Merge pull request 'feat(health): detect no-Xid GPU freezes (open-module VA-space faults)' (#46) from feat/gpu-vaspace-spt into main

Reviewed-on: #46

CHANGELOG.md

@@ -5,6 +5,26 @@ All notable changes to RigDoctor are recorded here. Format follows
 (`MAJOR.MINOR.PATCH`, pre-1.0). `__version__` and `pyproject.toml` must match the git
 release tag (so the auto-updater, D18, can compare versions).
 
+## [0.42.0] - 2026-05-29
+### Added
+- **Detect hard freezes that log no Xid.** The kernel-log scanner caught Xid codes, OOM, panic,
+  MCE, PCIe AER, thermal events, and amdgpu resets — but a crash that logs *no* Xid slipped
+  through. It now flags the NVIDIA open-kernel-module **VA-space mapping fault** (`gpu_vaspace.c`
+  / `dmaAllocMapping` assertions, NVKMS GEM-allocation failures) — a driver-internal error that
+  can storm for minutes and end in a freeze without the GPU ever "falling off the bus" (distinct
+  from Xid 79). A new `check_nvidia_module()` notes when the open module (`nvidia-*-open`) is
+  loaded — the context behind these faults — and a new `ai_knowledge` entry lets the assistant
+  tell the no-Xid freeze apart from the Xid 79 hardware drop.
+- **Add games no launcher reports (e.g. SPT).** A user-authored custom-games list
+  (`core/customgames.py`) shows alongside Steam/Lutris/Heroic in `rigdoctor games` and the GUI
+  ("Add game…"), for standalone mod launchers (Single-Player Tarkov), itch.io downloads, or any
+  hand-installed game. Each entry can carry a launch command and a log directory:
+  `rigdoctor games add "SPT" --command .../tarkov.sh` (a sibling `logs/` is auto-detected),
+  `rigdoctor games play "SPT"` launches it under the crash-capture wrapper (tagged with the real
+  name, not the script's), and the diagnostic now tails the game's *own* logs — SPT's
+  server/launcher logs — alongside the kernel log so the analysis sees what the game logged
+  before the freeze.
+
 ## [0.41.0] - 2026-05-25
 ### Added
 - **Import a crash dump (`.dmp`) and explain it with AI.** The **Games** page gains an

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "rigdoctor"
-version = "0.41.0"
+version = "0.42.0"
 description = "Modular hardware monitoring & crash diagnostics for Linux gamers."
 readme = "README.md"
 requires-python = ">=3.11"

src/rigdoctor/__init__.py

@@ -1,3 +1,3 @@
 """RigDoctor — modular hardware monitoring & crash diagnostics for Linux gamers."""
 
-__version__ = "0.41.0"
+__version__ = "0.42.0"

src/rigdoctor/cli.py

@@ -525,13 +525,13 @@ def cmd_gameenv(args) -> int:
 def cmd_games(args) -> int:
     from dataclasses import asdict
 
-    from .core import launchers, steam
+    from .core import customgames, launchers, steam
 
     selected = steam.selected_library_paths()
     result = steam.rescan() if selected else None
     steam_games = result.games if result else []
     extra = launchers.scan()  # non-Steam (Lutris/Heroic)
-    all_games = list(steam_games) + list(extra)
+    all_games = list(steam_games) + list(extra) + customgames.scan()  # + user-added (SPT etc.)
 
     if args.json:
         print(json.dumps({
@@ -596,6 +596,50 @@ def cmd_games_libraries(args) -> int:
     return 0
 
