Request compression.

Add new model_provider flag for compression to enable request
compression.  We support zstd and gzip, server also supports brotli

You can test this against the sign in with chatgpt flow by adding the
following profile:

```
[profiles.compressed]
name = "compressed"
model_provider = "openai-zstd"

[model_providers.openai-zstd]
name = "OpenAI (ChatGPT, zstd)"
wire_api = "responses"
request_compression = "zstd"
requires_openai_auth = true
```

This will zstd compress your request before sending it to the server.

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

@@ -5,6 +5,7 @@ use crate::error::ApiError;
 use crate::provider::Provider;
 use crate::provider::WireApi;
 use crate::telemetry::run_with_request_telemetry;
+use codex_client::Body;
 use codex_client::HttpTransport;
 use codex_client::RequestTelemetry;
 use codex_protocol::models::ResponseItem;
@@ -54,7 +55,7 @@ impl<T: HttpTransport, A: AuthProvider> CompactClient<T, A> {
         let builder = || {
             let mut req = self.provider.build_request(Method::POST, path);
             req.headers.extend(extra_headers.clone());
-            req.body = Some(body.clone());
+            req.body = Some(Body::Json(body.clone()));
             add_auth_headers(&self.auth, req)
         };
 
@@ -89,6 +90,7 @@ struct CompactHistoryResponse {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::provider::RequestCompression;
     use crate::provider::RetryConfig;
     use async_trait::async_trait;
     use codex_client::Request;
@@ -135,6 +137,7 @@ mod tests {
                 retry_5xx: true,
                 retry_transport: true,
             },
+            request_compression: RequestCompression::None,
             stream_idle_timeout: Duration::from_secs(1),
         }
     }