修改config

config.yaml

@@ -100,6 +100,7 @@ model_list:
       model: volcengine/doubao-seed-1-8-251228
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY 
+      timeout: 120   
       extra_body:
         reasoning_effort: "minimal"    
 
@@ -110,6 +111,7 @@ model_list:
       model: volcengine/glm-4-7-251222
       api_base: os.environ/HUOSHAN_BASE_URL
       api_key: os.environ/HUOSHAN_API_KEY 
+      timeout: 120        
       extra_body:
         thinking:
           type: "disabled" 
@@ -288,7 +290,7 @@ model_list:
 
 
 litellm_settings:
-  num_retries: 2 # retry call 3 times on each model_name (e.g. zephyr-beta)
+  num_retries: 3 # retry call 3 times on each model_name (e.g. zephyr-beta)
   request_timeout: 120 # raise Timeout error if call takes longer than 10s. Sets litellm.request_timeout 
   #fallbacks: [{"zephyr-beta": ["gpt-4o"]}] # fallback to gpt-4o if call fails num_retries 
   #context_window_fallbacks: [{"zephyr-beta": ["gpt-3.5-turbo-16k"]}, {"gpt-4o": ["gpt-3.5-turbo-16k"]}] # fallback to gpt-3.5-turbo-16k if context window error