🎯 refactor: Centralize Agent Model Handling Across Conversation Lifecycle (#10956)

* refactor: Implement clearModelForNonEphemeralAgent utility for improved agent handling

- Introduced clearModelForNonEphemeralAgent function to manage model state for non-ephemeral agents across various components.
- Updated ModelSelectorContext to initialize model based on agent type.
- Enhanced useNavigateToConvo, useQueryParams, and useSelectMention hooks to clear model for non-ephemeral agents.
- Refactored buildDefaultConvo and endpoints utility to ensure proper handling of agent_id and model state.
- Improved overall conversation logic and state management for better performance and reliability.

* refactor: Enhance useNewConvo hook to improve agent conversation handling

- Added logic to skip access checks for existing agent conversations, utilizing localStorage to restore conversations after refresh.
- Improved handling of default endpoints for agents based on user access and existing conversation state, ensuring more reliable conversation initialization.

* refactor: Update ChatRoute and useAuthRedirect to include user roles

- Enhanced ChatRoute to utilize user roles for improved conversation state management.
- Modified useAuthRedirect to return user roles alongside authentication status, ensuring roles are available for conditional logic in ChatRoute.
- Adjusted conversation initialization logic to depend on the loaded roles, enhancing the reliability of the conversation setup.

* refactor: Update BaseClient to handle non-ephemeral agents in conversation logic

- Added a check for non-ephemeral agents in BaseClient, modifying the exceptions set to include 'model' when applicable.
- Enhanced conversation handling to improve flexibility based on agent type.

* test: Add mock for clearModelForNonEphemeralAgent in useQueryParams tests

- Introduced a mock for clearModelForNonEphemeralAgent to enhance testing of query parameters related to non-ephemeral agents.
- This addition supports improved test coverage and ensures proper handling of model state in relevant scenarios.

* refactor: Simplify mocks in useQueryParams tests for improved clarity

- Updated the mocking strategy for utilities in useQueryParams tests to use actual implementations where possible, while still suppressing test output for the logger.
- Enhanced the mock for tQueryParamsSchema to minimize complexity and avoid unnecessary validation during tests, improving test reliability and maintainability.

* refactor: Enhance agent identification logic in BaseClient for improved clarity

* chore: Import Constants in families.ts for enhanced functionality

client/src/components/Chat/Menus/Endpoints/ModelSelectorContext.tsx

@@ -104,10 +104,18 @@ export function ModelSelectorProvider({ children, startupConfig }: ModelSelector
   });
 
   // State
-  const [selectedValues, setSelectedValues] = useState<SelectedValues>({
-    endpoint: endpoint || '',
-    model: model || '',
-    modelSpec: spec || '',
+  const [selectedValues, setSelectedValues] = useState<SelectedValues>(() => {
+    let initialModel = model || '';
+    if (isAgentsEndpoint(endpoint) && agent_id) {
+      initialModel = agent_id;
+    } else if (isAssistantsEndpoint(endpoint) && assistant_id) {
+      initialModel = assistant_id;
+    }
+    return {
+      endpoint: endpoint || '',
+      model: initialModel,
+      modelSpec: spec || '',
+    };
   });
   useSelectorEffects({
     agentsMap,