Compare commits
25 Commits
v0.30.0
...
87fa678ccb
| Author | SHA1 | Date | |
|---|---|---|---|
|
87fa678ccb
|
|||
|
21cc6a4813
|
|||
| ee73049248 | |||
|
3a8ad5bd5d
|
|||
| e8b84bf046 | |||
|
2342dd83aa
|
|||
| a028fe6d38 | |||
|
a6453335e9
|
|||
| baec47dd4e | |||
| 47ecb702e7 | |||
| 944945ce72 | |||
|
dc719f6a89
|
|||
|
78cd417d0b
|
|||
| 856a3305ad | |||
| 3b1a2e7393 | |||
| 2989e8e23e | |||
| 670df23e06 | |||
| 2ee7763d00 | |||
| bd6cad5a42 | |||
| 7fa9b63661 | |||
| c443a8b9f8 | |||
| bbc22fa288 | |||
| 5502251789 | |||
| 4bd51a40c3 | |||
| 984292c368 |
@@ -11,7 +11,20 @@ on:
|
||||
branches: [main]
|
||||
|
||||
jobs:
|
||||
test:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.12"
|
||||
- name: Install (core only)
|
||||
run: python -m pip install -e .
|
||||
- name: Run tests
|
||||
run: python -m unittest discover -s tests -v
|
||||
|
||||
release:
|
||||
needs: test # don't publish a release if the tests fail
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
@@ -30,6 +43,9 @@ jobs:
|
||||
- name: Build self-extracting installer (.run)
|
||||
run: python packaging/make_run.py
|
||||
|
||||
- name: Build .deb
|
||||
run: python packaging/make_deb.py
|
||||
|
||||
- name: Read version
|
||||
id: ver
|
||||
run: |
|
||||
@@ -90,3 +106,26 @@ jobs:
|
||||
"${API}/releases/${rid}/assets?name=$(basename "$f")" >/dev/null
|
||||
done
|
||||
echo "Published ${TAG}."
|
||||
|
||||
- name: Publish .deb to the Gitea apt registry (optional — needs REGISTRY_TOKEN)
|
||||
env:
|
||||
PKG_TOKEN: ${{ secrets.REGISTRY_TOKEN }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
if [ -z "${PKG_TOKEN:-}" ]; then
|
||||
echo "REGISTRY_TOKEN not set — skipping apt publish (the .deb is still a release asset)."
|
||||
exit 0
|
||||
fi
|
||||
OWNER="${{ github.repository_owner }}"
|
||||
URL="${{ github.server_url }}/api/packages/${OWNER}/debian/pool/stable/main/upload"
|
||||
for f in dist/*.deb; do
|
||||
echo "Uploading $(basename "$f") to the apt registry…"
|
||||
code=$(curl -sS -o /tmp/apt_upload.txt -w '%{http_code}' \
|
||||
--user "${OWNER}:${PKG_TOKEN}" --upload-file "$f" "$URL" || true)
|
||||
case "$code" in
|
||||
2*) echo " uploaded ($code)";;
|
||||
409) echo " already published ($code) — skipping (registry versions are immutable)";;
|
||||
*) echo " upload failed ($code):"; cat /tmp/apt_upload.txt || true; exit 1;;
|
||||
esac
|
||||
done
|
||||
echo "apt source: deb ${{ github.server_url }}/api/packages/${OWNER}/debian stable main"
|
||||
|
||||
@@ -0,0 +1,44 @@
|
||||
name: tests
|
||||
run-name: Run test suite
|
||||
|
||||
# Runs the unittest suite on pull requests (once per PR). Pushes to main are covered by the
|
||||
# `test` job in release.yml, so we don't trigger on push here — that would double every run.
|
||||
# Two jobs:
|
||||
# core — stdlib-only install; the GUI tests skip (@skipUnless HAVE_QT). Bulletproof.
|
||||
# gui-smoke — installs the GUI extra + offscreen Qt libs and runs the same suite headless,
|
||||
# exercising the MainWindow/SetupWizard/DiagnosticDialog construction tests.
|
||||
# Make `tests / core (pull_request)` a required status check on `main` so a PR can't merge red.
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
|
||||
jobs:
|
||||
core:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.12"
|
||||
- name: Install (core only — no PySide6)
|
||||
run: python -m pip install -e .
|
||||
- name: Run tests (GUI tests skip without PySide6)
|
||||
run: python -m unittest discover -s tests -v
|
||||
|
||||
gui-smoke:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.12"
|
||||
- name: System libraries for offscreen Qt
|
||||
run: |
|
||||
sudo apt-get update
|
||||
sudo apt-get install -y libegl1 libgl1 libxkbcommon0 libdbus-1-3 libglib2.0-0
|
||||
- name: Install (with GUI extra)
|
||||
run: python -m pip install -e ".[gui]"
|
||||
- name: Run tests (headless)
|
||||
env:
|
||||
QT_QPA_PLATFORM: offscreen
|
||||
run: python -m unittest discover -s tests -v
|
||||
@@ -5,6 +5,69 @@ 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).
|
||||
|
||||
## [0.36.1] - 2026-05-22
|
||||
### Fixed
|
||||
- `rigdoctor gui` printed the wrong fix when PySide6 is missing — it suggested the non-existent
|
||||
`python3-pyside6` package. Now it names the real split modules
|
||||
(`python3-pyside6.qt{widgets,gui,websockets,svg}` + `python3-pyte`).
|
||||
|
||||
## [0.36.0] - 2026-05-22
|
||||
### Fixed
|
||||
- **`.deb` now installs all dependencies automatically — no manual tool install.** The previous
|
||||
`Recommends: python3-pyside6` named a package that doesn't exist on Debian/Ubuntu (PySide6 is
|
||||
split per module), so apt silently skipped it and the GUI wouldn't start. Now it Recommends the
|
||||
actual modules the GUI imports — `python3-pyside6.qt{widgets,gui,websockets,svg}` + `python3-pyte`.
|
||||
### Changed
|
||||
- **`apt install rigdoctor` sets up the whole toolset.** The `.deb` also Recommends the optional
|
||||
diagnostic/gaming tools (smartmontools, lm-sensors, dmidecode, pciutils, libnotify-bin,
|
||||
libsecret-tools, gamemode, mangohud) so they install by default — users never hand-install
|
||||
tools. `cpupower` is a Suggests (kernel-tied); `--no-install-recommends` still gives CLI-only.
|
||||
|
||||
## [0.35.0] - 2026-05-22
|
||||
### Added
|
||||
- **`.deb` package (M9 / D8)** — `packaging/make_deb.py` builds a `rigdoctor_<version>_all.deb`
|
||||
(pure-Python, `Architecture: all`) via `dpkg-deb`: `Depends: python3`, with the GUI deps
|
||||
(`python3-pyside6`, `python3-pyte`) as **Recommends** so `sudo apt install ./rigdoctor_*.deb`
|
||||
gives the full app and `--no-install-recommends` gives CLI-only. Installs the package, both
|
||||
launchers, the desktop entry, and the icon. CI (`release.yml`) builds it as a **release asset**
|
||||
every release, and optionally publishes it to the Gitea **apt registry** (set a `REGISTRY_TOKEN`
|
||||
secret) for `sudo apt install rigdoctor`. **M9 is now complete.**
|
||||
|
||||
## [0.34.0] - 2026-05-22
|
||||
### Added
|
||||
- **Event-based alerts (M8).** Beyond temperature + GPU-lost, RigDoctor now notifies on
|
||||
**critical kernel events** — Xid (GPU error), out-of-memory kills, CPU machine-checks, PCIe
|
||||
AER errors, and disk I/O errors — scanned from the kernel log every ~30s while monitoring and
|
||||
fired one-shot (cooldown-gated, so no spam). A proactive warning the moment something goes
|
||||
wrong, not just on a temperature threshold. Included whenever desktop notifications are on.
|
||||
|
||||
## [0.33.0] - 2026-05-22
|
||||
### Added
|
||||
- **AI explanations stream live.** "Explain with AI" now fills token-by-token as the model
|
||||
generates (Ollama NDJSON + Claude SSE, both via stdlib `urllib`) instead of a multi-second
|
||||
freeze, then re-renders the finished answer as Markdown. `core/ai.explain_stream()`.
|
||||
|
||||
## [0.32.0] - 2026-05-22
|
||||
### Added
|
||||
- **More for diagnostics & reports:**
|
||||
- **`nvidia-smi -q` snapshot** — driver, throttle/clock-event reasons, clocks, power, temps,
|
||||
PCIe link, ECC + retired pages (point-in-time at diagnostic time).
|
||||
- **Display-server log** — auto-detected: `Xorg.0.log` on X11, or the compositor's user-journal
|
||||
slice (gnome-shell/kwin/sway/gamescope) on Wayland.
|
||||
- **Full system inventory** (M5 hardware/OS) is now included in each stored diagnostic and the
|
||||
**Report** bundle — invaluable for larger/shared debugging.
|
||||
These join the kernel log + coredump records in `syslogs.txt`/`inventory.*`, are saved per
|
||||
diagnostic, included in the Report zip, and (logs) fed to the AI on "Explain".
|
||||
|
||||
## [0.31.0] - 2026-05-22
|
||||
### Added
|
||||
- **Diagnostics now collect session-scoped system logs** (`core/syslogs.py`): a kernel-log
|
||||
slice (`journalctl -k` — Xid, OOM-killer, MCE, PCIe AER, thermal, hung tasks) and
|
||||
**crashed-process records** (`coredumpctl` — which executable, signal, and when). They're saved
|
||||
to the diagnostic directory (`syslogs.txt`), included in the **Report** bundle, and fed to the
|
||||
AI on "Explain" alongside the game logs. Best-effort — degrades quietly if the tools are
|
||||
missing or access is denied; scoped to the session window so it doesn't drag in old noise.
|
||||
|
||||
## [0.30.0] - 2026-05-22
|
||||
### Added
|
||||
- **Logging & report bundles (M15, D25)** — opt-in via one **Settings → Logging** toggle
|
||||
|
||||
@@ -1,132 +1,146 @@
|
||||
# RigDoctor
|
||||
|
||||
A **modular diagnostics, monitoring, and health-check toolkit for Linux gamers.**
|
||||
**Hardware monitoring & crash diagnostics for Linux gamers.** Live sensors, crash-safe
|
||||
logging, plain-language health reports, per-game diagnostics, and optional AI explanations —
|
||||
in a desktop app, a tray applet, or the terminal. Ubuntu/Debian + NVIDIA first.
|
||||
|
||||
> **Status:** 🟢 Phase 1 (MVP) complete. The **sensor core (M1)**, **crash-capture logger
|
||||
> (M3)**, and **health report (M4)** all work — live `snapshot`/`monitor`, crash-safe `record`
|
||||
> with a post-crash report, and `report` to scan logs/SMART/driver for likely causes. A
|
||||
> desktop GUI (M10) ties them together (dashboard, recording, health). See `docs/ROADMAP.md`.
|
||||
Linux gaming faults are hard to pin down — GPUs falling off the PCIe bus, black screens
|
||||
mid-game, silent thermal/VRAM throttling, driver/Proton mismatches. The useful data is
|
||||
scattered across `nvidia-smi`, `/sys`, `journalctl`, and SMART, and the readings right before a
|
||||
freeze are usually lost. RigDoctor pulls it together and keeps the evidence.
|
||||
|
||||
## Why this exists
|
||||
## Features
|
||||
|
||||
Linux gaming hardware faults are hard to diagnose: GPUs falling off the PCIe bus, the screen
|
||||
suddenly going black mid-game, silent thermal/VRAM throttling, power transients,
|
||||
driver/library mismatches, Proton quirks, and CPU governor / power-profile misconfiguration.
|
||||
The data needed to diagnose them is scattered across `nvidia-smi`, `/sys/class/hwmon`,
|
||||
`journalctl`, SMART, and more — and the most useful readings (the ones right before a hard
|
||||
freeze) are usually lost because nothing flushed them to disk.
|
||||
- **Live monitoring** — a dark desktop **dashboard** (history graphs + per-subsystem cards), a
|
||||
**tray applet** with at-a-glance status, and a terminal view (`rigdoctor monitor`).
|
||||
- **Crash-safe recording** — background logger that `fsync`s every sample, so the state right
|
||||
before a hard freeze survives. Manual, always-on, or auto-start when a game launches.
|
||||
- **Health report** — scans `journalctl`/SMART/driver for likely causes (Xid, OOM, disk
|
||||
errors, throttling…) and explains them with suggested fixes.
|
||||
- **Per-game diagnostics** — pick a game, capture while you play, get a focused report; hard
|
||||
crashes are detected and analysed on next launch.
|
||||
- **Gaming tune-ups** — flags risky settings (CPU governor, PCIe ASPM, persistence mode…) with
|
||||
**one-click, reversible fixes**.
|
||||
- **Proactive alerts** — desktop notifications on overheating and critical kernel events
|
||||
(GPU-lost, Xid, out-of-memory, disk I/O).
|
||||
- **AI explanations** *(optional, opt-in)* — explain a diagnostic in plain language with a
|
||||
**local model (Ollama)** or **Claude**. Never automatic; only when you press the button.
|
||||
- **Shareable reports** — zip a diagnostic (logs, inventory, AI transcript) to hand to someone,
|
||||
or share a live **terminal session** for remote help.
|
||||
- **Self-updating** — `apt upgrade`, or the in-app updater.
|
||||
|
||||
RigDoctor pulls all of that into one modular tool: live monitoring, crash-safe logging, a
|
||||
one-shot health report, and an interactive installer that only sets up the modules a given
|
||||
user actually needs for their hardware.
|
||||
## Install
|
||||
|
||||
**Seed use cases:** an RTX 3070 that intermittently "falls off the bus" under heavy GPU load
|
||||
(Path of Exile on Linux, Escape from Tarkov on Windows), and a monitor going black mid-game.
|
||||
See `docs/SPEC.md` §1.
|
||||
### Debian / Ubuntu — `.deb`
|
||||
|
||||
## How you run it
|
||||
|
||||
RigDoctor is **GUI-first** — the desktop app is the primary way in — but every feature is
|
||||
also available headless:
|
||||
- **Desktop GUI** — graphical dashboard, recording controls, log browser, reports. The
|
||||
default interface for most users.
|
||||
- **Tray applet** — a small top-menu-bar applet with quick actions and at-a-glance status.
|
||||
- **CLI** — full functionality from the terminal; works over SSH and in scripts.
|
||||
|
||||
The GUI/tray are optional modules; a headless (CLI-only) install loses no capability.
|
||||
|
||||
## Key decisions (settled)
|
||||
|
||||
| Topic | Decision |
|
||||
|-------|----------|
|
||||
| Name | **RigDoctor** |
|
||||
| Language / stack | **Python 3 + Qt (PySide6)** — core/CLI/daemon stdlib-only; Qt only for GUI/tray |
|
||||
| Primary distro | **Ubuntu** (Debian via apt); others best-effort later |
|
||||
| Primary GPU | **NVIDIA** first; AMD, then Intel later |
|
||||
| MVP | **Sensor core + crash logger + health report** (NVIDIA-only, CLI-first) |
|
||||
| Distribution | **User-local install** (self-updating from the public repo, no root); **`.deb`** optional |
|
||||
| Scope of action | **Read-only + suggestions** (no auto-apply yet) |
|
||||
| Stress tests | **Out of scope** |
|
||||
|
||||
Full rationale and the still-open questions are in `docs/DECISIONS.md`.
|
||||
|
||||
## Repo layout
|
||||
|
||||
| Path | Purpose |
|
||||
|------|---------|
|
||||
| `docs/SPEC.md` | Product specification — vision, requirements, modules (the main planning doc) |
|
||||
| `docs/ARCHITECTURE.md` | Technical design — core engine, front-ends, daemon, installer |
|
||||
| `docs/MODULES.md` | Catalog of modules with scope, dependencies, status |
|
||||
| `docs/ROADMAP.md` | Phased milestones |
|
||||
| `docs/DECISIONS.md` | Decision log + remaining open questions |
|
||||
| `src/rigdoctor/` | Source code — `core/` engine + sources, `cli.py`, `render.py` |
|
||||
| `installer/` | Installer / `.deb` packaging (empty until Phase 4) |
|
||||
| `tests/` | Tests (stdlib `unittest`) |
|
||||
|
||||
## Install (user-local, no root)
|
||||
|
||||
RigDoctor installs into a private venv under `~/.local` — no root, self-updating:
|
||||
The simplest path: grab the latest **`rigdoctor_<version>_all.deb`** from the
|
||||
[releases page](https://git.jesseyvanofferen.com/jessey/rigdoctor/releases) and install it —
|
||||
apt pulls the GUI dependencies (PySide6, pyte) automatically:
|
||||
|
||||
```bash
|
||||
./install.sh # from a source checkout or the self-extracting .run
|
||||
./install.sh --ref v0.0.6 # install a specific released tag (needs a token)
|
||||
./install.sh --uninstall # remove it
|
||||
sudo apt install ./rigdoctor_*_all.deb # CLI only: add --no-install-recommends
|
||||
```
|
||||
|
||||
This adds `rigdoctor` / `rigdoctor-gui` to `~/.local/bin` and a desktop entry. Each release
|
||||
also ships a one-file **`.run`** installer (download, `chmod +x`, run). Updates are gated to
|
||||
accounts on the Git server (a Personal Access Token); save one via the GUI **Setup → Update
|
||||
access** panel or `rigdoctor login`, then `rigdoctor update` (or the sidebar button).
