refactor: rename workflows for clarity
Renamed three implementation workflows to avoid confusion: - batch-super-dev → batch-stories (processes multiple stories) - super-dev-pipeline → story-full-pipeline (single story with validation/review) - story-pipeline → story-dev-only (basic TDD implementation only) Changes include: - Renamed workflow directories - Updated workflow.yaml name fields and installed_path references - Updated all cross-references in workflow.md files - Updated state file naming conventions for clarity - Updated references in documentation and other workflows This naming convention eliminates pattern-matching confusion by using completely distinct names for each workflow level.
This commit is contained in:
Jonah Schulte
parent
e38282b063
commit
2526e7c9cb
|
|
@ -227,7 +227,7 @@ async function checkoutStory(storyKey) {
|
|||
}
|
||||
```
|
||||
|
||||
**Lock Verification** (before each task in super-dev-pipeline):
|
||||
**Lock Verification** (before each task in story-full-pipeline):
|
||||
|
||||
```javascript
|
||||
// Integrated into step-03-implement.md
|
||||
|
|
@ -270,8 +270,8 @@ async function verifyLockBeforeTask(storyKey) {
|
|||
**Files to Modify**:
|
||||
|
||||
1. `src/modules/bmm/workflows/4-implementation/dev-story/instructions.xml` (Step 8, lines 502-533)
|
||||
2. `src/modules/bmm/workflows/4-implementation/super-dev-pipeline/steps/step-03-implement.md`
|
||||
3. `src/modules/bmm/workflows/4-implementation/batch-super-dev/step-4.5-reconcile-story-status.md`
|
||||
2. `src/modules/bmm/workflows/4-implementation/story-full-pipeline/steps/step-03-implement.md`
|
||||
3. `src/modules/bmm/workflows/4-implementation/batch-stories/step-4.5-reconcile-story-status.md`
|
||||
|
||||
**Add After Task Completion**:
|
||||
|
||||
|
|
@ -391,8 +391,8 @@ Result:
|
|||
|
||||
**Files to Modify**:
|
||||
|
||||
1. `super-dev-pipeline/steps/step-06-complete.md` - Add PR creation
|
||||
2. Add new: `super-dev-pipeline/steps/step-07-sync-github.md`
|
||||
1. `story-full-pipeline/steps/step-06-complete.md` - Add PR creation
|
||||
2. Add new: `story-full-pipeline/steps/step-07-sync-github.md`
|
||||
|
||||
**PR Creation** (after git commit):
|
||||
|
||||
|
|
@ -576,7 +576,7 @@ This is a HARD REQUIREMENT for team coordination.
|
|||
└─────────────────────────────────────────────────────────────┘
|
||||
|
||||
┌─────────────────────────────────────────────────────────────┐
|
||||
│ 3. IMPLEMENTATION (Developer via super-dev-pipeline) │
|
||||
│ 3. IMPLEMENTATION (Developer via story-full-pipeline) │
|
||||
├─────────────────────────────────────────────────────────────┤
|
||||
│ Step 1: Init │
|
||||
│ └─ Verify lock held (HALT if lost) │
|
||||
|
|
@ -750,9 +750,9 @@ try {
|
|||
|
||||
## Critical Integration Points
|
||||
|
||||
### Point 1: batch-super-dev Story Selection
|
||||
### Point 1: batch-stories Story Selection
|
||||
|
||||
**File**: `batch-super-dev/instructions.md` (Step 2)
|
||||
**File**: `batch-stories/instructions.md` (Step 2)
|
||||
**Change**: Filter locked stories BEFORE user selection
|
||||
|
||||
```xml
|
||||
|
|
@ -794,9 +794,9 @@ try {
|
|||
</step>
|
||||
```
|
||||
|
||||
### Point 2: super-dev-pipeline Lock Verification
|
||||
### Point 2: story-full-pipeline Lock Verification
|
||||
|
||||
**File**: `super-dev-pipeline/steps/step-03-implement.md`
|
||||
**File**: `story-full-pipeline/steps/step-03-implement.md`
|
||||
**Change**: Add lock check before each task
|
||||
|
||||
```markdown
|
||||
|
|
@ -1028,7 +1028,7 @@ Try: /available-stories
|
|||
# → HALT
|
||||
|
||||
# Developer fixes network, resumes:
|
||||
$ /super-dev-pipeline story_key=2-5-auth
|
||||
$ /story-full-pipeline story_key=2-5-auth
|
||||
|
||||
# System:
|
||||
# → Detects saved state
|
||||
|
|
@ -1120,10 +1120,10 @@ $ /super-dev-pipeline story_key=2-5-auth
|
|||
|
||||
### MODIFIED Files (5 total)
|
||||
|
||||
1. `batch-super-dev/instructions.md` (+150 lines)
|
||||
2. `super-dev-pipeline/steps/step-01-init.md` (+80 lines)
|
||||
3. `super-dev-pipeline/steps/step-03-implement.md` (+120 lines)
|
||||
4. `super-dev-pipeline/steps/step-06-complete.md` (+100 lines)
|
||||
1. `batch-stories/instructions.md` (+150 lines)
|
||||
2. `story-full-pipeline/steps/step-01-init.md` (+80 lines)
|
||||
3. `story-full-pipeline/steps/step-03-implement.md` (+120 lines)
|
||||
4. `story-full-pipeline/steps/step-06-complete.md` (+100 lines)
|
||||
5. `dev-story/instructions.xml` (+60 lines)
|
||||
|
||||
**Total MODIFIED**: ~510 lines
|
||||
|
|
@ -1208,7 +1208,7 @@ $ /super-dev-pipeline story_key=2-5-auth
|
|||
|
||||
### Week 2-3
|
||||
|
||||
1. Integrate with batch-super-dev
|
||||
1. Integrate with batch-stories
|
||||
2. Add progress sync to dev-story
|
||||
3. Build PO agent + story creation workflow
|
||||
4. Test with 3-5 developers
|
||||
|
|
|
|||
|
|
@ -33,8 +33,8 @@ Replace trust-based workflow with enforcement-based:
|
|||
### 1. Auto-Fix Missing Prerequisites (Guardrail 1)
|
||||
|
||||
**Files Modified:**
|
||||
- `src/modules/bmm/workflows/4-implementation/super-dev-pipeline/workflow.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/batch-super-dev/workflow.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/story-full-pipeline/workflow.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/batch-stories/workflow.md`
|
||||
|
||||
**What Changed:**
|
||||
- Old: Block with error if story file or gap analysis missing
|
||||
|
|
@ -60,10 +60,10 @@ fi
|
|||
### 2. File-Based Completion Verification (Guardrail 2)
|
||||
|
||||
**Files Modified:**
|
||||
- `src/modules/bmm/workflows/4-implementation/super-dev-pipeline/agents/builder.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/super-dev-pipeline/agents/inspector.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/super-dev-pipeline/agents/reviewer.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/super-dev-pipeline/agents/fixer.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/story-full-pipeline/agents/builder.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/story-full-pipeline/agents/inspector.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/story-full-pipeline/agents/reviewer.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/story-full-pipeline/agents/fixer.md`
|
||||
|
||||
**What Changed:**
|
||||
- Agents now MUST create completion artifact: `{{story_key}}-{{agent}}.json`
|
||||
|
|
@ -93,7 +93,7 @@ fi
|
|||
### 3. Verification Gates Between Agents (Guardrail 4)
|
||||
|
||||
**Files Modified:**
|
||||
- `src/modules/bmm/workflows/4-implementation/super-dev-pipeline/workflow.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/story-full-pipeline/workflow.md`
|
||||
|
||||
**What Changed:**
|
||||
- Added verification step after Builder agent
|
||||
|
|
@ -126,8 +126,8 @@ done
|
|||
### 4. Orchestrator-Driven Reconciliation (Guardrail 2 cont.)
|
||||
|
||||
**Files Modified:**
|
||||
- `src/modules/bmm/workflows/4-implementation/super-dev-pipeline/workflow.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/batch-super-dev/workflow.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/story-full-pipeline/workflow.md`
|
||||
- `src/modules/bmm/workflows/4-implementation/batch-stories/workflow.md`
|
||||
|
||||
**What Changed:**
|
||||
- Orchestrator reads Fixer completion artifact
|
||||
|
|
@ -167,8 +167,8 @@ done
|
|||
|
||||
| File | Type | Lines Changed | Purpose |
|
||||
|------|------|---------------|---------|
|
||||
| super-dev-pipeline/workflow.md | Modified | ~100 | Add preconditions, verification gates, artifact-based reconciliation |
|
||||
| batch-super-dev/workflow.md | Modified | ~80 | Add preconditions, artifact-based reconciliation |
|
||||
| story-full-pipeline/workflow.md | Modified | ~100 | Add preconditions, verification gates, artifact-based reconciliation |
|
||||
| batch-stories/workflow.md | Modified | ~80 | Add preconditions, artifact-based reconciliation |
|
||||
| agents/builder.md | Modified | ~30 | Add completion artifact requirement |
|
||||
| agents/inspector.md | Modified | ~25 | Add completion artifact requirement |
|
||||
| agents/reviewer.md | Modified | ~30 | Add completion artifact requirement |
|
||||
|
|
@ -189,7 +189,7 @@ done
|
|||
rm docs/sprint-artifacts/test-story.md
|
||||
|
||||
# Run workflow
|
||||
/bmad_bmm_super-dev-pipeline test-story
|
||||
/bmad_bmm_story-full-pipeline test-story
|
||||
|
||||
# Expected: Workflow auto-creates story file and gap analysis
|
||||
# Expected: Implementation proceeds without manual intervention
|
||||
|
|
@ -208,7 +208,7 @@ rm docs/sprint-artifacts/test-story.md
|
|||
### Test 3: File-Based Reconciliation ✅
|
||||
```bash
|
||||
# Run complete workflow
|
||||
/bmad_bmm_super-dev-pipeline test-story
|
||||
/bmad_bmm_story-full-pipeline test-story
|
||||
|
||||
# After completion, verify:
|
||||
CHECKED=$(grep -c "^- \[x\]" docs/sprint-artifacts/test-story.md)
|
||||
|
|
@ -223,7 +223,7 @@ grep -A 10 "### Dev Agent Record" docs/sprint-artifacts/test-story.md
|
|||
### Test 4: Batch Sequential Processing ✅
|
||||
```bash
|
||||
# Run batch in sequential mode
|
||||
/bmad_bmm_batch-super-dev
|
||||
/bmad_bmm_batch-stories
|
||||
# Select: Sequential mode
|
||||
# Select: Multiple stories
|
||||
|
||||
|
|
|
|||
|
|
@ -75,7 +75,7 @@ Implemented Phase 2 of GSD-style refactoring: pattern extraction and explicit st
|
|||
|
||||
### 2. Explicit Step Enumeration
|
||||
|
||||
**Added to super-dev-pipeline/workflow.md:**
|
||||
**Added to story-full-pipeline/workflow.md:**
|
||||
|
||||
```markdown
|
||||
<verification_checklist>
|
||||
|
|
@ -154,7 +154,7 @@ Implemented Phase 2 of GSD-style refactoring: pattern extraction and explicit st
|
|||
| patterns/verification.md | Created | Independent verification |
|
||||
| patterns/security-checklist.md | Created | Security review checklist |
|
||||
| patterns/README.md | Created | Patterns documentation |
|
||||
| super-dev-pipeline/workflow.md | Modified | Add explicit step checklist |
|
||||
| story-full-pipeline/workflow.md | Modified | Add explicit step checklist |
|
||||
| gsd-style-guardrails-phase2.md | Created | Phase 2 summary (this file) |
|
||||
|
||||
**Total:**
|
||||
|
|
@ -239,7 +239,7 @@ When workflow runs:
|
|||
### Test 1: Pattern Resolution ✅
|
||||
```bash
|
||||
# Verify patterns are properly resolved
|
||||
cat _bmad/bmm/workflows/4-implementation/super-dev-pipeline/agents/builder.md
|
||||
cat _bmad/bmm/workflows/4-implementation/story-full-pipeline/agents/builder.md
|
||||
|
||||
# Expected: Pattern content inlined in compiled agent
|
||||
# Expected: No @patterns/ references remain
|
||||
|
|
@ -248,7 +248,7 @@ cat _bmad/bmm/workflows/4-implementation/super-dev-pipeline/agents/builder.md
|
|||
### Test 2: Step Enumeration Visible ✅
|
||||
```bash
|
||||
# Run workflow
|
||||
/bmad_bmm_super-dev-pipeline test-story
|
||||
/bmad_bmm_story-full-pipeline test-story
|
||||
|
||||
# Expected: User sees "Step 1.1: Builder agent spawned"
|
||||
# Expected: User sees "Step 1.2: Builder creates completion artifact"
|
||||
|
|
@ -264,7 +264,7 @@ echo "New quality standard" >> patterns/hospital-grade.md
|
|||
bmad install
|
||||
|
||||
# Run workflow
|
||||
/bmad_bmm_super-dev-pipeline test-story
|
||||
/bmad_bmm_story-full-pipeline test-story
|
||||
|
||||
# Expected: All agents receive updated pattern
|
||||
```
|
||||
|
|
|
|||
|
|
@ -73,7 +73,7 @@ Build it, one story at a time. All implementation workflows use a unified GSD-st
|
|||
| Workflow | Purpose | Produces |
|
||||
| -------------------- | ------------------------------------------ | ---------------------------- |
|
||||
| `super-dev-story` | Dev + validation + review + push pipeline | Production-ready code |
|
||||
| `batch-super-dev` | Parallel execution of multiple stories | Multiple stories completed |
|
||||
| `batch-stories` | Parallel execution of multiple stories | Multiple stories completed |
|
||||
| `push-all` | Safe git staging/commit/push with checks | Committed and pushed changes |
|
||||
|
||||
### Maintenance & Recovery
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Agent Limitations in Batch Mode
|
||||
|
||||
**CRITICAL:** Agents running in batch-super-dev have specific limitations. Understanding these prevents wasted time and sets correct expectations.
|
||||
**CRITICAL:** Agents running in batch-stories have specific limitations. Understanding these prevents wasted time and sets correct expectations.
