feat(doctor): audit supervisor config + docs

steipete · steipete · commit 01641b34ea62 · 2026-01-08T21:28:48.000+01:00
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,7 @@
 
 ## Unreleased
 
+- Doctor/Daemon: audit supervisor configs, recommend doctor from daemon status, and document user vs system services. (#?) — thanks @steipete
 - Daemon: align generated systemd unit with docs for network-online + restart delay. (#479) — thanks @azade-c
 - Outbound: default Telegram account selection for config-only tokens; remove heartbeat-specific accountId handling. (follow-up #516) — thanks @YuriNachos
 - Cron: allow Telegram delivery targets with topic/thread IDs (e.g. `-100…:topic:123`). (#474) — thanks @mitschabaude-bot
diff --git a/docs/gateway/doctor.md b/docs/gateway/doctor.md
@@ -51,6 +51,7 @@ cat ~/.clawdbot/clawdbot.json
 - Sandbox image repair when sandboxing is enabled.
 - Legacy service migration and extra gateway detection.
 - Gateway runtime checks (service installed but not running; cached launchd label).
+- Supervisor config audit (launchd/systemd/schtasks) with optional repair.
 - Gateway port collision diagnostics (default `18789`).
 - Security warnings for open DM policies.
 - systemd linger check on Linux.
@@ -143,17 +144,23 @@ workspace.
 Doctor runs a health check and offers to restart the gateway when it looks
 unhealthy.
 
-### 11) Gateway runtime + port diagnostics
+### 11) Supervisor config audit + repair
+Doctor checks the installed supervisor config (launchd/systemd/schtasks) for
+missing or outdated defaults (e.g., systemd network-online dependencies and
+restart delay). When it finds a mismatch, it recommends an update and can
+rewrite the service file/task to the current defaults.
+
+### 12) Gateway runtime + port diagnostics
 Doctor inspects the daemon runtime (PID, last exit status) and warns when the
 service is installed but not actually running. It also checks for port collisions
 on the gateway port (default `18789`) and reports likely causes (gateway already
 running, SSH tunnel).
 
-### 12) Config write + wizard metadata
+### 13) Config write + wizard metadata
 Doctor persists any config changes and stamps wizard metadata to record the
 doctor run.
 
-### 13) Workspace tips (backup + memory system)
+### 14) Workspace tips (backup + memory system)
 Doctor suggests a workspace memory system when missing and prints a backup tip
 if the workspace is not already under git.
 
diff --git a/docs/gateway/index.md b/docs/gateway/index.md
@@ -189,6 +189,14 @@ Bundled mac app:
   - `launchctl` only works if the LaunchAgent is installed; otherwise use `clawdbot daemon install` first.
 
 ## Supervision (systemd user unit)
+Clawdbot installs a **systemd user service** by default on Linux/WSL2. We
+recommend user services for single-user machines (simpler env, per-user config).
+Use a **system service** for multi-user or always-on servers (no lingering
+required, shared supervision).
+
+`clawdbot daemon install` writes the user unit. `clawdbot doctor` audits the
+unit and can update it to match the current recommended defaults.
+
 Create `~/.config/systemd/user/clawdbot-gateway.service`:
 ```
 [Unit]
diff --git a/docs/platforms/linux.md b/docs/platforms/linux.md
@@ -54,7 +54,11 @@ clawdbot doctor
 ```
 
 ## System control (systemd user unit)
-Full unit example lives in the [Gateway runbook](/gateway). Minimal setup:
+Clawdbot installs a systemd **user** service by default. Use a **system**
+service for shared or always-on servers. The full unit example and guidance
+live in the [Gateway runbook](/gateway).
+
+Minimal setup:
 
 Create `~/.config/systemd/user/clawdbot-gateway.service`:
 
diff --git a/src/cli/daemon-cli.ts b/src/cli/daemon-cli.ts
@@ -33,6 +33,8 @@ import { resolveGatewayLogPaths } from "../daemon/launchd.js";
 import { findLegacyGatewayServices } from "../daemon/legacy.js";
 import { resolveGatewayProgramArguments } from "../daemon/program-args.js";
 import { resolveGatewayService } from "../daemon/service.js";
+import type { ServiceConfigAudit } from "../daemon/service-audit.js";
+import { auditGatewayServiceConfig } from "../daemon/service-audit.js";
 import { callGateway } from "../gateway/call.js";
 import { resolveGatewayBindHost } from "../gateway/net.js";
 import {
@@ -89,6 +91,7 @@ type DaemonStatus = {
       cachedLabel?: boolean;
       missingUnit?: boolean;
     };
+    configAudit?: ServiceConfigAudit;
   };
   config?: {
     cli: ConfigSummary;
@@ -343,6 +346,10 @@ async function gatherDaemonStatus(opts: {
     service.readCommand(process.env).catch(() => null),
     service.readRuntime(process.env).catch(() => undefined),
   ]);
+  const configAudit = await auditGatewayServiceConfig({
+    env: process.env,
+    command,
+  });
 
