siesa-agents 2.1.39 → 2.1.41

package/bmad/bmm/workflows/testarch/automate/workflow.yaml

@@ -0,0 +1,52 @@
+# Test Architect workflow: automate
+name: testarch-automate
+description: "Expand test automation coverage after implementation or analyze existing codebase to generate comprehensive test suite"
+author: "BMad"
+
+# Critical variables from config
+config_source: "{project-root}/_bmad/bmm/config.yaml"
+output_folder: "{config_source}:output_folder"
+user_name: "{config_source}:user_name"
+communication_language: "{config_source}:communication_language"
+document_output_language: "{config_source}:document_output_language"
+date: system-generated
+
+# Workflow components
+installed_path: "{project-root}/_bmad/bmm/workflows/testarch/automate"
+instructions: "{installed_path}/instructions.md"
+validation: "{installed_path}/checklist.md"
+template: false
+
+# Variables and inputs
+variables:
+  # Execution mode and targeting
+  standalone_mode: true # Can work without BMad artifacts (true) or integrate with BMad (false)
+  coverage_target: "critical-paths" # critical-paths, comprehensive, selective
+
+  # Directory paths
+  test_dir: "{project-root}/tests" # Root test directory
+  source_dir: "{project-root}/src" # Source code directory
+
+# Output configuration
+default_output_file: "{output_folder}/automation-summary.md"
+
+# Required tools
+required_tools:
+  - read_file # Read source code, existing tests, BMad artifacts
+  - write_file # Create test files, fixtures, factories, summaries
+  - create_directory # Create test directories
+  - list_files # Discover features and existing tests
+  - search_repo # Find coverage gaps and patterns
+  - glob # Find test files and source files
+
+tags:
+  - qa
+  - automation
+  - test-architect
+  - regression
+  - coverage
+
+execution_hints:
+  interactive: false # Minimize prompts
+  autonomous: true # Proceed without user input unless blocked
+  iterative: true

package/bmad/bmm/workflows/testarch/ci/checklist.md

@@ -0,0 +1,248 @@
+# CI/CD Pipeline Setup - Validation Checklist
+
+## Prerequisites
+
+- [ ] Git repository initialized (`.git/` exists)
+- [ ] Git remote configured (`git remote -v` shows origin)
+- [ ] Test framework configured (`playwright.config._` or `cypress.config._`)
+- [ ] Local tests pass (`npm run test:e2e` succeeds)
+- [ ] Team agrees on CI platform
+- [ ] Access to CI platform settings (if updating)
+
+Note: CI setup is typically a one-time task per repo and can be run any time after the test framework is configured.
+
+## Process Steps
+
+### Step 1: Preflight Checks
+
+- [ ] Git repository validated
+- [ ] Framework configuration detected
+- [ ] Local test execution successful
+- [ ] CI platform detected or selected
+- [ ] Node version identified (.nvmrc or default)
+- [ ] No blocking issues found
+
+### Step 2: CI Pipeline Configuration
+
+- [ ] CI configuration file created (`.github/workflows/test.yml` or `.gitlab-ci.yml`)
+- [ ] File is syntactically valid (no YAML errors)
+- [ ] Correct framework commands configured
+- [ ] Node version matches project
+- [ ] Test directory paths correct
+
+### Step 3: Parallel Sharding
+
+- [ ] Matrix strategy configured (4 shards default)
+- [ ] Shard syntax correct for framework
+- [ ] fail-fast set to false
+- [ ] Shard count appropriate for test suite size
+
+### Step 4: Burn-In Loop
+
+- [ ] Burn-in job created
+- [ ] 10 iterations configured
+- [ ] Proper exit on failure (`|| exit 1`)
+- [ ] Runs on appropriate triggers (PR, cron)
+- [ ] Failure artifacts uploaded
+
+### Step 5: Caching Configuration
+
+- [ ] Dependency cache configured (npm/yarn)
+- [ ] Cache key uses lockfile hash
+- [ ] Browser cache configured (Playwright/Cypress)
+- [ ] Restore-keys defined for fallback
+- [ ] Cache paths correct for platform
+
+### Step 6: Artifact Collection
+
+- [ ] Artifacts upload on failure only
+- [ ] Correct artifact paths (test-results/, traces/, etc.)
