Merge pull request 'feat: Zulip Gateway v3 — Production Resilience Rewrite' (#34) from feat/zulip-v3-resilience into main
This commit was merged in pull request #34.
This commit is contained in:
@@ -1,26 +1,76 @@
|
|||||||
|
/**
|
||||||
|
* PM2 Ecosystem Config — Zulip Gateway v3 (Resilience)
|
||||||
|
*
|
||||||
|
* Deploy: pm2 start /root/.pm2/ecosystem.config.cjs
|
||||||
|
* Status: pm2 status
|
||||||
|
* Logs: pm2 logs abiba-zulip
|
||||||
|
*/
|
||||||
|
|
||||||
module.exports = {
|
module.exports = {
|
||||||
apps: [
|
apps: [
|
||||||
{
|
{
|
||||||
|
// ── Router (main Zulip gateway) ──
|
||||||
name: "abiba-zulip",
|
name: "abiba-zulip",
|
||||||
script: "/usr/bin/pi",
|
script: "/bin/pi",
|
||||||
args: "--mode rpc --session-id zulip-service",
|
args: "--mode rpc --session-id zulip-service",
|
||||||
cwd: "/root",
|
cwd: "/root",
|
||||||
|
|
||||||
|
// Resilience hardening — up from pi defaults
|
||||||
|
max_restarts: 100, // Crash loops won't exhaust PM2 (was default 10)
|
||||||
|
min_uptime: "10s", // Must survive 10s to count as "alive"
|
||||||
|
max_memory_restart: "500M", // OOM protection — restart before swap thrash
|
||||||
|
restart_delay: 5000, // 5s cooldown between restarts
|
||||||
|
kill_timeout: 15000, // 15s SIGTERM grace before SIGKILL
|
||||||
|
listen_timeout: 30000, // 30s to bind health port
|
||||||
|
|
||||||
|
// Logging
|
||||||
|
log_date_format: "YYYY-MM-DD HH:mm:ss Z",
|
||||||
|
error_file: "/root/.pm2/logs/abiba-zulip-error.log",
|
||||||
|
out_file: "/root/.pm2/logs/abiba-zulip-out.log",
|
||||||
|
merge_logs: true,
|
||||||
|
log_type: "json",
|
||||||
|
|
||||||
|
// Process management
|
||||||
|
autorestart: true,
|
||||||
|
watch: false,
|
||||||
|
instances: 1,
|
||||||
|
exec_mode: "fork",
|
||||||
|
|
||||||
|
// Environment
|
||||||
env: {
|
env: {
|
||||||
ZULIP_ROLE: "router",
|
ZULIP_ROLE: "router",
|
||||||
ZULIP_EXTENSION_ACTIVE: "true",
|
ZULIP_SITE: "https://chat.sysloggh.net",
|
||||||
NODE_OPTIONS: "--max-old-space-size=512",
|
ZULIP_EMAIL: "abiba-bot@chat.sysloggh.net",
|
||||||
|
ZULIP_API_KEY: "cKTDMZAPW08dk3zl05sStzO7HRztzyn8",
|
||||||
|
AGENT_NAME: "abiba",
|
||||||
|
AGENT_OWNER_EMAIL: "jerome@sysloggh.com",
|
||||||
|
NODE_ENV: "production",
|
||||||
},
|
},
|
||||||
// Prevent rapid crash-looping: restart with backoff, limit retries
|
|
||||||
min_uptime: "30s",
|
|
||||||
max_restarts: 15,
|
|
||||||
restart_delay: 10000,
|
|
||||||
kill_timeout: 5000,
|
|
||||||
autorestart: true,
|
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
name: "abiba-telegram",
|
// ── Supervisor (external watchdog) ──
|
||||||
script: "/usr/bin/pitg",
|
name: "zulip-watchdog",
|
||||||
|
script: "/root/.pi/agent/extensions/zulip/watchdog.js",
|
||||||
cwd: "/root",
|
cwd: "/root",
|
||||||
|
|
||||||
|
max_restarts: 10,
|
||||||
|
min_uptime: "3s",
|
||||||
|
restart_delay: 3000,
|
||||||
|
kill_timeout: 5000,
|
||||||
|
|
||||||
|
log_date_format: "YYYY-MM-DD HH:mm:ss Z",
|
||||||
|
error_file: "/root/.pm2/logs/zulip-watchdog-error.log",
|
||||||
|
out_file: "/root/.pm2/logs/zulip-watchdog-out.log",
|
||||||
|
merge_logs: true,
|
||||||
|
|
||||||
|
autorestart: true,
|
||||||
|
watch: false,
|
||||||
|
instances: 1,
|
||||||
|
exec_mode: "fork",
|
||||||
|
|
||||||
|
env: {
|
||||||
|
NODE_ENV: "production",
|
||||||
|
},
|
||||||
},
|
},
|
||||||
],
|
],
|
||||||
};
|
};
|
||||||
|
|||||||
@@ -0,0 +1,11 @@
|
|||||||
|
{
|
||||||
|
"lastChangelogVersion": "0.80.6",
|
||||||
|
"defaultProvider": "syslog-harness",
|
||||||
|
"defaultModel": "syslog-auto",
|
||||||
|
"defaultThinkingLevel": "high",
|
||||||
|
"extensions": [
|
||||||
|
"+extensions/mcp/index.ts",
|
||||||
|
"+extensions/zulip/index.js"
|
||||||
|
],
|
||||||
|
"theme": "dark"
|
||||||
|
}
|
||||||
@@ -0,0 +1,84 @@
|
|||||||
|
/**
|
||||||
|
* Zulip Gateway Supervisor — external watchdog process.
