Replace zed_llm_client with cloud_llm_client (#35309)

This PR replaces the usage of the `zed_llm_client` with the
`cloud_llm_client`.

It was ported into this repo in #35307.

Release Notes:

- N/A

crates/agent/Cargo.toml

@@ -25,6 +25,7 @@ assistant_context.workspace = true
 assistant_tool.workspace = true
 chrono.workspace = true
 client.workspace = true
+cloud_llm_client.workspace = true
 collections.workspace = true
 component.workspace = true
 context_server.workspace = true
@@ -35,9 +36,9 @@ futures.workspace = true
 git.workspace = true
 gpui.workspace = true
 heed.workspace = true
+http_client.workspace = true
 icons.workspace = true
 indoc.workspace = true
-http_client.workspace = true
 itertools.workspace = true
 language.workspace = true
 language_model.workspace = true
@@ -63,7 +64,6 @@ time.workspace = true
 util.workspace = true
 uuid.workspace = true
 workspace-hack.workspace = true
-zed_llm_client.workspace = true
 zstd.workspace = true
 
 [dev-dependencies]

crates/agent/src/thread.rs

@@ -13,6 +13,7 @@ use anyhow::{Result, anyhow};
 use assistant_tool::{ActionLog, AnyToolCard, Tool, ToolWorkingSet};
 use chrono::{DateTime, Utc};
 use client::{ModelRequestUsage, RequestUsage};
+use cloud_llm_client::{CompletionIntent, CompletionRequestStatus, UsageLimit};
 use collections::HashMap;
 use feature_flags::{self, FeatureFlagAppExt};
 use futures::{FutureExt, StreamExt as _, future::Shared};
@@ -49,7 +50,6 @@ use std::{
 use thiserror::Error;
 use util::{ResultExt as _, post_inc};
 use uuid::Uuid;
-use zed_llm_client::{CompletionIntent, CompletionRequestStatus, UsageLimit};
 
 const MAX_RETRY_ATTEMPTS: u8 = 4;
 const BASE_RETRY_DELAY: Duration = Duration::from_secs(5);
@@ -1681,7 +1681,7 @@ impl Thread {
 
         let completion_mode = request
             .mode
-            .unwrap_or(zed_llm_client::CompletionMode::Normal);
+            .unwrap_or(cloud_llm_client::CompletionMode::Normal);
 
         self.last_received_chunk_at = Some(Instant::now());