Lazy-load agent registry (frontmatter index, parse on demand), copy agents by path during install, fix Makefile template tab lint issue, add registry performance tests, bump to 1.1.0, document CLI reinstall after pull.
10 KiB
10 KiB
Changelog
All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
Unreleased
[1.1.0] - 2026-06-18
Added
kaizen-agentic feedbackCLI and Gitea issue templates for developer feedback- Gitea CI (
.gitea/workflows/ci.yml) — black + pytest on Python 3.10/3.12 - Pre-commit hooks (
.pre-commit-config.yaml) andmake pre-commit-install docs/FEEDBACK.mdanddocs/TELEMETRY.md(ADR-004 two-layer telemetry model)- Ecosystem integration (WP-0004): Helix correlation, artifact-store publish, activity-core definitions
- Project metrics (WP-0003): ADR-004 storage, metrics CLI, optimizer wiring, tdd-workflow pilot
- sys-medic agent and packaged fleet sync (20 agents in
data/agents/)
Changed
- Lazy agent registry — index by frontmatter name; parse on demand; path-based install copy
- CLI error messages — clearer guidance when agents directory or package missing
- CONTRIBUTING.md — post-pull reinstall instructions (
pip install -e ./ pipx)
Fixed
- Makefile template in project initializer — tab characters no longer break Python linting
- Removed stale
agents_backup_*/scaffolding from development installs
1.0.1 - 2025-10-20
Fixed
- CLI Error Message Suppression: Resolved spurious "Got unexpected extra argument" error messages in Click library that were confusing users during
kaizen-agentic installcommands - YAML Frontmatter Issues: Fixed malformed YAML frontmatter in agent definition files (
agent-wisdom-encouragement.md,agent-tooling-optimization.md,agent-test-maintenance.md) - Global Installation Access: Enhanced global installation capability with improved
make install-globaltarget using pipx for system-wide CLI availability
Added
- Click Library Workaround: Implemented intelligent error handling with
safe_cli_wrapper()function to provide clean user experience - Comprehensive Test Suite: Added
tests/test_cli_error_handling.pywith 11 test cases covering CLI error suppression, legitimate error preservation, and integration scenarios - Detailed Documentation: Created
CLICK_WORKAROUND.mdwith technical details and removal timeline for the Click library workaround - Future Maintenance Guide: Added clear instructions for testing and removing the workaround when Click library is updated
Technical Details
- Entry Point: Updated CLI entry point to use
safe_cli_wrapperinstead of direct CLI function - Error Detection: Intelligent detection and filtering of spurious Click error messages while preserving legitimate errors
- Test Coverage: Full test coverage for workaround functionality including removal readiness testing
- Code Documentation: Comprehensive inline documentation for future maintainers
Resolves: Issue #3 - CLI argument parsing errors and confusing error messages
1.0.0 - 2025-10-19
Added
Scenario 1: Greenfield Projects (Production Ready)
- Complete hybrid agent distribution system with AgentRegistry, AgentInstaller, and ProjectInitializer
- CLI tool
kaizen-agenticwith comprehensive command interface for agent management - Agent registry and installer functionality for discovering, installing, and managing agents across projects
- Project templates system with python-basic, python-web, python-cli, python-data, and comprehensive templates
- Agent categorization system (project-management, development-process, code-quality, documentation, testing)
- HelloWorld tutorial and comprehensive documentation for new users
- Integrated Makefile targets for agent management (agents-list, agents-update, agents-validate, agents-status)
- Automatic Claude Code configuration updates via CLAUDE.md integration
Scenario 2: Existing Project Integration (Production Ready)
- Existing agent system detection (
detection.py) supporting 10+ agent frameworks:- Kaizen Agentic, Claude Code, GitHub Copilot, Anthropic Workbench
- OpenAI Assistants, LangChain Agents, AutoGen, CrewAI, and custom agents
- Migration framework (
migration.py) with 5 migration strategies:- Replace, Extend, Preserve, Merge, and Remove conflicting agents
- Automated conflict resolution with namespace and rename capabilities
- Extension system (
extensions.py) for project-specific customizations:- Configuration overlays, functional extensions, workflow integrations
- Custom commands, data transformations, environment adaptations
- Enhanced CLI commands for existing project integration:
kaizen-agentic detect- Analyze existing agent systems with detailed reportingkaizen-agentic migrate- Automated migration with dry-run and auto-resolve optionskaizen-agentic extensions- Manage project-specific agent customizations
Core System Enhancements
- Comprehensive CLI with 8+ primary commands:
init- Initialize new projects with agentsinstall/update/remove- Manage agents in existing projectslist/status/validate- Discovery and maintenance operationstemplates- Project template managementdetect/migrate/extensions- Existing project integration
- Enhanced Makefile with release management and local testing:
install-local- Install from locally built package for PyPI-equivalent testingrelease-*targets - Complete structured release workflow (6 targets)- Agent management targets with
agents-prefix for consistency
- Dependency resolution and validation with safety measures and backup/rollback support
- Console script entry point making kaizen-agentic command available globally after pip install
- Context manifest system with external documentation references (ContextManifest.md)
- Reference documentation for Keep a Contributing-File V0.0.1 and Keep a Todofile V0.0.1 formats
- PythonVibes integration with Python project best practices reference
- Multi-language build system integration examples and patterns
- Complete test coverage for all distribution system components (134 test files)
- Package data distribution with all agents included in pip-installable package
- Release management system with agent-releaseManager and 6 structured make targets:
release-check- Validate release readiness with comprehensive checklistrelease-prepare- Build packages and prepare for publicationrelease-test- Test publication workflow using TestPyPIrelease-publish- Publish to production PyPI with safety checksrelease-finalize- Post-release tasks (tags, GitHub releases, documentation)release-rollback- Emergency rollback procedures and guidance
- Local package installation with
make install-localtarget for PyPI-equivalent testing
Documentation and User Experience
- Comprehensive documentation suite:
- GETTING_STARTED.md - Complete setup and usage guide
- AGENT_DISTRIBUTION.md - Agent distribution system architecture
- CLI_CHEAT_SHEET.md - Quick reference for all CLI commands
- Integration patterns documentation for existing projects
- Production-ready tutorials for both greenfield and existing project scenarios
Changed
- Makefile target reorganization with consistent naming conventions:
- Agent management targets now use
agents-prefix (agents-list, agents-update, agents-validate) - Setup targets maintain
setup-prefix for consistency - Standards targets use
standards-prefix (standards-check, standards-fix, standards-test)
- Agent management targets now use
- Enhanced dependency management with YAML frontmatter support and precise reference detection
- Improved backup and safety systems with microsecond timestamps and collision prevention
- Updated agent definitions to align with official documentation standards and distribution requirements
- Streamlined Makefile structure with visual section separators and clear help documentation
- Agent repository consolidation removing duplicates and focusing on comprehensive implementations
Fixed
- All flake8 violations across the entire codebase for PEP 8 compliance
- Agent template name mappings and ProjectInitializer Makefile creation issues
- All failing tests for agent framework updates (24 core tests + 134 total tests now passing)
- Test reliability issues with backup directory collision prevention
- Dependency detection accuracy with more precise agent reference detection
- Code style compliance:
- Line length violations with appropriate line breaks
- Unused imports and variables removal
- F-string usage corrections
- Import organization and newline standardization
- Validation error reporting improvements for better debugging
- Virtual environment setup reliability issues on fresh repositories
0.1.0 - 2025-10-18
Added
- Initial Kaizen Agentic framework with core agent optimization infrastructure
- Agent and AgentConfig base classes for AI agent development
- OptimizationLoop and PerformanceMetrics for continuous improvement tracking
- Complete Python project structure with pyproject.toml configuration
- Comprehensive testing infrastructure with pytest framework
- Code quality tools integration (black, flake8, mypy)
- Virtual environment management with automatic setup
- Specialized agent definitions framework in
agents/directory - Claude Code integration with settings and permissions configuration
- Comprehensive Makefile with 50+ development commands
- Test-driven development (TDD) workflow support
- Issue management integration with Gitea API
- Architectural testing capabilities for 7-layer architecture
- Randomized testing for dependency detection
- Requirements engineering toolkit integration
- TODO.md and CHANGELOG.md following Keep a Todofile and Keep a Changelog formats
- 17+ specialized agents for development tasks
- Changelog keeper agent for version history maintenance
- Todo keeper agent for structured task management
- Project assistant agent for status and progress management
- Repository assistant agent for structure management and refactoring