fix(runtime-fallback): classify localized balance failures

src/hooks/runtime-fallback/error-classifier.ts

@@ -97,6 +97,13 @@ export function extractErrorName(error: unknown): string | undefined {
   return undefined
 }
 
+function isLocalizedQuotaExhaustionMessage(message: string): boolean {
+  return (
+    (/预扣费额度失败/i.test(message) && /用户剩余额度/i.test(message)) ||
+    (/用户剩余额度/i.test(message) && /需要预扣费额度/i.test(message))
+  )
+}
+
 export function classifyErrorType(error: unknown): string | undefined {
   const message = getErrorMessage(error)
   const errorName = extractErrorName(error)?.toLowerCase()
@@ -135,7 +142,8 @@ export function classifyErrorType(error: unknown): string | undefined {
     /out\s+of\s+credits?/i.test(message) ||
     /payment.?required/i.test(message) ||
     /usage\s+limit/i.test(message) ||
-    /credit\s+balance.*too\s+low/i.test(message)
+    /credit\s+balance.*too\s+low/i.test(message) ||
+    isLocalizedQuotaExhaustionMessage(message)
   ) {
     return "quota_exceeded"
   }

src/hooks/runtime-fallback/quota-error-classifier.regression.test.ts

@@ -73,4 +73,20 @@ describe("runtime-fallback quota error regressions", () => {
     // Volcano Engine quota errors trigger fallback to the next model
     expect(retryable).toBe(true)
   })
+
+  test("classifies UnifyLLM pre-charge balance failures as quota_exceeded", () => {
+    //#given
+    const error = {
+      message:
+        "预扣费额度失败, 用户剩余额度: 0.265718, 需要预扣费额度: 0.680208 (request id: test-request-id)",
+    }
+
+    //#when
+    const errorType = classifyErrorType(error)
+    const retryable = isRetryableError(error, [429, 500, 502, 503, 504])
+
+    //#then
+    expect(errorType).toBe("quota_exceeded")
+    expect(retryable).toBe(true)
+  })
 })