mosaicstack/stack
25
0
Fork 1
Code Issues 367 Pull Requests 13 Actions Packages Projects Releases 15 Wiki Activity

feat(discord): systemd user service with a supervised run; brakes exit 3 and are never retried (#1509)

Browse Source 
QUEUE row 17, MVP iteration 2. scripts/discord-service.sh renders and
installs mosaic-discord@<binding> from packages/discord/systemd/. The
unit's main process is `run --supervised`, which applies the new recover
policy first: a lock whose owner is gone is cleared and only the STOP
written for that is removed; an operator STOP or a held binding refuses
with exit 3, which RestartPreventExitStatus never retries. `recover` is
also a CLI verb. First cut used ExecStartPre and looped live, since systemd
honours the never-retry status only from the main process; replaced and
re-verified before any message traffic. Suite 40/40, 95 node tests.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
This commit is contained in:
jason.woltje
2026-09-13 14:39:11 -05:00
co-authored by Claude Fable 5.1
parent dc5902aafd
commit 436ba6ed6b
15 changed files with 630 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/discord/src/cli.mjs
+37 -7
View File
@@ -1,9 +1,10 @@
#!/usr/bin/env node
// Usage:
// mosaic-discord check <binding> [--config PATH] [--repo PATH]
// mosaic-discord run <binding> [--config PATH] [--repo PATH]
// mosaic-discord run <binding> [--config PATH] [--repo PATH] [--supervised]
// mosaic-discord stop <binding> [--config PATH]
// mosaic-discord unlock <binding> [--config PATH]
// mosaic-discord recover <binding> [--config PATH]
//
// <binding> names <dataRoot>/discord/<binding>.json. The repository wrapper
// is scripts/discord.sh.
@@ -23,8 +24,18 @@
// with unverifiable identity, or recorded in a file it cannot read. `run` never reclaims on its own, and a
// claim that finds STOP after publishing releases itself, so unlock cannot
// race a start. Remove STOP to run again.
// recover: the supervised pre-start. Refuses while STOP is present or the
// binding is held by a live or unverifiable process; clears a lock whose
// owner is gone the way unlock does, then removes the STOP it wrote for
// that, so the run that follows can claim. Never removes a STOP an operator
// wrote. `run --supervised` does the same first thing itself; the service
// unit (scripts/discord-service.sh) uses that form, because systemd only
// honours a never-retry exit status from the main process, not from a
// pre-start command.
//
// Exit codes: 0 ok; 1 operation failed; 2 invalid data or configuration; 4 usage.
// Exit codes: 0 ok; 1 operation failed; 2 invalid data or configuration;
// 3 refused by a brake (STOP present or the binding held; a supervisor must
// not retry); 4 usage.
import { existsSync, mkdirSync, mkdtempSync, writeFileSync, statSync, readdirSync } from "node:fs";
import { join, resolve } from "node:path";
@@ -36,17 +47,18 @@ import { createGateway, CONNECTOR_INTENTS } from "./gateway.mjs";
import { createEngine, buildPiArgs } from "./engine-pi.mjs";
import { assembleContext } from "./context.mjs";
import { createConnector } from "./connector.mjs";
import { ensureJournal, requestStop, stopRequested, readPid, stopTarget, writePid, clearPid, unlock } from "./journal.mjs";
import { ensureJournal, requestStop, stopRequested, readPid, stopTarget, writePid, clearPid, unlock, recover, BRAKE_EXIT } from "./journal.mjs";
const USAGE = [
"usage: mosaic-discord check <binding> [--config PATH] [--repo PATH]",
" mosaic-discord run <binding> [--config PATH] [--repo PATH]",
" mosaic-discord run <binding> [--config PATH] [--repo PATH] [--supervised]",
" mosaic-discord stop <binding> [--config PATH]",
" mosaic-discord unlock <binding> [--config PATH]",
" mosaic-discord recover <binding> [--config PATH]",
].join("\n");
function parse(argv) {
const opts = { command: null, binding: null, config: defaultConfigPath(), repo: process.cwd() };
const opts = { command: null, binding: null, config: defaultConfigPath(), repo: process.cwd(), supervised: false };
for (let i = 0; i < argv.length; i++) {
const a = argv[i];
if (a === "--config" || a === "--repo") {
@@ -54,14 +66,17 @@ function parse(argv) {
opts[a.slice(2)] = resolve(argv[++i]);
} else if (a === "--help" || a === "-h") {
opts.command = "help";
} else if (a === "--supervised") {
opts.supervised = true;
} else if (a.startsWith("--")) throw new DiscordError(`unknown argument: ${a}\n${USAGE}`, 4);
else if (opts.command === null) opts.command = a;
else if (opts.binding === null) opts.binding = a;
else throw new DiscordError(`unexpected argument: ${a}\n${USAGE}`, 4);
}
if (opts.command === "help") return opts;
if (!["check", "run", "stop", "unlock"].includes(opts.command)) throw new DiscordError(USAGE, 4);
if (!["check", "run", "stop", "unlock", "recover"].includes(opts.command)) throw new DiscordError(USAGE, 4);
if (opts.binding === null) throw new DiscordError(`${opts.command} needs a binding name\n${USAGE}`, 4);
if (opts.supervised && opts.command !== "run") throw new DiscordError(`--supervised applies to run only\n${USAGE}`, 4);
return opts;
}
@@ -136,7 +151,11 @@ async function run(opts) {
const { binding, contextFiles, pi, journalDir, sessionDir } = prepare(opts);
const token = readToken(binding);
ensureJournal(journalDir);
if (stopRequested(journalDir)) throw new DiscordError(`STOP is present in ${journalDir}; remove it to run`, 1);
if (opts.supervised) {
const outcome = recover(journalDir);
if (outcome === "cleared") warn("supervised start: run.lock left by a process that is gone was removed");
}
if (stopRequested(journalDir)) throw new DiscordError(`STOP is present in ${journalDir}; remove it to run`, BRAKE_EXIT);
writePid(journalDir, process.pid);
const cleanupPid = () => clearPid(journalDir, process.pid);
try {
@@ -242,6 +261,16 @@ function unlockCommand(opts) {
say("remove STOP to run again");
}
function recoverCommand(opts) {
const dataRoot = loadDataRoot(opts.config);
const binding = loadBinding(bindingPath(dataRoot, opts.binding));
const journalDir = bindingDataDir(dataRoot, binding.name);
ensureJournal(journalDir);
const outcome = recover(journalDir);
if (outcome === "cleared") say("run.lock left by a process that is gone was removed; STOP is absent; ready to run");
else say("no lock and no STOP; ready to run");
}
async function main() {
const opts = parse(process.argv.slice(2));
if (opts.command === "help") {
@@ -251,6 +280,7 @@ async function main() {
if (opts.command === "check") await check(opts);
else if (opts.command === "run") await run(opts);
else if (opts.command === "unlock") unlockCommand(opts);
else if (opts.command === "recover") recoverCommand(opts);
else stop(opts);
return opts.command === "run" ? null : 0;
}