fix(ingest): refuse an external id that cannot be a stable identity

An external id is half of every ingest dedup key — (userId, source,
externalId), (userId, externalSource, externalId), (userId, type,
source, externalId). Re-posting the same triple is idempotent and
returns the existing row, which holds only while the id is stable
across client launches. A client that serialised an opaque platform
object with its default object description sent a per-allocation
memory address instead, so no sweep ever matched its own earlier row
and each one minted a fresh record: a live instance grew 23 phantom
medications in a day, none of which could collect a dose, because the
dose side resolved through the same rotating string.

Add one shared classifier for identifiers that provably cannot be an
identity — an angle-bracketed object description carrying a hex
pointer, a bare 0x address, and a blank value — and wire it at every
surface that accepts a client-supplied externalId.

Single-entry creates refuse through the schema, so the client gets the
standard 422 multi-issue envelope with a message naming the shape it
sent and what to send instead. Batch and bulk surfaces classify per
entry and report the offending row as skipped with reason
unstable_external_id, leaving the rest of the payload to land: one bad
row must not stop a sync. Every refusal carries pinned wide-event meta
(count, shape, surface) and never the id itself.

A structural guard freezes both routes into the floor: a request-side
externalId declaration either applies the field check or carries a
marker naming the file that checks it per entry, and the guard verifies
that file really does. The backup-restore payload is the one exemption,
with its reason recorded — it replays ids the server itself wrote.
This commit is contained in:
Marc-André Bombeck committed 2026-07-25 17:21:00 +02:00
1 parent ef9891fec5
commit 2ab66ab2e3
26 files changed
+1232 -64

No files matched your search

+42 -1
View File
@@ -23,6 +23,11 @@ import {
isPlausibleEntryInstant,
validateEntryInstant,
} from "@/lib/validations/entry-instant";
import {
classifyExternalId,
unstableExternalIdMeta,
type UnstableExternalIdShape,
} from "@/lib/validations/external-id";
import { encryptNote } from "@/lib/crypto/note-cipher";
import { recomputeUserMoodRollups } from "@/lib/rollups/mood-rollups";
import {
@@ -60,6 +65,10 @@ const measurementSchema = z
// export is idempotent rather than minting a duplicate set — mirrors the
// mood path. Absent → first-write-wins create with a NULL externalId
// (distinct in the unique key), which DOES duplicate on re-import.
// Stability is enforced per entry in the import loop, not at the
// field: a schema-level refusal would fail the whole file on one bad
// row.
// @external-id-checked-per-entry: src/app/api/import/route.ts
externalId: z.string().min(1).max(120).optional(),
})
.refine(
@@ -92,6 +101,10 @@ const moodEntrySchema = z
// present, the import upserts on `(userId, source, externalId)` so a
// re-import of the same export is idempotent rather than minting a
// duplicate; absent → the legacy first-write-wins create path.
// Stability is enforced per entry in the import loop, not at the
// field: a schema-level refusal would fail the whole file on one bad
// row.
// @external-id-checked-per-entry: src/app/api/import/route.ts
externalId: z.string().min(1).max(120).optional(),
})
.superRefine((entry, ctx) => {
@@ -170,6 +183,7 @@ export const POST = apiHandler(async (request: NextRequest) => {
const userId = user.id;
const data = parsed.data;
const stats = { measurements: 0, moodEntries: 0, skipped: 0 };
const unstableShapes: UnstableExternalIdShape[] = [];
let writeFailed = false;
// Import measurements
@@ -189,6 +203,17 @@ export const POST = apiHandler(async (request: NextRequest) => {
}> = [];
if (data.measurements?.length) {
for (const m of data.measurements) {
// The `(userId, type, source, externalId)` upsert key is only
// idempotent while the id is STABLE; an id that rotates between
// exports re-imports as a fresh row every time. Skipped per entry,
// like every other rejected row in this importer.
const unstable =
m.externalId === undefined ? null : classifyExternalId(m.externalId);
if (unstable) {
unstableShapes.push(unstable);
stats.skipped++;
continue;
}
try {
// `measuredAt` is already a `Date` (validateEntryInstant transform).
const measuredAt = m.measuredAt;
@@ -299,6 +324,15 @@ export const POST = apiHandler(async (request: NextRequest) => {
const fallbackOccurrences = new Map<string, number>();
const reservedFallbackInstants = new Set<number>();
for (const e of data.moodEntries) {
// Same stability floor as the measurement loop above — the mood
// upsert keys on `(userId, source, externalId)`.
const unstableMood =
e.externalId === undefined ? null : classifyExternalId(e.externalId);
if (unstableMood) {
unstableShapes.push(unstableMood);
stats.skipped++;
continue;
}
const identity = e.loggedAt ? null : fallbackMoodIdentity(e);
const occurrence =
identity === null ? 0 : (fallbackOccurrences.get(identity) ?? 0);
@@ -455,7 +489,14 @@ export const POST = apiHandler(async (request: NextRequest) => {
}
}
annotate({ meta: { import_stats: stats } });
annotate({
meta: {
import_stats: stats,
...(unstableShapes.length > 0
? unstableExternalIdMeta("import.json", unstableShapes)
: {}),
},
});
try {
await auditLog("import.upload", {