Analytics

Every request through DVARA emits cost, latency, token, policy-decision, audit, and trace telemetry. That data fans out across three lenses — operator dashboards in the DVARA Flight Deck, self-service tenant views in the Portal, and raw machine-readable feeds (Prometheus, OpenTelemetry, structured logs, SIEM streams) you point your own observability stack at.

This page is a survey of what's available and where to find it. For deep dives, follow the links into the per-feature documentation.

The three lenses

Lens	Audience	What it gives you
Console dashboards (/, /costs, /audit, /latency, /analytics, …)	Platform operators, security admins, finance	Cross-tenant operational view with HTMX-polled fragments (3–10s refresh), role-based access controls, and click-through detail. The fastest way to answer "what's happening right now across the fleet".
Portal pages (/portal, /portal/usage, /portal/audit, …)	Tenant users — application developers, team leads, auditors	The same dashboards narrowed to the caller's own tenant. Self-service for tenant admin / developer / viewer roles; the operator never has to grant Console access.
Raw feeds (Prometheus scrape, OTLP push, stdout JSON logs, Kafka/Splunk/CloudWatch SIEM)	Your own observability stack — Grafana, Datadog, Tempo, Jaeger, Splunk, ELK, …	Machine-readable telemetry meant to feed your existing dashboards, alerts, and SIEM. DVARA does not try to replace your observability platform; it emits the standard formats so you don't have to.

Use the dashboards for day-to-day operations and the raw feeds for long-term retention, custom dashboards, and alerting. Reports (chargeback, compliance) are the one-shot PDF / CSV artifacts you hand to finance or auditors.

Quick orientation by audience

You are a …	Start here
Platform operator running the gateway	Console Dashboard (/) for live health; Console Latency (/latency) for routing decisions; Prometheus scrape for alerting
Security / compliance lead	Console Audit (/audit) for the live event stream; Compliance Reports (/compliance) for SOC2 / HIPAA / GDPR rollups; SIEM stream for long-term retention
Finance / FinOps	Console Cost Dashboard (/costs) for live spend; Chargeback Reports (/chargeback) for monthly per-tenant PDFs; gateway_cost_dollars_total Prometheus counter for time-series budget burn
Tenant developer or team lead	Portal Dashboard (/portal) for your tenant's request counts, tokens, and cost; Portal Usage (/portal/usage) for per-model breakdowns; Portal Audit for your own audit trail
Agent platform team	Console Agent Analytics (/analytics) for session outcomes, approval funnels, tool-call heatmaps; Console MCP Sessions (/mcp/sessions) for per-session timelines

The full surface

Every analytic the platform exposes, what it shows, where to view it, and the underlying endpoint.

Live dashboards

Analytic	What it shows	Where to view	Endpoint
Operational dashboard	Req/s, P95 latency, error rate, tokens/min, provider health, cache stats, priority-admission stats	Console /	GET /actuator/prometheus + GET /actuator/gateway-status
Per-tenant dashboard	Request count, token usage, 30-day cost, active API keys, recent audit events — scoped to caller's tenant	Portal /portal	PortalDashboardController (direct repo reads)
Cost dashboard	Total cost, Cost-by-Provider donut, Cost-by-Model bar, budget status, forecast cards, anomaly alerts, raw records table	Console /costs	GET /v1/admin/costs, /costs/summary, /costs/forecast, /costs/anomalies
Latency dashboard	EWMA latency per (provider, model) — sample count, raw last sample, freshness badge	Console /latency (owner + policy-admin)	GET /v1/admin/latency
Priority admission stats	Concurrent / max concurrent / load %, per-tier admitting vs throttling	Dashboard priority card (when routing.priority.enabled=true)	GET /v1/admin/priority/stats
Semantic cache stats	Hit rate, miss count, cache size, average similarity on hits	Console /cache (owner only)	GET /v1/admin/cache/stats
License status	Licensee, type, expiry, days remaining, runtime status badge	Console /license, Portal license panel	GET /actuator/gateway-status

Telemetry & event streams

Analytic	What it shows	Where to view	Endpoint
Token usage telemetry	Per-request input/output/total tokens, summary KPI card, masked API key, estimated-flag tooltip	Console /token-usage, Portal /portal/usage	GET /v1/admin/token-usage, …/summary
Audit event stream	Append-only HMAC-chained events — policy decisions, auth, config imports, license transitions; click-to-expand detail; CSV / JSON export	Console /audit, Portal /portal/audit	GET /v1/admin/audit/events, …/export, …/export/json
Budget cap usage	Current period spend vs limit, color-coded progress bar, period boundaries, dollars remaining	Console /budgets, Portal /portal/budgets	GET /v1/admin/budgets/{id}/usage
MCP tool-call telemetry	Per-call records (tenant, session, server, tool, status, latency, response bytes, PII flag); aggregated counts	Console /mcp/tool-calls, Portal /portal/mcp/tool-calls	GET /v1/admin/mcp/tool-calls, …/summary
Agent session timeline	Session list + detail with summary stats (avg latency, error rate, duration, response bytes) + distinct-tools table + per-call timeline + JSON export	Console /mcp/sessions, Portal /portal/mcp/sessions	GET /v1/admin/sessions, …/{id}/timeline
Approval queue stats	Pending + decision history, action badges, nav badge count	Console /approvals, Portal /portal/approvals	GET /v1/admin/approvals/pending, …/history, …/count

