telemetry

type Metrics struct {
	AlertsReceived            metric.Int64Counter
	AlertsCoalesced           metric.Int64Counter
	AlertsSuppressed          metric.Int64Counter
	InvestigationsStarted     metric.Int64Counter
	InvestigationsThrottled   metric.Int64Counter
	InvestigationsDropped     metric.Int64Counter
	GitOpsFailuresDebounced   metric.Int64Counter // GitOps failures dropped as transient (cleared within the debounce window)
	ToolOutputTruncatedBytes  metric.Int64Counter
	HistoryCompactions        metric.Int64Counter // mid-loop history compaction events
	HistoryElidedBytes        metric.Int64Counter // tool-output bytes elided by compaction
	HistorySummarizations     metric.Int64Counter // compaction events whose elided batch was replaced by a model digest
	HistorySummarizeFallbacks metric.Int64Counter // summarize-mode compactions that fell back to plain elision (summarizer error/refusal/truncation)
	RecallHits                metric.Int64Counter // KB cache hits, labelled by verify result
	RecallTokensSaved         metric.Int64Counter // estimated tokens saved by a recall short-circuit
	RecallRejections          metric.Int64Counter // recalls rejected before short-circuit (label: reason)
	CoalesceBatchSize         metric.Int64Histogram
	InvestigationTokens       metric.Int64Histogram
	// Per-investigation model usage totals (loop + verify), recorded once at
	// delivery — the actual provider-reported spend, distinct from the pre-request
	// InvestigationTokens estimate.
	InvestigationModelCalls        metric.Int64Histogram
	InvestigationInputTokens       metric.Int64Histogram
	InvestigationOutputTokens      metric.Int64Histogram
	InvestigationCachedInputTokens metric.Int64Histogram
	InvestigationCostUSD           metric.Float64Histogram // estimated per-investigation cost, USD (only when model.pricing is configured)
	RecallScore                    metric.Float64Histogram // BM25 score at the recall decision (tunes min_score)
	CurationDedupScore             metric.Float64Histogram // catalog top-hit BM25 score at the curation dedup decision
	OutcomesOpened                 metric.Int64Counter     // investigations recorded as open (label: kind)
	IncidentsResolved              metric.Int64Counter     // resolve events that matched an open investigation
	RecallOutcome                  metric.Int64Counter     // resolved incidents whose open was a recall (label: result)
	IncidentResolutionSeconds      metric.Float64Histogram // open→resolve duration, seconds

	InvestigationDuration   metric.Float64Histogram // wall-clock per investigation (label: result)
	InvestigationsCompleted metric.Int64Counter     // investigations finished (label: result)
	ToolCalls               metric.Int64Counter     // investigation tool calls (label: tool, result)
	ToolCallDuration        metric.Float64Histogram // tool call latency, seconds (label: tool)
	ModelRequests           metric.Int64Counter     // LLM completion requests (label: provider, result)
	ModelRequestDuration    metric.Float64Histogram // LLM completion latency, seconds (label: provider)
	ModelResponsesTruncated metric.Int64Counter     // LLM completions cut off at the output-token ceiling (label: provider)
	ModelInputTokens        metric.Int64Counter     // total input tokens across LLM requests (label: provider)
	ModelCachedInputTokens  metric.Int64Counter     // input tokens served from cache (label: provider)
	Curations               metric.Int64Counter     // curation outcomes (label: kind, result)
	CatalogInvalidEntries   metric.Int64Counter     // structurally-invalid entries found at catalog load
}