From perplexity-pack
Apply Perplexity advanced debugging techniques for hard-to-diagnose issues. Use when standard troubleshooting fails, investigating complex race conditions, or preparing evidence bundles for Perplexity support escalation. Trigger with phrases like "perplexity hard bug", "perplexity mystery error", "perplexity impossible to debug", "difficult perplexity issue", "perplexity deep debug".
How this skill is triggered — by the user, by Claude, or both
Slash command
/perplexity-pack:perplexity-advanced-troubleshootingThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Deep debugging techniques for complex Perplexity issues that resist standard troubleshooting.
Deep debugging techniques for complex Perplexity issues that resist standard troubleshooting.
#!/bin/bash
set -euo pipefail
# advanced-perplexity-debug.sh
BUNDLE="perplexity-advanced-debug-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$BUNDLE"/{logs,metrics,network,config,traces}
# 1. Extended logs (1 hour window)
kubectl logs -l app=perplexity-integration --since=1h > "$BUNDLE/logs/pods.log"
journalctl -u perplexity-service --since "1 hour ago" > "$BUNDLE/logs/system.log"
# 2. Metrics dump
curl -s localhost:9090/api/v1/query?query=perplexity_requests_total > "$BUNDLE/metrics/requests.json" # 9090: Prometheus port
curl -s localhost:9090/api/v1/query?query=perplexity_errors_total > "$BUNDLE/metrics/errors.json" # Prometheus port
# 3. Network capture (30 seconds)
timeout 30 tcpdump -i any port 443 -w "$BUNDLE/network/capture.pcap" & # 443: HTTPS port
# 4. Distributed traces
curl -s localhost:16686/api/traces?service=perplexity > "$BUNDLE/traces/jaeger.json" # 16686: Jaeger UI port
# 5. Configuration state
kubectl get cm perplexity-config -o yaml > "$BUNDLE/config/configmap.yaml"
kubectl get secret perplexity-secrets -o yaml > "$BUNDLE/config/secrets-redacted.yaml"
tar -czf "$BUNDLE.tar.gz" "$BUNDLE"
echo "Advanced debug bundle: $BUNDLE.tar.gz"
// Test each layer independently
async function diagnosePerplexityIssue(): Promise<DiagnosisReport> {
const results: DiagnosisResult[] = [];
// Layer 1: Network connectivity
results.push(await testNetworkConnectivity());
// Layer 2: DNS resolution
results.push(await testDNSResolution('api.perplexity.com'));
// Layer 3: TLS handshake
results.push(await testTLSHandshake('api.perplexity.com'));
// Layer 4: Authentication
results.push(await testAuthentication());
// Layer 5: API response
results.push(await testAPIResponse());
// Layer 6: Response parsing
results.push(await testResponseParsing());
return { results, firstFailure: results.find(r => !r.success) };
}
// Strip down to absolute minimum
async function minimalRepro(): Promise<void> {
// 1. Fresh client, no customization
const client = new PerplexityClient({
apiKey: process.env.PERPLEXITY_API_KEY!,
});
// 2. Simplest possible call
try {
const result = await client.ping();
console.log('Ping successful:', result);
} catch (error) {
console.error('Ping failed:', {
message: error.message,
code: error.code,
stack: error.stack,
});
}
}
class TimingAnalyzer {
private timings: Map<string, number[]> = new Map();
async measure<T>(label: string, fn: () => Promise<T>): Promise<T> {
const start = performance.now();
try {
return await fn();
} finally {
const duration = performance.now() - start;
const existing = this.timings.get(label) || [];
existing.push(duration);
this.timings.set(label, existing);
}
}
report(): TimingReport {
const report: TimingReport = {};
for (const [label, times] of this.timings) {
report[label] = {
count: times.length,
min: Math.min(...times),
max: Math.max(...times),
avg: times.reduce((a, b) => a + b, 0) / times.length,
p95: this.percentile(times, 95),
};
}
return report;
}
}
// Detect memory leaks in Perplexity client usage
const heapUsed: number[] = [];
setInterval(() => {
const usage = process.memoryUsage();
heapUsed.push(usage.heapUsed);
// Alert on sustained growth
if (heapUsed.length > 60) { // 1 hour at 1/min
const trend = heapUsed[59] - heapUsed[0];
if (trend > 100 * 1024 * 1024) { // 100MB growth # 1024: 1 KB
console.warn('Potential memory leak in perplexity integration');
}
}
}, 60000); # 60000: 1 minute in ms
// Detect concurrent access issues
class PerplexityConcurrencyChecker {
private inProgress: Set<string> = new Set();
async execute<T>(key: string, fn: () => Promise<T>): Promise<T> {
if (this.inProgress.has(key)) {
console.warn(`Concurrent access detected for ${key}`);
}
this.inProgress.add(key);
try {
return await fn();
} finally {
this.inProgress.delete(key);
}
}
}
## Perplexity Support Escalation
**Severity:** P[1-4]
**Request ID:** [from error response]
**Timestamp:** [ISO 8601] # 8601 = configured value
### Issue Summary
[One paragraph description]
### Steps to Reproduce
1. [Step 1]
2. [Step 2]
### Expected vs Actual
- Expected: [behavior]
- Actual: [behavior]
### Evidence Attached
- [ ] Debug bundle (perplexity-advanced-debug-*.tar.gz)
- [ ] Minimal reproduction code
- [ ] Timing analysis
- [ ] Network capture (if relevant)
### Workarounds Attempted
1. [Workaround 1] - Result: [outcome]
2. [Workaround 2] - Result: [outcome]
Run the comprehensive debug script to gather all relevant data.
Test each layer independently to identify the failure point.
Strip down to the simplest failing case.
Use the support template with all collected evidence.
| Issue | Cause | Solution |
|---|---|---|
| Can't reproduce | Race condition | Add timing analysis |
| Intermittent failure | Timing-dependent | Increase sample size |
| No useful logs | Missing instrumentation | Add debug logging |
| Memory growth | Resource leak | Use heap profiling |
set -euo pipefail
# Test each layer in sequence
curl -v https://api.perplexity.com/health 2>&1 | grep -E "(Connected|TLS|HTTP)"
For load testing, see perplexity-load-scale.
npx claudepluginhub nickloveinvesting/nick-love-plugins --plugin perplexity-packCollects redacted debug bundle for Perplexity API issues: environment info, Node/Python versions, API key status, connectivity tests via curl. For support tickets and troubleshooting.
Root cause analysis for bugs and unexpected behavior. Traces errors through code, uses structured reasoning, and hands off to fix when cause is found. Escalates memory leaks to perf for cost-impact analysis.
Systematically debugs issues via reproduction steps, isolation techniques like git bisect, log/stack trace analysis, and common error pattern fixes. For bugs, incidents, troubleshooting.