openclaw-aegis 1.5.0 → 1.5.1

package/README.md

@@ -23,7 +23,7 @@ It stands between your gateway and disaster — a tireless sentinel that detects
 
 | | |
 |---|---|
-| **Detects** | 10 health probes scan process, port, HTTP, config, WebSocket, TUN, memory, CPU, disk, and logs every 10 seconds |
+| **Detects** | 11 health probes scan process, port, HTTP, config, WebSocket, TUN, memory, CPU, disk, logs, and channel readiness every 10 seconds |
 | **Diagnoses** | 6 failure pattern matchers identify poison configs, stale PIDs, port conflicts, permission errors, corruption, and OOM kills |
 | **Heals** | L1 restart, L2 targeted repair, L3 deep repair (network, dependencies, safe mode, disk), config rollback — all automatic |
 | **Alerts** | 8 out-of-band providers (ntfy, Telegram, WhatsApp, Slack, Discord, Email, Pushover, webhook) that work even when the gateway is dead |
@@ -65,7 +65,7 @@ Your gateway is now protected.
 |---------|-------------|
 | `aegis init` | Interactive setup — walks you through everything |
 | `aegis init --auto` | Zero-config setup — detects gateway, sets defaults |
-| `aegis check` | Run all 10 probes, get a health verdict |
+| `aegis check` | Run all 11 probes, get a health verdict |
 | `aegis check --json` | Machine-readable output for scripts and monitoring |
 | `aegis status` | Live dashboard — every probe, color-coded |
 | `aegis test-alert` | Fire a test alert to all configured channels |
@@ -80,7 +80,7 @@ Your gateway is now protected.
 ```
 OpenClaw Gateway                  Aegis Sidecar
 ┌─────────────────────┐          ┌──────────────────────────────┐
-│                     │          │  Health Monitor (10 probes)  │
+│                     │          │  Health Monitor (11 probes)  │
 │  ~/.openclaw/       │◄────────►│  Config Guardian             │
 │    openclaw.json    │          │  Dead Man's Switch           │
 │    logs/            │          │  Recovery Orchestrator        │

package/dist/cli/index.js

@@ -263,7 +263,8 @@ var PROBE_WEIGHTS = {
   memory: 1,
   cpu: 1,
   disk: 1,
-  logTail: 1
+  logTail: 1,
+  channels: 1
 };
 var MAX_HEALTH_SCORE = Object.values(PROBE_WEIGHTS).reduce((a, b) => a + b, 0) * 2;
 var CRITICAL_CONFIG_KEYS = [
@@ -961,6 +962,110 @@ async function websocketProbe(target, port, timeoutMs = 5e3) {
   });
 }
 
+// src/health/probes/channels.ts
+var import_node_child_process6 = require("child_process");
+var import_node_util3 = require("util");
+var execFileAsync3 = (0, import_node_util3.promisify)(import_node_child_process6.execFile);
+async function channelsProbe(_target, timeoutMs = 1e4) {
+  const start = Date.now();
+  try {
+    const { stdout } = await execFileAsync3("openclaw", ["channels", "status", "--json"], {
+      timeout: timeoutMs
+    });
+    const jsonStart = stdout.indexOf("{");
+    if (jsonStart === -1) {
+      return {
+        name: "channels",
+        healthy: false,
+        score: 0,
+        message: "No JSON output from openclaw channels status",
+        latencyMs: Date.now() - start
+      };
+    }
+    const json = stdout.slice(jsonStart);
+    const data = JSON.parse(json);
+    if (!data.channels) {
+      return {
+        name: "channels",
+        healthy: false,
+        score: 0,
+        message: "No channels configured",
+        latencyMs: Date.now() - start
+      };
+    }
+    const issues = [];
+    let totalEnabled = 0;
+    let totalReady = 0;
+    for (const [channelName, accountData] of Object.entries(data.channels)) {
+      const accounts = Array.isArray(accountData) ? accountData : [accountData];
+      for (const account of accounts) {
+        if (!account.enabled && !account.configured) continue;
+        totalEnabled++;
+        const label = account.accountId ? `${channelName}/${account.accountId}` : channelName;
+        if (!account.running) {
+          issues.push(`${label}: not running`);
+          continue;
+        }
+        if ("connected" in account && !account.connected) {
+          issues.push(`${label}: running but not connected`);
