diff --git a/src/core/ai/gateway.ts b/src/core/ai/gateway.ts
index 05ac7a7b3..a4da36d7f 100644
--- a/src/core/ai/gateway.ts
+++ b/src/core/ai/gateway.ts
@@ -1259,7 +1259,10 @@ export function isTokenLimitError(err: unknown): boolean {
   return (
     /max.*allowed.*tokens.*batch/i.test(msg) ||
     /batch.*too.*many.*tokens/i.test(msg) ||
-    /token.*limit.*exceeded/i.test(msg)
+    /token.*limit.*exceeded/i.test(msg) ||
+    // OpenAI embeddings: "Invalid 'input': maximum request size is 300000 tokens per request."
+    /maximum request size.*tokens/i.test(msg) ||
+    /max.*tokens.*per.*request/i.test(msg)
   );
 }
 
diff --git a/test/ai/adaptive-embed-batch.test.ts b/test/ai/adaptive-embed-batch.test.ts
index 8ad53df0d..33050d4d4 100644
--- a/test/ai/adaptive-embed-batch.test.ts
+++ b/test/ai/adaptive-embed-batch.test.ts
@@ -155,6 +155,21 @@ describe('isTokenLimitError (pure helper)', () => {
     expect(isTokenLimitError(new Error('Batch contains too many tokens'))).toBe(true);
   });
 
+  test('matches OpenAI embeddings "maximum request size" error (regression: PR ###)', () => {
+    // Real error string returned by OpenAI's /v1/embeddings endpoint when the
+    // sum of all input items exceeds 300k tokens. Without this match, gbrain's
+    // recursive-halving safety net never engages on OpenAI and the queue stalls
+    // forever on token-dense pages.
+    const openaiErr = new Error(
+      "Invalid 'input': maximum request size is 300000 tokens per request.",
+    );
+    expect(isTokenLimitError(openaiErr)).toBe(true);
+  });
+
+  test('matches generic "max tokens per request" phrasing', () => {
+    expect(isTokenLimitError(new Error('Exceeded 300000 max tokens per request'))).toBe(true);
+  });
+
   test('does not match unrelated errors', () => {
     expect(isTokenLimitError(new Error('Connection refused'))).toBe(false);
     expect(isTokenLimitError(new Error('Invalid API key'))).toBe(false);