mirror of
https://github.com/Studio-Saelix/sencho.git
synced 2026-08-29 11:47:01 +00:00
5f1baa7522
* fix: harden deploy/update concurrency and node-targeting safety Release stabilization for deploy/update operational safety. Per-stack operation locking is now global. Background lifecycle paths (scheduler auto stop/down/start/backup/update, webhook execute, Git source auto-deploy, image auto-update, label bulk actions, fleet snapshot redeploy, and mesh redeploy) acquire the per-node, per-stack lock through a new StackOpLockService.runExclusive helper and skip rather than race a manual deploy/update/rollback/backup on the same stack and node. Skips surface honestly (a failed scheduled run, a recorded webhook failure, a per-stack batch result, or a thrown error) instead of a silent no-op. Update readiness and policy-bypass now run against the node captured when the dialog opened, not the live active node, so switching nodes while a dialog is open cannot retarget the update or the bypass retry. Rollback readiness no longer presents a moving-tag or unpinned image as a ready image revert. Restoring files does not revert a moving tag, so those stacks read as partial, and the rollback success message states that the compose and env files were restored. * fix: lock blueprint reconcile against manual ops and correct rollback wording Follow-up to the deploy/update safety hardening, closing two more gaps from a verification pass. BlueprintService.deployLocal and withdrawLocal called ComposeService directly, so blueprint reconciliation could race a manual deploy/update/rollback/backup on an owned stack. Both now run their compose lifecycle call through StackOpLockService.runExclusive and skip (recorded as a failed reconcile, retried on the next cycle) on conflict. The withdraw holds the lock across both the compose down and the directory delete so neither races a manual operation. The runtime rollback messages overstated recovery: a rollback restores the compose and env files and recreates containers, but does not revert an image behind a moving tag. The auto-rollback deploy-progress output, the recovery panel and chip, the failure toasts, and the manual rollback route message now state that the compose and env files were restored, with the matching OpenAPI example and atomic-deployments doc updated. * fix: acquire stack lock before blueprint deploy mutates compose and marker files Local blueprint deploy wrote the compose and marker files and ran the policy assert before acquiring the per-stack lock; the lock only wrapped the deploy itself. A reconcile could therefore rewrite an owned stack's files while a manual deploy/update/rollback/backup was running. The lock now wraps the whole critical section (create, write compose, write marker, policy assert, deploy), so on conflict nothing is written and the reconcile records a failed outcome. Adds a test asserting a deploy under a held lock records failed, writes no marker file, and leaves the manual lock untouched. * fix: make remote blueprint apply atomic under the receiving node's stack lock Remote blueprint deploy wrote the compose and marker files to the target node via separate HTTP calls and only locked on the final deploy, so the file writes could race a manual operation on that node. A node's operation lock is process-local and cannot be held by the hub across HTTP calls, so the locked create/write/deploy now runs on the receiving node. The locked critical section is extracted into BlueprintService.applyLocalUnderLock and exposed via POST /api/blueprints/apply-local. The hub posts the blueprint to that endpoint in one call; the receiving node runs create + write compose+marker + deploy under its own per-stack lock. Older nodes without the route answer 404 and fall back to the legacy multi-call flow. The endpoint is gated by paid tier and the same per-stack stack:edit and stack:deploy permissions as the PUT-compose + deploy it bundles, validates the stack name, compose size, and marker structure, and returns 409 on a lock conflict without writing anything. Adds tests for the atomic single-call path, the 404 legacy fallback, the 409 lock-conflict mapping, the route validation and permission paths, and the write-compose-then-marker-then-deploy ordering of the shared locked apply. * fix(deps): bump undici to 7.28.0 to clear high-severity advisory The frontend CI npm audit gate (--audit-level=high) failed on a transitive undici 7.25.0 (a dev-only dependency via jsdom): TLS certificate validation bypass (GHSA-vmh5-mc38-953g) and cross-user cache information disclosure (GHSA-pr7r-676h-xcf6). Bumping undici within jsdom's existing ^7.25.0 range to 7.28.0 clears the high-severity advisory and unblocks the frontend job. Lockfile only; no direct dependency or source change.
