fix: increase API timeout default from 900s to 1800s for slow-thinking models (#3431)

Models like GLM-5/5.1 can think for 15+ minutes. The previous 900s
(15 min) default for HERMES_API_TIMEOUT killed legitimate requests.

Raised to 1800s (30 min) in both places that read the env var:
- _build_api_kwargs() timeout (non-streaming total timeout)
- _call_chat_completions() write timeout (streaming connection)

The streaming per-chunk read timeout (60s) and stale stream detector
(180-300s) are unchanged — those are appropriate for inter-chunk timing.

run_agent.py

@@ -3772,7 +3772,7 @@ class AIAgent:
         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 @@ class AIAgent:
             "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: