feat(workflows): add auto-branch creation from labeled issues #110
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Workflow Health Monitor | ||
| on: | ||
| schedule: | ||
| # Run every 6 hours | ||
| - cron: '0 */6 * * *' | ||
| workflow_dispatch: # Allow manual triggering | ||
| permissions: | ||
| contents: read | ||
| issues: write | ||
| jobs: | ||
| health-check: | ||
| runs-on: ubuntu-latest | ||
| timeout-minutes: 5 | ||
| env: | ||
| GH_TOKEN: ${{ secrets.GITHUB_TOKEN }} | ||
| steps: | ||
| - name: Check Rate Limits | ||
| id: rate_limits | ||
| run: | | ||
| echo "🔍 Checking GitHub API rate limits..." | ||
| # Get rate limit data | ||
| RATE_DATA=$(gh api rate_limit) | ||
| # Extract values | ||
| core_remaining=$(echo "$RATE_DATA" | jq '.resources.core.remaining') | ||
| core_limit=$(echo "$RATE_DATA" | jq '.resources.core.limit') | ||
| core_reset=$(echo "$RATE_DATA" | jq '.resources.core.reset') | ||
| graphql_remaining=$(echo "$RATE_DATA" | jq '.resources.graphql.remaining') | ||
| graphql_limit=$(echo "$RATE_DATA" | jq '.resources.graphql.limit') | ||
| graphql_reset=$(echo "$RATE_DATA" | jq '.resources.graphql.reset') | ||
| # Calculate percentages | ||
| core_pct=$((core_remaining * 100 / core_limit)) | ||
| graphql_pct=$((graphql_remaining * 100 / graphql_limit)) | ||
| # Store for next step | ||
| echo "core_remaining=$core_remaining" >> $GITHUB_OUTPUT | ||
| echo "core_limit=$core_limit" >> $GITHUB_OUTPUT | ||
| echo "core_pct=$core_pct" >> $GITHUB_OUTPUT | ||
| echo "graphql_remaining=$graphql_remaining" >> $GITHUB_OUTPUT | ||
| echo "graphql_limit=$graphql_limit" >> $GITHUB_OUTPUT | ||
| echo "graphql_pct=$graphql_pct" >> $GITHUB_OUTPUT | ||
| # Convert reset timestamps to human-readable | ||
| core_reset_time=$(date -d @$core_reset '+%Y-%m-%d %H:%M:%S UTC' 2>/dev/null || date -r $core_reset '+%Y-%m-%d %H:%M:%S UTC') | ||
| graphql_reset_time=$(date -d @$graphql_reset '+%Y-%m-%d %H:%M:%S UTC' 2>/dev/null || date -r $graphql_reset '+%Y-%m-%d %H:%M:%S UTC') | ||
| echo "core_reset_time=$core_reset_time" >> $GITHUB_OUTPUT | ||
| echo "graphql_reset_time=$graphql_reset_time" >> $GITHUB_OUTPUT | ||
| # Determine health status | ||
| if [ $core_pct -lt 20 ] || [ $graphql_pct -lt 20 ]; then | ||
| echo "status=critical" >> $GITHUB_OUTPUT | ||
| echo "🚨 CRITICAL: Rate limits below 20%" | ||
| elif [ $core_pct -lt 40 ] || [ $graphql_pct -lt 40 ]; then | ||
| echo "status=warning" >> $GITHUB_OUTPUT | ||
| echo "⚠️ WARNING: Rate limits below 40%" | ||
| else | ||
| echo "status=healthy" >> $GITHUB_OUTPUT | ||
| echo "✅ HEALTHY: Rate limits above 40%" | ||
| fi | ||
| echo "" | ||
| echo "📊 Rate Limit Summary:" | ||
| echo " REST API: $core_remaining/$core_limit ($core_pct%)" | ||
| echo " GraphQL API: $graphql_remaining/$graphql_limit ($graphql_pct%)" | ||
| - name: Check Workflow Statistics | ||
| id: workflow_stats | ||
| run: | | ||
| echo "📈 Checking workflow run statistics (last 24 hours)..." | ||
| # Get workflow runs from last 24 hours | ||
| YESTERDAY=$(date -u -d '24 hours ago' +%Y-%m-%dT%H:%M:%SZ 2>/dev/null || date -u -v-24H +%Y-%m-%dT%H:%M:%SZ) | ||
| RUNS=$(gh api "repos/${{ github.repository }}/actions/runs?created=>=$YESTERDAY&per_page=100" --jq '.workflow_runs') | ||
| # Count runs by status | ||
| total=$(echo "$RUNS" | jq 'length') | ||
| success=$(echo "$RUNS" | jq '[.[] | select(.conclusion == "success")] | length') | ||
| failure=$(echo "$RUNS" | jq '[.[] | select(.conclusion == "failure")] | length') | ||
| cancelled=$(echo "$RUNS" | jq '[.[] | select(.conclusion == "cancelled")] | length') | ||
| in_progress=$(echo "$RUNS" | jq '[.[] | select(.status == "in_progress")] | length') | ||
