mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-06 10:48:12 +02:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - The local heartbeat/runtime subsystem starts long-running local agent processes and records their run state. > - Operators sometimes need to rebuild and restart the Paperclip server while local agent processes are still alive. > - A normal restart should remain conservative, but a guarded production hot restart needs an explicit marker, startup reconciliation, and an inspectable report. > - The broader hot-restart PR is currently merge-conflicted, so this pull request lands the minimal server-side recovery path on current `master`. > - The benefit is that deploy operators can restart from a current branch without reverting production changes and without marking adopted live runs as `process_lost`. ## Linked Issues or Issue Description No public GitHub issue exists for this deploy-safety fix. Bug fix: - What happened: the current deployable `master` branch did not include the hot-restart marker CLI, startup adoption report path, or health version proof needed by guarded service restarts. - Expected behavior: a deploy operator can write a one-shot marker before restarting, the old server snapshots eligible running child processes, the new server reports adopted/finalized/lost runs, and adopted live runs are not reaped as `process_lost`. - Steps to reproduce: restart a server with running local child-process heartbeat runs without the marker/adoption path; startup orphan reaping has no adoption metadata and treats live detached children as lost. - Paperclip version/commit: fixed on top of `master` at `b606869a6`. - Deployment mode: production/local-service style deployments that rebuild and restart the primary `paperclip.service`. - Related PR: Refs #9628. This PR intentionally lands a smaller deploy-safe subset because #9628 is currently merge-conflicted. - Duplicate search: searched public PRs/issues for `hot restart` and `process_lost adoption`; #9628 is the directly related prior implementation. ## What Changed - Added `scripts/request-hot-restart.ts` to write a one-shot hot-restart intent marker under `PAPERCLIP_HOME`. - Added `server/src/services/hot-restart.ts` for intent/report path resolution, parsing, atomic writes, shutdown snapshots, and marker cleanup. - Wired server shutdown/startup so explicit hot restarts snapshot active runs, skip the normal heartbeat drain, reconcile live child processes on boot, and write `hot-restart-report.json`. - Preserved adopted run metadata so normal orphan reaping does not regress adopted live runs to `process_lost`. - Added `serverVersion` health proof alongside existing `version`, plus docs and regression coverage. ## Verification - `pnpm vitest run server/src/__tests__/health.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts` — 2 files passed, 100 tests passed. - `pnpm --filter @paperclipai/server typecheck` - `env PAPERCLIP_HOME="$PAPERCLIP_RUN_SCRATCH_DIR/hot-restart-cli-smoke" pnpm --filter @paperclipai/server exec tsx ../scripts/request-hot-restart.ts --server-pid 12345` - Branch ancestry checked after `git fetch origin master`: `origin/master` was `b606869a6`, and `HEAD..origin/master` was empty. ## Risks - Medium risk: process adoption depends on PID/PGID metadata and the service manager leaving child processes alive for the guarded restart. - Normal restarts remain conservative, but an incorrect marker PID intentionally falls back to graceful drain instead of adoption. - The PR is server-only and does not include the broader UI/experimental-setting work from #9628. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - OpenAI GPT-5 via Codex coding agent in a Paperclip execution workspace; tool use and shell/code execution enabled; context window not surfaced by this runtime. ## Checklist - [x] I have included a thinking path that traces from project context to this change - [x] I have specified the model used (with version and capability details) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] I have searched GitHub for duplicate or related PRs and linked them above - [x] I have either (a) linked existing issues with `Fixes: #` / `Closes #` / `Refs #` OR (b) described the issue in-PR following the relevant issue template - [x] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
84 lines
2.4 KiB
JavaScript
84 lines
2.4 KiB
JavaScript
#!/usr/bin/env -S node --import tsx
|
|
import {
|
|
resolveHotRestartIntentPath,
|
|
writeHotRestartIntent,
|
|
} from "../server/src/services/hot-restart.js";
|
|
|
|
function usage(): never {
|
|
console.error([
|
|
"Usage: tsx scripts/request-hot-restart.ts --server-pid <pid> [--drain-required]",
|
|
"",
|
|
"Writes a one-shot hot-restart intent marker under PAPERCLIP_HOME.",
|
|
].join("\n"));
|
|
process.exit(2);
|
|
}
|
|
|
|
function readArgs(argv: string[]) {
|
|
let serverPid: number | null = null;
|
|
let drainRequired = false;
|
|
|
|
for (let index = 0; index < argv.length; index += 1) {
|
|
const arg = argv[index];
|
|
if (arg === "--server-pid") {
|
|
const raw = argv[index + 1];
|
|
if (!raw) usage();
|
|
const parsed = Number(raw);
|
|
if (!Number.isInteger(parsed) || parsed <= 0) usage();
|
|
serverPid = parsed;
|
|
index += 1;
|
|
continue;
|
|
}
|
|
if (arg === "--drain-required") {
|
|
drainRequired = true;
|
|
continue;
|
|
}
|
|
if (arg === "--help" || arg === "-h") usage();
|
|
console.error(`Unknown argument: ${arg}`);
|
|
usage();
|
|
}
|
|
|
|
if (!serverPid) usage();
|
|
return { serverPid, drainRequired };
|
|
}
|
|
|
|
function normalizeApiBase(raw: string | undefined) {
|
|
const trimmed = raw?.trim();
|
|
if (!trimmed) return null;
|
|
return trimmed.replace(/\/+$/, "").replace(/\/api$/, "");
|
|
}
|
|
|
|
async function readPreviousServerVersion() {
|
|
const apiBase = normalizeApiBase(process.env.PAPERCLIP_API_URL);
|
|
if (!apiBase) return null;
|
|
try {
|
|
const response = await fetch(`${apiBase}/api/health`, {
|
|
signal: AbortSignal.timeout(2_000),
|
|
});
|
|
if (!response.ok) return null;
|
|
const body = await response.json() as Record<string, unknown>;
|
|
return typeof body.serverVersion === "string"
|
|
? body.serverVersion
|
|
: typeof body.version === "string"
|
|
? body.version
|
|
: null;
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
const { serverPid, drainRequired } = readArgs(process.argv.slice(2));
|
|
const intent = await writeHotRestartIntent({
|
|
previousServerPid: serverPid,
|
|
previousServerVersion: await readPreviousServerVersion(),
|
|
drainRequired,
|
|
requestedByRunId: process.env.PAPERCLIP_RUN_ID?.trim() || null,
|
|
});
|
|
|
|
console.log(JSON.stringify({
|
|
status: "hot_restart_intent_written",
|
|
intentPath: resolveHotRestartIntentPath(),
|
|
previousServerPid: intent.previousServerPid,
|
|
previousServerVersion: intent.previousServerVersion,
|
|
drainRequired: intent.drainRequired,
|
|
}, null, 2));
|