refactor(docker): container CPU and memory live in the one metric store (#5752)

#5752 "Container CPU and memory history lives in the one metric store;
docker_metrics and docker_metrics_hourly are retired". Container cpu_pct and
mem_pct already went to plugin_metrics for alerting; now mem_usage_bytes does
too, and every snapshot in an ingest (backlog included) is recorded at its
own time. The container history chart, Busiest Containers, a service's
history and the MCP container tools read plugin_metrics under resource
"<host>/<container>", rolled up and pruned by the shared metric retention.

docker_012_drop_metrics drops both tables. Their history is not copied
(lesson #5221 "A data migration's cost is set by the live table"); the
store already holds 7 days of container CPU and memory %. Docker retention
now prunes only lifecycle events, and Settings -> Thresholds has one
"Metric retention" card for every source.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

plugins/docker/ingest.py

@@ -306,9 +306,10 @@ async def persist_host_docker(session, host, snapshots, swarm=None, disk=None,
 
     `snapshots` is a list of (recorded_at: datetime, containers: list[dict]) —
     one entry per ingested sample carrying docker data (usually one; more when
-    the agent flushes a backlog). Every snapshot contributes time-series
-    DockerMetric rows; the newest snapshot drives current container state, the
-    alert pipeline, and lifecycle-event derivation. `swarm` is the newest
+    the agent flushes a backlog). Every snapshot's running containers record
+    cpu_pct, mem_pct and mem_usage_bytes into the one metric store, at the
+    snapshot's time; the newest snapshot drives current container state and
+    lifecycle-event derivation. `swarm` is the newest
     sample's swarm object (or None off managers) — persisted when present.
     `disk` is the newest sample's /system/df summary (or None on Docker-less
     hosts) — persisted when present. `logs` is a list of (recorded_at, records)
@@ -323,7 +324,7 @@ async def persist_host_docker(session, host, snapshots, swarm=None, disk=None,
     flushed before its mark, so a slow ingest names the part (#5181).
     """
     from steward.core.alerts import MetricBatch
-    from .models import DockerContainer, DockerEvent, DockerMetric
+    from .models import DockerContainer, DockerEvent
 
     async def mark(name: str) -> None:
         if phases is not None:
@@ -350,18 +351,20 @@ async def persist_host_docker(session, host, snapshots, swarm=None, disk=None,
     ordered = sorted(snapshots, key=lambda s: s[0])
     latest_at, latest_containers = ordered[-1]
 
-    # Time-series points for every snapshot (running containers with a CPU read).
+    # Time series for every snapshot (running containers with a CPU read), in
+    # the one metric store (#5752): resource "<host>/<container>", so
+    # containers of the same name on different hosts don't collide. Recorded
+    # with the alert batch below, at each snapshot's own time.
+    batch = MetricBatch()
     for recorded_at, containers in ordered:
         for c in containers:
-            if c.get("status") == "running" and c.get("cpu_pct") is not None:
-                session.add(DockerMetric(
-                    host_id=host.id,
-                    container_name=c["name"],
-                    scraped_at=recorded_at,
-                    cpu_pct=c["cpu_pct"],
-                    mem_pct=c.get("mem_pct") or 0.0,
-                    mem_usage_bytes=c.get("mem_usage_bytes") or 0,
-                ))
+            if c.get("status") != "running" or c.get("cpu_pct") is None or not c.get("name"):
+                continue
+            resource = f"{host.name}/{c['name']}"
+            for metric in ("cpu_pct", "mem_pct", "mem_usage_bytes"):
+                if c.get(metric) is not None:
+                    batch.add(source_module="docker", resource_name=resource,
+                              metric_name=metric, value=c[metric], recorded_at=recorded_at)
     await mark("metrics")
 
     # Snapshot of stored per-container state BEFORE the upsert overwrites it —
@@ -389,8 +392,7 @@ async def persist_host_docker(session, host, snapshots, swarm=None, disk=None,
             ))
     await mark("events")
 
-    # Current state + alerts from the newest snapshot only.
-    batch = MetricBatch()
+    # Current state, and the restart and health alerts, from the newest snapshot only.
     for c in latest_containers:
         name = c.get("name")
         if not name:
@@ -424,19 +426,7 @@ async def persist_host_docker(session, host, snapshots, swarm=None, disk=None,
         existing.blk_read_bytes = c.get("blk_read_bytes")
         existing.blk_write_bytes = c.get("blk_write_bytes")
 
-        # Alert pipeline — resource is host-scoped so containers of the same name
-        # on different hosts don't collide in the metric/alert namespace.
         resource = f"{host.name}/{name}"
-        if c.get("status") == "running" and c.get("cpu_pct") is not None:
-            batch.add(
-                source_module="docker",
-                resource_name=resource, metric_name="cpu_pct", value=c["cpu_pct"],
-            )
-            if c.get("mem_pct") is not None:
-                batch.add(
-                    source_module="docker",
-                    resource_name=resource, metric_name="mem_pct", value=c["mem_pct"],
-                )
         # Restart count is alertable regardless of state (crash-looping matters
         # most while the container is down/restarting).
         batch.add(