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -93,7 +93,7 @@
|
|||
|
||||
## Pre-Batch Validation Checklist
|
||||
|
||||
**Before running /batch-super-dev, verify ALL selected stories:**
|
||||
**Before running /batch-stories, verify ALL selected stories:**
|
||||
|
||||
```bash
|
||||
# 1. Check story files exist
|
||||
|
|
@ -121,7 +121,7 @@ done
|
|||
**If any checks fail:**
|
||||
1. Regenerate those stories: `/create-story-with-gap-analysis`
|
||||
2. Validate again
|
||||
3. THEN run batch-super-dev
|
||||
3. THEN run batch-stories
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -150,7 +150,7 @@ done
|
|||
**What it means:** Agent tried to create story but couldn't
|
||||
**Is this a bug?** ❌ NO - Agents can't create stories
|
||||
**What to do:**
|
||||
- Exit batch-super-dev
|
||||
- Exit batch-stories
|
||||
- Manually run /create-story-with-gap-analysis
|
||||
- Re-run batch after story created
|
||||
|
||||
|
|
@ -165,7 +165,7 @@ done
|
|||
1. Plan epic → Identify stories → Create list
|
||||
2. Generate stories: /create-story-with-gap-analysis (1-2 days)
|
||||
3. Validate stories: ./scripts/validate-all-stories.sh
|
||||
4. Execute stories: /batch-super-dev (parallel, fast)
|
||||
4. Execute stories: /batch-stories (parallel, fast)
|
||||
```
|
||||
|
||||
### ✅ DO: Use Small Batches for Mixed Complexity
|
||||
|
|
@ -183,7 +183,7 @@ done
|
|||
**Why it fails:**
|
||||
```
|
||||
1. Create 20 skeleton files with just widget lists
|
||||
2. Run /batch-super-dev
|
||||
2. Run /batch-stories
|
||||
3. Expect agents to regenerate them
|
||||
→ FAILS: Agents can't invoke /create-story workflow
|
||||
```
|
||||
|
|
@ -193,7 +193,7 @@ done
|
|||
**Why it fails:**
|
||||
```
|
||||
1. 10 proper BMAD stories + 10 skeletons
|
||||
2. Run /batch-super-dev
|
||||
2. Run /batch-stories
|
||||
3. Expect batch to handle both
|
||||
→ RESULT: 10 execute, 10 skipped (confusing)
|
||||
```
|
||||
|
|
@ -9,9 +9,9 @@
|
|||
|
||||
## Critical Prerequisites
|
||||
|
||||
> **⚠️ IMPORTANT: Read before running batch-super-dev!**
|
||||
> **⚠️ IMPORTANT: Read before running batch-stories!**
|
||||
|
||||
**BEFORE running batch-super-dev:**
|
||||
**BEFORE running batch-stories:**
|
||||
|
||||
### ✅ 1. All stories must be properly generated
|
||||
|
||||
|
|
@ -48,13 +48,13 @@ Required sections:
|
|||
**What you might try:**
|
||||
```
|
||||
1. Create 20 skeleton story files (just headers + widget lists)
|
||||
2. Run /batch-super-dev
|
||||
2. Run /batch-stories
|
||||
3. Expect agents to regenerate them
|
||||
```
|
||||
|
||||
**What happens:**
|
||||
- Agents identify stories are incomplete
|
||||
- Agents correctly halt per super-dev-pipeline validation
|
||||
- Agents correctly halt per story-full-pipeline validation
|
||||
- Stories get skipped (not regenerated)
|
||||
- You waste time
|
||||
|
||||
|
|
@ -67,7 +67,7 @@ Required sections:
|
|||
./scripts/validate-all-stories.sh
|
||||
|
||||
# 3. Execute (4-8 hours, parallel autonomous)
|
||||
/batch-super-dev
|
||||
/batch-stories
|
||||
```
|
||||
|
||||
See: `AGENT-LIMITATIONS.md` for full documentation on what agents can and cannot do.
|
||||
|
|
@ -76,7 +76,7 @@ See: `AGENT-LIMITATIONS.md` for full documentation on what agents can and cannot
|
|||
|
||||
## Overview
|
||||
|
||||
Interactive batch workflow for processing multiple `ready-for-dev` stories sequentially or in parallel using the super-dev-pipeline with full quality gates.
|
||||
Interactive batch workflow for processing multiple `ready-for-dev` stories sequentially or in parallel using the story-full-pipeline with full quality gates.
|
||||
|
||||
**New in v1.2.0:** Smart Story Validation & Auto-Creation - validates story files, creates missing stories, regenerates invalid ones automatically.
|
||||
**New in v1.1.0:** Smart Story Reconciliation - automatically verifies story accuracy after each implementation.
|
||||
|
|
@ -107,7 +107,7 @@ Interactive batch workflow for processing multiple `ready-for-dev` stories seque
|
|||
- **Parallel:** Spawn Task agents to process stories concurrently (faster, autonomous)
|
||||
- Configurable parallelism: 2, 4, or all stories at once
|
||||
|
||||
4. **Full Quality Gates** (from super-dev-pipeline)
|
||||
4. **Full Quality Gates** (from story-full-pipeline)
|
||||
- Pre-gap analysis (validate story completeness)
|
||||
- Test-driven implementation
|
||||
- Post-validation (verify requirements met)
|
||||
|
|
@ -150,7 +150,7 @@ Before v1.2.0:
|
|||
```
|
||||
User: "Process stories 3.1, 3.2, 3.3, 3.4"
|
||||
Workflow: "Story 3.3 file missing - please create it first"
|
||||
User: Ctrl+C → /create-story → /batch-super-dev again
|
||||
User: Ctrl+C → /create-story → /batch-stories again
|
||||
```
|
||||
|
||||
After v1.2.0:
|
||||
|
|
@ -232,7 +232,7 @@ validation:
|
|||
### Example Session (v1.2.0)
|
||||
|
||||
```
|
||||
🤖 /batch-super-dev
|
||||
🤖 /batch-stories
|
||||
|
||||
📊 Ready-for-Dev Stories (5)
|
||||
|
||||
|
|
@ -398,7 +398,7 @@ sprint-status.yaml: done
|
|||
|
||||
```bash
|
||||
# Process all ready-for-dev stories
|
||||
/batch-super-dev
|
||||
/batch-stories
|
||||
|
||||
# Follow prompts:
|
||||
# 1. See list of ready stories
|
||||
|
|
@ -413,7 +413,7 @@ sprint-status.yaml: done
|
|||
|
||||
```bash
|
||||
# Only process Epic 3 stories
|
||||
/batch-super-dev filter_by_epic=3
|
||||
/batch-stories filter_by_epic=3
|
||||
```
|
||||
|
||||
### Selection Syntax
|
||||
|
|
@ -444,7 +444,7 @@ All: all (processes all ready-for-dev stories)
|
|||
|
||||
## Workflow Configuration
|
||||
|
||||
**File:** `_bmad/bmm/workflows/4-implementation/batch-super-dev/workflow.yaml`
|
||||
**File:** `_bmad/bmm/workflows/4-implementation/batch-stories/workflow.yaml`
|
||||
|
||||
### Key Settings
|
||||
|
||||
|
|
@ -503,7 +503,7 @@ reconciliation:
|
|||
### 4. Process Stories
|
||||
**Sequential Mode:**
|
||||
- For each selected story:
|
||||
- Invoke super-dev-pipeline
|
||||
- Invoke story-full-pipeline
|
||||
- Execute reconciliation (Step 4.5)
|
||||
- Report results
|
||||
- Pause between stories
|
||||
|
|
@ -547,7 +547,7 @@ See: `step-4.5-reconcile-story-status.md` for detailed algorithm
|
|||
|
||||
### Batch Log
|
||||
|
||||
**Location:** `docs/sprint-artifacts/batch-super-dev-{date}.log`
|
||||
**Location:** `docs/sprint-artifacts/batch-stories-{date}.log`
|
||||
|
||||
**Contains:**
|
||||
- Start/end timestamps
|
||||
|
|
@ -628,7 +628,7 @@ See: `step-4.5-reconcile-story-status.md` for detailed algorithm
|
|||
**Fix:**
|
||||
1. Review listed stories manually
|
||||
2. Check Dev Agent Record has all required sections
|
||||
3. Re-run super-dev-pipeline for problematic stories
|
||||
3. Re-run story-full-pipeline for problematic stories
|
||||
4. Manually reconcile checkboxes if needed
|
||||
|
||||
### Parallel Mode Hangs
|
||||
|
|
@ -713,24 +713,24 @@ See: `step-4.5-reconcile-story-status.md` for detailed algorithm
|
|||
- Initial release
|
||||
- Interactive story selector
|
||||
- Sequential and parallel execution modes
|
||||
- Integration with super-dev-pipeline
|
||||
- Integration with story-full-pipeline
|
||||
- Batch summary and logging
|
||||
|
||||
---
|
||||
|
||||
## Related Workflows
|
||||
|
||||
- **super-dev-pipeline:** Individual story implementation (invoked by batch-super-dev)
|
||||
- **story-full-pipeline:** Individual story implementation (invoked by batch-stories)
|
||||
- **create-story-with-gap-analysis:** Create new stories with codebase scan
|
||||
- **sprint-status:** View/update sprint status
|
||||
- **multi-agent-review:** Standalone code review (part of super-dev-pipeline)
|
||||
- **multi-agent-review:** Standalone code review (part of story-full-pipeline)
|
||||
|
||||
---
|
||||
|
||||
## Support
|
||||
|
||||
**Questions or Issues:**
|
||||
- Check workflow logs: `docs/sprint-artifacts/batch-super-dev-*.log`
|
||||
- Check workflow logs: `docs/sprint-artifacts/batch-stories-*.log`
|
||||
- Review reconciliation step: `step-4.5-reconcile-story-status.md`
|
||||
- Check story file format: Ensure 12-section BMAD format
|
||||
- Verify Dev Agent Record populated: Required for reconciliation
|
||||
|
|
@ -81,7 +81,7 @@ This workflow requires:
|
|||
```
|
||||
Must show: "✅ All 12 sections present"
|
||||
|
||||
4. **Re-run batch-super-dev:**
|
||||
4. **Re-run batch-stories:**
|
||||
- Story will now be properly formatted
|
||||
- Can be executed in next batch run
|
||||
|
||||
|
|
@ -132,7 +132,7 @@ This workflow requires:
|
|||
|
||||
**After completing these actions:**
|
||||
1. Validate all stories: ./scripts/validate-all-stories.sh
|
||||
2. Re-run batch-super-dev for these stories
|
||||
2. Re-run batch-stories for these stories
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
</output>
|
||||
</check>
|
||||
|
|
@ -220,14 +220,14 @@ fi
|
|||
|
||||
## Documentation Update
|
||||
|
||||
**Add to:** `_bmad/bmm/workflows/4-implementation/batch-super-dev/README.md`
|
||||
**Add to:** `_bmad/bmm/workflows/4-implementation/batch-stories/README.md`
|
||||
|
||||
```markdown
|
||||
# Batch Super-Dev Workflow
|
||||
|
||||
## Critical Prerequisites
|
||||
|
||||
**BEFORE running batch-super-dev:**
|
||||
**BEFORE running batch-stories:**
|
||||
|
||||
1. ✅ **All stories must be properly generated**
|
||||
- Run: `/create-story-with-gap-analysis` for each story
|
||||
|
|
@ -252,13 +252,13 @@ fi
|
|||
**What you might try:**
|
||||
```
|
||||
1. Create 20 skeleton story files (just headers + widget lists)
|
||||
2. Run /batch-super-dev
|
||||
2. Run /batch-stories
|
||||
3. Expect agents to regenerate them
|
||||
```
|
||||
|
||||
**What happens:**
|
||||
- Agents identify stories are incomplete
|
||||
- Agents correctly halt per super-dev-pipeline validation
|
||||
- Agents correctly halt per story-full-pipeline validation
|
||||
- Stories get skipped (not regenerated)
|
||||
- You waste time
|
||||
|
||||
|
|
@ -270,7 +270,7 @@ fi
|
|||
**Solution:**
|
||||
- Generate ALL stories manually FIRST: /create-story-with-gap-analysis
|
||||
- Validate: ./scripts/validate-all-stories.sh
|
||||
- THEN run batch: /batch-super-dev
|
||||
- THEN run batch: /batch-stories
|
||||
|
||||
### ❌ Mixed Story Quality
|
||||
|
||||
|
|
@ -301,7 +301,7 @@ done
|
|||
./scripts/validate-all-stories.sh
|
||||
|
||||
# 3. Execute (4-8 hours, parallel autonomous)
|
||||
/batch-super-dev
|
||||
/batch-stories
|
||||
# Select all 5 stories
|
||||
# Choose 2-4 agents parallel
|
||||
|
||||
|
|
@ -325,13 +325,13 @@ done
|
|||
|
||||
**To apply these improvements:**
|
||||
|
||||
- [ ] Update `batch-super-dev/instructions.md` Step 2.5 (lines 82-99)
|
||||
- [ ] Add `batch-super-dev/AGENT-LIMITATIONS.md` (new file)
|
||||
- [ ] Add `batch-super-dev/BATCH-BEST-PRACTICES.md` (new file)
|
||||
- [ ] Update `batch-super-dev/README.md` with prerequisites
|
||||
- [ ] Update `batch-stories/instructions.md` Step 2.5 (lines 82-99)
|
||||
- [ ] Add `batch-stories/AGENT-LIMITATIONS.md` (new file)
|
||||
- [ ] Add `batch-stories/BATCH-BEST-PRACTICES.md` (new file)
|
||||
- [ ] Update `batch-stories/README.md` with prerequisites
|
||||
- [ ] Create `scripts/validate-all-stories.sh` (new script)
|
||||
- [ ] Add manual actions tracking to Step 5 summary
|
||||
- [ ] Update super-dev-pipeline Step 1.4.5 with agent guidance
|
||||
- [ ] Update story-full-pipeline Step 1.4.5 with agent guidance
|
||||
|
||||
**Testing:**
|
||||
- Try batch with mixed story quality → Should skip skeletons gracefully
|
||||
|
|
@ -1,7 +1,7 @@
|
|||
# Step 4.5: Story Reconciliation (Orchestrator-Driven)
|
||||
|
||||
**Version:** 2.1.0
|
||||
**Execute:** AFTER super-dev-pipeline completes, BEFORE marking story done
|
||||
**Execute:** AFTER story-full-pipeline completes, BEFORE marking story done
|
||||
**Who:** Orchestrator (YOU) - not an agent
|
||||
|
||||
---
|
||||
|
|
@ -1,7 +1,7 @@
|
|||
# Batch Super-Dev v3.0 - Unified Workflow
|
||||
|
||||
<purpose>
|
||||
Interactive story selector for batch implementation. Scan codebase for gaps, select stories, process with super-dev-pipeline, reconcile results.
|
||||
Interactive story selector for batch implementation. Scan codebase for gaps, select stories, process with story-full-pipeline, reconcile results.
|
||||
|
||||
**AKA:** "Mend the Gap" - Mind the gap between story requirements and reality, then mend it.
|
||||
</purpose>
|
||||
|
|
@ -18,7 +18,7 @@ Orchestrator coordinates. Agents do implementation. Orchestrator does reconcilia
|
|||
</philosophy>
|
||||
|
||||
<config>
|
||||
name: batch-super-dev
|
||||
name: batch-stories
|
||||
version: 3.1.0
|
||||
|
||||
modes:
|
||||
|
|
@ -37,7 +37,7 @@ defaults:
|
|||
<execution_context>
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/agent-completion.md
|
||||
@super-dev-pipeline/workflow.md
|
||||
@story-full-pipeline/workflow.md
|
||||
</execution_context>
|
||||
|
||||
<process>
|
||||
|
|
@ -203,16 +203,16 @@ If missing, auto-create using greenfield workflow:
|
|||
echo "✅ Prerequisites satisfied"
|
||||
```
|
||||
|
||||
**Step B: Invoke super-dev-pipeline**
|
||||
**Step B: Invoke story-full-pipeline**
|
||||
|
||||
Use super-dev-pipeline workflow with:
|
||||
Use story-full-pipeline workflow with:
|
||||
- mode: batch
|
||||
- story_key: {{story_key}}
|
||||
- complexity_level: {{complexity}}
|
||||
|
||||
**Step C: Reconcile Using Completion Artifacts (orchestrator does this directly)**
|
||||
|
||||
After super-dev-pipeline completes:
|
||||
After story-full-pipeline completes:
|
||||
|
||||
**C1. Load Fixer completion artifact:**
|
||||
```bash
|
||||
|
|
@ -294,10 +294,10 @@ Task({
|
|||
subagent_type: "general-purpose",
|
||||
description: "Implement {{story_key}}",
|
||||
prompt: `
|
||||
Execute super-dev-pipeline for story {{story_key}}.
|
||||
Execute story-full-pipeline for story {{story_key}}.
|
||||
|
||||
<execution_context>
|
||||
@super-dev-pipeline/workflow.md
|
||||
@story-full-pipeline/workflow.md
|
||||
</execution_context>
|
||||
|
||||
<context>
|
||||
|
|
@ -1,5 +1,5 @@
|
|||
name: batch-super-dev
|
||||
description: "Interactive batch selector for super-dev-pipeline with complexity-based routing. Micro stories get lightweight path, standard stories get full pipeline, complex stories get enhanced validation."
|
||||
name: batch-stories
|
||||
description: "Interactive batch selector for story-full-pipeline with complexity-based routing. Micro stories get lightweight path, standard stories get full pipeline, complex stories get enhanced validation."