|
||||
|
||||
## Run it (dev)
|
||||
|
||||
Stdlib-only, no install needed (target is Python ≥ 3.11; tested on 3.14):
|
||||
**Or add the apt repository** for `apt install` + automatic updates. The registry is private and
|
||||
GPG-signed, so you need a Gitea token with **`read:package`**, the signing key, and the deb822
|
||||
source (`read -rsp` keeps the token out of your shell history):
|
||||
|
||||
```bash
|
||||
PYTHONPATH=src python3 -m rigdoctor snapshot # one-shot sensor read
|
||||
PYTHONPATH=src python3 -m rigdoctor snapshot --json
|
||||
PYTHONPATH=src python3 -m rigdoctor monitor -n 1 # live view (Ctrl-C to quit)
|
||||
PYTHONPATH=src python3 -m rigdoctor sources # list detected sensor sources
|
||||
PYTHONPATH=src python3 -m unittest discover -s tests
|
||||
read -rsp 'Gitea read:package token: ' TOKEN; echo
|
||||
|
||||
# signing key → dearmored into the keyring (the key endpoint requires the token too)
|
||||
sudo install -d -m 0755 /etc/apt/keyrings
|
||||
curl -fsSL --user <user>:"$TOKEN" \
|
||||
https://git.jesseyvanofferen.com/api/packages/jessey/debian/repository.key \
|
||||
| sudo gpg --dearmor -o /etc/apt/keyrings/gitea-jessey.gpg
|
||||
|
||||
# download credentials, kept out of the sources file
|
||||
printf 'machine git.jesseyvanofferen.com login <user> password %s\n' "$TOKEN" \
|
||||
| sudo tee /etc/apt/auth.conf.d/rigdoctor.conf >/dev/null
|
||||
sudo chmod 0600 /etc/apt/auth.conf.d/rigdoctor.conf
|
||||
|
||||
# the source (modern deb822 format, GPG-verified, all-arch)
|
||||
sudo tee /etc/apt/sources.list.d/rigdoctor.sources >/dev/null <<'EOF'
|
||||
Types: deb
|
||||
URIs: https://git.jesseyvanofferen.com/api/packages/jessey/debian
|
||||
Suites: stable
|
||||
Components: main
|
||||
Architectures: all
|
||||
Signed-By: /etc/apt/keyrings/gitea-jessey.gpg
|
||||
EOF
|
||||
|
||||
sudo apt update && sudo apt install rigdoctor
|
||||
```
|
||||
|
||||
### Crash-capture logger (M3)
|
||||
Then `sudo apt upgrade` keeps it current. *(Quick-and-dirty alternative if the registry isn't
|
||||
signed: skip the key and use a one-line `deb [arch=all trusted=yes] …/debian stable main` source.)*
|
||||
|
||||
A crash-safe background logger (JSONL, `fsync` per sample, bounded by rotation) for catching
|
||||
the state right before a freeze:
|
||||
### Any distro — self-extracting `.run` (no root)
|
||||
|
||||
Download **`rigdoctor-<version>-installer.run`** from the releases page and run it. It installs
|
||||
into a private virtualenv under `~/.local` (no root), adds the launchers + desktop entry, and
|
||||
opens the first-run setup wizard:
|
||||
|
||||
```bash
|
||||
rigdoctor record start # start logging in the background
|
||||
rigdoctor record status # is it running? latest readings, sample count
|
||||
rigdoctor record stop # stop it
|
||||
rigdoctor record report # post-crash summary: peaks, events, last samples
|
||||
rigdoctor record run # run in the foreground (the systemd-ready entrypoint)
|
||||
sh rigdoctor-*-installer.run
|
||||
```
|
||||
|
||||
Logs live in `~/.local/share/rigdoctor/logs/`. It detects GPU "lost"/hang (nvidia-smi query
|
||||
timeout) and writes an event marker. Trigger modes (always-on / game-launch) and the
|
||||
`systemd --user` service arrive in Phase 4.
|
||||
### Updating & removing
|
||||
|
||||
### Desktop GUI (M10)
|
||||
- **`.deb`:** `sudo apt upgrade` (or reinstall a newer `.deb`).
|
||||
- **`.run` / user-local:** the in-app **Update** button, or `rigdoctor update`.
|
||||
- **Remove:** `sudo apt remove rigdoctor`, or `rigdoctor uninstall` for the user-local install.
|
||||
|
||||
The GUI uses PySide6 (Qt) — the only part of RigDoctor that needs a non-stdlib dep:
|
||||
## Using it
|
||||
|
||||
Launch **RigDoctor** from your app menu, or:
|
||||
|
||||
```bash
|
||||
pip install -e '.[gui]' # core + PySide6, gives `rigdoctor` and `rigdoctor-gui`
|
||||
rigdoctor gui # or: rigdoctor-gui
|
||||
rigdoctor-gui # desktop app (+ tray)
|
||||
rigdoctor --help # everything from the terminal (works over SSH)
|
||||
```
|
||||
|
||||
It opens a dark-themed window with sidebar navigation and a **live dashboard** over the
|
||||
same sensor core — circular gauges for the headline metrics plus collapsible per-subsystem
|
||||
cards (GPU/CPU/memory/storage) with temperature-colored values (icey-blue → green → red).
|
||||
The **Logs** and **Health** sections are full pages (recording controls + post-crash report;
|
||||
and the kernel-log / SMART / driver scan). **Inventory** is a placeholder until M5 lands.
|
||||
Handy CLI commands:
|
||||
|
||||
Without the GUI extra, `pip install -e .` gives just the stdlib-only CLI.
|
||||
```bash
|
||||
rigdoctor snapshot # one-shot reading of every sensor
|
||||
rigdoctor monitor # live terminal dashboard
|
||||
rigdoctor report # health report (logs / SMART / driver)
|
||||
rigdoctor diagnose start|finish # capture while gaming, then analyse
|
||||
rigdoctor gameenv # flag risky gaming settings + fixes
|
||||
rigdoctor inventory # hardware/OS inventory
|
||||
rigdoctor ai explain # AI explanation of the current findings (opt-in)
|
||||
rigdoctor bundle # zip the latest diagnostic into a shareable report
|
||||
```
|
||||
|
||||
## Start here
|
||||
## Requirements
|
||||
|
||||
1. Read `docs/SPEC.md` for what we're building.
|
||||
2. Read `docs/ROADMAP.md` for the build order (Phase 1 = the MVP).
|
||||
3. Read `docs/DECISIONS.md` for the settled decisions (D1–D15).
|
||||
</content>
|
||||
- **Linux** — Ubuntu/Debian first-class (the `.deb`); the `.run` works on any distro with
|
||||
Python ≥ 3.11.
|
||||
- **GPU** — NVIDIA fully supported (via `nvidia-smi`); AMD/Intel sensors are best-effort.
|
||||
- **CLI/daemon** need only Python 3 (stdlib). The **GUI/tray** add **PySide6** (`python3-pyside6`).
|
||||
- Optional tools unlock more: `smartmontools`, `lm-sensors`, `gamemode`, `mangohud`. The setup
|
||||
wizard offers to install them.
|
||||
|
||||
## Privacy
|
||||
|
||||
Everything stays on your machine — no telemetry, no phone-home. The AI assistant is **off by
|
||||
default** and runs only when you explicitly trigger it; with Ollama nothing leaves the machine,
|
||||
and the Claude option asks before sending. Reports are local files; they leave only if you share
|
||||
the zip.
|
||||
|
||||
## Development
|
||||
|
||||
RigDoctor's core is stdlib-only Python; the GUI/tray use PySide6.
|
||||
|
||||
```bash
|
||||
git clone https://git.jesseyvanofferen.com/jessey/rigdoctor && cd rigdoctor
|
||||
pip install -e ".[gui]" # core + GUI; omit [gui] for CLI-only
|
||||
python -m unittest discover -s tests # run the test suite
|
||||
PYTHONPATH=src python3 -m rigdoctor snapshot # run without installing
|
||||
```
|
||||
|
||||
Design docs live in `docs/` — `SPEC.md` (vision/requirements), `ARCHITECTURE.md`,
|
||||
`MODULES.md` (module catalog), `ROADMAP.md`, and `DECISIONS.md` (the decision log).
|
||||
Contributions: branch off `main`, keep tests green (CI runs them on PRs), and bump the version
|
||||
+ `CHANGELOG.md` for shipped changes.
