Daniel/meeting-assistant
1
0
Fork 0
forked from Manuel/meeting-assistant
Code Pull Requests Actions Activity Open in Coder

ci: retain an owned guest monitor screenshot before cleanup

Browse Source
This commit is contained in:
dh
2026-10-03 16:08:26 +02:00
parent 90d86af887
commit 6e58928c1f
2 changed files with 40 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/macos-native-diagnostic.md
+2
View File
@@ -26,6 +26,8 @@ The VM uses TCG (`KVM=N`), slirp networking, a 4-GiB guest, two virtual CPUs and
Evidence is written under the requested output directory: run identity and candidate commit, Docker/runner resources, exact source patch artifacts and hashes, image/container inspection, Recovery hash, native platform/process/launchctl/diskutil logs, machine-readable guest result, outcome and cleanup receipt. The workflow retains these as a seven-day artifact. Phase names and up to 512 KiB of the final native proof also appear in CI stdout, on success or failure, with the run token replaced; no environment or credential dump is printed. A Docker start/build exit zero is not a successful native result. A missing, stale, unsupported-platform, read-only or wrong-size guest receipt fails.
Before final cleanup, an optional ten-second capture rechecks the saved container ID/ownership label and uses the pinned image's existing Unix HMP socket, `nc.openbsd` and a five-second `timeout` to collect only [`info status` and `screendump`](https://www.qemu.org/docs/master/system/monitor.html), retaining the command transcript, exit codes and fresh bounded PPM screenshot; capture failure is visible and never changes native readiness or test success.
Every container/image has a random run token in its ownership label. `finally` cleanup and the workflow's `always()` step inspect that exact label before removing the matching container and its anonymous storage volume, then the matching image. They never remove an unrelated name or volume, prune Docker, modify host settings or restart Meeting Assistant. Temporary source files are deleted only when their local marker matches the same token. Evidence remains available after cleanup.
The earlier background-only local bootstrap never obtained DiskManagement readiness. This separate LaunchDaemon probe is still an experiment until the actual remote run produces the required native evidence. Full macOS CI support remains unverified until an installed guest subsequently compiles/signs the native helpers and passes all application tests, including all five native tests without skips.
tools/ci/MacOsNativeDiagnostic.cs
+38 -2
View File
@@ -203,7 +203,7 @@ static class NativeDiagnostic
{
Console.CancelKeyPress -= cancelHandler;
using var captureDeadline = new CancellationTokenSource(TimeSpan.FromSeconds(45));
try { await CaptureGuest(state.ContainerName, output, captureDeadline.Token, full, true); } catch (Exception exception) { Console.Error.WriteLine("Final evidence capture: " + exception.Message); }
try { await CaptureGuest(state.ContainerId ?? state.ContainerName, output, captureDeadline.Token, full, true, state.Token); } catch (Exception exception) { Console.Error.WriteLine("Final evidence capture: " + exception.Message); }
try { PrintGuestProof(output, state.Token); } catch (Exception exception) { Console.Error.WriteLine("Native proof output: " + exception.Message); }
if (full) try { PrintFullProof(output, state.Token); } catch (Exception exception) { Console.Error.WriteLine("Full native proof output: " + exception.Message); }
var clean = await Cleanup(output);
@@ -572,8 +572,9 @@ static class NativeDiagnostic
throw new InvalidOperationException("Created container exceeds the owned/unprivileged diagnostic boundary.");
}
static async Task CaptureGuest(string id, string output, CancellationToken cancellation, bool full = false, bool final = false)