|
||||
author: "BMad"
|
||||
version: "1.3.0"
|
||||
|
||||
|
|
@ -11,12 +11,12 @@ communication_language: "{config_source}:communication_language"
|
|||
date: system-generated
|
||||
|
||||
# Workflow paths
|
||||
installed_path: "{project-root}/_bmad/bmm/workflows/4-implementation/batch-super-dev"
|
||||
installed_path: "{project-root}/_bmad/bmm/workflows/4-implementation/batch-stories"
|
||||
instructions: "{installed_path}/instructions.md"
|
||||
|
||||
# State management
|
||||
sprint_status: "{sprint_artifacts}/sprint-status.yaml"
|
||||
batch_log: "{sprint_artifacts}/batch-super-dev-{date}.log"
|
||||
batch_log: "{sprint_artifacts}/batch-stories-{date}.log"
|
||||
|
||||
# Variables
|
||||
filter_by_epic: "" # Optional: Filter stories by epic number (e.g., "3" for only Epic 3 stories)
|
||||
|
|
@ -26,7 +26,7 @@ pause_between_stories: 5 # Seconds to pause between stories (allows monitoring,
|
|||
# Super-dev-pipeline invocation settings
|
||||
super_dev_settings:
|
||||
mode: "batch" # Always use batch mode for autonomous execution
|
||||
workflow_path: "{project-root}/_bmad/bmm/workflows/4-implementation/super-dev-pipeline"
|
||||
workflow_path: "{project-root}/_bmad/bmm/workflows/4-implementation/story-full-pipeline"
|
||||
|
||||
# Story validation settings (NEW in v1.2.0)
|
||||
validation:
|
||||
|
|
@ -228,7 +228,7 @@ Ready for implementation.
|
|||
|
||||
Next Steps:
|
||||
1. Review story for accuracy
|
||||
2. Use /story-pipeline or /super-dev-pipeline to implement
|
||||
2. Use /story-dev-only or /story-full-pipeline to implement
|
||||
3. All context loaded and ready
|
||||
|
||||
[N] Create next story
|
||||
|
|
|
|||
|
|
@ -19,9 +19,9 @@ name: multi-agent-review
|
|||
version: 3.0.0
|
||||
|
||||
agent_selection:
|
||||
micro: {count: 2, agents: [security, code_quality]}
|
||||
standard: {count: 4, agents: [security, code_quality, architecture, testing]}
|
||||
complex: {count: 6, agents: [security, code_quality, architecture, testing, performance, domain_expert]}
|
||||
micro: {count: 1, agents: [security]}
|
||||
standard: {count: 2, agents: [security, code_quality]}
|
||||
complex: {count: 3, agents: [security, code_quality, architecture]}
|
||||
|
||||
available_agents:
|
||||
security: "Identifies vulnerabilities and security risks"
|
||||
|
|
@ -41,21 +41,40 @@ available_agents:
|
|||
<process>
|
||||
|
||||
<step name="determine_agent_count" priority="first">
|
||||
**Select agents based on complexity**
|
||||
**Select agents based on override or complexity**
|
||||
|
||||
```
|
||||
If complexity_level == "micro":
|
||||
agents = ["security", "code_quality"]
|
||||
Display: 🔍 MICRO Review (2 agents)
|
||||
# Priority 1: Check for explicit override
|
||||
If override_agent_count is provided (not null):
|
||||
agent_count = min(override_agent_count, 6) # Cap at 6 max
|
||||
Select top N agents based on changed code patterns
|
||||
Display: 🔧 CUSTOM Review ({{agent_count}} agents)
|
||||
|
||||
# Priority 2: Use complexity-based default
|
||||
Else if complexity_level == "micro":
|
||||
agent_count = 1
|
||||
agents = ["security"]
|
||||
Display: 🔍 MICRO Review (1 agent)
|
||||
|
||||
Else if complexity_level == "standard":
|
||||
agents = ["security", "code_quality", "architecture", "testing"]
|
||||
Display: 📋 STANDARD Review (4 agents)
|
||||
agent_count = 2
|
||||
agents = ["security", "code_quality"]
|
||||
Display: 📋 STANDARD Review (2 agents)
|
||||
|
||||
Else if complexity_level == "complex":
|
||||
agents = ALL 6 agents
|
||||
Display: 🔬 COMPLEX Review (6 agents)
|
||||
agent_count = 3
|
||||
agents = ["security", "code_quality", "architecture"]
|
||||
Display: 🔬 COMPLEX Review (3 agents)
|
||||
```
|
||||
|
||||
**Agent Selection Priority:**
|
||||
1. Security (always first)
|
||||
2. Code Quality (always second)
|
||||
3-6. Selected based on code patterns:
|
||||
- Architecture (for structural changes)
|
||||
- Testing (for test coverage)
|
||||
- Performance (for optimization)
|
||||
- Domain Expert (for business logic)
|
||||
</step>
|
||||
|
||||
<step name="load_story_context">
|
||||
|
|
@ -183,6 +202,28 @@ If only LOW/INFO findings:
|
|||
- Micro stories (≤3 tasks)
|
||||
- Standard stories with simple changes
|
||||
- Stories that passed adversarial review cleanly
|
||||
|
||||
**Usage Examples:**
|
||||
|
||||
```bash
|
||||
# Default: Use complexity-based agent count
|
||||
/bmad_bmm_multi-agent-review 28-1-volunteer-role-permissions
|
||||
|
||||
# Override: Force specific count (token-conscious)
|
||||
/bmad_bmm_multi-agent-review 28-2-volunteer-profile --count 2
|
||||
|
||||
# Complex story but budget-conscious
|
||||
/bmad_bmm_multi-agent-review 28-3-volunteer-opportunities --count 3
|
||||
|
||||
# Skip review entirely (micro story)
|
||||
/bmad_bmm_multi-agent-review 28-4-tiny-fix --count 0
|
||||
```
|
||||
|
||||
**Parameter:**
|
||||
- `--count N` (optional): Override complexity-based count
|
||||
- Range: 0-6 (0 = skip review)
|
||||
- Default: null (uses complexity_level)
|
||||
- Capped at 6 maximum for safety
|
||||
</integration>
|
||||
|
||||
<failure_handling>
|
||||
|
|
|
|||
|
|
@ -17,29 +17,30 @@ instructions: "{installed_path}/instructions.md"
|
|||
story_id: "{story_id}" # Required
|
||||
story_file: "{sprint_artifacts}/story-{story_id}.md"
|
||||
base_branch: "main" # Optional: branch to compare against
|
||||
complexity_level: "standard" # micro | standard | complex (passed from super-dev-pipeline)
|
||||
complexity_level: "standard" # micro | standard | complex (passed from story-full-pipeline)
|
||||
override_agent_count: null # Optional: override complexity-based count (1-6, null = use complexity_level)
|
||||
|
||||
# Complexity-based agent selection (NEW v1.0.0)
|
||||
# Cost-effective review depth based on story RISK and technical complexity
|
||||
# Complexity determined by batch-super-dev based on: risk keywords, architectural impact, security concerns
|
||||
# Complexity determined by batch-stories based on: risk keywords, architectural impact, security concerns
|
||||
complexity_routing:
|
||||
micro:
|
||||
agent_count: 2
|
||||
agents: ["security", "code_quality"]
|
||||
agent_count: 1
|
||||
agents: ["security"]
|
||||
description: "Quick sanity check for low-risk stories"
|
||||
examples: ["UI tweaks", "text changes", "simple CRUD", "documentation"]
|
||||
cost_multiplier: 1x
|
||||
|
||||
standard:
|
||||
agent_count: 4
|
||||
agents: ["security", "code_quality", "architecture", "testing"]
|
||||
agent_count: 2
|
||||
agents: ["security", "code_quality"]
|
||||
description: "Balanced multi-perspective review for medium-risk changes"
|
||||
examples: ["API endpoints", "business logic", "data validation", "component refactors"]
|
||||
cost_multiplier: 2x
|
||||
|
||||
complex:
|
||||
agent_count: 6
|
||||
agents: ["security", "code_quality", "architecture", "testing", "performance", "domain_expert"]
|
||||
agent_count: 3
|
||||
agents: ["security", "code_quality", "architecture"]
|
||||
description: "Comprehensive review for high-risk/high-complexity changes"
|
||||
examples: ["auth/security", "payments", "data migration", "architecture changes", "performance-critical", "complex algorithms"]
|
||||
cost_multiplier: 3x
|
||||
|
|
|
|||
|
|
@ -101,7 +101,7 @@ Human-in-the-loop with approval at each step:
|
|||
bmad build 1-4
|
||||
|
||||
# Or invoke workflow directly
|
||||
claude -p "Load and execute: _bmad/bmm/workflows/4-implementation/story-pipeline/workflow.md
|
||||
claude -p "Load and execute: _bmad/bmm/workflows/4-implementation/story-dev-only/workflow.md
|
||||
Story: 1-4"
|
||||
```
|
||||
|
||||
|
|
@ -121,7 +121,7 @@ Unattended execution for trusted stories:
|
|||
bmad build 1-4 --batch
|
||||
|
||||
# Or use batch runner directly
|
||||
./_bmad/bmm/workflows/4-implementation/story-pipeline/batch-runner.sh 1-4
|
||||
./_bmad/bmm/workflows/4-implementation/story-dev-only/batch-runner.sh 1-4
|
||||
```
|
||||
|
||||
Batch mode:
|
||||
|
|
@ -148,7 +148,7 @@ Resume automatically:
|
|||
## Directory Structure
|
||||
|
||||
```
|
||||
story-pipeline/
|
||||
story-dev-only/
|
||||
├── workflow.yaml # Configuration, agent mapping, quality gates
|
||||
├── workflow.md # Interactive mode orchestration
|
||||
├── batch-runner.sh # Batch mode runner script
|
||||
|
|
@ -178,7 +178,7 @@ story-pipeline/
|
|||
### workflow.yaml
|
||||
|
||||
```yaml
|
||||
name: story-pipeline
|
||||
name: story-dev-only
|
||||
version: "2.0"
|
||||
description: "Single-session story implementation with step-file loading"
|
||||
|
||||
|
|
@ -3,7 +3,7 @@ name: 'step-01-init'
|
|||
description: 'Initialize story pipeline: load context, detect mode, cache documents'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-01-init.md'
|
||||
|
|
@ -3,7 +3,7 @@ name: 'step-01b-resume'
|
|||
description: 'Resume pipeline from checkpoint after failure or interruption'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-01b-resume.md'
|
||||
|
|
@ -3,7 +3,7 @@ name: 'step-02-create-story'
|
|||
description: 'Create detailed story file from epic definition with research'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-02-create-story.md'
|
||||
|
|
@ -3,7 +3,7 @@ name: 'step-03-validate-story'
|
|||
description: 'Adversarial validation of story completeness and quality'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-03-validate-story.md'
|
||||
|
|
@ -3,7 +3,7 @@ name: 'step-04-atdd'
|
|||
description: 'Generate failing acceptance tests before implementation (RED phase)'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-04-atdd.md'
|
||||
|
|
@ -3,7 +3,7 @@ name: 'step-05-implement'
|
|||
description: 'Implement story to make tests pass (GREEN phase)'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-05-implement.md'
|
||||
|
|
@ -3,7 +3,7 @@ name: 'step-05b-post-validation'
|
|||
description: 'Verify completed tasks against codebase reality (catch false positives)'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-05b-post-validation.md'
|
||||
|
|
@ -3,7 +3,7 @@ name: 'step-06-code-review'
|
|||
description: 'Adversarial code review finding 3-10 specific issues'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-06-code-review.md'
|
||||
|
|
@ -3,7 +3,7 @@ name: 'step-07-complete'
|
|||
description: 'Update sprint status and create git commit'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-07-complete.md'
|
||||
|
|
@ -89,7 +89,7 @@ stories:
|
|||
code_reviewed: true
|
||||
issues_found: {count}
|
||||
issues_fixed: {count}
|
||||
pipeline_version: "story-pipeline-v2.0"
|
||||
pipeline_version: "story-dev-only-v2.0"
|
||||
```
|
||||
|
||||
### 4. Stage Git Changes
|
||||
|
|
@ -119,7 +119,7 @@ feat(epic-{epic_num}): complete story {story_id}
|
|||
- Code reviewed: {issues_found} issues found and fixed
|
||||
|
||||
Story: {story_title}
|
||||
Pipeline: story-pipeline-v2.0
|
||||
Pipeline: story-dev-only-v2.0
|
||||
|
||||
🤖 Generated with BMAD Story Pipeline
|
||||
|
||||
|
|
@ -3,7 +3,7 @@ name: 'step-08-summary'
|
|||
description: 'Generate audit trail and pipeline summary report'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-08-summary.md'
|
||||
|
|
@ -48,7 +48,7 @@ Create: `{auditFile}`
|
|||
```yaml
|
||||
---
|
||||
audit_version: "1.0"
|
||||
pipeline: "story-pipeline-v2.0"
|
||||
pipeline: "story-dev-only-v2.0"
|
||||
story_id: "{story_id}"
|
||||
epic_num: {epic_num}
|
||||
---
|
||||
|
|
@ -1,5 +1,5 @@
|
|||
---
|
||||
name: story-pipeline
|
||||
name: story-dev-only
|
||||
description: Automated story development pipeline with token-efficient step-file architecture. Single-session orchestration replacing multiple Claude calls.
|
||||
web_bundle: true
|
||||
---
|
||||
|
|
@ -112,7 +112,7 @@ Load and cache these documents (read once, use across steps):
|
|||
### 4. First Step Execution
|
||||
|
||||
Load, read the full file and then execute:
|
||||
`{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline/steps/step-01-init.md`
|
||||
`{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only/steps/step-01-init.md`
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -1,5 +1,5 @@
|
|||
name: story-pipeline
|
||||
description: "Automated story development pipeline with token-efficient step-file architecture. Replaces separate Claude calls with single-session orchestration."
|
||||
name: story-dev-only
|
||||
description: "Basic TDD story development pipeline with token-efficient step-file architecture. Focuses on implementation without validation/review stages."
|
||||
author: "BMad + digital-bridge"
|
||||
version: "2.0.0"
|
||||
|
||||
|
|
@ -11,14 +11,14 @@ communication_language: "{config_source}:communication_language"
|
|||
date: system-generated
|
||||
|
||||
# Workflow paths
|
||||
installed_path: "{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline"
|
||||
installed_path: "{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only"
|
||||
steps_path: "{installed_path}/steps"
|
||||
templates_path: "{installed_path}/templates"
|
||||
checklists_path: "{installed_path}/checklists"
|
||||
|
||||
# State management
|
||||
state_file: "{sprint_artifacts}/pipeline-state-{{story_id}}.yaml"
|
||||
audit_trail: "{sprint_artifacts}/audit-{{story_id}}-{{date}}.yaml"
|
||||
state_file: "{sprint_artifacts}/story-dev-only-state-{{story_id}}.yaml"
|
||||
audit_trail: "{sprint_artifacts}/audit-story-dev-only-{{story_id}}-{{date}}.yaml"
|
||||
|
||||
# Workflow modes
|
||||
modes:
|
||||
|
|
@ -8,7 +8,7 @@
|
|||
|
||||
```bash
|
||||
# Run super-dev pipeline for a story
|
||||
/super-dev-pipeline story_key=17-10
|
||||
/story-full-pipeline story_key=17-10
|
||||
```
|
||||
|
||||
---
|
||||
|
|
@ -106,7 +106,7 @@ See `workflow.md` for complete architecture details.
|
|||
|
||||
**Directory Structure:**
|
||||
```
|
||||
super-dev-pipeline/
|
||||
story-full-pipeline/
|
||||
├── README.md (this file)
|
||||
├── workflow.yaml (configuration)
|
||||
├── workflow.md (complete documentation)
|
||||
|
|
@ -0,0 +1,215 @@
|
|||
# Super-Dev-Pipeline v3.1 - Token-Efficient Multi-Agent Pipeline
|
||||
|
||||
<purpose>
|
||||
Implement a story using parallel verification agents with Builder context reuse.
|
||||
Each agent has single responsibility. Builder fixes issues in its own context (50-70% token savings).
|
||||
Orchestrator handles bookkeeping (story file updates, verification).
|
||||
</purpose>
|
||||
|
||||
<philosophy>
|
||||
**Token-Efficient Multi-Agent Pipeline**
|
||||
|
||||
- Builder implements (creative, context preserved)
|
||||
- Inspector + Reviewers validate in parallel (verification, fresh context)
|
||||
- Builder fixes issues (creative, reuses context - 50-70% token savings)
|
||||
- Inspector re-checks (verification, quick check)
|
||||
- Orchestrator reconciles story file (mechanical)
|
||||
|
||||
**Key Innovation:** Resume Builder instead of spawning fresh Fixer.
|
||||
Builder already knows the codebase - just needs to fix specific issues.
