@remit/backend 0.0.23 → 0.0.24

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@remit/backend",
-  "version": "0.0.23",
+  "version": "0.0.24",
   "description": "Remit Mail Inspector API backend",
   "license": "MIT",
   "author": "",

package/src/service/semantic-capability.test.ts

@@ -14,6 +14,14 @@ const moduleNotFound = (): Error => {
 	return error;
 };
 
+const modelUnavailable = (): Error => {
+	const error = new Error(
+		'Embedding model "Xenova/paraphrase-multilingual-MiniLM-L12-v2" could not be loaded',
+	);
+	(error as Error & { code: string }).code = "ERR_EMBEDDING_MODEL_UNAVAILABLE";
+	return error;
+};
+
 describe("noteSemanticCapabilityAbsence", () => {
 	const ORIGINAL = process.env.DATA_BACKEND;
 	beforeEach(() => {
@@ -44,6 +52,16 @@ describe("noteSemanticCapabilityAbsence", () => {
 		assert.equal(noteSemanticCapabilityAbsence(error), true);
 	});
 
+	it("absorbs an embedding-model load failure (e2e-dev from source, HuggingFace fetch failed) and remembers it", () => {
+		for (const backend of ["sqlite", "postgres"]) {
+			_resetSemanticCapabilityForTest();
+			process.env.DATA_BACKEND = backend;
+			assert.equal(isSemanticSearchUnavailable(), false);
+			assert.equal(noteSemanticCapabilityAbsence(modelUnavailable()), true);
+			assert.equal(isSemanticSearchUnavailable(), true);
+		}
+	});
+
 	it("rethrows genuine query errors on the self-host SQL backends", () => {
 		process.env.DATA_BACKEND = "sqlite";
 		assert.equal(
@@ -57,8 +75,10 @@ describe("noteSemanticCapabilityAbsence", () => {
 	it("never engages on the AWS DynamoDB path — a missing module there is a broken deploy", () => {
 		delete process.env.DATA_BACKEND;
 		assert.equal(noteSemanticCapabilityAbsence(moduleNotFound()), false);
+		assert.equal(noteSemanticCapabilityAbsence(modelUnavailable()), false);
 		process.env.DATA_BACKEND = "dynamodb";
 		assert.equal(noteSemanticCapabilityAbsence(moduleNotFound()), false);
+		assert.equal(noteSemanticCapabilityAbsence(modelUnavailable()), false);
 		assert.equal(isSemanticSearchUnavailable(), false);
 	});
 });

package/src/service/semantic-capability.ts

@@ -13,6 +13,15 @@ import { isSelfHostSqlBackend } from "../data-backend.js";
  * fetches semantic hits alongside every literal search), retried by the client
  * on top.
  *
+ * The e2e-dev lane runs this backend from source rather than the container, so
+ * `@huggingface/transformers` IS present and the local embedder instead tries to
+ * lazily download the model from HuggingFace; a transient `fetch failed` there
+ * surfaces the same way. The search-service raises it as a typed
+ * `EmbeddingModelUnavailableError` (code ERR_EMBEDDING_MODEL_UNAVAILABLE), which
+ * this gate treats as the same capability absence — the model is not available,
+ * empty semantic results are the truthful answer, and the lane never depends on
+ * a live external download.
+ *
  * When the pipeline is genuinely absent, empty hits are the truthful answer:
  * the FTS/literal engine is the primary search surface on these profiles and is
  * unaffected. The absence is remembered so subsequent requests short-circuit.
@@ -29,6 +38,7 @@ const CAPABILITY_ABSENCE_CODES = new Set([
 	"ERR_MODULE_NOT_FOUND",
 	"MODULE_NOT_FOUND",
 	"ERR_DLOPEN_FAILED",
+	"ERR_EMBEDDING_MODEL_UNAVAILABLE",
 ]);
 
 let semanticUnavailable = false;