Initial curated RAGcore source from c16667f0c9397e2bfc8dd0255b114fba23c8d05e

ops/dashboards/operations_overview.yaml

@@ -0,0 +1,68 @@
+# Operations overview dashboard.
+#
+# Documents the panels a real dashboard (Grafana or equivalent) should
+# expose for the representative metric set
+# src/ragcore/platform/telemetry/metrics.py::TelemetryMetrics records, per
+# docs/09_OPERATIONS/OBSERVABILITY.md's "Metrics" list. Tool-agnostic on
+# purpose -- no specific dashboarding backend is assumed by this codebase
+# yet.
+#
+# This is a representative subset (request latency/error, job queue
+# depth/age, Qdrant/provider errors), not every metric that document
+# names; wiring metrics for every existing subsystem (search candidate
+# counts, zero-result rate, ingestion throughput, backup/restore age, ...)
+# is future work, not required by this task's own acceptance criteria.
+
+dashboard: RAGCore Operations Overview
+
+panels:
+  - title: Request latency
+    metric: ragcore_request_duration_seconds
+    type: histogram
+    unit: seconds
+    description: HTTP request duration, by status_code.
+
+  - title: Request error rate
+    metric: ragcore_request_errors_total
+    type: counter
+    description: >-
+      HTTP requests resulting in a server error (5xx) or rate-limited
+      (429) status, by status_code.
+
+  - title: Job queue depth
+    metric: ragcore_job_queue_depth
+    type: up_down_counter
+    description: Number of jobs currently queued (enqueued minus claimed).
+
+  - title: Job age at claim
+    metric: ragcore_job_age_seconds
+    type: histogram
+    unit: seconds
+    description: >-
+      How long a job waited between being enqueued and being claimed by a
+      worker. Feeds the queue-age SLO alert (see
+      ops/alerts/queue_age_slo.yaml).
+
+  - title: Qdrant errors
+    metric: ragcore_qdrant_errors_total
+    type: counter
+    description: Qdrant operation failures, by operation.
+
+  - title: Provider errors
+    metric: ragcore_provider_errors_total
+    type: counter
+    description: >-
+      Model provider (embedding/reranker/generation) operation failures,
+      by provider. Compare against
+      ops/alerts/provider_circuit_open.yaml (M5-07) for when a provider's
+      circuit breaker actually opens.
+
+correlation:
+  # How to find every span/log/metric for one request or job in whatever
+  # backend actually stores them: they all carry the same correlation_id
+  # attribute, and spans opened from different components (an API handler,
+  # a later job) for the same correlation_id share the literal same
+  # OpenTelemetry trace id (see
+  # src/ragcore/platform/telemetry/tracing.py::trace_id_from_correlation_id).
+  attribute: correlation_id
+  source: RequestCorrelationMiddleware's request_id / a job's own correlation id