ep: Compress settled requests to cloud (#56793)

Self-Review Checklist:

- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content is consistent with the [UI/UX
checklist](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
- [x] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable

Closes #ISSUE

Release Notes:

- N/A or Added/Fixed/Improved ...
This commit is contained in:
Ben Kunkle authored and GitHub committed 2026-05-15 15:14:41 +00:00
1 parent 1b557c7084
commit 3eeda10ede
2 files changed
+23 -13

No files matched your search

+12 -12
View File
@@ -1698,16 +1698,6 @@ impl EditPredictionStore {
..
} = pending_prediction;
let settled_editable_region_for_metrics = settled_editable_region.clone();
let kept_rate_result = cx
.background_spawn(async move {
compute_kept_rate(
&editable_region_before_prediction,
&predicted_editable_region,
&settled_editable_region_for_metrics,
)
})
.await;
#[cfg(test)]
{
let request_id = request_id.clone();
@@ -1718,12 +1708,17 @@ impl EditPredictionStore {
}
});
}
cx.background_spawn({
let client = client.clone();
let llm_token = llm_token.clone();
let app_version = app_version.clone();
async move {
let kept_rate_result = compute_kept_rate(
&editable_region_before_prediction,
&predicted_editable_region,
&settled_editable_region_for_metrics,
);
let result: anyhow::Result<()> = async {
let settled_editable_region =
can_collect_data.then_some(settled_editable_region);
@@ -1756,6 +1751,10 @@ impl EditPredictionStore {
model_version,
e2e_latency_ms: e2e_latency.as_millis(),
};
let json_bytes = serde_json::to_vec(&body)?;
let compressed = zstd::encode_all(&json_bytes[..], 3)?;
let url = client
.http_client()
.build_zed_llm_url("/predict_edits/settled", &[])?;
@@ -1763,7 +1762,8 @@ impl EditPredictionStore {
|builder| {
Ok(builder
.uri(url.as_ref())
.body(serde_json::to_string(&body)?.into())?)
.header("Content-Encoding", "zstd")
.body(compressed.clone().into())?)
},
client,
llm_token,
@@ -2541,6 +2541,11 @@ fn init_test_with_fake_client_and_legacy_data_collection(
let http_client = FakeHttpClient::create({
move |req| {
let uri = req.uri().path().to_string();
let content_encoding = req
.headers()
.get("Content-Encoding")
.and_then(|value| value.to_str().ok())
.map(str::to_owned);
let mut body = req.into_body();
let predict_req_tx = predict_req_tx.clone();
let reject_req_tx = reject_req_tx.clone();
@@ -2573,7 +2578,12 @@ fn init_test_with_fake_client_and_legacy_data_collection(
"/predict_edits/settled" => {
let mut buf = Vec::new();
body.read_to_end(&mut buf).await.ok();
let req = serde_json::from_slice(&buf).unwrap();
let body = if content_encoding.as_deref() == Some("zstd") {
zstd::decode_all(&buf[..]).unwrap()
} else {
buf
};
let req = serde_json::from_slice(&body).unwrap();
settled_req_tx.unbounded_send(req).unwrap();
serde_json::to_string(&SubmitEditPredictionSettledResponse {}).unwrap()
}