feat(assistant): improve chat functionality and update tests - refactor configurable model, update OpenAI provider, enhance chat form UI, and improve test coverage (#2316)

Updated model to GPT 4.1

test/models/assistant_message_test.rb

@@ -6,7 +6,7 @@ class AssistantMessageTest < ActiveSupport::TestCase
   end
 
   test "broadcasts append after creation" do
-    message = AssistantMessage.create!(chat: @chat, content: "Hello from assistant", ai_model: "gpt-4o")
+    message = AssistantMessage.create!(chat: @chat, content: "Hello from assistant", ai_model: "gpt-4.1")
     message.update!(content: "updated")
 
     streams = capture_turbo_stream_broadcasts(@chat)

test/models/assistant_test.rb

@@ -8,14 +8,14 @@ class AssistantTest < ActiveSupport::TestCase
     @message = @chat.messages.create!(
       type: "UserMessage",
       content: "What is my net worth?",
-      ai_model: "gpt-4o"
+      ai_model: "gpt-4.1"
     )
     @assistant = Assistant.for_chat(@chat)
     @provider = mock
   end
 
   test "errors get added to chat" do
-    @assistant.expects(:get_model_provider).with("gpt-4o").returns(@provider)
+    @assistant.expects(:get_model_provider).with("gpt-4.1").returns(@provider)
 
     error = StandardError.new("test error")
     @provider.expects(:chat_response).returns(provider_error_response(error))
@@ -28,7 +28,7 @@ class AssistantTest < ActiveSupport::TestCase
   end
 
   test "responds to basic prompt" do
-    @assistant.expects(:get_model_provider).with("gpt-4o").returns(@provider)
+    @assistant.expects(:get_model_provider).with("gpt-4.1").returns(@provider)
 
     text_chunks = [
       provider_text_chunk("I do not "),
@@ -38,7 +38,7 @@ class AssistantTest < ActiveSupport::TestCase
 
     response_chunk = provider_response_chunk(
       id: "1",
-      model: "gpt-4o",
+      model: "gpt-4.1",
       messages: [ provider_message(id: "1", text: text_chunks.join) ],
       function_requests: []
     )
@@ -63,7 +63,7 @@ class AssistantTest < ActiveSupport::TestCase
   end
 
   test "responds with tool function calls" do
-    @assistant.expects(:get_model_provider).with("gpt-4o").returns(@provider).once
+    @assistant.expects(:get_model_provider).with("gpt-4.1").returns(@provider).once
 
     # Only first provider call executes function
     Assistant::Function::GetAccounts.any_instance.stubs(:call).returns("test value").once
@@ -71,7 +71,7 @@ class AssistantTest < ActiveSupport::TestCase
     # Call #1: Function requests
     call1_response_chunk = provider_response_chunk(
       id: "1",
-      model: "gpt-4o",
+      model: "gpt-4.1",
       messages: [],
       function_requests: [
         provider_function_request(id: "1", call_id: "1", function_name: "get_accounts", function_args: "{}")
@@ -88,7 +88,7 @@ class AssistantTest < ActiveSupport::TestCase
 
     call2_response_chunk = provider_response_chunk(
       id: "2",
-      model: "gpt-4o",
+      model: "gpt-4.1",
       messages: [ provider_message(id: "1", text: call2_text_chunks.join) ],
       function_requests: []
     )

test/models/chat_test.rb

@@ -22,7 +22,7 @@ class ChatTest < ActiveSupport::TestCase
     prompt = "Test prompt"
 
     assert_difference "@user.chats.count", 1 do
-      chat = @user.chats.start!(prompt, model: "gpt-4o")
+      chat = @user.chats.start!(prompt, model: "gpt-4.1")
 
       assert_equal 1, chat.messages.count
       assert_equal 1, chat.messages.where(type: "UserMessage").count

test/models/provider/openai_test.rb

@@ -5,7 +5,7 @@ class Provider::OpenaiTest < ActiveSupport::TestCase
 
   setup do
     @subject = @openai = Provider::Openai.new(ENV.fetch("OPENAI_ACCESS_TOKEN", "test-openai-token"))
-    @subject_model = "gpt-4o"
+    @subject_model = "gpt-4.1"
   end
 
   test "openai errors are automatically raised" do

test/models/user_message_test.rb

@@ -8,7 +8,7 @@ class UserMessageTest < ActiveSupport::TestCase
   test "requests assistant response after creation" do
     @chat.expects(:ask_assistant_later).once
 
-    message = UserMessage.create!(chat: @chat, content: "Hello from user", ai_model: "gpt-4o")
+    message = UserMessage.create!(chat: @chat, content: "Hello from user", ai_model: "gpt-4.1")
     message.update!(content: "updated")
 
     streams = capture_turbo_stream_broadcasts(@chat)