ldy26098
/
BMAD-METHOD
mirror of https://github.com/bmad-code-org/BMAD-METHOD.git
1
0
Fork 0
Code Packages Projects Releases Wiki Activity
867 Commits 38 Branches 131 Tags 47 MiB
Commit Graph

18 Commits

Author SHA1 Message Date
Brian Madison 6f7e9f0653 refactor: Major v6 epic creation improvements and documentation overhaul 
## Key Changes

### 1. Epic Creation Workflow Enhancements
- Added user-value focused epic structure principles (NO technical layer breakdown)
- Implemented multi-mode detection: CONTINUE, REPLACE, or UPDATE existing epics
- Added comprehensive anti-pattern examples showing wrong vs right epic breakdown
- Epics now created AFTER architecture for technically-informed story breakdown
- Added checkpoint protocol for interactive workflow progression

### 2. Removed Deprecated Solutioning Gate Check
- Deleted entire solutioning-gate-check workflow (682 lines)
- Replaced by new implementation-readiness workflow
- Cleaner separation of concerns in solutioning phase

### 3. PRD Template Simplification
- Removed hardcoded "Implementation Planning", "References", and "Next Steps" sections
- PRD now focuses purely on requirements, not workflow orchestration
- Epics/stories created as separate step after architecture

### 4. Documentation Overhaul (15+ docs updated)
- Updated quick-start guide with v6 workflow sequence
- Clarified that epics are created AFTER architecture, not during PRD
- Updated solutioning docs to reflect implementation-readiness pattern
- Improved agents-guide, brownfield-guide, enterprise docs
- Enhanced glossary, FAQ, and workflow reference documentation

### 5. Workflow Path Adjustments
- All 4 paths updated (enterprise/method × brownfield/greenfield)
- Version bumps across BMGD, BMM, and CIS workflow YAMLs
- Minor instruction file updates for consistency

### Files Changed
- 65 files total: 468 insertions, 978 deletions (net reduction of 510 lines)
- 4 files deleted (entire solutioning-gate-check workflow)
- 1 new directory added (implementation-readiness placeholder)
 2025-11-16 00:23:47 -06:00
Brian Madison f14014f0c7 refactor: Major workflow enhancements - time estimates prohibition, progressive epic creation, and workflow simplification 
## Key Changes

### 1. Time Estimate Prohibition (All Modules)
- Added critical warnings against providing ANY time estimates (hours/days/weeks/months)
- Acknowledges AI has fundamentally changed development speed
- Applied to 33 workflow instruction files across BMB, BMGD, BMM, and CIS modules
- Updated workflow creation guide with prohibition guidelines

### 2. Enhanced Epic Creation Workflow
- Added intelligent UPDATE vs CREATE mode detection
- Detects available context (UX, Architecture, Domain brief, Product brief)
- Progressive enhancement: creates basic epics, then enriches with UX/Architecture
- Living document approach with continuous updates
- Added 305 lines of sophisticated workflow logic

### 3. Workflow Status Initialization Refactoring
- Simplified from 893 to 318 lines (65% reduction)
- Streamlined state detection: CLEAN, PLANNING, ACTIVE, LEGACY, UNCLEAR
- Cleaner path selection and initialization logic
- Removed redundant complexity while maintaining functionality

### 4. Workflow Path Updates
- Updated all 4 workflow paths (enterprise/method × brownfield/greenfield)
- Added multiple optional epic creation steps at different phases:
  - After PRD (basic structure)
  - After UX Design (with interaction context)
  - After Architecture (final with full context)
- Changed PRD output description from "with epics and stories" to "with FRs and NFRs"

### 5. Architecture & Innovation Updates
- Made epics input optional in architecture workflow (falls back to PRD FRs)
- Updated innovation strategy phases to remove time-based language
- Phases now: Immediate Impact → Foundation Building → Scale & Optimization

### Files Changed
- 33 instruction files updated with time estimate prohibition
- 2 workflow.yaml files updated (create-epics-and-stories, architecture)
- 4 workflow path YAML files updated
- 1 workflow creation guide enhanced