+          continue;
+        }
+        if ("linked" in account && !account.linked) {
+          issues.push(`${label}: not linked`);
+          continue;
+        }
+        if (account.lastError) {
+          issues.push(`${label}: ${account.lastError}`);
+          continue;
+        }
+        totalReady++;
+      }
+    }
+    if (totalEnabled === 0) {
+      return {
+        name: "channels",
+        healthy: true,
+        score: 2,
+        message: "No channels enabled",
+        latencyMs: Date.now() - start
+      };
+    }
+    if (totalReady === totalEnabled) {
+      return {
+        name: "channels",
+        healthy: true,
+        score: 2,
+        message: `${totalReady}/${totalEnabled} channels ready`,
+        latencyMs: Date.now() - start
+      };
+    }
+    if (totalReady > 0) {
+      return {
+        name: "channels",
+        healthy: false,
+        score: 1,
+        message: `${totalReady}/${totalEnabled} channels ready. Issues: ${issues.join("; ")}`,
+        latencyMs: Date.now() - start
+      };
+    }
+    return {
+      name: "channels",
+      healthy: false,
+      score: 0,
+      message: `0/${totalEnabled} channels ready. Issues: ${issues.join("; ")}`,
+      latencyMs: Date.now() - start
+    };
+  } catch (err) {
+    return {
+      name: "channels",
+      healthy: false,
+      score: 0,
+      message: `Channel probe failed: ${err instanceof Error ? err.message : String(err)}`,
+      latencyMs: Date.now() - start
+    };
+  }
+}
+
 // src/health/monitor.ts
 var HealthMonitor = class extends import_node_events.EventEmitter {
   constructor(config) {
@@ -1030,7 +1135,8 @@ var HealthMonitor = class extends import_node_events.EventEmitter {
         "disk"
       ),
       withTimeout(() => logTailProbe(target, this.config.gateway.logPath), "logTail"),
-      withTimeout(() => websocketProbe(target, this.config.gateway.port, timeout), "websocket")
+      withTimeout(() => websocketProbe(target, this.config.gateway.port, timeout), "websocket"),
+      withTimeout(() => channelsProbe(target, timeout), "channels")
     ]);
     const probeResults = results.map((r, i) => {
       if (r.status === "fulfilled") return r.value;
@@ -1044,7 +1150,8 @@ var HealthMonitor = class extends import_node_events.EventEmitter {
         "cpu",
         "disk",
         "logTail",
-        "websocket"
+        "websocket",
+        "channels"
       ];
       return {
         name: names[i] ?? "unknown",
@@ -3379,8 +3486,8 @@ var DeadManSwitch = class extends import_node_events2.EventEmitter {
 
 // src/recovery/orchestrator.ts
 var import_node_events3 = require("events");
-var import_node_child_process7 = require("child_process");
-var import_node_util4 = require("util");
+var import_node_child_process8 = require("child_process");
+var import_node_util5 = require("util");
 var fs16 = __toESM(require("fs"));
 
 // src/recovery/circuit-breaker.ts
@@ -3427,9 +3534,9 @@ var CircuitBreaker = class {
 var fs15 = __toESM(require("fs"));
 var os7 = __toESM(require("os"));
 var path6 = __toESM(require("path"));
-var import_node_child_process6 = require("child_process");
-var import_node_util3 = require("util");
-var execFileAsync3 = (0, import_node_util3.promisify)(import_node_child_process6.execFile);
+var import_node_child_process7 = require("child_process");
+var import_node_util4 = require("util");
+var execFileAsync4 = (0, import_node_util4.promisify)(import_node_child_process7.execFile);
 function createL3Patterns() {
   return [
     // L3-1: Network Repair — DNS resolution, stale routes, TUN interface reset
@@ -3438,7 +3545,7 @@ function createL3Patterns() {
       name: "network-repair",
       async detect(_ctx) {
         try {
-          await execFileAsync3("getent", ["hosts", "localhost"], { timeout: 5e3 });
+          await execFileAsync4("getent", ["hosts", "localhost"], { timeout: 5e3 });
         } catch {
           return true;
         }
@@ -3466,7 +3573,7 @@ function createL3Patterns() {
         try {
