assistant: Limit amount of concurrent completion requests (#13856)

This PR refactors the completion providers to only process a maximum
amount of completion requests at a time.

Also started refactoring language model providers to use traits, so it's
easier to allow specifying multiple providers in the future.

Release Notes:

- N/A

crates/assistant/src/assistant_settings.rs

@@ -1,5 +1,6 @@
 use std::fmt;
 
+use crate::{preprocess_anthropic_request, LanguageModel, LanguageModelRequest};
 pub use anthropic::Model as AnthropicModel;
 use gpui::Pixels;
 pub use ollama::Model as OllamaModel;
@@ -15,8 +16,6 @@ use serde::{
 use settings::{Settings, SettingsSources};
 use strum::{EnumIter, IntoEnumIterator};
 
-use crate::{preprocess_anthropic_request, LanguageModel, LanguageModelRequest};
-
 #[derive(Clone, Debug, Default, PartialEq, EnumIter)]
 pub enum CloudModel {
     Gpt3Point5Turbo,