 
+def cmd_games_add(args) -> int:
+    from .core import customgames
+
+    if customgames.add(args.name, command=args.command, logdir=args.logdir):
+        print(f"Added '{args.name}' to your games (custom). It'll show in `rigdoctor games` "
+              "and the diagnostic game picker.")
+        entry = customgames.get(args.name) or {}
+        if entry.get("command"):
+            print(f"  launch:  {entry['command']}   (run with: rigdoctor games play \"{args.name}\")")
+        if entry.get("logdir"):
+            print(f"  logs:    {entry['logdir']}   (included in crash diagnostics)")
+        return 0
+    print(f"'{args.name}' is blank or already in your custom games.")
+    return 1
+
+
+def cmd_games_play(args) -> int:
+    from .core import customgames, wrap
+
+    command = customgames.command(args.name)
+    if command is None:
+        if customgames.get(args.name) is None:
+            print(f"'{args.name}' isn't in your custom games. Add it: "
+                  f"rigdoctor games add \"{args.name}\" --command <launch script>")
+        else:
+            print(f"'{args.name}' has no launch command. Set one: "
+                  f"rigdoctor games remove \"{args.name}\" && rigdoctor games add \"{args.name}\" "
+                  "--command <launch script>")
+        return 1
+    print(f"Launching '{args.name}' with crash-capture… (capture stops cleanly on exit; "
+          "a hard freeze is flagged next time you open RigDoctor)")
+    return wrap.run(command, game=args.name)
+
+
+def cmd_games_remove(args) -> int:
+    from .core import customgames
+
+    if customgames.remove(args.name):
+        print(f"Removed '{args.name}' from your custom games.")
+        return 0
+    print(f"'{args.name}' isn't in your custom games. Current: {', '.join(customgames.names()) or '(none)'}")
+    return 1
+
+
 def build_parser() -> argparse.ArgumentParser:
     p = argparse.ArgumentParser(
         prog="rigdoctor",
@@ -681,6 +725,20 @@ def build_parser() -> argparse.ArgumentParser:
     lib_p.add_argument("--json", action="store_true", help="output JSON")
     lib_p.set_defaults(func=cmd_games_libraries)
 
+    add_p = games_sub.add_parser("add", help="add a game no launcher reports (e.g. SPT)")
+    add_p.add_argument("name", help="game name, e.g. \"SPT\"")
+    add_p.add_argument("--command", default=None,
+                       help="launch command/script (e.g. the path to tarkov.sh) — enables `games play`")
+    add_p.add_argument("--logdir", default=None,
+                       help="the game's own log directory (auto-detected as <command dir>/logs if present)")
+    add_p.set_defaults(func=cmd_games_add)
+    play_p = games_sub.add_parser("play", help="launch a custom game with crash-capture (e.g. SPT)")
+    play_p.add_argument("name", help="game name to launch")
+    play_p.set_defaults(func=cmd_games_play)
+    rm_p = games_sub.add_parser("remove", help="remove a previously added custom game")
+    rm_p.add_argument("name", help="game name to remove")
+    rm_p.set_defaults(func=cmd_games_remove)
+
     env_p = sub.add_parser("gameenv", help="gaming environment checks (M6): flag stability/perf settings")
     env_p.add_argument("--json", action="store_true", help="output JSON instead of text")
     env_p.set_defaults(func=cmd_gameenv)

src/rigdoctor/config.py

@@ -36,6 +36,9 @@ SPAWN_LOG = STATE_DIR / "recorder.out"
 # Gaming environment / game detection (M6) — cached Steam game scan (mutable state,
 # not config: refreshed by the background scan on every launch).
 GAMES_FILE = STATE_DIR / "games.json"
+# User-added games that no launcher reports (e.g. SPT/standalone mod launchers). Authored
+# by the user (not a refreshable cache), so it lives in DATA_DIR and persists across scans.
+CUSTOM_GAMES_FILE = DATA_DIR / "custom-games.json"
 
 # Logging & reports (opt-in via `logging_enabled`). App log: rotating file of app events.
 # Each diagnostic is stored under DIAGNOSTICS_DIR/<id>/; "Report" zips one into REPORTS_DIR.

