Skip to main content
OpenClaw can expose diagnostics metrics through the bundled diagnostics-prometheus plugin. It listens to trusted internal diagnostics and renders a Prometheus text endpoint at: 
GET /api/diagnostics/prometheus
Content type is text/plain; version=0.0.4; charset=utf-8, the standard Prometheus exposition format.
The route uses Gateway authentication (operator scope). Do not expose it as a public unauthenticated /metrics endpoint. Scrape it through the same auth path you use for other operator APIs.
For traces, logs, OTLP push, and OpenTelemetry GenAI semantic attributes, see OpenTelemetry export.

​
Quick start

1

Enable the plugin

{
  plugins: {
    allow: ["diagnostics-prometheus"],
    entries: {
      "diagnostics-prometheus": { enabled: true },
    },
  },
  diagnostics: {
    enabled: true,
  },
}
2

Restart the Gateway

The HTTP route is registered at plugin startup, so reload after enabling.
3

Scrape the protected route

Send the same gateway auth your operator clients use:
curl -H "Authorization: Bearer $OPENCLAW_GATEWAY_TOKEN" \
  http://127.0.0.1:18789/api/diagnostics/prometheus
4

Wire Prometheus

# prometheus.yml
scrape_configs:
  - job_name: openclaw
    scrape_interval: 30s
    metrics_path: /api/diagnostics/prometheus
    authorization:
      credentials_file: /etc/prometheus/openclaw-gateway-token
    static_configs:
      - targets: ["openclaw-gateway:18789"]
diagnostics.enabled: true is required. Without it, the plugin still registers the HTTP route but no diagnostic events flow into the exporter, so the response is empty.

​
Metrics exported

MetricTypeLabels
openclaw_run_completed_totalcounterchannel, model, outcome, provider, trigger
openclaw_run_duration_secondshistogramchannel, model, outcome, provider, trigger
openclaw_model_call_totalcounterapi, error_category, model, outcome, provider, transport
openclaw_model_call_duration_secondshistogramapi, error_category, model, outcome, provider, transport
openclaw_model_tokens_totalcounteragent, channel, model, provider, token_type
openclaw_gen_ai_client_token_usagehistogrammodel, provider, token_type
openclaw_model_cost_usd_totalcounteragent, channel, model, provider
openclaw_tool_execution_totalcountererror_category, outcome, params_kind, tool
openclaw_tool_execution_duration_secondshistogramerror_category, outcome, params_kind, tool
openclaw_harness_run_totalcounterchannel, error_category, harness, model, outcome, phase, plugin, provider
openclaw_harness_run_duration_secondshistogramchannel, error_category, harness, model, outcome, phase, plugin, provider
openclaw_message_processed_totalcounterchannel, outcome, reason
openclaw_message_processed_duration_secondshistogramchannel, outcome, reason
openclaw_message_delivery_totalcounterchannel, delivery_kind, error_category, outcome
openclaw_message_delivery_duration_secondshistogramchannel, delivery_kind, error_category, outcome
openclaw_queue_lane_sizegaugelane
openclaw_queue_lane_wait_secondshistogramlane
openclaw_session_state_totalcounterreason, state
openclaw_session_queue_depthgaugestate
openclaw_memory_bytesgaugekind
openclaw_memory_rss_byteshistogramnone
openclaw_memory_pressure_totalcounterlevel, reason
openclaw_telemetry_exporter_totalcounterexporter, reason, signal, status
openclaw_prometheus_series_dropped_totalcounternone

​
Label policy

Prometheus labels stay bounded and low-cardinality. The exporter does not emit raw diagnostic identifiers such as runId, sessionKey, sessionId, callId, toolCallId, message IDs, chat IDs, or provider request IDs.Label values are redacted and must match OpenClaw’s low-cardinality character policy. Values that fail the policy are replaced with unknown, other, or none, depending on the metric.
The exporter caps retained time series in memory at 2048 series across counters, gauges, and histograms combined. New series beyond that cap are dropped, and openclaw_prometheus_series_dropped_total increments by one each time.Watch this counter as a hard signal that an attribute upstream is leaking high-cardinality values. The exporter never lifts the cap automatically; if it climbs, fix the source rather than disabling the cap.
  • prompt text, response text, tool inputs, tool outputs, system prompts
  • raw provider request IDs (only bounded hashes, where applicable, on spans — never on metrics)
  • session keys and session IDs
  • hostnames, file paths, secret values

​
PromQL recipes

# Tokens per minute, split by provider
sum by (provider) (rate(openclaw_model_tokens_total[1m]))

# Spend (USD) over the last hour, by model
sum by (model) (increase(openclaw_model_cost_usd_total[1h]))

# 95th percentile model run duration
histogram_quantile(
  0.95,
  sum by (le, provider, model)
    (rate(openclaw_run_duration_seconds_bucket[5m]))
)

# Queue wait time SLO (95p under 2s)
histogram_quantile(
  0.95,
  sum by (le, lane) (rate(openclaw_queue_lane_wait_seconds_bucket[5m]))
) < 2

# Dropped Prometheus series (cardinality alarm)
increase(openclaw_prometheus_series_dropped_total[15m]) > 0
Prefer gen_ai_client_token_usage for cross-provider dashboards: it follows the OpenTelemetry GenAI semantic conventions and is consistent with metrics from non-OpenClaw GenAI services.

​
Choosing between Prometheus and OpenTelemetry export

OpenClaw supports both surfaces independently. You can run either, both, or neither.
  • Pull model: Prometheus scrapes /api/diagnostics/prometheus.
  • No external collector required.
  • Authenticated through normal Gateway auth.
  • Surface is metrics only (no traces or logs).
  • Best for stacks already standardized on Prometheus + Grafana.

​
Troubleshooting

  • Check diagnostics.enabled: true in config.
  • Confirm the plugin is enabled and loaded with openclaw plugins list --enabled.
  • Generate some traffic; counters and histograms only emit lines after at least one event.
The endpoint requires the Gateway operator scope (auth: "gateway" with gatewayRuntimeScopeSurface: "trusted-operator"). Use the same token or password Prometheus uses for any other Gateway operator route. There is no public unauthenticated mode.
A new attribute is exceeding the 2048-series cap. Inspect recent metrics for an unexpectedly high-cardinality label and fix it at the source. The exporter intentionally drops new series instead of silently rewriting labels.
The plugin keeps state in memory only. After a Gateway restart, counters reset to zero and gauges restart at their next reported value. Use PromQL rate() and increase() to handle resets cleanly.