| # Calculate success rate | ||
| if [ $total -gt 0 ]; then | ||
| success_rate=$((success * 100 / total)) | ||
| else | ||
| success_rate=100 | ||
| fi | ||
| # Store for next step | ||
| echo "total=$total" >> $GITHUB_OUTPUT | ||
| echo "success=$success" >> $GITHUB_OUTPUT | ||
| echo "failure=$failure" >> $GITHUB_OUTPUT | ||
| echo "cancelled=$cancelled" >> $GITHUB_OUTPUT | ||
| echo "in_progress=$in_progress" >> $GITHUB_OUTPUT | ||
| echo "success_rate=$success_rate" >> $GITHUB_OUTPUT | ||
| # Determine workflow health | ||
| if [ $success_rate -lt 70 ]; then | ||
| echo "workflow_status=critical" >> $GITHUB_OUTPUT | ||
| echo "🚨 Workflow success rate: $success_rate% (CRITICAL)" | ||
| elif [ $success_rate -lt 85 ]; then | ||
| echo "workflow_status=warning" >> $GITHUB_OUTPUT | ||
| echo "⚠️ Workflow success rate: $success_rate% (WARNING)" | ||
| else | ||
| echo "workflow_status=healthy" >> $GITHUB_OUTPUT | ||
| echo "✅ Workflow success rate: $success_rate% (HEALTHY)" | ||
| fi | ||
| echo "" | ||
| echo "📊 Workflow Statistics (24h):" | ||
| echo " Total: $total runs" | ||
| echo " Success: $success" | ||
| echo " Failure: $failure" | ||
| echo " Cancelled: $cancelled" | ||
| echo " In Progress: $in_progress" | ||
| echo " Success Rate: $success_rate%" | ||
| - name: Check Task Hierarchy Health | ||
| id: hierarchy_health | ||
| run: | | ||
| echo "🏗️ Checking task hierarchy health..." | ||
| # Count plan issues | ||
| plans=$(gh issue list --label "plan" --state all --limit 100 --json number --jq 'length') | ||
| plans_open=$(gh issue list --label "plan" --state open --limit 100 --json number --jq 'length') | ||
| # Count task issues | ||
| tasks=$(gh issue list --label "task" --state all --limit 500 --json number --jq 'length') | ||
| tasks_open=$(gh issue list --label "task" --state open --limit 500 --json number --jq 'length') | ||
| # Count subtask issues | ||
| subtasks=$(gh issue list --label "subtask" --state all --limit 500 --json number --jq 'length') | ||
| subtasks_open=$(gh issue list --label "subtask" --state open --limit 500 --json number --jq 'length') | ||
| # Store for next step | ||
| echo "plans=$plans" >> $GITHUB_OUTPUT | ||
| echo "plans_open=$plans_open" >> $GITHUB_OUTPUT | ||
| echo "tasks=$tasks" >> $GITHUB_OUTPUT | ||
| echo "tasks_open=$tasks_open" >> $GITHUB_OUTPUT | ||
| echo "subtasks=$subtasks" >> $GITHUB_OUTPUT | ||
| echo "subtasks_open=$subtasks_open" >> $GITHUB_OUTPUT | ||
| echo "" | ||
| echo "📊 Hierarchy Statistics:" | ||
| echo " Plans: $plans_open open / $plans total" | ||
| echo " Tasks: $tasks_open open / $tasks total" | ||
| echo " Subtasks: $subtasks_open open / $subtasks total" | ||
| - name: Create Health Report Issue (if problems detected) | ||
| if: steps.rate_limits.outputs.status != 'healthy' || steps.workflow_stats.outputs.workflow_status != 'healthy' | ||
| run: | | ||
| STATUS="${{ steps.rate_limits.outputs.status }}" | ||
| WORKFLOW_STATUS="${{ steps.workflow_stats.outputs.workflow_status }}" | ||
| # Determine severity | ||
| if [ "$STATUS" = "critical" ] || [ "$WORKFLOW_STATUS" = "critical" ]; then | ||
| SEVERITY="🚨 CRITICAL" | ||
| LABEL="priority: high" | ||
| else | ||
| SEVERITY="⚠️ WARNING" | ||
| LABEL="priority: medium" | ||
| fi | ||
| # Create issue body | ||
| BODY=$(cat <<EOF | ||
| ## $SEVERITY Workflow Health Alert | ||
| **Generated**: $(date -u '+%Y-%m-%d %H:%M:%S UTC') | ||
| ### 📊 Rate Limits | ||
| | Resource | Remaining | Limit | Usage | | ||
| |----------|-----------|-------|-------| | ||
| | REST API | ${{ steps.rate_limits.outputs.core_remaining }} | ${{ steps.rate_limits.outputs.core_limit }} | ${{ steps.rate_limits.outputs.core_pct }}% | | ||