src/rigdoctor/core/ai_knowledge.py

@@ -30,6 +30,14 @@ ENTRIES: list[tuple[tuple[str, ...], str]] = [
     (("xid 8", "xid 62", "xid 63", "xid 64"),
      "These Xid codes commonly indicate VRAM/ECC or memory-training problems — suspect failing "
      "VRAM or an unstable memory overclock."),
+    (("va-space mapping", "gpu_vaspace", "dmaallocmapping", "nvkms memory for gem",
+      "open kernel module", "nvidia open"),
+     "NVIDIA open-kernel-module VA-space mapping errors (gpu_vaspace.c / dmaAllocMapping / "
+     "'Failed to allocate NVKMS memory for GEM object') are a driver-internal fault on the open "
+     "module (nvidia-*-open). They can storm for minutes and end in a HARD FREEZE with NO Xid "
+     "logged — so the GPU never 'falls off the bus', and this is distinct from the Xid 79 "
+     "hardware drop. Fix path: switch from the open to the proprietary NVIDIA kernel module and "
+     "update to the latest driver branch."),
     (("smart 197", "current_pending_sector", "pending sector"),
      "SMART 197 (Current Pending Sector) > 0 = sectors the drive can't read and is waiting to "
      "reallocate — early sign of a failing disk. Back up now and run an extended self-test."),

src/rigdoctor/core/customgames.py

@@ -0,0 +1,113 @@
+"""User-added games (M6): a manual list for titles no launcher reports.
+
+Some games never show up in a Steam/Lutris/Heroic scan — standalone mod launchers like
+**SPT** (Single-Player Tarkov), itch.io downloads, or any hand-installed executable. This
+module keeps a small user-authored list so those still appear in the game list and can be
+picked for a focused diagnostic, in the same `steam.Game` shape as every other source.
+
+Each entry is a name plus two optionals: a **launch command** (so `rigdoctor games play`
+can start it under the auto-capture wrapper) and a **log directory** (so a crash diagnostic
+can read the game's own logs — e.g. SPT's `logs/tarkov-latest.log`). Stored as JSON in
+`config.CUSTOM_GAMES_FILE`; stdlib only; every reader degrades to [] on a missing/bad file.
+"""
+
+from __future__ import annotations
+
+import json
+import os
+import shlex
+
+from .. import config
+from .steam import Game
+
+LAUNCHER = "custom"
+
+
+def _load() -> list[dict]:
+    try:
+        data = json.loads(config.CUSTOM_GAMES_FILE.read_text())
+    except (OSError, ValueError):
+        return []
+    games = data.get("games") if isinstance(data, dict) else None
+    return [g for g in games if isinstance(g, dict) and g.get("name")] if isinstance(games, list) else []
+
+
+def _save(games: list[dict]) -> None:
+    config.CUSTOM_GAMES_FILE.parent.mkdir(parents=True, exist_ok=True)
+    config.CUSTOM_GAMES_FILE.write_text(json.dumps({"games": games}, indent=2, ensure_ascii=False) + "\n")
+
+
+def names() -> list[str]:
+    """Just the stored names (insertion order preserved)."""
+    return [str(g["name"]) for g in _load()]
+
+
+def get(name: str) -> dict | None:
+    """The stored entry (name + optional command/logdir) for a game, case-insensitive."""
+    name = (name or "").strip().lower()
+    return next((g for g in _load() if str(g["name"]).lower() == name), None)
+
+
+def add(name: str, command: str | None = None, logdir: str | None = None) -> bool:
+    """Add a game by name, with an optional launch command and log directory.
+
+    Returns False if the name is blank or already present (case-insensitive). When a command
+    is given but no logdir, a sibling `logs/` dir is inferred if it exists (covers SPT's layout).
+    """
+    name = (name or "").strip()
+    if not name:
+        return False
+    if get(name):
+        return False
+    entry: dict = {"name": name}
+    command = (command or "").strip()
+    if command:
+        entry["command"] = command
+        if not logdir:
+            sibling = os.path.join(os.path.dirname(_argv0(command)), "logs")
+            if os.path.isdir(sibling):
+                logdir = sibling
+    logdir = (logdir or "").strip()
+    if logdir:
+        entry["logdir"] = os.path.expanduser(logdir)
+    games = _load()
+    games.append(entry)
+    _save(games)
+    return True
+
+
+def remove(name: str) -> bool:
+    """Remove a game by name (case-insensitive). Returns True if one was removed."""
+    name = (name or "").strip().lower()
+    games = _load()
+    kept = [g for g in games if str(g["name"]).lower() != name]
+    if len(kept) == len(games):
+        return False
+    _save(kept)
+    return True
+
+
+def _argv0(command: str) -> str:
+    parts = shlex.split(command)
+    return parts[0] if parts else command
+
+
+def command(name: str) -> list[str] | None:
+    """The launch argv for a game (shlex-split), or None if it has no command."""
+    entry = get(name)
+    cmd = (entry or {}).get("command")
+    return shlex.split(cmd) if cmd else None
+
+
+def log_dir(name: str) -> str | None:
+    """The game's own log directory, or None if it isn't set / doesn't exist."""
+    entry = get(name)
+    path = (entry or {}).get("logdir")
+    return path if path and os.path.isdir(path) else None
+
+
+def scan() -> list[Game]:
+    """User-added games as `Game` objects (launcher='custom'), sorted by name."""
+    out = [Game(appid="", name=str(g["name"]), library="", installdir="", launcher=LAUNCHER)
+           for g in _load()]
+    return sorted(out, key=lambda g: g.name.lower())

