fix(#670): self-healing recovery for installer-migration checksum drift (#675)

Editing the body of an already-released installer migration drifts its computed
checksum (it hashes plan.toString()). The integrity guard then hard-aborted
every prior install on upgrade with "applied migration checksum changed" — a
100% reproducible blocker (v1.3.0, all platforms).

Already-applied migrations are filtered out of `pending` and never re-run, so
a drifted checksum is functionally inert. ADR-0008 anticipates checksum-mismatch
state as something the install-state layer must handle gracefully (plan -> apply
-> recover/report), not abort on.

This supersedes the published-checksum allowlist merged in #674 (per-release
maintenance debt — every historical checksum hand-pinned, still throws for any
unregistered value) with a general, self-healing recovery:

- Replace the throwing guard with non-fatal `collectAppliedChecksumDrift`,
  surfaced on `plan.checksumDrift`.
- Reconcile drifted stored checksums durably on the next state write
  (`reconcileDriftedChecksums`), idempotently (no perpetual writes).
- Relocate the "shipped migration bodies are immutable" rule to a CI baseline
  test that locks every shipped migration's checksum and fails on body drift —
  where #615 should have been caught, instead of blocking users.

Removes #674's legacyChecksums field, per-migration checksum pins,
published-checksums.json fixture, and compat test.

Fixes #670

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Tom Boucher
2026-06-04 13:44:05 -04:00
committed by GitHub
parent cb09aed208
commit cdd78bd2aa
14 changed files with 279 additions and 226 deletions

View File

@@ -91,7 +91,6 @@ export function validateInstallerMigrationRecord(record: unknown, source?: strin
throw new Error(`migration record must declare destructive as a boolean: ${displaySource}`);
}
validateStringArray(rec, 'runtimes', displaySource);
validateStringArray(rec, 'legacyChecksums', displaySource);
requireStringArray(rec, 'scopes', displaySource);
if (typeof rec['plan'] !== 'function') {
throw new Error(`migration record must include a plan function: ${displaySource}`);

