feat(monitors): problems first, a page per monitor, adding on its own page (#5121)

The Monitors list now opens with a count strip (down, up with how many
degraded, pending, paused) and sorts down, degraded, pending, up, paused,
by name within each. Degraded is up but worth a look: uptime at or below
its warning floor, or the latest response past its critical cutoff, both
from Settings → Thresholds; a slow-but-tolerable reply is coloured, not
sorted.

A monitor had no page of its own: every link went to the list. Now
/monitors/<id> shows its state and since when, latency, uptime for 24h/7d/
30d, TLS days, the last checks, recent failures with their errors, and its
settings (HTTP header names, never their values). Status links to it, and
adding or editing returns to it.

Adding is its own page (/monitors/new, form.html shared with edit) behind
an "Add monitor" button; a refused add re-renders the form with the error
and what was typed instead of a bare 400 text. Row actions are labelled
icon buttons, type names read Ping/TCP/DNS/HTTP (|monitor_type), and the
heartbeat uses pill-up/pill-down, so HEX_CEILING drops to 56.

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

steward/monitors/service.py

@@ -12,6 +12,7 @@ from datetime import datetime, timezone
 
 from sqlalchemy import func, select
 
+from steward.core.formatting import status_class
 from steward.core.status import _heartbeat_title, _last_n_results, _uptime_by_monitor
 from steward.core.time_range import parse_range
 from steward.models.monitors import MONITOR_TYPE_VALUES, Monitor, MonitorResult, MonitorType
@@ -128,12 +129,42 @@ async def check_name_free(db, mtype: str, name: str, exclude_id: str | None = No
                          "alert rules go by that name, so pick a different one.")
 
 
-async def monitor_rows(db, range_key: str):
-    """Per-monitor state: latest result, heartbeat strip, uptime and TLS days.
+# Where each state sorts on the Monitors page: what needs looking at first.
+STATE_ORDER = {"down": 0, "degraded": 1, "pending": 2, "up": 3, "paused": 4}
 
-    Returns (rows, up, down, pending, range_key). `range_key` picks the uptime
-    window surfaced (24h/7d/30d; anything else falls back to 24h) and comes
-    back normalised.
+
+def row_state(monitor: Monitor, latest, uptime_pct, thresholds: dict) -> str:
+    """paused, pending (never checked), down, degraded or up.
+
+    Degraded is up but worth a look: uptime over the window at or below its
+    warning cutoff, or the latest response time past its critical one
+    (Settings → Thresholds). A slow-but-tolerable reply is coloured, not sorted.
+    """
+    if not monitor.enabled:
+        return "paused"
+    if latest is None:
+        return "pending"
+    if not latest.is_up:
+        return "down"
+    if (status_class(uptime_pct, "uptime", thresholds) in ("warn", "crit")
+            or status_class(latest.response_ms, "latency", thresholds) == "crit"):
+        return "degraded"
+    return "up"
+
+
+def problems_first(rows: list[dict]) -> list[dict]:
+    """Down, then degraded, then pending, up and paused; by name within each."""
+    return sorted(rows, key=lambda d: (STATE_ORDER[d["state"]], d["monitor"].name.lower()))
+
+
+async def monitor_rows(db, range_key: str, thresholds: dict):
+    """Per-monitor state: latest result, heartbeat strip, uptime and TLS days,
+    problems first.
+
+    Returns (rows, counts, range_key). `counts` has up (degraded included),
+    degraded, down, pending and paused. `range_key` picks the uptime window
+    surfaced (24h/7d/30d; anything else falls back to 24h) and comes back
+    normalised.
     """
     _since, range_key = parse_range(range_key)
     monitors = list((await db.execute(select(Monitor).order_by(Monitor.name))).scalars())
@@ -148,21 +179,22 @@ async def monitor_rows(db, range_key: str):
     for m in monitors:
         rows = recent.get(m.id, [])
         latest = rows[-1] if rows else None
+        uptime_pct = uptime.get(m.id, {}).get(bucket)
         tls_days = None
         if latest and latest.tls_expires_at:
             tls_days = (latest.tls_expires_at - now).total_seconds() / 86400.0
         data.append({
             "monitor": m,
             "latest": latest,
+            "state": row_state(m, latest, uptime_pct, thresholds),
             "heartbeat": [{"state": "up" if r.is_up else "down",
                            "title": _heartbeat_title(m.type, r)} for r in rows],
-            "uptime_pct": uptime.get(m.id, {}).get(bucket),
+            "uptime_pct": uptime_pct,
             "tls_days": tls_days,
         })
-    up = sum(1 for d in data if d["latest"] and d["latest"].is_up)
-    down = sum(1 for d in data if d["latest"] and not d["latest"].is_up)
-    pending = sum(1 for d in data if not d["latest"])
-    return data, up, down, pending, range_key
+    counts = {k: sum(d["state"] == k for d in data) for k in STATE_ORDER}
+    counts["up"] += counts["degraded"]
+    return problems_first(data), counts, range_key
 
 
 async def down_since(db, monitor_id: str):