feat(hosts): the hottest sensor is named with its chip, and the host-reading cutoffs are read and set over MCP (#6806)

Agent 1.27.0 sends each temperature sensor's hwmon chip. Steward keeps the
chip per host and label beside the reading, so a sensor's metric key stays
its label, and the strip and the heat alert name it as "NVMe · Sensor 2"
rather than a bare "Sensor 2".

get_thresholds (viewer) and set_thresholds (admin, audited) read and change
the warn/crit cutoffs CPU, memory, disk, load and temperature are graded by,
as Settings → Thresholds does.

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

plugins/host_agent/agent.py

@@ -22,7 +22,7 @@ from collections import deque
 from concurrent.futures import ThreadPoolExecutor, wait as wait_futures
 from datetime import datetime, timezone
 
-AGENT_VERSION = "1.26.1"
+AGENT_VERSION = "1.27.0"
 
 # Default path to the local Docker Engine socket. Overridable via the
 # `docker_socket` config key; collection is silently skipped if it's absent or
@@ -480,7 +480,9 @@ def nfs_delays(cur: dict, prev: dict, dt: float) -> list:
 
 
 def collect_temps() -> list:
-    """Return [{label, celsius}] from /sys/class/hwmon (best-effort, may be empty)."""
+    """Return [{label, celsius, chip}] from /sys/class/hwmon (best-effort, may
+    be empty). `chip` is the hwmon driver's name (coretemp, nvme, nct6798…),
+    which says what a bare label like "Sensor 2" is measuring."""
     out: list = []
     try:
         chips = os.listdir(HWMON_DIR)
@@ -511,7 +513,7 @@ def collect_temps() -> list:
             except OSError:
                 pass
             name = label or (f"{chip}_{idx}" if chip else idx)
-            out.append({"label": name, "celsius": round(milli / 1000.0, 1)})
+            out.append({"label": name, "celsius": round(milli / 1000.0, 1), "chip": chip})
     return out
 
 

plugins/host_agent/routes.py

@@ -124,13 +124,15 @@ def is_thermometer(host_name: str, label: str, celsius: float) -> bool:
 
 def hottest_sensor(host_name: str, temps: dict[str, float]) -> list[str]:
     """Which sensor sets a host's temperature, as an alert on it says:
-    ["Package id 0 at 86°C"], or [] with no thermometer among `temps`."""
+    ["CPU · Package id 0 at 86°C"], or [] with no thermometer among `temps`.
+    The chip leads the label when the host's agent has said which it is."""
     from steward.core.formatting import metric_value
     real = {label: c for label, c in temps.items() if is_thermometer(host_name, label, c)}
     if not real:
         return []
+    from .sensors import sensor_name
     label = max(real, key=real.get)
-    return [f"{label} at {metric_value('temp_c', real[label])}"]
+    return [f"{sensor_name(host_name, label)} at {metric_value('temp_c', real[label])}"]
 
 
 async def name_hottest_sensor(session, resource: str) -> list[str]:
@@ -374,6 +376,8 @@ def _expand_sample_to_metrics(
     # counts only readings that can be real (#5759), from sensors that behave
     # like thermometers (#5783).
     max_temp: float | None = None
+    from .sensors import note_chips
+    note_chips(host_name, sample.get("temps"))
     for t in sample.get("temps") or []:
         c = t.get("celsius")
         if c is None:

plugins/host_agent/sensors.py

@@ -53,6 +53,51 @@ def unwired(host_name: str) -> dict[str, str]:
     return _unwired.get(host_name, {})
 
 
+# {host name: {sensor label: hwmon chip}}, as the host's latest sample said.
+# A sensor's metric is keyed by its label alone; the chip only names it.
+_chips: dict[str, dict[str, str]] = {}
+
+# What each hwmon driver measures, in the words a page uses. A driver not
+# listed is shown by its own name.
+_CHIP_WORDS = (
+    (re.compile(r"^(coretemp|k10temp|zenpower|cpu_thermal)$"), "CPU"),
+    (re.compile(r"^nvme$"), "NVMe"),
+    (re.compile(r"^drivetemp$"), "Drive"),
+    (re.compile(r"^(nct\d+|it\d+|w83\w+|f71\w+)$"), "Board"),
+    (re.compile(r"^pch_\w+$"), "Chipset"),
+    (re.compile(r"^(amdgpu|radeon|nouveau|i915|xe)$"), "GPU"),
+    (re.compile(r"^(spd5118|jc42)$"), "Memory"),
+    (re.compile(r"^iwlwifi"), "Wi-Fi"),
+    (re.compile(r"^acpitz$"), "ACPI"),
+)
+
+
+def note_chips(host_name: str, temps) -> None:
+    """Remember which chip each of a host's sensors is on, from a sample's
+    temps. An agent that doesn't say leaves what is known as it is."""
+    seen = {str(t["label"]): str(t["chip"]) for t in temps or [] if t.get("chip")}
+    if seen:
+        _chips[host_name] = seen
+
+
+def chip_word(chip: str) -> str:
+    """What a hwmon chip measures ("nvme" → "NVMe"), or its own name."""
+    for pattern, word in _CHIP_WORDS:
+        if pattern.match(chip):
+            return word
+    return chip
+
+
+def sensor_name(host_name: str, label: str) -> str:
+    """A sensor as a page names it: its chip, then its label, as in
+    "NVMe · Sensor 2". The label alone when the chip isn't known or the
+    label already carries it ("nvme_temp1")."""
+    chip = _chips.get(host_name, {}).get(label)
+    if not chip or label.lower().startswith(chip.lower()):
+        return label
+    return f"{chip_word(chip)} · {label}"
+
+
 def reference_label(labels) -> str | None:
     """The sensor that reads the host's CPU, or None when it has none."""
     labels = sorted(labels)