This refactor significantly improves workflow intelligence, removes harmful time-based planning assumptions, and creates more adaptive, context-aware workflows that better leverage AI capabilities.
 2025-11-14 23:54:29 -06:00
Brian Madison 48cf5c8056 feat(workflows): Implement intelligent file discovery protocol and Phase 4 BMGD workflows 
## Core Workflow Engine Enhancements

### discover_inputs Protocol (MAJOR)
- Added reusable `discover_inputs` protocol to workflow.xml for intelligent file loading
- Supports three loading strategies:
  - FULL_LOAD: Load all shards for PRD, Architecture, UX (changed pattern from /index.md to /*/*.md)
  - SELECTIVE_LOAD: Load specific shard via template variable (e.g., epic-{{epic_num}}.md)
  - INDEX_GUIDED: Load index, analyze TOC, intelligently load relevant docs (with "DO NOT BE LAZY" mandate)
- Auto-discovers whole vs sharded documents with proper fallback
- Provides transparent reporting of loaded content with file counts
- Invoked via <invoke-protocol name="discover_inputs" /> tag in workflow instructions

### Advanced Elicitation Improvements
- Renamed adv-elicit.xml to advanced-elicitation.xml for clarity
- Updated all references across agents and commands

### Shard Document Tool Enhancement
- Added Step 6: Handle Original Document with three options:
  - [d] Delete - Remove original (recommended, prevents confusion)
  - [m] Move to archive - Backup original to archive folder
  - [k] Keep - Warning about defeating sharding purpose
- Prevents issue where both whole and sharded versions exist, confusing discover_inputs protocol

## BMM Module - Input File Pattern Standardization

### Phase 1 - Analysis (1 workflow)
- product-brief: Added load_strategy (FULL_LOAD for research/brainstorming, INDEX_GUIDED for document_project)
- Updated instructions.md to use invoke-protocol, replaced manual fuzzy matching

### Phase 2 - Planning (4 workflows)
- prd: Added load_strategy, updated instructions to reference {product_brief_content}, {research_content}
- create-ux-design: Added load_strategy, removed fuzzy matching from instructions
- tech-spec: Added load_strategy for brownfield context discovery
- All epics patterns updated to support SELECTIVE_LOAD for specific epic shards

### Phase 3 - Solutioning (2 workflows)
- architecture: Added load_strategy, updated instructions to use pre-loaded {prd_content}, {epics_content}, {ux_design_content}
- solutioning-gate-check: Added load_strategy, replaced manual discovery with protocol invocation

### Phase 4 - Implementation (8 workflows)
- code-review: Added load_strategy, fixed sharded patterns to /*/*.md, added step 1.5 for protocol
- correct-course: Added complete input_file_patterns section (was missing), added step 0.5
- create-story: Added load_strategy, updated to SELECTIVE_LOAD for epics, added step 1.5
- dev-story: Added complete input_file_patterns section (was missing), added step 0.5
- epic-tech-context: Added load_strategy, updated PRD extraction to use {prd_content}, added step 1.5
- retrospective: Added load_strategy for architecture/prd (FULL_LOAD), epics (SELECTIVE_LOAD), added step 0.5
- sprint-planning: Fixed sharded pattern to load ALL epics (/*/*.md), added step 0.5
- story-context: Added load_strategy, updated doc collection to reference pre-loaded content, added step 1.5

### Sprint Artifacts Path Corrections
- story-done: Added missing sprint_artifacts variable, fixed sprint_status path from {context_dir} to {sprint_artifacts}
- story-ready: Added missing sprint_artifacts variable
- story-context: Fixed undefined {context_dir} -> {sprint_artifacts}
- correct-course: Added sprint_artifacts and sprint_status variables

## BMGD Module - Phase 4 Production Workflows (NEW)

Added complete Phase 4 implementation workflows for game development:
- code-review: Senior developer review for completed game features
- correct-course: Sprint change management for game projects
- create-story: Story generation for game mechanics/features
- dev-story: Feature implementation workflow
- epic-tech-context: Technical spec generation per game epic
- retrospective: Epic completion review and lessons learned
- sprint-planning: Game development sprint status tracking
- story-context: Dynamic context assembly for game stories
- story-done: Story completion workflow
- story-ready: Story readiness workflow

All BMGD workflows follow BMM patterns with game-specific adaptations.

