/.claude/skills/performance-testing/SKILL.md +5 -0
- package/.claude/skills/performance-testing/evals/performance-testing.yaml +772 -0
- package/.claude/skills/performance-testing/schemas/output.json +1184 -0
- package/.claude/skills/performance-testing/scripts/validate.sh +1090 -0
- package/.claude/skills/qcsd-ideation-swarm/SKILL.md +1759 -1753
- package/.claude/skills/qcsd-ideation-swarm/evals/qcsd-ideation-swarm.yaml +138 -0
- package/.claude/skills/qcsd-ideation-swarm/schemas/output.json +568 -0
- package/.claude/skills/qcsd-ideation-swarm/scripts/validate.sh +56 -0
- package/.claude/skills/qe-chaos-resilience/SKILL.md +6 -0
- package/.claude/skills/qe-chaos-resilience/evals/qe-chaos-resilience.yaml +443 -0
- package/.claude/skills/qe-chaos-resilience/schemas/output.json +314 -0
- package/.claude/skills/qe-chaos-resilience/scripts/validate.sh +401 -0
- package/.claude/skills/qe-code-intelligence/SKILL.md +6 -0
- package/.claude/skills/qe-code-intelligence/evals/qe-code-intelligence.yaml +459 -0
- package/.claude/skills/qe-code-intelligence/schemas/output.json +315 -0
- package/.claude/skills/qe-code-intelligence/scripts/validate.sh +408 -0
- package/.claude/skills/qe-contract-testing/SKILL.md +6 -0
- package/.claude/skills/qe-contract-testing/evals/qe-contract-testing.yaml +513 -0
- package/.claude/skills/qe-contract-testing/schemas/output.json +295 -0
- package/.claude/skills/qe-contract-testing/scripts/validate.sh +421 -0
- package/.claude/skills/qe-coverage-analysis/SKILL.md +6 -0
- package/.claude/skills/qe-coverage-analysis/evals/qe-coverage-analysis.yaml +494 -0
- package/.claude/skills/qe-coverage-analysis/schemas/output.json +286 -0
- package/.claude/skills/qe-coverage-analysis/scripts/validate.sh +453 -0
- package/.claude/skills/qe-defect-intelligence/SKILL.md +6 -0
- package/.claude/skills/qe-defect-intelligence/evals/qe-defect-intelligence.yaml +511 -0
- package/.claude/skills/qe-defect-intelligence/schemas/output.json +283 -0
- package/.claude/skills/qe-defect-intelligence/scripts/validate.sh +466 -0
- package/.claude/skills/qe-iterative-loop/SKILL.md +445 -440
- package/.claude/skills/qe-iterative-loop/schemas/output.json +264 -0
- package/.claude/skills/qe-iterative-loop/scripts/validate.sh +474 -0
- package/.claude/skills/qe-learning-optimization/SKILL.md +6 -0
- package/.claude/skills/qe-learning-optimization/evals/qe-learning-optimization.yaml +144 -0
- package/.claude/skills/qe-learning-optimization/schemas/output.json +288 -0
- package/.claude/skills/qe-learning-optimization/scripts/validate.sh +56 -0
- package/.claude/skills/qe-quality-assessment/SKILL.md +6 -0
- package/.claude/skills/qe-quality-assessment/evals/qe-quality-assessment.yaml +506 -0
- package/.claude/skills/qe-quality-assessment/schemas/output.json +550 -0
- package/.claude/skills/qe-quality-assessment/scripts/validate.sh +352 -0
- package/.claude/skills/qe-requirements-validation/SKILL.md +6 -0
- package/.claude/skills/qe-requirements-validation/evals/qe-requirements-validation.yaml +598 -0
- package/.claude/skills/qe-requirements-validation/schemas/output.json +587 -0
- package/.claude/skills/qe-requirements-validation/scripts/validate.sh +275 -0
- package/.claude/skills/qe-security-compliance/SKILL.md +6 -0
- package/.claude/skills/qe-security-compliance/evals/qe-security-compliance.yaml +595 -0
- package/.claude/skills/qe-security-compliance/schemas/output.json +498 -0
- package/.claude/skills/qe-security-compliance/scripts/validate.sh +305 -0
- package/.claude/skills/qe-test-execution/SKILL.md +6 -0
- package/.claude/skills/qe-test-execution/evals/qe-test-execution.yaml +607 -0
- package/.claude/skills/qe-test-execution/schemas/output.json +529 -0
- package/.claude/skills/qe-test-execution/scripts/validate.sh +323 -0
- package/.claude/skills/qe-test-generation/SKILL.md +6 -0
- package/.claude/skills/qe-test-generation/evals/qe-test-generation.yaml +148 -0
- package/.claude/skills/qe-test-generation/schemas/output.json +439 -0
- package/.claude/skills/qe-test-generation/scripts/validate.sh +56 -0
- package/.claude/skills/qe-visual-accessibility/SKILL.md +6 -0
- package/.claude/skills/qe-visual-accessibility/evals/qe-visual-accessibility.yaml +142 -0
- package/.claude/skills/qe-visual-accessibility/schemas/output.json +491 -0
- package/.claude/skills/qe-visual-accessibility/scripts/validate.sh +56 -0
- package/.claude/skills/quality-metrics/SKILL.md +6 -0
- package/.claude/skills/quality-metrics/evals/quality-metrics.yaml +494 -0
- package/.claude/skills/quality-metrics/schemas/output.json +403 -0
- package/.claude/skills/quality-metrics/scripts/validate.sh +434 -0
- package/.claude/skills/refactoring-patterns/SKILL.md +5 -0
- package/.claude/skills/refactoring-patterns/schemas/output.json +475 -0
- package/.claude/skills/refactoring-patterns/scripts/validate.sh +241 -0
- package/.claude/skills/regression-testing/SKILL.md +6 -0
- package/.claude/skills/regression-testing/evals/regression-testing.yaml +504 -0
- package/.claude/skills/regression-testing/schemas/output.json +311 -0
- package/.claude/skills/regression-testing/scripts/validate.sh +130 -0
- package/.claude/skills/risk-based-testing/SKILL.md +6 -0
- package/.claude/skills/risk-based-testing/evals/risk-based-testing.yaml +141 -0
- package/.claude/skills/risk-based-testing/schemas/output.json +480 -0
- package/.claude/skills/risk-based-testing/scripts/validate.sh +56 -0
- package/.claude/skills/security-testing/SKILL.md +5 -0
- package/.claude/skills/security-testing/evals/security-testing.yaml +789 -0
- package/.claude/skills/security-testing/schemas/output.json +879 -0
- package/.claude/skills/security-testing/scripts/validate.sh +967 -0
- package/.claude/skills/security-visual-testing/SKILL.md +223 -217
- package/.claude/skills/security-visual-testing/evals/security-visual-testing.yaml +163 -0
- package/.claude/skills/security-visual-testing/schemas/output.json +486 -0
- package/.claude/skills/security-visual-testing/scripts/validate.sh +748 -0
- package/.claude/skills/sherlock-review/SKILL.md +5 -0
- package/.claude/skills/sherlock-review/schemas/output.json +297 -0
- package/.claude/skills/sherlock-review/scripts/validate.sh +115 -0
- package/.claude/skills/shift-left-testing/SKILL.md +6 -0
- package/.claude/skills/shift-left-testing/evals/shift-left-testing.yaml +145 -0
- package/.claude/skills/shift-left-testing/schemas/output.json +459 -0
- package/.claude/skills/shift-left-testing/scripts/validate.sh +56 -0
- package/.claude/skills/shift-right-testing/SKILL.md +6 -0
- package/.claude/skills/shift-right-testing/evals/shift-right-testing.yaml +147 -0
- package/.claude/skills/shift-right-testing/schemas/output.json +418 -0
- package/.claude/skills/shift-right-testing/scripts/validate.sh +56 -0
- package/.claude/skills/six-thinking-hats/SKILL.md +3 -0
- package/.claude/skills/tdd-london-chicago/SKILL.md +5 -0
- package/.claude/skills/tdd-london-chicago/schemas/output.json +444 -0
