skills/proffesor-for-testing__agentic-qe
1
0
Fork 0
mirror of https://github.com/proffesor-for-testing/agentic-qe.git synced 2026-09-19 08:45:47 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
release/v2.2.0
proffesor-for-testing__agen…/docs/architecture/INDEX.md
T
Dragan Spiridonov 346438f0de Release v2.0.0: Claude 4.5 Optimization, QUIC Transport, 29 Agent Compaction (#100) 
* SwarmMemoryManager Refactoring Plan

* fix: add missing directories to npm package (v1.9.3)

Added templates/, .claude/helpers/, and docs/reference/ to package.json
files array. These were missing from the npm distribution, causing
`aqe init` to fail with "Template file not found" errors.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

* checkpoint improvements

* fix: critical memory/learning system fixes for v1.9.4

## Critical Fixes
- Vector embeddings now stored correctly (was storing NULL)
- SQL parameter style fixed for agentdb's SqlJsDatabase wrapper
- HNSW index schema mismatch resolved with pattern_id column
- Hooks now save to correct database (.agentic-qe/agentdb.db)

## New Features
- Added 5 SwarmMemoryManager methods for learning data retrieval:
  - getBestAction() - Q-learning best action selection
  - getRecentLearningExperiences() - Recent experience retrieval
  - getLearningExperiencesByTaskType() - Task-filtered experiences
  - getHighRewardExperiences() - Successful experience extraction
  - getLearningStats() - Aggregate learning statistics
- Added comprehensive integration test for memory/learning loop
- Added RuVector pattern store integration (experimental)

## Technical Details
- Vector embeddings: 384 dimensions × 4 bytes = 1,536 bytes per pattern
- All 12 integration tests pass
- HNSW index: 150x faster vector search enabled

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

* fix: move ARM64-only ruvector packages to optionalDependencies

Fixes CI failures caused by platform-specific dependencies:
- @ruvector/node-linux-arm64-gnu (ARM64 only)
- ruvector-core-linux-arm64-gnu (ARM64 only)

These packages caused npm ci to fail on x64 CI runners with:
"EBADPLATFORM - wanted linux/arm64, current linux/x64"

Solution: Move ARM64 packages to optionalDependencies and add
x64 variants for cross-platform compatibility.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

* chore: regenerate package-lock.json with x64 ruvector packages

Updates lockfile to include optional x64 platform packages for
CI compatibility:
- @ruvector/node-linux-x64-gnu@0.1.17
- ruvector-core-linux-x64-gnu@0.1.15

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

* fix: replace fake QUIC with proper implementation and clean up skills manifest

QUIC Transport:
- Remove fake HTTP/2-based QUICTransport.ts that pretended to be QUIC
- Add proper QUIC implementation via Rust/WASM (@agentic-flow/quic-wasm)
- Add WebSocket fallback transport for when WASM unavailable
- Add dedicated type declarations for optional WASM module
- Features: 0-RTT connection, stream multiplexing, TLS 1.3 built-in

Skills Manifest:
- Rewrite skills-manifest.json with only QE skills (41 skills)
- Remove Claude Flow platform skills (agentdb-*, flow-nexus-*, github-*, etc.)
- Organize into proper categories: qe-core, testing-methodologies, etc.

Bug Fixes:
- Fix UnifiedMemoryCoordinator.ts TypeScript errors
- Use Logger.getInstance() instead of private constructor
- Use swarmMemory.query() instead of non-existent list() method
- Use correct close() method signatures for backends

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

* feat: add QX Partner agent, compact subagents, fix CLAUDE.md dynamic counts

- Add QX Partner agent for Quality Experience analysis combining QA + UX perspectives
- Compact 9 subagent definitions to ~80 lines each (88% reduction)
- Fix CLAUDE.md template to dynamically count agents (including subagents) and skills
- Move CLAUDE.md creation after parallel phases for accurate counts
- Remove 'Production-Ready' claim from README and CHANGELOG
- Clean up backup files and move docs to proper directory

Initialization now correctly reports:
- 31 QE Agents (20 main + 11 subagents)
- 53 QE Skills
- 8 Slash Commands

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

---------

Co-authored-by: Claude <noreply@anthropic.com>
2025-12-02 11:31:30 +01:00

6.7 KiB
Raw Permalink Blame History

Agentic QE Fleet - Architecture Documentation

Current Version: v1.8.0 Last Updated: November 16, 2025

Documentation Index

This folder contains comprehensive architecture documentation for the Agentic QE Fleet, covering learning systems, database architecture, and performance optimizations.

