feat: add reasoning_effort configuration support for Doubao/GPT-5 models (#947)

* feat: Add reasoning effort configuration support

* Add `reasoning_effort` parameter to model config and agent initialization
* Support reasoning effort levels (minimal/low/medium/high) for Doubao/GPT-5 models
* Add UI controls in input box for reasoning effort selection
* Update doubao-seed-1.8 example config with reasoning effort support

Fixes & Cleanup:
* Ensure UTF-8 encoding for file operations
* Remove unused imports

* fix: set reasoning_effort to None for unsupported models

* fix: unit test error

* Update frontend/src/components/workspace/input-box.tsx

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

backend/tests/test_client.py

@@ -25,6 +25,8 @@ def mock_app_config():
     """Provide a minimal AppConfig mock."""
     model = MagicMock()
     model.name = "test-model"
+    model.supports_thinking = False
+    model.supports_reasoning_effort = False
     model.model_dump.return_value = {"name": "test-model", "use": "langchain_openai:ChatOpenAI"}
 
     config = MagicMock()
@@ -379,6 +381,7 @@ class TestGetModel:
         model_cfg.display_name = "Test Model"
         model_cfg.description = "A test model"
         model_cfg.supports_thinking = True
+        model_cfg.supports_reasoning_effort = True
         client._app_config.get_model_config.return_value = model_cfg
 
         result = client.get_model("test-model")
@@ -387,6 +390,7 @@ class TestGetModel:
             "display_name": "Test Model",
             "description": "A test model",
             "supports_thinking": True,
+            "supports_reasoning_effort": True,
         }
 
     def test_not_found(self, client):
@@ -928,6 +932,7 @@ class TestScenarioConfigManagement:
         model_cfg.display_name = None
         model_cfg.description = None
         model_cfg.supports_thinking = False
+        model_cfg.supports_reasoning_effort = False
         client._app_config.get_model_config.return_value = model_cfg
         detail = client.get_model(model_name)
         assert detail["name"] == model_name

backend/tests/test_lead_agent_model_resolution.py

@@ -84,9 +84,10 @@ def test_make_lead_agent_disables_thinking_when_model_does_not_support_it(monkey
 
     captured: dict[str, object] = {}
 
-    def _fake_create_chat_model(*, name, thinking_enabled):
+    def _fake_create_chat_model(*, name, thinking_enabled, reasoning_effort=None):
         captured["name"] = name
         captured["thinking_enabled"] = thinking_enabled
+        captured["reasoning_effort"] = reasoning_effort
         return object()
 
     monkeypatch.setattr(lead_agent_module, "create_chat_model", _fake_create_chat_model)