235 lines
8.9 KiB
TypeScript
235 lines
8.9 KiB
TypeScript
import { beforeAll, beforeEach, afterAll, describe, expect, it, vi } from 'vitest';
|
|
import request from 'supertest';
|
|
import jwt from 'jsonwebtoken';
|
|
import { setupTestDb, cleanupTestDb, TEST_USERNAME, TEST_JWT_SECRET } from './helpers/setupTestDb';
|
|
|
|
let mockFsStacks: string[] = [];
|
|
const deployStack = vi.fn();
|
|
const getContainersByStack = vi.fn();
|
|
const stopContainer = vi.fn();
|
|
const restartContainer = vi.fn();
|
|
const enforcePolicyPreDeploy = vi.fn();
|
|
const invalidateNodeCaches = vi.fn();
|
|
|
|
vi.mock('../services/FileSystemService', () => ({
|
|
FileSystemService: {
|
|
getInstance: vi.fn(() => ({
|
|
getStacks: vi.fn(async () => mockFsStacks),
|
|
})),
|
|
},
|
|
}));
|
|
|
|
vi.mock('../services/ComposeService', () => ({
|
|
ComposeService: {
|
|
getInstance: vi.fn(() => ({ deployStack })),
|
|
},
|
|
}));
|
|
|
|
vi.mock('../services/DockerController', () => ({
|
|
default: {
|
|
getInstance: vi.fn(() => ({
|
|
getContainersByStack,
|
|
stopContainer,
|
|
restartContainer,
|
|
})),
|
|
},
|
|
}));
|
|
|
|
vi.mock('../services/PolicyEnforcement', () => ({
|
|
enforcePolicyPreDeploy,
|
|
}));
|
|
|
|
vi.mock('../helpers/cacheInvalidation', () => ({
|
|
invalidateNodeCaches,
|
|
}));
|
|
|
|
let tmpDir: string;
|
|
let app: import('express').Express;
|
|
let authHeader: string;
|
|
let db: import('../services/DatabaseService').DatabaseService;
|
|
let LicenseService: typeof import('../services/LicenseService').LicenseService;
|
|
let activeBulkActions: typeof import('../routes/labels').activeBulkActions;
|
|
let StackOpLockService: typeof import('../services/StackOpLockService').StackOpLockService;
|
|
let labelCounter = 0;
|
|
|
|
beforeAll(async () => {
|
|
tmpDir = await setupTestDb();
|
|
({ app } = await import('../index'));
|
|
({ LicenseService } = await import('../services/LicenseService'));
|
|
({ activeBulkActions } = await import('../routes/labels'));
|
|
({ StackOpLockService } = await import('../services/StackOpLockService'));
|
|
const { DatabaseService } = await import('../services/DatabaseService');
|
|
db = DatabaseService.getInstance();
|
|
authHeader = `Bearer ${jwt.sign({ username: TEST_USERNAME }, TEST_JWT_SECRET, { expiresIn: '1m' })}`;
|
|
});
|
|
|
|
afterAll(() => cleanupTestDb(tmpDir));
|
|
|
|
beforeEach(() => {
|
|
vi.restoreAllMocks();
|
|
// restoreAllMocks only resets spies; bare vi.fn() mocks keep their call
|
|
// history across tests. Clear them all so each test sees a fresh slate
|
|
// before its `.not.toHaveBeenCalled()` assertions run.