|
||||
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 42 KiB |
@@ -0,0 +1,17 @@
|
||||
<svg xmlns="http://www.w3.org/2000/svg" width="512" height="512" viewBox="0 0 512 512">
|
||||
<defs>
|
||||
<radialGradient id="bg" cx="50%" cy="42%" r="78%">
|
||||
<stop offset="0%" stop-color="#1b2230"/>
|
||||
<stop offset="100%" stop-color="#0d0f13"/>
|
||||
</radialGradient>
|
||||
</defs>
|
||||
<rect width="512" height="512" fill="url(#bg)"/>
|
||||
<!-- gauge ring -->
|
||||
<circle cx="256" cy="256" r="168" fill="none" stroke="#2a2f39" stroke-width="28"/>
|
||||
<!-- accent sweep -->
|
||||
<path d="M256 88 a168 168 0 1 1 -118.8 49.2" fill="none" stroke="#38bdf8"
|
||||
stroke-width="28" stroke-linecap="round"/>
|
||||
<!-- heartbeat / monitoring trace -->
|
||||
<path d="M120 264 H200 L232 192 L280 336 L312 264 H392" fill="none" stroke="#e6e8eb"
|
||||
stroke-width="28" stroke-linecap="round" stroke-linejoin="round"/>
|
||||
</svg>
|
||||
|
After Width: | Height: | Size: 798 B |
+8
-5
@@ -18,7 +18,7 @@ Status: ⬜ not started · 🟦 designing · 🟨 in progress · ✅ done
|
||||
| M6 | Gaming env checks | Diagnostics | none | all | P2 | 🟨 |
|
||||
| M10 | Desktop GUI | Desktop UI | **python3-pyside6** | all | P2 | ✅ |
|
||||
| M11 | Tray / menu-bar applet | Desktop UI | **python3-pyside6** (+ AppIndicator on GNOME) | all | P2 | ✅ |
|
||||
| M9 | Installer | (meta) | none | all | P1 | 🟨 |
|
||||
| M9 | Installer (+ `.deb`) | (meta) | none | all | P1 | ✅ |
|
||||
| M12 | Session sharing (shared terminal) | Sharing | none (relay) | all | P3 | ✅ |
|
||||
| M13 | Auto-update | (core) | none (stdlib; user-local file swap) | all | P3 | ✅ |
|
||||
| M14 | AI assistant (explain diagnostics) | (optional) | none (stdlib urllib; Ollama or Claude) | all | P3 | ✅ |
|
||||
@@ -132,10 +132,13 @@ Status: ⬜ not started · 🟦 designing · 🟨 in progress · ✅ done
|
||||
|
||||
- **M15 Logging & report bundles** (D25) — opt-in via one `logging_enabled` toggle (default off):
|
||||
application logging to a rotating `app.log` (`core/applog.py`) and **per-diagnostic storage**
|
||||
(`core/diagstore.py`) — each diagnostic gets its own `DATA_DIR/diagnostics/<id>/` (capture,
|
||||
`result.json`, `report.txt`, scoped game logs, and an `ai/` record of every AI interaction:
|
||||
exact data sent, model, reply). **"Report"** zips one into `DATA_DIR/reports/` (GUI button on
|
||||
the diagnostic dialog; CLI `rigdoctor bundle`). Stays local; shareable on demand.
|
||||
(`core/diagstore.py`) — each diagnostic gets its own `DATA_DIR/diagnostics/<id>/`: capture,
|
||||
`result.json`, `report.txt`, the full **inventory** (M5: hardware/OS), scoped **game logs**
|
||||
(`core/gamelogs.py`), scoped **system logs** (`core/syslogs.py` — `journalctl -k`,
|
||||
`coredumpctl`, an `nvidia-smi -q` snapshot, and the X11/Wayland display-server log), and an
|
||||
`ai/` record of every AI interaction (exact data sent, model, reply). **"Report"** zips one
|
||||
into `DATA_DIR/reports/` (GUI button on the diagnostic dialog; CLI `rigdoctor bundle`). Logs
|
||||
are session-scoped and fed to the AI on "Explain". Stays local; shareable on demand.
|
||||
|
||||
## Bundles (final — D14)
|
||||
- **Essential:** M1 + M3 + M4 *(the MVP, NVIDIA-only — D5)*
|
||||
|
||||
+6
-3
@@ -67,9 +67,12 @@ Ubuntu + NVIDIA first; `.deb` distribution (see `DECISIONS.md`).
|
||||
Settings "Recording trigger") incl. the zero-config **game-launch watcher**
|
||||
(`core/watcher.py`, `rigdoctor watch`); and a **graphical first-run setup wizard**
|
||||
(`gui/setup_wizard.py`): environment → dependency-bundle selection → install → recording
|
||||
trigger → readiness, auto-launched by install.sh and re-runnable from Settings.
|
||||
*Pending:* `.deb` packaging (next bullet).
|
||||
- [ ] `.deb` packaging (D8) declaring per-bundle deps incl. python3-pyside6 for Desktop UI
|
||||
trigger → readiness, auto-launched by install.sh and re-runnable from Settings; and a
|
||||
**`.deb`** (`packaging/make_deb.py`, `Architecture: all`, `Depends: python3`,
|
||||
`Recommends: python3-pyside6/pyte`) built + published in CI (release asset + optional
|
||||
Gitea apt registry). **M9 complete.**
|
||||
- [x] `.deb` packaging (D8) — built via `dpkg-deb` (no debhelper); GUI deps as Recommends so
|
||||
`apt install rigdoctor` includes the Desktop UI, `--no-install-recommends` = CLI only.
|
||||
|
||||
## Phase 5 — Breadth (later)
|
||||
- [ ] AMD GPU support in M1 (Steam Deck / Radeon)
|
||||
|
||||
+5
-2
@@ -165,8 +165,11 @@ the actual findings plus matched reference facts from a curated, exact-match kno
|
||||
### M15 — Logging & report bundles (D25)
|
||||
Opt-in (one `logging_enabled` toggle, default off). When on: the application logs to a rotating
|
||||
`app.log`, and **each diagnostic is stored in its own directory** (capture log, structured
|
||||
result, human-readable report, scoped game logs, and a record of every AI interaction — the
|
||||
exact data sent, the model, and its reply). A **Report** action zips one diagnostic's directory
|
||||
result, human-readable report, the full **inventory** (M5 hardware/OS), session-scoped **game
|
||||
logs** (Proton/Steam) and **system logs** (`journalctl -k`, `coredumpctl`, an `nvidia-smi -q`
|
||||
snapshot, and the X11/Wayland display-server log), and a record of every AI interaction — the
|
||||
exact data sent, the model, and its reply). The collected logs are also fed to the AI on
|
||||
"Explain". Collection is best-effort (degrades if tools are missing/denied). A **Report** action zips one diagnostic's directory
|
||||
(plus the app log) into a shareable bundle saved under the reports folder (GUI button; CLI
|
||||
`rigdoctor bundle`). Everything stays local — a report only leaves the machine if the user
|
||||
shares the zip. Stdlib only (`logging` + `zipfile`).
|
||||
|
||||
@@ -0,0 +1,121 @@
|
||||
"""Build a `.deb` for RigDoctor (M9 / D8) — dependency-light, no debhelper.
|
||||
|
||||
Pure-Python app, so it's `Architecture: all`: we stage the package into dist-packages, drop the
|
||||
two launchers in /usr/bin, install the desktop entry + icon, write a DEBIAN/control, and call
|
||||
`dpkg-deb`. The core is stdlib (`Depends: python3`); everything else is **Recommends** so a
|
||||
plain `apt install rigdoctor` sets up the whole toolset automatically (users never hand-install
|
||||
deps) — the GUI modules (Debian/Ubuntu split PySide6 per module, so we name
|
||||
`python3-pyside6.qt{widgets,gui,websockets,svg}`) + `python3-pyte`, plus the diagnostic/gaming
|
||||
tools (smartmontools, lm-sensors, dmidecode, pciutils, libnotify-bin, libsecret-tools, gamemode,
|
||||
mangohud). `--no-install-recommends` still yields a CLI-only install; `cpupower` is a Suggests
|
||||
(kernel-tied/heavy).
|
||||
|
||||
Run: `python packaging/make_deb.py` → `dist/rigdoctor_<version>_all.deb`.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import shutil
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
DIST = ROOT / "dist"
|
||||
MAINTAINER = "Jessey van Offeren <jjvanofferen@gmail.com>"
|
||||
HOMEPAGE = "https://git.jesseyvanofferen.com/jessey/rigdoctor"
|
||||
|
||||
|
||||
def _version() -> str:
|
||||
text = (ROOT / "src" / "rigdoctor" / "__init__.py").read_text(encoding="utf-8")
|
||||
for line in text.splitlines():
|
||||
if line.startswith("__version__"):
|
||||
return line.split('"')[1]
|
||||
raise SystemExit("could not read __version__")
|
||||
|
||||
|
||||
_LAUNCHER = """\
|
||||
#!/usr/bin/python3
|
||||
import sys
|
||||
from {module} import main
|
||||
sys.exit(main())
|
||||
"""
|
||||
|
||||
_DESKTOP = """\
|
||||
[Desktop Entry]
|
||||
Type=Application
|
||||
Name=RigDoctor
|
||||
Comment=Hardware monitoring & crash diagnostics for Linux gamers
|
||||
Exec=rigdoctor-gui
|
||||
Icon=rigdoctor
|
||||
Terminal=false
|
||||
Categories=System;Monitor;Utility;
|
||||
StartupWMClass=rigdoctor
|
||||
"""
|
||||
|
||||
_CONTROL = """\
|
||||
Package: rigdoctor
|
||||
Version: {version}
|
||||
Architecture: all
|
||||
Maintainer: {maintainer}
|
||||
Section: utils
|
||||
Priority: optional
|
||||
Depends: python3 (>= 3.11)
|
||||
Recommends: python3-pyside6.qtwidgets, python3-pyside6.qtgui, python3-pyside6.qtwebsockets, python3-pyside6.qtsvg, python3-pyte, smartmontools, lm-sensors, dmidecode, pciutils, libnotify-bin, libsecret-tools, gamemode, mangohud
|
||||
Suggests: linux-tools-generic
|
||||
Homepage: {homepage}
|
||||
Description: Hardware monitoring & crash diagnostics for Linux gamers
|
||||
RigDoctor monitors GPU/CPU temperatures, load, and sensors, captures crash
|
||||
diagnostics while gaming, scans logs (Xid/SMART/kernel) for problems, and can
|
||||
explain them in plain language. The CLI and background daemon are pure Python
|
||||
(stdlib only); the optional desktop GUI and system-tray applet use PySide6,
|
||||
pulled in via Recommends. Install with --no-install-recommends for CLI only.
