fix(doctor): bound embedding provider health probe (#3364)

Co-Authored-By: Time Attakc <89218912+time-attack@users.noreply.github.com>

src/commands/doctor.ts

@@ -6102,7 +6102,10 @@ export async function buildChecks(
     } else {
       // Live embed test
       const start = Date.now();
-      const vec = await embedOne('gbrain doctor embedding smoke test');
+      // Doctor is itself the provider-health circuit breaker. A permanent
+      // billing/auth failure must be sampled once, not multiplied by the AI
+      // SDK's default retries (which can add ~90s to every health check).
+      const vec = await embedOne('gbrain doctor embedding smoke test', { maxRetries: 0 });
       const ms = Date.now() - start;
       const actualDims = vec.length;
 

src/core/ai/gateway.ts

@@ -1951,8 +1951,8 @@ async function embedSubBatch(
 }
 
 /** Embed one text (convenience wrapper). */
-export async function embedOne(text: string): Promise<Float32Array> {
-  const [v] = await embed([text]);
+export async function embedOne(text: string, opts?: EmbedOpts): Promise<Float32Array> {
+  const [v] = await embed([text], opts);
   return v;
 }
 

test/ai/gateway.test.ts

@@ -5,6 +5,8 @@ import {
   __unconfigureGatewayForTests,
   isAvailable,
   embed,
+  embedOne,
+  __setEmbedTransportForTests,
   getEmbeddingModel,
   getEmbeddingDimensions,
   getExpansionModel,
@@ -17,7 +19,10 @@ import {
 // (capture / ingest-capture tests), where it produced "Incorrect API key
 // provided: openai-fake" against the real OpenAI endpoint and wedged
 // the shard. Reset once at file teardown so no caller sees the residue.
-afterAll(() => resetGateway());
+afterAll(() => {
+  resetGateway();
+  __setEmbedTransportForTests(null);
+});
 import { parseModelId, resolveRecipe } from '../../src/core/ai/model-resolver.ts';
 import {
   dimsProviderOptions,
@@ -52,6 +57,35 @@ describe('gateway configuration', () => {
   });
 });
 
+describe('gateway.embedOne options', () => {
+  beforeEach(() => {
+    resetGateway();
+    __setEmbedTransportForTests(null);
+  });
+
+  test('passes maxRetries=0 to the provider transport for health probes', async () => {
+    let observedMaxRetries: number | undefined;
+    configureGateway({
+      embedding_model: 'google:gemini-embedding-001',
+      embedding_dimensions: 3,
+      env: { GOOGLE_GENERATIVE_AI_API_KEY: 'fake-google' },
+    });
+    __setEmbedTransportForTests(async (args: any) => {
+      observedMaxRetries = args.maxRetries;
+      return {
+        embeddings: [new Array(3).fill(0.1)],
+        usage: { tokens: 1 },
+      } as any;
+    });
+
+    const vector = await embedOne('health probe', { maxRetries: 0 });
+
+    expect(observedMaxRetries).toBe(0);
+    expect(vector.length).toBe(3);
+    __setEmbedTransportForTests(null);
+  });
+});
+
 describe('gateway.isAvailable (silent-drop regression surface)', () => {
   beforeEach(() => resetGateway());