+- [ ] Retention days set (30 default)
+- [ ] Artifact names unique per shard
+- [ ] No sensitive data in artifacts
+
+### Step 7: Retry Logic
+
+- [ ] Retry action/strategy configured
+- [ ] Max attempts: 2-3
+- [ ] Timeout appropriate (30 min)
+- [ ] Retry only on transient errors
+
+### Step 8: Helper Scripts
+
+- [ ] `scripts/test-changed.sh` created
+- [ ] `scripts/ci-local.sh` created
+- [ ] `scripts/burn-in.sh` created (optional)
+- [ ] Scripts are executable (`chmod +x`)
+- [ ] Scripts use correct test commands
+- [ ] Shebang present (`#!/bin/bash`)
+
+### Step 9: Documentation
+
+- [ ] `docs/ci.md` created with pipeline guide
+- [ ] `docs/ci-secrets-checklist.md` created
+- [ ] Required secrets documented
+- [ ] Setup instructions clear
+- [ ] Troubleshooting section included
+- [ ] Badge URLs provided (optional)
+
+## Output Validation
+
+### Configuration Validation
+
+- [ ] CI file loads without errors
+- [ ] All paths resolve correctly
+- [ ] No hardcoded values (use env vars)
+- [ ] Triggers configured (push, pull_request, schedule)
+- [ ] Platform-specific syntax correct
+
+### Execution Validation
+
+- [ ] First CI run triggered (push to remote)
+- [ ] Pipeline starts without errors
+- [ ] All jobs appear in CI dashboard
+- [ ] Caching works (check logs for cache hit)
+- [ ] Tests execute in parallel
+- [ ] Artifacts collected on failure
+
+### Performance Validation
+
+- [ ] Lint stage: <2 minutes
+- [ ] Test stage (per shard): <10 minutes
+- [ ] Burn-in stage: <30 minutes
+- [ ] Total pipeline: <45 minutes
+- [ ] Cache reduces install time by 2-5 minutes
+
+## Quality Checks
+
+### Best Practices Compliance
+
+- [ ] Burn-in loop follows production patterns
+- [ ] Parallel sharding configured optimally
+- [ ] Failure-only artifact collection
+- [ ] Selective testing enabled (optional)
+- [ ] Retry logic handles transient failures only
+- [ ] No secrets in configuration files
+
+### Knowledge Base Alignment
+
+- [ ] Burn-in pattern matches `ci-burn-in.md`
+- [ ] Selective testing matches `selective-testing.md`
+- [ ] Artifact collection matches `visual-debugging.md`
+- [ ] Test quality matches `test-quality.md`
+
+### Security Checks
+
+- [ ] No credentials in CI configuration
+- [ ] Secrets use platform secret management
+- [ ] Environment variables for sensitive data
+- [ ] Artifact retention appropriate (not too long)
+- [ ] No debug output exposing secrets
+
+## Integration Points
+
+### Status File Integration
+
+- [ ] `bmm-workflow-status.md` exists
+- [ ] CI setup logged in Quality & Testing Progress section
+- [ ] Status updated with completion timestamp
+- [ ] Platform and configuration noted
+
+### Knowledge Base Integration
+
+- [ ] Relevant knowledge fragments loaded
+- [ ] Patterns applied from knowledge base
+- [ ] Documentation references knowledge base
+- [ ] Knowledge base references in README
+
+### Workflow Dependencies
+
+- [ ] `framework` workflow completed first
+- [ ] Can proceed to `atdd` workflow after CI setup
+- [ ] Can proceed to `automate` workflow
+- [ ] CI integrates with `gate` workflow
+
+## Completion Criteria
+
+**All must be true:**
+
+- [ ] All prerequisites met
+- [ ] All process steps completed
+- [ ] All output validations passed
+- [ ] All quality checks passed
+- [ ] All integration points verified
+- [ ] First CI run successful
+- [ ] Performance targets met
+- [ ] Documentation complete
+
+## Post-Workflow Actions
+
+**User must complete:**
+
+1. [ ] Commit CI configuration
+2. [ ] Push to remote repository
+3. [ ] Configure required secrets in CI platform
+4. [ ] Open PR to trigger first CI run
+5. [ ] Monitor and verify pipeline execution
+6. [ ] Adjust parallelism if needed (based on actual run times)
+7. [ ] Set up notifications (optional)
+
+**Recommended next workflows:**
+
+1. [ ] Run `atdd` workflow for test generation
+2. [ ] Run `automate` workflow for coverage expansion
+3. [ ] Run `gate` workflow for quality gates
+
+## Rollback Procedure
+
+If workflow fails:
+
+1. [ ] Delete CI configuration file
+2. [ ] Remove helper scripts directory
+3. [ ] Remove documentation (docs/ci.md, etc.)
