fix: increase API timeout default from 900s to 1800s for slow-thinking models

run_agent.py

@@ -3772,7 +3772,7 @@ def _fire_first_delta():
         def _call_chat_completions():
             """Stream a chat completions response."""
             import httpx as _httpx
-            _base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 900.0))
+            _base_timeout = float(os.getenv("HERMES_API_TIMEOUT", 1800.0))
             _stream_read_timeout = float(os.getenv("HERMES_STREAM_READ_TIMEOUT", 60.0))
             stream_kwargs = {
                 **api_kwargs,
@@ -4497,7 +4497,7 @@ def _build_api_kwargs(self, api_messages: list) -> dict:
             "model": self.model,
             "messages": sanitized_messages,
             "tools": self.tools if self.tools else None,
-            "timeout": float(os.getenv("HERMES_API_TIMEOUT", 900.0)),
+            "timeout": float(os.getenv("HERMES_API_TIMEOUT", 1800.0)),
         }
 
         if self.max_tokens is not None:

tests/test_run_agent.py

@@ -637,7 +637,7 @@ def test_basic_kwargs(self, agent):
         kwargs = agent._build_api_kwargs(messages)
         assert kwargs["model"] == agent.model
         assert kwargs["messages"] is messages
-        assert kwargs["timeout"] == 900.0
+        assert kwargs["timeout"] == 1800.0
 
     def test_provider_preferences_injected(self, agent):
         agent.providers_allowed = ["Anthropic"]