aigroup-workflow 2.1.1 → 2.2.0

package/skills/infra/monitoring-expert/references/structured-logging.md

@@ -0,0 +1,142 @@
+# Structured Logging
+
+## Pino (Node.js)
+
+```typescript
+import pino from 'pino';
+
+const logger = pino({
+  level: process.env.LOG_LEVEL || 'info',
+  formatters: {
+    level: (label) => ({ level: label }),
+  },
+  redact: ['password', 'token', 'authorization'],
+});
+
+// Structured logging
+logger.info({
+  event: 'user.login',
+  userId: user.id,
+  ip: req.ip,
+  userAgent: req.headers['user-agent'],
+  duration: Date.now() - start,
+});
+
+// Error logging with context
+logger.error({
+  event: 'payment.failed',
+  error: err.message,
+  stack: err.stack,
+  orderId: order.id,
+  amount: order.total,
+  userId: user.id,
+});
+```
+
+## Request Logging Middleware
+
+```typescript
+import { randomUUID } from 'crypto';
+
+app.use((req, res, next) => {
+  const requestId = req.headers['x-request-id'] || randomUUID();
+  const start = Date.now();
+
+  res.setHeader('x-request-id', requestId);
+
+  res.on('finish', () => {
+    logger.info({
+      event: 'http.request',
+      requestId,
+      method: req.method,
+      path: req.path,
+      status: res.statusCode,
+      duration: Date.now() - start,
+      userAgent: req.headers['user-agent'],
+      ip: req.ip,
+    });
+  });
+
+  next();
+});
+```
+
+## Python (structlog)
+
+```python
+import structlog
+
+structlog.configure(
+    processors=[
+        structlog.stdlib.filter_by_level,
+        structlog.stdlib.add_logger_name,
+        structlog.stdlib.add_log_level,
+        structlog.processors.TimeStamper(fmt="iso"),
+        structlog.processors.JSONRenderer()
+    ],
+)
+
+logger = structlog.get_logger()
+
+# Structured logging
+logger.info(
+    "user.login",
+    user_id=user.id,
+    ip=request.client.host,
+    duration=elapsed_time,
+)
+
+# Error logging
+logger.error(
+    "payment.failed",
+    error=str(exc),
+    order_id=order.id,
+    amount=order.total,
+)
+```
+
+## Log Levels
+
+| Level | Use Case |
+|-------|----------|
+| `error` | Failures needing attention |
+| `warn` | Potential problems |
+| `info` | Business events, requests |
+| `debug` | Development details |
+| `trace` | Verbose debugging |
+
+## Best Practices
+
+```typescript
+// Good: Structured fields
+logger.info({ event: 'order.created', orderId: '123', total: 99.99 });
+
+// Bad: String interpolation
+logger.info(`Order 123 created with total 99.99`);
+
+// Good: Consistent event names
+logger.info({ event: 'user.registered' });
+logger.info({ event: 'user.login' });
+logger.info({ event: 'user.logout' });
+
+// Good: Include correlation ID
+logger.info({ event: 'request.processed', requestId, userId });
+```
+
+## Quick Reference
+
+| Field | Purpose |
+|-------|---------|
+| `event` | Event name |
+| `requestId` | Correlation ID |
+| `userId` | User context |
+| `duration` | Timing info |
+| `error` / `stack` | Error details |
+| `timestamp` | When (auto-added) |
+
+| Library | Language |
+|---------|----------|
+| pino | Node.js |
+| structlog | Python |
+| slog | Go |
+| logrus | Go |

