ldy26098
/
BMAD-METHOD
mirror of https://github.com/bmad-code-org/BMAD-METHOD.git
1
0
Fork 0
Code Packages Projects Releases Wiki Activity
1,302 Commits 62 Branches 141 Tags 74 MiB
Commit Graph

4 Commits

Author SHA1 Message Date
Jonah Schulte 1ddf2afcea feat: enhance sprint scripts with smart path resolution and conditional batching 
- Add auto-detection of project root and story directories
- Enable scripts to work from any working directory
- Add explicit path override options via CLI arguments
- Improve error messages with suggested paths when files not found
- Update smart batching to show options only when time_saved > 0
- Reduce decision fatigue by skipping batching menu when no benefit
 2026-01-06 08:21:44 -05:00
Jonah Schulte 343e029250 feat(validation): Add progress tracker for resumable validation runs 
Enables resume capability for long-running validation (4-6 hour runs)
 2026-01-02 19:21:26 -05:00
Jonah Schulte 73b8190e7b feat(validation): Add comprehensive story validation system with Haiku agents 
VALIDATION WORKFLOWS (6 total):
- validate-story: Quick task checkbox validation
- validate-story-deep: Deep code verification with Haiku agent
- validate-all-stories: Batch quick validation
- validate-all-stories-deep: Comprehensive platform audit
- validate-epic-status: Per-epic validation
- validate-all-epics: All epics validation

VALIDATION SCRIPTS (4 total):
- sprint-status-updater.py: Compare story files vs sprint-status.yaml
- task-verification-engine.py: Python-based task verification
- llm-task-verifier.py: LLM-powered verification (alternative)
- add-status-fields.py: Add Status field to stories

HAIKU AGENT APPROACH:
- One agent per story (not per task - avoids 99% overhead)
- Agent reads actual code with Glob/Read tools
- Verifies stubs vs real implementation
- Checks multi-tenant, error handling, tests
- Evidence-based verification (line numbers, code snippets)

COST OPTIMIZATION:
- Haiku: $0.15/story vs Sonnet: $1.80/story (92% savings)
- Full platform: $76 vs $920 (saves $844)
- Batching: 5 concurrent agents (prevents overload)

CAPABILITIES:
- False positive detection (checked but code missing)
- False negative detection (unchecked but code exists)
- Code quality review (TODOs, stubs, missing features)
- Status recommendation (done/review/in-progress)
- Automated status updates

DOCUMENTATION:
- HOW-TO-VALIDATE-SPRINT-STATUS.md
- SPRINT-STATUS-VALIDATION-COMPLETE.md
- Slash command docs in .claude-commands/

USE CASES:
- Weekly: Quick validation (free, 5 sec)
- Pre-done: Deep story check ($0.15, 2-5 min)
- Pre-launch: Full audit ($76, 4-6h)
- Quality sweep: Phase 3 comprehensive validation

Enables bulletproof production confidence for any BMAD project.
 2026-01-02 19:20:11 -05:00
Jonah Schulte afaba40f80 feat(workflows): Add --epic and --mode flags to sprint-status-updater.py 
- Add --epic flag to filter validation to specific epic (e.g., epic-1)
- Add --mode flag with 'validate' and 'fix' options
- Filter logic extracts epic number and matches story file prefixes
- Enables per-epic validation for validate-all-epics workflow

Part of: validate-all-epics workflow infrastructure
 2026-01-02 17:46:27 -05:00