|
||||
|
||||
Trust but verify. Fresh context for verification. Reuse context for fixes.
|
||||
</philosophy>
|
||||
|
||||
<config>
|
||||
name: story-full-pipeline
|
||||
version: 3.1.0
|
||||
execution_mode: multi_agent
|
||||
|
||||
phases:
|
||||
phase_1: Builder (saves agent_id)
|
||||
phase_2: [Inspector + N Reviewers] in parallel (N = 1/2/3 based on complexity)
|
||||
phase_3: Resume Builder with all findings (reuses context)
|
||||
phase_4: Inspector re-check (quick verification)
|
||||
phase_5: Orchestrator reconciliation
|
||||
|
||||
reviewer_counts:
|
||||
micro: 1 reviewer (security only)
|
||||
standard: 2 reviewers (security, performance)
|
||||
complex: 3 reviewers (security, performance, code quality)
|
||||
|
||||
token_efficiency:
|
||||
- Phase 2 agents spawn in parallel (same cost, faster)
|
||||
- Phase 3 resumes Builder (50-70% token savings vs fresh Fixer)
|
||||
- Phase 4 Inspector only (no full re-review)
|
||||
</config>
|
||||
|
||||
<execution_context>
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/agent-completion.md
|
||||
</execution_context>
|
||||
|
||||
<process>
|
||||
|
||||
<step name="load_story" priority="first">
|
||||
Load and validate the story file.
|
||||
|
||||
\`\`\`bash
|
||||
STORY_FILE="docs/sprint-artifacts/{{story_key}}.md"
|
||||
[ -f "$STORY_FILE" ] || { echo "ERROR: Story file not found"; exit 1; }
|
||||
\`\`\`
|
||||
|
||||
Use Read tool on the story file. Parse:
|
||||
- Complexity level (micro/standard/complex)
|
||||
- Task count
|
||||
- Acceptance criteria count
|
||||
|
||||
Determine which agents to spawn based on complexity routing.
|
||||
</step>
|
||||
|
||||
<step name="spawn_builder">
|
||||
**Phase 1: Builder Agent (Steps 1-4)**
|
||||
|
||||
\`\`\`
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔨 PHASE 1: BUILDER
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
\`\`\`
|
||||
|
||||
Spawn Builder agent and save agent_id for later resume.
|
||||
|
||||
**CRITICAL: Save Builder's agent_id for later resume**
|
||||
|
||||
\`\`\`
|
||||
BUILDER_AGENT_ID={{agent_id_from_task_result}}
|
||||
echo "Builder agent: $BUILDER_AGENT_ID"
|
||||
\`\`\`
|
||||
|
||||
Wait for completion. Parse structured output. Verify files exist.
|
||||
|
||||
If files missing or status FAILED: halt pipeline.
|
||||
</step>
|
||||
|
||||
<step name="spawn_verification_parallel">
|
||||
**Phase 2: Parallel Verification (Inspector + Reviewers)**
|
||||
|
||||
\`\`\`
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔍 PHASE 2: PARALLEL VERIFICATION
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
\`\`\`
|
||||
|
||||
**CRITICAL: Spawn ALL verification agents in ONE message (parallel execution)**
|
||||
|
||||
Determine reviewer count based on complexity:
|
||||
\`\`\`
|
||||
if complexity == "micro": REVIEWER_COUNT = 1
|
||||
if complexity == "standard": REVIEWER_COUNT = 2
|
||||
if complexity == "complex": REVIEWER_COUNT = 3
|
||||
\`\`\`
|
||||
|
||||
Spawn Inspector + N Reviewers in single message. Wait for ALL agents to complete. Collect findings.
|
||||
|
||||
Aggregate all findings from Inspector + Reviewers.
|
||||
</step>
|
||||
|
||||
<step name="resume_builder_with_findings">
|
||||
**Phase 3: Resume Builder with All Findings**
|
||||
|
||||
\`\`\`
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔧 PHASE 3: RESUME BUILDER (Fix Issues)
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
\`\`\`
|
||||
|
||||
**CRITICAL: Resume Builder agent (reuses context!)**
|
||||
|
||||
Use Task tool with `resume: "{{BUILDER_AGENT_ID}}"` parameter.
|
||||
|
||||
Builder receives all consolidated findings and fixes:
|
||||
1. ALL CRITICAL issues (security, blockers)
|
||||
2. ALL HIGH issues (bugs, logic errors)
|
||||
3. MEDIUM if quick (<30 min total)
|
||||
4. Skip LOW (gold-plating)
|
||||
5. Commit with descriptive message
|
||||
|
||||
Wait for completion. Parse commit hash and fix counts.
|
||||
</step>
|
||||
|
||||
<step name="inspector_recheck">
|
||||
**Phase 4: Quick Inspector Re-Check**
|
||||
|
||||
\`\`\`
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
✅ PHASE 4: RE-VERIFICATION
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
\`\`\`
|
||||
|
||||
Spawn Inspector only (not full review). Quick functional verification.
|
||||
|
||||
If FAIL: Resume Builder again with new issues.
|
||||
If PASS: Proceed to reconciliation.
|
||||
</step>
|
||||
|
||||
<step name="reconcile_story">
|
||||
**Phase 5: Orchestrator Reconciliation**
|
||||
|
||||
\`\`\`
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔧 PHASE 5: RECONCILIATION (Orchestrator)
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
\`\`\`
|
||||
|
||||
**YOU (orchestrator) do this directly. No agent spawn.**
|
||||
|
||||
1. Get what was built (git log, git diff)
|
||||
2. Read story file
|
||||
3. Check off completed tasks (Edit tool)
|
||||
4. Fill Dev Agent Record with pipeline details
|
||||
5. Verify updates (grep task checkboxes)
|
||||
6. Update sprint-status.yaml to "done"
|
||||
</step>
|
||||
|
||||
<step name="final_verification">
|
||||
**Final Quality Gate**
|
||||
|
||||
Verify:
|
||||
1. Git commit exists
|
||||
2. Story tasks checked (count > 0)
|
||||
3. Dev Agent Record filled
|
||||
4. Sprint status updated
|
||||
|
||||
If verification fails: fix using Edit, then re-verify.
|
||||
</step>
|
||||
|
||||
</process>
|
||||
|
||||
<failure_handling>
|
||||
**Builder fails:** Don't spawn verification. Report failure and halt.
|
||||
**Inspector fails (Phase 2):** Still run Reviewers in parallel, collect all findings together.
|
||||
**Inspector fails (Phase 4):** Resume Builder again with new issues (iterative fix loop).
|
||||
**Builder resume fails:** Report unfixed issues. Manual intervention needed.
|
||||
**Reconciliation fails:** Fix using Edit tool. Re-verify checkboxes.
|
||||
</failure_handling>
|
||||
|
||||
<complexity_routing>
|
||||
| Complexity | Pipeline | Reviewers | Total Phase 2 Agents |
|
||||
|------------|----------|-----------|---------------------|
|
||||
| micro | Builder → [Inspector + 1 Reviewer] → Resume Builder → Inspector recheck | 1 (security) | 2 agents |
|
||||
| standard | Builder → [Inspector + 2 Reviewers] → Resume Builder → Inspector recheck | 2 (security, performance) | 3 agents |
|
||||
| complex | Builder → [Inspector + 3 Reviewers] → Resume Builder → Inspector recheck | 3 (security, performance, quality) | 4 agents |
|
||||
|
||||
**Key Improvement:** All verification agents spawn in parallel (single message, faster execution).
|
||||
**Token Savings:** Builder resume in Phase 3 saves 50-70% tokens vs spawning fresh Fixer.
|
||||
</complexity_routing>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] Builder spawned and agent_id saved
|
||||
- [ ] All verification agents completed in parallel
|
||||
- [ ] Builder resumed with consolidated findings
|
||||
- [ ] Inspector recheck passed
|
||||
- [ ] Git commit exists for story
|
||||
- [ ] Story file has checked tasks (count > 0)
|
||||
- [ ] Dev Agent Record filled with all phases
|
||||
- [ ] Sprint status updated to "done"
|
||||
</success_criteria>
|
||||
|
|
@ -1,4 +1,4 @@
|
|||
name: super-dev-pipeline
|
||||
name: story-full-pipeline
|
||||
description: "Multi-agent pipeline with wave-based execution, independent validation, and adversarial code review (GSDMAD)"
|
||||
author: "BMAD Method + GSD"
|
||||
version: "2.0.0"
|
||||
|
|
@ -14,7 +14,7 @@ communication_language: "{config_source}:communication_language"
|
|||
date: system-generated
|
||||
|
||||
# Workflow paths
|
||||
installed_path: "{project-root}/_bmad/bmm/workflows/4-implementation/super-dev-pipeline"
|
||||
installed_path: "{project-root}/_bmad/bmm/workflows/4-implementation/story-full-pipeline"
|
||||
agents_path: "{installed_path}/agents"
|
||||
steps_path: "{installed_path}/steps"
|
||||
|
||||
|
|
@ -23,8 +23,8 @@ agent_history: "{sprint_artifacts}/agent-history.json"
|
|||
current_agent_id: "{sprint_artifacts}/current-agent-id.txt"
|
||||
|
||||
# State management
|
||||
state_file: "{sprint_artifacts}/super-dev-state-{{story_id}}.yaml"
|
||||
audit_trail: "{sprint_artifacts}/audit-super-dev-{{story_id}}-{{date}}.yaml"
|
||||
state_file: "{sprint_artifacts}/story-full-pipeline-state-{{story_id}}.yaml"
|
||||
audit_trail: "{sprint_artifacts}/audit-story-full-pipeline-{{story_id}}-{{date}}.yaml"
|
||||
|
||||
# Multi-agent configuration
|
||||
agents:
|
||||
|
|
@ -55,14 +55,15 @@ agents:
|
|||
trust_level: "high" # Wants to find problems
|
||||
timeout: 1800 # 30 minutes
|
||||
review_agent_count:
|
||||
micro: 2
|
||||
standard: 4
|
||||
complex: 6
|
||||
micro: 1 # Minimal review (1 agent)
|
||||
standard: 2 # Balanced review (2 agents)
|
||||
complex: 3 # Full review (3 agents)
|
||||
|
||||
fixer:
|
||||
description: "Issue resolution - fixes critical/high issues"
|
||||
steps: [8, 9]
|
||||
subagent_type: "general-purpose"
|
||||
resume_builder: true # IMPORTANT: Resume Builder agent instead of spawning fresh
|
||||
prompt_file: "{agents_path}/fixer.md"
|
||||
trust_level: "medium" # Incentive to minimize work
|
||||
timeout: 2400 # 40 minutes
|
||||
|
|
@ -118,6 +119,6 @@ final_verification:
|
|||
fallback_to_v1:
|
||||
enabled: true
|
||||
condition: "execution_mode == 'single_agent'"
|
||||
workflow: "{project-root}/_bmad/bmm/workflows/4-implementation/super-dev-pipeline"
|
||||
workflow: "{project-root}/_bmad/bmm/workflows/4-implementation/story-full-pipeline"
|
||||
|
||||
standalone: true
|
||||
|
|
@ -1,396 +0,0 @@
|
|||
# Super-Dev-Pipeline v3.0 - Unified Workflow
|
||||
|
||||
<purpose>
|
||||
Implement a story using 4 independent agents with orchestrator-driven reconciliation.
|
||||
Each agent has single responsibility. No agent validates its own work.
|
||||
Orchestrator handles bookkeeping (story file updates, verification).
|
||||
</purpose>
|
||||
|
||||
<philosophy>
|
||||
**Agents do creative work. Orchestrator does bookkeeping.**
|
||||
|
||||
- Builder implements (creative)
|
||||
- Inspector validates (verification)
|
||||
- Reviewer finds issues (adversarial)
|
||||
- Fixer resolves issues (creative)
|
||||
- Orchestrator reconciles story file (mechanical)
|
||||
|
||||
Trust but verify. Fresh context per phase. Adversarial review.
|
||||
</philosophy>
|
||||
|
||||
<config>
|
||||
name: super-dev-pipeline
|
||||
version: 3.0.0
|
||||
execution_mode: multi_agent
|
||||
|
||||
agents:
|
||||
builder: {steps: 1-4, trust: low, timeout: 60min}
|
||||
inspector: {steps: 5-6, trust: medium, fresh_context: true, timeout: 30min}
|
||||
reviewer: {steps: 7, trust: high, adversarial: true, timeout: 30min}
|
||||
fixer: {steps: 8-9, trust: medium, timeout: 40min}
|
||||
|
||||
complexity_routing:
|
||||
micro: {skip: [reviewer], description: "Low-risk stories"}
|
||||
standard: {skip: [], description: "Normal stories"}
|
||||
complex: {skip: [], enhanced_review: true, description: "High-risk stories"}
|
||||
</config>
|
||||
|
||||
<execution_context>
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/agent-completion.md
|
||||
</execution_context>
|
||||
|
||||
<process>
|
||||
|
||||
<step name="load_story" priority="first">
|
||||
Load and validate the story file.
|
||||
|
||||
```bash
|
||||
STORY_FILE="docs/sprint-artifacts/{{story_key}}.md"
|
||||
[ -f "$STORY_FILE" ] || { echo "ERROR: Story file not found"; exit 1; }
|
||||
```
|
||||
|
||||
Use Read tool on the story file. Parse:
|
||||
- Complexity level (micro/standard/complex)
|
||||
- Task count
|
||||
- Acceptance criteria count
|
||||
|
||||
Determine which agents to spawn based on complexity routing.
|
||||
</step>
|
||||
|
||||
<step name="spawn_builder">
|
||||
**Phase 1: Builder Agent (Steps 1-4)**
|
||||
|
||||
```
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔨 PHASE 1: BUILDER
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
|
||||
Spawn Builder agent:
|
||||
|
||||
```
|
||||
Task({
|
||||
subagent_type: "general-purpose",
|
||||
description: "Implement story {{story_key}}",
|
||||
prompt: `
|
||||
You are the BUILDER agent for story {{story_key}}.
|
||||
|
||||
<execution_context>
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/tdd.md
|
||||
@patterns/agent-completion.md
|
||||
</execution_context>
|
||||
|
||||
<context>
|
||||
Story: [inline story file content]
|
||||
</context>
|
||||
|
||||
<objective>
|
||||
Implement the story requirements:
|
||||
1. Load and understand requirements
|
||||
2. Analyze what exists vs needed
|
||||
3. Write tests first (TDD)
|
||||
4. Implement production code
|
||||
</objective>
|
||||
|
||||
<constraints>
|
||||
- DO NOT validate your own work
|
||||
- DO NOT review your code
|
||||
- DO NOT update story checkboxes
|
||||
- DO NOT commit changes
|
||||
</constraints>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] Tests written for all requirements
|
||||
- [ ] Production code implements tests
|
||||
- [ ] Return ## AGENT COMPLETE with file lists
|
||||
</success_criteria>
|
||||
`
|
||||
})
|
||||
```
|
||||
|
||||
**Wait for completion. Parse structured output.**
|
||||
|
||||
Verify files exist:
|
||||
```bash
|
||||
# For each file in "Files Created" and "Files Modified":
|
||||
[ -f "$file" ] || echo "MISSING: $file"
|
||||
```
|
||||
|
||||
If files missing or status FAILED: halt pipeline.
|
||||
</step>
|
||||
|
||||
<step name="spawn_inspector">
|
||||
**Phase 2: Inspector Agent (Steps 5-6)**
|
||||
|
||||
```
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔍 PHASE 2: INSPECTOR
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
|
||||
Spawn Inspector agent with **fresh context** (no Builder knowledge):
|
||||
|
||||
```
|
||||
Task({
|
||||
subagent_type: "general-purpose",
|
||||
description: "Validate story {{story_key}} implementation",
|
||||
prompt: `
|
||||
You are the INSPECTOR agent for story {{story_key}}.
