assistant: Improve /docs argument completions (#13876)

This PR improves the completions for arguments in the `/docs` slash
command.

We achieved this by extending the `complete_argument` method on the
`SlashCommand` trait to return a `Vec<ArgumentCompletion>` instead of a
`Vec<String>`.

In addition to the completion `label`, `ArgumentCompletion` has two new
fields that are can be used to customize the completion behavior:

- `new_text`: The actual text that will be inserted when the completion
is accepted, which may be different from what is shown by the completion
label.
- `run_command`: Whether the command is run when the completion is
accepted. This can be set to `false` to allow accepting a completion
without running the command.

Release Notes:

- N/A

---------

Co-authored-by: Antonio <antonio@zed.dev>

crates/assistant/src/slash_command/default_command.rs

@@ -1,7 +1,7 @@
 use super::{SlashCommand, SlashCommandOutput};
 use crate::prompt_library::PromptStore;
 use anyhow::{anyhow, Result};
-use assistant_slash_command::SlashCommandOutputSection;
+use assistant_slash_command::{ArgumentCompletion, SlashCommandOutputSection};
 use gpui::{AppContext, Task, WeakView};
 use language::LspAdapterDelegate;
 use std::{
@@ -36,7 +36,7 @@ impl SlashCommand for DefaultSlashCommand {
         _cancellation_flag: Arc<AtomicBool>,
         _workspace: Option<WeakView<Workspace>>,
         _cx: &mut AppContext,
-    ) -> Task<Result<Vec<String>>> {
+    ) -> Task<Result<Vec<ArgumentCompletion>>> {
         Task::ready(Err(anyhow!("this command does not require argument")))
     }