Jonah Schulte
|
e5ede9ec3f
|
feat: add complexity-based routing and pipeline optimizations (v1.3.0)
Phase 1 & 2 improvements to reduce token waste and improve robustness:
1. Complexity scoring in batch-super-dev (step 2.6)
- Score stories as micro/standard/complex based on task count + risk keywords
- Micro (≤3 tasks, low risk): lightweight path
- Standard: full pipeline
- Complex (≥16 tasks or high-risk): enhanced validation
2. Lightweight path for micro stories
- Skip pre-gap analysis (step 2) for micro complexity
- Skip code review (step 5) for micro complexity
- Estimated 50-70% token savings on simple stories
3. Smart batching clarification
- Fixed contradictory instructions in step-03-implement.md
- Default: one task at a time
- Exception: batch low-risk patterns (package installs, imports)
4. Gap analysis optimization
- dev-story skips step 1.5 if recent gap analysis exists (<24h)
- Added skip_gap_analysis flag for pre-validated stories
5. Early bailout pre-flight check (step 4.5)
- Bail early if story already complete (all tasks checked)
- Bail if no tasks found (malformed story)
- Bail if missing required sections
- Saves tokens on stories that don't need processing
6. Multi-agent review integration (step 5)
- For complex stories: recommend /multi-agent-review
- Provides architecture, security, and performance review
- Dynamic agent selection based on changed files
|
2026-01-07 16:20:34 -05:00 |
|
Jonah Schulte
|
d4b8246bd9
|
feat: add super-dev-pipeline for brownfield + anti-vibe-coding enforcement
Create new super-dev-pipeline workflow that solves critical issues:
1. Works for BOTH greenfield AND brownfield development
2. Uses step-file architecture to prevent vibe coding at high token counts
3. Adaptive implementation (TDD for new, refactor for existing)
4. All quality gates with disciplined execution
PROBLEM SOLVED:
- story-pipeline assumes greenfield (ATDD doesn't work for brownfield)
- super-dev-story allows vibe coding when tokens >100K
- Need workflow that handles real-world scenarios (most work is brownfield!)
NEW WORKFLOW: super-dev-pipeline
- 7 step files with mandatory sequences
- Detects greenfield vs brownfield automatically
- Pre-gap analysis validates against existing code
- Adaptive implementation methodology
- Post-validation catches false positives
- Code review finds 3-10 issues
- Anti-vibe-coding enforcement
STEPS:
1. Init - Load story, detect development mode
2. Pre-gap - Validate tasks against codebase (critical for brownfield!)
3. Implement - Adaptive (TDD for new, refactor for existing)
4. Post-validate - Verify completion vs reality
5. Code review - Adversarial (3-10 issues)
6. Complete - Commit + push
7. Summary - Audit trail
BENEFITS:
- Works for greenfield AND brownfield
- 40-60K tokens per story (vs 100-150K for orchestration)
- Prevents vibe coding even at 200K+ tokens
- All super-dev quality gates preserved
- Step-file discipline from story-pipeline
AUTONOMOUS-EPIC UPDATED:
- Now uses super-dev-pipeline instead of story-pipeline
- Handles create-story separately for backlog stories
- More realistic token estimates (40-60K vs 25-30K)
- Updated time estimates
FILES ADDED:
- src/modules/bmm/workflows/4-implementation/super-dev-pipeline/* (14 files)
- .claude-commands/super-dev-pipeline.md
- ~/.codex/prompts/bmad-super-dev-pipeline.md
FILES MODIFIED:
- autonomous-epic/instructions.xml (use super-dev-pipeline)
- autonomous-epic/workflow.yaml (updated settings)
INSTALLATIONS:
- craftedcall: super-dev-pipeline + updated autonomous-epic
- usmax-nda: super-dev-pipeline + updated autonomous-epic
This is the production-ready solution for autonomous epic processing!
|
2025-12-28 12:09:06 -05:00 |