View File

@@ -208,27 +208,51 @@ function migrationChecksum(migration: MigrationRecord): string {
return `sha256:${sha256Text(JSON.stringify(serializable))}`;
}
function migrationLegacyChecksums(migration: MigrationRecord): string[] {
return Array.isArray(migration.legacyChecksums)
? migration.legacyChecksums.filter((checksum): checksum is string => typeof checksum === 'string' && checksum.length > 0)
: [];
// Rewrite the stored checksum of any already-applied entry whose id drifted, so the
// drift is reconciled durably and not re-detected on every subsequent run (issue #670).
// Returns the number of entries actually changed (so callers know whether a write is needed).
function reconcileDriftedChecksums(
appliedEntries: Array<Record<string, unknown>>,
checksumDrift: Array<{ id: string; currentChecksum: string }> | undefined
): number {
if (!Array.isArray(checksumDrift) || checksumDrift.length === 0) return 0;
const reconcile = new Map(checksumDrift.map((d) => [d.id, d.currentChecksum]));
let changed = 0;
for (let i = 0; i < appliedEntries.length; i++) {
const existing = appliedEntries[i];
if (existing && typeof existing.id === 'string' && reconcile.has(existing.id)) {
const next = reconcile.get(existing.id) as string;
if (existing.checksum !== next) {
appliedEntries[i] = { ...existing, checksum: next };
changed += 1;
}
}
}
return changed;
}
function migrationAcceptedChecksums(migration: MigrationRecord): Set<string> {
return new Set([migrationChecksum(migration), ...migrationLegacyChecksums(migration)]);
}
function assertAppliedMigrationChecksums(applied: Map<string, Record<string, unknown>>, migrations: MigrationRecord[]): void {
function collectAppliedChecksumDrift(
applied: Map<string, Record<string, unknown>>,
migrations: MigrationRecord[]
): Array<{ id: string; storedChecksum: string; currentChecksum: string }> {
const drift: Array<{ id: string; storedChecksum: string; currentChecksum: string }> = [];
for (const migration of migrations) {
const entry = applied.get(migration.id as string);
if (!entry || !entry.checksum) continue;
const accepted = migrationAcceptedChecksums(migration);
if (!accepted.has(entry.checksum as string)) {
throw new Error(
`applied migration checksum changed for ${migration.id as string}; create a new fix-forward migration id`
);
const currentChecksum = migrationChecksum(migration);
if (entry.checksum !== currentChecksum) {
// An already-applied migration is never re-run (it is filtered out of `pending`),
// so a checksum drift here is functionally inert. A prior release may have edited a
// shipped migration body (see issue #670). Surface it for reconciliation instead of
// hard-aborting the user's upgrade.
drift.push({
id: migration.id as string,
storedChecksum: entry.checksum as string,
currentChecksum,
});
}
}
return drift;
}
function migrationMatchesContext(migration: MigrationRecord, { runtime, scope }: { runtime: string | null; scope: string | null }): boolean {
@@ -461,6 +485,7 @@ interface MigrationPlan {
pendingMigrations: MigrationRecord[];
actions: PlannedAction[];
blocked: PlannedAction[];
checksumDrift: Array<{ id: string; storedChecksum: string; currentChecksum: string }>;
}
function planInstallerMigrations({
@@ -490,7 +515,7 @@ function planInstallerMigrations({
migrationMatchesContext(migration, { runtime, scope })
);
const applied = appliedMigrationEntries(state);
assertAppliedMigrationChecksums(applied, scopedMigrations);
const checksumDrift = collectAppliedChecksumDrift(applied, scopedMigrations);
const pending = scopedMigrations.filter((migration) => !applied.has(migration.id as string));
const actions: PlannedAction[] = [];
const blocked: PlannedAction[] = [];
@@ -578,6 +603,7 @@ function planInstallerMigrations({
pendingMigrations: pending,
actions,
blocked,
checksumDrift,
};
}
@@ -757,6 +783,7 @@ function applyInstallerMigrationPlan({
const state = readInstallState(configDir);
const applied = appliedMigrationIds(state);
const nextApplied = [...state.appliedMigrations];
reconcileDriftedChecksums(nextApplied, plan.checksumDrift);
const actionsByMigrationId = new Map<string, PlannedAction>();
for (const action of plan.actions) {
if (action.migrationId && !actionsByMigrationId.has(action.migrationId)) {
@@ -819,29 +846,36 @@ function markPendingMigrationsApplied({
plan: MigrationPlan;
now?: () => string;
}): string[] {
if (!plan || !Array.isArray(plan.pendingMigrationIds) || plan.pendingMigrationIds.length === 0) {
return [];
}
if (!plan) return [];
const hasPending = Array.isArray(plan.pendingMigrationIds) && plan.pendingMigrationIds.length > 0;
const hasDrift = Array.isArray(plan.checksumDrift) && plan.checksumDrift.length > 0;
if (!hasPending && !hasDrift) return [];
const appliedAt = now();
const state = readInstallState(configDir);
const applied = appliedMigrationIds(state);
const checksumsByMigrationId = new Map<string, string>();
for (const migration of plan.pendingMigrations || []) {
checksumsByMigrationId.set(migration.id as string, migrationChecksum(migration));
}
const nextApplied = [...state.appliedMigrations];
const reconciledCount = reconcileDriftedChecksums(nextApplied, plan.checksumDrift);
const newlyApplied: string[] = [];
for (const id of plan.pendingMigrationIds) {
if (applied.has(id)) continue;
nextApplied.push({
id,
appliedAt,
journal: null,
checksum: checksumsByMigrationId.get(id) || null,
});
newlyApplied.push(id);
if (hasPending) {
const checksumsByMigrationId = new Map<string, string>();
for (const migration of plan.pendingMigrations || []) {
checksumsByMigrationId.set(migration.id as string, migrationChecksum(migration));
}
for (const id of plan.pendingMigrationIds) {
if (applied.has(id)) continue;
nextApplied.push({
id,
appliedAt,
journal: null,
checksum: checksumsByMigrationId.get(id) || null,
});
newlyApplied.push(id);
}
}
if (newlyApplied.length > 0) {
if (newlyApplied.length > 0 || reconciledCount > 0) {
writeInstallState(configDir, {
schemaVersion: 1,
appliedMigrations: nextApplied,
@@ -933,8 +967,8 @@ export = {
acquireInstallMigrationLock,
applyInstallerMigrationPlan,
classifyArtifact,
computeInstallerMigrationChecksum: migrationChecksum,
discoverInstallerMigrations,
migrationChecksum,
planInstallerMigrations,
readInstallManifest,
readInstallState,

