ai-observability

# AI Observability ## Dependencies ```xml <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 2.0 includes built-in Micrometer instrumentation: ```yaml spring: ai: chat: client: observations: log-prompt: true # OFF in prod (PII). log-completion: true observations: log-prompt: true # ChatModel prompt logging; OFF in prod (PII). log-completion: true include-error-logging: true 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 model - `gen_ai.client.token.usage` — token counts (input/output/total) - `spring.ai.chat.client` — ChatClient-level operation timer/span ## Custom AI Metrics ```java @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.use...