Add job and runner failure monitor workflow for CI (#13104)

.github/workflows/ci-failure-monitor.yml

@@ -0,0 +1,64 @@
+name: CI Failure Monitor
+
+on:
+  schedule:
+    - cron: '*/30 * * * *' # Every 30 minutes
+  workflow_dispatch:
+    inputs:
+      limit:
+        description: 'Number of workflow runs to analyze'
+        required: false
+        default: '300'
+        type: string
+      threshold:
+        description: 'Alert threshold for consecutive failures'
+        required: false
+        default: '4'
+        type: string
+
+concurrency:
+  group: ci-failure-monitor-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+  actions: read
+
+jobs:
+  failure-analysis:
+    if: github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.14'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install requests
+
+      - name: Run Failure Analysis
+        env:
+          GITHUB_TOKEN: ${{ secrets.GH_PAT_FOR_NIGHTLY_CI_DATA }}
+          PYTHONUNBUFFERED: 1
+          PYTHONIOENCODING: utf-8
+        run: |
+          cd scripts/ci_monitor
+          python ci_failures_analysis.py \
+            --token $GITHUB_TOKEN \
+            --limit ${{ inputs.limit || '300' }} \
+            --threshold ${{ inputs.threshold || '2' }} \
+            --output ci_failure_analysis_$(date +%Y%m%d_%H%M%S).json
+
+      - name: Upload Analysis Results
+        uses: actions/upload-artifact@v4
+        with:
+          name: ci-failure-analysis-${{ github.run_number }}
+          path: |
+            scripts/ci_monitor/ci_failure_analysis_*.json
+          retention-days: 7