|
|
vi.clearAllMocks();
|
|
vi.spyOn(LicenseService.getInstance(), 'getTier').mockReturnValue('paid');
|
|
mockFsStacks = ['alpha', 'beta'];
|
|
deployStack.mockResolvedValue(undefined);
|
|
getContainersByStack.mockResolvedValue([{ Id: 'container-1' }]);
|
|
stopContainer.mockResolvedValue(undefined);
|
|
restartContainer.mockResolvedValue(undefined);
|
|
enforcePolicyPreDeploy.mockResolvedValue({ ok: true });
|
|
activeBulkActions.clear();
|
|
StackOpLockService.resetForTests();
|
|
db.getDb().prepare('DELETE FROM stack_label_assignments').run();
|
|
db.getDb().prepare('DELETE FROM stack_labels').run();
|
|
});
|
|
|
|
async function createAssignedLabel(stacks: string[] = ['alpha']) {
|
|
const created = await request(app)
|
|
.post('/api/labels')
|
|
.set('Authorization', authHeader)
|
|
.send({ name: `bulk-${++labelCounter}`, color: 'teal' });
|
|
expect(created.status).toBe(201);
|
|
|
|
for (const stack of stacks) {
|
|
const assigned = await request(app)
|
|
.put(`/api/stacks/${stack}/labels`)
|
|
.set('Authorization', authHeader)
|
|
.send({ labelIds: [created.body.id] });
|
|
expect(assigned.status).toBe(200);
|
|
}
|
|
|
|
return created.body as { id: number; node_id: number; name: string; color: string };
|
|
}
|
|
|
|
describe('Stack Labels bulk actions', () => {
|
|
it('deploys every existing stack assigned to the label', async () => {
|
|
const label = await createAssignedLabel(['alpha']);
|
|
|
|
const res = await request(app)
|
|
.post(`/api/labels/${label.id}/action`)
|
|
.set('Authorization', authHeader)
|
|
.send({ action: 'deploy' });
|
|
|
|
expect(res.status).toBe(200);
|
|
expect(res.body.results).toEqual([{ stackName: 'alpha', success: true }]);
|
|
expect(enforcePolicyPreDeploy).toHaveBeenCalledWith('alpha', label.node_id, expect.any(Object));
|
|
expect(deployStack).toHaveBeenCalledWith('alpha', undefined, false);
|
|
expect(invalidateNodeCaches).toHaveBeenCalledWith(label.node_id);
|
|
});
|
|
|
|
it('reports partial Docker stop failures without aborting other stacks', async () => {
|
|
const label = await createAssignedLabel(['alpha', 'beta']);
|
|
getContainersByStack.mockImplementation(async (stackName: string) => {
|
|
if (stackName === 'beta') throw new Error('socket permission denied');
|
|
return [{ Id: `${stackName}-1` }];
|
|
});
|
|
|
|
const res = await request(app)
|
|
.post(`/api/labels/${label.id}/action`)
|
|
.set('Authorization', authHeader)
|
|
.send({ action: 'stop' });
|
|
|
|
expect(res.status).toBe(200);
|
|
expect(res.body.results).toEqual([
|
|
{ stackName: 'alpha', success: true },
|
|
{ stackName: 'beta', success: false, error: 'socket permission denied' },
|
|
]);
|
|
expect(stopContainer).toHaveBeenCalledWith('alpha-1');
|
|
expect(invalidateNodeCaches).toHaveBeenCalledWith(label.node_id);
|
|
});
|
|
|
|
it('rejects a second bulk action while the node lock is held', async () => {
|
|
const label = await createAssignedLabel(['alpha']);
|
|
activeBulkActions.add(`bulk:${label.node_id}`);
|
|
|
|
const res = await request(app)
|
|
.post(`/api/labels/${label.id}/action`)
|
|
.set('Authorization', authHeader)
|
|
.send({ action: 'restart' });
|
|
|
|
expect(res.status).toBe(429);
|
|
expect(res.body.error).toContain('already running');
|
|
expect(restartContainer).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('skips a stack whose per-stack lock is held by a manual operation', async () => {
|
|
const label = await createAssignedLabel(['alpha', 'beta']);
|
|
// A manual operation holds 'alpha'; the bulk deploy must not race it.
