fix: keep running containers until stack pull/build succeeds (#1657)

* fix: keep running containers until stack pull/build succeeds Acquire images before reconcile, capture a recovery generation for compensation, and only remove classified orphans after handoff. * fix: address recovery audit blockers for safe stack updates Retire abandoned and expired recovery artifacts, probe compensated runtimes before reporting rollback success, preserve local Docker when deleting a node, validate the exact Compose invocation before capture, and repair updateStack return-contract fixtures. * fix: resolve ESLint errors blocking CI on this branch Unused-import and unused-variable errors left over from the stack deletion refactor: MeshService in stacks.ts (its opt-out cascade moved into DeployedStackDeletionService), a redundant pruneVolumes destructure in deleteDeployedStack (the real one is re-derived from the same input object inside runDeletionBody), and an unused beforeAll import in a Docker-integration test stub. Also scopes the webhook pull-action case body in a block to satisfy no-case-declarations; purely syntactic, no behavior change. * fix: harden recovery probe, cleanup retry, and failed-pull Docker test Reject absent or unhealthy expected replicas before reporting rollback success, keep cleanup records until artifacts are actually removed, fail closed when a mesh override cannot be generated, and assert a real failed pull leaves the original container running. * fix: verify recovery probe image identity and stack-scoped override paths Reject recovered runtimes that use the wrong image or leave scale-zero services running, and confine tombstone override deletion to the intent stack directory so forged cross-stack paths cannot be swept. * test: batch notification cap fixtures in a SQLite transaction Unbatched 1200-row inserts were timing out at the default 30s under CI load even though the same assertions pass in under 2s when green.
2026-08-19 06:46:23 +00:00 · 2026-07-21 12:18:01 -04:00
parent b1decbb32a
commit 3f1f15a6f4
41 changed files with 3087 additions and 244 deletions
@@ -0,0 +1,94 @@
+/**
+ * Thin Compose project context for safe full-stack updates.
+ *
+ * Wraps the current authored compose argument path and atomic file backup/restore.
+ * When a richer shared Compose project context lands, migrate callers to that type;
+ * this module must not become a competing full-manifest resolver.
+ */
+import path from 'path';
+import { randomUUID } from 'crypto';
+import { ComposeService } from './ComposeService';
+import { FileSystemService } from './FileSystemService';
+import { buildEffectiveServiceModel } from './effectiveServiceModel';
+import { getErrorMessage } from '../utils/errors';
+
+export type ImageReferenceKind = 'moving_tag' | 'digest_pinned' | 'none';
+
+const DIGEST_PIN_PATTERN = /@sha256:[a-f0-9]{64}$/i;
+
+export function classifyReferenceKind(declaredImageRef: string | null): ImageReferenceKind {
+  if (!declaredImageRef) return 'none';
+  if (DIGEST_PIN_PATTERN.test(declaredImageRef)) return 'digest_pinned';
+  return 'moving_tag';
+}
+
+async function requireRenderableModel(nodeId: number, stackName: string) {
+  const model = await buildEffectiveServiceModel(nodeId, stackName);
+  if (!model.renderable) {
+    throw new Error(model.error || 'Effective Compose model failed to render');
+  }
+  return model;
+}
+
+export interface ComposeProjectContext {
+  readonly nodeId: number;
+  readonly stackName: string;
+  readonly stackDir: string;
+  backupSlotId: string | null;
+  toComposeArgs(action: string[]): Promise<string[]>;
+  validateForMutation(): Promise<void>;
+  backupFromContext(operation: 'update' | 'deployment'): Promise<string>;
+  restoreFromContext(): Promise<void>;
+  resolveServiceImageMap(): Promise<Map<string, string | null>>;
+}
+
+class AuthoredComposeProjectContext implements ComposeProjectContext {
+  backupSlotId: string | null = null;
+
+  constructor(
+    readonly nodeId: number,
+    readonly stackName: string,
+    readonly stackDir: string,
+  ) {}
+
+  async toComposeArgs(action: string[]): Promise<string[]> {
+    return ComposeService.getInstance(this.nodeId).buildAuthoredComposeArgs(this.stackName, action);
+  }
+
+  async validateForMutation(): Promise<void> {
+    await ComposeService.getInstance(this.nodeId).validateStackForMutation(this.stackName);
+    await requireRenderableModel(this.nodeId, this.stackName);
+  }
+
+  async backupFromContext(_operation: 'update' | 'deployment'): Promise<string> {
+    await FileSystemService.getInstance(this.nodeId).backupStackFiles(this.stackName);
+    const slotId = randomUUID();
+    this.backupSlotId = slotId;
+    return slotId;
+  }
+
+  async restoreFromContext(): Promise<void> {
+    await FileSystemService.getInstance(this.nodeId).restoreStackFiles(this.stackName);
+  }
+
+  async resolveServiceImageMap(): Promise<Map<string, string | null>> {
+    const model = await requireRenderableModel(this.nodeId, this.stackName);
+    const map = new Map<string, string | null>();
+    for (const svc of model.services) {
+      map.set(svc.name, svc.declaredImage);
+    }
+    return map;
+  }
+}
+
+export async function resolveComposeProjectContext(
+  nodeId: number,
+  stackName: string,
+): Promise<ComposeProjectContext> {
+  const stackDir = path.join(FileSystemService.getInstance(nodeId).getBaseDir(), stackName);
+  return new AuthoredComposeProjectContext(nodeId, stackName, stackDir);
+}
+
+export function describeContextError(error: unknown): string {
+  return getErrorMessage(error, 'Compose project context failed');
+}