- package/.claude/skills/tdd-london-chicago/scripts/validate.sh +214 -0
- package/.claude/skills/technical-writing/SKILL.md +4 -0
- package/.claude/skills/technical-writing/schemas/output.json +268 -0
- package/.claude/skills/test-automation-strategy/SKILL.md +6 -0
- package/.claude/skills/test-automation-strategy/evals/test-automation-strategy.yaml +148 -0
- package/.claude/skills/test-automation-strategy/schemas/output.json +444 -0
- package/.claude/skills/test-automation-strategy/scripts/validate.sh +195 -0
- package/.claude/skills/test-data-management/SKILL.md +6 -0
- package/.claude/skills/test-data-management/evals/test-data-management.yaml +504 -0
- package/.claude/skills/test-data-management/schemas/output.json +284 -0
- package/.claude/skills/test-data-management/scripts/validate.sh +137 -0
- package/.claude/skills/test-design-techniques/SKILL.md +6 -0
- package/.claude/skills/test-design-techniques/evals/test-design-techniques.yaml +142 -0
- package/.claude/skills/test-design-techniques/schemas/output.json +295 -0
- package/.claude/skills/test-design-techniques/scripts/validate.sh +91 -0
- package/.claude/skills/test-environment-management/SKILL.md +4 -0
- package/.claude/skills/test-environment-management/schemas/output.json +310 -0
- package/.claude/skills/test-reporting-analytics/SKILL.md +6 -0
- package/.claude/skills/test-reporting-analytics/evals/test-reporting-analytics.yaml +155 -0
- package/.claude/skills/test-reporting-analytics/schemas/output.json +329 -0
- package/.claude/skills/test-reporting-analytics/scripts/validate.sh +77 -0
- package/.claude/skills/testability-scoring/SKILL.md +5 -0
- package/.claude/skills/testability-scoring/evals/testability-scoring.yaml +814 -0
- package/.claude/skills/testability-scoring/schemas/output.json +606 -0
- package/.claude/skills/testability-scoring/scripts/validate.sh +891 -0
- package/.claude/skills/trust-tier-manifest.json +2333 -0
- package/.claude/skills/verification-quality/SKILL.md +6 -0
- package/.claude/skills/verification-quality/evals/verification-quality.yaml +150 -0
- package/.claude/skills/verification-quality/schemas/output.json +432 -0
- package/.claude/skills/verification-quality/scripts/validate.sh +77 -0
- package/.claude/skills/visual-testing-advanced/SKILL.md +6 -0
- package/.claude/skills/visual-testing-advanced/evals/visual-testing-advanced.yaml +154 -0
- package/.claude/skills/visual-testing-advanced/schemas/output.json +294 -0
- package/.claude/skills/visual-testing-advanced/scripts/validate.sh +77 -0
- package/.claude/skills/xp-practices/SKILL.md +3 -0
- package/README.md +39 -2
- package/package.json +4 -1
- package/scripts/run-skill-eval.ts +1097 -0
- package/scripts/test-schema-validation.js +301 -0
- package/scripts/update-skill-manifest.ts +751 -0
- package/scripts/validate-skill-frontmatter.js +141 -0
- package/v3/CHANGELOG.md +21 -0
- package/v3/README.md +43 -3
- package/v3/assets/agents/v3/qe-test-idea-rewriter.md +375 -375
- package/v3/assets/skills/.validation/README.md +111 -0
- package/v3/assets/skills/.validation/examples/chaos-engineering-output.example.json +530 -0
- package/v3/assets/skills/.validation/examples/performance-testing-output.example.json +252 -0
- package/v3/assets/skills/.validation/examples/security-testing-output.example.json +413 -0
- package/v3/assets/skills/.validation/examples/testability-scoring-output.example.json +350 -0
- package/v3/assets/skills/.validation/schemas/skill-eval.schema.json +452 -0
- package/v3/assets/skills/.validation/schemas/skill-frontmatter.schema.json +341 -0
- package/v3/assets/skills/.validation/schemas/skill-output-meta.schema.json +199 -0
- package/v3/assets/skills/.validation/schemas/skill-output.template.json +610 -0
- package/v3/assets/skills/.validation/skill-validation-mcp-integration.md +250 -0
- package/v3/assets/skills/.validation/templates/eval.template.yaml +366 -0
- package/v3/assets/skills/.validation/templates/schemas/output.json +145 -0
- package/v3/assets/skills/.validation/templates/security-testing-eval.template.yaml +725 -0
- package/v3/assets/skills/.validation/templates/skill-frontmatter.example.yaml +225 -0
- package/v3/assets/skills/.validation/templates/validate.template.sh +1060 -0
- package/v3/assets/skills/.validation/templates/validator-lib.sh +1031 -0
- package/v3/assets/skills/.validation/test-data/invalid-output.json +5 -0
- package/v3/assets/skills/.validation/test-data/minimal-output.json +9 -0
- package/v3/assets/skills/.validation/test-data/sample-output.json +73 -0
- package/v3/assets/skills/accessibility-testing/SKILL.md +8 -1
- package/v3/assets/skills/accessibility-testing/evals/accessibility-testing.yaml +719 -0
- package/v3/assets/skills/accessibility-testing/schemas/output.json +776 -0
- package/v3/assets/skills/accessibility-testing/scripts/validate.sh +943 -0
- package/v3/assets/skills/accessibility-testing/test-data/sample-output.json +191 -0
- package/v3/assets/skills/agentic-quality-engineering/SKILL.md +4 -0
- package/v3/assets/skills/agentic-quality-engineering/schemas/output.json +577 -0
- package/v3/assets/skills/api-testing-patterns/SKILL.md +5 -0
- package/v3/assets/skills/api-testing-patterns/evals/api-testing-patterns.yaml +696 -0
- package/v3/assets/skills/api-testing-patterns/schemas/output.json +845 -0
- package/v3/assets/skills/api-testing-patterns/scripts/validate.sh +931 -0
- package/v3/assets/skills/aqe-v2-v3-migration/schemas/output.json +513 -0
- package/v3/assets/skills/aqe-v2-v3-migration/skill.md +20 -16
- package/v3/assets/skills/bug-reporting-excellence/SKILL.md +5 -0
- package/v3/assets/skills/bug-reporting-excellence/schemas/output.json +288 -0
- package/v3/assets/skills/bug-reporting-excellence/scripts/validate.sh +108 -0
- package/v3/assets/skills/chaos-engineering-resilience/SKILL.md +5 -0
- package/v3/assets/skills/chaos-engineering-resilience/evals/chaos-engineering-resilience.yaml +761 -0
- package/v3/assets/skills/chaos-engineering-resilience/schemas/output.json +1205 -0
- package/v3/assets/skills/chaos-engineering-resilience/scripts/validate.sh +1107 -0
- package/v3/assets/skills/code-review-quality/SKILL.md +5 -0
- package/v3/assets/skills/code-review-quality/schemas/output.json +264 -0
- package/v3/assets/skills/code-review-quality/scripts/validate.sh +113 -0
- package/v3/assets/skills/compatibility-testing/evals/compatibility-testing.yaml +410 -0
- package/v3/assets/skills/compatibility-testing/schemas/output.json +551 -0
- package/v3/assets/skills/compatibility-testing/scripts/validate.sh +605 -0
- package/v3/assets/skills/compliance-testing/SKILL.md +7 -0
- package/v3/assets/skills/compliance-testing/evals/compliance-testing.yaml +1107 -0
- package/v3/assets/skills/compliance-testing/schemas/output.json +845 -0
- package/v3/assets/skills/compliance-testing/scripts/validate.sh +888 -0
- package/v3/assets/skills/consultancy-practices/SKILL.md +4 -0
