feat(voyage): add examples/observability/ Docker Compose stack — version-pinned per research/01

Step 14 of v4.1 — local-development observability stack with version-pinned
container images:
  - prom/prometheus:v3.0.1
  - prom/node-exporter:v1.10.2 (textfile collector enabled)
  - grafana/grafana:11.4.0
  - otel/opentelemetry-collector-contrib:0.115.0

Two complementary export paths from voyage hooks/scripts/otel-export.mjs:
  - VOYAGE_EXPORT_MODE=textfile → node-exporter textfile collector
  - VOYAGE_EXPORT_MODE=otlp     → otel-collector OTLP/HTTP receiver (:4318)
Both feed Prometheus → Grafana.

Files:
  examples/observability/docker-compose.yml
  examples/observability/otel-collector-config.yaml
  examples/observability/prometheus.yml
  examples/observability/grafana-datasource.yml
  examples/observability/README.md

Verified manifest expected_paths (5 files). docker compose config validation
runs in Step 16 with proper skip-pattern when docker is unavailable.

plugins/voyage/examples/observability/otel-collector-config.yaml

@@ -0,0 +1,47 @@
+# OpenTelemetry Collector config for voyage v4.1
+# Receives OTLP/HTTP push from hooks/scripts/otel-export.mjs (port 4318)
+# and exposes a Prometheus scrape endpoint at :8889 for the Prometheus
+# container to pull voyage metrics.
+
+receivers:
+  otlp:
+    protocols:
+      http:
+        endpoint: 0.0.0.0:4318
+      grpc:
+        endpoint: 0.0.0.0:4317
+
+processors:
+  batch:
+    send_batch_size: 1024
+    timeout: 5s
+  # Conservative resource attribute limits — voyage emits small payloads but
+  # we cap to prevent runaway label-cardinality blowing up Prometheus.
+  memory_limiter:
+    check_interval: 5s
+    limit_mib: 256
+    spike_limit_mib: 64
+
+exporters:
+  prometheus:
+    endpoint: 0.0.0.0:8889
+    namespace: voyage
+    send_timestamps: true
+    metric_expiration: 5m
+    enable_open_metrics: true
+  # Debug exporter — echoes every received metric to stderr. Useful for
+  # local development; comment out in production to reduce log volume.
+  debug:
+    verbosity: detailed
+    sampling_initial: 5
+    sampling_thereafter: 200
+
+service:
+  pipelines:
+    metrics:
+      receivers: [otlp]
+      processors: [memory_limiter, batch]
+      exporters: [prometheus, debug]
+  telemetry:
+    logs:
+      level: info