feat(alerts): the metric catalog is written by what emits it (#5061)

#5061 "Metric catalog belongs to what emits: plugins register their
metrics; names match what is recorded".

- The static METRIC_CATALOG is gone. metric_catalog() is core's own sources
  (the four monitor types and "steward", the app's open_fds/open_fds_pct,
  which were recorded but never offered) plus each loaded plugin's
  get_alert_metrics() export. A disabled plugin's sources leave the picker.
- traefik offers what it records: error_rate_4xx_pct and error_rate_5xx_pct.
  The old "error_rate" was never recorded, so a rule on it could not fire.
- tests/core/test_metric_catalog.py walks every MetricBatch.add /
  record_metric call (traefik's tuple loop included) and fails on a recorded
  metric the catalog lacks; it shows on a synthetic writer that it can fail.

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

plugins/docker/__init__.py

@@ -62,3 +62,10 @@ async def mcp_overview(db) -> list[dict]:
 def get_nav() -> list[dict]:
     # Surfaces in the sidebar's Infrastructure group (fleet-wide container view).
     return [{"label": "Docker", "href": "/plugins/docker/"}]
+
+
+def get_alert_metrics() -> dict[str, list[str]]:
+    """What ingest.py records per container (resource "<host>/<container>"):
+    restart_count is cumulative (alert on crash-looping); is_healthy is 1.0 /
+    0.0 from the container's HEALTHCHECK, only for containers that define one."""
+    return {"docker": ["cpu_pct", "mem_pct", "restart_count", "is_healthy"]}

plugins/host_agent/__init__.py

@@ -31,3 +31,13 @@ def register_mcp_tools(register) -> None:
 async def mcp_overview(db) -> list[dict]:
     from .mcp_tools import mcp_overview as findings
     return await findings(db)
+
+
+def get_alert_metrics() -> dict[str, list[str]]:
+    """Host metrics ingest records for alert rules (resource = the host name;
+    disk_used_pct per mount, resource "<host>:<mount>")."""
+    return {"host_agent": [
+        "cpu_pct", "mem_used_pct", "mem_available_bytes", "swap_used_bytes",
+        "disk_used_pct_worst", "disk_used_pct", "load_1m", "load_5m", "load_15m",
+        "uptime_secs",
+    ]}

plugins/snmp/__init__.py

@@ -26,3 +26,9 @@ def get_blueprint():
 def get_nav() -> list[dict]:
     # Surfaces in the sidebar's Infrastructure group (SNMP device readings).
     return [{"label": "SNMP", "href": "/plugins/snmp/"}]
+
+
+def get_alert_metrics() -> dict[str, list[str]]:
+    """SNMP metric names are the OID labels each device is configured with, so
+    the list is empty here and the rule form offers the labels recorded so far."""
+    return {"snmp": []}

plugins/traefik/__init__.py

@@ -33,3 +33,11 @@ def get_blueprint():
 def get_nav() -> list[dict]:
     # Surfaces in the sidebar's Infrastructure group (Traefik services view).
     return [{"label": "Traefik", "href": "/plugins/traefik/"}]
+
+
+def get_alert_metrics() -> dict[str, list[str]]:
+    """What scheduler.py records for alert rules: per router (resource = the
+    router name) and cert_expiry_days per certificate (resource = its CN)."""
+    return {"traefik": ["request_rate", "error_rate_4xx_pct", "error_rate_5xx_pct",
+                        "latency_p50_ms", "latency_p95_ms", "latency_p99_ms",
+                        "response_bytes_rate", "cert_expiry_days"]}

plugins/unifi/__init__.py

@@ -31,3 +31,9 @@ def get_blueprint():
 def get_nav() -> list[dict]:
     # Surfaces in the sidebar's Infrastructure group (UniFi network overview).
     return [{"label": "UniFi", "href": "/plugins/unifi/"}]
+
+
+def get_alert_metrics() -> dict[str, list[str]]:
+    """What scheduler.py records: the WAN (resource "wan") and the client count
+    (resource "clients")."""
+    return {"unifi": ["is_up", "latency_ms", "total_clients"]}