|
||||
|
||||
<execution_context>
|
||||
@patterns/verification.md
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/agent-completion.md
|
||||
</execution_context>
|
||||
|
||||
<context>
|
||||
Story: [inline story file content]
|
||||
</context>
|
||||
|
||||
<objective>
|
||||
Independently verify the implementation:
|
||||
1. Verify files exist and have content
|
||||
2. Run type-check, lint, build
|
||||
3. Run tests yourself
|
||||
4. Give honest PASS/FAIL verdict
|
||||
</objective>
|
||||
|
||||
<constraints>
|
||||
- You have NO KNOWLEDGE of what Builder did
|
||||
- Run all checks yourself
|
||||
- Don't trust any claims
|
||||
</constraints>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] All files verified to exist
|
||||
- [ ] Type check passes (0 errors)
|
||||
- [ ] Lint passes (0 warnings)
|
||||
- [ ] Tests pass
|
||||
- [ ] Return ## AGENT COMPLETE with evidence
|
||||
</success_criteria>
|
||||
`
|
||||
})
|
||||
```
|
||||
|
||||
**Wait for completion. Parse verdict.**
|
||||
|
||||
If FAIL: halt pipeline, report specific failures.
|
||||
</step>
|
||||
|
||||
<step name="spawn_reviewer" if="complexity != micro">
|
||||
**Phase 3: Reviewer Agent (Step 7)**
|
||||
|
||||
```
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔎 PHASE 3: REVIEWER
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
|
||||
Spawn Reviewer agent with **adversarial stance**:
|
||||
|
||||
```
|
||||
Task({
|
||||
subagent_type: "general-purpose",
|
||||
description: "Review story {{story_key}} code",
|
||||
prompt: `
|
||||
You are the ADVERSARIAL REVIEWER for story {{story_key}}.
|
||||
|
||||
<execution_context>
|
||||
@patterns/security-checklist.md
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/agent-completion.md
|
||||
</execution_context>
|
||||
|
||||
<context>
|
||||
Story: [inline story file content]
|
||||
</context>
|
||||
|
||||
<objective>
|
||||
Find problems. Be critical. Look for:
|
||||
- Security vulnerabilities (CRITICAL)
|
||||
- Logic bugs and edge cases (HIGH)
|
||||
- Performance issues (MEDIUM)
|
||||
- Code style issues (LOW)
|
||||
</objective>
|
||||
|
||||
<constraints>
|
||||
- Your goal is to FIND ISSUES
|
||||
- Don't rubber-stamp
|
||||
- Be thorough
|
||||
</constraints>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] All new files reviewed
|
||||
- [ ] Security checks completed
|
||||
- [ ] Issues categorized by severity
|
||||
- [ ] Return ## AGENT COMPLETE with issue list
|
||||
</success_criteria>
|
||||
`
|
||||
})
|
||||
```
|
||||
|
||||
**Wait for completion. Parse issue counts.**
|
||||
</step>
|
||||
|
||||
<step name="spawn_fixer">
|
||||
**Phase 4: Fixer Agent (Steps 8-9)**
|
||||
|
||||
```
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔧 PHASE 4: FIXER
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
|
||||
Spawn Fixer agent:
|
||||
|
||||
```
|
||||
Task({
|
||||
subagent_type: "general-purpose",
|
||||
description: "Fix issues in story {{story_key}}",
|
||||
prompt: `
|
||||
You are the FIXER agent for story {{story_key}}.
|
||||
|
||||
<execution_context>
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/agent-completion.md
|
||||
</execution_context>
|
||||
|
||||
<context>
|
||||
Story: [inline story file content]
|
||||
Review issues: [inline reviewer findings]
|
||||
</context>
|
||||
|
||||
<objective>
|
||||
Fix CRITICAL and HIGH issues:
|
||||
1. Fix ALL CRITICAL issues (security)
|
||||
2. Fix ALL HIGH issues (bugs)
|
||||
3. Fix MEDIUM if time allows
|
||||
4. Skip LOW (gold-plating)
|
||||
5. Commit with descriptive message
|
||||
</objective>
|
||||
|
||||
<constraints>
|
||||
- DO NOT skip CRITICAL issues
|
||||
- DO NOT update story checkboxes (orchestrator does this)
|
||||
- DO NOT update sprint-status (orchestrator does this)
|
||||
</constraints>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] All CRITICAL fixed
|
||||
- [ ] All HIGH fixed
|
||||
- [ ] Tests still pass
|
||||
- [ ] Git commit created
|
||||
- [ ] Return ## AGENT COMPLETE with fix summary
|
||||
</success_criteria>
|
||||
`
|
||||
})
|
||||
```
|
||||
|
||||
**Wait for completion. Parse commit hash and fix counts.**
|
||||
</step>
|
||||
|
||||
<step name="reconcile_story">
|
||||
**Phase 5: Orchestrator Reconciliation**
|
||||
|
||||
```
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔧 PHASE 5: RECONCILIATION (Orchestrator)
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
|
||||
**YOU (orchestrator) do this directly. No agent spawn.**
|
||||
|
||||
**Step 5.1: Get what was built**
|
||||
```bash
|
||||
git log -3 --oneline | grep "{{story_key}}"
|
||||
git diff HEAD~1 --name-only | head -20
|
||||
```
|
||||
|
||||
**Step 5.2: Read story file**
|
||||
Use Read tool: `docs/sprint-artifacts/{{story_key}}.md`
|
||||
|
||||
**Step 5.3: Check off completed tasks**
|
||||
For each task related to files changed, use Edit tool:
|
||||
```
|
||||
old_string: "- [ ] Task description"
|
||||
new_string: "- [x] Task description"
|
||||
```
|
||||
|
||||
**Step 5.4: Fill Dev Agent Record**
|
||||
Use Edit tool to update Dev Agent Record section with:
|
||||
- Agent Model: Claude Sonnet 4 (multi-agent pipeline)
|
||||
- Implementation Date: {{date}}
|
||||
- Files Created/Modified: [list from git diff]
|
||||
- Tests Added: [count from Inspector]
|
||||
- Completion Notes: [brief summary]
|
||||
|
||||
**Step 5.5: Verify updates**
|
||||
```bash
|
||||
CHECKED=$(grep -c "^- \[x\]" docs/sprint-artifacts/{{story_key}}.md)
|
||||
if [ "$CHECKED" -eq 0 ]; then
|
||||
echo "❌ BLOCKER: Zero checked tasks"
|
||||
exit 1
|
||||
fi
|
||||
echo "✅ Verified: $CHECKED tasks checked"
|
||||
```
|
||||
|
||||
If verification fails: fix using Edit, then re-verify.
|
||||
</step>
|
||||
|
||||
<step name="final_verification">
|
||||
**Final Quality Gate**
|
||||
|
||||
```bash
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔍 FINAL VERIFICATION"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
# 1. Git commit exists
|
||||
git log --oneline -3 | grep "{{story_key}}" || { echo "❌ No commit"; exit 1; }
|
||||
echo "✅ Git commit found"
|
||||
|
||||
# 2. Story tasks checked
|
||||
CHECKED=$(grep -c "^- \[x\]" docs/sprint-artifacts/{{story_key}}.md)
|
||||
[ "$CHECKED" -gt 0 ] || { echo "❌ No tasks checked"; exit 1; }
|
||||
echo "✅ $CHECKED tasks checked"
|
||||
|
||||
# 3. Dev Agent Record filled
|
||||
grep -A 3 "### Dev Agent Record" docs/sprint-artifacts/{{story_key}}.md | grep -q "202" || { echo "❌ Record not filled"; exit 1; }
|
||||
echo "✅ Dev Agent Record filled"
|
||||
|
||||
echo ""
|
||||
echo "✅ STORY COMPLETE"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
```
|
||||
|
||||
**Update sprint-status.yaml:**
|
||||
Use Edit tool to change story status from `ready-for-dev` to `done`.
|
||||
</step>
|
||||
|
||||
</process>
|
||||
|
||||
<failure_handling>
|
||||
**Builder fails:** Don't spawn Inspector. Report failure.
|
||||
**Inspector fails:** Don't spawn Reviewer. Report specific failures.
|
||||
**Reviewer finds CRITICAL:** Fixer must fix (not optional).
|
||||
**Fixer fails:** Report unfixed issues. Manual intervention needed.
|
||||
**Reconciliation fails:** Fix using Edit tool. Re-verify.
|
||||
</failure_handling>
|
||||
|
||||
<complexity_routing>
|
||||
| Complexity | Agents | Notes |
|
||||
|------------|--------|-------|
|
||||
| micro | Builder → Inspector → Fixer | Skip Reviewer (low risk) |
|
||||
| standard | Builder → Inspector → Reviewer → Fixer | Full pipeline |
|
||||
| complex | Builder → Inspector → Reviewer (enhanced) → Fixer | Extra scrutiny |
|
||||
</complexity_routing>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] All agents completed successfully
|
||||
- [ ] Git commit exists for story
|
||||
- [ ] Story file has checked tasks (count > 0)
|
||||
- [ ] Dev Agent Record filled
|
||||
- [ ] Sprint status updated to "done"
|
||||
</success_criteria>
|
||||
|
|
@ -29,7 +29,7 @@ super_dev_settings:
|
|||
fail_on_critical_issues: true
|
||||
max_fix_iterations: 3
|
||||
|
||||
# Autonomous mode settings (passed from parent workflow like batch-super-dev)
|
||||
# Autonomous mode settings (passed from parent workflow like batch-stories)
|
||||
auto_accept_gap_analysis: false # When true, skip gap analysis approval prompt
|
||||
|
||||
standalone: true
|
||||
|
|
|
|||
|
|
@ -71,11 +71,11 @@ Instead of main agent trying to execute workflow:
|
|||
|
||||
```typescript
|
||||
// OLD (doesn't work - I skip steps):
|
||||
Execute super-dev-pipeline for story X
|
||||
Execute story-full-pipeline for story X
|
||||
|
||||
// NEW (enforcement active):
|
||||
Task agent: workflow-executor
|
||||
Prompt: Execute super-dev-pipeline for story 18-4
|
||||
Prompt: Execute story-full-pipeline for story 18-4
|
||||
- Load ALL step files into context at start
|
||||
- Execute steps 1-11 in exact order
|
||||
- Spawn Task agents when step requires it
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# Agent Limitations in Batch Mode
|
||||
|
||||
**CRITICAL:** Agents running in batch-super-dev have specific limitations. Understanding these prevents wasted time and sets correct expectations.
|
||||
**CRITICAL:** Agents running in batch-stories have specific limitations. Understanding these prevents wasted time and sets correct expectations.
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -93,7 +93,7 @@
|
|||
|
||||
## Pre-Batch Validation Checklist
|
||||
|
||||
**Before running /batch-super-dev, verify ALL selected stories:**
|
||||
**Before running /batch-stories, verify ALL selected stories:**
|
||||
|
||||
```bash
|
||||
# 1. Check story files exist
|
||||
|
|
@ -121,7 +121,7 @@ done
|
|||
**If any checks fail:**
|
||||
1. Regenerate those stories: `/create-story-with-gap-analysis`
|
||||
2. Validate again
|
||||
3. THEN run batch-super-dev
|
||||
3. THEN run batch-stories
|
||||
|
||||
---
|
||||
|
||||
|
|
@ -150,7 +150,7 @@ done
|
|||
**What it means:** Agent tried to create story but couldn't
|
||||
**Is this a bug?** ❌ NO - Agents can't create stories
|
||||
**What to do:**
|
||||
- Exit batch-super-dev
|
||||
- Exit batch-stories
|
||||
- Manually run /create-story-with-gap-analysis
|
||||
- Re-run batch after story created
|
||||
|
||||
|
|
@ -165,7 +165,7 @@ done
|
|||
1. Plan epic → Identify stories → Create list
|
||||
2. Generate stories: /create-story-with-gap-analysis (1-2 days)
|
||||
3. Validate stories: ./scripts/validate-all-stories.sh
|
||||
4. Execute stories: /batch-super-dev (parallel, fast)
|
||||
4. Execute stories: /batch-stories (parallel, fast)
|
||||
```
|
||||
|
||||
### ✅ DO: Use Small Batches for Mixed Complexity
|
||||
|
|
@ -183,7 +183,7 @@ done
|
|||
**Why it fails:**
|
||||
```
|
||||
1. Create 20 skeleton files with just widget lists
|
||||
2. Run /batch-super-dev
|
||||
2. Run /batch-stories
|
||||
3. Expect agents to regenerate them
|
||||
→ FAILS: Agents can't invoke /create-story workflow
|
||||
```
|
||||
|
|
@ -193,7 +193,7 @@ done
|
|||
**Why it fails:**
|
||||
```
|
||||
1. 10 proper BMAD stories + 10 skeletons
|
||||
2. Run /batch-super-dev
|
||||
2. Run /batch-stories
|
||||
3. Expect batch to handle both
|
||||
→ RESULT: 10 execute, 10 skipped (confusing)
|
||||
```
|
||||
|
|
|
|||
|
|
@ -9,9 +9,9 @@
|
|||
|
||||
## Critical Prerequisites
|
||||
|
||||
> **⚠️ IMPORTANT: Read before running batch-super-dev!**
|
||||
> **⚠️ IMPORTANT: Read before running batch-stories!**
|
||||
|
||||
**BEFORE running batch-super-dev:**
|
||||
**BEFORE running batch-stories:**
|
||||
|
||||
### ✅ 1. All stories must be properly generated
|
||||
|
||||
|
|
@ -48,13 +48,13 @@ Required sections:
|
|||
**What you might try:**
|
||||
```
|
||||
1. Create 20 skeleton story files (just headers + widget lists)
|
||||
2. Run /batch-super-dev
|
||||
2. Run /batch-stories
|
||||
3. Expect agents to regenerate them
|
||||
```
|
||||
|
||||
**What happens:**
|
||||
- Agents identify stories are incomplete
|
||||
- Agents correctly halt per super-dev-pipeline validation
|
||||
- Agents correctly halt per story-full-pipeline validation
|
||||
- Stories get skipped (not regenerated)
|
||||
- You waste time
|
||||
|
||||
|
|
@ -67,7 +67,7 @@ Required sections:
|
|||
./scripts/validate-all-stories.sh
|
||||
|
||||
# 3. Execute (4-8 hours, parallel autonomous)
|
||||
/batch-super-dev
|
||||
/batch-stories
|
||||
```
|
||||
|
||||
See: `AGENT-LIMITATIONS.md` for full documentation on what agents can and cannot do.
|
||||
|
|
@ -76,7 +76,7 @@ See: `AGENT-LIMITATIONS.md` for full documentation on what agents can and cannot
|
|||
|
||||
## Overview
|
||||
|
||||
Interactive batch workflow for processing multiple `ready-for-dev` stories sequentially or in parallel using the super-dev-pipeline with full quality gates.
|
||||
Interactive batch workflow for processing multiple `ready-for-dev` stories sequentially or in parallel using the story-full-pipeline with full quality gates.
|
||||
|
||||
**New in v1.2.0:** Smart Story Validation & Auto-Creation - validates story files, creates missing stories, regenerates invalid ones automatically.
