skills/proffesor-for-testing__agentic-qe

mirror of https://github.com/proffesor-for-testing/agentic-qe.git synced 2026-09-19 08:45:47 +08:00

Files

T

Profa c0d469a3bb fix: clean up stale v3/ references and protect memory namespaces post-flatten

Brutal honesty review of the flatten-to-root migration found 12 categories
of issues. This commit fixes all of them:

- Fix @agentic-qe/v3 package refs in init installers and quality-criteria-service
- Fix 7 broken import() paths in rvf-baseline-benchmark.ts (v3/src → src)
- Fix prepare-assets.sh and demo-warmup.sh path references
- Delete dead scripts/migrate-v2-to-v3-memory.js
- Remove .claude-flow daemon state dirs (284KB) from agents/skills
- Add .claude-flow exclusion to .npmignore
- Fix JSDoc @agentic-qe/v3/ → agentic-qe/ in 27 source files
- Fix @module v3/ tags in 9 dream engine files
- Fix stale v3/ path refs in docs and architecture ADRs
- Revert memory namespace changes (aqe/v3/domains/* are DB identifiers,
  not filesystem paths — changing them orphans 150K+ existing records)
- Update CLAUDE.md with agent classification rules (QE vs non-QE agents)
- Fix domain-team-manager test (scaling is not capped by defaultTeamSize)
- Fix adr-040 timing test threshold (20ms → 50ms for CI tolerance)
- Rename test:v3 → test:all in package.json
- Update README.md project structure tree
- Fix infra-healing test and demo script cd v3 references

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-01 12:27:44 +00:00

3.3 KiB

Raw Permalink Blame History

Getting Started with Agentic QE v3

This guide walks you through setting up and using Agentic QE v3's DDD-based quality engineering system.

Prerequisites

Node.js 18+
TypeScript 5.0+
Claude Code CLI
(Optional) PostgreSQL for RuVector code intelligence

Installation

# Install Agentic QE
npm install -g agentic-qe

# Verify installation
aqe --version
# v3.0.0

# Initialize in your project
aqe init

Quick Start

1. Generate Tests

# Generate unit tests for a file
aqe test generate --file src/services/UserService.ts --framework jest

# Generate with coverage target
aqe test generate --scope src/api/ --coverage 90

2. Analyze Coverage

# O(log n) coverage gap detection
aqe coverage analyze --source src/ --tests tests/

# Risk-weighted analysis
aqe coverage gaps --risk-weighted --threshold 80

3. Run Quality Gate

# Evaluate deployment readiness
aqe quality assess --gates all

# Check specific gates
aqe quality check --coverage 80 --no-critical-vulns

4. Execute Tests

# Parallel execution with retry
aqe test run --parallel --workers 4 --retry 3

# Run affected tests only
aqe test run --affected --since HEAD~1

Using Agents

Spawn Individual Agents

// Via Claude Code Task tool
Task("Generate tests", `
  Analyze src/services/PaymentService.ts and generate comprehensive tests.
  Include happy paths, edge cases, and error handling.
`, "qe-test-generator")

Multi-Agent Workflows

// Parallel agent execution
Task("Coverage analysis", "Analyze coverage gaps", "qe-coverage-specialist")
Task("Quality check", "Evaluate quality gates", "qe-quality-gate")
Task("Security scan", "Run security audit", "qe-security-scanner")

Domain Commands

Each of the 12 domains has dedicated CLI commands:

Domain	Command Prefix	Example
Test Generation	`aqe test`	`aqe test generate`
Test Execution	`aqe test run`	`aqe test run --parallel`
Coverage	`aqe coverage`	`aqe coverage analyze`
Quality	`aqe quality`	`aqe quality assess`
Defects	`aqe defect`	`aqe defect predict`
Code Intelligence	`aqe kg`	`aqe kg index`
Requirements	`aqe requirements`	`aqe requirements trace`
Security	`aqe security`	`aqe security scan`
Contracts	`aqe contract`	`aqe contract verify`
Visual	`aqe visual`	`aqe visual test`
Chaos	`aqe chaos`	`aqe chaos run`
Learning	`aqe learn`	`aqe learn status`

Configuration

Create .agentic-qe/config.yaml:

v3:
  version: "3.0.0"

  # Enable all 12 domains
  domains:
    - test-generation
    - test-execution
    - coverage-analysis
    - quality-assessment
    - defect-intelligence
    - code-intelligence
    - requirements-validation
    - security-compliance
    - contract-testing
    - visual-accessibility
    - chaos-resilience
    - learning-optimization

  # Agent limits
  maxConcurrentAgents: 15

  # Memory backend
  memoryBackend: hybrid  # SQLite + AgentDB
  hnswEnabled: true

  # Learning
  neuralLearning: true

3.3 KiB Raw Permalink Blame History