From d1b5174fb8fac096fff4299bb429dc9f782f3397 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E7=A8=8B=E5=BA=8F=E5=91=98=E9=98=BF=E6=B1=9F=28Relakkes?=
 =?UTF-8?q?=29?= <relakkes@gmail.com>
Date: Sun, 31 May 2026 23:55:49 +0800
Subject: [PATCH] fix: broaden OpenAI image schema recovery

OpenAI-compatible text-only providers do not all report the same schema error when they reject image_url content parts. Match the broader protocol-level shape instead of one DeepSeek-style deserialization sentence, while still avoiding preflight image stripping for vision-capable endpoints.

Constraint: OpenAI-compatible upstream validation wording varies by provider and framework.

Rejected: Treat every image_url error as unsupported media | malformed image URLs should not be conflated unless the message says the part is disallowed or text-only.

Confidence: high

Scope-risk: narrow

Directive: Keep this classifier focused on image_url part rejection; provider capability modeling is the cleaner long-term preflight path.

Tested: bun test src/services/api/errors.test.ts

Tested: bun test tests/mediaRecoveryAndEstimation.test.ts

Tested: bun run check:server

Not-tested: Live provider matrix across every OpenAI-compatible endpoint.
---
 src/services/api/errors.test.ts | 27 ++++++++++++---------------
 src/services/api/errors.ts      | 27 ++++++++++++++++++++++++++-
 2 files changed, 38 insertions(+), 16 deletions(-)

diff --git a/src/services/api/errors.test.ts b/src/services/api/errors.test.ts
index 92508240..0d49bb11 100644
--- a/src/services/api/errors.test.ts
+++ b/src/services/api/errors.test.ts
@@ -7,21 +7,18 @@ import {
 
 describe('image unsupported API errors', () => {
   test('detects provider-specific text-only model image rejections', () => {
-    expect(
-      isUnsupportedImageInputErrorMessage(
-        'This model does not support image blocks',
-      ),
-    ).toBe(true)
-    expect(
-      isUnsupportedImageInputErrorMessage(
-        'unsupported modality: image input is not available',
-      ),
-    ).toBe(true)
-    expect(
-      isUnsupportedImageInputErrorMessage(
-        'Failed to deserialize the JSON body into the target type: messages[1]: unknown variant `image_url`, expected `text` at line 1 column 394097',
-      ),
-    ).toBe(true)
+    const unsupportedImageErrors = [
+      'This model does not support image blocks',
+      'unsupported modality: image input is not available',
+      'Failed to deserialize the JSON body into the target type: messages[1]: unknown variant `image_url`, expected `text` at line 1 column 394097',
+      "Invalid value for 'messages[0].content[1].type': 'image_url' is not one of ['text']",
+      "messages.0.content.1.type: Input should be 'text'; received 'image_url'",
+      'image_url content parts are not allowed for this model',
+    ]
+
+    for (const message of unsupportedImageErrors) {
+      expect(isUnsupportedImageInputErrorMessage(message)).toBe(true)
+    }
     expect(isUnsupportedImageInputErrorMessage('image exceeds maximum')).toBe(false)
   })
 
diff --git a/src/services/api/errors.ts b/src/services/api/errors.ts
index a77459c6..1b8708eb 100644
--- a/src/services/api/errors.ts
+++ b/src/services/api/errors.ts
@@ -430,7 +430,7 @@ export function extractUnknownErrorFormat(value: unknown): string | undefined {
 export function isUnsupportedImageInputErrorMessage(message: string): boolean {
   const raw = message.toLowerCase()
   if (!raw.includes('image')) return false
-  if (raw.includes('image_url') && raw.includes('expected') && raw.includes('text')) {
+  if (isOpenAIImageUrlTextOnlySchemaError(raw)) {
     return true
   }
   return (
@@ -444,6 +444,31 @@ export function isUnsupportedImageInputErrorMessage(message: string): boolean {
   )
 }
 
+function isOpenAIImageUrlTextOnlySchemaError(raw: string): boolean {
+  if (!raw.includes('image_url')) return false
+  if (
+    raw.includes('not allowed') ||
+    raw.includes('not permitted') ||
+    raw.includes('disallowed') ||
+    raw.includes('forbidden')
+  ) {
+    return true
+  }
+  if (!raw.includes('text')) return false
+  return (
+    raw.includes('expected') ||
+    raw.includes('input should be') ||
+    raw.includes('not one of') ||
+    raw.includes('permitted') ||
+    raw.includes('received') ||
+    raw.includes('unknown variant') ||
+    raw.includes('invalid value') ||
+    raw.includes('invalid type') ||
+    raw.includes('valid enumeration') ||
+    raw.includes('only text')
+  )
+}
+
 export function getAssistantMessageFromError(
   error: unknown,
   model: string,