Add feature for optional request compression (#8767)

Adds a new feature
`enable_request_compression` that will compress using zstd requests to
the codex-backend. Currently only enabled for codex-backend so only enabled for openai providers when using chatgpt::auth even when the feature is enabled

Added a new info log line too for evaluating the compression ratio and
overhead off compressing before requesting. You can enable with
`RUST_LOG=$RUST_LOG,codex_client::transport=info`

```
2026-01-06T00:09:48.272113Z  INFO codex_client::transport: Compressed request body with zstd pre_compression_bytes=28914 post_compression_bytes=11485 compression_duration_ms=0
```

codex-rs/codex-api/src/endpoint/chat.rs

@@ -10,6 +10,7 @@ use crate::provider::WireApi;
 use crate::sse::chat::spawn_chat_stream;
 use crate::telemetry::SseTelemetry;
 use codex_client::HttpTransport;
+use codex_client::RequestCompression;
 use codex_client::RequestTelemetry;
 use codex_protocol::models::ContentItem;
 use codex_protocol::models::ReasoningItemContent;
@@ -80,7 +81,13 @@ impl<T: HttpTransport, A: AuthProvider> ChatClient<T, A> {
         extra_headers: HeaderMap,
     ) -> Result<ResponseStream, ApiError> {
         self.streaming
-            .stream(self.path(), body, extra_headers, spawn_chat_stream)
+            .stream(
+                self.path(),
+                body,
+                extra_headers,
+                RequestCompression::None,
+                spawn_chat_stream,
+            )
             .await
     }
 }

codex-rs/codex-api/src/endpoint/responses.rs

@@ -9,9 +9,11 @@ use crate::provider::Provider;
 use crate::provider::WireApi;
 use crate::requests::ResponsesRequest;
 use crate::requests::ResponsesRequestBuilder;
+use crate::requests::responses::Compression;
 use crate::sse::spawn_response_stream;
 use crate::telemetry::SseTelemetry;
 use codex_client::HttpTransport;
+use codex_client::RequestCompression;
 use codex_client::RequestTelemetry;
 use codex_protocol::protocol::SessionSource;
 use http::HeaderMap;
@@ -33,6 +35,7 @@ pub struct ResponsesOptions {
     pub conversation_id: Option<String>,
     pub session_source: Option<SessionSource>,
     pub extra_headers: HeaderMap,
+    pub compression: Compression,
 }
 
 impl<T: HttpTransport, A: AuthProvider> ResponsesClient<T, A> {
@@ -56,7 +59,8 @@ impl<T: HttpTransport, A: AuthProvider> ResponsesClient<T, A> {
         &self,
         request: ResponsesRequest,
     ) -> Result<ResponseStream, ApiError> {
-        self.stream(request.body, request.headers).await
+        self.stream(request.body, request.headers, request.compression)
+            .await
     }
 
     #[instrument(level = "trace", skip_all, err)]
@@ -75,6 +79,7 @@ impl<T: HttpTransport, A: AuthProvider> ResponsesClient<T, A> {
             conversation_id,
             session_source,
             extra_headers,
+            compression,
         } = options;
 
         let request = ResponsesRequestBuilder::new(model, &prompt.instructions, &prompt.input)
@@ -88,6 +93,7 @@ impl<T: HttpTransport, A: AuthProvider> ResponsesClient<T, A> {
             .session_source(session_source)
             .store_override(store_override)
             .extra_headers(extra_headers)
+            .compression(compression)
             .build(self.streaming.provider())?;
 
         self.stream_request(request).await
@@ -104,9 +110,21 @@ impl<T: HttpTransport, A: AuthProvider> ResponsesClient<T, A> {
         &self,
         body: Value,
         extra_headers: HeaderMap,
+        compression: Compression,
     ) -> Result<ResponseStream, ApiError> {
+        let compression = match compression {
+            Compression::None => RequestCompression::None,
+            Compression::Zstd => RequestCompression::Zstd,
+        };
+
         self.streaming
-            .stream(self.path(), body, extra_headers, spawn_response_stream)
+            .stream(
+                self.path(),
+                body,
+                extra_headers,
+                compression,
+                spawn_response_stream,
+            )
             .await
     }
 }

codex-rs/codex-api/src/endpoint/streaming.rs

@@ -6,6 +6,7 @@ use crate::provider::Provider;
 use crate::telemetry::SseTelemetry;
 use crate::telemetry::run_with_request_telemetry;
 use codex_client::HttpTransport;
+use codex_client::RequestCompression;
 use codex_client::RequestTelemetry;
 use codex_client::StreamResponse;
 use http::HeaderMap;
@@ -52,6 +53,7 @@ impl<T: HttpTransport, A: AuthProvider> StreamingClient<T, A> {
         path: &str,
         body: Value,
         extra_headers: HeaderMap,
+        compression: RequestCompression,
         spawner: fn(StreamResponse, Duration, Option<Arc<dyn SseTelemetry>>) -> ResponseStream,
     ) -> Result<ResponseStream, ApiError> {
         let builder = || {
@@ -62,6 +64,7 @@ impl<T: HttpTransport, A: AuthProvider> StreamingClient<T, A> {
                 http::HeaderValue::from_static("text/event-stream"),
             );
             req.body = Some(body.clone());
+            req.compression = compression;
             add_auth_headers(&self.auth, req)
         };
 

codex-rs/codex-api/src/provider.rs

@@ -1,4 +1,5 @@
 use codex_client::Request;
+use codex_client::RequestCompression;
 use codex_client::RetryOn;
 use codex_client::RetryPolicy;
 use http::Method;
@@ -87,6 +88,7 @@ impl Provider {
             url: self.url_for_path(path),
             headers: self.headers.clone(),
             body: None,
+            compression: RequestCompression::None,
             timeout: None,
         }
     }

codex-rs/codex-api/src/requests/responses.rs

@@ -11,10 +11,18 @@ use codex_protocol::protocol::SessionSource;
 use http::HeaderMap;
 use serde_json::Value;
 
