feature: ci failure monitor slack bot (#15110)

Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>

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

@@ -29,7 +29,7 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install requests
+          pip install requests slack_sdk
 
       - name: Run Failure Analysis
         env:
@@ -41,7 +41,6 @@ jobs:
           python ci_failures_analysis.py \
             --token $GITHUB_TOKEN \
             --limit 100 \
-            --threshold 4 \
             --output ci_failure_analysis_$(date +%Y%m%d_%H%M%S).json
 
       - name: Upload Analysis Results
@@ -51,3 +50,22 @@ jobs:
           path: |
             scripts/ci_monitor/ci_failure_analysis_*.json
           retention-days: 7
+
+      - name: Send Slack Notification
+        if: always()
+        env:
+          SGLANG_DIFFUSION_SLACK_TOKEN: ${{ secrets.SGLANG_DIFFUSION_SLACK_TOKEN }}
+        run: |
+          cd scripts/ci_monitor
+          LATEST_REPORT=$(ls -t ci_failure_analysis_*.json | head -1)
+
+          if [ ! -f "$LATEST_REPORT" ]; then
+            echo "No report found, so skipping Slack notification"
+            exit 0
+          fi
+
+          if [ -n "$SGLANG_DIFFUSION_SLACK_TOKEN" ]; then
+            python3 post_ci_failures_to_slack.py --report-file "$LATEST_REPORT"
+          else
+            echo "SGLANG_DIFFUSION_SLACK_TOKEN not configured, skipping notification"
+          fi