fix: use OpenAI provider for Doubao multimodal models

DeepSeek provider was not properly formatting image content for Doubao's
API. Now uses OpenAI provider for Doubao models (multimodal support),
while keeping DeepSeek provider for DeepSeek/Kimi models on the platform.

app/api/validate-model/route.ts

@@ -251,13 +251,26 @@ export async function POST(req: Request) {
             }
 
             case "doubao": {
-                // ByteDance Doubao uses DeepSeek-compatible API
-                const doubao = createDeepSeek({
-                    apiKey,
-                    baseURL:
-                        baseUrl || "https://ark.cn-beijing.volces.com/api/v3",
-                })
-                model = doubao(modelId)
+                // ByteDance Doubao: use DeepSeek for DeepSeek/Kimi models, OpenAI for others
+                const doubaoBaseUrl =
+                    baseUrl || "https://ark.cn-beijing.volces.com/api/v3"
+                const lowerModelId = modelId.toLowerCase()
+                if (
+                    lowerModelId.includes("deepseek") ||
+                    lowerModelId.includes("kimi")
+                ) {
+                    const doubao = createDeepSeek({
+                        apiKey,
+                        baseURL: doubaoBaseUrl,
+                    })
+                    model = doubao(modelId)
+                } else {
+                    const doubao = createOpenAI({
+                        apiKey,
+                        baseURL: doubaoBaseUrl,
+                    })
+                    model = doubao.chat(modelId)
+                }
                 break
             }
 

lib/ai-providers.ts

@@ -871,11 +871,24 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
                 overrides?.baseUrl ||
                 process.env.DOUBAO_BASE_URL ||
                 "https://ark.cn-beijing.volces.com/api/v3"
-            const doubaoProvider = createDeepSeek({
-                apiKey,
-                baseURL,
-            })
-            model = doubaoProvider(modelId)
+            const lowerModelId = modelId.toLowerCase()
+            // Use DeepSeek provider for DeepSeek/Kimi models, OpenAI for others (multimodal support)
+            if (
+                lowerModelId.includes("deepseek") ||
+                lowerModelId.includes("kimi")
+            ) {
+                const doubaoProvider = createDeepSeek({
+                    apiKey,
+                    baseURL,
+                })
+                model = doubaoProvider(modelId)
+            } else {
+                const doubaoProvider = createOpenAI({
+                    apiKey,
+                    baseURL,
+                })
+                model = doubaoProvider.chat(modelId)
+            }
             break
         }