Allow AI interactions to be proxied through Zed's server so you don't need an API key (#7367)

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

Resurrected this from some assistant work I did in Spring of 2023.
- [x] Resurrect streaming responses
- [x] Use streaming responses to enable AI via Zed's servers by default
(but preserve API key option for now)
- [x] Simplify protobuf
- [x] Proxy to OpenAI on zed.dev
- [x] Proxy to Gemini on zed.dev
- [x] Improve UX for switching between openAI and google models
- We current disallow cycling when setting a custom model, but we need a
better solution to keep OpenAI models available while testing the google
ones
- [x] Show remaining tokens correctly for Google models
- [x] Remove semantic index
- [x] Delete `ai` crate
- [x] Cloud front so we can ban abuse
- [x] Rate-limiting
- [x] Fix panic when using inline assistant
- [x] Double check the upgraded `AssistantSettings` are
backwards-compatible
- [x] Add hosted LLM interaction behind a `language-models` feature
flag.

Release Notes:

- We are temporarily removing the semantic index in order to redesign it
from scratch.

---------

Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Thorsten <thorsten@zed.dev>
Co-authored-by: Max <max@zed.dev>

crates/collab/src/main.rs

@@ -7,7 +7,7 @@ use axum::{
 };
 use collab::{
     api::fetch_extensions_from_blob_store_periodically, db, env, executor::Executor, AppState,
-    Config, MigrateConfig, Result,
+    Config, MigrateConfig, RateLimiter, Result,
 };
 use db::Database;
 use std::{
@@ -62,18 +62,27 @@ async fn main() -> Result<()> {
 
             run_migrations().await?;
 
-            let state = AppState::new(config).await?;
+            let state = AppState::new(config, Executor::Production).await?;
 
             let listener = TcpListener::bind(&format!("0.0.0.0:{}", state.config.http_port))
                 .expect("failed to bind TCP listener");
 
+            let epoch = state
+                .db
+                .create_server(&state.config.zed_environment)
+                .await?;
+            let rpc_server = collab::rpc::Server::new(epoch, state.clone());
+            rpc_server.start().await?;
+
+            fetch_extensions_from_blob_store_periodically(state.clone());
+            RateLimiter::save_periodically(state.rate_limiter.clone(), state.executor.clone());
+
             let rpc_server = if is_collab {
                 let epoch = state
                     .db
                     .create_server(&state.config.zed_environment)
                     .await?;
-                let rpc_server =
-                    collab::rpc::Server::new(epoch, state.clone(), Executor::Production);
+                let rpc_server = collab::rpc::Server::new(epoch, state.clone());
                 rpc_server.start().await?;
 
                 Some(rpc_server)
@@ -82,7 +91,7 @@ async fn main() -> Result<()> {
             };
 
             if is_api {
-                fetch_extensions_from_blob_store_periodically(state.clone(), Executor::Production);
+                fetch_extensions_from_blob_store_periodically(state.clone());
             }
 
             let mut app = collab::api::routes(rpc_server.clone(), state.clone());