src/rigdoctor/core/diagstore.py

@@ -75,7 +75,7 @@ def store(result, capture_path=None, since: float | None = None) -> Path | None:
     _write(target / "report.txt", "\n".join(report))
 
     try:
-        logs = gamelogs.collect(since=since)
+        logs = gamelogs.collect(since=since, game=getattr(result, "game", None))
         if logs:
             _write(target / "gamelogs.txt", logs)
     except OSError:

src/rigdoctor/core/gamelogs.py

@@ -81,15 +81,48 @@ def available() -> bool:
     return bool(_proton_logs() or _steam_console())
 
 
-def collect(since: float | None = None, max_bytes: int = 8000) -> str:
-    """Recent Proton + Steam log tails as one labelled text block ('' if none).
+def _custom_game_logs(game: str, since: float | None, max_bytes: int) -> list[str]:
+    """Tail the recent ``*.log`` files in a custom game's own log dir (e.g. SPT's
+    ``logs/tarkov-latest.log`` + ``server-latest.log``), newest first, freshness-scoped by mtime.
+
+    Custom-game logs use their own timestamp formats, so we scope by file mtime (like the Proton
+    log) rather than the ``[YYYY-MM-DD …]`` line filter used for the Steam console.
+    """
+    from . import customgames
+
+    directory = customgames.log_dir(game)
+    if not directory:
+        return []
+    try:
+        files = [p for p in Path(directory).glob("*.log") if p.is_file()]
+    except OSError:
+        return []
+    files.sort(key=_mtime, reverse=True)
+    sections: list[str] = []
+    for log in files[:4]:  # a session touches a handful (tarkov/server/launcher latest)
+        if since is not None and _mtime(log) < since:
+            continue
+        tail = _tail(log, max_bytes).strip()
+        if tail:
+            sections.append(f"--- {game} log ({log.name}) ---\n{tail}")
+    return sections
+
+
+def collect(since: float | None = None, max_bytes: int = 8000, game: str | None = None) -> str:
+    """Recent Proton + Steam (+ custom-game) log tails as one labelled text block ('' if none).
 
     With ``since`` (epoch), scope to that session: skip a Proton log not written during/after
     the session (a stale per-app log from an earlier game), and keep only Steam-console lines
     timestamped at/after ``since`` — so we don't feed the model an unrelated past session.
+
+    ``game`` (the diagnostic's focused title) pulls in that custom game's own logs if it has a
+    registered log dir — e.g. SPT's server/launcher logs, which Steam/Proton never see.
     """
     sections: list[str] = []
 
+    if game:
+        sections += _custom_game_logs(game, since, max_bytes)
+
     protons = _proton_logs()
     if protons:
         log = protons[0]

src/rigdoctor/core/health.py

@@ -116,6 +116,31 @@ def scan_journal_text(text: str) -> list[Finding]:
             "Check power/thermals/driver; capture a session with `rigdoctor record`.",
         ))
 
