fix(ecommerce): 502 bug - vision model upgrade + MIME normalization + fallback

- Upgrade VISION_MODEL to qwen3.7-plus (latest, confirmed working with image_url)
- Add VISION_FALLBACK_MODEL = qwen-vl-plus for retry on "image format" errors
- Normalize upload MIME types: unsupported formats (HEIC/AVIF) fall back to image/png
  to prevent server saving as .bin which DashScope can't read
- Server-side: add image/avif, image/heic, image/heif to MIME_EXTENSIONS

Root cause: DashScope returned "image format is illegal" when uploaded images
had unrecognized MIME types → saved as .bin → DashScope couldn't decode.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

src/api/adVideoPlanClient.ts

@@ -1,7 +1,8 @@
 import { buildApiUrl, buildAuthHeaders } from "./serverConnection";
 
 const TEXT_MODEL = "qwen-max";
-const VISION_MODEL = "qwen3.6-plus";
+const VISION_MODEL = "qwen3.7-plus";
+const VISION_FALLBACK_MODEL = "qwen-vl-plus";
 
 export interface AdVideoUserConfig {
   platform: string;
@@ -149,30 +150,39 @@ async function visionChat(
     ...imageUrls.map((url) => ({ type: "image_url", image_url: { url } })),
     { type: "text", text },
   ];
-  const timeoutSignal = AbortSignal.timeout(60000);
-  const combinedSignal = signal
-    ? AbortSignal.any([signal, timeoutSignal])
-    : timeoutSignal;
-  const res = await fetch(buildApiUrl("ai/chat"), {
-    method: "POST",
-    headers: buildAuthHeaders(),
-    body: JSON.stringify({
-      model: VISION_MODEL,
-      messages: [
-        { role: "system", content: systemPrompt },
-        { role: "user", content },
-      ],
-      stream: false,
-      temperature: 0.3,
-    }),
-    signal: combinedSignal,
-  });
-  if (!res.ok) throw new Error(`图片理解调用失败 (${res.status})`);
-  const payload = await res.json();
-  const out: string =
-    payload?.content ?? payload?.choices?.[0]?.message?.content ?? payload?.text ?? "";
-  if (!out) throw new Error("图片理解未返回有效内容");
-  return out;
+  const messages = [
+    { role: "system", content: systemPrompt },
+    { role: "user", content },
+  ];
+
+  for (const model of [VISION_MODEL, VISION_FALLBACK_MODEL]) {
+    const timeoutSignal = AbortSignal.timeout(60000);
+    const combinedSignal = signal
+      ? AbortSignal.any([signal, timeoutSignal])
+      : timeoutSignal;
+    try {
+      const res = await fetch(buildApiUrl("ai/chat"), {
+        method: "POST",
+        headers: buildAuthHeaders(),
+        body: JSON.stringify({ model, messages, stream: false, temperature: 0.3 }),
+        signal: combinedSignal,
+      });
+      if (!res.ok) {
+        const errBody = await res.text().catch(() => "");
+        if (model === VISION_MODEL && errBody.includes("image format")) continue;
+        throw new Error(`图片理解调用失败 (${res.status})`);
+      }
+      const payload = await res.json();
+      const out: string =
+        payload?.content ?? payload?.choices?.[0]?.message?.content ?? payload?.text ?? "";
+      if (!out) throw new Error("图片理解未返回有效内容");
+      return out;
+    } catch (err) {
+      if (model === VISION_MODEL && err instanceof Error && err.message?.includes("图片理解调用失败")) continue;
+      throw err;
+    }
+  }
+  throw new Error("图片理解调用失败，所有模型均不可用");
 }
 
 const IMAGE_UNDERSTANDING_PROMPT = `你是电商产品图片分析专家。请分析用户提供的产品图片，识别产品主体、外观、颜色、材质、形状、尺寸感、品牌标识、关键部件、可视化卖点和适合展示的镜头角度。请用简洁的中文段落描述，不要编造图片中看不到的信息。`;