perf: fix cache key generation for model list caching

- Replace Request object with user.id in cache key for get_all_models
- Request objects are new instances per HTTP request, preventing cache hits
- Cache keys now use user.id ensuring proper cache functionality
- Affects both Ollama and OpenAI model list endpoints

Signed-off-by: Sihyeon Jang <sihyeon.jang@navercorp.com>

backend/open_webui/routers/ollama.py

@@ -340,7 +340,7 @@ def merge_ollama_models_lists(model_lists):
     return list(merged_models.values())
 
 
-@cached(ttl=MODELS_CACHE_TTL)
+@cached(ttl=MODELS_CACHE_TTL, key=lambda _, user: f"ollama_all_models_{user.id}" if user else "ollama_all_models")
 async def get_all_models(request: Request, user: UserModel = None):
     log.info("get_all_models()")
     if request.app.state.config.ENABLE_OLLAMA_API:

backend/open_webui/routers/openai.py

@@ -401,7 +401,7 @@ async def get_filtered_models(models, user):
     return filtered_models
 
 
-@cached(ttl=MODELS_CACHE_TTL)
+@cached(ttl=MODELS_CACHE_TTL, key=lambda _, user: f"openai_all_models_{user.id}" if user else "openai_all_models")
 async def get_all_models(request: Request, user: UserModel) -> dict[str, list]:
     log.info("get_all_models()")