|
|
StackOpLockService.getInstance().tryAcquire(label.node_id, 'alpha', 'update', 'admin');
|
|
|
|
const res = await request(app)
|
|
.post(`/api/labels/${label.id}/action`)
|
|
.set('Authorization', authHeader)
|
|
.send({ action: 'deploy' });
|
|
|
|
expect(res.status).toBe(200);
|
|
const alpha = res.body.results.find((r: { stackName: string }) => r.stackName === 'alpha');
|
|
const beta = res.body.results.find((r: { stackName: string }) => r.stackName === 'beta');
|
|
expect(alpha).toMatchObject({ stackName: 'alpha', success: false });
|
|
expect(alpha.error).toContain('another operation (update) is already in progress');
|
|
expect(beta).toEqual({ stackName: 'beta', success: true });
|
|
// 'alpha' was skipped; only 'beta' reached ComposeService.
|
|
expect(deployStack).toHaveBeenCalledTimes(1);
|
|
expect(deployStack).toHaveBeenCalledWith('beta', undefined, false);
|
|
});
|
|
|
|
it('dry-run deploy runs the policy gate and reports blocked stacks honestly', async () => {
|
|
const label = await createAssignedLabel(['alpha']);
|
|
enforcePolicyPreDeploy.mockResolvedValue({
|
|
ok: false,
|
|
policy: { name: 'block-criticals', max_severity: 'high' },
|
|
violations: [{ image: 'nginx:latest', severity: 'critical' }],
|
|
});
|
|
|
|
const res = await request(app)
|
|
.post(`/api/labels/${label.id}/action`)
|
|
.set('Authorization', authHeader)
|
|
.send({ action: 'deploy', dryRun: true });
|
|
|
|
expect(res.status).toBe(200);
|
|
expect(res.body.results).toEqual([
|
|
expect.objectContaining({ stackName: 'alpha', success: false, dryRun: true }),
|
|
]);
|
|
expect(res.body.results[0].error).toContain('Policy "block-criticals" blocked deploy');
|
|
expect(deployStack).not.toHaveBeenCalled();
|
|
expect(invalidateNodeCaches).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('dry-run deploy reports success when the policy gate passes, without touching Docker', async () => {
|
|
const label = await createAssignedLabel(['alpha']);
|
|
enforcePolicyPreDeploy.mockResolvedValue({ ok: true });
|
|
|
|
const res = await request(app)
|
|
.post(`/api/labels/${label.id}/action`)
|
|
.set('Authorization', authHeader)
|
|
.send({ action: 'deploy', dryRun: true });
|
|
|
|
expect(res.status).toBe(200);
|
|
expect(res.body.results).toEqual([
|
|
{ stackName: 'alpha', success: true, dryRun: true },
|
|
]);
|
|
expect(enforcePolicyPreDeploy).toHaveBeenCalledWith('alpha', label.node_id, expect.any(Object));
|
|
expect(deployStack).not.toHaveBeenCalled();
|
|
expect(invalidateNodeCaches).not.toHaveBeenCalled();
|
|
});
|
|
|
|
it('dry-run stop reports per-stack success without dispatching real stops', async () => {
|
|
const label = await createAssignedLabel(['alpha', 'beta']);
|
|
|
|
const res = await request(app)
|
|
.post(`/api/labels/${label.id}/action`)
|
|
.set('Authorization', authHeader)
|
|
.send({ action: 'stop', dryRun: true });
|
|
|
|
expect(res.status).toBe(200);
|
|
expect(res.body.results).toEqual([
|
|
{ stackName: 'alpha', success: true, dryRun: true },
|
|
{ stackName: 'beta', success: true, dryRun: true },
|
|
]);
|
|
expect(getContainersByStack).not.toHaveBeenCalled();
|
|
expect(stopContainer).not.toHaveBeenCalled();
|
|
expect(invalidateNodeCaches).not.toHaveBeenCalled();
|
|
});
|
|
});
|