Comparison & experimentation analytics

Analytic	What it shows	Where to view	Endpoint
Canary A/B report	Per-variant metrics on a canary-routed route; reset + live split-percentage update	Console /routes/{id}/canary	GET /v1/admin/routes/{id}/canary/report
Shadow policy report	Divergence stats (1h / 24h / 7d) + per-event diff between active and SHADOW policy	Console /policies/{id}/shadow	GET /v1/admin/policies/{id}/shadow/stats, …/events
Shadow routing report	Provider-vs-shadow comparison on a route (latency, status, response delta)	Console /routes/{id}/shadow	GET /v1/admin/routes/{id}/shadow/report
Prompt experiment metrics	Per-variant A/B metrics snapshot for a prompt experiment	Console + Portal experiment pages	GET /v1/admin/prompts/experiments/{id}/report
Agent behaviour analytics	Session-outcomes donut, approval-funnel bar, top-20 agent leaderboard, tool-call heatmap (server × tool), policy firing frequency	Console /analytics	AnalyticsController (composed from MCP + audit repos)
Model fingerprint drift	Drift report per golden prompt — when an upstream model's response semantics shifted	Console eval/fingerprint surface	GET /v1/admin/golden-prompts/{id}/drift
Eval pipeline reports	Per-model eval suite results vs golden corpus, drift detection, time-ranged report queries	Console /eval/reports	GET /v1/admin/eval/reports, …/model/{model}

Downloadable reports

Analytic	What it shows	Where to view	Endpoint
Chargeback reports	Per-tenant monthly rollup: tenant summary, model/provider breakdown, daily cost trend, forecasts, anomalies — PDF + CSV	Console /chargeback, Portal /portal/chargeback	POST /v1/admin/chargeback, GET …/{id}/pdf, …/{id}/csv
Compliance reports	SOC2 / HIPAA / GDPR rollups aggregated from audit + token usage + tenant + policy data — PDF	Console /compliance, Portal /portal/compliance	POST /v1/admin/reports, GET …/{id}/pdf

Raw feeds — point your own stack at these

Analytic	What it shows	Where to view	Endpoint
Prometheus metrics	~35 named counters / histograms — gateway_requests_total, gateway_latency_seconds, gateway_tokens_total, gateway_cost_dollars_total, gateway_guardrail_blocked_total, gateway_budget_blocked_total, mcp_tool_calls_total, dvara_emails_sent_total, etc.	Your Grafana / Datadog / Mimir	GET /actuator/prometheus on gateway-server, mcp-proxy-server, flightdeck — Bearer $DVARA_ACTUATOR_METRICS_API_KEY
OpenTelemetry traces	Distributed spans — gateway.provider.chat, …stream, …embed; mcp.filter.*, mcp.server.call — with traceparent propagation	Your OTel collector → Jaeger / Tempo / Datadog	OTLP push to OTEL_EXPORTER_OTLP_ENDPOINT (default http://localhost:4318/v1/traces)
Structured access log	One JSON line per request: trace_id, method, path, status, latency_ms, model, provider, cache_status, masked api_key, tenant_id, token counts, error_code	Your log aggregator	stdout (Logback LogstashEncoder)
SIEM stream	All audit events forwarded to Splunk HEC, CloudWatch Logs, or Kafka	Your SIEM	dvara.llm-gateway.siem.{splunk|cloudwatch|kafka}.*

Per-tenant vs platform scoping

Almost every analytic in the tables above respects DVARA's multi-tenant scoping rules:

• Platform-role callers (owner / policy-admin / billing-admin) see cross-tenant data by default. Most list endpoints accept an optional ?tenant_id= filter to narrow.
• Tenant-role callers (admin / developer / viewer) only ever see their own tenant's rows. Passing another tenant's id returns HTTP 403 with a TENANT_SCOPE_VIOLATION audit event.

The Portal pages enforce the same rule at the URL level — a tenant user lands at /portal/* and physically cannot construct a path that crosses tenants. See Multi-Tenancy for the full isolation model.

What's deliberately not in the box

A few things the platform deliberately leaves to your existing tools:

• Long-term metric retention beyond the Prometheus scrape window — point a Mimir / Thanos / Datadog at the scrape endpoint.
• Custom dashboards beyond the built-in Console / Portal views — Grafana on top of the Prometheus + OTLP feeds covers the long tail.
• Alerting — Prometheus AlertManager or Grafana alerts on the same metrics; the platform emits the data, not the alert routing.
• Cross-system correlation (joining DVARA spans against your service's app spans) — handled by your APM via the traceparent propagation DVARA already emits.

Where to go next

• DVARA Flight Deck — the full Console tour, including every dashboard listed above with screenshots.
• Cost Management — cost dashboard, forecasts, anomaly alerts, budget caps, chargeback reports.
• Observability — audit event taxonomy, Prometheus metrics list, OpenTelemetry span names, SIEM configuration.
• Multi-Tenancy — the scoping rules that govern who sees what data.
• Admin API reference — programmatic access to every analytic above for CI/CD, IaC, and custom integrations.