assistant: Remove low_speed_timeout (#20681)

This removes the `low_speed_timeout` setting from all providers as a
response to issue #19509.

Reason being that the original `low_speed_timeout` was only as part of
#9913 because users wanted to _get rid of timeouts_. They wanted to bump
the default timeout from 5sec to a lot more.

Then, in the meantime, the meaning of `low_speed_timeout` changed in
#19055 and was changed to a normal `timeout`, which is a different thing
and breaks slower LLMs that don't reply with a complete response in the
configured timeout.

So we figured: let's remove the whole thing and replace it with a
default _connect_ timeout to make sure that we can connect to a server
in 10s, but then give the server as long as it wants to complete its
response.

Closes #19509

Release Notes:

- Removed the `low_speed_timeout` setting from LLM provider settings,
since it was only used to _increase_ the timeout to give LLMs more time,
but since we don't have any other use for it, we simply remove the
setting to give LLMs as long as they need.

---------

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

crates/google_ai/src/google_ai.rs

@@ -2,9 +2,8 @@ mod supported_countries;
 
 use anyhow::{anyhow, Result};
 use futures::{io::BufReader, stream::BoxStream, AsyncBufReadExt, AsyncReadExt, Stream, StreamExt};
-use http_client::{AsyncBody, HttpClient, HttpRequestExt, Method, Request as HttpRequest};
+use http_client::{AsyncBody, HttpClient, Method, Request as HttpRequest};
 use serde::{Deserialize, Serialize};
-use std::time::Duration;
 
 pub use supported_countries::*;
 
@@ -15,7 +14,6 @@ pub async fn stream_generate_content(
     api_url: &str,
     api_key: &str,
     mut request: GenerateContentRequest,
-    low_speed_timeout: Option<Duration>,
 ) -> Result<BoxStream<'static, Result<GenerateContentResponse>>> {
     let uri = format!(
         "{api_url}/v1beta/models/{model}:streamGenerateContent?alt=sse&key={api_key}",
@@ -23,15 +21,11 @@ pub async fn stream_generate_content(
     );
     request.model.clear();
 
-    let mut request_builder = HttpRequest::builder()
+    let request_builder = HttpRequest::builder()
         .method(Method::POST)
         .uri(uri)
         .header("Content-Type", "application/json");
 
-    if let Some(low_speed_timeout) = low_speed_timeout {
-        request_builder = request_builder.read_timeout(low_speed_timeout);
-    };
-
     let request = request_builder.body(AsyncBody::from(serde_json::to_string(&request)?))?;
     let mut response = client.send(request).await?;
     if response.status().is_success() {
@@ -70,7 +64,6 @@ pub async fn count_tokens(
     api_url: &str,
     api_key: &str,
     request: CountTokensRequest,
-    low_speed_timeout: Option<Duration>,
 ) -> Result<CountTokensResponse> {
     let uri = format!(
         "{}/v1beta/models/gemini-pro:countTokens?key={}",
@@ -78,15 +71,11 @@ pub async fn count_tokens(
     );
     let request = serde_json::to_string(&request)?;
 
-    let mut request_builder = HttpRequest::builder()
+    let request_builder = HttpRequest::builder()
         .method(Method::POST)
         .uri(&uri)
         .header("Content-Type", "application/json");
 
-    if let Some(low_speed_timeout) = low_speed_timeout {
-        request_builder = request_builder.read_timeout(low_speed_timeout);
-    }
-
     let http_request = request_builder.body(AsyncBody::from(request))?;
     let mut response = client.send(http_request).await?;
     let mut text = String::new();