View File

@@ -171,8 +171,6 @@ interface InstallerMigration {
title: string;
description: string;
introducedIn: string;
checksum: string;
legacyChecksums?: string[];
scopes: string[];
destructive: boolean;
plan: (ctx: PlanContext) => BaselineAction[];
@@ -183,10 +181,6 @@ const migration: InstallerMigration = {
title: 'Record first-time installer migration baseline',
description: 'Classify existing install surfaces before destructive installer migrations run.',
introducedIn: '1.50.0',
checksum: 'sha256:4ec58d35b30dbf39cc56e3972146086d8d31861ecd800cf0b37a7aa94fe74c2a',
legacyChecksums: [
'sha256:34608ea4e2f4e1c53b069604892860e603600d8573cc6a5584e4194044b48e67',
],
scopes: ['global', 'local'],
destructive: false,
plan: ({ configDir, runtime, baselineScan, classifyArtifact }: PlanContext): BaselineAction[] => {

View File

@@ -31,8 +31,6 @@ interface InstallerMigration {
title: string;
description: string;
introducedIn: string;
checksum: string;
legacyChecksums?: string[];
scopes: string[];
destructive: boolean;
plan: (ctx: MigrationPlanContext) => MigrationAction[];
@@ -48,10 +46,6 @@ const migration: InstallerMigration = {
title: 'Remove manifest-managed legacy orphan hook files',
description: 'Remove legacy orphan hook files that are still manifest-managed.',
introducedIn: '1.50.0',
checksum: 'sha256:e492698748a2436a12a55f0940f539b9bf651d8ffcac6f60cd856a6dabd6788c',
legacyChecksums: [
'sha256:4488e38c127a5225b31016918bcbc85ba3fd3139291ad407b94e76c03c0b89d3',
],
scopes: ['global', 'local'],
destructive: true,
// Retired generated hook files are removed only with manifest-managed

View File

@@ -48,8 +48,6 @@ interface InstallerMigration {
title: string;
description: string;
introducedIn: string;
checksum: string;
legacyChecksums?: string[];
runtimes: string[];
scopes: string[];
destructive: boolean;
@@ -112,10 +110,6 @@ const migration: InstallerMigration = {
title: 'Remove legacy Codex hooks.json GSD hook registrations',
description: 'Remove legacy Codex hooks.json GSD hook registrations after config.toml migration.',
introducedIn: '1.50.0',
checksum: 'sha256:5ce55294aa02f25758f604a569c899a6d2d060299189f5f447f68d8033157058',
legacyChecksums: [
'sha256:41f1545704dc72dfc3ab019207677a8652e389b200e8c450d52317df5bc198da',
],
runtimes: ['codex'],
scopes: ['global', 'local'],
destructive: true,

View File

@@ -48,7 +48,6 @@ interface InstallerMigration {
title: string;
description: string;
introducedIn: string;
checksum: string;
scopes: string[];
destructive: boolean;
plan(ctx: MigrationPlanContext): MigrationAction[];
@@ -81,7 +80,6 @@ const migration: InstallerMigration = {
'After the config dir rename from get-shit-done/ to gsd-core/ (#604), remove prior-manifest-managed files ' + // gsd-allow-legacy-name
'from the stale legacy directory during install (framework rollback restores them if install fails). User-added files are preserved.',
introducedIn: '1.2.0',
checksum: 'sha256:3a9f1d97f64097fb313203d19c6d93a187a38df61dd299afa5eef73e16124e95',
scopes: ['global', 'local'],
destructive: true,
plan(ctx: MigrationPlanContext): MigrationAction[] {