## Agent Updates

### BMM Agents
- Updated all 7 BMM agents (analyst, architect, dev, pm, sm, tea, tech-writer, ux-designer)
- Standardized web bundle configurations

### BMGD Agents
- Updated 4 game development agents (game-architect, game-designer, game-dev, game-scrum-master)
- Aligned with BMM agent structure

### CIS Agents
- Updated 5 creative intelligence agents for consistency

## Documentation & Configuration

- Updated CHANGELOG.md with Phase 4 workflow additions
- Updated files-manifest.csv and task-manifest.csv
- Updated .claude commands for all agents
- Fixed formatting issues from previous commits

## Breaking Changes

NONE - All changes are backward compatible. Workflows without input_file_patterns continue to work.
Workflows with input_file_patterns now benefit from intelligent auto-loading.

## Migration Notes

Existing workflows can gradually adopt discover_inputs protocol by:
1. Adding load_strategy to existing input_file_patterns in workflow.yaml
2. Adding <invoke-protocol name="discover_inputs" /> step in instructions.md
3. Replacing manual file loading with references to {pattern_name_content} variables
 2025-11-12 19:18:38 -06:00
Brian Madison 8f7d259c81 remaining bad character removal 2025-11-11 20:10:33 -06:00
Brian Madison 4d745532aa refactor(tech-spec): unify story generation and adopt intent-based approach 
Major refactoring of tech-spec workflow for quick-flow projects:

## Unified Story Generation
- Consolidated instructions-level0-story.md and instructions-level1-stories.md into single instructions-generate-stories.md
- Always generates epic + stories (minimal epic for 1 story, detailed for multiple)
- Consistent naming: story-{epic-slug}-N.md for all stories (1-5)
- Eliminated branching logic and duplicate code

## Intent-Based Intelligence
- Removed 150+ lines of hardcoded stack detection examples (Node.js, Python, Ruby, Java, Go, Rust, PHP)
- Replaced prescriptive instructions with intelligent guidance that trusts LLM capabilities
- PHASE 2 stack detection now adapts to ANY project type automatically
- Step 2 discovery changed from scripted Q&A to adaptive conversation goals

## Terminology Updates
- Replaced "Level 0" and "Level 1" with "quick-flow" terminology throughout
- Updated to "single story" vs "multiple stories (2-5)" language
- Consistent modern terminology across all files

## Variable and Structure Improvements
- Fixed variable references: now uses {instructions_generate_stories} instead of hardcoded paths
- Updated workflow.yaml with cleaner variable structure
- Removed unused variables (project_level, development_context)
- Added story_count and epic_slug runtime variables

## Files Changed
- Deleted: instructions-level0-story.md (7,259 bytes)
- Deleted: instructions-level1-stories.md (16,274 bytes)
- Created: instructions-generate-stories.md (13,109 bytes)
- Updated: instructions.md (reduced from 35,028 to 32,006 bytes)
- Updated: workflow.yaml, checklist.md

## Impact
- 50% fewer workflow files (3 → 1 for story generation)
- More adaptable to any tech stack
- Clearer, more maintainable code
- Better developer and user experience
- Trusts modern LLM intelligence instead of constraining with examples
 2025-11-11 17:30:43 -06:00
Brian Madison 2d99833b9e feat: Add documentation guides, simplify folder structure, and major workflow refactoring 
Created two comprehensive guides for v6 features:

**docs/agent-customization-guide.md**
- Complete guide for customizing agent names, personas, memories, and behaviors
- Update-safe customization via bmad/_cfg/agents/ configuration files
- Real-world examples (TDD setup, multilingual agents, custom workflows)
- Troubleshooting and best practices

**docs/web-bundles-gemini-gpt-guide.md**
- Comprehensive guide for using BMad agents in Gemini Gems and Custom GPTs
- Critical setup rules with exact configuration text required
- Cost-saving strategy: web planning → local implementation (60-80% savings)
- Platform comparison (Gemini Gems strongly recommended over Custom GPTs)
- Complete workflow examples showing full planning-to-implementation cycle
- Team bundle guidance (Gemini 2.5 Pro+ only)