+4. [ ] Clear CI platform secrets (if added)
+5. [ ] Review error logs
+6. [ ] Fix issues and retry workflow
+
+## Notes
+
+### Common Issues
+
+**Issue**: CI file syntax errors
+
+- **Solution**: Validate YAML syntax online or with linter
+
+**Issue**: Tests fail in CI but pass locally
+
+- **Solution**: Use `scripts/ci-local.sh` to mirror CI environment
+
+**Issue**: Caching not working
+
+- **Solution**: Check cache key formula, verify paths
+
+**Issue**: Burn-in too slow
+
+- **Solution**: Reduce iterations or run on cron only
+
+### Platform-Specific
+
+**GitHub Actions:**
+
+- Secrets: Repository Settings → Secrets and variables → Actions
+- Runners: Ubuntu latest recommended
+- Concurrency limits: 20 jobs for free tier
+
+**GitLab CI:**
+
+- Variables: Project Settings → CI/CD → Variables
+- Runners: Shared or project-specific
+- Pipeline quota: 400 minutes/month free tier
+
+---
+
+**Checklist Complete**: Sign off when all items validated.
+
+**Completed by:** {name}
+**Date:** {date}
+**Platform:** {GitHub Actions, GitLab CI, Other}
+**Notes:** {notes}

package/bmad/bmm/workflows/testarch/ci/github-actions-template.yaml

@@ -0,0 +1,198 @@
+# GitHub Actions CI/CD Pipeline for Test Execution
+# Generated by BMad TEA Agent - Test Architect Module
+# Optimized for: Playwright/Cypress, Parallel Sharding, Burn-In Loop
+
+name: Test Pipeline
+
+on:
+  push:
+    branches: [main, develop]
+  pull_request:
+    branches: [main, develop]
+  schedule:
+    # Weekly burn-in on Sundays at 2 AM UTC
+    - cron: "0 2 * * 0"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  # Lint stage - Code quality checks
+  lint:
+    name: Lint
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Determine Node version
+        id: node-version
+        run: |
+          if [ -f .nvmrc ]; then
+            echo "value=$(cat .nvmrc)" >> "$GITHUB_OUTPUT"
+            echo "Using Node from .nvmrc"
+          else
+            echo "value=24" >> "$GITHUB_OUTPUT"
+            echo "Using default Node 24 (current LTS)"
+          fi
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ steps.node-version.outputs.value }}
+          cache: "npm"
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Run linter
+        run: npm run lint
+
+  # Test stage - Parallel execution with sharding
+  test:
+    name: Test (Shard ${{ matrix.shard }})
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    needs: lint
+
+    strategy:
+      fail-fast: false
+      matrix:
+        shard: [1, 2, 3, 4]
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Determine Node version
+        id: node-version
+        run: |
+          if [ -f .nvmrc ]; then
+            echo "value=$(cat .nvmrc)" >> "$GITHUB_OUTPUT"
+            echo "Using Node from .nvmrc"
+          else
+            echo "value=22" >> "$GITHUB_OUTPUT"
+            echo "Using default Node 22 (current LTS)"
+          fi
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ steps.node-version.outputs.value }}
+          cache: "npm"
+
+      - name: Cache Playwright browsers
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/ms-playwright
+          key: ${{ runner.os }}-playwright-${{ hashFiles('**/package-lock.json') }}
+          restore-keys: |
+            ${{ runner.os }}-playwright-
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Install Playwright browsers
+        run: npx playwright install --with-deps chromium