|
||||
"""
|
||||
|
||||
|
||||
def _write(path: Path, text: str, mode: int = 0o644) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.write_text(text, encoding="utf-8")
|
||||
path.chmod(mode)
|
||||
|
||||
|
||||
def build() -> Path:
|
||||
version = _version()
|
||||
DIST.mkdir(exist_ok=True)
|
||||
stage = DIST / f"rigdoctor_{version}_all"
|
||||
if stage.exists():
|
||||
shutil.rmtree(stage)
|
||||
|
||||
# Python package → dist-packages (importable system-wide), minus bytecode.
|
||||
pkg_dst = stage / "usr/lib/python3/dist-packages/rigdoctor"
|
||||
shutil.copytree(ROOT / "src" / "rigdoctor", pkg_dst,
|
||||
ignore=shutil.ignore_patterns("__pycache__", "*.pyc"))
|
||||
|
||||
# Launchers.
|
||||
_write(stage / "usr/bin/rigdoctor", _LAUNCHER.format(module="rigdoctor.cli"), 0o755)
|
||||
_write(stage / "usr/bin/rigdoctor-gui", _LAUNCHER.format(module="rigdoctor.gui.app"), 0o755)
|
||||
|
||||
# Desktop entry + icon.
|
||||
_write(stage / "usr/share/applications/rigdoctor.desktop", _DESKTOP)
|
||||
icon = ROOT / "src" / "rigdoctor" / "gui" / "assets" / "rigdoctor.svg"
|
||||
_write(stage / "usr/share/icons/hicolor/scalable/apps/rigdoctor.svg",
|
||||
icon.read_text(encoding="utf-8"))
|
||||
|
||||
# Refresh the desktop database on install/remove (best-effort).
|
||||
_write(stage / "DEBIAN/postinst",
|
||||
"#!/bin/sh\nset -e\nupdate-desktop-database -q 2>/dev/null || true\n", 0o755)
|
||||
_write(stage / "DEBIAN/postrm",
|
||||
"#!/bin/sh\nset -e\nupdate-desktop-database -q 2>/dev/null || true\n", 0o755)
|
||||
_write(stage / "DEBIAN/control",
|
||||
_CONTROL.format(version=version, maintainer=MAINTAINER, homepage=HOMEPAGE))
|
||||
|
||||
out = DIST / f"rigdoctor_{version}_all.deb"
|
||||
subprocess.run(["dpkg-deb", "--root-owner-group", "--build", str(stage), str(out)], check=True)
|
||||
shutil.rmtree(stage)
|
||||
return out
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
path = build()
|
||||
print(f"built {path}")
|
||||
sys.exit(0)
|
||||
+1
-1
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "rigdoctor"
|
||||
version = "0.30.0"
|
||||
version = "0.36.1"
|
||||
description = "Modular hardware monitoring & crash diagnostics for Linux gamers."
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.11"
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
"""RigDoctor — modular hardware monitoring & crash diagnostics for Linux gamers."""
|
||||
|
||||
__version__ = "0.30.0"
|
||||
__version__ = "0.36.1"
|
||||
|
||||
@@ -55,8 +55,9 @@ def cmd_gui(args) -> int:
|
||||
from .gui.app import main as gui_main
|
||||
except ImportError as exc:
|
||||
print("The GUI needs PySide6, which isn't installed.")
|
||||
print(" Install it with: pip install 'rigdoctor[gui]'")
|
||||
print(" or on Ubuntu: sudo apt install python3-pyside6")
|
||||
print(" Ubuntu/Debian: sudo apt install python3-pyside6.qtwidgets "
|
||||
"python3-pyside6.qtgui python3-pyside6.qtwebsockets python3-pyside6.qtsvg python3-pyte")
|
||||
print(" pip: pip install 'rigdoctor[gui]'")
|
||||
print(f" ({exc})")
|
||||
return 2
|
||||
return gui_main([sys.argv[0]])
|
||||
|
||||
@@ -150,6 +150,24 @@ def explain(findings_text: str, timeout: float = 120.0) -> tuple[bool, str]:
|
||||
return False, f"Unexpected response from the AI provider: {exc}"
|
||||
|
||||
|
||||
def explain_stream(findings_text: str, on_chunk, timeout: float = 180.0) -> tuple[bool, str]:
|
||||
"""Like :func:`explain`, but calls ``on_chunk(text_delta)`` as tokens arrive and returns
|
||||
``(ok, full_text)`` at the end. Caller MUST be a direct user action (D24)."""
|
||||
content = build_prompt(findings_text)
|
||||
try:
|
||||
if provider() == "claude":
|
||||
return _claude_stream(content, on_chunk, timeout)
|
||||
if provider() == "ollama":
|
||||
return _ollama_stream(content, on_chunk, timeout)
|
||||
return False, "No AI provider is configured (Settings → AI assistant)."
|
||||
except urllib.error.HTTPError as exc:
|
||||
return False, _http_error(exc)
|
||||
except (urllib.error.URLError, OSError, TimeoutError) as exc:
|
||||
return False, f"Couldn't reach the AI provider: {exc}"
|
||||
except (ValueError, KeyError, IndexError) as exc:
|
||||
return False, f"Unexpected response from the AI provider: {exc}"
|
||||
|
||||
|
||||
def _post(url: str, payload: dict, headers: dict, timeout: float) -> dict:
|
||||
req = urllib.request.Request(
|
||||
url, data=json.dumps(payload).encode("utf-8"),
|
||||
@@ -185,6 +203,65 @@ def _claude(content: str, timeout: float) -> tuple[bool, str]:
|
||||
return True, text.strip() or "(the model returned no text)"
|
||||
|
||||
|
||||
def _stream_request(url: str, payload: dict, headers: dict, timeout: float):
|
||||
req = urllib.request.Request(
|
||||
url, data=json.dumps(payload).encode("utf-8"),
|
||||
headers={"Content-Type": "application/json", **headers})
|
||||
return urllib.request.urlopen(req, timeout=timeout)
|
||||
|
||||
|
||||
def _ollama_stream(content: str, on_chunk, timeout: float) -> tuple[bool, str]:
|
||||
if not model():
|
||||
return False, "No Ollama model is set (Settings → AI assistant)."
|
||||
payload = {"model": model(), "system": SYSTEM_PROMPT, "prompt": content, "stream": True}
|
||||
parts: list[str] = []
|
||||
with _stream_request(endpoint().rstrip("/") + "/api/generate", payload, {}, timeout) as resp:
|
||||
for raw in resp: # newline-delimited JSON objects
|
||||
line = raw.decode("utf-8", "replace").strip()
|
||||
if not line:
|
||||
continue
|
||||
obj = json.loads(line)
|
||||
chunk = obj.get("response", "")
|
||||
if chunk:
|
||||
parts.append(chunk)
|
||||
on_chunk(chunk)
|
||||
if obj.get("done"):
|
||||
break
|
||||
return True, "".join(parts).strip() or "(the model returned an empty response)"
|
||||
|
||||
|
||||
def _claude_stream(content: str, on_chunk, timeout: float) -> tuple[bool, str]:
|
||||
key = config.load_ai_key()
|
||||
if not key:
|
||||
return False, "No Claude API key is set (Settings → AI assistant)."