package/skills/infra/sre-engineer/SKILL.md

@@ -0,0 +1,181 @@
+---
+name: sre-engineer
+description: Defines service level objectives, creates error budget policies, designs incident response procedures, develops capacity models, and produces monitoring configurations and automation scripts for production systems. Use when defining SLIs/SLOs, managing error budgets, building reliable systems at scale, incident management, chaos engineering, toil reduction, or capacity planning.
+license: MIT
+metadata:
+  author: https://github.com/Jeffallan
+  version: "1.1.0"
+  domain: devops
+  triggers: SRE, site reliability, SLO, SLI, error budget, incident management, chaos engineering, toil reduction, on-call, MTTR
+  role: specialist
+  scope: implementation
+  output-format: code
+  related-skills: devops-engineer, cloud-architect, kubernetes-specialist
+---
+
+# SRE Engineer
+
+## Core Workflow
+
+1. **Assess reliability** - Review architecture, SLOs, incidents, toil levels
+2. **Define SLOs** - Identify meaningful SLIs and set appropriate targets
+3. **Verify alignment** - Confirm SLO targets reflect user expectations before proceeding
+4. **Implement monitoring** - Build golden signal dashboards and alerting
+5. **Automate toil** - Identify repetitive tasks and build automation
+6. **Test resilience** - Design and execute chaos experiments; verify recovery meets RTO/RPO targets before marking the experiment complete; validate recovery behavior end-to-end
+
+## Reference Guide
+
+Load detailed guidance based on context:
+
+| Topic | Reference | Load When |
+|-------|-----------|-----------|
+| SLO/SLI | `references/slo-sli-management.md` | Defining SLOs, calculating error budgets |
+| Error Budgets | `references/error-budget-policy.md` | Managing budgets, burn rates, policies |
+| Monitoring | `references/monitoring-alerting.md` | Golden signals, alert design, dashboards |
+| Automation | `references/automation-toil.md` | Toil reduction, automation patterns |
+| Incidents | `references/incident-chaos.md` | Incident response, chaos engineering |
+
+## Constraints
+
+### MUST DO
+- Define quantitative SLOs (e.g., 99.9% availability)
+- Calculate error budgets from SLO targets
+- Monitor golden signals (latency, traffic, errors, saturation)
+- Write blameless postmortems for all incidents
+- Measure toil and track reduction progress
+- Automate repetitive operational tasks
+- Test failure scenarios with chaos engineering
+- Balance reliability with feature velocity
+
+### MUST NOT DO
+- Set SLOs without user impact justification
+- Alert on symptoms without actionable runbooks
+- Tolerate >50% toil without automation plan
+- Skip postmortems or assign blame
+- Implement manual processes for recurring tasks
+- Deploy without capacity planning
+- Ignore error budget exhaustion
+- Build systems that can't degrade gracefully
+
+## Output Templates
+
+When implementing SRE practices, provide:
+1. SLO definitions with SLI measurements and targets
+2. Monitoring/alerting configuration (Prometheus, etc.)
+3. Automation scripts (Python, Go, Terraform)
+4. Runbooks with clear remediation steps
+5. Brief explanation of reliability impact
+
+## Concrete Examples
+
+### SLO Definition & Error Budget Calculation
+
+```
+# 99.9% availability SLO over a 30-day window
+# Allowed downtime: (1 - 0.999) * 30 * 24 * 60 = 43.2 minutes/month
+# Error budget (request-based): 0.001 * total_requests
+
+# Example: 10M requests/month → 10,000 error budget requests
+# If 5,000 errors consumed in week 1 → 50% budget burned in 25% of window
+# → Trigger error budget policy: freeze non-critical releases
+```
+
+### Prometheus SLO Alerting Rule (Multiwindow Burn Rate)
+
+```yaml
+groups:
+  - name: slo_availability
+    rules:
+      # Fast burn: 2% budget in 1h (14.4x burn rate)
+      - alert: HighErrorBudgetBurn
+        expr: |
+          (
+            sum(rate(http_requests_total{status=~"5.."}[1h]))
+            /
+            sum(rate(http_requests_total[1h]))
+          ) > 0.014400
+          and
+          (
+            sum(rate(http_requests_total{status=~"5.."}[5m]))
+            /
+            sum(rate(http_requests_total[5m]))
+          ) > 0.014400
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "High error budget burn rate detected"
+          runbook: "https://wiki.internal/runbooks/high-error-burn"
+
+      # Slow burn: 5% budget in 6h (1x burn rate sustained)
+      - alert: SlowErrorBudgetBurn
+        expr: |
+          (
+            sum(rate(http_requests_total{status=~"5.."}[6h]))
+            /
+            sum(rate(http_requests_total[6h]))
+          ) > 0.001
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Sustained error budget consumption"
+          runbook: "https://wiki.internal/runbooks/slow-error-burn"
+```
+
+### PromQL Golden Signal Queries
+
+```promql
+# Latency — 99th percentile request duration
+histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket[5m])) by (le, service))
+
+# Traffic — requests per second by service
+sum(rate(http_requests_total[5m])) by (service)
+
+# Errors — error rate ratio
+sum(rate(http_requests_total{status=~"5.."}[5m])) by (service)
+  /
+sum(rate(http_requests_total[5m])) by (service)
+
+# Saturation — CPU throttling ratio
+sum(rate(container_cpu_cfs_throttled_seconds_total[5m])) by (pod)
+  /
+sum(rate(container_cpu_cfs_periods_total[5m])) by (pod)
+```
+
+### Toil Automation Script (Python)
+
+```python
+#!/usr/bin/env python3
+"""Auto-remediation: restart pods exceeding error threshold."""
+import subprocess, sys, json
+
+ERROR_THRESHOLD = 0.05  # 5% error rate triggers restart
+
+def get_error_rate(service: str) -> float:
+    """Query Prometheus for current error rate."""
+    import urllib.request
+    query = f'sum(rate(http_requests_total{{status=~"5..",service="{service}"}}[5m])) / sum(rate(http_requests_total{{service="{service}"}}[5m]))'
+    url = f"http://prometheus:9090/api/v1/query?query={urllib.request.quote(query)}"
+    with urllib.request.urlopen(url) as resp:
+        data = json.load(resp)
+    results = data["data"]["result"]
+    return float(results[0]["value"][1]) if results else 0.0
+
+def restart_deployment(namespace: str, deployment: str) -> None:
+    subprocess.run(
+        ["kubectl", "rollout", "restart", f"deployment/{deployment}", "-n", namespace],
+        check=True
+    )
+    print(f"Restarted {namespace}/{deployment}")
+
+if __name__ == "__main__":
+    service, namespace, deployment = sys.argv[1], sys.argv[2], sys.argv[3]
+    rate = get_error_rate(service)
+    print(f"Error rate for {service}: {rate:.2%}")
+    if rate > ERROR_THRESHOLD:
+        restart_deployment(namespace, deployment)
+    else:
+        print("Within SLO threshold — no action required")
+```