Skip to content

armgit / mso

Public Imported from GitHub
0

Browser-based graphical shell and control plane for a Linux server you own — real terminal, file manager, live metrics and BYOK AI in one mobile-first workspace. Next.js 16 · React 19 · node-pty · Tailwind v4 · shadcn/ui. Public alpha, self-hosted.

fix(doctor): respect no-systemd and remote runtimes

Rahmanfa60f4329bc7
diff --git a/bin/mso-doctor.test.ts b/bin/mso-doctor.test.ts
index 904c603d..95c64d57 100644
--- a/bin/mso-doctor.test.ts
+++ b/bin/mso-doctor.test.ts
@@ -6,7 +6,7 @@ import { describe, expect, it } from "vitest";
const CLI = path.join(__dirname, "mso");
-function fixture() {
+function fixture(manager: "active" | "unavailable" | "inactive" = "active") {
const root = fs.mkdtempSync(path.join(os.tmpdir(), "mso-doctor-"));
const bin = path.join(root, "bin");
const envFile = path.join(root, ".env.local");
@@ -19,6 +19,9 @@ function fixture() {
fs.writeFileSync(store, JSON.stringify({ approved: {}, pending: { [device]: { label: "mso cli", firstSeen: 1, lastSeen: 1, ip: "127.0.0.1", attempts: 1 } } }));
fs.writeFileSync(path.join(bin, "curl"), `#!/bin/sh
case "$*" in
+ *api/health*)
+ [ "\${FAKE_HEALTH_DOWN:-0}" != 1 ] || exit 7
+ if [ "\${FAKE_HEALTH_OTHER:-0}" = 1 ]; then body='{"status":"ok","service":"other"}'; else body='{"status":"ok","service":"mso"}'; fi ;;
*api/auth/login*) body='{"success":true}' ;;
*api/auth/me*) body='{"authenticated":true,"role":"owner"}' ;;
*) body='{"status":"ok","service":"mso"}' ;;
@@ -26,6 +29,14 @@ esac
case "$*" in *'-w '*) printf '%s\n200' "$body" ;; *) printf '%s' "$body" ;; esac
`, { mode: 0o700 });
fs.writeFileSync(path.join(bin, "systemctl"), `#!/bin/sh
+printf '%s\n' "$*" >> '${root}/systemctl-calls.log'
+if [ '${manager}' = unavailable ]; then
+ printf '%s\n' 'System has not been booted with systemd as init system (PID 1)' >&2
+ exit 1
+fi
+if [ '${manager}' = inactive ]; then
+ case "$*" in *is-active*) exit 3 ;; esac
+fi
case "$*" in
*'show -p WorkingDirectory --value mso.service'*) printf '%s\n' '${path.dirname(CLI)}' ;;
*'show -p Environment --value mso.service'*) printf 'PORT=4005\n' ;;
@@ -64,4 +75,47 @@ describe("mso doctor", () => {
expect(parsed.pending[fx.device]).toBeUndefined();
} finally { fs.rmSync(fx.root, { recursive: true, force: true }); }
});
+ it("accepts healthy no-systemd runtime without claiming a system service or exposing probe stderr", () => {
+ const fx = fixture("unavailable");
+ try {
+ const result = spawnSync(CLI, ["doctor", "--fix"], { encoding: "utf8", env: fx.env });
+ expect(result.status).toBe(0);
+ expect(result.stdout).toContain("systemd manager unavailable");
+ expect(result.stdout).not.toContain("FAIL service unit");
+ expect(result.stderr).not.toContain("System has not been booted");
+ const calls = fs.readFileSync(path.join(fx.root, "systemctl-calls.log"), "utf8");
+ expect(calls).not.toMatch(/(?:^|\s)(?:start|restart|enable)(?:\s|$)/);
+ } finally { fs.rmSync(fx.root, { recursive: true, force: true }); }
+ });
+
+ it("still reports an inactive service when a real systemd manager is available", () => {
+ const fx = fixture("inactive");
+ try {
+ const result = spawnSync(CLI, ["doctor"], { encoding: "utf8", env: fx.env });
+ expect(result.status).toBe(1);
+ expect(result.stdout).toContain("FAIL service unit");
+ } finally { fs.rmSync(fx.root, { recursive: true, force: true }); }
+ });
+
+ it("does not inspect this host's service manager for a remote HTTPS base", () => {
+ const fx = fixture("unavailable");
+ try {
+ const result = spawnSync(CLI, ["--base", "https://mso.example.test", "doctor"], { encoding: "utf8", env: fx.env });
+ expect(result.status).toBe(0);
+ expect(result.stdout).toContain("service unit (skipped: --base is remote)");