+    # NVIDIA open-kernel-module VA-space mapping faults: a driver-internal failure that can
+    # storm for minutes and end in a HARD FREEZE with NO Xid logged — the GPU never "falls off
+    # the bus", so the Xid scan above misses it entirely. These code paths live in the open
+    # kernel module (nvidia-*-open); the proprietary module doesn't hit them.
+    nvrm_va = [
+        ln for ln in lines
+        if "gpu_vaspace.c" in ln
+        or "_gvaspaceMappingInsert" in ln
+        or "dmaAllocMapping" in ln
+        or "NVKMS memory for GEM object" in ln
+    ]
+    if nvrm_va:
+        findings.append(Finding(
+            WARNING, "GPU", f"NVIDIA driver VA-space mapping errors ×{len(nvrm_va)}",
+            "The NVIDIA kernel module repeatedly failed to update the GPU's virtual address "
+            "space (gpu_vaspace / dmaAllocMapping assertions, NVKMS GEM-allocation failures). "
+            "This is a driver-internal fault that can recur for minutes and end in a hard freeze "
+            "with NO Xid logged — distinct from an Xid 79 hardware drop. These code paths are "
+            "specific to the open kernel module (nvidia-*-open).",
+            "If you're on the open module, switch to the proprietary NVIDIA driver "
+            "(install `nvidia-driver-###` instead of the `…-open` variant) and update to the "
+            "latest branch, then reboot. Capture a session with `rigdoctor record` to confirm "
+            "the errors precede the freeze.",
+        ))
+
     return findings
 
 
@@ -188,6 +213,53 @@ def check_nvidia_driver() -> list[Finding]:
     return []
 
 
+def _read_text(path: str) -> str | None:
+    try:
+        return Path(path).read_text()
+    except OSError:
+        return None
+
+
+def _nvidia_module_is_open() -> bool | None:
+    """Whether the *loaded* NVIDIA kernel module is the open-source flavor.
+
+    True = open (nvidia-*-open), False = proprietary, None = can't tell / no NVIDIA module.
+    /proc is authoritative for the loaded module and needs no external tool; modinfo's filename
+    (…/nvidia-###-open/nvidia.ko) is the fallback.
+    """
+    proc = _read_text("/proc/driver/nvidia/version")
+    if proc:
+        low = proc.lower()
+        if "open kernel module" in low:
+            return True
+        if "kernel module" in low:  # proprietary banner: "NVIDIA UNIX … Kernel Module …"
+            return False
+    if shutil.which("modinfo"):
+        try:
+            out = subprocess.run(["modinfo", "nvidia"], capture_output=True, text=True, timeout=10).stdout
+        except (subprocess.SubprocessError, OSError):
+            out = ""
+        for line in out.splitlines():
+            if line.startswith("filename:"):
+                return "-open" in line
+    return None
+
+
+def check_nvidia_module() -> list[Finding]:
+    """Note when the open-source NVIDIA kernel module is loaded — the context behind the no-Xid
+    VA-space freeze signature, which lives in the open module's code paths (suggestion-only)."""
+    if _nvidia_module_is_open() is not True:
+        return []
+    return [Finding(
+        INFO, "Driver", "NVIDIA open kernel module in use",
+        "The loaded NVIDIA driver is the open-source kernel module (nvidia-*-open). It's fine for "
+        "most setups, but on some GeForce cards it hits driver-internal faults (VA-space mapping "
+        "errors, hard freezes with no Xid) that the proprietary module doesn't.",
+        "If you get unexplained hard freezes with no Xid in the logs, try the proprietary NVIDIA "
+        "driver (`nvidia-driver-###` rather than the `…-open` variant) on the latest branch.",
+    )]
+
+
 def _smart_devices() -> list[str]:
     try:
         proc = subprocess.run(["smartctl", "--scan"], capture_output=True, text=True, timeout=10)
@@ -336,6 +408,7 @@ def run_health_checks(include_journal: bool = True) -> list[Finding]:
 
     findings: list[Finding] = []
     findings += check_nvidia_driver()
+    findings += check_nvidia_module()
     if include_journal:
         findings += check_journal()
     findings += check_journal_persistence()

src/rigdoctor/core/wrap.py

@@ -40,16 +40,20 @@ def launch_option() -> str:
     return f"{quoted} wrap %command%"
 
