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

Let agents idle for updates required by creation cancellation

Browse Source
This commit is contained in:
josh
2026-10-04 18:14:11 -04:00
parent 176b7dd86b
commit fae7775c72
5 changed files with 65 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lib/server/hosts/index.ts
+7
View File
@@ -319,6 +319,13 @@ export function queueHostOperation(hostId: string, kind: string, payload: Record
export function pendingHostOperations(hostId: string): HostOperation[] {
const host = requireHost(hostId);
if (host.mode === 'disabled' || !host.connected) return [];
// Older agents hold activity.lock across the entire delivered batch, including
// observations. Filtering only the unsupported cleanup can keep the updater
// busy indefinitely. Drain the old batch by withholding ALL further work;
// heartbeats and receipts still flow, and the new capability releases this hold.
// This must live in the controller so the fix also works before an agent update.
if (!host.inventory.capabilities?.includes('instance.cancel-create') && database().prepare(`SELECT 1 FROM ec_host_operations
WHERE host_id=? AND kind='instance.cancel-create' AND state IN ('pending','accepted','running','unknown') LIMIT 1`).get(hostId)) return [];
// Accepted/running/unknown commands keep the same immutable ID. The agent
// consults its durable journal before acknowledging or executing a replay.
return database().transaction(() => {
src/lib/server/provisioning/native.ts
+5 -2
View File
@@ -21,6 +21,7 @@ import { sha256Buffer } from '../fleet/files.js';
import type { StagedFileChange } from '../fleet/staged-files.js';
import type { LaunchPreview } from '../../deployment-plan.js';
import type { ProvisioningAction } from '../../provisioning.js';
import { hostAgentUpdatesEnabled } from '../../hosts.js';
import { cancelCreation, finishCreationCancellation } from './cancel-creation.js';
export interface NativeSelection { hostId: string; libraryId: string; image?: string; bindAddress?: string; publicAddress?: string; publicPort?: number }
@@ -282,8 +283,10 @@ async function processJob(job: Job, eligibility: (job: Job) => string | null) {
}
if (job.operation_id) {
const operation = getHostOperation(job.operation_id);
if (operation?.kind === 'instance.cancel-create' && operation.state === 'pending' && !host.inventory.capabilities?.includes('instance.cancel-create')) {
hold(job, 'Update the host agent to support creation cancellation. Creation is cancelled; cleanup and port release await the updated agent.'); return;
if (operation?.kind === 'instance.cancel-create' && !['completed', 'failed'].includes(operation.state) && !host.inventory.capabilities?.includes('instance.cancel-create')) {
hold(job, hostAgentUpdatesEnabled(host.inventory)
? 'Waiting for the host agent update. New command delivery is paused so its current batch can finish and the automatic updater can run. Cleanup resumes after the updated agent connects.'
: 'Update the host agent to support creation cancellation: rerun the current installer on this host. Automatic updates are not enabled. New command delivery is paused; cleanup and port release await the updated agent.'); return;
}
if (!operation || operation.state === 'unknown') { hold(job, 'Agent result is unknown. Reconciling the original operation; no replacement or repeated command will be sent.'); return; }
if (operation.state === 'failed') {