- package/v3/assets/skills/consultancy-practices/schemas/output.json +282 -0
- package/v3/assets/skills/context-driven-testing/SKILL.md +3 -0
- package/v3/assets/skills/contract-testing/SKILL.md +5 -0
- package/v3/assets/skills/contract-testing/evals/contract-testing.yaml +748 -0
- package/v3/assets/skills/contract-testing/schemas/output.json +638 -0
- package/v3/assets/skills/contract-testing/scripts/validate.sh +1033 -0
- package/v3/assets/skills/database-testing/SKILL.md +5 -0
- package/v3/assets/skills/database-testing/evals/database-testing.yaml +968 -0
- package/v3/assets/skills/database-testing/schemas/output.json +1446 -0
- package/v3/assets/skills/database-testing/scripts/validate.sh +1099 -0
- package/v3/assets/skills/exploratory-testing-advanced/SKILL.md +3 -0
- package/v3/assets/skills/holistic-testing-pact/SKILL.md +3 -0
- package/v3/assets/skills/localization-testing/SKILL.md +6 -0
- package/v3/assets/skills/localization-testing/evals/localization-testing.yaml +544 -0
- package/v3/assets/skills/localization-testing/schemas/output.json +325 -0
- package/v3/assets/skills/localization-testing/scripts/validate.sh +131 -0
- package/v3/assets/skills/mobile-testing/SKILL.md +6 -0
- package/v3/assets/skills/mobile-testing/evals/mobile-testing.yaml +537 -0
- package/v3/assets/skills/mobile-testing/schemas/output.json +318 -0
- package/v3/assets/skills/mobile-testing/scripts/validate.sh +127 -0
- package/v3/assets/skills/mutation-testing/SKILL.md +8 -1
- package/v3/assets/skills/mutation-testing/evals/mutation-testing.yaml +652 -0
- package/v3/assets/skills/mutation-testing/schemas/output.json +707 -0
- package/v3/assets/skills/mutation-testing/scripts/validate.sh +992 -0
- package/v3/assets/skills/mutation-testing/test-data/sample-output.json +295 -0
- package/v3/assets/skills/n8n-expression-testing/scripts/validate.sh +162 -0
- package/v3/assets/skills/n8n-integration-testing-patterns/scripts/validate.sh +104 -0
- package/v3/assets/skills/n8n-security-testing/scripts/validate.sh +120 -0
- package/v3/assets/skills/n8n-trigger-testing-strategies/scripts/validate.sh +121 -0
- package/v3/assets/skills/n8n-workflow-testing-fundamentals/scripts/validate.sh +126 -0
- package/v3/assets/skills/performance-testing/SKILL.md +5 -0
- package/v3/assets/skills/performance-testing/evals/performance-testing.yaml +772 -0
- package/v3/assets/skills/performance-testing/schemas/output.json +1184 -0
- package/v3/assets/skills/performance-testing/scripts/validate.sh +1090 -0
- package/v3/assets/skills/qe-chaos-resilience/SKILL.md +6 -0
- package/v3/assets/skills/qe-chaos-resilience/evals/qe-chaos-resilience.yaml +443 -0
- package/v3/assets/skills/qe-chaos-resilience/schemas/output.json +314 -0
- package/v3/assets/skills/qe-chaos-resilience/scripts/validate.sh +401 -0
- package/v3/assets/skills/qe-code-intelligence/SKILL.md +6 -0
- package/v3/assets/skills/qe-code-intelligence/evals/qe-code-intelligence.yaml +459 -0
- package/v3/assets/skills/qe-code-intelligence/schemas/output.json +315 -0
- package/v3/assets/skills/qe-code-intelligence/scripts/validate.sh +408 -0
- package/v3/assets/skills/qe-contract-testing/SKILL.md +6 -0
- package/v3/assets/skills/qe-contract-testing/evals/qe-contract-testing.yaml +513 -0
- package/v3/assets/skills/qe-contract-testing/schemas/output.json +295 -0
- package/v3/assets/skills/qe-contract-testing/scripts/validate.sh +421 -0
- package/v3/assets/skills/qe-coverage-analysis/SKILL.md +6 -0
- package/v3/assets/skills/qe-coverage-analysis/evals/qe-coverage-analysis.yaml +494 -0
- package/v3/assets/skills/qe-coverage-analysis/schemas/output.json +286 -0
- package/v3/assets/skills/qe-coverage-analysis/scripts/validate.sh +453 -0
- package/v3/assets/skills/qe-defect-intelligence/SKILL.md +6 -0
- package/v3/assets/skills/qe-defect-intelligence/evals/qe-defect-intelligence.yaml +511 -0
- package/v3/assets/skills/qe-defect-intelligence/schemas/output.json +283 -0
- package/v3/assets/skills/qe-defect-intelligence/scripts/validate.sh +466 -0
- package/v3/assets/skills/qe-iterative-loop/SKILL.md +445 -443
- package/v3/assets/skills/qe-iterative-loop/schemas/output.json +264 -0
- package/v3/assets/skills/qe-iterative-loop/scripts/validate.sh +474 -0
- package/v3/assets/skills/qe-learning-optimization/SKILL.md +6 -0
- package/v3/assets/skills/qe-learning-optimization/evals/qe-learning-optimization.yaml +144 -0
- package/v3/assets/skills/qe-learning-optimization/schemas/output.json +288 -0
- package/v3/assets/skills/qe-learning-optimization/scripts/validate.sh +56 -0
- package/v3/assets/skills/qe-quality-assessment/SKILL.md +6 -0
- package/v3/assets/skills/qe-quality-assessment/evals/qe-quality-assessment.yaml +506 -0
- package/v3/assets/skills/qe-quality-assessment/schemas/output.json +550 -0
- package/v3/assets/skills/qe-quality-assessment/scripts/validate.sh +352 -0
- package/v3/assets/skills/qe-requirements-validation/SKILL.md +6 -0
- package/v3/assets/skills/qe-requirements-validation/evals/qe-requirements-validation.yaml +598 -0
- package/v3/assets/skills/qe-requirements-validation/schemas/output.json +587 -0
- package/v3/assets/skills/qe-requirements-validation/scripts/validate.sh +275 -0
- package/v3/assets/skills/qe-security-compliance/SKILL.md +6 -0
- package/v3/assets/skills/qe-security-compliance/evals/qe-security-compliance.yaml +595 -0
- package/v3/assets/skills/qe-security-compliance/schemas/output.json +498 -0
- package/v3/assets/skills/qe-security-compliance/scripts/validate.sh +305 -0
- package/v3/assets/skills/qe-test-execution/SKILL.md +6 -0
- package/v3/assets/skills/qe-test-execution/evals/qe-test-execution.yaml +607 -0
- package/v3/assets/skills/qe-test-execution/schemas/output.json +529 -0
- package/v3/assets/skills/qe-test-execution/scripts/validate.sh +323 -0
- package/v3/assets/skills/qe-test-generation/SKILL.md +6 -0
- package/v3/assets/skills/qe-test-generation/evals/qe-test-generation.yaml +148 -0
- package/v3/assets/skills/qe-test-generation/schemas/output.json +439 -0
- package/v3/assets/skills/qe-test-generation/scripts/validate.sh +56 -0
- package/v3/assets/skills/qe-visual-accessibility/SKILL.md +6 -0
- package/v3/assets/skills/qe-visual-accessibility/evals/qe-visual-accessibility.yaml +142 -0
- package/v3/assets/skills/qe-visual-accessibility/schemas/output.json +491 -0
- package/v3/assets/skills/qe-visual-accessibility/scripts/validate.sh +56 -0
- package/v3/assets/skills/quality-metrics/SKILL.md +6 -0
- package/v3/assets/skills/quality-metrics/evals/quality-metrics.yaml +494 -0
- package/v3/assets/skills/quality-metrics/schemas/output.json +403 -0
- package/v3/assets/skills/quality-metrics/scripts/validate.sh +434 -0
- package/v3/assets/skills/refactoring-patterns/SKILL.md +5 -0
- package/v3/assets/skills/refactoring-patterns/schemas/output.json +475 -0
- package/v3/assets/skills/refactoring-patterns/scripts/validate.sh +241 -0
- package/v3/assets/skills/regression-testing/SKILL.md +6 -0
