josh/electric-cherry
1
0
Fork 0
Code Issues 18 Pull Requests Actions Packages Projects Releases Wiki Activity

Defer server file changes until guarded restart activation

Browse Source 
Persist beta, promotion, drift, and rollback payloads until occupancy and restart-capacity checks pass. Preserve rollback snapshots and campaign ordering, and allow held rollback campaigns to resume safely.

Fixes #28

Validation: 805 tests passed, Svelte checks clean, production build passed.
This commit is contained in:
josh
2026-09-27 23:06:16 -04:00
parent eb2a852fdc
commit fb48f64de1
36 changed files with 1634 additions and 421 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lib/server/provisioning/restarts.ts
+13 -2
View File
@@ -3,6 +3,7 @@ import { db } from '../db/index.js';
import { komodoInspectHealthy, komodoRestart, komodoRuntimeAction } from '../integrations/komodo.js';
import { probeServerStatus } from '../fleet/status-evidence.js';
import { deploymentStage, finishDeployment } from './history.js';
import { applyStagedFilesForOperation } from '../fleet/staged-files.js';
// Komodo queues restart work. Don't mistake the still-running old container
// for a completed restart when an API kick immediately follows the request.
@@ -64,16 +65,26 @@ export async function restartInRollout(server: string, options: { operationId: s
if (!db().prepare('SELECT 1 FROM server_deployments WHERE id = ? AND server_deleted_at IS NULL').get(operationId)) return 'Original server was deleted';
const reason = rolloutWaitReason(server, operationId);
if (reason) return reason;
db().prepare('UPDATE server_deployments SET submitted_at = ? WHERE id = ?').run(new Date().toISOString(), operationId);
db().prepare(`INSERT INTO restart_rollout (server, requested_at, operation_id) VALUES (?, ?, ?)
ON CONFLICT(server) DO UPDATE SET requested_at = excluded.requested_at,
checked_at = NULL, healthy_at = NULL, players = NULL, error = NULL, operation_id = excluded.operation_id`)
.run(server, new Date().toISOString(), operationId);
deploymentStage(operationId, options.action === 'start' ? 'Starting container' : 'Restarting container');
return null;
}).immediate();
if (waitReason) return { kind: 'queued', message: waitReason };
// Every gate, including rollout capacity, has cleared. No async work may
// intervene between applying these files and submitting the restart.
try {
applyStagedFilesForOperation(operationId, server);
} catch (err) {
const message = `File activation failed: ${(err as Error).message}`;
db().prepare('DELETE FROM restart_rollout WHERE server = ? AND operation_id = ?').run(server, operationId);
finishDeployment(operationId, { ok: false, message });
return { kind: 'failed', message };
}
db().prepare('UPDATE server_deployments SET submitted_at = ? WHERE id = ?').run(new Date().toISOString(), operationId);
deploymentStage(operationId, options.action === 'start' ? 'Starting container' : 'Restarting container');
requestsInFlight.set(server, operationId);
db().prepare(`UPDATE servers SET container_state = 'restarting', last_error = NULL, last_reply_snippet = NULL,
game_started_at = NULL, game_ended_at = NULL WHERE name = ?`).run(server);