 Profa
|
514313d416
|
feat(mcp): implement Phase 3 hierarchical tool loading (Issue #115)
Phase 3 Track H - Tool Categories:
- Add category comments to all 95 tool definitions
- Organize tools with section headers (11 major sections)
- Enhance tools_discover with category filtering (comma-separated)
- Add tools_discover and tools_load_domain to TOOL_NAMES
Phase 3 Track I - Keyword Auto-Loading:
- Expand keywords from 81 to 341 across 7 domains
- Add domain relationships (security→quality, coverage→quality, etc.)
- Implement tool caching with usage tracking
- Add auto-load metrics and history tracking
Verified Metrics:
- Initial load: 95 → 12 core tools (87% reduction)
- Token cost: ~18,652 → ~2,463 tokens (87% savings)
- Keyword coverage: 341 keywords across 9 domains
- Auto-detection: Working for all domains
Files Changed:
- src/mcp/tools.ts - Category comments, section headers
- src/mcp/tool-categories.ts - 341 keywords, domain relationships
- src/mcp/lazy-loader.ts - Usage tracking, caching
- src/mcp/server.ts - Enhanced tools_discover handler
Documentation:
- docs/analysis/phase3-track-h-category-assignment.md
- docs/analysis/phase3-tracki-keyword-enhancements.md
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-12-06 08:42:42 +00:00 |
|
|
Profa
|
56d1502089
|
feat(mcp): implement Phase 1 & 2 tool optimization (Issue #115)
Phase 1 Track A - Legacy Tool Removal:
- Remove 11 legacy tools from agenticQETools array
- Remove corresponding TOOL_NAMES entries
- Remove legacy handler registrations from server.ts
- Legacy tools removed: test_generate, quality_analyze, predict_defects,
optimize_tests, quality_gate_execute, quality_validate_metrics,
quality_risk_assess, quality_decision_make, quality_policy_check,
requirements_validate, requirements_generate_bdd
Phase 2 - Lazy Loading Integration:
- Wire ListToolsRequestSchema to use lazy loader
- Return only 14 core tools on initial load (vs 84 total)
- Domain-specific tools loaded on-demand via tools_load_domain
- Add tools_discover and tools_load_domain meta-tools
- Add tool-categories.ts with domain organization
- Add lazy-loader.ts for dynamic tool loading
- Add server-instructions.ts for MCP instructions
Additional Changes:
- Add analysis documentation for optimization work
- Add IntervalRegistry utility for timer management
- Update jest.setup.ts and MemoryManager for stability
- Add coverage tools consolidation plan
Verified Metrics:
- Tool count: 98 → 84 (-14 legacy tools)
- Initial load: 84 → 14 tools
- Token reduction: ~16,885 → ~2,612 tokens (85% reduction)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-12-05 18:49:18 +00:00 |
|
|
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 |
|
|
Profa
|
b3d2018ee2
|
feat: v1.8.0 - Quality Hardening & Pattern Isolation
Critical bug fixes and code quality improvements from brutal-honest-review.
## Critical Fixes (9/10 completed, 1 deferred)
1. Fixed Agent Pattern Isolation (CRITICAL)
- Added SwarmMemoryManager.queryPatternsByAgent()
- SQL filtering by agent_id in metadata
- Each agent now isolated
2. Fixed Async Method Cascade
- Changed getPatterns() to async
- Fixed 10 callers across 6 files
- Build passes
3. Fixed Misleading Logging
- Added isRealAgentDB() detection
- Honest mock vs real reporting
4. Consolidated Embedding Generation
- Created EmbeddingGenerator utility
- Removed 50+ duplicate lines
5. Added AgentDB Initialization Checks
- Empty DB detection
- HNSW index verification
6. Integration Test Suite
- 26 new test cases
- Error path coverage
7. Repository Cleanup
- Removed 19 temp test files
8. New QE Skill: sherlock-review
- Evidence-based investigative review
- 38 QE skills total
9. Deferred: Wire Up Real Test Execution
- Deferred to v1.9.0 (documented)
## Statistics
- Fixes: 9/10 (90%, 1 deferred)
- Files Modified: 16
- Files Created: 3
- Files Deleted: 19
- Integration Tests: 26
- Build: PASSING
## Breaking Changes
- getPatterns() now async - add await
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
|
2025-11-17 12:32:03 +00:00 |
|
|
Profa
|
25cb212c06
|
possible improvements
|
2025-11-15 16:42:35 +00:00 |
|