feat(m8): event-based alerts — Xid/OOM/MCE/PCIe/disk from the kernel log — 0.34.0

AlertMonitor now scans the kernel log (journalctl -k) every ~30s and fires
one-shot, cooldown-gated desktop alerts on critical events: NVIDIA Xid, OOM
kills, CPU machine-checks, PCIe AER, and disk I/O errors — so users are warned
the moment something goes wrong, not only on a temperature threshold. Disk I/O
errors come from the kernel log (no root needed, unlike smartctl). Edge/spam
protection reuses the existing cooldown model. syslogs.scan_critical() does the
matching; init seeds last-scan to "now" so old boot logs don't alert on launch.
Tests for the matcher + monitor gating/cooldown; Settings note updated.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/rigdoctor/__init__.py

@@ -1,3 +1,3 @@
 """RigDoctor — modular hardware monitoring & crash diagnostics for Linux gamers."""
 
-__version__ = "0.33.0"
+__version__ = "0.34.0"

src/rigdoctor/core/alerts.py

@@ -1,8 +1,9 @@
-"""Desktop alerts (M8): notify on overheat / GPU-lost / new version via notify-send.
+"""Desktop alerts (M8): notify on overheat / GPU-lost / critical kernel events / new version.
 
-Edge-triggered: an alert fires when a condition becomes true (not every sample), and
-can fire again only after it has cleared and a cooldown has passed — so a hot GPU or a
-1-Hz sample loop doesn't spam notifications. Degrades to a no-op if notify-send is absent.
+Edge-triggered: a sustained condition (hot GPU, GPU-lost) fires once when it becomes true and
+can re-fire only after it clears + a cooldown; momentary **kernel events** (Xid, OOM-kill, MCE,
+PCIe AER, disk I/O errors) are scanned from the kernel log every `event_interval` seconds and
+fire one-shot (cooldown-gated). So a 1-Hz sample loop never spams. No-op if notify-send absent.
 """
 
 from __future__ import annotations
@@ -57,13 +58,16 @@ def notify(title: str, message: str, urgency: str = "normal") -> bool:
 class AlertMonitor:
     """Evaluate samples and raise edge-triggered desktop alerts."""
 
-    def __init__(self, gpu_temp: float = 90.0, cpu_temp: float = 95.0, cooldown: float = 300.0):
+    def __init__(self, gpu_temp: float = 90.0, cpu_temp: float = 95.0, cooldown: float = 300.0,
+                 event_interval: float = 30.0):
         self.gpu_temp = gpu_temp
         self.cpu_temp = cpu_temp
         self.cooldown = cooldown
+        self.event_interval = event_interval     # how often to scan the kernel log
         self.enabled = True
         self._active: dict[str, bool] = {}
         self._last: dict[str, float] = {}
+        self._last_kernel_scan = time.time()     # only alert on events after the monitor starts
 
     def _fire(self, key: str, title: str, message: str, urgency: str = "critical") -> None:
         if self._active.get(key):
@@ -75,9 +79,39 @@ class AlertMonitor:
         self._last[key] = now
         notify(title, message, urgency)
 
+    def _notify_once(self, key: str, title: str, message: str, urgency: str = "critical") -> None:
+        """One-shot alert for a momentary event (cooldown-gated, no active latch)."""
+        now = time.time()
+        if now - self._last.get(key, 0.0) < self.cooldown:
+            return
+        self._last[key] = now
+        notify(title, message, urgency)
+
     def _clear(self, key: str) -> None:
         self._active[key] = False
 
+    def _scan_kernel_events(self) -> None:
+        """Periodically scan the kernel log for new critical events (Xid/OOM/MCE/PCIe/disk)."""
+        now = time.time()
+        if now - self._last_kernel_scan < self.event_interval:
+            return
+        since = self._last_kernel_scan
+        self._last_kernel_scan = now
+        try:
+            from . import syslogs
+
+            text = syslogs.kernel_log(since=since)
+        except Exception:  # alerting must never crash the sample loop
+            return
+        if not text:
+            return
+        seen: set[str] = set()
+        for label, line in syslogs.scan_critical(text):
+            if label in seen:  # one alert per category per scan
+                continue
+            seen.add(label)
+            self._notify_once(f"kernel:{label}", label, line[:180])
+
     def check(self, sample: Sample) -> None:
         if not self.enabled:
             return
@@ -107,3 +141,5 @@ class AlertMonitor:
             self._fire("gpu_lost", "GPU not responding", "nvidia-smi query timed out — the GPU may have dropped")
         else:
             self._clear("gpu_lost")
+
+        self._scan_kernel_events()  # Xid / OOM / MCE / PCIe / disk I/O from the kernel log

src/rigdoctor/core/syslogs.py

@@ -13,6 +13,7 @@ Best-effort and size-bounded: degrades silently if a tool is missing or access i
 from __future__ import annotations
 
 import os
+import re
 import shutil
 import subprocess
 import time
@@ -118,6 +119,29 @@ def display_log(since: float | None = None, max_bytes: int = _MAX) -> str:
     return _tail_file(log, max_bytes) if log else ""
 
 
+# Kernel-log patterns worth alerting on in real time (M8 event alerts). (label, regex).
+_CRITICAL = [
+    ("GPU error (Xid)", re.compile(r"NVRM:\s*Xid", re.I)),
+    ("Out of memory", re.compile(r"out of memory|oom-kill|killed process \d+", re.I)),
+    ("CPU machine-check", re.compile(r"\bmce:|machine check", re.I)),
+    ("PCIe error", re.compile(r"\bAER:|pcie bus error", re.I)),
+    ("Disk I/O error", re.compile(
+        r"buffer i/o error|\bi/o error\b|critical medium error|ext4-fs error|"
+        r"blk_update_request:.*error|ata\d+.*(?:failed|error)", re.I)),
+]
+
+
+def scan_critical(text: str) -> list[tuple[str, str]]:
+    """(label, line) for kernel lines matching a critical pattern (first match per line)."""
+    events: list[tuple[str, str]] = []
+    for line in text.splitlines():
+        for label, pat in _CRITICAL:
+            if pat.search(line):
+                events.append((label, line.strip()))
+                break
+    return events
+
+
 def available() -> bool:
     return bool(shutil.which("journalctl") or shutil.which("coredumpctl")
                 or shutil.which("nvidia-smi") or _xorg_log())

src/rigdoctor/gui/setup_page.py

@@ -114,7 +114,8 @@ class SetupPage(QWidget):
         grid.addWidget(QLabel("CPU temperature alert"), 1, 0)
         grid.addWidget(self._cpu_alert, 1, 1)
         alerts_layout.addLayout(grid)
-        alerts_note = QLabel("GPU-lost and new-version alerts are included whenever notifications are enabled.")
+        alerts_note = QLabel("GPU-lost, critical kernel events (Xid, out-of-memory, disk I/O, PCIe), "
+                             "and new-version alerts are included whenever notifications are enabled.")
         alerts_note.setObjectName("Muted")
         alerts_note.setWordWrap(True)
         alerts_layout.addWidget(alerts_note)