+ expect(fs.existsSync(path.join(fx.root, "systemctl-calls.log"))).toBe(false);
+ } finally { fs.rmSync(fx.root, { recursive: true, force: true }); }
+ });
+
+ it.each(["FAKE_HEALTH_DOWN", "FAKE_HEALTH_OTHER"])("fails closed for an unhealthy no-systemd runtime: %s", (flag) => {
+ const fx = fixture("unavailable");
+ try {
+ const result = spawnSync(CLI, ["doctor", "--fix"], { encoding: "utf8", env: { ...fx.env, [flag]: "1" } });
+ expect(result.status).toBe(1);
+ expect(result.stdout).toContain("FAIL reachable");
+ expect(result.stdout).toContain("mso web --local --print");
+ expect(result.stdout).not.toContain("FAIL service unit");
+ } finally { fs.rmSync(fx.root, { recursive: true, force: true }); }
+ });
+
});
diff --git a/docs/CHANGELOG.md b/docs/CHANGELOG.md
index 1abfcb54..779111ba 100644
--- a/docs/CHANGELOG.md
+++ b/docs/CHANGELOG.md
@@ -12,6 +12,7 @@ this is the *what*, and it is what Settings → About shows as “What's new”.
**Fixed**
+- `doctor` respect no-systemd and remote runtimes
- `hosted` restore updates and Hermes runtime
- `update` recover no-systemd container installs
- `installer` build node-pty reliably on Codespaces
diff --git a/docs/INSTALL.md b/docs/INSTALL.md
index 1756ca32..e836aa82 100644
--- a/docs/INSTALL.md
+++ b/docs/INSTALL.md
@@ -620,6 +620,28 @@ restore those fallbacks. `mso service start` and `mso service restart` take the
checkout lock and refuse while an offline update/deploy is mutating `.next`; they also refuse when the
installed service belongs to another checkout.
+### No-systemd and hosted workspaces
+
+The presence of `systemctl` does not mean the host runs systemd. `mso doctor` checks
+manager availability before diagnosing a system service; containers with a healthy
+MSO runtime are not failures merely because PID 1 is tini or another supervisor.
+The health check requires an actual MSO response, not an arbitrary HTTP 200. With
+`--base` pointing at a remote server, doctor does not inspect or start local units.
+
+Use `mso web --local --print` to recover an installed, built loopback runtime without
+publishing it. `mso update` remains the update path; `mso service` and `mso deploy`
+are for installations actually controlled by the corresponding systemd unit.
+A detached process surviving a shell exit is not proof of restart persistence: wire
+the local startup command into the platform's supported startup configuration and
+verify a real workspace/container restart before claiming that guarantee.
+
+Cursor's [environment setup](https://cursor.com/docs/cloud-agent/setup) separates
+`install` (disk preparation) from `start`/`terminals` (per-run processes). Use the
+existing environment's startup configuration rather than modifying Cursor's private
+supervisor. Editor port forwarding is not by itself a verified public HTTPS origin.
+Only register a replacement gateway after its health identity and authenticated MCP
+work; keep the existing provider until that cutover is verified. See [Gateway](./GATEWAY.md).
+
### Developer release
After code/docs changes and verification:
diff --git a/docs/PROGRESS.md b/docs/PROGRESS.md
index 3a9c5849..3943fe0d 100644
--- a/docs/PROGRESS.md
+++ b/docs/PROGRESS.md
@@ -1,3 +1,7 @@
+## 2026-09-17 — Doctor respects no-systemd and remote runtime boundaries
+