static async Task CaptureGuest(string id, string output, CancellationToken cancellation, bool full = false, bool final = false, string? token = null)
{
if (final && token is not null) await CaptureMonitor(id, output, token, cancellation);
var logs = await Command("docker", ["logs", "--tail", "3000", id], output, "container", cancellation, requireSuccess: false);
var files = new List<(string, string)> { ("proof.log", "guest-proof.log"), ("result.json", "guest-result.json") };
if (full) files.AddRange([("guest-phase.json", "guest-phase.json"), ("full-result.json", "full-result.json"), ("firstboot.log", "firstboot.log"), ("install.log", "install.log"), ("apple.log", "apple.log"), ("disk-ownership-ioreg.log", "disk-ownership-ioreg.log"), ("installed-root.plist", "installed-root.plist"), ("clt-catalog.log", "clt-catalog.log"), ("clt-install.log", "clt-install.log")]);
@@ -596,6 +597,41 @@ static class NativeDiagnostic
await Command("docker", ["exec", id, "sh", "-c", "printf '[qemu]\n'; qemu-system-x86_64 --version | head -n 1; printf '[Recovery hash]\n'; test ! -f /storage/14/setup.dmg || sha256sum /storage/14/setup.dmg; printf '[resources]\n'; df -Pk /storage; cat /sys/fs/cgroup/memory.max /sys/fs/cgroup/cpu.max 2>/dev/null || true"], output, "guest-container-resources", cancellation, requireSuccess: false);
}
static async Task CaptureMonitor(string id, string output, string token, CancellationToken cancellation)
{
using var deadline = CancellationTokenSource.CreateLinkedTokenSource(cancellation);
deadline.CancelAfter(TimeSpan.FromSeconds(10));
int? monitorExit = null, copyExit = null;
string? error = null;
try
{
if (!System.Text.RegularExpressions.Regex.IsMatch(id, "^[0-9a-f]{64}$") || !System.Text.RegularExpressions.Regex.IsMatch(token, "^[0-9a-f]{32}$")) throw new InvalidOperationException("No saved owned container identity for the optional monitor capture.");
var inspection = await Command("docker", ["inspect", id], output, "capture-monitor-container", deadline.Token);
AssertContainer(inspection.Output, token);
using (var document = JsonDocument.Parse(inspection.Output))
if (document.RootElement[0].GetProperty("Id").GetString() != id || !document.RootElement[0].GetProperty("State").GetProperty("Running").GetBoolean()) throw new InvalidOperationException("Owned guest container is no longer running for the optional monitor capture.");
var screen = "/dev/shm/native-diagnostic-screen-" + token + ".ppm";
var monitor = await Command("docker", ["exec", id, "sh", "-c", """
test -S /run/shm/monitor.sock || exit 1
rm -f -- "$1" || exit 1
printf 'info status\nscreendump %s\n' "$1" | /usr/bin/timeout -s KILL 5 /usr/bin/nc.openbsd -q 1 -w 2 -U /run/shm/monitor.sock
monitor_exit=$?
printf '\n[monitor-exit] %s\n' "$monitor_exit"
[ "$monitor_exit" -eq 0 ] || exit "$monitor_exit"
bytes=$(stat -c%s "$1") || exit 1
[ "$bytes" -gt 0 ] && [ "$bytes" -le 8388608 ] || exit 1
printf '[screen-bytes] %s\n' "$bytes"
""", "native-monitor", screen], output, "capture-monitor", deadline.Token, requireSuccess: false);
monitorExit = monitor.ExitCode;
if (monitorExit != 0) throw new InvalidOperationException("Optional monitor status/screenshot command exited " + monitorExit + ".");
var copy = await Command("docker", ["cp", id + ":" + screen, Path.Combine(output, "guest-screen-" + token + ".ppm")], output, "capture-monitor-screen", deadline.Token, requireSuccess: false);
copyExit = copy.ExitCode;
if (copyExit != 0) throw new InvalidOperationException("Optional monitor screenshot copy exited " + copyExit + ".");
}
catch (Exception exception) { error = exception.Message; Console.Error.WriteLine("Optional final monitor capture: " + error); }
finally { Save(Path.Combine(output, "monitor-capture.json"), new { token, monitorExit, copyExit, success = error is null, error, capturedUtc = DateTimeOffset.UtcNow }); }
}
static async Task<bool> Cleanup(string output)
{
var path = Path.Combine(output, "owned-resources.json");