diff --git a/docs/observability.md b/docs/observability.md
index 139b6e08..922144db 100644
--- a/docs/observability.md
+++ b/docs/observability.md
@@ -219,6 +219,32 @@ Cadence follows `metricIntervalMs` (default 60s). Transport is OTLP/HTTP
 first hop is unauthenticated for every producer on this host, and the upstream
 credential stays on the swarm tier.
 
+## Agent-emitted per-turn metrics (`hive-agent`)
+
+When OTEL is enabled, the harness itself (`hive-agent`) exports one small set
+of metrics per claude turn, recorded the moment the turn ends (not polled).
+These are deliberately the fields Claude Code's own built-in export (see
+above) can't know about — the harness's own wall-clock timing, what woke the
+turn, its own outcome classification, the loose-ends backlog, and session
+boundaries. Token usage, cost, and tool-call counts are **not** duplicated
+here; that's already covered by Claude's own export.
+
+| Metric | Unit | Kind | Attributes |
+|--------|------|------|------------|
+| `hyperhive.agent.turn.duration` | `ms` | histogram | `wake_from`, `result_kind`, `model` |
+| `hyperhive.agent.turn.count` | — | counter | `wake_from`, `result_kind`, `model` |
+| `hyperhive.agent.session.count` | — | counter | `model` (incremented once per fresh, non-`--continue`'d session) |
+| `hyperhive.agent.loose_ends.threads` | — | gauge | none |
+| `hyperhive.agent.loose_ends.reminders` | — | gauge | none |
+
+Resource attributes (`service.name`, `agent`, `hive`, `swarm`) come from the
+same container-wide `OTEL_RESOURCE_ATTRIBUTES` as everything else in this
+section — nothing extra to configure. Cadence follows
+`HYPERHIVE_OTEL_METRIC_INTERVAL_MS` (default 60s, same variable + default as
+`hive-c0re`'s container-resource export above) — that only controls how often
+the batched points are flushed to the collector, not how often they're
+recorded (every turn, always).
+
 ## Agent-emitted custom metrics (`hive-metric`)
 
 Agents can push arbitrary labeled metrics to the same OTEL collector via the