 
-def run(command: list[str]) -> int:
+def run(command: list[str], game: str | None = None) -> int:
     """Start a focused capture (unless one's already running), run the game, then stop it.
-    Returns the game's exit code so Steam sees the right status."""
+    Returns the game's exit code so Steam sees the right status.
+
+    `game` overrides name detection — used by `games play` for a custom game (e.g. SPT), where
+    there's no SteamAppId and the bare script name (tarkov.sh) wouldn't tag the capture usefully.
+    """
     from . import diagnostic, reccontrol
 
     if not command:
         print("usage: rigdoctor wrap %command%  (set as a Steam launch option)", file=sys.stderr)
         return 2
 
-    game = game_name_from_env() or os.path.basename(command[0])
+    game = game or game_name_from_env() or os.path.basename(command[0])
     started = False
     if not reccontrol.running_pid():  # don't disturb an existing capture
         started = diagnostic.start(game=game) is not None

src/rigdoctor/gui/diagnostic_dialog.py

@@ -143,7 +143,7 @@ class DiagnosticDialog(QDialog):
         lines.append("\nCapture summary:\n" + render_summary(summary))
 
         since = (summary.start - 60) if summary.start else None
-        logs = gamelogs.collect(since=since)  # scoped to this session
+        logs = gamelogs.collect(since=since, game=result.game)  # scoped to this session
         if logs:
             lines.append("\nGame/Proton/Steam logs for this session:\n" + logs)
         sys_logs = syslogs.collect(since=since)  # kernel log + crashed-process records

src/rigdoctor/gui/games_page.py

@@ -115,6 +115,10 @@ class GamesPage(QWidget):
         self._autocap_btn = QPushButton("Auto-capture…")
         self._autocap_btn.clicked.connect(self._show_autocapture)
         header.addWidget(self._autocap_btn)
+        # Add a game no launcher reports (e.g. SPT / standalone mod launchers).
+        self._add_btn = QPushButton("Add game…")
+        self._add_btn.clicked.connect(self._add_custom_game)
+        header.addWidget(self._add_btn)
         self._rescan_btn = QPushButton("Rescan")
         self._rescan_btn.setObjectName("PrimaryButton")
         self._rescan_btn.clicked.connect(self.refresh)
@@ -235,7 +239,9 @@ class GamesPage(QWidget):
             ]
             self._libraries_ready.emit(libs)
             try:
-                self._extra_games = launchers.scan()  # Lutris / Heroic (non-Steam)
+                from ..core import customgames
+                # non-Steam: Lutris/Heroic + user-added games (SPT etc.)
+                self._extra_games = list(launchers.scan()) + customgames.scan()
             except Exception:
                 self._extra_games = []
             self._scanned.emit(steam.rescan())
@@ -423,6 +429,24 @@ class GamesPage(QWidget):
         reccontrol.stop_background()
         self._banner.hide()
 
+    def _add_custom_game(self) -> None:
+        """Manually add a game no launcher reports (e.g. SPT), then rescan to show it."""
+        from PySide6.QtWidgets import QInputDialog
+
+        from ..core import customgames
+
+        name, ok = QInputDialog.getText(
+            self, "Add game", "Game name (e.g. SPT) — for titles no launcher reports:")
+        if not ok:
+            return
+        name = name.strip()
+        if not name:
+            return
+        if customgames.add(name):
+            self.refresh()
+        else:
+            QMessageBox.information(self, "Add game", f"'{name}' is already in your games.")
+
     def _show_autocapture(self) -> None:
         from ..core import wrap
 