+
+      - name: Run tests (shard ${{ matrix.shard }}/4)
+        run: npm run test:e2e -- --shard=${{ matrix.shard }}/4
+
+      - name: Upload test results
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: test-results-${{ matrix.shard }}
+          path: |
+            test-results/
+            playwright-report/
+          retention-days: 30
+
+  # Burn-in stage - Flaky test detection
+  burn-in:
+    name: Burn-In (Flaky Detection)
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+    needs: test
+    # Only run burn-in on PRs to main/develop or on schedule
+    if: github.event_name == 'pull_request' || github.event_name == 'schedule'
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Determine Node version
+        id: node-version
+        run: |
+          if [ -f .nvmrc ]; then
+            echo "value=$(cat .nvmrc)" >> "$GITHUB_OUTPUT"
+            echo "Using Node from .nvmrc"
+          else
+            echo "value=22" >> "$GITHUB_OUTPUT"
+            echo "Using default Node 22 (current LTS)"
+          fi
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ steps.node-version.outputs.value }}
+          cache: "npm"
+
+      - name: Cache Playwright browsers
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/ms-playwright
+          key: ${{ runner.os }}-playwright-${{ hashFiles('**/package-lock.json') }}
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Install Playwright browsers
+        run: npx playwright install --with-deps chromium
+
+      - name: Run burn-in loop (10 iterations)
+        run: |
+          echo "🔥 Starting burn-in loop - detecting flaky tests"
+          for i in {1..10}; do
+            echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+            echo "🔥 Burn-in iteration $i/10"
+            echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+            npm run test:e2e || exit 1
+          done
+          echo "✅ Burn-in complete - no flaky tests detected"
+
+      - name: Upload burn-in failure artifacts
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: burn-in-failures
+          path: |
+            test-results/
+            playwright-report/
+          retention-days: 30
+
+  # Report stage - Aggregate and publish results
+  report:
+    name: Test Report
+    runs-on: ubuntu-latest
+    needs: [test, burn-in]
+    if: always()
+
+    steps:
+      - name: Download all artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: artifacts
+
+      - name: Generate summary
+        run: |
+          echo "## Test Execution Summary" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+          echo "- **Status**: ${{ needs.test.result }}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Burn-in**: ${{ needs.burn-in.result }}" >> $GITHUB_STEP_SUMMARY
+          echo "- **Shards**: 4" >> $GITHUB_STEP_SUMMARY
+          echo "" >> $GITHUB_STEP_SUMMARY
+
+          if [ "${{ needs.burn-in.result }}" == "failure" ]; then
+            echo "⚠️ **Flaky tests detected** - Review burn-in artifacts" >> $GITHUB_STEP_SUMMARY
+          fi

package/bmad/bmm/workflows/testarch/ci/gitlab-ci-template.yaml

@@ -0,0 +1,149 @@
+# GitLab CI/CD Pipeline for Test Execution
+# Generated by BMad TEA Agent - Test Architect Module
+# Optimized for: Playwright/Cypress, Parallel Sharding, Burn-In Loop
+
+stages:
+  - lint
+  - test
+  - burn-in
+  - report
+
+variables:
+  # Disable git depth for accurate change detection
+  GIT_DEPTH: 0
+  # Use npm ci for faster, deterministic installs
+  npm_config_cache: "$CI_PROJECT_DIR/.npm"
+  # Playwright browser cache
+  PLAYWRIGHT_BROWSERS_PATH: "$CI_PROJECT_DIR/.cache/ms-playwright"
+  # Default Node version when .nvmrc is missing
+  DEFAULT_NODE_VERSION: "24"
+
+# Caching configuration
+cache:
+  key:
+    files:
+      - package-lock.json
+  paths:
+    - .npm/
+    - .cache/ms-playwright/
+    - node_modules/
+
+# Lint stage - Code quality checks
+lint:
+  stage: lint
+  image: node:$DEFAULT_NODE_VERSION
+  before_script:
+    - |
+      NODE_VERSION=$(cat .nvmrc 2>/dev/null || echo "$DEFAULT_NODE_VERSION")
+      echo "Using Node $NODE_VERSION"
+      npm install -g n
+      n "$NODE_VERSION"
+      node -v
+    - npm ci
+  script:
+    - npm run lint
+  timeout: 5 minutes
+
+# Test stage - Parallel execution with sharding
+.test-template: &test-template
+  stage: test
+  image: node:$DEFAULT_NODE_VERSION
+  needs:
+    - lint
+  before_script:
+    - |
+      NODE_VERSION=$(cat .nvmrc 2>/dev/null || echo "$DEFAULT_NODE_VERSION")
+      echo "Using Node $NODE_VERSION"
+      npm install -g n
+      n "$NODE_VERSION"
+      node -v
+    - npm ci
+    - npx playwright install --with-deps chromium
+  artifacts:
+    when: on_failure
+    paths:
+      - test-results/
+      - playwright-report/
+    expire_in: 30 days
+  timeout: 30 minutes
+
+test:shard-1:
+  <<: *test-template
+  script:
+    - npm run test:e2e -- --shard=1/4
+
+test:shard-2:
+  <<: *test-template
+  script:
+    - npm run test:e2e -- --shard=2/4
+
+test:shard-3:
+  <<: *test-template
+  script:
+    - npm run test:e2e -- --shard=3/4
+
+test:shard-4:
+  <<: *test-template
+  script:
+    - npm run test:e2e -- --shard=4/4
+
+# Burn-in stage - Flaky test detection
+burn-in:
+  stage: burn-in
+  image: node:$DEFAULT_NODE_VERSION
+  needs:
+    - test:shard-1
+    - test:shard-2
+    - test:shard-3
+    - test:shard-4
+  # Only run burn-in on merge requests to main/develop or on schedule
+  rules:
+    - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
+    - if: '$CI_PIPELINE_SOURCE == "schedule"'
+  before_script:
+    - |
+      NODE_VERSION=$(cat .nvmrc 2>/dev/null || echo "$DEFAULT_NODE_VERSION")
+      echo "Using Node $NODE_VERSION"
+      npm install -g n
+      n "$NODE_VERSION"
+      node -v
+    - npm ci
+    - npx playwright install --with-deps chromium
+  script:
+    - |
+      echo "🔥 Starting burn-in loop - detecting flaky tests"
+      for i in {1..10}; do
+        echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+        echo "🔥 Burn-in iteration $i/10"
+        echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
+        npm run test:e2e || exit 1
+      done
+      echo "✅ Burn-in complete - no flaky tests detected"
+  artifacts:
+    when: on_failure
+    paths:
+      - test-results/
+      - playwright-report/
+    expire_in: 30 days
+  timeout: 60 minutes
+
+# Report stage - Aggregate results
+report:
+  stage: report
+  image: alpine:latest
+  needs:
+    - test:shard-1
+    - test:shard-2
+    - test:shard-3
+    - test:shard-4
+    - burn-in
+  when: always
+  script:
+    - |
+      echo "## Test Execution Summary"
+      echo ""
+      echo "- Pipeline: $CI_PIPELINE_ID"
+      echo "- Shards: 4"
+      echo "- Branch: $CI_COMMIT_REF_NAME"
+      echo ""
+      echo "View detailed results in job artifacts"