mirror of
https://github.com/proffesor-for-testing/agentic-qe.git
synced 2026-09-19 08:45:47 +08:00
Dragan Spiridonov
99511738c1
* fix(v3.4.1): bundle missing dependencies and test timeouts - Fixed issue #219: MCP bundle failing due to missing packages - Changed build scripts from --packages=external to selective externalization - Pure JS deps (fast-json-patch, jose, uuid) now bundled inline - Native modules properly externalized (better-sqlite3, hnswlib-node, etc.) - CommonJS modules with dynamic requires externalized (typescript, fast-glob, yaml, commander, cli-progress, ora) - Bundle size reduced from ~15MB to ~5MB - Added timeouts to handleQualityAssess tests to prevent CI failures - Updated version to 3.4.1 Closes #219 Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * feat(v3.4.2): add skill validation system with trust tiers (ADR-056) Implement 4-layer skill validation system for deterministic outputs: - Tier 3 (Verified): 46 skills with full eval test suites - Tier 2 (Validated): 7 skills with executable validators - Tier 1 (Structured): 5 skills with JSON output schemas - Tier 0 (Advisory): 5 skills with SKILL.md guidance only Key additions: - JSON Schema validation templates for skill outputs - Executable validator scripts for correctness verification - Evaluation test framework with multi-model support - CLI commands: aqe skill report/summary/compare, aqe eval run/status - ReasoningBank integration for validation pattern learning - GitHub Actions workflow for CI skill validation - Trust tier frontmatter in all 63 skill SKILL.md files - Comprehensive documentation and user guides Infrastructure: - .claude/skills/.validation/ - Templates and frameworks - .claude/skills/*/schemas/ - Output schemas per skill - .claude/skills/*/scripts/ - Validator scripts per skill - .claude/skills/*/evals/ - Test cases per skill Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(ci): trust tier-based skill validation - Tier 3 (Verified): Blocks PR on validation failure - Tier 2 (Validated): Warns only, doesn't block - Tier 1 (Structured): Warns only, doesn't block - Tier 0 (Advisory): Skipped entirely Reads trust_tier from SKILL.md frontmatter to determine validation requirements. Only 46 Tier 3 skills block merge. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(validators): remove local keyword from self-test blocks Shell script fix: 'local' can only be used inside functions, not in if/else blocks. Both accessibility-testing and compatibility-testing validators had 'local' declarations in their self-test sections that caused errors when run outside of a function context. - Remove local test_file from accessibility-testing self-test - Remove local test_file, browser_count, tier1_pass from compatibility-testing self-test - Sync fixes to v3/assets/skills/ Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * fix(validators): add --self-test support to n8n skill validators The 5 n8n skill validators were failing CI because they didn't handle the --self-test flag properly. Added self-test handling that: - Checks for required tools (jq) - Verifies schema file exists and is valid JSON - Returns exit 0 on success Fixed validators: - n8n-expression-testing - n8n-integration-testing-patterns - n8n-security-testing - n8n-trigger-testing-strategies - n8n-workflow-testing-fundamentals Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
74 lines
2.1 KiB
JSON
74 lines
2.1 KiB
JSON
{
|
|
"$schema": "https://agentic-qe.dev/schemas/skill-output-template.json",
|
|
"skillName": "sample-skill",
|
|
"version": "1.0.0",
|
|
"timestamp": "2026-02-02T12:00:00Z",
|
|
"status": "success",
|
|
"trustTier": 2,
|
|
"output": {
|
|
"summary": "Sample skill execution completed successfully. This is a demonstration output for validator self-testing.",
|
|
"findings": [
|
|
{
|
|
"id": "FINDING-001",
|
|
"title": "Sample Finding",
|
|
"description": "This is a sample finding to demonstrate the output structure. In a real skill, this would contain actual analysis results.",
|
|
"severity": "medium",
|
|
"category": "demonstration",
|
|
"location": {
|
|
"file": "src/example.ts",
|
|
"line": 42
|
|
},
|
|
"evidence": "Example code snippet showing the issue"
|
|
},
|
|
{
|
|
"id": "FINDING-002",
|
|
"title": "Another Sample Finding",
|
|
"description": "A second sample finding showing multiple findings can exist.",
|
|
"severity": "low",
|
|
"category": "demonstration"
|
|
}
|
|
],
|
|
"recommendations": [
|
|
{
|
|
"id": "REC-001",
|
|
"title": "Implement Best Practice",
|
|
"description": "Consider implementing this best practice to improve code quality.",
|
|
"priority": "medium",
|
|
"effort": "low",
|
|
"relatedFindings": ["FINDING-001"]
|
|
}
|
|
],
|
|
"metrics": {
|
|
"totalIssues": 2,
|
|
"criticalCount": 0,
|
|
"highCount": 0,
|
|
"mediumCount": 1,
|
|
"lowCount": 1,
|
|
"score": 85.5,
|
|
"passRate": 0.95
|
|
},
|
|
"artifacts": [
|
|
{
|
|
"type": "report",
|
|
"path": "reports/sample-report.html",
|
|
"format": "html",
|
|
"description": "Detailed HTML report with findings"
|
|
}
|
|
]
|
|
},
|
|
"metadata": {
|
|
"executionTimeMs": 1250,
|
|
"toolsUsed": ["eslint", "typescript", "custom-analyzer"],
|
|
"agentId": "qe-test-architect",
|
|
"modelUsed": "claude-sonnet-4",
|
|
"inputHash": "sha256:abc123def456",
|
|
"parentTaskId": "task-789"
|
|
},
|
|
"validation": {
|
|
"schemaValid": true,
|
|
"contentValid": true,
|
|
"confidence": 0.95,
|
|
"warnings": []
|
|
}
|
|
}
|