+#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
+pub enum Compression {
+    #[default]
+    None,
+    Zstd,
+}
+
 /// Assembled request body plus headers for a Responses stream request.
 pub struct ResponsesRequest {
     pub body: Value,
     pub headers: HeaderMap,
+    pub compression: Compression,
 }
 
 #[derive(Default)]
@@ -32,6 +40,7 @@ pub struct ResponsesRequestBuilder<'a> {
     session_source: Option<SessionSource>,
     store_override: Option<bool>,
     headers: HeaderMap,
+    compression: Compression,
 }
 
 impl<'a> ResponsesRequestBuilder<'a> {
@@ -94,6 +103,11 @@ impl<'a> ResponsesRequestBuilder<'a> {
         self
     }
 
+    pub fn compression(mut self, compression: Compression) -> Self {
+        self.compression = compression;
+        self
+    }
+
     pub fn build(self, provider: &Provider) -> Result<ResponsesRequest, ApiError> {
         let model = self
             .model
@@ -138,7 +152,11 @@ impl<'a> ResponsesRequestBuilder<'a> {
             insert_header(&mut headers, "x-openai-subagent", &subagent);
         }
 
-        Ok(ResponsesRequest { body, headers })
+        Ok(ResponsesRequest {
+            body,
+            headers,
+            compression: self.compression,
+        })
     }
 }
 

codex-rs/codex-api/tests/clients.rs

@@ -11,6 +11,7 @@ use codex_api::Provider;
 use codex_api::ResponsesClient;
 use codex_api::ResponsesOptions;
 use codex_api::WireApi;
+use codex_api::requests::responses::Compression;
 use codex_client::HttpTransport;
 use codex_client::Request;
 use codex_client::Response;
@@ -229,7 +230,9 @@ async fn responses_client_uses_responses_path_for_responses_wire() -> Result<()>
     let client = ResponsesClient::new(transport, provider("openai", WireApi::Responses), NoAuth);
 
     let body = serde_json::json!({ "echo": true });
-    let _stream = client.stream(body, HeaderMap::new()).await?;
+    let _stream = client
+        .stream(body, HeaderMap::new(), Compression::None)
+        .await?;
 
     let requests = state.take_stream_requests();
     assert_path_ends_with(&requests, "/responses");
@@ -243,7 +246,9 @@ async fn responses_client_uses_chat_path_for_chat_wire() -> Result<()> {
     let client = ResponsesClient::new(transport, provider("openai", WireApi::Chat), NoAuth);
 
     let body = serde_json::json!({ "echo": true });
-    let _stream = client.stream(body, HeaderMap::new()).await?;
+    let _stream = client
+        .stream(body, HeaderMap::new(), Compression::None)
+        .await?;
 
     let requests = state.take_stream_requests();
     assert_path_ends_with(&requests, "/chat/completions");
@@ -258,7 +263,9 @@ async fn streaming_client_adds_auth_headers() -> Result<()> {
     let client = ResponsesClient::new(transport, provider("openai", WireApi::Responses), auth);
 
     let body = serde_json::json!({ "model": "gpt-test" });
-    let _stream = client.stream(body, HeaderMap::new()).await?;
+    let _stream = client
+        .stream(body, HeaderMap::new(), Compression::None)
+        .await?;
 
     let requests = state.take_stream_requests();
     assert_eq!(requests.len(), 1);

codex-rs/codex-api/tests/sse_end_to_end.rs

@@ -9,6 +9,7 @@ use codex_api::Provider;
 use codex_api::ResponseEvent;
 use codex_api::ResponsesClient;
 use codex_api::WireApi;
+use codex_api::requests::responses::Compression;
 use codex_client::HttpTransport;
 use codex_client::Request;
 use codex_client::Response;
@@ -124,7 +125,11 @@ async fn responses_stream_parses_items_and_completed_end_to_end() -> Result<()>
     let client = ResponsesClient::new(transport, provider("openai", WireApi::Responses), NoAuth);
 
     let mut stream = client
-        .stream(serde_json::json!({"echo": true}), HeaderMap::new())
+        .stream(
+            serde_json::json!({"echo": true}),
+            HeaderMap::new(),
+            Compression::None,
+        )
         .await?;
 
     let mut events = Vec::new();
@@ -189,7 +194,11 @@ async fn responses_stream_aggregates_output_text_deltas() -> Result<()> {
     let client = ResponsesClient::new(transport, provider("openai", WireApi::Responses), NoAuth);
 
     let stream = client
-        .stream(serde_json::json!({"echo": true}), HeaderMap::new())
+        .stream(
+            serde_json::json!({"echo": true}),
+            HeaderMap::new(),
+            Compression::None,
+        )
         .await?;
 
     let mut stream = stream.aggregate();