**README.md updates**
- Added prominent links in v6 Core Enhancements section
- Created new "Customization & Sharing" documentation category
- Web Bundles feature highlighted with direct guide link

**Unified output folder structure across all modules:**

**Before (confusing):**
- output_folder: Main docs
- game_design_docs: Separate design folder
- tech_docs: Separate technical folder
- dev_ephemeral_location: Separate ephemeral folder outside docs

**After (simplified):**
- output_folder: Single location for ALL AI-generated artifacts (default: "docs")
  - Clearer prompt: "Where should AI Generated Artifacts be saved?"
- sprint_artifacts: Phase 4 ephemeral content now WITHIN output_folder
  - BMM: {output_folder}/stories (stories, context, reports)
  - BMGD: {output_folder}/sprint-artifacts
  - No longer in separate {bmad_folder}-ephemeral location

**Benefits:**
- One clear location for all planning artifacts (PRD, Architecture, UX, etc.)
- Phase 4 ephemeral items logically grouped within output folder
- Eliminated confusing separate folder proliferation
- sprint_artifacts now configurable per module

**Files changed:**
- src/core/_module-installer/install-config.yaml
- src/modules/bmm/_module-installer/install-config.yaml
- src/modules/bmgd/_module-installer/install-config.yaml

**Also cleaned up BMGD config:**
- Renamed: specified_framework → primary_platform (clearer naming)
- Removed: unused data_path variable

Replaced old "project_level" (0-4) system with new "selected_track" terminology:
- **quick-flow**: Bug fixes and small features (replaces Level 0-1)
- **bmad-method**: Full planning track (replaces Level 2-3)
- **enterprise-bmad-method**: Extended planning (replaces Level 4)

**Core workflow updates:**
- solutioning-gate-check: Complete rewrite of validation logic for track-based artifacts
- architecture: Updated context detection, error handling, and messaging for tracks
- workflow-init: Updated artifact detection patterns for track-based paths
- All workflow status paths updated (method-greenfield, method-brownfield, enterprise-*)

Unified variable naming conventions across all workflows:
- {output_folder} → {output-folder} (hyphenated format)
- {dev_ephemeral_location} → {sprint_artifacts} (clearer purpose)
- Hardcoded status file paths → {workflow_status_file} variable

Fixed corrupted variable patterns throughout workflow files:
- {output*folder} → {output-folder}
- {ephemeral*location} → {sprint_artifacts}
- \_prd* → *prd* (escaped underscore artifacts)
- **\*\***\_\_\_**\*\*** → proper field placeholders

Affected patterns included malformed glob patterns, template variables, and markdown formatting artifacts from previous edits.

**Architecture workflow (create-architecture):**
- Fixed: "Decision Architecture" → "Create Architecture" (consistent naming)
- Improved PRD not found handling with exit/continue options
- Better user guidance when running standalone vs. within workflow path
- Removed hardcoded Level checks, now track-aware
- Enhanced validation checklist formatting (□ → - [])
- Typo fixes: "mulitple" → "multiple"

**Solutioning gate check:**
- Complete validation logic rewrite for track-based system
- Removed Level-specific artifact expectations
- Simplified document discovery (track determines what exists)
- Better analysis prompts and user feedback

**Workflow-init:**
- Updated artifact detection patterns for new folder structure
- Fixed corrupt glob patterns throughout
- Better sprint_artifacts location detection
- Improved workflow path assignment logic

**Various workflows:**
- Consistent variable naming across 40+ workflow files
- Improved error messages and user guidance
- Better markdown formatting (checkboxes, lists)
- Removed redundant validation criteria files (now inline)

Removed duplicate BMGD 4-production workflows (12 workflows):
- code-review, correct-course, create-story, dev-story
- epic-tech-context, retrospective, sprint-planning
- story-context, story-done, story-ready

**Why:** BMGD now uses shared BMM Phase 4 implementation workflows
**Benefit:** Single source of truth, no duplication to maintain