tests/test_customgames.py

@@ -0,0 +1,85 @@
+"""Tests for user-added games (M6): add/remove/scan of titles no launcher reports (e.g. SPT)."""
+
+import tempfile
+import unittest
+from pathlib import Path
+from unittest import mock
+
+from rigdoctor.core import customgames
+
+
+class CustomGamesTests(unittest.TestCase):
+    def setUp(self):
+        self._tmp = tempfile.TemporaryDirectory()
+        self._file = Path(self._tmp.name) / "custom-games.json"
+        self._patch = mock.patch.object(customgames.config, "CUSTOM_GAMES_FILE", self._file)
+        self._patch.start()
+
+    def tearDown(self):
+        self._patch.stop()
+        self._tmp.cleanup()
+
+    def test_missing_file_scans_empty(self):
+        self.assertEqual(customgames.scan(), [])
+        self.assertEqual(customgames.names(), [])
+
+    def test_add_then_scan_returns_game(self):
+        self.assertTrue(customgames.add("SPT"))
+        games = customgames.scan()
+        self.assertEqual(len(games), 1)
+        self.assertEqual(games[0].name, "SPT")
+        self.assertEqual(games[0].launcher, "custom")
+        self.assertTrue(self._file.exists())  # persisted
+
+    def test_add_is_idempotent_case_insensitive(self):
+        self.assertTrue(customgames.add("SPT"))
+        self.assertFalse(customgames.add("spt"))   # already present
+        self.assertFalse(customgames.add("   "))    # blank
+        self.assertEqual(customgames.names(), ["SPT"])
+
+    def test_remove(self):
+        customgames.add("SPT")
+        customgames.add("Minecraft")
+        self.assertTrue(customgames.remove("spt"))  # case-insensitive
+        self.assertEqual(customgames.names(), ["Minecraft"])
+        self.assertFalse(customgames.remove("nope"))
+
+    def test_scan_sorted_by_name(self):
+        for n in ("Zomboid", "Apex", "SPT"):
+            customgames.add(n)
+        self.assertEqual([g.name for g in customgames.scan()], ["Apex", "SPT", "Zomboid"])
+
+    def test_command_and_logdir_stored_and_resolved(self):
+        logs = Path(self._tmp.name) / "logs"
+        logs.mkdir()
+        sh = Path(self._tmp.name) / "tarkov.sh"
+        sh.write_text("#!/bin/sh\n")
+        self.assertTrue(customgames.add("SPT", command=str(sh), logdir=str(logs)))
+        self.assertEqual(customgames.command("SPT"), [str(sh)])
+        self.assertEqual(customgames.log_dir("SPT"), str(logs))
+
+    def test_logdir_inferred_from_sibling_logs(self):
+        # A command with a sibling logs/ dir (SPT's layout) → logdir auto-detected.
+        sh = Path(self._tmp.name) / "tarkov.sh"
+        sh.write_text("#!/bin/sh\n")
+        (Path(self._tmp.name) / "logs").mkdir()
+        self.assertTrue(customgames.add("SPT", command=str(sh)))
+        self.assertEqual(customgames.log_dir("SPT"), str(Path(self._tmp.name) / "logs"))
+
+    def test_no_command_resolves_to_none(self):
+        customgames.add("SPT")
+        self.assertIsNone(customgames.command("SPT"))
+        self.assertIsNone(customgames.command("missing"))
+        self.assertIsNone(customgames.log_dir("SPT"))
+
+    def test_corrupt_file_degrades_to_empty(self):
+        self._file.parent.mkdir(parents=True, exist_ok=True)
+        self._file.write_text("{not json")
+        self.assertEqual(customgames.scan(), [])
+        # and a subsequent add still works (overwrites the garbage)
+        self.assertTrue(customgames.add("SPT"))
+        self.assertEqual(customgames.names(), ["SPT"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/test_gamelogs.py

@@ -47,6 +47,36 @@ class CollectTests(unittest.TestCase):
             self.assertEqual(gamelogs.collect(), "")
 