|
||||
**New in v1.1.0:** Smart Story Reconciliation - automatically verifies story accuracy after each implementation.
|
||||
|
|
@ -107,7 +107,7 @@ Interactive batch workflow for processing multiple `ready-for-dev` stories seque
|
|||
- **Parallel:** Spawn Task agents to process stories concurrently (faster, autonomous)
|
||||
- Configurable parallelism: 2, 4, or all stories at once
|
||||
|
||||
4. **Full Quality Gates** (from super-dev-pipeline)
|
||||
4. **Full Quality Gates** (from story-full-pipeline)
|
||||
- Pre-gap analysis (validate story completeness)
|
||||
- Test-driven implementation
|
||||
- Post-validation (verify requirements met)
|
||||
|
|
@ -150,7 +150,7 @@ Before v1.2.0:
|
|||
```
|
||||
User: "Process stories 3.1, 3.2, 3.3, 3.4"
|
||||
Workflow: "Story 3.3 file missing - please create it first"
|
||||
User: Ctrl+C → /create-story → /batch-super-dev again
|
||||
User: Ctrl+C → /create-story → /batch-stories again
|
||||
```
|
||||
|
||||
After v1.2.0:
|
||||
|
|
@ -232,7 +232,7 @@ validation:
|
|||
### Example Session (v1.2.0)
|
||||
|
||||
```
|
||||
🤖 /batch-super-dev
|
||||
🤖 /batch-stories
|
||||
|
||||
📊 Ready-for-Dev Stories (5)
|
||||
|
||||
|
|
@ -398,7 +398,7 @@ sprint-status.yaml: done
|
|||
|
||||
```bash
|
||||
# Process all ready-for-dev stories
|
||||
/batch-super-dev
|
||||
/batch-stories
|
||||
|
||||
# Follow prompts:
|
||||
# 1. See list of ready stories
|
||||
|
|
@ -413,7 +413,7 @@ sprint-status.yaml: done
|
|||
|
||||
```bash
|
||||
# Only process Epic 3 stories
|
||||
/batch-super-dev filter_by_epic=3
|
||||
/batch-stories filter_by_epic=3
|
||||
```
|
||||
|
||||
### Selection Syntax
|
||||
|
|
@ -444,7 +444,7 @@ All: all (processes all ready-for-dev stories)
|
|||
|
||||
## Workflow Configuration
|
||||
|
||||
**File:** `_bmad/bmm/workflows/4-implementation/batch-super-dev/workflow.yaml`
|
||||
**File:** `_bmad/bmm/workflows/4-implementation/batch-stories/workflow.yaml`
|
||||
|
||||
### Key Settings
|
||||
|
||||
|
|
@ -503,7 +503,7 @@ reconciliation:
|
|||
### 4. Process Stories
|
||||
**Sequential Mode:**
|
||||
- For each selected story:
|
||||
- Invoke super-dev-pipeline
|
||||
- Invoke story-full-pipeline
|
||||
- Execute reconciliation (Step 4.5)
|
||||
- Report results
|
||||
- Pause between stories
|
||||
|
|
@ -547,7 +547,7 @@ See: `step-4.5-reconcile-story-status.md` for detailed algorithm
|
|||
|
||||
### Batch Log
|
||||
|
||||
**Location:** `docs/sprint-artifacts/batch-super-dev-{date}.log`
|
||||
**Location:** `docs/sprint-artifacts/batch-stories-{date}.log`
|
||||
|
||||
**Contains:**
|
||||
- Start/end timestamps
|
||||
|
|
@ -628,7 +628,7 @@ See: `step-4.5-reconcile-story-status.md` for detailed algorithm
|
|||
**Fix:**
|
||||
1. Review listed stories manually
|
||||
2. Check Dev Agent Record has all required sections
|
||||
3. Re-run super-dev-pipeline for problematic stories
|
||||
3. Re-run story-full-pipeline for problematic stories
|
||||
4. Manually reconcile checkboxes if needed
|
||||
|
||||
### Parallel Mode Hangs
|
||||
|
|
@ -713,24 +713,24 @@ See: `step-4.5-reconcile-story-status.md` for detailed algorithm
|
|||
- Initial release
|
||||
- Interactive story selector
|
||||
- Sequential and parallel execution modes
|
||||
- Integration with super-dev-pipeline
|
||||
- Integration with story-full-pipeline
|
||||
- Batch summary and logging
|
||||
|
||||
---
|
||||
|
||||
## Related Workflows
|
||||
|
||||
- **super-dev-pipeline:** Individual story implementation (invoked by batch-super-dev)
|
||||
- **story-full-pipeline:** Individual story implementation (invoked by batch-stories)
|
||||
- **create-story-with-gap-analysis:** Create new stories with codebase scan
|
||||
- **sprint-status:** View/update sprint status
|
||||
- **multi-agent-review:** Standalone code review (part of super-dev-pipeline)
|
||||
- **multi-agent-review:** Standalone code review (part of story-full-pipeline)
|
||||
|
||||
---
|
||||
|
||||
## Support
|
||||
|
||||
**Questions or Issues:**
|
||||
- Check workflow logs: `docs/sprint-artifacts/batch-super-dev-*.log`
|
||||
- Check workflow logs: `docs/sprint-artifacts/batch-stories-*.log`
|
||||
- Review reconciliation step: `step-4.5-reconcile-story-status.md`
|
||||
- Check story file format: Ensure 12-section BMAD format
|
||||
- Verify Dev Agent Record populated: Required for reconciliation
|
||||
|
|
|
|||
|
|
@ -47,7 +47,7 @@ Story 18-5:
|
|||
### Add state file tracking:
|
||||
|
||||
```yaml
|
||||
# In batch-super-dev/workflow.yaml
|
||||
# In batch-stories/workflow.yaml
|
||||
state_tracking:
|
||||
enabled: true
|
||||
state_file: "{sprint_artifacts}/batch-execution-state-{batch_id}.yaml"
|
||||
|
|
@ -92,7 +92,7 @@ stories:
|
|||
### Resume logic:
|
||||
|
||||
```bash
|
||||
# At batch-super-dev start, check for existing state file
|
||||
# At batch-stories start, check for existing state file
|
||||
state_file="{sprint_artifacts}/batch-execution-state-*.yaml"
|
||||
|
||||
if ls $state_file 2>/dev/null; then
|
||||
|
|
@ -172,7 +172,7 @@ story_content=$(read_with_retry "$story_file") || {
|
|||
|
||||
## Implementation
|
||||
|
||||
Add to batch-super-dev Step 4-Sequential:
|
||||
Add to batch-stories Step 4-Sequential:
|
||||
|
||||
```xml
|
||||
<substep n="4s-0" title="Check for previous execution state">
|
||||
|
|
@ -204,7 +204,7 @@ Add to batch-super-dev Step 4-Sequential:
|
|||
|
||||
<try>
|
||||
<action>Read story file with retry</action>
|
||||
<action>Execute super-dev-pipeline</action>
|
||||
<action>Execute story-full-pipeline</action>
|
||||
<action>Save state: story completed</action>
|
||||
</try>
|
||||
|
||||
|
|
@ -236,7 +236,7 @@ Story 18-5: ❌ Crashed (state saved with error)
|
|||
|
||||
State file created: batch-execution-state-epic-18.yaml
|
||||
|
||||
User re-runs: /batch-super-dev
|
||||
User re-runs: /batch-stories
|
||||
|
||||
Workflow: "🔄 Found interrupted batch. Resume? (yes/no)"
|
||||
User: "yes"
|
||||
|
|
|
|||
|
|
@ -81,7 +81,7 @@ This workflow requires:
|
|||
```
|
||||
Must show: "✅ All 12 sections present"
|
||||
|
||||
4. **Re-run batch-super-dev:**
|
||||
4. **Re-run batch-stories:**
|
||||
- Story will now be properly formatted
|
||||
- Can be executed in next batch run
|
||||
|
||||
|
|
@ -132,7 +132,7 @@ This workflow requires:
|
|||
|
||||
**After completing these actions:**
|
||||
1. Validate all stories: ./scripts/validate-all-stories.sh
|
||||
2. Re-run batch-super-dev for these stories
|
||||
2. Re-run batch-stories for these stories
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
</output>
|
||||
</check>
|
||||
|
|
@ -220,14 +220,14 @@ fi
|
|||
|
||||
## Documentation Update
|
||||
|
||||
**Add to:** `_bmad/bmm/workflows/4-implementation/batch-super-dev/README.md`
|
||||
**Add to:** `_bmad/bmm/workflows/4-implementation/batch-stories/README.md`
|
||||
|
||||
```markdown
|
||||
# Batch Super-Dev Workflow
|
||||
|
||||
## Critical Prerequisites
|
||||
|
||||
**BEFORE running batch-super-dev:**
|
||||
**BEFORE running batch-stories:**
|
||||
|
||||
1. ✅ **All stories must be properly generated**
|
||||
- Run: `/create-story-with-gap-analysis` for each story
|
||||
|
|
@ -252,13 +252,13 @@ fi
|
|||
**What you might try:**
|
||||
```
|
||||
1. Create 20 skeleton story files (just headers + widget lists)
|
||||
2. Run /batch-super-dev
|
||||
2. Run /batch-stories
|
||||
3. Expect agents to regenerate them
|
||||
```
|
||||
|
||||
**What happens:**
|
||||
- Agents identify stories are incomplete
|
||||
- Agents correctly halt per super-dev-pipeline validation
|
||||
- Agents correctly halt per story-full-pipeline validation
|
||||
- Stories get skipped (not regenerated)
|
||||
- You waste time
|
||||
|
||||
|
|
@ -270,7 +270,7 @@ fi
|
|||
**Solution:**
|
||||
- Generate ALL stories manually FIRST: /create-story-with-gap-analysis
|
||||
- Validate: ./scripts/validate-all-stories.sh
|
||||
- THEN run batch: /batch-super-dev
|
||||
- THEN run batch: /batch-stories
|
||||
|
||||
### ❌ Mixed Story Quality
|
||||
|
||||
|
|
@ -301,7 +301,7 @@ done
|
|||
./scripts/validate-all-stories.sh
|
||||
|
||||
# 3. Execute (4-8 hours, parallel autonomous)
|
||||
/batch-super-dev
|
||||
/batch-stories
|
||||
# Select all 5 stories
|
||||
# Choose 2-4 agents parallel
|
||||
|
||||
|
|
@ -325,13 +325,13 @@ done
|
|||
|
||||
**To apply these improvements:**
|
||||
|
||||
- [ ] Update `batch-super-dev/instructions.md` Step 2.5 (lines 82-99)
|
||||
- [ ] Add `batch-super-dev/AGENT-LIMITATIONS.md` (new file)
|
||||
- [ ] Add `batch-super-dev/BATCH-BEST-PRACTICES.md` (new file)
|
||||
- [ ] Update `batch-super-dev/README.md` with prerequisites
|
||||
- [ ] Update `batch-stories/instructions.md` Step 2.5 (lines 82-99)
|
||||
- [ ] Add `batch-stories/AGENT-LIMITATIONS.md` (new file)
|
||||
- [ ] Add `batch-stories/BATCH-BEST-PRACTICES.md` (new file)
|
||||
- [ ] Update `batch-stories/README.md` with prerequisites
|
||||
- [ ] Create `scripts/validate-all-stories.sh` (new script)
|
||||
- [ ] Add manual actions tracking to Step 5 summary
|
||||
- [ ] Update super-dev-pipeline Step 1.4.5 with agent guidance
|
||||
- [ ] Update story-full-pipeline Step 1.4.5 with agent guidance
|
||||
|
||||
**Testing:**
|
||||
- Try batch with mixed story quality → Should skip skeletons gracefully
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
# Step 4.5: Story Reconciliation (Orchestrator-Driven)
|
||||
|
||||
**Version:** 2.1.0
|
||||
**Execute:** AFTER super-dev-pipeline completes, BEFORE marking story done
|
||||
**Execute:** AFTER story-full-pipeline completes, BEFORE marking story done
|
||||
**Who:** Orchestrator (YOU) - not an agent
|
||||
|
||||
---
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
# Batch Super-Dev v3.0 - Unified Workflow
|
||||
|
||||
<purpose>
|
||||
Interactive story selector for batch implementation. Scan codebase for gaps, select stories, process with super-dev-pipeline, reconcile results.
|
||||
Interactive story selector for batch implementation. Scan codebase for gaps, select stories, process with story-full-pipeline, reconcile results.
|
||||
|
||||
**AKA:** "Mend the Gap" - Mind the gap between story requirements and reality, then mend it.
|
||||
</purpose>
|
||||
|
|
@ -18,7 +18,7 @@ Orchestrator coordinates. Agents do implementation. Orchestrator does reconcilia
|
|||
</philosophy>
|
||||
|
||||
<config>
|
||||
name: batch-super-dev
|
||||
name: batch-stories
|
||||
version: 3.1.0
|
||||
|
||||
modes:
|
||||
|
|
@ -37,7 +37,7 @@ defaults:
|
|||
<execution_context>
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/agent-completion.md
|
||||
@super-dev-pipeline/workflow.md
|
||||
@story-full-pipeline/workflow.md
|
||||
</execution_context>
|
||||
|
||||
<process>
|
||||
|
|
@ -203,16 +203,16 @@ If missing, auto-create using greenfield workflow:
|
|||
echo "✅ Prerequisites satisfied"
|
||||
```
|
||||
|
||||
**Step B: Invoke super-dev-pipeline**
|
||||
**Step B: Invoke story-full-pipeline**
|
||||
|
||||
Use super-dev-pipeline workflow with:
|
||||
Use story-full-pipeline workflow with:
|
||||
- mode: batch
|
||||
- story_key: {{story_key}}
|
||||
- complexity_level: {{complexity}}
|
||||
|
||||
**Step C: Reconcile Using Completion Artifacts (orchestrator does this directly)**
|
||||
|
||||
After super-dev-pipeline completes:
|
||||
After story-full-pipeline completes:
|
||||
|
||||
**C1. Load Fixer completion artifact:**
|
||||
```bash
|
||||
|
|
@ -294,10 +294,10 @@ Task({
|
|||
subagent_type: "general-purpose",
|
||||
description: "Implement {{story_key}}",
|
||||
prompt: `
|
||||
Execute super-dev-pipeline for story {{story_key}}.
|
||||
Execute story-full-pipeline for story {{story_key}}.
|
||||
|
||||
<execution_context>
|
||||
@super-dev-pipeline/workflow.md
|
||||
@story-full-pipeline/workflow.md
|
||||
</execution_context>
|
||||
|
||||
<context>
|
||||
|
|
|
|||
|
|
@ -228,7 +228,7 @@ Ready for implementation.
|
|||
|
||||
Next Steps:
|
||||
1. Review story for accuracy
|
||||
2. Use /story-pipeline or /super-dev-pipeline to implement
|
||||
2. Use /story-dev-only or /story-full-pipeline to implement
|
||||
3. All context loaded and ready
|
||||
|
||||
[N] Create next story
|
||||
|
|
|
|||
|
|
@ -101,7 +101,7 @@ Human-in-the-loop with approval at each step:
|
|||
bmad build 1-4
|
||||
|
||||
# Or invoke workflow directly
|
||||
claude -p "Load and execute: _bmad/bmm/workflows/4-implementation/story-pipeline/workflow.md
|
||||
claude -p "Load and execute: _bmad/bmm/workflows/4-implementation/story-dev-only/workflow.md
|
||||
Story: 1-4"
|
||||
```
|
||||
|
||||
|
|
@ -121,7 +121,7 @@ Unattended execution for trusted stories:
|
|||
bmad build 1-4 --batch
|
||||
|
||||
# Or use batch runner directly
|
||||
./_bmad/bmm/workflows/4-implementation/story-pipeline/batch-runner.sh 1-4
|
||||
./_bmad/bmm/workflows/4-implementation/story-dev-only/batch-runner.sh 1-4
|
||||
```
|
||||
|
||||
Batch mode:
|
||||
|
|
@ -148,7 +148,7 @@ Resume automatically:
|
|||
## Directory Structure
|
||||
|
||||
```
|
||||
story-pipeline/
|
||||
story-dev-only/
|
||||
├── workflow.yaml # Configuration, agent mapping, quality gates
|
||||
├── workflow.md # Interactive mode orchestration
|
||||
├── batch-runner.sh # Batch mode runner script
|
||||
|
|
@ -178,7 +178,7 @@ story-pipeline/
|
|||
### workflow.yaml
|
||||
|
||||
```yaml
|
||||
name: story-pipeline
|
||||
name: story-dev-only
|
||||
version: "2.0"
|
||||
description: "Single-session story implementation with step-file loading"
|
||||
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ name: 'step-01-init'
|
|||
description: 'Initialize story pipeline: load context, detect mode, cache documents'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-01-init.md'
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ name: 'step-01b-resume'
|
|||
description: 'Resume pipeline from checkpoint after failure or interruption'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-01b-resume.md'
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ name: 'step-02-create-story'
|
|||
description: 'Create detailed story file from epic definition with research'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-02-create-story.md'
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ name: 'step-03-validate-story'
|
|||
description: 'Adversarial validation of story completeness and quality'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-03-validate-story.md'
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ name: 'step-04-atdd'
|
|||
description: 'Generate failing acceptance tests before implementation (RED phase)'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-04-atdd.md'
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ name: 'step-05-implement'
|
|||
description: 'Implement story to make tests pass (GREEN phase)'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-05-implement.md'
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ name: 'step-05b-post-validation'
|
|||
description: 'Verify completed tasks against codebase reality (catch false positives)'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-05b-post-validation.md'
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ name: 'step-06-code-review'
|
|||
description: 'Adversarial code review finding 3-10 specific issues'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-06-code-review.md'
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ name: 'step-07-complete'
|
|||
description: 'Update sprint status and create git commit'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-07-complete.md'
|
||||
|
|
@ -89,7 +89,7 @@ stories:
|
|||
code_reviewed: true
|
||||
issues_found: {count}
|
||||
issues_fixed: {count}
|
||||
pipeline_version: "story-pipeline-v2.0"
|
||||
pipeline_version: "story-dev-only-v2.0"
|
||||
```
|
||||
|
||||
### 4. Stage Git Changes
|
||||
|
|
@ -119,7 +119,7 @@ feat(epic-{epic_num}): complete story {story_id}
|
|||
- Code reviewed: {issues_found} issues found and fixed
|
||||
|
||||
Story: {story_title}
|
||||
Pipeline: story-pipeline-v2.0
|
||||
Pipeline: story-dev-only-v2.0
|
||||
|
||||
🤖 Generated with BMAD Story Pipeline
|
||||
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ name: 'step-08-summary'
|
|||
description: 'Generate audit trail and pipeline summary report'
|
||||
|
||||
# Path Definitions
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline'
|
||||
workflow_path: '{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only'
|
||||
|
||||
# File References
|
||||
thisStepFile: '{workflow_path}/steps/step-08-summary.md'
|
||||
|
|
@ -48,7 +48,7 @@ Create: `{auditFile}`
|
|||
```yaml
|
||||
---
|
||||
audit_version: "1.0"
|
||||
pipeline: "story-pipeline-v2.0"
|
||||
pipeline: "story-dev-only-v2.0"
|
||||
story_id: "{story_id}"
|
||||
epic_num: {epic_num}
|
||||
---
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
---
|
||||
name: story-pipeline
|
||||
name: story-dev-only
|
||||
description: Automated story development pipeline with token-efficient step-file architecture. Single-session orchestration replacing multiple Claude calls.
