From e17ea13745ba8757321c3ed16cf3e9b2c2ef5c6c Mon Sep 17 00:00:00 2001
From: Matt Gunnin <mgunnin@esports.one>
Date: Thu, 14 May 2026 08:46:33 -0500
Subject: [PATCH] fix(ai/embed): recognize OpenAI 'maximum request size' error
 in isTokenLimitError
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

OpenAI's /v1/embeddings endpoint hard-caps a single request at 300k tokens
total across all input items. When the cap is exceeded it returns:

    Invalid 'input': maximum request size is 300000 tokens per request.

None of the three existing regexes in isTokenLimitError matched this
phrasing, so the recursive-halving safety net in embedSubBatch never
engaged for OpenAI. The same fat page (a token-dense markdown export,
e.g. a Discord transcript) would re-fail every pass, blocking forward
progress on the whole batch indefinitely.

Locally reproduced on a 31,129-chunk Postgres brain: 2,125 chunks
stuck at 'remaining' across 30+ embed --stale passes with retry
loops + sleep delays. Adding the two new patterns lets halving fire;
the same backlog cleared in one pass after the regex change (the
companion max_batch_tokens recipe fix from PR #924 caps fresh batches,
but existing oversize pages still need halving to recover).

Adds:
  - /maximum request size.*tokens/i  — OpenAI verbatim
  - /max.*tokens.*per.*request/i    — defensive against minor rewording

Tests:
  - Regression test for the exact OpenAI error string
  - Coverage for the generic 'max tokens per request' variant
  - All 25 tests in adaptive-embed-batch.test.ts pass

No behavior change for providers whose errors already matched.

(cherry picked from commit b834e84c56e939e687659f6228b4d60fc4c7dce3)
---
 src/core/ai/gateway.ts               |  5 ++++-
 test/ai/adaptive-embed-batch.test.ts | 15 +++++++++++++++
 2 files changed, 19 insertions(+), 1 deletion(-)

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);