observability

var (
	// RequestsTotal counts total LLM requests by provider, model, endpoint, and status
	RequestsTotal = promauto.NewCounterVec(
		prometheus.CounterOpts{
			Name: "gomodel_requests_total",
			Help: "Total number of LLM requests",
		},
		[]string{"provider", "model", "endpoint", "status_code", "status_type", "stream"},
	)

	// RequestDuration measures request latency distribution
	// For streaming requests, this measures time to stream establishment, not total stream duration
	RequestDuration = promauto.NewHistogramVec(
		prometheus.HistogramOpts{
			Name:    "gomodel_request_duration_seconds",
			Help:    "LLM request duration in seconds",
			Buckets: []float64{0.1, 0.25, 0.5, 1, 2, 5, 10, 30, 60},
		},
		[]string{"provider", "model", "endpoint", "stream"},
	)

	// InFlightRequests tracks concurrent requests per provider
	InFlightRequests = promauto.NewGaugeVec(
		prometheus.GaugeOpts{
			Name: "gomodel_requests_in_flight",
			Help: "Number of LLM requests currently in flight",
		},
		[]string{"provider", "endpoint", "stream"},
	)

	// ResponseSnapshotStoreFailures counts failures while storing response snapshots.
	ResponseSnapshotStoreFailures = promauto.NewCounterVec(
		prometheus.CounterOpts{
			Name: "gomodel_response_snapshot_store_failures_total",
			Help: "Total number of response snapshot store failures",
		},
		[]string{"provider", "provider_name", "operation"},
	)

	// CircuitBreakerState reports each provider's circuit breaker state as of
	// its most recent request (0=closed, 1=half-open, 2=open). The value is
	// updated per request, so an idle provider keeps its last observed state.
	CircuitBreakerState = promauto.NewGaugeVec(
		prometheus.GaugeOpts{
			Name: "gomodel_circuit_breaker_state",
			Help: "Circuit breaker state per provider (0=closed, 1=half-open, 2=open)",
		},
		[]string{"provider"},
	)
)