   const serviceEnv = command?.environment ?? undefined;
   const mergedDaemonEnv = {
@@ -484,6 +491,7 @@ async function gatherDaemonStatus(opts: {
       notLoadedText: service.notLoadedText,
       command,
       runtime,
+      configAudit,
     },
     config: {
       cli: cliConfigSummary,
@@ -538,6 +546,16 @@ function printDaemonStatus(status: DaemonStatus, opts: { json: boolean }) {
   if (daemonEnvLines.length > 0) {
     defaultRuntime.log(`Daemon env: ${daemonEnvLines.join(" ")}`);
   }
+  if (service.configAudit?.issues.length) {
+    defaultRuntime.error(
+      "Service config looks out of date or non-standard.",
+    );
+    for (const issue of service.configAudit.issues) {
+      const detail = issue.detail ? ` (${issue.detail})` : "";
+      defaultRuntime.error(`Service config issue: ${issue.message}${detail}`);
+    }
+    defaultRuntime.error('Recommendation: run "clawdbot doctor".');
+  }
   if (status.config) {
     const cliCfg = `${status.config.cli.path}${status.config.cli.exists ? "" : " (missing)"}${status.config.cli.valid ? "" : " (invalid)"}`;
     defaultRuntime.log(`Config (cli): ${cliCfg}`);
diff --git a/src/commands/doctor-gateway-services.ts b/src/commands/doctor-gateway-services.ts
@@ -15,6 +15,7 @@ import {
 } from "../daemon/legacy.js";
 import { resolveGatewayProgramArguments } from "../daemon/program-args.js";
 import { resolveGatewayService } from "../daemon/service.js";
+import { auditGatewayServiceConfig } from "../daemon/service-audit.js";
 import type { RuntimeEnv } from "../runtime.js";
 import {
   DEFAULT_GATEWAY_DAEMON_RUNTIME,
@@ -23,6 +24,18 @@ import {
 } from "./daemon-runtime.js";
 import type { DoctorOptions, DoctorPrompter } from "./doctor-prompter.js";
 
+function detectGatewayRuntime(
+  programArguments: string[] | undefined,
+): GatewayDaemonRuntime {
+  const first = programArguments?.[0];
+  if (first) {
+    const base = path.basename(first).toLowerCase();
+    if (base === "bun" || base === "bun.exe") return "bun";
+    if (base === "node" || base === "node.exe") return "node";
+  }
+  return DEFAULT_GATEWAY_DAEMON_RUNTIME;
+}
+
 export async function maybeMigrateLegacyGatewayService(
   cfg: ClawdbotConfig,
   mode: "local" | "remote",
@@ -112,6 +125,83 @@ export async function maybeMigrateLegacyGatewayService(
   });
 }
 
+export async function maybeRepairGatewayServiceConfig(
+  cfg: ClawdbotConfig,
+  mode: "local" | "remote",
+  runtime: RuntimeEnv,
+  prompter: DoctorPrompter,
+) {
+  if (resolveIsNixMode(process.env)) {
+    note("Nix mode detected; skip service updates.", "Gateway");
+    return;
+  }
+
+  if (mode === "remote") {
+    note("Gateway mode is remote; skipped local service audit.", "Gateway");
+    return;
+  }
+
+  const service = resolveGatewayService();
+  const command = await service.readCommand(process.env).catch(() => null);
+  if (!command) return;
+
+  const audit = await auditGatewayServiceConfig({
+    env: process.env,
+    command,
+  });
+  if (audit.issues.length === 0) return;
+
+  note(
+    audit.issues
+      .map((issue) =>
+        issue.detail ? `- ${issue.message} (${issue.detail})` : `- ${issue.message}`,
+      )
+      .join("\n"),
+    "Gateway service config",
+  );
+
+  const repair = await prompter.confirmSkipInNonInteractive({
+    message: "Update gateway service config to the recommended defaults now?",
+    initialValue: true,
+  });
+  if (!repair) return;
+
+  const devMode =
+    process.argv[1]?.includes(`${path.sep}src${path.sep}`) &&
+    process.argv[1]?.endsWith(".ts");
+  const port = resolveGatewayPort(cfg, process.env);
+  const runtimeChoice = detectGatewayRuntime(command.programArguments);
+  const { programArguments, workingDirectory } =
+    await resolveGatewayProgramArguments({
+      port,
+      dev: devMode,
+      runtime: runtimeChoice,
+    });
+  const environment: Record<string, string | undefined> = {
+    PATH: process.env.PATH,
+    CLAWDBOT_PROFILE: process.env.CLAWDBOT_PROFILE,
+    CLAWDBOT_STATE_DIR: process.env.CLAWDBOT_STATE_DIR,
+    CLAWDBOT_CONFIG_PATH: process.env.CLAWDBOT_CONFIG_PATH,
+    CLAWDBOT_GATEWAY_PORT: String(port),
+    CLAWDBOT_GATEWAY_TOKEN:
+      cfg.gateway?.auth?.token ?? process.env.CLAWDBOT_GATEWAY_TOKEN,
+    CLAWDBOT_LAUNCHD_LABEL:
+      process.platform === "darwin" ? GATEWAY_LAUNCH_AGENT_LABEL : undefined,
+  };
+
+  try {
+    await service.install({
+      env: process.env,
+      stdout: process.stdout,
+      programArguments,
+      workingDirectory,
+      environment,
+    });
+  } catch (err) {
+    runtime.error(`Gateway service update failed: ${String(err)}`);
+  }
+}
+
 export async function maybeScanExtraGatewayServices(options: DoctorOptions) {
   const extraServices = await findExtraGatewayServices(process.env, {
     deep: options.deep,
diff --git a/src/commands/doctor.ts b/src/commands/doctor.ts
@@ -30,6 +30,7 @@ import {
 } from "./doctor-format.js";
 import {
   maybeMigrateLegacyGatewayService,
+  maybeRepairGatewayServiceConfig,
   maybeScanExtraGatewayServices,
 } from "./doctor-gateway-services.js";
 import {
@@ -157,6 +158,12 @@ export async function doctorCommand(
     prompter,
   );
   await maybeScanExtraGatewayServices(options);
+  await maybeRepairGatewayServiceConfig(
+    cfg,
+    resolveMode(cfg),
+    runtime,
+    prompter,
+  );
 
   await noteSecurityWarnings(cfg);
 
diff --git a/src/daemon/service-audit.ts b/src/daemon/service-audit.ts
diff --git a/src/daemon/systemd.ts b/src/daemon/systemd.ts