Also removed:
- validation-criteria.yaml (validation now inline in instructions)
- architecture-patterns.yaml references (patterns now managed differently)
- AUDIT-REPORT.md files (stale audit artifacts)

**BMB workflows:**
- Updated checklists for workflow and module creation
- Improved agent architecture documentation
- Minor instruction clarifications

**Core brainstorming workflow:**
- Updated README with usage examples
- Enhanced instructions and template clarity
- Better integration with other modules

**BMM installer:**
- Updated for track-based system
- sprint_artifacts configuration

**Tech Writer agent:**
- Minor configuration update for documentation workflows

Removed 200+ files that should not be in repository:
- Installed agent markdown files (analyst, architect, dev, pm, sm, tea, etc.)
- Complete workflow instruction copies
- Documentation duplicates (quick-start, agents-guide, workflows-*)
- Test architecture knowledge base (22 files, 14,000+ lines)
- Configuration files (config.yaml, team definitions)

These are generated during installation and should not be version controlled.

Removed 21 pre-generated XML bundles:
- BMM agents (analyst, architect, dev, pm, sm, tea, tech-writer, ux-designer)
- BMGD agents (game-architect, game-designer, game-dev, game-scrum-master)
- CIS agents (brainstorming-coach, creative-problem-solver, etc.)
- Team bundles (team-fullstack, team-gamedev, creative-squad)

**Why:** Users should generate fresh bundles via `npm run bundle` to get latest changes and customizations.

- **2 new documentation files** (comprehensive guides)
- **98 source files modified** (299 insertions, 6,567 deletions)
- **3 installer config files simplified** (major folder structure improvement)
- **200+ .bmad/ artifacts removed** (should not be in repo)
- **21 web-bundle files removed** (users regenerate as needed)
- **12 duplicate workflows removed** (BMGD consolidation)
- **40+ workflows updated** (track system, variable standardization, corruption fixes)
 2025-11-11 17:30:43 -06:00
Brian Madison 1728acfb0f The install directory is now configurable, with a few minute issues 2025-11-08 13:58:43 -06:00
Brian Madison accae5d789 refactor: comprehensive workflow modernization and standardization 
## Major Improvements

### 1. Elicitation System Modernization
- Removed legacy `<elicit-required />` tag from workflow.xml
- Replaced with direct `<invoke-task halt="true">{project-root}/bmad/core/tasks/adv-elicit.xml</invoke-task>` pattern
- More explicit, self-documenting, and eliminates indirection layer
- Added strategic elicitation points across all planning workflows:
  - PRD: After success criteria, scope, functional requirements, and final review
  - Create-Epics-And-Stories: After epic proposals and each epic's stories
  - Architecture: After decisions, structure, patterns, implementation patterns, and final doc
  - Updated audit-workflow tag scanner to remove obsolete elicit-required reference

### 2. Input Document Discovery Streamlined
- Replaced verbose 19-line "Input Document Discovery" sections with single critical tag
- New format: `<critical>Input documents specified in workflow.yaml input_file_patterns...</critical>`
- Eliminates duplication - workflow.yaml already defines patterns
- Updated across 6 workflows (PRD, create-epics-and-stories, architecture, tech-spec, UX, gate-check)
- Saved ~114 lines of repeated bloat

### 3. Scale System Migration (Levels 0-4 → 3 Tracks)
- Updated PRD workflow from "Level 0-4" to "Quick Flow / BMad Method / Enterprise Method"
- Changed `project_level` variable to `project_track`
- Removed `target_scale` variable (no longer needed)
- Updated workflow.yaml descriptions to reference tracks not levels
- Updated checklist from "Level 2" and "Level 3-4" to "BMad Method" and "Enterprise Method"
- Aligns with new scale-adaptive-system.md (3-track methodology)

### 4. Epic/Story Template Standardization
- Replaced hardcoded 8-epic template with clean repeating pattern using N/M variables
- Added BDD-style acceptance criteria (Given/When/Then/And)
- Removed instructional bloat from templates (moved to instructions.md where it belongs)
- Template shows OUTPUT structure, instructions show PROCESS
- Applied to both create-epics-and-stories and tech-spec workflows
- Templates now use HTML comments to indicate repeating sections

