feat(norms): hosts, containers and monitor response times are graded against their own normal (#5742)

Host CPU, memory and load per core, container CPU and memory, and every
monitor's response time learn a normal per hour (milestone 513, System 182).
A reading past its fixed cutoff but within its normal reads healthy and says
what is usual at this hour; one well out of it keeps its grade and is a
metric anomaly. Disk, a monitor down and an agent offline keep their cutoffs.

- Each normal's floor, the smallest departure that counts, is a setting:
  Settings -> Thresholds -> Normals (norms.floor.*). Defaults: host CPU 10
  points, host memory 5, load per core 10, container CPU 10 points of one
  core, container memory 5, monitor response 100 ms; Traefik's 2-point 4xx
  and 50 ms p95 floors move there from constants. learn_normal takes a
  floor function (floor_setting) read at each pass.
- learn_normal(parts=False): a host learns, its cores don't.
- Ingest records load_pct (load_1m / cores x 100), the figure pages grade.
- Shared grading: anomalies.against / graded, worst_reading(normals=),
  hosts' host_grades, docker usage(thresholds=, norms=), monitors'
  latency_grade. Applied to host vitals, the Hosts widget, MCP overview,
  Docker usage, and the monitor list, widget and page.
- The monitor and container pages list their anomalies.

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

plugins/host_agent/routes.py

@@ -21,6 +21,7 @@ from steward.core.health import ingest as ingest_tally
 from steward.core.metric_series import points as metric_points
 from steward.core.settings import get_setting, public_base_url
 from steward.core.time_range import parse_range, RANGE_OPTIONS
+from steward.hosts import service as host_svc
 from steward.models.hosts import Host
 from steward.models.metrics import PluginMetric
 from .models import HostAgentRegistration
@@ -118,6 +119,10 @@ def _expand_sample_to_metrics(
     for key in ("1m", "5m", "15m"):
         if key in load:
             row(f"load_{key}", host_name, load[key])
+    # Load per core as a %, the figure the pages grade, so it can learn a
+    # normal (#5742): a load of 6 is idle on 32 cores and busy on 4.
+    if "1m" in load and sample.get("cpu_cores"):
+        row("load_pct", host_name, 100.0 * load["1m"] / len(sample["cpu_cores"]))
 
     if sample.get("uptime_secs") is not None:
         row("uptime_secs", host_name, sample["uptime_secs"])
@@ -725,6 +730,7 @@ async def host_vitals(host_id: str):
         reg = (await db.execute(select(HostAgentRegistration).where(
             HostAgentRegistration.host_id == host_id))).scalar_one_or_none()
         latest = await _latest_metrics_for_host(db, host.name) if reg else {}
+        norms = await host_svc.host_norms(db, host.name) if reg else {}
 
         # The last 6 h for the at-a-glance sparklines (cpu/mem/load host-level,
         # disk from the root mount), averaged into ~120 points in SQL, so the
@@ -759,13 +765,23 @@ async def host_vitals(host_id: str):
     reporting = bool(reg) and ls is not None
     stale = reporting and (datetime.now(timezone.utc) - ls).total_seconds() > _stale_after_seconds()
     cpu, mem = hostlvl.get("cpu_pct"), hostlvl.get("mem_used_pct")
+    thresholds = current_app.config.get("THRESHOLDS", {})
     worst = worst_reading((("CPU", cpu, "cpu"), ("Memory", mem, "mem"), ("Disk /", disk_root, "disk"),
                            ("Load per core", load_per_core, "load")),
-                          current_app.config.get("THRESHOLDS", {}))
+                          thresholds, host_svc.host_normals(norms, thresholds))
+    # Each tile's grade; CPU, memory and load within the host's own normal
+    # for the hour read healthy, and say what is usual (#5742).
+    grades = host_svc.host_grades({"cpu": cpu, "mem": mem, "disk": disk_root, "load": load_per_core},
+                                  norms, thresholds)
+    usual = [f"{label} {value:.0f}% is {grades[kind][1]}"
+             for label, value, kind in (("CPU", cpu, "cpu"), ("Memory", mem, "mem"),
+                                        ("load per core", load_per_core, "load"))
+             if grades[kind][1]]
     return await render_template(
         "_host_vitals.html",
         reg=reg, cpu=cpu, mem=mem, disk_root=disk_root, load_per_core=load_per_core,
         sparks=sparks, psi=psi, reporting=reporting, stale=stale, worst=worst,
+        grades=grades, usual=usual,
         clock=clock_words(reg.clock_offset_s if reg else None, current_app.config.get("THRESHOLDS", {})),
     )