|
||||
payload = {
|
||||
"model": model(), "max_tokens": CLAUDE_MAX_TOKENS, "system": SYSTEM_PROMPT,
|
||||
"messages": [{"role": "user", "content": content}], "stream": True,
|
||||
}
|
||||
headers = {"x-api-key": key, "anthropic-version": ANTHROPIC_VERSION}
|
||||
parts: list[str] = []
|
||||
with _stream_request(CLAUDE_ENDPOINT, payload, headers, timeout) as resp:
|
||||
for raw in resp: # SSE: parse `data:` lines, accumulate text deltas
|
||||
line = raw.decode("utf-8", "replace").strip()
|
||||
if not line.startswith("data:"):
|
||||
continue
|
||||
try:
|
||||
event = json.loads(line[5:].strip())
|
||||
except ValueError:
|
||||
continue
|
||||
etype = event.get("type")
|
||||
if etype == "content_block_delta" and event.get("delta", {}).get("type") == "text_delta":
|
||||
chunk = event["delta"].get("text", "")
|
||||
if chunk:
|
||||
parts.append(chunk)
|
||||
on_chunk(chunk)
|
||||
elif etype == "error":
|
||||
return False, event.get("error", {}).get("message", "stream error")
|
||||
elif etype == "message_stop":
|
||||
break
|
||||
return True, "".join(parts).strip() or "(the model returned no text)"
|
||||
|
||||
|
||||
def _http_error(exc: urllib.error.HTTPError) -> str:
|
||||
detail = ""
|
||||
try:
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -51,7 +51,7 @@ def store(result, capture_path=None, since: float | None = None) -> Path | None:
|
||||
if not enabled():
|
||||
return None
|
||||
from ..render import render_summary
|
||||
from . import ai, gamelogs
|
||||
from . import ai, gamelogs, syslogs
|
||||
|
||||
target = _new_dir(getattr(result, "game", None))
|
||||
|
||||
@@ -80,6 +80,22 @@ def store(result, capture_path=None, since: float | None = None) -> Path | None:
|
||||
_write(target / "gamelogs.txt", logs)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
try:
|
||||
sys_logs = syslogs.collect(since=since)
|
||||
if sys_logs:
|
||||
_write(target / "syslogs.txt", sys_logs)
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
try: # full hardware/OS inventory (M5) — invaluable for larger debugging in a shared report
|
||||
from . import inventory
|
||||
|
||||
sections = inventory.collect()
|
||||
_write(target / "inventory.txt", inventory.render_text(sections))
|
||||
_write(target / "inventory.json", inventory.render_json(sections))
|
||||
except Exception: # inventory probes vary by machine; never let it break storage
|
||||
pass
|
||||
return target
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,165 @@
|
||||
"""Session-scoped system logs for diagnostics (M15): kernel, coredumps, NVIDIA, display.
|
||||
|
||||
Covers what the *system* logged when something went wrong, so the report bundle and the AI both
|
||||
see it:
|
||||
* kernel ring-buffer slice (`journalctl -k`) — Xid, OOM-killer, MCE, PCIe AER, thermal, hung tasks
|
||||
* systemd-coredump records (`coredumpctl`) — did the game/wine dump core (SIGSEGV/ABRT), when
|
||||
* an `nvidia-smi -q` snapshot — driver, throttle/clock-event reasons, clocks, power, temps, PCIe,
|
||||
ECC + retired pages (point-in-time at diagnostic time)
|
||||
* the display-server log — `Xorg.0.log` on X11, or the compositor's user-journal slice on Wayland
|
||||
Best-effort and size-bounded: degrades silently if a tool is missing or access is denied. Stdlib only.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import subprocess
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
_MAX = 8000 # cap each log section so the prompt/report stays small
|
||||
_NV_MAX = 10000 # nvidia-smi -q is structured + valuable; allow a bit more (head-truncated)
|
||||
|
||||
# Compositors whose user-journal entries are the "Wayland log" (OR-matched by journalctl).
|
||||
_COMPOSITORS = ("gnome-shell", "mutter", "kwin_wayland", "Xwayland", "sway", "gamescope")
|
||||
_XORG_LOGS = ("~/.local/share/xorg/Xorg.0.log", "/var/log/Xorg.0.log")
|
||||
|
||||
|
||||
def _since_arg(since: float | None) -> str | None:
|
||||
return time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(since)) if since else None
|
||||
|
||||
|
||||
def _run(cmd: list[str], timeout: float = 15.0) -> str:
|
||||
try:
|
||||
proc = subprocess.run(cmd, capture_output=True, text=True, timeout=timeout)
|
||||
except (OSError, subprocess.SubprocessError):
|
||||
return ""
|
||||
return (proc.stdout or "").strip()
|
||||
|
||||
|
||||
def kernel_log(since: float | None = None, max_bytes: int = _MAX) -> str:
|
||||
if not shutil.which("journalctl"):
|
||||
return ""
|
||||
cmd = ["journalctl", "-k", "--no-pager"]
|
||||
since_arg = _since_arg(since)
|
||||
if since_arg:
|
||||
cmd += ["--since", since_arg]
|
||||
out = _run(cmd)
|
||||
if not out or out.strip().lower() == "-- no entries --": # journalctl's empty marker
|
||||
return ""
|
||||
return out[-max_bytes:]
|
||||
|
||||
|
||||
def coredumps(since: float | None = None, max_bytes: int = _MAX) -> str:
|
||||
if not shutil.which("coredumpctl"):
|
||||
return ""
|
||||
cmd = ["coredumpctl", "list", "--no-pager"]
|
||||
since_arg = _since_arg(since)
|
||||
if since_arg:
|
||||
cmd += ["--since", since_arg]
|
||||
out = _run(cmd)
|
||||
if not out or "no coredumps" in out.lower():
|
||||
return ""
|
||||
return out[-max_bytes:]
|
||||
|
||||
|
||||
def nvidia_snapshot(max_bytes: int = _NV_MAX) -> str:
|
||||
"""Point-in-time `nvidia-smi -q` (head-truncated — driver/temps/clocks/ECC sit near the top)."""
|
||||
if not shutil.which("nvidia-smi"):
|
||||
return ""
|
||||
out = _run(["nvidia-smi", "-q"])
|
||||
return out[:max_bytes] if out else ""
|
||||
|
||||
|
||||
def _xorg_log() -> Path | None:
|
||||
for cand in _XORG_LOGS:
|
||||
path = Path(os.path.expanduser(cand))
|
||||
if path.exists():
|
||||
return path
|
||||
return None
|
||||
|
||||
|
||||
def _session_type() -> str:
|
||||
declared = os.environ.get("XDG_SESSION_TYPE", "").lower()
|
||||
if declared in ("x11", "wayland"):
|
||||
return declared
|
||||
if os.environ.get("WAYLAND_DISPLAY"):
|
||||
return "wayland"
|
||||
return "x11" if _xorg_log() else "unknown"
|
||||
|
||||
|
||||
def _tail_file(path: Path, max_bytes: int) -> str:
|
||||
try:
|
||||
size = path.stat().st_size
|
||||
with path.open("rb") as fh:
|
||||
if size > max_bytes:
|
||||
fh.seek(size - max_bytes)
|
||||
return fh.read().decode("utf-8", "replace")
|
||||
except OSError:
|
||||
return ""
|
||||
|
||||
|
||||
def display_log(since: float | None = None, max_bytes: int = _MAX) -> str:
|
||||
"""Xorg.0.log on X11, or the compositor's user-journal slice on Wayland ('' if none)."""
|
||||
if _session_type() == "wayland":
|
||||
if not shutil.which("journalctl"):
|
||||
return ""
|
||||
cmd = ["journalctl", "--user", "--no-pager"]
|
||||
since_arg = _since_arg(since)
|
||||
if since_arg:
|
||||
cmd += ["--since", since_arg]
|
||||
cmd += [f"_COMM={comp}" for comp in _COMPOSITORS] # OR-matched
|
||||
out = _run(cmd)
|
||||
if not out or out.strip().lower() == "-- no entries --":
|
||||
return ""
|
||||
return out[-max_bytes:]
|
||||
log = _xorg_log() # X11: Xorg log isn't wall-clock-timestamped, so tail rather than scope
|
||||
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())
|
||||
|
||||
|
||||
def collect(since: float | None = None) -> str:
|
||||
"""Kernel + coredumps + NVIDIA snapshot + display log as one labelled block ('' if none)."""