### 5. Workflow.yaml Pattern Consistency
- Standardized input_file_patterns across all workflows
- Separated `recommended_inputs` (semantic WHAT) from `input_file_patterns` (file discovery WHERE)
- Removed duplication between recommended_inputs file paths and input_file_patterns
- Create-epics-and-stories now uses proper whole/sharded pattern like architecture workflow
- Solutioning-gate-check cleaned up to use semantic descriptions not file paths

## Files Changed (18)
- Core: workflow.xml (removed elicit-required tag and references)
- Audit workflow: Updated tag pattern scanner
- PRD workflow: Elicitation points, track migration, input discovery
- Create-epics-and-stories: Template rebuild, BDD format, elicitation, input patterns
- Tech-spec: Template rebuild, BDD format, input discovery
- UX Design: Input discovery streamlined
- Architecture: Elicitation at 5 key decision points, input discovery
- Gate-check: Input pattern cleanup, input discovery

## Impact
- More consistent elicitation across workflows
- Cleaner, more maintainable templates
- Better separation of concerns (templates vs instructions)
- Aligned with v6 3-track scale system
- Reduced bloat and duplication significantly
 2025-11-04 00:09:19 -06:00
Brian Madison 8a00f8ad70 feat: transform tech-spec workflow into intelligent Quick Spec Flow for Level 0-1 
This major enhancement revolutionizes the tech-spec workflow from a basic template-filling exercise into a context-aware, intelligent planning system for rapid development of bug fixes and small features.

## Tech-Spec Workflow Transformation (11 files)

### Core Workflow Intelligence (instructions.md)
- Add standalone mode with interactive level/field-type detection
- Implement brownfield convention detection and user confirmation
- Integrate WebSearch for current framework versions and starter templates
- Add comprehensive context discovery (stack, patterns, dependencies)
- Implement auto-validation with quality scoring (always runs)
- Add UX/UI considerations capture for user-facing changes
- Add test framework detection and pattern analysis
- Transform from batch generation to living document approach

### Comprehensive Tech-Spec Template (tech-spec-template.md)
- Expand from 8 to 23 sections for complete context
- Add Context section (available docs, project stack, existing structure)
- Add Development Context (conventions, test framework, existing code)
- Add UX/UI Considerations section
- Add Developer Resources (file paths, key locations, testing)
- Add Integration Points and Configuration Changes
- All sections populated via template-output tags during workflow

### Enhanced Story Generation
- Level 0 (instructions-level0-story.md): Extract from comprehensive tech-spec
- Level 1 (instructions-level1-stories.md): Add story sequence validation, AC quality checks
- User Story Template: Add Dev Agent Record sections for implementation tracking
- Epic Template: Complete rewrite with proper structure and variables

### Validation & Quality (checklist.md)
- Add context gathering completeness checks
- Add definitiveness validation (no "use X or Y" statements)
- Add brownfield integration quality scoring
- Add stack alignment verification
- Add implementation readiness assessment
- Auto-generates validation report with scores

### Configuration (workflow.yaml)
- Add runtime variables: project_level, project_type, development_context, change_type, field_type
- Enable standalone operation without workflow-status.yaml
- Support both workflow-init integration and quick-start mode

## Phase 4 Integration (3 files)

### Story Context Workflow
- Add tech_spec to input_file_patterns (recognizes as authoritative source)
- Update instructions to prioritize tech-spec for Level 0-1 projects
- Tech-spec provides brownfield analysis, framework details, existing patterns

### Create Story Workflow
- Add tech_spec to input_file_patterns
- Enable story generation from tech-spec (alternative to PRD)
- Supports both Quick Spec Flow and traditional BMM flow

## Documentation (2 new files)

### Quick Spec Flow Guide (docs/quick-spec-flow.md)
- Comprehensive 595-line guide for Level 0-1 rapid development
- Complete user journey examples (bug fix, small feature)
- Context discovery explanation (stack, brownfield, conventions)
- Auto-validation details and benefits
- Integration with Phase 4 workflows
- Comparison: Quick Spec vs Full BMM
- Real-world examples and best practices