 
+class CustomGameLogTests(unittest.TestCase):
+    def test_collect_includes_custom_game_logs(self):
+        tmp = Path(tempfile.mkdtemp())
+        (tmp / "tarkov-latest.log").write_text(">>> Tarkov gone. clean exit")
+        (tmp / "server-latest.log").write_text("SPT server error: mod failed to load")
+        with mock.patch.object(gamelogs, "_proton_logs", return_value=[]), \
+             mock.patch.object(gamelogs, "_steam_console", return_value=None), \
+             mock.patch("rigdoctor.core.customgames.log_dir", return_value=str(tmp)):
+            out = gamelogs.collect(game="SPT")
+        self.assertIn("SPT log", out)
+        self.assertIn("server-latest.log", out)
+        self.assertIn("mod failed to load", out)
+
+    def test_custom_logs_skipped_when_stale(self):
+        tmp = Path(tempfile.mkdtemp())
+        old = tmp / "tarkov-latest.log"
+        old.write_text("an earlier session")
+        old_mtime = time.time() - 3600
+        os.utime(old, (old_mtime, old_mtime))
+        with mock.patch.object(gamelogs, "_proton_logs", return_value=[]), \
+             mock.patch.object(gamelogs, "_steam_console", return_value=None), \
+             mock.patch("rigdoctor.core.customgames.log_dir", return_value=str(tmp)):
+            self.assertEqual(gamelogs.collect(since=time.time() - 60, game="SPT"), "")
+
+    def test_no_game_means_no_custom_logs(self):
+        with mock.patch.object(gamelogs, "_proton_logs", return_value=[]), \
+             mock.patch.object(gamelogs, "_steam_console", return_value=None):
+            self.assertEqual(gamelogs.collect(), "")  # game=None → custom lookup skipped
+
+
 class SinceScopingTests(unittest.TestCase):
     def test_since_filter_keeps_window_only(self):
         text = (

tests/test_health.py

@@ -11,11 +11,19 @@ from rigdoctor.core.health import (
     WARNING,
     check_displays,
     check_memory_speed,
+    check_nvidia_module,
     check_pcie_links,
     run_health_checks,
     scan_journal_text,
 )
 
+# A real no-Xid freeze: the open-module VA-space storm captured on 2026-05-29.
+_VASPACE_LOG = """\
+NVRM: nvCheckFailedNoLog: Check failed: 0 == (pMapNode->gpuMask & gpuMask) @ gpu_vaspace.c:4547
+NVRM: dmaAllocMapping_GM107: can't update VA space for mapping @vaddr=0x4be00000
+[drm:nv_drm_gem_alloc_nvkms_memory_ioctl [nvidia_drm]] *ERROR* Failed to allocate NVKMS memory for GEM object
+"""
+
 
 class HealthScanTests(unittest.TestCase):
     def test_xid_79_is_critical(self):
@@ -44,6 +52,28 @@ class HealthScanTests(unittest.TestCase):
     def test_clean_text_yields_no_findings(self):
         self.assertEqual(scan_journal_text("usb 1-1: new high-speed USB device\nbluetooth: ok"), [])
 
+    def test_vaspace_freeze_detected_without_any_xid(self):
+        findings = scan_journal_text(_VASPACE_LOG)
+        gpu = [f for f in findings if f.category == "GPU"]
+        self.assertEqual(len(gpu), 1)
+        self.assertEqual(gpu[0].severity, WARNING)
+        self.assertIn("VA-space", gpu[0].title)
+        # It must NOT be misreported as an Xid finding (the log has no Xid at all).
+        self.assertNotIn("Xid", gpu[0].title)
+        self.assertIn("open kernel module", gpu[0].detail.lower())
+
+    def test_open_module_finding_when_open_loaded(self):
+        with mock.patch("rigdoctor.core.health._nvidia_module_is_open", return_value=True):
+            findings = check_nvidia_module()
+        self.assertEqual(len(findings), 1)
+        self.assertEqual(findings[0].severity, INFO)
+        self.assertEqual(findings[0].category, "Driver")
+
+    def test_no_module_finding_when_proprietary_or_absent(self):
+        for state in (False, None):
+            with mock.patch("rigdoctor.core.health._nvidia_module_is_open", return_value=state):
+                self.assertEqual(check_nvidia_module(), [])
+
     def test_run_health_checks_returns_findings(self):
         # Runs against the real system; just assert it returns a sorted list of Findings.
         findings = run_health_checks()