- package/v3/assets/skills/regression-testing/evals/regression-testing.yaml +504 -0
- package/v3/assets/skills/regression-testing/schemas/output.json +311 -0
- package/v3/assets/skills/regression-testing/scripts/validate.sh +130 -0
- package/v3/assets/skills/risk-based-testing/SKILL.md +6 -0
- package/v3/assets/skills/risk-based-testing/evals/risk-based-testing.yaml +141 -0
- package/v3/assets/skills/risk-based-testing/schemas/output.json +480 -0
- package/v3/assets/skills/risk-based-testing/scripts/validate.sh +56 -0
- package/v3/assets/skills/security-testing/SKILL.md +5 -0
- package/v3/assets/skills/security-testing/evals/security-testing.yaml +789 -0
- package/v3/assets/skills/security-testing/schemas/output.json +879 -0
- package/v3/assets/skills/security-testing/scripts/validate.sh +967 -0
- package/v3/assets/skills/shift-left-testing/SKILL.md +6 -0
- package/v3/assets/skills/shift-left-testing/evals/shift-left-testing.yaml +145 -0
- package/v3/assets/skills/shift-left-testing/schemas/output.json +459 -0
- package/v3/assets/skills/shift-left-testing/scripts/validate.sh +56 -0
- package/v3/assets/skills/shift-right-testing/SKILL.md +6 -0
- package/v3/assets/skills/shift-right-testing/evals/shift-right-testing.yaml +147 -0
- package/v3/assets/skills/shift-right-testing/schemas/output.json +418 -0
- package/v3/assets/skills/shift-right-testing/scripts/validate.sh +56 -0
- package/v3/assets/skills/six-thinking-hats/SKILL.md +3 -0
- package/v3/assets/skills/tdd-london-chicago/SKILL.md +5 -0
- package/v3/assets/skills/tdd-london-chicago/schemas/output.json +444 -0
- package/v3/assets/skills/tdd-london-chicago/scripts/validate.sh +214 -0
- package/v3/assets/skills/technical-writing/SKILL.md +4 -0
- package/v3/assets/skills/technical-writing/schemas/output.json +268 -0
- package/v3/assets/skills/test-automation-strategy/SKILL.md +6 -0
- package/v3/assets/skills/test-automation-strategy/evals/test-automation-strategy.yaml +148 -0
- package/v3/assets/skills/test-automation-strategy/schemas/output.json +444 -0
- package/v3/assets/skills/test-automation-strategy/scripts/validate.sh +195 -0
- package/v3/assets/skills/test-data-management/SKILL.md +6 -0
- package/v3/assets/skills/test-data-management/evals/test-data-management.yaml +504 -0
- package/v3/assets/skills/test-data-management/schemas/output.json +284 -0
- package/v3/assets/skills/test-data-management/scripts/validate.sh +137 -0
- package/v3/assets/skills/test-design-techniques/SKILL.md +6 -0
- package/v3/assets/skills/test-design-techniques/evals/test-design-techniques.yaml +142 -0
- package/v3/assets/skills/test-design-techniques/schemas/output.json +295 -0
- package/v3/assets/skills/test-design-techniques/scripts/validate.sh +91 -0
- package/v3/assets/skills/test-environment-management/SKILL.md +4 -0
- package/v3/assets/skills/test-environment-management/schemas/output.json +310 -0
- package/v3/assets/skills/test-reporting-analytics/SKILL.md +6 -0
- package/v3/assets/skills/test-reporting-analytics/evals/test-reporting-analytics.yaml +155 -0
- package/v3/assets/skills/test-reporting-analytics/schemas/output.json +329 -0
- package/v3/assets/skills/test-reporting-analytics/scripts/validate.sh +77 -0
- package/v3/assets/skills/verification-quality/SKILL.md +6 -0
- package/v3/assets/skills/verification-quality/evals/verification-quality.yaml +150 -0
- package/v3/assets/skills/verification-quality/schemas/output.json +432 -0
- package/v3/assets/skills/verification-quality/scripts/validate.sh +77 -0
- package/v3/assets/skills/visual-testing-advanced/SKILL.md +6 -0
- package/v3/assets/skills/visual-testing-advanced/evals/visual-testing-advanced.yaml +154 -0
- package/v3/assets/skills/visual-testing-advanced/schemas/output.json +294 -0
- package/v3/assets/skills/visual-testing-advanced/scripts/validate.sh +77 -0
- package/v3/assets/skills/xp-practices/SKILL.md +3 -0
- package/v3/assets/templates/validation-report.md.hbs +139 -0
- package/v3/assets/templates/validation-summary.json +56 -0
- package/v3/dist/cli/bundle.js +7368 -3418
- package/v3/dist/cli/commands/eval.d.ts +18 -0
- package/v3/dist/cli/commands/eval.d.ts.map +1 -0
- package/v3/dist/cli/commands/eval.js +505 -0
- package/v3/dist/cli/commands/eval.js.map +1 -0
- package/v3/dist/cli/commands/validate-swarm.d.ts +16 -0
- package/v3/dist/cli/commands/validate-swarm.d.ts.map +1 -0
- package/v3/dist/cli/commands/validate-swarm.js +251 -0
- package/v3/dist/cli/commands/validate-swarm.js.map +1 -0
- package/v3/dist/cli/commands/validate.d.ts +14 -0
- package/v3/dist/cli/commands/validate.d.ts.map +1 -0
- package/v3/dist/cli/commands/validate.js +408 -0
- package/v3/dist/cli/commands/validate.js.map +1 -0
- package/v3/dist/cli/index.js +6 -0
- package/v3/dist/cli/index.js.map +1 -1
- package/v3/dist/index.d.ts +2 -0
- package/v3/dist/index.d.ts.map +1 -1
- package/v3/dist/index.js +10 -0
- package/v3/dist/index.js.map +1 -1
- package/v3/dist/init/skills-installer.d.ts +6 -0
- package/v3/dist/init/skills-installer.d.ts.map +1 -1
- package/v3/dist/init/skills-installer.js +48 -0
- package/v3/dist/init/skills-installer.js.map +1 -1
- package/v3/dist/learning/index.d.ts +2 -0
- package/v3/dist/learning/index.d.ts.map +1 -1
- package/v3/dist/learning/index.js +4 -0
- package/v3/dist/learning/index.js.map +1 -1
- package/v3/dist/learning/skill-validation-learner.d.ts +264 -0
- package/v3/dist/learning/skill-validation-learner.d.ts.map +1 -0
- package/v3/dist/learning/skill-validation-learner.js +515 -0
- package/v3/dist/learning/skill-validation-learner.js.map +1 -0
- package/v3/dist/validation/index.d.ts +19 -0
- package/v3/dist/validation/index.d.ts.map +1 -0
- package/v3/dist/validation/index.js +31 -0
- package/v3/dist/validation/index.js.map +1 -0
- package/v3/dist/validation/parallel-eval-runner.d.ts +307 -0
- package/v3/dist/validation/parallel-eval-runner.d.ts.map +1 -0
- package/v3/dist/validation/parallel-eval-runner.js +566 -0
- package/v3/dist/validation/parallel-eval-runner.js.map +1 -0
- package/v3/dist/validation/swarm-skill-validator.d.ts +282 -0
- package/v3/dist/validation/swarm-skill-validator.d.ts.map +1 -0
- package/v3/dist/validation/swarm-skill-validator.js +460 -0
- package/v3/dist/validation/swarm-skill-validator.js.map +1 -0
- package/v3/dist/validation/validation-result-aggregator.d.ts +232 -0
- package/v3/dist/validation/validation-result-aggregator.d.ts.map +1 -0
- package/v3/dist/validation/validation-result-aggregator.js +630 -0
- package/v3/dist/validation/validation-result-aggregator.js.map +1 -0
- package/v3/package.json +1 -1
|
@@ -0,0 +1,307 @@
|
|
|
1
|
+
/**
|
|
2
|
+
* Parallel Evaluation Runner for Skill Validation
|
|
3
|
+
* ADR-056 Phase 5: Distributed test execution across worker pool
|
|
4
|
+
*
|
|
5
|
+
* This module provides parallel execution of skill evaluation test cases
|
|
6
|
+
* using a worker pool pattern for faster skill validation.