### Scale Adaptive System (docs/scale-adaptive-system.md)
- Complete 950-line technical guide to BMad Method's 5-level system
- Key terminology: Analysis, Tech-Spec, Epic-Tech-Spec, Architecture
- Level 0-4 workflows, planning docs, and progression
- Brownfield emphasis: document-project required first
- Tech-spec (upfront, Level 0-1) vs epic-tech-spec (during implementation, Level 2-4)
- Architecture document replaces tech-spec at Level 2+ (scales with complexity)
- Retrospectives after each epic in multi-epic projects
- Workflow path configuration reference

### README Updates
- Add Quick Spec Flow announcement with benefits
- Link to Scale Adaptive System documentation
- Clarify when to use Quick Spec Flow vs Full BMM

## Key Features

### Context-Aware Intelligence
- Auto-detects project stack from package.json, requirements.txt, etc.
- Analyzes brownfield codebases using document-project output
- Detects code conventions and confirms with user before proceeding
- Uses WebSearch for up-to-date framework info and starter templates

### Brownfield Respect
- Detects existing patterns (code style, test framework, naming conventions)
- Asks user for confirmation before applying conventions
- Adapts to existing code vs forcing changes
- References document-project analysis for comprehensive context

### Auto-Validation
- Always runs (not optional)
- Validates context gathering, definitiveness, brownfield integration
- Scores tech-spec quality and implementation readiness
- Validates story sequence for Level 1 (no forward dependencies)

### Living Document Approach
- Write to tech-spec continuously during discovery
- Progressive refinement vs batch generation
- Template variables populated via template-output tags in real-time

## Breaking Changes

None - all changes are additive and backward compatible.

## Impact

This transformation enables:
- Bug fixes and small features implemented in minutes vs hours
- Automatic stack detection and brownfield analysis
- Respect for existing conventions and patterns
- Current best practices via WebSearch integration
- Comprehensive context that can replace story-context for simple efforts
- Seamless integration with Phase 4 implementation workflows

Quick Spec Flow now provides a **true fast path from idea to implementation** for Level 0-1 projects while maintaining quality through auto-validation and comprehensive context gathering.
 2025-11-02 08:17:23 -06:00
Brian Madison 3d4ea5ffd2 feat: add universal document sharding support with dual-strategy loading 
Implement comprehensive document sharding system across all BMM workflows enabling 90%+ token savings for large multi-epic projects through selective loading optimization.

## Document Sharding System

### Core Features
- **Universal Support**: All 12 BMM workflows (Phase 1-4) handle both whole and sharded documents
- **Dual Loading Strategy**: Full Load (Phase 1-3) vs Selective Load (Phase 4)
- **Automatic Discovery**: Workflows detect format transparently (whole → sharded priority)
- **Efficiency Optimization**: 90%+ token reduction for 10+ epic projects in Phase 4

### Implementation Details

**Phase 1-3 Workflows (7 workflows) - Full Load Strategy:**
- product-brief, prd, gdd, create-ux-design, tech-spec, architecture, solutioning-gate-check
- Load entire sharded documents when present
- Transparent to user experience
- Better organization for large projects

**Phase 4 Workflows (5 workflows) - Selective Load Strategy:**
- sprint-planning (Full Load exception - needs all epics)
- epic-tech-context, create-story, story-context, code-review (Selective Load)
- Load ONLY the specific epic needed (e.g., epic-3.md for Epic 3 stories)
- Massive efficiency: Skip loading 9 other epics in 10-epic project

### Workflow Enhancements

**Added to all workflows:**
- `input_file_patterns` in workflow.yaml with wildcard discovery
- Document Discovery section in instructions.md
- Support for sharded index + section files
- Brownfield `docs/index.md` support

**Pattern standardization:**
```yaml
input_file_patterns:
  document:
    whole: "{output_folder}/*doc*.md"
    sharded: "{output_folder}/*doc*/index.md"
    sharded_single: "{output_folder}/*doc*/section-{{id}}.md"  # Selective load
```

### Retrospective Workflow Major Overhaul

Transformed retrospective into immersive, interactive team experience:

**Epic Discovery Priority (Fixed):**
- Priority 1: Check sprint-status.yaml for last completed epic
- Priority 2: Ask user directly
- Priority 3: Scan stories folder (last resort)

**New Capabilities:**
- Deep story analysis: Extract dev notes, mistakes, review feedback, lessons learned
- Previous retro integration: Track action items, verify lessons applied
- Significant change detection: Alert when discoveries require epic updates
- Intent-based facilitation: Natural conversation vs scripted phrases
- Party mode protocol: Clear speaker identification (Name (Role): dialogue)
- Team dynamics: Drama, disagreements, diverse perspectives, authentic conflict

**Structure:**
- 12 whole-number steps (no decimals)
- Highly interactive with constant user engagement
- Cross-references previous retro for accountability
- Synthesizes patterns across all stories
- Detects architectural assumption changes

## Documentation

**Created:**
- `docs/document-sharding-guide.md` - Comprehensive 300+ line guide
  - What is sharding, when to use it (token thresholds)
  - How sharding works (discovery system, loading strategies)
  - Using shard-doc tool
  - Full Load vs Selective Load patterns
  - Complete examples and troubleshooting
  - Custom workflow integration patterns

**Updated:**
- `README.md` - Added Document Sharding feature section
- `docs/index.md` - Added under Advanced Topics → Optimization
- `src/modules/bmm/workflows/README.md` - Added sharding section with usage
- `src/modules/bmb/workflows/create-workflow/workflow-creation-guide.md` - Added complete implementation patterns for workflow builders

**Documentation levels:**
1. Overview (README.md) - Quick feature highlight
2. User guide (BMM workflows README) - Practical usage
3. Reference (document-sharding-guide.md) - Complete details
4. Builder guide (workflow-creation-guide.md) - Implementation patterns

## Efficiency Gains

**Example: 10-Epic Project**

Before sharding:
- epic-tech-context for Epic 3: Load all 10 epics (~50k tokens)
- create-story for Epic 3: Load all 10 epics (~50k tokens)
- story-context for Epic 3: Load all 10 epics (~50k tokens)

After sharding with selective load:
- epic-tech-context for Epic 3: Load Epic 3 only (~5k tokens) = 90% reduction
- create-story for Epic 3: Load Epic 3 only (~5k tokens) = 90% reduction
- story-context for Epic 3: Load Epic 3 only (~5k tokens) = 90% reduction

## Breaking Changes

None - fully backward compatible. Workflows work with existing whole documents.

## Files Changed

**Workflows Updated (25 files):**
- 7 Phase 1-3 workflows: Added full load sharding support
- 5 Phase 4 workflows: Added selective load sharding support
- 1 retrospective workflow: Complete overhaul with sharding support

**Documentation (5 files):**
- Created: document-sharding-guide.md
- Updated: README.md, docs/index.md, BMM workflows README, BMB workflow-creation-guide
- Removed: Old conversion report (obsolete)

## Future Extensibility

- BMB workflows now aware of sharding patterns
- Custom modules can easily implement sharding support
- Standard patterns documented for consistency
- No need to explain concept in future development
 2025-11-02 00:13:33 -05:00
Brian Madison ec111972a0 some output should be improved and not run together in chat windows 2025-10-30 08:13:18 -05:00
Brian Madison 66c66f602d all workflows can optionally run without a workflow 2025-10-27 23:51:22 -05:00
Brian Madison 92bff333b1 plan-project gone, and all level 1-3 workflows are dynamic from the workflow in suggesting what is next 2025-10-24 23:16:08 -05:00
Brian Madison b54bb9e47d workflow references to moved workflow status workflow 2025-10-17 22:34:21 -05:00
Brian Madison e92f138f3d doc output lang vs com lang 2025-10-17 19:46:25 -05:00
Brian Madison ffd354b605 arch alignment with workflows 2025-10-17 16:44:06 -05:00
Brian Madison e77a1c036b 1-analysis workflow-state yaml streamlined 2025-10-16 08:26:26 -05:00
Brian Madison f4b16bfacf planning workflow alignment 2025-10-15 23:10:33 -05:00