           const cmd = os7.platform() === "darwin" ? "netstat" : "ip";
           const args = os7.platform() === "darwin" ? ["-rn"] : ["route", "show", "default"];
-          const { stdout } = await execFileAsync3(cmd, args, { timeout: 5e3 });
+          const { stdout } = await execFileAsync4(cmd, args, { timeout: 5e3 });
           if (!stdout.includes("default") && !stdout.includes("0.0.0.0")) return true;
         } catch {
           return true;
@@ -3478,9 +3585,9 @@ function createL3Patterns() {
         let fixed = false;
         try {
           if (os7.platform() === "darwin") {
-            await execFileAsync3("dscacheutil", ["-flushcache"], { timeout: 5e3 });
+            await execFileAsync4("dscacheutil", ["-flushcache"], { timeout: 5e3 });
           } else {
-            await execFileAsync3("systemd-resolve", ["--flush-caches"], { timeout: 5e3 });
+            await execFileAsync4("systemd-resolve", ["--flush-caches"], { timeout: 5e3 });
           }
           fixed = true;
         } catch {
@@ -3499,7 +3606,7 @@ function createL3Patterns() {
                   if (fs15.existsSync(operstatePath)) {
                     const state = fs15.readFileSync(operstatePath, "utf-8").trim();
                     if (state === "down") {
-                      await execFileAsync3("ip", ["link", "set", iface, "up"], { timeout: 5e3 });
+                      await execFileAsync4("ip", ["link", "set", iface, "up"], { timeout: 5e3 });
                       fixed = true;
                     }
                   }
@@ -3523,7 +3630,7 @@ function createL3Patterns() {
       name: "process-resurrection",
       async detect(_ctx) {
         try {
-          await execFileAsync3("which", ["openclaw"], { timeout: 5e3 });
+          await execFileAsync4("which", ["openclaw"], { timeout: 5e3 });
           return false;
         } catch {
           return true;
@@ -3532,11 +3639,11 @@ function createL3Patterns() {
       async fix(_ctx) {
         const start = Date.now();
         try {
-          await execFileAsync3("npm", ["install", "-g", "openclaw"], {
+          await execFileAsync4("npm", ["install", "-g", "openclaw"], {
             timeout: 12e4,
             env: { ...process.env, NODE_ENV: "production" }
           });
-          await execFileAsync3("which", ["openclaw"], { timeout: 5e3 });
+          await execFileAsync4("which", ["openclaw"], { timeout: 5e3 });
           return {
             level: "L3",
             action: "process-resurrection-reinstall",
@@ -3572,7 +3679,7 @@ function createL3Patterns() {
           }
         }
         try {
-          await execFileAsync3(
+          await execFileAsync4(
             "node",
             ["-e", "try { require('openclaw') } catch(e) { if (e.code === 'MODULE_NOT_FOUND') process.exit(1) }"],
             { timeout: 1e4, cwd: installDir }
@@ -3598,7 +3705,7 @@ function createL3Patterns() {
           if (fs15.existsSync(nodeModules)) {
             fs15.rmSync(nodeModules, { recursive: true, force: true });
           }
-          await execFileAsync3("npm", ["install", "--production"], {
+          await execFileAsync4("npm", ["install", "--production"], {
             timeout: 12e4,
             cwd: installDir
           });
@@ -3624,7 +3731,7 @@ function createL3Patterns() {
       name: "safe-mode-boot",
       async detect(ctx) {
         try {
-          const { stdout } = await execFileAsync3("pgrep", ["-f", "openclaw"], { timeout: 5e3 });
+          const { stdout } = await execFileAsync4("pgrep", ["-f", "openclaw"], { timeout: 5e3 });
           if (stdout.trim().length > 0) return false;
         } catch {
         }
@@ -3643,14 +3750,14 @@ function createL3Patterns() {
         const safeModeConfigPath = ctx.configPath + ".safemode";
         try {
           fs15.writeFileSync(safeModeConfigPath, JSON.stringify(safeModeConfig, null, 2));
-          await execFileAsync3(
+          await execFileAsync4(
             "openclaw",
             ["gateway", "start", "--config", safeModeConfigPath],
