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>

Cargo.toml

@@ -56,6 +56,7 @@ members = [
     "crates/edit_prediction",
     "crates/edit_prediction_button",
     "crates/edit_prediction_context",
+    "crates/edit_prediction_context2",
     "crates/zeta2_tools",
     "crates/editor",
     "crates/eval",
@@ -316,6 +317,7 @@ image_viewer = { path = "crates/image_viewer" }
 edit_prediction = { path = "crates/edit_prediction" }
 edit_prediction_button = { path = "crates/edit_prediction_button" }
 edit_prediction_context = { path = "crates/edit_prediction_context" }
+edit_prediction_context2 = { path = "crates/edit_prediction_context2" }
 zeta2_tools = { path = "crates/zeta2_tools" }
 inspector_ui = { path = "crates/inspector_ui" }
 install_cli = { path = "crates/install_cli" }