🆕 v1.8.0 Architecture (Production)

Core System Architecture

Document Purpose Highlights Status
database-architecture.md Database consolidation & design • 2-database architecture (agentdb.db + memory.db)
• 150x faster vector search
• 3,766 records migrated
• Clear separation: learning vs coordination		 ✅ Production
learning-system.md QE agent learning architecture • Reflexion-based learning (self-reflection + critique)
• Q-learning reinforcement
• HNSW semantic search
• Persistent cross-session memory		 ✅ Production
mcp-optimizations.md MCP server performance • 95-99% token reduction (filtering)
• 60-80% latency reduction (batching)
• 90% cost savings (prompt caching)
• $500-1000/month savings		 ✅ Production

Key Metrics (v1.8.0)

Database Performance:
  • Vector search:     87µs (172x faster than v1.7.0)
  • Pattern retrieval: 1.8ms (2.8x faster)
  • Learning update:   7ms (2.9x faster)

Learning Impact:
  • Test coverage:     +17% improvement after 500 tasks
  • Detection speed:   -53% faster after 500 tasks
  • Pattern reuse:     92% of tasks benefit from prior learning

MCP Optimizations:
  • Token reduction:   95-99% across all tools
  • API cost:          99.1% reduction
  • Response time:     69.2% faster

📚 v1.0.5 Architecture (Historical)

Phase 1: Multi-Model Router + Streaming

Document Purpose Audience Status
PHASE1-SUMMARY.md Executive overview and quick reference All stakeholders ✅ Complete
PHASE1-ARCHITECTURE.md Complete technical architecture design Architects, Senior Engineers ✅ Complete
COMPONENT-DIAGRAM.md Visual component breakdown and interactions All Engineers ✅ Complete
INTEGRATION-SPEC.md Detailed integration specifications Implementation Team ✅ Complete
MIGRATION-STRATEGY.md 7-week deployment and migration plan Ops Team, Tech Leads ✅ Complete

🗺️ Additional Architecture Documents

Learning & ReasoningBank

Document Purpose Status
LEARNING-SYSTEM-ARCHITECTURE.md Original learning system design ✅ Complete
REASONING-BANK-V1.1.md ReasoningBank architecture v1.1 ✅ Complete
REASONING-BANK-COORDINATION.md Multi-agent coordination patterns ✅ Complete
AGENTDB-INTEGRATION-ARCHITECTURE.md AgentDB integration design ✅ Complete

Implementation Summaries

Document Purpose Status
learning-system-summary.md Learning system implementation summary ✅ Complete
ARCHITECTURE-SUMMARY.md Overall architecture summary ✅ Complete
IMPLEMENTATION-GUIDE.md Implementation guidelines ✅ Complete

🚀 Quick Start

For v1.8.0 (Current Release)

🏗️ Architects & Tech Leads:

  1. Start with database-architecture.md - understand the 2-database design
  2. Review learning-system.md - see how agents learn and improve
  3. Check mcp-optimizations.md - understand performance gains

👨‍💻 Developers:

  1. Read database-architecture.md - developer guide section
  2. Study learning-system.md - integration examples
  3. Implement using mcp-optimizations.md - optimization patterns

📊 Product Managers:

  1. Review learning-system.md - performance metrics
  2. Check mcp-optimizations.md - cost savings analysis
  3. See database-architecture.md - migration summary

For v1.0.5 (Historical Reference)

For Stakeholders: Start with PHASE1-SUMMARY.md

For Engineers: Review PHASE1-ARCHITECTURE.md and COMPONENT-DIAGRAM.md

For Implementation: Follow INTEGRATION-SPEC.md and MIGRATION-STRATEGY.md

📖 Documentation Structure

docs/architecture/
├── database-architecture.md        # ⭐ v1.8.0 Database design
├── learning-system.md              # ⭐ v1.8.0 Learning architecture
├── mcp-optimizations.md            # ⭐ v1.8.0 Performance optimizations
├── PHASE1-ARCHITECTURE.md          # v1.0.5 Multi-model router
├── PHASE1-SUMMARY.md               # v1.0.5 Executive summary
├── AGENTDB-INTEGRATION-ARCHITECTURE.md  # AgentDB integration
├── LEARNING-SYSTEM-ARCHITECTURE.md      # Original learning design
├── REASONING-BANK-V1.1.md          # ReasoningBank patterns
└── [28 other architecture documents]

🔗 Related Documentation

  • Implementation: docs/implementation/ - Detailed implementation summaries
  • Database: docs/database/ - Database schema and migration guides
  • Testing: docs/testing/ - Test strategies and coverage analysis
  • Planning: docs/planning/ - Roadmaps and improvement plans
  • Analysis: docs/analysis/ - Coverage and optimization analysis

📈 Version History

Version Date Key Changes
v1.8.0 Nov 16, 2025 Database consolidation, learning system, MCP optimizations
v1.7.0 Nov 13, 2025 Sherlock-review skill, brutal-honesty-review improvements
v1.6.1 Oct 2025 ReasoningBank integration, 18 QE agents
v1.0.5 Earlier 2025 Multi-model router, streaming support

Current Status: ✅ v1.8.0 Production Ready Database Migration: ✅ Complete (3,766 records migrated) Learning System: ✅ Active (150x faster vector search) MCP Optimizations: ✅ Deployed (95-99% token reduction)

Reference in New Issue View Git Blame Copy Permalink