|
||||
sections: list[str] = []
|
||||
kern = kernel_log(since)
|
||||
if kern:
|
||||
sections.append(f"--- Kernel log (journalctl -k) ---\n{kern}")
|
||||
cores = coredumps(since)
|
||||
if cores:
|
||||
sections.append(f"--- Crashed processes (coredumpctl) ---\n{cores}")
|
||||
nvidia = nvidia_snapshot()
|
||||
if nvidia:
|
||||
sections.append(f"--- NVIDIA snapshot (nvidia-smi -q) ---\n{nvidia}")
|
||||
display = display_log(since)
|
||||
if display:
|
||||
sections.append(f"--- Display server log ({_session_type()}) ---\n{display}")
|
||||
return "\n\n".join(sections)
|
||||
@@ -5,7 +5,7 @@ from __future__ import annotations
|
||||
import threading
|
||||
|
||||
from PySide6.QtCore import Qt, Signal
|
||||
from PySide6.QtGui import QFont
|
||||
from PySide6.QtGui import QFont, QTextCursor
|
||||
from PySide6.QtWidgets import (
|
||||
QDialog,
|
||||
QFrame,
|
||||
@@ -24,11 +24,15 @@ from .widgets import finding_card
|
||||
|
||||
|
||||
class DiagnosticDialog(QDialog):
|
||||
_explained = Signal(object) # (ok, text) from a user-triggered AI explanation
|
||||
_chunk = Signal(str) # streamed token delta (worker thread -> GUI)
|
||||
_explained = Signal(object) # (ok, full_text) when the AI stream finishes
|
||||
|
||||
def __init__(self, result, parent=None) -> None:
|
||||
super().__init__(parent)
|
||||
self._result = result
|
||||
self._stream_view = None
|
||||
self._stream_status = None
|
||||
self._chunk.connect(self._on_chunk)
|
||||
self._explained.connect(self._on_explained)
|
||||
self.setWindowTitle(f"Diagnostic — {result.game}" if result.game else "Diagnostic")
|
||||
self.resize(660, 680)
|
||||
@@ -97,7 +101,7 @@ class DiagnosticDialog(QDialog):
|
||||
buttons.addWidget(close)
|
||||
root.addLayout(buttons)
|
||||
|
||||
# --- AI explanation (M14, D24) — runs only on this button press ----------------
|
||||
# --- AI explanation (M14, D24) — streamed; runs only on this button press ----------
|
||||
def _explain_with_ai(self) -> None:
|
||||
from ..core import ai
|
||||
|
||||
@@ -111,11 +115,14 @@ class DiagnosticDialog(QDialog):
|
||||
if confirm != QMessageBox.StandardButton.Yes:
|
||||
return
|
||||
self._explain_btn.setEnabled(False)
|
||||
self._explain_btn.setText("Asking the AI…")
|
||||
dialog = self._open_stream_dialog()
|
||||
threading.Thread(target=self._work_explain, daemon=True).start()
|
||||
dialog.exec() # streaming fills the view live via signals during this nested loop
|
||||
self._stream_view = self._stream_status = None
|
||||
self._explain_btn.setEnabled(True)
|
||||
|
||||
def _work_explain(self) -> None:
|
||||
from ..core import ai, gamelogs
|
||||
from ..core import ai, gamelogs, syslogs
|
||||
|
||||
result = self._result
|
||||
summary = result.summary
|
||||
@@ -139,8 +146,12 @@ class DiagnosticDialog(QDialog):
|
||||
logs = gamelogs.collect(since=since) # 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
|
||||
if sys_logs:
|
||||
lines.append("\nSystem logs for this session (kernel + crashed processes):\n" + sys_logs)
|
||||
text = "\n".join(lines)
|
||||
ok, reply = ai.explain(text)
|
||||
|
||||
ok, reply = ai.explain_stream(text, on_chunk=lambda d: self._chunk.emit(d))
|
||||
if result.dir: # record exactly what was sent, the model, and the reply (M15)
|
||||
from ..core import diagstore
|
||||
diagstore.record_ai(
|
||||
@@ -149,11 +160,24 @@ class DiagnosticDialog(QDialog):
|
||||
response=reply if ok else f"[error] {reply}")
|
||||
self._explained.emit((ok, reply))
|
||||
|
||||
def _on_chunk(self, delta: str) -> None:
|
||||
if self._stream_view is None:
|
||||
return
|
||||
self._stream_view.moveCursor(QTextCursor.MoveOperation.End)
|
||||
self._stream_view.insertPlainText(delta) # live plain text as tokens arrive
|
||||
self._stream_view.ensureCursorVisible()
|
||||
|
||||
def _on_explained(self, result) -> None:
|
||||
ok, text = result
|
||||
self._explain_btn.setEnabled(True)
|
||||
self._explain_btn.setText("Explain with AI")
|
||||
self._show_explanation(text if ok else f"AI explanation failed:\n\n{text}")
|
||||
if self._stream_view is not None:
|
||||
if ok:
|
||||
self._stream_view.setMarkdown(text) # re-render the finished answer as Markdown
|
||||
else:
|
||||
self._stream_view.setPlainText(f"AI explanation failed:\n\n{text}")
|
||||
if self._stream_status is not None:
|
||||
self._stream_status.setText(
|
||||
"AI-generated suggestions — verify before acting, especially anything that changes "
|
||||
"settings or data." if ok else "The request failed.")
|
||||
|
||||
# --- Report bundle (M15) ------------------------------------------------------
|
||||
def _make_report(self) -> None:
|
||||
@@ -180,7 +204,8 @@ class DiagnosticDialog(QDialog):
|
||||
if box.clickedButton() is open_btn:
|
||||
QDesktopServices.openUrl(QUrl.fromLocalFile(str(out.parent)))
|
||||
|
||||
def _show_explanation(self, text: str) -> None:
|
||||
def _open_stream_dialog(self) -> QDialog:
|
||||
"""A live dialog the AI streams into; finalized to rendered Markdown when done."""
|
||||
from ..core import ai
|
||||
|
||||
dlg = QDialog(self)
|
||||
@@ -190,14 +215,15 @@ class DiagnosticDialog(QDialog):
|
||||
view = QTextEdit()
|
||||
view.setObjectName("Report")
|
||||
view.setReadOnly(True)
|
||||
view.setMarkdown(text) # the model replies in Markdown — render it
|
||||
lay.addWidget(view)
|
||||
note = QLabel("AI-generated suggestions — verify before acting, especially anything that changes settings or data.")
|
||||
note.setObjectName("Muted")
|
||||
note.setWordWrap(True)
|
||||
lay.addWidget(note)
|
||||
status = QLabel("Streaming from the model…")
|
||||
status.setObjectName("Muted")
|
||||
status.setWordWrap(True)
|
||||
lay.addWidget(status)
|
||||
close = QPushButton("Close")
|
||||
close.setObjectName("PrimaryButton")
|
||||
close.clicked.connect(dlg.accept)
|
||||
lay.addWidget(close, alignment=Qt.AlignmentFlag.AlignRight)
|
||||
dlg.exec()
|
||||
self._stream_view = view
|
||||
self._stream_status = status
|
||||
return dlg
|
||||
|
||||
@@ -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)
|
||||
|
||||
@@ -114,5 +114,51 @@ class ExplainTests(unittest.TestCase):
|
||||
self.assertEqual(headers["x-api-key"], "sk-ant-x")
|
||||
|
||||
|
||||
class _FakeResp:
|
||||
"""A context-managed iterable of byte lines, like urlopen() returns."""
|
||||
def __init__(self, lines):
|
||||
self._lines = [l.encode("utf-8") for l in lines]
|
||||
def __enter__(self):
|
||||
return iter(self._lines)
|
||||
def __exit__(self, *a):
|
||||
return False
|
||||
|
||||
|
||||
class StreamTests(unittest.TestCase):
|
||||
def _cfg(self, **over):
|
||||
base = {"ai_provider": "", "ai_model": "", "ai_endpoint": "http://localhost:11434"}
|
||||
base.update(over)
|
||||
return base
|
||||
|
||||
def test_ollama_stream_accumulates_and_callbacks(self):
|
||||
lines = ['{"response": "It is ", "done": false}',
|
||||
'{"response": "the PSU.", "done": false}',
|
||||
'{"response": "", "done": true}']
|
||||
chunks = []
|
||||
with mock.patch.object(ai.config, "load_config",
|
||||
return_value=self._cfg(ai_provider="ollama", ai_model="qwen2.5:7b")), \
|
||||
mock.patch.object(ai, "_stream_request", return_value=_FakeResp(lines)):
|
||||
ok, full = ai.explain_stream("Xid 79", on_chunk=chunks.append)
|
||||
self.assertTrue(ok)
|
||||
self.assertEqual(full, "It is the PSU.")
|
||||
self.assertEqual(chunks, ["It is ", "the PSU."])
|
||||
|
||||
def test_claude_stream_parses_sse(self):
|
||||
lines = [
|
||||
'event: content_block_delta',
|
||||
'data: {"type":"content_block_delta","delta":{"type":"text_delta","text":"Failing "}}',
|
||||
'data: {"type":"content_block_delta","delta":{"type":"text_delta","text":"disk."}}',
|
||||
'data: {"type":"message_stop"}',
|
||||
]
|
||||
chunks = []
|
||||
with mock.patch.object(ai.config, "load_config", return_value=self._cfg(ai_provider="claude")), \
|
||||
mock.patch.object(ai.config, "load_ai_key", return_value="sk-ant-x"), \
|
||||
mock.patch.object(ai, "_stream_request", return_value=_FakeResp(lines)):
|
||||
ok, full = ai.explain_stream("SMART 197", on_chunk=chunks.append)
|
||||
self.assertTrue(ok)
|
||||
self.assertEqual(full, "Failing disk.")
