Files
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

104 lines
3.6 KiB
Markdown

# Database Init Implementation - Extraction Report
## Summary
Successfully extracted all database initialization code from the old monolithic `src/cli/commands/init.ts` into the new modular `src/cli/init/database-init.ts`.
## Implemented Functions
### 1. `initializeDatabases(config: FleetConfig)` - Main Entry Point
- Orchestrates all database initialization in correct order
- Calls 4 sub-initialization functions sequentially
### 2. `initializeMemoryDatabase()` - Memory Manager
**Extracted from**: `init.ts` line 2048-2068
- Creates SwarmMemoryManager database at `.agentic-qe/memory.db`
- Initializes 12 tables for persistent memory storage
- Implements 5 access control levels (private, team, swarm, public, system)
- Dynamic import of SwarmMemoryManager
- Verifies initialization with stats check
- Proper cleanup with `close()`
### 3. `initializeAgentDB(config: FleetConfig)` - Learning System
**Extracted from**: `init.ts` line 2010-2041
- Creates AgentDB database at `.agentic-qe/agentdb.db`
- Replaces deprecated patterns.db with vector-based learning
- Configuration:
- `enableLearning: true`
- `enableReasoning: true`
- `cacheSize: 1000`
- `quantizationType: 'scalar'`
- HNSW vector search enabled (150x faster)
- Reflexion pattern + Q-values for learning
- Used by all 18 QE agents
- CRITICAL: Calls `initialize()` before `getStats()`
### 4. `initializeLearningSystem(config: FleetConfig)` - Learning Config
**Extracted from**: `init.ts` line 2073-2110
- Creates `.agentic-qe/config/learning.json` with full configuration:
- Learning rate: 0.1
- Discount factor: 0.95
- Exploration rate: 0.2 (with decay)
- Target improvement: 20%
- Replay buffer: 10,000 entries
- Batch size: 32
- Creates `.agentic-qe/data/learning/` directory
- Creates learning state JSON with version tracking
### 5. `initializeImprovementLoop(config: FleetConfig)` - A/B Testing
**Extracted from**: `init.ts` line 2226-2267
- Creates `.agentic-qe/config/improvement.json` with:
- 1-hour cycle interval
- A/B testing enabled (sample size: 100)
- Auto-apply disabled (requires user approval)
- 3 optimization strategies (parallel, retry, resource)
- Statistical significance testing (p < 0.05)
- Creates improvement state JSON at `.agentic-qe/data/improvement/state.json`
## Implementation Details
### Imports Added
```typescript
import * as path from 'path';
import * as fs from 'fs-extra';
import chalk from 'chalk';
import { FleetConfig } from '../../types';
```
### Version Tracking
```typescript
const packageJson = require('../../../package.json');
const PACKAGE_VERSION = packageJson.version;
```
### Dynamic Imports (Preserved from Original)
- `import('../../core/memory/AgentDBManager')`
- `import('../../core/memory/SwarmMemoryManager')`
## Verification
✅ **No TODOs remaining** - All placeholders replaced with real implementation
✅ **Build successful** - TypeScript compilation passes
✅ **Exact code extraction** - All logic, error handling, and logging preserved
✅ **Database paths preserved** - Same paths as original implementation
✅ **Configuration values unchanged** - All numeric values, thresholds, and settings match
## Files Modified
- `/workspaces/agentic-qe-cf/src/cli/init/database-init.ts` - 199 lines (was 33 lines)
- Added 4 complete implementation functions
- Added all necessary imports
- Added version tracking
- Removed all TODO comments
## Next Steps
This module is now ready to be integrated into the new modular init command flow in `src/cli/init/index.ts`.
---
**Extraction Date**: 2025-11-22
**Source**: `src/cli/commands/init.ts` (lines 2010-2267)
**Target**: `src/cli/init/database-init.ts`
**Status**: ✅ Complete