fix: Don't retry api calls by default

It may be unsafe to retry since the server may have already started
executing the requested work. At best, the consequent request will fail
because the previous request is already running. At worst, the server
may attempt to run the same work the second time.

Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>

Author: booxter

src/llama_stack_client/_constants.py

@@ -7,7 +7,7 @@
 
 # default timeout is 1 minute
 DEFAULT_TIMEOUT = httpx.Timeout(timeout=60, connect=5.0)
-DEFAULT_MAX_RETRIES = 2
+DEFAULT_MAX_RETRIES = 0
 DEFAULT_CONNECTION_LIMITS = httpx.Limits(max_connections=100, max_keepalive_connections=20)
 
 INITIAL_RETRY_DELAY = 0.5