|
|
7
|
+
*
|
|
8
|
+
* Features:
|
|
9
|
+
* - Worker pool with configurable concurrency
|
|
10
|
+
* - Batch-based test case distribution
|
|
11
|
+
* - Automatic retry of failed tests
|
|
12
|
+
* - Progress tracking and heartbeat monitoring
|
|
13
|
+
* - Integration with SkillValidationLearner for outcome recording
|
|
14
|
+
* - Parallel speedup measurement vs sequential execution
|
|
15
|
+
*
|
|
16
|
+
* @module validation/parallel-eval-runner
|
|
17
|
+
* @see .claude/skills/.validation/schemas/skill-eval.schema.json
|
|
18
|
+
*/
|
|
19
|
+
import { SkillValidationLearner, TestCaseResult } from '../learning/skill-validation-learner.js';
|
|
20
|
+
/**
|
|
21
|
+
* Configuration for the parallel evaluation runner
|
|
22
|
+
*/
|
|
23
|
+
export interface ParallelEvalConfig {
|
|
24
|
+
/** Maximum number of concurrent workers (default: 5) */
|
|
25
|
+
maxWorkers: number;
|
|
26
|
+
/** Number of test cases per worker batch */
|
|
27
|
+
batchSize: number;
|
|
28
|
+
/** Whether to retry failed tests once */
|
|
29
|
+
retryFailedTests: boolean;
|
|
30
|
+
/** Timeout per test case in milliseconds */
|
|
31
|
+
timeout: number;
|
|
32
|
+
/** Directory containing skill eval suites */
|
|
33
|
+
skillsDir: string;
|
|
34
|
+
/** Progress reporting interval in milliseconds */
|
|
35
|
+
progressIntervalMs: number;
|
|
36
|
+
}
|
|
37
|
+
/**
|
|
38
|
+
* Default configuration values
|
|
39
|
+
*/
|
|
40
|
+
export declare const DEFAULT_PARALLEL_EVAL_CONFIG: ParallelEvalConfig;
|
|
41
|
+
/**
|
|
42
|
+
* Test case input structure from eval YAML
|
|
43
|
+
*/
|
|
44
|
+
export interface EvalTestCaseInput {
|
|
45
|
+
code: string;
|
|
46
|
+
context: {
|
|
47
|
+
language?: string;
|
|
48
|
+
wcagLevel?: string;
|
|
49
|
+
description?: string;
|
|
50
|
+
environment?: string;
|
|
51
|
+
options?: Record<string, unknown>;
|
|
52
|
+
};
|
|
53
|
+
}
|
|
54
|
+
/**
|
|
55
|
+
* Expected output structure from eval YAML
|
|
56
|
+
*/
|
|
57
|
+
export interface EvalTestCaseExpectedOutput {
|
|
58
|
+
must_contain?: string[];
|
|
59
|
+
must_not_contain?: string[];
|
|
60
|
+
must_match_regex?: string[];
|
|
61
|
+
finding_count?: {
|
|
62
|
+
min?: number;
|
|
63
|
+
max?: number;
|
|
64
|
+
};
|
|
65
|
+
severity_classification?: string;
|
|
66
|
+
}
|
|
67
|
+
/**
|
|
68
|
+
* Validation criteria from eval YAML
|
|
69
|
+
*/
|
|
70
|
+
export interface EvalTestCaseValidation {
|
|
71
|
+
schema_check?: boolean;
|
|
72
|
+
keyword_match_threshold?: number;
|
|
73
|
+
reasoning_quality_min?: number;
|
|
74
|
+
grading_rubric?: {
|
|
75
|
+
completeness?: number;
|
|
76
|
+
accuracy?: number;
|
|
77
|
+
actionability?: number;
|
|
78
|
+
};
|
|
79
|
+
}
|
|
80
|
+
/**
|
|
81
|
+
* Single test case from eval suite YAML
|
|
82
|
+
*/
|
|
83
|
+
export interface EvalTestCase {
|
|
84
|
+
id: string;
|
|
85
|
+
description: string;
|
|
86
|
+
category: string;
|
|
87
|
+
priority: 'critical' | 'high' | 'medium' | 'low';
|
|
88
|
+
input: EvalTestCaseInput;
|
|
89
|
+
expected_output: EvalTestCaseExpectedOutput;
|
|
90
|
+
validation?: EvalTestCaseValidation;
|
|
91
|
+
}
|
|
92
|
+
/**
|
|
93
|
+
* Complete eval suite loaded from YAML
|
|
94
|
+
*/
|
|
95
|
+
export interface EvalSuite {
|
|
96
|
+
skill: string;
|
|
97
|
+
version: string;
|
|
98
|
+
description: string;
|
|
99
|
+
models_to_test: string[];
|
|
100
|
+
mcp_integration?: {
|
|
101
|
+
enabled: boolean;
|
|
102
|
+
namespace?: string;
|
|
103
|
+
query_patterns?: boolean;
|
|
104
|
+
track_outcomes?: boolean;
|
|
105
|
+
store_patterns?: boolean;
|
|
106
|
+
share_learning?: boolean;
|
|
107
|
+
update_quality_gate?: boolean;
|
|
108
|
+
target_agents?: string[];
|
|
109
|
+
};
|
|
110
|
+
learning?: {
|
|
111
|
+
store_success_patterns?: boolean;
|
|
112
|
+
store_failure_patterns?: boolean;
|
|
113
|
+
pattern_ttl_days?: number;
|
|
114
|
+
min_confidence_to_store?: number;
|
|
115
|
+
cross_model_comparison?: boolean;
|
|
116
|
+
};
|
|
117
|
+
setup?: {
|
|
118
|
+
required_tools?: string[];
|
|
119
|
+
environment_variables?: Record<string, string>;
|
|
120
|
+
fixtures?: Array<{
|
|
121
|
+
name: string;
|
|
122
|
+
content: string;
|
|
123
|
+
}>;
|
|
124
|
+
};
|
|