             { timeout: 3e4 }
           );
           await sleep(3e3);
           try {
-            await execFileAsync3("pgrep", ["-f", "openclaw"], { timeout: 5e3 });
+            await execFileAsync4("pgrep", ["-f", "openclaw"], { timeout: 5e3 });
           } catch {
             return {
               level: "L3",
@@ -3687,7 +3794,7 @@ function createL3Patterns() {
       async detect(ctx) {
         try {
           const configDir = path6.dirname(ctx.configPath);
-          const { stdout } = await execFileAsync3("df", ["-BM", configDir], { timeout: 5e3 });
+          const { stdout } = await execFileAsync4("df", ["-BM", configDir], { timeout: 5e3 });
           const lines = stdout.trim().split("\n");
           if (lines.length < 2) return false;
           const parts = lines[1].split(/\s+/);
@@ -3751,7 +3858,7 @@ function createL3Patterns() {
 }
 function resolveGatewayInstallDir() {
   try {
-    const output = (0, import_node_child_process6.execSync)("which openclaw", { encoding: "utf-8", timeout: 5e3 }).trim();
+    const output = (0, import_node_child_process7.execSync)("which openclaw", { encoding: "utf-8", timeout: 5e3 }).trim();
     const realPath = fs15.realpathSync(output);
     let dir = path6.dirname(realPath);
     for (let i = 0; i < 5; i++) {
@@ -3782,7 +3889,7 @@ function sleep(ms) {
 }
 
 // src/recovery/orchestrator.ts
-var execFileAsync4 = (0, import_node_util4.promisify)(import_node_child_process7.execFile);
+var execFileAsync5 = (0, import_node_util5.promisify)(import_node_child_process8.execFile);
 var RecoveryOrchestrator = class extends import_node_events3.EventEmitter {
   config;
   diagnosisEngine;
@@ -3868,7 +3975,7 @@ var RecoveryOrchestrator = class extends import_node_events3.EventEmitter {
       }
       const start = Date.now();
       try {
-        await execFileAsync4("openclaw", ["gateway", "restart"], { timeout: 3e4 });
+        await execFileAsync5("openclaw", ["gateway", "restart"], { timeout: 3e4 });
         actions.push({
           level: "L1",
           action: "restart",
@@ -3978,9 +4085,9 @@ function sleep2(ms) {
 
 // src/diagnosis/engine.ts
 var fs17 = __toESM(require("fs"));
-var import_node_child_process8 = require("child_process");
-var import_node_util5 = require("util");
-var execFileAsync5 = (0, import_node_util5.promisify)(import_node_child_process8.execFile);
+var import_node_child_process9 = require("child_process");
+var import_node_util6 = require("util");
+var execFileAsync6 = (0, import_node_util6.promisify)(import_node_child_process9.execFile);
 var DiagnosisEngine = class {
   patterns;
   constructor(backupManager) {
@@ -4064,7 +4171,7 @@ function createPatterns(backupManager) {
       name: "port-conflict",
       async detect(ctx) {
         try {
-          const { stdout } = await execFileAsync5("lsof", ["-i", `:${ctx.gatewayPort}`, "-t"]);
+          const { stdout } = await execFileAsync6("lsof", ["-i", `:${ctx.gatewayPort}`, "-t"]);
           const pids = stdout.trim().split("\n").filter(Boolean);
           if (pids.length === 0) return false;
           if (fs17.existsSync(ctx.pidFile)) {
@@ -4079,7 +4186,7 @@ function createPatterns(backupManager) {
       async fix(ctx) {
         const start = Date.now();
         try {
-          const { stdout } = await execFileAsync5("lsof", ["-i", `:${ctx.gatewayPort}`, "-t"]);
+          const { stdout } = await execFileAsync6("lsof", ["-i", `:${ctx.gatewayPort}`, "-t"]);
           const pids = stdout.trim().split("\n").filter(Boolean);
           return {
             level: "L2",
@@ -4158,7 +4265,7 @@ function createPatterns(backupManager) {
       name: "oom-kill",
       async detect(_ctx) {
         try {
-          const { stdout } = await execFileAsync5("dmesg", ["--time-format", "reltime"], {
+          const { stdout } = await execFileAsync6("dmesg", ["--time-format", "reltime"], {
             timeout: 5e3
           });
           return /oom_kill_process|Out of memory/.test(stdout);