This release introduces significant enhancements across multiple areas:
QA Agent Transformation:
- Transform QA agent into senior developer role with active code refactoring abilities
- Add review-story task enabling QA to review, refactor, and improve code directly
- Integrate QA review step into standard development workflow (SM → Dev → QA)
- QA can fix small issues directly and leave checklist for remaining items
- Updated dev agent to maintain File List for QA review focus
Knowledge Base Improvements:
- Add extensive brownfield development documentation and best practices
- Clarify Web UI vs IDE usage with cost optimization strategies
- Document PRD-first approach for large codebases/monorepos
- Add comprehensive expansion packs explanation
- Update IDE workflow to include QA review step
- Clarify agent usage (bmad-master vs specialized agents)
Brownfield Enhancements:
- Create comprehensive Working in the Brownfield guide
- Add document-project task to analyst agent capabilities
- Implement PRD-first workflow option for focused documentation
- Transform document-project to create practical brownfield architecture docs
- Document technical debt, workarounds, and real-world constraints
- Reference actual files instead of duplicating content
- Add impact analysis when PRD is provided
Documentation Task Improvements:
- Simplify to always create ONE unified architecture document
- Add deep codebase analysis phase with targeted questions
- Focus on documenting reality including technical debt
- Include Quick Reference section with key file paths
- Add practical sections: useful commands, debugging tips, known issues
Workflow Updates:
- Update all 6 workflow files with detailed IDE transition instructions
- Add clear SM → Dev → QA → Dev cycle explanation
- Emphasize Gemini Web for brownfield analysis (1M+ context advantage)
- Support both PRD-first and document-first approaches
This release significantly improves the brownfield development experience and introduces a powerful shift-left QA approach with senior developer mentoring.
Issue Being Solved:
Dev agent was marking tasks as complete even when tests/lint/typecheck failed,
causing broken code to reach merge and creating technical debt.
Gap in System:
Missing explicit quality gates in dev agent configuration to block task completion
until all automated validations pass.
Solution:
- Add "Quality Gate Discipline" core principle
- Update task execution flow: Execute validations→Only if ALL pass→Update [x]
- Add "Failing validations" to blocking conditions
- Simplify completion criteria to focus on validation success
Alignment with BMAD Core Principles:
- Quality-First: Prevents defective code progression through workflow
- Agent Excellence: Ensures dev agent maintains high standards
- Technology Agnostic: Uses generic "validations" concept vs specific tools
Small, focused change that strengthens existing dev agent without architectural changes.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
- Add markdownExploder setting to core-config.yml
- Update shard-doc task to use md-tree command when enabled
- Implement proper fallback handling when tool is unavailable
- Update core-config structure to remove nested wrapper
- Fix field naming to use camelCase throughout
When users enter "." as the installation directory, the web bundles directory
path was not being resolved correctly, causing the bundles to not be copied.
This fix ensures the web bundles directory is resolved using the same logic
as the main installation directory, resolving relative paths from the original
working directory where npx was executed.
# [4.8.0](https://github.com/bmadcode/BMAD-METHOD/compare/v4.7.0...v4.8.0) (2025-06-19)
### Bug Fixes
* installer has fast v4 update option now to keep the bmad method up to date with changes easily without breaking any customizations from the user. The SM and DEV are much more configurable to find epics stories and architectureal information when the prd and architecture are deviant from v4 templates and/or have not been sharded. so a config will give the user the option to configure the SM to use the full large documents or the sharded versions! ([aea7f3c](aea7f3cc86))
* prevent double installation when updating v4 ([af0e767](af0e767ecf))
* resolve undefined config properties in performUpdate ([0185e01](0185e012bb))
* update file-manager to properly handle YAML manifest files ([724cdd0](724cdd07a1))
### Features
* add early v4 detection for improved update flow ([29e7bbf](29e7bbf4c5))
* add file resolution context for IDE agents ([74d9bb4](74d9bb4b2b))
* update web builder to remove IDE-specific properties from agent bundles ([2f2a1e7](2f2a1e72d6))
- Remove 'root' property from YAML when building web bundles
- Remove 'IDE-FILE-RESOLUTION' and 'REQUEST-RESOLUTION' properties
- Filter out IDE-specific activation instructions
- Keep agent header minimal for web bundles
- Ensures web bundles are clean of IDE-specific configuration
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added two concise activation instructions to SM agent
- IDE-FILE-RESOLUTION: One-line explanation of file path mapping
- REQUEST-RESOLUTION: One-line instruction for flexible request matching
- Simplified file-resolution-context.md to be a quick reference
- Removed verbose documentation in favor of clear, actionable instructions
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added file resolution section to SM agent explaining path patterns
- Created reusable file-resolution-context.md utility
- Documents how agents resolve tasks/templates/checklists to file paths
- Provides natural language to command mapping examples
- Helps IDE agents understand file system structure
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added prominent section about updating existing installations
- Explains how npx bmad-method install detects and updates v4
- Highlights backup feature for custom modifications
- Makes it clear that updates are safe and preserve customizations
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added flag to prevent installer.install() being called twice
- Fixed undefined 'directory' error by using answers.directory
- Update flow now completes without errors
- Prevents 'Cannot read properties of undefined' error after successful update
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added optional chaining for newConfig.ide access
- Added ides array to config object in performUpdate
- Fixes 'Cannot read properties of undefined' error after update
- Ensures all required config properties are present for showSuccessMessage
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Now detects existing v4 installations immediately after directory prompt
- Offers update option upfront for existing v4 installations
- If user declines update, continues with normal installation flow
- Added 'update' install type handling in installer
- Improves user experience by streamlining the update process
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
