Introduce a separate backend service for LLM calls (#15831)

This PR introduces a separate backend service for making LLM calls.

It exposes an HTTP interface that can be called by Zed clients. To call
these endpoints, the client must provide a `Bearer` token. These tokens
are issued/refreshed by the collab service over RPC.

We're adding this in a backwards-compatible way. Right now the access
tokens can only be minted for Zed staff, and calling this separate LLM
service is behind the `llm-service` feature flag (which is not
automatically enabled for Zed staff).

Release Notes:

- N/A

---------

Co-authored-by: Marshall <marshall@zed.dev>
Co-authored-by: Marshall Bowers <elliott.codes@gmail.com>

crates/rpc/src/llm.rs

@@ -0,0 +1,8 @@
+use serde::{Deserialize, Serialize};
+
+pub const EXPIRED_LLM_TOKEN_HEADER_NAME: &str = "x-zed-expired-token";
+
+#[derive(Serialize, Deserialize)]
+pub struct PerformCompletionParams {
+    pub provider_request: Box<serde_json::value::RawValue>,
+}

crates/rpc/src/rpc.rs

@@ -1,12 +1,14 @@
 pub mod auth;
 mod conn;
 mod extension;
+mod llm;
 mod notification;
 mod peer;
 pub mod proto;
 
 pub use conn::Connection;
 pub use extension::*;
+pub use llm::*;
 pub use notification::*;
 pub use peer::*;
 pub use proto::{error::*, Receipt, TypedEnvelope};