rrezartprebreza/spring-boot-skills / skills/spring-boot-3/ai-observability
ai-observability
VerifiedUse when adding Spring AI-specific model observations, token usage, latency, externally configured cost attribution, advisor telemetry, or protected prompt and completion logging. Use production-observability for general service metrics, health, logs, and OTLP setup.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.2 KB |
| agents/openai.yaml | config | 200 B |
| examples/bad-ai-audit-advisor.java | other | 2.1 KB |
| examples/good-ai-audit-advisor.java | other | 2.6 KB |
| templates/AiAuditAdvisor.java | other | 4.9 KB |
| templates/AiMetrics.java | other | 2.3 KB |
examples/good-ai-audit-advisor.java
View on GitHub// GOOD — GA CallAdvisor API, Micrometer metrics, async audit via separate bean, no PII in logs
@Component
@RequiredArgsConstructor
@Slf4j
public class AiAuditAdvisor implements CallAdvisor {
private final MeterRegistry meterRegistry;
private final AiAuditRecorder auditRecorder; // separate bean — @Async needs the proxy
@Override
public int getOrder() {
return 0;
}
@Override
public String getName() {
return "AiAuditAdvisor";
}
@Override
public ChatClientResponse adviseCall(ChatClientRequest request, CallAdvisorChain chain) {
String requestId = UUID.randomUUID().toString();
Timer.Sample sample = Timer.start(meterRegistry);
try {
ChatClientResponse response = chain.nextCall(request);
ChatResponse chatResponse = response.chatResponse();
// Record metrics
sample.stop(Timer.builder("ai.request.duration")
.tag("status", "success")
.register(meterRegistry));
// Track token usage from response metadata
if (chatResponse != null && chatResponse.getMetadata() != null
&& chatResponse.getMetadata().getUsage() != null) {
var usage = chatResponse.getMetadata().getUsage();
meterRegistry.counter("ai.tokens.input").increment(usage.getPromptTokens());
meterRegistry.counter("ai.tokens.output").increment(usage.getCompletionTokens()); // GA name
}
// Async audit — separate bean, so the @Async proxy is actually used
auditRecorder.record(requestId, "SUCCESS", null);
// Log without PII — only metadata
log.info("AI request {} completed", requestId);
return response;
} catch (Exception e) {
sample.stop(Timer.builder("ai.request.duration")
.tag("status", "error")
.register(meterRegistry));
meterRegistry.counter("ai.request.errors").increment();
auditRecorder.record(requestId, "ERROR", e.getMessage());
throw e;
}
}
}
// Separate bean: calling an @Async method on `this` bypasses the Spring proxy and
// runs synchronously — the same self-invocation pitfall as @Transactional.
@Component
@RequiredArgsConstructor
class AiAuditRecorder {
private final AuditLogRepository auditLogRepository;
@Async
public void record(String requestId, String status, String errorMessage) {
auditLogRepository.save(new AiAuditLog(requestId, status, errorMessage, Instant.now()));
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |