ai-observability
Use 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.
How do I install this agent skill?
npx skills add https://github.com/rrezartprebreza/spring-boot-skills --skill ai-observabilityIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill provides templates and best practices for implementing observability in Spring AI applications. It correctly identifies and warns against insecure patterns such as logging full prompt content (PII) and synchronous auditing. It identifies a potential surface for indirect prompt injection via the processing of untrusted AI prompt and response data.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
AI Observability
Dependencies
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-actuator</artifactId>
</dependency>
<dependency>
<groupId>io.micrometer</groupId>
<artifactId>micrometer-registry-prometheus</artifactId>
</dependency>
Spring AI Built-in Observability
Spring AI 1.0+ includes built-in Micrometer instrumentation:
spring:
ai:
chat:
observations:
log-prompt: false # GA renamed include-prompt → log-prompt. true only in local dev (PII)
log-completion: false # GA renamed include-completion → log-completion
management:
metrics:
tags:
application: order-service
endpoints:
web:
exposure:
include: health,prometheus,metrics
Auto-generated metrics (OpenTelemetry GenAI semantic conventions):
gen_ai.client.operation— model call latency, tagged with provider and modelgen_ai.client.token.usage— token counts (input/output/total)spring.ai.chat.client— ChatClient-level operation timer/span
Custom AI Metrics
@Component
@RequiredArgsConstructor
public class AiMetrics {
private final MeterRegistry meterRegistry;
private final Timer.Builder promptTimer = Timer.builder("ai.prompt.latency")
.description("LLM prompt latency");
private final Counter.Builder tokenCounter = Counter.builder("ai.tokens.used")
.description("Total tokens consumed");
public <T> T track(String operation, String model, Supplier<T> call) {
return Timer.builder("ai.prompt.latency")
.tag("operation", operation)
.tag("model", model)
.register(meterRegistry)
.record(call); // record(Supplier) — recordCallable throws checked Exception
}
public void recordTokens(String operation, String model, int inputTokens, int outputTokens) {
Counter.builder("ai.tokens.used")
.tag("operation", operation)
.tag("model", model)
.tag("type", "input")
.register(meterRegistry)
.increment(inputTokens);
Counter.builder("ai.tokens.used")
.tag("operation", operation)
.tag("model", model)
.tag("type", "output")
.register(meterRegistry)
.increment(outputTokens);
}
}
Prompt/Response Logging Advisor
GA replaced the whole advisor API: CallAroundAdvisor → CallAdvisor, AdvisedRequest →
ChatClientRequest, AdvisedResponse → ChatClientResponse, and Usage.getGenerationTokens() →
getCompletionTokens(). Agents reliably generate the old one — it does not compile on 1.0.
@Component
public class AiAuditAdvisor implements CallAdvisor {
private static final Logger log = LoggerFactory.getLogger(AiAuditAdvisor.class);
@Override
public ChatClientResponse adviseCall(ChatClientRequest request, CallAdvisorChain chain) {
String requestId = UUID.randomUUID().toString();
long start = System.currentTimeMillis();
log.info("[AI-AUDIT] requestId={} promptLength={}",
requestId, request.prompt().getUserMessage().getText().length());
try {
ChatClientResponse response = chain.nextCall(request);
long latency = System.currentTimeMillis() - start;
ChatResponse chatResponse = response.chatResponse();
if (chatResponse != null && chatResponse.getMetadata() != null) {
Usage usage = chatResponse.getMetadata().getUsage();
log.info("[AI-AUDIT] requestId={} latencyMs={} inputTokens={} outputTokens={}",
requestId, latency,
usage.getPromptTokens(), usage.getCompletionTokens()); // GA: not getGenerationTokens()
}
return response;
} catch (Exception e) {
log.error("[AI-AUDIT] requestId={} FAILED after {}ms", requestId,
System.currentTimeMillis() - start, e);
throw e;
}
}
@Override
public String getName() { return "AiAuditAdvisor"; }
@Override
public int getOrder() { return Ordered.LOWEST_PRECEDENCE; }
}
Cost attribution
- Keep provider prices in externally managed configuration with an effective date and currency.
- Key prices by the exact provider model identifier returned in usage metadata.
- Reject an unknown model instead of silently applying a default price.
- Preserve the raw token usage so historical costs can be recalculated after pricing changes.
- Prefer provider billing exports for invoices; application estimates are operational signals only.
Structured AI Audit Log (DB)
The audit advisor template treats telemetry as best-effort. Catch submission failures around the call to the separate async bean, as well as persistence failures inside it: a full or stopped executor can reject a task before its method runs. Use a bounded executor and monitor rejected audit tasks; do not use caller-runs when response latency must remain independent of audit storage. Store sanitized error types, not raw provider exception messages. Mandatory compliance audit records need durable delivery, not this best-effort design.
See Spring task execution and rejection policies.
@Entity
@Table(name = "ai_audit_log")
public class AiAuditLog {
@Id @GeneratedValue(strategy = GenerationType.UUID)
private UUID id;
private String operation;
private String model;
private int inputTokens;
private int outputTokens;
private double estimatedCostUsd;
private long latencyMs;
private boolean success;
private Instant createdAt;
}
// Async to avoid blocking main flow
@Async
public void saveAuditLog(AiAuditLog log) {
auditLogRepository.save(log);
}
application.yml — Full Observability
management:
endpoints:
web:
exposure:
include: health,prometheus,metrics,info
metrics:
distribution:
percentiles-histogram:
ai.prompt.latency: true # enables P50/P95/P99
tracing:
sampling:
probability: 1.0 # 100% trace sampling in dev, reduce in prod
logging:
level:
org.springframework.ai: DEBUG # enable in dev only
Gotchas
- Agent implements
CallAroundAdvisor/AdvisedRequest— removed in GA; useCallAdvisor/ChatClientRequest - Agent calls
usage.getGenerationTokens()— GA renamed it togetCompletionTokens() - Agent logs full prompts in production — keep
log-prompt: falsefor PII safety - Agent skips async on audit saves — always
@Asyncto avoid latency impact, and put the@Asyncmethod on a separate bean; calling it onthisbypasses the proxy and runs synchronously - Agent hardcodes token pricing — extract to config, prices change
- Agent misses failed calls in metrics — track errors separately with error tag
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/rrezartprebreza/spring-boot-skills/ai-observability">View ai-observability on skillZs</a>