refactor: Change timeout handling to use float type and global request_timeout

aider/args.py

@@ -216,7 +216,7 @@ def get_parser(default_config_files, git_root):
     )
     group.add_argument(
         "--timeout",
-        type=int,
+        type=float,
         default=None,
         help="Timeout in seconds for API calls (default: None)",
     )

aider/main.py

@@ -509,8 +509,7 @@ def main(argv=None, input=None, output=None, force_git_root=None, return_coder=F
         litellm._lazy_module.aclient_session = httpx.AsyncClient(verify=False)
 
     if args.timeout:
-        litellm._load_litellm()
-        litellm._lazy_module.request_timeout = args.timeout
+        models.request_timeout = args.timeout
 
     if args.dark_mode:
         args.user_input_color = "#32FF32"

aider/models.py

@@ -22,6 +22,8 @@ from aider.sendchat import ensure_alternating_roles, sanity_check_messages
 
 RETRY_TIMEOUT = 60
 
+request_timeout = 600
+
 DEFAULT_MODEL_NAME = "gpt-4o"
 ANTHROPIC_BETA_HEADER = "prompt-caching-2024-07-31,pdfs-2024-09-25"
 
@@ -599,7 +601,7 @@ class Model(ModelSettings):
         # dump(kwargs)
 
         hash_object = hashlib.sha1(key)
-        res = litellm.completion(**kwargs)
+        res = litellm.completion(timeout=request_timeout, **kwargs)
         return hash_object, res
 
     def remove_reasoning_content(self, res):