125
|
+
test_cases: EvalTestCase[];
|
|
126
|
+
success_criteria: {
|
|
127
|
+
pass_rate: number;
|
|
128
|
+
critical_pass_rate: number;
|
|
129
|
+
avg_reasoning_quality?: number;
|
|
130
|
+
max_execution_time_ms?: number;
|
|
131
|
+
cross_model_variance?: number;
|
|
132
|
+
};
|
|
133
|
+
metadata?: Record<string, unknown>;
|
|
134
|
+
}
|
|
135
|
+
/**
|
|
136
|
+
* Task unit sent to a worker
|
|
137
|
+
*/
|
|
138
|
+
export interface TestCaseTask {
|
|
139
|
+
/** Name of the skill being validated */
|
|
140
|
+
skillName: string;
|
|
141
|
+
/** Unique test case identifier */
|
|
142
|
+
testCaseId: string;
|
|
143
|
+
/** Full test case definition */
|
|
144
|
+
testCase: EvalTestCase;
|
|
145
|
+
/** Model to use for this test */
|
|
146
|
+
model: string;
|
|
147
|
+
/** Worker batch ID */
|
|
148
|
+
batchId: number;
|
|
149
|
+
/** Index within the batch */
|
|
150
|
+
indexInBatch: number;
|
|
151
|
+
}
|
|
152
|
+
/**
|
|
153
|
+
* Result of parallel evaluation for a skill
|
|
154
|
+
*/
|
|
155
|
+
export interface ParallelEvalResult {
|
|
156
|
+
/** Name of the skill evaluated */
|
|
157
|
+
skill: string;
|
|
158
|
+
/** Model used for evaluation */
|
|
159
|
+
model: string;
|
|
160
|
+
/** Total number of test cases */
|
|
161
|
+
totalTests: number;
|
|
162
|
+
/** Number of tests that passed */
|
|
163
|
+
passedTests: number;
|
|
164
|
+
/** Number of tests that failed */
|
|
165
|
+
failedTests: number;
|
|
166
|
+
/** Number of tests that were skipped */
|
|
167
|
+
skippedTests: number;
|
|
168
|
+
/** Pass rate as a decimal (0-1) */
|
|
169
|
+
passRate: number;
|
|
170
|
+
/** Individual test case results */
|
|
171
|
+
testResults: TestCaseResult[];
|
|
172
|
+
/** Total duration in milliseconds */
|
|
173
|
+
totalDurationMs: number;
|
|
174
|
+
/** Speedup factor vs sequential (e.g., 3.5x faster) */
|
|
175
|
+
parallelSpeedup: number;
|
|
176
|
+
/** Average reasoning quality score */
|
|
177
|
+
avgReasoningQuality: number;
|
|
178
|
+
/** Whether the eval suite passed overall */
|
|
179
|
+
passed: boolean;
|
|
180
|
+
/** Workers used in this run */
|
|
181
|
+
workersUsed: number;
|
|
182
|
+
/** Timestamp of evaluation */
|
|
183
|
+
timestamp: Date;
|
|
184
|
+
}
|
|
185
|
+
/**
|
|
186
|
+
* Worker communication message types
|
|
187
|
+
*/
|
|
188
|
+
export interface WorkerMessage {
|
|
189
|
+
type: 'task' | 'result' | 'error' | 'heartbeat' | 'progress';
|
|
190
|
+
workerId: number;
|
|
191
|
+
payload: unknown;
|
|
192
|
+
}
|
|
193
|
+
/**
|
|
194
|
+
* Progress report from a worker
|
|
195
|
+
*/
|
|
196
|
+
export interface WorkerProgress {
|
|
197
|
+
workerId: number;
|
|
198
|
+
tasksCompleted: number;
|
|
199
|
+
tasksTotal: number;
|
|
200
|
+
currentTask?: string;
|
|
201
|
+
elapsedMs: number;
|
|
202
|
+
}
|
|
203
|
+
/**
|
|
204
|
+
* Aggregated progress across all workers
|
|
205
|
+
*/
|
|
206
|
+
export interface EvalProgress {
|
|
207
|
+
skill: string;
|
|
208
|
+
model: string;
|
|
209
|
+
totalTasks: number;
|
|
210
|
+
completedTasks: number;
|
|
211
|
+
failedTasks: number;
|
|
212
|
+
activeWorkers: number;
|
|
213
|
+
elapsedMs: number;
|
|
214
|
+
estimatedRemainingMs: number;
|
|
215
|
+
workerProgress: WorkerProgress[];
|
|
216
|
+
}
|
|
217
|
+
/**
|
|
218
|
+
* LLM executor interface for test case execution
|
|
219
|
+
*/
|
|
220
|
+
export interface LLMExecutor {
|
|
221
|
+
execute(prompt: string, model: string, options?: {
|
|
222
|
+
timeout?: number;
|
|
223
|
+
}): Promise<{
|
|
224
|
+
output: string;
|
|
225
|
+
tokensUsed: number;
|
|
226
|
+
durationMs: number;
|
|
227
|
+
}>;
|
|
228
|
+
}
|
|
229
|
+
/**
|
|
230
|
+
* Mock LLM executor for testing
|
|
231
|
+
*/
|
|
232
|
+
export declare class MockLLMExecutor implements LLMExecutor {
|
|
233
|
+
execute(prompt: string, model: string, options?: {
|
|
234
|
+
timeout?: number;
|
|
235
|
+
}): Promise<{
|
|
236
|
+
output: string;
|
|
237
|
+
tokensUsed: number;
|
|
238
|
+
durationMs: number;
|
|
239
|
+
}>;
|
|
240
|
+
private generateMockResponse;
|
|
241
|
+
}
|
|
242
|
+
/**
|
|
243
|
+
* Parallel evaluation runner using worker pool pattern
|
|
244
|
+
* Distributes eval test cases across agents for faster execution
