From c85d2f9bc8b7ad998c7f8095a32895037cda6eb9 Mon Sep 17 00:00:00 2001
From: MoerAI <friendnt@g.skku.edu>
Date: Fri, 8 May 2026 18:31:54 +0900
Subject: [PATCH] fix(model-error-classifier): mark OpenAI server_error
 patterns as retryable (fixes #3799)

OpenAI streaming responses can surface mid-stream errors with type
'server_error' or with the prose message 'An error occurred while processing
your request'. Neither matched any entry in RETRYABLE_MESSAGE_PATTERNS, so
shouldRetryError returned false and the runtime-fallback / fallback-retry
code paths skipped retry. The result was that GPT-5.5 subagent (and main)
turns silently stalled until the stale timeout fired.

The maintainer's diagnosis on issue #3799 explicitly recommends adding
these two patterns to model-error-classifier.ts; this commit does exactly
that and adds two regression tests covering the JSON envelope and the
prose form.
---
 src/shared/model-error-classifier.test.ts | 28 +++++++++++++++++++++++
 src/shared/model-error-classifier.ts      |  5 ++++
 2 files changed, 33 insertions(+)

diff --git a/src/shared/model-error-classifier.test.ts b/src/shared/model-error-classifier.test.ts
index 0ab40e8eb..172899e64 100644
--- a/src/shared/model-error-classifier.test.ts
+++ b/src/shared/model-error-classifier.test.ts
@@ -434,6 +434,34 @@ describe("model-error-classifier", () => {
     //#then
     expect(result).toBe(true)
   })
+
+  test("treats OpenAI streaming server_error envelopes as retryable (issue #3799)", () => {
+    //#given: OpenAI surfaces its mid-stream error with type 'server_error'
+    const error = {
+      name: undefined,
+      message: "{\"error\":{\"type\":\"server_error\",\"message\":\"server_error\"}}",
+    }
+
+    //#when
+    const result = shouldRetryError(error)
+
+    //#then
+    expect(result).toBe(true)
+  })
+
+  test("treats the OpenAI prose 'An error occurred while processing' message as retryable (issue #3799)", () => {
+    //#given: the human-readable prose surfaced when OpenAI's stream fails
+    const error = {
+      name: undefined,
+      message: "An error occurred while processing your request. Please try again later.",
+    }
+
+    //#when
+    const result = shouldRetryError(error)
+
+    //#then
+    expect(result).toBe(true)
+  })
 })
 
 export {}
diff --git a/src/shared/model-error-classifier.ts b/src/shared/model-error-classifier.ts
index 787f4825a..a4bbbb9e0 100644
--- a/src/shared/model-error-classifier.ts
+++ b/src/shared/model-error-classifier.ts
@@ -80,6 +80,11 @@ const RETRYABLE_MESSAGE_PATTERNS = [
   "请求过于频繁",       // "too many requests"
   "暂时不可用",         // "temporarily unavailable"
   "服务不可用",         // "service unavailable"
+  // OpenAI streaming server_error events surface either as a literal "server_error"
+  // type or as the prose error sentence below. Without these patterns subagent
+  // streams stall instead of being retried (issue #3799).
+  "server_error",
+  "an error occurred while processing",
 ]
 
 /**