ldy26098
/
BMAD-METHOD
mirror of https://github.com/bmad-code-org/BMAD-METHOD.git
1
0
Fork 0
Code Packages Projects Releases Wiki Activity
1,150 Commits 142 Branches 161 Tags 126 MiB
Commit Graph

2 Commits

Author SHA1 Message Date
Caleb 9f532eff65 feat(uat-validate): add human intervention detection and enhanced fix context 
- Add human intervention detection with BLOCKING/WARNING pattern matching
  - Detects .env issues, API keys, permissions, connection failures
  - Categorizes issues for Barry to handle appropriately

- Add story context extraction for fix documents
  - Extracts acceptance criteria from story files
  - Includes Dev Agent Record (implementation notes)

- Enhance fix context generation
  - Includes human intervention items section
  - Adds root cause hints for each failure
  - Appends story context with AC mapping

- Add human actions file generation
  - Creates epic-{id}-human-actions.md with actionable checklist
  - Provides specific guidance per issue type

- Add timing metrics to track UAT evaluation duration
  - Captures start_time, end_time, duration_seconds
  - Shows duration in summary output

- Update output signals with human action flags
  - UAT_HUMAN_ACTION_REQUIRED: true/false
  - UAT_HUMAN_ACTION_COUNT: N
  - UAT_HUMAN_ACTION_FILE: path

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-19 04:37:29 -06:00
Caleb 15b7bb1ae6 feat: implement UAT validation with self-healing fix loop 
Add complete UAT validation workflow implementation:

- scripts/uat-validate.sh: Core UAT validation script with scenario
  classification, automated execution, and self-healing fix loop
- scripts/epic-execute.sh: Add metrics instrumentation for story
  execution tracking (init, update, finalize metrics)
- scripts/epic-chain.sh: Integrate UAT gate after each epic with
  configurable blocking mode, and add report generation phase

New workflow step documentation:
- step-01-load-uat.md: UAT document loading and parsing
- step-02-classify-scenarios.md: Scenario classification logic
- step-03-execute-scenarios.md: Automated scenario execution
- step-04-evaluate-gate.md: Gate evaluation and fix loop
- step-05-report-results.md: Metrics and signal output

Key features:
- Gate modes: quick (automatable only), full (+ semi-auto), skip
- Self-healing: spawns fresh Claude context for targeted fixes
- Metrics: YAML files track execution stats and UAT results
- Signals: parseable output for orchestration (UAT_GATE_RESULT, etc.)
- Handoffs: include UAT status and fix context references

Also fixes lint/format issues in pre-existing files.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-05 19:24:18 -06:00