|
||||
web_bundle: true
|
||||
---
|
||||
|
|
@ -112,7 +112,7 @@ Load and cache these documents (read once, use across steps):
|
|||
### 4. First Step Execution
|
||||
|
||||
Load, read the full file and then execute:
|
||||
`{project-root}/_bmad/bmm/workflows/4-implementation/story-pipeline/steps/step-01-init.md`
|
||||
`{project-root}/_bmad/bmm/workflows/4-implementation/story-dev-only/steps/step-01-init.md`
|
||||
|
||||
---
|
||||
|
||||
|
|
|
|||
|
|
@ -8,10 +8,10 @@
|
|||
|
||||
```bash
|
||||
# Use v2.0 for a story
|
||||
/super-dev-pipeline mode=multi_agent story_key=17-10
|
||||
/story-full-pipeline mode=multi_agent story_key=17-10
|
||||
|
||||
# Use v1.x (fallback)
|
||||
/super-dev-pipeline mode=single_agent story_key=17-10
|
||||
/story-full-pipeline mode=single_agent story_key=17-10
|
||||
```
|
||||
|
||||
---
|
||||
|
|
@ -107,7 +107,7 @@ Separate agents for each phase:
|
|||
## Files in This Directory
|
||||
|
||||
```
|
||||
super-dev-pipeline/
|
||||
story-full-pipeline/
|
||||
├── README.md (this file)
|
||||
├── workflow.yaml (configuration)
|
||||
├── workflow.md (complete documentation)
|
||||
|
|
|
|||
|
|
@ -1,38 +1,47 @@
|
|||
# Super-Dev-Pipeline v3.0 - Unified Workflow
|
||||
# Super-Dev-Pipeline v3.1 - Token-Efficient Multi-Agent Pipeline
|
||||
|
||||
<purpose>
|
||||
Implement a story using 4 independent agents with orchestrator-driven reconciliation.
|
||||
Each agent has single responsibility. No agent validates its own work.
|
||||
Implement a story using parallel verification agents with Builder context reuse.
|
||||
Each agent has single responsibility. Builder fixes issues in its own context (50-70% token savings).
|
||||
Orchestrator handles bookkeeping (story file updates, verification).
|
||||
</purpose>
|
||||
|
||||
<philosophy>
|
||||
**Agents do creative work. Orchestrator does bookkeeping.**
|
||||
**Token-Efficient Multi-Agent Pipeline**
|
||||
|
||||
- Builder implements (creative)
|
||||
- Inspector validates (verification)
|
||||
- Reviewer finds issues (adversarial)
|
||||
- Fixer resolves issues (creative)
|
||||
- Builder implements (creative, context preserved)
|
||||
- Inspector + Reviewers validate in parallel (verification, fresh context)
|
||||
- Builder fixes issues (creative, reuses context - 50-70% token savings)
|
||||
- Inspector re-checks (verification, quick check)
|
||||
- Orchestrator reconciles story file (mechanical)
|
||||
|
||||
Trust but verify. Fresh context per phase. Adversarial review.
|
||||
**Key Innovation:** Resume Builder instead of spawning fresh Fixer.
|
||||
Builder already knows the codebase - just needs to fix specific issues.
|
||||
|
||||
Trust but verify. Fresh context for verification. Reuse context for fixes.
|
||||
</philosophy>
|
||||
|
||||
<config>
|
||||
name: super-dev-pipeline
|
||||
version: 3.0.0
|
||||
name: story-full-pipeline
|
||||
version: 3.1.0
|
||||
execution_mode: multi_agent
|
||||
|
||||
agents:
|
||||
builder: {steps: 1-4, trust: low, timeout: 60min}
|
||||
inspector: {steps: 5-6, trust: medium, fresh_context: true, timeout: 30min}
|
||||
reviewer: {steps: 7, trust: high, adversarial: true, timeout: 30min}
|
||||
fixer: {steps: 8-9, trust: medium, timeout: 40min}
|
||||
phases:
|
||||
phase_1: Builder (saves agent_id)
|
||||
phase_2: [Inspector + N Reviewers] in parallel (N = 1/2/3 based on complexity)
|
||||
phase_3: Resume Builder with all findings (reuses context)
|
||||
phase_4: Inspector re-check (quick verification)
|
||||
phase_5: Orchestrator reconciliation
|
||||
|
||||
complexity_routing:
|
||||
micro: {skip: [reviewer], description: "Low-risk stories"}
|
||||
standard: {skip: [], description: "Normal stories"}
|
||||
complex: {skip: [], enhanced_review: true, description: "High-risk stories"}
|
||||
reviewer_counts:
|
||||
micro: 1 reviewer (security only)
|
||||
standard: 2 reviewers (security, performance)
|
||||
complex: 3 reviewers (security, performance, code quality)
|
||||
|
||||
token_efficiency:
|
||||
- Phase 2 agents spawn in parallel (same cost, faster)
|
||||
- Phase 3 resumes Builder (50-70% token savings vs fresh Fixer)
|
||||
- Phase 4 Inspector only (no full re-review)
|
||||
</config>
|
||||
|
||||
<execution_context>
|
||||
|
|
@ -42,109 +51,13 @@ complexity_routing:
|
|||
|
||||
<process>
|
||||
|
||||
<verification_checklist>
|
||||
## Implementation Execution Checklist
|
||||
<step name="load_story" priority="first">
|
||||
Load and validate the story file.
|
||||
|
||||
**Story {{story_key}} requires these exact steps (cannot skip):**
|
||||
|
||||
### Prerequisites (Auto-Fixed)
|
||||
- [ ] **Step 0.1:** Story file exists (auto-create if missing)
|
||||
- [ ] **Step 0.2:** Gap analysis complete (auto-run if missing)
|
||||
|
||||
### Phase 1: Builder (Steps 1-4)
|
||||
- [ ] **Step 1.1:** Builder agent spawned
|
||||
- [ ] **Step 1.2:** Builder creates completion artifact
|
||||
- [ ] **Step 1.3:** Verify artifact exists (file check)
|
||||
- [ ] **Step 1.4:** Verify claimed files exist
|
||||
|
||||
### Phase 2: Inspector (Steps 5-6)
|
||||
- [ ] **Step 2.1:** Inspector agent spawned (fresh context)
|
||||
- [ ] **Step 2.2:** Inspector runs all quality checks
|
||||
- [ ] **Step 2.3:** Inspector creates completion artifact
|
||||
- [ ] **Step 2.4:** Verify PASS verdict
|
||||
|
||||
### Phase 3: Reviewer (Step 7) [Skip if micro complexity]
|
||||
- [ ] **Step 3.1:** Reviewer agent spawned (adversarial)
|
||||
- [ ] **Step 3.2:** Reviewer finds issues
|
||||
- [ ] **Step 3.3:** Reviewer creates completion artifact
|
||||
- [ ] **Step 3.4:** Categorize issues (CRITICAL/HIGH/MEDIUM/LOW)
|
||||
|
||||
### Phase 4: Fixer (Steps 8-9)
|
||||
- [ ] **Step 4.1:** Fixer agent spawned
|
||||
- [ ] **Step 4.2:** Fixer resolves CRITICAL + HIGH issues
|
||||
- [ ] **Step 4.3:** Fixer creates completion artifact
|
||||
- [ ] **Step 4.4:** Fixer commits changes
|
||||
- [ ] **Step 4.5:** Verify git commit exists
|
||||
|
||||
### Phase 5: Reconciliation (Orchestrator)
|
||||
- [ ] **Step 5.1:** Load Fixer completion artifact
|
||||
- [ ] **Step 5.2:** Parse JSON for structured data
|
||||
- [ ] **Step 5.3:** Update story file tasks (check off completed)
|
||||
- [ ] **Step 5.4:** Fill Dev Agent Record
|
||||
- [ ] **Step 5.5:** Verify story file updated (bash check)
|
||||
|
||||
### Final Verification
|
||||
- [ ] **Step 6.1:** Git commit exists for story
|
||||
- [ ] **Step 6.2:** Story has checked tasks (count > 0)
|
||||
- [ ] **Step 6.3:** Dev Agent Record filled
|
||||
- [ ] **Step 6.4:** Sprint status updated to "done"
|
||||
|
||||
**If any step fails:**
|
||||
- HALT immediately
|
||||
- Report which step failed
|
||||
- Fix before proceeding
|
||||
- Cannot skip steps
|
||||
</verification_checklist>
|
||||
|
||||
<step name="ensure_prerequisites" priority="first">
|
||||
**AUTO-FIX MISSING PREREQUISITES**
|
||||
|
||||
```bash
|
||||
\`\`\`bash
|
||||
STORY_FILE="docs/sprint-artifacts/{{story_key}}.md"
|
||||
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔍 CHECKING PREREQUISITES"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
```
|
||||
|
||||
**Check 1: Story file exists?**
|
||||
```bash
|
||||
if [ ! -f "$STORY_FILE" ]; then
|
||||
echo "⚠️ Story file not found, creating it..."
|
||||
fi
|
||||
```
|
||||
|
||||
If story file missing:
|
||||
- Use Skill tool to invoke: `/bmad_bmm_create-story {{story_key}}`
|
||||
- Wait for completion
|
||||
- Verify file created: `[ -f "$STORY_FILE" ] || exit 1`
|
||||
|
||||
```bash
|
||||
echo "✅ Story file exists: $STORY_FILE"
|
||||
```
|
||||
|
||||
**Check 2: Gap analysis complete?**
|
||||
```bash
|
||||
GAP_COUNT=$(grep -c "^✅\|^❌" "$STORY_FILE" || echo "0")
|
||||
|
||||
if [ "$GAP_COUNT" -eq 0 ]; then
|
||||
echo "⚠️ Gap analysis missing, running it..."
|
||||
fi
|
||||
```
|
||||
|
||||
If gap analysis missing:
|
||||
- Use Skill tool to invoke: `/bmad_bmm_gap-analysis {{story_key}}`
|
||||
- Wait for completion
|
||||
- Verify markers exist: `GAP_COUNT=$(grep -c "^✅\|^❌" "$STORY_FILE")`
|
||||
- If still 0: exit 1 (can't auto-fix)
|
||||
|
||||
```bash
|
||||
echo "✅ Gap analysis complete: $GAP_COUNT markers found"
|
||||
echo "✅ All prerequisites satisfied"
|
||||
echo ""
|
||||
```
|
||||
|
||||
**Load story metadata:**
|
||||
[ -f "$STORY_FILE" ] || { echo "ERROR: Story file not found"; exit 1; }
|
||||
\`\`\`
|
||||
|
||||
Use Read tool on the story file. Parse:
|
||||
- Complexity level (micro/standard/complex)
|
||||
|
|
@ -157,420 +70,146 @@ Determine which agents to spawn based on complexity routing.
|
|||
<step name="spawn_builder">
|
||||
**Phase 1: Builder Agent (Steps 1-4)**
|
||||
|
||||
```
|
||||
\`\`\`
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔨 PHASE 1: BUILDER
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
\`\`\`
|
||||
|
||||
Spawn Builder agent:
|
||||
Spawn Builder agent and save agent_id for later resume.
|
||||
|
||||
```
|
||||
Task({
|
||||
subagent_type: "general-purpose",
|
||||
description: "Implement story {{story_key}}",
|
||||
prompt: `
|
||||
You are the BUILDER agent for story {{story_key}}.
|
||||
**CRITICAL: Save Builder's agent_id for later resume**
|
||||
|
||||
<execution_context>
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/tdd.md
|
||||
@patterns/agent-completion.md
|
||||
</execution_context>
|
||||
\`\`\`
|
||||
BUILDER_AGENT_ID={{agent_id_from_task_result}}
|
||||
echo "Builder agent: $BUILDER_AGENT_ID"
|
||||
\`\`\`
|
||||
|
||||
<context>
|
||||
Story: [inline story file content]
|
||||
</context>
|
||||
Wait for completion. Parse structured output. Verify files exist.
|
||||
|
||||
<objective>
|
||||
Implement the story requirements:
|
||||
1. Load and understand requirements
|
||||
2. Analyze what exists vs needed
|
||||
3. Write tests first (TDD)
|
||||
4. Implement production code
|
||||
</objective>
|
||||
|
||||
<constraints>
|
||||
- DO NOT validate your own work
|
||||
- DO NOT review your code
|
||||
- DO NOT update story checkboxes
|
||||
- DO NOT commit changes
|
||||
</constraints>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] Tests written for all requirements
|
||||
- [ ] Production code implements tests
|
||||
- [ ] Return ## AGENT COMPLETE with file lists
|
||||
</success_criteria>
|
||||
`
|
||||
})
|
||||
```
|
||||
|
||||
**Wait for completion.**
|
||||
|
||||
**VERIFICATION GATE: Builder Completion**
|
||||
|
||||
```bash
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔍 VERIFYING BUILDER COMPLETION"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
# Check completion artifact exists
|
||||
COMPLETION_FILE="docs/sprint-artifacts/completions/{{story_key}}-builder.json"
|
||||
|
||||
if [ ! -f "$COMPLETION_FILE" ]; then
|
||||
echo ""
|
||||
echo "❌ BLOCKER: Builder failed to create completion artifact"
|
||||
echo "Expected: $COMPLETION_FILE"
|
||||
echo ""
|
||||
echo "Pipeline halted. Builder must create completion.json"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✅ Completion artifact found"
|
||||
|
||||
# Verify files claimed in artifact actually exist
|
||||
echo "Verifying claimed files..."
|
||||
|
||||
# Parse files from JSON and verify existence
|
||||
# (Simplified - orchestrator will do full JSON parsing)
|
||||
FILES_MISSING=0
|
||||
while IFS= read -r file; do
|
||||
if [ ! -f "$file" ]; then
|
||||
echo "❌ MISSING: $file"
|
||||
FILES_MISSING=$((FILES_MISSING + 1))
|
||||
else
|
||||
echo "✅ Found: $file"
|
||||
fi
|
||||
done < <(grep -o '"[^"]*\.\(ts\|tsx\|js\|jsx\)"' "$COMPLETION_FILE" | tr -d '"')
|
||||
|
||||
if [ "$FILES_MISSING" -gt 0 ]; then
|
||||
echo ""
|
||||
echo "❌ BLOCKER: $FILES_MISSING files missing"
|
||||
echo "Builder claimed to create files that don't exist"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✅ All claimed files verified"
|
||||
echo ""
|
||||
```
|
||||
|
||||
If verification fails: halt pipeline.
|
||||
If files missing or status FAILED: halt pipeline.
|
||||
</step>
|
||||
|
||||
<step name="spawn_inspector">
|
||||
**Phase 2: Inspector Agent (Steps 5-6)**
|
||||
<step name="spawn_verification_parallel">
|
||||
**Phase 2: Parallel Verification (Inspector + Reviewers)**
|
||||
|
||||
```
|
||||
\`\`\`
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔍 PHASE 2: INSPECTOR
|
||||
🔍 PHASE 2: PARALLEL VERIFICATION
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
\`\`\`
|
||||
|
||||
Spawn Inspector agent with **fresh context** (no Builder knowledge):
|
||||
**CRITICAL: Spawn ALL verification agents in ONE message (parallel execution)**
|
||||
|
||||
```
|
||||
Task({
|
||||
subagent_type: "general-purpose",
|
||||
description: "Validate story {{story_key}} implementation",
|
||||
prompt: `
|
||||
You are the INSPECTOR agent for story {{story_key}}.
|
||||
Determine reviewer count based on complexity:
|
||||
\`\`\`
|
||||
if complexity == "micro": REVIEWER_COUNT = 1
|
||||
if complexity == "standard": REVIEWER_COUNT = 2
|
||||
if complexity == "complex": REVIEWER_COUNT = 3
|
||||
\`\`\`
|
||||
|
||||
<execution_context>
|
||||
@patterns/verification.md
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/agent-completion.md
|
||||
</execution_context>
|
||||
Spawn Inspector + N Reviewers in single message. Wait for ALL agents to complete. Collect findings.
|
||||
|
||||
<context>
|
||||
Story: [inline story file content]
|
||||
</context>
|
||||
|
||||
<objective>
|
||||
Independently verify the implementation:
|
||||
1. Verify files exist and have content
|
||||
2. Run type-check, lint, build
|
||||
3. Run tests yourself
|
||||
4. Give honest PASS/FAIL verdict
|
||||
</objective>
|
||||
|
||||
<constraints>
|
||||
- You have NO KNOWLEDGE of what Builder did
|
||||
- Run all checks yourself
|
||||
- Don't trust any claims
|
||||
</constraints>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] All files verified to exist
|
||||
- [ ] Type check passes (0 errors)
|
||||
- [ ] Lint passes (0 warnings)
|
||||
- [ ] Tests pass
|
||||
- [ ] Return ## AGENT COMPLETE with evidence
|
||||
</success_criteria>
|
||||
`
|
||||
})
|
||||
```
|
||||
|
||||
**Wait for completion. Parse verdict.**
|
||||
|
||||
If FAIL: halt pipeline, report specific failures.
|
||||
Aggregate all findings from Inspector + Reviewers.
|
||||
</step>
|
||||
|
||||
<step name="spawn_reviewer" if="complexity != micro">
|
||||
**Phase 3: Reviewer Agent (Step 7)**
|
||||
<step name="resume_builder_with_findings">
|
||||
**Phase 3: Resume Builder with All Findings**
|
||||
|
||||
```
|
||||
\`\`\`
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔎 PHASE 3: REVIEWER
|
||||
🔧 PHASE 3: RESUME BUILDER (Fix Issues)
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
\`\`\`
|
||||
|
||||
Spawn Reviewer agent with **adversarial stance**:
|
||||
**CRITICAL: Resume Builder agent (reuses context!)**
|
||||
|
||||
```
|
||||
Task({
|
||||
subagent_type: "general-purpose",
|
||||
description: "Review story {{story_key}} code",
|
||||
prompt: `
|
||||
You are the ADVERSARIAL REVIEWER for story {{story_key}}.
|
||||
Use Task tool with `resume: "{{BUILDER_AGENT_ID}}"` parameter.
|
||||
|
||||
<execution_context>
|
||||
@patterns/security-checklist.md
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/agent-completion.md
|
||||
</execution_context>
|
||||
|
||||
<context>
|
||||
Story: [inline story file content]
|
||||
</context>
|
||||
|
||||
<objective>
|
||||
Find problems. Be critical. Look for:
|
||||
- Security vulnerabilities (CRITICAL)
|
||||
- Logic bugs and edge cases (HIGH)
|
||||
- Performance issues (MEDIUM)
|
||||
- Code style issues (LOW)
|
||||
</objective>
|
||||
|
||||
<constraints>
|
||||
- Your goal is to FIND ISSUES
|
||||
- Don't rubber-stamp
|
||||
- Be thorough
|
||||
</constraints>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] All new files reviewed
|
||||
- [ ] Security checks completed
|
||||
- [ ] Issues categorized by severity
|
||||
- [ ] Return ## AGENT COMPLETE with issue list
|
||||
</success_criteria>
|
||||
`
|
||||
})
|
||||
```
|
||||
|
||||
**Wait for completion. Parse issue counts.**
|
||||
</step>
|
||||
|
||||
<step name="spawn_fixer">
|
||||
**Phase 4: Fixer Agent (Steps 8-9)**
|
||||
|
||||
```
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔧 PHASE 4: FIXER
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
|
||||
Spawn Fixer agent:
|
||||
|
||||
```
|
||||
Task({
|
||||
subagent_type: "general-purpose",
|
||||
description: "Fix issues in story {{story_key}}",
|
||||
prompt: `
|
||||
You are the FIXER agent for story {{story_key}}.
|
||||
|
||||
<execution_context>
|
||||
@patterns/hospital-grade.md
|
||||
@patterns/agent-completion.md
|
||||
</execution_context>
|
||||
|
||||
<context>
|
||||
Story: [inline story file content]
|
||||
Review issues: [inline reviewer findings]
|
||||
</context>
|
||||
|
||||
<objective>
|
||||
Fix CRITICAL and HIGH issues:
|
||||
1. Fix ALL CRITICAL issues (security)
|
||||
2. Fix ALL HIGH issues (bugs)
|
||||
3. Fix MEDIUM if time allows
|
||||
Builder receives all consolidated findings and fixes:
|
||||
1. ALL CRITICAL issues (security, blockers)
|
||||
2. ALL HIGH issues (bugs, logic errors)
|
||||
3. MEDIUM if quick (<30 min total)
|
||||
4. Skip LOW (gold-plating)
|
||||
5. Commit with descriptive message
|
||||
</objective>
|
||||
|
||||
<constraints>
|
||||
- DO NOT skip CRITICAL issues
|
||||
- DO NOT update story checkboxes (orchestrator does this)
|
||||
- DO NOT update sprint-status (orchestrator does this)
|
||||
</constraints>
|
||||
Wait for completion. Parse commit hash and fix counts.
|
||||
</step>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] All CRITICAL fixed
|
||||
- [ ] All HIGH fixed
|
||||
- [ ] Tests still pass
|
||||
- [ ] Git commit created
|
||||
- [ ] Return ## AGENT COMPLETE with fix summary
|
||||
</success_criteria>
|
||||
`
|
||||
})
|
||||
```
|
||||
<step name="inspector_recheck">
|
||||
**Phase 4: Quick Inspector Re-Check**
|
||||
|
||||
**Wait for completion. Parse commit hash and fix counts.**
|
||||
\`\`\`
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
✅ PHASE 4: RE-VERIFICATION
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
\`\`\`
|
||||
|
||||
Spawn Inspector only (not full review). Quick functional verification.
|
||||
|
||||
If FAIL: Resume Builder again with new issues.
|
||||
If PASS: Proceed to reconciliation.
|
||||
</step>
|
||||
|
||||
<step name="reconcile_story">
|
||||
**Phase 5: Orchestrator Reconciliation**
|
||||
|
||||
```
|
||||
\`\`\`
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
🔧 PHASE 5: RECONCILIATION (Orchestrator)
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
\`\`\`
|
||||
|
||||
**YOU (orchestrator) do this directly. No agent spawn.**
|
||||
|
||||
**Step 5.1: Verify completion artifact exists**
|
||||
```bash
|
||||
FIXER_COMPLETION="docs/sprint-artifacts/completions/{{story_key}}-fixer.json"
|
||||
|
||||
if [ ! -f "$FIXER_COMPLETION" ]; then
|
||||
echo "❌ BLOCKER: Fixer completion artifact missing"
|
||||
echo "Cannot reconcile without completion data"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✅ Completion artifact found"
|
||||
```
|
||||
|
||||
**Step 5.2: Load completion data**
|
||||
Use Read tool on the Fixer completion artifact:
|
||||
- `docs/sprint-artifacts/completions/{{story_key}}-fixer.json`
|
||||
|
||||
Parse JSON to extract:
|
||||
- files_modified array
|
||||
- files_created array (from Builder artifact if needed)
|
||||
- git_commit hash
|
||||
- quality_checks results
|
||||
- tests counts
|
||||
|
||||
**Step 5.3: Read story file**
|
||||
Use Read tool: `docs/sprint-artifacts/{{story_key}}.md`
|
||||
|
||||
**Step 5.4: Check off completed tasks**
|
||||
For each task in the story:
|
||||
- Match task description to files in completion artifact
|
||||
- If file mentioned in task was created/modified, check off task
|
||||
- Use Edit tool to change `- [ ]` to `- [x]`
|
||||
|
||||
**Step 5.5: Fill Dev Agent Record**
|
||||
Use Edit tool to update Dev Agent Record section with data from completion.json:
|
||||
```markdown
|
||||
### Dev Agent Record
|
||||
**Implementation Date:** {{timestamp from completion.json}}
|
||||
**Agent Model:** Claude Sonnet 4.5 (multi-agent pipeline)
|
||||
**Git Commit:** {{git_commit from completion.json}}
|
||||
|
||||
**Files Created:**
|
||||
{{files_created from Builder completion.json}}
|
||||
|
||||
**Files Modified:**
|
||||
{{files_modified from Fixer completion.json}}
|
||||
|
||||
**Tests:**
|
||||
- Passing: {{tests.passing from Fixer completion.json}}
|
||||
- Total: {{tests.total from Fixer completion.json}}
|
||||
- Coverage: {{tests.coverage from Fixer completion.json}}%
|
||||
|
||||
**Quality Checks:**
|
||||
{{quality_checks from Fixer completion.json}}
|
||||
|
||||
**Issues Fixed:**
|
||||
{{fixes_applied from Fixer completion.json}}
|
||||
```
|
||||
|
||||
**Step 5.6: Verify updates**
|
||||
```bash
|
||||
CHECKED=$(grep -c "^- \[x\]" docs/sprint-artifacts/{{story_key}}.md)
|
||||
if [ "$CHECKED" -eq 0 ]; then
|
||||
echo "❌ BLOCKER: Zero checked tasks"
|
||||
echo "Orchestrator failed to update story file"
|
||||
exit 1
|
||||
fi
|
||||
echo "✅ Verified: $CHECKED tasks checked"
|
||||
|
||||
# Verify Dev Agent Record has timestamp
|
||||
grep -A 10 "### Dev Agent Record" docs/sprint-artifacts/{{story_key}}.md | grep -q "202" || {
|
||||
echo "❌ BLOCKER: Dev Agent Record not filled"
|
||||
exit 1
|
||||
}
|
||||
echo "✅ Dev Agent Record filled"
|
||||
```
|
||||
|
||||
If verification fails: fix using Edit, then re-verify.
|
||||
1. Get what was built (git log, git diff)
|
||||
2. Read story file
|
||||
3. Check off completed tasks (Edit tool)
|
||||
4. Fill Dev Agent Record with pipeline details
|
||||
5. Verify updates (grep task checkboxes)
|
||||
6. Update sprint-status.yaml to "done"
|
||||
</step>
|
||||
|
||||
<step name="final_verification">
|
||||
**Final Quality Gate**
|
||||
|
||||
```bash
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
echo "🔍 FINAL VERIFICATION"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
Verify:
|
||||
1. Git commit exists
|
||||
2. Story tasks checked (count > 0)
|
||||
3. Dev Agent Record filled
|
||||
4. Sprint status updated
|
||||
|
||||
# 1. Git commit exists
|
||||
git log --oneline -3 | grep "{{story_key}}" || { echo "❌ No commit"; exit 1; }
|
||||
echo "✅ Git commit found"
|
||||
|
||||
# 2. Story tasks checked
|
||||
CHECKED=$(grep -c "^- \[x\]" docs/sprint-artifacts/{{story_key}}.md)
|
||||
[ "$CHECKED" -gt 0 ] || { echo "❌ No tasks checked"; exit 1; }
|
||||
echo "✅ $CHECKED tasks checked"
|
||||
|
||||
# 3. Dev Agent Record filled
|
||||
grep -A 3 "### Dev Agent Record" docs/sprint-artifacts/{{story_key}}.md | grep -q "202" || { echo "❌ Record not filled"; exit 1; }
|
||||
echo "✅ Dev Agent Record filled"
|
||||
|
||||
echo ""
|
||||
echo "✅ STORY COMPLETE"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
```
|
||||
|
||||
**Update sprint-status.yaml:**
|
||||
Use Edit tool to change story status from `ready-for-dev` to `done`.
|
||||
If verification fails: fix using Edit, then re-verify.
|
||||
</step>
|
||||
|
||||
</process>
|
||||
|
||||
<failure_handling>
|
||||
**Builder fails:** Don't spawn Inspector. Report failure.
|
||||
**Inspector fails:** Don't spawn Reviewer. Report specific failures.
|
||||
**Reviewer finds CRITICAL:** Fixer must fix (not optional).
|
||||
**Fixer fails:** Report unfixed issues. Manual intervention needed.
|
||||
**Reconciliation fails:** Fix using Edit tool. Re-verify.
|
||||
**Builder fails:** Don't spawn verification. Report failure and halt.
|
||||
**Inspector fails (Phase 2):** Still run Reviewers in parallel, collect all findings together.
|
||||
**Inspector fails (Phase 4):** Resume Builder again with new issues (iterative fix loop).
|
||||
**Builder resume fails:** Report unfixed issues. Manual intervention needed.
|
||||
**Reconciliation fails:** Fix using Edit tool. Re-verify checkboxes.
|
||||
</failure_handling>
|
||||
|
||||
<complexity_routing>
|
||||
| Complexity | Agents | Notes |
|
||||
|------------|--------|-------|
|
||||
| micro | Builder → Inspector → Fixer | Skip Reviewer (low risk) |
|
||||
| standard | Builder → Inspector → Reviewer → Fixer | Full pipeline |
|
||||
| complex | Builder → Inspector → Reviewer (enhanced) → Fixer | Extra scrutiny |
|
||||
| Complexity | Pipeline | Reviewers | Total Phase 2 Agents |
|
||||
|------------|----------|-----------|---------------------|
|
||||
| micro | Builder → [Inspector + 1 Reviewer] → Resume Builder → Inspector recheck | 1 (security) | 2 agents |
|
||||
| standard | Builder → [Inspector + 2 Reviewers] → Resume Builder → Inspector recheck | 2 (security, performance) | 3 agents |
|
||||
| complex | Builder → [Inspector + 3 Reviewers] → Resume Builder → Inspector recheck | 3 (security, performance, quality) | 4 agents |
|
||||
|
||||
**Key Improvement:** All verification agents spawn in parallel (single message, faster execution).
|
||||
**Token Savings:** Builder resume in Phase 3 saves 50-70% tokens vs spawning fresh Fixer.
|
||||
</complexity_routing>
|
||||
|
||||
<success_criteria>
|
||||
- [ ] All agents completed successfully
|
||||
- [ ] Builder spawned and agent_id saved
|
||||
- [ ] All verification agents completed in parallel
|
||||
- [ ] Builder resumed with consolidated findings
|
||||
- [ ] Inspector recheck passed
|
||||
- [ ] Git commit exists for story
|
||||
- [ ] Story file has checked tasks (count > 0)
|
||||
- [ ] Dev Agent Record filled
|
||||
- [ ] Dev Agent Record filled with all phases
|
||||
- [ ] Sprint status updated to "done"
|
||||
</success_criteria>
|
||||
|
|
|
|||
Loading…
Reference in New Issue