Intelligent Triage

Automatically detects and correlates infrastructure incidents. Each incident includes severity, estimated impact, and recommended action.

Usage

# Full infrastructure triage
valqore checkup
 
# Scoped triage
valqore checkup --scope reliability,k8s --context prod

Via MCP:

"What's wrong with my production cluster?"
→ Claude calls triage_environment

Deep-Dive: investigate_resource

# Via CLI
valqore investigate pod/api-gateway -n payments

Example Output

$ valqore checkup --scope reliability,k8s --context prod
 
╔══════════════════════════════════════════════════════════════╗
║              Infrastructure Triage Report                    ║
║              Cluster: prod | Scope: reliability, k8s         ║
╠══════════════════════════════════════════════════════════════╣
║                                                              ║
║  Incident #1: Memory Exhaustion (Confidence: 94%)            ║
║  ├─ Severity: CRITICAL                                       ║
║  ├─ Blast Radius: 3 services, ~2,400 requests/min affected   ║
║  ├─ Root Cause: Memory limits too low for current traffic     ║
║  └─ Action: Increase payment-api memory limit to 1Gi         ║
║                                                              ║
║  Incident #2: Deployment Stall (Confidence: 87%)             ║
║  ├─ Severity: HIGH                                           ║
║  ├─ Blast Radius: 1 service                                  ║
║  ├─ Root Cause: Image tag "v2.3.1" not found in registry     ║
║  └─ Action: Verify image tag exists; check registry auth     ║
║                                                              ║
╚══════════════════════════════════════════════════════════════╝