Make LanguageModel::use_any_tool return a stream of chunks (#16262)

This PR is a refactor to pave the way for allowing the user to view and
edit workflow step resolutions. I've made tool calls work more like
normal streaming completions for all providers. The `use_any_tool`
method returns a stream of strings (which contain chunks of JSON). I've
also done some minor cleanup of language model providers in general,
removing the duplication around handling streaming responses.

Release Notes:

- N/A

crates/assistant/src/inline_assistant.rs

@@ -1280,12 +1280,6 @@ fn build_assist_editor_renderer(editor: &View<PromptEditor>) -> RenderBlock {
     })
 }
 
-#[derive(Copy, Clone, Debug, Eq, PartialEq)]
-pub enum InitialInsertion {
-    NewlineBefore,
-    NewlineAfter,
-}
-
 #[derive(Copy, Clone, Default, Debug, PartialEq, Eq, Hash)]
 pub struct InlineAssistId(usize);