Módulo 3: MCP Servers e Integrações Externas

# investigate-production-bug.md
# Production Bug Investigation Workflow

Investigate critical production bug using integrated MCP tools:

## Phase 1: Error Discovery & Triage
{{#mcp sentry}}
1. **Sentry Analysis**
   - Get error details from issue: {{issue_id}}
   - Analyze error frequency and user impact
   - Extract stack trace and affected components
{{/mcp}}

{{#mcp github}}
2. **Code Context** 
   - Find related code files from stack trace
   - Check recent commits that might have introduced the issue
   - Identify potential contributors for context
{{/mcp}}

## Phase 2: Impact Assessment
{{#mcp docker}}
3. **Infrastructure Health**
   - Check container resources and logs
   - Verify deployment status
   - Analyze performance metrics during error timeframe
{{/mcp}}

{{#mcp database}}
4. **Data Integrity Check**
   - Query patterns around error occurrence  
   - Check for data inconsistencies
   - Identify slow queries during incident
{{/mcp}}

## Phase 3: Resolution Planning
Based on gathered data:
- **Root Cause**: [To be determined from analysis]
- **Priority Level**: {{priority_level}}
- **Estimated Fix Time**: [Based on complexity]
- **Rollback Strategy**: [If immediate fix needed]

## Phase 4: Automated Actions
{{#if auto_fix_enabled}}
{{#mcp sentry}}
- Create Sentry issue assignment
- Set up error monitoring alerts
{{/mcp}}

{{#mcp github}}  
- Create GitHub issue with full context
- Assign to appropriate team members
- Create branch for fix implementation
{{/mcp}}
{{/if}}

## Output Format
Provide comprehensive bug report with:
- **Executive Summary**: Impact and urgency
- **Technical Details**: Stack traces, logs, queries
- **Resolution Plan**: Step-by-step fix approach
- **Prevention**: Long-term improvements to avoid recurrence

**Focus Area**: {{focus_area}} (if specified)
**Environment**: {{environment}}

# intelligent-deploy-pipeline.md  
# Intelligent Deploy Pipeline with MCP Integration

Execute comprehensive deployment with automated checks and rollback:

## Pre-Deploy Validation
{{#mcp github}}
### Code Quality Gates
- Run automated tests on branch: {{branch_name}}
- Check PR approval status
- Verify no merge conflicts exist
- Validate commit messages follow convention
{{/mcp}}

{{#mcp sentry}}
### Error Baseline
- Capture current error rates for comparison
- Set up deployment monitoring alerts
- Create deployment marker in Sentry
{{/mcp}}

## Deployment Execution  
{{#mcp docker}}
### Container Management
- Build new image with tag: {{version}}
- Run security scans on image
- Execute zero-downtime rolling deployment
- Health check all containers post-deploy
{{/mcp}}

{{#mcp database}}
### Database Operations
{{#if has_migrations}}
- Backup current database state
- Run migrations with rollback capability  
- Verify data integrity post-migration
{{/if}}
{{/mcp}}

## Post-Deploy Monitoring
{{#mcp sentry}}
### Error Monitoring (15-minute window)
- Monitor error rate increase >20% → Auto-rollback
- Check for new error types introduced
- Validate critical user journeys
{{/mcp}}

{{#mcp github}}
### Documentation Updates
- Update CHANGELOG.md with deployment info
- Create release notes from commits
- Close related issues automatically
{{/mcp}}

## Rollback Strategy
If issues detected:
1. **Immediate**: Rollback containers to previous version
2. **Database**: Restore from pre-deploy backup if needed
3. **Monitoring**: Reset alerts and create incident report
4. **Communication**: Auto-notify team via GitHub issue

## Success Criteria
- ✅ Zero critical errors in 15-minute window
- ✅ Response times within 10% of baseline  
- ✅ All health checks passing
- ✅ Database integrity verified

**Environment**: {{environment}}
**Version**: {{version}}
**Rollback Enabled**: {{auto_rollback}}