Add experimental LSP-based context retrieval system for edit prediction (#44036)

To do

* [x] Default to no context retrieval. Allow opting in to LSP-based
retrieval via a setting (for users in `zeta2` feature flag)
* [x] Feed this context to models when enabled
* [x] Make the zeta2 context view work well with LSP retrieval
* [x] Add a UI for the setting (for feature-flagged users)
* [x] Ensure Zeta CLI `context` command is usable

---

* [ ] Filter out LSP definitions that are too large / entire files (e.g.
modules)
* [ ] Introduce timeouts
* [ ] Test with other LSPs
* [ ] Figure out hangs

Release Notes:

- N/A

---------

Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Agus Zubiaga <agus@zed.dev>

crates/extension_host/src/extension_store_test.rs

@@ -705,7 +705,7 @@ async fn test_extension_store_with_test_extension(cx: &mut TestAppContext) {
         .await
         .unwrap();
 
-    let mut fake_servers = language_registry.register_fake_language_server(
+    let mut fake_servers = language_registry.register_fake_lsp_server(
         LanguageServerName("gleam".into()),
         lsp::ServerCapabilities {
             completion_provider: Some(Default::default()),