|
|
245
|
+
*/
|
|
246
|
+
export declare class ParallelEvalRunner {
|
|
247
|
+
private readonly config;
|
|
248
|
+
private readonly skillValidationLearner;
|
|
249
|
+
private readonly executor;
|
|
250
|
+
private readonly workers;
|
|
251
|
+
private progressCallback?;
|
|
252
|
+
constructor(config: ParallelEvalConfig | undefined, skillValidationLearner: SkillValidationLearner, executor?: LLMExecutor);
|
|
253
|
+
/**
|
|
254
|
+
* Set progress callback for reporting
|
|
255
|
+
*/
|
|
256
|
+
onProgress(callback: (progress: EvalProgress) => void): void;
|
|
257
|
+
/**
|
|
258
|
+
* Run eval suite for a skill in parallel
|
|
259
|
+
*/
|
|
260
|
+
runEvalParallel(skill: string, model: string): Promise<ParallelEvalResult>;
|
|
261
|
+
/**
|
|
262
|
+
* Run multiple skill evals in parallel
|
|
263
|
+
*/
|
|
264
|
+
runMultipleEvalsParallel(skills: string[], models: string[]): Promise<Map<string, ParallelEvalResult[]>>;
|
|
265
|
+
/**
|
|
266
|
+
* Load eval suite from skill's evals/ directory
|
|
267
|
+
*/
|
|
268
|
+
loadEvalSuite(skill: string): EvalSuite | null;
|
|
269
|
+
/**
|
|
270
|
+
* Create test case tasks from suite
|
|
271
|
+
*/
|
|
272
|
+
private createTasks;
|
|
273
|
+
/**
|
|
274
|
+
* Partition test cases into batches for workers
|
|
275
|
+
*/
|
|
276
|
+
private partitionTestCases;
|
|
277
|
+
/**
|
|
278
|
+
* Determine trust tier based on suite configuration
|
|
279
|
+
*/
|
|
280
|
+
private determineTrustTier;
|
|
281
|
+
/**
|
|
282
|
+
* Start progress reporting interval
|
|
283
|
+
*/
|
|
284
|
+
private startProgressReporting;
|
|
285
|
+
/**
|
|
286
|
+
* Record validation outcome to learner
|
|
287
|
+
*/
|
|
288
|
+
private recordOutcome;
|
|
289
|
+
/**
|
|
290
|
+
* Get worker pool status
|
|
291
|
+
*/
|
|
292
|
+
getWorkerStatus(): Array<{
|
|
293
|
+
id: number;
|
|
294
|
+
status: string;
|
|
295
|
+
tasksCompleted: number;
|
|
296
|
+
tasksFailed: number;
|
|
297
|
+
}>;
|
|
298
|
+
/**
|
|
299
|
+
* Reset worker statistics
|
|
300
|
+
*/
|
|
301
|
+
resetWorkers(): void;
|
|
302
|
+
}
|
|
303
|
+
/**
|
|
304
|
+
* Create a ParallelEvalRunner instance
|
|
305
|
+
*/
|
|
306
|
+
export declare function createParallelEvalRunner(skillValidationLearner: SkillValidationLearner, config?: Partial<ParallelEvalConfig>, executor?: LLMExecutor): ParallelEvalRunner;
|
|
307
|
+
//# sourceMappingURL=parallel-eval-runner.d.ts.map
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
{"version":3,"file":"parallel-eval-runner.d.ts","sourceRoot":"","sources":["../../src/validation/parallel-eval-runner.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AAKH,OAAO,EACL,sBAAsB,EACtB,cAAc,EAIf,MAAM,yCAAyC,CAAC;AAMjD;;GAEG;AACH,MAAM,WAAW,kBAAkB;IACjC,wDAAwD;IACxD,UAAU,EAAE,MAAM,CAAC;IAEnB,4CAA4C;IAC5C,SAAS,EAAE,MAAM,CAAC;IAElB,yCAAyC;IACzC,gBAAgB,EAAE,OAAO,CAAC;IAE1B,4CAA4C;IAC5C,OAAO,EAAE,MAAM,CAAC;IAEhB,6CAA6C;IAC7C,SAAS,EAAE,MAAM,CAAC;IAElB,kDAAkD;IAClD,kBAAkB,EAAE,MAAM,CAAC;CAC5B;AAED;;GAEG;AACH,eAAO,MAAM,4BAA4B,EAAE,kBAO1C,CAAC;AAEF;;GAEG;AACH,MAAM,WAAW,iBAAiB;IAChC,IAAI,EAAE,MAAM,CAAC;IACb,OAAO,EAAE;QACP,QAAQ,CAAC,EAAE,MAAM,CAAC;QAClB,SAAS,CAAC,EAAE,MAAM,CAAC;QACnB,WAAW,CAAC,EAAE,MAAM,CAAC;QACrB,WAAW,CAAC,EAAE,MAAM,CAAC;QACrB,OAAO,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;KACnC,CAAC;CACH;AAED;;GAEG;AACH,MAAM,WAAW,0BAA0B;IACzC,YAAY,CAAC,EAAE,MAAM,EAAE,CAAC;IACxB,gBAAgB,CAAC,EAAE,MAAM,EAAE,CAAC;IAC5B,gBAAgB,CAAC,EAAE,MAAM,EAAE,CAAC;IAC5B,aAAa,CAAC,EAAE;QACd,GAAG,CAAC,EAAE,MAAM,CAAC;QACb,GAAG,CAAC,EAAE,MAAM,CAAC;KACd,CAAC;IACF,uBAAuB,CAAC,EAAE,MAAM,CAAC;CAClC;AAED;;GAEG;AACH,MAAM,WAAW,sBAAsB;IACrC,YAAY,CAAC,EAAE,OAAO,CAAC;IACvB,uBAAuB,CAAC,EAAE,MAAM,CAAC;IACjC,qBAAqB,CAAC,EAAE,MAAM,CAAC;IAC/B,cAAc,CAAC,EAAE;QACf,YAAY,CAAC,EAAE,MAAM,CAAC;QACtB,QAAQ,CAAC,EAAE,MAAM,CAAC;QAClB,aAAa,CAAC,EAAE,MAAM,CAAC;KACxB,CAAC;CACH;AAED;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,EAAE,EAAE,MAAM,CAAC;IACX,WAAW,EAAE,MAAM,CAAC;IACpB,QAAQ,EAAE,MAAM,CAAC;IACjB,QAAQ,EAAE,UAAU,GAAG,MAAM,GAAG,QAAQ,GAAG,KAAK,CAAC;IACjD,KAAK,EAAE,iBAAiB,CAAC;IACzB,eAAe,EAAE,0BAA0B,CAAC;IAC5C,UAAU,CAAC,EAAE,sBAAsB,CAAC;CACrC;AAED;;GAEG;AACH,MAAM,WAAW,SAAS;IACxB,KAAK,EAAE,MAAM,CAAC;IACd,OAAO,EAAE,MAAM,CAAC;IAChB,WAAW,EAAE,MAAM,CAAC;IACpB,cAAc,EAAE,MAAM,EAAE,CAAC;IACzB,eAAe,CAAC,EAAE;QAChB,OAAO,EAAE,OAAO,CAAC;QACjB,SAAS,CAAC,EAAE,MAAM,CAAC;QACnB,cAAc,CAAC,EAAE,OAAO,CAAC;QACzB,cAAc,CAAC,EAAE,OAAO,CAAC;QACzB,cAAc,CAAC,EAAE,OAAO,CAAC;QACzB,cAAc,CAAC,EAAE,OAAO,CAAC;QACzB,mBAAmB,CAAC,EAAE,OAAO,CAAC;QAC9B,aAAa,CAAC,EAAE,MAAM,EAAE,CAAC;KAC1B,CAAC;IACF,QAAQ,CAAC,EAAE;QACT,sBAAsB,CAAC,EAAE,OAAO,CAAC;QACjC,sBAAsB,CAAC,EAAE,OAAO,CAAC;QACjC,gBAAgB,CAAC,EAAE,MAAM,CAAC;QAC1B,uBAAuB,CAAC,EAAE,MAAM,CAAC;QACjC,sBAAsB,CAAC,EAAE,OAAO,CAAC;KAClC,CAAC;IACF,KAAK,CAAC,EAAE;QACN,cAAc,CAAC,EAAE,MAAM,EAAE,CAAC;QAC1B,qBAAqB,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;QAC/C,QAAQ,CAAC,EAAE,KAAK,CAAC;YACf,IAAI,EAAE,MAAM,CAAC;YACb,OAAO,EAAE,MAAM,CAAC;SACjB,CAAC,CAAC;KACJ,CAAC;IACF,UAAU,EAAE,YAAY,EAAE,CAAC;IAC3B,gBAAgB,EAAE;QAChB,SAAS,EAAE,MAAM,CAAC;QAClB,kBAAkB,EAAE,MAAM,CAAC;QAC3B,qBAAqB,CAAC,EAAE,MAAM,CAAC;QAC/B,qBAAqB,CAAC,EAAE,MAAM,CAAC;QAC/B,oBAAoB,CAAC,EAAE,MAAM,CAAC;KAC/B,CAAC;IACF,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;CACpC;AAED;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,wCAAwC;IACxC,SAAS,EAAE,MAAM,CAAC;IAElB,kCAAkC;IAClC,UAAU,EAAE,MAAM,CAAC;IAEnB,gCAAgC;IAChC,QAAQ,EAAE,YAAY,CAAC;IAEvB,iCAAiC;IACjC,KAAK,EAAE,MAAM,CAAC;IAEd,sBAAsB;IACtB,OAAO,EAAE,MAAM,CAAC;IAEhB,6BAA6B;IAC7B,YAAY,EAAE,MAAM,CAAC;CACtB;AAED;;GAEG;AACH,MAAM,WAAW,kBAAkB;IACjC,kCAAkC;IAClC,KAAK,EAAE,MAAM,CAAC;IAEd,gCAAgC;IAChC,KAAK,EAAE,MAAM,CAAC;IAEd,iCAAiC;IACjC,UAAU,EAAE,MAAM,CAAC;IAEnB,kCAAkC;IAClC,WAAW,EAAE,MAAM,CAAC;IAEpB,kCAAkC;IAClC,WAAW,EAAE,MAAM,CAAC;IAEpB,wCAAwC;IACxC,YAAY,EAAE,MAAM,CAAC;IAErB,mCAAmC;IACnC,QAAQ,EAAE,MAAM,CAAC;IAEjB,mCAAmC;IACnC,WAAW,EAAE,cAAc,EAAE,CAAC;IAE9B,qCAAqC;IACrC,eAAe,EAAE,MAAM,CAAC;IAExB,uDAAuD;IACvD,eAAe,EAAE,MAAM,CAAC;IAExB,sCAAsC;IACtC,mBAAmB,EAAE,MAAM,CAAC;IAE5B,4CAA4C;IAC5C,MAAM,EAAE,OAAO,CAAC;IAEhB,+BAA+B;IAC/B,WAAW,EAAE,MAAM,CAAC;IAEpB,8BAA8B;IAC9B,SAAS,EAAE,IAAI,CAAC;CACjB;AAED;;GAEG;AACH,MAAM,WAAW,aAAa;IAC5B,IAAI,EAAE,MAAM,GAAG,QAAQ,GAAG,OAAO,GAAG,WAAW,GAAG,UAAU,CAAC;IAC7D,QAAQ,EAAE,MAAM,CAAC;IACjB,OAAO,EAAE,OAAO,CAAC;CAClB;AAED;;GAEG;AACH,MAAM,WAAW,cAAc;IAC7B,QAAQ,EAAE,MAAM,CAAC;IACjB,cAAc,EAAE,MAAM,CAAC;IACvB,UAAU,EAAE,MAAM,CAAC;IACnB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,SAAS,EAAE,MAAM,CAAC;CACnB;AAED;;GAEG;AACH,MAAM,WAAW,YAAY;IAC3B,KAAK,EAAE,MAAM,CAAC;IACd,KAAK,EAAE,MAAM,CAAC;IACd,UAAU,EAAE,MAAM,CAAC;IACnB,cAAc,EAAE,MAAM,CAAC;IACvB,WAAW,EAAE,MAAM,CAAC;IACpB,aAAa,EAAE,MAAM,CAAC;IACtB,SAAS,EAAE,MAAM,CAAC;IAClB,oBAAoB,EAAE,MAAM,CAAC;IAC7B,cAAc,EAAE,cAAc,EAAE,CAAC;CAClC;AAED;;GAEG;AACH,MAAM,WAAW,WAAW;IAC1B,OAAO,CACL,MAAM,EAAE,MAAM,EACd,KAAK,EAAE,MAAM,EACb,OAAO,CAAC,EAAE;QAAE,OAAO,CAAC,EAAE,MAAM,CAAA;KAAE,GAC7B,OAAO,CAAC;QACT,MAAM,EAAE,MAAM,CAAC;QACf,UAAU,EAAE,MAAM,CAAC;QACnB,UAAU,EAAE,MAAM,CAAC;KACpB,CAAC,CAAC;CACJ;AAED;;GAEG;AACH,qBAAa,eAAgB,YAAW,WAAW;IAC3C,OAAO,CACX,MAAM,EAAE,MAAM,EACd,KAAK,EAAE,MAAM,EACb,OAAO,CAAC,EAAE;QAAE,OAAO,CAAC,EAAE,MAAM,CAAA;KAAE,GAC7B,OAAO,CAAC;QAAE,MAAM,EAAE,MAAM,CAAC;QAAC,UAAU,EAAE,MAAM,CAAC;QAAC,UAAU,EAAE,MAAM,CAAA;KAAE,CAAC;IAetE,OAAO,CAAC,oBAAoB;CA4B7B;AA6QD;;;GAGG;AACH,qBAAa,kBAAkB;IAK3B,OAAO,CAAC,QAAQ,CAAC,MAAM;IACvB,OAAO,CAAC,QAAQ,CAAC,sBAAsB;IACvC,OAAO,CAAC,QAAQ,CAAC,QAAQ;IAN3B,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAoB;IAC5C,OAAO,CAAC,gBAAgB,CAAC,CAAmC;gBAGzC,MAAM,EAAE,kBAAkB,YAA+B,EACzD,sBAAsB,EAAE,sBAAsB,EAC9C,QAAQ,GAAE,WAAmC;IAQhE;;OAEG;IACH,UAAU,CAAC,QAAQ,EAAE,CAAC,QAAQ,EAAE,YAAY,KAAK,IAAI,GAAG,IAAI;IAI5D;;OAEG;IACG,eAAe,CACnB,KAAK,EAAE,MAAM,EACb,KAAK,EAAE,MAAM,GACZ,OAAO,CAAC,kBAAkB,CAAC;IA+G9B;;OAEG;IACG,wBAAwB,CAC5B,MAAM,EAAE,MAAM,EAAE,EAChB,MAAM,EAAE,MAAM,EAAE,GACf,OAAO,CAAC,GAAG,CAAC,MAAM,EAAE,kBAAkB,EAAE,CAAC,CAAC;IA4B7C;;OAEG;IACH,aAAa,CAAC,KAAK,EAAE,MAAM,GAAG,SAAS,GAAG,IAAI;IAwB9C;;OAEG;IACH,OAAO,CAAC,WAAW;IAWnB;;OAEG;IACH,OAAO,CAAC,kBAAkB;IAa1B;;OAEG;IACH,OAAO,CAAC,kBAAkB;IAc1B;;OAEG;IACH,OAAO,CAAC,sBAAsB;IA4C9B;;OAEG;YACW,aAAa;IAM3B;;OAEG;IACH,eAAe,IAAI,KAAK,CAAC;QACvB,EAAE,EAAE,MAAM,CAAC;QACX,MAAM,EAAE,MAAM,CAAC;QACf,cAAc,EAAE,MAAM,CAAC;QACvB,WAAW,EAAE,MAAM,CAAC;KACrB,CAAC;IASF;;OAEG;IACH,YAAY,IAAI,IAAI;CAOrB;AAMD;;GAEG;AACH,wBAAgB,wBAAwB,CACtC,sBAAsB,EAAE,sBAAsB,EAC9C,MAAM,GAAE,OAAO,CAAC,kBAAkB,CAAM,EACxC,QAAQ,CAAC,EAAE,WAAW,GACrB,kBAAkB,CAOpB"}
|