|
||||||
|
*
|
||||||
|
* Monitors the router health endpoint every 30s. If 3 consecutive checks fail,
|
||||||
|
* restarts the abiba-zulip PM2 process gracefully.
|
||||||
|
*
|
||||||
|
* This is the pattern Hermes uses: an external supervisor that can recover
|
||||||
|
* the gateway even when the gateway process itself is hung (not just crashed).
|
||||||
|
*
|
||||||
|
* Deployed via PM2 as a separate process in ecosystem.config.cjs.
|
||||||
|
*/
|
||||||
|
|
||||||
|
const HEALTH_URL = "http://127.0.0.1:9200/health";
|
||||||
|
const CHECK_INTERVAL_MS = 30_000;
|
||||||
|
const MAX_FAILURES = 3;
|
||||||
|
const RESTART_GRACE_MS = 15_000;
|
||||||
|
|
||||||
|
let failures = 0;
|
||||||
|
|
||||||
|
async function check() {
|
||||||
|
try {
|
||||||
|
const res = await fetch(HEALTH_URL, {
|
||||||
|
signal: AbortSignal.timeout(5000),
|
||||||
|
});
|
||||||
|
|
||||||
|
if (res.ok) {
|
||||||
|
const data = await res.json();
|
||||||
|
|
||||||
|
if (data.status === "ok" && data.zulip?.connected) {
|
||||||
|
if (failures > 0) {
|
||||||
|
console.log(`[watchdog] Router recovered after ${failures} failure(s)`);
|
||||||
|
}
|
||||||
|
failures = 0;
|
||||||
|
// Silent health log every 10 checks (~5 min) for monitoring
|
||||||
|
if (Math.random() < 0.1) {
|
||||||
|
console.log(`[watchdog] Router healthy (uptime: ${Math.round(process.uptime())}s)`);
|
||||||
|
}
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
|
// Connected but degraded
|
||||||
|
console.warn(`[watchdog] Router degraded: status=${data.status}, connected=${data.zulip?.connected}`);
|
||||||
|
failures++;
|
||||||
|
} else {
|
||||||
|
console.warn(`[watchdog] Health check returned ${res.status}`);
|
||||||
|
failures++;
|
||||||
|
}
|
||||||
|
} catch (err) {
|
||||||
|
failures++;
|
||||||
|
console.warn(`[watchdog] Health check ${failures}/${MAX_FAILURES}: ${err.message}`);
|
||||||
|
}
|
||||||
|
|
||||||
|
if (failures >= MAX_FAILURES) {
|
||||||
|
console.error(`[watchdog] ${MAX_FAILURES} consecutive failures — restarting abiba-zulip`);
|
||||||
|
|
||||||
|
const { execSync } = await import("node:child_process");
|
||||||
|
try {
|
||||||
|
execSync("pm2 restart abiba-zulip", { timeout: 30000, encoding: "utf-8" });
|
||||||
|
console.log("[watchdog] Restart command sent successfully");
|
||||||
|
} catch (e) {
|
||||||
|
console.error(`[watchdog] Restart failed: ${e.message}`);
|
||||||
|
|
||||||
|
// Fallback: try resurrect if restart fails (process may be deleted)
|
||||||
|
try {
|
||||||
|
execSync("pm2 resurrect", { timeout: 30000 });
|
||||||
|
console.log("[watchdog] PM2 resurrected (fallback)");
|
||||||
|
} catch (e2) {
|
||||||
|
console.error(`[watchdog] Resurrect also failed: ${e2.message}`);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
failures = 0;
|
||||||
|
// Wait for restart to fully initialize before checking again
|
||||||
|
await new Promise((r) => setTimeout(r, RESTART_GRACE_MS));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
console.log("[watchdog] Zulip gateway supervisor started");
|
||||||
|
console.log(`[watchdog] Monitoring ${HEALTH_URL} every ${CHECK_INTERVAL_MS / 1000}s`);
|
||||||
|
console.log(`[watchdog] Max failures before restart: ${MAX_FAILURES}`);
|
||||||
|
|
||||||
|
// Immediate first check, then periodic
|
||||||
|
check();
|
||||||
|
setInterval(check, CHECK_INTERVAL_MS);
|
||||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user