|
||||
self.assertEqual(chunks, ["Failing ", "disk."])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -34,5 +34,35 @@ class AlertTests(unittest.TestCase):
|
||||
m.assert_called_once()
|
||||
|
||||
|
||||
class KernelEventAlertTests(unittest.TestCase):
|
||||
@mock.patch.object(alerts, "notify")
|
||||
def test_kernel_event_fires_once_within_cooldown(self, m):
|
||||
mon = alerts.AlertMonitor(cooldown=300.0, event_interval=0.0)
|
||||
mon._last_kernel_scan = 0.0 # force a scan
|
||||
with mock.patch("rigdoctor.core.syslogs.kernel_log",
|
||||
return_value="NVRM: Xid (PCI:0000:01:00): 79, GPU has fallen off the bus"):
|
||||
mon._scan_kernel_events()
|
||||
mon._last_kernel_scan = 0.0 # force another scan — cooldown must suppress it
|
||||
mon._scan_kernel_events()
|
||||
self.assertEqual(m.call_count, 1)
|
||||
self.assertIn("Xid", m.call_args[0][0])
|
||||
|
||||
@mock.patch.object(alerts, "notify")
|
||||
def test_no_alert_when_kernel_log_empty(self, m):
|
||||
mon = alerts.AlertMonitor(event_interval=0.0)
|
||||
mon._last_kernel_scan = 0.0
|
||||
with mock.patch("rigdoctor.core.syslogs.kernel_log", return_value=""):
|
||||
mon._scan_kernel_events()
|
||||
m.assert_not_called()
|
||||
|
||||
@mock.patch.object(alerts, "notify")
|
||||
def test_scan_gated_by_interval(self, m):
|
||||
mon = alerts.AlertMonitor(event_interval=9999.0) # just constructed → not due yet
|
||||
with mock.patch("rigdoctor.core.syslogs.kernel_log", return_value="NVRM: Xid 79") as kl:
|
||||
mon._scan_kernel_events()
|
||||
kl.assert_not_called()
|
||||
m.assert_not_called()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -47,11 +47,15 @@ class StoreTests(unittest.TestCase):
|
||||
with mock.patch.object(diagstore, "enabled", return_value=True), \
|
||||
mock.patch("rigdoctor.render.render_summary", return_value="SUMMARY-TEXT"), \
|
||||
mock.patch("rigdoctor.core.gamelogs.collect", return_value="LOG-TEXT"), \
|
||||
mock.patch("rigdoctor.core.syslogs.collect", return_value="SYS-LOG"), \
|
||||
mock.patch("rigdoctor.core.inventory.collect", return_value=[]), \
|
||||
mock.patch.object(diagstore.config, "DIAGNOSTICS_DIR", self.tmp / "diagnostics"):
|
||||
directory = diagstore.store(FakeResult())
|
||||
self.assertTrue((directory / "result.json").exists())
|
||||
self.assertTrue((directory / "report.txt").exists())
|
||||
self.assertEqual((directory / "gamelogs.txt").read_text(), "LOG-TEXT")
|
||||
self.assertEqual((directory / "syslogs.txt").read_text(), "SYS-LOG")
|
||||
self.assertTrue((directory / "inventory.txt").exists()) # inventory included for debugging
|
||||
data = json.loads((directory / "result.json").read_text())
|
||||
self.assertEqual(data["game"], "Path of Exile 2")
|
||||
self.assertEqual(len(data["findings"]), 1)
|
||||
|
||||
@@ -0,0 +1,114 @@
|
||||
"""Tests for M15 session-scoped system-log collection (kernel + coredumps)."""
|
||||
|
||||
import unittest
|
||||
from unittest import mock
|
||||
|
||||
from rigdoctor.core import syslogs
|
||||
|
||||
|
||||
class KernelLogTests(unittest.TestCase):
|
||||
def test_passes_since_and_tails(self):
|
||||
with mock.patch("shutil.which", return_value="/usr/bin/journalctl"), \
|
||||
mock.patch.object(syslogs, "_run", return_value="X" * 100 + "TAILLINE") as run:
|
||||
out = syslogs.kernel_log(since=1_000_000_000, max_bytes=8)
|
||||
self.assertEqual(out, "TAILLINE")
|
||||
cmd = run.call_args[0][0]
|
||||
self.assertIn("-k", cmd)
|
||||
self.assertIn("--since", cmd)
|
||||
|
||||
def test_missing_tool_returns_empty(self):
|
||||
with mock.patch("shutil.which", return_value=None):
|
||||
self.assertEqual(syslogs.kernel_log(), "")
|
||||
|
||||
|
||||
class CoredumpTests(unittest.TestCase):
|
||||
def test_empty_when_no_coredumps(self):
|
||||
with mock.patch("shutil.which", return_value="/usr/bin/coredumpctl"), \
|
||||
mock.patch.object(syslogs, "_run", return_value="No coredumps found."):
|
||||
self.assertEqual(syslogs.coredumps(), "")
|
||||
|
||||
def test_returns_list(self):
|
||||
with mock.patch("shutil.which", return_value="/usr/bin/coredumpctl"), \
|
||||
mock.patch.object(syslogs, "_run", return_value="TIME PID SIG EXE\n... SEGV PathOfExile"):
|
||||
out = syslogs.coredumps()
|
||||
self.assertIn("PathOfExile", out)
|
||||
|
||||
|
||||
class NvidiaTests(unittest.TestCase):
|
||||
def test_missing_tool(self):
|
||||
with mock.patch("shutil.which", return_value=None):
|
||||
self.assertEqual(syslogs.nvidia_snapshot(), "")
|
||||
|
||||
def test_snapshot_head_truncated(self):
|
||||
with mock.patch("shutil.which", return_value="/usr/bin/nvidia-smi"), \
|
||||
mock.patch.object(syslogs, "_run", return_value="DRIVER\n" + "x" * 99999):
|
||||
out = syslogs.nvidia_snapshot(max_bytes=10)
|
||||
self.assertEqual(out, "DRIVER\nxxx") # head, not tail
|
||||
|
||||
|
||||
class DisplayTests(unittest.TestCase):
|
||||
def test_session_type_env(self):
|
||||
with mock.patch.dict("os.environ", {"XDG_SESSION_TYPE": "wayland"}):
|
||||
self.assertEqual(syslogs._session_type(), "wayland")
|
||||
|
||||
def test_x11_tails_xorg_log(self):
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
log = Path(tempfile.mkdtemp()) / "Xorg.0.log"
|
||||
log.write_text("(EE) NVIDIA(GPU-0): something failed")
|
||||
with mock.patch.object(syslogs, "_session_type", return_value="x11"), \
|
||||
mock.patch.object(syslogs, "_xorg_log", return_value=log):
|
||||
out = syslogs.display_log()
|
||||
self.assertIn("(EE) NVIDIA", out)
|
||||
|
||||
def test_wayland_uses_user_journal(self):
|
||||
with mock.patch.object(syslogs, "_session_type", return_value="wayland"), \
|
||||
mock.patch("shutil.which", return_value="/usr/bin/journalctl"), \
|
||||
mock.patch.object(syslogs, "_run", return_value="gnome-shell: GPU error") as run:
|
||||
out = syslogs.display_log(since=1_000_000_000)
|
||||
self.assertIn("GPU error", out)
|
||||
cmd = run.call_args[0][0]
|
||||
self.assertIn("--user", cmd)
|
||||
self.assertTrue(any(a.startswith("_COMM=") for a in cmd))
|
||||
|
||||
|
||||
class ScanCriticalTests(unittest.TestCase):
|
||||
def test_matches_each_category(self):
|
||||
text = "\n".join([
|
||||
"NVRM: Xid (PCI:0000:01:00): 79, GPU has fallen off the bus",
|
||||
"Out of memory: Killed process 1234 (PathOfExile)",
|
||||
"mce: [Hardware Error]: CPU 0",
|
||||
"pcieport 0000:00:01.0: AER: Corrected error received",
|
||||
"blk_update_request: I/O error, dev sda, sector 99",
|
||||
"this is a perfectly normal line",
|
||||
])
|
||||
labels = {label for label, _ in syslogs.scan_critical(text)}
|
||||
self.assertEqual(labels, {
|
||||
"GPU error (Xid)", "Out of memory", "CPU machine-check",
|
||||
"PCIe error", "Disk I/O error"})
|
||||
|
||||
def test_clean_log_no_events(self):
|
||||
self.assertEqual(syslogs.scan_critical("usb 1-2: new high-speed device\nsystemd: started"), [])
|
||||
|
||||
|
||||
class CollectTests(unittest.TestCase):
|
||||
def test_collect_combines_sections(self):
|
||||
with mock.patch.object(syslogs, "kernel_log", return_value="NVRM: Xid 79"), \
|
||||
mock.patch.object(syslogs, "coredumps", return_value="game SIGSEGV"), \
|
||||
mock.patch.object(syslogs, "nvidia_snapshot", return_value="Driver Version 595"), \
|
||||
mock.patch.object(syslogs, "display_log", return_value="(EE) NVIDIA"):
|
||||
out = syslogs.collect()
|
||||
for needle in ("Kernel log", "Xid 79", "Crashed processes", "SIGSEGV",
|
||||
"NVIDIA snapshot", "595", "Display server log"):
|
||||
self.assertIn(needle, out)
|
||||
|
||||
def test_collect_empty_when_nothing(self):
|
||||
with mock.patch.object(syslogs, "kernel_log", return_value=""), \
|
||||
mock.patch.object(syslogs, "coredumps", return_value=""), \
|
||||
mock.patch.object(syslogs, "nvidia_snapshot", return_value=""), \
|
||||
mock.patch.object(syslogs, "display_log", return_value=""):
|
||||
self.assertEqual(syslogs.collect(), "")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user