claude-flow 2.7.0 → 2.7.1

package/CHANGELOG.md

@@ -5,6 +5,48 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [2.7.1] - 2025-10-22
+
+> **🐛 Critical Bug Fix**: MCP Pattern Persistence - Fixed neural pattern storage, search, and statistics
+
+### 🐛 Bug Fixes
+
+#### **MCP Pattern Persistence (Critical)**
+- **Fixed `neural_train` persistence**: Patterns now properly persist to memory instead of being discarded
+  - Added storage to `patterns` namespace with 30-day TTL
+  - Added automatic statistics tracking to `pattern-stats` namespace
+  - Tracks: total trainings, avg/max/min accuracy, model history (last 50)
+
+- **Implemented `neural_patterns` handler**: Complete implementation of missing handler
+  - **`analyze` action**: Retrieve specific patterns by modelId or list all patterns
+  - **`learn` action**: Store learning experiences with operation and outcome tracking
+  - **`predict` action**: Generate predictions based on historical training data
+  - **`stats` action**: Retrieve comprehensive statistics per pattern type or all types
+
+- **Added error handling**: Robust error management with detailed logging for debugging
+
+### 📁 Files Changed
+- `src/mcp/mcp-server.js` - Enhanced neural_train handler (lines 1288-1391) and implemented neural_patterns handler (lines 1393-1614)
+
+### 🧪 Testing
+- Added integration test suite: `tests/integration/mcp-pattern-persistence.test.js` (16 test cases)
+- Added manual test script: `tests/manual/test-pattern-persistence.js` (8 end-to-end scenarios)
+- Added comprehensive documentation: `docs/PATTERN_PERSISTENCE_FIX.md`
+
+### 📊 Impact
+- **Before**: ⚠️ Pattern Store/Search/Stats all partially functional (data not persisting)
+- **After**: ✅ All operations fully functional with complete persistence and retrieval
+
+### ✅ Backward Compatibility
+- Fully backward compatible - no breaking changes
+- Existing `neural_train` calls return same response format
+- New persistence happens transparently in background
+
+### 📈 Performance
+- Storage: ~1KB per pattern with configurable 30-day TTL
+- Operations: 2 memory store operations per training (pattern + stats)
+- Stats optimization: Only last 50 models tracked per pattern type
+
 ## [2.7.0] - 2025-10-20
 
 > **📚 AgentDB Skills Expansion**: Comprehensive AgentDB documentation with 6 specialized skills covering all CLI commands and advanced features

package/bin/claude-flow

@@ -1,7 +1,7 @@
 #!/bin/sh
 # Claude-Flow Smart Dispatcher - Detects and uses the best available runtime
 
-VERSION="2.7.0"
+VERSION="2.7.1"
 
 # Determine the correct path based on how the script is invoked
 if [ -L "$0" ]; then

package/dist/src/cli/simple-cli.js

@@ -2973,4 +2973,108 @@ if (import.meta.url === `file://${process.argv[1]}`) {
     await main();
 }
 
+//# sourceMappingURL=simple-cli.js.map sparc run spec-pseudocode "User profile management feature"
+
+# 2. Design architecture
+npx claude-flow sparc run architect "Profile service architecture with data validation"
+
+# 3. Implement with TDD
+npx claude-flow sparc tdd "user profile CRUD operations"
+
+# 4. Security review
+npx claude-flow sparc run security-review "profile data access and validation"
+
+# 5. Integration testing
+npx claude-flow sparc run integration "profile service with authentication system"
+
+# 6. Documentation
+npx claude-flow sparc run docs-writer "profile service API documentation"
+\`\`\`
+
+### Bug Fix Workflow
+\`\`\`bash
+# 1. Debug and analyze
+npx claude-flow sparc run debug "authentication token expiration issue"
+
+# 2. Write regression tests
+npx claude-flow sparc run tdd "token refresh mechanism tests"
+
+# 3. Implement fix
+npx claude-flow sparc run code "fix token refresh in authentication service"
+
+# 4. Security review
+npx claude-flow sparc run security-review "token handling security implications"
+\`\`\`
+
+## Configuration Files
+
+### SPARC Configuration
+- **\`.roomodes\`**: SPARC mode definitions and configurations
+- **\`.roo/\`**: Templates, workflows, and mode-specific rules
+
+### Claude-Flow Configuration
+- **\`memory/\`**: Persistent memory and session data
+- **\`coordination/\`**: Multi-agent coordination settings
+
+## Git Workflow Integration
+
+### Commit Strategy with SPARC
+- **Specification commits**: After completing requirements analysis
+- **Architecture commits**: After design phase completion
+- **TDD commits**: After each Red-Green-Refactor cycle
+- **Integration commits**: After successful component integration
+- **Documentation commits**: After completing documentation updates
+
+### Branch Strategy
+- **\`feature/sparc-<feature-name>\`**: Feature development with SPARC methodology
+- **\`hotfix/sparc-<issue>\`**: Bug fixes using SPARC debugging workflow
+- **\`refactor/sparc-<component>\`**: Refactoring using optimization mode
+
+## Troubleshooting
+
+### Common SPARC Issues
+- **Mode not found**: Check \`.roomodes\` file exists and is valid JSON
+- **Memory persistence**: Ensure \`memory/\` directory has write permissions
+- **Tool access**: Verify required tools are available for the selected mode
+- **Namespace conflicts**: Use unique memory namespaces for different features
+
+### Debug Commands
+\`\`\`bash
+# Check SPARC configuration
+npx claude-flow sparc modes
+
+# Verify memory system
+npx claude-flow memory stats
+
+# Check system status
+npx claude-flow status
+
+# View detailed mode information
+npx claude-flow sparc info <mode-name>
+\`\`\`
+
+## Project Architecture
+
+This SPARC-enabled project follows a systematic development approach:
+- **Clear separation of concerns** through modular design
+- **Test-driven development** ensuring reliability and maintainability
+- **Iterative refinement** for continuous improvement
+- **Comprehensive documentation** for team collaboration
+- **AI-assisted development** through specialized SPARC modes
+
+## Important Notes
+
+- Always run tests before committing (\`npm run test\`)
+- Use SPARC memory system to maintain context across sessions
+- Follow the Red-Green-Refactor cycle during TDD phases
+- Document architectural decisions in memory for future reference
+- Regular security reviews for any authentication or data handling code
+
+For more information about SPARC methodology, see: https://github.com/ruvnet/claude-code-flow/docs/sparc.md
+`;
+}
+if (isMainModule(import.meta.url)) {
+    await main();
+}
+
 //# sourceMappingURL=simple-cli.js.map