fix: inherit reasoning config in API server runs

gateway/platforms/api_server.py

@@ -738,10 +738,11 @@ class APIServerAdapter(BasePlatformAdapter):
         gateway platforms), falling back to the hermes-api-server default.
         """
         from run_agent import AIAgent
-        from gateway.run import _resolve_runtime_agent_kwargs, _resolve_gateway_model, _load_gateway_config
+        from gateway.run import _resolve_runtime_agent_kwargs, _resolve_gateway_model, _load_gateway_config, GatewayRunner
         from hermes_cli.tools_config import _get_platform_tools
 
         runtime_kwargs = _resolve_runtime_agent_kwargs()
+        reasoning_config = GatewayRunner._load_reasoning_config()
         model = _resolve_gateway_model()
 
         user_config = _load_gateway_config()
@@ -751,7 +752,6 @@ class APIServerAdapter(BasePlatformAdapter):
 
         # Load fallback provider chain so the API server platform has the
         # same fallback behaviour as Telegram/Discord/Slack (fixes #4954).
-        from gateway.run import GatewayRunner
         fallback_model = GatewayRunner._load_fallback_model()
 
         agent = AIAgent(
@@ -770,6 +770,7 @@ class APIServerAdapter(BasePlatformAdapter):
             tool_complete_callback=tool_complete_callback,
             session_db=self._ensure_session_db(),
             fallback_model=fallback_model,
+            reasoning_config=reasoning_config,
         )
         return agent
 

tests/gateway/test_api_server.py

@@ -246,6 +246,42 @@ class TestAdapterInit:
         adapter = APIServerAdapter(config)
         assert adapter._port == 8642
 
+    def test_create_agent_forwards_config_reasoning_effort(self, monkeypatch):
+        captured = {}
+
+        class FakeAgent:
+            def __init__(self, **kwargs):
+                captured.update(kwargs)
+
+        monkeypatch.setattr("run_agent.AIAgent", FakeAgent)
+        monkeypatch.setattr(
+            "gateway.run._resolve_runtime_agent_kwargs",
+            lambda: {
+                "provider": "openai-codex",
+                "base_url": "https://example.test/v1",
+                "api_mode": "codex_responses",
+            },
+        )
+        monkeypatch.setattr("gateway.run._resolve_gateway_model", lambda: "gpt-5.5")
+        monkeypatch.setattr(
+            "gateway.run._load_gateway_config",
+            lambda: {"agent": {"reasoning_effort": "xhigh"}},
+        )
+        monkeypatch.setattr(
+            "gateway.run.GatewayRunner._load_reasoning_config",
+            staticmethod(lambda: {"enabled": True, "effort": "xhigh"}),
+        )
+        monkeypatch.setattr("gateway.run.GatewayRunner._load_fallback_model", staticmethod(lambda: None))
+        monkeypatch.setattr("hermes_cli.tools_config._get_platform_tools", lambda *_: set())
+
+        adapter = APIServerAdapter(PlatformConfig(enabled=True))
+        monkeypatch.setattr(adapter, "_ensure_session_db", lambda: None)
+
+        agent = adapter._create_agent(session_id="api-session")
+
+        assert isinstance(agent, FakeAgent)
+        assert captured["reasoning_config"] == {"enabled": True, "effort": "xhigh"}
+
 
 # ---------------------------------------------------------------------------
 # Auth checking