| | GraphQL API | ${{ steps.rate_limits.outputs.graphql_remaining }} | ${{ steps.rate_limits.outputs.graphql_limit }} | ${{ steps.rate_limits.outputs.graphql_pct }}% | | ||
| **Reset Times**: | ||
| - REST API: ${{ steps.rate_limits.outputs.core_reset_time }} | ||
| - GraphQL API: ${{ steps.rate_limits.outputs.graphql_reset_time }} | ||
| ### 📈 Workflow Statistics (Last 24 Hours) | ||
| | Metric | Count | Percentage | | ||
| |--------|-------|------------| | ||
| | Total Runs | ${{ steps.workflow_stats.outputs.total }} | - | | ||
| | Successful | ${{ steps.workflow_stats.outputs.success }} | ${{ steps.workflow_stats.outputs.success_rate }}% | | ||
| | Failed | ${{ steps.workflow_stats.outputs.failure }} | - | | ||
| | Cancelled | ${{ steps.workflow_stats.outputs.cancelled }} | - | | ||
| | In Progress | ${{ steps.workflow_stats.outputs.in_progress }} | - | | ||
| ### 🏗️ Task Hierarchy | ||
| | Level | Open | Total | | ||
| |-------|------|-------| | ||
| | Plans | ${{ steps.hierarchy_health.outputs.plans_open }} | ${{ steps.hierarchy_health.outputs.plans }} | | ||
| | Tasks | ${{ steps.hierarchy_health.outputs.tasks_open }} | ${{ steps.hierarchy_health.outputs.tasks }} | | ||
| | Subtasks | ${{ steps.hierarchy_health.outputs.subtasks_open }} | ${{ steps.hierarchy_health.outputs.subtasks }} | | ||
| ### 🔧 Recommended Actions | ||
| EOF | ||
| ) | ||
| # Add specific recommendations based on status | ||
| if [ "$STATUS" = "critical" ]; then | ||
| BODY="$BODY | ||
| **Rate Limit Issues**: | ||
| - ⚠️ Rate limits are critically low (<20%) | ||
| - Pause non-critical workflow activity | ||
| - Wait for rate limit reset | ||
| - Consider reducing workflow frequency | ||
| " | ||
| elif [ "$STATUS" = "warning" ]; then | ||
| BODY="$BODY | ||
| **Rate Limit Issues**: | ||
| - ⚠️ Rate limits are getting low (<40%) | ||
| - Monitor workflow activity | ||
| - Consider optimizing API usage | ||
| " | ||
| fi | ||
| if [ "$WORKFLOW_STATUS" = "critical" ]; then | ||
| BODY="$BODY | ||
| **Workflow Health Issues**: | ||
| - ⚠️ Success rate below 70% | ||
| - Review failed workflow runs | ||
| - Check for systematic issues | ||
| - Fix failing workflows | ||
| " | ||
| elif [ "$WORKFLOW_STATUS" = "warning" ]; then | ||
| BODY="$BODY | ||
| **Workflow Health Issues**: | ||
| - ⚠️ Success rate below 85% | ||
| - Monitor workflow failures | ||
| - Investigate common failure patterns | ||
| " | ||
| fi | ||
| BODY="$BODY | ||
| ### 📋 Next Steps | ||
| 1. Review this health report | ||
| 2. Address critical issues first | ||
| 3. Monitor rate limit recovery | ||
| 4. Check failed workflow runs | ||
| --- | ||
| *🤖 Automated health check by workflow-health.yml*" | ||
| # Create the issue | ||
| gh issue create \ | ||
| --title "$SEVERITY Workflow Health Alert - $(date -u '+%Y-%m-%d %H:%M UTC')" \ | ||
| --body "$BODY" \ | ||
| --label "workflow-health,$LABEL" | ||
| echo "✅ Health alert issue created" | ||
| - name: Summary | ||
| if: always() | ||
| run: | | ||
| echo "## 🏥 Workflow Health Check Complete" | ||
| echo "" | ||
| echo "**Rate Limits**: ${{ steps.rate_limits.outputs.status }}" | ||
| echo "**Workflows**: ${{ steps.workflow_stats.outputs.workflow_status }}" | ||
| echo "" | ||
| echo "**Details**:" | ||
| echo "- REST API: ${{ steps.rate_limits.outputs.core_pct }}% available" | ||
| echo "- GraphQL: ${{ steps.rate_limits.outputs.graphql_pct }}% available" | ||
| echo "- Success Rate: ${{ steps.workflow_stats.outputs.success_rate }}%" | ||
| echo "- Plans: ${{ steps.hierarchy_health.outputs.plans_open }} open" | ||
| echo "- Tasks: ${{ steps.hierarchy_health.outputs.tasks_open }} open" | ||
| echo "- Subtasks: ${{ steps.hierarchy_health.outputs.subtasks_open }} open" | ||