+A live hosted/container audit reproduced a false `mso.service not active` failure while the loopback runtime, public HTTPS and authenticated CLI were healthy. Doctor now probes actual systemd manager availability before diagnosing its service and never inspects this machine's units for a remote `--base`. No-systemd hosts continue through the normal health/auth checks without suppressing real failures: health must be JSON identifying a healthy MSO service, and local probes bypass outbound proxy variables. `--fix` never creates a tunnel, adopts an external supervisor, or claims boot persistence. Added regressions for unavailable managers, inactive real services, remote bases, failed health and unrelated HTTP 200 responses; documented the hosted startup and verified-public-origin boundaries. This changes diagnosis only; no runtime, bind, provider, Node version or existing hosted Hermes/update behavior is replaced.
+
## 2026-09-17 — Gateway core becomes deployment/provider/supervisor agnostic
Refactored the gateway reliability boundary without removing the existing Cloudflare lifecycle or process-ownership protections. The new read-only classifier separates local, public, provider and process health from ownership/supervisor state and reports `managed-running`, `external-running`, `degraded`, `recovering`, `stopped` or `unknown`. A configured public origin is healthy only when its structured MSO health identity matches the selected local runtime, including `buildSha` when present; this fixes the real case where a healthy externally supervised public route was previously displayed as stopped. Added `mso gateway status --json`, capability-based provider metadata, external duplicate-start protection, and provider-neutral non-mutating doctor diagnostics. Cloudflare remains the current managed/default adapter; external reverse proxies/tunnels are detected but never adopted, stopped or restarted. Existing PID/start-ticks/executable/argv/runtime-instance, atomic private state, update locks and recovery markers remain authoritative. No generic `gateway supervise` daemon was added because the current external-supervisor model already covers systemd/s6/container/Kubernetes/PaaS ownership without duplicating supervisor semantics. Added provider-neutral regression coverage and a dedicated `docs/GATEWAY.md` architecture/operations reference.
diff --git a/scripts/cli/commands-host.sh b/scripts/cli/commands-host.sh
index 2c922d73..3d155572 100755
--- a/scripts/cli/commands-host.sh
+++ b/scripts/cli/commands-host.sh
@@ -114,7 +114,15 @@ case "$cmd" in
fails=$((fails+1))
fi
- if ! service_manager_read is-active --quiet mso.service 2>/dev/null; then
+ local_runtime=0
+ case "$B" in http://127.*:*|http://localhost:*|http://\[::1\]:*) local_runtime=1 ;; esac
+ if [ "$local_runtime" = 0 ]; then
+ echo " -- service unit (skipped: --base is remote)"
+ elif ! service_manager_read show --property=Version --value >/dev/null 2>&1; then
+ # A systemctl binary is not proof that this environment runs systemd.
+ # Do not start/adopt an external supervisor; health below is authoritative.
+ echo " -- service unit (systemd manager unavailable; runtime health checked below)"
+ elif ! service_manager_read is-active --quiet mso.service 2>/dev/null; then
if [ "$fix" = 1 ] && service_manager_read show -p WorkingDirectory --value mso.service 2>/dev/null | grep -q .; then
if ( service_start_safe >/dev/null 2>&1 ); then fixed "service unit started"; else printf ' FAIL service unit — automatic start failed; run: mso service logs\n'; fails=$((fails+1)); fi
else
@@ -124,7 +132,13 @@ case "$cmd" in
else
echo " ok service unit"
fi
- chk "reachable" "curl -fsS --max-time 5 '$B/api/health'" "nothing answering at $B"
+ doctor_health_ok() {
+ local direct=()
+ [ "$local_runtime" = 0 ] || direct=(--noproxy '*')
+ curl "${direct[@]}" -fsS --max-time 5 "$B/api/health" \
+ | jq -e 'type == "object" and .status == "ok" and .service == "mso"' >/dev/null
+ }
+ chk "reachable" "doctor_health_ok" "no healthy MSO at $B; for local recovery run: mso web --local --print"
d=$(cli_device); device_ready=0
case "$B" in