fix code

backend/app/ai/tools/qa_tool.py

@@ -2,12 +2,15 @@ import asyncio
 from typing import Dict, Any, List
 import json
 import os
+import time
+import hashlib
 from dashscope import MultiModalConversation
 from backend.app.admin.service.file_service import file_service
 from langchain_core.messages import SystemMessage, HumanMessage
 from backend.core.llm import LLMFactory, AuditLogCallbackHandler
 from backend.core.conf import settings
 from backend.core.prompts.scene_variation import get_scene_variation_prompt
+from backend.database.redis import redis_client
 
 class SceneVariationGenerator:
     """
@@ -86,6 +89,59 @@ class SceneVariationGenerator:
         except Exception as e:
             return {"success": False, "error": str(e)}
 
+
+class QwenImageKeyManager:
+    RATE_LIMIT_PER_SECOND = 2
+    WINDOW_SECONDS = 1
+    REDIS_PREFIX = "qwen:image_edit:rate"
+
+    @classmethod
+    def _get_keys(cls) -> List[str]:
+        raw = settings.QWEN_API_KEY or ""
+        if not raw:
+            raw = os.getenv("DASHSCOPE_API_KEY") or ""
+        parts = [p.strip() for p in raw.split(";") if p.strip()]
+        if parts:
+            return parts
+        if raw:
+            return [raw]
+        return []
+
+    @classmethod
+    def _key_id(cls, key: str) -> str:
+        return hashlib.sha256(key.encode()).hexdigest()[:16]
+
+    @classmethod
+    async def acquire_key(cls) -> str:
+        keys = cls._get_keys()
+        if not keys:
+            raise Exception("Qwen API key not configured")
+        now = int(time.time())
+        n = len(keys)
+        start = now % n
+        for i in range(n):
+            key = keys[(start + i) % n]
+            kid = cls._key_id(key)
+            redis_key = f"{cls.REDIS_PREFIX}:{kid}:{now}"
+            count = await redis_client.incr(redis_key)
+            if count == 1:
+                await redis_client.expire(redis_key, cls.WINDOW_SECONDS + 1)
+            if count <= cls.RATE_LIMIT_PER_SECOND:
+                return key
+        await asyncio.sleep(1.0 / cls.RATE_LIMIT_PER_SECOND)
+        now2 = int(time.time())
+        for i in range(n):
+            key = keys[(start + i) % n]
+            kid = cls._key_id(key)
+            redis_key = f"{cls.REDIS_PREFIX}:{kid}:{now2}"
+            count = await redis_client.incr(redis_key)
+            if count == 1:
+                await redis_client.expire(redis_key, cls.WINDOW_SECONDS + 1)
+            if count <= cls.RATE_LIMIT_PER_SECOND:
+                return key
+        raise Exception("Qwen image edit rate limited")
+
+
 class Illustrator:
     """
     Component for generating edited images based on text descriptions (Step 2 of the advanced workflow).
@@ -116,11 +172,14 @@ class Illustrator:
         ]
         
         try:
-            # Wrap the blocking SDK call in asyncio.to_thread
+            if api_key:
+                final_api_key = api_key
+            else:
+                final_api_key = await QwenImageKeyManager.acquire_key()
             response = await asyncio.to_thread(
                 MultiModalConversation.call,
-                api_key=api_key or os.getenv("DASHSCOPE_API_KEY") or settings.QWEN_API_KEY,
-                model="qwen-image-edit-plus", # Assuming this is the model name for image editing
+                api_key=final_api_key,
+                model="qwen-image-edit-plus",
                 messages=messages,
                 stream=False,
                 n=1,

backend/core/llm.py

@@ -12,6 +12,15 @@ from backend.app.admin.service.audit_log_service import audit_log_service
 from backend.core.conf import settings
 from backend.common.log import log as logger
 
+
+def _get_primary_qwen_api_key() -> str:
+    raw = settings.QWEN_API_KEY or ""
+    parts = [p.strip() for p in raw.split(";") if p.strip()]
+    if parts:
+        return parts[0]
+    return raw
+
+
 class AuditLogCallbackHandler(BaseCallbackHandler):
     def __init__(self, metadata: Optional[Dict[str, Any]] = None):
         super().__init__()
@@ -99,7 +108,7 @@ class LLMFactory:
         
         if model_type == 'qwen':
             return ChatTongyi(
-                api_key=settings.QWEN_API_KEY,
+                api_key=_get_primary_qwen_api_key(),
                 model_name=settings.QWEN_TEXT_MODEL,
                 **kwargs
             )
@@ -110,10 +119,9 @@ class LLMFactory:
                 **kwargs
             )
         else:
-             # Default to Qwen if unknown
              logger.warning(f"Unknown model type {model_type}, defaulting to Qwen")
              return ChatTongyi(
-                api_key=settings.QWEN_API_KEY,
+                api_key=_get_primary_qwen_api_key(),
                 model_name=settings.QWEN_TEXT_MODEL,
                 **kwargs
             )

backend/middleware/qwen.py

@@ -23,6 +23,14 @@ from sqlalchemy.exc import IntegrityError
 from asyncio import sleep
 
 
+def _get_primary_qwen_api_key() -> str:
+    raw = settings.QWEN_API_KEY or ""
+    parts = [p.strip() for p in raw.split(";") if p.strip()]
+    if parts:
+        return parts[0]
+    return raw
+
+
 class Qwen:
     # 创建一个类级别的线程池执行器
     _executor = ThreadPoolExecutor(max_workers=10)
@@ -33,7 +41,7 @@ class Qwen:
 
     @staticmethod
     async def text_to_speak(content: str, image_text_id: int | None = None, image_id: int | None = None, user_id: int | None = None, ref_type: str | None = None, ref_id: int | None = None) -> Dict[str, Any]:
-        api_key = settings.QWEN_API_KEY
+        api_key = _get_primary_qwen_api_key()
         model_name = "qwen3-tts-flash"
         voice = "Jennifer"
         language_type = "English"
@@ -185,7 +193,7 @@ class Qwen:
 
     @staticmethod
     async def chat(messages: List[Dict[str, str]], image_id: int = 0, user_id: int = 0, api_type: str = "chat") -> Dict[str, Any]:
-        api_key = settings.QWEN_API_KEY
+        api_key = _get_primary_qwen_api_key()
         model_name = settings.QWEN_TEXT_MODEL
         start_time = time.time()
         start_at = datetime.now()
@@ -314,7 +322,7 @@ class Qwen:
         """通用API调用方法"""
 
         model_name = ""
-        api_key = settings.QWEN_API_KEY
+        api_key = _get_primary_qwen_api_key()
         response = None
         start_time = time.time()
         start_at = datetime.now()
@@ -481,7 +489,7 @@ class Qwen:
         # 轮询任务状态
         start_time = time.time()
         headers = {
-            "Authorization": f"Bearer {settings.QWEN_API_KEY}",
+            "Authorization": f"Bearer {_get_primary_qwen_api_key()}",
             "Content-Type": "application/json"
         }